*.o.*
*.patch
*.rmeta
+*.rpm
*.rsi
*.s
*.so
Alexander Lobakin <alobakin@pm.me> <alobakin@dlink.ru>
Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com>
Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru>
+Alexander Mikhalitsyn <alexander@mihalicyn.com> <alexander.mikhalitsyn@virtuozzo.com>
+Alexander Mikhalitsyn <alexander@mihalicyn.com> <aleksandr.mikhalitsyn@canonical.com>
Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com>
Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
Douglas Gilbert <dougg@torque.net>
Ed L. Cashin <ecashin@coraid.com>
Erik Kaneda <erik.kaneda@intel.com> <erik.schmauss@intel.com>
+Eugen Hristev <eugen.hristev@collabora.com> <eugen.hristev@microchip.com>
Evgeniy Polyakov <johnpol@2ka.mipt.ru>
Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> <ezequiel@collabora.com>
Felipe W Damasio <felipewd@terra.com.br>
Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com>
Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
+John Crispin <john@phrozen.org> <blogic@openwrt.org>
John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
John Stultz <johnstul@us.ibm.com>
Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org>
Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com>
Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org>
Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
+Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org>
Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>
TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
+Tudor Ambarus <tudor.ambarus@linaro.org> <tudor.ambarus@microchip.com>
Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
D: APM driver (early port)
D: DRM drivers (author of several)
+N: Veaceslav Falico
+E: vfalico@gmail.com
+D: Co-maintainer and co-author of the network bonding driver.
+
N: János Farkas
E: chexum@shadow.banki.hu
D: romfs, various (mostly networking) fixes
D: XF86_8514
D: cfdisk (curses based disk partitioning program)
+N: Mat Martineau
+E: mat@martineau.name
+D: MPTCP subsystem co-maintainer 2020-2023
+D: Keyctl restricted keyring and Diffie-Hellman UAPI
+D: Bluetooth L2CAP ERTM mode and AMP
+S: USA
+
N: John S. Marvin
E: jsm@fc.hp.com
D: PA-RISC port
S: 16 Baliqiao Nanjie, Beijing 101100
S: People's Repulic of China
+N: Vlad Yasevich
+E: vyasevich@gmail.com
+D: SCTP protocol maintainer.
+
N: Aviad Yehezkel
E: aviadye@nvidia.com
D: Kernel TLS implementation and offload support.
--- /dev/null
+What: /sys/kernel/debug/pktcdvd/pktcdvd[0-7]
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+
+The pktcdvd module (packet writing driver) creates
+these files in debugfs:
+
+/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
+
+ ==== ====== ====================================
+ info 0444 Lots of driver statistics and infos.
+ ==== ====== ====================================
+
+Example::
+
+ cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
--- /dev/null
+sysfs interface
+---------------
+The pktcdvd module (packet writing driver) creates the following files in the
+sysfs: (<devid> is in the format major:minor)
+
+What: /sys/class/pktcdvd/add
+What: /sys/class/pktcdvd/remove
+What: /sys/class/pktcdvd/device_map
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+
+ ========== ==============================================
+ add (WO) Write a block device id (major:minor) to
+ create a new pktcdvd device and map it to the
+ block device.
+
+ remove (WO) Write the pktcdvd device id (major:minor)
+ to remove the pktcdvd device.
+
+ device_map (RO) Shows the device mapping in format:
+ pktcdvd[0-7] <pktdevid> <blkdevid>
+ ========== ==============================================
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/dev
+What: /sys/class/pktcdvd/pktcdvd[0-7]/uevent
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ dev: (RO) Device id
+
+ uevent: (WO) To send a uevent
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_started
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_finished
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_written
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read_gather
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/reset
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ packets_started: (RO) Number of started packets.
+
+ packets_finished: (RO) Number of finished packets.
+
+ kb_written: (RO) kBytes written.
+
+ kb_read: (RO) kBytes read.
+
+ kb_read_gather: (RO) kBytes read to fill write packets.
+
+ reset: (WO) Write any value to it to reset
+ pktcdvd device statistic values, like
+ bytes read/written.
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/size
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_off
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_on
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ ============== ================================================
+ size (RO) Contains the size of the bio write queue.
+
+ congestion_off (RW) If bio write queue size is below this mark,
+ accept new bio requests from the block layer.
+
+ congestion_on (RW) If bio write queue size is higher as this
+ mark, do no longer accept bio write requests
+ from the block layer and wait till the pktcdvd
+ device has processed enough bio's so that bio
+ write queue size is below congestion off mark.
+ A value of <= 0 disables congestion control.
+ ============== ================================================
+
+
+Example:
+--------
+To use the pktcdvd sysfs interface directly, you can do::
+
+ # create a new pktcdvd device mapped to /dev/hdc
+ echo "22:0" >/sys/class/pktcdvd/add
+ cat /sys/class/pktcdvd/device_map
+ # assuming device pktcdvd0 was created, look at stat's
+ cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
+ # print the device id of the mapped block device
+ fgrep pktcdvd0 /sys/class/pktcdvd/device_map
+ # remove device, using pktcdvd0 device id 253:0
+ echo "253:0" >/sys/class/pktcdvd/remove
This is a simple interface to trigger memory reclaim in the
target cgroup.
- This file accepts a string which contains the number of bytes to
- reclaim.
+ This file accepts a single key, the number of bytes to reclaim.
+ No nested keys are currently supported.
Example::
echo "1G" > memory.reclaim
+ The interface can be later extended with nested keys to
+ configure the reclaim behavior. For example, specify the
+ type of memory to reclaim from (anon, file, ..).
+
Please note that the kernel can over or under reclaim from
the target cgroup. If less bytes are reclaimed than the
specified amount, -EAGAIN is returned.
This means that the networking layer will not adapt based on
reclaim induced by memory.reclaim.
- This file also allows the user to specify the nodes to reclaim from,
- via the 'nodes=' key, for example::
-
- echo "1G nodes=0,1" > memory.reclaim
-
- The above instructs the kernel to reclaim memory from nodes 0,1.
-
memory.peak
A read-only single value file which exists on non-root
cgroups.
--- /dev/null
+
+.. SPDX-License-Identifier: GPL-2.0
+
+Cross-Thread Return Address Predictions
+=======================================
+
+Certain AMD and Hygon processors are subject to a cross-thread return address
+predictions vulnerability. When running in SMT mode and one sibling thread
+transitions out of C0 state, the other sibling thread could use return target
+predictions from the sibling thread that transitioned out of C0.
+
+The Spectre v2 mitigations protect the Linux kernel, as it fills the return
+address prediction entries with safe targets when context switching to the idle
+thread. However, KVM does allow a VMM to prevent exiting guest mode when
+transitioning out of C0. This could result in a guest-controlled return target
+being consumed by the sibling thread.
+
+Affected processors
+-------------------
+
+The following CPUs are vulnerable:
+
+ - AMD Family 17h processors
+ - Hygon Family 18h processors
+
+Related CVEs
+------------
+
+The following CVE entry is related to this issue:
+
+ ============== =======================================
+ CVE-2022-27672 Cross-Thread Return Address Predictions
+ ============== =======================================
+
+Problem
+-------
+
+Affected SMT-capable processors support 1T and 2T modes of execution when SMT
+is enabled. In 2T mode, both threads in a core are executing code. For the
+processor core to enter 1T mode, it is required that one of the threads
+requests to transition out of the C0 state. This can be communicated with the
+HLT instruction or with an MWAIT instruction that requests non-C0.
+When the thread re-enters the C0 state, the processor transitions back
+to 2T mode, assuming the other thread is also still in C0 state.
+
+In affected processors, the return address predictor (RAP) is partitioned
+depending on the SMT mode. For instance, in 2T mode each thread uses a private
+16-entry RAP, but in 1T mode, the active thread uses a 32-entry RAP. Upon
+transition between 1T/2T mode, the RAP contents are not modified but the RAP
+pointers (which control the next return target to use for predictions) may
+change. This behavior may result in return targets from one SMT thread being
+used by RET predictions in the sibling thread following a 1T/2T switch. In
+particular, a RET instruction executed immediately after a transition to 1T may
+use a return target from the thread that just became idle. In theory, this
+could lead to information disclosure if the return targets used do not come
+from trustworthy code.
+
+Attack scenarios
+----------------
+
+An attack can be mounted on affected processors by performing a series of CALL
+instructions with targeted return locations and then transitioning out of C0
+state.
+
+Mitigation mechanism
+--------------------
+
+Before entering idle state, the kernel context switches to the idle thread. The
+context switch fills the RAP entries (referred to as the RSB in Linux) with safe
+targets by performing a sequence of CALL instructions.
+
+Prevent a guest VM from directly putting the processor into an idle state by
+intercepting HLT and MWAIT instructions.
+
+Both mitigations are required to fully address this issue.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+Use existing Spectre v2 mitigations that will fill the RSB on context switch.
+
+Mitigation control for KVM - module parameter
+---------------------------------------------
+
+By default, the KVM hypervisor mitigates this issue by intercepting guest
+attempts to transition out of C0. A VMM can use the KVM_CAP_X86_DISABLE_EXITS
+capability to override those interceptions, but since this is not common, the
+mitigation that covers this path is not enabled by default.
+
+The mitigation for the KVM_CAP_X86_DISABLE_EXITS capability can be turned on
+using the boolean module parameter mitigate_smt_rsb, e.g. ``kvm.mitigate_smt_rsb=1``.
core-scheduling.rst
l1d_flush.rst
processor_mmio_stale_data.rst
+ cross-thread-rsb.rst
The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which
means the compression ratio will always be 2:1 or worse (because of half-full
zbud pages). The zsmalloc type zpool has a more complex compressed page
-storage method, and it can achieve greater storage densities. However,
-zsmalloc does not implement compressed page eviction, so once zswap fills it
-cannot evict the oldest page, it can only reject new pages.
+storage method, and it can achieve greater storage densities.
When a swap page is passed from frontswap to zswap, zswap maintains a mapping
of the swap entry, a combination of the swap type and swap offset, to the zpool
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 |
+----------------+-----------------+-----------------+-----------------------------+
+| ARM | Cortex-A715 | #2645198 | ARM64_ERRATUM_2645198 |
++----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 |
# Get Sphinx version
major, minor, patch = sphinx.version_info[:3]
+#
+# Warn about older versions that we don't want to support for much
+# longer.
+#
+if (major < 2) or (major == 2 and minor < 4):
+ print('WARNING: support for Sphinx < 2.4 will be removed soon.')
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# Custom sidebar templates, maps document names to template names.
# Note that the RTD theme ignores this
-html_sidebars = { '**': ["about.html", 'searchbox.html', 'localtoc.html', 'sourcelink.html']}
+html_sidebars = { '**': ['searchbox.html', 'localtoc.html', 'sourcelink.html']}
+
+# about.html is available for alabaster theme. Add it at the front.
+if html_theme == 'alabaster':
+ html_sidebars['**'].insert(0, 'about.html')
# Output file base name for HTML help builder.
htmlhelp_basename = 'TheLinuxKerneldoc'
*.example.dts
/processed-schema*.yaml
/processed-schema*.json
+
+#
+# We don't want to ignore the following even if they are dot-files
+#
+!.yamllint
- const: xo
- const: alternate
+ interrupts:
+ minItems: 1
+ maxItems: 3
+
+ interrupt-names:
+ minItems: 1
+ items:
+ - const: dcvsh-irq-0
+ - const: dcvsh-irq-1
+ - const: dcvsh-irq-2
+
'#freq-domain-cells':
const: 1
title: Atmel Advanced Encryption Standard (AES) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
title: Atmel Secure Hash Algorithm (SHA) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
title: Atmel Triple Data Encryption Standard (TDES) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
- description: Display byte clock
- description: Display byte interface clock
- description: Display pixel clock
- - description: Display escape clock
+ - description: Display core clock
- description: Display AHB clock
- description: Display AXI clock
- phys
- assigned-clocks
- assigned-clock-parents
- - power-domains
- - operating-points-v2
- ports
additionalProperties: false
- compatible
- reg
- reg-names
- - vdds-supply
unevaluatedProperties: false
- compatible
- reg
- reg-names
- - vcca-supply
unevaluatedProperties: false
vddio-supply:
description: Phandle to vdd-io regulator device node.
+ qcom,dsi-phy-regulator-ldo-mode:
+ type: boolean
+ description: Indicates if the LDO mode PHY regulator is wanted.
+
required:
- compatible
- reg
#include <dt-bindings/interconnect/qcom,qcm2290.h>
#include <dt-bindings/power/qcom-rpmpd.h>
- mdss@5e00000 {
+ display-subsystem@5e00000 {
#address-cells = <1>;
#size-cells = <1>;
compatible = "qcom,qcm2290-mdss";
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/power/qcom-rpmpd.h>
- mdss@5e00000 {
+ display-subsystem@5e00000 {
#address-cells = <1>;
#size-cells = <1>;
compatible = "qcom,sm6115-mdss";
compatible:
items:
- enum:
- - renesas,i2c-r9a09g011 # RZ/V2M
+ - renesas,r9a09g011-i2c # RZ/V2M
- const: renesas,rzv2m-i2c
reg:
#include <dt-bindings/interrupt-controller/arm-gic.h>
i2c0: i2c@a4030000 {
- compatible = "renesas,i2c-r9a09g011", "renesas,rzv2m-i2c";
+ compatible = "renesas,r9a09g011-i2c", "renesas,rzv2m-i2c";
reg = <0xa4030000 0x80>;
interrupts = <GIC_SPI 232 IRQ_TYPE_EDGE_RISING>,
<GIC_SPI 236 IRQ_TYPE_EDGE_RISING>;
- qcom,msm8939-pcnoc
- qcom,msm8939-snoc
- qcom,msm8996-a1noc
- - qcom,msm8996-a2noc
- qcom,msm8996-bimc
- qcom,msm8996-cnoc
- qcom,msm8996-pnoc
required:
- power-domains
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - qcom,msm8996-a2noc
+
+ then:
+ properties:
+ clock-names:
+ items:
+ - const: bus
+ - const: bus_a
+ - const: aggre2_ufs_axi
+ - const: ufs_axi
+
+ clocks:
+ items:
+ - description: Bus Clock
+ - description: Bus A Clock
+ - description: Aggregate2 NoC UFS AXI Clock
+ - description: UFS AXI Clock
+
- if:
properties:
compatible:
msi-controller:
description:
- Only present if the Message Based Interrupt functionnality is
+ Only present if the Message Based Interrupt functionality is
being exposed by the HW, and the mbi-ranges property present.
mbi-ranges:
clock-names:
const: stmmaceth
+ phy-supply:
+ description: PHY regulator
+
syscon:
$ref: /schemas/types.yaml#/definitions/phandle
description:
8k has a second unit which provides an interface with the xMDIO bus. This
driver handles these interfaces.
-allOf:
- - $ref: "mdio.yaml#"
-
properties:
compatible:
enum:
- compatible
- reg
+allOf:
+ - $ref: mdio.yaml#
+
+ - if:
+ required:
+ - interrupts
+
+ then:
+ properties:
+ reg:
+ items:
+ - items:
+ - $ref: /schemas/types.yaml#/definitions/cell
+ - const: 0x84
+
+ else:
+ properties:
+ reg:
+ items:
+ - items:
+ - $ref: /schemas/types.yaml#/definitions/cell
+ - enum:
+ - 0x4
+ - 0x10
+
unevaluatedProperties: false
examples:
- |
mdio@d0072004 {
compatible = "marvell,orion-mdio";
- reg = <0xd0072004 0x4>;
+ reg = <0xd0072004 0x84>;
#address-cells = <1>;
#size-cells = <0>;
interrupts = <30>;
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+# Copyright 2019 BayLibre, SAS
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb2-phy.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Amlogic G12A USB2 PHY
+
+maintainers:
+ - Neil Armstrong <neil.armstrong@linaro.org>
+
+properties:
+ compatible:
+ enum:
+ - amlogic,g12a-usb2-phy
+ - amlogic,a1-usb2-phy
+
+ reg:
+ maxItems: 1
+
+ clocks:
+ maxItems: 1
+
+ clock-names:
+ items:
+ - const: xtal
+
+ resets:
+ maxItems: 1
+
+ reset-names:
+ items:
+ - const: phy
+
+ "#phy-cells":
+ const: 0
+
+ phy-supply:
+ description:
+ Phandle to a regulator that provides power to the PHY. This
+ regulator will be managed during the PHY power on/off sequence.
+
+required:
+ - compatible
+ - reg
+ - clocks
+ - clock-names
+ - resets
+ - reset-names
+ - "#phy-cells"
+
+if:
+ properties:
+ compatible:
+ enum:
+ - amlogic,meson-a1-usb-ctrl
+
+then:
+ properties:
+ power-domains:
+ maxItems: 1
+ required:
+ - power-domains
+
+additionalProperties: false
+
+examples:
+ - |
+ phy@36000 {
+ compatible = "amlogic,g12a-usb2-phy";
+ reg = <0x36000 0x2000>;
+ clocks = <&xtal>;
+ clock-names = "xtal";
+ resets = <&phy_reset>;
+ reset-names = "phy";
+ #phy-cells = <0>;
+ };
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+# Copyright 2019 BayLibre, SAS
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb3-pcie-phy.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Amlogic G12A USB3 + PCIE Combo PHY
+
+maintainers:
+ - Neil Armstrong <neil.armstrong@linaro.org>
+
+properties:
+ compatible:
+ enum:
+ - amlogic,g12a-usb3-pcie-phy
+
+ reg:
+ maxItems: 1
+
+ clocks:
+ maxItems: 1
+
+ clock-names:
+ items:
+ - const: ref_clk
+
+ resets:
+ maxItems: 1
+
+ reset-names:
+ items:
+ - const: phy
+
+ "#phy-cells":
+ const: 1
+
+required:
+ - compatible
+ - reg
+ - clocks
+ - clock-names
+ - resets
+ - reset-names
+ - "#phy-cells"
+
+additionalProperties: false
+
+examples:
+ - |
+ phy@46000 {
+ compatible = "amlogic,g12a-usb3-pcie-phy";
+ reg = <0x46000 0x2000>;
+ clocks = <&ref_clk>;
+ clock-names = "ref_clk";
+ resets = <&phy_reset>;
+ reset-names = "phy";
+ #phy-cells = <1>;
+ };
+++ /dev/null
-# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
-# Copyright 2019 BayLibre, SAS
-%YAML 1.2
----
-$id: "http://devicetree.org/schemas/phy/amlogic,meson-g12a-usb2-phy.yaml#"
-$schema: "http://devicetree.org/meta-schemas/core.yaml#"
-
-title: Amlogic G12A USB2 PHY
-
-maintainers:
- - Neil Armstrong <neil.armstrong@linaro.org>
-
-properties:
- compatible:
- enum:
- - amlogic,meson-g12a-usb2-phy
- - amlogic,meson-a1-usb2-phy
-
- reg:
- maxItems: 1
-
- clocks:
- maxItems: 1
-
- clock-names:
- items:
- - const: xtal
-
- resets:
- maxItems: 1
-
- reset-names:
- items:
- - const: phy
-
- "#phy-cells":
- const: 0
-
- phy-supply:
- description:
- Phandle to a regulator that provides power to the PHY. This
- regulator will be managed during the PHY power on/off sequence.
-
-required:
- - compatible
- - reg
- - clocks
- - clock-names
- - resets
- - reset-names
- - "#phy-cells"
-
-if:
- properties:
- compatible:
- enum:
- - amlogic,meson-a1-usb-ctrl
-
-then:
- properties:
- power-domains:
- maxItems: 1
- required:
- - power-domains
-
-additionalProperties: false
-
-examples:
- - |
- phy@36000 {
- compatible = "amlogic,meson-g12a-usb2-phy";
- reg = <0x36000 0x2000>;
- clocks = <&xtal>;
- clock-names = "xtal";
- resets = <&phy_reset>;
- reset-names = "phy";
- #phy-cells = <0>;
- };
+++ /dev/null
-# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
-# Copyright 2019 BayLibre, SAS
-%YAML 1.2
----
-$id: "http://devicetree.org/schemas/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml#"
-$schema: "http://devicetree.org/meta-schemas/core.yaml#"
-
-title: Amlogic G12A USB3 + PCIE Combo PHY
-
-maintainers:
- - Neil Armstrong <neil.armstrong@linaro.org>
-
-properties:
- compatible:
- enum:
- - amlogic,meson-g12a-usb3-pcie-phy
-
- reg:
- maxItems: 1
-
- clocks:
- maxItems: 1
-
- clock-names:
- items:
- - const: ref_clk
-
- resets:
- maxItems: 1
-
- reset-names:
- items:
- - const: phy
-
- "#phy-cells":
- const: 1
-
-required:
- - compatible
- - reg
- - clocks
- - clock-names
- - resets
- - reset-names
- - "#phy-cells"
-
-additionalProperties: false
-
-examples:
- - |
- phy@46000 {
- compatible = "amlogic,meson-g12a-usb3-pcie-phy";
- reg = <0x46000 0x2000>;
- clocks = <&ref_clk>;
- clock-names = "ref_clk";
- resets = <&phy_reset>;
- reset-names = "phy";
- #phy-cells = <1>;
- };
compatible:
enum:
- qcom,usb-hs-28nm-femtophy
- - qcom,usb-hs-28nm-mdm9607
reg:
maxItems: 1
additional information and example.
patternProperties:
- # 25 LDOs
- "^LDO([1-9]|[1][0-9]|2[0-5])$":
+ # 25 LDOs, without LDO10-12
+ "^LDO([1-9]|1[3-9]|2[0-5])$":
type: object
$ref: regulator.yaml#
unevaluatedProperties: false
required:
- regulator-name
+ "^LDO(1[0-2])$":
+ type: object
+ $ref: regulator.yaml#
+ unevaluatedProperties: false
+ description:
+ Properties for single LDO regulator.
+
+ properties:
+ samsung,ext-control-gpios:
+ maxItems: 1
+ description:
+ LDO10, LDO11 and LDO12 can be configured to external control over
+ GPIO.
+
+ required:
+ - regulator-name
+
# 5 bucks
"^BUCK[1-5]$":
type: object
insensitive, letters in the riscv,isa string must be all
lowercase to simplify parsing.
$ref: "/schemas/types.yaml#/definitions/string"
- pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:_[hsxz](?:[a-z])+)*$
+ pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$
# RISC-V requires 'timebase-frequency' in /cpus, so disallow it here
timebase-frequency: false
description:
Indicates that the setting of RTC time is allowed by the host CPU.
+ wakeup-source: true
+
required:
- compatible
- reg
qcom,protection-domain:
$ref: /schemas/types.yaml#/definitions/string-array
description: |
- Protection domain service name and path for APR service
- possible values are::
+ Protection domain service name and path for APR service (if supported).
+ Possible values are::
"avs/audio", "msm/adsp/audio_pd".
"kernel/elf_loader", "msm/modem/wlan_pd".
"tms/servreg", "msm/adsp/audio_pd".
required:
- reg
- - qcom,protection-domain
additionalProperties: true
compatible:
enum:
- mediatek,mt8186-mt6366-rt1019-rt5682s-sound
+ - mediatek,mt8186-mt6366-rt5682s-max98360-sound
mediatek,platform:
$ref: "/schemas/types.yaml#/definitions/phandle"
const: 0
clocks:
- maxItems: 5
+ oneOf:
+ - maxItems: 3
+ - maxItems: 5
clock-names:
oneOf:
maintainers:
- Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
-allOf:
- - $ref: dai-common.yaml#
-
properties:
compatible:
enum:
const: 0
clocks:
- maxItems: 5
+ minItems: 5
+ maxItems: 6
clock-names:
- items:
- - const: mclk
- - const: npl
- - const: macro
- - const: dcodec
- - const: fsgen
+ minItems: 5
+ maxItems: 6
clock-output-names:
maxItems: 1
- reg
- "#sound-dai-cells"
+allOf:
+ - $ref: dai-common.yaml#
+
+ - if:
+ properties:
+ compatible:
+ enum:
+ - qcom,sc7280-lpass-wsa-macro
+ - qcom,sm8450-lpass-wsa-macro
+ - qcom,sc8280xp-lpass-wsa-macro
+ then:
+ properties:
+ clocks:
+ maxItems: 5
+ clock-names:
+ items:
+ - const: mclk
+ - const: npl
+ - const: macro
+ - const: dcodec
+ - const: fsgen
+
+ - if:
+ properties:
+ compatible:
+ enum:
+ - qcom,sm8250-lpass-wsa-macro
+ then:
+ properties:
+ clocks:
+ minItems: 6
+ clock-names:
+ items:
+ - const: mclk
+ - const: npl
+ - const: macro
+ - const: dcodec
+ - const: va
+ - const: fsgen
+
unevaluatedProperties: false
examples:
- |
+ #include <dt-bindings/clock/qcom,sm8250-lpass-aoncc.h>
#include <dt-bindings/sound/qcom,q6afe.h>
codec@3240000 {
compatible = "qcom,sm8250-lpass-wsa-macro";
<&audiocc 0>,
<&q6afecc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
<&q6afecc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+ <&aoncc LPASS_CDC_VA_MCLK>,
<&vamacro>;
- clock-names = "mclk", "npl", "macro", "dcodec", "fsgen";
+ clock-names = "mclk", "npl", "macro", "dcodec", "va", "fsgen";
clock-output-names = "mclk";
};
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
qcom,ports-sinterval-low:
$ref: /schemas/types.yaml#/definitions/uint8-array
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
qcom,ports-block-pack-mode:
$ref: /schemas/types.yaml#/definitions/uint8-array
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
title: Atmel SPI device
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
allOf:
- $ref: spi-controller.yaml#
title: Atmel Quad Serial Peripheral Interface (QSPI)
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
allOf:
- $ref: spi-controller.yaml#
description:
Maximum SPI clocking speed of the device in Hz.
- spi-cs-setup-ns:
+ spi-cs-setup-delay-ns:
description:
- Delay in nanosecods to be introduced by the controller after CS is
+ Delay in nanoseconds to be introduced by the controller after CS is
asserted.
spi-rx-bus-width:
dax A legacy option which is an alias for ``dax=always``.
device=%s Specify a path to an extra device to be used together.
fsid=%s Specify a filesystem image ID for Fscache back-end.
+domain_id=%s Specify a domain ID in fscache mode so that different images
+ with the same blobs under a given domain ID can share storage.
=================== =========================================================
Sysfs Entries
When executing "make clean", the file "crc32table.h" will be deleted.
Kbuild will assume files to be in the same relative directory as the
-Makefile, except if prefixed with $(objtree).
+Makefile.
To exclude certain files or directories from make clean, use the
$(no-clean-files) variable.
../riscv/patch-acceptance
../driver-api/media/maintainer-entry-profile
../driver-api/vfio-pci-device-specific-driver-acceptance
+ ../nvme/feature-and-quirk-policy
userspace tools.
Documentation for Linux bridging is on:
- http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge
+ https://wiki.linuxfoundation.org/networking/bridge
The bridge-utilities are maintained at:
git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/bridge-utils.git
----
This driver supports NAPI (Rx polling mode).
For more information on NAPI, see
-https://www.linuxfoundation.org/collaborate/workgroups/networking/napi
+https://wiki.linuxfoundation.org/networking/napi
MACVLAN
Support
=======
-If you got any problem, contact Wangxun support team via support@trustnetic.com
+If you got any problem, contact Wangxun support team via nic-support@net-swift.com
and Cc: netdev.
default 3
nf_conntrack_sctp_timeout_established - INTEGER (seconds)
- default 432000 (5 days)
+ default 210
+
+ Default is set to (hb_interval * path_max_retrans + rto_max)
nf_conntrack_sctp_timeout_shutdown_sent - INTEGER (seconds)
default 0.3
This timeout is used to setup conntrack entry on secondary paths.
Default is set to hb_interval.
-nf_conntrack_sctp_timeout_heartbeat_acked - INTEGER (seconds)
- default 210
-
- This timeout is used to setup conntrack entry on secondary paths.
- Default is set to (hb_interval * path_max_retrans + rto_max)
-
nf_conntrack_udp_timeout - INTEGER (seconds)
default 30
notify_end_rx can be NULL or it can be used to specify a function to be
called when the call changes state to end the Tx phase. This function is
- called with the call-state spinlock held to prevent any reply or final ACK
- from being delivered first.
+ called with a spinlock held to prevent the last DATA packet from being
+ transmitted until the function returns.
(#) Receive data from a call::
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================================
+Linux NVMe feature and and quirk policy
+=======================================
+
+This file explains the policy used to decide what is supported by the
+Linux NVMe driver and what is not.
+
+
+Introduction
+============
+
+NVM Express is an open collection of standards and information.
+
+The Linux NVMe host driver in drivers/nvme/host/ supports devices
+implementing the NVM Express (NVMe) family of specifications, which
+currently consists of a number of documents:
+
+ - the NVMe Base specification
+ - various Command Set specifications (e.g. NVM Command Set)
+ - various Transport specifications (e.g. PCIe, Fibre Channel, RDMA, TCP)
+ - the NVMe Management Interface specification
+
+See https://nvmexpress.org/developers/ for the NVMe specifications.
+
+
+Supported features
+==================
+
+NVMe is a large suite of specifications, and contains features that are only
+useful or suitable for specific use-cases. It is important to note that Linux
+does not aim to implement every feature in the specification. Every additional
+feature implemented introduces more code, more maintenance and potentially more
+bugs. Hence there is an inherent tradeoff between functionality and
+maintainability of the NVMe host driver.
+
+Any feature implemented in the Linux NVMe host driver must support the
+following requirements:
+
+ 1. The feature is specified in a release version of an official NVMe
+ specification, or in a ratified Technical Proposal (TP) that is
+ available on NVMe website. Or if it is not directly related to the
+ on-wire protocol, does not contradict any of the NVMe specifications.
+ 2. Does not conflict with the Linux architecture, nor the design of the
+ NVMe host driver.
+ 3. Has a clear, indisputable value-proposition and a wide consensus across
+ the community.
+
+Vendor specific extensions are generally not supported in the NVMe host
+driver.
+
+It is strongly recommended to work with the Linux NVMe and block layer
+maintainers and get feedback on specification changes that are intended
+to be used by the Linux NVMe host driver in order to avoid conflict at a
+later stage.
+
+
+Quirks
+======
+
+Sometimes implementations of open standards fail to correctly implement parts
+of the standards. Linux uses identifier-based quirks to work around such
+implementation bugs. The intent of quirks is to deal with widely available
+hardware, usually consumer, which Linux users can't use without these quirks.
+Typically these implementations are not or only superficially tested with Linux
+by the hardware manufacturer.
+
+The Linux NVMe maintainers decide ad hoc whether to quirk implementations
+based on the impact of the problem to Linux users and how it impacts
+maintainability of the driver. In general quirks are a last resort, if no
+firmware updates or other workarounds are available from the vendor.
+
+Quirks will not be added to the Linux kernel for hardware that isn't available
+on the mass market. Hardware that fails qualification for enterprise Linux
+distributions, ChromeOS, Android or other consumers of the Linux kernel
+should be fixed before it is shipped instead of relying on Linux quirks.
.. _netdev-FAQ:
-==========
-netdev FAQ
-==========
+=============================
+Networking subsystem (netdev)
+=============================
tl;dr
-----
- don't repost your patches within one 24h period
- reverse xmas tree
-What is netdev?
----------------
-It is a mailing list for all network-related Linux stuff. This
+netdev
+------
+
+netdev is a mailing list for all network-related Linux stuff. This
includes anything found under net/ (i.e. core code like IPv6) and
drivers/net (i.e. hardware specific drivers) in the Linux source tree.
Note that some subsystems (e.g. wireless drivers) which have a high
-volume of traffic have their own specific mailing lists.
+volume of traffic have their own specific mailing lists and trees.
The netdev list is managed (like many other Linux mailing lists) through
VGER (http://vger.kernel.org/) with archives available at
Linux development (i.e. RFC, review, comments, etc.) takes place on
netdev.
-How do the changes posted to netdev make their way into Linux?
---------------------------------------------------------------
-There are always two trees (git repositories) in play. Both are
-driven by David Miller, the main network maintainer. There is the
-``net`` tree, and the ``net-next`` tree. As you can probably guess from
-the names, the ``net`` tree is for fixes to existing code already in the
-mainline tree from Linus, and ``net-next`` is where the new code goes
-for the future release. You can find the trees here:
-
-- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
-- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
-
-How do I indicate which tree (net vs. net-next) my patch should be in?
-----------------------------------------------------------------------
-To help maintainers and CI bots you should explicitly mark which tree
-your patch is targeting. Assuming that you use git, use the prefix
-flag::
-
- git format-patch --subject-prefix='PATCH net-next' start..finish
+Development cycle
+-----------------
-Use ``net`` instead of ``net-next`` (always lower case) in the above for
-bug-fix ``net`` content.
-
-How often do changes from these trees make it to the mainline Linus tree?
--------------------------------------------------------------------------
-To understand this, you need to know a bit of background information on
+Here is a bit of background information on
the cadence of Linux development. Each new release starts off with a
two week "merge window" where the main maintainers feed their new stuff
to Linus for merging into the mainline tree. After the two weeks, the
state of churn), and a week after the last vX.Y-rcN was done, the
official vX.Y is released.
-Relating that to netdev: At the beginning of the 2-week merge window,
-the ``net-next`` tree will be closed - no new changes/features. The
-accumulated new content of the past ~10 weeks will be passed onto
+To find out where we are now in the cycle - load the mainline (Linus)
+page here:
+
+ https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+
+and note the top of the "tags" section. If it is rc1, it is early in
+the dev cycle. If it was tagged rc7 a week ago, then a release is
+probably imminent. If the most recent tag is a final release tag
+(without an ``-rcN`` suffix) - we are most likely in a merge window
+and ``net-next`` is closed.
+
+git trees and patch flow
+------------------------
+
+There are two networking trees (git repositories) in play. Both are
+driven by David Miller, the main network maintainer. There is the
+``net`` tree, and the ``net-next`` tree. As you can probably guess from
+the names, the ``net`` tree is for fixes to existing code already in the
+mainline tree from Linus, and ``net-next`` is where the new code goes
+for the future release. You can find the trees here:
+
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
+
+Relating that to kernel development: At the beginning of the 2-week
+merge window, the ``net-next`` tree will be closed - no new changes/features.
+The accumulated new content of the past ~10 weeks will be passed onto
mainline/Linus via a pull request for vX.Y -- at the same time, the
``net`` tree will start accumulating fixes for this pulled content
relating to vX.Y
Finally, the vX.Y gets released, and the whole cycle starts over.
-So where are we now in this cycle?
-----------------------------------
+netdev patch review
+-------------------
-Load the mainline (Linus) page here:
+Patch status
+~~~~~~~~~~~~
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-
-and note the top of the "tags" section. If it is rc1, it is early in
-the dev cycle. If it was tagged rc7 a week ago, then a release is
-probably imminent. If the most recent tag is a final release tag
-(without an ``-rcN`` suffix) - we are most likely in a merge window
-and ``net-next`` is closed.
-
-How can I tell the status of a patch I've sent?
------------------------------------------------
-Start by looking at the main patchworks queue for netdev:
+Status of a patch can be checked by looking at the main patchwork
+queue for netdev:
https://patchwork.kernel.org/project/netdevbpf/list/
which carried them so if you have trouble finding your patch append
the value of ``Message-ID`` to the URL above.
-How long before my patch is accepted?
--------------------------------------
-Generally speaking, the patches get triaged quickly (in less than
-48h). But be patient, if your patch is active in patchwork (i.e. it's
-listed on the project's patch list) the chances it was missed are close to zero.
-Asking the maintainer for status updates on your
-patch is a good way to ensure your patch is ignored or pushed to the
-bottom of the priority list.
+Updating patch status
+~~~~~~~~~~~~~~~~~~~~~
-Should I directly update patchwork state of my own patches?
------------------------------------------------------------
It may be tempting to help the maintainers and update the state of your
-own patches when you post a new version or spot a bug. Please do not do that.
+own patches when you post a new version or spot a bug. Please **do not**
+do that.
Interfering with the patch status on patchwork will only cause confusion. Leave
it to the maintainer to figure out what is the most recent and current
version that should be applied. If there is any doubt, the maintainer
will reply and ask what should be done.
-How do I divide my work into patches?
--------------------------------------
+Review timelines
+~~~~~~~~~~~~~~~~
-Put yourself in the shoes of the reviewer. Each patch is read separately
-and therefore should constitute a comprehensible step towards your stated
-goal.
+Generally speaking, the patches get triaged quickly (in less than
+48h). But be patient, if your patch is active in patchwork (i.e. it's
+listed on the project's patch list) the chances it was missed are close to zero.
+Asking the maintainer for status updates on your
+patch is a good way to ensure your patch is ignored or pushed to the
+bottom of the priority list.
-Avoid sending series longer than 15 patches. Larger series takes longer
-to review as reviewers will defer looking at it until they find a large
-chunk of time. A small series can be reviewed in a short time, so Maintainers
-just do it. As a result, a sequence of smaller series gets merged quicker and
-with better review coverage. Re-posting large series also increases the mailing
-list traffic.
+Partial resends
+~~~~~~~~~~~~~~~
-I made changes to only a few patches in a patch series should I resend only those changed?
-------------------------------------------------------------------------------------------
-No, please resend the entire patch series and make sure you do number your
+Please always resend the entire patch series and make sure you do number your
patches such that it is clear this is the latest and greatest set of patches
-that can be applied.
-
-I have received review feedback, when should I post a revised version of the patches?
--------------------------------------------------------------------------------------
-Allow at least 24 hours to pass between postings. This will ensure reviewers
-from all geographical locations have a chance to chime in. Do not wait
-too long (weeks) between postings either as it will make it harder for reviewers
-to recall all the context.
+that can be applied. Do not try to resend just the patches which changed.
-Make sure you address all the feedback in your new posting. Do not post a new
-version of the code if the discussion about the previous version is still
-ongoing, unless directly instructed by a reviewer.
+Handling misapplied patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
-I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
-----------------------------------------------------------------------------------------------------------------------------------------
+Occasionally a patch series gets applied before receiving critical feedback,
+or the wrong version of a series gets applied.
There is no revert possible, once it is pushed out, it stays like that.
Please send incremental versions on top of what has been merged in order to fix
the patches the way they would look like if your latest patch series was to be
merged.
-Are there special rules regarding stable submissions on netdev?
----------------------------------------------------------------
+Stable tree
+~~~~~~~~~~~
+
While it used to be the case that netdev submissions were not supposed
to carry explicit ``CC: stable@vger.kernel.org`` tags that is no longer
the case today. Please follow the standard stable rules in
:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`,
and make sure you include appropriate Fixes tags!
-Is the comment style convention different for the networking content?
----------------------------------------------------------------------
-Yes, in a largely trivial way. Instead of this::
+Security fixes
+~~~~~~~~~~~~~~
+
+Do not email netdev maintainers directly if you think you discovered
+a bug that might have possible security implications.
+The current netdev maintainer has consistently requested that
+people use the mailing lists and not reach out directly. If you aren't
+OK with that, then perhaps consider mailing security@kernel.org or
+reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
+as possible alternative mechanisms.
+
+
+Co-posting changes to user space components
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+User space code exercising kernel features should be posted
+alongside kernel patches. This gives reviewers a chance to see
+how any new interface is used and how well it works.
+
+When user space tools reside in the kernel repo itself all changes
+should generally come as one series. If series becomes too large
+or the user space project is not reviewed on netdev include a link
+to a public repo where user space patches can be seen.
+
+In case user space tooling lives in a separate repository but is
+reviewed on netdev (e.g. patches to ``iproute2`` tools) kernel and
+user space patches should form separate series (threads) when posted
+to the mailing list, e.g.::
+
+ [PATCH net-next 0/3] net: some feature cover letter
+ └─ [PATCH net-next 1/3] net: some feature prep
+ └─ [PATCH net-next 2/3] net: some feature do it
+ └─ [PATCH net-next 3/3] selftest: net: some feature
+
+ [PATCH iproute2-next] ip: add support for some feature
+
+Posting as one thread is discouraged because it confuses patchwork
+(as of patchwork 2.2.2).
+
+Preparing changes
+-----------------
+
+Attention to detail is important. Re-read your own work as if you were the
+reviewer. You can start with using ``checkpatch.pl``, perhaps even with
+the ``--strict`` flag. But do not be mindlessly robotic in doing so.
+If your change is a bug fix, make sure your commit log indicates the
+end-user visible symptom, the underlying reason as to why it happens,
+and then if necessary, explain why the fix proposed is the best way to
+get things done. Don't mangle whitespace, and as is common, don't
+mis-indent function arguments that span multiple lines. If it is your
+first patch, mail it to yourself so you can test apply it to an
+unpatched tree to confirm infrastructure didn't mangle it.
+
+Finally, go back and read
+:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
+to be sure you are not repeating some common mistake documented there.
+
+Indicating target tree
+~~~~~~~~~~~~~~~~~~~~~~
+
+To help maintainers and CI bots you should explicitly mark which tree
+your patch is targeting. Assuming that you use git, use the prefix
+flag::
+
+ git format-patch --subject-prefix='PATCH net-next' start..finish
+
+Use ``net`` instead of ``net-next`` (always lower case) in the above for
+bug-fix ``net`` content.
+
+Dividing work into patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Put yourself in the shoes of the reviewer. Each patch is read separately
+and therefore should constitute a comprehensible step towards your stated
+goal.
+
+Avoid sending series longer than 15 patches. Larger series takes longer
+to review as reviewers will defer looking at it until they find a large
+chunk of time. A small series can be reviewed in a short time, so Maintainers
+just do it. As a result, a sequence of smaller series gets merged quicker and
+with better review coverage. Re-posting large series also increases the mailing
+list traffic.
+
+Multi-line comments
+~~~~~~~~~~~~~~~~~~~
+
+Comment style convention is slightly different for networking and most of
+the tree. Instead of this::
/*
* foobar blah blah blah
* another line of text
*/
-What is "reverse xmas tree"?
-----------------------------
+Local variable ordering ("reverse xmas tree", "RCS")
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Netdev has a convention for ordering local variables in functions.
Order the variable declaration lines longest to shortest, e.g.::
If there are dependencies between the variables preventing the ordering
move the initialization out of line.
-I am working in existing code which uses non-standard formatting. Which formatting should I use?
-------------------------------------------------------------------------------------------------
-Make your code follow the most recent guidelines, so that eventually all code
+Format precedence
+~~~~~~~~~~~~~~~~~
+
+When working in existing code which uses nonstandard formatting make
+your code follow the most recent guidelines, so that eventually all code
in the domain of netdev is in the preferred format.
-I found a bug that might have possible security implications or similar. Should I mail the main netdev maintainer off-list?
----------------------------------------------------------------------------------------------------------------------------
-No. The current netdev maintainer has consistently requested that
-people use the mailing lists and not reach out directly. If you aren't
-OK with that, then perhaps consider mailing security@kernel.org or
-reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
-as possible alternative mechanisms.
+Resending after review
+~~~~~~~~~~~~~~~~~~~~~~
+
+Allow at least 24 hours to pass between postings. This will ensure reviewers
+from all geographical locations have a chance to chime in. Do not wait
+too long (weeks) between postings either as it will make it harder for reviewers
+to recall all the context.
+
+Make sure you address all the feedback in your new posting. Do not post a new
+version of the code if the discussion about the previous version is still
+ongoing, unless directly instructed by a reviewer.
+
+Testing
+-------
+
+Expected level of testing
+~~~~~~~~~~~~~~~~~~~~~~~~~
-What level of testing is expected before I submit my change?
-------------------------------------------------------------
At the very minimum your changes must survive an ``allyesconfig`` and an
``allmodconfig`` build with ``W=1`` set without new warnings or failures.
You are expected to test your changes on top of the relevant networking
tree (``net`` or ``net-next``) and not e.g. a stable tree or ``linux-next``.
-How do I post corresponding changes to user space components?
--------------------------------------------------------------
-User space code exercising kernel features should be posted
-alongside kernel patches. This gives reviewers a chance to see
-how any new interface is used and how well it works.
-
-When user space tools reside in the kernel repo itself all changes
-should generally come as one series. If series becomes too large
-or the user space project is not reviewed on netdev include a link
-to a public repo where user space patches can be seen.
-
-In case user space tooling lives in a separate repository but is
-reviewed on netdev (e.g. patches to ``iproute2`` tools) kernel and
-user space patches should form separate series (threads) when posted
-to the mailing list, e.g.::
-
- [PATCH net-next 0/3] net: some feature cover letter
- └─ [PATCH net-next 1/3] net: some feature prep
- └─ [PATCH net-next 2/3] net: some feature do it
- └─ [PATCH net-next 3/3] selftest: net: some feature
-
- [PATCH iproute2-next] ip: add support for some feature
-
-Posting as one thread is discouraged because it confuses patchwork
-(as of patchwork 2.2.2).
-
-Can I reproduce the checks from patchwork on my local machine?
---------------------------------------------------------------
+patchwork checks
+~~~~~~~~~~~~~~~~
Checks in patchwork are mostly simple wrappers around existing kernel
scripts, the sources are available at:
https://github.com/kuba-moo/nipa/tree/master/tests
-Running all the builds and checks locally is a pain, can I post my patches and have the patchwork bot validate them?
---------------------------------------------------------------------------------------------------------------------
-
-No, you must ensure that your patches are ready by testing them locally
+**Do not** post your patches just to run them through the checks.
+You must ensure that your patches are ready by testing them locally
before posting to the mailing list. The patchwork build bot instance
gets overloaded very easily and netdev@vger really doesn't need more
traffic if we can help it.
-netdevsim is great, can I extend it for my out-of-tree tests?
--------------------------------------------------------------
+netdevsim
+~~~~~~~~~
-No, ``netdevsim`` is a test vehicle solely for upstream tests.
-(Please add your tests under ``tools/testing/selftests/``.)
+``netdevsim`` is a test driver which can be used to exercise driver
+configuration APIs without requiring capable hardware.
+Mock-ups and tests based on ``netdevsim`` are strongly encouraged when
+adding new APIs, but ``netdevsim`` in itself is **not** considered
+a use case/user. You must also implement the new APIs in a real driver.
-We also give no guarantees that ``netdevsim`` won't change in the future
+We give no guarantees that ``netdevsim`` won't change in the future
in a way which would break what would normally be considered uAPI.
-Is netdevsim considered a "user" of an API?
--------------------------------------------
-
-Linux kernel has a long standing rule that no API should be added unless
-it has a real, in-tree user. Mock-ups and tests based on ``netdevsim`` are
-strongly encouraged when adding new APIs, but ``netdevsim`` in itself
-is **not** considered a use case/user.
-
-Any other tips to help ensure my net/net-next patch gets OK'd?
---------------------------------------------------------------
-Attention to detail. Re-read your own work as if you were the
-reviewer. You can start with using ``checkpatch.pl``, perhaps even with
-the ``--strict`` flag. But do not be mindlessly robotic in doing so.
-If your change is a bug fix, make sure your commit log indicates the
-end-user visible symptom, the underlying reason as to why it happens,
-and then if necessary, explain why the fix proposed is the best way to
-get things done. Don't mangle whitespace, and as is common, don't
-mis-indent function arguments that span multiple lines. If it is your
-first patch, mail it to yourself so you can test apply it to an
-unpatched tree to confirm infrastructure didn't mangle it.
-
-Finally, go back and read
-:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
-to be sure you are not repeating some common mistake documented there.
+``netdevsim`` is reserved for use by upstream tests only, so any
+new ``netdevsim`` features must be accompanied by selftests under
+``tools/testing/selftests/``.
-My company uses peer feedback in employee performance reviews. Can I ask netdev maintainers for feedback?
----------------------------------------------------------------------------------------------------------
+Testimonials / feedback
+-----------------------
-Yes, especially if you spend significant amount of time reviewing code
+Some companies use peer feedback in employee performance reviews.
+Please feel free to request feedback from netdev maintainers,
+especially if you spend significant amount of time reviewing code
and go out of your way to improve shared infrastructure.
The feedback must be requested by you, the contributor, and will always
import os
import sys
-from sphinx.util.pycompat import execfile_
+from sphinx.util.osutil import fs_encoding
# ------------------------------------------------------------------------------
def loadConfig(namespace):
sys.stdout.write("load additional sphinx-config: %s\n" % config_file)
config = namespace.copy()
config['__file__'] = config_file
- execfile_(config_file, config)
+ with open(config_file, 'rb') as f:
+ code = compile(f.read(), fs_encoding, 'exec')
+ exec(code, config)
del config['__file__']
namespace.update(config)
else:
mmap() that affects the region will be made visible immediately. Another
example is madvise(MADV_DROP).
+Note: On arm64, a write generated by the page-table walker (to update
+the Access and Dirty flags, for example) never results in a
+KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This
+is because KVM cannot provide the data that would be written by the
+page-table walker, making it impossible to emulate the access.
+Instead, an abort (data abort if the cause of the page-table update
+was a load or a store, instruction abort if it was an instruction
+fetch) is injected in the guest.
4.36 KVM_SET_TSS_ADDR
---------------------
32 vCPUs in the shared_info page, KVM does not automatically do so
and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO be used
explicitly even when the vcpu_info for a given vCPU resides at the
- "default" location in the shared_info page. This is because KVM is
- not aware of the Xen CPU id which is used as the index into the
- vcpu_info[] array, so cannot know the correct default location.
+ "default" location in the shared_info page. This is because KVM may
+ not be aware of the Xen CPU id which is used as the index into the
+ vcpu_info[] array, so may know the correct default location.
Note that the shared info page may be constantly written to by KVM;
it contains the event channel bitmap used to deliver interrupts to
any vCPU has been running or any event channel interrupts can be
routed to the guest.
+ Setting the gfn to KVM_XEN_INVALID_GFN will disable the shared info
+ page.
+
KVM_XEN_ATTR_TYPE_UPCALL_VECTOR
Sets the exception vector used to deliver Xen event channel upcalls.
This is the HVM-wide vector injected directly by the hypervisor
(not through the local APIC), typically configured by a guest via
- HVM_PARAM_CALLBACK_IRQ.
+ HVM_PARAM_CALLBACK_IRQ. This can be disabled again (e.g. for guest
+ SHUTDOWN_soft_reset) by setting it to zero.
KVM_XEN_ATTR_TYPE_EVTCHN
This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
an outbound port number for interception of EVTCHNOP_send requests
- from the guest. A given sending port number may be directed back
- to a specified vCPU (by APIC ID) / port / priority on the guest,
- or to trigger events on an eventfd. The vCPU and priority can be
- changed by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call,
- but other fields cannot change for a given sending port. A port
- mapping is removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags
- field.
+ from the guest. A given sending port number may be directed back to
+ a specified vCPU (by APIC ID) / port / priority on the guest, or to
+ trigger events on an eventfd. The vCPU and priority can be changed
+ by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but but other
+ fields cannot change for a given sending port. A port mapping is
+ removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing
+ KVM_XEN_EVTCHN_RESET in the flags field removes all interception of
+ outbound event channels. The values of the flags field are mutually
+ exclusive and cannot be combined as a bitmask.
KVM_XEN_ATTR_TYPE_XEN_VERSION
This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the
XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read
other vCPUs' vcpu_runstate_info. Xen guests enable this feature via
- the VM_ASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist
+ the VMASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist
hypercall.
4.127 KVM_XEN_HVM_GET_ATTR
As with the shared_info page for the VM, the corresponding page may be
dirtied at any time if event channel interrupt delivery is enabled, so
userspace should always assume that the page is dirty without relying
- on dirty logging.
+ on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable
+ the vcpu_info.
KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO
Sets the guest physical address of an additional pvclock structure
for a given vCPU. This is typically used for guest vsyscall support.
+ Setting the gpa to KVM_XEN_INVALID_GPA will disable the structure.
KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR
Sets the guest physical address of the vcpu_runstate_info for a given
vCPU. This is how a Xen guest tracks CPU state such as steal time.
+ Setting the gpa to KVM_XEN_INVALID_GPA will disable the runstate area.
KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT
Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of
This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
event channel port/priority for the VIRQ_TIMER of the vCPU, as well
- as allowing a pending timer to be saved/restored.
+ as allowing a pending timer to be saved/restored. Setting the timer
+ port to zero disables kernel handling of the singleshot timer.
KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR
This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
per-vCPU local APIC upcall vector, configured by a Xen guest with
the HVMOP_set_evtchn_upcall_vector hypercall. This is typically
used by Windows guests, and is distinct from the HVM-wide upcall
- vector configured with HVM_PARAM_CALLBACK_IRQ.
+ vector configured with HVM_PARAM_CALLBACK_IRQ. It is disabled by
+ setting the vector to zero.
4.129 KVM_XEN_VCPU_GET_ATTR
primary storage for certain register types. Therefore, the kernel may use the
values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.
-::
-
- };
-
-
6. Capabilities that can be enabled on vCPUs
============================================
state is final and avoid missing dirty pages from another ioctl ordered
after the bitmap collection.
-NOTE: One example of using the backup bitmap is saving arm64 vgic/its
-tables through KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} command on
-KVM device "kvm-arm-vgic-its" when dirty ring is enabled.
+NOTE: Multiple examples of using the backup bitmap: (1) save vgic/its
+tables through command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} on
+KVM device "kvm-arm-vgic-its". (2) restore vgic/its tables through
+command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_RESTORE_TABLES} on KVM device
+"kvm-arm-vgic-its". VGICv3 LPI pending status is restored. (3) save
+vgic3 pending table through KVM_DEV_ARM_VGIC_{GRP_CTRL, SAVE_PENDING_TABLES}
+command on KVM device "kvm-arm-vgic-v3".
8.30 KVM_CAP_XEN_HVM
--------------------
It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel
has enabled in-kernel emulation of the local APIC.
+CPU topology
+~~~~~~~~~~~~
+
+Several CPUID values include topology information for the host CPU:
+0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems. Different
+versions of KVM return different values for this information and userspace
+should not rely on it. Currently they return all zeroes.
+
+If userspace wishes to set up a guest topology, it should be careful that
+the values of these three leaves differ for each CPU. In particular,
+the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX
+for 0x8000001e; the latter also encodes the core id and node id in bits
+7:0 of EBX and ECX respectively.
+
Obsolete ioctls and capabilities
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
them together is quite rare.
-- Unlike kvm->slots_lock, kvm->slots_arch_lock is released before
- synchronize_srcu(&kvm->srcu). Therefore kvm->slots_arch_lock
- can be taken inside a kvm->srcu read-side critical section,
- while kvm->slots_lock cannot.
-
- kvm->mn_active_invalidate_count ensures that pairs of
invalidate_range_start() and invalidate_range_end() callbacks
use the same memslots array. kvm->slots_lock and kvm->slots_arch_lock
are taken on the waiting side in install_new_memslots, so MMU notifiers
must not take either kvm->slots_lock or kvm->slots_arch_lock.
+For SRCU:
+
+- ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections
+ for kvm->lock, vcpu->mutex and kvm->slots_lock. These locks _cannot_
+ be taken inside a kvm->srcu read-side critical section; that is, the
+ following is broken::
+
+ srcu_read_lock(&kvm->srcu);
+ mutex_lock(&kvm->slots_lock);
+
+- kvm->slots_arch_lock instead is released before the call to
+ ``synchronize_srcu()``. It _can_ therefore be taken inside a
+ kvm->srcu read-side critical section, for example while processing
+ a vmexit.
+
On x86:
-- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock
+- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock
- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock and
kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and
not enable SME, then Linux will not be able to activate memory encryption, even
if configured to do so by default or the mem_encrypt=on command line parameter
is specified.
+
+Secure Nested Paging (SNP)
+==========================
+
+SEV-SNP introduces new features (SEV_FEATURES[1:63]) which can be enabled
+by the hypervisor for security enhancements. Some of these features need
+guest side implementation to function correctly. The below table lists the
+expected guest behavior with various possible scenarios of guest/hypervisor
+SNP feature support.
+
++-----------------+---------------+---------------+------------------+
+| Feature Enabled | Guest needs | Guest has | Guest boot |
+| by the HV | implementation| implementation| behaviour |
++=================+===============+===============+==================+
+| No | No | No | Boot |
+| | | | |
++-----------------+---------------+---------------+------------------+
+| No | Yes | No | Boot |
+| | | | |
++-----------------+---------------+---------------+------------------+
+| No | Yes | Yes | Boot |
+| | | | |
++-----------------+---------------+---------------+------------------+
+| Yes | No | No | Boot with |
+| | | | feature enabled |
++-----------------+---------------+---------------+------------------+
+| Yes | Yes | No | Graceful boot |
+| | | | failure |
++-----------------+---------------+---------------+------------------+
+| Yes | Yes | Yes | Boot with |
+| | | | feature enabled |
++-----------------+---------------+---------------+------------------+
+
+More details in AMD64 APM[1] Vol 2: 15.34.10 SEV_STATUS MSR
+
+[1] https://www.amd.com/system/files/TechDocs/40332.pdf
M: Robert Moore <robert.moore@intel.com>
M: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
L: linux-acpi@vger.kernel.org
-L: devel@acpica.org
+L: acpica-devel@lists.linuxfoundation.org
S: Supported
W: https://acpica.org/
W: https://github.com/acpica/acpica/
F: drivers/dma/ptdma/
AMD SEATTLE DEVICE TREE SUPPORT
-M: Brijesh Singh <brijeshkumar.singh@amd.com>
M: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
M: Tom Lendacky <thomas.lendacky@amd.com>
S: Supported
F: arch/arm64/boot/dts/amd/
AMD XGBE DRIVER
-M: Tom Lendacky <thomas.lendacky@amd.com>
M: "Shyam Sundar S K" <Shyam-sundar.S-k@amd.com>
L: netdev@vger.kernel.org
S: Supported
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
X: drivers/media/i2c/
+F: arch/arm64/boot/dts/freescale/
+X: arch/arm64/boot/dts/freescale/fsl-*
+X: arch/arm64/boot/dts/freescale/qoriq-*
N: imx
N: mxs
ARM/Mediatek SoC support
M: Matthias Brugger <matthias.bgg@gmail.com>
+R: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
+L: linux-kernel@vger.kernel.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-mediatek@lists.infradead.org (moderated for non-subscribers)
S: Maintained
W: https://mtk.wiki.kernel.org/
-C: irc://chat.freenode.net/linux-mediatek
+C: irc://irc.libera.chat/linux-mediatek
+F: arch/arm/boot/dts/mt2*
F: arch/arm/boot/dts/mt6*
F: arch/arm/boot/dts/mt7*
F: arch/arm/boot/dts/mt8*
F: arch/arm64/boot/dts/mediatek/
F: drivers/soc/mediatek/
N: mtk
-N: mt[678]
+N: mt[2678]
K: mediatek
ARM/Mediatek USB3 PHY DRIVER
BONDING DRIVER
M: Jay Vosburgh <j.vosburgh@gmail.com>
-M: Veaceslav Falico <vfalico@gmail.com>
M: Andy Gospodarek <andy@greyhouse.net>
L: netdev@vger.kernel.org
S: Supported
DRM DRIVERS FOR BRIDGE CHIPS
M: Andrzej Hajda <andrzej.hajda@intel.com>
M: Neil Armstrong <neil.armstrong@linaro.org>
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
R: Laurent Pinchart <Laurent.pinchart@ideasonboard.com>
R: Jonas Karlman <jonas@kwiboo.se>
R: Jernej Skrabec <jernej.skrabec@gmail.com>
F: drivers/firmware/efi/test/
EFI VARIABLE FILESYSTEM
-M: Matthew Garrett <matthew.garrett@nebula.com>
M: Jeremy Kerr <jk@ozlabs.org>
M: Ard Biesheuvel <ardb@kernel.org>
L: linux-efi@vger.kernel.org
EXTRA BOOT CONFIG
M: Masami Hiramatsu <mhiramat@kernel.org>
+L: linux-kernel@vger.kernel.org
+L: linux-trace-kernel@vger.kernel.org
+Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/
S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
F: Documentation/admin-guide/bootconfig.rst
F: fs/proc/bootconfig.c
F: include/linux/bootconfig.h
FPU EMULATOR
M: Bill Metzenthen <billm@melbpc.org.au>
S: Maintained
-W: http://floatingpoint.sourceforge.net/emulator/index.html
+W: https://floatingpoint.billm.au/
F: arch/x86/math-emu/
FRAMEBUFFER CORE
F: include/linux/fscache*.h
FSCRYPT: FILE SYSTEM LEVEL ENCRYPTION SUPPORT
+M: Eric Biggers <ebiggers@kernel.org>
M: Theodore Y. Ts'o <tytso@mit.edu>
M: Jaegeuk Kim <jaegeuk@kernel.org>
-M: Eric Biggers <ebiggers@kernel.org>
L: linux-fscrypt@vger.kernel.org
S: Supported
Q: https://patchwork.kernel.org/project/linux-fscrypt/list/
-T: git git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt.git
+T: git https://git.kernel.org/pub/scm/fs/fscrypt/linux.git
F: Documentation/filesystems/fscrypt.rst
F: fs/crypto/
-F: include/linux/fscrypt*.h
+F: include/linux/fscrypt.h
F: include/uapi/linux/fscrypt.h
FSI SUBSYSTEM
FSVERITY: READ-ONLY FILE-BASED AUTHENTICITY PROTECTION
M: Eric Biggers <ebiggers@kernel.org>
M: Theodore Y. Ts'o <tytso@mit.edu>
-L: linux-fscrypt@vger.kernel.org
+L: fsverity@lists.linux.dev
S: Supported
-Q: https://patchwork.kernel.org/project/linux-fscrypt/list/
-T: git git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt.git fsverity
+Q: https://patchwork.kernel.org/project/fsverity/list/
+T: git https://git.kernel.org/pub/scm/fs/fsverity/linux.git
F: Documentation/filesystems/fsverity.rst
F: fs/verity/
F: include/linux/fsverity.h
F: arch/*/*/*/*ftrace*
F: arch/*/*/*ftrace*
F: include/*/ftrace.h
+F: samples/ftrace
FUNGIBLE ETHERNET DRIVERS
M: Dimitris Michailidis <dmichail@fungible.com>
HISILICON DMA DRIVER
M: Zhou Wang <wangzhou1@hisilicon.com>
-M: Jie Hai <haijie1@hisilicon.com>
+M: Jie Hai <haijie1@huawei.com>
L: dmaengine@vger.kernel.org
S: Maintained
F: drivers/dma/hisi_dma.c
KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
M: Marc Zyngier <maz@kernel.org>
R: James Morse <james.morse@arm.com>
-R: Alexandru Elisei <alexandru.elisei@arm.com>
R: Suzuki K Poulose <suzuki.poulose@arm.com>
R: Oliver Upton <oliver.upton@linux.dev>
+R: Zenghui Yu <yuzenghui@huawei.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: kvmarm@lists.linux.dev
L: kvmarm@lists.cs.columbia.edu (deprecated, moderated for non-subscribers)
F: arch/x86/kvm/kvm_onhyperv.*
F: arch/x86/kvm/svm/hyperv.*
F: arch/x86/kvm/svm/svm_onhyperv.*
-F: arch/x86/kvm/vmx/evmcs.*
+F: arch/x86/kvm/vmx/hyperv.*
KVM X86 Xen (KVM/Xen)
M: David Woodhouse <dwmw2@infradead.org>
MICROCHIP AT91 DMA DRIVERS
M: Ludovic Desroches <ludovic.desroches@microchip.com>
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: dmaengine@vger.kernel.org
S: Supported
F: drivers/media/platform/microchip/microchip-csi2dc.c
MICROCHIP ECC DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-crypto@vger.kernel.org
S: Maintained
F: drivers/crypto/atmel-ecc.*
F: drivers/mmc/host/atmel-mci.c
MICROCHIP NAND DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-mtd@lists.infradead.org
S: Supported
F: Documentation/devicetree/bindings/mtd/atmel-nand.txt
F: drivers/power/reset/at91-sama5d2_shdwc.c
MICROCHIP SPI DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
S: Supported
F: drivers/spi/spi-atmel.*
NETWORKING [IPv4/IPv6]
M: "David S. Miller" <davem@davemloft.net>
-M: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
M: David Ahern <dsahern@kernel.org>
L: netdev@vger.kernel.org
S: Maintained
F: net/netlabel/
NETWORKING [MPTCP]
-M: Mat Martineau <mathew.j.martineau@linux.intel.com>
M: Matthieu Baerts <matthieu.baerts@tessares.net>
L: netdev@vger.kernel.org
L: mptcp@lists.linux.dev
S: Supported
W: http://git.infradead.org/nvme.git
T: git://git.infradead.org/nvme.git
+F: Documentation/nvme/
F: drivers/nvme/host/
F: drivers/nvme/common/
-F: include/linux/nvme*
+F: include/linux/nvme.h
+F: include/linux/nvme-*.h
F: include/uapi/linux/nvme_ioctl.h
NVM EXPRESS FABRICS AUTHENTICATION
M: Jonas Bonn <jonas@southpole.se>
M: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
M: Stafford Horne <shorne@gmail.com>
-L: openrisc@lists.librecores.org
+L: linux-openrisc@vger.kernel.org
S: Maintained
W: http://openrisc.io
T: git https://github.com/openrisc/linux.git
W: https://wireless.wiki.kernel.org/en/users/Drivers/p54
F: drivers/net/wireless/intersil/p54/
+PACKET SOCKETS
+M: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+S: Maintained
+F: include/uapi/linux/if_packet.h
+F: net/packet/af_packet.c
+
PACKING
M: Vladimir Oltean <olteanv@gmail.com>
L: netdev@vger.kernel.org
PCI ENDPOINT SUBSYSTEM
M: Lorenzo Pieralisi <lpieralisi@kernel.org>
-R: Krzysztof Wilczyński <kw@linux.com>
+M: Krzysztof Wilczyński <kw@linux.com>
R: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
R: Kishon Vijay Abraham I <kishon@kernel.org>
L: linux-pci@vger.kernel.org
Q: https://patchwork.kernel.org/project/linux-pci/list/
B: https://bugzilla.kernel.org
C: irc://irc.oftc.net/linux-pci
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/lpieralisi/pci.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
F: Documentation/PCI/endpoint/*
F: Documentation/misc-devices/pci-endpoint-test.rst
F: drivers/misc/pci_endpoint_test.c
Q: https://patchwork.kernel.org/project/linux-pci/list/
B: https://bugzilla.kernel.org
C: irc://irc.oftc.net/linux-pci
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
F: Documentation/driver-api/pci/p2pdma.rst
F: drivers/pci/p2pdma.c
F: include/linux/pci-p2pdma.h
PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
M: Lorenzo Pieralisi <lpieralisi@kernel.org>
+M: Krzysztof Wilczyński <kw@linux.com>
R: Rob Herring <robh@kernel.org>
-R: Krzysztof Wilczyński <kw@linux.com>
L: linux-pci@vger.kernel.org
S: Supported
Q: https://patchwork.kernel.org/project/linux-pci/list/
B: https://bugzilla.kernel.org
C: irc://irc.oftc.net/linux-pci
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/lpieralisi/pci.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
F: Documentation/devicetree/bindings/pci/
F: drivers/pci/controller/
F: drivers/pci/pci-bridge-emul.c
Q: https://patchwork.kernel.org/project/linux-pci/list/
B: https://bugzilla.kernel.org
C: irc://irc.oftc.net/linux-pci
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git
F: Documentation/PCI/
F: Documentation/devicetree/bindings/pci/
F: arch/x86/kernel/early-quirks.c
F: Documentation/devicetree/bindings/input/pine64,pinephone-keyboard.yaml
F: drivers/input/keyboard/pinephone-keyboard.c
+PKTCDVD DRIVER
+M: linux-block@vger.kernel.org
+S: Orphan
+F: drivers/block/pktcdvd.c
+F: include/linux/pktcdvd.h
+F: include/uapi/linux/pktcdvd.h
+
PLANTOWER PMS7003 AIR POLLUTION SENSOR DRIVER
M: Tomasz Duszynski <tduszyns@gmail.com>
S: Maintained
F: drivers/net/wwan/qcom_bam_dmux.c
QUALCOMM CAMERA SUBSYSTEM DRIVER
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
M: Todor Tomov <todor.too@gmail.com>
L: linux-media@vger.kernel.org
S: Maintained
QUALCOMM I2C CCI DRIVER
M: Loic Poulain <loic.poulain@linaro.org>
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
L: linux-i2c@vger.kernel.org
L: linux-arm-msm@vger.kernel.org
S: Maintained
L: linux-riscv@lists.infradead.org
S: Supported
Q: https://patchwork.kernel.org/project/linux-riscv/list/
+C: irc://irc.libera.chat/riscv
P: Documentation/riscv/patch-acceptance.rst
T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git
F: arch/riscv/
F: include/target/
SCTP PROTOCOL
-M: Vlad Yasevich <vyasevich@gmail.com>
M: Neil Horman <nhorman@tuxdriver.com>
M: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+M: Xin Long <lucien.xin@gmail.com>
L: linux-sctp@vger.kernel.org
S: Maintained
W: http://lksctp.sourceforge.net
S: Orphan
F: sound/soc/uniphier/
+SOCKET TIMESTAMPING
+M: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+S: Maintained
+F: Documentation/networking/timestamping.rst
+F: include/uapi/linux/net_tstamp.h
+F: tools/testing/selftests/net/so_txtime.c
+
SOEKRIS NET48XX LED SUPPORT
M: Chris Boot <bootc@bootc.net>
S: Maintained
F: drivers/pinctrl/spear/
SPI NOR SUBSYSTEM
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
M: Pratyush Yadav <pratyush@kernel.org>
R: Michael Walle <michael@walle.cc>
L: linux-mtd@lists.infradead.org
SUPERH
M: Yoshinori Sato <ysato@users.sourceforge.jp>
M: Rich Felker <dalias@libc.org>
+M: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
L: linux-sh@vger.kernel.org
S: Maintained
Q: http://patchwork.kernel.org/project/linux-sh/list/
F: drivers/platform/x86/system76_acpi.c
SYSV FILESYSTEM
-M: Christoph Hellwig <hch@infradead.org>
-S: Maintained
+S: Orphan
F: Documentation/filesystems/sysv-fs.rst
F: fs/sysv/
F: include/linux/sysv_fs.h
USB WEBCAM GADGET
M: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+M: Daniel Scally <dan.scally@ideasonboard.com>
L: linux-usb@vger.kernel.org
S: Maintained
F: drivers/usb/gadget/function/*uvc*
F: Documentation/admin-guide/media/zr364xx*
F: drivers/staging/media/deprecated/zr364xx/
+USER DATAGRAM PROTOCOL (UDP)
+M: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+S: Maintained
+F: include/linux/udp.h
+F: net/ipv4/udp.c
+F: net/ipv6/udp.c
+
USER-MODE LINUX (UML)
M: Richard Weinberger <richard@nod.at>
M: Anton Ivanov <anton.ivanov@cambridgegreys.com>
T: git git://git.kernel.org/pub/scm/utils/util-linux/util-linux.git
UUID HELPERS
-M: Christoph Hellwig <hch@lst.de>
R: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
L: linux-kernel@vger.kernel.org
S: Maintained
-T: git git://git.infradead.org/users/hch/uuid.git
F: include/linux/uuid.h
F: include/uapi/linux/uuid.h
F: lib/test_uuid.c
F: drivers/scsi/vmw_pvscsi.h
VMWARE VIRTUAL PTP CLOCK DRIVER
-M: Vivek Thampi <vithampi@vmware.com>
+M: Srivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
+M: Deep Shah <sdeep@vmware.com>
+R: Alexey Makhalov <amakhalov@vmware.com>
R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
L: netdev@vger.kernel.org
S: Supported
VERSION = 6
PATCHLEVEL = 2
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION =
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
headers_install modules_install kernelrelease image_name
no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \
image_name
-single-targets := %.a %.i %.rsi %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
+single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.rsi %.s %.symtypes %/
config-build :=
mixed-build :=
CFLAGS_KERNEL =
RUSTFLAGS_KERNEL =
AFLAGS_KERNEL =
-export LDFLAGS_vmlinux =
+LDFLAGS_vmlinux =
# Use USERINCLUDE when you must reference the UAPI directories only.
USERINCLUDE := \
@:
PHONY += vmlinux
+# LDFLAGS_vmlinux in the top Makefile defines linker flags for the top vmlinux,
+# not for decompressors. LDFLAGS_vmlinux in arch/*/boot/compressed/Makefile is
+# unrelated; the decompressors just happen to have the same base name,
+# arch/*/boot/compressed/vmlinux.
+# Export LDFLAGS_vmlinux only to scripts/Makefile.vmlinux.
+#
+# _LDFLAGS_vmlinux is a workaround for the 'private export' bug:
+# https://savannah.gnu.org/bugs/?61463
+# For Make > 4.4, the following simple code will work:
+# vmlinux: private export LDFLAGS_vmlinux := $(LDFLAGS_vmlinux)
+vmlinux: private _LDFLAGS_vmlinux := $(LDFLAGS_vmlinux)
+vmlinux: export LDFLAGS_vmlinux = $(_LDFLAGS_vmlinux)
vmlinux: vmlinux.o $(KBUILD_LDS) modpost
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux
# *.ko are usually independent of vmlinux, but CONFIG_DEBUG_INFOBTF_MODULES
# is an exception.
ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+KBUILD_BUILTIN := 1
modules: vmlinux
endif
# Remove MODORDER when done because it is not the real one.
PHONY += single_modules
single_modules: $(single-no-ko) modules_prepare
- $(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$m;) } > $(MODORDER)
+ $(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$(m:%.ko=%.o);) } > $(MODORDER)
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
ifneq ($(KBUILD_MODPOST_NOFINAL),1)
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal
ifeq ($(CONFIG_THUMB2_KERNEL),y)
CFLAGS_ISA :=-Wa,-mimplicit-it=always $(AFLAGS_NOWARN)
-AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb -D__thumb2__=2
+AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb
CFLAGS_ISA +=-mthumb
else
CFLAGS_ISA :=$(call cc-option,-marm,) $(AFLAGS_NOWARN)
};
gpio0: gpio@18100 {
- compatible = "marvell,armadaxp-gpio",
+ compatible = "marvell,armada-370-gpio",
"marvell,orion-gpio";
reg = <0x18100 0x40>, <0x181c0 0x08>;
reg-names = "gpio", "pwm";
};
gpio1: gpio@18140 {
- compatible = "marvell,armadaxp-gpio",
+ compatible = "marvell,armada-370-gpio",
"marvell,orion-gpio";
reg = <0x18140 0x40>, <0x181c8 0x08>;
reg-names = "gpio", "pwm";
};
gpio0: gpio@18100 {
- compatible = "marvell,armadaxp-gpio", "marvell,orion-gpio";
+ compatible = "marvell,orion-gpio";
reg = <0x18100 0x40>;
ngpios = <32>;
gpio-controller;
};
gpio1: gpio@18140 {
- compatible = "marvell,armadaxp-gpio", "marvell,orion-gpio";
+ compatible = "marvell,orion-gpio";
reg = <0x18140 0x40>;
ngpios = <28>;
gpio-controller;
};
pca9849@75 {
- compatible = "nxp,pca849";
+ compatible = "nxp,pca9849";
reg = <0x75>;
#address-cells = <1>;
#size-cells = <0>;
scl-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
status = "okay";
- i2c-switch@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9547";
#address-cells = <1>;
#size-cells = <0>;
&uart1 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_uart1>;
- uart-has-rtscts;
rts-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>;
status = "okay";
};
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
};
&i2c1 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c1>;
status = "okay";
};
&i2c4 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c1>;
status = "okay";
};
&i2c1 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c1>;
status = "okay";
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
&usbotg2 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usbotg2>;
+ over-current-active-low;
dr_mode = "host";
status = "okay";
};
pinctrl_usbotg2: usbotg2grp {
fsl,pins = <
- MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x04
+ MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x5c
>;
};
reg = <0xc8000000 0x1000>, <0xc0000000 0x4000000>;
reg-names = "control", "memory";
clocks = <&clk 0>;
+ nuvoton,shm = <&shm>;
status = "disabled";
};
serial@f995e000 {
status = "okay";
};
+ };
+};
- sdhci@f9824900 {
- bus-width = <8>;
- non-removable;
- status = "okay";
- };
+&sdhc_1 {
+ bus-width = <8>;
+ non-removable;
+ status = "okay";
+};
- sdhci@f98a4900 {
- cd-gpios = <&tlmm 122 GPIO_ACTIVE_LOW>;
- bus-width = <4>;
- };
- };
+&sdhc_2 {
+ cd-gpios = <&tlmm 122 GPIO_ACTIVE_LOW>;
+ bus-width = <4>;
};
status = "disabled";
};
- mmc@f9824900 {
+ sdhc_1: mmc@f9824900 {
compatible = "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4";
reg = <0xf9824900 0x11c>, <0xf9824000 0x800>;
reg-names = "hc", "core";
status = "disabled";
};
- mmc@f98a4900 {
+ sdhc_2: mmc@f98a4900 {
compatible = "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4";
reg = <0xf98a4900 0x11c>, <0xf98a4000 0x800>;
reg-names = "hc", "core";
clock-names = "dp", "pclk";
phys = <&edp_phy>;
phy-names = "dp";
+ power-domains = <&power RK3288_PD_VIO>;
resets = <&cru SRST_EDP>;
reset-names = "dp";
rockchip,grf = <&grf>;
mpddrc: mpddrc@ffffe800 {
compatible = "microchip,sam9x60-ddramc", "atmel,sama5d3-ddramc";
reg = <0xffffe800 0x200>;
- clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_CORE PMC_MCK>;
+ clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_PERIPHERAL 49>;
clock-names = "ddrck", "mpddr";
};
tsin-num = <0>;
serial-not-parallel;
i2c-bus = <&ssc2>;
- reset-gpios = <&pio15 4 GPIO_ACTIVE_HIGH>;
+ reset-gpios = <&pio15 4 GPIO_ACTIVE_LOW>;
dvb-card = <STV0367_TDA18212_NIMA_1>;
};
};
&qspi {
pinctrl-names = "default", "sleep";
- pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>;
- pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>;
+ pinctrl-0 = <&qspi_clk_pins_a
+ &qspi_bk1_pins_a
+ &qspi_cs1_pins_a>;
+ pinctrl-1 = <&qspi_clk_sleep_pins_a
+ &qspi_bk1_sleep_pins_a
+ &qspi_cs1_sleep_pins_a>;
reg = <0x58003000 0x1000>, <0x70000000 0x4000000>;
#address-cells = <1>;
#size-cells = <0>;
&qspi {
pinctrl-names = "default", "sleep";
- pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>;
- pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>;
+ pinctrl-0 = <&qspi_clk_pins_a
+ &qspi_bk1_pins_a
+ &qspi_cs1_pins_a>;
+ pinctrl-1 = <&qspi_clk_sleep_pins_a
+ &qspi_bk1_sleep_pins_a
+ &qspi_cs1_sleep_pins_a>;
reg = <0x58003000 0x1000>, <0x70000000 0x4000000>;
#address-cells = <1>;
#size-cells = <0>;
&qspi {
pinctrl-names = "default", "sleep";
- pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>;
- pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>;
+ pinctrl-0 = <&qspi_clk_pins_a
+ &qspi_bk1_pins_a
+ &qspi_cs1_pins_a>;
+ pinctrl-1 = <&qspi_clk_sleep_pins_a
+ &qspi_bk1_sleep_pins_a
+ &qspi_cs1_sleep_pins_a>;
reg = <0x58003000 0x1000>, <0x70000000 0x4000000>;
#address-cells = <1>;
#size-cells = <0>;
&qspi {
pinctrl-names = "default", "sleep";
- pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>;
- pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>;
+ pinctrl-0 = <&qspi_clk_pins_a
+ &qspi_bk1_pins_a
+ &qspi_cs1_pins_a>;
+ pinctrl-1 = <&qspi_clk_sleep_pins_a
+ &qspi_bk1_sleep_pins_a
+ &qspi_cs1_sleep_pins_a>;
reg = <0x58003000 0x1000>, <0x70000000 0x200000>;
#address-cells = <1>;
#size-cells = <0>;
};
&i2c2 {
- tca9548@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9548";
pinctrl-0 = <&pinctrl_i2c_mux_reset>;
pinctrl-names = "default";
};
&i2c2 {
- tca9548@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9548";
pinctrl-0 = <&pinctrl_i2c_mux_reset>;
pinctrl-names = "default";
clean-files += poly1305-core.S sha256-core.S sha512-core.S
+aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1
+
+AFLAGS_sha256-core.o += $(aflags-thumb2-y)
+AFLAGS_sha512-core.o += $(aflags-thumb2-y)
+
# massage the perlasm code a bit so we only get the NEON routine if we need it
poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
-AFLAGS_poly1305-core.o += $(poly1305-aflags-y)
+AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y)
#define TIF_NEED_RESCHED 1 /* rescheduling necessary */
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_UPROBE 3 /* breakpointed or singlestepping */
-#define TIF_SYSCALL_TRACE 4 /* syscall trace active */
-#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
-#define TIF_SECCOMP 7 /* seccomp syscall filtering active */
-#define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */
+#define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */
#define TIF_USING_IWMMXT 17
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK 20
+#define TIF_RESTORE_SIGMASK 19
+#define TIF_SYSCALL_TRACE 20 /* syscall trace active */
+#define TIF_SYSCALL_AUDIT 21 /* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT 22 /* syscall tracepoint instrumentation */
+#define TIF_SECCOMP 23 /* seccomp syscall filtering active */
+
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#include <linux/init.h>
#include <linux/mc146818rtc.h>
-#include <linux/bcd.h>
#include <linux/io.h>
#include "common.h"
np = of_find_compatible_node(NULL, NULL, "fsl,imx25-iim");
iim_base = of_iomap(np, 0);
+ of_node_put(np);
BUG_ON(!iim_base);
rev = readl(iim_base + MXC_IIMSREV);
iounmap(iim_base);
np = of_find_compatible_node(NULL, NULL, "fsl,imx27-ccm");
ccm_base = of_iomap(np, 0);
+ of_node_put(np);
BUG_ON(!ccm_base);
/*
* now we have access to the IO registers. As we need
np = of_find_compatible_node(NULL, NULL, "fsl,imx31-iim");
iim_base = of_iomap(np, 0);
+ of_node_put(np);
BUG_ON(!iim_base);
/* read SREV register from IIM module */
np = of_find_compatible_node(NULL, NULL, "fsl,imx35-iim");
iim_base = of_iomap(np, 0);
+ of_node_put(np);
BUG_ON(!iim_base);
rev = imx_readl(iim_base + MXC_IIMSREV);
np = of_find_compatible_node(NULL, NULL, compat);
iim_base = of_iomap(np, 0);
+ of_node_put(np);
WARN_ON(!iim_base);
srev = readl(iim_base + IIM_SREV) & 0xff;
depends on ARCH_MULTI_V4T || ARCH_MULTI_V5
depends on CPU_LITTLE_ENDIAN
depends on ATAGS
+ select ARCH_OMAP
select ARCH_HAS_HOLES_MEMORYMODEL
select ARCH_OMAP
select CLKSRC_MMIO
select CPU_ARM926T
select OMAP_DM_TIMER
-config ARCH_OMAP1_ANY
- select ARCH_OMAP
- def_bool ARCH_OMAP730 || ARCH_OMAP850 || ARCH_OMAP15XX || ARCH_OMAP16XX
-
config ARCH_OMAP
bool
# Makefile for the linux kernel.
#
-ifdef CONFIG_ARCH_OMAP1_ANY
-
# Common support
obj-y := io.o id.o sram-init.o sram.o time.o irq.o mux.o flash.o \
serial.o devices.o dma.o omap-dma.o fb.o
obj-$(CONFIG_ARCH_OMAP850) += gpio7xx.o
obj-$(CONFIG_ARCH_OMAP15XX) += gpio15xx.o
obj-$(CONFIG_ARCH_OMAP16XX) += gpio16xx.o
-
-endif
#include <linux/gpio.h>
#include <linux/platform_data/gpio-omap.h>
#include <linux/soc/ti/omap1-soc.h>
+#include <asm/irq.h>
#include "irqs.h"
* The machine specific code may provide the extra mapping besides the
* default mapping provided here.
*/
-static struct map_desc omap_io_desc[] __initdata = {
+#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850)
+static struct map_desc omap7xx_io_desc[] __initdata = {
{
.virtual = OMAP1_IO_VIRT,
.pfn = __phys_to_pfn(OMAP1_IO_PHYS),
.length = OMAP1_IO_SIZE,
.type = MT_DEVICE
- }
-};
-
-#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850)
-static struct map_desc omap7xx_io_desc[] __initdata = {
+ },
{
.virtual = OMAP7XX_DSP_BASE,
.pfn = __phys_to_pfn(OMAP7XX_DSP_START),
#ifdef CONFIG_ARCH_OMAP15XX
static struct map_desc omap1510_io_desc[] __initdata = {
+ {
+ .virtual = OMAP1_IO_VIRT,
+ .pfn = __phys_to_pfn(OMAP1_IO_PHYS),
+ .length = OMAP1_IO_SIZE,
+ .type = MT_DEVICE
+ },
{
.virtual = OMAP1510_DSP_BASE,
.pfn = __phys_to_pfn(OMAP1510_DSP_START),
#if defined(CONFIG_ARCH_OMAP16XX)
static struct map_desc omap16xx_io_desc[] __initdata = {
+ {
+ .virtual = OMAP1_IO_VIRT,
+ .pfn = __phys_to_pfn(OMAP1_IO_PHYS),
+ .length = OMAP1_IO_SIZE,
+ .type = MT_DEVICE
+ },
{
.virtual = OMAP16XX_DSP_BASE,
.pfn = __phys_to_pfn(OMAP16XX_DSP_START),
};
#endif
-/*
- * Maps common IO regions for omap1
- */
-static void __init omap1_map_common_io(void)
-{
- iotable_init(omap_io_desc, ARRAY_SIZE(omap_io_desc));
-}
-
#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850)
void __init omap7xx_map_io(void)
{
- omap1_map_common_io();
iotable_init(omap7xx_io_desc, ARRAY_SIZE(omap7xx_io_desc));
}
#endif
#ifdef CONFIG_ARCH_OMAP15XX
void __init omap15xx_map_io(void)
{
- omap1_map_common_io();
iotable_init(omap1510_io_desc, ARRAY_SIZE(omap1510_io_desc));
}
#endif
#if defined(CONFIG_ARCH_OMAP16XX)
void __init omap16xx_map_io(void)
{
- omap1_map_common_io();
iotable_init(omap16xx_io_desc, ARRAY_SIZE(omap16xx_io_desc));
}
#endif
#define OMAP1610_MCBSP2_BASE 0xfffb1000
#define OMAP1610_MCBSP3_BASE 0xe1017000
-#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850)
struct resource omap7xx_mcbsp_res[][6] = {
{
{
};
#define OMAP7XX_MCBSP_RES_SZ ARRAY_SIZE(omap7xx_mcbsp_res[1])
#define OMAP7XX_MCBSP_COUNT ARRAY_SIZE(omap7xx_mcbsp_res)
-#else
-#define omap7xx_mcbsp_res_0 NULL
-#define omap7xx_mcbsp_pdata NULL
-#define OMAP7XX_MCBSP_RES_SZ 0
-#define OMAP7XX_MCBSP_COUNT 0
-#endif
-#ifdef CONFIG_ARCH_OMAP15XX
struct resource omap15xx_mcbsp_res[][6] = {
{
{
};
#define OMAP15XX_MCBSP_RES_SZ ARRAY_SIZE(omap15xx_mcbsp_res[1])
#define OMAP15XX_MCBSP_COUNT ARRAY_SIZE(omap15xx_mcbsp_res)
-#else
-#define omap15xx_mcbsp_res_0 NULL
-#define omap15xx_mcbsp_pdata NULL
-#define OMAP15XX_MCBSP_RES_SZ 0
-#define OMAP15XX_MCBSP_COUNT 0
-#endif
-#ifdef CONFIG_ARCH_OMAP16XX
struct resource omap16xx_mcbsp_res[][6] = {
{
{
};
#define OMAP16XX_MCBSP_RES_SZ ARRAY_SIZE(omap16xx_mcbsp_res[1])
#define OMAP16XX_MCBSP_COUNT ARRAY_SIZE(omap16xx_mcbsp_res)
-#else
-#define omap16xx_mcbsp_res_0 NULL
-#define omap16xx_mcbsp_pdata NULL
-#define OMAP16XX_MCBSP_RES_SZ 0
-#define OMAP16XX_MCBSP_COUNT 0
-#endif
static void omap_mcbsp_register_board_cfg(struct resource *res, int res_count,
struct omap_mcbsp_platform_data *config, int size)
#define OMAP7XX_IDLECT3 0xfffece24
#define OMAP7XX_IDLE_LOOP_REQUEST 0x0C00
-#if !defined(CONFIG_ARCH_OMAP730) && \
- !defined(CONFIG_ARCH_OMAP850) && \
- !defined(CONFIG_ARCH_OMAP15XX) && \
- !defined(CONFIG_ARCH_OMAP16XX)
-#warning "Power management for this processor not implemented yet"
-#endif
-
#ifndef __ASSEMBLER__
#include <linux/clk.h>
config MACH_PXA3XX_DT
bool "Support PXA3xx platforms from device tree"
select CPU_PXA300
+ select CPU_PXA310
+ select CPU_PXA320
select PINCTRL
select POWER_SUPPLY
select PXA3xx
mpu_setup();
/* allocate the zero page. */
- zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE);
if (!zero_page)
panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
__func__, PAGE_SIZE, PAGE_SIZE);
* VM_EXEC
*/
#include <asm/asm-offsets.h>
+#include <asm/pgtable.h>
#include <asm/thread_info.h>
#ifdef CONFIG_CPU_V7M
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
- select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
- if $(cc-option,-fpatchable-function-entry=2)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
if DYNAMIC_FTRACE_WITH_ARGS
select HAVE_EFFICIENT_UNALIGNED_ACCESS
If unsure, say Y.
+config ARM64_ERRATUM_2645198
+ bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption"
+ default y
+ help
+ This option adds the workaround for ARM Cortex-A715 erratum 2645198.
+
+ If a Cortex-A715 cpu sees a page mapping permissions change from executable
+ to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the
+ next instruction abort caused by permission fault.
+
+ Only user-space does executable to non-executable permission transition via
+ mprotect() system call. Workaround the problem by doing a break-before-make
+ TLB invalidation, for all changes to executable user space mappings.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
sd_emmc_b: sd@5000 {
compatible = "amlogic,meson-axg-mmc";
reg = <0x0 0x5000 0x0 0x800>;
- interrupts = <GIC_SPI 217 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 217 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_B>,
<&clkc CLKID_SD_EMMC_B_CLK0>,
sd_emmc_c: mmc@7000 {
compatible = "amlogic,meson-axg-mmc";
reg = <0x0 0x7000 0x0 0x800>;
- interrupts = <GIC_SPI 218 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 218 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_C>,
<&clkc CLKID_SD_EMMC_C_CLK0>,
sd_emmc_a: sd@ffe03000 {
compatible = "amlogic,meson-axg-mmc";
reg = <0x0 0xffe03000 0x0 0x800>;
- interrupts = <GIC_SPI 189 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_A>,
<&clkc CLKID_SD_EMMC_A_CLK0>,
sd_emmc_b: sd@ffe05000 {
compatible = "amlogic,meson-axg-mmc";
reg = <0x0 0xffe05000 0x0 0x800>;
- interrupts = <GIC_SPI 190 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 190 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_B>,
<&clkc CLKID_SD_EMMC_B_CLK0>,
sd_emmc_c: mmc@ffe07000 {
compatible = "amlogic,meson-axg-mmc";
reg = <0x0 0xffe07000 0x0 0x800>;
- interrupts = <GIC_SPI 191 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
clocks = <&clkc CLKID_SD_EMMC_C>,
<&clkc CLKID_SD_EMMC_C_CLK0>,
sd_emmc_a: mmc@70000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
reg = <0x0 0x70000 0x0 0x800>;
- interrupts = <GIC_SPI 216 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 216 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
};
sd_emmc_b: mmc@72000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
reg = <0x0 0x72000 0x0 0x800>;
- interrupts = <GIC_SPI 217 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 217 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
};
sd_emmc_c: mmc@74000 {
compatible = "amlogic,meson-gx-mmc", "amlogic,meson-gxbb-mmc";
reg = <0x0 0x74000 0x0 0x800>;
- interrupts = <GIC_SPI 218 IRQ_TYPE_EDGE_RISING>;
+ interrupts = <GIC_SPI 218 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
};
};
};
&usb {
- phys = <&usb2_phy1>;
- phy-names = "usb2-phy1";
-};
-
-&usb2_phy0 {
- status = "disabled";
+ phys = <&usb2_phy0>, <&usb2_phy1>;
+ phy-names = "usb2-phy0", "usb2-phy1";
};
&i2c0 {
status = "okay";
- pca9547@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
&i2c0 {
status = "okay";
- pca9547@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
&i2c0 {
status = "okay";
- pca9547@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
&i2c0 {
status = "okay";
- i2c-switch@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
&i2c0 {
status = "okay";
- i2c-switch@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
&i2c3 {
status = "okay";
- i2c-switch@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9540";
#address-cells = <1>;
#size-cells = <0>;
&i2c0 {
status = "okay";
- pca9547@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
&i2c0 {
status = "okay";
- pca9547@75 {
+ i2c-mux@75 {
compatible = "nxp,pca9547";
reg = <0x75>;
#address-cells = <1>;
&i2c0 {
status = "okay";
- i2c-switch@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
#address-cells = <1>;
#size-cells = <0>;
sc_pwrkey: keys {
compatible = "fsl,imx8qxp-sc-key", "fsl,imx-sc-key";
- linux,keycode = <KEY_POWER>;
+ linux,keycodes = <KEY_POWER>;
wakeup-source;
};
&ecspi2 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_espi2>;
- cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
+ cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
status = "okay";
eeprom@0 {
MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0x82
MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0x82
MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0x82
- MX8MM_IOMUXC_ECSPI1_SS0_GPIO5_IO9 0x41
+ MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0x41
>;
};
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_watchdog_gpio>;
compatible = "linux,wdt-gpio";
+ always-running;
gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>;
hw_algo = "level";
/* Reset triggers in 2..3 seconds */
compatible = "rohm,bd71847";
reg = <0x4b>;
#clock-cells = <0>;
- clocks = <&clk_xtal32k 0>;
+ clocks = <&clk_xtal32k>;
clock-output-names = "clk-32k-out";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
pinctrl-0 = <&pinctrl_i2c3>;
status = "okay";
- i2cmux@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9540";
reg = <0x70>;
#address-cells = <1>;
#define MX8MM_IOMUXC_UART1_RXD_GPIO5_IO22 0x234 0x49C 0x000 0x5 0x0
#define MX8MM_IOMUXC_UART1_RXD_TPSMP_HDATA24 0x234 0x49C 0x000 0x7 0x0
#define MX8MM_IOMUXC_UART1_TXD_UART1_DCE_TX 0x238 0x4A0 0x000 0x0 0x0
-#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x0
+#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x1
#define MX8MM_IOMUXC_UART1_TXD_ECSPI3_MOSI 0x238 0x4A0 0x000 0x1 0x0
#define MX8MM_IOMUXC_UART1_TXD_GPIO5_IO23 0x238 0x4A0 0x000 0x5 0x0
#define MX8MM_IOMUXC_UART1_TXD_TPSMP_HDATA25 0x238 0x4A0 0x000 0x7 0x0
pinctrl-0 = <&pinctrl_uart2>;
rts-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>;
cts-gpios = <&gpio5 28 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
};
pinctrl-0 = <&pinctrl_uart2>;
rts-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>;
cts-gpios = <&gpio5 28 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
};
pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_bten>;
cts-gpios = <&gpio5 8 GPIO_ACTIVE_LOW>;
rts-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
bluetooth {
dtr-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;
dsr-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
dcd-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
};
pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>;
cts-gpios = <&gpio4 10 GPIO_ACTIVE_LOW>;
rts-gpios = <&gpio4 9 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
};
pinctrl-0 = <&pinctrl_uart4>, <&pinctrl_uart4_gpio>;
cts-gpios = <&gpio5 11 GPIO_ACTIVE_LOW>;
rts-gpios = <&gpio5 12 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
};
&usbotg2 {
dr_mode = "host";
vbus-supply = <®_usb2_vbus>;
+ over-current-active-low;
status = "okay";
};
pinctrl-0 = <&pinctrl_uart1>, <&pinctrl_uart1_gpio>;
rts-gpios = <&gpio4 10 GPIO_ACTIVE_LOW>;
cts-gpios = <&gpio4 24 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
};
pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>;
rts-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
cts-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
bluetooth {
dtr-gpios = <&gpio4 3 GPIO_ACTIVE_LOW>;
dsr-gpios = <&gpio4 4 GPIO_ACTIVE_LOW>;
dcd-gpios = <&gpio4 6 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
};
dtr-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
dsr-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
dcd-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
};
simple-audio-card,bitclock-master = <&dailink_master>;
simple-audio-card,format = "i2s";
simple-audio-card,frame-master = <&dailink_master>;
+ simple-audio-card,mclk-fs = <256>;
simple-audio-card,name = "imx8mm-wm8904";
simple-audio-card,routing =
"Headphone Jack", "HPOUTL",
simple-audio-card,bitclock-master = <&dailink_master>;
simple-audio-card,format = "i2s";
simple-audio-card,frame-master = <&dailink_master>;
+ simple-audio-card,mclk-fs = <256>;
simple-audio-card,name = "imx8mm-nau8822";
simple-audio-card,routing =
"Headphones", "LHP",
off-on-delay = <500000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_reg_eth>;
+ regulator-always-on;
regulator-boot-on;
regulator-max-microvolt = <3300000>;
regulator-min-microvolt = <3300000>;
pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>;
rts-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
cts-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
bluetooth {
pcie0_refclk: pcie0-refclk {
compatible = "fixed-clock";
- #clock-cells = <0>;
- clock-frequency = <100000000>;
+ #clock-cells = <0>;
+ clock-frequency = <100000000>;
};
reg_can1_stby: regulator-can1-stby {
regulators {
buck1: BUCK1 {
- regulator-compatible = "BUCK1";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <2187500>;
regulator-boot-on;
};
buck2: BUCK2 {
- regulator-compatible = "BUCK2";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <2187500>;
regulator-boot-on;
};
buck4: BUCK4 {
- regulator-compatible = "BUCK4";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <3400000>;
regulator-boot-on;
};
buck5: BUCK5 {
- regulator-compatible = "BUCK5";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <3400000>;
regulator-boot-on;
};
buck6: BUCK6 {
- regulator-compatible = "BUCK6";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <3400000>;
regulator-boot-on;
};
ldo1: LDO1 {
- regulator-compatible = "LDO1";
regulator-min-microvolt = <1600000>;
regulator-max-microvolt = <3300000>;
regulator-boot-on;
};
ldo2: LDO2 {
- regulator-compatible = "LDO2";
regulator-min-microvolt = <800000>;
regulator-max-microvolt = <1150000>;
regulator-boot-on;
};
ldo3: LDO3 {
- regulator-compatible = "LDO3";
regulator-min-microvolt = <800000>;
regulator-max-microvolt = <3300000>;
regulator-boot-on;
};
ldo4: LDO4 {
- regulator-compatible = "LDO4";
regulator-min-microvolt = <800000>;
regulator-max-microvolt = <3300000>;
};
ldo5: LDO5 {
- regulator-compatible = "LDO5";
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <3300000>;
regulator-boot-on;
pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>;
cts-gpios = <&gpio3 21 GPIO_ACTIVE_LOW>;
rts-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>;
- uart-has-rtscts;
status = "okay";
bluetooth {
compatible = "fsl,imx8mp-gpc";
reg = <0x303a0000 0x1000>;
interrupt-parent = <&gic>;
+ interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
interrupt-controller;
#interrupt-cells = <3>;
reg = <IMX8MP_POWER_DOMAIN_MIPI_PHY2>;
};
- pgc_hsiomix: power-domains@17 {
+ pgc_hsiomix: power-domain@17 {
#power-domain-cells = <0>;
reg = <IMX8MP_POWER_DOMAIN_HSIOMIX>;
clocks = <&clk IMX8MP_CLK_HSIO_AXI>,
reg = <0x32f10100 0x8>,
<0x381f0000 0x20>;
clocks = <&clk IMX8MP_CLK_HSIO_ROOT>,
- <&clk IMX8MP_CLK_USB_ROOT>;
+ <&clk IMX8MP_CLK_USB_SUSP>;
clock-names = "hsio", "suspend";
interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
power-domains = <&hsio_blk_ctrl IMX8MP_HSIOBLK_PD_USB>;
usb_dwc3_0: usb@38100000 {
compatible = "snps,dwc3";
reg = <0x38100000 0x10000>;
- clocks = <&clk IMX8MP_CLK_HSIO_AXI>,
+ clocks = <&clk IMX8MP_CLK_USB_ROOT>,
<&clk IMX8MP_CLK_USB_CORE_REF>,
- <&clk IMX8MP_CLK_USB_ROOT>;
+ <&clk IMX8MP_CLK_USB_SUSP>;
clock-names = "bus_early", "ref", "suspend";
interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
phys = <&usb3_phy0>, <&usb3_phy0>;
reg = <0x32f10108 0x8>,
<0x382f0000 0x20>;
clocks = <&clk IMX8MP_CLK_HSIO_ROOT>,
- <&clk IMX8MP_CLK_USB_ROOT>;
+ <&clk IMX8MP_CLK_USB_SUSP>;
clock-names = "hsio", "suspend";
interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
power-domains = <&hsio_blk_ctrl IMX8MP_HSIOBLK_PD_USB>;
usb_dwc3_1: usb@38200000 {
compatible = "snps,dwc3";
reg = <0x38200000 0x10000>;
- clocks = <&clk IMX8MP_CLK_HSIO_AXI>,
+ clocks = <&clk IMX8MP_CLK_USB_ROOT>,
<&clk IMX8MP_CLK_USB_CORE_REF>,
- <&clk IMX8MP_CLK_USB_ROOT>;
+ <&clk IMX8MP_CLK_USB_SUSP>;
clock-names = "bus_early", "ref", "suspend";
interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
phys = <&usb3_phy1>, <&usb3_phy1>;
pinctrl-0 = <&pinctrl_i2c1>;
status = "okay";
- i2cmux@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9546";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c1_pca9546>;
pinctrl-0 = <&pinctrl_i2c4>;
status = "okay";
- pca9546: i2cmux@70 {
+ pca9546: i2c-mux@70 {
compatible = "nxp,pca9546";
reg = <0x70>;
#address-cells = <1>;
bus-width = <4>;
non-removable;
no-sd;
- no-emmc;
+ no-mmc;
status = "okay";
brcmf: wifi@1 {
cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>;
bus-width = <4>;
no-sdio;
- no-emmc;
+ no-mmc;
disable-wp;
status = "okay";
};
pinctrl-0 = <&pinctrl_lpi2c1 &pinctrl_ioexp_rst>;
status = "okay";
- i2c-switch@71 {
+ i2c-mux@71 {
compatible = "nxp,pca9646", "nxp,pca9546";
#address-cells = <1>;
#size-cells = <0>;
pinctrl_usdhc1: usdhc1grp {
fsl,pins = <
- MX93_PAD_SD1_CLK__USDHC1_CLK 0x17fe
+ MX93_PAD_SD1_CLK__USDHC1_CLK 0x15fe
MX93_PAD_SD1_CMD__USDHC1_CMD 0x13fe
MX93_PAD_SD1_DATA0__USDHC1_DATA0 0x13fe
MX93_PAD_SD1_DATA1__USDHC1_DATA1 0x13fe
MX93_PAD_SD1_DATA5__USDHC1_DATA5 0x13fe
MX93_PAD_SD1_DATA6__USDHC1_DATA6 0x13fe
MX93_PAD_SD1_DATA7__USDHC1_DATA7 0x13fe
- MX93_PAD_SD1_STROBE__USDHC1_STROBE 0x17fe
+ MX93_PAD_SD1_STROBE__USDHC1_STROBE 0x15fe
>;
};
pinctrl_usdhc2: usdhc2grp {
fsl,pins = <
- MX93_PAD_SD2_CLK__USDHC2_CLK 0x17fe
+ MX93_PAD_SD2_CLK__USDHC2_CLK 0x15fe
MX93_PAD_SD2_CMD__USDHC2_CMD 0x13fe
MX93_PAD_SD2_DATA0__USDHC2_DATA0 0x13fe
MX93_PAD_SD2_DATA1__USDHC2_DATA1 0x13fe
uart1: serial@12100 {
compatible = "snps,dw-apb-uart";
- reg = <0x11000 0x100>;
+ reg = <0x12100 0x100>;
reg-shift = <2>;
interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
reg-io-width = <1>;
};
vdosys0: syscon@1c01a000 {
- compatible = "mediatek,mt8195-mmsys", "syscon";
+ compatible = "mediatek,mt8195-vdosys0", "mediatek,mt8195-mmsys", "syscon";
reg = <0 0x1c01a000 0 0x1000>;
mboxes = <&gce0 0 CMDQ_THR_PRIO_4>;
#clock-cells = <1>;
};
vdosys1: syscon@1c100000 {
- compatible = "mediatek,mt8195-mmsys", "syscon";
+ compatible = "mediatek,mt8195-vdosys1", "syscon";
reg = <0 0x1c100000 0 0x1000>;
#clock-cells = <1>;
};
* Copyright (c) 2015, LGE Inc. All rights reserved.
* Copyright (c) 2016, The Linux Foundation. All rights reserved.
* Copyright (c) 2021, Petr Vorel <petr.vorel@gmail.com>
+ * Copyright (c) 2022, Dominik Kobinski <dominikkobinski314@gmail.com>
*/
/dts-v1/;
reg = <0 0x03400000 0 0x1200000>;
no-map;
};
+
+ removed_region: reserved@5000000 {
+ reg = <0 0x05000000 0 0x2200000>;
+ no-map;
+ };
};
};
#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/input/gpio-keys.h>
+/delete-node/ &adsp_mem;
+/delete-node/ &audio_mem;
+/delete-node/ &mpss_mem;
+/delete-node/ &peripheral_region;
+/delete-node/ &rmtfs_mem;
+
/ {
model = "Xiaomi Mi 4C";
compatible = "xiaomi,libra", "qcom,msm8992";
#size-cells = <2>;
ranges;
- /* This is for getting crash logs using Android downstream kernels */
- ramoops@dfc00000 {
- compatible = "ramoops";
- reg = <0x0 0xdfc00000 0x0 0x40000>;
- console-size = <0x10000>;
- record-size = <0x10000>;
- ftrace-size = <0x10000>;
- pmsg-size = <0x20000>;
+ memory_hole: hole@6400000 {
+ reg = <0 0x06400000 0 0x600000>;
+ no-map;
+ };
+
+ memory_hole2: hole2@6c00000 {
+ reg = <0 0x06c00000 0 0x2400000>;
+ no-map;
+ };
+
+ mpss_mem: mpss@9000000 {
+ reg = <0 0x09000000 0 0x5a00000>;
+ no-map;
+ };
+
+ tzapp: tzapp@ea00000 {
+ reg = <0 0x0ea00000 0 0x1900000>;
+ no-map;
+ };
+
+ mdm_rfsa_mem: mdm-rfsa@ca0b0000 {
+ reg = <0 0xca0b0000 0 0x10000>;
+ no-map;
+ };
+
+ rmtfs_mem: rmtfs@ca100000 {
+ compatible = "qcom,rmtfs-mem";
+ reg = <0 0xca100000 0 0x180000>;
+ no-map;
+
+ qcom,client-id = <1>;
};
- modem_region: modem_region@9000000 {
- reg = <0x0 0x9000000 0x0 0x5a00000>;
+ audio_mem: audio@cb400000 {
+ reg = <0 0xcb000000 0 0x400000>;
+ no-mem;
+ };
+
+ qseecom_mem: qseecom@cb400000 {
+ reg = <0 0xcb400000 0 0x1c00000>;
+ no-mem;
+ };
+
+ adsp_rfsa_mem: adsp-rfsa@cd000000 {
+ reg = <0 0xcd000000 0 0x10000>;
no-map;
};
- tzapp: modem_region@ea00000 {
- reg = <0x0 0xea00000 0x0 0x1900000>;
+ sensor_rfsa_mem: sensor-rfsa@cd010000 {
+ reg = <0 0xcd010000 0 0x10000>;
no-map;
};
+
+ ramoops@dfc00000 {
+ compatible = "ramoops";
+ reg = <0 0xdfc00000 0 0x40000>;
+ console-size = <0x10000>;
+ record-size = <0x10000>;
+ ftrace-size = <0x10000>;
+ pmsg-size = <0x20000>;
+ };
};
};
status = "okay";
};
-&peripheral_region {
- reg = <0x0 0x7400000 0x0 0x1c00000>;
- no-map;
-};
-
&pm8994_spmi_regulators {
VDD_APC0: s8 {
regulator-min-microvolt = <680000>;
compatible = "qcom,rpmcc-msm8992", "qcom,rpmcc";
};
-&tcsr_mutex {
- compatible = "qcom,sfpb-mutex";
-};
-
&timer {
interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
#include "msm8994.dtsi"
-/* Angler's firmware does not report where the memory is allocated */
-/delete-node/ &cont_splash_mem;
-
/ {
model = "Huawei Nexus 6P";
compatible = "huawei,angler", "qcom,msm8994";
chosen {
stdout-path = "serial0:115200n8";
};
+
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ tzapp_mem: tzapp@4800000 {
+ reg = <0 0x04800000 0 0x1900000>;
+ no-map;
+ };
+
+ removed_region: reserved@6300000 {
+ reg = <0 0x06300000 0 0xD00000>;
+ no-map;
+ };
+ };
};
&blsp1_uart2 {
#include <dt-bindings/interconnect/qcom,sc8280xp.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/mailbox/qcom-ipcc.h>
+#include <dt-bindings/phy/phy-qcom-qmp.h>
#include <dt-bindings/power/qcom-rpmpd.h>
#include <dt-bindings/soc/qcom,rpmh-rsc.h>
#include <dt-bindings/thermal/thermal.h>
<0>,
<0>,
<0>,
- <&usb_0_ssphy>,
+ <&usb_0_qmpphy QMP_USB43DP_USB3_PIPE_CLK>,
<0>,
<0>,
<0>,
<0>,
<0>,
<0>,
- <&usb_1_ssphy>,
+ <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>,
<0>,
<0>,
<0>,
};
};
- usb_0_qmpphy: phy-wrapper@88ec000 {
+ usb_0_qmpphy: phy@88eb000 {
compatible = "qcom,sc8280xp-qmp-usb43dp-phy";
- reg = <0 0x088ec000 0 0x1e4>,
- <0 0x088eb000 0 0x40>,
- <0 0x088ed000 0 0x1c8>;
- #address-cells = <2>;
- #size-cells = <2>;
- ranges;
+ reg = <0 0x088eb000 0 0x4000>;
clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>,
- <&rpmhcc RPMH_CXO_CLK>,
<&gcc GCC_USB4_EUD_CLKREF_CLK>,
- <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>;
- clock-names = "aux", "ref_clk_src", "ref", "com_aux";
+ <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>,
+ <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>;
+ clock-names = "aux", "ref", "com_aux", "usb3_pipe";
+
+ power-domains = <&gcc USB30_PRIM_GDSC>;
resets = <&gcc GCC_USB3_PHY_PRIM_BCR>,
- <&gcc GCC_USB3_DP_PHY_PRIM_BCR>;
+ <&gcc GCC_USB4_DP_PHY_PRIM_BCR>;
reset-names = "phy", "common";
- power-domains = <&gcc USB30_PRIM_GDSC>;
+ #clock-cells = <1>;
+ #phy-cells = <1>;
status = "disabled";
-
- usb_0_ssphy: usb3-phy@88eb400 {
- reg = <0 0x088eb400 0 0x100>,
- <0 0x088eb600 0 0x3ec>,
- <0 0x088ec400 0 0x364>,
- <0 0x088eba00 0 0x100>,
- <0 0x088ebc00 0 0x3ec>,
- <0 0x088ec200 0 0x18>;
- #phy-cells = <0>;
- #clock-cells = <0>;
- clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>;
- clock-names = "pipe0";
- clock-output-names = "usb0_phy_pipe_clk_src";
- };
};
usb_1_hsphy: phy@8902000 {
status = "disabled";
};
- usb_1_qmpphy: phy-wrapper@8904000 {
+ usb_1_qmpphy: phy@8903000 {
compatible = "qcom,sc8280xp-qmp-usb43dp-phy";
- reg = <0 0x08904000 0 0x1e4>,
- <0 0x08903000 0 0x40>,
- <0 0x08905000 0 0x1c8>;
- #address-cells = <2>;
- #size-cells = <2>;
- ranges;
+ reg = <0 0x08903000 0 0x4000>;
clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>,
- <&rpmhcc RPMH_CXO_CLK>,
<&gcc GCC_USB4_CLKREF_CLK>,
- <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>;
- clock-names = "aux", "ref_clk_src", "ref", "com_aux";
+ <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>,
+ <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
+ clock-names = "aux", "ref", "com_aux", "usb3_pipe";
+
+ power-domains = <&gcc USB30_SEC_GDSC>;
resets = <&gcc GCC_USB3_PHY_SEC_BCR>,
<&gcc GCC_USB4_1_DP_PHY_PRIM_BCR>;
reset-names = "phy", "common";
- power-domains = <&gcc USB30_SEC_GDSC>;
+ #clock-cells = <1>;
+ #phy-cells = <1>;
status = "disabled";
-
- usb_1_ssphy: usb3-phy@8903400 {
- reg = <0 0x08903400 0 0x100>,
- <0 0x08903600 0 0x3ec>,
- <0 0x08904400 0 0x364>,
- <0 0x08903a00 0 0x100>,
- <0 0x08903c00 0 0x3ec>,
- <0 0x08904200 0 0x18>;
- #phy-cells = <0>;
- #clock-cells = <0>;
- clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
- clock-names = "pipe0";
- clock-output-names = "usb1_phy_pipe_clk_src";
- };
};
pmu@9091000 {
reg = <0 0x0a600000 0 0xcd00>;
interrupts = <GIC_SPI 803 IRQ_TYPE_LEVEL_HIGH>;
iommus = <&apps_smmu 0x820 0x0>;
- phys = <&usb_0_hsphy>, <&usb_0_ssphy>;
+ phys = <&usb_0_hsphy>, <&usb_0_qmpphy QMP_USB43DP_USB3_PHY>;
phy-names = "usb2-phy", "usb3-phy";
};
};
reg = <0 0x0a800000 0 0xcd00>;
interrupts = <GIC_SPI 810 IRQ_TYPE_LEVEL_HIGH>;
iommus = <&apps_smmu 0x860 0x0>;
- phys = <&usb_1_hsphy>, <&usb_1_ssphy>;
+ phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>;
phy-names = "usb2-phy", "usb3-phy";
};
};
exit-latency-us = <6562>;
min-residency-us = <9987>;
local-timer-stop;
- status = "disabled";
};
};
};
<&rpmhcc RPMH_CXO_CLK>;
clock-names = "iface", "core", "xo";
resets = <&gcc GCC_SDCC2_BCR>;
- interconnects = <&aggre2_noc MASTER_SDCC_2 0 &mc_virt SLAVE_EBI1 0>,
- <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_SDCC_2 0>;
+ interconnects = <&aggre2_noc MASTER_SDCC_2 &mc_virt SLAVE_EBI1>,
+ <&gem_noc MASTER_APPSS_PROC &config_noc SLAVE_SDCC_2>;
interconnect-names = "sdhc-ddr","cpu-sdhc";
iommus = <&apps_smmu 0x4a0 0x0>;
power-domains = <&rpmhpd SM8350_CX>;
linux,default-trigger = "heartbeat";
gpios = <&rk805 1 GPIO_ACTIVE_LOW>;
default-state = "on";
- mode = <0x23>;
};
user_led: led-1 {
linux,default-trigger = "mmc1";
gpios = <&rk805 0 GPIO_ACTIVE_LOW>;
default-state = "off";
- mode = <0x05>;
};
};
};
};
};
- dmc_opp_table: dmc_opp_table {
+ dmc_opp_table: opp-table-3 {
compatible = "operating-points-v2";
opp00 {
};
};
+&cpu_alert0 {
+ temperature = <65000>;
+};
+&cpu_alert1 {
+ temperature = <68000>;
+};
+
&cpu_l0 {
cpu-supply = <&vdd_cpu_l>;
};
clocks = <&cru HCLK_M_CRYPTO0>, <&cru HCLK_S_CRYPTO0>, <&cru SCLK_CRYPTO0>;
clock-names = "hclk_master", "hclk_slave", "sclk";
resets = <&cru SRST_CRYPTO0>, <&cru SRST_CRYPTO0_S>, <&cru SRST_CRYPTO0_M>;
- reset-names = "master", "lave", "crypto";
+ reset-names = "master", "slave", "crypto-rst";
};
crypto1: crypto@ff8b8000 {
clocks = <&cru HCLK_M_CRYPTO1>, <&cru HCLK_S_CRYPTO1>, <&cru SCLK_CRYPTO1>;
clock-names = "hclk_master", "hclk_slave", "sclk";
resets = <&cru SRST_CRYPTO1>, <&cru SRST_CRYPTO1_S>, <&cru SRST_CRYPTO1_M>;
- reset-names = "master", "slave", "crypto";
+ reset-names = "master", "slave", "crypto-rst";
};
i2c1: i2c@ff110000 {
pcfg_input_pull_up: pcfg-input-pull-up {
input-enable;
bias-pull-up;
- drive-strength = <2>;
};
pcfg_input_pull_down: pcfg-input-pull-down {
input-enable;
bias-pull-down;
- drive-strength = <2>;
};
clock {
};
};
+&pmu_io_domains {
+ pmuio2-supply = <&vcc_3v3>;
+ vccio1-supply = <&vcc_3v3>;
+ vccio3-supply = <&vcc_3v3>;
+ vccio4-supply = <&vcca_1v8>;
+ vccio5-supply = <&vcc_3v3>;
+ vccio6-supply = <&vcca_1v8>;
+ vccio7-supply = <&vcc_3v3>;
+ status = "okay";
+};
+
&pwm0 {
status = "okay";
};
};
&i2s1_8ch {
+ pinctrl-names = "default";
+ pinctrl-0 = <&i2s1m0_sclktx &i2s1m0_lrcktx &i2s1m0_sdi0 &i2s1m0_sdo0>;
rockchip,trcm-sync-tx-only;
status = "okay";
};
disable-wp;
pinctrl-names = "default";
pinctrl-0 = <&sdmmc0_bus4 &sdmmc0_clk &sdmmc0_cmd &sdmmc0_det>;
- sd-uhs-sdr104;
+ sd-uhs-sdr50;
vmmc-supply = <&vcc3v3_sd>;
vqmmc-supply = <&vccio_sd>;
status = "okay";
};
&sdmmc2 {
- supports-sdio;
bus-width = <4>;
disable-wp;
cap-sd-highspeed;
clock-names = "aclk_mst", "aclk_slv",
"aclk_dbi", "pclk", "aux";
device_type = "pci";
+ #interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0 0 0 1 &pcie_intc 0>,
<0 0 0 2 &pcie_intc 1>,
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/assembler.h>
#include "sm4-ce-asm.h"
SYM_FUNC_END(sm4_ce_ccm_final)
.align 3
-SYM_FUNC_START(sm4_ce_ccm_enc)
+SYM_TYPED_FUNC_START(sm4_ce_ccm_enc)
/* input:
* x0: round key array, CTX
* x1: dst
SYM_FUNC_END(sm4_ce_ccm_enc)
.align 3
-SYM_FUNC_START(sm4_ce_ccm_dec)
+SYM_TYPED_FUNC_START(sm4_ce_ccm_dec)
/* input:
* x0: round key array, CTX
* x1: dst
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/assembler.h>
#include "sm4-ce-asm.h"
SYM_FUNC_END(pmull_ghash_update)
.align 3
-SYM_FUNC_START(sm4_ce_pmull_gcm_enc)
+SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_enc)
/* input:
* x0: round key array, CTX
* x1: dst
#define RH3 v20
.align 3
-SYM_FUNC_START(sm4_ce_pmull_gcm_dec)
+SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_dec)
/* input:
* x0: round key array, CTX
* x1: dst
" cbnz %w0, 1b\n" \
" " #mb "\n" \
"2:" \
- : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \
+ : "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr) \
: "r" (old1), "r" (old2), "r" (new1), "r" (new2) \
: cl); \
\
" eor %[old2], %[old2], %[oldval2]\n" \
" orr %[old1], %[old1], %[old2]" \
: [old1] "+&r" (x0), [old2] "+&r" (x1), \
- [v] "+Q" (*(unsigned long *)ptr) \
+ [v] "+Q" (*(__uint128_t *)ptr) \
: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \
[oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \
: cl); \
#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025
#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028
#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029
+#define APPLE_CPU_PART_M2_BLIZZARD 0x032
+#define APPLE_CPU_PART_M2_AVALANCHE 0x033
#define AMPERE_CPU_PART_AMPERE1 0xAC3
#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
+#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
})
extern spinlock_t efi_rt_lock;
+extern u64 *efi_rt_stack_top;
efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...);
+/*
+ * efi_rt_stack_top[-1] contains the value the stack pointer had before
+ * switching to the EFI runtime stack.
+ */
+#define current_in_efi() \
+ (!preemptible() && efi_rt_stack_top != NULL && \
+ on_task_stack(current, READ_ONCE(efi_rt_stack_top[-1]), 1))
+
#define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
/*
#define ESR_ELx_FSC_ACCESS (0x08)
#define ESR_ELx_FSC_FAULT (0x04)
#define ESR_ELx_FSC_PERM (0x0C)
+#define ESR_ELx_FSC_SEA_TTW0 (0x14)
+#define ESR_ELx_FSC_SEA_TTW1 (0x15)
+#define ESR_ELx_FSC_SEA_TTW2 (0x16)
+#define ESR_ELx_FSC_SEA_TTW3 (0x17)
+#define ESR_ELx_FSC_SECC (0x18)
+#define ESR_ELx_FSC_SECC_TTW0 (0x1c)
+#define ESR_ELx_FSC_SECC_TTW1 (0x1d)
+#define ESR_ELx_FSC_SECC_TTW2 (0x1e)
+#define ESR_ELx_FSC_SECC_TTW3 (0x1f)
/* ISS field definitions for Data Aborts */
#define ESR_ELx_ISV_SHIFT (24)
void __init arm64_hugetlb_cma_reserve(void);
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t new_pte);
+
#include <asm-generic/hugetlb.h>
#endif /* __ASM_HUGETLB_H */
BIT(18) | \
GENMASK(16, 15))
-/* For compatibility with fault code shared with 32-bit */
-#define FSC_FAULT ESR_ELx_FSC_FAULT
-#define FSC_ACCESS ESR_ELx_FSC_ACCESS
-#define FSC_PERM ESR_ELx_FSC_PERM
-#define FSC_SEA ESR_ELx_FSC_EXTABT
-#define FSC_SEA_TTW0 (0x14)
-#define FSC_SEA_TTW1 (0x15)
-#define FSC_SEA_TTW2 (0x16)
-#define FSC_SEA_TTW3 (0x17)
-#define FSC_SECC (0x18)
-#define FSC_SECC_TTW0 (0x1c)
-#define FSC_SECC_TTW1 (0x1d)
-#define FSC_SECC_TTW2 (0x1e)
-#define FSC_SECC_TTW3 (0x1f)
-
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
/*
static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
{
switch (kvm_vcpu_trap_get_fault(vcpu)) {
- case FSC_SEA:
- case FSC_SEA_TTW0:
- case FSC_SEA_TTW1:
- case FSC_SEA_TTW2:
- case FSC_SEA_TTW3:
- case FSC_SECC:
- case FSC_SECC_TTW0:
- case FSC_SECC_TTW1:
- case FSC_SECC_TTW2:
- case FSC_SECC_TTW3:
+ case ESR_ELx_FSC_EXTABT:
+ case ESR_ELx_FSC_SEA_TTW0:
+ case ESR_ELx_FSC_SEA_TTW1:
+ case ESR_ELx_FSC_SEA_TTW2:
+ case ESR_ELx_FSC_SEA_TTW3:
+ case ESR_ELx_FSC_SECC:
+ case ESR_ELx_FSC_SECC_TTW0:
+ case ESR_ELx_FSC_SECC_TTW1:
+ case ESR_ELx_FSC_SECC_TTW2:
+ case ESR_ELx_FSC_SECC_TTW3:
return true;
default:
return false;
static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
{
- if (kvm_vcpu_abt_iss1tw(vcpu))
- return true;
+ if (kvm_vcpu_abt_iss1tw(vcpu)) {
+ /*
+ * Only a permission fault on a S1PTW should be
+ * considered as a write. Otherwise, page tables baked
+ * in a read-only memslot will result in an exception
+ * being delivered in the guest.
+ *
+ * The drawback is that we end-up faulting twice if the
+ * guest is using any of HW AF/DB: a translation fault
+ * to map the page containing the PT (read only at
+ * first), then a permission fault to allow the flags
+ * to be set.
+ */
+ switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+ case ESR_ELx_FSC_PERM:
+ return true;
+ default:
+ return false;
+ }
+ }
if (kvm_vcpu_trap_is_iabt(vcpu))
return false;
#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud))
#define pud_valid(pud) pte_valid(pud_pte(pud))
#define pud_user(pud) pte_user(pud_pte(pud))
-
+#define pud_user_exec(pud) pte_user_exec(pud_pte(pud))
static inline void set_pud(pud_t *pudp, pud_t pud)
{
#else
#define pud_page_paddr(pud) ({ BUILD_BUG(); 0; })
+#define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */
/* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */
#define pmd_set_fixmap(addr) NULL
static inline bool pmd_user_accessible_page(pmd_t pmd)
{
- return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+ return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
}
static inline bool pud_user_accessible_page(pud_t pud)
{
- return pud_leaf(pud) && pud_user(pud);
+ return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud));
}
#endif
}
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+#define ptep_modify_prot_start ptep_modify_prot_start
+extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define ptep_modify_prot_commit ptep_modify_prot_commit
+extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t new_pte);
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */
#define stackinfo_get_sdei_critical() stackinfo_get_unknown()
#endif
+#ifdef CONFIG_EFI
+extern u64 *efi_rt_stack_top;
+
+static inline struct stack_info stackinfo_get_efi(void)
+{
+ unsigned long high = (u64)efi_rt_stack_top;
+ unsigned long low = high - THREAD_SIZE;
+
+ return (struct stack_info) {
+ .low = low,
+ .high = high,
+ };
+}
+#endif
+
#endif /* __ASM_STACKTRACE_H */
#define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE
#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES
-typedef u32 uprobe_opcode_t;
+typedef __le32 uprobe_opcode_t;
struct arch_uprobe_task {
};
CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_2645198
+ {
+ .desc = "ARM erratum 2645198",
+ .capability = ARM64_WORKAROUND_2645198,
+ ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715)
+ },
+#endif
#ifdef CONFIG_ARM64_ERRATUM_2077057
{
.desc = "ARM erratum 2077057",
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
SYM_FUNC_START(__efi_rt_asm_wrapper)
stp x29, x30, [sp, #-112]!
mov x4, x6
blr x8
+ mov x16, sp
mov sp, x29
+ str xzr, [x16, #8] // clear recorded task SP value
+
ldp x1, x2, [sp, #16]
cmp x2, x18
ldp x29, x30, [sp], #112
SYM_CODE_START(__efi_rt_asm_recover)
mov sp, x30
+ ldr_l x16, efi_rt_stack_top // clear recorded task SP value
+ str xzr, [x16, #-8]
+
ldp x19, x20, [sp, #32]
ldp x21, x22, [sp, #48]
ldp x23, x24, [sp, #64]
#include <linux/init.h>
#include <asm/efi.h>
+#include <asm/stacktrace.h>
static bool region_is_misaligned(const efi_memory_desc_t *md)
{
bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg)
{
/* Check whether the exception occurred while running the firmware */
- if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64)
+ if (!current_in_efi() || regs->pc >= TASK_SIZE_64)
return false;
pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg);
#include <asm/cpufeature.h>
#include <asm/mte.h>
-#define for_each_mte_vma(vmi, vma) \
+#define for_each_mte_vma(cprm, i, m) \
if (system_supports_mte()) \
- for_each_vma(vmi, vma) \
- if (vma->vm_flags & VM_MTE)
+ for (i = 0, m = cprm->vma_meta; \
+ i < cprm->vma_count; \
+ i++, m = cprm->vma_meta + i) \
+ if (m->flags & VM_MTE)
-static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
+static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m)
{
- if (vma->vm_flags & VM_DONTDUMP)
- return 0;
-
- return vma_pages(vma) * MTE_PAGE_TAG_STORAGE;
+ return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE;
}
/* Derived from dump_user_range(); start/end must be page-aligned */
static int mte_dump_tag_range(struct coredump_params *cprm,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long len)
{
int ret = 1;
unsigned long addr;
void *tags = NULL;
- for (addr = start; addr < end; addr += PAGE_SIZE) {
+ for (addr = start; addr < start + len; addr += PAGE_SIZE) {
struct page *page = get_dump_page(addr);
/*
mte_save_page_tags(page_address(page), tags);
put_page(page);
if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) {
- mte_free_tag_storage(tags);
ret = 0;
break;
}
return ret;
}
-Elf_Half elf_core_extra_phdrs(void)
+Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
+ int i;
+ struct core_vma_metadata *m;
int vma_count = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
+ for_each_mte_vma(cprm, i, m)
vma_count++;
return vma_count;
int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
+ int i;
+ struct core_vma_metadata *m;
- for_each_mte_vma(vmi, vma) {
+ for_each_mte_vma(cprm, i, m) {
struct elf_phdr phdr;
phdr.p_type = PT_AARCH64_MEMTAG_MTE;
phdr.p_offset = offset;
- phdr.p_vaddr = vma->vm_start;
+ phdr.p_vaddr = m->start;
phdr.p_paddr = 0;
- phdr.p_filesz = mte_vma_tag_dump_size(vma);
- phdr.p_memsz = vma->vm_end - vma->vm_start;
+ phdr.p_filesz = mte_vma_tag_dump_size(m);
+ phdr.p_memsz = m->end - m->start;
offset += phdr.p_filesz;
phdr.p_flags = 0;
phdr.p_align = 0;
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
+ int i;
+ struct core_vma_metadata *m;
size_t data_size = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
- data_size += mte_vma_tag_dump_size(vma);
+ for_each_mte_vma(cprm, i, m)
+ data_size += mte_vma_tag_dump_size(m);
return data_size;
}
int elf_core_write_extra_data(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
-
- for_each_mte_vma(vmi, vma) {
- if (vma->vm_flags & VM_DONTDUMP)
- continue;
+ int i;
+ struct core_vma_metadata *m;
- if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end))
+ for_each_mte_vma(cprm, i, m) {
+ if (!mte_dump_tag_range(cprm, m->start, m->dump_size))
return 0;
}
WARN_ON(!system_supports_fpsimd());
WARN_ON(!have_cpu_fpsimd_context());
- if (system_supports_sve()) {
+ if (system_supports_sve() || system_supports_sme()) {
switch (current->thread.fp_type) {
case FP_STATE_FPSIMD:
/* Stop tracking SVE for this task until next use. */
return 0;
}
-static bool armv8pmu_filter(struct pmu *pmu, int cpu)
-{
- struct arm_pmu *armpmu = to_arm_pmu(pmu);
- return !cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus);
-}
-
static void armv8pmu_reset(void *info)
{
struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
&armv8_pmuv3_perf_cache_map,
ARMV8_PMU_EVTYPE_EVENT);
+ /*
+ * CHAIN events only work when paired with an adjacent counter, and it
+ * never makes sense for a user to open one in isolation, as they'll be
+ * rotated arbitrarily.
+ */
+ if (hw_event_id == ARMV8_PMUV3_PERFCTR_CHAIN)
+ return -EINVAL;
+
if (armv8pmu_event_is_64bit(event))
event->hw.flags |= ARMPMU_EVT_64BIT;
cpu_pmu->stop = armv8pmu_stop;
cpu_pmu->reset = armv8pmu_reset;
cpu_pmu->set_event_filter = armv8pmu_set_event_filter;
- cpu_pmu->filter = armv8pmu_filter;
cpu_pmu->pmu.event_idx = armv8pmu_user_event_idx;
#ifdef CONFIG_ARM64_SVE
REGSET_SVE,
#endif
-#ifdef CONFIG_ARM64_SVE
+#ifdef CONFIG_ARM64_SME
REGSET_SSVE,
REGSET_ZA,
#endif
vl = task_get_sme_vl(current);
} else {
- if (!system_supports_sve())
+ /*
+ * A SME only system use SVE for streaming mode so can
+ * have a SVE formatted context with a zero VL and no
+ * payload data.
+ */
+ if (!system_supports_sve() && !system_supports_sme())
return -EINVAL;
vl = task_get_sve_vl(current);
return err;
}
- if (system_supports_sve()) {
+ if (system_supports_sve() || system_supports_sme()) {
unsigned int vq = 0;
if (add_all || test_thread_flag(TIF_SVE) ||
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/kernel.h>
+#include <linux/efi.h>
#include <linux/export.h>
#include <linux/ftrace.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
+#include <asm/efi.h>
#include <asm/irq.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
: stackinfo_get_unknown(); \
})
+#define STACKINFO_EFI \
+ ({ \
+ ((task == current) && current_in_efi()) \
+ ? stackinfo_get_efi() \
+ : stackinfo_get_unknown(); \
+ })
+
noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
void *cookie, struct task_struct *task,
struct pt_regs *regs)
#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_ARM_SDE_INTERFACE)
STACKINFO_SDEI(normal),
STACKINFO_SDEI(critical),
+#endif
+#ifdef CONFIG_EFI
+ STACKINFO_EFI,
#endif
};
struct unwind_state state = {
/* uaccess failed, don't leave stale tags */
if (num_tags != MTE_GRANULES_PER_PAGE)
- mte_clear_page_tags(page);
+ mte_clear_page_tags(maddr);
set_page_mte_tagged(page);
kvm_release_pfn_dirty(pfn);
*/
if (!(esr & ESR_ELx_S1PTW) &&
(cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
- (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+ (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
if (!__translate_far_to_hpfar(far, &hpfar))
return false;
} else {
if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
bool valid;
- valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+ valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
kvm_vcpu_dabt_isvalid(vcpu) &&
!kvm_vcpu_abt_issea(vcpu) &&
!kvm_vcpu_abt_iss1tw(vcpu);
exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
VM_BUG_ON(write_fault && exec_fault);
- if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
+ if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
* only exception to this is when dirty logging is enabled at runtime
* and a write fault needs to collapse a block entry into a table.
*/
- if (fault_status != FSC_PERM || (logging_active && write_fault)) {
+ if (fault_status != ESR_ELx_FSC_PERM ||
+ (logging_active && write_fault)) {
ret = kvm_mmu_topup_memory_cache(memcache,
kvm_mmu_cache_min_pages(kvm));
if (ret)
* backed by a THP and thus use block mapping if possible.
*/
if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
- if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+ if (fault_status == ESR_ELx_FSC_PERM &&
+ fault_granule > PAGE_SIZE)
vma_pagesize = fault_granule;
else
vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
&fault_ipa);
}
- if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
+ if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new disallowed VMA */
if (kvm_vma_mte_allowed(vma)) {
sanitise_mte_tags(kvm, pfn, vma_pagesize);
* permissions only if vma_pagesize equals fault_granule. Otherwise,
* kvm_pgtable_stage2_map() should be called to change block size.
*/
- if (fault_status == FSC_PERM && vma_pagesize == fault_granule)
+ if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
else
ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
- if (fault_status == FSC_FAULT) {
+ if (fault_status == ESR_ELx_FSC_FAULT) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
kvm_vcpu_get_hfar(vcpu), fault_ipa);
/* Check the stage-2 fault is trans. fault or write fault */
- if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
- fault_status != FSC_ACCESS) {
+ if (fault_status != ESR_ELx_FSC_FAULT &&
+ fault_status != ESR_ELx_FSC_PERM &&
+ fault_status != ESR_ELx_FSC_ACCESS) {
kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
kvm_vcpu_trap_get_class(vcpu),
(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
/* Userspace should not be able to register out-of-bounds IPAs */
VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
- if (fault_status == FSC_ACCESS) {
+ if (fault_status == ESR_ELx_FSC_ACCESS) {
handle_access_fault(vcpu, fault_ipa);
ret = 1;
goto out_unlock;
return;
/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
- pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK;
+ pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
if (!kvm_supports_32bit_el0())
pmcr |= ARMV8_PMU_PMCR_LC;
((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) |
ite->collection->collection_id;
val = cpu_to_le64(val);
- return kvm_write_guest_lock(kvm, gpa, &val, ite_esz);
+ return vgic_write_guest_lock(kvm, gpa, &val, ite_esz);
}
/**
(itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) |
(dev->num_eventid_bits - 1));
val = cpu_to_le64(val);
- return kvm_write_guest_lock(kvm, ptr, &val, dte_esz);
+ return vgic_write_guest_lock(kvm, ptr, &val, dte_esz);
}
/**
((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) |
collection->collection_id);
val = cpu_to_le64(val);
- return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz);
+ return vgic_write_guest_lock(its->dev->kvm, gpa, &val, esz);
}
/*
*/
val = 0;
BUG_ON(cte_esz > sizeof(val));
- ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz);
+ ret = vgic_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz);
return ret;
}
static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr)
{
const struct vgic_its_abi *abi = vgic_its_get_abi(its);
- struct vgic_dist *dist = &kvm->arch.vgic;
int ret = 0;
if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */
vgic_its_reset(kvm, its);
break;
case KVM_DEV_ARM_ITS_SAVE_TABLES:
- dist->save_its_tables_in_progress = true;
ret = abi->save_tables(its);
- dist->save_its_tables_in_progress = false;
break;
case KVM_DEV_ARM_ITS_RESTORE_TABLES:
ret = abi->restore_tables(its);
{
struct vgic_dist *dist = &kvm->arch.vgic;
- return dist->save_its_tables_in_progress;
+ return dist->table_write_in_progress;
}
static int vgic_its_set_attr(struct kvm_device *dev,
if (status) {
/* clear consumed data */
val &= ~(1 << bit_nr);
- ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
+ ret = vgic_write_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
}
* The deactivation of the doorbell interrupt will trigger the
* unmapping of the associated vPE.
*/
-static void unmap_all_vpes(struct vgic_dist *dist)
+static void unmap_all_vpes(struct kvm *kvm)
{
- struct irq_desc *desc;
+ struct vgic_dist *dist = &kvm->arch.vgic;
int i;
- for (i = 0; i < dist->its_vm.nr_vpes; i++) {
- desc = irq_to_desc(dist->its_vm.vpes[i]->irq);
- irq_domain_deactivate_irq(irq_desc_get_irq_data(desc));
- }
+ for (i = 0; i < dist->its_vm.nr_vpes; i++)
+ free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i));
}
-static void map_all_vpes(struct vgic_dist *dist)
+static void map_all_vpes(struct kvm *kvm)
{
- struct irq_desc *desc;
+ struct vgic_dist *dist = &kvm->arch.vgic;
int i;
- for (i = 0; i < dist->its_vm.nr_vpes; i++) {
- desc = irq_to_desc(dist->its_vm.vpes[i]->irq);
- irq_domain_activate_irq(irq_desc_get_irq_data(desc), false);
- }
+ for (i = 0; i < dist->its_vm.nr_vpes; i++)
+ WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i),
+ dist->its_vm.vpes[i]->irq));
}
/**
* and enabling of the doorbells have already been done.
*/
if (kvm_vgic_global_state.has_gicv4_1) {
- unmap_all_vpes(dist);
+ unmap_all_vpes(kvm);
vlpi_avail = true;
}
else
val &= ~(1 << bit_nr);
- ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
+ ret = vgic_write_guest_lock(kvm, ptr, &val, 1);
if (ret)
goto out;
}
out:
if (vlpi_avail)
- map_all_vpes(dist);
+ map_all_vpes(kvm);
return ret;
}
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
{},
};
*val = !!(*ptr & mask);
}
+int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq)
+{
+ return request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu);
+}
+
/**
* vgic_v4_init - Initialize the GICv4 data structures
* @kvm: Pointer to the VM being initialized
irq_flags &= ~IRQ_NOAUTOEN;
irq_set_status_flags(irq, irq_flags);
- ret = request_irq(irq, vgic_v4_doorbell_handler,
- 0, "vcpu", vcpu);
+ ret = vgic_v4_request_vpe_irq(vcpu, irq);
if (ret) {
kvm_err("failed to allocate vcpu IRQ%d\n", irq);
/*
#define __KVM_ARM_VGIC_NEW_H__
#include <linux/irqchip/arm-gic-common.h>
+#include <asm/kvm_mmu.h>
#define PRODUCT_ID_KVM 0x4b /* ASCII code K */
#define IMPLEMENTER_ARM 0x43b
return vgic_irq_get_lr_count(irq) > 1;
}
+static inline int vgic_write_guest_lock(struct kvm *kvm, gpa_t gpa,
+ const void *data, unsigned long len)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ int ret;
+
+ dist->table_write_in_progress = true;
+ ret = kvm_write_guest_lock(kvm, gpa, data, len);
+ dist->table_write_in_progress = false;
+
+ return ret;
+}
+
/*
* This struct provides an intermediate representation of the fields contained
* in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
void vgic_v4_teardown(struct kvm *kvm);
void vgic_v4_configure_vsgis(struct kvm *kvm);
void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val);
+int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq);
#endif
{
return __hugetlb_valid_size(size);
}
+
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+ cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+ /*
+ * Break-before-make (BBM) is required for all user space mappings
+ * when the permission changes from executable to non-executable
+ * in cases where cpu is affected with errata #2645198.
+ */
+ if (pte_user_exec(READ_ONCE(*ptep)))
+ return huge_ptep_clear_flush(vma, addr, ptep);
+ }
+ return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte)
+{
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
}
early_initcall(prevent_bootmem_remove_init);
#endif
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+ cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+ /*
+ * Break-before-make (BBM) is required for all user space mappings
+ * when the permission changes from executable to non-executable
+ * in cases where cpu is affected with errata #2645198.
+ */
+ if (pte_user_exec(READ_ONCE(*ptep)))
+ return ptep_clear_flush(vma, addr, ptep);
+ }
+ return ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte)
+{
+ set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
WORKAROUND_2064142
WORKAROUND_2077057
WORKAROUND_2457168
+WORKAROUND_2645198
WORKAROUND_2658417
WORKAROUND_TRBE_OVERWRITE_FILL_MODE
WORKAROUND_TSB_FLUSH_FAILURE
#include <asm/elf.h>
-Elf64_Half elf_core_extra_phdrs(void)
+Elf64_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return GATE_EHDR->e_phnum;
}
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
const struct elf_phdr *const gate_phdrs =
(const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff);
asmlinkage long
ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *tp)
{
+ struct timespec64 rtn_tp;
+ s64 tick_ns;
+
/*
* ia64's clock_gettime() syscall is implemented as a vdso call
* fsys_clock_gettime(). Currently it handles only
switch (which_clock) {
case CLOCK_REALTIME:
case CLOCK_MONOTONIC:
- s64 tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq);
- struct timespec64 rtn_tp = ns_to_timespec64(tick_ns);
+ tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq);
+ rtn_tp = ns_to_timespec64(tick_ns);
return put_timespec64(&rtn_tp, tp);
}
#define FTRACE_REGS_PLT_IDX 1
#define NR_FTRACE_PLTS 2
-#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1]))
-
#ifdef CONFIG_FUNCTION_TRACER
#define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */
return val < (1UL << bit);
}
-static inline unsigned long sign_extend(unsigned long val, unsigned int idx)
-{
- if (!is_imm_negative(val, idx + 1))
- return ((1UL << idx) - 1) & val;
- else
- return ~((1UL << idx) - 1) | val;
-}
-
#define DEF_EMIT_REG0I26_FORMAT(NAME, OP) \
static inline void emit_##NAME(union loongarch_instruction *insn, \
int offset) \
}
DEF_EMIT_REG0I26_FORMAT(b, b_op)
+DEF_EMIT_REG0I26_FORMAT(bl, bl_op)
#define DEF_EMIT_REG1I20_FORMAT(NAME, OP) \
static inline void emit_##NAME(union loongarch_instruction *insn, \
#define _ASM_UNWIND_H
#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
#include <asm/stacktrace.h>
enum unwinder_type {
char type; /* UNWINDER_XXX */
struct stack_info stack_info;
struct task_struct *task;
- bool first, error, is_ftrace;
+ bool first, error, reset;
int graph_idx;
unsigned long sp, pc, ra;
};
+bool default_next_frame(struct unwind_state *state);
+
void unwind_start(struct unwind_state *state,
struct task_struct *task, struct pt_regs *regs);
bool unwind_next_frame(struct unwind_state *state);
return state->error;
}
+#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1]))
+
+static inline unsigned long unwind_graph_addr(struct unwind_state *state,
+ unsigned long pc, unsigned long cfa)
+{
+ return ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ pc, (unsigned long *)(cfa - GRAPH_FAKE_OFFSET));
+}
+
+static __always_inline void __unwind_start(struct unwind_state *state,
+ struct task_struct *task, struct pt_regs *regs)
+{
+ memset(state, 0, sizeof(*state));
+ if (regs) {
+ state->sp = regs->regs[3];
+ state->pc = regs->csr_era;
+ state->ra = regs->regs[1];
+ } else if (task && task != current) {
+ state->sp = thread_saved_fp(task);
+ state->pc = thread_saved_ra(task);
+ state->ra = 0;
+ } else {
+ state->sp = (unsigned long)__builtin_frame_address(0);
+ state->pc = (unsigned long)__builtin_return_address(0);
+ state->ra = 0;
+ }
+ state->task = task;
+ get_stack_info(state->sp, state->task, &state->stack_info);
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
+}
+
+static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state)
+{
+ return unwind_done(state) ? 0 : state->pc;
+}
#endif /* _ASM_UNWIND_H */
obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \
elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \
- alternative.o unaligned.o
+ alternative.o unaligned.o unwind.o
obj-$(CONFIG_ACPI) += acpi.o
obj-$(CONFIG_EFI) += efi.o
switch (src->reg0i26_format.opcode) {
case b_op:
case bl_op:
- jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 27);
+ jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 27);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
fallthrough;
case beqz_op:
case bnez_op:
- jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 22);
+ jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 22);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
case bge_op:
case bltu_op:
case bgeu_op:
- jump_addr = cur_pc + sign_extend(si << 2, 17);
+ jump_addr = cur_pc + sign_extend64(si << 2, 17);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR |
LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH;
- elf_hwcap |= HWCAP_LOONGARCH_CRC32;
+ elf_hwcap = HWCAP_LOONGARCH_CPUCFG | HWCAP_LOONGARCH_CRC32;
config = read_cpucfg(LOONGARCH_CPUCFG1);
if (config & CPUCFG1_UAL) {
.macro BUILD_HANDLER exception handler prep
.align 5
SYM_FUNC_START(handle_\exception)
+ 666:
BACKUP_T0T1
SAVE_ALL
build_prep_\prep
move a0, sp
la.abs t0, do_\handler
jirl ra, t0, 0
+ 668:
RESTORE_ALL_AND_RET
SYM_FUNC_END(handle_\exception)
+ SYM_DATA(unwind_hint_\exception, .word 668b - 666b)
.endm
BUILD_HANDLER ade ade badv
u32 larch_insn_gen_b(unsigned long pc, unsigned long dest)
{
long offset = dest - pc;
- unsigned int immediate_l, immediate_h;
union loongarch_instruction insn;
if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) {
return INSN_BREAK;
}
- offset >>= 2;
-
- immediate_l = offset & 0xffff;
- offset >>= 16;
- immediate_h = offset & 0x3ff;
-
- insn.reg0i26_format.opcode = b_op;
- insn.reg0i26_format.immediate_l = immediate_l;
- insn.reg0i26_format.immediate_h = immediate_h;
+ emit_b(&insn, offset >> 2);
return insn.word;
}
u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest)
{
long offset = dest - pc;
- unsigned int immediate_l, immediate_h;
union loongarch_instruction insn;
if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) {
return INSN_BREAK;
}
- offset >>= 2;
-
- immediate_l = offset & 0xffff;
- offset >>= 16;
- immediate_h = offset & 0x3ff;
-
- insn.reg0i26_format.opcode = bl_op;
- insn.reg0i26_format.immediate_l = immediate_l;
- insn.reg0i26_format.immediate_h = immediate_h;
+ emit_bl(&insn, offset >> 2);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg3_format.opcode = or_op;
- insn.reg3_format.rd = rd;
- insn.reg3_format.rj = rj;
- insn.reg3_format.rk = rk;
+ emit_or(&insn, rd, rj, rk);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg1i20_format.opcode = lu12iw_op;
- insn.reg1i20_format.rd = rd;
- insn.reg1i20_format.immediate = imm;
+ emit_lu12iw(&insn, rd, imm);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg1i20_format.opcode = lu32id_op;
- insn.reg1i20_format.rd = rd;
- insn.reg1i20_format.immediate = imm;
+ emit_lu32id(&insn, rd, imm);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg2i12_format.opcode = lu52id_op;
- insn.reg2i12_format.rd = rd;
- insn.reg2i12_format.rj = rj;
- insn.reg2i12_format.immediate = imm;
+ emit_lu52id(&insn, rd, rj, imm);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg2i16_format.opcode = jirl_op;
- insn.reg2i16_format.rd = rd;
- insn.reg2i16_format.rj = rj;
- insn.reg2i16_format.immediate = (dest - pc) >> 2;
+ emit_jirl(&insn, rj, rd, (dest - pc) >> 2);
return insn.word;
}
unsigned long __get_wchan(struct task_struct *task)
{
- unsigned long pc;
+ unsigned long pc = 0;
struct unwind_state state;
if (!try_get_task_stack(task))
return 0;
- unwind_start(&state, task, NULL);
- state.sp = thread_saved_fp(task);
- get_stack_info(state.sp, state.task, &state.stack_info);
- state.pc = thread_saved_ra(task);
-#ifdef CONFIG_UNWINDER_PROLOGUE
- state.type = UNWINDER_PROLOGUE;
-#endif
- for (; !unwind_done(&state); unwind_next_frame(&state)) {
+ for (unwind_start(&state, task, NULL);
+ !unwind_done(&state); unwind_next_frame(&state)) {
pc = unwind_get_return_address(&state);
if (!pc)
break;
if (!task)
task = current;
- if (user_mode(regs))
- state.type = UNWINDER_GUESS;
-
printk("%sCall Trace:", loglvl);
for (unwind_start(&state, task, pregs);
!unwind_done(&state); unwind_next_frame(&state)) {
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2023 Loongson Technology Corporation Limited
+ */
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+
+#include <asm/unwind.h>
+
+bool default_next_frame(struct unwind_state *state)
+{
+ struct stack_info *info = &state->stack_info;
+ unsigned long addr;
+
+ if (unwind_done(state))
+ return false;
+
+ do {
+ for (state->sp += sizeof(unsigned long);
+ state->sp < info->end; state->sp += sizeof(unsigned long)) {
+ addr = *(unsigned long *)(state->sp);
+ state->pc = unwind_graph_addr(state, addr, state->sp + 8);
+ if (__kernel_text_address(state->pc))
+ return true;
+ }
+
+ state->sp = info->next_sp;
+
+ } while (!get_stack_info(state->sp, state->task, info));
+
+ return false;
+}
/*
* Copyright (C) 2022 Loongson Technology Corporation Limited
*/
-#include <linux/kernel.h>
-#include <linux/ftrace.h>
-
#include <asm/unwind.h>
unsigned long unwind_get_return_address(struct unwind_state *state)
{
- if (unwind_done(state))
- return 0;
- else if (state->first)
- return state->pc;
-
- return *(unsigned long *)(state->sp);
+ return __unwind_get_return_address(state);
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
void unwind_start(struct unwind_state *state, struct task_struct *task,
struct pt_regs *regs)
{
- memset(state, 0, sizeof(*state));
-
- if (regs) {
- state->sp = regs->regs[3];
- state->pc = regs->csr_era;
- }
-
- state->task = task;
- state->first = true;
-
- get_stack_info(state->sp, state->task, &state->stack_info);
-
+ __unwind_start(state, task, regs);
if (!unwind_done(state) && !__kernel_text_address(state->pc))
unwind_next_frame(state);
}
bool unwind_next_frame(struct unwind_state *state)
{
- struct stack_info *info = &state->stack_info;
- unsigned long addr;
-
- if (unwind_done(state))
- return false;
-
- if (state->first)
- state->first = false;
-
- do {
- for (state->sp += sizeof(unsigned long);
- state->sp < info->end;
- state->sp += sizeof(unsigned long)) {
- addr = *(unsigned long *)(state->sp);
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- if (__kernel_text_address(addr))
- return true;
- }
-
- state->sp = info->next_sp;
-
- } while (!get_stack_info(state->sp, state->task, info));
-
- return false;
+ return default_next_frame(state);
}
EXPORT_SYMBOL_GPL(unwind_next_frame);
/*
* Copyright (C) 2022 Loongson Technology Corporation Limited
*/
+#include <linux/cpumask.h>
#include <linux/ftrace.h>
#include <linux/kallsyms.h>
#include <asm/inst.h>
+#include <asm/loongson.h>
#include <asm/ptrace.h>
+#include <asm/setup.h>
#include <asm/unwind.h>
-static inline void unwind_state_fixup(struct unwind_state *state)
-{
-#ifdef CONFIG_DYNAMIC_FTRACE
- static unsigned long ftrace = (unsigned long)ftrace_call + 4;
-
- if (state->pc == ftrace)
- state->is_ftrace = true;
+extern const int unwind_hint_ade;
+extern const int unwind_hint_ale;
+extern const int unwind_hint_bp;
+extern const int unwind_hint_fpe;
+extern const int unwind_hint_fpu;
+extern const int unwind_hint_lsx;
+extern const int unwind_hint_lasx;
+extern const int unwind_hint_lbt;
+extern const int unwind_hint_ri;
+extern const int unwind_hint_watch;
+extern unsigned long eentry;
+#ifdef CONFIG_NUMA
+extern unsigned long pcpu_handlers[NR_CPUS];
#endif
-}
-unsigned long unwind_get_return_address(struct unwind_state *state)
+static inline bool scan_handlers(unsigned long entry_offset)
{
+ int idx, offset;
- if (unwind_done(state))
- return 0;
- else if (state->type)
- return state->pc;
- else if (state->first)
- return state->pc;
-
- return *(unsigned long *)(state->sp);
+ if (entry_offset >= EXCCODE_INT_START * VECSIZE)
+ return false;
+ idx = entry_offset / VECSIZE;
+ offset = entry_offset % VECSIZE;
+ switch (idx) {
+ case EXCCODE_ADE:
+ return offset == unwind_hint_ade;
+ case EXCCODE_ALE:
+ return offset == unwind_hint_ale;
+ case EXCCODE_BP:
+ return offset == unwind_hint_bp;
+ case EXCCODE_FPE:
+ return offset == unwind_hint_fpe;
+ case EXCCODE_FPDIS:
+ return offset == unwind_hint_fpu;
+ case EXCCODE_LSXDIS:
+ return offset == unwind_hint_lsx;
+ case EXCCODE_LASXDIS:
+ return offset == unwind_hint_lasx;
+ case EXCCODE_BTDIS:
+ return offset == unwind_hint_lbt;
+ case EXCCODE_INE:
+ return offset == unwind_hint_ri;
+ case EXCCODE_WATCH:
+ return offset == unwind_hint_watch;
+ default:
+ return false;
+ }
}
-EXPORT_SYMBOL_GPL(unwind_get_return_address);
-static bool unwind_by_guess(struct unwind_state *state)
+static inline bool fix_exception(unsigned long pc)
{
- struct stack_info *info = &state->stack_info;
- unsigned long addr;
-
- for (state->sp += sizeof(unsigned long);
- state->sp < info->end;
- state->sp += sizeof(unsigned long)) {
- addr = *(unsigned long *)(state->sp);
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- if (__kernel_text_address(addr))
+#ifdef CONFIG_NUMA
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ if (!pcpu_handlers[cpu])
+ continue;
+ if (scan_handlers(pc - pcpu_handlers[cpu]))
return true;
}
+#endif
+ return scan_handlers(pc - eentry);
+}
+/*
+ * As we meet ftrace_regs_entry, reset first flag like first doing
+ * tracing. Prologue analysis will stop soon because PC is at entry.
+ */
+static inline bool fix_ftrace(unsigned long pc)
+{
+#ifdef CONFIG_DYNAMIC_FTRACE
+ return pc == (unsigned long)ftrace_call + LOONGARCH_INSN_SIZE;
+#else
return false;
+#endif
}
+static inline bool unwind_state_fixup(struct unwind_state *state)
+{
+ if (!fix_exception(state->pc) && !fix_ftrace(state->pc))
+ return false;
+
+ state->reset = true;
+ return true;
+}
+
+/*
+ * LoongArch function prologue is like follows,
+ * [instructions not use stack var]
+ * addi.d sp, sp, -imm
+ * st.d xx, sp, offset <- save callee saved regs and
+ * st.d yy, sp, offset save ra if function is nest.
+ * [others instructions]
+ */
static bool unwind_by_prologue(struct unwind_state *state)
{
long frame_ra = -1;
unsigned long frame_size = 0;
- unsigned long size, offset, pc = state->pc;
+ unsigned long size, offset, pc;
struct pt_regs *regs;
struct stack_info *info = &state->stack_info;
union loongarch_instruction *ip, *ip_end;
if (state->sp >= info->end || state->sp < info->begin)
return false;
- if (state->is_ftrace) {
- /*
- * As we meet ftrace_regs_entry, reset first flag like first doing
- * tracing. Prologue analysis will stop soon because PC is at entry.
- */
+ if (state->reset) {
regs = (struct pt_regs *)state->sp;
state->first = true;
- state->is_ftrace = false;
+ state->reset = false;
state->pc = regs->csr_era;
state->ra = regs->regs[1];
state->sp = regs->regs[3];
return true;
}
+ /*
+ * When first is not set, the PC is a return address in the previous frame.
+ * We need to adjust its value in case overflow to the next symbol.
+ */
+ pc = state->pc - (state->first ? 0 : LOONGARCH_INSN_SIZE);
if (!kallsyms_lookup_size_offset(pc, &size, &offset))
return false;
ip++;
}
+ /*
+ * Can't find stack alloc action, PC may be in a leaf function. Only the
+ * first being true is reasonable, otherwise indicate analysis is broken.
+ */
if (!frame_size) {
if (state->first)
goto first;
ip++;
}
+ /* Can't find save $ra action, PC may be in a leaf function, too. */
if (frame_ra < 0) {
if (state->first) {
state->sp = state->sp + frame_size;
return false;
}
- if (state->first)
- state->first = false;
-
state->pc = *(unsigned long *)(state->sp + frame_ra);
state->sp = state->sp + frame_size;
goto out;
first:
- state->first = false;
- if (state->pc == state->ra)
- return false;
-
state->pc = state->ra;
out:
- unwind_state_fixup(state);
- return !!__kernel_text_address(state->pc);
-}
-
-void unwind_start(struct unwind_state *state, struct task_struct *task,
- struct pt_regs *regs)
-{
- memset(state, 0, sizeof(*state));
-
- if (regs && __kernel_text_address(regs->csr_era)) {
- state->pc = regs->csr_era;
- state->sp = regs->regs[3];
- state->ra = regs->regs[1];
- state->type = UNWINDER_PROLOGUE;
- }
-
- state->task = task;
- state->first = true;
-
- get_stack_info(state->sp, state->task, &state->stack_info);
-
- if (!unwind_done(state) && !__kernel_text_address(state->pc))
- unwind_next_frame(state);
+ state->first = false;
+ return unwind_state_fixup(state) || __kernel_text_address(state->pc);
}
-EXPORT_SYMBOL_GPL(unwind_start);
-bool unwind_next_frame(struct unwind_state *state)
+static bool next_frame(struct unwind_state *state)
{
- struct stack_info *info = &state->stack_info;
- struct pt_regs *regs;
unsigned long pc;
+ struct pt_regs *regs;
+ struct stack_info *info = &state->stack_info;
if (unwind_done(state))
return false;
do {
- switch (state->type) {
- case UNWINDER_GUESS:
- state->first = false;
- if (unwind_by_guess(state))
- return true;
- break;
+ if (unwind_by_prologue(state)) {
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
+ return true;
+ }
+
+ if (info->type == STACK_TYPE_IRQ && info->end == state->sp) {
+ regs = (struct pt_regs *)info->next_sp;
+ pc = regs->csr_era;
+
+ if (user_mode(regs) || !__kernel_text_address(pc))
+ return false;
+
+ state->first = true;
+ state->pc = pc;
+ state->ra = regs->regs[1];
+ state->sp = regs->regs[3];
+ get_stack_info(state->sp, state->task, info);
- case UNWINDER_PROLOGUE:
- if (unwind_by_prologue(state)) {
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- state->pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- return true;
- }
-
- if (info->type == STACK_TYPE_IRQ &&
- info->end == state->sp) {
- regs = (struct pt_regs *)info->next_sp;
- pc = regs->csr_era;
-
- if (user_mode(regs) || !__kernel_text_address(pc))
- return false;
-
- state->first = true;
- state->ra = regs->regs[1];
- state->sp = regs->regs[3];
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- get_stack_info(state->sp, state->task, info);
-
- return true;
- }
+ return true;
}
state->sp = info->next_sp;
return false;
}
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+ return __unwind_get_return_address(state);
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+void unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs)
+{
+ __unwind_start(state, task, regs);
+ state->type = UNWINDER_PROLOGUE;
+ state->first = true;
+
+ /*
+ * The current PC is not kernel text address, we cannot find its
+ * relative symbol. Thus, prologue analysis will be broken. Luckily,
+ * we can use the default_next_frame().
+ */
+ if (!__kernel_text_address(state->pc)) {
+ state->type = UNWINDER_GUESS;
+ if (!unwind_done(state))
+ unwind_next_frame(state);
+ }
+}
+EXPORT_SYMBOL_GPL(unwind_start);
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+ return state->type == UNWINDER_PROLOGUE ?
+ next_frame(state) : default_next_frame(state);
+}
EXPORT_SYMBOL_GPL(unwind_next_frame);
}
#ifdef CONFIG_NUMA
-static unsigned long pcpu_handlers[NR_CPUS];
+unsigned long pcpu_handlers[NR_CPUS];
#endif
extern long exception_handlers[VECSIZE * 128 / sizeof(long)];
dtb = get_fdt();
__dt_setup_arch(dtb);
- if (!early_init_dt_scan_memory())
+ if (early_init_dt_scan_memory())
return;
if (soc_info.mem_detect)
*/
int pdc_iodc_print(const unsigned char *str, unsigned count)
{
- unsigned int i;
+ unsigned int i, found = 0;
unsigned long flags;
count = min_t(unsigned int, count, sizeof(iodc_dbuf));
iodc_dbuf[i+0] = '\r';
iodc_dbuf[i+1] = '\n';
i += 2;
+ found = 1;
goto print;
default:
iodc_dbuf[i] = str[i];
__pa(pdc_result), 0, __pa(iodc_dbuf), i, 0);
spin_unlock_irqrestore(&pdc_lock, flags);
- return i;
+ return i - found;
}
#if !defined(BOOTLOADER)
unsigned long tmp;
long ret = -EIO;
+ unsigned long user_regs_struct_size = sizeof(struct user_regs_struct);
+#ifdef CONFIG_64BIT
+ if (is_compat_task())
+ user_regs_struct_size /= 2;
+#endif
+
switch (request) {
/* Read the word at location addr in the USER area. For ptraced
addr >= sizeof(struct pt_regs))
break;
if (addr == PT_IAOQ0 || addr == PT_IAOQ1) {
- data |= 3; /* ensure userspace privilege */
+ data |= PRIV_USER; /* ensure userspace privilege */
}
if ((addr >= PT_GR1 && addr <= PT_GR31) ||
addr == PT_IAOQ0 || addr == PT_IAOQ1 ||
return copy_regset_to_user(child,
task_user_regset_view(current),
REGSET_GENERAL,
- 0, sizeof(struct user_regs_struct),
+ 0, user_regs_struct_size,
datap);
case PTRACE_SETREGS: /* Set all gp regs in the child. */
return copy_regset_from_user(child,
task_user_regset_view(current),
REGSET_GENERAL,
- 0, sizeof(struct user_regs_struct),
+ 0, user_regs_struct_size,
datap);
case PTRACE_GETFPREGS: /* Get the child FPU state. */
if (addr >= sizeof(struct pt_regs))
break;
if (addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4) {
- data |= 3; /* ensure userspace privilege */
+ data |= PRIV_USER; /* ensure userspace privilege */
}
if (addr >= PT_FR0 && addr <= PT_FR31 + 4) {
/* Special case, fp regs are 64 bits anyway */
}
}
break;
+ case PTRACE_GETREGS:
+ case PTRACE_SETREGS:
+ case PTRACE_GETFPREGS:
+ case PTRACE_SETFPREGS:
+ return arch_ptrace(child, request, addr, data);
default:
ret = compat_ptrace_request(child, request, addr, data);
case RI(iaoq[0]):
case RI(iaoq[1]):
/* set 2 lowest bits to ensure userspace privilege: */
- regs->iaoq[num - RI(iaoq[0])] = val | 3;
+ regs->iaoq[num - RI(iaoq[0])] = val | PRIV_USER;
return;
case RI(sar): regs->sar = val;
return;
select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WANTS_MODULES_DATA_IN_VMALLOC if PPC_BOOK3S_32 || PPC_8xx
- select ARCH_WANTS_NO_INSTR
select ARCH_WEAK_RELEASE_ACQUIRE
select BINFMT_ELF
select BUILDTIME_TABLE_SORT
interrupts = <16 2 1 9>;
};
};
+
+&fman0_rx_0x08 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x28 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_rx_0x09 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x29 {
+ /delete-property/ fsl,fman-10g-port;
+};
gsub(".*version ", "");
gsub("-.*", "");
split($1,a, ".");
+ if( length(a[3]) == "8" )
+ # a[3] is probably a date of format yyyymmdd used for release snapshots. We
+ # can assume it to be zero as it does not signify a new version as such.
+ a[3] = 0;
print a[1]*100000000 + a[2]*1000000 + a[3]*10000;
exit
}'
{
if (radix_enabled())
radix__tlb_flush(tlb);
+ else
+ hash__tlb_flush(tlb);
}
#ifdef CONFIG_SMP
return flags;
}
+static inline notrace unsigned long irq_soft_mask_andc_return(unsigned long mask)
+{
+ unsigned long flags = irq_soft_mask_return();
+
+ irq_soft_mask_set(flags & ~mask);
+
+ return flags;
+}
+
static inline unsigned long arch_local_save_flags(void)
{
return irq_soft_mask_return();
static inline unsigned long arch_local_irq_save(void)
{
- return irq_soft_mask_set_return(IRQS_DISABLED);
+ return irq_soft_mask_or_return(IRQS_DISABLED);
}
static inline bool arch_irqs_disabled_flags(unsigned long flags)
* is a different soft-masked interrupt pending that requires hard
* masking.
*/
-static inline bool should_hard_irq_enable(void)
+static inline bool should_hard_irq_enable(struct pt_regs *regs)
{
if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
- WARN_ON(irq_soft_mask_return() == IRQS_ENABLED);
+ WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+ WARN_ON(!(get_paca()->irq_happened & PACA_IRQ_HARD_DIS));
WARN_ON(mfmsr() & MSR_EE);
}
*
* TODO: Add test for 64e
*/
- if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !power_pmu_wants_prompt_pmi())
- return false;
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
+ if (!power_pmu_wants_prompt_pmi())
+ return false;
+ /*
+ * If PMIs are disabled then IRQs should be disabled as well,
+ * so we shouldn't see this condition, check for it just in
+ * case because we are about to enable PMIs.
+ */
+ if (WARN_ON_ONCE(regs->softe & IRQS_PMI_DISABLED))
+ return false;
+ }
if (get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK)
return false;
/*
* Do the hard enabling, only call this if should_hard_irq_enable is true.
+ * This allows PMI interrupts to profile irq handlers.
*/
static inline void do_hard_irq_enable(void)
{
- if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
- WARN_ON(irq_soft_mask_return() == IRQS_ENABLED);
- WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK);
- WARN_ON(mfmsr() & MSR_EE);
- }
/*
- * This allows PMI interrupts (and watchdog soft-NMIs) through.
- * There is no other reason to enable this way.
+ * Asynch interrupts come in with IRQS_ALL_DISABLED,
+ * PACA_IRQ_HARD_DIS, and MSR[EE]=0.
*/
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64))
+ irq_soft_mask_andc_return(IRQS_PMI_DISABLED);
get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS;
__hard_irq_enable();
}
return !(regs->msr & MSR_EE);
}
-static __always_inline bool should_hard_irq_enable(void)
+static __always_inline bool should_hard_irq_enable(struct pt_regs *regs)
{
return false;
}
* are inited.
*/
struct imc_pmu_ref {
- struct mutex lock;
+ spinlock_t lock;
unsigned int id;
int refc;
};
ppc_msgsync();
- if (should_hard_irq_enable())
+ if (should_hard_irq_enable(regs))
do_hard_irq_enable();
kvmppc_clear_host_ipi(smp_processor_id());
* SPE unavailable trap from kernel - print a message, but let
* the task use SPE in the kernel until it returns to user mode.
*/
-KernelSPE:
+SYM_FUNC_START_LOCAL(KernelSPE)
lwz r3,_MSR(r1)
oris r3,r3,MSR_SPE@h
stw r3,_MSR(r1) /* enable use of SPE after return */
#endif
.align 4,0
+SYM_FUNC_END(KernelSPE)
#endif /* CONFIG_SPE */
/*
*/
static notrace __always_inline bool prep_irq_for_enabled_exit(bool restartable)
{
+ bool must_hard_disable = (exit_must_hard_disable() || !restartable);
+
/* This must be done with RI=1 because tracing may touch vmaps */
trace_hardirqs_on();
- if (exit_must_hard_disable() || !restartable)
+ if (must_hard_disable)
__hard_EE_RI_disable();
#ifdef CONFIG_PPC64
/* This pattern matches prep_irq_for_idle */
if (unlikely(lazy_irq_pending_nocheck())) {
- if (exit_must_hard_disable() || !restartable) {
+ if (must_hard_disable) {
local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
__hard_RI_enable();
}
irq = static_call(ppc_get_irq)();
/* We can hard enable interrupts now to allow perf interrupts */
- if (should_hard_irq_enable())
+ if (should_hard_irq_enable(regs))
do_hard_irq_enable();
/* And finally process it */
}
/* Conditionally hard-enable interrupts. */
- if (should_hard_irq_enable()) {
+ if (should_hard_irq_enable(regs)) {
/*
* Ensure a positive value is written to the decrementer, or
* else some CPUs will continue to take decrementer exceptions.
#define BSS_FIRST_SECTIONS *(.bss.prominit)
#define EMITS_PT_NOTE
#define RO_EXCEPTION_TABLE_ALIGN 0
+#define RUNTIME_DISCARD_EXIT
#define SOFT_MASK_TABLE(align) \
. = ALIGN(align); \
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
- *(.glink .iplt .plt .rela* .comment)
+ *(.glink .iplt .plt)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+ *(.rela*)
+#endif
}
}
#include <asm/firmware.h>
#include <asm/kexec_ranges.h>
#include <asm/crashdump-ppc64.h>
+#include <asm/mmzone.h>
#include <asm/prom.h>
struct umem_info {
* linux,drconf-usable-memory properties. Get an approximate on the
* number of usable memory entries and use for FDT size estimation.
*/
- usm_entries = ((memblock_end_of_DRAM() / drmem_lmb_size()) +
- (2 * (resource_size(&crashk_res) / drmem_lmb_size())));
-
- extra_size = (unsigned int)(usm_entries * sizeof(u64));
+ if (drmem_lmb_size()) {
+ usm_entries = ((memory_hotplug_max() / drmem_lmb_size()) +
+ (2 * (resource_size(&crashk_res) / drmem_lmb_size())));
+ extra_size = (unsigned int)(usm_entries * sizeof(u64));
+ } else {
+ extra_size = 0;
+ }
/*
* Get the number of CPU nodes in the current DT. This allows to
static void kvmppc_fill_pt_regs(struct pt_regs *regs)
{
- ulong r1, ip, msr, lr;
+ ulong r1, msr, lr;
asm("mr %0, 1" : "=r"(r1));
asm("mflr %0" : "=r"(lr));
asm("mfmsr %0" : "=r"(msr));
- asm("bl 1f; 1: mflr %0" : "=r"(ip));
memset(regs, 0, sizeof(*regs));
regs->gpr[1] = r1;
- regs->nip = ip;
+ regs->nip = _THIS_IP_;
regs->msr = msr;
regs->link = lr;
}
void hpt_clear_stress(void);
static struct timer_list stress_hpt_timer;
-void stress_hpt_timer_fn(struct timer_list *timer)
+static void stress_hpt_timer_fn(struct timer_list *timer)
{
int next_cpu;
end = (unsigned long)__end_rodata;
radix__change_memory_range(start, end, _PAGE_WRITE);
+
+ for (start = PAGE_OFFSET; start < (unsigned long)_stext; start += PAGE_SIZE) {
+ end = start + PAGE_SIZE;
+ if (overlaps_interrupt_vector_text(start, end))
+ radix__change_memory_range(start, end, _PAGE_WRITE);
+ else
+ break;
+ }
}
void radix__mark_initmem_nx(void)
static unsigned long next_boundary(unsigned long addr, unsigned long end)
{
#ifdef CONFIG_STRICT_KERNEL_RWX
+ unsigned long stext_phys;
+
+ stext_phys = __pa_symbol(_stext);
+
+ // Relocatable kernel running at non-zero real address
+ if (stext_phys != 0) {
+ // The end of interrupts code at zero is a rodata boundary
+ unsigned long end_intr = __pa_symbol(__end_interrupts) - stext_phys;
+ if (addr < end_intr)
+ return end_intr;
+
+ // Start of relocated kernel text is a rodata boundary
+ if (addr < stext_phys)
+ return stext_phys;
+ }
+
if (addr < __pa_symbol(__srwx_boundary))
return __pa_symbol(__srwx_boundary);
#endif
#include <asm/cputhreads.h>
#include <asm/smp.h>
#include <linux/string.h>
+#include <linux/spinlock.h>
/* Nest IMC data structures and variables */
* core and trace-imc
*/
static struct imc_pmu_ref imc_global_refc = {
- .lock = __MUTEX_INITIALIZER(imc_global_refc.lock),
+ .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock),
.id = 0,
.refc = 0,
};
get_hard_smp_processor_id(cpu));
/*
* If this is the last cpu in this chip then, skip the reference
- * count mutex lock and make the reference count on this chip zero.
+ * count lock and make the reference count on this chip zero.
*/
ref = get_nest_pmu_ref(cpu);
if (!ref)
/*
* See if we need to disable the nest PMU.
* If no events are currently in use, then we have to take a
- * mutex to ensure that we don't race with another task doing
+ * lock to ensure that we don't race with another task doing
* enable or disable the nest counters.
*/
ref = get_nest_pmu_ref(event->cpu);
if (!ref)
return;
- /* Take the mutex lock for this node and then decrement the reference count */
- mutex_lock(&ref->lock);
+ /* Take the lock for this node and then decrement the reference count */
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
/*
* The scenario where this is true is, when perf session is
* an OPAL call to disable the engine in that node.
*
*/
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return;
}
ref->refc--;
rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id);
return;
}
WARN(1, "nest-imc: Invalid event reference count\n");
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
}
static int nest_imc_event_init(struct perf_event *event)
/*
* Get the imc_pmu_ref struct for this node.
- * Take the mutex lock and then increment the count of nest pmu events
- * inited.
+ * Take the lock and then increment the count of nest pmu events inited.
*/
ref = get_nest_pmu_ref(event->cpu);
if (!ref)
return -EINVAL;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("nest-imc: Unable to start the counters for node %d\n",
node_id);
return rc;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
event->destroy = nest_imc_counters_release;
return 0;
return -ENOMEM;
mem_info->vbase = page_address(page);
- /* Init the mutex */
core_imc_refc[core_id].id = core_id;
- mutex_init(&core_imc_refc[core_id].lock);
+ spin_lock_init(&core_imc_refc[core_id].lock);
rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE,
__pa((void *)mem_info->vbase),
perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu);
} else {
/*
- * If this is the last cpu in this core then, skip taking refernce
- * count mutex lock for this core and directly zero "refc" for
- * this core.
+ * If this is the last cpu in this core then skip taking reference
+ * count lock for this core and directly zero "refc" for this core.
*/
opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(cpu));
* last cpu in this core and core-imc event running
* in this cpu.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_CORE)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
}
return 0;
}
static void reset_global_refc(struct perf_event *event)
{
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
imc_global_refc.refc--;
/*
imc_global_refc.refc = 0;
imc_global_refc.id = 0;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
}
static void core_imc_counters_release(struct perf_event *event)
/*
* See if we need to disable the IMC PMU.
* If no events are currently in use, then we have to take a
- * mutex to ensure that we don't race with another task doing
+ * lock to ensure that we don't race with another task doing
* enable or disable the core counters.
*/
core_id = event->cpu / threads_per_core;
- /* Take the mutex lock and decrement the refernce count for this core */
+ /* Take the lock and decrement the refernce count for this core */
ref = &core_imc_refc[core_id];
if (!ref)
return;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
/*
* The scenario where this is true is, when perf session is
* an OPAL call to disable the engine in that core.
*
*/
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return;
}
ref->refc--;
rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("IMC: Unable to stop the counters for core %d\n", core_id);
return;
}
WARN(1, "core-imc: Invalid event reference count\n");
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
reset_global_refc(event);
}
if ((!pcmi->vbase))
return -ENODEV;
- /* Get the core_imc mutex for this core */
ref = &core_imc_refc[core_id];
if (!ref)
return -EINVAL;
/*
* Core pmu units are enabled only when it is used.
* See if this is triggered for the first time.
- * If yes, take the mutex lock and enable the core counters.
+ * If yes, take the lock and enable the core counters.
* If not, just increment the count in core_imc_refc struct.
*/
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("core-imc: Unable to start the counters for core %d\n",
core_id);
return rc;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
/*
* Since the system can run either in accumulation or trace-mode
* to know whether any other trace/thread imc
* events are running.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) {
/*
* No other trace/thread imc events are running in
imc_global_refc.id = IMC_DOMAIN_CORE;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK);
event->destroy = core_imc_counters_release;
mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
/* Reduce the refc if thread-imc event running on this cpu */
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_THREAD)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return 0;
}
if (!target)
return -EINVAL;
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
/*
* Check if any other trace/core imc events are running in the
* system, if not set the global id to thread-imc.
imc_global_refc.id = IMC_DOMAIN_THREAD;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->pmu->task_ctx_nr = perf_sw_context;
event->destroy = reset_global_refc;
/*
* imc pmus are enabled only when it is used.
* See if this is triggered for the first time.
- * If yes, take the mutex lock and enable the counters.
+ * If yes, take the lock and enable the counters.
* If not, just increment the count in ref count struct.
*/
ref = &core_imc_refc[core_id];
if (!ref)
return -EINVAL;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("thread-imc: Unable to start the counter\
for core %d\n", core_id);
return -EINVAL;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return 0;
}
return;
}
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
ref->refc--;
if (ref->refc == 0) {
if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("thread-imc: Unable to stop the counters\
for core %d\n", core_id);
return;
} else if (ref->refc < 0) {
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
/* Set bit 0 of LDBAR to zero, to stop posting updates to memory */
mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
}
}
- /* Init the mutex, if not already */
trace_imc_refc[core_id].id = core_id;
- mutex_init(&trace_imc_refc[core_id].lock);
+ spin_lock_init(&trace_imc_refc[core_id].lock);
mtspr(SPRN_LDBAR, 0);
return 0;
* Reduce the refc if any trace-imc event running
* on this cpu.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_TRACE)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return 0;
}
}
mtspr(SPRN_LDBAR, ldbar_value);
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
return -EINVAL;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return 0;
}
return;
}
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
ref->refc--;
if (ref->refc == 0) {
if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id);
return;
}
} else if (ref->refc < 0) {
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
trace_imc_event_stop(event, flags);
}
* no other thread is running any core/thread imc
* events
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) {
/*
* No core/thread imc events are running in the
imc_global_refc.id = IMC_DOMAIN_TRACE;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->hw.idx = -1;
i = 0;
for_each_node(nid) {
/*
- * Mutex lock to avoid races while tracking the number of
+ * Take the lock to avoid races while tracking the number of
* sessions using the chip's nest pmu units.
*/
- mutex_init(&nest_imc_refc[i].lock);
+ spin_lock_init(&nest_imc_refc[i].lock);
/*
* Loop to init the "id" with the node_id. Variable "i" initialized to
KBUILD_CFLAGS += -fno-omit-frame-pointer
endif
+# Avoid generating .eh_frame sections.
+KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
+
KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
bus-range = <0x0 0xff>;
ranges = <0x81000000 0x0 0x60080000 0x0 0x60080000 0x0 0x10000>, /* I/O */
<0x82000000 0x0 0x60090000 0x0 0x60090000 0x0 0xff70000>, /* mem */
- <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x1000000>, /* mem */
+ <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x10000000>, /* mem */
<0xc3000000 0x20 0x00000000 0x20 0x00000000 0x20 0x00000000>; /* mem prefetchable */
num-lanes = <0x8>;
interrupts = <56>, <57>, <58>, <59>, <60>, <61>, <62>, <63>, <64>;
.macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \
new_c_2, vendor_id_2, errata_id_2, enable_2
- ALTERNATIVE_CFG \old_c, \new_c_1, \vendor_id_1, \errata_id_1, \enable_1
+ ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \errata_id_1, \enable_1
ALT_NEW_CONTENT \vendor_id_2, \errata_id_2, \enable_2, \new_c_2
.endm
*/
enum riscv_isa_ext_key {
RISCV_ISA_EXT_KEY_FPU, /* For 'F' and 'D' */
- RISCV_ISA_EXT_KEY_ZIHINTPAUSE,
RISCV_ISA_EXT_KEY_SVINVAL,
RISCV_ISA_EXT_KEY_MAX,
};
return RISCV_ISA_EXT_KEY_FPU;
case RISCV_ISA_EXT_d:
return RISCV_ISA_EXT_KEY_FPU;
- case RISCV_ISA_EXT_ZIHINTPAUSE:
- return RISCV_ISA_EXT_KEY_ZIHINTPAUSE;
case RISCV_ISA_EXT_SVINVAL:
return RISCV_ISA_EXT_KEY_SVINVAL;
default:
page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd);
return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd)));
}
+
+#define pmdp_collapse_flush pmdp_collapse_flush
+extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
might_fault(); \
access_ok(__p, sizeof(*__p)) ? \
__get_user((x), __p) : \
- ((x) = 0, -EFAULT); \
+ ((x) = (__force __typeof__(x))0, -EFAULT); \
})
#define __put_user_asm(insn, x, ptr, err) \
#ifndef __ASSEMBLY__
-#include <linux/jump_label.h>
#include <asm/barrier.h>
-#include <asm/hwcap.h>
static inline void cpu_relax(void)
{
- if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) {
#ifdef __riscv_muldiv
- int dummy;
- /* In lieu of a halt instruction, induce a long-latency stall. */
- __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
+ int dummy;
+ /* In lieu of a halt instruction, induce a long-latency stall. */
+ __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
#endif
- } else {
- /*
- * Reduce instruction retirement.
- * This assumes the PC changes.
- */
-#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
- __asm__ __volatile__ ("pause");
+
+#ifdef __riscv_zihintpause
+ /*
+ * Reduce instruction retirement.
+ * This assumes the PC changes.
+ */
+ __asm__ __volatile__ ("pause");
#else
- /* Encoding of the pause instruction */
- __asm__ __volatile__ (".4byte 0x100000F");
+ /* Encoding of the pause instruction */
+ __asm__ __volatile__ (".4byte 0x100000F");
#endif
- }
barrier();
}
call soc_early_init
tail start_kernel
-#if CONFIG_RISCV_BOOT_SPINWAIT
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
.Lsecondary_start:
/* Set trap vector to spin forever to help debug */
la a3, .Lsecondary_park
post_kprobe_handler(p, kcb, regs);
}
+static bool __kprobes arch_check_kprobe(struct kprobe *p)
+{
+ unsigned long tmp = (unsigned long)p->addr - p->offset;
+ unsigned long addr = (unsigned long)p->addr;
+
+ while (tmp <= addr) {
+ if (tmp == addr)
+ return true;
+
+ tmp += GET_INSN_LENGTH(*(u16 *)tmp);
+ }
+
+ return false;
+}
+
int __kprobes arch_prepare_kprobe(struct kprobe *p)
{
- unsigned long probe_addr = (unsigned long)p->addr;
+ u16 *insn = (u16 *)p->addr;
+
+ if ((unsigned long)insn & 0x1)
+ return -EILSEQ;
- if (probe_addr & 0x1)
+ if (!arch_check_kprobe(p))
return -EILSEQ;
/* copy instruction */
- p->opcode = *p->addr;
+ p->opcode = (kprobe_opcode_t)(*insn++);
+ if (GET_INSN_LENGTH(p->opcode) == 4)
+ p->opcode |= (kprobe_opcode_t)(*insn) << 16;
/* decode instruction */
switch (riscv_probe_decode_insn(p->addr, &p->ainsn.api)) {
u32 rd_index = (opcode >> 7) & 0x1f;
u32 rs1_index = (opcode >> 15) & 0x1f;
- ret = rv_insn_reg_set_val(regs, rd_index, addr + 4);
+ ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr);
if (!ret)
return ret;
- ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr);
+ ret = rv_insn_reg_set_val(regs, rd_index, addr + 4);
if (!ret)
return ret;
} while (0)
__RISCV_INSN_FUNCS(c_j, 0xe003, 0xa001);
-__RISCV_INSN_FUNCS(c_jr, 0xf007, 0x8002);
+__RISCV_INSN_FUNCS(c_jr, 0xf07f, 0x8002);
__RISCV_INSN_FUNCS(c_jal, 0xe003, 0x2001);
-__RISCV_INSN_FUNCS(c_jalr, 0xf007, 0x9002);
+__RISCV_INSN_FUNCS(c_jalr, 0xf07f, 0x9002);
__RISCV_INSN_FUNCS(c_beqz, 0xe003, 0xc001);
__RISCV_INSN_FUNCS(c_bnez, 0xe003, 0xe001);
__RISCV_INSN_FUNCS(c_ebreak, 0xffff, 0x9002);
void __init smp_prepare_boot_cpu(void)
{
- init_cpu_topology();
}
void __init smp_prepare_cpus(unsigned int max_cpus)
int ret;
unsigned int curr_cpuid;
+ init_cpu_topology();
+
curr_cpuid = smp_processor_id();
store_cpu_topology(curr_cpuid);
numa_store_cpu_info(curr_cpuid);
fp = (unsigned long)__builtin_frame_address(0);
sp = current_stack_pointer;
pc = (unsigned long)walk_stackframe;
+ level = -1;
} else {
/* task blocked in __switch_to */
fp = task->thread.s[0];
unsigned long low, high;
struct stackframe *frame;
- if (unlikely(!__kernel_text_address(pc) || (level++ >= 1 && !fn(arg, pc))))
+ if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc))))
break;
/* Validate frame pointer */
if (PageHuge(page))
page = compound_head(page);
- if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+ if (!test_bit(PG_dcache_clean, &page->flags)) {
flush_icache_all();
+ set_bit(PG_dcache_clean, &page->flags);
+ }
}
#endif /* CONFIG_MMU */
}
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp)
+{
+ pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
+
+ VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+ VM_BUG_ON(pmd_trans_huge(*pmdp));
+ /*
+ * When leaf PTE entries (regular pages) are collapsed into a leaf
+ * PMD entry (huge page), a valid non-leaf PTE is converted into a
+ * valid leaf PTE at the level 1 page table. Since the sfence.vma
+ * forms that specify an address only apply to leaf PTEs, we need a
+ * global flush here. collapse_huge_page() assumes these flushes are
+ * eager, so just do the fence here.
+ */
+ flush_tlb_mm(vma->vm_mm);
+ return pmd;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#define memmove memmove
#define memzero(s, n) memset((s), 0, (n))
-#ifdef CONFIG_KERNEL_BZIP2
+#if defined(CONFIG_KERNEL_BZIP2)
#define BOOT_HEAP_SIZE 0x400000
-#elif CONFIG_KERNEL_ZSTD
+#elif defined(CONFIG_KERNEL_ZSTD)
#define BOOT_HEAP_SIZE 0x30000
#else
#define BOOT_HEAP_SIZE 0x10000
void *output = (void *)decompress_offset;
__decompress(_compressed_start, _compressed_end - _compressed_start,
- NULL, NULL, output, 0, NULL, error);
+ NULL, NULL, output, vmlinux.image_size, NULL, error);
return output;
}
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_NAT=m
-CONFIG_NFT_OBJREF=m
CONFIG_NFT_REJECT=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
+# CONFIG_LEGACY_TIOCSTI is not set
CONFIG_VIRTIO_CONSOLE=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_ECRYPT_FS=m
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
+CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y
CONFIG_SQUASHFS_XATTR=y
CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_LZO=y
CONFIG_SECURITY_LANDLOCK=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_INTEGRITY_PLATFORM_KEYRING=y
CONFIG_IMA=y
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_PKEY=m
CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_SYSTEM_BLACKLIST_KEYRING=y
CONFIG_CORDIC=m
CONFIG_CRYPTO_LIB_CURVE25519=m
CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_BPF_KPROBE_OVERRIDE=y
CONFIG_HIST_TRIGGERS=y
CONFIG_FTRACE_STARTUP_TEST=y
# CONFIG_EVENT_TRACE_STARTUP_TEST is not set
CONFIG_FAIL_IO_TIMEOUT=y
CONFIG_FAIL_FUTEX=y
CONFIG_FAULT_INJECTION_DEBUG_FS=y
-CONFIG_FAIL_FUNCTION=y
CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
CONFIG_LKDTM=m
CONFIG_TEST_MIN_HEAP=y
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_NAT=m
-CONFIG_NFT_OBJREF=m
CONFIG_NFT_REJECT=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
+# CONFIG_LEGACY_TIOCSTI is not set
CONFIG_VIRTIO_CONSOLE=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_ECRYPT_FS=m
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
+CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y
CONFIG_SQUASHFS_XATTR=y
CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_LZO=y
CONFIG_SECURITY_LANDLOCK=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_INTEGRITY_PLATFORM_KEYRING=y
CONFIG_IMA=y
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_PKEY=m
CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_SYSTEM_BLACKLIST_KEYRING=y
CONFIG_CORDIC=m
CONFIG_PRIME_NUMBERS=m
CONFIG_CRYPTO_LIB_CURVE25519=m
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_BPF_KPROBE_OVERRIDE=y
CONFIG_HIST_TRIGGERS=y
CONFIG_SAMPLES=y
CONFIG_SAMPLE_TRACE_PRINTK=m
# CONFIG_COMPAT is not set
CONFIG_NR_CPUS=2
CONFIG_HZ_100=y
-# CONFIG_RELOCATABLE is not set
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
CONFIG_CRASH_DUMP=y
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
+# CONFIG_LEGACY_TIOCSTI is not set
# CONFIG_HVC_IUCV is not set
# CONFIG_HW_RANDOM_S390 is not set
# CONFIG_HMC_DRV is not set
struct hws_diag_entry diag; /* Diagnostic-sampling data entry */
} __packed;
-struct hws_trailer_entry {
- union {
- struct {
- unsigned int f:1; /* 0 - Block Full Indicator */
- unsigned int a:1; /* 1 - Alert request control */
- unsigned int t:1; /* 2 - Timestamp format */
- unsigned int :29; /* 3 - 31: Reserved */
- unsigned int bsdes:16; /* 32-47: size of basic SDE */
- unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */
- };
- unsigned long long flags; /* 0 - 63: All indicators */
+union hws_trailer_header {
+ struct {
+ unsigned int f:1; /* 0 - Block Full Indicator */
+ unsigned int a:1; /* 1 - Alert request control */
+ unsigned int t:1; /* 2 - Timestamp format */
+ unsigned int :29; /* 3 - 31: Reserved */
+ unsigned int bsdes:16; /* 32-47: size of basic SDE */
+ unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */
+ unsigned long long overflow; /* 64 - Overflow Count */
};
- unsigned long long overflow; /* 64 - sample Overflow count */
+ __uint128_t val;
+};
+
+struct hws_trailer_entry {
+ union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count */
unsigned char timestamp[16]; /* 16 - 31 timestamp */
unsigned long long reserved1; /* 32 -Reserved */
unsigned long long reserved2; /* */
return USEC_PER_SEC * qsi->cpu_speed / rate;
}
-#define SDB_TE_ALERT_REQ_MASK 0x4000000000000000UL
-#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL
-
/* Return TOD timestamp contained in an trailer entry */
static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
{
/* TOD in STCKE format */
- if (te->t)
+ if (te->header.t)
return *((unsigned long long *) &te->timestamp[1]);
/* TOD in STCK format */
*
* Copyright IBM Corp. 1999, 2020
*/
-#ifndef DEBUG_H
-#define DEBUG_H
+#ifndef _ASM_S390_DEBUG_H
+#define _ASM_S390_DEBUG_H
#include <linux/string.h>
#include <linux/spinlock.h>
#endif /* MODULE */
-#endif /* DEBUG_H */
+#endif /* _ASM_S390_DEBUG_H */
pcp_op_T__ *ptr__; \
preempt_disable_notrace(); \
ptr__ = raw_cpu_ptr(&(pcp)); \
- prev__ = *ptr__; \
+ prev__ = READ_ONCE(*ptr__); \
do { \
old__ = prev__; \
new__ = old__ op (val); \
data->memsz = ALIGN(data->memsz, PAGE_SIZE);
buf.mem = data->memsz;
- if (image->type == KEXEC_TYPE_CRASH)
- buf.mem += crashk_res.start;
ptr = (void *)ipl_cert_list_addr;
end = ptr + ipl_cert_list_size;
data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
*lc_ipl_parmblock_ptr = (__u32)buf.mem;
+ if (image->type == KEXEC_TYPE_CRASH)
+ buf.mem += crashk_res.start;
+
ret = kexec_add_buffer(&buf);
out:
return ret;
static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags)
{
- unsigned long sdb, *trailer;
+ struct hws_trailer_entry *te;
+ unsigned long sdb;
/* Allocate and initialize sample-data-block */
sdb = get_zeroed_page(gfp_flags);
if (!sdb)
return -ENOMEM;
- trailer = trailer_entry_ptr(sdb);
- *trailer = SDB_TE_ALERT_REQ_MASK;
+ te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb);
+ te->header.a = 1;
/* Link SDB into the sample-data-block-table */
*sdbt = sdb;
"%s: Found unknown"
" sampling data entry: te->f %i"
" basic.def %#4x (%p)\n", __func__,
- te->f, sample->def, sample);
+ te->header.f, sample->def, sample);
/* Sample slot is not yet written or other record.
*
* This condition can occur if the buffer was reused
* that are not full. Stop processing if the first
* invalid format was detected.
*/
- if (!te->f)
+ if (!te->header.f)
break;
}
}
}
+static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new)
+{
+ asm volatile(
+ " cdsg %[old],%[new],%[ptr]\n"
+ : [old] "+d" (old), [ptr] "+QS" (*ptr)
+ : [new] "d" (new)
+ : "memory", "cc");
+ return old;
+}
+
/* hw_perf_event_update() - Process sampling buffer
* @event: The perf event
* @flush_all: Flag to also flush partially filled sample-data-blocks
*/
static void hw_perf_event_update(struct perf_event *event, int flush_all)
{
+ unsigned long long event_overflow, sampl_overflow, num_sdb;
+ union hws_trailer_header old, prev, new;
struct hw_perf_event *hwc = &event->hw;
struct hws_trailer_entry *te;
unsigned long *sdbt;
- unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags;
int done;
/*
te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
/* Leave loop if no more work to do (block full indicator) */
- if (!te->f) {
+ if (!te->header.f) {
done = 1;
if (!flush_all)
break;
}
/* Check the sample overflow count */
- if (te->overflow)
+ if (te->header.overflow)
/* Account sample overflows and, if a particular limit
* is reached, extend the sampling buffer.
* For details, see sfb_account_overflows().
*/
- sampl_overflow += te->overflow;
+ sampl_overflow += te->header.overflow;
/* Timestamps are valid for full sample-data-blocks only */
debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx "
"overflow %llu timestamp %#llx\n",
- __func__, (unsigned long)sdbt, te->overflow,
- (te->f) ? trailer_timestamp(te) : 0ULL);
+ __func__, (unsigned long)sdbt, te->header.overflow,
+ (te->header.f) ? trailer_timestamp(te) : 0ULL);
/* Collect all samples from a single sample-data-block and
* flag if an (perf) event overflow happened. If so, the PMU
num_sdb++;
/* Reset trailer (using compare-double-and-swap) */
+ /* READ_ONCE() 16 byte header */
+ prev.val = __cdsg(&te->header.val, 0, 0);
do {
- te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
- te_flags |= SDB_TE_ALERT_REQ_MASK;
- } while (!cmpxchg_double(&te->flags, &te->overflow,
- te->flags, te->overflow,
- te_flags, 0ULL));
+ old.val = prev.val;
+ new.val = prev.val;
+ new.f = 0;
+ new.a = 1;
+ new.overflow = 0;
+ prev.val = __cdsg(&te->header.val, old.val, new.val);
+ } while (prev.val != old.val);
/* Advance to next sample-data-block */
sdbt++;
range_scan = AUX_SDB_NUM_ALERT(aux);
for (i = 0, idx = aux->head; i < range_scan; i++, idx++) {
te = aux_sdb_trailer(aux, idx);
- if (!(te->flags & SDB_TE_BUFFER_FULL_MASK))
+ if (!te->header.f)
break;
}
/* i is num of SDBs which are full */
/* Remove alert indicators in the buffer */
te = aux_sdb_trailer(aux, aux->alert_mark);
- te->flags &= ~SDB_TE_ALERT_REQ_MASK;
+ te->header.a = 0;
debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n",
__func__, i, range_scan, aux->head);
idx = aux->empty_mark + 1;
for (i = 0; i < range_scan; i++, idx++) {
te = aux_sdb_trailer(aux, idx);
- te->flags &= ~(SDB_TE_BUFFER_FULL_MASK |
- SDB_TE_ALERT_REQ_MASK);
- te->overflow = 0;
+ te->header.f = 0;
+ te->header.a = 0;
+ te->header.overflow = 0;
}
/* Save the position of empty SDBs */
aux->empty_mark = aux->head + range - 1;
/* Set alert indicator */
aux->alert_mark = aux->head + range/2 - 1;
te = aux_sdb_trailer(aux, aux->alert_mark);
- te->flags = te->flags | SDB_TE_ALERT_REQ_MASK;
+ te->header.a = 1;
/* Reset hardware buffer head */
head = AUX_SDB_INDEX(aux, aux->head);
static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
unsigned long long *overflow)
{
- unsigned long long orig_overflow, orig_flags, new_flags;
+ union hws_trailer_header old, prev, new;
struct hws_trailer_entry *te;
te = aux_sdb_trailer(aux, alert_index);
+ /* READ_ONCE() 16 byte header */
+ prev.val = __cdsg(&te->header.val, 0, 0);
do {
- orig_flags = te->flags;
- *overflow = orig_overflow = te->overflow;
- if (orig_flags & SDB_TE_BUFFER_FULL_MASK) {
+ old.val = prev.val;
+ new.val = prev.val;
+ *overflow = old.overflow;
+ if (old.f) {
/*
* SDB is already set by hardware.
* Abort and try to set somewhere
*/
return false;
}
- new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK;
- } while (!cmpxchg_double(&te->flags, &te->overflow,
- orig_flags, orig_overflow,
- new_flags, 0ULL));
+ new.a = 1;
+ new.overflow = 0;
+ prev.val = __cdsg(&te->header.val, old.val, new.val);
+ } while (prev.val != old.val);
return true;
}
static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range,
unsigned long long *overflow)
{
- unsigned long long orig_overflow, orig_flags, new_flags;
unsigned long i, range_scan, idx, idx_old;
+ union hws_trailer_header old, prev, new;
+ unsigned long long orig_overflow;
struct hws_trailer_entry *te;
debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld "
idx_old = idx = aux->empty_mark + 1;
for (i = 0; i < range_scan; i++, idx++) {
te = aux_sdb_trailer(aux, idx);
+ /* READ_ONCE() 16 byte header */
+ prev.val = __cdsg(&te->header.val, 0, 0);
do {
- orig_flags = te->flags;
- orig_overflow = te->overflow;
- new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK;
+ old.val = prev.val;
+ new.val = prev.val;
+ orig_overflow = old.overflow;
+ new.f = 0;
+ new.overflow = 0;
if (idx == aux->alert_mark)
- new_flags |= SDB_TE_ALERT_REQ_MASK;
+ new.a = 1;
else
- new_flags &= ~SDB_TE_ALERT_REQ_MASK;
- } while (!cmpxchg_double(&te->flags, &te->overflow,
- orig_flags, orig_overflow,
- new_flags, 0ULL));
+ new.a = 0;
+ prev.val = __cdsg(&te->header.val, old.val, new.val);
+ } while (prev.val != old.val);
*overflow += orig_overflow;
}
{
struct lowcore *abs_lc;
unsigned long flags;
+ int i;
__ctl_clear_bit(0, 28);
S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT;
abs_lc = get_abs_lowcore(&flags);
abs_lc->restart_flags = RESTART_FLAG_CTLREGS;
abs_lc->program_new_psw = S390_lowcore.program_new_psw;
- memcpy(abs_lc->cregs_save_area, S390_lowcore.cregs_save_area,
- sizeof(abs_lc->cregs_save_area));
+ for (i = 0; i < 16; i++)
+ abs_lc->cregs_save_area[i] = S390_lowcore.cregs_save_area[i];
put_abs_lowcore(abs_lc, flags);
}
/* Handle ro_after_init data on our own. */
#define RO_AFTER_INIT_DATA
+#define RUNTIME_DISCARD_EXIT
+
#define EMITS_PT_NOTE
#include <asm-generic/vmlinux.lds.h>
_end_amode31_refs = .;
}
+ . = ALIGN(PAGE_SIZE);
_edata = .; /* End of data section */
/* will be freed after init */
BSS_SECTION(PAGE_SIZE, 4 * PAGE_SIZE, PAGE_SIZE)
+ . = ALIGN(PAGE_SIZE);
_end = . ;
/*
struct esca_block *sca = vcpu->kvm->arch.sca;
union esca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+ union esca_sigp_ctrl new_val = {0}, old_val;
+ old_val = READ_ONCE(*sigp_ctrl);
new_val.scn = src_id;
new_val.c = 1;
old_val.c = 0;
struct bsca_block *sca = vcpu->kvm->arch.sca;
union bsca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+ union bsca_sigp_ctrl new_val = {0}, old_val;
+ old_val = READ_ONCE(*sigp_ctrl);
new_val.scn = src_id;
new_val.c = 1;
old_val.c = 0;
struct esca_block *sca = vcpu->kvm->arch.sca;
union esca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union esca_sigp_ctrl old = *sigp_ctrl;
+ union esca_sigp_ctrl old;
+ old = READ_ONCE(*sigp_ctrl);
expect = old.value;
rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
} else {
struct bsca_block *sca = vcpu->kvm->arch.sca;
union bsca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union bsca_sigp_ctrl old = *sigp_ctrl;
+ union bsca_sigp_ctrl old;
+ old = READ_ONCE(*sigp_ctrl);
expect = old.value;
rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
}
#define pmd_ERROR(e) \
printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
-typedef struct {
+typedef union {
struct {
unsigned long pmd_low;
unsigned long pmd_high;
* Written by Niibe Yutaka and Paul Mundt
*/
OUTPUT_ARCH(sh)
+#define RUNTIME_DISCARD_EXIT
#include <asm/thread_info.h>
#include <asm/cache.h>
#include <asm/vmlinux.lds.h>
ifdef CONFIG_CC_IS_GCC
RETPOLINE_CFLAGS := $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
-RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix)
RETPOLINE_VDSO_CFLAGS := $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register)
endif
ifdef CONFIG_CC_IS_CLANG
RETPOLINE_CFLAGS := -mretpoline-external-thunk
RETPOLINE_VDSO_CFLAGS := -mretpoline
endif
+RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix)
ifdef CONFIG_RETHUNK
RETHUNK_CFLAGS := -mfunction-return=thunk-extern
movw %dx, %si
movw %sp, %di
movw $11, %cx
- rep; movsd
+ rep; movsl
/* Pop full state from the stack */
popal
jz 4f
movw %sp, %si
movw $11, %cx
- rep; movsd
+ rep; movsl
4: addw $44, %sp
/* Restore state and return */
/* Load the new page-table. */
write_cr3(top_level_pgt);
+
+ /*
+ * Now that the required page table mappings are established and a
+ * GHCB can be used, check for SNP guest/HV feature compatibility.
+ */
+ snp_check_features();
}
static pte_t *split_large_pmd(struct x86_mapping_info *info,
#ifdef CONFIG_AMD_MEM_ENCRYPT
void sev_enable(struct boot_params *bp);
+void snp_check_features(void);
void sev_es_shutdown_ghcb(void);
extern bool sev_es_check_ghcb_fault(unsigned long address);
void snp_set_page_private(unsigned long paddr);
if (bp)
bp->cc_blob_address = 0;
}
+static inline void snp_check_features(void) { }
static inline void sev_es_shutdown_ghcb(void) { }
static inline bool sev_es_check_ghcb_fault(unsigned long address)
{
error("Can't unmap GHCB page");
}
+static void __noreturn sev_es_ghcb_terminate(struct ghcb *ghcb, unsigned int set,
+ unsigned int reason, u64 exit_info_2)
+{
+ u64 exit_info_1 = SVM_VMGEXIT_TERM_REASON(set, reason);
+
+ vc_ghcb_invalidate(ghcb);
+ ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_TERM_REQUEST);
+ ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
+ ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
+
+ sev_es_wr_ghcb_msr(__pa(ghcb));
+ VMGEXIT();
+
+ while (true)
+ asm volatile("hlt\n" : : : "memory");
+}
+
bool sev_es_check_ghcb_fault(unsigned long address)
{
/* Check whether the fault was on the GHCB page */
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
}
+/*
+ * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need
+ * guest side implementation for proper functioning of the guest. If any
+ * of these features are enabled in the hypervisor but are lacking guest
+ * side implementation, the behavior of the guest will be undefined. The
+ * guest could fail in non-obvious way making it difficult to debug.
+ *
+ * As the behavior of reserved feature bits is unknown to be on the
+ * safe side add them to the required features mask.
+ */
+#define SNP_FEATURES_IMPL_REQ (MSR_AMD64_SNP_VTOM | \
+ MSR_AMD64_SNP_REFLECT_VC | \
+ MSR_AMD64_SNP_RESTRICTED_INJ | \
+ MSR_AMD64_SNP_ALT_INJ | \
+ MSR_AMD64_SNP_DEBUG_SWAP | \
+ MSR_AMD64_SNP_VMPL_SSS | \
+ MSR_AMD64_SNP_SECURE_TSC | \
+ MSR_AMD64_SNP_VMGEXIT_PARAM | \
+ MSR_AMD64_SNP_VMSA_REG_PROTECTION | \
+ MSR_AMD64_SNP_RESERVED_BIT13 | \
+ MSR_AMD64_SNP_RESERVED_BIT15 | \
+ MSR_AMD64_SNP_RESERVED_MASK)
+
+/*
+ * SNP_FEATURES_PRESENT is the mask of SNP features that are implemented
+ * by the guest kernel. As and when a new feature is implemented in the
+ * guest kernel, a corresponding bit should be added to the mask.
+ */
+#define SNP_FEATURES_PRESENT (0)
+
+void snp_check_features(void)
+{
+ u64 unsupported;
+
+ if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+ return;
+
+ /*
+ * Terminate the boot if hypervisor has enabled any feature lacking
+ * guest side implementation. Pass on the unsupported features mask through
+ * EXIT_INFO_2 of the GHCB protocol so that those features can be reported
+ * as part of the guest boot failure.
+ */
+ unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT;
+ if (unsupported) {
+ if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb()))
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
+ sev_es_ghcb_terminate(boot_ghcb, SEV_TERM_SET_GEN,
+ GHCB_SNP_UNSUPPORTED, unsupported);
+ }
+}
+
void sev_enable(struct boot_params *bp)
{
unsigned int eax, ebx, ecx, edx;
{
unsigned long *reg, val, vaddr;
char buffer[MAX_INSN_SIZE];
+ enum insn_mmio_type mmio;
struct insn insn = {};
- enum mmio_type mmio;
int size, extend_size;
u8 extend_val = 0;
return -EINVAL;
mmio = insn_decode_mmio(&insn, &size);
- if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
+ if (WARN_ON_ONCE(mmio == INSN_MMIO_DECODE_FAILED))
return -EINVAL;
- if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+ if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
reg = insn_get_modrm_reg_ptr(&insn, regs);
if (!reg)
return -EINVAL;
/* Handle writes first */
switch (mmio) {
- case MMIO_WRITE:
+ case INSN_MMIO_WRITE:
memcpy(&val, reg, size);
if (!mmio_write(size, ve->gpa, val))
return -EIO;
return insn.length;
- case MMIO_WRITE_IMM:
+ case INSN_MMIO_WRITE_IMM:
val = insn.immediate.value;
if (!mmio_write(size, ve->gpa, val))
return -EIO;
return insn.length;
- case MMIO_READ:
- case MMIO_READ_ZERO_EXTEND:
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ:
+ case INSN_MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
/* Reads are handled below */
break;
- case MMIO_MOVS:
- case MMIO_DECODE_FAILED:
+ case INSN_MMIO_MOVS:
+ case INSN_MMIO_DECODE_FAILED:
/*
* MMIO was accessed with an instruction that could not be
* decoded or handled properly. It was likely not using io.h
return -EIO;
switch (mmio) {
- case MMIO_READ:
+ case INSN_MMIO_READ:
/* Zero-extend for 32-bit operation */
extend_size = size == 4 ? sizeof(*reg) : 0;
break;
- case MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_ZERO_EXTEND:
/* Zero extend based on operand size */
extend_size = insn.opnd_bytes;
break;
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
/* Sign extend based on operand size */
extend_size = insn.opnd_bytes;
if (size == 1 && val & BIT(7))
* numbered counter following it.
*/
for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
- even_ctr_mask |= 1 << i;
+ even_ctr_mask |= BIT_ULL(i);
pair_constraint = (struct event_constraint)
__EVENT_CONSTRAINT(0, even_ctr_mask, 0,
void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
{
- if (!x86_pmu_initialized()) {
+ /* This API doesn't currently support enumerating hybrid PMUs. */
+ if (WARN_ON_ONCE(cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) ||
+ !x86_pmu_initialized()) {
memset(cap, 0, sizeof(*cap));
return;
}
- cap->version = x86_pmu.version;
/*
- * KVM doesn't support the hybrid PMU yet.
- * Return the common value in global x86_pmu,
- * which available for all cores.
+ * Note, hybrid CPU models get tracked as having hybrid PMUs even when
+ * all E-cores are disabled via BIOS. When E-cores are disabled, the
+ * base PMU holds the correct number of counters for P-cores.
*/
+ cap->version = x86_pmu.version;
cap->num_counters_gp = x86_pmu.num_counters;
cap->num_counters_fixed = x86_pmu.num_counters_fixed;
cap->bit_width_gp = x86_pmu.cntval_bits;
break;
case INTEL_FAM6_SAPPHIRERAPIDS_X:
+ case INTEL_FAM6_EMERALDRAPIDS_X:
pmem = true;
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids));
* MSR_CORE_C1_RES: CORE C1 Residency Counter
* perf code: 0x00
* Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
+ * MTL
* Scope: Core (each processor core has a MSR)
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- * TGL,TNT,RKL,ADL,RPL,SPR
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
* Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- * ICL,TGL,RKL,ADL,RPL
+ * ICL,TGL,RKL,ADL,RPL,MTL
* Scope: Core
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
* Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
* KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- * RPL,SPR
+ * RPL,SPR,MTL
* Scope: Package (physical package)
* MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
* perf code: 0x01
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
* GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- * TGL,TNT,RKL,ADL,RPL,SPR
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- * KBL,CML,ICL,TGL,RKL,ADL,RPL
+ * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
* Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
* Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
* Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- * TNT,RKL,ADL,RPL
+ * TNT,RKL,ADL,RPL,MTL
* Scope: Package (physical package)
*
*/
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init),
{},
};
case INTEL_FAM6_BROADWELL_G:
case INTEL_FAM6_BROADWELL_X:
case INTEL_FAM6_SAPPHIRERAPIDS_X:
+ case INTEL_FAM6_EMERALDRAPIDS_X:
case INTEL_FAM6_ATOM_SILVERMONT:
case INTEL_FAM6_ATOM_SILVERMONT_D:
case INTEL_FAM6_RAPTORLAKE:
case INTEL_FAM6_RAPTORLAKE_P:
case INTEL_FAM6_RAPTORLAKE_S:
+ case INTEL_FAM6_METEORLAKE:
+ case INTEL_FAM6_METEORLAKE_L:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx),
X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr),
+ X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl),
{},
};
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
#include <asm/mmu.h>
#include <asm/mpspec.h>
#include <asm/x86_init.h>
+#include <asm/cpufeature.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
/* Physical address to resume after wakeup */
unsigned long acpi_get_wakeup_address(void);
+static inline bool acpi_skip_set_wakeup_address(void)
+{
+ return cpu_feature_enabled(X86_FEATURE_XENPV);
+}
+
+#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address
+
/*
* Check if the CPU can handle C2 and deeper
*/
#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */
#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
#endif /* _ASM_X86_CPUFEATURES_H */
asm("mov %%db6, %0" :"=r" (val));
break;
case 7:
- asm("mov %%db7, %0" :"=r" (val));
+ /*
+ * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them
+ * with other code.
+ *
+ * This is needed because a DR7 access can cause a #VC exception
+ * when running under SEV-ES. Taking a #VC exception is not a
+ * safe thing to do just anywhere in the entry code and
+ * re-ordering might place the access into an unsafe location.
+ *
+ * This happened in the NMI handler, where the DR7 read was
+ * re-ordered to happen before the call to sev_es_ist_enter(),
+ * causing stack recursion.
+ */
+ asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER);
break;
default:
BUG();
asm("mov %0, %%db6" ::"r" (value));
break;
case 7:
- asm("mov %0, %%db7" ::"r" (value));
+ /*
+ * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them
+ * with other code.
+ *
+ * While is didn't happen with a DR7 write (see the DR7 read
+ * comment above which explains where it happened), add the
+ * __FORCE_ORDER here too to avoid similar problems in the
+ * future.
+ */
+ asm volatile("mov %0, %%db7" ::"r" (value), __FORCE_ORDER);
break;
default:
BUG();
bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
unsigned char buf[MAX_INSN_SIZE], int buf_size);
-enum mmio_type {
- MMIO_DECODE_FAILED,
- MMIO_WRITE,
- MMIO_WRITE_IMM,
- MMIO_READ,
- MMIO_READ_ZERO_EXTEND,
- MMIO_READ_SIGN_EXTEND,
- MMIO_MOVS,
+enum insn_mmio_type {
+ INSN_MMIO_DECODE_FAILED,
+ INSN_MMIO_WRITE,
+ INSN_MMIO_WRITE_IMM,
+ INSN_MMIO_READ,
+ INSN_MMIO_READ_ZERO_EXTEND,
+ INSN_MMIO_READ_SIGN_EXTEND,
+ INSN_MMIO_MOVS,
};
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
#endif /* _ASM_X86_INSN_EVAL_H */
#define INTEL_FAM6_METEORLAKE 0xAC
#define INTEL_FAM6_METEORLAKE_L 0xAA
+#define INTEL_FAM6_LUNARLAKE_M 0xBD
+
/* "Small Core" Processors (Atom/E-Core) */
#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
/* Xen emulation context */
struct kvm_xen {
+ struct mutex xen_lock;
u32 xen_version;
bool long_mode;
bool runstate_update_flag;
#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
+/* SNP feature bits enabled by the hypervisor */
+#define MSR_AMD64_SNP_VTOM BIT_ULL(3)
+#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4)
+#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5)
+#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6)
+#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8)
+#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9)
+#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10)
+#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12)
+#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14)
+#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16)
+#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17)
+
+/* SNP feature bits reserved for future use. */
+#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13)
+#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15)
+#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18)
+
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
/* AMD Collaborative Processor Performance Control MSRs */
#define SVM_VMGEXIT_AP_CREATE 1
#define SVM_VMGEXIT_AP_DESTROY 2
#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd
+#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe
+#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \
+ /* SW_EXITINFO1[3:0] */ \
+ (((((u64)reason_set) & 0xf)) | \
+ /* SW_EXITINFO1[11:4] */ \
+ ((((u64)reason_code) & 0xff) << 4))
#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff
/* Exit code reserved for hypervisor/software use */
return within_module_coretext(addr);
}
-static __init_or_module bool skip_addr(void *dest)
+static bool skip_addr(void *dest)
{
if (dest == error_entry)
return true;
0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
};
-static __init_or_module void *patch_dest(void *dest, bool direct)
+static void *patch_dest(void *dest, bool direct)
{
unsigned int tsize = SKL_TMPL_SIZE;
u8 *pad = dest - tsize;
static void disable_freq_invariance_workfn(struct work_struct *work)
{
+ int cpu;
+
static_branch_disable(&arch_scale_freq_key);
+
+ /*
+ * Set arch_freq_scale to a default value on all cpus
+ * This negates the effect of scaling
+ */
+ for_each_possible_cpu(cpu)
+ per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE;
}
static DECLARE_WORK(disable_freq_invariance_work,
if (ctrl == PR_SPEC_FORCE_DISABLE)
task_set_spec_ib_force_disable(task);
task_update_spec_tif(task);
+ if (task == current)
+ indirect_branch_prediction_barrier();
break;
default:
return -ERANGE;
#define MMIO_SBDS BIT(2)
/* CPU is affected by RETbleed, speculating where you would not expect it */
#define RETBLEED BIT(3)
+/* CPU is affected by SMT (cross-thread) return predictions */
+#define SMT_RSB BIT(4)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
- VULNBL_AMD(0x17, RETBLEED),
- VULNBL_HYGON(0x18, RETBLEED),
+ VULNBL_AMD(0x17, RETBLEED | SMT_RSB),
+ VULNBL_HYGON(0x18, RETBLEED | SMT_RSB),
{}
};
!(ia32_cap & ARCH_CAP_PBRSB_NO))
setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
+ if (cpu_matches(cpu_vuln_blacklist, SMT_RSB))
+ setup_force_cpu_bug(X86_BUG_SMT_RSB);
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
return entry;
}
+static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+ u64 msr_val;
+
+ /*
+ * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+ * with a valid event code for supported resource type and the bits
+ * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+ * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+ * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+ * are error bits.
+ */
+ wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+ rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+ if (msr_val & RMID_VAL_ERROR)
+ return -EIO;
+ if (msr_val & RMID_VAL_UNAVAIL)
+ return -EINVAL;
+
+ *val = msr_val;
+ return 0;
+}
+
static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
u32 rmid,
enum resctrl_event_id eventid)
struct arch_mbm_state *am;
am = get_arch_mbm_state(hw_dom, rmid, eventid);
- if (am)
+ if (am) {
memset(am, 0, sizeof(*am));
+
+ /* Record any initial, non-zero count value. */
+ __rmid_read(rmid, eventid, &am->prev_msr);
+ }
}
static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
struct arch_mbm_state *am;
u64 msr_val, chunks;
+ int ret;
if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
return -EINVAL;
- /*
- * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
- * with a valid event code for supported resource type and the bits
- * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
- * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
- * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
- * are error bits.
- */
- wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
- rdmsrl(MSR_IA32_QM_CTR, msr_val);
-
- if (msr_val & RMID_VAL_ERROR)
- return -EIO;
- if (msr_val & RMID_VAL_UNAVAIL)
- return -EINVAL;
+ ret = __rmid_read(rmid, eventid, &msr_val);
+ if (ret)
+ return ret;
am = get_arch_mbm_state(hw_dom, rmid, eventid);
if (am) {
/*
* Ensure the task's closid and rmid are written before determining if
* the task is current that will decide if it will be interrupted.
+ * This pairs with the full barrier between the rq->curr update and
+ * resctrl_sched_in() during context switch.
*/
- barrier();
+ smp_mb();
/*
* By now, the task's closid and rmid are set. If the task is current
WRITE_ONCE(t->closid, to->closid);
WRITE_ONCE(t->rmid, to->mon.rmid);
+ /*
+ * Order the closid/rmid stores above before the loads
+ * in task_curr(). This pairs with the full barrier
+ * between the rq->curr update and resctrl_sched_in()
+ * during context switch.
+ */
+ smp_mb();
+
/*
* If the task is on a CPU, set the CPU in the mask.
* The detection is inaccurate as tasks might move or
kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
ret = kexec_add_buffer(&kbuf);
- if (ret) {
- vfree((void *)image->elf_headers);
+ if (ret)
return ret;
- }
image->elf_load_addr = kbuf.mem;
pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
+ irq_set_status_flags(irq, IRQ_LEVEL);
enable_irq(irq);
lapic_assign_legacy_vector(irq, true);
}
legacy_pic->init(0);
- for (i = 0; i < nr_legacy_irqs(); i++)
+ for (i = 0; i < nr_legacy_irqs(); i++) {
irq_set_chip_and_handler(i, chip, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
+ }
}
void __init init_IRQ(void)
#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/kallsyms.h>
+#include <linux/kgdb.h>
#include <linux/ftrace.h>
#include <linux/kasan.h>
#include <linux/moduleloader.h>
if (ret < 0)
return 0;
+#ifdef CONFIG_KGDB
/*
- * Another debugging subsystem might insert this breakpoint.
- * In that case, we can't recover it.
+ * If there is a dynamically installed kgdb sw breakpoint,
+ * this function should not be probed.
*/
- if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
+ if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+ kgdb_has_hit_break(addr))
return 0;
+#endif
addr += insn.length;
}
/* 1 byte conditional jump */
p->ainsn.emulate_op = kprobe_emulate_jcc;
p->ainsn.jcc.type = opcode & 0xf;
- p->ainsn.rel32 = *(char *)insn->immediate.bytes;
+ p->ainsn.rel32 = insn->immediate.value;
break;
case 0x0f:
opcode = insn->opcode.bytes[1];
#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/kallsyms.h>
+#include <linux/kgdb.h>
#include <linux/ftrace.h>
#include <linux/objtool.h>
#include <linux/pgtable.h>
return ret;
}
-static bool is_padding_int3(unsigned long addr, unsigned long eaddr)
-{
- unsigned char ops;
-
- for (; addr < eaddr; addr++) {
- if (get_kernel_nofault(ops, (void *)addr) < 0 ||
- ops != INT3_INSN_OPCODE)
- return false;
- }
-
- return true;
-}
-
/* Decode whole function to ensure any instructions don't jump into target */
static int can_optimize(unsigned long paddr)
{
ret = insn_decode_kernel(&insn, (void *)recovered_insn);
if (ret < 0)
return 0;
-
+#ifdef CONFIG_KGDB
/*
- * In the case of detecting unknown breakpoint, this could be
- * a padding INT3 between functions. Let's check that all the
- * rest of the bytes are also INT3.
+ * If there is a dynamically installed kgdb sw breakpoint,
+ * this function should not be probed.
*/
- if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
- return is_padding_int3(addr, paddr - offset + size) ? 1 : 0;
-
+ if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+ kgdb_has_hit_break(addr))
+ return 0;
+#endif
/* Recover address */
insn.kaddr = (void *)addr;
insn.next_byte = (void *)(addr + insn.length);
static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
struct insn *insn = &ctxt->insn;
+ enum insn_mmio_type mmio;
unsigned int bytes = 0;
- enum mmio_type mmio;
enum es_result ret;
u8 sign_byte;
long *reg_data;
mmio = insn_decode_mmio(insn, &bytes);
- if (mmio == MMIO_DECODE_FAILED)
+ if (mmio == INSN_MMIO_DECODE_FAILED)
return ES_DECODE_FAILED;
- if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+ if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
if (!reg_data)
return ES_DECODE_FAILED;
}
switch (mmio) {
- case MMIO_WRITE:
+ case INSN_MMIO_WRITE:
memcpy(ghcb->shared_buffer, reg_data, bytes);
ret = vc_do_mmio(ghcb, ctxt, bytes, false);
break;
- case MMIO_WRITE_IMM:
+ case INSN_MMIO_WRITE_IMM:
memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
ret = vc_do_mmio(ghcb, ctxt, bytes, false);
break;
- case MMIO_READ:
+ case INSN_MMIO_READ:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_ZERO_EXTEND:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
memset(reg_data, 0, insn->opnd_bytes);
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
memset(reg_data, sign_byte, insn->opnd_bytes);
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_MOVS:
+ case INSN_MMIO_MOVS:
ret = vc_handle_mmio_movs(ctxt, bytes);
break;
default:
int nent;
};
+static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array)
+{
+ if (array->nent >= array->maxnent)
+ return NULL;
+
+ return &array->entries[array->nent++];
+}
+
static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
u32 function, u32 index)
{
- struct kvm_cpuid_entry2 *entry;
+ struct kvm_cpuid_entry2 *entry = get_next_cpuid(array);
- if (array->nent >= array->maxnent)
+ if (!entry)
return NULL;
- entry = &array->entries[array->nent++];
-
memset(entry, 0, sizeof(*entry));
entry->function = function;
entry->index = index;
entry->edx = edx.full;
break;
}
- /*
- * Per Intel's SDM, the 0x1f is a superset of 0xb,
- * thus they can be handled by common code.
- */
case 0x1f:
case 0xb:
/*
- * Populate entries until the level type (ECX[15:8]) of the
- * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is
- * the starting entry, filled by the primary do_host_cpuid().
+ * No topology; a valid topology is indicated by the presence
+ * of subleaf 1.
*/
- for (i = 1; entry->ecx & 0xff00; ++i) {
- entry = do_host_cpuid(array, function, i);
- if (!entry)
- goto out;
- }
+ entry->eax = entry->ebx = entry->ecx = 0;
break;
case 0xd: {
u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
entry->ebx = entry->ecx = entry->edx = 0;
break;
case 0x8000001e:
+ /* Do not return host topology information. */
+ entry->eax = entry->ebx = entry->ecx = 0;
+ entry->edx = 0; /* reserved */
break;
case 0x8000001F:
if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
}
struct kvm_hv_hcall {
+ /* Hypercall input data */
u64 param;
u64 ingpa;
u64 outgpa;
bool fast;
bool rep;
sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS];
+
+ /*
+ * Current read offset when KVM reads hypercall input data gradually,
+ * either offset in bytes from 'ingpa' for regular hypercalls or the
+ * number of already consumed 'XMM halves' for 'fast' hypercalls.
+ */
+ union {
+ gpa_t data_offset;
+ int consumed_xmm_halves;
+ };
};
static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc,
- u16 orig_cnt, u16 cnt_cap, u64 *data,
- int consumed_xmm_halves, gpa_t offset)
+ u16 orig_cnt, u16 cnt_cap, u64 *data)
{
/*
* Preserve the original count when ignoring entries via a "cap", KVM
* Each XMM holds two sparse banks, but do not count halves that
* have already been consumed for hypercall parameters.
*/
- if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves)
+ if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves)
return HV_STATUS_INVALID_HYPERCALL_INPUT;
for (i = 0; i < cnt; i++) {
- j = i + consumed_xmm_halves;
+ j = i + hc->consumed_xmm_halves;
if (j % 2)
data[i] = sse128_hi(hc->xmm[j / 2]);
else
return 0;
}
- return kvm_read_guest(kvm, hc->ingpa + offset, data,
+ return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data,
cnt * sizeof(*data));
}
static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc,
- u64 *sparse_banks, int consumed_xmm_halves,
- gpa_t offset)
+ u64 *sparse_banks)
{
if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS)
return -EINVAL;
/* Cap var_cnt to ignore banks that cannot contain a legal VP index. */
return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS,
- sparse_banks, consumed_xmm_halves, offset);
+ sparse_banks);
}
-static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[],
- int consumed_xmm_halves, gpa_t offset)
+static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[])
{
- return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt,
- entries, consumed_xmm_halves, offset);
+ return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries);
}
static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu,
struct kvm_vcpu *v;
unsigned long i;
bool all_cpus;
- int consumed_xmm_halves = 0;
- gpa_t data_offset;
/*
* The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS
flush.address_space = hc->ingpa;
flush.flags = hc->outgpa;
flush.processor_mask = sse128_lo(hc->xmm[0]);
- consumed_xmm_halves = 1;
+ hc->consumed_xmm_halves = 1;
} else {
if (unlikely(kvm_read_guest(kvm, hc->ingpa,
&flush, sizeof(flush))))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- data_offset = sizeof(flush);
+ hc->data_offset = sizeof(flush);
}
trace_kvm_hv_flush_tlb(flush.processor_mask,
flush_ex.flags = hc->outgpa;
memcpy(&flush_ex.hv_vp_set,
&hc->xmm[0], sizeof(hc->xmm[0]));
- consumed_xmm_halves = 2;
+ hc->consumed_xmm_halves = 2;
} else {
if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex,
sizeof(flush_ex))))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- data_offset = sizeof(flush_ex);
+ hc->data_offset = sizeof(flush_ex);
}
trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask,
if (!hc->var_cnt)
goto ret_success;
- if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks,
- consumed_xmm_halves, data_offset))
+ if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
}
* consumed_xmm_halves to make sure TLB flush entries are read
* from the correct offset.
*/
- data_offset += hc->var_cnt * sizeof(sparse_banks[0]);
- consumed_xmm_halves += hc->var_cnt;
+ if (hc->fast)
+ hc->consumed_xmm_halves += hc->var_cnt;
+ else
+ hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]);
}
if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE ||
hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) {
tlb_flush_entries = NULL;
} else {
- if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries,
- consumed_xmm_halves, data_offset))
+ if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
tlb_flush_entries = __tlb_flush_entries;
}
if (!hc->var_cnt)
goto ret_success;
- if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1,
- offsetof(struct hv_send_ipi_ex,
- vp_set.bank_contents)))
+ if (!hc->fast)
+ hc->data_offset = offsetof(struct hv_send_ipi_ex,
+ vp_set.bank_contents);
+ else
+ hc->consumed_xmm_halves = 1;
+
+ if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
}
kvm_set_msi_irq(vcpu->kvm, entry, &irq);
if (irq.trig_mode &&
- kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
- irq.dest_id, irq.dest_mode))
+ (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
+ irq.dest_id, irq.dest_mode) ||
+ kvm_apic_pending_eoi(vcpu, irq.vector)))
__set_bit(irq.vector, ioapic_handled_vectors);
}
}
extern struct static_key_false_deferred apic_hw_disabled;
-static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic)
+static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic)
{
if (static_branch_unlikely(&apic_hw_disabled.key))
return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
- return MSR_IA32_APICBASE_ENABLE;
+ return true;
}
extern struct static_key_false_deferred apic_sw_disabled;
* A shadow-present leaf SPTE may be non-writable for 4 possible reasons:
*
* 1. To intercept writes for dirty logging. KVM write-protects huge pages
- * so that they can be split be split down into the dirty logging
+ * so that they can be split down into the dirty logging
* granularity (4KiB) whenever the guest writes to them. KVM also
* write-protects 4KiB pages so that writes can be recorded in the dirty log
* (e.g. if not using PML). SPTEs are write-protected for dirty logging
int ret = RET_PF_FIXED;
bool wrprot = false;
- WARN_ON(sp->role.level != fault->goal_level);
+ if (WARN_ON_ONCE(sp->role.level != fault->goal_level))
+ return RET_PF_RETRY;
+
if (unlikely(!fault->slot))
new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
else
if (fault->nx_huge_page_workaround_enabled)
disallowed_hugepage_adjust(fault, iter.old_spte, iter.level);
- if (iter.level == fault->goal_level)
- break;
-
/*
* If SPTE has been frozen by another thread, just give up and
* retry, avoiding unnecessary page table allocation and free.
if (is_removed_spte(iter.old_spte))
goto retry;
+ if (iter.level == fault->goal_level)
+ goto map_target_level;
+
/* Step down into the lower level page table if it exists. */
if (is_shadow_present_pte(iter.old_spte) &&
!is_large_pte(iter.old_spte))
r = tdp_mmu_link_sp(kvm, &iter, sp, true);
/*
- * Also force the guest to retry the access if the upper level SPTEs
- * aren't in place.
+ * Force the guest to retry if installing an upper level SPTE
+ * failed, e.g. because a different task modified the SPTE.
*/
if (r) {
tdp_mmu_free_sp(sp);
if (fault->huge_page_disallowed &&
fault->req_level >= iter.level) {
spin_lock(&kvm->arch.tdp_mmu_pages_lock);
- track_possible_nx_huge_page(kvm, sp);
+ if (sp->nx_huge_page_disallowed)
+ track_possible_nx_huge_page(kvm, sp);
spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
}
}
+ /*
+ * The walk aborted before reaching the target level, e.g. because the
+ * iterator detected an upper level SPTE was frozen during traversal.
+ */
+ WARN_ON_ONCE(iter.level == fault->goal_level);
+ goto retry;
+
+map_target_level:
ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter);
retry:
return false;
/* recalibrate sample period and check if it's accepted by perf core */
- if (perf_event_period(pmc->perf_event,
+ if (is_sampling_event(pmc->perf_event) &&
+ perf_event_period(pmc->perf_event,
get_sample_period(pmc, pmc->counter)))
return false;
static inline void pmc_update_sample_period(struct kvm_pmc *pmc)
{
- if (!pmc->perf_event || pmc->is_paused)
+ if (!pmc->perf_event || pmc->is_paused ||
+ !is_sampling_event(pmc->perf_event))
return;
perf_event_period(pmc->perf_event,
{
bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL;
- perf_get_x86_pmu_capability(&kvm_pmu_cap);
-
- /*
- * For Intel, only support guest architectural pmu
- * on a host with architectural pmu.
- */
- if ((is_intel && !kvm_pmu_cap.version) || !kvm_pmu_cap.num_counters_gp)
+ /*
+ * Hybrid PMUs don't play nice with virtualization without careful
+ * configuration by userspace, and KVM's APIs for reporting supported
+ * vPMU features do not account for hybrid PMUs. Disable vPMU support
+ * for hybrid PMUs until KVM gains a way to let userspace opt-in.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
enable_pmu = false;
+ if (enable_pmu) {
+ perf_get_x86_pmu_capability(&kvm_pmu_cap);
+
+ /*
+ * For Intel, only support guest architectural pmu
+ * on a host with architectural pmu.
+ */
+ if ((is_intel && !kvm_pmu_cap.version) ||
+ !kvm_pmu_cap.num_counters_gp)
+ enable_pmu = false;
+ }
+
if (!enable_pmu) {
memset(&kvm_pmu_cap, 0, sizeof(kvm_pmu_cap));
return;
c->intercepts[i] = h->intercepts[i];
if (g->int_ctl & V_INTR_MASKING_MASK) {
- /* We only want the cr8 intercept bits of L1 */
- vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
- vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
-
/*
- * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
- * affect any interrupt we may want to inject; therefore,
- * interrupt window vmexits are irrelevant to L0.
+ * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8
+ * does not affect any interrupt we may want to inject;
+ * therefore, writes to CR8 are irrelevant to L0, as are
+ * interrupt window vmexits.
*/
+ vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
vmcb_clr_intercept(c, INTERCEPT_VINTR);
}
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vcpu);
- kvm_vcpu_write_guest(vcpu,
- vmptr + offsetof(struct vmcs12,
- launch_state),
- &zero, sizeof(zero));
+ /*
+ * Silently ignore memory errors on VMCLEAR, Intel's pseudocode
+ * for VMCLEAR includes a "ensure that data for VMCS referenced
+ * by the operand is in memory" clause that guards writes to
+ * memory, i.e. doing nothing for I/O is architecturally valid.
+ *
+ * FIXME: Suppress failures if and only if no memslot is found,
+ * i.e. exit to userspace if __copy_to_user() fails.
+ */
+ (void)kvm_vcpu_write_guest(vcpu,
+ vmptr + offsetof(struct vmcs12,
+ launch_state),
+ &zero, sizeof(zero));
} else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) {
nested_release_evmcs(vcpu);
}
SECONDARY_EXEC_ENABLE_INVPCID |
SECONDARY_EXEC_RDSEED_EXITING |
SECONDARY_EXEC_XSAVES |
- SECONDARY_EXEC_TSC_SCALING;
+ SECONDARY_EXEC_TSC_SCALING |
+ SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
/*
* We can emulate "VMCS shadowing," even if the hardware
{
u32 ar;
- if (var->unusable || !var->present)
- ar = 1 << 16;
- else {
- ar = var->type & 15;
- ar |= (var->s & 1) << 4;
- ar |= (var->dpl & 3) << 5;
- ar |= (var->present & 1) << 7;
- ar |= (var->avl & 1) << 12;
- ar |= (var->l & 1) << 13;
- ar |= (var->db & 1) << 14;
- ar |= (var->g & 1) << 15;
- }
+ ar = var->type & 15;
+ ar |= (var->s & 1) << 4;
+ ar |= (var->dpl & 3) << 5;
+ ar |= (var->present & 1) << 7;
+ ar |= (var->avl & 1) << 12;
+ ar |= (var->l & 1) << 13;
+ ar |= (var->db & 1) << 14;
+ ar |= (var->g & 1) << 15;
+ ar |= (var->unusable || !var->present) << 16;
return ar;
}
* controls for features that are/aren't exposed to the guest.
*/
if (nested) {
+ /*
+ * All features that can be added or removed to VMX MSRs must
+ * be supported in the first place for nested virtualization.
+ */
+ if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control)))
+ enabled = false;
+
if (enabled)
vmx->nested.msrs.secondary_ctls_high |= control;
else
bool __read_mostly eager_page_split = true;
module_param(eager_page_split, bool, 0644);
+/* Enable/disable SMT_RSB bug mitigation */
+bool __read_mostly mitigate_smt_rsb;
+module_param(mitigate_smt_rsb, bool, 0444);
+
/*
* Restoring the host value for MSRs that are only consumed when running in
* usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
r = KVM_CLOCK_VALID_FLAGS;
break;
case KVM_CAP_X86_DISABLE_EXITS:
- r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
- KVM_X86_DISABLE_EXITS_CSTATE;
- if(kvm_can_mwait_in_guest())
- r |= KVM_X86_DISABLE_EXITS_MWAIT;
+ r = KVM_X86_DISABLE_EXITS_PAUSE;
+
+ if (!mitigate_smt_rsb) {
+ r |= KVM_X86_DISABLE_EXITS_HLT |
+ KVM_X86_DISABLE_EXITS_CSTATE;
+
+ if (kvm_can_mwait_in_guest())
+ r |= KVM_X86_DISABLE_EXITS_MWAIT;
+ }
break;
case KVM_CAP_X86_SMM:
if (!IS_ENABLED(CONFIG_KVM_SMM))
{
unsigned long val;
+ memset(dbgregs, 0, sizeof(*dbgregs));
memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
kvm_get_dr(vcpu, 6, &val);
dbgregs->dr6 = val;
dbgregs->dr7 = vcpu->arch.dr7;
- dbgregs->flags = 0;
- memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved));
}
static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS)
break;
- if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) &&
- kvm_can_mwait_in_guest())
- kvm->arch.mwait_in_guest = true;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT)
- kvm->arch.hlt_in_guest = true;
if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
kvm->arch.pause_in_guest = true;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
- kvm->arch.cstate_in_guest = true;
+
+#define SMT_RSB_MSG "This processor is affected by the Cross-Thread Return Predictions vulnerability. " \
+ "KVM_CAP_X86_DISABLE_EXITS should only be used with SMT disabled or trusted guests."
+
+ if (!mitigate_smt_rsb) {
+ if (boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() &&
+ (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE))
+ pr_warn_once(SMT_RSB_MSG);
+
+ if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) &&
+ kvm_can_mwait_in_guest())
+ kvm->arch.mwait_in_guest = true;
+ if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT)
+ kvm->arch.hlt_in_guest = true;
+ if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
+ kvm->arch.cstate_in_guest = true;
+ }
+
r = 0;
break;
case KVM_CAP_MSR_PLATFORM_INFO:
struct x86_exception *e)
{
if (r == X86EMUL_PROPAGATE_FAULT) {
+ if (KVM_BUG_ON(!e, vcpu->kvm))
+ return -EIO;
+
kvm_inject_emulated_page_fault(vcpu, e);
return 1;
}
static int __init kvm_x86_init(void)
{
kvm_mmu_x86_module_init();
+ mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible();
return 0;
}
module_init(kvm_x86_init);
int ret = 0;
int idx = srcu_read_lock(&kvm->srcu);
- if (gfn == GPA_INVALID) {
+ if (gfn == KVM_XEN_INVALID_GFN) {
kvm_gpc_deactivate(gpc);
goto out;
}
* Attempt to obtain the GPC lock on *both* (if there are two)
* gfn_to_pfn caches that cover the region.
*/
- read_lock_irqsave(&gpc1->lock, flags);
+ if (atomic) {
+ local_irq_save(flags);
+ if (!read_trylock(&gpc1->lock)) {
+ local_irq_restore(flags);
+ return;
+ }
+ } else {
+ read_lock_irqsave(&gpc1->lock, flags);
+ }
while (!kvm_gpc_check(gpc1, user_len1)) {
read_unlock_irqrestore(&gpc1->lock, flags);
* The guest's runstate_info is split across two pages and we
* need to hold and validate both GPCs simultaneously. We can
* declare a lock ordering GPC1 > GPC2 because nothing else
- * takes them more than one at a time.
+ * takes them more than one at a time. Set a subclass on the
+ * gpc1 lock to make lockdep shut up about it.
*/
- read_lock(&gpc2->lock);
+ lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_);
+ if (atomic) {
+ if (!read_trylock(&gpc2->lock)) {
+ read_unlock_irqrestore(&gpc1->lock, flags);
+ return;
+ }
+ } else {
+ read_lock(&gpc2->lock);
+ }
if (!kvm_gpc_check(gpc2, user_len2)) {
read_unlock(&gpc2->lock);
if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) {
r = -EINVAL;
} else {
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.long_mode = !!data->u.long_mode;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
}
break;
case KVM_XEN_ATTR_TYPE_SHARED_INFO:
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
break;
case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
if (data->u.vector && data->u.vector < 0x10)
r = -EINVAL;
else {
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.upcall_vector = data->u.vector;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
}
break;
break;
case KVM_XEN_ATTR_TYPE_XEN_VERSION:
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.xen_version = data->u.xen_version;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
break;
r = -EOPNOTSUPP;
break;
}
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
break;
{
int r = -ENOENT;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
switch (data->type) {
case KVM_XEN_ATTR_TYPE_LONG_MODE:
if (kvm->arch.xen.shinfo_cache.active)
data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa);
else
- data->u.shared_info.gfn = GPA_INVALID;
+ data->u.shared_info.gfn = KVM_XEN_INVALID_GFN;
r = 0;
break;
break;
}
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return r;
}
{
int idx, r = -ENOENT;
- mutex_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
idx = srcu_read_lock(&vcpu->kvm->srcu);
switch (data->type) {
BUILD_BUG_ON(offsetof(struct vcpu_info, time) !=
offsetof(struct compat_vcpu_info, time));
- if (data->u.gpa == GPA_INVALID) {
+ if (data->u.gpa == KVM_XEN_INVALID_GPA) {
kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
r = 0;
break;
break;
case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
- if (data->u.gpa == GPA_INVALID) {
+ if (data->u.gpa == KVM_XEN_INVALID_GPA) {
kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache);
r = 0;
break;
r = -EOPNOTSUPP;
break;
}
- if (data->u.gpa == GPA_INVALID) {
+ if (data->u.gpa == KVM_XEN_INVALID_GPA) {
r = 0;
deactivate_out:
kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache);
}
srcu_read_unlock(&vcpu->kvm->srcu, idx);
- mutex_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
return r;
}
{
int r = -ENOENT;
- mutex_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
switch (data->type) {
case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
if (vcpu->arch.xen.vcpu_info_cache.active)
data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa;
else
- data->u.gpa = GPA_INVALID;
+ data->u.gpa = KVM_XEN_INVALID_GPA;
r = 0;
break;
if (vcpu->arch.xen.vcpu_time_info_cache.active)
data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa;
else
- data->u.gpa = GPA_INVALID;
+ data->u.gpa = KVM_XEN_INVALID_GPA;
r = 0;
break;
break;
}
- mutex_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
return r;
}
u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
: kvm->arch.xen_hvm_config.blob_size_32;
u8 *page;
+ int ret;
if (page_num >= blob_size)
return 1;
if (IS_ERR(page))
return PTR_ERR(page);
- if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) {
- kfree(page);
+ ret = kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE);
+ kfree(page);
+ if (ret)
return 1;
- }
}
return 0;
}
xhc->blob_size_32 || xhc->blob_size_64))
return -EINVAL;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
static_branch_inc(&kvm_xen_enabled.key);
memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return 0;
}
static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
u64 param, u64 *r)
{
- int idx, i;
struct sched_poll sched_poll;
evtchn_port_t port, *ports;
- gpa_t gpa;
+ struct x86_exception e;
+ int i;
if (!lapic_in_kernel(vcpu) ||
!(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND))
return false;
- idx = srcu_read_lock(&vcpu->kvm->srcu);
- gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
- if (!gpa) {
- *r = -EFAULT;
- return true;
- }
-
if (IS_ENABLED(CONFIG_64BIT) && !longmode) {
struct compat_sched_poll sp32;
/* Sanity check that the compat struct definition is correct */
BUILD_BUG_ON(sizeof(sp32) != 16);
- if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) {
+ if (kvm_read_guest_virt(vcpu, param, &sp32, sizeof(sp32), &e)) {
*r = -EFAULT;
return true;
}
sched_poll.nr_ports = sp32.nr_ports;
sched_poll.timeout = sp32.timeout;
} else {
- if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll,
- sizeof(sched_poll))) {
+ if (kvm_read_guest_virt(vcpu, param, &sched_poll,
+ sizeof(sched_poll), &e)) {
*r = -EFAULT;
return true;
}
} else
ports = &port;
+ if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports,
+ sched_poll.nr_ports * sizeof(*ports), &e)) {
+ *r = -EFAULT;
+ return true;
+ }
+
for (i = 0; i < sched_poll.nr_ports; i++) {
- idx = srcu_read_lock(&vcpu->kvm->srcu);
- gpa = kvm_mmu_gva_to_gpa_system(vcpu,
- (gva_t)(sched_poll.ports + i),
- NULL);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
-
- if (!gpa || kvm_vcpu_read_guest(vcpu, gpa,
- &ports[i], sizeof(port))) {
- *r = -EFAULT;
- goto out;
- }
if (ports[i] >= max_evtchn_port(vcpu->kvm)) {
*r = -EINVAL;
goto out;
int vcpu_id, u64 param, u64 *r)
{
struct vcpu_set_singleshot_timer oneshot;
+ struct x86_exception e;
s64 delta;
- gpa_t gpa;
- int idx;
if (!kvm_xen_timer_enabled(vcpu))
return false;
*r = -EINVAL;
return true;
}
- idx = srcu_read_lock(&vcpu->kvm->srcu);
- gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
/*
* The only difference for 32-bit compat is the 4 bytes of
BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, flags) !=
sizeof_field(struct vcpu_set_singleshot_timer, flags));
- if (!gpa ||
- kvm_vcpu_read_guest(vcpu, gpa, &oneshot, longmode ? sizeof(oneshot) :
- sizeof(struct compat_vcpu_set_singleshot_timer))) {
+ if (kvm_read_guest_virt(vcpu, param, &oneshot, longmode ? sizeof(oneshot) :
+ sizeof(struct compat_vcpu_set_singleshot_timer), &e)) {
*r = -EFAULT;
return true;
}
mm_borrowed = true;
}
- /*
- * For the irqfd workqueue, using the main kvm->lock mutex is
- * fine since this function is invoked from kvm_set_irq() with
- * no other lock held, no srcu. In future if it will be called
- * directly from a vCPU thread (e.g. on hypercall for an IPI)
- * then it may need to switch to using a leaf-node mutex for
- * serializing the shared_info mapping.
- */
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
/*
* It is theoretically possible for the page to be unmapped
srcu_read_unlock(&kvm->srcu, idx);
} while(!rc);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (mm_borrowed)
kthread_unuse_mm(kvm->mm);
{
u32 port = data->u.evtchn.send_port;
struct evtchnfd *evtchnfd;
+ int ret;
- if (!port || port >= max_evtchn_port(kvm))
- return -EINVAL;
-
- mutex_lock(&kvm->lock);
+ /* Protect writes to evtchnfd as well as the idr lookup. */
+ mutex_lock(&kvm->arch.xen.xen_lock);
evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);
- mutex_unlock(&kvm->lock);
+ ret = -ENOENT;
if (!evtchnfd)
- return -ENOENT;
+ goto out_unlock;
/* For an UPDATE, nothing may change except the priority/vcpu */
+ ret = -EINVAL;
if (evtchnfd->type != data->u.evtchn.type)
- return -EINVAL;
+ goto out_unlock;
/*
* Port cannot change, and if it's zero that was an eventfd
*/
if (!evtchnfd->deliver.port.port ||
evtchnfd->deliver.port.port != data->u.evtchn.deliver.port.port)
- return -EINVAL;
+ goto out_unlock;
/* We only support 2 level event channels for now */
if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
- return -EINVAL;
+ goto out_unlock;
- mutex_lock(&kvm->lock);
evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
if (evtchnfd->deliver.port.vcpu_id != data->u.evtchn.deliver.port.vcpu) {
evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu;
evtchnfd->deliver.port.vcpu_idx = -1;
}
- mutex_unlock(&kvm->lock);
- return 0;
+ ret = 0;
+out_unlock:
+ mutex_unlock(&kvm->arch.xen.xen_lock);
+ return ret;
}
/*
{
u32 port = data->u.evtchn.send_port;
struct eventfd_ctx *eventfd = NULL;
- struct evtchnfd *evtchnfd = NULL;
+ struct evtchnfd *evtchnfd;
int ret = -EINVAL;
- if (!port || port >= max_evtchn_port(kvm))
- return -EINVAL;
-
evtchnfd = kzalloc(sizeof(struct evtchnfd), GFP_KERNEL);
if (!evtchnfd)
return -ENOMEM;
evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
}
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1,
GFP_KERNEL);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (ret >= 0)
return 0;
{
struct evtchnfd *evtchnfd;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (!evtchnfd)
return -ENOENT;
- if (kvm)
- synchronize_srcu(&kvm->srcu);
+ synchronize_srcu(&kvm->srcu);
if (!evtchnfd->deliver.port.port)
eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
kfree(evtchnfd);
static int kvm_xen_eventfd_reset(struct kvm *kvm)
{
- struct evtchnfd *evtchnfd;
+ struct evtchnfd *evtchnfd, **all_evtchnfds;
int i;
+ int n = 0;
+
+ mutex_lock(&kvm->arch.xen.xen_lock);
- mutex_lock(&kvm->lock);
+ /*
+ * Because synchronize_srcu() cannot be called inside the
+ * critical section, first collect all the evtchnfd objects
+ * in an array as they are removed from evtchn_ports.
+ */
+ idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i)
+ n++;
+
+ all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL);
+ if (!all_evtchnfds) {
+ mutex_unlock(&kvm->arch.xen.xen_lock);
+ return -ENOMEM;
+ }
+
+ n = 0;
idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) {
+ all_evtchnfds[n++] = evtchnfd;
idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
- synchronize_srcu(&kvm->srcu);
+ }
+ mutex_unlock(&kvm->arch.xen.xen_lock);
+
+ synchronize_srcu(&kvm->srcu);
+
+ while (n--) {
+ evtchnfd = all_evtchnfds[n];
if (!evtchnfd->deliver.port.port)
eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
kfree(evtchnfd);
}
- mutex_unlock(&kvm->lock);
+ kfree(all_evtchnfds);
return 0;
}
{
struct evtchnfd *evtchnfd;
struct evtchn_send send;
- gpa_t gpa;
- int idx;
+ struct x86_exception e;
- idx = srcu_read_lock(&vcpu->kvm->srcu);
- gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
-
- if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &send, sizeof(send))) {
+ /* Sanity check: this structure is the same for 32-bit and 64-bit */
+ BUILD_BUG_ON(sizeof(send) != 4);
+ if (kvm_read_guest_virt(vcpu, param, &send, sizeof(send), &e)) {
*r = -EFAULT;
return true;
}
- /* The evtchn_ports idr is protected by vcpu->kvm->srcu */
+ /*
+ * evtchnfd is protected by kvm->srcu; the idr lookup instead
+ * is protected by RCU.
+ */
+ rcu_read_lock();
evtchnfd = idr_find(&vcpu->kvm->arch.xen.evtchn_ports, send.port);
+ rcu_read_unlock();
if (!evtchnfd)
return false;
void kvm_xen_init_vm(struct kvm *kvm)
{
+ mutex_init(&kvm->arch.xen.xen_lock);
idr_init(&kvm->arch.xen.evtchn_ports);
kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN);
}
* Returns:
*
* Type of the instruction. Size of the memory operand is stored in
- * @bytes. If decode failed, MMIO_DECODE_FAILED returned.
+ * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned.
*/
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
{
- enum mmio_type type = MMIO_DECODE_FAILED;
+ enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED;
*bytes = 0;
if (insn_get_opcode(insn))
- return MMIO_DECODE_FAILED;
+ return INSN_MMIO_DECODE_FAILED;
switch (insn->opcode.bytes[0]) {
case 0x88: /* MOV m8,r8 */
case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_WRITE;
+ type = INSN_MMIO_WRITE;
break;
case 0xc6: /* MOV m8, imm8 */
case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_WRITE_IMM;
+ type = INSN_MMIO_WRITE_IMM;
break;
case 0x8a: /* MOV r8, m8 */
case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_READ;
+ type = INSN_MMIO_READ;
break;
case 0xa4: /* MOVS m8, m8 */
case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_MOVS;
+ type = INSN_MMIO_MOVS;
break;
case 0x0f: /* Two-byte instruction */
case 0xb7: /* MOVZX r32/r64, m16 */
if (!*bytes)
*bytes = 2;
- type = MMIO_READ_ZERO_EXTEND;
+ type = INSN_MMIO_READ_ZERO_EXTEND;
break;
case 0xbe: /* MOVSX r16/r32/r64, m8 */
case 0xbf: /* MOVSX r32/r64, m16 */
if (!*bytes)
*bytes = 2;
- type = MMIO_READ_SIGN_EXTEND;
+ type = INSN_MMIO_READ_SIGN_EXTEND;
break;
}
break;
*/
SYM_FUNC_START(__iowrite32_copy)
movl %edx,%ecx
- rep movsd
+ rep movsl
RET
SYM_FUNC_END(__iowrite32_copy)
#include <asm/pti.h>
#include <asm/text-patching.h>
#include <asm/memtype.h>
+#include <asm/paravirt.h>
/*
* We need to define the tracepoints somewhere, and tlb.c
poking_mm = mm_alloc();
BUG_ON(!poking_mm);
+ /* Xen PV guests need the PGD to be pinned. */
+ paravirt_arch_dup_mmap(NULL, poking_mm);
+
/*
* Randomize the poking address, but make sure that the following page
* will be mapped at the same PMD. We need 2 pages, so find space for 3,
*/
#include <linux/acpi.h>
+#include <linux/efi.h>
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/bitmap.h>
return mcfg_res.flags;
}
+static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+{
+#ifdef CONFIG_EFI
+ efi_memory_desc_t *md;
+ u64 size, mmio_start, mmio_end;
+
+ for_each_efi_memory_desc(md) {
+ if (md->type == EFI_MEMORY_MAPPED_IO) {
+ size = md->num_pages << EFI_PAGE_SHIFT;
+ mmio_start = md->phys_addr;
+ mmio_end = mmio_start + size;
+
+ /*
+ * N.B. Caller supplies (start, start + size),
+ * so to match, mmio_end is the first address
+ * *past* the EFI_MEMORY_MAPPED_IO area.
+ */
+ if (mmio_start <= start && end <= mmio_end)
+ return true;
+ }
+ }
+#endif
+
+ return false;
+}
+
typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type);
static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
struct pci_mmcfg_region *cfg,
- struct device *dev, int with_e820)
+ struct device *dev, const char *method)
{
u64 addr = cfg->res.start;
u64 size = resource_size(&cfg->res);
u64 old_size = size;
int num_buses;
- char *method = with_e820 ? "E820" : "ACPI motherboard resources";
while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) {
size >>= 1;
return false;
if (dev)
- dev_info(dev, "MMCONFIG at %pR reserved in %s\n",
+ dev_info(dev, "MMCONFIG at %pR reserved as %s\n",
&cfg->res, method);
else
- pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n",
+ pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n",
&cfg->res, method);
if (old_size != size) {
pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
{
if (!early && !acpi_disabled) {
- if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0))
+ if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
+ "ACPI motherboard resource"))
return true;
if (dev)
"MMCONFIG at %pR not reserved in "
"ACPI motherboard resources\n",
&cfg->res);
+
+ if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
+ "EfiMemoryMappedIO"))
+ return true;
}
/*
/* Don't try to do this check unless configuration
type 1 is available. how about type 2 ?*/
if (raw_pci_ops)
- return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1);
+ return is_mmconf_reserved(e820__mapped_all, cfg, dev,
+ "E820 entry");
return false;
}
msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) {
for (i = 0; i < msidesc->nvec_used; i++)
xen_destroy_irq(msidesc->irq + i);
+ msidesc->irq = 0;
}
}
};
static struct msi_domain_info xen_pci_msi_domain_info = {
+ .flags = MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS,
.ops = &xen_pci_msi_domain_ops,
};
#include <asm/elf.h>
-Elf32_Half elf_core_extra_phdrs(void)
+Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0;
}
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
if ( vsyscall_ehdr ) {
const struct elfhdr *const ehdrp =
return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
}
-static inline unsigned p2m_index(unsigned long pfn)
-{
- return pfn % P2M_PER_PAGE;
-}
-
static void p2m_top_mfn_init(unsigned long *top)
{
unsigned i;
unsigned long ra; /* kernel's a0: return address and window call size */
unsigned long sp; /* kernel's a1: stack pointer */
- /* struct xtensa_cpuinfo info; */
-
- unsigned long bad_vaddr; /* last user fault */
- unsigned long bad_uaddr; /* last kernel fault accessing user space */
- unsigned long error_code;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK];
struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK];
{ \
ra: 0, \
sp: sizeof(init_stack) + (long) &init_stack, \
- /*info: {0}, */ \
- bad_vaddr: 0, \
- bad_uaddr: 0, \
- error_code: 0, \
}
__die_if_kernel("Unhandled unaligned exception in kernel",
regs, SIGKILL);
- current->thread.bad_vaddr = regs->excvaddr;
- current->thread.error_code = -3;
pr_info_ratelimited("Unaligned memory access to %08lx in '%s' "
"(pid = %d, pc = %#010lx)\n",
regs->excvaddr, current->comm,
bad_area:
mmap_read_unlock(mm);
if (user_mode(regs)) {
- current->thread.bad_vaddr = address;
- current->thread.error_code = is_write;
force_sig_fault(SIGSEGV, code, (void *) address);
return;
}
/* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
- current->thread.bad_vaddr = address;
force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address);
/* Kernel mode? Handle exceptions or die */
if ((entry = search_exception_tables(regs->pc)) != NULL) {
pr_debug("%s: Exception at pc=%#010lx (%lx)\n",
current->comm, regs->pc, entry->fixup);
- current->thread.bad_uaddr = address;
regs->pc = entry->fixup;
return;
}
bool "Enable the block layer" if EXPERT
default y
select SBITMAP
- select SRCU
help
Provide block layer support for the kernel.
static void bfqg_get(struct bfq_group *bfqg)
{
- bfqg->ref++;
+ refcount_inc(&bfqg->ref);
}
static void bfqg_put(struct bfq_group *bfqg)
{
- bfqg->ref--;
-
- if (bfqg->ref == 0)
+ if (refcount_dec_and_test(&bfqg->ref))
kfree(bfqg);
}
}
/* see comments in bfq_bic_update_cgroup for why refcounting */
- bfqg_get(bfqg);
+ refcount_set(&bfqg->ref, 1);
return &bfqg->pd;
}
* request from the old cgroup.
*/
bfq_put_cooperator(sync_bfqq);
- bfq_release_process_ref(bfqd, sync_bfqq);
bic_set_bfqq(bic, NULL, true);
+ bfq_release_process_ref(bfqd, sync_bfqq);
}
}
}
unsigned long flags;
spin_lock_irqsave(&bfqd->lock, flags);
- bfq_exit_bfqq(bfqd, bfqq);
bic_set_bfqq(bic, NULL, is_sync);
+ bfq_exit_bfqq(bfqd, bfqq);
spin_unlock_irqrestore(&bfqd->lock, flags);
}
}
bfqq = bic_to_bfqq(bic, false);
if (bfqq) {
- bfq_release_process_ref(bfqd, bfqq);
+ struct bfq_queue *old_bfqq = bfqq;
+
bfqq = bfq_get_queue(bfqd, bio, false, bic, true);
bic_set_bfqq(bic, bfqq, false);
+ bfq_release_process_ref(bfqd, old_bfqq);
}
bfqq = bic_to_bfqq(bic, true);
char blkg_path[128];
/* reference counter (see comments in bfq_bic_update_cgroup) */
- int ref;
+ refcount_t ref;
/* Is bfq_group still online? */
bool online;
}
EXPORT_SYMBOL(__bio_advance);
+void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+ struct bio *src, struct bvec_iter *src_iter)
+{
+ while (src_iter->bi_size && dst_iter->bi_size) {
+ struct bio_vec src_bv = bio_iter_iovec(src, *src_iter);
+ struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter);
+ unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
+ void *src_buf = bvec_kmap_local(&src_bv);
+ void *dst_buf = bvec_kmap_local(&dst_bv);
+
+ memcpy(dst_buf, src_buf, bytes);
+
+ kunmap_local(dst_buf);
+ kunmap_local(src_buf);
+
+ bio_advance_iter_single(src, src_iter, bytes);
+ bio_advance_iter_single(dst, dst_iter, bytes);
+ }
+}
+EXPORT_SYMBOL(bio_copy_data_iter);
+
/**
* bio_copy_data - copy contents of data buffers from one bio to another
* @src: source bio
struct bvec_iter src_iter = src->bi_iter;
struct bvec_iter dst_iter = dst->bi_iter;
- while (src_iter.bi_size && dst_iter.bi_size) {
- struct bio_vec src_bv = bio_iter_iovec(src, src_iter);
- struct bio_vec dst_bv = bio_iter_iovec(dst, dst_iter);
- unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
- void *src_buf = bvec_kmap_local(&src_bv);
- void *dst_buf = bvec_kmap_local(&dst_bv);
-
- memcpy(dst_buf, src_buf, bytes);
-
- kunmap_local(dst_buf);
- kunmap_local(src_buf);
-
- bio_advance_iter_single(src, &src_iter, bytes);
- bio_advance_iter_single(dst, &dst_iter, bytes);
- }
+ bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
}
EXPORT_SYMBOL(bio_copy_data);
list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
pol->pd_init_fn(blkg->pd[pol->plid]);
+ if (pol->pd_online_fn)
+ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
+ pol->pd_online_fn(blkg->pd[pol->plid]);
+
__set_bit(pol->plid, q->blkcg_pols);
ret = 0;
struct blkg_iostat_set *bis;
unsigned long flags;
+ /* Root-level stats are sourced from system-wide IO stats */
+ if (!cgroup_parent(blkcg->css.cgroup))
+ return;
+
cpu = get_cpu();
bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu);
flags = u64_stats_update_begin_irqsave(&bis->sync);
*
* Decrements the refcount of the request_queue and free it when the refcount
* reaches 0.
- *
- * Context: Can sleep.
*/
void blk_put_queue(struct request_queue *q)
{
- might_sleep();
if (refcount_dec_and_test(&q->refs))
blk_free_queue(q);
}
*segs = nsegs;
return NULL;
split:
+ /*
+ * We can't sanely support splitting for a REQ_NOWAIT bio. End it
+ * with EAGAIN if splitting is required and return an error pointer.
+ */
+ if (bio->bi_opf & REQ_NOWAIT) {
+ bio->bi_status = BLK_STS_AGAIN;
+ bio_endio(bio);
+ return ERR_PTR(-EAGAIN);
+ }
+
*segs = nsegs;
/*
default:
split = bio_split_rw(bio, lim, nr_segs, bs,
get_max_io_size(bio, lim) << SECTOR_SHIFT);
+ if (IS_ERR(split))
+ return NULL;
break;
}
if (split) {
- /* there isn't chance to merge the splitted bio */
+ /* there isn't chance to merge the split bio */
split->bi_opf |= REQ_NOMERGE;
blkcg_bio_issue_init(split);
struct blk_plug *plug, struct bio **bio, unsigned int nsegs)
{
struct request *rq;
+ enum hctx_type type, hctx_type;
if (!plug)
return NULL;
return NULL;
}
- if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type)
+ type = blk_mq_get_hctx_type((*bio)->bi_opf);
+ hctx_type = rq->mq_hctx->type;
+ if (type != hctx_type &&
+ !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
return NULL;
if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf))
return NULL;
blk_status_t ret;
bio = blk_queue_bounce(bio, q);
- if (bio_may_exceed_limits(bio, &q->limits))
+ if (bio_may_exceed_limits(bio, &q->limits)) {
bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+ if (!bio)
+ return;
+ }
if (!bio_integrity_prep(bio))
return;
* blk_mq_destroy_queue - shutdown a request queue
* @q: request queue to shutdown
*
- * This shuts down a request queue allocated by blk_mq_init_queue() and drops
- * the initial reference. All future requests will failed with -ENODEV.
+ * This shuts down a request queue allocated by blk_mq_init_queue(). All future
+ * requests will be failed with -ENODEV. The caller is responsible for dropping
+ * the reference from blk_mq_init_queue() by calling blk_put_queue().
*
* Context: can sleep
*/
.dev_uevent = block_uevent,
};
+static char *block_devnode(struct device *dev, umode_t *mode,
+ kuid_t *uid, kgid_t *gid)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+
+ if (disk->fops->devnode)
+ return disk->fops->devnode(disk, mode);
+ return NULL;
+}
+
const struct device_type disk_type = {
.name = "disk",
.groups = disk_attr_groups,
.release = disk_release,
+ .devnode = block_devnode,
};
#ifdef CONFIG_PROC_FS
targets += blacklist_hash_list
quiet_cmd_extract_certs = CERT $@
- cmd_extract_certs = $(obj)/extract-cert $(extract-cert-in) $@
-extract-cert-in = $(or $(filter-out $(obj)/extract-cert, $(real-prereqs)),"")
+ cmd_extract_certs = $(obj)/extract-cert "$(extract-cert-in)" $@
+extract-cert-in = $(filter-out $(obj)/extract-cert, $(real-prereqs))
$(obj)/system_certificates.o: $(obj)/x509_certificate_list
{
struct tty_struct *tty = in_synth->dev;
+ if (tty == NULL)
+ return;
+
tty_lock(tty);
if (tty->ops->close)
static int only_lcd = -1;
module_param(only_lcd, int, 0444);
-/*
- * Display probing is known to take up to 5 seconds, so delay the fallback
- * backlight registration by 5 seconds + 3 seconds for some extra margin.
- */
-static int register_backlight_delay = 8;
+static int register_backlight_delay;
module_param(register_backlight_delay, int, 0444);
MODULE_PARM_DESC(register_backlight_delay,
"Delay in seconds before doing fallback (non GPU driver triggered) "
return false;
}
+/*
+ * At least one graphics driver has reported that no LCD is connected
+ * via the native interface. cancel the registration for fallback acpi_video0.
+ * If another driver still deems this necessary, it can explicitly register it.
+ */
+void acpi_video_report_nolcd(void)
+{
+ cancel_delayed_work(&video_bus_register_backlight_work);
+}
+EXPORT_SYMBOL(acpi_video_report_nolcd);
+
int acpi_video_register(void)
{
int ret = 0;
}
#define FIND_CHILD_MIN_SCORE 1
-#define FIND_CHILD_MAX_SCORE 2
+#define FIND_CHILD_MID_SCORE 2
+#define FIND_CHILD_MAX_SCORE 3
static int match_any(struct acpi_device *adev, void *not_used)
{
return -ENODEV;
status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta);
- if (status == AE_NOT_FOUND)
+ if (status == AE_NOT_FOUND) {
+ /*
+ * Special case: backlight device objects without _STA are
+ * preferred to other objects with the same _ADR value, because
+ * it is more likely that they are actually useful.
+ */
+ if (adev->pnp.type.backlight)
+ return FIND_CHILD_MID_SCORE;
+
return FIND_CHILD_MIN_SCORE;
+ }
if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
return -ENODEV;
mutex_lock(&acpi_desc->init_mutex);
set_bit(ARS_CANCEL, &acpi_desc->scrub_flags);
- cancel_delayed_work_sync(&acpi_desc->dwork);
mutex_unlock(&acpi_desc->init_mutex);
+ cancel_delayed_work_sync(&acpi_desc->dwork);
/*
* Bounce the nvdimm bus lock to make sure any in-flight
efi_status_t status;
struct prm_context_buffer context;
+ if (!efi_enabled(EFI_RUNTIME_SERVICES)) {
+ pr_err_ratelimited("PRM: EFI runtime services no longer available\n");
+ return AE_NO_HANDLER;
+ }
+
/*
* The returned acpi_status will always be AE_OK. Error values will be
* saved in the first byte of the PRM message buffer to be used by ASL.
pr_info("PRM: found %u modules\n", mc);
+ if (!efi_enabled(EFI_RUNTIME_SERVICES)) {
+ pr_err("PRM: EFI runtime services unavailable\n");
+ return;
+ }
+
status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT,
ACPI_ADR_SPACE_PLATFORM_RT,
&acpi_platformrt_space_handler,
DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"),
},
},
+ {
+ .ident = "Asus ExpertBook B2402CBA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "B2402CBA"),
+ },
+ },
+ {
+ .ident = "Asus ExpertBook B2502",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "B2502CBA"),
+ },
+ },
{ }
};
-static const struct dmi_system_id lenovo_82ra[] = {
+static const struct dmi_system_id lenovo_laptop[] = {
+ {
+ .ident = "LENOVO IdeaPad Flex 5 14ALC7",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "82R9"),
+ },
+ },
{
.ident = "LENOVO IdeaPad Flex 5 16ALC7",
.matches = {
{ }
};
+static const struct dmi_system_id schenker_gm_rg[] = {
+ {
+ .ident = "XMG CORE 15 (M22)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"),
+ DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"),
+ },
+ },
+ { }
+};
+
struct irq_override_cmp {
const struct dmi_system_id *system;
unsigned char irq;
static const struct irq_override_cmp override_table[] = {
{ medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
{ asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
- { lenovo_82ra, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
- { lenovo_82ra, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+ { lenovo_laptop, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+ { lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+ { schenker_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true },
};
static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity,
* Some devices don't reliably have _HIDs & _CIDs, so add
* synthetic HIDs to make sure drivers can find them.
*/
- if (acpi_is_video_device(handle))
+ if (acpi_is_video_device(handle)) {
acpi_add_id(pnp, ACPI_VIDEO_HID);
- else if (acpi_bay_match(handle))
+ pnp->type.backlight = 1;
+ break;
+ }
+ if (acpi_bay_match(handle))
acpi_add_id(pnp, ACPI_BAY_HID);
else if (acpi_dock_match(handle))
acpi_add_id(pnp, ACPI_DOCK_HID);
.priority = 0,
};
+#ifndef acpi_skip_set_wakeup_address
+#define acpi_skip_set_wakeup_address() false
+#endif
+
static int acpi_sleep_prepare(u32 acpi_state)
{
#ifdef CONFIG_ACPI_SLEEP
unsigned long acpi_wakeup_address;
/* do we have a wakeup address for S2 and S3? */
- if (acpi_state == ACPI_STATE_S3) {
+ if (acpi_state == ACPI_STATE_S3 && !acpi_skip_set_wakeup_address()) {
acpi_wakeup_address = acpi_get_wakeup_address();
if (!acpi_wakeup_address)
return -EFAULT;
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/platform_data/x86/nvidia-wmi-ec-backlight.h>
+#include <linux/pnp.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include <acpi/video.h>
acpi_backlight_cmdline = acpi_backlight_video;
if (!strcmp("native", acpi_video_backlight_string))
acpi_backlight_cmdline = acpi_backlight_native;
+ if (!strcmp("nvidia_wmi_ec", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec;
+ if (!strcmp("apple_gmux", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_apple_gmux;
if (!strcmp("none", acpi_video_backlight_string))
acpi_backlight_cmdline = acpi_backlight_none;
}
DMI_MATCH(DMI_PRODUCT_NAME, "Precision 7510"),
},
},
+ {
+ .callback = video_detect_force_native,
+ /* Acer Aspire 4810T */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 4810T"),
+ },
+ },
{
.callback = video_detect_force_native,
/* Acer Aspire 5738z */
DMI_MATCH(DMI_PRODUCT_NAME, "GA503"),
},
},
+ {
+ .callback = video_detect_force_native,
+ /* Asus U46E */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "U46E"),
+ },
+ },
{
.callback = video_detect_force_native,
/* Asus UX303UB */
DMI_MATCH(DMI_PRODUCT_NAME, "UX303UB"),
},
},
+ {
+ .callback = video_detect_force_native,
+ /* HP EliteBook 8460p */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8460p"),
+ },
+ },
+ {
+ .callback = video_detect_force_native,
+ /* HP Pavilion g6-1d80nr / B4U19UA */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion g6 Notebook PC"),
+ DMI_MATCH(DMI_PRODUCT_SKU, "B4U19UA"),
+ },
+ },
{
.callback = video_detect_force_native,
/* Samsung N150P */
{
static DEFINE_MUTEX(init_mutex);
static bool nvidia_wmi_ec_present;
+ static bool apple_gmux_present;
static bool native_available;
static bool init_done;
static long video_caps;
ACPI_UINT32_MAX, find_video, NULL,
&video_caps, NULL);
nvidia_wmi_ec_present = nvidia_wmi_ec_supported();
+ apple_gmux_present = apple_gmux_detect(NULL, NULL);
init_done = true;
}
if (native)
if (nvidia_wmi_ec_present)
return acpi_backlight_nvidia_wmi_ec;
- if (apple_gmux_present())
+ if (apple_gmux_present)
return acpi_backlight_apple_gmux;
/* Use ACPI video if available, except when native should be preferred. */
module_param(sleep_no_lps0, bool, 0644);
MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface");
-static bool prefer_microsoft_dsm_guid __read_mostly;
-module_param(prefer_microsoft_dsm_guid, bool, 0644);
-MODULE_PARM_DESC(prefer_microsoft_dsm_guid, "Prefer using Microsoft GUID in LPS0 device _DSM evaluation");
-
static const struct acpi_device_id lps0_device_ids[] = {
{"PNP0D80", },
{"", },
}
struct amd_lps0_hid_device_data {
- const unsigned int rev_id;
const bool check_off_by_one;
- const bool prefer_amd_guid;
};
static const struct amd_lps0_hid_device_data amd_picasso = {
- .rev_id = 0,
.check_off_by_one = true,
- .prefer_amd_guid = false,
};
static const struct amd_lps0_hid_device_data amd_cezanne = {
- .rev_id = 0,
- .check_off_by_one = false,
- .prefer_amd_guid = false,
-};
-
-static const struct amd_lps0_hid_device_data amd_rembrandt = {
- .rev_id = 2,
.check_off_by_one = false,
- .prefer_amd_guid = true,
};
static const struct acpi_device_id amd_hid_ids[] = {
{"AMD0005", (kernel_ulong_t)&amd_picasso, },
{"AMDI0005", (kernel_ulong_t)&amd_picasso, },
{"AMDI0006", (kernel_ulong_t)&amd_cezanne, },
- {"AMDI0007", (kernel_ulong_t)&amd_rembrandt, },
{}
};
-static int lps0_prefer_microsoft(const struct dmi_system_id *id)
+static int lps0_prefer_amd(const struct dmi_system_id *id)
{
- pr_debug("Preferring Microsoft GUID.\n");
- prefer_microsoft_dsm_guid = true;
+ pr_debug("Using AMD GUID w/ _REV 2.\n");
+ rev_id = 2;
return 0;
}
-
static const struct dmi_system_id s2idle_dmi_table[] __initconst = {
{
/*
- * ASUS TUF Gaming A17 FA707RE
- * https://bugzilla.kernel.org/show_bug.cgi?id=216101
- */
- .callback = lps0_prefer_microsoft,
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_MATCH(DMI_PRODUCT_NAME, "ASUS TUF Gaming A17"),
- },
- },
- {
- /* ASUS ROG Zephyrus G14 (2022) */
- .callback = lps0_prefer_microsoft,
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_MATCH(DMI_PRODUCT_NAME, "ROG Zephyrus G14 GA402"),
- },
- },
- {
- /*
- * Lenovo Yoga Slim 7 Pro X 14ARH7
- * https://bugzilla.kernel.org/show_bug.cgi?id=216473 : 82V2
- * https://bugzilla.kernel.org/show_bug.cgi?id=216438 : 82TL
- */
- .callback = lps0_prefer_microsoft,
- .matches = {
- DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
- DMI_MATCH(DMI_PRODUCT_NAME, "82"),
- },
- },
- {
- /*
- * ASUSTeK COMPUTER INC. ROG Flow X13 GV301RE_GV301RE
- * https://gitlab.freedesktop.org/drm/amd/-/issues/2148
+ * AMD Rembrandt based HP EliteBook 835/845/865 G9
+ * Contains specialized AML in AMD/_REV 2 path to avoid
+ * triggering a bug in Qualcomm WLAN firmware. This may be
+ * removed in the future if that firmware is fixed.
*/
- .callback = lps0_prefer_microsoft,
+ .callback = lps0_prefer_amd,
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X13 GV301"),
- },
- },
- {
- /*
- * ASUSTeK COMPUTER INC. ROG Flow X16 GV601RW_GV601RW
- * https://gitlab.freedesktop.org/drm/amd/-/issues/2148
- */
- .callback = lps0_prefer_microsoft,
- .matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X16 GV601"),
+ DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+ DMI_MATCH(DMI_BOARD_NAME, "8990"),
},
},
{}
if (dev_id->id[0])
data = (const struct amd_lps0_hid_device_data *) dev_id->driver_data;
else
- data = &amd_rembrandt;
- rev_id = data->rev_id;
+ data = &amd_cezanne;
lps0_dsm_func_mask = validate_dsm(adev->handle,
ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid);
if (lps0_dsm_func_mask > 0x3 && data->check_off_by_one) {
lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1;
acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n",
ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask);
- } else if (lps0_dsm_func_mask_microsoft > 0 && data->prefer_amd_guid &&
- !prefer_microsoft_dsm_guid) {
+ } else if (lps0_dsm_func_mask_microsoft > 0 && rev_id) {
lps0_dsm_func_mask_microsoft = -EINVAL;
acpi_handle_debug(adev->handle, "_DSM Using AMD method\n");
}
rev_id = 1;
lps0_dsm_func_mask = validate_dsm(adev->handle,
ACPI_LPS0_DSM_UUID, rev_id, &lps0_dsm_guid);
- if (!prefer_microsoft_dsm_guid)
- lps0_dsm_func_mask_microsoft = -EINVAL;
+ lps0_dsm_func_mask_microsoft = -EINVAL;
}
if (lps0_dsm_func_mask < 0 && lps0_dsm_func_mask_microsoft < 0)
config PATA_CS5535
tristate "CS5535 PATA support (Experimental)"
depends on PCI && (X86_32 || (X86_64 && COMPILE_TEST))
+ depends on !UML
help
This option enables support for the NatSemi/AMD CS5535
companion chip used with the Geode processor family.
static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
static void ahci_remove_one(struct pci_dev *dev);
static void ahci_shutdown_one(struct pci_dev *dev);
+static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hpriv);
static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
unsigned long deadline);
static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
{ PCI_VDEVICE(INTEL, 0x34d3), board_ahci_low_power }, /* Ice Lake LP AHCI */
{ PCI_VDEVICE(INTEL, 0x02d3), board_ahci_low_power }, /* Comet Lake PCH-U AHCI */
{ PCI_VDEVICE(INTEL, 0x02d7), board_ahci_low_power }, /* Comet Lake PCH RAID */
+ { PCI_VDEVICE(INTEL, 0xa0d3), board_ahci_low_power }, /* Tiger Lake UP{3,4} AHCI */
/* JMicron 360/1/3/5/6, match class to avoid IDE function */
{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
ahci_save_initial_config(&pdev->dev, hpriv);
}
+static int ahci_pci_reset_controller(struct ata_host *host)
+{
+ struct pci_dev *pdev = to_pci_dev(host->dev);
+ struct ahci_host_priv *hpriv = host->private_data;
+ int rc;
+
+ rc = ahci_reset_controller(host);
+ if (rc)
+ return rc;
+
+ /*
+ * If platform firmware failed to enable ports, try to enable
+ * them here.
+ */
+ ahci_intel_pcs_quirk(pdev, hpriv);
+
+ return 0;
+}
+
static void ahci_pci_init_controller(struct ata_host *host)
{
struct ahci_host_priv *hpriv = host->private_data;
struct ata_host *host = pci_get_drvdata(pdev);
int rc;
- rc = ahci_reset_controller(host);
+ rc = ahci_pci_reset_controller(host);
if (rc)
return rc;
ahci_pci_init_controller(host);
ahci_mcp89_apple_enable(pdev);
if (pdev->dev.power.power_state.event == PM_EVENT_SUSPEND) {
- rc = ahci_reset_controller(host);
+ rc = ahci_pci_reset_controller(host);
if (rc)
return rc;
/* save initial config */
ahci_pci_save_initial_config(pdev, hpriv);
- /*
- * If platform firmware failed to enable ports, try to enable
- * them here.
- */
- ahci_intel_pcs_quirk(pdev, hpriv);
-
/* prepare host */
if (hpriv->cap & HOST_CAP_NCQ) {
pi.flags |= ATA_FLAG_NCQ;
if (rc)
return rc;
- rc = ahci_reset_controller(host);
+ rc = ahci_pci_reset_controller(host);
if (rc)
return rc;
*/
if (spd > 1)
mask &= (1 << (spd - 1)) - 1;
- else
+ else if (link->sata_spd)
return -EINVAL;
/* were we already at the bottom? */
{ "Samsung SSD 870*", NULL, ATA_HORKAGE_NO_NCQ_TRIM |
ATA_HORKAGE_ZERO_AFTER_TRIM |
ATA_HORKAGE_NO_NCQ_ON_ATI },
+ { "SAMSUNG*MZ7LH*", NULL, ATA_HORKAGE_NO_NCQ_TRIM |
+ ATA_HORKAGE_ZERO_AFTER_TRIM |
+ ATA_HORKAGE_NO_NCQ_ON_ATI, },
{ "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM |
ATA_HORKAGE_ZERO_AFTER_TRIM },
MODULE_PARM_DESC(enable_dma,
"Enable use of DMA on interfaces that support it (0=no dma [default], 1=use dma)");
-/**
+/*
* Convert nanosecond based time to setting used in the
* boot bus timing register, based on timing multiple
*/
cvmx_write_csr(CVMX_MIO_BOOT_REG_CFGX(cs), reg_cfg.u64);
}
-/**
+/*
* Called after libata determines the needed PIO mode. This
* function programs the Octeon bootbus regions to support the
* timing requirements of the PIO mode.
cvmx_write_csr(cf_port->dma_base + DMA_TIM, dma_tim.u64);
}
-/**
+/*
* Handle an 8 bit I/O request.
*
* @qc: Queued command
return buflen;
}
-/**
+/*
* Handle a 16 bit I/O request.
*
* @qc: Queued command
return buflen;
}
-/**
+/*
* Read the taskfile for 16bit non-True IDE only.
*/
static void octeon_cf_tf_read16(struct ata_port *ap, struct ata_taskfile *tf)
return 0;
}
-/**
+/*
* Load the taskfile for 16bit non-True IDE only. The device_addr is
* not loaded, we do this as part of octeon_cf_exec_command16.
*/
ap->ops->sff_exec_command(ap, &qc->tf);
}
-/**
+/*
* Start a DMA transfer that was already setup
*
* @qc: Information about the DMA
cvmx_write_csr(cf_port->dma_base + DMA_CFG, mio_boot_dma_cfg.u64);
}
-/**
+/*
*
* LOCKING:
* spin_lock_irqsave(host lock)
fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
struct fwnode_handle *prev)
{
+ struct fwnode_handle *ep, *port_parent = NULL;
const struct fwnode_handle *parent;
- struct fwnode_handle *ep;
/*
* If this function is in a loop and the previous iteration returned
* an endpoint from fwnode->secondary, then we need to use the secondary
* as parent rather than @fwnode.
*/
- if (prev)
- parent = fwnode_graph_get_port_parent(prev);
- else
+ if (prev) {
+ port_parent = fwnode_graph_get_port_parent(prev);
+ parent = port_parent;
+ } else {
parent = fwnode;
+ }
if (IS_ERR_OR_NULL(parent))
return NULL;
ep = fwnode_call_ptr_op(parent, graph_get_next_endpoint, prev);
if (ep)
- return ep;
+ goto out_put_port_parent;
+
+ ep = fwnode_graph_get_next_endpoint(parent->secondary, NULL);
- return fwnode_graph_get_next_endpoint(parent->secondary, NULL);
+out_put_port_parent:
+ fwnode_handle_put(port_parent);
+ return ep;
}
EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
calltime = ktime_get();
for_each_online_cpu(cpu) {
nid = cpu_to_node(cpu);
- pdev = &sync_dev[sync_id];
+ pdev = &async_dev[async_id];
*pdev = test_platform_device_register_node("test_async_driver",
async_id,
The default value is 4096 kilobytes. Only change this if you know
what you are doing.
+config CDROM_PKTCDVD
+ tristate "Packet writing on CD/DVD media (DEPRECATED)"
+ depends on !UML
+ depends on SCSI
+ select CDROM
+ help
+ Note: This driver is deprecated and will be removed from the
+ kernel in the near future!
+
+ If you have a CDROM/DVD drive that supports packet writing, say
+ Y to include support. It should work with any MMC/Mt Fuji
+ compliant ATAPI or SCSI drive, which is just about any newer
+ DVD/CD writer.
+
+ Currently only writing to CD-RW, DVD-RW, DVD+RW and DVDRAM discs
+ is possible.
+ DVD-RW disks must be in restricted overwrite mode.
+
+ See the file <file:Documentation/cdrom/packet-writing.rst>
+ for further information on the use of this driver.
+
+ To compile this driver as a module, choose M here: the
+ module will be called pktcdvd.
+
+config CDROM_PKTCDVD_BUFFERS
+ int "Free buffers for data gathering"
+ depends on CDROM_PKTCDVD
+ default "8"
+ help
+ This controls the maximum number of active concurrent packets. More
+ concurrent packets can increase write performance, but also require
+ more memory. Each concurrent packet will require approximately 64Kb
+ of non-swappable kernel memory, memory which will be allocated when
+ a disc is opened for writing.
+
+config CDROM_PKTCDVD_WCACHE
+ bool "Enable write caching"
+ depends on CDROM_PKTCDVD
+ help
+ If enabled, write caching will be set for the CD-R/W device. For now
+ this option is dangerous unless the CD-RW media is known good, as we
+ don't do deferred write error handling yet.
+
config ATA_OVER_ETH
tristate "ATA over Ethernet support"
depends on NET
obj-$(CONFIG_N64CART) += n64cart.o
obj-$(CONFIG_BLK_DEV_RAM) += brd.o
obj-$(CONFIG_BLK_DEV_LOOP) += loop.o
+obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
obj-$(CONFIG_BLK_DEV_NBD) += nbd.o
struct drbd_device *device = bio->bi_bdev->bd_disk->private_data;
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
/*
* what we "blindly" assume:
--- /dev/null
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ * Copyright (C) 2006 Thomas Maier <balagi@justmail.de>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-RW, DVD+RW, DVD-RW and
+ * DVD-RAM devices.
+ *
+ * Theory of operation:
+ *
+ * At the lowest level, there is the standard driver for the CD/DVD device,
+ * such as drivers/scsi/sr.c. This driver can handle read and write requests,
+ * but it doesn't know anything about the special restrictions that apply to
+ * packet writing. One restriction is that write requests must be aligned to
+ * packet boundaries on the physical media, and the size of a write request
+ * must be equal to the packet size. Another restriction is that a
+ * GPCMD_FLUSH_CACHE command has to be issued to the drive before a read
+ * command, if the previous command was a write.
+ *
+ * The purpose of the packet writing driver is to hide these restrictions from
+ * higher layers, such as file systems, and present a block device that can be
+ * randomly read and written using 2kB-sized blocks.
+ *
+ * The lowest layer in the packet writing driver is the packet I/O scheduler.
+ * Its data is defined by the struct packet_iosched and includes two bio
+ * queues with pending read and write requests. These queues are processed
+ * by the pkt_iosched_process_queue() function. The write requests in this
+ * queue are already properly aligned and sized. This layer is responsible for
+ * issuing the flush cache commands and scheduling the I/O in a good order.
+ *
+ * The next layer transforms unaligned write requests to aligned writes. This
+ * transformation requires reading missing pieces of data from the underlying
+ * block device, assembling the pieces to full packets and queuing them to the
+ * packet I/O scheduler.
+ *
+ * At the top layer there is a custom ->submit_bio function that forwards
+ * read requests directly to the iosched queue and puts write requests in the
+ * unaligned write queue. A kernel thread performs the necessary read
+ * gathering to convert the unaligned writes to aligned writes and then feeds
+ * them to the packet I/O scheduler.
+ *
+ *************************************************************************/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/pktcdvd.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/compat.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/miscdevice.h>
+#include <linux/freezer.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/backing-dev.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_ioctl.h>
+#include <scsi/scsi.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/nospec.h>
+#include <linux/uaccess.h>
+
+#define DRIVER_NAME "pktcdvd"
+
+#define pkt_err(pd, fmt, ...) \
+ pr_err("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_notice(pd, fmt, ...) \
+ pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_info(pd, fmt, ...) \
+ pr_info("%s: " fmt, pd->name, ##__VA_ARGS__)
+
+#define pkt_dbg(level, pd, fmt, ...) \
+do { \
+ if (level == 2 && PACKET_DEBUG >= 2) \
+ pr_notice("%s: %s():" fmt, \
+ pd->name, __func__, ##__VA_ARGS__); \
+ else if (level == 1 && PACKET_DEBUG >= 1) \
+ pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \
+} while (0)
+
+#define MAX_SPEED 0xffff
+
+static DEFINE_MUTEX(pktcdvd_mutex);
+static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
+static struct proc_dir_entry *pkt_proc;
+static int pktdev_major;
+static int write_congestion_on = PKT_WRITE_CONGESTION_ON;
+static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
+static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */
+static mempool_t psd_pool;
+static struct bio_set pkt_bio_set;
+
+static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */
+static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
+
+/* forward declaration */
+static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev);
+static int pkt_remove_dev(dev_t pkt_dev);
+static int pkt_seq_show(struct seq_file *m, void *p);
+
+static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd)
+{
+ return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1);
+}
+
+/**********************************************************
+ * sysfs interface for pktcdvd
+ * by (C) 2006 Thomas Maier <balagi@justmail.de>
+
+ /sys/class/pktcdvd/pktcdvd[0-7]/
+ stat/reset
+ stat/packets_started
+ stat/packets_finished
+ stat/kb_written
+ stat/kb_read
+ stat/kb_read_gather
+ write_queue/size
+ write_queue/congestion_off
+ write_queue/congestion_on
+ **********************************************************/
+
+static ssize_t packets_started_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started);
+}
+static DEVICE_ATTR_RO(packets_started);
+
+static ssize_t packets_finished_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended);
+}
+static DEVICE_ATTR_RO(packets_finished);
+
+static ssize_t kb_written_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1);
+}
+static DEVICE_ATTR_RO(kb_written);
+
+static ssize_t kb_read_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1);
+}
+static DEVICE_ATTR_RO(kb_read);
+
+static ssize_t kb_read_gather_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1);
+}
+static DEVICE_ATTR_RO(kb_read_gather);
+
+static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ if (len > 0) {
+ pd->stats.pkt_started = 0;
+ pd->stats.pkt_ended = 0;
+ pd->stats.secs_w = 0;
+ pd->stats.secs_rg = 0;
+ pd->stats.secs_r = 0;
+ }
+ return len;
+}
+static DEVICE_ATTR_WO(reset);
+
+static struct attribute *pkt_stat_attrs[] = {
+ &dev_attr_packets_finished.attr,
+ &dev_attr_packets_started.attr,
+ &dev_attr_kb_read.attr,
+ &dev_attr_kb_written.attr,
+ &dev_attr_kb_read_gather.attr,
+ &dev_attr_reset.attr,
+ NULL,
+};
+
+static const struct attribute_group pkt_stat_group = {
+ .name = "stat",
+ .attrs = pkt_stat_attrs,
+};
+
+static ssize_t size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->bio_queue_size);
+ spin_unlock(&pd->lock);
+ return n;
+}
+static DEVICE_ATTR_RO(size);
+
+static void init_write_congestion_marks(int* lo, int* hi)
+{
+ if (*hi > 0) {
+ *hi = max(*hi, 500);
+ *hi = min(*hi, 1000000);
+ if (*lo <= 0)
+ *lo = *hi - 100;
+ else {
+ *lo = min(*lo, *hi - 100);
+ *lo = max(*lo, 100);
+ }
+ } else {
+ *hi = -1;
+ *lo = -1;
+ }
+}
+
+static ssize_t congestion_off_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->write_congestion_off);
+ spin_unlock(&pd->lock);
+ return n;
+}
+
+static ssize_t congestion_off_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int val;
+
+ if (sscanf(buf, "%d", &val) == 1) {
+ spin_lock(&pd->lock);
+ pd->write_congestion_off = val;
+ init_write_congestion_marks(&pd->write_congestion_off,
+ &pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ }
+ return len;
+}
+static DEVICE_ATTR_RW(congestion_off);
+
+static ssize_t congestion_on_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ return n;
+}
+
+static ssize_t congestion_on_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int val;
+
+ if (sscanf(buf, "%d", &val) == 1) {
+ spin_lock(&pd->lock);
+ pd->write_congestion_on = val;
+ init_write_congestion_marks(&pd->write_congestion_off,
+ &pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ }
+ return len;
+}
+static DEVICE_ATTR_RW(congestion_on);
+
+static struct attribute *pkt_wq_attrs[] = {
+ &dev_attr_congestion_on.attr,
+ &dev_attr_congestion_off.attr,
+ &dev_attr_size.attr,
+ NULL,
+};
+
+static const struct attribute_group pkt_wq_group = {
+ .name = "write_queue",
+ .attrs = pkt_wq_attrs,
+};
+
+static const struct attribute_group *pkt_groups[] = {
+ &pkt_stat_group,
+ &pkt_wq_group,
+ NULL,
+};
+
+static void pkt_sysfs_dev_new(struct pktcdvd_device *pd)
+{
+ if (class_pktcdvd) {
+ pd->dev = device_create_with_groups(class_pktcdvd, NULL,
+ MKDEV(0, 0), pd, pkt_groups,
+ "%s", pd->name);
+ if (IS_ERR(pd->dev))
+ pd->dev = NULL;
+ }
+}
+
+static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd)
+{
+ if (class_pktcdvd)
+ device_unregister(pd->dev);
+}
+
+
+/********************************************************************
+ /sys/class/pktcdvd/
+ add map block device
+ remove unmap packet dev
+ device_map show mappings
+ *******************************************************************/
+
+static void class_pktcdvd_release(struct class *cls)
+{
+ kfree(cls);
+}
+
+static ssize_t device_map_show(struct class *c, struct class_attribute *attr,
+ char *data)
+{
+ int n = 0;
+ int idx;
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+ for (idx = 0; idx < MAX_WRITERS; idx++) {
+ struct pktcdvd_device *pd = pkt_devs[idx];
+ if (!pd)
+ continue;
+ n += sprintf(data+n, "%s %u:%u %u:%u\n",
+ pd->name,
+ MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev),
+ MAJOR(pd->bdev->bd_dev),
+ MINOR(pd->bdev->bd_dev));
+ }
+ mutex_unlock(&ctl_mutex);
+ return n;
+}
+static CLASS_ATTR_RO(device_map);
+
+static ssize_t add_store(struct class *c, struct class_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned int major, minor;
+
+ if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
+ /* pkt_setup_dev() expects caller to hold reference to self */
+ if (!try_module_get(THIS_MODULE))
+ return -ENODEV;
+
+ pkt_setup_dev(MKDEV(major, minor), NULL);
+
+ module_put(THIS_MODULE);
+
+ return count;
+ }
+
+ return -EINVAL;
+}
+static CLASS_ATTR_WO(add);
+
+static ssize_t remove_store(struct class *c, struct class_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned int major, minor;
+ if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
+ pkt_remove_dev(MKDEV(major, minor));
+ return count;
+ }
+ return -EINVAL;
+}
+static CLASS_ATTR_WO(remove);
+
+static struct attribute *class_pktcdvd_attrs[] = {
+ &class_attr_add.attr,
+ &class_attr_remove.attr,
+ &class_attr_device_map.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(class_pktcdvd);
+
+static int pkt_sysfs_init(void)
+{
+ int ret = 0;
+
+ /*
+ * create control files in sysfs
+ * /sys/class/pktcdvd/...
+ */
+ class_pktcdvd = kzalloc(sizeof(*class_pktcdvd), GFP_KERNEL);
+ if (!class_pktcdvd)
+ return -ENOMEM;
+ class_pktcdvd->name = DRIVER_NAME;
+ class_pktcdvd->owner = THIS_MODULE;
+ class_pktcdvd->class_release = class_pktcdvd_release;
+ class_pktcdvd->class_groups = class_pktcdvd_groups;
+ ret = class_register(class_pktcdvd);
+ if (ret) {
+ kfree(class_pktcdvd);
+ class_pktcdvd = NULL;
+ pr_err("failed to create class pktcdvd\n");
+ return ret;
+ }
+ return 0;
+}
+
+static void pkt_sysfs_cleanup(void)
+{
+ if (class_pktcdvd)
+ class_destroy(class_pktcdvd);
+ class_pktcdvd = NULL;
+}
+
+/********************************************************************
+ entries in debugfs
+
+ /sys/kernel/debug/pktcdvd[0-7]/
+ info
+
+ *******************************************************************/
+
+static int pkt_debugfs_seq_show(struct seq_file *m, void *p)
+{
+ return pkt_seq_show(m, p);
+}
+
+static int pkt_debugfs_fops_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, pkt_debugfs_seq_show, inode->i_private);
+}
+
+static const struct file_operations debug_fops = {
+ .open = pkt_debugfs_fops_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .owner = THIS_MODULE,
+};
+
+static void pkt_debugfs_dev_new(struct pktcdvd_device *pd)
+{
+ if (!pkt_debugfs_root)
+ return;
+ pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root);
+ if (!pd->dfs_d_root)
+ return;
+
+ pd->dfs_f_info = debugfs_create_file("info", 0444,
+ pd->dfs_d_root, pd, &debug_fops);
+}
+
+static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd)
+{
+ if (!pkt_debugfs_root)
+ return;
+ debugfs_remove(pd->dfs_f_info);
+ debugfs_remove(pd->dfs_d_root);
+ pd->dfs_f_info = NULL;
+ pd->dfs_d_root = NULL;
+}
+
+static void pkt_debugfs_init(void)
+{
+ pkt_debugfs_root = debugfs_create_dir(DRIVER_NAME, NULL);
+}
+
+static void pkt_debugfs_cleanup(void)
+{
+ debugfs_remove(pkt_debugfs_root);
+ pkt_debugfs_root = NULL;
+}
+
+/* ----------------------------------------------------------*/
+
+
+static void pkt_bio_finished(struct pktcdvd_device *pd)
+{
+ BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0);
+ if (atomic_dec_and_test(&pd->cdrw.pending_bios)) {
+ pkt_dbg(2, pd, "queue empty\n");
+ atomic_set(&pd->iosched.attention, 1);
+ wake_up(&pd->wqueue);
+ }
+}
+
+/*
+ * Allocate a packet_data struct
+ */
+static struct packet_data *pkt_alloc_packet_data(int frames)
+{
+ int i;
+ struct packet_data *pkt;
+
+ pkt = kzalloc(sizeof(struct packet_data), GFP_KERNEL);
+ if (!pkt)
+ goto no_pkt;
+
+ pkt->frames = frames;
+ pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL);
+ if (!pkt->w_bio)
+ goto no_bio;
+
+ for (i = 0; i < frames / FRAMES_PER_PAGE; i++) {
+ pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
+ if (!pkt->pages[i])
+ goto no_page;
+ }
+
+ spin_lock_init(&pkt->lock);
+ bio_list_init(&pkt->orig_bios);
+
+ for (i = 0; i < frames; i++) {
+ pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL);
+ if (!pkt->r_bios[i])
+ goto no_rd_bio;
+ }
+
+ return pkt;
+
+no_rd_bio:
+ for (i = 0; i < frames; i++)
+ kfree(pkt->r_bios[i]);
+no_page:
+ for (i = 0; i < frames / FRAMES_PER_PAGE; i++)
+ if (pkt->pages[i])
+ __free_page(pkt->pages[i]);
+ kfree(pkt->w_bio);
+no_bio:
+ kfree(pkt);
+no_pkt:
+ return NULL;
+}
+
+/*
+ * Free a packet_data struct
+ */
+static void pkt_free_packet_data(struct packet_data *pkt)
+{
+ int i;
+
+ for (i = 0; i < pkt->frames; i++)
+ kfree(pkt->r_bios[i]);
+ for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++)
+ __free_page(pkt->pages[i]);
+ kfree(pkt->w_bio);
+ kfree(pkt);
+}
+
+static void pkt_shrink_pktlist(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *next;
+
+ BUG_ON(!list_empty(&pd->cdrw.pkt_active_list));
+
+ list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) {
+ pkt_free_packet_data(pkt);
+ }
+ INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
+}
+
+static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets)
+{
+ struct packet_data *pkt;
+
+ BUG_ON(!list_empty(&pd->cdrw.pkt_free_list));
+
+ while (nr_packets > 0) {
+ pkt = pkt_alloc_packet_data(pd->settings.size >> 2);
+ if (!pkt) {
+ pkt_shrink_pktlist(pd);
+ return 0;
+ }
+ pkt->id = nr_packets;
+ pkt->pd = pd;
+ list_add(&pkt->list, &pd->cdrw.pkt_free_list);
+ nr_packets--;
+ }
+ return 1;
+}
+
+static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
+{
+ struct rb_node *n = rb_next(&node->rb_node);
+ if (!n)
+ return NULL;
+ return rb_entry(n, struct pkt_rb_node, rb_node);
+}
+
+static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
+{
+ rb_erase(&node->rb_node, &pd->bio_queue);
+ mempool_free(node, &pd->rb_pool);
+ pd->bio_queue_size--;
+ BUG_ON(pd->bio_queue_size < 0);
+}
+
+/*
+ * Find the first node in the pd->bio_queue rb tree with a starting sector >= s.
+ */
+static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s)
+{
+ struct rb_node *n = pd->bio_queue.rb_node;
+ struct rb_node *next;
+ struct pkt_rb_node *tmp;
+
+ if (!n) {
+ BUG_ON(pd->bio_queue_size > 0);
+ return NULL;
+ }
+
+ for (;;) {
+ tmp = rb_entry(n, struct pkt_rb_node, rb_node);
+ if (s <= tmp->bio->bi_iter.bi_sector)
+ next = n->rb_left;
+ else
+ next = n->rb_right;
+ if (!next)
+ break;
+ n = next;
+ }
+
+ if (s > tmp->bio->bi_iter.bi_sector) {
+ tmp = pkt_rbtree_next(tmp);
+ if (!tmp)
+ return NULL;
+ }
+ BUG_ON(s > tmp->bio->bi_iter.bi_sector);
+ return tmp;
+}
+
+/*
+ * Insert a node into the pd->bio_queue rb tree.
+ */
+static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *node)
+{
+ struct rb_node **p = &pd->bio_queue.rb_node;
+ struct rb_node *parent = NULL;
+ sector_t s = node->bio->bi_iter.bi_sector;
+ struct pkt_rb_node *tmp;
+
+ while (*p) {
+ parent = *p;
+ tmp = rb_entry(parent, struct pkt_rb_node, rb_node);
+ if (s < tmp->bio->bi_iter.bi_sector)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+ rb_link_node(&node->rb_node, parent, p);
+ rb_insert_color(&node->rb_node, &pd->bio_queue);
+ pd->bio_queue_size++;
+}
+
+/*
+ * Send a packet_command to the underlying block device and
+ * wait for completion.
+ */
+static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
+{
+ struct request_queue *q = bdev_get_queue(pd->bdev);
+ struct scsi_cmnd *scmd;
+ struct request *rq;
+ int ret = 0;
+
+ rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
+ REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
+ scmd = blk_mq_rq_to_pdu(rq);
+
+ if (cgc->buflen) {
+ ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
+ GFP_NOIO);
+ if (ret)
+ goto out;
+ }
+
+ scmd->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
+ memcpy(scmd->cmnd, cgc->cmd, CDROM_PACKET_SIZE);
+
+ rq->timeout = 60*HZ;
+ if (cgc->quiet)
+ rq->rq_flags |= RQF_QUIET;
+
+ blk_execute_rq(rq, false);
+ if (scmd->result)
+ ret = -EIO;
+out:
+ blk_mq_free_request(rq);
+ return ret;
+}
+
+static const char *sense_key_string(__u8 index)
+{
+ static const char * const info[] = {
+ "No sense", "Recovered error", "Not ready",
+ "Medium error", "Hardware error", "Illegal request",
+ "Unit attention", "Data protect", "Blank check",
+ };
+
+ return index < ARRAY_SIZE(info) ? info[index] : "INVALID";
+}
+
+/*
+ * A generic sense dump / resolve mechanism should be implemented across
+ * all ATAPI + SCSI devices.
+ */
+static void pkt_dump_sense(struct pktcdvd_device *pd,
+ struct packet_command *cgc)
+{
+ struct scsi_sense_hdr *sshdr = cgc->sshdr;
+
+ if (sshdr)
+ pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
+ CDROM_PACKET_SIZE, cgc->cmd,
+ sshdr->sense_key, sshdr->asc, sshdr->ascq,
+ sense_key_string(sshdr->sense_key));
+ else
+ pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
+}
+
+/*
+ * flush the drive cache to media
+ */
+static int pkt_flush_cache(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.cmd[0] = GPCMD_FLUSH_CACHE;
+ cgc.quiet = 1;
+
+ /*
+ * the IMMED bit -- we default to not setting it, although that
+ * would allow a much faster close, this is safer
+ */
+#if 0
+ cgc.cmd[1] = 1 << 1;
+#endif
+ return pkt_generic_packet(pd, &cgc);
+}
+
+/*
+ * speed is given as the normal factor, e.g. 4 for 4x
+ */
+static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
+ unsigned write_speed, unsigned read_speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ int ret;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_SET_SPEED;
+ cgc.cmd[2] = (read_speed >> 8) & 0xff;
+ cgc.cmd[3] = read_speed & 0xff;
+ cgc.cmd[4] = (write_speed >> 8) & 0xff;
+ cgc.cmd[5] = write_speed & 0xff;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ pkt_dump_sense(pd, &cgc);
+
+ return ret;
+}
+
+/*
+ * Queue a bio for processing by the low-level CD device. Must be called
+ * from process context.
+ */
+static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
+{
+ spin_lock(&pd->iosched.lock);
+ if (bio_data_dir(bio) == READ)
+ bio_list_add(&pd->iosched.read_queue, bio);
+ else
+ bio_list_add(&pd->iosched.write_queue, bio);
+ spin_unlock(&pd->iosched.lock);
+
+ atomic_set(&pd->iosched.attention, 1);
+ wake_up(&pd->wqueue);
+}
+
+/*
+ * Process the queued read/write requests. This function handles special
+ * requirements for CDRW drives:
+ * - A cache flush command must be inserted before a read request if the
+ * previous request was a write.
+ * - Switching between reading and writing is slow, so don't do it more often
+ * than necessary.
+ * - Optimize for throughput at the expense of latency. This means that streaming
+ * writes will never be interrupted by a read, but if the drive has to seek
+ * before the next write, switch to reading instead if there are any pending
+ * read requests.
+ * - Set the read speed according to current usage pattern. When only reading
+ * from the device, it's best to use the highest possible read speed, but
+ * when switching often between reading and writing, it's better to have the
+ * same read and write speeds.
+ */
+static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
+{
+
+ if (atomic_read(&pd->iosched.attention) == 0)
+ return;
+ atomic_set(&pd->iosched.attention, 0);
+
+ for (;;) {
+ struct bio *bio;
+ int reads_queued, writes_queued;
+
+ spin_lock(&pd->iosched.lock);
+ reads_queued = !bio_list_empty(&pd->iosched.read_queue);
+ writes_queued = !bio_list_empty(&pd->iosched.write_queue);
+ spin_unlock(&pd->iosched.lock);
+
+ if (!reads_queued && !writes_queued)
+ break;
+
+ if (pd->iosched.writing) {
+ int need_write_seek = 1;
+ spin_lock(&pd->iosched.lock);
+ bio = bio_list_peek(&pd->iosched.write_queue);
+ spin_unlock(&pd->iosched.lock);
+ if (bio && (bio->bi_iter.bi_sector ==
+ pd->iosched.last_write))
+ need_write_seek = 0;
+ if (need_write_seek && reads_queued) {
+ if (atomic_read(&pd->cdrw.pending_bios) > 0) {
+ pkt_dbg(2, pd, "write, waiting\n");
+ break;
+ }
+ pkt_flush_cache(pd);
+ pd->iosched.writing = 0;
+ }
+ } else {
+ if (!reads_queued && writes_queued) {
+ if (atomic_read(&pd->cdrw.pending_bios) > 0) {
+ pkt_dbg(2, pd, "read, waiting\n");
+ break;
+ }
+ pd->iosched.writing = 1;
+ }
+ }
+
+ spin_lock(&pd->iosched.lock);
+ if (pd->iosched.writing)
+ bio = bio_list_pop(&pd->iosched.write_queue);
+ else
+ bio = bio_list_pop(&pd->iosched.read_queue);
+ spin_unlock(&pd->iosched.lock);
+
+ if (!bio)
+ continue;
+
+ if (bio_data_dir(bio) == READ)
+ pd->iosched.successive_reads +=
+ bio->bi_iter.bi_size >> 10;
+ else {
+ pd->iosched.successive_reads = 0;
+ pd->iosched.last_write = bio_end_sector(bio);
+ }
+ if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) {
+ if (pd->read_speed == pd->write_speed) {
+ pd->read_speed = MAX_SPEED;
+ pkt_set_speed(pd, pd->write_speed, pd->read_speed);
+ }
+ } else {
+ if (pd->read_speed != pd->write_speed) {
+ pd->read_speed = pd->write_speed;
+ pkt_set_speed(pd, pd->write_speed, pd->read_speed);
+ }
+ }
+
+ atomic_inc(&pd->cdrw.pending_bios);
+ submit_bio_noacct(bio);
+ }
+}
+
+/*
+ * Special care is needed if the underlying block device has a small
+ * max_phys_segments value.
+ */
+static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
+{
+ if ((pd->settings.size << 9) / CD_FRAMESIZE
+ <= queue_max_segments(q)) {
+ /*
+ * The cdrom device can handle one segment/frame
+ */
+ clear_bit(PACKET_MERGE_SEGS, &pd->flags);
+ return 0;
+ } else if ((pd->settings.size << 9) / PAGE_SIZE
+ <= queue_max_segments(q)) {
+ /*
+ * We can handle this case at the expense of some extra memory
+ * copies during write operations
+ */
+ set_bit(PACKET_MERGE_SEGS, &pd->flags);
+ return 0;
+ } else {
+ pkt_err(pd, "cdrom max_phys_segments too small\n");
+ return -EIO;
+ }
+}
+
+static void pkt_end_io_read(struct bio *bio)
+{
+ struct packet_data *pkt = bio->bi_private;
+ struct pktcdvd_device *pd = pkt->pd;
+ BUG_ON(!pd);
+
+ pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
+ bio, (unsigned long long)pkt->sector,
+ (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status);
+
+ if (bio->bi_status)
+ atomic_inc(&pkt->io_errors);
+ bio_uninit(bio);
+ if (atomic_dec_and_test(&pkt->io_wait)) {
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+ }
+ pkt_bio_finished(pd);
+}
+
+static void pkt_end_io_packet_write(struct bio *bio)
+{
+ struct packet_data *pkt = bio->bi_private;
+ struct pktcdvd_device *pd = pkt->pd;
+ BUG_ON(!pd);
+
+ pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status);
+
+ pd->stats.pkt_ended++;
+
+ bio_uninit(bio);
+ pkt_bio_finished(pd);
+ atomic_dec(&pkt->io_wait);
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+}
+
+/*
+ * Schedule reads for the holes in a packet
+ */
+static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ int frames_read = 0;
+ struct bio *bio;
+ int f;
+ char written[PACKET_MAX_SIZE];
+
+ BUG_ON(bio_list_empty(&pkt->orig_bios));
+
+ atomic_set(&pkt->io_wait, 0);
+ atomic_set(&pkt->io_errors, 0);
+
+ /*
+ * Figure out which frames we need to read before we can write.
+ */
+ memset(written, 0, sizeof(written));
+ spin_lock(&pkt->lock);
+ bio_list_for_each(bio, &pkt->orig_bios) {
+ int first_frame = (bio->bi_iter.bi_sector - pkt->sector) /
+ (CD_FRAMESIZE >> 9);
+ int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE;
+ pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9);
+ BUG_ON(first_frame < 0);
+ BUG_ON(first_frame + num_frames > pkt->frames);
+ for (f = first_frame; f < first_frame + num_frames; f++)
+ written[f] = 1;
+ }
+ spin_unlock(&pkt->lock);
+
+ if (pkt->cache_valid) {
+ pkt_dbg(2, pd, "zone %llx cached\n",
+ (unsigned long long)pkt->sector);
+ goto out_account;
+ }
+
+ /*
+ * Schedule reads for missing parts of the packet.
+ */
+ for (f = 0; f < pkt->frames; f++) {
+ int p, offset;
+
+ if (written[f])
+ continue;
+
+ bio = pkt->r_bios[f];
+ bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ);
+ bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
+ bio->bi_end_io = pkt_end_io_read;
+ bio->bi_private = pkt;
+
+ p = (f * CD_FRAMESIZE) / PAGE_SIZE;
+ offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+ pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n",
+ f, pkt->pages[p], offset);
+ if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset))
+ BUG();
+
+ atomic_inc(&pkt->io_wait);
+ pkt_queue_bio(pd, bio);
+ frames_read++;
+ }
+
+out_account:
+ pkt_dbg(2, pd, "need %d frames for zone %llx\n",
+ frames_read, (unsigned long long)pkt->sector);
+ pd->stats.pkt_started++;
+ pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9);
+}
+
+/*
+ * Find a packet matching zone, or the least recently used packet if
+ * there is no match.
+ */
+static struct packet_data *pkt_get_packet_data(struct pktcdvd_device *pd, int zone)
+{
+ struct packet_data *pkt;
+
+ list_for_each_entry(pkt, &pd->cdrw.pkt_free_list, list) {
+ if (pkt->sector == zone || pkt->list.next == &pd->cdrw.pkt_free_list) {
+ list_del_init(&pkt->list);
+ if (pkt->sector != zone)
+ pkt->cache_valid = 0;
+ return pkt;
+ }
+ }
+ BUG();
+ return NULL;
+}
+
+static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ if (pkt->cache_valid) {
+ list_add(&pkt->list, &pd->cdrw.pkt_free_list);
+ } else {
+ list_add_tail(&pkt->list, &pd->cdrw.pkt_free_list);
+ }
+}
+
+static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state)
+{
+#if PACKET_DEBUG > 1
+ static const char *state_name[] = {
+ "IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED"
+ };
+ enum packet_data_state old_state = pkt->state;
+ pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n",
+ pkt->id, (unsigned long long)pkt->sector,
+ state_name[old_state], state_name[state]);
+#endif
+ pkt->state = state;
+}
+
+/*
+ * Scan the work queue to see if we can start a new packet.
+ * returns non-zero if any work was done.
+ */
+static int pkt_handle_queue(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *p;
+ struct bio *bio = NULL;
+ sector_t zone = 0; /* Suppress gcc warning */
+ struct pkt_rb_node *node, *first_node;
+ struct rb_node *n;
+
+ atomic_set(&pd->scan_queue, 0);
+
+ if (list_empty(&pd->cdrw.pkt_free_list)) {
+ pkt_dbg(2, pd, "no pkt\n");
+ return 0;
+ }
+
+ /*
+ * Try to find a zone we are not already working on.
+ */
+ spin_lock(&pd->lock);
+ first_node = pkt_rbtree_find(pd, pd->current_sector);
+ if (!first_node) {
+ n = rb_first(&pd->bio_queue);
+ if (n)
+ first_node = rb_entry(n, struct pkt_rb_node, rb_node);
+ }
+ node = first_node;
+ while (node) {
+ bio = node->bio;
+ zone = get_zone(bio->bi_iter.bi_sector, pd);
+ list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
+ if (p->sector == zone) {
+ bio = NULL;
+ goto try_next_bio;
+ }
+ }
+ break;
+try_next_bio:
+ node = pkt_rbtree_next(node);
+ if (!node) {
+ n = rb_first(&pd->bio_queue);
+ if (n)
+ node = rb_entry(n, struct pkt_rb_node, rb_node);
+ }
+ if (node == first_node)
+ node = NULL;
+ }
+ spin_unlock(&pd->lock);
+ if (!bio) {
+ pkt_dbg(2, pd, "no bio\n");
+ return 0;
+ }
+
+ pkt = pkt_get_packet_data(pd, zone);
+
+ pd->current_sector = zone + pd->settings.size;
+ pkt->sector = zone;
+ BUG_ON(pkt->frames != pd->settings.size >> 2);
+ pkt->write_size = 0;
+
+ /*
+ * Scan work queue for bios in the same zone and link them
+ * to this packet.
+ */
+ spin_lock(&pd->lock);
+ pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone);
+ while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
+ bio = node->bio;
+ pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long)
+ get_zone(bio->bi_iter.bi_sector, pd));
+ if (get_zone(bio->bi_iter.bi_sector, pd) != zone)
+ break;
+ pkt_rbtree_erase(pd, node);
+ spin_lock(&pkt->lock);
+ bio_list_add(&pkt->orig_bios, bio);
+ pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE;
+ spin_unlock(&pkt->lock);
+ }
+ /* check write congestion marks, and if bio_queue_size is
+ * below, wake up any waiters
+ */
+ if (pd->congested &&
+ pd->bio_queue_size <= pd->write_congestion_off) {
+ pd->congested = false;
+ wake_up_var(&pd->congested);
+ }
+ spin_unlock(&pd->lock);
+
+ pkt->sleep_time = max(PACKET_WAIT_TIME, 1);
+ pkt_set_state(pkt, PACKET_WAITING_STATE);
+ atomic_set(&pkt->run_sm, 1);
+
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_add(&pkt->list, &pd->cdrw.pkt_active_list);
+ spin_unlock(&pd->cdrw.active_list_lock);
+
+ return 1;
+}
+
+/**
+ * bio_list_copy_data - copy contents of data buffers from one chain of bios to
+ * another
+ * @src: source bio list
+ * @dst: destination bio list
+ *
+ * Stops when it reaches the end of either the @src list or @dst list - that is,
+ * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
+ * bios).
+ */
+static void bio_list_copy_data(struct bio *dst, struct bio *src)
+{
+ struct bvec_iter src_iter = src->bi_iter;
+ struct bvec_iter dst_iter = dst->bi_iter;
+
+ while (1) {
+ if (!src_iter.bi_size) {
+ src = src->bi_next;
+ if (!src)
+ break;
+
+ src_iter = src->bi_iter;
+ }
+
+ if (!dst_iter.bi_size) {
+ dst = dst->bi_next;
+ if (!dst)
+ break;
+
+ dst_iter = dst->bi_iter;
+ }
+
+ bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
+ }
+}
+
+/*
+ * Assemble a bio to write one packet and queue the bio for processing
+ * by the underlying block device.
+ */
+static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ int f;
+
+ bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames,
+ REQ_OP_WRITE);
+ pkt->w_bio->bi_iter.bi_sector = pkt->sector;
+ pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
+ pkt->w_bio->bi_private = pkt;
+
+ /* XXX: locking? */
+ for (f = 0; f < pkt->frames; f++) {
+ struct page *page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE];
+ unsigned offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+
+ if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset))
+ BUG();
+ }
+ pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt);
+
+ /*
+ * Fill-in bvec with data from orig_bios.
+ */
+ spin_lock(&pkt->lock);
+ bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head);
+
+ pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
+ spin_unlock(&pkt->lock);
+
+ pkt_dbg(2, pd, "Writing %d frames for zone %llx\n",
+ pkt->write_size, (unsigned long long)pkt->sector);
+
+ if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames))
+ pkt->cache_valid = 1;
+ else
+ pkt->cache_valid = 0;
+
+ /* Start the write request */
+ atomic_set(&pkt->io_wait, 1);
+ pkt_queue_bio(pd, pkt->w_bio);
+}
+
+static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status)
+{
+ struct bio *bio;
+
+ if (status)
+ pkt->cache_valid = 0;
+
+ /* Finish all bios corresponding to this packet */
+ while ((bio = bio_list_pop(&pkt->orig_bios))) {
+ bio->bi_status = status;
+ bio_endio(bio);
+ }
+}
+
+static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ pkt_dbg(2, pd, "pkt %d\n", pkt->id);
+
+ for (;;) {
+ switch (pkt->state) {
+ case PACKET_WAITING_STATE:
+ if ((pkt->write_size < pkt->frames) && (pkt->sleep_time > 0))
+ return;
+
+ pkt->sleep_time = 0;
+ pkt_gather_data(pd, pkt);
+ pkt_set_state(pkt, PACKET_READ_WAIT_STATE);
+ break;
+
+ case PACKET_READ_WAIT_STATE:
+ if (atomic_read(&pkt->io_wait) > 0)
+ return;
+
+ if (atomic_read(&pkt->io_errors) > 0) {
+ pkt_set_state(pkt, PACKET_RECOVERY_STATE);
+ } else {
+ pkt_start_write(pd, pkt);
+ }
+ break;
+
+ case PACKET_WRITE_WAIT_STATE:
+ if (atomic_read(&pkt->io_wait) > 0)
+ return;
+
+ if (!pkt->w_bio->bi_status) {
+ pkt_set_state(pkt, PACKET_FINISHED_STATE);
+ } else {
+ pkt_set_state(pkt, PACKET_RECOVERY_STATE);
+ }
+ break;
+
+ case PACKET_RECOVERY_STATE:
+ pkt_dbg(2, pd, "No recovery possible\n");
+ pkt_set_state(pkt, PACKET_FINISHED_STATE);
+ break;
+
+ case PACKET_FINISHED_STATE:
+ pkt_finish_packet(pkt, pkt->w_bio->bi_status);
+ return;
+
+ default:
+ BUG();
+ break;
+ }
+ }
+}
+
+static void pkt_handle_packets(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *next;
+
+ /*
+ * Run state machine for active packets
+ */
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (atomic_read(&pkt->run_sm) > 0) {
+ atomic_set(&pkt->run_sm, 0);
+ pkt_run_state_machine(pd, pkt);
+ }
+ }
+
+ /*
+ * Move no longer active packets to the free list
+ */
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->state == PACKET_FINISHED_STATE) {
+ list_del(&pkt->list);
+ pkt_put_packet_data(pd, pkt);
+ pkt_set_state(pkt, PACKET_IDLE_STATE);
+ atomic_set(&pd->scan_queue, 1);
+ }
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+}
+
+static void pkt_count_states(struct pktcdvd_device *pd, int *states)
+{
+ struct packet_data *pkt;
+ int i;
+
+ for (i = 0; i < PACKET_NUM_STATES; i++)
+ states[i] = 0;
+
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ states[pkt->state]++;
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+}
+
+/*
+ * kcdrwd is woken up when writes have been queued for one of our
+ * registered devices
+ */
+static int kcdrwd(void *foobar)
+{
+ struct pktcdvd_device *pd = foobar;
+ struct packet_data *pkt;
+ long min_sleep_time, residue;
+
+ set_user_nice(current, MIN_NICE);
+ set_freezable();
+
+ for (;;) {
+ DECLARE_WAITQUEUE(wait, current);
+
+ /*
+ * Wait until there is something to do
+ */
+ add_wait_queue(&pd->wqueue, &wait);
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /* Check if we need to run pkt_handle_queue */
+ if (atomic_read(&pd->scan_queue) > 0)
+ goto work_to_do;
+
+ /* Check if we need to run the state machine for some packet */
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (atomic_read(&pkt->run_sm) > 0)
+ goto work_to_do;
+ }
+
+ /* Check if we need to process the iosched queues */
+ if (atomic_read(&pd->iosched.attention) != 0)
+ goto work_to_do;
+
+ /* Otherwise, go to sleep */
+ if (PACKET_DEBUG > 1) {
+ int states[PACKET_NUM_STATES];
+ pkt_count_states(pd, states);
+ pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+ states[0], states[1], states[2],
+ states[3], states[4], states[5]);
+ }
+
+ min_sleep_time = MAX_SCHEDULE_TIMEOUT;
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->sleep_time && pkt->sleep_time < min_sleep_time)
+ min_sleep_time = pkt->sleep_time;
+ }
+
+ pkt_dbg(2, pd, "sleeping\n");
+ residue = schedule_timeout(min_sleep_time);
+ pkt_dbg(2, pd, "wake up\n");
+
+ /* make swsusp happy with our thread */
+ try_to_freeze();
+
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (!pkt->sleep_time)
+ continue;
+ pkt->sleep_time -= min_sleep_time - residue;
+ if (pkt->sleep_time <= 0) {
+ pkt->sleep_time = 0;
+ atomic_inc(&pkt->run_sm);
+ }
+ }
+
+ if (kthread_should_stop())
+ break;
+ }
+work_to_do:
+ set_current_state(TASK_RUNNING);
+ remove_wait_queue(&pd->wqueue, &wait);
+
+ if (kthread_should_stop())
+ break;
+
+ /*
+ * if pkt_handle_queue returns true, we can queue
+ * another request.
+ */
+ while (pkt_handle_queue(pd))
+ ;
+
+ /*
+ * Handle packet state machine
+ */
+ pkt_handle_packets(pd);
+
+ /*
+ * Handle iosched queues
+ */
+ pkt_iosched_process_queue(pd);
+ }
+
+ return 0;
+}
+
+static void pkt_print_settings(struct pktcdvd_device *pd)
+{
+ pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n",
+ pd->settings.fp ? "Fixed" : "Variable",
+ pd->settings.size >> 2,
+ pd->settings.block_mode == 8 ? '1' : '2');
+}
+
+static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control)
+{
+ memset(cgc->cmd, 0, sizeof(cgc->cmd));
+
+ cgc->cmd[0] = GPCMD_MODE_SENSE_10;
+ cgc->cmd[2] = page_code | (page_control << 6);
+ cgc->cmd[7] = cgc->buflen >> 8;
+ cgc->cmd[8] = cgc->buflen & 0xff;
+ cgc->data_direction = CGC_DATA_READ;
+ return pkt_generic_packet(pd, cgc);
+}
+
+static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc)
+{
+ memset(cgc->cmd, 0, sizeof(cgc->cmd));
+ memset(cgc->buffer, 0, 2);
+ cgc->cmd[0] = GPCMD_MODE_SELECT_10;
+ cgc->cmd[1] = 0x10; /* PF */
+ cgc->cmd[7] = cgc->buflen >> 8;
+ cgc->cmd[8] = cgc->buflen & 0xff;
+ cgc->data_direction = CGC_DATA_WRITE;
+ return pkt_generic_packet(pd, cgc);
+}
+
+static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
+{
+ struct packet_command cgc;
+ int ret;
+
+ /* set up command and get the disc info */
+ init_cdrom_command(&cgc, di, sizeof(*di), CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_READ_DISC_INFO;
+ cgc.cmd[8] = cgc.buflen = 2;
+ cgc.quiet = 1;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ return ret;
+
+ /* not all drives have the same disc_info length, so requeue
+ * packet with the length the drive tells us it can supply
+ */
+ cgc.buflen = be16_to_cpu(di->disc_information_length) +
+ sizeof(di->disc_information_length);
+
+ if (cgc.buflen > sizeof(disc_information))
+ cgc.buflen = sizeof(disc_information);
+
+ cgc.cmd[8] = cgc.buflen;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, track_information *ti)
+{
+ struct packet_command cgc;
+ int ret;
+
+ init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO;
+ cgc.cmd[1] = type & 3;
+ cgc.cmd[4] = (track & 0xff00) >> 8;
+ cgc.cmd[5] = track & 0xff;
+ cgc.cmd[8] = 8;
+ cgc.quiet = 1;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ return ret;
+
+ cgc.buflen = be16_to_cpu(ti->track_information_length) +
+ sizeof(ti->track_information_length);
+
+ if (cgc.buflen > sizeof(track_information))
+ cgc.buflen = sizeof(track_information);
+
+ cgc.cmd[8] = cgc.buflen;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
+ long *last_written)
+{
+ disc_information di;
+ track_information ti;
+ __u32 last_track;
+ int ret;
+
+ ret = pkt_get_disc_info(pd, &di);
+ if (ret)
+ return ret;
+
+ last_track = (di.last_track_msb << 8) | di.last_track_lsb;
+ ret = pkt_get_track_info(pd, last_track, 1, &ti);
+ if (ret)
+ return ret;
+
+ /* if this track is blank, try the previous. */
+ if (ti.blank) {
+ last_track--;
+ ret = pkt_get_track_info(pd, last_track, 1, &ti);
+ if (ret)
+ return ret;
+ }
+
+ /* if last recorded field is valid, return it. */
+ if (ti.lra_v) {
+ *last_written = be32_to_cpu(ti.last_rec_address);
+ } else {
+ /* make it up instead */
+ *last_written = be32_to_cpu(ti.track_start) +
+ be32_to_cpu(ti.track_size);
+ if (ti.free_blocks)
+ *last_written -= (be32_to_cpu(ti.free_blocks) + 7);
+ }
+ return 0;
+}
+
+/*
+ * write mode select package based on pd->settings
+ */
+static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ write_param_page *wp;
+ char buffer[128];
+ int ret, size;
+
+ /* doesn't apply to DVD+RW or DVD-RAM */
+ if ((pd->mmc3_profile == 0x1a) || (pd->mmc3_profile == 0x12))
+ return 0;
+
+ memset(buffer, 0, sizeof(buffer));
+ init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ size = 2 + ((buffer[0] << 8) | (buffer[1] & 0xff));
+ pd->mode_offset = (buffer[6] << 8) | (buffer[7] & 0xff);
+ if (size > sizeof(buffer))
+ size = sizeof(buffer);
+
+ /*
+ * now get it all
+ */
+ init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ /*
+ * write page is offset header + block descriptor length
+ */
+ wp = (write_param_page *) &buffer[sizeof(struct mode_page_header) + pd->mode_offset];
+
+ wp->fp = pd->settings.fp;
+ wp->track_mode = pd->settings.track_mode;
+ wp->write_type = pd->settings.write_type;
+ wp->data_block_type = pd->settings.block_mode;
+
+ wp->multi_session = 0;
+
+#ifdef PACKET_USE_LS
+ wp->link_size = 7;
+ wp->ls_v = 1;
+#endif
+
+ if (wp->data_block_type == PACKET_BLOCK_MODE1) {
+ wp->session_format = 0;
+ wp->subhdr2 = 0x20;
+ } else if (wp->data_block_type == PACKET_BLOCK_MODE2) {
+ wp->session_format = 0x20;
+ wp->subhdr2 = 8;
+#if 0
+ wp->mcn[0] = 0x80;
+ memcpy(&wp->mcn[1], PACKET_MCN, sizeof(wp->mcn) - 1);
+#endif
+ } else {
+ /*
+ * paranoia
+ */
+ pkt_err(pd, "write mode wrong %d\n", wp->data_block_type);
+ return 1;
+ }
+ wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
+
+ cgc.buflen = cgc.cmd[8] = size;
+ ret = pkt_mode_select(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ pkt_print_settings(pd);
+ return 0;
+}
+
+/*
+ * 1 -- we can write to this track, 0 -- we can't
+ */
+static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti)
+{
+ switch (pd->mmc3_profile) {
+ case 0x1a: /* DVD+RW */
+ case 0x12: /* DVD-RAM */
+ /* The track is always writable on DVD+RW/DVD-RAM */
+ return 1;
+ default:
+ break;
+ }
+
+ if (!ti->packet || !ti->fp)
+ return 0;
+
+ /*
+ * "good" settings as per Mt Fuji.
+ */
+ if (ti->rt == 0 && ti->blank == 0)
+ return 1;
+
+ if (ti->rt == 0 && ti->blank == 1)
+ return 1;
+
+ if (ti->rt == 1 && ti->blank == 0)
+ return 1;
+
+ pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
+ return 0;
+}
+
+/*
+ * 1 -- we can write to this disc, 0 -- we can't
+ */
+static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di)
+{
+ switch (pd->mmc3_profile) {
+ case 0x0a: /* CD-RW */
+ case 0xffff: /* MMC3 not supported */
+ break;
+ case 0x1a: /* DVD+RW */
+ case 0x13: /* DVD-RW */
+ case 0x12: /* DVD-RAM */
+ return 1;
+ default:
+ pkt_dbg(2, pd, "Wrong disc profile (%x)\n",
+ pd->mmc3_profile);
+ return 0;
+ }
+
+ /*
+ * for disc type 0xff we should probably reserve a new track.
+ * but i'm not sure, should we leave this to user apps? probably.
+ */
+ if (di->disc_type == 0xff) {
+ pkt_notice(pd, "unknown disc - no track?\n");
+ return 0;
+ }
+
+ if (di->disc_type != 0x20 && di->disc_type != 0) {
+ pkt_err(pd, "wrong disc type (%x)\n", di->disc_type);
+ return 0;
+ }
+
+ if (di->erasable == 0) {
+ pkt_notice(pd, "disc not erasable\n");
+ return 0;
+ }
+
+ if (di->border_status == PACKET_SESSION_RESERVED) {
+ pkt_err(pd, "can't write to last track (reserved)\n");
+ return 0;
+ }
+
+ return 1;
+}
+
+static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ unsigned char buf[12];
+ disc_information di;
+ track_information ti;
+ int ret, track;
+
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_GET_CONFIGURATION;
+ cgc.cmd[8] = 8;
+ ret = pkt_generic_packet(pd, &cgc);
+ pd->mmc3_profile = ret ? 0xffff : buf[6] << 8 | buf[7];
+
+ memset(&di, 0, sizeof(disc_information));
+ memset(&ti, 0, sizeof(track_information));
+
+ ret = pkt_get_disc_info(pd, &di);
+ if (ret) {
+ pkt_err(pd, "failed get_disc\n");
+ return ret;
+ }
+
+ if (!pkt_writable_disc(pd, &di))
+ return -EROFS;
+
+ pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
+
+ track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
+ ret = pkt_get_track_info(pd, track, 1, &ti);
+ if (ret) {
+ pkt_err(pd, "failed get_track\n");
+ return ret;
+ }
+
+ if (!pkt_writable_track(pd, &ti)) {
+ pkt_err(pd, "can't write to this track\n");
+ return -EROFS;
+ }
+
+ /*
+ * we keep packet size in 512 byte units, makes it easier to
+ * deal with request calculations.
+ */
+ pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2;
+ if (pd->settings.size == 0) {
+ pkt_notice(pd, "detected zero packet size!\n");
+ return -ENXIO;
+ }
+ if (pd->settings.size > PACKET_MAX_SECTORS) {
+ pkt_err(pd, "packet size is too big\n");
+ return -EROFS;
+ }
+ pd->settings.fp = ti.fp;
+ pd->offset = (be32_to_cpu(ti.track_start) << 2) & (pd->settings.size - 1);
+
+ if (ti.nwa_v) {
+ pd->nwa = be32_to_cpu(ti.next_writable);
+ set_bit(PACKET_NWA_VALID, &pd->flags);
+ }
+
+ /*
+ * in theory we could use lra on -RW media as well and just zero
+ * blocks that haven't been written yet, but in practice that
+ * is just a no-go. we'll use that for -R, naturally.
+ */
+ if (ti.lra_v) {
+ pd->lra = be32_to_cpu(ti.last_rec_address);
+ set_bit(PACKET_LRA_VALID, &pd->flags);
+ } else {
+ pd->lra = 0xffffffff;
+ set_bit(PACKET_LRA_VALID, &pd->flags);
+ }
+
+ /*
+ * fine for now
+ */
+ pd->settings.link_loss = 7;
+ pd->settings.write_type = 0; /* packet */
+ pd->settings.track_mode = ti.track_mode;
+
+ /*
+ * mode1 or mode2 disc
+ */
+ switch (ti.data_mode) {
+ case PACKET_MODE1:
+ pd->settings.block_mode = PACKET_BLOCK_MODE1;
+ break;
+ case PACKET_MODE2:
+ pd->settings.block_mode = PACKET_BLOCK_MODE2;
+ break;
+ default:
+ pkt_err(pd, "unknown data mode\n");
+ return -EROFS;
+ }
+ return 0;
+}
+
+/*
+ * enable/disable write caching on drive
+ */
+static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
+ int set)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[64];
+ int ret;
+
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.buflen = pd->mode_offset + 12;
+
+ /*
+ * caching mode page might not be there, so quiet this command
+ */
+ cgc.quiet = 1;
+
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
+ if (ret)
+ return ret;
+
+ buf[pd->mode_offset + 10] |= (!!set << 2);
+
+ cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff));
+ ret = pkt_mode_select(pd, &cgc);
+ if (ret) {
+ pkt_err(pd, "write caching control failed\n");
+ pkt_dump_sense(pd, &cgc);
+ } else if (!ret && set)
+ pkt_notice(pd, "enabled write caching\n");
+ return ret;
+}
+
+static int pkt_lock_door(struct pktcdvd_device *pd, int lockflag)
+{
+ struct packet_command cgc;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.cmd[0] = GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL;
+ cgc.cmd[4] = lockflag ? 1 : 0;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+/*
+ * Returns drive maximum write speed
+ */
+static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
+ unsigned *write_speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[256+18];
+ unsigned char *cap_buf;
+ int ret, offset;
+
+ cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
+ cgc.sshdr = &sshdr;
+
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
+ if (ret) {
+ cgc.buflen = pd->mode_offset + cap_buf[1] + 2 +
+ sizeof(struct mode_page_header);
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+ }
+
+ offset = 20; /* Obsoleted field, used by older drives */
+ if (cap_buf[1] >= 28)
+ offset = 28; /* Current write speed selected */
+ if (cap_buf[1] >= 30) {
+ /* If the drive reports at least one "Logical Unit Write
+ * Speed Performance Descriptor Block", use the information
+ * in the first block. (contains the highest speed)
+ */
+ int num_spdb = (cap_buf[30] << 8) + cap_buf[31];
+ if (num_spdb > 0)
+ offset = 34;
+ }
+
+ *write_speed = (cap_buf[offset] << 8) | cap_buf[offset + 1];
+ return 0;
+}
+
+/* These tables from cdrecord - I don't have orange book */
+/* standard speed CD-RW (1-4x) */
+static char clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 6, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+/* high speed CD-RW (-10x) */
+static char hs_clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 6, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+/* ultra high speed CD-RW */
+static char us_clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 8, 0, 0,16, 0,24,32,40,48, 0, 0, 0, 0
+};
+
+/*
+ * reads the maximum media speed from ATIP
+ */
+static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
+ unsigned *speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[64];
+ unsigned int size, st, sp;
+ int ret;
+
+ init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
+ cgc.cmd[1] = 2;
+ cgc.cmd[2] = 4; /* READ ATIP */
+ cgc.cmd[8] = 2;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+ size = ((unsigned int) buf[0]<<8) + buf[1] + 2;
+ if (size > sizeof(buf))
+ size = sizeof(buf);
+
+ init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
+ cgc.cmd[1] = 2;
+ cgc.cmd[2] = 4;
+ cgc.cmd[8] = size;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ if (!(buf[6] & 0x40)) {
+ pkt_notice(pd, "disc type is not CD-RW\n");
+ return 1;
+ }
+ if (!(buf[6] & 0x4)) {
+ pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n");
+ return 1;
+ }
+
+ st = (buf[6] >> 3) & 0x7; /* disc sub-type */
+
+ sp = buf[16] & 0xf; /* max speed from ATIP A1 field */
+
+ /* Info from cdrecord */
+ switch (st) {
+ case 0: /* standard speed */
+ *speed = clv_to_speed[sp];
+ break;
+ case 1: /* high speed */
+ *speed = hs_clv_to_speed[sp];
+ break;
+ case 2: /* ultra high speed */
+ *speed = us_clv_to_speed[sp];
+ break;
+ default:
+ pkt_notice(pd, "unknown disc sub-type %d\n", st);
+ return 1;
+ }
+ if (*speed) {
+ pkt_info(pd, "maximum media speed: %d\n", *speed);
+ return 0;
+ } else {
+ pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st);
+ return 1;
+ }
+}
+
+static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ int ret;
+
+ pkt_dbg(2, pd, "Performing OPC\n");
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.sshdr = &sshdr;
+ cgc.timeout = 60*HZ;
+ cgc.cmd[0] = GPCMD_SEND_OPC;
+ cgc.cmd[1] = 1;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+}
+
+static int pkt_open_write(struct pktcdvd_device *pd)
+{
+ int ret;
+ unsigned int write_speed, media_write_speed, read_speed;
+
+ ret = pkt_probe_settings(pd);
+ if (ret) {
+ pkt_dbg(2, pd, "failed probe\n");
+ return ret;
+ }
+
+ ret = pkt_set_write_settings(pd);
+ if (ret) {
+ pkt_dbg(1, pd, "failed saving write settings\n");
+ return -EIO;
+ }
+
+ pkt_write_caching(pd, USE_WCACHING);
+
+ ret = pkt_get_max_speed(pd, &write_speed);
+ if (ret)
+ write_speed = 16 * 177;
+ switch (pd->mmc3_profile) {
+ case 0x13: /* DVD-RW */
+ case 0x1a: /* DVD+RW */
+ case 0x12: /* DVD-RAM */
+ pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
+ break;
+ default:
+ ret = pkt_media_speed(pd, &media_write_speed);
+ if (ret)
+ media_write_speed = 16;
+ write_speed = min(write_speed, media_write_speed * 177);
+ pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
+ break;
+ }
+ read_speed = write_speed;
+
+ ret = pkt_set_speed(pd, write_speed, read_speed);
+ if (ret) {
+ pkt_dbg(1, pd, "couldn't set write speed\n");
+ return -EIO;
+ }
+ pd->write_speed = write_speed;
+ pd->read_speed = read_speed;
+
+ ret = pkt_perform_opc(pd);
+ if (ret) {
+ pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
+ }
+
+ return 0;
+}
+
+/*
+ * called at open time.
+ */
+static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
+{
+ int ret;
+ long lba;
+ struct request_queue *q;
+ struct block_device *bdev;
+
+ /*
+ * We need to re-open the cdrom device without O_NONBLOCK to be able
+ * to read/write from/to it. It is already opened in O_NONBLOCK mode
+ * so open should not fail.
+ */
+ bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd);
+ if (IS_ERR(bdev)) {
+ ret = PTR_ERR(bdev);
+ goto out;
+ }
+
+ ret = pkt_get_last_written(pd, &lba);
+ if (ret) {
+ pkt_err(pd, "pkt_get_last_written failed\n");
+ goto out_putdev;
+ }
+
+ set_capacity(pd->disk, lba << 2);
+ set_capacity_and_notify(pd->bdev->bd_disk, lba << 2);
+
+ q = bdev_get_queue(pd->bdev);
+ if (write) {
+ ret = pkt_open_write(pd);
+ if (ret)
+ goto out_putdev;
+ /*
+ * Some CDRW drives can not handle writes larger than one packet,
+ * even if the size is a multiple of the packet size.
+ */
+ blk_queue_max_hw_sectors(q, pd->settings.size);
+ set_bit(PACKET_WRITABLE, &pd->flags);
+ } else {
+ pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
+ clear_bit(PACKET_WRITABLE, &pd->flags);
+ }
+
+ ret = pkt_set_segment_merging(pd, q);
+ if (ret)
+ goto out_putdev;
+
+ if (write) {
+ if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
+ pkt_err(pd, "not enough memory for buffers\n");
+ ret = -ENOMEM;
+ goto out_putdev;
+ }
+ pkt_info(pd, "%lukB available on disc\n", lba << 1);
+ }
+
+ return 0;
+
+out_putdev:
+ blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
+out:
+ return ret;
+}
+
+/*
+ * called when the device is closed. makes sure that the device flushes
+ * the internal cache before we close.
+ */
+static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
+{
+ if (flush && pkt_flush_cache(pd))
+ pkt_dbg(1, pd, "not flushing cache\n");
+
+ pkt_lock_door(pd, 0);
+
+ pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
+ blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL);
+
+ pkt_shrink_pktlist(pd);
+}
+
+static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
+{
+ if (dev_minor >= MAX_WRITERS)
+ return NULL;
+
+ dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
+ return pkt_devs[dev_minor];
+}
+
+static int pkt_open(struct block_device *bdev, fmode_t mode)
+{
+ struct pktcdvd_device *pd = NULL;
+ int ret;
+
+ mutex_lock(&pktcdvd_mutex);
+ mutex_lock(&ctl_mutex);
+ pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev));
+ if (!pd) {
+ ret = -ENODEV;
+ goto out;
+ }
+ BUG_ON(pd->refcnt < 0);
+
+ pd->refcnt++;
+ if (pd->refcnt > 1) {
+ if ((mode & FMODE_WRITE) &&
+ !test_bit(PACKET_WRITABLE, &pd->flags)) {
+ ret = -EBUSY;
+ goto out_dec;
+ }
+ } else {
+ ret = pkt_open_dev(pd, mode & FMODE_WRITE);
+ if (ret)
+ goto out_dec;
+ /*
+ * needed here as well, since ext2 (among others) may change
+ * the blocksize at mount time
+ */
+ set_blocksize(bdev, CD_FRAMESIZE);
+ }
+
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+ return 0;
+
+out_dec:
+ pd->refcnt--;
+out:
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+ return ret;
+}
+
+static void pkt_close(struct gendisk *disk, fmode_t mode)
+{
+ struct pktcdvd_device *pd = disk->private_data;
+
+ mutex_lock(&pktcdvd_mutex);
+ mutex_lock(&ctl_mutex);
+ pd->refcnt--;
+ BUG_ON(pd->refcnt < 0);
+ if (pd->refcnt == 0) {
+ int flush = test_bit(PACKET_WRITABLE, &pd->flags);
+ pkt_release_dev(pd, flush);
+ }
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+}
+
+
+static void pkt_end_io_read_cloned(struct bio *bio)
+{
+ struct packet_stacked_data *psd = bio->bi_private;
+ struct pktcdvd_device *pd = psd->pd;
+
+ psd->bio->bi_status = bio->bi_status;
+ bio_put(bio);
+ bio_endio(psd->bio);
+ mempool_free(psd, &psd_pool);
+ pkt_bio_finished(pd);
+}
+
+static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
+{
+ struct bio *cloned_bio =
+ bio_alloc_clone(pd->bdev, bio, GFP_NOIO, &pkt_bio_set);
+ struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
+
+ psd->pd = pd;
+ psd->bio = bio;
+ cloned_bio->bi_private = psd;
+ cloned_bio->bi_end_io = pkt_end_io_read_cloned;
+ pd->stats.secs_r += bio_sectors(bio);
+ pkt_queue_bio(pd, cloned_bio);
+}
+
+static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
+{
+ struct pktcdvd_device *pd = q->queuedata;
+ sector_t zone;
+ struct packet_data *pkt;
+ int was_empty, blocked_bio;
+ struct pkt_rb_node *node;
+
+ zone = get_zone(bio->bi_iter.bi_sector, pd);
+
+ /*
+ * If we find a matching packet in state WAITING or READ_WAIT, we can
+ * just append this bio to that packet.
+ */
+ spin_lock(&pd->cdrw.active_list_lock);
+ blocked_bio = 0;
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->sector == zone) {
+ spin_lock(&pkt->lock);
+ if ((pkt->state == PACKET_WAITING_STATE) ||
+ (pkt->state == PACKET_READ_WAIT_STATE)) {
+ bio_list_add(&pkt->orig_bios, bio);
+ pkt->write_size +=
+ bio->bi_iter.bi_size / CD_FRAMESIZE;
+ if ((pkt->write_size >= pkt->frames) &&
+ (pkt->state == PACKET_WAITING_STATE)) {
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+ }
+ spin_unlock(&pkt->lock);
+ spin_unlock(&pd->cdrw.active_list_lock);
+ return;
+ } else {
+ blocked_bio = 1;
+ }
+ spin_unlock(&pkt->lock);
+ }
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+
+ /*
+ * Test if there is enough room left in the bio work queue
+ * (queue size >= congestion on mark).
+ * If not, wait till the work queue size is below the congestion off mark.
+ */
+ spin_lock(&pd->lock);
+ if (pd->write_congestion_on > 0
+ && pd->bio_queue_size >= pd->write_congestion_on) {
+ struct wait_bit_queue_entry wqe;
+
+ init_wait_var_entry(&wqe, &pd->congested, 0);
+ for (;;) {
+ prepare_to_wait_event(__var_waitqueue(&pd->congested),
+ &wqe.wq_entry,
+ TASK_UNINTERRUPTIBLE);
+ if (pd->bio_queue_size <= pd->write_congestion_off)
+ break;
+ pd->congested = true;
+ spin_unlock(&pd->lock);
+ schedule();
+ spin_lock(&pd->lock);
+ }
+ }
+ spin_unlock(&pd->lock);
+
+ /*
+ * No matching packet found. Store the bio in the work queue.
+ */
+ node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
+ node->bio = bio;
+ spin_lock(&pd->lock);
+ BUG_ON(pd->bio_queue_size < 0);
+ was_empty = (pd->bio_queue_size == 0);
+ pkt_rbtree_insert(pd, node);
+ spin_unlock(&pd->lock);
+
+ /*
+ * Wake up the worker thread.
+ */
+ atomic_set(&pd->scan_queue, 1);
+ if (was_empty) {
+ /* This wake_up is required for correct operation */
+ wake_up(&pd->wqueue);
+ } else if (!list_empty(&pd->cdrw.pkt_free_list) && !blocked_bio) {
+ /*
+ * This wake up is not required for correct operation,
+ * but improves performance in some cases.
+ */
+ wake_up(&pd->wqueue);
+ }
+}
+
+static void pkt_submit_bio(struct bio *bio)
+{
+ struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata;
+ struct bio *split;
+
+ bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
+
+ pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
+ (unsigned long long)bio->bi_iter.bi_sector,
+ (unsigned long long)bio_end_sector(bio));
+
+ /*
+ * Clone READ bios so we can have our own bi_end_io callback.
+ */
+ if (bio_data_dir(bio) == READ) {
+ pkt_make_request_read(pd, bio);
+ return;
+ }
+
+ if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
+ pkt_notice(pd, "WRITE for ro device (%llu)\n",
+ (unsigned long long)bio->bi_iter.bi_sector);
+ goto end_io;
+ }
+
+ if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) {
+ pkt_err(pd, "wrong bio size\n");
+ goto end_io;
+ }
+
+ do {
+ sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
+ sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
+
+ if (last_zone != zone) {
+ BUG_ON(last_zone != zone + pd->settings.size);
+
+ split = bio_split(bio, last_zone -
+ bio->bi_iter.bi_sector,
+ GFP_NOIO, &pkt_bio_set);
+ bio_chain(split, bio);
+ } else {
+ split = bio;
+ }
+
+ pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
+ } while (split != bio);
+
+ return;
+end_io:
+ bio_io_error(bio);
+}
+
+static void pkt_init_queue(struct pktcdvd_device *pd)
+{
+ struct request_queue *q = pd->disk->queue;
+
+ blk_queue_logical_block_size(q, CD_FRAMESIZE);
+ blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
+ q->queuedata = pd;
+}
+
+static int pkt_seq_show(struct seq_file *m, void *p)
+{
+ struct pktcdvd_device *pd = m->private;
+ char *msg;
+ int states[PACKET_NUM_STATES];
+
+ seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev);
+
+ seq_printf(m, "\nSettings:\n");
+ seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);
+
+ if (pd->settings.write_type == 0)
+ msg = "Packet";
+ else
+ msg = "Unknown";
+ seq_printf(m, "\twrite type:\t\t%s\n", msg);
+
+ seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable");
+ seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss);
+
+ seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode);
+
+ if (pd->settings.block_mode == PACKET_BLOCK_MODE1)
+ msg = "Mode 1";
+ else if (pd->settings.block_mode == PACKET_BLOCK_MODE2)
+ msg = "Mode 2";
+ else
+ msg = "Unknown";
+ seq_printf(m, "\tblock mode:\t\t%s\n", msg);
+
+ seq_printf(m, "\nStatistics:\n");
+ seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started);
+ seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended);
+ seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1);
+ seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1);
+ seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1);
+
+ seq_printf(m, "\nMisc:\n");
+ seq_printf(m, "\treference count:\t%d\n", pd->refcnt);
+ seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags);
+ seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed);
+ seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed);
+ seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset);
+ seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset);
+
+ seq_printf(m, "\nQueue state:\n");
+ seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size);
+ seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios));
+ seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", (unsigned long long)pd->current_sector);
+
+ pkt_count_states(pd, states);
+ seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+ states[0], states[1], states[2], states[3], states[4], states[5]);
+
+ seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n",
+ pd->write_congestion_off,
+ pd->write_congestion_on);
+ return 0;
+}
+
+static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
+{
+ int i;
+ struct block_device *bdev;
+ struct scsi_device *sdev;
+
+ if (pd->pkt_dev == dev) {
+ pkt_err(pd, "recursive setup not allowed\n");
+ return -EBUSY;
+ }
+ for (i = 0; i < MAX_WRITERS; i++) {
+ struct pktcdvd_device *pd2 = pkt_devs[i];
+ if (!pd2)
+ continue;
+ if (pd2->bdev->bd_dev == dev) {
+ pkt_err(pd, "%pg already setup\n", pd2->bdev);
+ return -EBUSY;
+ }
+ if (pd2->pkt_dev == dev) {
+ pkt_err(pd, "can't chain pktcdvd devices\n");
+ return -EBUSY;
+ }
+ }
+
+ bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL);
+ if (IS_ERR(bdev))
+ return PTR_ERR(bdev);
+ sdev = scsi_device_from_queue(bdev->bd_disk->queue);
+ if (!sdev) {
+ blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
+ return -EINVAL;
+ }
+ put_device(&sdev->sdev_gendev);
+
+ /* This is safe, since we have a reference from open(). */
+ __module_get(THIS_MODULE);
+
+ pd->bdev = bdev;
+ set_blocksize(bdev, CD_FRAMESIZE);
+
+ pkt_init_queue(pd);
+
+ atomic_set(&pd->cdrw.pending_bios, 0);
+ pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name);
+ if (IS_ERR(pd->cdrw.thread)) {
+ pkt_err(pd, "can't start kernel thread\n");
+ goto out_mem;
+ }
+
+ proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd);
+ pkt_dbg(1, pd, "writer mapped to %pg\n", bdev);
+ return 0;
+
+out_mem:
+ blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
+ return -ENOMEM;
+}
+
+static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg)
+{
+ struct pktcdvd_device *pd = bdev->bd_disk->private_data;
+ int ret;
+
+ pkt_dbg(2, pd, "cmd %x, dev %d:%d\n",
+ cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+
+ mutex_lock(&pktcdvd_mutex);
+ switch (cmd) {
+ case CDROMEJECT:
+ /*
+ * The door gets locked when the device is opened, so we
+ * have to unlock it or else the eject command fails.
+ */
+ if (pd->refcnt == 1)
+ pkt_lock_door(pd, 0);
+ fallthrough;
+ /*
+ * forward selected CDROM ioctls to CD-ROM, for UDF
+ */
+ case CDROMMULTISESSION:
+ case CDROMREADTOCENTRY:
+ case CDROM_LAST_WRITTEN:
+ case CDROM_SEND_PACKET:
+ case SCSI_IOCTL_SEND_COMMAND:
+ if (!bdev->bd_disk->fops->ioctl)
+ ret = -ENOTTY;
+ else
+ ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
+ break;
+ default:
+ pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd);
+ ret = -ENOTTY;
+ }
+ mutex_unlock(&pktcdvd_mutex);
+
+ return ret;
+}
+
+static unsigned int pkt_check_events(struct gendisk *disk,
+ unsigned int clearing)
+{
+ struct pktcdvd_device *pd = disk->private_data;
+ struct gendisk *attached_disk;
+
+ if (!pd)
+ return 0;
+ if (!pd->bdev)
+ return 0;
+ attached_disk = pd->bdev->bd_disk;
+ if (!attached_disk || !attached_disk->fops->check_events)
+ return 0;
+ return attached_disk->fops->check_events(attached_disk, clearing);
+}
+
+static char *pkt_devnode(struct gendisk *disk, umode_t *mode)
+{
+ return kasprintf(GFP_KERNEL, "pktcdvd/%s", disk->disk_name);
+}
+
+static const struct block_device_operations pktcdvd_ops = {
+ .owner = THIS_MODULE,
+ .submit_bio = pkt_submit_bio,
+ .open = pkt_open,
+ .release = pkt_close,
+ .ioctl = pkt_ioctl,
+ .compat_ioctl = blkdev_compat_ptr_ioctl,
+ .check_events = pkt_check_events,
+ .devnode = pkt_devnode,
+};
+
+/*
+ * Set up mapping from pktcdvd device to CD-ROM device.
+ */
+static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
+{
+ int idx;
+ int ret = -ENOMEM;
+ struct pktcdvd_device *pd;
+ struct gendisk *disk;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ for (idx = 0; idx < MAX_WRITERS; idx++)
+ if (!pkt_devs[idx])
+ break;
+ if (idx == MAX_WRITERS) {
+ pr_err("max %d writers supported\n", MAX_WRITERS);
+ ret = -EBUSY;
+ goto out_mutex;
+ }
+
+ pd = kzalloc(sizeof(struct pktcdvd_device), GFP_KERNEL);
+ if (!pd)
+ goto out_mutex;
+
+ ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
+ sizeof(struct pkt_rb_node));
+ if (ret)
+ goto out_mem;
+
+ INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
+ INIT_LIST_HEAD(&pd->cdrw.pkt_active_list);
+ spin_lock_init(&pd->cdrw.active_list_lock);
+
+ spin_lock_init(&pd->lock);
+ spin_lock_init(&pd->iosched.lock);
+ bio_list_init(&pd->iosched.read_queue);
+ bio_list_init(&pd->iosched.write_queue);
+ sprintf(pd->name, DRIVER_NAME"%d", idx);
+ init_waitqueue_head(&pd->wqueue);
+ pd->bio_queue = RB_ROOT;
+
+ pd->write_congestion_on = write_congestion_on;
+ pd->write_congestion_off = write_congestion_off;
+
+ ret = -ENOMEM;
+ disk = blk_alloc_disk(NUMA_NO_NODE);
+ if (!disk)
+ goto out_mem;
+ pd->disk = disk;
+ disk->major = pktdev_major;
+ disk->first_minor = idx;
+ disk->minors = 1;
+ disk->fops = &pktcdvd_ops;
+ disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART;
+ strcpy(disk->disk_name, pd->name);
+ disk->private_data = pd;
+
+ pd->pkt_dev = MKDEV(pktdev_major, idx);
+ ret = pkt_new_dev(pd, dev);
+ if (ret)
+ goto out_mem2;
+
+ /* inherit events of the host device */
+ disk->events = pd->bdev->bd_disk->events;
+
+ ret = add_disk(disk);
+ if (ret)
+ goto out_mem2;
+
+ pkt_sysfs_dev_new(pd);
+ pkt_debugfs_dev_new(pd);
+
+ pkt_devs[idx] = pd;
+ if (pkt_dev)
+ *pkt_dev = pd->pkt_dev;
+
+ mutex_unlock(&ctl_mutex);
+ return 0;
+
+out_mem2:
+ put_disk(disk);
+out_mem:
+ mempool_exit(&pd->rb_pool);
+ kfree(pd);
+out_mutex:
+ mutex_unlock(&ctl_mutex);
+ pr_err("setup of pktcdvd device failed\n");
+ return ret;
+}
+
+/*
+ * Tear down mapping from pktcdvd device to CD-ROM device.
+ */
+static int pkt_remove_dev(dev_t pkt_dev)
+{
+ struct pktcdvd_device *pd;
+ int idx;
+ int ret = 0;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ for (idx = 0; idx < MAX_WRITERS; idx++) {
+ pd = pkt_devs[idx];
+ if (pd && (pd->pkt_dev == pkt_dev))
+ break;
+ }
+ if (idx == MAX_WRITERS) {
+ pr_debug("dev not setup\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (pd->refcnt > 0) {
+ ret = -EBUSY;
+ goto out;
+ }
+ if (!IS_ERR(pd->cdrw.thread))
+ kthread_stop(pd->cdrw.thread);
+
+ pkt_devs[idx] = NULL;
+
+ pkt_debugfs_dev_remove(pd);
+ pkt_sysfs_dev_remove(pd);
+
+ blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY);
+
+ remove_proc_entry(pd->name, pkt_proc);
+ pkt_dbg(1, pd, "writer unmapped\n");
+
+ del_gendisk(pd->disk);
+ put_disk(pd->disk);
+
+ mempool_exit(&pd->rb_pool);
+ kfree(pd);
+
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
+
+out:
+ mutex_unlock(&ctl_mutex);
+ return ret;
+}
+
+static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
+{
+ struct pktcdvd_device *pd;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index);
+ if (pd) {
+ ctrl_cmd->dev = new_encode_dev(pd->bdev->bd_dev);
+ ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev);
+ } else {
+ ctrl_cmd->dev = 0;
+ ctrl_cmd->pkt_dev = 0;
+ }
+ ctrl_cmd->num_devices = MAX_WRITERS;
+
+ mutex_unlock(&ctl_mutex);
+}
+
+static long pkt_ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+ struct pkt_ctrl_command ctrl_cmd;
+ int ret = 0;
+ dev_t pkt_dev = 0;
+
+ if (cmd != PACKET_CTRL_CMD)
+ return -ENOTTY;
+
+ if (copy_from_user(&ctrl_cmd, argp, sizeof(struct pkt_ctrl_command)))
+ return -EFAULT;
+
+ switch (ctrl_cmd.command) {
+ case PKT_CTRL_CMD_SETUP:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev);
+ ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev);
+ break;
+ case PKT_CTRL_CMD_TEARDOWN:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev));
+ break;
+ case PKT_CTRL_CMD_STATUS:
+ pkt_get_status(&ctrl_cmd);
+ break;
+ default:
+ return -ENOTTY;
+ }
+
+ if (copy_to_user(argp, &ctrl_cmd, sizeof(struct pkt_ctrl_command)))
+ return -EFAULT;
+ return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static long pkt_ctl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ return pkt_ctl_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations pkt_ctl_fops = {
+ .open = nonseekable_open,
+ .unlocked_ioctl = pkt_ctl_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = pkt_ctl_compat_ioctl,
+#endif
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+};
+
+static struct miscdevice pkt_misc = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = DRIVER_NAME,
+ .nodename = "pktcdvd/control",
+ .fops = &pkt_ctl_fops
+};
+
+static int __init pkt_init(void)
+{
+ int ret;
+
+ mutex_init(&ctl_mutex);
+
+ ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
+ sizeof(struct packet_stacked_data));
+ if (ret)
+ return ret;
+ ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret) {
+ mempool_exit(&psd_pool);
+ return ret;
+ }
+
+ ret = register_blkdev(pktdev_major, DRIVER_NAME);
+ if (ret < 0) {
+ pr_err("unable to register block device\n");
+ goto out2;
+ }
+ if (!pktdev_major)
+ pktdev_major = ret;
+
+ ret = pkt_sysfs_init();
+ if (ret)
+ goto out;
+
+ pkt_debugfs_init();
+
+ ret = misc_register(&pkt_misc);
+ if (ret) {
+ pr_err("unable to register misc device\n");
+ goto out_misc;
+ }
+
+ pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL);
+
+ return 0;
+
+out_misc:
+ pkt_debugfs_cleanup();
+ pkt_sysfs_cleanup();
+out:
+ unregister_blkdev(pktdev_major, DRIVER_NAME);
+out2:
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
+ return ret;
+}
+
+static void __exit pkt_exit(void)
+{
+ remove_proc_entry("driver/"DRIVER_NAME, NULL);
+ misc_deregister(&pkt_misc);
+
+ pkt_debugfs_cleanup();
+ pkt_sysfs_cleanup();
+
+ unregister_blkdev(pktdev_major, DRIVER_NAME);
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
+}
+
+MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
+MODULE_AUTHOR("Jens Axboe <axboe@suse.de>");
+MODULE_LICENSE("GPL");
+
+module_init(pkt_init);
+module_exit(pkt_exit);
dev_dbg(&dev->core, "%s\n", __func__);
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
spin_lock_irq(&priv->lock);
busy = !bio_list_empty(&priv->list);
goto out_alloc;
}
- ret = ida_alloc_max(&index_ida, 1 << (MINORBITS - RNBD_PART_BITS),
+ ret = ida_alloc_max(&index_ida, (1 << (MINORBITS - RNBD_PART_BITS)) - 1,
GFP_KERNEL);
if (ret < 0) {
pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n",
char *__queues;
- unsigned short queue_size;
+ unsigned int queue_size;
struct ublksrv_ctrl_dev_info dev_info;
struct blk_mq_tag_set tag_set;
struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
int ret = -EINVAL;
+ if (issue_flags & IO_URING_F_NONBLOCK)
+ return -EAGAIN;
+
ublk_ctrl_cmd_dump(cmd);
if (!(issue_flags & IO_URING_F_SQE128))
struct ublk_device *ub;
int id;
- class_destroy(ublk_chr_class);
-
- misc_deregister(&ublk_misc);
-
idr_for_each_entry(&ublk_index_idr, ub, id)
ublk_remove(ub);
+ class_destroy(ublk_chr_class);
+ misc_deregister(&ublk_misc);
+
idr_destroy(&ublk_index_idr);
unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS);
}
virtqueue_notify(vq->vq);
}
+static blk_status_t virtblk_fail_to_queue(struct request *req, int rc)
+{
+ virtblk_cleanup_cmd(req);
+ switch (rc) {
+ case -ENOSPC:
+ return BLK_STS_DEV_RESOURCE;
+ case -ENOMEM:
+ return BLK_STS_RESOURCE;
+ default:
+ return BLK_STS_IOERR;
+ }
+}
+
static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
struct virtio_blk *vblk,
struct request *req,
struct virtblk_req *vbr)
{
blk_status_t status;
+ int num;
status = virtblk_setup_cmd(vblk->vdev, req, vbr);
if (unlikely(status))
return status;
- vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr);
- if (unlikely(vbr->sg_table.nents < 0)) {
- virtblk_cleanup_cmd(req);
- return BLK_STS_RESOURCE;
- }
+ num = virtblk_map_data(hctx, req, vbr);
+ if (unlikely(num < 0))
+ return virtblk_fail_to_queue(req, -ENOMEM);
+ vbr->sg_table.nents = num;
blk_mq_start_request(req);
blk_mq_stop_hw_queue(hctx);
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
virtblk_unmap_data(req, vbr);
- virtblk_cleanup_cmd(req);
- switch (err) {
- case -ENOSPC:
- return BLK_STS_DEV_RESOURCE;
- case -ENOMEM:
- return BLK_STS_RESOURCE;
- default:
- return BLK_STS_IOERR;
- }
+ return virtblk_fail_to_queue(req, err);
}
if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
blk_queue_max_segments(q, sg_elems);
/* No real sector limit. */
- blk_queue_max_hw_sectors(q, -1U);
+ blk_queue_max_hw_sectors(q, UINT_MAX);
max_size = virtio_max_dma_size(vdev);
return 0;
}
-static int xen_blkbk_remove(struct xenbus_device *dev)
+static void xen_blkbk_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
/* Put the reference we set in xen_blkif_alloc(). */
xen_blkif_put(be->blkif);
}
-
- return 0;
}
int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
}
}
-static int blkfront_remove(struct xenbus_device *xbdev)
+static void blkfront_remove(struct xenbus_device *xbdev)
{
struct blkfront_info *info = dev_get_drvdata(&xbdev->dev);
}
kfree(info);
- return 0;
}
static int blkfront_is_ready(struct xenbus_device *dev)
int timeout = msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS);
struct serdev_device *serdev = to_serdev_device(dev);
struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev);
+ struct hci_uart *hu = &qcadev->serdev_hu;
+ struct hci_dev *hdev = hu->hdev;
+ struct qca_data *qca = hu->priv;
const u8 ibs_wake_cmd[] = { 0xFD };
const u8 edl_reset_soc_cmd[] = { 0x01, 0x00, 0xFC, 0x01, 0x05 };
if (qcadev->btsoc_type == QCA_QCA6390) {
+ if (test_bit(QCA_BT_OFF, &qca->flags) ||
+ !test_bit(HCI_RUNNING, &hdev->flags))
+ return;
+
serdev_device_write_flush(serdev);
ret = serdev_device_write_buf(serdev, ibs_wake_cmd,
sizeof(ibs_wake_cmd));
return ret;
}
- return platform_driver_register(&sunxi_rsb_driver);
+ ret = platform_driver_register(&sunxi_rsb_driver);
+ if (ret) {
+ bus_unregister(&sunxi_rsb_bus);
+ return ret;
+ }
+
+ return 0;
}
module_init(sunxi_rsb_init);
}
suspended:
- return rc;
+ if (rc)
+ dev_err(dev, "Ignoring error %d while suspending\n", rc);
+ return 0;
}
EXPORT_SYMBOL_GPL(tpm_pm_suspend);
return tpm_chip_register(priv->chip);
}
-static int tpmfront_remove(struct xenbus_device *dev)
+static void tpmfront_remove(struct xenbus_device *dev)
{
struct tpm_chip *chip = dev_get_drvdata(&dev->dev);
struct tpm_private *priv = dev_get_drvdata(&chip->dev);
tpm_chip_unregister(chip);
ring_free(priv);
dev_set_drvdata(&chip->dev, NULL);
- return 0;
}
static int tpmfront_resume(struct xenbus_device *dev)
unsigned long rate, unsigned long parent_rate,
unsigned int *pm, unsigned int *pn, unsigned int *pod)
{
- unsigned int m, n, od, m_max = (1 << pll_info->m_bits) - 2;
+ unsigned int m, n, od, m_max = (1 << pll_info->m_bits) - 1;
/* The frequency after the N divider must be between 1 and 50 MHz. */
n = parent_rate / (1 * MHZ);
/* The N divider must be >= 2. */
n = clamp_val(n, 2, 1 << pll_info->n_bits);
- for (;; n >>= 1) {
- od = (unsigned int)-1;
+ rate /= MHZ;
+ parent_rate /= MHZ;
- do {
- m = (rate / MHZ) * (1 << ++od) * n / (parent_rate / MHZ);
- } while ((m > m_max || m & 1) && (od < 4));
-
- if (od < 4 && m >= 4 && m <= m_max)
- break;
+ for (m = m_max; m >= m_max && n >= 2; n--) {
+ m = rate * n / parent_rate;
+ od = m & 1;
+ m <<= od;
}
*pm = m;
- *pn = n;
+ *pn = n + 1;
*pod = 1 << od;
}
for (unsigned int i = 0; i < num_clks; i++) {
struct mpfs_ccc_out_hw_clock *out_hw = &out_hws[i];
- char *name = devm_kzalloc(dev, 23, GFP_KERNEL);
+ char *name = devm_kasprintf(dev, GFP_KERNEL, "%s_out%u", parent->name, i);
if (!name)
return -ENOMEM;
- snprintf(name, 23, "%s_out%u", parent->name, i);
out_hw->divider.hw.init = CLK_HW_INIT_HW(name, &parent->hw, &clk_divider_ops, 0);
out_hw->divider.reg = data->pll_base[i / MPFS_CCC_OUTPUTS_PER_PLL] +
out_hw->reg_offset;
for (unsigned int i = 0; i < num_clks; i++) {
struct mpfs_ccc_pll_hw_clock *pll_hw = &pll_hws[i];
- char *name = devm_kzalloc(dev, 18, GFP_KERNEL);
- if (!name)
+ pll_hw->name = devm_kasprintf(dev, GFP_KERNEL, "ccc%s_pll%u",
+ strchrnul(dev->of_node->full_name, '@'), i);
+ if (!pll_hw->name)
return -ENOMEM;
pll_hw->base = data->pll_base[i];
- snprintf(name, 18, "ccc%s_pll%u", strchrnul(dev->of_node->full_name, '@'), i);
- pll_hw->name = (const char *)name;
pll_hw->hw.init = CLK_HW_INIT_PARENTS_DATA_FIXED_SIZE(pll_hw->name,
pll_hw->parents,
&mpfs_ccc_pll_ops, 0);
#define PCI1760_CMD_CLR_IMB2 0x00 /* Clears IMB2 */
#define PCI1760_CMD_SET_DO 0x01 /* Set output state */
#define PCI1760_CMD_GET_DO 0x02 /* Read output status */
-#define PCI1760_CMD_GET_STATUS 0x03 /* Read current status */
+#define PCI1760_CMD_GET_STATUS 0x07 /* Read current status */
#define PCI1760_CMD_GET_FW_VER 0x0e /* Read firmware version */
#define PCI1760_CMD_GET_HW_VER 0x0f /* Read hardware version */
#define PCI1760_CMD_SET_PWM_HI(x) (0x10 + (x) * 2) /* Set "hi" period */
max_perf = min_perf;
amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true);
+ cpufreq_cpu_put(policy);
}
static int amd_get_min_freq(struct amd_cpudata *cpudata)
policy->cpuinfo.transition_latency = transition_latency;
policy->dvfs_possible_from_any_cpu = true;
policy->fast_switch_possible = true;
+ policy->suspend_freq = freq_table[0].frequency;
if (policy_has_boost_freq(policy)) {
ret = cpufreq_enable_boost_support();
.flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV,
.verify = cpufreq_generic_frequency_table_verify,
- .attr = cpufreq_generic_attr,
.get = apple_soc_cpufreq_get_rate,
.init = apple_soc_cpufreq_init,
.exit = apple_soc_cpufreq_exit,
.fast_switch = apple_soc_cpufreq_fast_switch,
.register_em = cpufreq_register_em_with_opp,
.attr = apple_soc_cpufreq_hw_attr,
+ .suspend = cpufreq_generic_suspend,
};
static int __init apple_soc_cpufreq_module_init(void)
return -ENODEV;
}
- clk = clk_get(cpu_dev, 0);
+ clk = clk_get(cpu_dev, NULL);
if (IS_ERR(clk)) {
dev_err(cpu_dev, "Cannot get clock for CPU0\n");
return PTR_ERR(clk);
cpu_data = policy->driver_data;
perf_caps = &cpu_data->perf_caps;
max_cap = arch_scale_cpu_capacity(cpu);
- min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf);
+ min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+ perf_caps->highest_perf);
if ((min_cap == 0) || (max_cap < min_cap))
return 0;
return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP;
cpu_data = policy->driver_data;
perf_caps = &cpu_data->perf_caps;
max_cap = arch_scale_cpu_capacity(cpu_dev->id);
- min_cap = div_u64(max_cap * perf_caps->lowest_perf,
- perf_caps->highest_perf);
-
- perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
+ min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+ perf_caps->highest_perf);
+ perf_step = div_u64((u64)CPPC_EM_CAP_STEP * perf_caps->highest_perf,
+ max_cap);
min_step = min_cap / CPPC_EM_CAP_STEP;
max_step = max_cap / CPPC_EM_CAP_STEP;
{ .compatible = "nvidia,tegra30", },
{ .compatible = "nvidia,tegra124", },
{ .compatible = "nvidia,tegra210", },
+ { .compatible = "nvidia,tegra234", },
{ .compatible = "qcom,apq8096", },
{ .compatible = "qcom,msm8996", },
{ .compatible = "qcom,sdm845", },
{ .compatible = "qcom,sm6115", },
{ .compatible = "qcom,sm6350", },
+ { .compatible = "qcom,sm6375", },
{ .compatible = "qcom,sm8150", },
{ .compatible = "qcom,sm8250", },
{ .compatible = "qcom,sm8350", },
return lval * xo_rate;
}
-/* Get the current frequency of the CPU (after throttling) */
-static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
+/* Get the frequency requested by the cpufreq core for the CPU */
+static unsigned int qcom_cpufreq_get_freq(unsigned int cpu)
{
struct qcom_cpufreq_data *data;
+ const struct qcom_cpufreq_soc_data *soc_data;
struct cpufreq_policy *policy;
+ unsigned int index;
policy = cpufreq_cpu_get_raw(cpu);
if (!policy)
return 0;
data = policy->driver_data;
+ soc_data = qcom_cpufreq.soc_data;
- return qcom_lmh_get_throttle_freq(data) / HZ_PER_KHZ;
+ index = readl_relaxed(data->base + soc_data->reg_perf_state);
+ index = min(index, LUT_MAX_ENTRIES - 1);
+
+ return policy->freq_table[index].frequency;
}
-/* Get the frequency requested by the cpufreq core for the CPU */
-static unsigned int qcom_cpufreq_get_freq(unsigned int cpu)
+static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
{
struct qcom_cpufreq_data *data;
- const struct qcom_cpufreq_soc_data *soc_data;
struct cpufreq_policy *policy;
- unsigned int index;
policy = cpufreq_cpu_get_raw(cpu);
if (!policy)
return 0;
data = policy->driver_data;
- soc_data = qcom_cpufreq.soc_data;
- index = readl_relaxed(data->base + soc_data->reg_perf_state);
- index = min(index, LUT_MAX_ENTRIES - 1);
+ if (data->throttle_irq >= 0)
+ return qcom_lmh_get_throttle_freq(data) / HZ_PER_KHZ;
- return policy->freq_table[index].frequency;
+ return qcom_cpufreq_get_freq(cpu);
}
static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
{
struct clk_hw_onecell_data *clk_data;
struct device *dev = &pdev->dev;
+ struct device_node *soc_node;
struct device *cpu_dev;
struct clk *clk;
- int ret, i, num_domains;
+ int ret, i, num_domains, reg_sz;
clk = clk_get(dev, "xo");
if (IS_ERR(clk))
return ret;
/* Allocate qcom_cpufreq_data based on the available frequency domains in DT */
- num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * 4);
+ soc_node = of_get_parent(dev->of_node);
+ if (!soc_node)
+ return -EINVAL;
+
+ ret = of_property_read_u32(soc_node, "#address-cells", ®_sz);
+ if (ret)
+ goto of_exit;
+
+ ret = of_property_read_u32(soc_node, "#size-cells", &i);
+ if (ret)
+ goto of_exit;
+
+ reg_sz += i;
+
+ num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * reg_sz);
if (num_domains <= 0)
return num_domains;
return -ENOMEM;
qcom_cpufreq.soc_data = of_device_get_match_data(dev);
+ if (!qcom_cpufreq.soc_data)
+ return -ENODEV;
clk_data = devm_kzalloc(dev, struct_size(clk_data, hws, num_domains), GFP_KERNEL);
if (!clk_data)
else
dev_dbg(dev, "QCOM CPUFreq HW driver initialized\n");
+of_exit:
+ of_node_put(soc_node);
+
return ret;
}
* Microchip / Atmel ECC (I2C) driver.
*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#include <linux/delay.h>
module_init(atmel_ecc_init);
module_exit(atmel_ecc_exit);
-MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>");
+MODULE_AUTHOR("Tudor Ambarus");
MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver");
MODULE_LICENSE("GPL v2");
* Microchip / Atmel ECC (I2C) driver.
*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#include <linux/bitrev.h>
module_init(atmel_i2c_init);
module_exit(atmel_i2c_exit);
-MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>");
+MODULE_AUTHOR("Tudor Ambarus");
MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver");
MODULE_LICENSE("GPL v2");
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#ifndef __ATMEL_I2C_H__
}
ctrlpriv = dev_get_drvdata(jrdev->parent);
- moo = FIELD_GET(CSTA_MOO, ioread32(&ctrlpriv->ctrl->perfmon.status));
+ moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->ctrl->perfmon.status));
if (moo != CSTA_MOO_SECURE && moo != CSTA_MOO_TRUSTED)
dev_warn(jrdev,
"using insecure test key, enable HAB to use unique device key!\n");
pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n",
ctrl_status->status, destroy_session->session_id);
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
err = 0;
MODULE_LICENSE("GPL v2");
MODULE_IMPORT_NS(CXL);
MODULE_IMPORT_NS(ACPI);
-MODULE_SOFTDEP("pre: cxl_pmem");
return cxl_nvd;
}
-static void cxl_nvd_unregister(void *_cxl_nvd)
+static void cxlmd_release_nvdimm(void *_cxlmd)
{
- struct cxl_nvdimm *cxl_nvd = _cxl_nvd;
- struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+ struct cxl_memdev *cxlmd = _cxlmd;
+ struct cxl_nvdimm *cxl_nvd = cxlmd->cxl_nvd;
struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb;
- /*
- * Either the bridge is in ->remove() context under the device_lock(),
- * or cxlmd_release_nvdimm() is cancelling the bridge's release action
- * for @cxl_nvd and doing it itself (while manually holding the bridge
- * lock).
- */
- device_lock_assert(&cxl_nvb->dev);
cxl_nvd->cxlmd = NULL;
cxlmd->cxl_nvd = NULL;
+ cxlmd->cxl_nvb = NULL;
device_unregister(&cxl_nvd->dev);
-}
-
-static void cxlmd_release_nvdimm(void *_cxlmd)
-{
- struct cxl_memdev *cxlmd = _cxlmd;
- struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb;
-
- device_lock(&cxl_nvb->dev);
- if (cxlmd->cxl_nvd)
- devm_release_action(&cxl_nvb->dev, cxl_nvd_unregister,
- cxlmd->cxl_nvd);
- device_unlock(&cxl_nvb->dev);
put_device(&cxl_nvb->dev);
}
dev_dbg(&cxlmd->dev, "register %s\n", dev_name(dev));
- /*
- * The two actions below arrange for @cxl_nvd to be deleted when either
- * the top-level PMEM bridge goes down, or the endpoint device goes
- * through ->remove().
- */
- device_lock(&cxl_nvb->dev);
- if (cxl_nvb->dev.driver)
- rc = devm_add_action_or_reset(&cxl_nvb->dev, cxl_nvd_unregister,
- cxl_nvd);
- else
- rc = -ENXIO;
- device_unlock(&cxl_nvb->dev);
-
- if (rc)
- goto err_alloc;
-
/* @cxlmd carries a reference on @cxl_nvb until cxlmd_release_nvdimm */
return devm_add_action_or_reset(&cxlmd->dev, cxlmd_release_nvdimm, cxlmd);
struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
struct cxl_port *iter = cxled_to_port(cxled);
struct cxl_ep *ep;
- int rc;
+ int rc = 0;
while (!is_cxl_root(to_cxl_port(iter->dev.parent)))
iter = to_cxl_port(iter->dev.parent);
cxl_rr = cxl_rr_load(iter, cxlr);
cxld = cxl_rr->decoder;
- rc = cxld->reset(cxld);
+ if (cxld->reset)
+ rc = cxld->reset(cxld);
if (rc)
return rc;
}
iter = ep->next, ep = cxl_ep_load(iter, cxlmd)) {
cxl_rr = cxl_rr_load(iter, cxlr);
cxld = cxl_rr->decoder;
- cxld->reset(cxld);
+ if (cxld->reset)
+ cxld->reset(cxld);
}
cxled->cxld.reset(&cxled->cxld);
int i, distance;
/*
- * Passthrough ports impose no distance requirements between
+ * Passthrough decoders impose no distance requirements between
* peers
*/
- if (port->nr_dports == 1)
+ if (cxl_rr->nr_targets == 1)
distance = 0;
else
distance = p->nr_targets / cxl_rr->nr_targets;
/* If multiple errors, log header points to first error from ctrl reg */
if (hweight32(status) > 1) {
- addr = cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
- fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, readl(addr)));
+ void __iomem *rcc_addr =
+ cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
+
+ fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+ readl(rcc_addr)));
} else {
fe = status;
}
return cxl_pmem_nvdimm_ctl(nvdimm, cmd, buf, buf_len);
}
+static int detach_nvdimm(struct device *dev, void *data)
+{
+ struct cxl_nvdimm *cxl_nvd;
+ bool release = false;
+
+ if (!is_cxl_nvdimm(dev))
+ return 0;
+
+ device_lock(dev);
+ if (!dev->driver)
+ goto out;
+
+ cxl_nvd = to_cxl_nvdimm(dev);
+ if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data)
+ release = true;
+out:
+ device_unlock(dev);
+ if (release)
+ device_release_driver(dev);
+ return 0;
+}
+
static void unregister_nvdimm_bus(void *_cxl_nvb)
{
struct cxl_nvdimm_bridge *cxl_nvb = _cxl_nvb;
struct nvdimm_bus *nvdimm_bus = cxl_nvb->nvdimm_bus;
+ bus_for_each_dev(&cxl_bus_type, NULL, cxl_nvb, detach_nvdimm);
+
cxl_nvb->nvdimm_bus = NULL;
nvdimm_bus_unregister(nvdimm_bus);
}
/**
* dax_holder() - obtain the holder of a dax device
* @dax_dev: a dax_device instance
-
+ *
* Return: the holder's data which represents the holder if registered,
* otherwize NULL.
*/
kset_unregister(dma_buf_stats_kset);
}
-int dma_buf_stats_setup(struct dma_buf *dmabuf)
+int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file)
{
struct dma_buf_sysfs_entry *sysfs_entry;
int ret;
- if (!dmabuf || !dmabuf->file)
- return -EINVAL;
-
if (!dmabuf->exp_name) {
pr_err("exporter name must not be empty if stats needed\n");
return -EINVAL;
/* create the directory for buffer stats */
ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL,
- "%lu", file_inode(dmabuf->file)->i_ino);
+ "%lu", file_inode(file)->i_ino);
if (ret)
goto err_sysfs_dmabuf;
int dma_buf_init_sysfs_statistics(void);
void dma_buf_uninit_sysfs_statistics(void);
-int dma_buf_stats_setup(struct dma_buf *dmabuf);
+int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file);
void dma_buf_stats_teardown(struct dma_buf *dmabuf);
#else
static inline void dma_buf_uninit_sysfs_statistics(void) {}
-static inline int dma_buf_stats_setup(struct dma_buf *dmabuf)
+static inline int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file)
{
return 0;
}
return -EINVAL;
dmabuf = file->private_data;
-
- mutex_lock(&db_list.lock);
- list_del(&dmabuf->list_node);
- mutex_unlock(&db_list.lock);
+ if (dmabuf) {
+ mutex_lock(&db_list.lock);
+ list_del(&dmabuf->list_node);
+ mutex_unlock(&db_list.lock);
+ }
return 0;
}
return file->f_op == &dma_buf_fops;
}
-static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags)
+static struct file *dma_buf_getfile(size_t size, int flags)
{
static atomic64_t dmabuf_inode = ATOMIC64_INIT(0);
- struct file *file;
struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb);
+ struct file *file;
if (IS_ERR(inode))
return ERR_CAST(inode);
- inode->i_size = dmabuf->size;
- inode_set_bytes(inode, dmabuf->size);
+ inode->i_size = size;
+ inode_set_bytes(inode, size);
/*
* The ->i_ino acquired from get_next_ino() is not unique thus
flags, &dma_buf_fops);
if (IS_ERR(file))
goto err_alloc_file;
- file->private_data = dmabuf;
- file->f_path.dentry->d_fsdata = dmabuf;
return file;
size_t alloc_size = sizeof(struct dma_buf);
int ret;
- if (!exp_info->resv)
- alloc_size += sizeof(struct dma_resv);
- else
- /* prevent &dma_buf[1] == dma_buf->resv */
- alloc_size += 1;
-
- if (WARN_ON(!exp_info->priv
- || !exp_info->ops
- || !exp_info->ops->map_dma_buf
- || !exp_info->ops->unmap_dma_buf
- || !exp_info->ops->release)) {
+ if (WARN_ON(!exp_info->priv || !exp_info->ops
+ || !exp_info->ops->map_dma_buf
+ || !exp_info->ops->unmap_dma_buf
+ || !exp_info->ops->release))
return ERR_PTR(-EINVAL);
- }
if (WARN_ON(exp_info->ops->cache_sgt_mapping &&
(exp_info->ops->pin || exp_info->ops->unpin)))
if (!try_module_get(exp_info->owner))
return ERR_PTR(-ENOENT);
+ file = dma_buf_getfile(exp_info->size, exp_info->flags);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto err_module;
+ }
+
+ if (!exp_info->resv)
+ alloc_size += sizeof(struct dma_resv);
+ else
+ /* prevent &dma_buf[1] == dma_buf->resv */
+ alloc_size += 1;
dmabuf = kzalloc(alloc_size, GFP_KERNEL);
if (!dmabuf) {
ret = -ENOMEM;
- goto err_module;
+ goto err_file;
}
dmabuf->priv = exp_info->priv;
init_waitqueue_head(&dmabuf->poll);
dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll;
dmabuf->cb_in.active = dmabuf->cb_out.active = 0;
+ INIT_LIST_HEAD(&dmabuf->attachments);
if (!resv) {
- resv = (struct dma_resv *)&dmabuf[1];
- dma_resv_init(resv);
+ dmabuf->resv = (struct dma_resv *)&dmabuf[1];
+ dma_resv_init(dmabuf->resv);
+ } else {
+ dmabuf->resv = resv;
}
- dmabuf->resv = resv;
- file = dma_buf_getfile(dmabuf, exp_info->flags);
- if (IS_ERR(file)) {
- ret = PTR_ERR(file);
+ ret = dma_buf_stats_setup(dmabuf, file);
+ if (ret)
goto err_dmabuf;
- }
+ file->private_data = dmabuf;
+ file->f_path.dentry->d_fsdata = dmabuf;
dmabuf->file = file;
- INIT_LIST_HEAD(&dmabuf->attachments);
-
mutex_lock(&db_list.lock);
list_add(&dmabuf->list_node, &db_list.head);
mutex_unlock(&db_list.lock);
- ret = dma_buf_stats_setup(dmabuf);
- if (ret)
- goto err_sysfs;
-
return dmabuf;
-err_sysfs:
- /*
- * Set file->f_path.dentry->d_fsdata to NULL so that when
- * dma_buf_release() gets invoked by dentry_ops, it exits
- * early before calling the release() dma_buf op.
- */
- file->f_path.dentry->d_fsdata = NULL;
- fput(file);
err_dmabuf:
+ if (!resv)
+ dma_resv_fini(dmabuf->resv);
kfree(dmabuf);
+err_file:
+ fput(file);
err_module:
module_put(exp_info->owner);
return ERR_PTR(ret);
0, 0);
set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
- &dma_fence_stub.flags);
+ &fence->flags);
dma_fence_signal(fence);
/* The channel is already in use, update client count */
if (chan->client_count) {
__module_get(owner);
- goto out;
+ chan->client_count++;
+ return 0;
}
if (!try_module_get(owner))
goto err_out;
}
+ chan->client_count++;
+
if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask))
balance_ref_count(chan);
-out:
- chan->client_count++;
return 0;
err_out:
/* The bad descriptor currently is in the head of vc list */
vd = vchan_next_desc(&chan->vc);
+ if (!vd) {
+ dev_err(chan2dev(chan), "BUG: %s, IRQ with no descriptors\n",
+ axi_chan_name(chan));
+ goto out;
+ }
/* Remove the completed descriptor from issued list */
list_del(&vd->node);
/* Try to restart the controller */
axi_chan_start_first_queued(chan);
+out:
spin_unlock_irqrestore(&chan->vc.lock, flags);
}
spin_unlock(&ie->list_lock);
list_for_each_entry_safe(desc, itr, &flist, list) {
+ struct dma_async_tx_descriptor *tx;
+
list_del(&desc->list);
ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
+ /*
+ * wq is being disabled. Any remaining descriptors are
+ * likely to be stuck and can be dropped. callback could
+ * point to code that is no longer accessible, for example
+ * if dmatest module has been unloaded.
+ */
+ tx = &desc->txd;
+ tx->callback = NULL;
+ tx->callback_result = NULL;
idxd_dma_complete_txd(desc, ctype, true);
}
}
err_irq:
idxd_wq_unmap_portal(wq);
err_map_portal:
- rc = idxd_wq_disable(wq, false);
- if (rc < 0)
+ if (idxd_wq_disable(wq, false))
dev_dbg(dev, "wq %s disable failed\n", dev_name(wq_confdev(wq)));
err:
return rc;
dev_warn(dev, "Clients has claim on wq %d: %d\n",
wq->id, idxd_wq_refcount(wq));
- idxd_wq_free_resources(wq);
idxd_wq_unmap_portal(wq);
idxd_wq_drain(wq);
idxd_wq_free_irq(wq);
idxd_wq_reset(wq);
+ idxd_wq_free_resources(wq);
percpu_ref_exit(&wq->wq_active);
wq->type = IDXD_WQT_NONE;
wq->client_count = 0;
sdma_config_ownership(sdmac, false, true, false);
if (sdma_load_context(sdmac))
- goto err_desc_out;
+ goto err_bd_out;
return desc;
+err_bd_out:
+ sdma_free_bd(desc);
err_desc_out:
kfree(desc);
err_out:
}
}
-static int ldma_cfg_init(struct ldma_dev *d)
+static int ldma_parse_dt(struct ldma_dev *d)
{
struct fwnode_handle *fwnode = dev_fwnode(d->dev);
struct ldma_port *p;
p->ldev = d;
}
- ret = ldma_cfg_init(d);
- if (ret)
- return ret;
-
dma_dev->dev = &pdev->dev;
ch_mask = (unsigned long)d->channels_mask;
ldma_dma_init_v3X(j, d);
}
+ ret = ldma_parse_dt(d);
+ if (ret)
+ return ret;
+
dma_dev->device_alloc_chan_resources = ldma_alloc_chan_resources;
dma_dev->device_free_chan_resources = ldma_free_chan_resources;
dma_dev->device_terminate_all = ldma_terminate_all;
bool soc = FIELD_GET(DWORD0_SOC, desc->dw0);
u8 *q_desc = (u8 *)&cmd_q->qbase[cmd_q->qidx];
u32 tail;
+ unsigned long flags;
if (soc) {
desc->dw0 |= FIELD_PREP(DWORD0_IOC, desc->dw0);
desc->dw0 &= ~DWORD0_SOC;
}
- mutex_lock(&cmd_q->q_mutex);
+ spin_lock_irqsave(&cmd_q->q_lock, flags);
/* Copy 32-byte command descriptor to hw queue. */
memcpy(q_desc, desc, 32);
/* Turn the queue back on using our cached control register */
pt_start_queue(cmd_q);
- mutex_unlock(&cmd_q->q_mutex);
+ spin_unlock_irqrestore(&cmd_q->q_lock, flags);
return 0;
}
cmd_q->pt = pt;
cmd_q->dma_pool = dma_pool;
- mutex_init(&cmd_q->q_mutex);
+ spin_lock_init(&cmd_q->q_lock);
/* Page alignment satisfies our needs for N <= 128 */
cmd_q->qsize = Q_SIZE(Q_DESC_SIZE);
struct ptdma_desc *qbase;
/* Aligned queue start address (per requirement) */
- struct mutex q_mutex ____cacheline_aligned;
+ spinlock_t q_lock ____cacheline_aligned;
unsigned int qidx;
unsigned int qsize;
tre->dword[3] = u32_encode_bits(TRE_TYPE_GO, TRE_FLAGS_TYPE);
if (spi->cmd == SPI_RX) {
tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOB);
+ tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_LINK);
} else if (spi->cmd == SPI_TX) {
tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
} else { /* SPI_DUPLEX */
return err;
}
+ vchan_terminate_vdesc(&tdc->dma_desc->vd);
tegra_dma_disable(tdc);
tdc->dma_desc = NULL;
}
int ret;
/* Clear any interrupts */
- tdma_write(tdma, tdma->cdata->global_int_clear, 0x1);
+ tdma_write(tdma, tdma->cdata->ch_base_offset + tdma->cdata->global_int_clear, 0x1);
/* Assert soft reset */
tdma_write(tdma, ADMA_GLOBAL_SOFT_RESET, 0x1);
if (uc->desc->dir == DMA_DEV_TO_MEM) {
udma_rchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
udma_rchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
- udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
+ if (uc->config.ep_type != PSIL_EP_NATIVE)
+ udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
} else {
udma_tchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
udma_tchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
- if (!uc->bchan)
+ if (!uc->bchan && uc->config.ep_type != PSIL_EP_NATIVE)
udma_tchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
}
}
/* Initialize the channels */
for_each_child_of_node(node, child) {
err = xilinx_dma_child_probe(xdev, child);
- if (err < 0)
+ if (err < 0) {
+ of_node_put(child);
goto error;
+ }
}
if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
static DEFINE_MUTEX(device_ctls_mutex);
static LIST_HEAD(edac_device_list);
+/* Default workqueue processing interval on this instance, in msecs */
+#define DEFAULT_POLL_INTERVAL 1000
+
#ifdef CONFIG_EDAC_DEBUG
static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev)
{
* whole one second to save timers firing all over the period
* between integral seconds
*/
- if (edac_dev->poll_msec == 1000)
+ if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL)
edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
else
edac_queue_work(&edac_dev->work, edac_dev->delay);
* timers firing on sub-second basis, while they are happy
* to fire together on the 1 second exactly
*/
- if (edac_dev->poll_msec == 1000)
+ if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL)
edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
else
edac_queue_work(&edac_dev->work, edac_dev->delay);
* Then restart the workq on the new delay
*/
void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev,
- unsigned long value)
+ unsigned long msec)
{
- unsigned long jiffs = msecs_to_jiffies(value);
-
- if (value == 1000)
- jiffs = round_jiffies_relative(value);
-
- edac_dev->poll_msec = value;
- edac_dev->delay = jiffs;
+ edac_dev->poll_msec = msec;
+ edac_dev->delay = msecs_to_jiffies(msec);
- edac_mod_work(&edac_dev->work, jiffs);
+ /* See comment in edac_device_workq_setup() above */
+ if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL)
+ edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
+ else
+ edac_mod_work(&edac_dev->work, edac_dev->delay);
}
int edac_device_alloc_index(void)
/* This instance is NOW RUNNING */
edac_dev->op_state = OP_RUNNING_POLL;
- /*
- * enable workq processing on this instance,
- * default = 1000 msec
- */
- edac_device_workq_setup(edac_dev, 1000);
+ edac_device_workq_setup(edac_dev, edac_dev->poll_msec ?: DEFAULT_POLL_INTERVAL);
} else {
edac_dev->op_state = OP_RUNNING_INTERRUPT;
}
bool edac_mod_work(struct delayed_work *work, unsigned long delay);
extern void edac_device_reset_delay_period(struct edac_device_ctl_info
- *edac_dev, unsigned long value);
+ *edac_dev, unsigned long msec);
extern void edac_mc_reset_delay_period(unsigned long value);
/*
drvdata = mci->pvt_info;
platform_set_drvdata(pdev, mci);
- if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL))
- return -ENOMEM;
+ if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) {
+ res = -ENOMEM;
+ goto free;
+ }
r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!r) {
edac_mc_del_mc(&pdev->dev);
err:
devres_release_group(&pdev->dev, NULL);
+free:
edac_mc_free(mci);
return res;
}
static int
dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank)
{
- struct llcc_drv_data *drv = edev_ctl->pvt_info;
+ struct llcc_drv_data *drv = edev_ctl->dev->platform_data;
int ret;
ret = dump_syn_reg_values(drv, bank, err_type);
llcc_ecc_irq_handler(int irq, void *edev_ctl)
{
struct edac_device_ctl_info *edac_dev_ctl = edev_ctl;
- struct llcc_drv_data *drv = edac_dev_ctl->pvt_info;
+ struct llcc_drv_data *drv = edac_dev_ctl->dev->platform_data;
irqreturn_t irq_rc = IRQ_NONE;
u32 drp_error, trp_error, i;
int ret;
edev_ctl->dev_name = dev_name(dev);
edev_ctl->ctl_name = "llcc";
edev_ctl->panic_on_ue = LLCC_ERP_PANIC_ON_UE;
- edev_ctl->pvt_info = llcc_driv_data;
rc = edac_device_add_device(edev_ctl);
if (rc)
r = container_of(resource, struct inbound_transaction_resource,
resource);
- if (is_fcp_request(r->request))
+ if (is_fcp_request(r->request)) {
+ kfree(r->data);
goto out;
+ }
if (a->length != fw_get_response_length(r->request)) {
ret = -EINVAL;
xfer->hdr.protocol_id, xfer->hdr.seq,
xfer->hdr.poll_completion);
+ /* Clear any stale status */
+ xfer->hdr.status = SCMI_SUCCESS;
xfer->state = SCMI_XFER_SENT_OK;
/*
* Even though spinlocking is not needed here since no race is possible
void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem,
struct scmi_xfer *xfer)
{
+ size_t len = ioread32(&shmem->length);
+
xfer->hdr.status = ioread32(shmem->msg_payload);
/* Skip the length of header and status in shmem area i.e 8 bytes */
- xfer->rx.len = min_t(size_t, xfer->rx.len,
- ioread32(&shmem->length) - 8);
+ xfer->rx.len = min_t(size_t, xfer->rx.len, len > 8 ? len - 8 : 0);
/* Take a copy to the rx buffer.. */
memcpy_fromio(xfer->rx.buf, shmem->msg_payload + 4, xfer->rx.len);
void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem,
size_t max_len, struct scmi_xfer *xfer)
{
+ size_t len = ioread32(&shmem->length);
+
/* Skip only the length of header in shmem area i.e 4 bytes */
- xfer->rx.len = min_t(size_t, max_len, ioread32(&shmem->length) - 4);
+ xfer->rx.len = min_t(size_t, max_len, len > 4 ? len - 4 : 0);
/* Take a copy to the rx buffer.. */
memcpy_fromio(xfer->rx.buf, shmem->msg_payload, xfer->rx.len);
}
vioch->shutdown_done = &vioch_shutdown_done;
- virtio_break_device(vioch->vqueue->vdev);
if (!vioch->is_rx && vioch->deferred_tx_wq)
/* Cannot be kicked anymore after this...*/
vioch->deferred_tx_wq = NULL;
struct scmi_chan_info *cinfo = p;
struct scmi_vio_channel *vioch = cinfo->transport_info;
+ /*
+ * Break device to inhibit further traffic flowing while shutting down
+ * the channels: doing it later holding vioch->lock creates unsafe
+ * locking dependency chains as reported by LOCKDEP.
+ */
+ virtio_break_device(vioch->vqueue->vdev);
scmi_vio_channel_cleanup_sync(vioch);
scmi_free_channel(cinfo, data, id);
efi_kobj = kobject_create_and_add("efi", firmware_kobj);
if (!efi_kobj) {
pr_err("efi: Firmware registration failed.\n");
- destroy_workqueue(efi_rts_wq);
- return -ENOMEM;
+ error = -ENOMEM;
+ goto err_destroy_wq;
}
if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE |
err_put:
kobject_put(efi_kobj);
efi_kobj = NULL;
- destroy_workqueue(efi_rts_wq);
+err_destroy_wq:
+ if (efi_rts_wq)
+ destroy_workqueue(efi_rts_wq);
+
return error;
}
/* first try to find a slot in an existing linked list entry */
for (prsv = efi_memreserve_root->next; prsv; ) {
rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB);
+ if (!rsv)
+ return -ENOMEM;
index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size);
if (index < rsv->size) {
rsv->entry[index].base = addr;
const u8 *type1_family = efi_get_smbios_string(1, family);
/*
- * Ampere Altra machines crash in SetTime() if SetVirtualAddressMap()
- * has not been called prior.
+ * Ampere eMAG, Altra, and Altra Max machines crash in SetTime() if
+ * SetVirtualAddressMap() has not been called prior.
*/
- if (!type1_family || strcmp(type1_family, "Altra"))
+ if (!type1_family || (
+ strcmp(type1_family, "eMAG") &&
+ strcmp(type1_family, "Altra") &&
+ strcmp(type1_family, "Altra Max")))
return false;
efi_warn("Working around broken SetVirtualAddressMap()\n");
return -ENOMEM;
}
- if (tbl->version > 1) {
+ if (tbl->version > 2) {
pr_warn("Unexpected EFI Memory Attributes table version %d\n",
tbl->version);
goto unmap;
\
if (!efi_enabled(EFI_RUNTIME_SERVICES)) { \
pr_warn_once("EFI Runtime Services are disabled!\n"); \
+ efi_rts_work.status = EFI_DEVICE_ERROR; \
goto exit; \
} \
\
for (i = 0; i < header->table_entries; i++) {
entry = ptr_entry;
- device = kzalloc(sizeof(struct device) + entry->size, GFP_KERNEL);
+ if (entry->size < sizeof(*entry)) {
+ dev_warn(dev, "coreboot table entry too small!\n");
+ return -EINVAL;
+ }
+
+ device = kzalloc(sizeof(device->dev) + entry->size, GFP_KERNEL);
if (!device)
return -ENOMEM;
device->dev.parent = dev;
device->dev.bus = &coreboot_bus_type;
device->dev.release = coreboot_device_release;
- memcpy(&device->entry, ptr_entry, entry->size);
+ memcpy(device->raw, ptr_entry, entry->size);
switch (device->entry.tag) {
case LB_TAG_CBMEM_ENTRY:
struct lb_cbmem_ref cbmem_ref;
struct lb_cbmem_entry cbmem_entry;
struct lb_framebuffer framebuffer;
+ DECLARE_FLEX_ARRAY(u8, raw);
};
};
memcpy(data, gsmi_dev.data_buf->start, *data_size);
/* All variables are have the following attributes */
- *attr = EFI_VARIABLE_NON_VOLATILE |
- EFI_VARIABLE_BOOTSERVICE_ACCESS |
- EFI_VARIABLE_RUNTIME_ACCESS;
+ if (attr)
+ *attr = EFI_VARIABLE_NON_VOLATILE |
+ EFI_VARIABLE_BOOTSERVICE_ACCESS |
+ EFI_VARIABLE_RUNTIME_ACCESS;
}
spin_unlock_irqrestore(&gsmi_dev.lock, flags);
static int __init psci_debugfs_init(void)
{
+ if (!invoke_psci_fn || !psci_ops.get_version)
+ return 0;
+
return PTR_ERR_OR_ZERO(debugfs_create_file("psci", 0444, NULL, NULL,
&psci_debugfs_ops));
}
len = scnprintf(buf, SEC_UPDATE_LEN_MAX, "secure-update%d",
sec->fw_name_id);
sec->fw_name = kmemdup_nul(buf, len, GFP_KERNEL);
- if (!sec->fw_name)
- return -ENOMEM;
+ if (!sec->fw_name) {
+ ret = -ENOMEM;
+ goto fw_name_fail;
+ }
fwl = firmware_upload_register(THIS_MODULE, sec->dev, sec->fw_name,
&m10bmc_ops, sec);
if (IS_ERR(fwl)) {
dev_err(sec->dev, "Firmware Upload driver failed to start\n");
- kfree(sec->fw_name);
- xa_erase(&fw_upload_xa, sec->fw_name_id);
- return PTR_ERR(fwl);
+ ret = PTR_ERR(fwl);
+ goto fw_uploader_fail;
}
sec->fwl = fwl;
return 0;
+
+fw_uploader_fail:
+ kfree(sec->fw_name);
+fw_name_fail:
+ xa_erase(&fw_upload_xa, sec->fw_name_id);
+ return ret;
}
static int m10bmc_sec_remove(struct platform_device *pdev)
/* Allocate buffers from the service layer's pool. */
for (i = 0; i < NUM_SVC_BUFS; i++) {
kbuf = stratix10_svc_allocate_memory(priv->chan, SVC_BUF_SIZE);
- if (!kbuf) {
+ if (IS_ERR(kbuf)) {
s10_free_buffers(mgr);
- ret = -ENOMEM;
+ ret = PTR_ERR(kbuf);
goto init_done;
}
tristate "Mellanox BlueField 2 SoC GPIO"
depends on (MELLANOX_PLATFORM && ARM64 && ACPI) || (64BIT && COMPILE_TEST)
select GPIO_GENERIC
+ select GPIOLIB_IRQCHIP
help
Say Y here if you want GPIO support on Mellanox BlueField 2 SoC.
struct sprd_eic {
struct gpio_chip chip;
- struct irq_chip intc;
void __iomem *base[SPRD_EIC_MAX_BANK];
enum sprd_eic_type type;
spinlock_t lock;
default:
dev_err(chip->parent, "Unsupported EIC type.\n");
}
+
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_eic_irq_unmask(struct irq_data *data)
struct sprd_eic *sprd_eic = gpiochip_get_data(chip);
u32 offset = irqd_to_hwirq(data);
+ gpiochip_enable_irq(chip, offset);
+
switch (sprd_eic->type) {
case SPRD_EIC_DEBOUNCE:
sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IE, 1);
chained_irq_exit(ic, desc);
}
+static const struct irq_chip sprd_eic_irq = {
+ .name = "sprd-eic",
+ .irq_ack = sprd_eic_irq_ack,
+ .irq_mask = sprd_eic_irq_mask,
+ .irq_unmask = sprd_eic_irq_unmask,
+ .irq_set_type = sprd_eic_irq_set_type,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
static int sprd_eic_probe(struct platform_device *pdev)
{
const struct sprd_eic_variant_data *pdata;
break;
}
- sprd_eic->intc.name = dev_name(&pdev->dev);
- sprd_eic->intc.irq_ack = sprd_eic_irq_ack;
- sprd_eic->intc.irq_mask = sprd_eic_irq_mask;
- sprd_eic->intc.irq_unmask = sprd_eic_irq_unmask;
- sprd_eic->intc.irq_set_type = sprd_eic_irq_set_type;
- sprd_eic->intc.flags = IRQCHIP_SKIP_SET_WAKE;
-
irq = &sprd_eic->chip.irq;
- irq->chip = &sprd_eic->intc;
+ gpio_irq_chip_set_chip(irq, &sprd_eic_irq);
irq->handler = handle_bad_irq;
irq->default_type = IRQ_TYPE_NONE;
irq->parent_handler = sprd_eic_irq_handler;
#include <linux/slab.h>
#include <linux/gpio/driver.h>
#include <linux/bitops.h>
+#include <linux/seq_file.h>
#define EP93XX_GPIO_F_INT_STATUS 0x5c
#define EP93XX_GPIO_A_INT_STATUS 0xa0
#define EP93XX_GPIO_F_IRQ_BASE 80
struct ep93xx_gpio_irq_chip {
- struct irq_chip ic;
u8 irq_offset;
u8 int_unmasked;
u8 int_enabled;
*/
struct irq_chip *irqchip = irq_desc_get_chip(desc);
unsigned int irq = irq_desc_get_irq(desc);
- int port_f_idx = ((irq + 1) & 7) ^ 4; /* {19..22,47..50} -> {0..7} */
+ int port_f_idx = (irq & 7) ^ 4; /* {20..23,48..51} -> {0..7} */
int gpio_irq = EP93XX_GPIO_F_IRQ_BASE + port_f_idx;
chained_irq_enter(irqchip, desc);
ep93xx_gpio_update_int_params(epg, eic);
writeb(port_mask, epg->base + eic->irq_offset + EP93XX_INT_EOI_OFFSET);
+ gpiochip_disable_irq(gc, irqd_to_hwirq(d));
}
static void ep93xx_gpio_irq_mask(struct irq_data *d)
eic->int_unmasked &= ~BIT(d->irq & 7);
ep93xx_gpio_update_int_params(epg, eic);
+ gpiochip_disable_irq(gc, irqd_to_hwirq(d));
}
static void ep93xx_gpio_irq_unmask(struct irq_data *d)
struct ep93xx_gpio_irq_chip *eic = to_ep93xx_gpio_irq_chip(gc);
struct ep93xx_gpio *epg = gpiochip_get_data(gc);
+ gpiochip_enable_irq(gc, irqd_to_hwirq(d));
eic->int_unmasked |= BIT(d->irq & 7);
ep93xx_gpio_update_int_params(epg, eic);
}
return 0;
}
-static void ep93xx_init_irq_chip(struct device *dev, struct irq_chip *ic)
+static void ep93xx_irq_print_chip(struct irq_data *data, struct seq_file *p)
{
- ic->irq_ack = ep93xx_gpio_irq_ack;
- ic->irq_mask_ack = ep93xx_gpio_irq_mask_ack;
- ic->irq_mask = ep93xx_gpio_irq_mask;
- ic->irq_unmask = ep93xx_gpio_irq_unmask;
- ic->irq_set_type = ep93xx_gpio_irq_type;
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+
+ seq_printf(p, dev_name(gc->parent));
}
+static const struct irq_chip gpio_eic_irq_chip = {
+ .name = "ep93xx-gpio-eic",
+ .irq_ack = ep93xx_gpio_irq_ack,
+ .irq_mask = ep93xx_gpio_irq_mask,
+ .irq_unmask = ep93xx_gpio_irq_unmask,
+ .irq_mask_ack = ep93xx_gpio_irq_mask_ack,
+ .irq_set_type = ep93xx_gpio_irq_type,
+ .irq_print_chip = ep93xx_irq_print_chip,
+ .flags = IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc,
struct platform_device *pdev,
struct ep93xx_gpio *epg,
girq = &gc->irq;
if (bank->has_irq || bank->has_hierarchical_irq) {
- struct irq_chip *ic;
-
gc->set_config = ep93xx_gpio_set_config;
egc->eic = devm_kcalloc(dev, 1,
sizeof(*egc->eic),
if (!egc->eic)
return -ENOMEM;
egc->eic->irq_offset = bank->irq;
- ic = &egc->eic->ic;
- ic->name = devm_kasprintf(dev, GFP_KERNEL, "gpio-irq-%s", bank->label);
- if (!ic->name)
- return -ENOMEM;
- ep93xx_init_irq_chip(dev, ic);
- girq->chip = ic;
+ gpio_irq_chip_set_chip(girq, &gpio_eic_irq_chip);
}
if (bank->has_irq) {
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/spinlock.h>
#include <linux/syscore_ops.h>
#include <linux/gpio/driver.h>
#include <linux/of.h>
{
struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
struct mxc_gpio_port *port = gc->private;
+ unsigned long flags;
u32 bit, val;
u32 gpio_idx = d->hwirq;
int edge;
return -EINVAL;
}
+ raw_spin_lock_irqsave(&port->gc.bgpio_lock, flags);
+
if (GPIO_EDGE_SEL >= 0) {
val = readl(port->base + GPIO_EDGE_SEL);
if (edge == GPIO_INT_BOTH_EDGES)
writel(1 << gpio_idx, port->base + GPIO_ISR);
port->pad_type[gpio_idx] = type;
- return 0;
+ raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags);
+
+ return port->gc.direction_input(&port->gc, gpio_idx);
}
static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio)
{
void __iomem *reg = port->base;
+ unsigned long flags;
u32 bit, val;
int edge;
+ raw_spin_lock_irqsave(&port->gc.bgpio_lock, flags);
+
reg += GPIO_ICR1 + ((gpio & 0x10) >> 2); /* lower or upper register */
bit = gpio & 0xf;
val = readl(reg);
} else {
pr_err("mxc: invalid configuration for GPIO %d: %x\n",
gpio, edge);
- return;
+ goto unlock;
}
writel(val | (edge << (bit << 1)), reg);
+
+unlock:
+ raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags);
}
/* handle 32 interrupts in one status register */
case PCAL6524_DEBOUNCE:
pinctrl = ((reg & PCAL_PINCTRL_MASK) >> 1) + 0x1c;
break;
+ default:
+ pinctrl = 0;
+ break;
}
return pinctrl + addr + (off / BANK_SZ);
/**
* struct sprd_pmic_eic - PMIC EIC controller
* @chip: the gpio_chip structure.
- * @intc: the irq_chip structure.
* @map: the regmap from the parent device.
* @offset: the EIC controller's offset address of the PMIC.
* @reg: the array to cache the EIC registers.
*/
struct sprd_pmic_eic {
struct gpio_chip chip;
- struct irq_chip intc;
struct regmap *map;
u32 offset;
u8 reg[CACHE_NR_REGS];
{
struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
struct sprd_pmic_eic *pmic_eic = gpiochip_get_data(chip);
+ u32 offset = irqd_to_hwirq(data);
pmic_eic->reg[REG_IE] = 0;
pmic_eic->reg[REG_TRIG] = 0;
+
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_pmic_eic_irq_unmask(struct irq_data *data)
{
struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
struct sprd_pmic_eic *pmic_eic = gpiochip_get_data(chip);
+ u32 offset = irqd_to_hwirq(data);
+
+ gpiochip_enable_irq(chip, offset);
pmic_eic->reg[REG_IE] = 1;
pmic_eic->reg[REG_TRIG] = 1;
return IRQ_HANDLED;
}
+static const struct irq_chip pmic_eic_irq_chip = {
+ .name = "sprd-pmic-eic",
+ .irq_mask = sprd_pmic_eic_irq_mask,
+ .irq_unmask = sprd_pmic_eic_irq_unmask,
+ .irq_set_type = sprd_pmic_eic_irq_set_type,
+ .irq_bus_lock = sprd_pmic_eic_bus_lock,
+ .irq_bus_sync_unlock = sprd_pmic_eic_bus_sync_unlock,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
static int sprd_pmic_eic_probe(struct platform_device *pdev)
{
struct gpio_irq_chip *irq;
pmic_eic->chip.set = sprd_pmic_eic_set;
pmic_eic->chip.get = sprd_pmic_eic_get;
- pmic_eic->intc.name = dev_name(&pdev->dev);
- pmic_eic->intc.irq_mask = sprd_pmic_eic_irq_mask;
- pmic_eic->intc.irq_unmask = sprd_pmic_eic_irq_unmask;
- pmic_eic->intc.irq_set_type = sprd_pmic_eic_irq_set_type;
- pmic_eic->intc.irq_bus_lock = sprd_pmic_eic_bus_lock;
- pmic_eic->intc.irq_bus_sync_unlock = sprd_pmic_eic_bus_sync_unlock;
- pmic_eic->intc.flags = IRQCHIP_SKIP_SET_WAKE;
-
irq = &pmic_eic->chip.irq;
- irq->chip = &pmic_eic->intc;
+ gpio_irq_chip_set_chip(irq, &pmic_eic_irq_chip);
irq->threaded = true;
ret = devm_gpiochip_add_data(&pdev->dev, &pmic_eic->chip, pmic_eic);
return -ENODEV;
}
parent = irq_find_host(irq_parent);
+ of_node_put(irq_parent);
if (!parent) {
dev_err(dev, "no IRQ parent domain\n");
return -ENODEV;
gpiod_remove_hogs(dev->hogs);
- for (hog = dev->hogs; !hog->chip_label; hog++) {
+ for (hog = dev->hogs; hog->chip_label; hog++) {
kfree(hog->chip_label);
kfree(hog->line_name);
}
u32 offset = irqd_to_hwirq(data);
sprd_gpio_update(chip, offset, SPRD_GPIO_IE, 0);
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_gpio_irq_ack(struct irq_data *data)
u32 offset = irqd_to_hwirq(data);
sprd_gpio_update(chip, offset, SPRD_GPIO_IE, 1);
+ gpiochip_enable_irq(chip, offset);
}
static int sprd_gpio_irq_set_type(struct irq_data *data,
chained_irq_exit(ic, desc);
}
-static struct irq_chip sprd_gpio_irqchip = {
+static const struct irq_chip sprd_gpio_irqchip = {
.name = "sprd-gpio",
.irq_ack = sprd_gpio_irq_ack,
.irq_mask = sprd_gpio_irq_mask,
.irq_unmask = sprd_gpio_irq_unmask,
.irq_set_type = sprd_gpio_irq_set_type,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
};
static int sprd_gpio_probe(struct platform_device *pdev)
sprd_gpio->chip.direction_output = sprd_gpio_direction_output;
irq = &sprd_gpio->chip.irq;
- irq->chip = &sprd_gpio_irqchip;
+ gpio_irq_chip_set_chip(irq, &sprd_gpio_irqchip);
irq->handler = handle_bad_irq;
irq->default_type = IRQ_TYPE_NONE;
irq->parent_handler = sprd_gpio_irq_handler;
struct vf610_gpio_port {
struct gpio_chip gc;
- struct irq_chip ic;
void __iomem *base;
void __iomem *gpio_base;
const struct fsl_gpio_soc_data *sdata;
static void vf610_gpio_irq_mask(struct irq_data *d)
{
- struct vf610_gpio_port *port =
- gpiochip_get_data(irq_data_get_irq_chip_data(d));
- void __iomem *pcr_base = port->base + PORT_PCR(d->hwirq);
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct vf610_gpio_port *port = gpiochip_get_data(gc);
+ irq_hw_number_t gpio_num = irqd_to_hwirq(d);
+ void __iomem *pcr_base = port->base + PORT_PCR(gpio_num);
vf610_gpio_writel(0, pcr_base);
+ gpiochip_disable_irq(gc, gpio_num);
}
static void vf610_gpio_irq_unmask(struct irq_data *d)
{
- struct vf610_gpio_port *port =
- gpiochip_get_data(irq_data_get_irq_chip_data(d));
- void __iomem *pcr_base = port->base + PORT_PCR(d->hwirq);
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct vf610_gpio_port *port = gpiochip_get_data(gc);
+ irq_hw_number_t gpio_num = irqd_to_hwirq(d);
+ void __iomem *pcr_base = port->base + PORT_PCR(gpio_num);
- vf610_gpio_writel(port->irqc[d->hwirq] << PORT_PCR_IRQC_OFFSET,
+ gpiochip_enable_irq(gc, gpio_num);
+ vf610_gpio_writel(port->irqc[gpio_num] << PORT_PCR_IRQC_OFFSET,
pcr_base);
}
return 0;
}
+static const struct irq_chip vf610_irqchip = {
+ .name = "gpio-vf610",
+ .irq_ack = vf610_gpio_irq_ack,
+ .irq_mask = vf610_gpio_irq_mask,
+ .irq_unmask = vf610_gpio_irq_unmask,
+ .irq_set_type = vf610_gpio_irq_set_type,
+ .irq_set_wake = vf610_gpio_irq_set_wake,
+ .flags = IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
static void vf610_gpio_disable_clk(void *data)
{
clk_disable_unprepare(data);
struct vf610_gpio_port *port;
struct gpio_chip *gc;
struct gpio_irq_chip *girq;
- struct irq_chip *ic;
int i;
int ret;
gc->direction_output = vf610_gpio_direction_output;
gc->set = vf610_gpio_set;
- ic = &port->ic;
- ic->name = "gpio-vf610";
- ic->irq_ack = vf610_gpio_irq_ack;
- ic->irq_mask = vf610_gpio_irq_mask;
- ic->irq_unmask = vf610_gpio_irq_unmask;
- ic->irq_set_type = vf610_gpio_irq_set_type;
- ic->irq_set_wake = vf610_gpio_irq_set_wake;
-
/* Mask all GPIO interrupts */
for (i = 0; i < gc->ngpio; i++)
vf610_gpio_writel(0, port->base + PORT_PCR(i));
vf610_gpio_writel(~0, port->base + PORT_ISFR);
girq = &gc->irq;
- girq->chip = ic;
+ gpio_irq_chip_set_chip(girq, &vf610_irqchip);
girq->parent_handler = vf610_gpio_irq_handler;
girq->num_parents = 1;
girq->parents = devm_kcalloc(&pdev->dev, 1,
}
static bool acpi_gpio_irq_is_wake(struct device *parent,
- struct acpi_resource_gpio *agpio)
+ const struct acpi_resource_gpio *agpio)
{
unsigned int pin = agpio->pin_table[0];
lookup->info.pin_config = agpio->pin_config;
lookup->info.debounce = agpio->debounce_timeout;
lookup->info.gpioint = gpioint;
- lookup->info.wake_capable = agpio->wake_capable == ACPI_WAKE_CAPABLE;
+ lookup->info.wake_capable = acpi_gpio_irq_is_wake(&lookup->info.adev->dev, agpio);
/*
* Polarity and triggering are only specified for GpioInt
dev_dbg(&adev->dev, "IRQ %d already in use\n", irq);
}
- if (wake_capable)
+ /* avoid suspend issues with GPIOs when systems are using S3 */
+ if (wake_capable && acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)
*wake_capable = info.wake_capable;
return irq;
.ignore_interrupt = "AMDI0030:00@18",
},
},
+ {
+ /*
+ * Spurious wakeups from TP_ATTN# pin
+ * Found in BIOS 1.7.8
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/1722#note_1720627
+ */
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"),
+ },
+ .driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+ .ignore_wake = "ELAN0415:00@9",
+ },
+ },
+ {
+ /*
+ * Spurious wakeups from TP_ATTN# pin
+ * Found in BIOS 1.7.7
+ */
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "NH5xAx"),
+ },
+ .driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+ .ignore_wake = "SYNA1202:00@16",
+ },
+ },
{} /* Terminating entry */
};
#include <linux/gpio/consumer.h>
-struct acpi_device;
struct device;
struct fwnode_handle;
const char *label,
bool platform_lookup_allowed)
{
+ unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT;
struct gpio_desc *desc = ERR_PTR(-ENOENT);
- unsigned long lookupflags;
int ret;
if (!IS_ERR_OR_NULL(fwnode))
config DRM_USE_DYNAMIC_DEBUG
bool "use dynamic debug to implement drm.debug"
- default y
+ default n
+ depends on BROKEN
depends on DRM
depends on DYNAMIC_DEBUG || DYNAMIC_DEBUG_CORE
depends on JUMP_LABEL
extern uint amdgpu_smu_memory_pool_size;
extern int amdgpu_smu_pptable_id;
extern uint amdgpu_dc_feature_mask;
+extern uint amdgpu_freesync_vid_mode;
extern uint amdgpu_dc_debug_mask;
extern uint amdgpu_dc_visual_confirm;
extern uint amdgpu_dm_abm_level;
#define AMDGPU_VCNFW_LOG_SIZE (32 * 1024)
extern int amdgpu_vcnfw_log;
+extern int amdgpu_sg_display;
#define AMDGPU_VM_MAX_NUM_CTX 4096
#define AMDGPU_SG_THRESHOLD (256*1024*1024)
}
amdgpu_amdkfd_remove_eviction_fence(
- bo, bo->kfd_bo->process_info->eviction_fence);
+ bo, bo->vm_bo->vm->process_info->eviction_fence);
amdgpu_bo_unreserve(bo);
amdgpu_ctx_put(p->ctx);
return -ECANCELED;
}
+
+ amdgpu_sync_create(&p->sync);
return 0;
}
}
r = amdgpu_sync_fence(&p->sync, fence);
- if (r)
- goto error;
-
- /*
- * When we have an explicit dependency it might be necessary to insert a
- * pipeline sync to make sure that all caches etc are flushed and the
- * next job actually sees the results from the previous one.
- */
- if (fence->context == p->gang_leader->base.entity->fence_context)
- r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
-
-error:
dma_fence_put(fence);
return r;
}
static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
{
struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+ struct drm_gpu_scheduler *sched;
struct amdgpu_bo_list_entry *e;
+ struct dma_fence *fence;
unsigned int i;
int r;
+ r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]);
+ if (r) {
+ if (r != -ERESTARTSYS)
+ DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n");
+ return r;
+ }
+
list_for_each_entry(e, &p->validated, tv.head) {
struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
struct dma_resv *resv = bo->tbo.base.resv;
return r;
}
- r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]);
- if (r && r != -ERESTARTSYS)
- DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n");
- return r;
+ sched = p->gang_leader->base.entity->rq->sched;
+ while ((fence = amdgpu_sync_get_fence(&p->sync))) {
+ struct drm_sched_fence *s_fence = to_drm_sched_fence(fence);
+
+ /*
+ * When we have an dependency it might be necessary to insert a
+ * pipeline sync to make sure that all caches etc are flushed and the
+ * next job actually sees the results from the previous one
+ * before we start executing on the same scheduler ring.
+ */
+ if (!s_fence || s_fence->sched != sched) {
+ dma_fence_put(fence);
+ continue;
+ }
+
+ r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
+ dma_fence_put(fence);
+ if (r)
+ return r;
+ }
+ return 0;
}
static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
continue;
fence = &p->jobs[i]->base.s_fence->scheduled;
+ dma_fence_get(fence);
r = drm_sched_job_add_dependency(&leader->base, fence);
- if (r)
+ if (r) {
+ dma_fence_put(fence);
goto error_cleanup;
+ }
}
if (p->gang_size > 1) {
{
unsigned i;
+ amdgpu_sync_free(&parser->sync);
for (i = 0; i < parser->num_post_deps; i++) {
drm_syncobj_put(parser->post_deps[i].syncobj);
kfree(parser->post_deps[i].chain);
#include <generated/utsrelease.h>
#include <linux/pci-p2pdma.h>
+#include <drm/drm_aperture.h>
#include <drm/drm_atomic_helper.h>
#include <drm/drm_fb_helper.h>
#include <drm/drm_probe_helper.h>
#define AMDGPU_MAX_RETRY_LIMIT 2
#define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL)
+static const struct drm_driver amdgpu_kms_driver;
+
const char *amdgpu_asic_name[] = {
"TAHITI",
"PITCAIRN",
if (r)
return r;
+ /* Get rid of things like offb */
+ r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
+ if (r)
+ return r;
+
/* Enable TMZ based on IP_VERSION */
amdgpu_gmc_tmz_set(adev);
}
adev->in_suspend = false;
+ if (adev->enable_mes)
+ amdgpu_mes_self_test(adev);
+
if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0))
DRM_WARN("smart shift update failed\n");
*/
#include <drm/amdgpu_drm.h>
-#include <drm/drm_aperture.h>
#include <drm/drm_drv.h>
#include <drm/drm_fbdev_generic.h>
#include <drm/drm_gem.h>
int amdgpu_noretry = -1;
int amdgpu_force_asic_type = -1;
int amdgpu_tmz = -1; /* auto */
+uint amdgpu_freesync_vid_mode;
int amdgpu_reset_method = -1; /* auto */
int amdgpu_num_kcq = -1;
int amdgpu_smartshift_bias;
int amdgpu_use_xgmi_p2p = 1;
int amdgpu_vcnfw_log;
+int amdgpu_sg_display = -1; /* auto */
static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
MODULE_PARM_DESC(tmz, "Enable TMZ feature (-1 = auto (default), 0 = off, 1 = on)");
module_param_named(tmz, amdgpu_tmz, int, 0444);
+/**
+ * DOC: freesync_video (uint)
+ * Enable the optimization to adjust front porch timing to achieve seamless
+ * mode change experience when setting a freesync supported mode for which full
+ * modeset is not needed.
+ *
+ * The Display Core will add a set of modes derived from the base FreeSync
+ * video mode into the corresponding connector's mode list based on commonly
+ * used refresh rates and VRR range of the connected display, when users enable
+ * this feature. From the userspace perspective, they can see a seamless mode
+ * change experience when the change between different refresh rates under the
+ * same resolution. Additionally, userspace applications such as Video playback
+ * can read this modeset list and change the refresh rate based on the video
+ * frame rate. Finally, the userspace can also derive an appropriate mode for a
+ * particular refresh rate based on the FreeSync Mode and add it to the
+ * connector's mode list.
+ *
+ * Note: This is an experimental feature.
+ *
+ * The default value: 0 (off).
+ */
+MODULE_PARM_DESC(
+ freesync_video,
+ "Enable freesync modesetting optimization feature (0 = off (default), 1 = on)");
+module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444);
+
/**
* DOC: reset_method (int)
* GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)
MODULE_PARM_DESC(vcnfw_log, "Enable vcnfw log(0 = disable (default value), 1 = enable)");
module_param_named(vcnfw_log, amdgpu_vcnfw_log, int, 0444);
+/**
+ * DOC: sg_display (int)
+ * Disable S/G (scatter/gather) display (i.e., display from system memory).
+ * This option is only relevant on APUs. Set this option to 0 to disable
+ * S/G display if you experience flickering or other issues under memory
+ * pressure and report the issue.
+ */
+MODULE_PARM_DESC(sg_display, "S/G Display (-1 = auto (default), 0 = disable)");
+module_param_named(sg_display, amdgpu_sg_display, int, 0444);
+
/**
* DOC: smu_pptable_id (int)
* Used to override pptable id. id = 0 use VBIOS pptable.
}
#endif
- /* Get rid of things like offb */
- ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver);
- if (ret)
- return ret;
-
adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev);
if (IS_ERR(adev))
return PTR_ERR(adev);
if (!ring || !ring->fence_drv.initialized)
continue;
- if (!ring->no_scheduler)
+ /*
+ * Notice we check for sched.ops since there's some
+ * override on the meaning of sched.ready by amdgpu.
+ * The natural check would be sched.ready, which is
+ * set as drm_sched_init() finishes...
+ */
+ if (ring->sched.ops)
drm_sched_fini(&ring->sched);
for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
return amdgpu_compute_multipipe == 1;
}
+ if (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0))
+ return true;
+
/* FIXME: spreading the queues across pipes causes perf regressions
* on POLARIS11 compute workloads */
if (adev->asic_type == CHIP_POLARIS11)
!--id_mgr->reserved_use_count) {
/* give the reserved ID back to normal round robin */
list_add(&id_mgr->reserved->list, &id_mgr->ids_lru);
+ id_mgr->reserved = NULL;
}
vm->reserved_vmid[vmhub] = false;
mutex_unlock(&id_mgr->lock);
struct dma_fence *f;
unsigned i;
- /* use sched fence if available */
- f = job->base.s_fence ? &job->base.s_fence->finished : &job->hw_fence;
+ /* Check if any fences where initialized */
+ if (job->base.s_fence && job->base.s_fence->finished.ops)
+ f = &job->base.s_fence->finished;
+ else if (job->hw_fence.ops)
+ f = &job->hw_fence;
+ else
+ f = NULL;
+
for (i = 0; i < job->num_ibs; ++i)
amdgpu_ib_free(ring->adev, &job->ibs[i], f);
}
return true;
fail:
- DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
- man->size);
+ if (man)
+ DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
+ man->size);
return false;
}
#define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib)))
#define amdgpu_ring_patch_cs_in_place(r, p, job, ib) ((r)->funcs->patch_cs_in_place((p), (job), (ib)))
#define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r))
-#define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t))
+#define amdgpu_ring_test_ib(r, t) ((r)->funcs->test_ib ? (r)->funcs->test_ib((r), (t)) : 0)
#define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
#define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r))
#define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))
dma_fence_get(f);
r = drm_sched_job_add_dependency(&job->base, f);
- if (r)
+ if (r) {
+ dma_fence_put(f);
return r;
+ }
}
return 0;
}
trace_amdgpu_vm_update_ptes(params, frag_start, upd_end,
min(nptes, 32u), dst, incr,
upd_flags,
- vm->task_info.pid,
+ vm->task_info.tgid,
vm->immediate.fence_context);
amdgpu_vm_pte_update_flags(params, to_amdgpu_bo_vm(pt),
cursor.level, pe_start, dst,
kfree(rsv);
list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
- drm_buddy_free_list(&mgr->mm, &rsv->blocks);
+ drm_buddy_free_list(&mgr->mm, &rsv->allocated);
kfree(rsv);
}
drm_buddy_fini(&mgr->mm);
* zero here */
WARN_ON(simd != 0);
- /* type 2 wave data */
- dst[(*no_fields)++] = 2;
+ /* type 3 wave data */
+ dst[(*no_fields)++] = 3;
dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_STATUS);
dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_LO);
dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_HI);
switch (adev->ip_versions[GC_HWIP][0]) {
case IP_VERSION(11, 0, 0):
- case IP_VERSION(11, 0, 1):
case IP_VERSION(11, 0, 2):
case IP_VERSION(11, 0, 3):
- case IP_VERSION(11, 0, 4):
adev->gfx.me.num_me = 1;
adev->gfx.me.num_pipe_per_me = 1;
adev->gfx.me.num_queue_per_pipe = 1;
adev->gfx.mec.num_pipe_per_mec = 4;
adev->gfx.mec.num_queue_per_pipe = 4;
break;
+ case IP_VERSION(11, 0, 1):
+ case IP_VERSION(11, 0, 4):
+ adev->gfx.me.num_me = 1;
+ adev->gfx.me.num_pipe_per_me = 1;
+ adev->gfx.me.num_queue_per_pipe = 1;
+ adev->gfx.mec.num_mec = 1;
+ adev->gfx.mec.num_pipe_per_mec = 4;
+ adev->gfx.mec.num_queue_per_pipe = 4;
+ break;
default:
adev->gfx.me.num_me = 1;
adev->gfx.me.num_pipe_per_me = 1;
.emit_gds_switch = gfx_v9_0_ring_emit_gds_switch,
.emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush,
.test_ring = gfx_v9_0_ring_test_ring,
- .test_ib = gfx_v9_0_ring_test_ib,
.insert_nop = amdgpu_ring_insert_nop,
.pad_ib = amdgpu_ring_generic_pad_ib,
.emit_switch_buffer = gfx_v9_ring_emit_sb,
MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin");
static int imu_v11_0_init_microcode(struct amdgpu_device *adev)
{
MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes1.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes1.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes1.bin");
static int mes_v11_0_hw_fini(void *handle);
static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev);
mes_add_queue_pkt.trap_handler_addr = input->tba_addr;
mes_add_queue_pkt.tma_addr = input->tma_addr;
mes_add_queue_pkt.is_kfd_process = input->is_kfd_process;
- mes_add_queue_pkt.trap_en = 1;
/* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */
mes_add_queue_pkt.is_aql_queue = input->is_aql_queue;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* it's only intended for use in mes_self_test case, not for s0ix and reset */
- if (!amdgpu_in_reset(adev) && !adev->in_s0ix &&
+ if (!amdgpu_in_reset(adev) && !adev->in_s0ix && !adev->in_suspend &&
(adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3)))
amdgpu_mes_self_test(adev);
static void nbio_v4_3_init_registers(struct amdgpu_device *adev)
{
- return;
+ if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(4, 3, 0)) {
+ uint32_t data;
+
+ data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2);
+ data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK;
+ WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data);
+ }
}
static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev)
AMD_CG_SUPPORT_GFX_CGCG |
AMD_CG_SUPPORT_GFX_CGLS |
AMD_CG_SUPPORT_REPEATER_FGCG |
- AMD_CG_SUPPORT_GFX_MGCG;
+ AMD_CG_SUPPORT_GFX_MGCG |
+ AMD_CG_SUPPORT_HDP_SD |
+ AMD_CG_SUPPORT_ATHUB_MGCG |
+ AMD_CG_SUPPORT_ATHUB_LS;
adev->pg_flags = AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_VCN_DPG |
AMD_PG_SUPPORT_JPEG;
queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
if (q->wptr_bo) {
- wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va;
+ wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1);
queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off;
}
goto reserve_bo_failed;
}
+ if (clear) {
+ r = amdgpu_bo_sync_wait(bo, AMDGPU_FENCE_OWNER_KFD, false);
+ if (r) {
+ pr_debug("failed %d to sync bo\n", r);
+ amdgpu_bo_unreserve(bo);
+ goto reserve_bo_failed;
+ }
+ }
+
r = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
if (r) {
pr_debug("failed %d to reserve bo\n", r);
p2plink->attr.name = "properties";
p2plink->attr.mode = KFD_SYSFS_FILE_MODE;
- sysfs_attr_init(&iolink->attr);
+ sysfs_attr_init(&p2plink->attr);
ret = sysfs_create_file(p2plink->kobj, &p2plink->attr);
if (ret < 0)
return ret;
memset(pa_config, 0, sizeof(*pa_config));
- logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
- pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
-
- if (adev->apu_flags & AMD_APU_IS_RAVEN2)
- /*
- * Raven2 has a HW issue that it is unable to use the vram which
- * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
- * workaround that increase system aperture high address (add 1)
- * to get rid of the VM fault and hardware hang.
- */
- logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18);
- else
- logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18;
-
agp_base = 0;
agp_bot = adev->gmc.agp_start >> 24;
agp_top = adev->gmc.agp_end >> 24;
+ /* AGP aperture is disabled */
+ if (agp_bot == agp_top) {
+ logical_addr_low = adev->gmc.vram_start >> 18;
+ if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+ /*
+ * Raven2 has a HW issue that it is unable to use the vram which
+ * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
+ * workaround that increase system aperture high address (add 1)
+ * to get rid of the VM fault and hardware hang.
+ */
+ logical_addr_high = (adev->gmc.fb_end >> 18) + 0x1;
+ else
+ logical_addr_high = adev->gmc.vram_end >> 18;
+ } else {
+ logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
+ if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+ /*
+ * Raven2 has a HW issue that it is unable to use the vram which
+ * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
+ * workaround that increase system aperture high address (add 1)
+ * to get rid of the VM fault and hardware hang.
+ */
+ logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18);
+ else
+ logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18;
+ }
+
+ pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF;
page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12);
}
break;
}
+ if (init_data.flags.gpu_vm_support &&
+ (amdgpu_sg_display == 0))
+ init_data.flags.gpu_vm_support = false;
if (init_data.flags.gpu_vm_support)
adev->mode_info.gpu_vm_support = true;
adev->dm.vblank_control_workqueue = NULL;
}
- for (i = 0; i < adev->dm.display_indexes_num; i++) {
- drm_encoder_cleanup(&adev->dm.mst_encoders[i].base);
- }
-
amdgpu_dm_destroy_drm_device(&adev->dm);
#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
amdgpu_set_panel_orientation(&aconnector->base);
}
+ /* If we didn't find a panel, notify the acpi video detection */
+ if (dm->adev->flags & AMD_IS_APU && dm->num_of_edps == 0)
+ acpi_video_report_nolcd();
+
/* Software is initialized. Now we can register interrupt handlers. */
switch (adev->asic_type) {
#if defined(CONFIG_DRM_AMD_DC_SI)
static int dm_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ struct amdgpu_mode_info *mode_info = &adev->mode_info;
+ struct atom_context *ctx = mode_info->atom_context;
+ int index = GetIndexIntoMasterTable(DATA, Object_Header);
+ u16 data_offset;
+
+ /* if there is no object header, skip DM */
+ if (!amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) {
+ adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK;
+ dev_info(adev->dev, "No object header, skipping DM\n");
+ return -ENOENT;
+ }
switch (adev->asic_type) {
#if defined(CONFIG_DRM_AMD_DC_SI)
timing_out->aspect_ratio = get_aspect_ratio(mode_in);
- stream->output_color_space = get_output_color_space(timing_out);
-
stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
adjust_colour_depth_from_display_info(timing_out, info);
}
}
+
+ stream->output_color_space = get_output_color_space(timing_out);
}
static void fill_audio_info(struct audio_info *audio_info,
*/
DRM_DEBUG_DRIVER("No preferred mode found\n");
} else {
- recalculate_timing = is_freesync_video_mode(&mode, aconnector);
+ recalculate_timing = amdgpu_freesync_vid_mode &&
+ is_freesync_video_mode(&mode, aconnector);
if (recalculate_timing) {
freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
drm_mode_copy(&saved_mode, &mode);
struct amdgpu_dm_connector *amdgpu_dm_connector =
to_amdgpu_dm_connector(connector);
- if (!edid)
+ if (!(amdgpu_freesync_vid_mode && edid))
return;
if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10)
* TODO: Refactor this function to allow this check to work
* in all conditions.
*/
- if (dm_new_crtc_state->stream &&
+ if (amdgpu_freesync_vid_mode &&
+ dm_new_crtc_state->stream &&
is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state))
goto skip_modeset;
if (!dm_old_crtc_state->stream)
goto skip_modeset;
- if (dm_new_crtc_state->stream &&
+ /* Unset freesync video if it was active before */
+ if (dm_old_crtc_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED) {
+ dm_new_crtc_state->freesync_config.state = VRR_STATE_INACTIVE;
+ dm_new_crtc_state->freesync_config.fixed_refresh_in_uhz = 0;
+ }
+
+ /* Now check if we should set freesync video mode */
+ if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream &&
is_timing_unchanged_for_freesync(new_crtc_state,
old_crtc_state)) {
new_crtc_state->mode_changed = false;
set_freesync_fixed_config(dm_new_crtc_state);
goto skip_modeset;
- } else if (aconnector &&
+ } else if (amdgpu_freesync_vid_mode && aconnector &&
is_freesync_video_mode(&new_crtc_state->mode,
aconnector)) {
struct drm_display_mode *high_mode;
bool lock_and_validation_needed = false;
struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
#if defined(CONFIG_DRM_AMD_DC_DCN)
+ struct drm_dp_mst_topology_mgr *mgr;
+ struct drm_dp_mst_topology_state *mst_state;
struct dsc_mst_fairness_vars vars[MAX_PIPES];
#endif
goto fail;
}
- if (dm_old_con_state->abm_level !=
- dm_new_con_state->abm_level)
+ if (dm_old_con_state->abm_level != dm_new_con_state->abm_level ||
+ dm_old_con_state->scaling != dm_new_con_state->scaling)
new_crtc_state->connectors_changed = true;
}
* `dcn10_can_pipe_disable_cursor`). By now, all modified planes are in
* atomic state, so call drm helper to normalize zpos.
*/
- drm_atomic_normalize_zpos(dev, state);
+ ret = drm_atomic_normalize_zpos(dev, state);
+ if (ret) {
+ drm_dbg(dev, "drm_atomic_normalize_zpos() failed\n");
+ goto fail;
+ }
/* Remove exiting planes if they are modified */
for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
lock_and_validation_needed = true;
}
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+ /* set the slot info for each mst_state based on the link encoding format */
+ for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) {
+ struct amdgpu_dm_connector *aconnector;
+ struct drm_connector *connector;
+ struct drm_connector_list_iter iter;
+ u8 link_coding_cap;
+
+ drm_connector_list_iter_begin(dev, &iter);
+ drm_for_each_connector_iter(connector, &iter) {
+ if (connector->index == mst_state->mgr->conn_base_id) {
+ aconnector = to_amdgpu_dm_connector(connector);
+ link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(aconnector->dc_link);
+ drm_dp_mst_update_slots(mst_state, link_coding_cap);
+
+ break;
+ }
+ }
+ drm_connector_list_iter_end(&iter);
+ }
+#endif
+
/**
* Streams and planes are reset when there are changes that affect
* bandwidth. Anything that affects bandwidth needs to go through
}
static void
-fill_dc_mst_payload_table_from_drm(struct drm_dp_mst_topology_state *mst_state,
- struct amdgpu_dm_connector *aconnector,
+fill_dc_mst_payload_table_from_drm(struct dc_link *link,
+ bool enable,
+ struct drm_dp_mst_atomic_payload *target_payload,
struct dc_dp_mst_stream_allocation_table *table)
{
struct dc_dp_mst_stream_allocation_table new_table = { 0 };
struct dc_dp_mst_stream_allocation *sa;
- struct drm_dp_mst_atomic_payload *payload;
+ struct link_mst_stream_allocation_table copy_of_link_table =
+ link->mst_stream_alloc_table;
+
+ int i;
+ int current_hw_table_stream_cnt = copy_of_link_table.stream_count;
+ struct link_mst_stream_allocation *dc_alloc;
+
+ /* TODO: refactor to set link->mst_stream_alloc_table directly if possible.*/
+ if (enable) {
+ dc_alloc =
+ ©_of_link_table.stream_allocations[current_hw_table_stream_cnt];
+ dc_alloc->vcp_id = target_payload->vcpi;
+ dc_alloc->slot_count = target_payload->time_slots;
+ } else {
+ for (i = 0; i < copy_of_link_table.stream_count; i++) {
+ dc_alloc =
+ ©_of_link_table.stream_allocations[i];
+
+ if (dc_alloc->vcp_id == target_payload->vcpi) {
+ dc_alloc->vcp_id = 0;
+ dc_alloc->slot_count = 0;
+ break;
+ }
+ }
+ ASSERT(i != copy_of_link_table.stream_count);
+ }
/* Fill payload info*/
- list_for_each_entry(payload, &mst_state->payloads, next) {
- if (payload->delete)
- continue;
-
- sa = &new_table.stream_allocations[new_table.stream_count];
- sa->slot_count = payload->time_slots;
- sa->vcp_id = payload->vcpi;
- new_table.stream_count++;
+ for (i = 0; i < MAX_CONTROLLER_NUM; i++) {
+ dc_alloc =
+ ©_of_link_table.stream_allocations[i];
+ if (dc_alloc->vcp_id > 0 && dc_alloc->slot_count > 0) {
+ sa = &new_table.stream_allocations[new_table.stream_count];
+ sa->slot_count = dc_alloc->slot_count;
+ sa->vcp_id = dc_alloc->vcp_id;
+ new_table.stream_count++;
+ }
}
/* Overwrite the old table */
* AUX message. The sequence is slot 1-63 allocated sequence for each
* stream. AMD ASIC stream slot allocation should follow the same
* sequence. copy DRM MST allocation to dc */
- fill_dc_mst_payload_table_from_drm(mst_state, aconnector, proposed_table);
+ fill_dc_mst_payload_table_from_drm(stream->link, enable, payload, proposed_table);
return true;
}
static void amdgpu_dm_encoder_destroy(struct drm_encoder *encoder)
{
drm_encoder_cleanup(encoder);
- kfree(encoder);
}
static const struct drm_encoder_funcs amdgpu_dm_encoder_funcs = {
if (IS_ERR(mst_state))
return PTR_ERR(mst_state);
- mst_state->pbn_div = dm_mst_get_pbn_divider(dc_link);
-#if defined(CONFIG_DRM_AMD_DC_DCN)
- drm_dp_mst_update_slots(mst_state, dc_link_dp_mst_decide_link_encoding_format(dc_link));
-#endif
-
/* Set up params */
for (i = 0; i < dc_state->stream_count; i++) {
struct dc_dsc_policy dsc_policy = {0};
{ 0xE00, 0xF349, 0xFEB7, 0x1000, 0x6CE, 0x16E3,
0x24F, 0x200, 0xFCCB, 0xF535, 0xE00, 0x1000} },
{ COLOR_SPACE_YCBCR2020_TYPE,
- { 0x1000, 0xF149, 0xFEB7, 0x0000, 0x0868, 0x15B2,
- 0x01E6, 0x0000, 0xFB88, 0xF478, 0x1000, 0x0000} },
+ { 0x1000, 0xF149, 0xFEB7, 0x1004, 0x0868, 0x15B2,
+ 0x01E6, 0x201, 0xFB88, 0xF478, 0x1000, 0x1004} },
{ COLOR_SPACE_YCBCR709_BLACK_TYPE,
{ 0x0000, 0x0000, 0x0000, 0x1000, 0x0000, 0x0000,
0x0000, 0x0200, 0x0000, 0x0000, 0x0000, 0x1000} },
struct fixed31_32 avg_time_slots_per_mtp = dc_fixpt_from_int(0);
int i;
bool mst_mode = (link->type == dc_connection_mst_branch);
+ /* adjust for drm changes*/
+ bool update_drm_mst_state = true;
const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res);
const struct dc_link_settings empty_link_settings = {0};
DC_LOGGER_INIT(link->ctx->logger);
+
/* deallocate_mst_payload is called before disable link. When mode or
* disable/enable monitor, new stream is created which is not in link
* stream[] yet. For this, payload is not allocated yet, so de-alloc
&empty_link_settings,
avg_time_slots_per_mtp);
- if (mst_mode) {
+ if (mst_mode || update_drm_mst_state) {
/* when link is in mst mode, reply on mst manager to remove
* payload
*/
stream->ctx,
stream);
+ if (!update_drm_mst_state)
+ dm_helpers_dp_mst_send_payload_allocation(
+ stream->ctx,
+ stream,
+ false);
+ }
+
+ if (update_drm_mst_state)
dm_helpers_dp_mst_send_payload_allocation(
stream->ctx,
stream,
false);
- }
return DC_OK;
}
(int)hubp->curs_attr.width || pos_cpy.x
<= (int)hubp->curs_attr.width +
pipe_ctx->plane_state->src_rect.x) {
- pos_cpy.x = temp_x + viewport_width;
+ pos_cpy.x = 2 * viewport_width - temp_x;
}
}
} else {
},
// 6:1 downscaling ratio: 1000/6 = 166.666
+ // 4:1 downscaling ratio for ARGB888 to prevent underflow during P010 playback: 1000/4 = 250
.max_downscale_factor = {
- .argb8888 = 167,
+ .argb8888 = 250,
.nv12 = 167,
.fp16 = 167
},
pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE;
pool->base.pipe_count = pool->base.res_cap->num_timing_generator;
pool->base.mpcc_count = pool->base.res_cap->num_timing_generator;
- dc->caps.max_downscale_ratio = 600;
+ dc->caps.max_downscale_ratio = 400;
dc->caps.i2c_speed_in_khz = 100;
dc->caps.i2c_speed_in_khz_hdcp = 100;
dc->caps.max_cursor_size = 256;
.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
.calc_vupdate_position = dcn10_calc_vupdate_position,
.apply_idle_power_optimizations = dcn32_apply_idle_power_optimizations,
- .does_plane_fit_in_mall = dcn30_does_plane_fit_in_mall,
+ .does_plane_fit_in_mall = NULL,
.set_backlight_level = dcn21_set_backlight_level,
.set_abm_immediate_disable = dcn21_set_abm_immediate_disable,
.hardware_release = dcn30_hardware_release,
} else {
v->MIN_DST_Y_NEXT_START[k] = v->VTotal[k] - v->VFrontPorch[k] + v->VTotal[k] - v->VActive[k] - v->VStartup[k];
}
- v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / (double)v->HTotal[k] / v->PixelClock[k], 1.0) / 4.0;
+ v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / ((double)v->HTotal[k] / v->PixelClock[k]), 1.0) / 4.0;
if (((v->VUpdateOffsetPix[k] + v->VUpdateWidthPix[k] + v->VReadyOffsetPix[k]) / v->HTotal[k])
<= (isInterlaceTiming ?
dml_floor((v->VTotal[k] - v->VActive[k] - v->VFrontPorch[k] - v->VStartup[k]) / 2.0, 1.0) :
double SwathSizePerSurfaceC[DC__NUM_DPP__MAX];
bool NotEnoughDETSwathFillLatencyHiding = false;
- /* calculate sum of single swath size for all pipes in bytes*/
+ /* calculate sum of single swath size for all pipes in bytes */
for (k = 0; k < NumberOfActiveSurfaces; k++) {
- SwathSizePerSurfaceY[k] += SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k];
+ SwathSizePerSurfaceY[k] = SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k];
if (SwathHeightC[k] != 0)
- SwathSizePerSurfaceC[k] += SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k];
+ SwathSizePerSurfaceC[k] = SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k];
else
SwathSizePerSurfaceC[k] = 0;
if (dmub->hw_funcs.reset)
dmub->hw_funcs.reset(dmub);
+ /* reset the cache of the last wptr as well now that hw is reset */
+ dmub->inbox1_last_wptr = 0;
+
cw0.offset.quad_part = inst_fb->gpu_addr;
cw0.region.base = DMUB_CW0_BASE;
cw0.region.top = cw0.region.base + inst_fb->size - 1;
if (dmub->hw_funcs.reset)
dmub->hw_funcs.reset(dmub);
+ /* mailboxes have been reset in hw, so reset the sw state as well */
+ dmub->inbox1_last_wptr = 0;
+ dmub->inbox1_rb.wrpt = 0;
+ dmub->inbox1_rb.rptr = 0;
+ dmub->outbox0_rb.wrpt = 0;
+ dmub->outbox0_rb.rptr = 0;
+ dmub->outbox1_rb.wrpt = 0;
+ dmub->outbox1_rb.rptr = 0;
+
dmub->hw_init = false;
return DMUB_STATUS_OK;
case IP_VERSION(9, 4, 2):
case IP_VERSION(10, 3, 0):
case IP_VERSION(11, 0, 0):
+ case IP_VERSION(11, 0, 1):
+ case IP_VERSION(11, 0, 2):
*states = ATTR_STATE_SUPPORTED;
break;
default:
gc_ver == IP_VERSION(10, 3, 0) ||
gc_ver == IP_VERSION(10, 1, 2) ||
gc_ver == IP_VERSION(11, 0, 0) ||
- gc_ver == IP_VERSION(11, 0, 2)))
+ gc_ver == IP_VERSION(11, 0, 2) ||
+ gc_ver == IP_VERSION(11, 0, 3)))
*states = ATTR_STATE_UNSUPPORTED;
} else if (DEVICE_ATTR_IS(pp_dpm_dclk)) {
if (!(gc_ver == IP_VERSION(10, 3, 1) ||
gc_ver == IP_VERSION(10, 3, 0) ||
gc_ver == IP_VERSION(10, 1, 2) ||
gc_ver == IP_VERSION(11, 0, 0) ||
- gc_ver == IP_VERSION(11, 0, 2)))
+ gc_ver == IP_VERSION(11, 0, 2) ||
+ gc_ver == IP_VERSION(11, 0, 3)))
*states = ATTR_STATE_UNSUPPORTED;
} else if (DEVICE_ATTR_IS(pp_power_profile_mode)) {
if (amdgpu_dpm_get_power_profile_mode(adev, NULL) == -EOPNOTSUPP)
}
}
+ /*
+ * For SMU 13.0.4/11, PMFW will handle the features disablement properly
+ * for gpu reset case. Driver involvement is unnecessary.
+ */
+ if (amdgpu_in_reset(adev)) {
+ switch (adev->ip_versions[MP1_HWIP][0]) {
+ case IP_VERSION(13, 0, 4):
+ case IP_VERSION(13, 0, 11):
+ return 0;
+ default:
+ break;
+ }
+ }
+
/*
* For gpu reset, runpm and hibernation through BACO,
* BACO feature has to be kept enabled.
(1 << FEATURE_DS_FCLK_BIT) | \
(1 << FEATURE_DS_LCLK_BIT) | \
(1 << FEATURE_DS_DCFCLK_BIT) | \
- (1 << FEATURE_DS_UCLK_BIT))
+ (1 << FEATURE_DS_UCLK_BIT) | \
+ (1ULL << FEATURE_DS_VCN_BIT))
//For use with feature control messages
typedef enum {
TEMP_HOTSPOT_M,
TEMP_MEM,
TEMP_VR_GFX,
- TEMP_VR_SOC,
TEMP_VR_MEM0,
TEMP_VR_MEM1,
+ TEMP_VR_SOC,
TEMP_VR_U,
TEMP_LIQUID0,
TEMP_LIQUID1,
#define NUM_FEATURES 64
#define ALLOWED_FEATURE_CTRL_DEFAULT 0xFFFFFFFFFFFFFFFFULL
-#define ALLOWED_FEATURE_CTRL_SCPM (1 << FEATURE_DPM_GFXCLK_BIT) | \
- (1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \
- (1 << FEATURE_DPM_UCLK_BIT) | \
- (1 << FEATURE_DPM_FCLK_BIT) | \
- (1 << FEATURE_DPM_SOCCLK_BIT) | \
- (1 << FEATURE_DPM_MP0CLK_BIT) | \
- (1 << FEATURE_DPM_LINK_BIT) | \
- (1 << FEATURE_DPM_DCN_BIT) | \
- (1 << FEATURE_DS_GFXCLK_BIT) | \
- (1 << FEATURE_DS_SOCCLK_BIT) | \
- (1 << FEATURE_DS_FCLK_BIT) | \
- (1 << FEATURE_DS_LCLK_BIT) | \
- (1 << FEATURE_DS_DCFCLK_BIT) | \
- (1 << FEATURE_DS_UCLK_BIT)
+#define ALLOWED_FEATURE_CTRL_SCPM ((1 << FEATURE_DPM_GFXCLK_BIT) | \
+ (1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \
+ (1 << FEATURE_DPM_UCLK_BIT) | \
+ (1 << FEATURE_DPM_FCLK_BIT) | \
+ (1 << FEATURE_DPM_SOCCLK_BIT) | \
+ (1 << FEATURE_DPM_MP0CLK_BIT) | \
+ (1 << FEATURE_DPM_LINK_BIT) | \
+ (1 << FEATURE_DPM_DCN_BIT) | \
+ (1 << FEATURE_DS_GFXCLK_BIT) | \
+ (1 << FEATURE_DS_SOCCLK_BIT) | \
+ (1 << FEATURE_DS_FCLK_BIT) | \
+ (1 << FEATURE_DS_LCLK_BIT) | \
+ (1 << FEATURE_DS_DCFCLK_BIT) | \
+ (1 << FEATURE_DS_UCLK_BIT) | \
+ (1ULL << FEATURE_DS_VCN_BIT))
//For use with feature control messages
typedef enum {
#define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF
#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04
#define SMU13_DRIVER_IF_VERSION_ALDE 0x08
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x34
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x37
#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07
#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x35
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x37
#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D
#define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms
int ret = 0;
uint32_t apu_percent = 0;
uint32_t dgpu_percent = 0;
+ struct amdgpu_device *adev = smu->adev;
ret = smu_cmn_get_metrics_table(smu,
*value = metrics->AverageUvdActivity / 100;
break;
case METRICS_AVERAGE_SOCKETPOWER:
- *value = (metrics->CurrentSocketPower << 8) / 1000;
+ if (((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 1)) && (adev->pm.fw_version >= 0x40000f)) ||
+ ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 0)) && (adev->pm.fw_version >= 0x373200)))
+ *value = metrics->CurrentSocketPower << 8;
+ else
+ *value = (metrics->CurrentSocketPower << 8) / 1000;
break;
case METRICS_TEMPERATURE_EDGE:
*value = (metrics->GfxTemperature / 100) *
uint32_t speed)
{
struct amdgpu_device *adev = smu->adev;
- uint32_t tach_period, crystal_clock_freq;
+ uint32_t crystal_clock_freq = 2500;
+ uint32_t tach_period;
int ret;
if (!speed)
if (ret)
return ret;
- crystal_clock_freq = amdgpu_asic_get_xclk(adev);
tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
WREG32_SOC15(THM, 0, regCG_TACH_CTRL,
REG_SET_FIELD(RREG32_SOC15(THM, 0, regCG_TACH_CTRL),
!smu_baco->platform_support)
return false;
+ /* return true if ASIC is in BACO state already */
+ if (smu_v13_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER)
+ return true;
+
if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) &&
!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
return false;
MSG_MAP(SetBadMemoryPagesRetiredFlagsPerChannel,
PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel, 0),
MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0),
+ MSG_MAP(AllowIHHostInterrupt, PPSMC_MSG_AllowIHHostInterrupt, 0),
};
static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = {
FEA_MAP(SOC_PCC),
[SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
[SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
+ [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT},
};
static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = {
struct amdgpu_device *adev = smu->adev;
int ret = 0;
+ if (amdgpu_sriov_vf(smu->adev))
+ return 0;
+
ret = smu_v13_0_0_get_pptable_from_pmfw(smu,
&smu_table->power_play_table,
&smu_table->power_play_table_size);
table_context->power_play_table;
PPTable_t *pptable = smu->smu_table.driver_pptable;
+ if (amdgpu_sriov_vf(smu->adev))
+ return 0;
+
if (!range)
return -EINVAL;
MSG_MAP(DFCstateControl, PPSMC_MSG_SetExternalClientDfCstateAllow, 0),
MSG_MAP(ArmD3, PPSMC_MSG_ArmD3, 0),
MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0),
+ MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 0),
};
static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = {
FEA_MAP(SOC_PCC),
[SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
[SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
+ [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT},
};
static struct cmn2asic_mapping smu_v13_0_7_table_map[SMU_TABLE_COUNT] = {
struct ast_plane *ast_primary_plane = &ast->primary_plane;
struct drm_plane *primary_plane = &ast_primary_plane->base;
void __iomem *vaddr = ast->vram;
- u64 offset = ast->vram_base;
+ u64 offset = 0; /* with shmem, the primary plane is always at offset 0 */
unsigned long cursor_size = roundup(AST_HWC_SIZE + AST_HWC_SIGNATURE_SIZE, PAGE_SIZE);
unsigned long size = ast->vram_fb_available - cursor_size;
int ret;
return -ENOMEM;
vaddr = ast->vram + ast->vram_fb_available - size;
- offset = ast->vram_base + ast->vram_fb_available - size;
+ offset = ast->vram_fb_available - size;
ret = ast_plane_init(dev, ast_cursor_plane, vaddr, offset, size,
0x01, &ast_cursor_plane_funcs,
struct hdmi_codec_pdata pdata;
struct platform_device *platform;
+ memset(&pdata, 0, sizeof(pdata));
pdata.ops = &dw_hdmi_i2s_ops;
pdata.i2s = 1;
pdata.max_i2s_channels = 8;
mgr->payload_count--;
mgr->next_start_slot -= payload->time_slots;
+
+ if (payload->delete)
+ drm_dp_mst_put_port_malloc(payload->port);
}
EXPORT_SYMBOL(drm_dp_remove_payload);
drm_dbg_atomic(mgr->dev, "[MST PORT:%p] TU %d -> 0\n", port, payload->time_slots);
if (!payload->delete) {
- drm_dp_mst_put_port_malloc(port);
payload->pbn = 0;
payload->delete = true;
topology_state->payload_mask &= ~BIT(payload->vcpi - 1);
kmem_cache_free(slab_blocks, block);
}
+static void list_insert_sorted(struct drm_buddy *mm,
+ struct drm_buddy_block *block)
+{
+ struct drm_buddy_block *node;
+ struct list_head *head;
+
+ head = &mm->free_list[drm_buddy_block_order(block)];
+ if (list_empty(head)) {
+ list_add(&block->link, head);
+ return;
+ }
+
+ list_for_each_entry(node, head, link)
+ if (drm_buddy_block_offset(block) < drm_buddy_block_offset(node))
+ break;
+
+ __list_add(&block->link, node->link.prev, &node->link);
+}
+
static void mark_allocated(struct drm_buddy_block *block)
{
block->header &= ~DRM_BUDDY_HEADER_STATE;
block->header &= ~DRM_BUDDY_HEADER_STATE;
block->header |= DRM_BUDDY_FREE;
- list_add(&block->link,
- &mm->free_list[drm_buddy_block_order(block)]);
+ list_insert_sorted(mm, block);
}
static void mark_split(struct drm_buddy_block *block)
}
static struct drm_buddy_block *
-get_maxblock(struct list_head *head)
+get_maxblock(struct drm_buddy *mm, unsigned int order)
{
struct drm_buddy_block *max_block = NULL, *node;
+ unsigned int i;
- max_block = list_first_entry_or_null(head,
- struct drm_buddy_block,
- link);
- if (!max_block)
- return NULL;
+ for (i = order; i <= mm->max_order; ++i) {
+ if (!list_empty(&mm->free_list[i])) {
+ node = list_last_entry(&mm->free_list[i],
+ struct drm_buddy_block,
+ link);
+ if (!max_block) {
+ max_block = node;
+ continue;
+ }
- list_for_each_entry(node, head, link) {
- if (drm_buddy_block_offset(node) >
- drm_buddy_block_offset(max_block))
- max_block = node;
+ if (drm_buddy_block_offset(node) >
+ drm_buddy_block_offset(max_block)) {
+ max_block = node;
+ }
+ }
}
return max_block;
unsigned long flags)
{
struct drm_buddy_block *block = NULL;
- unsigned int i;
+ unsigned int tmp;
int err;
- for (i = order; i <= mm->max_order; ++i) {
- if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
- block = get_maxblock(&mm->free_list[i]);
- if (block)
- break;
- } else {
- block = list_first_entry_or_null(&mm->free_list[i],
- struct drm_buddy_block,
- link);
- if (block)
- break;
+ if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
+ block = get_maxblock(mm, order);
+ if (block)
+ /* Store the obtained block order */
+ tmp = drm_buddy_block_order(block);
+ } else {
+ for (tmp = order; tmp <= mm->max_order; ++tmp) {
+ if (!list_empty(&mm->free_list[tmp])) {
+ block = list_last_entry(&mm->free_list[tmp],
+ struct drm_buddy_block,
+ link);
+ if (block)
+ break;
+ }
}
}
BUG_ON(!drm_buddy_block_is_free(block));
- while (i != order) {
+ while (tmp != order) {
err = split_block(mm, block);
if (unlikely(err))
goto err_undo;
block = block->right;
- i--;
+ tmp--;
}
return block;
err_undo:
- if (i != order)
+ if (tmp != order)
__drm_buddy_free(mm, block);
return ERR_PTR(err);
}
static void drm_client_buffer_delete(struct drm_client_buffer *buffer)
{
- struct drm_device *dev = buffer->client->dev;
-
if (buffer->gem) {
drm_gem_vunmap_unlocked(buffer->gem, &buffer->map);
drm_gem_object_put(buffer->gem);
}
- if (buffer->handle)
- drm_mode_destroy_dumb(dev, buffer->handle, buffer->client->file);
-
kfree(buffer);
}
static struct drm_client_buffer *
-drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format)
+drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height,
+ u32 format, u32 *handle)
{
const struct drm_format_info *info = drm_format_info(format);
struct drm_mode_create_dumb dumb_args = { };
if (ret)
goto err_delete;
- buffer->handle = dumb_args.handle;
- buffer->pitch = dumb_args.pitch;
-
obj = drm_gem_object_lookup(client->file, dumb_args.handle);
if (!obj) {
ret = -ENOENT;
goto err_delete;
}
+ buffer->pitch = dumb_args.pitch;
buffer->gem = obj;
+ *handle = dumb_args.handle;
return buffer;
}
static int drm_client_buffer_addfb(struct drm_client_buffer *buffer,
- u32 width, u32 height, u32 format)
+ u32 width, u32 height, u32 format,
+ u32 handle)
{
struct drm_client_dev *client = buffer->client;
struct drm_mode_fb_cmd fb_req = { };
fb_req.depth = info->depth;
fb_req.width = width;
fb_req.height = height;
- fb_req.handle = buffer->handle;
+ fb_req.handle = handle;
fb_req.pitch = buffer->pitch;
ret = drm_mode_addfb(client->dev, &fb_req, client->file);
drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format)
{
struct drm_client_buffer *buffer;
+ u32 handle;
int ret;
- buffer = drm_client_buffer_create(client, width, height, format);
+ buffer = drm_client_buffer_create(client, width, height, format,
+ &handle);
if (IS_ERR(buffer))
return buffer;
- ret = drm_client_buffer_addfb(buffer, width, height, format);
+ ret = drm_client_buffer_addfb(buffer, width, height, format, handle);
+
+ /*
+ * The handle is only needed for creating the framebuffer, destroy it
+ * again to solve a circular dependency should anybody export the GEM
+ * object as DMA-buf. The framebuffer and our buffer structure are still
+ * holding references to the GEM object to prevent its destruction.
+ */
+ drm_mode_destroy_dumb(client->dev, handle, client->file);
+
if (ret) {
drm_client_buffer_delete(buffer);
return ERR_PTR(ret);
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/console.h>
+#include <linux/pci.h>
#include <linux/sysrq.h>
+#include <linux/vga_switcheroo.h>
#include <drm/drm_atomic.h>
#include <drm/drm_drv.h>
return ret;
strcpy(fb_helper->fb->comm, "[fbcon]");
+
+ /* Set the fb info for vgaswitcheroo clients. Does nothing otherwise. */
+ if (dev_is_pci(dev->dev))
+ vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), fb_helper->info);
+
return 0;
}
.fb_imageblit = drm_fbdev_fb_imageblit,
};
-static struct fb_deferred_io drm_fbdev_defio = {
- .delay = HZ / 20,
- .deferred_io = drm_fb_helper_deferred_io,
-};
-
/*
* This function uses the client API to create a framebuffer backed by a dumb buffer.
*/
return -ENOMEM;
fbi->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST;
- fbi->fbdefio = &drm_fbdev_defio;
- fb_deferred_io_init(fbi);
+ /* Set a default deferred I/O handler */
+ fb_helper->fbdefio.delay = HZ / 20;
+ fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
+
+ fbi->fbdefio = &fb_helper->fbdefio;
+ ret = fb_deferred_io_init(fbi);
+ if (ret)
+ return ret;
} else {
/* buffer is mapped for HW framebuffer */
ret = drm_client_buffer_vmap(fb_helper->buffer, &map);
DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGM"),
},
.driver_data = (void *)&lcd1200x1920_rightside_up,
+ }, { /* Lenovo Ideapad D330-10IGL (HD) */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGL"),
+ },
+ .driver_data = (void *)&lcd800x1280_rightside_up,
}, { /* Lenovo Yoga Book X90F / X91F / X91L */
.matches = {
/* Non exact match to match all versions */
}
EXPORT_SYMBOL(drm_vma_offset_remove);
-/**
- * drm_vma_node_allow - Add open-file to list of allowed users
- * @node: Node to modify
- * @tag: Tag of file to remove
- *
- * Add @tag to the list of allowed open-files for this node. If @tag is
- * already on this list, the ref-count is incremented.
- *
- * The list of allowed-users is preserved across drm_vma_offset_add() and
- * drm_vma_offset_remove() calls. You may even call it if the node is currently
- * not added to any offset-manager.
- *
- * You must remove all open-files the same number of times as you added them
- * before destroying the node. Otherwise, you will leak memory.
- *
- * This is locked against concurrent access internally.
- *
- * RETURNS:
- * 0 on success, negative error code on internal failure (out-of-mem)
- */
-int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag)
+static int vma_node_allow(struct drm_vma_offset_node *node,
+ struct drm_file *tag, bool ref_counted)
{
struct rb_node **iter;
struct rb_node *parent = NULL;
entry = rb_entry(*iter, struct drm_vma_offset_file, vm_rb);
if (tag == entry->vm_tag) {
- entry->vm_count++;
+ if (ref_counted)
+ entry->vm_count++;
goto unlock;
} else if (tag > entry->vm_tag) {
iter = &(*iter)->rb_right;
kfree(new);
return ret;
}
+
+/**
+ * drm_vma_node_allow - Add open-file to list of allowed users
+ * @node: Node to modify
+ * @tag: Tag of file to remove
+ *
+ * Add @tag to the list of allowed open-files for this node. If @tag is
+ * already on this list, the ref-count is incremented.
+ *
+ * The list of allowed-users is preserved across drm_vma_offset_add() and
+ * drm_vma_offset_remove() calls. You may even call it if the node is currently
+ * not added to any offset-manager.
+ *
+ * You must remove all open-files the same number of times as you added them
+ * before destroying the node. Otherwise, you will leak memory.
+ *
+ * This is locked against concurrent access internally.
+ *
+ * RETURNS:
+ * 0 on success, negative error code on internal failure (out-of-mem)
+ */
+int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag)
+{
+ return vma_node_allow(node, tag, true);
+}
EXPORT_SYMBOL(drm_vma_node_allow);
+/**
+ * drm_vma_node_allow_once - Add open-file to list of allowed users
+ * @node: Node to modify
+ * @tag: Tag of file to remove
+ *
+ * Add @tag to the list of allowed open-files for this node.
+ *
+ * The list of allowed-users is preserved across drm_vma_offset_add() and
+ * drm_vma_offset_remove() calls. You may even call it if the node is currently
+ * not added to any offset-manager.
+ *
+ * This is not ref-counted unlike drm_vma_node_allow() hence drm_vma_node_revoke()
+ * should only be called once after this.
+ *
+ * This is locked against concurrent access internally.
+ *
+ * RETURNS:
+ * 0 on success, negative error code on internal failure (out-of-mem)
+ */
+int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag)
+{
+ return vma_node_allow(node, tag, false);
+}
+EXPORT_SYMBOL(drm_vma_node_allow_once);
+
/**
* drm_vma_node_revoke - Remove open-file from list of allowed users
* @node: Node to modify
dvo_port);
}
+static enum port
+dsi_dvo_port_to_port(struct drm_i915_private *i915, u8 dvo_port)
+{
+ switch (dvo_port) {
+ case DVO_PORT_MIPIA:
+ return PORT_A;
+ case DVO_PORT_MIPIC:
+ if (DISPLAY_VER(i915) >= 11)
+ return PORT_B;
+ else
+ return PORT_C;
+ default:
+ return PORT_NONE;
+ }
+}
+
static int parse_bdb_230_dp_max_link_rate(const int vbt_max_link_rate)
{
switch (vbt_max_link_rate) {
dvo_port = child->dvo_port;
- if (dvo_port == DVO_PORT_MIPIA ||
- (dvo_port == DVO_PORT_MIPIB && DISPLAY_VER(i915) >= 11) ||
- (dvo_port == DVO_PORT_MIPIC && DISPLAY_VER(i915) < 11)) {
- if (port)
- *port = dvo_port - DVO_PORT_MIPIA;
- return true;
- } else if (dvo_port == DVO_PORT_MIPIB ||
- dvo_port == DVO_PORT_MIPIC ||
- dvo_port == DVO_PORT_MIPID) {
+ if (dsi_dvo_port_to_port(i915, dvo_port) == PORT_NONE) {
drm_dbg_kms(&i915->drm,
"VBT has unsupported DSI port %c\n",
port_name(dvo_port - DVO_PORT_MIPIA));
+ continue;
}
+
+ if (port)
+ *port = dsi_dvo_port_to_port(i915, dvo_port);
+ return true;
}
return false;
if (!(child->device_type & DEVICE_TYPE_MIPI_OUTPUT))
continue;
- if (child->dvo_port - DVO_PORT_MIPIA == encoder->port) {
+ if (dsi_dvo_port_to_port(i915, child->dvo_port) == encoder->port) {
if (!devdata->dsc)
return false;
{ .refclk = 24000, .cdclk = 192000, .divider = 2, .ratio = 16 },
{ .refclk = 24000, .cdclk = 312000, .divider = 2, .ratio = 26 },
{ .refclk = 24000, .cdclk = 552000, .divider = 2, .ratio = 46 },
- { .refclk = 24400, .cdclk = 648000, .divider = 2, .ratio = 54 },
+ { .refclk = 24000, .cdclk = 648000, .divider = 2, .ratio = 54 },
{ .refclk = 38400, .cdclk = 179200, .divider = 3, .ratio = 14 },
{ .refclk = 38400, .cdclk = 192000, .divider = 2, .ratio = 10 },
#include "i915_drv.h"
#include "i915_reg.h"
+#include "intel_de.h"
#include "intel_display_types.h"
#include "intel_dsi.h"
#include "intel_dsi_vbt.h"
+#include "intel_gmbus_regs.h"
#include "vlv_dsi.h"
#include "vlv_dsi_regs.h"
#include "vlv_sideband.h"
drm_dbg_kms(&dev_priv->drm, "Skipping ICL GPIO element execution\n");
}
+enum {
+ MIPI_RESET_1 = 0,
+ MIPI_AVDD_EN_1,
+ MIPI_BKLT_EN_1,
+ MIPI_AVEE_EN_1,
+ MIPI_VIO_EN_1,
+ MIPI_RESET_2,
+ MIPI_AVDD_EN_2,
+ MIPI_BKLT_EN_2,
+ MIPI_AVEE_EN_2,
+ MIPI_VIO_EN_2,
+};
+
+static void icl_native_gpio_set_value(struct drm_i915_private *dev_priv,
+ int gpio, bool value)
+{
+ int index;
+
+ if (drm_WARN_ON(&dev_priv->drm, DISPLAY_VER(dev_priv) == 11 && gpio >= MIPI_RESET_2))
+ return;
+
+ switch (gpio) {
+ case MIPI_RESET_1:
+ case MIPI_RESET_2:
+ index = gpio == MIPI_RESET_1 ? HPD_PORT_A : HPD_PORT_B;
+
+ /*
+ * Disable HPD to set the pin to output, and set output
+ * value. The HPD pin should not be enabled for DSI anyway,
+ * assuming the board design and VBT are sane, and the pin isn't
+ * used by a non-DSI encoder.
+ *
+ * The locking protects against concurrent SHOTPLUG_CTL_DDI
+ * modifications in irq setup and handling.
+ */
+ spin_lock_irq(&dev_priv->irq_lock);
+ intel_de_rmw(dev_priv, SHOTPLUG_CTL_DDI,
+ SHOTPLUG_CTL_DDI_HPD_ENABLE(index) |
+ SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index),
+ value ? SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index) : 0);
+ spin_unlock_irq(&dev_priv->irq_lock);
+ break;
+ case MIPI_AVDD_EN_1:
+ case MIPI_AVDD_EN_2:
+ index = gpio == MIPI_AVDD_EN_1 ? 0 : 1;
+
+ intel_de_rmw(dev_priv, PP_CONTROL(index), PANEL_POWER_ON,
+ value ? PANEL_POWER_ON : 0);
+ break;
+ case MIPI_BKLT_EN_1:
+ case MIPI_BKLT_EN_2:
+ index = gpio == MIPI_BKLT_EN_1 ? 0 : 1;
+
+ intel_de_rmw(dev_priv, PP_CONTROL(index), EDP_BLC_ENABLE,
+ value ? EDP_BLC_ENABLE : 0);
+ break;
+ case MIPI_AVEE_EN_1:
+ case MIPI_AVEE_EN_2:
+ index = gpio == MIPI_AVEE_EN_1 ? 1 : 2;
+
+ intel_de_rmw(dev_priv, GPIO(dev_priv, index),
+ GPIO_CLOCK_VAL_OUT,
+ GPIO_CLOCK_DIR_MASK | GPIO_CLOCK_DIR_OUT |
+ GPIO_CLOCK_VAL_MASK | (value ? GPIO_CLOCK_VAL_OUT : 0));
+ break;
+ case MIPI_VIO_EN_1:
+ case MIPI_VIO_EN_2:
+ index = gpio == MIPI_VIO_EN_1 ? 1 : 2;
+
+ intel_de_rmw(dev_priv, GPIO(dev_priv, index),
+ GPIO_DATA_VAL_OUT,
+ GPIO_DATA_DIR_MASK | GPIO_DATA_DIR_OUT |
+ GPIO_DATA_VAL_MASK | (value ? GPIO_DATA_VAL_OUT : 0));
+ break;
+ default:
+ MISSING_CASE(gpio);
+ }
+}
+
static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
{
struct drm_device *dev = intel_dsi->base.base.dev;
struct intel_connector *connector = intel_dsi->attached_connector;
u8 gpio_source, gpio_index = 0, gpio_number;
bool value;
-
- drm_dbg_kms(&dev_priv->drm, "\n");
+ bool native = DISPLAY_VER(dev_priv) >= 11;
if (connector->panel.vbt.dsi.seq_version >= 3)
gpio_index = *data++;
else
gpio_source = 0;
+ if (connector->panel.vbt.dsi.seq_version >= 4 && *data & BIT(1))
+ native = false;
+
/* pull up/down */
value = *data++ & 1;
- if (DISPLAY_VER(dev_priv) >= 11)
+ drm_dbg_kms(&dev_priv->drm, "GPIO index %u, number %u, source %u, native %s, set to %s\n",
+ gpio_index, gpio_number, gpio_source, str_yes_no(native), str_on_off(value));
+
+ if (native)
+ icl_native_gpio_set_value(dev_priv, gpio_number, value);
+ else if (DISPLAY_VER(dev_priv) >= 11)
icl_exec_gpio(connector, gpio_source, gpio_index, value);
else if (IS_VALLEYVIEW(dev_priv))
vlv_exec_gpio(connector, gpio_source, gpio_number, value);
return ret;
}
+static int intelfb_dirty(struct drm_fb_helper *helper, struct drm_clip_rect *clip)
+{
+ if (!(clip->x1 < clip->x2 && clip->y1 < clip->y2))
+ return 0;
+
+ if (helper->fb->funcs->dirty)
+ return helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1);
+
+ return 0;
+}
+
static const struct drm_fb_helper_funcs intel_fb_helper_funcs = {
.fb_probe = intelfb_create,
+ .fb_dirty = intelfb_dirty,
};
static void intel_fbdev_destroy(struct intel_fbdev *ifbdev)
u32 offset;
int ret;
- if (w > max_width || w < min_width || h > max_height) {
+ if (w > max_width || w < min_width || h > max_height || h < 1) {
drm_dbg_kms(&dev_priv->drm,
"requested Y/RGB source size %dx%d outside limits (min: %dx1 max: %dx%d)\n",
w, h, min_width, max_width, max_height);
skl_check_wm_level(&wm->wm[level], ddb);
if (icl_need_wm1_wa(i915, plane_id) &&
- level == 1 && wm->wm[0].enable) {
+ level == 1 && !wm->wm[level].enable &&
+ wm->wm[0].enable) {
wm->wm[level].blocks = wm->wm[0].blocks;
wm->wm[level].lines = wm->wm[0].lines;
wm->wm[level].ignore_lines = wm->wm[0].ignore_lines;
init_contexts(&i915->gem.contexts);
}
+/*
+ * Note that this implicitly consumes the ctx reference, by placing
+ * the ctx in the context_xa.
+ */
static void gem_context_register(struct i915_gem_context *ctx,
struct drm_i915_file_private *fpriv,
u32 id)
snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
current->comm, pid_nr(ctx->pid));
- /* And finally expose ourselves to userspace via the idr */
- old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
- WARN_ON(old);
-
spin_lock(&ctx->client->ctx_lock);
list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list);
spin_unlock(&ctx->client->ctx_lock);
spin_lock(&i915->gem.contexts.lock);
list_add_tail(&ctx->link, &i915->gem.contexts.list);
spin_unlock(&i915->gem.contexts.lock);
+
+ /* And finally expose ourselves to userspace via the idr */
+ old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
+ WARN_ON(old);
}
int i915_gem_context_open(struct drm_i915_private *i915,
vm = ctx->vm;
GEM_BUG_ON(!vm);
+ /*
+ * Get a reference for the allocated handle. Once the handle is
+ * visible in the vm_xa table, userspace could try to close it
+ * from under our feet, so we need to hold the extra reference
+ * first.
+ */
+ i915_vm_get(vm);
+
err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL);
- if (err)
+ if (err) {
+ i915_vm_put(vm);
return err;
-
- i915_vm_get(vm);
+ }
GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
args->value = id;
if (IS_ERR(ctx))
return ctx;
+ /*
+ * One for the xarray and one for the caller. We need to grab
+ * the reference *prior* to making the ctx visble to userspace
+ * in gem_context_register(), as at any point after that
+ * userspace can try to race us with another thread destroying
+ * the context under our feet.
+ */
+ i915_gem_context_get(ctx);
+
gem_context_register(ctx, file_priv, id);
old = xa_erase(&file_priv->proto_context_xa, id);
GEM_BUG_ON(old != pc);
proto_context_close(file_priv->dev_priv, pc);
- /* One for the xarray and one for the caller */
- return i915_gem_context_get(ctx);
+ return ctx;
}
struct i915_gem_context *
bool unpinned;
/*
- * Attempt to pin all of the buffers into the GTT.
- * This is done in 2 phases:
+ * We have one more buffers that we couldn't bind, which could be due to
+ * various reasons. To resolve this we have 4 passes, with every next
+ * level turning the screws tighter:
*
- * 1. Unbind all objects that do not match the GTT constraints for
- * the execbuffer (fenceable, mappable, alignment etc).
- * 2. Bind new objects.
+ * 0. Unbind all objects that do not match the GTT constraints for the
+ * execbuffer (fenceable, mappable, alignment etc). Bind all new
+ * objects. This avoids unnecessary unbinding of later objects in order
+ * to make room for the earlier objects *unless* we need to defragment.
*
- * This avoid unnecessary unbinding of later objects in order to make
- * room for the earlier objects *unless* we need to defragment.
+ * 1. Reorder the buffers, where objects with the most restrictive
+ * placement requirements go first (ignoring fixed location buffers for
+ * now). For example, objects needing the mappable aperture (the first
+ * 256M of GTT), should go first vs objects that can be placed just
+ * about anywhere. Repeat the previous pass.
*
- * Defragmenting is skipped if all objects are pinned at a fixed location.
+ * 2. Consider buffers that are pinned at a fixed location. Also try to
+ * evict the entire VM this time, leaving only objects that we were
+ * unable to lock. Try again to bind the buffers. (still using the new
+ * buffer order).
+ *
+ * 3. We likely have object lock contention for one or more stubborn
+ * objects in the VM, for which we need to evict to make forward
+ * progress (perhaps we are fighting the shrinker?). When evicting the
+ * VM this time around, anything that we can't lock we now track using
+ * the busy_bo, using the full lock (after dropping the vm->mutex to
+ * prevent deadlocks), instead of trylock. We then continue to evict the
+ * VM, this time with the stubborn object locked, which we can now
+ * hopefully unbind (if still bound in the VM). Repeat until the VM is
+ * evicted. Finally we should be able bind everything.
*/
- for (pass = 0; pass <= 2; pass++) {
+ for (pass = 0; pass <= 3; pass++) {
int pin_flags = PIN_USER | PIN_VALIDATE;
if (pass == 0)
pin_flags |= PIN_NONBLOCK;
if (pass >= 1)
- unpinned = eb_unbind(eb, pass == 2);
+ unpinned = eb_unbind(eb, pass >= 2);
if (pass == 2) {
err = mutex_lock_interruptible(&eb->context->vm->mutex);
if (!err) {
- err = i915_gem_evict_vm(eb->context->vm, &eb->ww);
+ err = i915_gem_evict_vm(eb->context->vm, &eb->ww, NULL);
mutex_unlock(&eb->context->vm->mutex);
}
if (err)
return err;
}
+ if (pass == 3) {
+retry:
+ err = mutex_lock_interruptible(&eb->context->vm->mutex);
+ if (!err) {
+ struct drm_i915_gem_object *busy_bo = NULL;
+
+ err = i915_gem_evict_vm(eb->context->vm, &eb->ww, &busy_bo);
+ mutex_unlock(&eb->context->vm->mutex);
+ if (err && busy_bo) {
+ err = i915_gem_object_lock(busy_bo, &eb->ww);
+ i915_gem_object_put(busy_bo);
+ if (!err)
+ goto retry;
+ }
+ }
+ if (err)
+ return err;
+ }
+
list_for_each_entry(ev, &eb->unbound, bind_link) {
err = eb_reserve_vma(eb, ev, pin_flags);
if (err)
eb.composite_fence :
&eb.requests[0]->fence);
+ if (unlikely(eb.gem_context->syncobj)) {
+ drm_syncobj_replace_fence(eb.gem_context->syncobj,
+ eb.composite_fence ?
+ eb.composite_fence :
+ &eb.requests[0]->fence);
+ }
+
if (out_fence) {
if (err == 0) {
fd_install(out_fence_fd, out_fence->file);
}
}
- if (unlikely(eb.gem_context->syncobj)) {
- drm_syncobj_replace_fence(eb.gem_context->syncobj,
- eb.composite_fence ?
- eb.composite_fence :
- &eb.requests[0]->fence);
- }
-
if (!out_fence && eb.composite_fence)
dma_fence_put(eb.composite_fence);
if (vma == ERR_PTR(-ENOSPC)) {
ret = mutex_lock_interruptible(&ggtt->vm.mutex);
if (!ret) {
- ret = i915_gem_evict_vm(&ggtt->vm, &ww);
+ ret = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
mutex_unlock(&ggtt->vm.mutex);
}
if (ret)
GEM_BUG_ON(lookup_mmo(obj, mmap_type) != mmo);
out:
if (file)
- drm_vma_node_allow(&mmo->vma_node, file);
+ drm_vma_node_allow_once(&mmo->vma_node, file);
return mmo;
err:
mapping_set_gfp_mask(mapping, mask);
GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM));
- i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, 0);
+ i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class, flags);
obj->mem_flags |= I915_BO_FLAG_STRUCT_PAGE;
obj->write_domain = I915_GEM_DOMAIN_CPU;
obj->read_domains = I915_GEM_DOMAIN_CPU;
spin_unlock(&obj->vma.lock);
obj->tiling_and_stride = tiling | stride;
- i915_gem_object_unlock(obj);
-
- /* Force the fence to be reacquired for GTT access */
- i915_gem_object_release_mmap_gtt(obj);
/* Try to preallocate memory required to save swizzling on put-pages */
if (i915_gem_object_needs_bit17_swizzle(obj)) {
obj->bit_17 = NULL;
}
+ i915_gem_object_unlock(obj);
+
+ /* Force the fence to be reacquired for GTT access */
+ i915_gem_object_release_mmap_gtt(obj);
+
return 0;
}
I915_SHRINK_ACTIVE);
i915_vma_unpin(vma);
if (err)
- goto out_put;
+ goto out_wf;
/*
* Now that the pages are *unpinned* shrinking should invoke
pr_err("unexpected pages mismatch, should_swap=%s\n",
str_yes_no(should_swap));
err = -EINVAL;
- goto out_put;
+ goto out_wf;
}
if (should_swap == (obj->mm.page_sizes.sg || obj->mm.page_sizes.phys)) {
pr_err("unexpected residual page-size bits, should_swap=%s\n",
str_yes_no(should_swap));
err = -EINVAL;
- goto out_put;
+ goto out_wf;
}
err = i915_vma_pin(vma, 0, 0, flags);
if (err)
- goto out_put;
+ goto out_wf;
while (n--) {
err = cpu_check(obj, n, 0xdeadbeaf);
return rq;
}
-struct i915_request *intel_context_find_active_request(struct intel_context *ce)
+struct i915_request *intel_context_get_active_request(struct intel_context *ce)
{
struct intel_context *parent = intel_context_to_parent(ce);
struct i915_request *rq, *active = NULL;
active = rq;
}
+ if (active)
+ active = i915_request_get_rcu(active);
spin_unlock_irqrestore(&parent->guc_state.lock, flags);
return active;
struct i915_request *intel_context_create_request(struct intel_context *ce);
-struct i915_request *
-intel_context_find_active_request(struct intel_context *ce);
+struct i915_request *intel_context_get_active_request(struct intel_context *ce);
static inline bool intel_context_is_barrier(const struct intel_context *ce)
{
ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine,
ktime_t *now);
-struct i915_request *
-intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine);
+void intel_engine_get_hung_entity(struct intel_engine_cs *engine,
+ struct intel_context **ce, struct i915_request **rq);
u32 intel_engine_context_size(struct intel_gt *gt, u8 class);
struct intel_context *
}
}
-static unsigned long list_count(struct list_head *list)
-{
- struct list_head *pos;
- unsigned long count = 0;
-
- list_for_each(pos, list)
- count++;
-
- return count;
-}
-
static unsigned long read_ul(void *p, size_t x)
{
return *(unsigned long *)(p + x);
}
}
-static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m)
+static void engine_dump_active_requests(struct intel_engine_cs *engine,
+ struct drm_printer *m)
{
+ struct intel_context *hung_ce = NULL;
struct i915_request *hung_rq = NULL;
- struct intel_context *ce;
- bool guc;
/*
* No need for an engine->irq_seqno_barrier() before the seqno reads.
* But the intention here is just to report an instantaneous snapshot
* so that's fine.
*/
- lockdep_assert_held(&engine->sched_engine->lock);
+ intel_engine_get_hung_entity(engine, &hung_ce, &hung_rq);
drm_printf(m, "\tRequests:\n");
- guc = intel_uc_uses_guc_submission(&engine->gt->uc);
- if (guc) {
- ce = intel_engine_get_hung_context(engine);
- if (ce)
- hung_rq = intel_context_find_active_request(ce);
- } else {
- hung_rq = intel_engine_execlist_find_hung_request(engine);
- }
-
if (hung_rq)
engine_dump_request(hung_rq, m, "\t\thung");
+ else if (hung_ce)
+ drm_printf(m, "\t\tGot hung ce but no hung rq!\n");
- if (guc)
+ if (intel_uc_uses_guc_submission(&engine->gt->uc))
intel_guc_dump_active_requests(engine, hung_rq, m);
else
- intel_engine_dump_active_requests(&engine->sched_engine->requests,
- hung_rq, m);
+ intel_execlists_dump_active_requests(engine, hung_rq, m);
+
+ if (hung_rq)
+ i915_request_put(hung_rq);
}
void intel_engine_dump(struct intel_engine_cs *engine,
struct i915_gpu_error * const error = &engine->i915->gpu_error;
struct i915_request *rq;
intel_wakeref_t wakeref;
- unsigned long flags;
ktime_t dummy;
if (header) {
i915_reset_count(error));
print_properties(engine, m);
- spin_lock_irqsave(&engine->sched_engine->lock, flags);
engine_dump_active_requests(engine, m);
- drm_printf(m, "\tOn hold?: %lu\n",
- list_count(&engine->sched_engine->hold));
- spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
-
drm_printf(m, "\tMMIO base: 0x%08x\n", engine->mmio_base);
wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm);
if (wakeref) {
return siblings[0]->cops->create_virtual(siblings, count, flags);
}
-struct i915_request *
-intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
+static struct i915_request *engine_execlist_find_hung_request(struct intel_engine_cs *engine)
{
struct i915_request *request, *active = NULL;
return active;
}
+void intel_engine_get_hung_entity(struct intel_engine_cs *engine,
+ struct intel_context **ce, struct i915_request **rq)
+{
+ unsigned long flags;
+
+ *ce = intel_engine_get_hung_context(engine);
+ if (*ce) {
+ intel_engine_clear_hung_context(engine);
+
+ *rq = intel_context_get_active_request(*ce);
+ return;
+ }
+
+ /*
+ * Getting here with GuC enabled means it is a forced error capture
+ * with no actual hang. So, no need to attempt the execlist search.
+ */
+ if (intel_uc_uses_guc_submission(&engine->gt->uc))
+ return;
+
+ spin_lock_irqsave(&engine->sched_engine->lock, flags);
+ *rq = engine_execlist_find_hung_request(engine);
+ if (*rq)
+ *rq = i915_request_get_rcu(*rq);
+ spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
+}
+
void xehp_enable_ccs_engines(struct intel_engine_cs *engine)
{
/*
spin_unlock_irqrestore(&sched_engine->lock, flags);
}
+static unsigned long list_count(struct list_head *list)
+{
+ struct list_head *pos;
+ unsigned long count = 0;
+
+ list_for_each(pos, list)
+ count++;
+
+ return count;
+}
+
+void intel_execlists_dump_active_requests(struct intel_engine_cs *engine,
+ struct i915_request *hung_rq,
+ struct drm_printer *m)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&engine->sched_engine->lock, flags);
+
+ intel_engine_dump_active_requests(&engine->sched_engine->requests, hung_rq, m);
+
+ drm_printf(m, "\tOn hold?: %lu\n",
+ list_count(&engine->sched_engine->hold));
+
+ spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
+}
+
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftest_execlists.c"
#endif
int indent),
unsigned int max);
+void intel_execlists_dump_active_requests(struct intel_engine_cs *engine,
+ struct i915_request *hung_rq,
+ struct drm_printer *m);
+
bool
intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine);
continue;
if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+ u32 val = BIT(engine->instance);
+
+ if (engine->class == VIDEO_DECODE_CLASS ||
+ engine->class == VIDEO_ENHANCEMENT_CLASS ||
+ engine->class == COMPUTE_CLASS)
+ val = _MASKED_BIT_ENABLE(val);
intel_gt_mcr_multicast_write_fw(gt,
xehp_regs[engine->class],
- BIT(engine->instance));
+ val);
} else {
rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
if (!i915_mmio_reg_offset(rb.reg))
#define GEN9_WM_CHICKEN3 _MMIO(0x5588)
#define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9)
-#define CHICKEN_RASTER_1 _MMIO(0x6204)
+#define CHICKEN_RASTER_1 MCR_REG(0x6204)
#define DIS_SF_ROUND_NEAREST_EVEN REG_BIT(8)
-#define CHICKEN_RASTER_2 _MMIO(0x6208)
+#define CHICKEN_RASTER_2 MCR_REG(0x6208)
#define TBIMR_FAST_CLIP REG_BIT(5)
#define VFLSKPD MCR_REG(0x62a8)
#define RC_OP_FLUSH_ENABLE (1 << 0)
#define HIZ_RAW_STALL_OPT_DISABLE (1 << 2)
#define CACHE_MODE_1 _MMIO(0x7004) /* IVB+ */
-#define PIXEL_SUBSPAN_COLLECT_OPT_DISABLE (1 << 6)
-#define GEN8_4x4_STC_OPTIMIZATION_DISABLE (1 << 6)
-#define GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE (1 << 1)
+#define MSAA_OPTIMIZATION_REDUC_DISABLE REG_BIT(11)
+#define PIXEL_SUBSPAN_COLLECT_OPT_DISABLE REG_BIT(6)
+#define GEN8_4x4_STC_OPTIMIZATION_DISABLE REG_BIT(6)
+#define GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE REG_BIT(1)
#define GEN7_GT_MODE _MMIO(0x7008)
#define GEN9_IZ_HASHING_MASK(slice) (0x3 << ((slice) * 2))
#define GEN8_L3CNTLREG _MMIO(0x7034)
#define GEN8_ERRDETBCTRL (1 << 9)
+#define PSS_MODE2 _MMIO(0x703c)
+#define SCOREBOARD_STALL_FLUSH_CONTROL REG_BIT(5)
+
#define GEN7_SC_INSTDONE _MMIO(0x7100)
#define GEN12_SC_INSTDONE_EXTRA _MMIO(0x7104)
#define GEN12_SC_INSTDONE_EXTRA2 _MMIO(0x7108)
END
};
-static const u8 mtl_xcs_offsets[] = {
- NOP(1),
- LRI(13, POSTED),
- REG16(0x244),
- REG(0x034),
- REG(0x030),
- REG(0x038),
- REG(0x03c),
- REG(0x168),
- REG(0x140),
- REG(0x110),
- REG(0x1c0),
- REG(0x1c4),
- REG(0x1c8),
- REG(0x180),
- REG16(0x2b4),
- NOP(4),
-
- NOP(1),
- LRI(9, POSTED),
- REG16(0x3a8),
- REG16(0x28c),
- REG16(0x288),
- REG16(0x284),
- REG16(0x280),
- REG16(0x27c),
- REG16(0x278),
- REG16(0x274),
- REG16(0x270),
-
- END
-};
-
static const u8 gen8_rcs_offsets[] = {
NOP(1),
LRI(14, POSTED),
else
return gen8_rcs_offsets;
} else {
- if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70))
- return mtl_xcs_offsets;
- else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+ if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
return dg2_xcs_offsets;
else if (GRAPHICS_VER(engine->i915) >= 12)
return gen12_xcs_offsets;
static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
{
struct intel_uncore *uncore = gt->uncore;
+ int loops = 2;
int err;
/*
* for fifo space for the write or forcewake the chip for
* the read
*/
- intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
+ do {
+ intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
- /* Wait for the device to ack the reset requests */
- err = __intel_wait_for_register_fw(uncore,
- GEN6_GDRST, hw_domain_mask, 0,
- 500, 0,
- NULL);
+ /*
+ * Wait for the device to ack the reset requests.
+ *
+ * On some platforms, e.g. Jasperlake, we see that the
+ * engine register state is not cleared until shortly after
+ * GDRST reports completion, causing a failure as we try
+ * to immediately resume while the internal state is still
+ * in flux. If we immediately repeat the reset, the second
+ * reset appears to serialise with the first, and since
+ * it is a no-op, the registers should retain their reset
+ * value. However, there is still a concern that upon
+ * leaving the second reset, the internal engine state
+ * is still in flux and not ready for resuming.
+ */
+ err = __intel_wait_for_register_fw(uncore, GEN6_GDRST,
+ hw_domain_mask, 0,
+ 2000, 0,
+ NULL);
+ } while (err == 0 && --loops);
if (err)
GT_TRACE(gt,
"Wait for 0x%08x engines reset failed\n",
hw_domain_mask);
+ /*
+ * As we have observed that the engine state is still volatile
+ * after GDRST is acked, impose a small delay to let everything settle.
+ */
+ udelay(50);
+
return err;
}
static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine,
struct i915_wa_list *wal)
{
- wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
+ wa_mcr_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
wa_mcr_add(wal,
/* Wa_14014947963:dg2 */
if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) ||
- IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
+ IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000);
+ /* Wa_18018764978:dg2 */
+ if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_C0, STEP_FOREVER) ||
+ IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
+ wa_masked_en(wal, PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL);
+
/* Wa_15010599737:dg2 */
- wa_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
+ wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
+
+ /* Wa_18019271663:dg2 */
+ wa_masked_en(wal, CACHE_MODE_1, MSAA_OPTIMIZATION_REDUC_DISABLE);
}
static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine,
GAMT_CHKN_BIT_REG,
GAMT_CHKN_DISABLE_L3_COH_PIPE);
+ /*
+ * Wa_1408615072:icl,ehl (vsunit)
+ * Wa_1407596294:icl,ehl (hsunit)
+ */
+ wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE,
+ VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
+
/* Wa_1407352427:icl,ehl */
wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
PSDUNIT_CLKGATE_DIS);
wa_masked_en(wal, GEN9_CSFE_CHICKEN1_RCS,
GEN11_ENABLE_32_PLANE_MODE);
- /*
- * Wa_1408615072:icl,ehl (vsunit)
- * Wa_1407596294:icl,ehl (hsunit)
- */
- wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE,
- VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
-
/*
* Wa_1408767742:icl[a2..forever],ehl[all]
* Wa_1605460711:icl[a0..c0]
goto next_context;
guilty = false;
- rq = intel_context_find_active_request(ce);
+ rq = intel_context_get_active_request(ce);
if (!rq) {
head = ce->ring->tail;
goto out_replay;
head = intel_ring_wrap(ce->ring, rq->head);
__i915_request_reset(rq, guilty);
+ i915_request_put(rq);
out_replay:
guc_reset_state(ce, head, guilty);
next_context:
xa_lock_irqsave(&guc->context_lookup, flags);
xa_for_each(&guc->context_lookup, index, ce) {
+ bool found;
+
if (!kref_get_unless_zero(&ce->ref))
continue;
goto next;
}
+ found = false;
+ spin_lock(&ce->guc_state.lock);
list_for_each_entry(rq, &ce->guc_state.requests, sched.link) {
if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE)
continue;
+ found = true;
+ break;
+ }
+ spin_unlock(&ce->guc_state.lock);
+
+ if (found) {
intel_engine_set_hung_context(engine, ce);
/* Can only cope with one hang at a time... */
xa_lock(&guc->context_lookup);
goto done;
}
+
next:
intel_context_put(ce);
xa_lock(&guc->context_lookup);
return 0;
}
+static int try_firmware_load(struct intel_uc_fw *uc_fw, const struct firmware **fw)
+{
+ struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
+ struct device *dev = gt->i915->drm.dev;
+ int err;
+
+ err = firmware_request_nowarn(fw, uc_fw->file_selected.path, dev);
+
+ if (err)
+ return err;
+
+ if ((*fw)->size > INTEL_UC_RSVD_GGTT_PER_FW) {
+ drm_err(>->i915->drm,
+ "%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n",
+ intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path,
+ (*fw)->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K);
+
+ /* try to find another blob to load */
+ release_firmware(*fw);
+ *fw = NULL;
+ return -ENOENT;
+ }
+
+ return 0;
+}
+
/**
* intel_uc_fw_fetch - fetch uC firmware
* @uc_fw: uC firmware
struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
struct drm_i915_private *i915 = gt->i915;
struct intel_uc_fw_file file_ideal;
- struct device *dev = i915->drm.dev;
struct drm_i915_gem_object *obj;
const struct firmware *fw = NULL;
bool old_ver = false;
__force_fw_fetch_failures(uc_fw, -EINVAL);
__force_fw_fetch_failures(uc_fw, -ESTALE);
- err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev);
+ err = try_firmware_load(uc_fw, &fw);
memcpy(&file_ideal, &uc_fw->file_wanted, sizeof(file_ideal));
- if (!err && fw->size > INTEL_UC_RSVD_GGTT_PER_FW) {
- drm_err(&i915->drm,
- "%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n",
- intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path,
- fw->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K);
-
- /* try to find another blob to load */
- release_firmware(fw);
- err = -ENOENT;
- }
-
/* Any error is terminal if overriding. Don't bother searching for older versions */
if (err && intel_uc_fw_is_overridden(uc_fw))
goto fail;
break;
}
- err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev);
+ err = try_firmware_load(uc_fw, &fw);
}
if (err)
vgpu_scan_nonprivbb_get, vgpu_scan_nonprivbb_set,
"0x%llx\n");
+static int vgpu_status_get(void *data, u64 *val)
+{
+ struct intel_vgpu *vgpu = (struct intel_vgpu *)data;
+
+ *val = 0;
+
+ if (test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+ *val |= (1 << INTEL_VGPU_STATUS_ATTACHED);
+ if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
+ *val |= (1 << INTEL_VGPU_STATUS_ACTIVE);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vgpu_status_fops, vgpu_status_get, NULL, "0x%llx\n");
+
/**
* intel_gvt_debugfs_add_vgpu - register debugfs entries for a vGPU
* @vgpu: a vGPU
snprintf(name, 16, "vgpu%d", vgpu->id);
vgpu->debugfs = debugfs_create_dir(name, vgpu->gvt->debugfs_root);
- debugfs_create_bool("active", 0444, vgpu->debugfs, &vgpu->active);
debugfs_create_file("mmio_diff", 0444, vgpu->debugfs, vgpu,
&vgpu_mmio_diff_fops);
debugfs_create_file("scan_nonprivbb", 0644, vgpu->debugfs, vgpu,
&vgpu_scan_nonprivbb_fops);
+ debugfs_create_file("status", 0644, vgpu->debugfs, vgpu,
+ &vgpu_status_fops);
}
/**
*/
void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu)
{
- debugfs_remove_recursive(vgpu->debugfs);
- vgpu->debugfs = NULL;
+ struct intel_gvt *gvt = vgpu->gvt;
+ struct drm_minor *minor = gvt->gt->i915->drm.primary;
+
+ if (minor->debugfs_root && gvt->debugfs_root) {
+ debugfs_remove_recursive(vgpu->debugfs);
+ vgpu->debugfs = NULL;
+ }
}
/**
*/
void intel_gvt_debugfs_clean(struct intel_gvt *gvt)
{
- debugfs_remove_recursive(gvt->debugfs_root);
- gvt->debugfs_root = NULL;
+ struct drm_minor *minor = gvt->gt->i915->drm.primary;
+
+ if (minor->debugfs_root) {
+ debugfs_remove_recursive(gvt->debugfs_root);
+ gvt->debugfs_root = NULL;
+ }
}
struct list_head *pos;
struct intel_vgpu_dmabuf_obj *dmabuf_obj;
- if (vgpu && vgpu->active && !list_empty(&vgpu->dmabuf_obj_list_head)) {
+ if (vgpu && test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status) &&
+ !list_empty(&vgpu->dmabuf_obj_list_head)) {
list_for_each(pos, &vgpu->dmabuf_obj_list_head) {
dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list);
if (dmabuf_obj == obj) {
int idx;
bool ret;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return false;
idx = srcu_read_lock(&kvm->srcu);
if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
return 0;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -EINVAL;
pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
if (is_error_noslot_pfn(pfn))
for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
ret = intel_gvt_dma_map_guest_page(vgpu, start_gfn + sub_index,
PAGE_SIZE, &dma_addr);
- if (ret) {
- ppgtt_invalidate_spt(spt);
- return ret;
- }
+ if (ret)
+ goto err;
sub_se.val64 = se->val64;
/* Copy the PAT field from PDE. */
ops->set_pfn(se, sub_spt->shadow_page.mfn);
ppgtt_set_shadow_entry(spt, se, index);
return 0;
+err:
+ /* Cancel the existing addess mappings of DMA addr. */
+ for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) {
+ gvt_vdbg_mm("invalidate 4K entry\n");
+ ppgtt_invalidate_pte(sub_spt, &sub_se);
+ }
+ /* Release the new allocated spt. */
+ trace_spt_change(sub_spt->vgpu->id, "release", sub_spt,
+ sub_spt->guest_page.gfn, sub_spt->shadow_page.type);
+ ppgtt_free_spt(sub_spt);
+ return ret;
}
static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
#define KVMGT_DEBUGFS_FILENAME "kvmgt_nr_cache_entries"
+enum {
+ INTEL_VGPU_STATUS_ATTACHED = 0,
+ INTEL_VGPU_STATUS_ACTIVE,
+ INTEL_VGPU_STATUS_NR_BITS,
+};
+
struct intel_vgpu {
struct vfio_device vfio_device;
struct intel_gvt *gvt;
struct mutex vgpu_lock;
int id;
- bool active;
- bool attached;
+ DECLARE_BITMAP(status, INTEL_VGPU_STATUS_NR_BITS);
bool pv_notified;
bool failsafe;
unsigned int resetting_eng;
#define for_each_active_vgpu(gvt, vgpu, id) \
idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) \
- for_each_if(vgpu->active)
+ for_each_if(test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
static inline void intel_vgpu_write_pci_bar(struct intel_vgpu *vgpu,
u32 offset, u32 val, bool low)
static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa,
void *buf, unsigned long len)
{
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, false);
}
static inline int intel_gvt_write_gpa(struct intel_vgpu *vgpu,
unsigned long gpa, void *buf, unsigned long len)
{
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, true);
}
* enabled by guest. so if msi_trigger is null, success is still
* returned and don't inject interrupt into guest.
*/
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1)
return -EFAULT;
mutex_lock(&vgpu->gvt->lock);
for_each_active_vgpu(vgpu->gvt, itr, id) {
- if (!itr->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, itr->status))
continue;
if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) {
{
struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
- if (vgpu->attached)
- return -EEXIST;
-
if (!vgpu->vfio_device.kvm ||
vgpu->vfio_device.kvm->mm != current->mm) {
gvt_vgpu_err("KVM is required to use Intel vGPU\n");
if (__kvmgt_vgpu_exist(vgpu))
return -EEXIST;
- vgpu->attached = true;
-
vgpu->track_node.track_write = kvmgt_page_track_write;
vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
kvm_get_kvm(vgpu->vfio_device.kvm);
kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
&vgpu->track_node);
+ set_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
+
debugfs_create_ulong(KVMGT_DEBUGFS_FILENAME, 0444, vgpu->debugfs,
&vgpu->nr_cache_entries);
{
struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
- if (!vgpu->attached)
- return;
-
intel_gvt_release_vgpu(vgpu);
+ clear_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
+
debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs));
kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm,
vgpu->dma_addr_cache = RB_ROOT;
intel_vgpu_release_msi_eventfd_ctx(vgpu);
-
- vgpu->attached = false;
}
static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
{
struct intel_vgpu *vgpu = dev_get_drvdata(&mdev->dev);
- if (WARN_ON_ONCE(vgpu->attached))
- return;
-
vfio_unregister_group_dev(&vgpu->vfio_device);
vfio_put_device(&vgpu->vfio_device);
}
struct kvm_memory_slot *slot;
int idx;
- if (!info->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
return -ESRCH;
idx = srcu_read_lock(&kvm->srcu);
struct kvm_memory_slot *slot;
int idx;
- if (!info->attached)
- return 0;
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
+ return -ESRCH;
idx = srcu_read_lock(&kvm->srcu);
slot = gfn_to_memslot(kvm, gfn);
struct gvt_dma *entry;
int ret;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -EINVAL;
mutex_lock(&vgpu->cache_lock);
struct gvt_dma *entry;
int ret = 0;
- if (!vgpu->attached)
- return -ENODEV;
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+ return -EINVAL;
mutex_lock(&vgpu->cache_lock);
entry = __gvt_cache_find_dma_addr(vgpu, dma_addr);
{
struct gvt_dma *entry;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return;
mutex_lock(&vgpu->cache_lock);
idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) {
if (test_and_clear_bit(INTEL_GVT_REQUEST_EMULATE_VBLANK + id,
(void *)&gvt->service_request)) {
- if (vgpu->active)
+ if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
intel_vgpu_emulate_vblank(vgpu);
}
}
if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT ||
!workload->shadow_mm->ppgtt_mm.shadowed) {
+ intel_vgpu_unpin_mm(workload->shadow_mm);
gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
return -EINVAL;
}
goto out;
}
- if (!scheduler->current_vgpu->active ||
+ if (!test_bit(INTEL_VGPU_STATUS_ACTIVE,
+ scheduler->current_vgpu->status) ||
list_empty(workload_q_head(scheduler->current_vgpu, engine)))
goto out;
*/
void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
{
- mutex_lock(&vgpu->vgpu_lock);
- vgpu->active = true;
- mutex_unlock(&vgpu->vgpu_lock);
+ set_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
}
/**
{
mutex_lock(&vgpu->vgpu_lock);
- vgpu->active = false;
+ clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
if (atomic_read(&vgpu->submission.running_workload_num)) {
mutex_unlock(&vgpu->vgpu_lock);
struct intel_gvt *gvt = vgpu->gvt;
struct drm_i915_private *i915 = gvt->gt->i915;
- drm_WARN(&i915->drm, vgpu->active, "vGPU is still active!\n");
+ drm_WARN(&i915->drm, test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status),
+ "vGPU is still active!\n");
/*
* remove idr first so later clean can judge if need to stop
if (ret)
goto out_free_vgpu;
- vgpu->active = false;
-
+ clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
return vgpu;
out_free_vgpu:
*/
static void i915_driver_lastclose(struct drm_device *dev)
{
- struct drm_i915_private *i915 = to_i915(dev);
-
intel_fbdev_restore_mode(dev);
- if (HAS_DISPLAY(i915))
- vga_switcheroo_process_delayed_switch();
+ vga_switcheroo_process_delayed_switch();
}
static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
* @vm: Address space to cleanse
* @ww: An optional struct i915_gem_ww_ctx. If not NULL, i915_gem_evict_vm
* will be able to evict vma's locked by the ww as well.
+ * @busy_bo: Optional pointer to struct drm_i915_gem_object. If not NULL, then
+ * in the event i915_gem_evict_vm() is unable to trylock an object for eviction,
+ * then @busy_bo will point to it. -EBUSY is also returned. The caller must drop
+ * the vm->mutex, before trying again to acquire the contended lock. The caller
+ * also owns a reference to the object.
*
* This function evicts all vmas from a vm.
*
* To clarify: This is for freeing up virtual address space, not for freeing
* memory in e.g. the shrinker.
*/
-int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww)
+int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww,
+ struct drm_i915_gem_object **busy_bo)
{
int ret = 0;
* the resv is shared among multiple objects, we still
* need the object ref.
*/
- if (dying_vma(vma) ||
+ if (!i915_gem_object_get_rcu(vma->obj) ||
(ww && (dma_resv_locking_ctx(vma->obj->base.resv) == &ww->ctx))) {
__i915_vma_pin(vma);
list_add(&vma->evict_link, &locked_eviction_list);
continue;
}
- if (!i915_gem_object_trylock(vma->obj, ww))
+ if (!i915_gem_object_trylock(vma->obj, ww)) {
+ if (busy_bo) {
+ *busy_bo = vma->obj; /* holds ref */
+ ret = -EBUSY;
+ break;
+ }
+ i915_gem_object_put(vma->obj);
continue;
+ }
__i915_vma_pin(vma);
list_add(&vma->evict_link, &eviction_list);
if (list_empty(&eviction_list) && list_empty(&locked_eviction_list))
break;
- ret = 0;
/* Unbind locked objects first, before unlocking the eviction_list */
list_for_each_entry_safe(vma, vn, &locked_eviction_list, evict_link) {
__i915_vma_unpin(vma);
- if (ret == 0)
+ if (ret == 0) {
ret = __i915_vma_unbind(vma);
- if (ret != -EINTR) /* "Get me out of here!" */
- ret = 0;
+ if (ret != -EINTR) /* "Get me out of here!" */
+ ret = 0;
+ }
+ if (!dying_vma(vma))
+ i915_gem_object_put(vma->obj);
}
list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) {
__i915_vma_unpin(vma);
- if (ret == 0)
+ if (ret == 0) {
ret = __i915_vma_unbind(vma);
- if (ret != -EINTR) /* "Get me out of here!" */
- ret = 0;
+ if (ret != -EINTR) /* "Get me out of here!" */
+ ret = 0;
+ }
i915_gem_object_unlock(vma->obj);
+ i915_gem_object_put(vma->obj);
}
} while (ret == 0);
struct drm_mm_node;
struct i915_address_space;
struct i915_gem_ww_ctx;
+struct drm_i915_gem_object;
int __must_check i915_gem_evict_something(struct i915_address_space *vm,
struct i915_gem_ww_ctx *ww,
struct drm_mm_node *node,
unsigned int flags);
int i915_gem_evict_vm(struct i915_address_space *vm,
- struct i915_gem_ww_ctx *ww);
+ struct i915_gem_ww_ctx *ww,
+ struct drm_i915_gem_object **busy_bo);
#endif /* __I915_GEM_EVICT_H__ */
{
struct intel_engine_capture_vma *capture = NULL;
struct intel_engine_coredump *ee;
- struct intel_context *ce;
+ struct intel_context *ce = NULL;
struct i915_request *rq = NULL;
- unsigned long flags;
ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL, dump_flags);
if (!ee)
return NULL;
- ce = intel_engine_get_hung_context(engine);
- if (ce) {
- intel_engine_clear_hung_context(engine);
- rq = intel_context_find_active_request(ce);
- if (!rq || !i915_request_started(rq))
- goto no_request_capture;
- } else {
- /*
- * Getting here with GuC enabled means it is a forced error capture
- * with no actual hang. So, no need to attempt the execlist search.
- */
- if (!intel_uc_uses_guc_submission(&engine->gt->uc)) {
- spin_lock_irqsave(&engine->sched_engine->lock, flags);
- rq = intel_engine_execlist_find_hung_request(engine);
- spin_unlock_irqrestore(&engine->sched_engine->lock,
- flags);
- }
- }
- if (rq)
- rq = i915_request_get_rcu(rq);
-
- if (!rq)
+ intel_engine_get_hung_entity(engine, &ce, &rq);
+ if (!rq || !i915_request_started(rq))
goto no_request_capture;
capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);
- if (!capture) {
- i915_request_put(rq);
+ if (!capture)
goto no_request_capture;
- }
if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
intel_guc_capture_get_matching_node(engine->gt, ee, ce);
return ee;
no_request_capture:
+ if (rq)
+ i915_request_put(rq);
kfree(ee);
return NULL;
}
if (ddi_hotplug_trigger) {
u32 dig_hotplug_reg;
+ /* Locking due to DSI native GPIO sequences */
+ spin_lock(&dev_priv->irq_lock);
dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_DDI, 0, 0);
+ spin_unlock(&dev_priv->irq_lock);
intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
ddi_hotplug_trigger, dig_hotplug_reg,
.has_coherent_ggtt = true, \
.has_llc = 1, \
.has_rc6 = 1, \
- .has_rc6p = 1, \
+ /* snb does support rc6p, but enabling it causes various issues */ \
+ .has_rc6p = 0, \
.has_rps = true, \
.dma_mask_size = 40, \
.__runtime.ppgtt_type = INTEL_PPGTT_ALIASING, \
{}
};
-__maybe_unused
static const struct intel_device_info mtl_info = {
XE_HP_FEATURES,
XE_LPDP_FEATURES,
#define SHOTPLUG_CTL_DDI _MMIO(0xc4030)
#define SHOTPLUG_CTL_DDI_HPD_ENABLE(hpd_pin) (0x8 << (_HPD_PIN_DDI(hpd_pin) * 4))
+#define SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(hpd_pin) (0x4 << (_HPD_PIN_DDI(hpd_pin) * 4))
#define SHOTPLUG_CTL_DDI_HPD_STATUS_MASK(hpd_pin) (0x3 << (_HPD_PIN_DDI(hpd_pin) * 4))
#define SHOTPLUG_CTL_DDI_HPD_NO_DETECT(hpd_pin) (0x0 << (_HPD_PIN_DDI(hpd_pin) * 4))
#define SHOTPLUG_CTL_DDI_HPD_SHORT_DETECT(hpd_pin) (0x1 << (_HPD_PIN_DDI(hpd_pin) * 4))
dev_err(&pdev->dev, "DRM not initialized, aborting switch.\n");
return;
}
+ if (!HAS_DISPLAY(i915)) {
+ dev_err(&pdev->dev, "Device state not initialized, aborting switch.\n");
+ return;
+ }
if (state == VGA_SWITCHEROO_ON) {
drm_info(&i915->drm, "switched on\n");
* locking inversion with the driver load path. And the access here is
* completely racy anyway. So don't bother with locking for now.
*/
- return i915 && atomic_read(&i915->drm.open_count) == 0;
+ return i915 && HAS_DISPLAY(i915) && atomic_read(&i915->drm.open_count) == 0;
}
static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
* locked objects when called from execbuf when pinning
* is removed. This would probably regress badly.
*/
- i915_gem_evict_vm(vm, NULL);
+ i915_gem_evict_vm(vm, NULL, NULL);
mutex_unlock(&vm->mutex);
}
} while (1);
if (!obj->mm.rsgt)
return -EBUSY;
- err = dma_resv_reserve_fences(obj->base.resv, 1);
+ err = dma_resv_reserve_fences(obj->base.resv, 2);
if (err)
return -EBUSY;
/* Everything is pinned, nothing should happen */
mutex_lock(&ggtt->vm.mutex);
- err = i915_gem_evict_vm(&ggtt->vm, NULL);
+ err = i915_gem_evict_vm(&ggtt->vm, NULL, NULL);
mutex_unlock(&ggtt->vm.mutex);
if (err) {
pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
for_i915_gem_ww(&ww, err, false) {
mutex_lock(&ggtt->vm.mutex);
- err = i915_gem_evict_vm(&ggtt->vm, &ww);
+ err = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
mutex_unlock(&ggtt->vm.mutex);
}
int intel_selftest_modify_policy(struct intel_engine_cs *engine,
struct intel_selftest_saved_policy *saved,
- u32 modify_type)
-
+ enum selftest_scheduler_modify modify_type)
{
int err;
break;
}
+ if (ipu_plane->dp_flow == IPU_DP_FLOW_SYNC_BG)
+ width = ipu_src_rect_width(new_state);
+ else
+ width = drm_rect_width(&new_state->src) >> 16;
+
eba = drm_plane_state_to_eba(new_state, 0);
/*
*/
if (ipu_state->use_pre) {
axi_id = ipu_chan_assign_axi_id(ipu_plane->dma);
- ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id,
- ipu_src_rect_width(new_state),
+ ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id, width,
drm_rect_height(&new_state->src) >> 16,
fb->pitches[0], fb->format->format,
fb->modifier, &eba);
break;
}
- ipu_dmfc_config_wait4eot(ipu_plane->dmfc, ALIGN(drm_rect_width(dst), 8));
+ ipu_dmfc_config_wait4eot(ipu_plane->dmfc, width);
- width = ipu_src_rect_width(new_state);
height = drm_rect_height(&new_state->src) >> 16;
info = drm_format_info(fb->format->format);
ipu_calculate_bursts(width, info->cpp[0], fb->pitches[0],
ipu_cpmem_set_burstsize(ipu_plane->ipu_ch, 16);
ipu_cpmem_zero(ipu_plane->alpha_ch);
- ipu_cpmem_set_resolution(ipu_plane->alpha_ch,
- ipu_src_rect_width(new_state),
+ ipu_cpmem_set_resolution(ipu_plane->alpha_ch, width,
drm_rect_height(&new_state->src) >> 16);
ipu_cpmem_set_format_passthrough(ipu_plane->alpha_ch, 8);
ipu_cpmem_set_high_priority(ipu_plane->alpha_ch);
/* Initialize OSD1 fifo control register */
reg = VIU_OSD_DDR_PRIORITY_URGENT |
- VIU_OSD_HOLD_FIFO_LINES(31) |
VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */
VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */
VIU_OSD_FIFO_LIMITS(2); /* fifo_lim: 2*16=32 */
if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
- reg |= VIU_OSD_BURST_LENGTH_32;
+ reg |= (VIU_OSD_BURST_LENGTH_32 | VIU_OSD_HOLD_FIFO_LINES(31));
else
- reg |= VIU_OSD_BURST_LENGTH_64;
+ reg |= (VIU_OSD_BURST_LENGTH_64 | VIU_OSD_HOLD_FIFO_LINES(4));
writel_relaxed(reg, priv->io_base + _REG(VIU_OSD1_FIFO_CTRL_STAT));
writel_relaxed(reg, priv->io_base + _REG(VIU_OSD2_FIFO_CTRL_STAT));
#define GBIF_CLIENT_HALT_MASK BIT(0)
#define GBIF_ARB_HALT_MASK BIT(1)
-static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu,
+ bool gx_off)
{
struct msm_gpu *gpu = &adreno_gpu->base;
return;
}
- /* Halt the gx side of GBIF */
- gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1);
- spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1);
+ if (gx_off) {
+ /* Halt the gx side of GBIF */
+ gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1);
+ spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1);
+ }
/* Halt new client requests on GBIF */
gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
/* Halt the gmu cm3 core */
gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);
- a6xx_bus_clear_pending_transactions(adreno_gpu);
+ a6xx_bus_clear_pending_transactions(adreno_gpu, true);
/* Reset GPU core blocks */
gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, 1);
return;
}
- a6xx_bus_clear_pending_transactions(adreno_gpu);
+ a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung);
/* tell the GMU we want to slumber */
ret = a6xx_gmu_notify_slumber(gmu);
if (hang_debug)
a6xx_dump(gpu);
+ /*
+ * To handle recovery specific sequences during the rpm suspend we are
+ * about to trigger
+ */
+ a6xx_gpu->hung = true;
+
/* Halt SQE first */
gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3);
mutex_unlock(&gpu->active_lock);
msm_gpu_hw_init(gpu);
+ a6xx_gpu->hung = false;
}
static const char *a6xx_uche_fault_block(struct msm_gpu *gpu, u32 mid)
void *llc_slice;
void *htw_llc_slice;
bool have_mmu500;
+ bool hung;
};
#define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base)
return 0;
}
+static int adreno_system_suspend(struct device *dev);
static void adreno_unbind(struct device *dev, struct device *master,
void *data)
{
struct msm_drm_private *priv = dev_get_drvdata(master);
struct msm_gpu *gpu = dev_to_gpu(dev);
- pm_runtime_force_suspend(dev);
+ WARN_ON_ONCE(adreno_system_suspend(dev));
gpu->funcs->destroy(gpu);
priv->gpu_pdev = NULL;
static void adreno_shutdown(struct platform_device *pdev)
{
- pm_runtime_force_suspend(&pdev->dev);
+ WARN_ON_ONCE(adreno_system_suspend(&pdev->dev));
}
static const struct of_device_id dt_match[] = {
/* Ensure string is null terminated: */
str[len] = '\0';
+ mutex_lock(&gpu->lock);
+
if (param == MSM_PARAM_COMM) {
paramp = &ctx->comm;
} else {
kfree(*paramp);
*paramp = str;
+ mutex_unlock(&gpu->lock);
+
return 0;
}
case MSM_PARAM_SYSPROF:
ADRENO_FW_MAX,
};
-enum adreno_quirks {
- ADRENO_QUIRK_TWO_PASS_USE_WFI = 1,
- ADRENO_QUIRK_FAULT_DETECT_MASK = 2,
- ADRENO_QUIRK_LMLOADKILL_DISABLE = 3,
-};
+#define ADRENO_QUIRK_TWO_PASS_USE_WFI BIT(0)
+#define ADRENO_QUIRK_FAULT_DETECT_MASK BIT(1)
+#define ADRENO_QUIRK_LMLOADKILL_DISABLE BIT(2)
struct adreno_rev {
uint8_t core;
const char *name;
const char *fw[ADRENO_FW_MAX];
uint32_t gmem;
- enum adreno_quirks quirks;
+ u64 quirks;
struct msm_gpu *(*init)(struct drm_device *dev);
const char *zapfw;
u32 inactive_period;
* dpu_encoder_phys_wb_setup_fb - setup output framebuffer
* @phys_enc: Pointer to physical encoder
* @fb: Pointer to output framebuffer
- * @wb_roi: Pointer to output region of interest
*/
static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc,
struct drm_framebuffer *fb)
/**
* dpu_encoder_phys_wb_init - initialize writeback encoder
- * @init: Pointer to init info structure with initialization params
+ * @p: Pointer to init info structure with initialization params
*/
struct dpu_encoder_phys *dpu_encoder_phys_wb_init(
struct dpu_enc_phys_init_params *p)
isr = dp_catalog_aux_get_irq(aux->catalog);
+ /* no interrupts pending, return immediately */
+ if (!isr)
+ return;
+
if (!aux->cmd_busy)
return;
ret = devm_pm_runtime_enable(&pdev->dev);
if (ret)
- return ret;
+ goto err_put_phy;
platform_set_drvdata(pdev, hdmi);
- return component_add(&pdev->dev, &msm_hdmi_ops);
+ ret = component_add(&pdev->dev, &msm_hdmi_ops);
+ if (ret)
+ goto err_put_phy;
+
+ return 0;
+
+err_put_phy:
+ msm_hdmi_put_phy(hdmi);
+ return ret;
}
static int msm_hdmi_dev_remove(struct platform_device *pdev)
* msm_drm_init, drm_dev->registered is used as an indicator that the
* shutdown will be successful.
*/
- if (drm && drm->registered)
+ if (drm && drm->registered && priv->kms)
drm_atomic_helper_shutdown(drm);
}
struct msm_file_private *ctx = submit->queue->ctx;
struct task_struct *task;
+ WARN_ON(!mutex_is_locked(&submit->gpu->lock));
+
/* Note that kstrdup will return NULL if argument is NULL: */
*comm = kstrdup(ctx->comm, GFP_KERNEL);
*cmd = kstrdup(ctx->cmdline, GFP_KERNEL);
*/
int sysprof;
- /** comm: Overridden task comm, see MSM_PARAM_COMM */
+ /**
+ * comm: Overridden task comm, see MSM_PARAM_COMM
+ *
+ * Accessed under msm_gpu::lock
+ */
char *comm;
- /** cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE */
+ /**
+ * cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE
+ *
+ * Accessed under msm_gpu::lock
+ */
char *cmdline;
/**
static int msm_mdss_parse_data_bus_icc_path(struct device *dev,
struct msm_mdss *msm_mdss)
{
- struct icc_path *path0 = of_icc_get(dev, "mdp0-mem");
- struct icc_path *path1 = of_icc_get(dev, "mdp1-mem");
+ struct icc_path *path0;
+ struct icc_path *path1;
+ path0 = of_icc_get(dev, "mdp0-mem");
if (IS_ERR_OR_NULL(path0))
return PTR_ERR_OR_ZERO(path0);
msm_mdss->path[0] = path0;
msm_mdss->num_paths = 1;
+ path1 = of_icc_get(dev, "mdp1-mem");
if (!IS_ERR_OR_NULL(path1)) {
msm_mdss->path[1] = path1;
msm_mdss->num_paths++;
int gp102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **);
int gp10b_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **);
int gv100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **);
+int tu102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **);
int ga100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **);
int ga102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **);
+++ /dev/null
-/*
- * Copyright © 2007 David Airlie
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Authors:
- * David Airlie
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/tty.h>
-#include <linux/sysrq.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/screen_info.h>
-#include <linux/vga_switcheroo.h>
-#include <linux/console.h>
-
-#include <drm/drm_crtc.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_probe_helper.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_atomic.h>
-
-#include "nouveau_drv.h"
-#include "nouveau_gem.h"
-#include "nouveau_bo.h"
-#include "nouveau_fbcon.h"
-#include "nouveau_chan.h"
-#include "nouveau_vmm.h"
-
-#include "nouveau_crtc.h"
-
-MODULE_PARM_DESC(nofbaccel, "Disable fbcon acceleration");
-int nouveau_nofbaccel = 0;
-module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400);
-
-MODULE_PARM_DESC(fbcon_bpp, "fbcon bits-per-pixel (default: auto)");
-static int nouveau_fbcon_bpp;
-module_param_named(fbcon_bpp, nouveau_fbcon_bpp, int, 0400);
-
-static void
-nouveau_fbcon_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_fillrect(info, rect);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_fillrect(info, rect);
- else
- ret = nvc0_fbcon_fillrect(info, rect);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_fillrect(info, rect);
-}
-
-static void
-nouveau_fbcon_copyarea(struct fb_info *info, const struct fb_copyarea *image)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_copyarea(info, image);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_copyarea(info, image);
- else
- ret = nvc0_fbcon_copyarea(info, image);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_copyarea(info, image);
-}
-
-static void
-nouveau_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_imageblit(info, image);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_imageblit(info, image);
- else
- ret = nvc0_fbcon_imageblit(info, image);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_imageblit(info, image);
-}
-
-static int
-nouveau_fbcon_sync(struct fb_info *info)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nouveau_channel *chan = drm->channel;
- int ret;
-
- if (!chan || !chan->accel_done || in_interrupt() ||
- info->state != FBINFO_STATE_RUNNING ||
- info->flags & FBINFO_HWACCEL_DISABLED)
- return 0;
-
- if (!mutex_trylock(&drm->client.mutex))
- return 0;
-
- ret = nouveau_channel_idle(chan);
- mutex_unlock(&drm->client.mutex);
- if (ret) {
- nouveau_fbcon_gpu_lockup(info);
- return 0;
- }
-
- chan->accel_done = false;
- return 0;
-}
-
-static int
-nouveau_fbcon_open(struct fb_info *info, int user)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- int ret = pm_runtime_get_sync(drm->dev->dev);
- if (ret < 0 && ret != -EACCES) {
- pm_runtime_put(drm->dev->dev);
- return ret;
- }
- return 0;
-}
-
-static int
-nouveau_fbcon_release(struct fb_info *info, int user)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- pm_runtime_put(drm->dev->dev);
- return 0;
-}
-
-static const struct fb_ops nouveau_fbcon_ops = {
- .owner = THIS_MODULE,
- DRM_FB_HELPER_DEFAULT_OPS,
- .fb_open = nouveau_fbcon_open,
- .fb_release = nouveau_fbcon_release,
- .fb_fillrect = nouveau_fbcon_fillrect,
- .fb_copyarea = nouveau_fbcon_copyarea,
- .fb_imageblit = nouveau_fbcon_imageblit,
- .fb_sync = nouveau_fbcon_sync,
-};
-
-static const struct fb_ops nouveau_fbcon_sw_ops = {
- .owner = THIS_MODULE,
- DRM_FB_HELPER_DEFAULT_OPS,
- .fb_open = nouveau_fbcon_open,
- .fb_release = nouveau_fbcon_release,
- .fb_fillrect = drm_fb_helper_cfb_fillrect,
- .fb_copyarea = drm_fb_helper_cfb_copyarea,
- .fb_imageblit = drm_fb_helper_cfb_imageblit,
-};
-
-void
-nouveau_fbcon_accel_save_disable(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- if (drm->fbcon && drm->fbcon->helper.info) {
- drm->fbcon->saved_flags = drm->fbcon->helper.info->flags;
- drm->fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED;
- }
-}
-
-void
-nouveau_fbcon_accel_restore(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- if (drm->fbcon && drm->fbcon->helper.info)
- drm->fbcon->helper.info->flags = drm->fbcon->saved_flags;
-}
-
-static void
-nouveau_fbcon_accel_fini(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- if (fbcon && drm->channel) {
- console_lock();
- if (fbcon->helper.info)
- fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED;
- console_unlock();
- nouveau_channel_idle(drm->channel);
- nvif_object_dtor(&fbcon->twod);
- nvif_object_dtor(&fbcon->blit);
- nvif_object_dtor(&fbcon->gdi);
- nvif_object_dtor(&fbcon->patt);
- nvif_object_dtor(&fbcon->rop);
- nvif_object_dtor(&fbcon->clip);
- nvif_object_dtor(&fbcon->surf2d);
- }
-}
-
-static void
-nouveau_fbcon_accel_init(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- struct fb_info *info = fbcon->helper.info;
- int ret;
-
- if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_accel_init(info);
- else
- if (drm->client.device.info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_accel_init(info);
- else
- ret = nvc0_fbcon_accel_init(info);
-
- if (ret == 0)
- info->fbops = &nouveau_fbcon_ops;
-}
-
-static void
-nouveau_fbcon_zfill(struct drm_device *dev, struct nouveau_fbdev *fbcon)
-{
- struct fb_info *info = fbcon->helper.info;
- struct fb_fillrect rect;
-
- /* Clear the entire fbcon. The drm will program every connector
- * with it's preferred mode. If the sizes differ, one display will
- * quite likely have garbage around the console.
- */
- rect.dx = rect.dy = 0;
- rect.width = info->var.xres_virtual;
- rect.height = info->var.yres_virtual;
- rect.color = 0;
- rect.rop = ROP_COPY;
- info->fbops->fb_fillrect(info, &rect);
-}
-
-static int
-nouveau_fbcon_create(struct drm_fb_helper *helper,
- struct drm_fb_helper_surface_size *sizes)
-{
- struct nouveau_fbdev *fbcon =
- container_of(helper, struct nouveau_fbdev, helper);
- struct drm_device *dev = fbcon->helper.dev;
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nvif_device *device = &drm->client.device;
- struct fb_info *info;
- struct drm_framebuffer *fb;
- struct nouveau_channel *chan;
- struct nouveau_bo *nvbo;
- struct drm_mode_fb_cmd2 mode_cmd = {};
- int ret;
-
- mode_cmd.width = sizes->surface_width;
- mode_cmd.height = sizes->surface_height;
-
- mode_cmd.pitches[0] = mode_cmd.width * (sizes->surface_bpp >> 3);
- mode_cmd.pitches[0] = roundup(mode_cmd.pitches[0], 256);
-
- mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp,
- sizes->surface_depth);
-
- ret = nouveau_gem_new(&drm->client, mode_cmd.pitches[0] *
- mode_cmd.height, 0, NOUVEAU_GEM_DOMAIN_VRAM,
- 0, 0x0000, &nvbo);
- if (ret) {
- NV_ERROR(drm, "failed to allocate framebuffer\n");
- goto out;
- }
-
- ret = nouveau_framebuffer_new(dev, &mode_cmd, &nvbo->bo.base, &fb);
- if (ret)
- goto out_unref;
-
- ret = nouveau_bo_pin(nvbo, NOUVEAU_GEM_DOMAIN_VRAM, false);
- if (ret) {
- NV_ERROR(drm, "failed to pin fb: %d\n", ret);
- goto out_unref;
- }
-
- ret = nouveau_bo_map(nvbo);
- if (ret) {
- NV_ERROR(drm, "failed to map fb: %d\n", ret);
- goto out_unpin;
- }
-
- chan = nouveau_nofbaccel ? NULL : drm->channel;
- if (chan && device->info.family >= NV_DEVICE_INFO_V0_TESLA) {
- ret = nouveau_vma_new(nvbo, chan->vmm, &fbcon->vma);
- if (ret) {
- NV_ERROR(drm, "failed to map fb into chan: %d\n", ret);
- chan = NULL;
- }
- }
-
- info = drm_fb_helper_alloc_info(helper);
- if (IS_ERR(info)) {
- ret = PTR_ERR(info);
- goto out_unlock;
- }
-
- /* setup helper */
- fbcon->helper.fb = fb;
-
- if (!chan)
- info->flags = FBINFO_HWACCEL_DISABLED;
- else
- info->flags = FBINFO_HWACCEL_COPYAREA |
- FBINFO_HWACCEL_FILLRECT |
- FBINFO_HWACCEL_IMAGEBLIT;
- info->fbops = &nouveau_fbcon_sw_ops;
- info->fix.smem_start = nvbo->bo.resource->bus.offset;
- info->fix.smem_len = nvbo->bo.base.size;
-
- info->screen_base = nvbo_kmap_obj_iovirtual(nvbo);
- info->screen_size = nvbo->bo.base.size;
-
- drm_fb_helper_fill_info(info, &fbcon->helper, sizes);
-
- /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
-
- if (chan)
- nouveau_fbcon_accel_init(dev);
- nouveau_fbcon_zfill(dev, fbcon);
-
- /* To allow resizeing without swapping buffers */
- NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n",
- fb->width, fb->height, nvbo->offset, nvbo);
-
- if (dev_is_pci(dev->dev))
- vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), info);
-
- return 0;
-
-out_unlock:
- if (chan)
- nouveau_vma_del(&fbcon->vma);
- nouveau_bo_unmap(nvbo);
-out_unpin:
- nouveau_bo_unpin(nvbo);
-out_unref:
- nouveau_bo_ref(NULL, &nvbo);
-out:
- return ret;
-}
-
-static int
-nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon)
-{
- struct drm_framebuffer *fb = fbcon->helper.fb;
- struct nouveau_bo *nvbo;
-
- drm_fb_helper_unregister_info(&fbcon->helper);
- drm_fb_helper_fini(&fbcon->helper);
-
- if (fb && fb->obj[0]) {
- nvbo = nouveau_gem_object(fb->obj[0]);
- nouveau_vma_del(&fbcon->vma);
- nouveau_bo_unmap(nvbo);
- nouveau_bo_unpin(nvbo);
- drm_framebuffer_put(fb);
- }
-
- return 0;
-}
-
-void nouveau_fbcon_gpu_lockup(struct fb_info *info)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
-
- NV_ERROR(drm, "GPU lockup - switching to software fbcon\n");
- info->flags |= FBINFO_HWACCEL_DISABLED;
-}
-
-static const struct drm_fb_helper_funcs nouveau_fbcon_helper_funcs = {
- .fb_probe = nouveau_fbcon_create,
-};
-
-static void
-nouveau_fbcon_set_suspend_work(struct work_struct *work)
-{
- struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work);
- int state = READ_ONCE(drm->fbcon_new_state);
-
- if (state == FBINFO_STATE_RUNNING)
- pm_runtime_get_sync(drm->dev->dev);
-
- console_lock();
- if (state == FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_restore(drm->dev);
- drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
- if (state != FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_save_disable(drm->dev);
- console_unlock();
-
- if (state == FBINFO_STATE_RUNNING) {
- nouveau_fbcon_hotplug_resume(drm->fbcon);
- pm_runtime_mark_last_busy(drm->dev->dev);
- pm_runtime_put_autosuspend(drm->dev->dev);
- }
-}
-
-void
-nouveau_fbcon_set_suspend(struct drm_device *dev, int state)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
-
- if (!drm->fbcon)
- return;
-
- drm->fbcon_new_state = state;
- /* Since runtime resume can happen as a result of a sysfs operation,
- * it's possible we already have the console locked. So handle fbcon
- * init/deinit from a seperate work thread
- */
- schedule_work(&drm->fbcon_work);
-}
-
-void
-nouveau_fbcon_output_poll_changed(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- int ret;
-
- if (!fbcon)
- return;
-
- mutex_lock(&fbcon->hotplug_lock);
-
- ret = pm_runtime_get(dev->dev);
- if (ret == 1 || ret == -EACCES) {
- drm_fb_helper_hotplug_event(&fbcon->helper);
-
- pm_runtime_mark_last_busy(dev->dev);
- pm_runtime_put_autosuspend(dev->dev);
- } else if (ret == 0) {
- /* If the GPU was already in the process of suspending before
- * this event happened, then we can't block here as we'll
- * deadlock the runtime pmops since they wait for us to
- * finish. So, just defer this event for when we runtime
- * resume again. It will be handled by fbcon_work.
- */
- NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n");
- fbcon->hotplug_waiting = true;
- pm_runtime_put_noidle(drm->dev->dev);
- } else {
- DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n",
- ret);
- }
-
- mutex_unlock(&fbcon->hotplug_lock);
-}
-
-void
-nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon)
-{
- struct nouveau_drm *drm;
-
- if (!fbcon)
- return;
- drm = nouveau_drm(fbcon->helper.dev);
-
- mutex_lock(&fbcon->hotplug_lock);
- if (fbcon->hotplug_waiting) {
- fbcon->hotplug_waiting = false;
-
- NV_DEBUG(drm, "Handling deferred fbcon HPD events\n");
- drm_fb_helper_hotplug_event(&fbcon->helper);
- }
- mutex_unlock(&fbcon->hotplug_lock);
-}
-
-int
-nouveau_fbcon_init(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon;
- int preferred_bpp = nouveau_fbcon_bpp;
- int ret;
-
- if (!dev->mode_config.num_crtc ||
- (to_pci_dev(dev->dev)->class >> 8) != PCI_CLASS_DISPLAY_VGA)
- return 0;
-
- fbcon = kzalloc(sizeof(struct nouveau_fbdev), GFP_KERNEL);
- if (!fbcon)
- return -ENOMEM;
-
- drm->fbcon = fbcon;
- INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work);
- mutex_init(&fbcon->hotplug_lock);
-
- drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs);
-
- ret = drm_fb_helper_init(dev, &fbcon->helper);
- if (ret)
- goto free;
-
- if (preferred_bpp != 8 && preferred_bpp != 16 && preferred_bpp != 32) {
- if (drm->client.device.info.ram_size <= 32 * 1024 * 1024)
- preferred_bpp = 8;
- else
- if (drm->client.device.info.ram_size <= 64 * 1024 * 1024)
- preferred_bpp = 16;
- else
- preferred_bpp = 32;
- }
-
- /* disable all the possible outputs/crtcs before entering KMS mode */
- if (!drm_drv_uses_atomic_modeset(dev))
- drm_helper_disable_unused_functions(dev);
-
- ret = drm_fb_helper_initial_config(&fbcon->helper, preferred_bpp);
- if (ret)
- goto fini;
-
- if (fbcon->helper.info)
- fbcon->helper.info->pixmap.buf_align = 4;
- return 0;
-
-fini:
- drm_fb_helper_fini(&fbcon->helper);
-free:
- kfree(fbcon);
- drm->fbcon = NULL;
- return ret;
-}
-
-void
-nouveau_fbcon_fini(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
-
- if (!drm->fbcon)
- return;
-
- drm_kms_helper_poll_fini(dev);
- nouveau_fbcon_accel_fini(dev);
- nouveau_fbcon_destroy(dev, drm->fbcon);
- kfree(drm->fbcon);
- drm->fbcon = NULL;
-}
static enum nvkm_memory_target
nvkm_firmware_mem_target(struct nvkm_memory *memory)
{
+ if (nvkm_firmware_mem(memory)->device->func->tegra)
+ return NVKM_MEM_TARGET_NCOH;
+
return NVKM_MEM_TARGET_HOST;
}
.bus = { 0x00000001, gf100_bus_new },
.devinit = { 0x00000001, tu102_devinit_new },
.fault = { 0x00000001, tu102_fault_new },
- .fb = { 0x00000001, gv100_fb_new },
+ .fb = { 0x00000001, tu102_fb_new },
.fuse = { 0x00000001, gm107_fuse_new },
.gpio = { 0x00000001, gk104_gpio_new },
.gsp = { 0x00000001, gv100_gsp_new },
.bus = { 0x00000001, gf100_bus_new },
.devinit = { 0x00000001, tu102_devinit_new },
.fault = { 0x00000001, tu102_fault_new },
- .fb = { 0x00000001, gv100_fb_new },
+ .fb = { 0x00000001, tu102_fb_new },
.fuse = { 0x00000001, gm107_fuse_new },
.gpio = { 0x00000001, gk104_gpio_new },
.gsp = { 0x00000001, gv100_gsp_new },
.bus = { 0x00000001, gf100_bus_new },
.devinit = { 0x00000001, tu102_devinit_new },
.fault = { 0x00000001, tu102_fault_new },
- .fb = { 0x00000001, gv100_fb_new },
+ .fb = { 0x00000001, tu102_fb_new },
.fuse = { 0x00000001, gm107_fuse_new },
.gpio = { 0x00000001, gk104_gpio_new },
.gsp = { 0x00000001, gv100_gsp_new },
.bus = { 0x00000001, gf100_bus_new },
.devinit = { 0x00000001, tu102_devinit_new },
.fault = { 0x00000001, tu102_fault_new },
- .fb = { 0x00000001, gv100_fb_new },
+ .fb = { 0x00000001, tu102_fb_new },
.fuse = { 0x00000001, gm107_fuse_new },
.gpio = { 0x00000001, gk104_gpio_new },
.gsp = { 0x00000001, gv100_gsp_new },
.bus = { 0x00000001, gf100_bus_new },
.devinit = { 0x00000001, tu102_devinit_new },
.fault = { 0x00000001, tu102_fault_new },
- .fb = { 0x00000001, gv100_fb_new },
+ .fb = { 0x00000001, tu102_fb_new },
.fuse = { 0x00000001, gm107_fuse_new },
.gpio = { 0x00000001, gk104_gpio_new },
.gsp = { 0x00000001, gv100_gsp_new },
img += 4;
len -= 4;
}
+
+ /* Sigh. Tegra PMU FW's init message... */
+ if (len) {
+ u32 data = nvkm_falcon_rd32(falcon, 0x1c4 + (port * 8));
+
+ while (len--) {
+ *(u8 *)img++ = data & 0xff;
+ data >>= 8;
+ }
+ }
}
static void
img += 4;
len -= 4;
}
+
+ WARN_ON(len);
}
static void
const struct nvkm_falcon_func_pio
gm200_flcn_dmem_pio = {
- .min = 4,
+ .min = 1,
.max = 0x100,
.wr_init = gm200_flcn_pio_dmem_wr_init,
.wr = gm200_flcn_pio_dmem_wr,
return ret;
}
+static int
+tu102_devinit_wait(struct nvkm_device *device)
+{
+ unsigned timeout = 50 + 2000;
+
+ do {
+ if (nvkm_rd32(device, 0x118128) & 0x00000001) {
+ if ((nvkm_rd32(device, 0x118234) & 0x000000ff) == 0xff)
+ return 0;
+ }
+
+ usleep_range(1000, 2000);
+ } while (timeout--);
+
+ return -ETIMEDOUT;
+}
+
int
tu102_devinit_post(struct nvkm_devinit *base, bool post)
{
struct nv50_devinit *init = nv50_devinit(base);
+ int ret;
+
+ ret = tu102_devinit_wait(init->base.subdev.device);
+ if (ret)
+ return ret;
+
gm200_devinit_preos(init, post);
return 0;
}
nvkm-y += nvkm/subdev/fb/gp102.o
nvkm-y += nvkm/subdev/fb/gp10b.o
nvkm-y += nvkm/subdev/fb/gv100.o
+nvkm-y += nvkm/subdev/fb/tu102.o
nvkm-y += nvkm/subdev/fb/ga100.o
nvkm-y += nvkm/subdev/fb/ga102.o
return ret;
}
-static bool
-ga102_fb_vpr_scrub_required(struct nvkm_fb *fb)
-{
- return (nvkm_rd32(fb->subdev.device, 0x1fa80c) & 0x00000010) != 0;
-}
-
static const struct nvkm_fb_func
ga102_fb = {
.dtor = gf100_fb_dtor,
.sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init,
.ram_new = ga102_ram_new,
.default_bigpage = 16,
- .vpr.scrub_required = ga102_fb_vpr_scrub_required,
+ .vpr.scrub_required = tu102_fb_vpr_scrub_required,
.vpr.scrub = ga102_fb_vpr_scrub,
};
}
MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin");
int gp102_fb_vpr_scrub(struct nvkm_fb *);
int gv100_fb_init_page(struct nvkm_fb *);
+
+bool tu102_fb_vpr_scrub_required(struct nvkm_fb *);
#endif
--- /dev/null
+/*
+ * Copyright 2018 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+bool
+tu102_fb_vpr_scrub_required(struct nvkm_fb *fb)
+{
+ return (nvkm_rd32(fb->subdev.device, 0x1fa80c) & 0x00000010) != 0;
+}
+
+static const struct nvkm_fb_func
+tu102_fb = {
+ .dtor = gf100_fb_dtor,
+ .oneinit = gf100_fb_oneinit,
+ .init = gm200_fb_init,
+ .init_page = gv100_fb_init_page,
+ .init_unkn = gp100_fb_init_unkn,
+ .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init,
+ .vpr.scrub_required = tu102_fb_vpr_scrub_required,
+ .vpr.scrub = gp102_fb_vpr_scrub,
+ .ram_new = gp100_ram_new,
+ .default_bigpage = 16,
+};
+
+int
+tu102_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb)
+{
+ return gp102_fb_new_(&tu102_fb, device, type, inst, pfb);
+}
+
+MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin");
pmu->initmsg_received = false;
- nvkm_falcon_load_dmem(falcon, &args, addr_args, sizeof(args), 0);
+ nvkm_falcon_pio_wr(falcon, (u8 *)&args, 0, 0, DMEM, addr_args, sizeof(args), 0, false);
nvkm_falcon_start(falcon);
return 0;
}
return 0;
}
-static int boe_panel_unprepare(struct drm_panel *panel)
+static int boe_panel_disable(struct drm_panel *panel)
{
struct boe_panel *boe = to_boe_panel(panel);
int ret;
- if (!boe->prepared)
- return 0;
-
ret = boe_panel_enter_sleep_mode(boe);
if (ret < 0) {
dev_err(panel->dev, "failed to set panel off: %d\n", ret);
msleep(150);
+ return 0;
+}
+
+static int boe_panel_unprepare(struct drm_panel *panel)
+{
+ struct boe_panel *boe = to_boe_panel(panel);
+
+ if (!boe->prepared)
+ return 0;
+
if (boe->desc->discharge_on_disable) {
regulator_disable(boe->avee);
regulator_disable(boe->avdd);
}
static const struct drm_panel_funcs boe_panel_funcs = {
+ .disable = boe_panel_disable,
.unprepare = boe_panel_unprepare,
.prepare = boe_panel_prepare,
.enable = boe_panel_enable,
config DRM_PANFROST
tristate "Panfrost (DRM support for ARM Mali Midgard/Bifrost GPUs)"
depends on DRM
- depends on ARM || ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64)
+ depends on ARM || ARM64 || COMPILE_TEST
+ depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE
depends on MMU
select DRM_SCHED
select IOMMU_SUPPORT
struct panfrost_gem_object *bo;
struct drm_panfrost_create_bo *args = data;
struct panfrost_gem_mapping *mapping;
+ int ret;
if (!args->size || args->pad ||
(args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP)))
!(args->flags & PANFROST_BO_NOEXEC))
return -EINVAL;
- bo = panfrost_gem_create_with_handle(file, dev, args->size, args->flags,
- &args->handle);
+ bo = panfrost_gem_create(dev, args->size, args->flags);
if (IS_ERR(bo))
return PTR_ERR(bo);
+ ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
+ if (ret)
+ goto out;
+
mapping = panfrost_gem_mapping_get(bo, priv);
- if (!mapping) {
- drm_gem_object_put(&bo->base.base);
- return -EINVAL;
+ if (mapping) {
+ args->offset = mapping->mmnode.start << PAGE_SHIFT;
+ panfrost_gem_mapping_put(mapping);
+ } else {
+ /* This can only happen if the handle from
+ * drm_gem_handle_create() has already been guessed and freed
+ * by user space
+ */
+ ret = -EINVAL;
}
- args->offset = mapping->mmnode.start << PAGE_SHIFT;
- panfrost_gem_mapping_put(mapping);
-
- return 0;
+out:
+ drm_gem_object_put(&bo->base.base);
+ return ret;
}
/**
}
struct panfrost_gem_object *
-panfrost_gem_create_with_handle(struct drm_file *file_priv,
- struct drm_device *dev, size_t size,
- u32 flags,
- uint32_t *handle)
+panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags)
{
- int ret;
struct drm_gem_shmem_object *shmem;
struct panfrost_gem_object *bo;
bo->noexec = !!(flags & PANFROST_BO_NOEXEC);
bo->is_heap = !!(flags & PANFROST_BO_HEAP);
- /*
- * Allocate an id of idr table where the obj is registered
- * and handle has the id what user can see.
- */
- ret = drm_gem_handle_create(file_priv, &shmem->base, handle);
- /* drop reference from allocate - handle holds it now. */
- drm_gem_object_put(&shmem->base);
- if (ret)
- return ERR_PTR(ret);
-
return bo;
}
struct sg_table *sgt);
struct panfrost_gem_object *
-panfrost_gem_create_with_handle(struct drm_file *file_priv,
- struct drm_device *dev, size_t size,
- u32 flags,
- uint32_t *handle);
+panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags);
int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv);
void panfrost_gem_close(struct drm_gem_object *obj,
init_completion(&entity->entity_idle);
/* We start in an idle state. */
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
spin_lock_init(&entity->rq_lock);
spsc_queue_init(&entity->job_queue);
sched_job = drm_sched_entity_pop_job(entity);
if (!sched_job) {
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
continue;
}
trace_drm_run_job(sched_job, entity);
fence = sched->ops->run_job(sched_job);
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
drm_sched_fence_scheduled(s_fence);
if (!IS_ERR_OR_NULL(fence)) {
.atomic_check = drm_crtc_helper_atomic_check,
};
-static void ssd130x_crtc_reset(struct drm_crtc *crtc)
-{
- struct drm_device *drm = crtc->dev;
- struct ssd130x_device *ssd130x = drm_to_ssd130x(drm);
-
- ssd130x_init(ssd130x);
-
- drm_atomic_helper_crtc_reset(crtc);
-}
-
static const struct drm_crtc_funcs ssd130x_crtc_funcs = {
- .reset = ssd130x_crtc_reset,
+ .reset = drm_atomic_helper_crtc_reset,
.destroy = drm_crtc_cleanup,
.set_config = drm_atomic_helper_set_config,
.page_flip = drm_atomic_helper_page_flip,
if (ret)
return;
+ ret = ssd130x_init(ssd130x);
+ if (ret) {
+ ssd130x_power_off(ssd130x);
+ return;
+ }
+
ssd130x_write_cmd(ssd130x, 1, SSD130X_DISPLAY_ON);
backlight_enable(ssd130x->bl_dev);
drm_mm_test.o \
drm_plane_helper_test.o \
drm_rect_test.o
+
+CFLAGS_drm_mm_test.o := $(DISABLE_STRUCTLEAK_PLUGIN)
return false;
}
-static bool check_reserve_boundaries(struct kunit *test, struct drm_mm *mm,
- unsigned int count,
- u64 size)
+static bool noinline_for_stack check_reserve_boundaries(struct kunit *test, struct drm_mm *mm,
+ unsigned int count,
+ u64 size)
{
const struct boundary {
u64 start, size;
clear = src_iter->ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm));
if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC)))
- ttm_move_memcpy(clear, ttm->num_pages, dst_iter, src_iter);
+ ttm_move_memcpy(clear, PFN_UP(dst_mem->size), dst_iter, src_iter);
if (!src_iter->ops->maps_tt)
ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, src_mem);
bo->validated_shader = NULL;
}
+ mutex_destroy(&bo->madv_lock);
drm_gem_dma_free(&bo->base);
}
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
struct vc4_bo *bo;
- int ret;
if (WARN_ON_ONCE(vc4->is_vc5))
return ERR_PTR(-ENODEV);
bo->madv = VC4_MADV_WILLNEED;
refcount_set(&bo->usecnt, 0);
- ret = drmm_mutex_init(dev, &bo->madv_lock);
- if (ret)
- return ERR_PTR(ret);
+ mutex_init(&bo->madv_lock);
mutex_lock(&vc4->bo_lock);
bo->label = VC4_BO_TYPE_KERNEL;
struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
if (vc4_encoder->type == VC4_ENCODER_TYPE_HDMI0) {
- vc4_state->hvs_load = max(mode->clock * mode->hdisplay / mode->htotal + 1000,
+ vc4_state->hvs_load = max(mode->clock * mode->hdisplay / mode->htotal + 8000,
mode->clock * 9 / 10) * 1000;
} else {
vc4_state->hvs_load = mode->clock * 1000;
#define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_1_SHIFT 8
#define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_1_MASK VC4_MASK(15, 8)
+#define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_MASK VC4_MASK(7, 0)
+#define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_SET_AVMUTE BIT(0)
+#define VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_CLEAR_AVMUTE BIT(4)
+
# define VC4_HD_M_SW_RST BIT(2)
# define VC4_HD_M_ENABLE BIT(0)
VC4_HDMI_VERTB_VBP));
unsigned long flags;
unsigned char gcp;
- bool gcp_en;
u32 reg;
int idx;
switch (vc4_state->output_bpc) {
case 12:
gcp = 6;
- gcp_en = true;
break;
case 10:
gcp = 5;
- gcp_en = true;
break;
case 8:
default:
- gcp = 4;
- gcp_en = false;
+ gcp = 0;
break;
}
* doesn't signal in GCP.
*/
if (vc4_state->output_format == VC4_HDMI_OUTPUT_YUV422) {
- gcp = 4;
- gcp_en = false;
+ gcp = 0;
}
reg = HDMI_READ(HDMI_DEEP_COLOR_CONFIG_1);
reg = HDMI_READ(HDMI_GCP_WORD_1);
reg &= ~VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_1_MASK;
reg |= VC4_SET_FIELD(gcp, VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_1);
+ reg &= ~VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_MASK;
+ reg |= VC5_HDMI_GCP_WORD_1_GCP_SUBPACKET_BYTE_0_CLEAR_AVMUTE;
HDMI_WRITE(HDMI_GCP_WORD_1, reg);
reg = HDMI_READ(HDMI_GCP_CONFIG);
- reg &= ~VC5_HDMI_GCP_CONFIG_GCP_ENABLE;
- reg |= gcp_en ? VC5_HDMI_GCP_CONFIG_GCP_ENABLE : 0;
+ reg |= VC5_HDMI_GCP_CONFIG_GCP_ENABLE;
HDMI_WRITE(HDMI_GCP_CONFIG, reg);
reg = HDMI_READ(HDMI_MISC_CONTROL);
}
vc4_hdmi->cec_adap = cec_allocate_adapter(&vc4_hdmi_cec_adap_ops,
- vc4_hdmi, "vc4",
+ vc4_hdmi,
+ vc4_hdmi->variant->card_name,
CEC_CAP_DEFAULTS |
CEC_CAP_CONNECTOR_INFO, 1);
ret = PTR_ERR_OR_ZERO(vc4_hdmi->cec_adap);
{
struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
struct drm_framebuffer *fb = state->fb;
- struct drm_gem_dma_object *bo = drm_fb_dma_get_gem_obj(fb, 0);
+ struct drm_gem_dma_object *bo;
int num_planes = fb->format->num_planes;
struct drm_crtc_state *crtc_state;
u32 h_subsample = fb->format->hsub;
if (ret)
return ret;
- for (i = 0; i < num_planes; i++)
+ for (i = 0; i < num_planes; i++) {
+ bo = drm_fb_dma_get_gem_obj(fb, i);
vc4_state->offsets[i] = bo->dma_addr + fb->offsets[i];
+ }
/*
* We don't support subpixel source positioning for scaling,
void __user *user_bo_handles = NULL;
struct virtio_gpu_object_array *buflist = NULL;
struct sync_file *sync_file;
- int in_fence_fd = exbuf->fence_fd;
int out_fence_fd = -1;
void *buf;
uint64_t fence_ctx;
ring_idx = exbuf->ring_idx;
}
- exbuf->fence_fd = -1;
-
virtio_gpu_create_context(dev, file);
if (exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_IN) {
struct dma_fence *in_fence;
- in_fence = sync_file_get_fence(in_fence_fd);
+ in_fence = sync_file_get_fence(exbuf->fence_fd);
if (!in_fence)
return -EINVAL;
drm_gem_object_release(obj);
return ret;
}
- drm_gem_object_put(obj);
rc->res_handle = qobj->hw_res_handle; /* similiar to a VM address */
rc->bo_handle = handle;
+
+ /*
+ * The handle owns the reference now. But we must drop our
+ * remaining reference *after* we no longer need to dereference
+ * the obj. Otherwise userspace could guess the handle and
+ * race closing it from another thread.
+ */
+ drm_gem_object_put(obj);
+
return 0;
}
drm_gem_object_release(obj);
return ret;
}
- drm_gem_object_put(obj);
rc_blob->res_handle = bo->hw_res_handle;
rc_blob->bo_handle = handle;
+ /*
+ * The handle owns the reference now. But we must drop our
+ * remaining reference *after* we no longer need to dereference
+ * the obj. Otherwise userspace could guess the handle and
+ * race closing it from another thread.
+ */
+ drm_gem_object_put(obj);
+
return 0;
}
struct virtio_gpu_object_array *objs = NULL;
struct drm_gem_shmem_object *shmem_obj;
struct virtio_gpu_object *bo;
- struct virtio_gpu_mem_entry *ents;
+ struct virtio_gpu_mem_entry *ents = NULL;
unsigned int nents;
int ret;
ret = -ENOMEM;
objs = virtio_gpu_array_alloc(1);
if (!objs)
- goto err_put_id;
+ goto err_free_entry;
virtio_gpu_array_add_obj(objs, &bo->base.base);
ret = virtio_gpu_array_lock_resv(objs);
err_put_objs:
virtio_gpu_array_put_free(objs);
+err_free_entry:
+ kvfree(ents);
err_put_id:
virtio_gpu_resource_id_put(vgdev, bo->hw_res_handle);
err_free_gem:
kref_put(&base->refcount, ttm_release_base);
}
-/**
- * ttm_base_object_noref_lookup - look up a base object without reference
- * @tfile: The struct ttm_object_file the object is registered with.
- * @key: The object handle.
- *
- * This function looks up a ttm base object and returns a pointer to it
- * without refcounting the pointer. The returned pointer is only valid
- * until ttm_base_object_noref_release() is called, and the object
- * pointed to by the returned pointer may be doomed. Any persistent usage
- * of the object requires a refcount to be taken using kref_get_unless_zero().
- * Iff this function returns successfully it needs to be paired with
- * ttm_base_object_noref_release() and no sleeping- or scheduling functions
- * may be called inbetween these function callse.
- *
- * Return: A pointer to the object if successful or NULL otherwise.
- */
-struct ttm_base_object *
-ttm_base_object_noref_lookup(struct ttm_object_file *tfile, uint64_t key)
-{
- struct vmwgfx_hash_item *hash;
- int ret;
-
- rcu_read_lock();
- ret = ttm_tfile_find_ref_rcu(tfile, key, &hash);
- if (ret) {
- rcu_read_unlock();
- return NULL;
- }
-
- __release(RCU);
- return hlist_entry(hash, struct ttm_ref_object, hash)->obj;
-}
-EXPORT_SYMBOL(ttm_base_object_noref_lookup);
-
struct ttm_base_object *ttm_base_object_lookup(struct ttm_object_file *tfile,
uint64_t key)
{
struct vmwgfx_hash_item *hash;
int ret;
- rcu_read_lock();
- ret = ttm_tfile_find_ref_rcu(tfile, key, &hash);
+ spin_lock(&tfile->lock);
+ ret = ttm_tfile_find_ref(tfile, key, &hash);
if (likely(ret == 0)) {
base = hlist_entry(hash, struct ttm_ref_object, hash)->obj;
if (!kref_get_unless_zero(&base->refcount))
base = NULL;
}
- rcu_read_unlock();
+ spin_unlock(&tfile->lock);
+
return base;
}
#define ttm_prime_object_kfree(__obj, __prime) \
kfree_rcu(__obj, __prime.base.rhead)
-struct ttm_base_object *
-ttm_base_object_noref_lookup(struct ttm_object_file *tfile, uint64_t key);
-
-/**
- * ttm_base_object_noref_release - release a base object pointer looked up
- * without reference
- *
- * Releases a base object pointer looked up with ttm_base_object_noref_lookup().
- */
-static inline void ttm_base_object_noref_release(void)
-{
- __acquire(RCU);
- rcu_read_unlock();
-}
#endif
return -ENOMEM;
}
+ /*
+ * vmw_bo_init will delete the *p_bo object if it fails
+ */
ret = vmw_bo_init(vmw, *p_bo, size,
placement, interruptible, pin,
bo_free);
return ret;
out_error:
- kfree(*p_bo);
*p_bo = NULL;
return ret;
}
ttm_bo_put(&vmw_bo->base);
}
+ drm_gem_object_put(&vmw_bo->base.base);
return ret;
}
ret = vmw_user_bo_synccpu_grab(vbo, arg->flags);
vmw_bo_unreference(&vbo);
+ drm_gem_object_put(&vbo->base.base);
if (unlikely(ret != 0)) {
if (ret == -ERESTARTSYS || ret == -EBUSY)
return -EBUSY;
* struct vmw_buffer_object should be placed.
* Return: Zero on success, Negative error code on error.
*
- * The vmw buffer object pointer will be refcounted.
+ * The vmw buffer object pointer will be refcounted (both ttm and gem)
*/
int vmw_user_bo_lookup(struct drm_file *filp,
uint32_t handle,
*out = gem_to_vmw_bo(gobj);
ttm_bo_get(&(*out)->base);
- drm_gem_object_put(gobj);
return 0;
}
-/**
- * vmw_user_bo_noref_lookup - Look up a vmw user buffer object without reference
- * @filp: The TTM object file the handle is registered with.
- * @handle: The user buffer object handle.
- *
- * This function looks up a struct vmw_bo and returns a pointer to the
- * struct vmw_buffer_object it derives from without refcounting the pointer.
- * The returned pointer is only valid until vmw_user_bo_noref_release() is
- * called, and the object pointed to by the returned pointer may be doomed.
- * Any persistent usage of the object requires a refcount to be taken using
- * ttm_bo_reference_unless_doomed(). Iff this function returns successfully it
- * needs to be paired with vmw_user_bo_noref_release() and no sleeping-
- * or scheduling functions may be called in between these function calls.
- *
- * Return: A struct vmw_buffer_object pointer if successful or negative
- * error pointer on failure.
- */
-struct vmw_buffer_object *
-vmw_user_bo_noref_lookup(struct drm_file *filp, u32 handle)
-{
- struct vmw_buffer_object *vmw_bo;
- struct ttm_buffer_object *bo;
- struct drm_gem_object *gobj = drm_gem_object_lookup(filp, handle);
-
- if (!gobj) {
- DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
- (unsigned long)handle);
- return ERR_PTR(-ESRCH);
- }
- vmw_bo = gem_to_vmw_bo(gobj);
- bo = ttm_bo_get_unless_zero(&vmw_bo->base);
- vmw_bo = vmw_buffer_object(bo);
- drm_gem_object_put(gobj);
-
- return vmw_bo;
-}
-
-
/**
* vmw_bo_fence_single - Utility function to fence a single TTM buffer
* object without unreserving it.
ret = vmw_gem_object_create_with_handle(dev_priv, file_priv,
args->size, &args->handle,
&vbo);
-
+ /* drop reference from allocate - handle holds it now */
+ drm_gem_object_put(&vbo->base.base);
return ret;
}
uint32_t handle,
const struct vmw_user_resource_conv *converter,
struct vmw_resource **p_res);
-extern struct vmw_resource *
-vmw_user_resource_noref_lookup_handle(struct vmw_private *dev_priv,
- struct ttm_object_file *tfile,
- uint32_t handle,
- const struct vmw_user_resource_conv *
- converter);
+
extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
return !RB_EMPTY_NODE(&res->mob_node);
}
-/**
- * vmw_user_resource_noref_release - release a user resource pointer looked up
- * without reference
- */
-static inline void vmw_user_resource_noref_release(void)
-{
- ttm_base_object_noref_release();
-}
-
/**
* Buffer object helper functions - vmwgfx_bo.c
*/
extern void vmw_bo_move_notify(struct ttm_buffer_object *bo,
struct ttm_resource *mem);
extern void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
-extern struct vmw_buffer_object *
-vmw_user_bo_noref_lookup(struct drm_file *filp, u32 handle);
/**
* vmw_bo_adjust_prio - Adjust the buffer object eviction priority
rcache->valid_handle = 0;
}
+enum vmw_val_add_flags {
+ vmw_val_add_flag_none = 0,
+ vmw_val_add_flag_noctx = 1 << 0,
+};
+
/**
- * vmw_execbuf_res_noref_val_add - Add a resource described by an unreferenced
- * rcu-protected pointer to the validation list.
+ * vmw_execbuf_res_val_add - Add a resource to the validation list.
*
* @sw_context: Pointer to the software context.
* @res: Unreferenced rcu-protected pointer to the resource.
* @dirty: Whether to change dirty status.
+ * @flags: specifies whether to use the context or not
*
* Returns: 0 on success. Negative error code on failure. Typical error codes
* are %-EINVAL on inconsistency and %-ESRCH if the resource was doomed.
*/
-static int vmw_execbuf_res_noref_val_add(struct vmw_sw_context *sw_context,
- struct vmw_resource *res,
- u32 dirty)
+static int vmw_execbuf_res_val_add(struct vmw_sw_context *sw_context,
+ struct vmw_resource *res,
+ u32 dirty,
+ u32 flags)
{
struct vmw_private *dev_priv = res->dev_priv;
int ret;
if (dirty)
vmw_validation_res_set_dirty(sw_context->ctx,
rcache->private, dirty);
- vmw_user_resource_noref_release();
return 0;
}
- priv_size = vmw_execbuf_res_size(dev_priv, res_type);
- ret = vmw_validation_add_resource(sw_context->ctx, res, priv_size,
- dirty, (void **)&ctx_info,
- &first_usage);
- vmw_user_resource_noref_release();
- if (ret)
- return ret;
+ if ((flags & vmw_val_add_flag_noctx) != 0) {
+ ret = vmw_validation_add_resource(sw_context->ctx, res, 0, dirty,
+ (void **)&ctx_info, NULL);
+ if (ret)
+ return ret;
- if (priv_size && first_usage) {
- ret = vmw_cmd_ctx_first_setup(dev_priv, sw_context, res,
- ctx_info);
- if (ret) {
- VMW_DEBUG_USER("Failed first usage context setup.\n");
+ } else {
+ priv_size = vmw_execbuf_res_size(dev_priv, res_type);
+ ret = vmw_validation_add_resource(sw_context->ctx, res, priv_size,
+ dirty, (void **)&ctx_info,
+ &first_usage);
+ if (ret)
return ret;
+
+ if (priv_size && first_usage) {
+ ret = vmw_cmd_ctx_first_setup(dev_priv, sw_context, res,
+ ctx_info);
+ if (ret) {
+ VMW_DEBUG_USER("Failed first usage context setup.\n");
+ return ret;
+ }
}
}
return 0;
}
-/**
- * vmw_execbuf_res_noctx_val_add - Add a non-context resource to the resource
- * validation list if it's not already on it
- *
- * @sw_context: Pointer to the software context.
- * @res: Pointer to the resource.
- * @dirty: Whether to change dirty status.
- *
- * Returns: Zero on success. Negative error code on failure.
- */
-static int vmw_execbuf_res_noctx_val_add(struct vmw_sw_context *sw_context,
- struct vmw_resource *res,
- u32 dirty)
-{
- struct vmw_res_cache_entry *rcache;
- enum vmw_res_type res_type = vmw_res_type(res);
- void *ptr;
- int ret;
-
- rcache = &sw_context->res_cache[res_type];
- if (likely(rcache->valid && rcache->res == res)) {
- if (dirty)
- vmw_validation_res_set_dirty(sw_context->ctx,
- rcache->private, dirty);
- return 0;
- }
-
- ret = vmw_validation_add_resource(sw_context->ctx, res, 0, dirty,
- &ptr, NULL);
- if (ret)
- return ret;
-
- vmw_execbuf_rcache_update(rcache, res, ptr);
-
- return 0;
-}
-
/**
* vmw_view_res_val_add - Add a view and the surface it's pointing to to the
* validation list
* First add the resource the view is pointing to, otherwise it may be
* swapped out when the view is validated.
*/
- ret = vmw_execbuf_res_noctx_val_add(sw_context, vmw_view_srf(view),
- vmw_view_dirtying(view));
+ ret = vmw_execbuf_res_val_add(sw_context, vmw_view_srf(view),
+ vmw_view_dirtying(view), vmw_val_add_flag_noctx);
if (ret)
return ret;
- return vmw_execbuf_res_noctx_val_add(sw_context, view,
- VMW_RES_DIRTY_NONE);
+ return vmw_execbuf_res_val_add(sw_context, view, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
}
/**
if (IS_ERR(res))
continue;
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_SET);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_SET,
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
return ret;
}
if (vmw_res_type(entry->res) == vmw_res_view)
ret = vmw_view_res_val_add(sw_context, entry->res);
else
- ret = vmw_execbuf_res_noctx_val_add
- (sw_context, entry->res,
- vmw_binding_dirtying(entry->bt));
+ ret = vmw_execbuf_res_val_add(sw_context, entry->res,
+ vmw_binding_dirtying(entry->bt),
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
break;
}
{
struct vmw_res_cache_entry *rcache = &sw_context->res_cache[res_type];
struct vmw_resource *res;
- int ret;
+ int ret = 0;
+ bool needs_unref = false;
if (p_res)
*p_res = NULL;
if (ret)
return ret;
- res = vmw_user_resource_noref_lookup_handle
- (dev_priv, sw_context->fp->tfile, *id_loc, converter);
- if (IS_ERR(res)) {
+ ret = vmw_user_resource_lookup_handle
+ (dev_priv, sw_context->fp->tfile, *id_loc, converter, &res);
+ if (ret != 0) {
VMW_DEBUG_USER("Could not find/use resource 0x%08x.\n",
(unsigned int) *id_loc);
- return PTR_ERR(res);
+ return ret;
}
+ needs_unref = true;
- ret = vmw_execbuf_res_noref_val_add(sw_context, res, dirty);
+ ret = vmw_execbuf_res_val_add(sw_context, res, dirty, vmw_val_add_flag_none);
if (unlikely(ret != 0))
- return ret;
+ goto res_check_done;
if (rcache->valid && rcache->res == res) {
rcache->valid_handle = true;
if (p_res)
*p_res = res;
- return 0;
+res_check_done:
+ if (needs_unref)
+ vmw_resource_unreference(&res);
+
+ return ret;
}
/**
int ret;
vmw_validation_preload_bo(sw_context->ctx);
- vmw_bo = vmw_user_bo_noref_lookup(sw_context->filp, handle);
- if (IS_ERR(vmw_bo)) {
- VMW_DEBUG_USER("Could not find or use MOB buffer.\n");
+ ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo);
+ if (ret != 0) {
+ drm_dbg(&dev_priv->drm, "Could not find or use MOB buffer.\n");
return PTR_ERR(vmw_bo);
}
ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, true, false);
ttm_bo_put(&vmw_bo->base);
+ drm_gem_object_put(&vmw_bo->base.base);
if (unlikely(ret != 0))
return ret;
int ret;
vmw_validation_preload_bo(sw_context->ctx);
- vmw_bo = vmw_user_bo_noref_lookup(sw_context->filp, handle);
- if (IS_ERR(vmw_bo)) {
- VMW_DEBUG_USER("Could not find or use GMR region.\n");
+ ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo);
+ if (ret != 0) {
+ drm_dbg(&dev_priv->drm, "Could not find or use GMR region.\n");
return PTR_ERR(vmw_bo);
}
ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, false, false);
ttm_bo_put(&vmw_bo->base);
+ drm_gem_object_put(&vmw_bo->base.base);
if (unlikely(ret != 0))
return ret;
res = vmw_shader_lookup(vmw_context_res_man(ctx),
cmd->body.shid, cmd->body.type);
if (!IS_ERR(res)) {
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
return ret;
return PTR_ERR(res);
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret)
return ret;
}
return PTR_ERR(res);
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
VMW_DEBUG_USER("Error creating resource validation node.\n");
return ret;
vmw_dx_streamoutput_set_size(res, cmd->body.sizeInBytes);
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
DRM_ERROR("Error creating resource validation node.\n");
return ret;
return 0;
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
DRM_ERROR("Error creating resource validation node.\n");
return ret;
if (ret)
return ret;
- res = vmw_user_resource_noref_lookup_handle
+ ret = vmw_user_resource_lookup_handle
(dev_priv, sw_context->fp->tfile, handle,
- user_context_converter);
- if (IS_ERR(res)) {
+ user_context_converter, &res);
+ if (ret != 0) {
VMW_DEBUG_USER("Could not find or user DX context 0x%08x.\n",
(unsigned int) handle);
- return PTR_ERR(res);
+ return ret;
}
- ret = vmw_execbuf_res_noref_val_add(sw_context, res, VMW_RES_DIRTY_SET);
- if (unlikely(ret != 0))
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_SET,
+ vmw_val_add_flag_none);
+ if (unlikely(ret != 0)) {
+ vmw_resource_unreference(&res);
return ret;
+ }
sw_context->dx_ctx_node = vmw_execbuf_info_from_res(sw_context, res);
sw_context->man = vmw_context_res_man(res);
+ vmw_resource_unreference(&res);
return 0;
}
&vmw_sys_placement :
&vmw_vram_sys_placement,
true, false, &vmw_gem_destroy, p_vbo);
-
- (*p_vbo)->base.base.funcs = &vmw_gem_object_funcs;
if (ret != 0)
goto out_no_bo;
+ (*p_vbo)->base.base.funcs = &vmw_gem_object_funcs;
+
ret = drm_gem_handle_create(filp, &(*p_vbo)->base.base, handle);
- /* drop reference from allocate - handle holds it now */
- drm_gem_object_put(&(*p_vbo)->base.base);
out_no_bo:
return ret;
}
rep->map_handle = drm_vma_node_offset_addr(&vbo->base.base.vma_node);
rep->cur_gmr_id = handle;
rep->cur_gmr_offset = 0;
+ /* drop reference from allocate - handle holds it now */
+ drm_gem_object_put(&vbo->base.base);
out_no_bo:
return ret;
}
err_out:
/* vmw_user_lookup_handle takes one ref so does new_fb */
- if (bo)
+ if (bo) {
vmw_bo_unreference(&bo);
+ drm_gem_object_put(&bo->base.base);
+ }
if (surface)
vmw_surface_unreference(&surface);
ret = vmw_overlay_update_stream(dev_priv, buf, arg, true);
vmw_bo_unreference(&buf);
+ drm_gem_object_put(&buf->base.base);
out_unlock:
mutex_unlock(&overlay->mutex);
return ret;
}
-/**
- * vmw_user_resource_noref_lookup_handle - lookup a struct resource from a
- * TTM user-space handle and perform basic type checks
- *
- * @dev_priv: Pointer to a device private struct
- * @tfile: Pointer to a struct ttm_object_file identifying the caller
- * @handle: The TTM user-space handle
- * @converter: Pointer to an object describing the resource type
- *
- * If the handle can't be found or is associated with an incorrect resource
- * type, -EINVAL will be returned.
- */
-struct vmw_resource *
-vmw_user_resource_noref_lookup_handle(struct vmw_private *dev_priv,
- struct ttm_object_file *tfile,
- uint32_t handle,
- const struct vmw_user_resource_conv
- *converter)
-{
- struct ttm_base_object *base;
-
- base = ttm_base_object_noref_lookup(tfile, handle);
- if (!base)
- return ERR_PTR(-ESRCH);
-
- if (unlikely(ttm_base_object_type(base) != converter->object_type)) {
- ttm_base_object_noref_release();
- return ERR_PTR(-EINVAL);
- }
-
- return converter->base_obj_to_res(base);
-}
-
/*
* Helper function that looks either a surface or bo.
*
num_output_sig, tfile, shader_handle);
out_bad_arg:
vmw_bo_unreference(&buffer);
+ drm_gem_object_put(&buffer->base.base);
return ret;
}
container_of(base, struct vmw_user_surface, prime.base);
struct vmw_resource *res = &user_srf->srf.res;
- if (base->shareable && res && res->backup)
+ if (res && res->backup)
drm_gem_object_put(&res->backup->base.base);
*p_base = NULL;
goto out_unlock;
}
vmw_bo_reference(res->backup);
- drm_gem_object_get(&res->backup->base.base);
+ /*
+ * We don't expose the handle to the userspace and surface
+ * already holds a gem reference
+ */
+ drm_gem_handle_delete(file_priv, backup_handle);
}
tmp = vmw_resource_reference(&srf->res);
drm_vma_node_offset_addr(&res->backup->base.base.vma_node);
rep->buffer_size = res->backup->base.base.size;
rep->buffer_handle = backup_handle;
- if (user_srf->prime.base.shareable)
- drm_gem_object_get(&res->backup->base.base);
} else {
rep->buffer_map_handle = 0;
rep->buffer_size = 0;
return xenbus_switch_state(xb_dev, XenbusStateInitialising);
}
-static int xen_drv_remove(struct xenbus_device *dev)
+static void xen_drv_remove(struct xenbus_device *dev)
{
struct xen_drm_front_info *front_info = dev_get_drvdata(&dev->dev);
int to = 100;
xen_drm_drv_fini(front_info);
xenbus_frontend_closed(dev);
- return 0;
}
static const struct xenbus_device_id xen_driver_ids[] = {
cl_data->num_hid_devices = amd_mp2_get_sensor_num(privdata, &cl_data->sensor_idx[0]);
if (cl_data->num_hid_devices == 0)
return -ENODEV;
+ cl_data->is_any_sensor_enabled = false;
INIT_DELAYED_WORK(&cl_data->work, amd_sfh_work);
INIT_DELAYED_WORK(&cl_data->work_buffer, amd_sfh_work_buffer);
}
rc = mp2_ops->get_rep_desc(cl_idx, cl_data->report_descr[i]);
if (rc)
- return rc;
+ goto cleanup;
mp2_ops->start(privdata, info);
status = amd_sfh_wait_for_response
(privdata, cl_data->sensor_idx[i], SENSOR_ENABLED);
if (status == SENSOR_ENABLED) {
+ cl_data->is_any_sensor_enabled = true;
cl_data->sensor_sts[i] = SENSOR_ENABLED;
rc = amdtp_hid_probe(cl_data->cur_hid_dev, cl_data);
if (rc) {
cl_data->sensor_sts[i]);
goto cleanup;
}
+ } else {
+ cl_data->sensor_sts[i] = SENSOR_DISABLED;
+ dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n",
+ cl_data->sensor_idx[i],
+ get_sensor_name(cl_data->sensor_idx[i]),
+ cl_data->sensor_sts[i]);
}
dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n",
cl_data->sensor_idx[i], get_sensor_name(cl_data->sensor_idx[i]),
cl_data->sensor_sts[i]);
}
- if (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0) {
+ if (!cl_data->is_any_sensor_enabled ||
+ (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) {
amd_sfh_hid_client_deinit(privdata);
for (i = 0; i < cl_data->num_hid_devices; i++) {
devm_kfree(dev, cl_data->feature_report[i]);
devm_kfree(dev, in_data->input_report[i]);
devm_kfree(dev, cl_data->report_descr[i]);
}
- dev_warn(dev, "Failed to discover, sensors not enabled\n");
+ dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", cl_data->is_any_sensor_enabled);
return -EOPNOTSUPP;
}
schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP));
struct amdtp_cl_data {
u8 init_done;
u32 cur_hid_dev;
+ bool is_any_sensor_enabled;
u32 hid_dev_count;
u32 num_hid_devices;
struct device_info *hid_devices;
}
rc = mp2_ops->get_rep_desc(cl_idx, cl_data->report_descr[i]);
if (rc)
- return rc;
+ goto cleanup;
writel(0, privdata->mmio + AMD_P2C_MSG(0));
mp2_ops->start(privdata, info);
struct list_head *report_list =
&hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct input_dev *dev;
- int field_count = 0;
int error;
int i, j;
* -----------------------------------------
* Do init them with default value.
*/
+ if (report->maxfield < 4) {
+ hid_err(hid, "not enough fields in the report: %d\n",
+ report->maxfield);
+ return -ENODEV;
+ }
for (i = 0; i < report->maxfield; i++) {
+ if (report->field[i]->report_count < 1) {
+ hid_err(hid, "no values in the field\n");
+ return -ENODEV;
+ }
for (j = 0; j < report->field[i]->report_count; j++) {
report->field[i]->value[j] = 0x00;
- field_count++;
}
}
- if (field_count < 4) {
- hid_err(hid, "not enough fields in the report: %d\n",
- field_count);
- return -ENODEV;
- }
-
betopff = kzalloc(sizeof(*betopff), GFP_KERNEL);
if (!betopff)
return -ENOMEM;
}
report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
+ if (list_empty(report_list)) {
+ hid_err(hid, "no output report found\n");
+ error = -ENODEV;
+ goto error_hw_stop;
+ }
bigben->report = list_entry(report_list->next,
struct hid_report, list);
* Validating on id 0 means we should examine the first
* report in the list.
*/
- report = list_entry(
- hid->report_enum[type].report_list.next,
+ report = list_first_entry_or_null(
+ &hid->report_enum[type].report_list,
struct hid_report, list);
} else {
report = hid->report_enum[type].report_id_hash[id];
__u8 *end;
__u8 *next;
int ret;
+ int i;
static int (*dispatch_type[])(struct hid_parser *parser,
struct hid_item *item) = {
hid_parser_main,
goto err;
}
device->collection_size = HID_DEFAULT_NUM_COLLECTIONS;
+ for (i = 0; i < HID_DEFAULT_NUM_COLLECTIONS; i++)
+ device->collection[i].parent_idx = -1;
ret = -EINVAL;
while ((next = fetch_item(start, end, &item)) != NULL) {
* Copyright (c) 2017 Alex Manoussakis <amanou@gnu.org>
* Copyright (c) 2017 Tomasz Kramkowski <tk@the-tk.com>
* Copyright (c) 2020 YOSHIOKA Takuma <lo48576@hard-wi.red>
+ * Copyright (c) 2022 Takahiro Fujii <fujii@xaxxi.net>
*/
/*
case USB_DEVICE_ID_ELECOM_M_DT1URBK:
case USB_DEVICE_ID_ELECOM_M_DT1DRBK:
case USB_DEVICE_ID_ELECOM_M_HT1URBK:
- case USB_DEVICE_ID_ELECOM_M_HT1DRBK:
+ case USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D:
/*
* Report descriptor format:
* 12: button bit count
*/
mouse_button_fixup(hdev, rdesc, *rsize, 12, 30, 14, 20, 8);
break;
+ case USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C:
+ /*
+ * Report descriptor format:
+ * 22: button bit count
+ * 30: padding bit count
+ * 24: button report size
+ * 16: button usage maximum
+ */
+ mouse_button_fixup(hdev, rdesc, *rsize, 22, 30, 24, 16, 8);
+ break;
}
return rdesc;
}
{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK) },
- { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C) },
{ }
};
MODULE_DEVICE_TABLE(hid, elecom_devices);
#define USB_DEVICE_ID_CH_AXIS_295 0x001c
#define USB_VENDOR_ID_CHERRY 0x046a
-#define USB_DEVICE_ID_CHERRY_MOUSE_000C 0x000c
#define USB_DEVICE_ID_CHERRY_CYMOTION 0x0023
#define USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR 0x0027
#define I2C_DEVICE_ID_HP_ENVY_X360_15T_DR100 0x29CF
#define I2C_DEVICE_ID_HP_ENVY_X360_EU0009NV 0x2CF9
#define I2C_DEVICE_ID_HP_SPECTRE_X360_15 0x2817
+#define I2C_DEVICE_ID_HP_SPECTRE_X360_13_AW0020NG 0x29DF
+#define I2C_DEVICE_ID_ASUS_TP420IA_TOUCHSCREEN 0x2BC8
#define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN 0x2544
#define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706
#define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A
#define USB_DEVICE_ID_ELECOM_M_DT1URBK 0x00fe
#define USB_DEVICE_ID_ELECOM_M_DT1DRBK 0x00ff
#define USB_DEVICE_ID_ELECOM_M_HT1URBK 0x010c
-#define USB_DEVICE_ID_ELECOM_M_HT1DRBK 0x010d
+#define USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D 0x010d
+#define USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C 0x011c
#define USB_VENDOR_ID_DREAM_CHEEKY 0x1d34
#define USB_DEVICE_ID_DREAM_CHEEKY_WN 0x0004
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540 0x0075
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640 0x0094
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01 0x0042
+#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2 0x0905
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L 0x0935
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_S 0x0909
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_STAR06 0x0078
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH,
USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD),
HID_BATTERY_QUIRK_IGNORE },
+ { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_TP420IA_TOUCHSCREEN),
+ HID_BATTERY_QUIRK_IGNORE },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN),
HID_BATTERY_QUIRK_IGNORE },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN),
HID_BATTERY_QUIRK_IGNORE },
{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15),
HID_BATTERY_QUIRK_IGNORE },
+ { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_13_AW0020NG),
+ HID_BATTERY_QUIRK_IGNORE },
{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN),
HID_BATTERY_QUIRK_IGNORE },
{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN),
}
hidpp_initialize_battery(hidpp);
- hidpp_initialize_hires_scroll(hidpp);
+ if (!hid_is_usb(hidpp->hid_dev))
+ hidpp_initialize_hires_scroll(hidpp);
/* forward current battery state */
if (hidpp->capabilities & HIDPP_CAPABILITY_HIDPP10_BATTERY) {
static int dualsense_get_calibration_data(struct dualsense *ds)
{
+ struct hid_device *hdev = ds->base.hdev;
short gyro_pitch_bias, gyro_pitch_plus, gyro_pitch_minus;
short gyro_yaw_bias, gyro_yaw_plus, gyro_yaw_minus;
short gyro_roll_bias, gyro_roll_plus, gyro_roll_minus;
int speed_2x;
int range_2g;
int ret = 0;
+ int i;
uint8_t *buf;
buf = kzalloc(DS_FEATURE_REPORT_CALIBRATION_SIZE, GFP_KERNEL);
ds->gyro_calib_data[2].sens_numer = speed_2x*DS_GYRO_RES_PER_DEG_S;
ds->gyro_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus;
+ /*
+ * Sanity check gyro calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing
+ * calibration data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds->gyro_calib_data); i++) {
+ if (ds->gyro_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.",
+ ds->gyro_calib_data[i].abs_code);
+ ds->gyro_calib_data[i].bias = 0;
+ ds->gyro_calib_data[i].sens_numer = DS_GYRO_RANGE;
+ ds->gyro_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
/*
* Set accelerometer calibration and normalization parameters.
* Data values will be normalized to 1/DS_ACC_RES_PER_G g.
ds->accel_calib_data[2].sens_numer = 2*DS_ACC_RES_PER_G;
ds->accel_calib_data[2].sens_denom = range_2g;
+ /*
+ * Sanity check accelerometer calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing calibration
+ * data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds->accel_calib_data); i++) {
+ if (ds->accel_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.",
+ ds->accel_calib_data[i].abs_code);
+ ds->accel_calib_data[i].bias = 0;
+ ds->accel_calib_data[i].sens_numer = DS_ACC_RANGE;
+ ds->accel_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
err_free:
kfree(buf);
return ret;
int speed_2x;
int range_2g;
int ret = 0;
+ int i;
uint8_t *buf;
if (ds4->base.hdev->bus == BUS_USB) {
ds4->gyro_calib_data[2].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S;
ds4->gyro_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus;
+ /*
+ * Sanity check gyro calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing
+ * calibration data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds4->gyro_calib_data); i++) {
+ if (ds4->gyro_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.",
+ ds4->gyro_calib_data[i].abs_code);
+ ds4->gyro_calib_data[i].bias = 0;
+ ds4->gyro_calib_data[i].sens_numer = DS4_GYRO_RANGE;
+ ds4->gyro_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
/*
* Set accelerometer calibration and normalization parameters.
* Data values will be normalized to 1/DS4_ACC_RES_PER_G g.
ds4->accel_calib_data[2].sens_numer = 2*DS4_ACC_RES_PER_G;
ds4->accel_calib_data[2].sens_denom = range_2g;
+ /*
+ * Sanity check accelerometer calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing calibration
+ * data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds4->accel_calib_data); i++) {
+ if (ds4->accel_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.",
+ ds4->accel_calib_data[i].abs_code);
+ ds4->accel_calib_data[i].bias = 0;
+ ds4->accel_calib_data[i].sens_numer = DS4_ACC_RANGE;
+ ds4->accel_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
err_free:
kfree(buf);
return ret;
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_YOKE), HID_QUIRK_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS), HID_QUIRK_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_THROTTLE), HID_QUIRK_NOGET },
- { HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_MOUSE_000C), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK) },
- { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C) },
#endif
#if IS_ENABLED(CONFIG_HID_ELO)
{ HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009) },
USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
+ USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
break;
case VID_PID(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_PARBLO_A610_PRO):
+ case VID_PID(USB_VENDOR_ID_UGEE,
+ USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2):
case VID_PID(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L):
case VID_PID(USB_VENDOR_ID_UGEE,
int required_slots = (size / DMA_SLOT_SIZE)
+ 1 * (size % DMA_SLOT_SIZE != 0);
+ if (!dev->ishtp_dma_tx_map) {
+ dev_err(dev->devc, "Fail to allocate Tx map\n");
+ return NULL;
+ }
+
spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags);
for (i = 0; i <= (dev->ishtp_dma_num_slots - required_slots); i++) {
free = 1;
return;
}
+ if (!dev->ishtp_dma_tx_map) {
+ dev_err(dev->devc, "Fail to allocate Tx map\n");
+ return;
+ }
+
i = (msg_addr - dev->ishtp_host_dma_tx_buf) / DMA_SLOT_SIZE;
spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags);
for (j = 0; j < acked_slots; j++) {
static void hv_balloon_debugfs_exit(struct hv_dynmem_device *b)
{
- debugfs_remove(debugfs_lookup("hv-balloon", NULL));
+ debugfs_lookup_and_remove("hv-balloon", NULL);
}
#else
#define SDA_HOLD_TIME 0x90
/**
- * axxia_i2c_dev - I2C device context
+ * struct axxia_i2c_dev - I2C device context
* @base: pointer to register struct
* @msg: pointer to current message
* @msg_r: pointer to current read message (sequence transfer)
*
* If your hardware is free from tHD;STA issue, try this one.
*/
- return DIV_ROUND_CLOSEST(ic_clk * tSYMBOL, MICRO) - 8 + offset;
+ return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * tSYMBOL, MICRO) -
+ 8 + offset;
else
/*
* Conditional expression:
* The reason why we need to take into account "tf" here,
* is the same as described in i2c_dw_scl_lcnt().
*/
- return DIV_ROUND_CLOSEST(ic_clk * (tSYMBOL + tf), MICRO) - 3 + offset;
+ return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tSYMBOL + tf), MICRO) -
+ 3 + offset;
}
u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset)
* account the fall time of SCL signal (tf). Default tf value
* should be 0.3 us, for safety.
*/
- return DIV_ROUND_CLOSEST(ic_clk * (tLOW + tf), MICRO) - 1 + offset;
+ return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tLOW + tf), MICRO) -
+ 1 + offset;
}
int i2c_dw_set_sda_hold(struct dw_i2c_dev *dev)
{ PCI_VDEVICE(ATI, 0x73a4), navi_amd },
{ PCI_VDEVICE(ATI, 0x73e4), navi_amd },
{ PCI_VDEVICE(ATI, 0x73c4), navi_amd },
+ { PCI_VDEVICE(ATI, 0x7444), navi_amd },
+ { PCI_VDEVICE(ATI, 0x7464), navi_amd },
{ 0,}
};
MODULE_DEVICE_TABLE(pci, i2_designware_pci_ids);
if (dev->flags & ACCESS_NO_IRQ_SUSPEND) {
dev_pm_set_driver_flags(&pdev->dev,
- DPM_FLAG_SMART_PREPARE |
- DPM_FLAG_MAY_SKIP_RESUME);
+ DPM_FLAG_SMART_PREPARE);
} else {
dev_pm_set_driver_flags(&pdev->dev,
DPM_FLAG_SMART_PREPARE |
- DPM_FLAG_SMART_SUSPEND |
- DPM_FLAG_MAY_SKIP_RESUME);
+ DPM_FLAG_SMART_SUSPEND);
}
device_enable_async_suspend(&pdev->dev);
*/
return !has_acpi_companion(dev);
}
-
-static void dw_i2c_plat_complete(struct device *dev)
-{
- /*
- * The device can only be in runtime suspend at this point if it has not
- * been resumed throughout the ending system suspend/resume cycle, so if
- * the platform firmware might mess up with it, request the runtime PM
- * framework to resume it.
- */
- if (pm_runtime_suspended(dev) && pm_resume_via_firmware())
- pm_request_resume(dev);
-}
#else
#define dw_i2c_plat_prepare NULL
-#define dw_i2c_plat_complete NULL
#endif
#ifdef CONFIG_PM
static const struct dev_pm_ops dw_i2c_dev_pm_ops = {
.prepare = dw_i2c_plat_prepare,
- .complete = dw_i2c_plat_complete,
SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume)
SET_RUNTIME_PM_OPS(dw_i2c_plat_runtime_suspend, dw_i2c_plat_runtime_resume, NULL)
};
/* Setup the DMA */
i2c->dmach = dma_request_chan(dev, "rx-tx");
if (IS_ERR(i2c->dmach)) {
- dev_err(dev, "Failed to request dma\n");
- return PTR_ERR(i2c->dmach);
+ return dev_err_probe(dev, PTR_ERR(i2c->dmach),
+ "Failed to request dma\n");
}
platform_set_drvdata(pdev, i2c);
#define DEFAULT_SCL_RATE (100 * 1000) /* Hz */
/**
- * struct i2c_spec_values:
+ * struct i2c_spec_values - I2C specification values for various modes
* @min_hold_start_ns: min hold time (repeated) START condition
* @min_low_ns: min LOW period of the SCL clock
* @min_high_ns: min HIGH period of the SCL cloc
};
/**
- * struct rk3x_i2c_calced_timings:
+ * struct rk3x_i2c_calced_timings - calculated V1 timings
* @div_low: Divider output for low
* @div_high: Divider output for high
* @tuning: Used to adjust setup/hold data time,
};
/**
- * struct rk3x_i2c_soc_data:
+ * struct rk3x_i2c_soc_data - SOC-specific data
* @grf_offset: offset inside the grf regmap for setting the i2c type
* @calc_timings: Callback function for i2c timing information calculated
*/
}
/**
- * Generate a START condition, which triggers a REG_INT_START interrupt.
+ * rk3x_i2c_start - Generate a START condition, which triggers a REG_INT_START interrupt.
+ * @i2c: target controller data
*/
static void rk3x_i2c_start(struct rk3x_i2c *i2c)
{
}
/**
- * Generate a STOP condition, which triggers a REG_INT_STOP interrupt.
- *
+ * rk3x_i2c_stop - Generate a STOP condition, which triggers a REG_INT_STOP interrupt.
+ * @i2c: target controller data
* @error: Error code to return in rk3x_i2c_xfer
*/
static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error)
}
/**
- * Setup a read according to i2c->msg
+ * rk3x_i2c_prepare_read - Setup a read according to i2c->msg
+ * @i2c: target controller data
*/
static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c)
{
}
/**
- * Fill the transmit buffer with data from i2c->msg
+ * rk3x_i2c_fill_transmit_buf - Fill the transmit buffer with data from i2c->msg
+ * @i2c: target controller data
*/
static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c)
{
}
/**
- * Get timing values of I2C specification
- *
+ * rk3x_i2c_get_spec - Get timing values of I2C specification
* @speed: Desired SCL frequency
*
- * Returns: Matched i2c spec values.
+ * Return: Matched i2c_spec_values.
*/
static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed)
{
}
/**
- * Calculate divider values for desired SCL frequency
- *
+ * rk3x_i2c_v0_calc_timings - Calculate divider values for desired SCL frequency
* @clk_rate: I2C input clock rate
* @t: Known I2C timing information
* @t_calc: Caculated rk3x private timings that would be written into regs
*
- * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case
+ * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case
* a best-effort divider value is returned in divs. If the target rate is
* too high, we silently use the highest possible rate.
*/
}
/**
- * Calculate timing values for desired SCL frequency
- *
+ * rk3x_i2c_v1_calc_timings - Calculate timing values for desired SCL frequency
* @clk_rate: I2C input clock rate
* @t: Known I2C timing information
* @t_calc: Caculated rk3x private timings that would be written into regs
*
- * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case
+ * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case
* a best-effort divider value is returned in divs. If the target rate is
* too high, we silently use the highest possible rate.
* The following formulas are v1's method to calculate timings.
}
/**
- * Setup I2C registers for an I2C operation specified by msgs, num.
- *
- * Must be called with i2c->lock held.
- *
+ * rk3x_i2c_setup - Setup I2C registers for an I2C operation specified by msgs, num.
+ * @i2c: target controller data
* @msgs: I2C msgs to process
* @num: Number of msgs
*
- * returns: Number of I2C msgs processed or negative in case of error
+ * Must be called with i2c->lock held.
+ *
+ * Return: Number of I2C msgs processed or negative in case of error
*/
static int rk3x_i2c_setup(struct rk3x_i2c *i2c, struct i2c_msg *msgs, int num)
{
hid_sensor_convert_timestamp(
&accel_state->common_attributes,
*(int64_t *)raw_data);
+ ret = 0;
break;
default:
break;
int ret;
indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*priv));
- if (!indio_dev)
+ if (!indio_dev) {
+ of_node_put(parent_np);
return -ENOMEM;
+ }
priv = iio_priv(indio_dev);
#define IMX8QXP_ADC_TIMEOUT msecs_to_jiffies(100)
+#define IMX8QXP_ADC_MAX_FIFO_SIZE 16
+
struct imx8qxp_adc {
struct device *dev;
void __iomem *regs;
/* Serialise ADC channel reads */
struct mutex lock;
struct completion completion;
+ u32 fifo[IMX8QXP_ADC_MAX_FIFO_SIZE];
};
#define IMX8QXP_ADC_CHAN(_idx) { \
return ret;
}
- *val = FIELD_GET(IMX8QXP_ADC_RESFIFO_VAL_MASK,
- readl(adc->regs + IMX8QXP_ADR_ADC_RESFIFO));
+ *val = adc->fifo[0];
mutex_unlock(&adc->lock);
return IIO_VAL_INT;
{
struct imx8qxp_adc *adc = dev_id;
u32 fifo_count;
+ int i;
fifo_count = FIELD_GET(IMX8QXP_ADC_FCTRL_FCOUNT_MASK,
readl(adc->regs + IMX8QXP_ADR_ADC_FCTRL));
+ for (i = 0; i < fifo_count; i++)
+ adc->fifo[i] = FIELD_GET(IMX8QXP_ADC_RESFIFO_VAL_MASK,
+ readl_relaxed(adc->regs + IMX8QXP_ADR_ADC_RESFIFO));
+
if (fifo_count)
complete(&adc->completion);
},
{}
};
+MODULE_DEVICE_TABLE(of, stm32_dfsdm_adc_match);
static int stm32_dfsdm_adc_probe(struct platform_device *pdev)
{
#define TWL6030_GPADCS BIT(1)
#define TWL6030_GPADCR BIT(0)
+#define USB_VBUS_CTRL_SET 0x04
+#define USB_ID_CTRL_SET 0x06
+
+#define TWL6030_MISC1 0xE4
+#define VBUS_MEAS 0x01
+#define ID_MEAS 0x01
+
+#define VAC_MEAS 0x04
+#define VBAT_MEAS 0x02
+#define BB_MEAS 0x01
+
+
/**
* struct twl6030_chnl_calib - channel calibration
* @gain: slope coefficient for ideal curve
return ret;
}
+ ret = twl_i2c_write_u8(TWL_MODULE_USB, VBUS_MEAS, USB_VBUS_CTRL_SET);
+ if (ret < 0) {
+ dev_err(dev, "failed to wire up inputs\n");
+ return ret;
+ }
+
+ ret = twl_i2c_write_u8(TWL_MODULE_USB, ID_MEAS, USB_ID_CTRL_SET);
+ if (ret < 0) {
+ dev_err(dev, "failed to wire up inputs\n");
+ return ret;
+ }
+
+ ret = twl_i2c_write_u8(TWL6030_MODULE_ID0,
+ VBAT_MEAS | BB_MEAS | VAC_MEAS,
+ TWL6030_MISC1);
+ if (ret < 0) {
+ dev_err(dev, "failed to wire up inputs\n");
+ return ret;
+ }
+
indio_dev->name = DRIVER_NAME;
indio_dev->info = &twl6030_gpadc_iio_info;
indio_dev->modes = INDIO_DIRECT_MODE;
dev_channels = devm_krealloc(dev, ams_channels, dev_size, GFP_KERNEL);
if (!dev_channels)
- ret = -ENOMEM;
+ return -ENOMEM;
indio_dev->channels = dev_channels;
indio_dev->num_channels = num_channels;
gyro_state->timestamp =
hid_sensor_convert_timestamp(&gyro_state->common_attributes,
*(s64 *)raw_data);
+ ret = 0;
break;
default:
break;
#include <linux/regmap.h>
#include <linux/acpi.h>
#include <linux/bitops.h>
+#include <linux/bitfield.h>
#include <linux/iio/iio.h>
#include <linux/iio/sysfs.h>
#define FXOS8700_NVM_DATA_BNK0 0xa7
/* Bit definitions for FXOS8700_CTRL_REG1 */
-#define FXOS8700_CTRL_ODR_MSK 0x38
#define FXOS8700_CTRL_ODR_MAX 0x00
-#define FXOS8700_CTRL_ODR_MIN GENMASK(4, 3)
+#define FXOS8700_CTRL_ODR_MSK GENMASK(5, 3)
/* Bit definitions for FXOS8700_M_CTRL_REG1 */
#define FXOS8700_HMS_MASK GENMASK(1, 0)
switch (iio_type) {
case IIO_ACCEL:
return FXOS8700_ACCEL;
- case IIO_ANGL_VEL:
+ case IIO_MAGN:
return FXOS8700_MAGN;
default:
return -EINVAL;
static int fxos8700_set_scale(struct fxos8700_data *data,
enum fxos8700_sensor t, int uscale)
{
- int i;
+ int i, ret, val;
+ bool active_mode;
static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale);
struct device *dev = regmap_get_device(data->regmap);
if (t == FXOS8700_MAGN) {
- dev_err(dev, "Magnetometer scale is locked at 1200uT\n");
+ dev_err(dev, "Magnetometer scale is locked at 0.001Gs\n");
return -EINVAL;
}
+ /*
+ * When device is in active mode, it failed to set an ACCEL
+ * full-scale range(2g/4g/8g) in FXOS8700_XYZ_DATA_CFG.
+ * This is not align with the datasheet, but it is a fxos8700
+ * chip behavier. Set the device in standby mode before setting
+ * an ACCEL full-scale range.
+ */
+ ret = regmap_read(data->regmap, FXOS8700_CTRL_REG1, &val);
+ if (ret)
+ return ret;
+
+ active_mode = val & FXOS8700_ACTIVE;
+ if (active_mode) {
+ ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1,
+ val & ~FXOS8700_ACTIVE);
+ if (ret)
+ return ret;
+ }
+
for (i = 0; i < scale_num; i++)
if (fxos8700_accel_scale[i].uscale == uscale)
break;
if (i == scale_num)
return -EINVAL;
- return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG,
+ ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG,
fxos8700_accel_scale[i].bits);
+ if (ret)
+ return ret;
+ return regmap_write(data->regmap, FXOS8700_CTRL_REG1,
+ active_mode);
}
static int fxos8700_get_scale(struct fxos8700_data *data,
static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale);
if (t == FXOS8700_MAGN) {
- *uscale = 1200; /* Magnetometer is locked at 1200uT */
+ *uscale = 1000; /* Magnetometer is locked at 0.001Gs */
return 0;
}
int axis, int *val)
{
u8 base, reg;
+ s16 tmp;
int ret;
- enum fxos8700_sensor type = fxos8700_to_sensor(chan_type);
- base = type ? FXOS8700_OUT_X_MSB : FXOS8700_M_OUT_X_MSB;
+ /*
+ * Different register base addresses varies with channel types.
+ * This bug hasn't been noticed before because using an enum is
+ * really hard to read. Use an a switch statement to take over that.
+ */
+ switch (chan_type) {
+ case IIO_ACCEL:
+ base = FXOS8700_OUT_X_MSB;
+ break;
+ case IIO_MAGN:
+ base = FXOS8700_M_OUT_X_MSB;
+ break;
+ default:
+ return -EINVAL;
+ }
/* Block read 6 bytes of device output registers to avoid data loss */
ret = regmap_bulk_read(data->regmap, base, data->buf,
- FXOS8700_DATA_BUF_SIZE);
+ sizeof(data->buf));
if (ret)
return ret;
/* Convert axis to buffer index */
reg = axis - IIO_MOD_X;
+ /*
+ * Convert to native endianness. The accel data and magn data
+ * are signed, so a forced type conversion is needed.
+ */
+ tmp = be16_to_cpu(data->buf[reg]);
+
+ /*
+ * ACCEL output data registers contain the X-axis, Y-axis, and Z-axis
+ * 14-bit left-justified sample data and MAGN output data registers
+ * contain the X-axis, Y-axis, and Z-axis 16-bit sample data. Apply
+ * a signed 2 bits right shift to the readback raw data from ACCEL
+ * output data register and keep that from MAGN sensor as the origin.
+ * Value should be extended to 32 bit.
+ */
+ switch (chan_type) {
+ case IIO_ACCEL:
+ tmp = tmp >> 2;
+ break;
+ case IIO_MAGN:
+ /* Nothing to do */
+ break;
+ default:
+ return -EINVAL;
+ }
+
/* Convert to native endianness */
- *val = sign_extend32(be16_to_cpu(data->buf[reg]), 15);
+ *val = sign_extend32(tmp, 15);
return 0;
}
if (i >= odr_num)
return -EINVAL;
- return regmap_update_bits(data->regmap,
- FXOS8700_CTRL_REG1,
- FXOS8700_CTRL_ODR_MSK + FXOS8700_ACTIVE,
- fxos8700_odr[i].bits << 3 | active_mode);
+ val &= ~FXOS8700_CTRL_ODR_MSK;
+ val |= FIELD_PREP(FXOS8700_CTRL_ODR_MSK, fxos8700_odr[i].bits) | FXOS8700_ACTIVE;
+ return regmap_write(data->regmap, FXOS8700_CTRL_REG1, val);
}
static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t,
if (ret)
return ret;
- val &= FXOS8700_CTRL_ODR_MSK;
+ val = FIELD_GET(FXOS8700_CTRL_ODR_MSK, val);
for (i = 0; i < odr_num; i++)
if (val == fxos8700_odr[i].bits)
static IIO_CONST_ATTR(in_magn_sampling_frequency_available,
"1.5625 6.25 12.5 50 100 200 400 800");
static IIO_CONST_ATTR(in_accel_scale_available, "0.000244 0.000488 0.000976");
-static IIO_CONST_ATTR(in_magn_scale_available, "0.000001200");
+static IIO_CONST_ATTR(in_magn_scale_available, "0.001000");
static struct attribute *fxos8700_attrs[] = {
&iio_const_attr_in_accel_sampling_frequency_available.dev_attr.attr,
if (ret)
return ret;
- /* Max ODR (800Hz individual or 400Hz hybrid), active mode */
- ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1,
- FXOS8700_CTRL_ODR_MAX | FXOS8700_ACTIVE);
+ /*
+ * Set max full-scale range (+/-8G) for ACCEL sensor in chip
+ * initialization then activate the device.
+ */
+ ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G);
if (ret)
return ret;
- /* Set for max full-scale range (+/-8G) */
- return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G);
+ /* Max ODR (800Hz individual or 400Hz hybrid), active mode */
+ return regmap_update_bits(data->regmap, FXOS8700_CTRL_REG1,
+ FXOS8700_CTRL_ODR_MSK | FXOS8700_ACTIVE,
+ FIELD_PREP(FXOS8700_CTRL_ODR_MSK, FXOS8700_CTRL_ODR_MAX) |
+ FXOS8700_ACTIVE);
}
static void fxos8700_chip_uninit(void *data)
tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors"
depends on (I2C || SPI || I3C)
select IIO_BUFFER
+ select IIO_TRIGGERED_BUFFER
select IIO_KFIFO_BUF
select IIO_ST_LSM6DSX_I2C if (I2C)
select IIO_ST_LSM6DSX_SPI if (SPI_MASTER)
if (!indio_dev)
return -ENOMEM;
+ i2c_set_clientdata(client, indio_dev);
+
/*
* Some ACPI systems list 2 I2C resources for the CM3218 sensor, the
* SMBus Alert Response Address (ARA, 0x0c) and the actual I2C address.
return PTR_ERR(client);
}
- i2c_set_clientdata(client, indio_dev);
-
cm32181 = iio_priv(indio_dev);
cm32181->client = client;
cm32181->dev = dev;
static int cm32181_suspend(struct device *dev)
{
- struct i2c_client *client = to_i2c_client(dev);
+ struct cm32181_chip *cm32181 = iio_priv(dev_get_drvdata(dev));
+ struct i2c_client *client = cm32181->client;
return i2c_smbus_write_word_data(client, CM32181_REG_ADDR_CMD,
CM32181_CMD_ALS_DISABLE);
static int cm32181_resume(struct device *dev)
{
- struct i2c_client *client = to_i2c_client(dev);
struct cm32181_chip *cm32181 = iio_priv(dev_get_drvdata(dev));
+ struct i2c_client *client = cm32181->client;
return i2c_smbus_write_word_data(client, CM32181_REG_ADDR_CMD,
cm32181->conf_regs[CM32181_REG_ADDR_CMD]);
if (umem_dmabuf->sgt)
goto wait_fence;
- sgt = dma_buf_map_attachment_unlocked(umem_dmabuf->attach,
- DMA_BIDIRECTIONAL);
+ sgt = dma_buf_map_attachment(umem_dmabuf->attach,
+ DMA_BIDIRECTIONAL);
if (IS_ERR(sgt))
return PTR_ERR(sgt);
umem_dmabuf->last_sg_trim = 0;
}
- dma_buf_unmap_attachment_unlocked(umem_dmabuf->attach, umem_dmabuf->sgt,
- DMA_BIDIRECTIONAL);
+ dma_buf_unmap_attachment(umem_dmabuf->attach, umem_dmabuf->sgt,
+ DMA_BIDIRECTIONAL);
umem_dmabuf->sgt = NULL;
}
bool __rdma_block_iter_next(struct ib_block_iter *biter)
{
unsigned int block_offset;
+ unsigned int sg_delta;
if (!biter->__sg_nents || !biter->__sg)
return false;
biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance;
block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1);
- biter->__sg_advance += BIT_ULL(biter->__pg_bit) - block_offset;
+ sg_delta = BIT_ULL(biter->__pg_bit) - block_offset;
- if (biter->__sg_advance >= sg_dma_len(biter->__sg)) {
+ if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) {
+ biter->__sg_advance += sg_delta;
+ } else {
biter->__sg_advance = 0;
biter->__sg = sg_next(biter->__sg);
biter->__sg_nents--;
addr = arg + offsetof(struct hfi1_tid_info, tidcnt);
if (copy_to_user((void __user *)addr, &tinfo.tidcnt,
sizeof(tinfo.tidcnt)))
- return -EFAULT;
+ ret = -EFAULT;
addr = arg + offsetof(struct hfi1_tid_info, length);
- if (copy_to_user((void __user *)addr, &tinfo.length,
+ if (!ret && copy_to_user((void __user *)addr, &tinfo.length,
sizeof(tinfo.length)))
ret = -EFAULT;
+
+ if (ret)
+ hfi1_user_exp_rcv_invalid(fd, &tinfo);
}
return ret;
static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
const struct mmu_notifier_range *range,
unsigned long cur_seq);
+static bool tid_cover_invalidate(struct mmu_interval_notifier *mni,
+ const struct mmu_notifier_range *range,
+ unsigned long cur_seq);
static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *,
struct tid_group *grp,
unsigned int start, u16 count,
u32 *tidlist, unsigned int *tididx,
unsigned int *pmapped);
-static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
- struct tid_group **grp);
+static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo);
+static void __clear_tid_node(struct hfi1_filedata *fd,
+ struct tid_rb_node *node);
static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node);
static const struct mmu_interval_notifier_ops tid_mn_ops = {
.invalidate = tid_rb_invalidate,
};
+static const struct mmu_interval_notifier_ops tid_cover_ops = {
+ .invalidate = tid_cover_invalidate,
+};
/*
* Initialize context and file private data needed for Expected
static int pin_rcv_pages(struct hfi1_filedata *fd, struct tid_user_buf *tidbuf)
{
int pinned;
- unsigned int npages;
+ unsigned int npages = tidbuf->npages;
unsigned long vaddr = tidbuf->vaddr;
struct page **pages = NULL;
struct hfi1_devdata *dd = fd->uctxt->dd;
- /* Get the number of pages the user buffer spans */
- npages = num_user_pages(vaddr, tidbuf->length);
- if (!npages)
- return -EINVAL;
-
if (npages > fd->uctxt->expected_count) {
dd_dev_err(dd, "Expected buffer too big\n");
return -EINVAL;
return pinned;
}
tidbuf->pages = pages;
- tidbuf->npages = npages;
fd->tid_n_pinned += pinned;
return pinned;
}
tididx = 0, mapped, mapped_pages = 0;
u32 *tidlist = NULL;
struct tid_user_buf *tidbuf;
+ unsigned long mmu_seq = 0;
if (!PAGE_ALIGNED(tinfo->vaddr))
return -EINVAL;
+ if (tinfo->length == 0)
+ return -EINVAL;
tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL);
if (!tidbuf)
return -ENOMEM;
+ mutex_init(&tidbuf->cover_mutex);
tidbuf->vaddr = tinfo->vaddr;
tidbuf->length = tinfo->length;
+ tidbuf->npages = num_user_pages(tidbuf->vaddr, tidbuf->length);
tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets),
GFP_KERNEL);
if (!tidbuf->psets) {
- kfree(tidbuf);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto fail_release_mem;
+ }
+
+ if (fd->use_mn) {
+ ret = mmu_interval_notifier_insert(
+ &tidbuf->notifier, current->mm,
+ tidbuf->vaddr, tidbuf->npages * PAGE_SIZE,
+ &tid_cover_ops);
+ if (ret)
+ goto fail_release_mem;
+ mmu_seq = mmu_interval_read_begin(&tidbuf->notifier);
}
pinned = pin_rcv_pages(fd, tidbuf);
if (pinned <= 0) {
- kfree(tidbuf->psets);
- kfree(tidbuf);
- return pinned;
+ ret = (pinned < 0) ? pinned : -ENOSPC;
+ goto fail_unpin;
}
/* Find sets of physically contiguous pages */
tidbuf->n_psets = find_phys_blocks(tidbuf, pinned);
- /*
- * We don't need to access this under a lock since tid_used is per
- * process and the same process cannot be in hfi1_user_exp_rcv_clear()
- * and hfi1_user_exp_rcv_setup() at the same time.
- */
+ /* Reserve the number of expected tids to be used. */
spin_lock(&fd->tid_lock);
if (fd->tid_used + tidbuf->n_psets > fd->tid_limit)
pageset_count = fd->tid_limit - fd->tid_used;
else
pageset_count = tidbuf->n_psets;
+ fd->tid_used += pageset_count;
spin_unlock(&fd->tid_lock);
- if (!pageset_count)
- goto bail;
+ if (!pageset_count) {
+ ret = -ENOSPC;
+ goto fail_unreserve;
+ }
ngroups = pageset_count / dd->rcv_entries.group_size;
tidlist = kcalloc(pageset_count, sizeof(*tidlist), GFP_KERNEL);
if (!tidlist) {
ret = -ENOMEM;
- goto nomem;
+ goto fail_unreserve;
}
tididx = 0;
}
unlock:
mutex_unlock(&uctxt->exp_mutex);
-nomem:
hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx,
mapped_pages, ret);
- if (tididx) {
- spin_lock(&fd->tid_lock);
- fd->tid_used += tididx;
- spin_unlock(&fd->tid_lock);
- tinfo->tidcnt = tididx;
- tinfo->length = mapped_pages * PAGE_SIZE;
-
- if (copy_to_user(u64_to_user_ptr(tinfo->tidlist),
- tidlist, sizeof(tidlist[0]) * tididx)) {
- /*
- * On failure to copy to the user level, we need to undo
- * everything done so far so we don't leak resources.
- */
- tinfo->tidlist = (unsigned long)&tidlist;
- hfi1_user_exp_rcv_clear(fd, tinfo);
- tinfo->tidlist = 0;
- ret = -EFAULT;
- goto bail;
+
+ /* fail if nothing was programmed, set error if none provided */
+ if (tididx == 0) {
+ if (ret >= 0)
+ ret = -ENOSPC;
+ goto fail_unreserve;
+ }
+
+ /* adjust reserved tid_used to actual count */
+ spin_lock(&fd->tid_lock);
+ fd->tid_used -= pageset_count - tididx;
+ spin_unlock(&fd->tid_lock);
+
+ /* unpin all pages not covered by a TID */
+ unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages,
+ false);
+
+ if (fd->use_mn) {
+ /* check for an invalidate during setup */
+ bool fail = false;
+
+ mutex_lock(&tidbuf->cover_mutex);
+ fail = mmu_interval_read_retry(&tidbuf->notifier, mmu_seq);
+ mutex_unlock(&tidbuf->cover_mutex);
+
+ if (fail) {
+ ret = -EBUSY;
+ goto fail_unprogram;
}
}
- /*
- * If not everything was mapped (due to insufficient RcvArray entries,
- * for example), unpin all unmapped pages so we can pin them nex time.
- */
- if (mapped_pages != pinned)
- unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages,
- (pinned - mapped_pages), false);
-bail:
+ tinfo->tidcnt = tididx;
+ tinfo->length = mapped_pages * PAGE_SIZE;
+
+ if (copy_to_user(u64_to_user_ptr(tinfo->tidlist),
+ tidlist, sizeof(tidlist[0]) * tididx)) {
+ ret = -EFAULT;
+ goto fail_unprogram;
+ }
+
+ if (fd->use_mn)
+ mmu_interval_notifier_remove(&tidbuf->notifier);
+ kfree(tidbuf->pages);
kfree(tidbuf->psets);
+ kfree(tidbuf);
kfree(tidlist);
+ return 0;
+
+fail_unprogram:
+ /* unprogram, unmap, and unpin all allocated TIDs */
+ tinfo->tidlist = (unsigned long)tidlist;
+ hfi1_user_exp_rcv_clear(fd, tinfo);
+ tinfo->tidlist = 0;
+ pinned = 0; /* nothing left to unpin */
+ pageset_count = 0; /* nothing left reserved */
+fail_unreserve:
+ spin_lock(&fd->tid_lock);
+ fd->tid_used -= pageset_count;
+ spin_unlock(&fd->tid_lock);
+fail_unpin:
+ if (fd->use_mn)
+ mmu_interval_notifier_remove(&tidbuf->notifier);
+ if (pinned > 0)
+ unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false);
+fail_release_mem:
kfree(tidbuf->pages);
+ kfree(tidbuf->psets);
kfree(tidbuf);
- return ret > 0 ? 0 : ret;
+ kfree(tidlist);
+ return ret;
}
int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd,
mutex_lock(&uctxt->exp_mutex);
for (tididx = 0; tididx < tinfo->tidcnt; tididx++) {
- ret = unprogram_rcvarray(fd, tidinfo[tididx], NULL);
+ ret = unprogram_rcvarray(fd, tidinfo[tididx]);
if (ret) {
hfi1_cdbg(TID, "Failed to unprogram rcv array %d",
ret);
}
node->fdata = fd;
+ mutex_init(&node->invalidate_mutex);
node->phys = page_to_phys(pages[0]);
node->npages = npages;
node->rcventry = rcventry;
&tid_mn_ops);
if (ret)
goto out_unmap;
- /*
- * FIXME: This is in the wrong order, the notifier should be
- * established before the pages are pinned by pin_rcv_pages.
- */
- mmu_interval_read_begin(&node->notifier);
}
fd->entry_to_rb[node->rcventry - uctxt->expected_base] = node;
return -EFAULT;
}
-static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
- struct tid_group **grp)
+static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo)
{
struct hfi1_ctxtdata *uctxt = fd->uctxt;
struct hfi1_devdata *dd = uctxt->dd;
if (!node || node->rcventry != (uctxt->expected_base + rcventry))
return -EBADF;
- if (grp)
- *grp = node->grp;
-
if (fd->use_mn)
mmu_interval_notifier_remove(&node->notifier);
cacheless_tid_rb_remove(fd, node);
return 0;
}
-static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
+static void __clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
{
struct hfi1_ctxtdata *uctxt = fd->uctxt;
struct hfi1_devdata *dd = uctxt->dd;
+ mutex_lock(&node->invalidate_mutex);
+ if (node->freed)
+ goto done;
+ node->freed = true;
+
trace_hfi1_exp_tid_unreg(uctxt->ctxt, fd->subctxt, node->rcventry,
node->npages,
node->notifier.interval_tree.start, node->phys,
node->dma_addr);
- /*
- * Make sure device has seen the write before we unpin the
- * pages.
- */
+ /* Make sure device has seen the write before pages are unpinned */
hfi1_put_tid(dd, node->rcventry, PT_INVALID_FLUSH, 0, 0);
unpin_rcv_pages(fd, NULL, node, 0, node->npages, true);
+done:
+ mutex_unlock(&node->invalidate_mutex);
+}
+
+static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
+{
+ struct hfi1_ctxtdata *uctxt = fd->uctxt;
+
+ __clear_tid_node(fd, node);
node->grp->used--;
node->grp->map &= ~(1 << (node->rcventry - node->grp->base));
if (node->freed)
return true;
+ /* take action only if unmapping */
+ if (range->event != MMU_NOTIFY_UNMAP)
+ return true;
+
trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt,
node->notifier.interval_tree.start,
node->rcventry, node->npages, node->dma_addr);
- node->freed = true;
+
+ /* clear the hardware rcvarray entry */
+ __clear_tid_node(fdata, node);
spin_lock(&fdata->invalid_lock);
if (fdata->invalid_tid_idx < uctxt->expected_count) {
return true;
}
+static bool tid_cover_invalidate(struct mmu_interval_notifier *mni,
+ const struct mmu_notifier_range *range,
+ unsigned long cur_seq)
+{
+ struct tid_user_buf *tidbuf =
+ container_of(mni, struct tid_user_buf, notifier);
+
+ /* take action only if unmapping */
+ if (range->event == MMU_NOTIFY_UNMAP) {
+ mutex_lock(&tidbuf->cover_mutex);
+ mmu_interval_set_seq(mni, cur_seq);
+ mutex_unlock(&tidbuf->cover_mutex);
+ }
+
+ return true;
+}
+
static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
struct tid_rb_node *tnode)
{
};
struct tid_user_buf {
+ struct mmu_interval_notifier notifier;
+ struct mutex cover_mutex;
unsigned long vaddr;
unsigned long length;
unsigned int npages;
struct tid_rb_node {
struct mmu_interval_notifier notifier;
struct hfi1_filedata *fdata;
+ struct mutex invalidate_mutex; /* covers hw removal */
unsigned long phys;
struct tid_group *grp;
u32 rcventry;
continue;
idev = in_dev_get(ip_dev);
+ if (!idev)
+ continue;
+
in_dev_for_each_ifa_rtnl(ifa, idev) {
ibdev_dbg(&iwdev->ibdev,
"CM: Allocating child CM Listener forIP=%pI4, vlan_id=%d, MAC=%pM\n",
/* IB ports start with 1, MANA Ethernet ports start with 0 */
port = ucmd.port;
- if (ucmd.port > mc->num_ports)
+ if (port < 1 || port > mc->num_ports)
return -EINVAL;
if (attr->cap.max_send_wr > MAX_SEND_BUFFERS_PER_QUEUE) {
const struct mlx5_ib_counters *cnts = get_counters(dev, port_num - 1);
struct mlx5_core_dev *mdev;
int ret, num_counters;
- u32 mdev_port_num;
if (!stats)
return -EINVAL;
}
if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
- mdev = mlx5_ib_get_native_port_mdev(dev, port_num,
- &mdev_port_num);
+ if (!port_num)
+ port_num = 1;
+ mdev = mlx5_ib_get_native_port_mdev(dev, port_num, NULL);
if (!mdev) {
/* If port is not affiliated yet, its in down state
* which doesn't have any counters yet, so it would be
return false;
}
+static int validate_rd_atomic(struct mlx5_ib_dev *dev, struct ib_qp_attr *attr,
+ int attr_mask, enum ib_qp_type qp_type)
+{
+ int log_max_ra_res;
+ int log_max_ra_req;
+
+ if (qp_type == MLX5_IB_QPT_DCI) {
+ log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_res_dc);
+ log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_req_dc);
+ } else {
+ log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_res_qp);
+ log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_req_qp);
+ }
+
+ if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
+ attr->max_rd_atomic > log_max_ra_res) {
+ mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n",
+ attr->max_rd_atomic);
+ return false;
+ }
+
+ if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
+ attr->max_dest_rd_atomic > log_max_ra_req) {
+ mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n",
+ attr->max_dest_rd_atomic);
+ return false;
+ }
+ return true;
+}
+
int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
int attr_mask, struct ib_udata *udata)
{
goto out;
}
- if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
- attr->max_rd_atomic >
- (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_res_qp))) {
- mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n",
- attr->max_rd_atomic);
- goto out;
- }
-
- if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
- attr->max_dest_rd_atomic >
- (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_req_qp))) {
- mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n",
- attr->max_dest_rd_atomic);
+ if (!validate_rd_atomic(dev, attr, attr_mask, qp_type))
goto out;
- }
if (cur_state == new_state && cur_state == IB_QPS_RESET) {
err = 0;
size = pa_end - pa_start + PAGE_SIZE;
usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x",
va_start, &pa_start, size, flags);
- err = iommu_map(pd->domain, va_start, pa_start,
- size, flags);
+ err = iommu_map_atomic(pd->domain, va_start,
+ pa_start, size, flags);
if (err) {
usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n",
va_start, &pa_start, size, err);
size = pa - pa_start + PAGE_SIZE;
usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x\n",
va_start, &pa_start, size, flags);
- err = iommu_map(pd->domain, va_start, pa_start,
- size, flags);
+ err = iommu_map_atomic(pd->domain, va_start,
+ pa_start, size, flags);
if (err) {
usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n",
va_start, &pa_start, size, err);
RXE_MAX_SRQ = DEFAULT_MAX_VALUE - RXE_MIN_SRQ_INDEX,
RXE_MIN_MR_INDEX = 0x00000001,
- RXE_MAX_MR_INDEX = DEFAULT_MAX_VALUE,
- RXE_MAX_MR = DEFAULT_MAX_VALUE - RXE_MIN_MR_INDEX,
- RXE_MIN_MW_INDEX = 0x00010001,
- RXE_MAX_MW_INDEX = 0x00020000,
- RXE_MAX_MW = 0x00001000,
+ RXE_MAX_MR_INDEX = DEFAULT_MAX_VALUE >> 1,
+ RXE_MAX_MR = RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX,
+ RXE_MIN_MW_INDEX = RXE_MAX_MR_INDEX + 1,
+ RXE_MAX_MW_INDEX = DEFAULT_MAX_VALUE,
+ RXE_MAX_MW = RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX,
RXE_MAX_PKT_PER_ACK = 64,
.size = sizeof(struct rxe_ucontext),
.elem_offset = offsetof(struct rxe_ucontext, elem),
.min_index = 1,
- .max_index = UINT_MAX,
- .max_elem = UINT_MAX,
+ .max_index = RXE_MAX_UCONTEXT,
+ .max_elem = RXE_MAX_UCONTEXT,
},
[RXE_TYPE_PD] = {
.name = "pd",
.size = sizeof(struct rxe_pd),
.elem_offset = offsetof(struct rxe_pd, elem),
.min_index = 1,
- .max_index = UINT_MAX,
- .max_elem = UINT_MAX,
+ .max_index = RXE_MAX_PD,
+ .max_elem = RXE_MAX_PD,
},
[RXE_TYPE_AH] = {
.name = "ah",
.elem_offset = offsetof(struct rxe_ah, elem),
.min_index = RXE_MIN_AH_INDEX,
.max_index = RXE_MAX_AH_INDEX,
- .max_elem = RXE_MAX_AH_INDEX - RXE_MIN_AH_INDEX + 1,
+ .max_elem = RXE_MAX_AH,
},
[RXE_TYPE_SRQ] = {
.name = "srq",
.cleanup = rxe_srq_cleanup,
.min_index = RXE_MIN_SRQ_INDEX,
.max_index = RXE_MAX_SRQ_INDEX,
- .max_elem = RXE_MAX_SRQ_INDEX - RXE_MIN_SRQ_INDEX + 1,
+ .max_elem = RXE_MAX_SRQ,
},
[RXE_TYPE_QP] = {
.name = "qp",
.cleanup = rxe_qp_cleanup,
.min_index = RXE_MIN_QP_INDEX,
.max_index = RXE_MAX_QP_INDEX,
- .max_elem = RXE_MAX_QP_INDEX - RXE_MIN_QP_INDEX + 1,
+ .max_elem = RXE_MAX_QP,
},
[RXE_TYPE_CQ] = {
.name = "cq",
.elem_offset = offsetof(struct rxe_cq, elem),
.cleanup = rxe_cq_cleanup,
.min_index = 1,
- .max_index = UINT_MAX,
- .max_elem = UINT_MAX,
+ .max_index = RXE_MAX_CQ,
+ .max_elem = RXE_MAX_CQ,
},
[RXE_TYPE_MR] = {
.name = "mr",
.cleanup = rxe_mr_cleanup,
.min_index = RXE_MIN_MR_INDEX,
.max_index = RXE_MAX_MR_INDEX,
- .max_elem = RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX + 1,
+ .max_elem = RXE_MAX_MR,
},
[RXE_TYPE_MW] = {
.name = "mw",
.cleanup = rxe_mw_cleanup,
.min_index = RXE_MIN_MW_INDEX,
.max_index = RXE_MAX_MW_INDEX,
- .max_elem = RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX + 1,
+ .max_elem = RXE_MAX_MW,
},
};
rn->attach_mcast = ipoib_mcast_attach;
rn->detach_mcast = ipoib_mcast_detach;
rn->hca = hca;
+
+ rc = netif_set_real_num_tx_queues(dev, 1);
+ if (rc)
+ goto out;
+
+ rc = netif_set_real_num_rx_queues(dev, 1);
+ if (rc)
+ goto out;
}
priv->rn_ops = dev->netdev_ops;
if (srv_path->kobj.state_in_sysfs) {
sysfs_remove_group(&srv_path->kobj, &rtrs_srv_path_attr_group);
- kobject_del(&srv_path->kobj);
kobject_put(&srv_path->kobj);
+ rtrs_srv_destroy_once_sysfs_root_folders(srv_path);
}
- rtrs_srv_destroy_once_sysfs_root_folders(srv_path);
}
SRP_DEFAULT_CMD_SQ_SIZE = SRP_DEFAULT_QUEUE_SIZE - SRP_RSP_SQ_SIZE -
SRP_TSK_MGMT_SQ_SIZE,
- SRP_TAG_NO_REQ = ~0U,
- SRP_TAG_TSK_MGMT = 1U << 31,
-
SRP_MAX_PAGES_PER_MR = 512,
SRP_MAX_ADD_CDB_LEN = 16,
sizeof(struct srp_imm_buf),
};
+enum {
+ SRP_TAG_NO_REQ = ~0U,
+ SRP_TAG_TSK_MGMT = BIT(31),
+};
+
enum srp_target_state {
SRP_TARGET_SCANNING,
SRP_TARGET_LIVE,
MODULE_PARM_DESC(ptr_size,
"Pointing device width, height in pixels (default 800,600)");
-static int xenkbd_remove(struct xenbus_device *);
+static void xenkbd_remove(struct xenbus_device *);
static int xenkbd_connect_backend(struct xenbus_device *, struct xenkbd_info *);
static void xenkbd_disconnect_backend(struct xenkbd_info *);
return xenkbd_connect_backend(dev, info);
}
-static int xenkbd_remove(struct xenbus_device *dev)
+static void xenkbd_remove(struct xenbus_device *dev)
{
struct xenkbd_info *info = dev_get_drvdata(&dev->dev);
input_unregister_device(info->mtouch);
free_page((unsigned long)info->page);
kfree(info);
- return 0;
}
static int xenkbd_connect_backend(struct xenbus_device *dev,
"SYN3221", /* HP 15-ay000 */
"SYN323d", /* HP Spectre X360 13-w013dx */
"SYN3257", /* HP Envy 13-ad105ng */
- "SYN3286", /* HP Laptop 15-da3001TU */
NULL
};
.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"),
+ },
+ .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+ SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+ },
{
.matches = {
DMI_MATCH(DMI_BOARD_NAME, "X170SM"),
}
regmap_done:
- ret = devm_clk_bulk_get(dev, qp->num_clks, qp->bus_clks);
+ ret = devm_clk_bulk_get_optional(dev, qp->num_clks, qp->bus_clks);
if (ret)
return ret;
"aggre0_noc_mpu_cfg"
};
+static const char * const bus_a2noc_clocks[] = {
+ "bus",
+ "bus_a",
+ "aggre2_ufs_axi",
+ "ufs_axi"
+};
+
static const u16 mas_a0noc_common_links[] = {
MSM8996_SLAVE_A0NOC_SNOC
};
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0x9000,
+ .max_register = 0x6000,
.fast_io = true
};
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0x7000,
+ .max_register = 0x5000,
.fast_io = true
};
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0xa000,
+ .max_register = 0x7000,
.fast_io = true
};
.type = QCOM_ICC_NOC,
.nodes = a2noc_nodes,
.num_nodes = ARRAY_SIZE(a2noc_nodes),
+ .clocks = bus_a2noc_clocks,
+ .num_clocks = ARRAY_SIZE(bus_a2noc_clocks),
.regmap_cfg = &msm8996_a2noc_regmap_config
};
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0x62000,
+ .max_register = 0x5a000,
.fast_io = true
};
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0x20000,
+ .max_register = 0x1c000,
.fast_io = true
};
static void arm_smmu_device_shutdown(struct platform_device *pdev)
{
- arm_smmu_device_remove(pdev);
+ struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+ arm_smmu_device_disable(smmu);
}
static const struct of_device_id arm_smmu_of_match[] = {
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
- /* Assume that a coherent TCU implies coherent TBUs */
- return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK;
+ /*
+ * It's overwhelmingly the case in practice that when the pagetable
+ * walk interface is connected to a coherent interconnect, all the
+ * translation interfaces are too. Furthermore if the device is
+ * natively coherent, then its translation interface must also be.
+ */
+ return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK ||
+ device_get_dma_attr(dev) == DEV_DMA_COHERENT;
case IOMMU_CAP_NOEXEC:
return true;
default:
return 0;
}
-static int arm_smmu_device_remove(struct platform_device *pdev)
+static void arm_smmu_device_shutdown(struct platform_device *pdev)
{
struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
if (!smmu)
- return -ENODEV;
+ return;
if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
dev_notice(&pdev->dev, "disabling translation\n");
- iommu_device_unregister(&smmu->iommu);
- iommu_device_sysfs_remove(&smmu->iommu);
-
arm_smmu_rpm_get(smmu);
/* Turn the thing off */
arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD);
clk_bulk_disable(smmu->num_clks, smmu->clks);
clk_bulk_unprepare(smmu->num_clks, smmu->clks);
- return 0;
}
-static void arm_smmu_device_shutdown(struct platform_device *pdev)
+static int arm_smmu_device_remove(struct platform_device *pdev)
{
- arm_smmu_device_remove(pdev);
+ struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+ if (!smmu)
+ return -ENODEV;
+
+ iommu_device_unregister(&smmu->iommu);
+ iommu_device_sysfs_remove(&smmu->iommu);
+
+ arm_smmu_device_shutdown(pdev);
+
+ return 0;
}
static int __maybe_unused arm_smmu_runtime_resume(struct device *dev)
*/
int iommu_device_claim_dma_owner(struct device *dev, void *owner)
{
- struct iommu_group *group = iommu_group_get(dev);
+ struct iommu_group *group;
int ret = 0;
- if (!group)
- return -ENODEV;
if (WARN_ON(!owner))
return -EINVAL;
+ group = iommu_group_get(dev);
+ if (!group)
+ return -ENODEV;
+
mutex_lock(&group->mutex);
if (group->owner_cnt) {
if (group->owner != owner) {
curr = __get_cached_rbnode(iovad, limit_pfn);
curr_iova = to_iova(curr);
- retry_pfn = curr_iova->pfn_hi + 1;
+ retry_pfn = curr_iova->pfn_hi;
retry:
do {
if (high_pfn < size || new_pfn < low_pfn) {
if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
high_pfn = limit_pfn;
- low_pfn = retry_pfn;
+ low_pfn = retry_pfn + 1;
curr = iova_find_limit(iovad, limit_pfn);
curr_iova = to_iova(curr);
goto retry;
ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
dev_name(&pdev->dev));
if (ret)
- return ret;
+ goto out_clk_unprepare;
ret = iommu_device_register(&data->iommu, &mtk_iommu_v1_ops, dev);
if (ret)
iommu_device_unregister(&data->iommu);
out_sysfs_remove:
iommu_device_sysfs_remove(&data->iommu);
+out_clk_unprepare:
+ clk_disable_unprepare(data->bclk);
return ret;
}
return bkey_u64s(k) * sizeof(__u64);
}
-#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src))
+#define bkey_copy(_dest, _src) unsafe_memcpy(_dest, _src, bkey_bytes(_src), \
+ /* bkey is always padded */)
static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
{
bytes, GFP_KERNEL);
if (!i)
return -ENOMEM;
- memcpy(&i->j, j, bytes);
+ unsafe_memcpy(&i->j, j, bytes,
+ /* "bytes" was calculated by set_bytes() above */);
/* Add to the location after 'where' points to */
list_add(&i->list, where);
ret = 1;
* otherwise associated queue_limits won't be imposed.
*/
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
}
init_clone_info(&ci, md, map, bio, is_abnormal);
}
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
if (mddev->ro == MD_RDONLY && unlikely(rw == WRITE)) {
if (bio_sectors(bio) != 0)
*/
static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor)
{
- static struct md_rdev *claim_rdev; /* just for claiming the bdev */
+ static struct md_rdev claim_rdev; /* just for claiming the bdev */
struct md_rdev *rdev;
sector_t size;
int err;
rdev->bdev = blkdev_get_by_dev(newdev,
FMODE_READ | FMODE_WRITE | FMODE_EXCL,
- super_format == -2 ? claim_rdev : rdev);
+ super_format == -2 ? &claim_rdev : rdev);
if (IS_ERR(rdev->bdev)) {
pr_warn("md: could not open device unknown-block(%u,%u).\n",
MAJOR(newdev), MINOR(newdev));
if (ret)
return ret;
- q->streaming = 1;
-
/*
* Tell driver to start streaming provided sufficient buffers
* are available.
goto unprepare;
}
+ q->streaming = 1;
+
dprintk(q, 3, "successful\n");
return 0;
unprepare:
call_void_qop(q, unprepare_streaming, q);
- q->streaming = 0;
return ret;
}
EXPORT_SYMBOL_GPL(vb2_core_streamon);
* then return an error.
*/
if (strlen(ctrl->p_new.p_char) == ctrl->maximum && last)
- ctrl->is_new = 1;
return -ERANGE;
+ ctrl->is_new = 1;
}
return ret;
default:
caps = of_device_get_match_data(&pdev->dev);
if (caps->has_ddrck) {
- clk = devm_clk_get(&pdev->dev, "ddrck");
+ clk = devm_clk_get_enabled(&pdev->dev, "ddrck");
if (IS_ERR(clk))
return PTR_ERR(clk);
- clk_prepare_enable(clk);
}
if (caps->has_mpddr_clk) {
- clk = devm_clk_get(&pdev->dev, "mpddr");
+ clk = devm_clk_get_enabled(&pdev->dev, "mpddr");
if (IS_ERR(clk)) {
pr_err("AT91 RAMC: couldn't get mpddr clock\n");
return PTR_ERR(clk);
}
- clk_prepare_enable(clk);
}
return 0;
if (IS_ERR(devbus->base))
return PTR_ERR(devbus->base);
- clk = devm_clk_get(&pdev->dev, NULL);
+ clk = devm_clk_get_enabled(&pdev->dev, NULL);
if (IS_ERR(clk))
return PTR_ERR(clk);
- clk_prepare_enable(clk);
/*
* Obtain clock period in picoseconds,
}
}
- if (p->wait_pin > gpmc_nr_waitpins) {
+ if (p->wait_pin != GPMC_WAITPIN_INVALID &&
+ p->wait_pin > gpmc_nr_waitpins) {
pr_err("%s: invalid wait-pin (%d)\n", __func__, p->wait_pin);
return -EINVAL;
}
#define MC_SID_STREAMID_SECURITY_WRITE_ACCESS_DISABLED BIT(16)
#define MC_SID_STREAMID_SECURITY_OVERRIDE BIT(8)
-static void tegra186_mc_program_sid(struct tegra_mc *mc)
-{
- unsigned int i;
-
- for (i = 0; i < mc->soc->num_clients; i++) {
- const struct tegra_mc_client *client = &mc->soc->clients[i];
- u32 override, security;
-
- override = readl(mc->regs + client->regs.sid.override);
- security = readl(mc->regs + client->regs.sid.security);
-
- dev_dbg(mc->dev, "client %s: override: %x security: %x\n",
- client->name, override, security);
-
- dev_dbg(mc->dev, "setting SID %u for %s\n", client->sid,
- client->name);
- writel(client->sid, mc->regs + client->regs.sid.override);
-
- override = readl(mc->regs + client->regs.sid.override);
- security = readl(mc->regs + client->regs.sid.security);
-
- dev_dbg(mc->dev, "client %s: override: %x security: %x\n",
- client->name, override, security);
- }
-}
-
static int tegra186_mc_probe(struct tegra_mc *mc)
{
struct platform_device *pdev = to_platform_device(mc->dev);
if (err < 0)
return err;
- tegra186_mc_program_sid(mc);
-
return 0;
}
of_platform_depopulate(mc->dev);
}
-static int tegra186_mc_resume(struct tegra_mc *mc)
-{
- tegra186_mc_program_sid(mc);
-
- return 0;
-}
-
#if IS_ENABLED(CONFIG_IOMMU_API)
static void tegra186_mc_client_sid_override(struct tegra_mc *mc,
const struct tegra_mc_client *client,
const struct tegra_mc_ops tegra186_mc_ops = {
.probe = tegra186_mc_probe,
.remove = tegra186_mc_remove,
- .resume = tegra186_mc_resume,
.probe_device = tegra186_mc_probe_device,
.handle_irq = tegra30_mc_handle_irq,
};
perm.vmid = QCOM_SCM_VMID_HLOS;
perm.perm = QCOM_SCM_PERM_RWX;
err = qcom_scm_assign_mem(map->phys, map->size,
- &(map->fl->cctx->vmperms[0].vmid), &perm, 1);
+ &map->fl->cctx->perms, &perm, 1);
if (err) {
dev_err(map->fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
map->phys, map->size, err);
dma_buf_put(map->buf);
}
+ if (map->fl) {
+ spin_lock(&map->fl->lock);
+ list_del(&map->node);
+ spin_unlock(&map->fl->lock);
+ map->fl = NULL;
+ }
+
kfree(map);
}
kref_put(&map->refcount, fastrpc_free_map);
}
-static void fastrpc_map_get(struct fastrpc_map *map)
+static int fastrpc_map_get(struct fastrpc_map *map)
{
- if (map)
- kref_get(&map->refcount);
+ if (!map)
+ return -ENOENT;
+
+ return kref_get_unless_zero(&map->refcount) ? 0 : -ENOENT;
}
static int fastrpc_map_lookup(struct fastrpc_user *fl, int fd,
- struct fastrpc_map **ppmap)
+ struct fastrpc_map **ppmap, bool take_ref)
{
+ struct fastrpc_session_ctx *sess = fl->sctx;
struct fastrpc_map *map = NULL;
+ int ret = -ENOENT;
- mutex_lock(&fl->mutex);
+ spin_lock(&fl->lock);
list_for_each_entry(map, &fl->maps, node) {
- if (map->fd == fd) {
- *ppmap = map;
- mutex_unlock(&fl->mutex);
- return 0;
- }
- }
- mutex_unlock(&fl->mutex);
-
- return -ENOENT;
-}
+ if (map->fd != fd)
+ continue;
-static int fastrpc_map_find(struct fastrpc_user *fl, int fd,
- struct fastrpc_map **ppmap)
-{
- int ret = fastrpc_map_lookup(fl, fd, ppmap);
+ if (take_ref) {
+ ret = fastrpc_map_get(map);
+ if (ret) {
+ dev_dbg(sess->dev, "%s: Failed to get map fd=%d ret=%d\n",
+ __func__, fd, ret);
+ break;
+ }
+ }
- if (!ret)
- fastrpc_map_get(*ppmap);
+ *ppmap = map;
+ ret = 0;
+ break;
+ }
+ spin_unlock(&fl->lock);
return ret;
}
struct fastrpc_map *map = NULL;
int err = 0;
- if (!fastrpc_map_find(fl, fd, ppmap))
+ if (!fastrpc_map_lookup(fl, fd, ppmap, true))
return 0;
map = kzalloc(sizeof(*map), GFP_KERNEL);
* If subsystem VMIDs are defined in DTSI, then do
* hyp_assign from HLOS to those VM(s)
*/
- unsigned int perms = BIT(QCOM_SCM_VMID_HLOS);
-
map->attr = attr;
- err = qcom_scm_assign_mem(map->phys, (u64)map->size, &perms,
+ err = qcom_scm_assign_mem(map->phys, (u64)map->size, &fl->cctx->perms,
fl->cctx->vmperms, fl->cctx->vmcount);
if (err) {
dev_err(sess->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d",
for (i = 0; i < FASTRPC_MAX_FDLIST; i++) {
if (!fdlist[i])
break;
- if (!fastrpc_map_lookup(fl, (int)fdlist[i], &mmap))
+ if (!fastrpc_map_lookup(fl, (int)fdlist[i], &mmap, false))
fastrpc_map_put(mmap);
}
/* Map if we have any heap VMIDs associated with this ADSP Static Process. */
if (fl->cctx->vmcount) {
- unsigned int perms = BIT(QCOM_SCM_VMID_HLOS);
-
err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys,
- (u64)fl->cctx->remote_heap->size, &perms,
+ (u64)fl->cctx->remote_heap->size,
+ &fl->cctx->perms,
fl->cctx->vmperms, fl->cctx->vmcount);
if (err) {
dev_err(fl->sctx->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d",
perm.perm = QCOM_SCM_PERM_RWX;
err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys,
(u64)fl->cctx->remote_heap->size,
- &(fl->cctx->vmperms[0].vmid), &perm, 1);
+ &fl->cctx->perms, &perm, 1);
if (err)
dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
fl->cctx->remote_heap->phys, fl->cctx->remote_heap->size, err);
fl->init_mem = NULL;
fastrpc_buf_free(imem);
err_alloc:
- if (map) {
- spin_lock(&fl->lock);
- list_del(&map->node);
- spin_unlock(&fl->lock);
- fastrpc_map_put(map);
- }
+ fastrpc_map_put(map);
err:
kfree(args);
fastrpc_context_put(ctx);
}
- list_for_each_entry_safe(map, m, &fl->maps, node) {
- list_del(&map->node);
+ list_for_each_entry_safe(map, m, &fl->maps, node)
fastrpc_map_put(map);
- }
list_for_each_entry_safe(buf, b, &fl->mmaps, node) {
list_del(&buf->node);
/* Add memory to static PD pool, protection thru hypervisor */
if (req.flags != ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) {
struct qcom_scm_vmperm perm;
- int err = 0;
perm.vmid = QCOM_SCM_VMID_HLOS;
perm.perm = QCOM_SCM_PERM_RWX;
err = qcom_scm_assign_mem(buf->phys, buf->size,
- &(fl->cctx->vmperms[0].vmid), &perm, 1);
+ &fl->cctx->perms, &perm, 1);
if (err) {
dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
buf->phys, buf->size, err);
if (cl->state == MEI_FILE_UNINITIALIZED) {
ret = mei_cl_link(cl);
if (ret)
- goto out;
+ goto notlinked;
/* update pointers */
cl->cldev = cldev;
}
ret = mei_cl_dma_alloc_and_map(cl, NULL, buffer_id, size);
-out:
+ if (ret)
+ mei_cl_unlink(cl);
+notlinked:
mutex_unlock(&bus->device_lock);
if (ret)
return ERR_PTR(ret);
if (cl->state == MEI_FILE_UNINITIALIZED) {
ret = mei_cl_link(cl);
if (ret)
- goto out;
+ goto notlinked;
/* update pointers */
cl->cldev = cldev;
}
}
out:
+ if (ret)
+ mei_cl_unlink(cl);
+notlinked:
mutex_unlock(&bus->device_lock);
return ret;
mei_cl_flush_queues(cldev->cl, NULL);
mei_me_cl_put(cldev->me_cl);
mei_dev_bus_put(cldev->bus);
- mei_cl_unlink(cldev->cl);
kfree(cldev->cl);
kfree(cldev);
}
#define MEI_DEV_ID_RPL_S 0x7A68 /* Raptor Lake Point S */
+#define MEI_DEV_ID_MTL_M 0x7E70 /* Meteor Lake Point M */
+
/*
* MEI HW Section
*/
{MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)},
+
/* required last entry */
{0, }
};
bool exclusive_vectors;
- struct tasklet_struct datagram_tasklet;
- struct tasklet_struct bm_tasklet;
struct wait_queue_head inout_wq;
void *data_buffer;
* This function assumes that it has exclusive access to the data
* in register(s) for the duration of the call.
*/
-static void vmci_dispatch_dgs(unsigned long data)
+static void vmci_dispatch_dgs(struct vmci_guest_device *vmci_dev)
{
- struct vmci_guest_device *vmci_dev = (struct vmci_guest_device *)data;
u8 *dg_in_buffer = vmci_dev->data_buffer;
struct vmci_datagram *dg;
size_t dg_in_buffer_size = VMCI_MAX_DG_SIZE;
* Scans the notification bitmap for raised flags, clears them
* and handles the notifications.
*/
-static void vmci_process_bitmap(unsigned long data)
+static void vmci_process_bitmap(struct vmci_guest_device *dev)
{
- struct vmci_guest_device *dev = (struct vmci_guest_device *)data;
-
if (!dev->notification_bitmap) {
dev_dbg(dev->dev, "No bitmap present in %s\n", __func__);
return;
struct vmci_guest_device *dev = _dev;
/*
- * If we are using MSI-X with exclusive vectors then we simply schedule
- * the datagram tasklet, since we know the interrupt was meant for us.
+ * If we are using MSI-X with exclusive vectors then we simply call
+ * vmci_dispatch_dgs(), since we know the interrupt was meant for us.
* Otherwise we must read the ICR to determine what to do.
*/
if (dev->exclusive_vectors) {
- tasklet_schedule(&dev->datagram_tasklet);
+ vmci_dispatch_dgs(dev);
} else {
unsigned int icr;
return IRQ_NONE;
if (icr & VMCI_ICR_DATAGRAM) {
- tasklet_schedule(&dev->datagram_tasklet);
+ vmci_dispatch_dgs(dev);
icr &= ~VMCI_ICR_DATAGRAM;
}
if (icr & VMCI_ICR_NOTIFICATION) {
- tasklet_schedule(&dev->bm_tasklet);
+ vmci_process_bitmap(dev);
icr &= ~VMCI_ICR_NOTIFICATION;
}
struct vmci_guest_device *dev = _dev;
/* For MSI-X we can just assume it was meant for us. */
- tasklet_schedule(&dev->bm_tasklet);
+ vmci_process_bitmap(dev);
return IRQ_HANDLED;
}
vmci_dev->iobase = iobase;
vmci_dev->mmio_base = mmio_base;
- tasklet_init(&vmci_dev->datagram_tasklet,
- vmci_dispatch_dgs, (unsigned long)vmci_dev);
- tasklet_init(&vmci_dev->bm_tasklet,
- vmci_process_bitmap, (unsigned long)vmci_dev);
init_waitqueue_head(&vmci_dev->inout_wq);
if (mmio_base != NULL) {
* Request IRQ for legacy or MSI interrupts, or for first
* MSI-X vector.
*/
- error = request_irq(pci_irq_vector(pdev, 0), vmci_interrupt,
- IRQF_SHARED, KBUILD_MODNAME, vmci_dev);
+ error = request_threaded_irq(pci_irq_vector(pdev, 0), NULL,
+ vmci_interrupt, IRQF_SHARED,
+ KBUILD_MODNAME, vmci_dev);
if (error) {
dev_err(&pdev->dev, "Irq %u in use: %d\n",
pci_irq_vector(pdev, 0), error);
* between the vectors.
*/
if (vmci_dev->exclusive_vectors) {
- error = request_irq(pci_irq_vector(pdev, 1),
- vmci_interrupt_bm, 0, KBUILD_MODNAME,
- vmci_dev);
+ error = request_threaded_irq(pci_irq_vector(pdev, 1), NULL,
+ vmci_interrupt_bm, 0,
+ KBUILD_MODNAME, vmci_dev);
if (error) {
dev_err(&pdev->dev,
"Failed to allocate irq %u: %d\n",
goto err_free_irq;
}
if (caps_in_use & VMCI_CAPS_DMA_DATAGRAM) {
- error = request_irq(pci_irq_vector(pdev, 2),
- vmci_interrupt_dma_datagram,
- 0, KBUILD_MODNAME, vmci_dev);
+ error = request_threaded_irq(pci_irq_vector(pdev, 2),
+ NULL,
+ vmci_interrupt_dma_datagram,
+ 0, KBUILD_MODNAME,
+ vmci_dev);
if (error) {
dev_err(&pdev->dev,
"Failed to allocate irq %u: %d\n",
err_free_irq:
free_irq(pci_irq_vector(pdev, 0), vmci_dev);
- tasklet_kill(&vmci_dev->datagram_tasklet);
- tasklet_kill(&vmci_dev->bm_tasklet);
err_disable_msi:
pci_free_irq_vectors(pdev);
free_irq(pci_irq_vector(pdev, 0), vmci_dev);
pci_free_irq_vectors(pdev);
- tasklet_kill(&vmci_dev->datagram_tasklet);
- tasklet_kill(&vmci_dev->bm_tasklet);
-
if (vmci_dev->notification_bitmap) {
/*
* The device reset above cleared the bitmap state of the
if (!(func->card->quirks & MMC_QUIRK_NONSTD_SDIO))
sdio_free_func_cis(func);
+ /*
+ * We have now removed the link to the tuples in the
+ * card structure, so remove the reference.
+ */
+ put_device(&func->card->dev);
+
kfree(func->info);
kfree(func->tmpbuf);
kfree(func);
device_initialize(&func->dev);
+ /*
+ * We may link to tuples in the card structure,
+ * we need make sure we have a reference to it.
+ */
+ get_device(&func->card->dev);
+
func->dev.parent = &card->dev;
func->dev.bus = &sdio_bus_type;
func->dev.release = sdio_release_func;
*/
void sdio_remove_func(struct sdio_func *func)
{
- if (!sdio_func_present(func))
- return;
+ if (sdio_func_present(func))
+ device_del(&func->dev);
- device_del(&func->dev);
of_node_put(func->dev.of_node);
put_device(&func->dev);
}
if (ret)
return ret;
- /*
- * Since we've linked to tuples in the card structure,
- * we must make sure we have a reference to it.
- */
- get_device(&func->card->dev);
-
/*
* Vendor/device id is optional for function CIS, so
* copy it from the card structure as needed.
}
func->tuples = NULL;
-
- /*
- * We have now removed the link to the tuples in the
- * card structure, so remove the reference.
- */
- put_device(&func->card->dev);
}
mmc->ops = &jz4740_mmc_ops;
if (!mmc->f_max)
mmc->f_max = JZ_MMC_CLK_RATE;
+
+ /*
+ * There seems to be a problem with this driver on the JZ4760 and
+ * JZ4760B SoCs. There, when using the maximum rate supported (50 MHz),
+ * the communication fails with many SD cards.
+ * Until this bug is sorted out, limit the maximum rate to 24 MHz.
+ */
+ if (host->version == JZ_MMC_JZ4760 && mmc->f_max > JZ_MMC_CLK_RATE)
+ mmc->f_max = JZ_MMC_CLK_RATE;
+
mmc->f_min = mmc->f_max / 128;
mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
clk_reg |= FIELD_PREP(CLK_CORE_PHASE_MASK, CLK_PHASE_180);
clk_reg |= FIELD_PREP(CLK_TX_PHASE_MASK, CLK_PHASE_0);
clk_reg |= FIELD_PREP(CLK_RX_PHASE_MASK, CLK_PHASE_0);
- clk_reg |= CLK_IRQ_SDIO_SLEEP(host);
+ if (host->mmc->caps & MMC_CAP_SDIO_IRQ)
+ clk_reg |= CLK_IRQ_SDIO_SLEEP(host);
writel(clk_reg, host->regs + SD_EMMC_CLOCK);
/* get the mux parents */
{
struct meson_host *host = dev_id;
struct mmc_command *cmd;
- u32 status, raw_status;
+ u32 status, raw_status, irq_mask = IRQ_EN_MASK;
irqreturn_t ret = IRQ_NONE;
+ if (host->mmc->caps & MMC_CAP_SDIO_IRQ)
+ irq_mask |= IRQ_SDIO;
raw_status = readl(host->regs + SD_EMMC_STATUS);
- status = raw_status & (IRQ_EN_MASK | IRQ_SDIO);
+ status = raw_status & irq_mask;
if (!status) {
dev_dbg(host->dev,
- "Unexpected IRQ! irq_en 0x%08lx - status 0x%08x\n",
- IRQ_EN_MASK | IRQ_SDIO, raw_status);
+ "Unexpected IRQ! irq_en 0x%08x - status 0x%08x\n",
+ irq_mask, raw_status);
return IRQ_NONE;
}
goto free_host;
}
+ mmc->caps |= MMC_CAP_CMD23;
+
+ if (mmc->caps & MMC_CAP_SDIO_IRQ)
+ mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
+
host->data = (struct meson_mmc_data *)
of_device_get_match_data(&pdev->dev);
if (!host->data) {
spin_lock_init(&host->lock);
- mmc->caps |= MMC_CAP_CMD23;
-
- if (mmc->caps & MMC_CAP_SDIO_IRQ)
- mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
-
if (host->dram_access_quirk) {
/* Limit segments to 1 due to low available sram memory */
mmc->max_segs = 1;
status = mmc_add_host(mmc);
if (status != 0)
- goto fail_add_host;
+ goto fail_glue_init;
/*
* Index 0 is card detect
*/
status = mmc_gpiod_request_cd(mmc, NULL, 0, false, 1000);
if (status == -EPROBE_DEFER)
- goto fail_add_host;
+ goto fail_gpiod_request;
if (!status) {
/*
* The platform has a CD GPIO signal that may support
/* Index 1 is write protect/read only */
status = mmc_gpiod_request_ro(mmc, NULL, 1, 0);
if (status == -EPROBE_DEFER)
- goto fail_add_host;
+ goto fail_gpiod_request;
if (!status)
has_ro = true;
? ", cd polling" : "");
return 0;
-fail_add_host:
+fail_gpiod_request:
mmc_remove_host(mmc);
fail_glue_init:
mmc_spi_dma_free(host);
#define ESDHC_TUNING_START_TAP_DEFAULT 0x1
#define ESDHC_TUNING_START_TAP_MASK 0x7f
#define ESDHC_TUNING_CMD_CRC_CHECK_DISABLE (1 << 7)
+#define ESDHC_TUNING_STEP_DEFAULT 0x1
#define ESDHC_TUNING_STEP_MASK 0x00070000
#define ESDHC_TUNING_STEP_SHIFT 16
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
struct cqhci_host *cq_host = host->mmc->cqe_private;
- int tmp;
+ u32 tmp;
if (esdhc_is_usdhc(imx_data)) {
/*
if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
tmp = readl(host->ioaddr + ESDHC_TUNING_CTRL);
- tmp |= ESDHC_STD_TUNING_EN |
- ESDHC_TUNING_START_TAP_DEFAULT;
- if (imx_data->boarddata.tuning_start_tap) {
- tmp &= ~ESDHC_TUNING_START_TAP_MASK;
+ tmp |= ESDHC_STD_TUNING_EN;
+
+ /*
+ * ROM code or bootloader may config the start tap
+ * and step, unmask them first.
+ */
+ tmp &= ~(ESDHC_TUNING_START_TAP_MASK | ESDHC_TUNING_STEP_MASK);
+ if (imx_data->boarddata.tuning_start_tap)
tmp |= imx_data->boarddata.tuning_start_tap;
- }
+ else
+ tmp |= ESDHC_TUNING_START_TAP_DEFAULT;
if (imx_data->boarddata.tuning_step) {
- tmp &= ~ESDHC_TUNING_STEP_MASK;
tmp |= imx_data->boarddata.tuning_step
<< ESDHC_TUNING_STEP_SHIFT;
+ } else {
+ tmp |= ESDHC_TUNING_STEP_DEFAULT
+ << ESDHC_TUNING_STEP_SHIFT;
}
/* Disable the CMD CRC check for tuning, if not, need to
struct sunxi_mmc_host *host = mmc_priv(mmc);
mmc_remove_host(mmc);
- pm_runtime_force_suspend(&pdev->dev);
- disable_irq(host->irq);
- sunxi_mmc_disable(host);
+ pm_runtime_disable(&pdev->dev);
+ if (!pm_runtime_status_suspended(&pdev->dev)) {
+ disable_irq(host->irq);
+ sunxi_mmc_disable(host);
+ }
dma_free_coherent(&pdev->dev, PAGE_SIZE, host->sg_cpu, host->sg_dma);
mmc_free_host(mmc);
int cnt = 0;
int res = 0;
int res2;
- loff_t offs;
+ uint32_t offs;
size_t retlen;
struct sc_part_desc *pdesc = NULL;
struct sc_part_desc *tmpdesc;
buf = mtd_parser_tplink_safeloader_read_table(mtd);
if (!buf) {
err = -ENOENT;
- goto err_out;
+ goto err_free_parts;
}
for (idx = 0, offset = TPLINK_SAFELOADER_DATA_OFFSET;
err_free:
for (idx -= 1; idx >= 0; idx--)
kfree(parts[idx].name);
+err_free_parts:
+ kfree(parts);
err_out:
return err;
};
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/module.h>
+#include <linux/delay.h>
#include <linux/device.h>
#include <linux/mutex.h>
#include <linux/math64.h>
slave_err(bond->dev, port->slave->dev,
"Port %d did not find a suitable aggregator\n",
port->actor_port_number);
+ return;
}
}
/* if all aggregator's ports are READY_N == TRUE, set ready=TRUE
d = debugfs_rename(bonding_debug_root, bond->debug_dir,
bonding_debug_root, bond->dev->name);
- if (d) {
+ if (!IS_ERR(d)) {
bond->debug_dir = d;
} else {
netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n");
static void bond_miimon_commit(struct bonding *bond)
{
- struct slave *slave, *primary;
+ struct slave *slave, *primary, *active;
bool do_failover = false;
struct list_head *iter;
+ ASSERT_RTNL();
+
bond_for_each_slave(bond, slave, iter) {
switch (slave->link_new_state) {
case BOND_LINK_NOCHANGE:
bond_miimon_link_change(bond, slave, BOND_LINK_UP);
- if (!rcu_access_pointer(bond->curr_active_slave) || slave == primary ||
- slave->prio > rcu_dereference(bond->curr_active_slave)->prio)
+ active = rtnl_dereference(bond->curr_active_slave);
+ if (!active || slave == primary || slave->prio > active->prio)
do_failover = true;
continue;
priv->rx_obj_num = layout.cur_rx;
priv->rx_obj_num_coalesce_irq = layout.rx_coalesce;
priv->tx->obj_num = layout.cur_tx;
+ priv->tx_obj_num_coalesce_irq = layout.tx_coalesce;
return 0;
}
the xrx200 / VR9 SoC.
config NET_DSA_MT7530
- tristate "MediaTek MT753x and MT7621 Ethernet switch support"
+ tristate "MediaTek MT7530 and MT7531 Ethernet switch support"
select NET_DSA_TAG_MTK
select MEDIATEK_GE_PHY
help
- This enables support for the MediaTek MT7530, MT7531, and MT7621
- Ethernet switch chips.
+ This enables support for the MediaTek MT7530 and MT7531 Ethernet
+ switch chips. Multi-chip module MT7530 in MT7621AT, MT7621DAT,
+ MT7621ST and MT7623AI SoCs is supported.
config NET_DSA_MV88E6060
tristate "Marvell 88E6060 ethernet switch chip support"
ksz_read32(dev, REG_SW_ALU_VAL_D, &alu_table[3]);
/* clear forwarding port */
- alu_table[2] &= ~BIT(port);
+ alu_table[1] &= ~BIT(port);
/* if there is no port to forward, clear table */
- if ((alu_table[2] & ALU_V_PORT_MAP) == 0) {
+ if ((alu_table[1] & ALU_V_PORT_MAP) == 0) {
alu_table[0] = 0;
alu_table[1] = 0;
alu_table[2] = 0;
},
{
.compatible = "microchip,ksz8563",
- .data = &ksz_switch_chips[KSZ9893]
+ .data = &ksz_switch_chips[KSZ8563]
},
{
.compatible = "microchip,ksz9567",
if (!priv->ports[port].pvid)
mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
MT7530_VLAN_ACC_TAGGED);
- }
- /* Set the port as a user port which is to be able to recognize VID
- * from incoming packets before fetching entry within the VLAN table.
- */
- mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
- VLAN_ATTR(MT7530_VLAN_USER) |
- PVC_EG_TAG(MT7530_VLAN_EG_DISABLED));
+ /* Set the port as a user port which is to be able to recognize
+ * VID from incoming packets before fetching entry within the
+ * VLAN table.
+ */
+ mt7530_rmw(priv, MT7530_PVC_P(port),
+ VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
+ VLAN_ATTR(MT7530_VLAN_USER) |
+ PVC_EG_TAG(MT7530_VLAN_EG_DISABLED));
+ } else {
+ /* Also set CPU ports to the "user" VLAN port attribute, to
+ * allow VLAN classification, but keep the EG_TAG attribute as
+ * "consistent" (i.o.w. don't change its value) for packets
+ * received by the switch from the CPU, so that tagged packets
+ * are forwarded to user ports as tagged, and untagged as
+ * untagged.
+ */
+ mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
+ VLAN_ATTR(MT7530_VLAN_USER));
+ }
}
static void
config NET_DSA_MV88E6XXX
tristate "Marvell 88E6xxx Ethernet switch fabric support"
depends on NET_DSA
- depends on PTP_1588_CLOCK_OPTIONAL
select IRQ_DOMAIN
select NET_DSA_TAG_EDSA
select NET_DSA_TAG_DSA
config NET_DSA_MV88E6XXX_PTP
bool "PTP support for Marvell 88E6xxx"
default n
- depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK
+ depends on (NET_DSA_MV88E6XXX = y && PTP_1588_CLOCK = y) || \
+ (NET_DSA_MV88E6XXX = m && PTP_1588_CLOCK)
help
Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch
chips that support it.
}
static int
-qca8k_set_lo(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 lo)
+qca8k_mii_write_lo(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
{
- u16 *cached_lo = &priv->mdio_cache.lo;
- struct mii_bus *bus = priv->bus;
int ret;
+ u16 lo;
- if (lo == *cached_lo)
- return 0;
-
+ lo = val & 0xffff;
ret = bus->write(bus, phy_id, regnum, lo);
if (ret < 0)
dev_err_ratelimited(&bus->dev,
"failed to write qca8k 32bit lo register\n");
- *cached_lo = lo;
- return 0;
+ return ret;
}
static int
-qca8k_set_hi(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 hi)
+qca8k_mii_write_hi(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
{
- u16 *cached_hi = &priv->mdio_cache.hi;
- struct mii_bus *bus = priv->bus;
int ret;
+ u16 hi;
- if (hi == *cached_hi)
- return 0;
-
+ hi = (u16)(val >> 16);
ret = bus->write(bus, phy_id, regnum, hi);
if (ret < 0)
dev_err_ratelimited(&bus->dev,
"failed to write qca8k 32bit hi register\n");
- *cached_hi = hi;
- return 0;
+ return ret;
}
static int
-qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+qca8k_mii_read_lo(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
{
int ret;
ret = bus->read(bus, phy_id, regnum);
- if (ret >= 0) {
- *val = ret;
- ret = bus->read(bus, phy_id, regnum + 1);
- *val |= ret << 16;
- }
+ if (ret < 0)
+ goto err;
- if (ret < 0) {
- dev_err_ratelimited(&bus->dev,
- "failed to read qca8k 32bit register\n");
- *val = 0;
- return ret;
- }
+ *val = ret & 0xffff;
+ return 0;
+
+err:
+ dev_err_ratelimited(&bus->dev,
+ "failed to read qca8k 32bit lo register\n");
+ *val = 0;
+
+ return ret;
+}
+static int
+qca8k_mii_read_hi(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+{
+ int ret;
+
+ ret = bus->read(bus, phy_id, regnum);
+ if (ret < 0)
+ goto err;
+
+ *val = ret << 16;
return 0;
+
+err:
+ dev_err_ratelimited(&bus->dev,
+ "failed to read qca8k 32bit hi register\n");
+ *val = 0;
+
+ return ret;
}
-static void
-qca8k_mii_write32(struct qca8k_priv *priv, int phy_id, u32 regnum, u32 val)
+static int
+qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
{
- u16 lo, hi;
+ u32 hi, lo;
int ret;
- lo = val & 0xffff;
- hi = (u16)(val >> 16);
+ *val = 0;
- ret = qca8k_set_lo(priv, phy_id, regnum, lo);
- if (ret >= 0)
- ret = qca8k_set_hi(priv, phy_id, regnum + 1, hi);
+ ret = qca8k_mii_read_lo(bus, phy_id, regnum, &lo);
+ if (ret < 0)
+ goto err;
+
+ ret = qca8k_mii_read_hi(bus, phy_id, regnum + 1, &hi);
+ if (ret < 0)
+ goto err;
+
+ *val = lo | hi;
+
+err:
+ return ret;
+}
+
+static void
+qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
+{
+ if (qca8k_mii_write_lo(bus, phy_id, regnum, val) < 0)
+ return;
+
+ qca8k_mii_write_hi(bus, phy_id, regnum + 1, val);
}
static int
command = get_unaligned_le32(&mgmt_ethhdr->command);
cmd = FIELD_GET(QCA_HDR_MGMT_CMD, command);
+
len = FIELD_GET(QCA_HDR_MGMT_LENGTH, command);
+ /* Special case for len of 15 as this is the max value for len and needs to
+ * be increased before converting it from word to dword.
+ */
+ if (len == 15)
+ len++;
+
+ /* We can ignore odd value, we always round up them in the alloc function. */
+ len *= sizeof(u16);
/* Make sure the seq match the requested packet */
if (get_unaligned_le32(&mgmt_ethhdr->seq) == mgmt_eth_data->seq)
if (!skb)
return NULL;
- /* Max value for len reg is 15 (0xf) but the switch actually return 16 byte
- * Actually for some reason the steps are:
- * 0: nothing
- * 1-4: first 4 byte
- * 5-6: first 12 byte
- * 7-15: all 16 byte
+ /* Hdr mgmt length value is in step of word size.
+ * As an example to process 4 byte of data the correct length to set is 2.
+ * To process 8 byte 4, 12 byte 6, 16 byte 8...
+ *
+ * Odd values will always return the next size on the ack packet.
+ * (length of 3 (6 byte) will always return 8 bytes of data)
+ *
+ * This means that a value of 15 (0xf) actually means reading/writing 32 bytes
+ * of data.
+ *
+ * To correctly calculate the length we devide the requested len by word and
+ * round up.
+ * On the ack function we can skip the odd check as we already handle the
+ * case here.
*/
- if (len == 16)
- real_len = 15;
- else
- real_len = len;
+ real_len = DIV_ROUND_UP(len, sizeof(u16));
+
+ /* We check if the result len is odd and we round up another time to
+ * the next size. (length of 3 will be increased to 4 as switch will always
+ * return 8 bytes)
+ */
+ if (real_len % sizeof(u16) != 0)
+ real_len++;
+
+ /* Max reg value is 0xf(15) but switch will always return the next size (32 byte) */
+ if (real_len == 16)
+ real_len--;
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->len);
if (ret < 0)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
exit:
mutex_unlock(&bus->mdio_lock);
val &= ~mask;
val |= write_val;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
exit:
mutex_unlock(&bus->mdio_lock);
qca8k_split_addr(reg, &r1, &r2, &page);
- ret = read_poll_timeout(qca8k_mii_read32, ret1, !(val & mask), 0,
+ ret = read_poll_timeout(qca8k_mii_read_hi, ret1, !(val & mask), 0,
QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false,
- bus, 0x10 | r2, r1, &val);
+ bus, 0x10 | r2, r1 + 1, &val);
/* Check if qca8k_read has failed for a different reason
* before returnting -ETIMEDOUT
if (ret)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, 0);
mutex_unlock(&bus->mdio_lock);
if (ret)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
if (ret)
goto exit;
- ret = qca8k_mii_read32(bus, 0x10 | r2, r1, &val);
+ ret = qca8k_mii_read_lo(bus, 0x10 | r2, r1, &val);
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, 0);
mutex_unlock(&bus->mdio_lock);
}
priv->mdio_cache.page = 0xffff;
- priv->mdio_cache.lo = 0xffff;
- priv->mdio_cache.hi = 0xffff;
/* Check the detected switch id */
ret = qca8k_read_switch_id(priv);
* mdio writes
*/
u16 page;
-/* lo and hi can also be cached and from Documentation we can skip one
- * extra mdio write if lo or hi is didn't change.
- */
- u16 lo;
- u16 hi;
};
struct qca8k_pcs {
if ((port_priv->flags & IFF_ALLMULTI && rxb->pkt_type == PACKET_MULTICAST) ||
(port_priv->flags & IFF_BROADCAST && rxb->pkt_type == PACKET_BROADCAST))
- rxb->offload_fwd_mark = 1;
+ rxb->offload_fwd_mark = port_priv->priv->forwarding;
netif_rx(rxb);
return -EOPNOTSUPP;
}
- switch (func) {
- case ENA_ADMIN_TOEPLITZ:
- if (key) {
- if (key_len != sizeof(hash_key->key)) {
- netdev_err(ena_dev->net_device,
- "key len (%u) doesn't equal the supported size (%zu)\n",
- key_len, sizeof(hash_key->key));
- return -EINVAL;
- }
- memcpy(hash_key->key, key, key_len);
- rss->hash_init_val = init_val;
- hash_key->key_parts = key_len / sizeof(hash_key->key[0]);
+ if ((func == ENA_ADMIN_TOEPLITZ) && key) {
+ if (key_len != sizeof(hash_key->key)) {
+ netdev_err(ena_dev->net_device,
+ "key len (%u) doesn't equal the supported size (%zu)\n",
+ key_len, sizeof(hash_key->key));
+ return -EINVAL;
}
- break;
- case ENA_ADMIN_CRC32:
- rss->hash_init_val = init_val;
- break;
- default:
- netdev_err(ena_dev->net_device, "Invalid hash function (%d)\n",
- func);
- return -EINVAL;
+ memcpy(hash_key->key, key, key_len);
+ hash_key->key_parts = key_len / sizeof(hash_key->key[0]);
}
+ rss->hash_init_val = init_val;
old_func = rss->hash_func;
rss->hash_func = func;
rc = ena_com_set_hash_function(ena_dev);
switch (tuna->id) {
case ETHTOOL_RX_COPYBREAK:
len = *(u32 *)data;
- if (len > adapter->netdev->mtu) {
- ret = -EINVAL;
- break;
- }
- adapter->rx_copybreak = len;
+ ret = ena_set_rx_copybreak(adapter, len);
break;
default:
ret = -EINVAL;
static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
{
+ u32 verdict = ENA_XDP_PASS;
struct bpf_prog *xdp_prog;
struct ena_ring *xdp_ring;
- u32 verdict = XDP_PASS;
struct xdp_frame *xdpf;
u64 *xdp_stat;
if (unlikely(!xdpf)) {
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
- verdict = XDP_ABORTED;
+ verdict = ENA_XDP_DROP;
break;
}
spin_unlock(&xdp_ring->xdp_tx_lock);
xdp_stat = &rx_ring->rx_stats.xdp_tx;
+ verdict = ENA_XDP_TX;
break;
case XDP_REDIRECT:
if (likely(!xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))) {
xdp_stat = &rx_ring->rx_stats.xdp_redirect;
+ verdict = ENA_XDP_REDIRECT;
break;
}
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
- verdict = XDP_ABORTED;
+ verdict = ENA_XDP_DROP;
break;
case XDP_ABORTED:
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
+ verdict = ENA_XDP_DROP;
break;
case XDP_DROP:
xdp_stat = &rx_ring->rx_stats.xdp_drop;
+ verdict = ENA_XDP_DROP;
break;
case XDP_PASS:
xdp_stat = &rx_ring->rx_stats.xdp_pass;
+ verdict = ENA_XDP_PASS;
break;
default:
bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_invalid;
+ verdict = ENA_XDP_DROP;
}
ena_increase_stat(xdp_stat, 1, &rx_ring->syncp);
struct bpf_prog *prog,
int first, int count)
{
+ struct bpf_prog *old_bpf_prog;
struct ena_ring *rx_ring;
int i = 0;
for (i = first; i < count; i++) {
rx_ring = &adapter->rx_ring[i];
- xchg(&rx_ring->xdp_bpf_prog, prog);
- if (prog) {
+ old_bpf_prog = xchg(&rx_ring->xdp_bpf_prog, prog);
+
+ if (!old_bpf_prog && prog) {
ena_xdp_register_rxq_info(rx_ring);
rx_ring->rx_headroom = XDP_PACKET_HEADROOM;
- } else {
+ } else if (old_bpf_prog && !prog) {
ena_xdp_unregister_rxq_info(rx_ring);
rx_ring->rx_headroom = NET_SKB_PAD;
}
ring->ena_dev = adapter->ena_dev;
ring->per_napi_packets = 0;
ring->cpu = 0;
+ ring->numa_node = 0;
ring->no_interrupt_event_cnt = 0;
u64_stats_init(&ring->syncp);
}
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
tx_ring->cpu = ena_irq->cpu;
+ tx_ring->numa_node = node;
return 0;
err_push_buf_intermediate_buf:
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
rx_ring->cpu = ena_irq->cpu;
+ rx_ring->numa_node = node;
return 0;
}
* we expect, then we simply drop it
*/
if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU))
- return XDP_DROP;
+ return ENA_XDP_DROP;
ret = ena_xdp_execute(rx_ring, xdp);
/* The xdp program might expand the headers */
- if (ret == XDP_PASS) {
+ if (ret == ENA_XDP_PASS) {
rx_info->page_offset = xdp->data - xdp->data_hard_start;
rx_ring->ena_bufs[0].len = xdp->data_end - xdp->data;
}
xdp_init_buff(&xdp, ENA_PAGE_SIZE, &rx_ring->xdp_rxq);
do {
- xdp_verdict = XDP_PASS;
+ xdp_verdict = ENA_XDP_PASS;
skb = NULL;
ena_rx_ctx.ena_bufs = rx_ring->ena_bufs;
ena_rx_ctx.max_bufs = rx_ring->sgl_size;
xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp);
/* allocate skb and fill it */
- if (xdp_verdict == XDP_PASS)
+ if (xdp_verdict == ENA_XDP_PASS)
skb = ena_rx_skb(rx_ring,
rx_ring->ena_bufs,
ena_rx_ctx.descs,
/* Packets was passed for transmission, unmap it
* from RX side.
*/
- if (xdp_verdict == XDP_TX || xdp_verdict == XDP_REDIRECT) {
+ if (xdp_verdict & ENA_XDP_FORWARDED) {
ena_unmap_rx_buff(rx_ring,
&rx_ring->rx_buffer_info[req_id]);
rx_ring->rx_buffer_info[req_id].page = NULL;
}
}
- if (xdp_verdict != XDP_PASS) {
+ if (xdp_verdict != ENA_XDP_PASS) {
xdp_flags |= xdp_verdict;
+ total_len += ena_rx_ctx.ena_bufs[0].len;
res_budget--;
continue;
}
ena_refill_rx_bufs(rx_ring, refill_required);
}
- if (xdp_flags & XDP_REDIRECT)
+ if (xdp_flags & ENA_XDP_REDIRECT)
xdp_do_flush_map();
return work_done;
static void ena_unmask_interrupt(struct ena_ring *tx_ring,
struct ena_ring *rx_ring)
{
+ u32 rx_interval = tx_ring->smoothed_interval;
struct ena_eth_io_intr_reg intr_reg;
- u32 rx_interval = 0;
+
/* Rx ring can be NULL when for XDP tx queues which don't have an
* accompanying rx_ring pair.
*/
if (likely(tx_ring->cpu == cpu))
goto out;
+ tx_ring->cpu = cpu;
+ if (rx_ring)
+ rx_ring->cpu = cpu;
+
numa_node = cpu_to_node(cpu);
+
+ if (likely(tx_ring->numa_node == numa_node))
+ goto out;
+
put_cpu();
if (numa_node != NUMA_NO_NODE) {
ena_com_update_numa_node(tx_ring->ena_com_io_cq, numa_node);
- if (rx_ring)
+ tx_ring->numa_node = numa_node;
+ if (rx_ring) {
+ rx_ring->numa_node = numa_node;
ena_com_update_numa_node(rx_ring->ena_com_io_cq,
numa_node);
+ }
}
- tx_ring->cpu = cpu;
- if (rx_ring)
- rx_ring->cpu = cpu;
-
return;
out:
put_cpu();
if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev))
ena_adjust_adaptive_rx_intr_moderation(ena_napi);
+ ena_update_ring_numa_node(tx_ring, rx_ring);
ena_unmask_interrupt(tx_ring, rx_ring);
}
- ena_update_ring_numa_node(tx_ring, rx_ring);
-
ret = rx_work_done;
} else {
ret = budget;
ctx.mem_queue_type = ena_dev->tx_mem_queue_type;
ctx.msix_vector = msix_vector;
ctx.queue_size = tx_ring->ring_size;
- ctx.numa_node = cpu_to_node(tx_ring->cpu);
+ ctx.numa_node = tx_ring->numa_node;
rc = ena_com_create_io_queue(ena_dev, &ctx);
if (rc) {
ctx.mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST;
ctx.msix_vector = msix_vector;
ctx.queue_size = rx_ring->ring_size;
- ctx.numa_node = cpu_to_node(rx_ring->cpu);
+ ctx.numa_node = rx_ring->numa_node;
rc = ena_com_create_io_queue(ena_dev, &ctx);
if (rc) {
return dev_was_up ? ena_up(adapter) : 0;
}
+int ena_set_rx_copybreak(struct ena_adapter *adapter, u32 rx_copybreak)
+{
+ struct ena_ring *rx_ring;
+ int i;
+
+ if (rx_copybreak > min_t(u16, adapter->netdev->mtu, ENA_PAGE_SIZE))
+ return -EINVAL;
+
+ adapter->rx_copybreak = rx_copybreak;
+
+ for (i = 0; i < adapter->num_io_queues; i++) {
+ rx_ring = &adapter->rx_ring[i];
+ rx_ring->rx_copybreak = rx_copybreak;
+ }
+
+ return 0;
+}
+
int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count)
{
struct ena_com_dev *ena_dev = adapter->ena_dev;
bool disable_meta_caching;
u16 no_interrupt_event_cnt;
- /* cpu for TPH */
+ /* cpu and NUMA for TPH */
int cpu;
- /* number of tx/rx_buffer_info's entries */
+ int numa_node;
+
+ /* number of tx/rx_buffer_info's entries */
int ring_size;
enum ena_admin_placement_policy_type tx_mem_queue_type;
int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count);
+int ena_set_rx_copybreak(struct ena_adapter *adapter, u32 rx_copybreak);
+
int ena_get_sset_count(struct net_device *netdev, int sset);
static inline void ena_reset_device(struct ena_adapter *adapter,
ENA_XDP_NO_ENOUGH_QUEUES,
};
+enum ENA_XDP_ACTIONS {
+ ENA_XDP_PASS = 0,
+ ENA_XDP_TX = BIT(0),
+ ENA_XDP_REDIRECT = BIT(1),
+ ENA_XDP_DROP = BIT(2)
+};
+
+#define ENA_XDP_FORWARDED (ENA_XDP_TX | ENA_XDP_REDIRECT)
+
static inline bool ena_xdp_present(struct ena_adapter *adapter)
{
return !!adapter->xdp_bpf_prog;
netif_dbg(pdata, drv, pdata->netdev, "VXLAN acceleration disabled\n");
}
+static unsigned int xgbe_get_fc_queue_count(struct xgbe_prv_data *pdata)
+{
+ unsigned int max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES;
+
+ /* From MAC ver 30H the TFCR is per priority, instead of per queue */
+ if (XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER) >= 0x30)
+ return max_q_count;
+ else
+ return min_t(unsigned int, pdata->tx_q_count, max_q_count);
+}
+
static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata)
{
- unsigned int max_q_count, q_count;
unsigned int reg, reg_val;
- unsigned int i;
+ unsigned int i, q_count;
/* Clear MTL flow control */
for (i = 0; i < pdata->rx_q_count; i++)
XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, 0);
/* Clear MAC flow control */
- max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES;
- q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+ q_count = xgbe_get_fc_queue_count(pdata);
reg = MAC_Q0TFCR;
for (i = 0; i < q_count; i++) {
reg_val = XGMAC_IOREAD(pdata, reg);
{
struct ieee_pfc *pfc = pdata->pfc;
struct ieee_ets *ets = pdata->ets;
- unsigned int max_q_count, q_count;
unsigned int reg, reg_val;
- unsigned int i;
+ unsigned int i, q_count;
/* Set MTL flow control */
for (i = 0; i < pdata->rx_q_count; i++) {
}
/* Set MAC flow control */
- max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES;
- q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+ q_count = xgbe_get_fc_queue_count(pdata);
reg = MAC_Q0TFCR;
for (i = 0; i < q_count; i++) {
reg_val = XGMAC_IOREAD(pdata, reg);
devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+ tasklet_kill(&pdata->tasklet_dev);
+ tasklet_kill(&pdata->tasklet_ecc);
+
if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq))
devm_free_irq(pdata->dev, pdata->ecc_irq, pdata);
xgbe_i2c_disable(pdata);
xgbe_i2c_clear_all_interrupts(pdata);
- if (pdata->dev_irq != pdata->i2c_irq)
+ if (pdata->dev_irq != pdata->i2c_irq) {
devm_free_irq(pdata->dev, pdata->i2c_irq, pdata);
+ tasklet_kill(&pdata->tasklet_i2c);
+ }
}
static int xgbe_i2c_start(struct xgbe_prv_data *pdata)
reg |= XGBE_KR_TRAINING_ENABLE;
reg |= XGBE_KR_TRAINING_START;
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg);
+ pdata->kr_start_time = jiffies;
netif_dbg(pdata, link, pdata->netdev,
"KR training initiated\n");
xgbe_switch_mode(pdata);
+ pdata->an_result = XGBE_AN_READY;
+
xgbe_an_restart(pdata);
return XGBE_AN_INCOMPAT_LINK;
static void xgbe_check_link_timeout(struct xgbe_prv_data *pdata)
{
unsigned long link_timeout;
+ unsigned long kr_time;
+ int wait;
link_timeout = pdata->link_check + (XGBE_LINK_TIMEOUT * HZ);
if (time_after(jiffies, link_timeout)) {
+ if ((xgbe_cur_mode(pdata) == XGBE_MODE_KR) &&
+ pdata->phy.autoneg == AUTONEG_ENABLE) {
+ /* AN restart should not happen while KR training is in progress.
+ * The while loop ensures no AN restart during KR training,
+ * waits up to 500ms and AN restart is triggered only if KR
+ * training is failed.
+ */
+ wait = XGBE_KR_TRAINING_WAIT_ITER;
+ while (wait--) {
+ kr_time = pdata->kr_start_time +
+ msecs_to_jiffies(XGBE_AN_MS_TIMEOUT);
+ if (time_after(jiffies, kr_time))
+ break;
+ /* AN restart is not required, if AN result is COMPLETE */
+ if (pdata->an_result == XGBE_AN_COMPLETE)
+ return;
+ usleep_range(10000, 11000);
+ }
+ }
netif_dbg(pdata, link, pdata->netdev, "AN link timeout\n");
xgbe_phy_config_aneg(pdata);
}
/* Disable auto-negotiation */
xgbe_an_disable_all(pdata);
- if (pdata->dev_irq != pdata->an_irq)
+ if (pdata->dev_irq != pdata->an_irq) {
devm_free_irq(pdata->dev, pdata->an_irq, pdata);
+ tasklet_kill(&pdata->tasklet_an);
+ }
pdata->phy_if.phy_impl.stop(pdata);
/* Auto-negotiation */
#define XGBE_AN_MS_TIMEOUT 500
#define XGBE_LINK_TIMEOUT 5
+#define XGBE_KR_TRAINING_WAIT_ITER 50
#define XGBE_SGMII_AN_LINK_STATUS BIT(1)
#define XGBE_SGMII_AN_LINK_SPEED (BIT(2) | BIT(3))
unsigned int parallel_detect;
unsigned int fec_ability;
unsigned long an_start;
+ unsigned long kr_start_time;
enum xgbe_an_mode an_mode;
/* I2C support */
return 0;
}
-static int bcm_enet_shared_remove(struct platform_device *pdev)
-{
- return 0;
-}
-
/* this "shared" driver is needed because both macs share a single
* address space
*/
struct platform_driver bcm63xx_enet_shared_driver = {
.probe = bcm_enet_shared_probe,
- .remove = bcm_enet_shared_remove,
.driver = {
.name = "bcm63xx_enet_shared",
.owner = THIS_MODULE,
bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1;
bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY;
- if (ci->pkg == BCMA_PKG_ID_BCM47188 ||
- ci->pkg == BCMA_PKG_ID_BCM47186) {
+ if ((ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM47186) ||
+ (ci->id == BCMA_CHIP_ID_BCM53572 && ci->pkg == BCMA_PKG_ID_BCM47188)) {
bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII;
bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
}
- if (ci->pkg == BCMA_PKG_ID_BCM5358)
+ if (ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM5358)
bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII;
break;
case BCMA_CHIP_ID_BCM53573:
dma_addr -= bp->rx_dma_offset;
dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir,
DMA_ATTR_WEAK_ORDERING);
- skb = build_skb(page_address(page), BNXT_PAGE_MODE_BUF_SIZE +
- bp->rx_dma_offset);
+ skb = build_skb(page_address(page), PAGE_SIZE);
if (!skb) {
- __free_page(page);
+ page_pool_recycle_direct(rxr->page_pool, page);
return NULL;
}
skb_mark_for_recycle(skb);
skb = napi_alloc_skb(&rxr->bnapi->napi, payload);
if (!skb) {
- __free_page(page);
+ page_pool_recycle_direct(rxr->page_pool, page);
return NULL;
}
dma_addr = rx_buf->mapping;
if (bnxt_xdp_attached(bp, rxr)) {
- bnxt_xdp_buff_init(bp, rxr, cons, &data_ptr, &len, &xdp);
+ bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
if (agg_bufs) {
u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
cp_cons, agg_bufs,
}
if (xdp_active) {
- if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &len, event)) {
+ if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &data_ptr, &len, event)) {
rc = 1;
goto next_rx;
}
bp->rx_agg_ring_mask = (bp->rx_agg_nr_pages * RX_DESC_CNT) - 1;
if (BNXT_RX_PAGE_MODE(bp)) {
- rx_space = BNXT_PAGE_MODE_BUF_SIZE;
- rx_size = BNXT_MAX_PAGE_MODE_MTU;
+ rx_space = PAGE_SIZE;
+ rx_size = PAGE_SIZE -
+ ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) -
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
} else {
rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN);
rx_space = rx_size + NET_SKB_PAD +
req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT);
req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID);
- if (BNXT_RX_PAGE_MODE(bp) && !BNXT_RX_JUMBO_MODE(bp)) {
+ if (BNXT_RX_PAGE_MODE(bp)) {
+ req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size);
+ } else {
req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
req->enables |=
cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
+ req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
+ req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
}
- /* thresholds not implemented in firmware yet */
- req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
- req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
return hwrm_req_send(bp, req);
}
netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc);
return rc;
}
- if (tcs && (bp->tx_nr_rings_per_tc * tcs != bp->tx_nr_rings)) {
+ if (tcs && (bp->tx_nr_rings_per_tc * tcs !=
+ bp->tx_nr_rings - bp->tx_nr_rings_xdp)) {
netdev_err(bp->dev, "tx ring reservation failure\n");
netdev_reset_tc(bp->dev);
- bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+ if (bp->tx_nr_rings_xdp)
+ bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp;
+ else
+ bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
return -ENOMEM;
}
return 0;
return -ENOMEM;
bp = netdev_priv(dev);
- SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
bp->board_idx = ent->driver_data;
bp->msg_enable = BNXT_DEF_MSG_ENABLE;
bnxt_set_max_func_irqs(bp, max_irqs);
if (bnxt_vf_pciid(bp->board_idx))
bp->flags |= BNXT_FLAG_VF;
+ /* No devlink port registration in case of a VF */
+ if (BNXT_PF(bp))
+ SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
+
if (pdev->msix_cap)
bp->flags |= BNXT_FLAG_MSIX_CAP;
#define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT)
#define BNXT_MAX_MTU 9500
-#define BNXT_PAGE_MODE_BUF_SIZE \
+
+/* First RX buffer page in XDP multi-buf mode
+ *
+ * +-------------------------------------------------------------------------+
+ * | XDP_PACKET_HEADROOM | bp->rx_buf_use_size | skb_shared_info|
+ * | (bp->rx_dma_offset) | | |
+ * +-------------------------------------------------------------------------+
+ */
+#define BNXT_MAX_PAGE_MODE_MTU_SBUF \
((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \
XDP_PACKET_HEADROOM)
#define BNXT_MAX_PAGE_MODE_MTU \
- BNXT_PAGE_MODE_BUF_SIZE - \
- SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))
+ (BNXT_MAX_PAGE_MODE_MTU_SBUF - \
+ SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info)))
#define BNXT_MIN_PKT_SIZE 52
#define BNXT_DUMP_CRASH 1
struct bpf_prog *xdp_prog;
- u8 xdp_has_frags;
struct bnxt_ptp_cfg *ptp_cfg;
u8 ptp_all_rx_tstamp;
test_info->timeout = HWRM_CMD_TIMEOUT;
for (i = 0; i < bp->num_tests; i++) {
char *str = test_info->string[i];
- char *fw_str = resp->test0_name + i * 32;
+ char *fw_str = resp->test_name[i];
if (i == BNXT_MACLPBK_TEST_IDX) {
strcpy(str, "Mac loopback test (offline)");
} else if (i == BNXT_IRQ_TEST_IDX) {
strcpy(str, "Interrupt_test (offline)");
} else {
- strscpy(str, fw_str, ETH_GSTRING_LEN);
- strncat(str, " test", ETH_GSTRING_LEN - strlen(str));
- if (test_info->offline_mask & (1 << i))
- strncat(str, " (offline)",
- ETH_GSTRING_LEN - strlen(str));
- else
- strncat(str, " (online)",
- ETH_GSTRING_LEN - strlen(str));
+ snprintf(str, ETH_GSTRING_LEN, "%s test (%s)",
+ fw_str, test_info->offline_mask & (1 << i) ?
+ "offline" : "online");
}
}
u8 unused_0;
__le16 test_timeout;
u8 unused_1[2];
- char test0_name[32];
- char test1_name[32];
- char test2_name[32];
- char test3_name[32];
- char test4_name[32];
- char test5_name[32];
- char test6_name[32];
- char test7_name[32];
+ char test_name[8][32];
u8 eyescope_target_BER_support;
#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E8_SUPPORTED 0x0UL
#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E9_SUPPORTED 0x1UL
}
void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
- u16 cons, u8 **data_ptr, unsigned int *len,
+ u16 cons, u8 *data_ptr, unsigned int len,
struct xdp_buff *xdp)
{
struct bnxt_sw_rx_bd *rx_buf;
offset = bp->rx_offset;
mapping = rx_buf->mapping - bp->rx_dma_offset;
- dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
-
- if (bp->xdp_has_frags)
- buflen = BNXT_PAGE_MODE_BUF_SIZE + offset;
+ dma_sync_single_for_cpu(&pdev->dev, mapping + offset, len, bp->rx_dir);
xdp_init_buff(xdp, buflen, &rxr->xdp_rxq);
- xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false);
+ xdp_prepare_buff(xdp, data_ptr - offset, offset, len, false);
}
void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
* false - packet should be passed to the stack.
*/
bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
- struct xdp_buff xdp, struct page *page, unsigned int *len, u8 *event)
+ struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+ unsigned int *len, u8 *event)
{
struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog);
struct bnxt_tx_ring_info *txr;
*event &= ~BNXT_RX_EVENT;
*len = xdp.data_end - xdp.data;
- if (orig_data != xdp.data)
+ if (orig_data != xdp.data) {
offset = xdp.data - xdp.data_hard_start;
+ *data_ptr = xdp.data_hard_start + offset;
+ }
switch (act) {
case XDP_PASS:
netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n");
return -EOPNOTSUPP;
}
- if (prog) {
+ if (prog)
tx_xdp = bp->rx_nr_rings;
- bp->xdp_has_frags = prog->aux->xdp_has_frags;
- }
tc = netdev_get_num_tc(dev);
if (!tc)
struct xdp_buff *xdp);
void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
- struct xdp_buff xdp, struct page *page, unsigned int *len,
- u8 *event);
+ struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+ unsigned int *len, u8 *event);
int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
struct xdp_frame **frames, u32 flags);
bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr);
void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
- u16 cons, u8 **data_ptr, unsigned int *len,
+ u16 cons, u8 *data_ptr, unsigned int len,
struct xdp_buff *xdp);
void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
struct xdp_buff *xdp);
rtnl_lock();
tg3_full_lock(tp, 0);
- if (!netif_running(tp->dev)) {
+ if (tp->pcierr_recovery || !netif_running(tp->dev)) {
tg3_flag_clear(tp, RESET_TASK_PENDING);
tg3_full_unlock(tp);
rtnl_unlock();
netdev_info(netdev, "PCI I/O error detected\n");
+ /* Want to make sure that the reset task doesn't run */
+ tg3_reset_task_cancel(tp);
+
rtnl_lock();
/* Could be second call or maybe we don't have netdev yet */
tg3_timer_stop(tp);
- /* Want to make sure that the reset task doesn't run */
- tg3_reset_task_cancel(tp);
-
netif_device_detach(netdev);
/* Clean up software state, even if MMIO is blocked */
bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) ||
skb_is_nonlinear(*skb);
int padlen = ETH_ZLEN - (*skb)->len;
- int headroom = skb_headroom(*skb);
int tailroom = skb_tailroom(*skb);
struct sk_buff *nskb;
u32 fcs;
/* FCS could be appeded to tailroom. */
if (tailroom >= ETH_FCS_LEN)
goto add_fcs;
- /* FCS could be appeded by moving data to headroom. */
- else if (!cloned && headroom + tailroom >= ETH_FCS_LEN)
- padlen = 0;
/* No room for FCS, need to reallocate skb. */
else
padlen = ETH_FCS_LEN;
padlen += ETH_FCS_LEN;
}
- if (!cloned && headroom + tailroom >= padlen) {
- (*skb)->data = memmove((*skb)->head, (*skb)->data, (*skb)->len);
- skb_set_tail_pointer(*skb, (*skb)->len);
- } else {
+ if (cloned || tailroom < padlen) {
nskb = skb_copy_expand(*skb, 0, padlen, GFP_ATOMIC);
if (!nskb)
return -ENOMEM;
if (ret)
return dev_err_probe(&pdev->dev, ret,
"failed to init SGMII PHY\n");
- }
- ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG);
- if (!ret) {
- u32 pm_info[2];
+ ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG);
+ if (!ret) {
+ u32 pm_info[2];
+
+ ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains",
+ pm_info, ARRAY_SIZE(pm_info));
+ if (ret) {
+ dev_err(&pdev->dev, "Failed to read power management information\n");
+ goto err_out_phy_exit;
+ }
+ ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0);
+ if (ret)
+ goto err_out_phy_exit;
- ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains",
- pm_info, ARRAY_SIZE(pm_info));
- if (ret) {
- dev_err(&pdev->dev, "Failed to read power management information\n");
- goto err_out_phy_exit;
+ ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1);
+ if (ret)
+ goto err_out_phy_exit;
}
- ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0);
- if (ret)
- goto err_out_phy_exit;
- ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1);
- if (ret)
- goto err_out_phy_exit;
}
/* Fully reset controller at hardware level if mapped in device tree */
/* ring full, shall not happen because queue is stopped if full
* below
*/
- netif_stop_queue(tx->adapter->netdev);
+ netif_stop_subqueue(tx->adapter->netdev, tx->queue_index);
spin_unlock_irqrestore(&tx->lock, flags);
if (tsnep_tx_desc_available(tx) < (MAX_SKB_FRAGS + 1)) {
/* ring can get full with next frame */
- netif_stop_queue(tx->adapter->netdev);
+ netif_stop_subqueue(tx->adapter->netdev, tx->queue_index);
}
spin_unlock_irqrestore(&tx->lock, flags);
static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
{
+ struct tsnep_tx_entry *entry;
+ struct netdev_queue *nq;
unsigned long flags;
int budget = 128;
- struct tsnep_tx_entry *entry;
- int count;
int length;
+ int count;
+
+ nq = netdev_get_tx_queue(tx->adapter->netdev, tx->queue_index);
spin_lock_irqsave(&tx->lock, flags);
} while (likely(budget));
if ((tsnep_tx_desc_available(tx) >= ((MAX_SKB_FRAGS + 1) * 2)) &&
- netif_queue_stopped(tx->adapter->netdev)) {
- netif_wake_queue(tx->adapter->netdev);
+ netif_tx_queue_stopped(nq)) {
+ netif_tx_wake_queue(nq);
}
spin_unlock_irqrestore(&tx->lock, flags);
cleaned = qman_p_poll_dqrr(np->p, budget);
+ if (np->xdp_act & XDP_REDIRECT)
+ xdp_do_flush();
+
if (cleaned < budget) {
napi_complete_done(napi, cleaned);
qman_p_irqsource_add(np->p, QM_PIRQ_DQRI);
qman_p_irqsource_add(np->p, QM_PIRQ_DQRI);
}
- if (np->xdp_act & XDP_REDIRECT)
- xdp_do_flush();
-
return cleaned;
}
if (rx_cleaned >= budget ||
txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI) {
work_done = budget;
+ if (ch->xdp.res & XDP_REDIRECT)
+ xdp_do_flush();
goto out;
}
} while (store_cleaned);
+ if (ch->xdp.res & XDP_REDIRECT)
+ xdp_do_flush();
+
/* Update NET DIM with the values for this CDAN */
dpaa2_io_update_net_dim(ch->dpio, ch->stats.frames_per_cdan,
ch->stats.bytes_per_cdan);
txc_fq->dq_bytes = 0;
}
- if (ch->xdp.res & XDP_REDIRECT)
- xdp_do_flush_map();
- else if (rx_cleaned && ch->xdp.res & XDP_TX)
+ if (rx_cleaned && ch->xdp.res & XDP_TX)
dpaa2_eth_xdp_tx_flush(priv, ch, &priv->fq[flowid]);
return work_done;
priv = container_of(work, struct enetc_ndev_priv, tx_onestep_tstamp);
- netif_tx_lock(priv->ndev);
+ netif_tx_lock_bh(priv->ndev);
clear_bit_unlock(ENETC_TX_ONESTEP_TSTAMP_IN_PROGRESS, &priv->flags);
skb = skb_dequeue(&priv->tx_skbs);
if (skb)
enetc_start_xmit(skb, priv->ndev);
- netif_tx_unlock(priv->ndev);
+ netif_tx_unlock_bh(priv->ndev);
}
static void enetc_tx_onestep_tstamp_init(struct enetc_ndev_priv *priv)
return 0;
}
-static int enetc_ierb_remove(struct platform_device *pdev)
-{
- return 0;
-}
-
static const struct of_device_id enetc_ierb_match[] = {
{ .compatible = "fsl,ls1028a-enetc-ierb", },
{},
.of_match_table = enetc_ierb_match,
},
.probe = enetc_ierb_probe,
- .remove = enetc_ierb_remove,
};
module_platform_driver(enetc_ierb_driver);
for (q = 0; q < fep->num_rx_queues; q++) {
rxq = fep->rx_queue[q];
for (i = 0; i < rxq->bd.ring_size; i++)
- page_pool_release_page(rxq->page_pool, rxq->rx_skb_info[i].page);
+ page_pool_put_full_page(rxq->page_pool, rxq->rx_skb_info[i].page, false);
for (i = 0; i < XDP_STATS_TOTAL; i++)
rxq->stats[i] = 0;
dtsec->dtsec_drv_param->tx_pad_crc = true;
phy_node = of_parse_phandle(mac_node, "tbi-handle", 0);
- if (!phy_node || of_device_is_available(phy_node)) {
+ if (!phy_node || !of_device_is_available(phy_node)) {
of_node_put(phy_node);
err = -EINVAL;
dev_err_probe(mac_dev->dev, err,
return ERR_PTR(-EPROBE_DEFER);
pcs = lynx_pcs_create(mdiodev);
+ if (!pcs)
+ mdio_device_free(mdiodev);
+
return pcs;
}
return 0;
}
-static bool hns3_checksum_complete(struct hns3_enet_ring *ring,
+static void hns3_checksum_complete(struct hns3_enet_ring *ring,
struct sk_buff *skb, u32 ptype, u16 csum)
{
if (ptype == HNS3_INVALID_PTYPE ||
hns3_rx_ptype_tbl[ptype].ip_summed != CHECKSUM_COMPLETE)
- return false;
+ return;
hns3_ring_stats_update(ring, csum_complete);
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)csum);
-
- return true;
}
static void hns3_rx_handle_csum(struct sk_buff *skb, u32 l234info,
ptype = hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M,
HNS3_RXD_PTYPE_S);
- if (hns3_checksum_complete(ring, skb, ptype, csum))
- return;
+ hns3_checksum_complete(ring, skb, ptype, csum);
/* check if hardware has done checksum */
if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) |
BIT(HNS3_RXD_OL3E_B) |
BIT(HNS3_RXD_OL4E_B)))) {
+ skb->ip_summed = CHECKSUM_NONE;
hns3_ring_stats_update(ring, l3l4_csum_err);
return;
return ret;
}
- if (!reset || !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ if (!reset ||
+ !test_bit(HCLGE_VPORT_STATE_INITED, &vport->state))
continue;
+ if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state) &&
+ hdev->reset_type == HNAE3_FUNC_RESET) {
+ set_bit(HCLGE_VPORT_NEED_NOTIFY_RESET,
+ &vport->need_notify);
+ continue;
+ }
+
/* Inform VF to process the reset.
* hclge_inform_reset_assert_to_vf may fail if VF
* driver is not loaded.
static void hclge_update_vport_alive(struct hclge_dev *hdev)
{
+#define HCLGE_ALIVE_SECONDS_NORMAL 8
+
+ unsigned long alive_time = HCLGE_ALIVE_SECONDS_NORMAL * HZ;
int i;
/* start from vport 1 for PF is always alive */
for (i = 1; i < hdev->num_alloc_vport; i++) {
struct hclge_vport *vport = &hdev->vport[i];
- if (time_after(jiffies, vport->last_active_jiffies + 8 * HZ))
+ if (!test_bit(HCLGE_VPORT_STATE_INITED, &vport->state) ||
+ !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ continue;
+ if (time_after(jiffies, vport->last_active_jiffies +
+ alive_time)) {
clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
-
- /* If vf is not alive, set to default value */
- if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
- vport->mps = HCLGE_MAC_DEFAULT_FRAME;
+ dev_warn(&hdev->pdev->dev,
+ "VF %u heartbeat timeout\n",
+ i - HCLGE_VF_VPORT_START_NUM);
+ }
}
}
{
struct hclge_dev *hdev = vport->back;
+ set_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
vport->last_active_jiffies = jiffies;
+ vport->need_notify = 0;
if (test_bit(vport->vport_id, hdev->vport_config_block)) {
if (vport->vport_id) {
void hclge_vport_stop(struct hclge_vport *vport)
{
+ clear_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ vport->need_notify = 0;
}
static int hclge_client_start(struct hnae3_handle *handle)
return 0;
}
- dev_info(&hdev->pdev->dev, "MAC of VF %d has been set to %s\n",
+ dev_info(&hdev->pdev->dev,
+ "MAC of VF %d has been set to %s, will be active after VF reset\n",
vf, format_mac_addr);
return 0;
}
* for DEVICE_VERSION_V3, vf doesn't need to know about the port based
* VLAN state.
*/
- if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3 &&
- test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
- (void)hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
- vport->vport_id,
- state, &vlan_info);
-
+ if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) {
+ if (test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ (void)hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+ vport->vport_id,
+ state,
+ &vlan_info);
+ else
+ set_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN,
+ &vport->need_notify);
+ }
return 0;
}
int i;
for (i = 0; i < hdev->num_alloc_vport; i++) {
- hclge_vport_stop(vport);
+ clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
vport++;
}
}
return ret;
}
-static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+static int hclge_sync_vport_promisc_mode(struct hclge_vport *vport)
{
- struct hclge_vport *vport = &hdev->vport[0];
struct hnae3_handle *handle = &vport->nic;
+ struct hclge_dev *hdev = vport->back;
+ bool uc_en = false;
+ bool mc_en = false;
u8 tmp_flags;
+ bool bc_en;
int ret;
- u16 i;
if (vport->last_promisc_flags != vport->overflow_promisc_flags) {
set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
vport->last_promisc_flags = vport->overflow_promisc_flags;
}
- if (test_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state)) {
+ if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+ &vport->state))
+ return 0;
+
+ /* for PF */
+ if (!vport->vport_id) {
tmp_flags = handle->netdev_flags | vport->last_promisc_flags;
ret = hclge_set_promisc_mode(handle, tmp_flags & HNAE3_UPE,
tmp_flags & HNAE3_MPE);
- if (!ret) {
- clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state);
+ if (!ret)
set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
&vport->state);
- }
+ else
+ set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+ &vport->state);
+ return ret;
}
- for (i = 1; i < hdev->num_alloc_vport; i++) {
- bool uc_en = false;
- bool mc_en = false;
- bool bc_en;
+ /* for VF */
+ if (vport->vf_info.trusted) {
+ uc_en = vport->vf_info.request_uc_en > 0 ||
+ vport->overflow_promisc_flags & HNAE3_OVERFLOW_UPE;
+ mc_en = vport->vf_info.request_mc_en > 0 ||
+ vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE;
+ }
+ bc_en = vport->vf_info.request_bc_en > 0;
- vport = &hdev->vport[i];
+ ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
+ mc_en, bc_en);
+ if (ret) {
+ set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
+ return ret;
+ }
+ hclge_set_vport_vlan_fltr_change(vport);
- if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state))
- continue;
+ return 0;
+}
- if (vport->vf_info.trusted) {
- uc_en = vport->vf_info.request_uc_en > 0 ||
- vport->overflow_promisc_flags &
- HNAE3_OVERFLOW_UPE;
- mc_en = vport->vf_info.request_mc_en > 0 ||
- vport->overflow_promisc_flags &
- HNAE3_OVERFLOW_MPE;
- }
- bc_en = vport->vf_info.request_bc_en > 0;
+static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+{
+ struct hclge_vport *vport;
+ int ret;
+ u16 i;
- ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
- mc_en, bc_en);
- if (ret) {
- set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state);
+ for (i = 0; i < hdev->num_alloc_vport; i++) {
+ vport = &hdev->vport[i];
+
+ ret = hclge_sync_vport_promisc_mode(vport);
+ if (ret)
return;
- }
- hclge_set_vport_vlan_fltr_change(vport);
}
}
struct hclge_vlan_info vlan_info;
int ret;
+ clear_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
+ clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ vport->need_notify = 0;
+ vport->mps = 0;
+
/* after disable sriov, clean VF rate configured by PF */
ret = hclge_tm_qs_shaper_cfg(vport, 0);
if (ret)
HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
HCLGE_VPORT_STATE_PROMISC_CHANGE,
HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
+ HCLGE_VPORT_STATE_INITED,
HCLGE_VPORT_STATE_MAX
};
+enum HCLGE_VPORT_NEED_NOTIFY {
+ HCLGE_VPORT_NEED_NOTIFY_RESET,
+ HCLGE_VPORT_NEED_NOTIFY_VF_VLAN,
+};
+
struct hclge_vlan_info {
u16 vlan_proto; /* so far support 802.1Q only */
u16 qos;
struct hnae3_handle roce;
unsigned long state;
+ unsigned long need_notify;
unsigned long last_active_jiffies;
u32 mps; /* Max packet size */
struct hclge_vf_info vf_info;
return status;
}
+static int hclge_inform_vf_reset(struct hclge_vport *vport, u16 reset_type)
+{
+ __le16 msg_data;
+ u8 dest_vfid;
+
+ dest_vfid = (u8)vport->vport_id;
+ msg_data = cpu_to_le16(reset_type);
+
+ /* send this requested info to VF */
+ return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data),
+ HCLGE_MBX_ASSERTING_RESET, dest_vfid);
+}
+
int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
{
struct hclge_dev *hdev = vport->back;
- __le16 msg_data;
u16 reset_type;
- u8 dest_vfid;
BUILD_BUG_ON(HNAE3_MAX_RESET > U16_MAX);
- dest_vfid = (u8)vport->vport_id;
-
if (hdev->reset_type == HNAE3_FUNC_RESET)
reset_type = HNAE3_VF_PF_FUNC_RESET;
else if (hdev->reset_type == HNAE3_FLR_RESET)
else
reset_type = HNAE3_VF_FUNC_RESET;
- msg_data = cpu_to_le16(reset_type);
-
- /* send this requested info to VF */
- return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data),
- HCLGE_MBX_ASSERTING_RESET, dest_vfid);
+ return hclge_inform_vf_reset(vport, reset_type);
}
static void hclge_free_vector_ring_chain(struct hnae3_ring_chain_node *head)
return hclge_func_reset_cmd(hdev, vport->vport_id);
}
+static void hclge_notify_vf_config(struct hclge_vport *vport)
+{
+ struct hclge_dev *hdev = vport->back;
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+ struct hclge_port_base_vlan_config *vlan_cfg;
+ int ret;
+
+ hclge_push_vf_link_status(vport);
+ if (test_bit(HCLGE_VPORT_NEED_NOTIFY_RESET, &vport->need_notify)) {
+ ret = hclge_inform_vf_reset(vport, HNAE3_VF_PF_FUNC_RESET);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "failed to inform VF %u reset!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ return;
+ }
+ vport->need_notify = 0;
+ return;
+ }
+
+ if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3 &&
+ test_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN, &vport->need_notify)) {
+ vlan_cfg = &vport->port_base_vlan_cfg;
+ ret = hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+ vport->vport_id,
+ vlan_cfg->state,
+ &vlan_cfg->vlan_info);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "failed to inform VF %u port base vlan!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ return;
+ }
+ clear_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN, &vport->need_notify);
+ }
+}
+
static void hclge_vf_keep_alive(struct hclge_vport *vport)
{
+ struct hclge_dev *hdev = vport->back;
+
vport->last_active_jiffies = jiffies;
+
+ if (test_bit(HCLGE_VPORT_STATE_INITED, &vport->state) &&
+ !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state)) {
+ set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ dev_info(&hdev->pdev->dev, "VF %u is alive!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ hclge_notify_vf_config(vport);
+ }
}
static int hclge_set_vf_mtu(struct hclge_vport *vport,
hclge_rm_vport_all_mac_table(param->vport, true,
HCLGE_MAC_ADDR_MC);
hclge_rm_vport_all_vlan_table(param->vport, true);
+ param->vport->mps = 0;
return 0;
}
struct pci_dev *pdev = hdev->pdev;
int ret = 0;
- if (hdev->reset_type == HNAE3_VF_FULL_RESET &&
+ if ((hdev->reset_type == HNAE3_VF_FULL_RESET ||
+ hdev->reset_type == HNAE3_FLR_RESET) &&
test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
hclgevf_misc_irq_uninit(hdev);
hclgevf_uninit_msi(hdev);
hclgevf_update_rss_size(handle, new_tqps_num);
- hclge_comm_get_rss_tc_info(cur_rss_size, hdev->hw_tc_map,
+ hclge_comm_get_rss_tc_info(kinfo->rss_size, hdev->hw_tc_map,
tc_offset, tc_valid, tc_size);
ret = hclge_comm_set_rss_tc_mode(&hdev->hw.hw, tc_offset,
tc_valid, tc_size);
struct i40e_pf *pf = vsi->back;
if (i40e_enabled_xdp_vsi(vsi)) {
- int frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+ int frame_size = new_mtu + I40E_PACKET_HDR_PAD;
if (frame_size > i40e_max_xdp_frame_size(vsi))
return -EINVAL;
}
br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+ if (!br_spec)
+ return -EINVAL;
nla_for_each_nested(attr, br_spec, rem) {
__u16 mode;
/* board specific private data structure */
struct iavf_adapter {
+ struct workqueue_struct *wq;
struct work_struct reset_task;
struct work_struct adminq_task;
struct delayed_work client_task;
/* needed by iavf_ethtool.c */
extern char iavf_driver_name[];
-extern struct workqueue_struct *iavf_wq;
static inline const char *iavf_state_str(enum iavf_state_t state)
{
if (changed_flags & IAVF_FLAG_LEGACY_RX) {
if (netif_running(netdev)) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
}
if (netif_running(netdev)) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
return 0;
adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
spin_unlock_bh(&adapter->fdir_fltr_lock);
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
ret:
if (err && fltr)
spin_unlock_bh(&adapter->fdir_fltr_lock);
if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST)
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
return err;
}
spin_unlock_bh(&adapter->adv_rss_lock);
if (!err)
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
mutex_unlock(&adapter->crit_lock);
MODULE_LICENSE("GPL v2");
static const struct net_device_ops iavf_netdev_ops;
-struct workqueue_struct *iavf_wq;
int iavf_status_to_errno(enum iavf_status status)
{
if (!(adapter->flags &
(IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
}
void iavf_schedule_request_stats(struct iavf_adapter *adapter)
{
adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS;
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
}
/**
if (adapter->state != __IAVF_REMOVE)
/* schedule work on the private workqueue */
- queue_work(iavf_wq, &adapter->adminq_task);
+ queue_work(adapter->wq, &adapter->adminq_task);
return IRQ_HANDLED;
}
/* schedule the watchdog task to immediately process the request */
if (f) {
- queue_work(iavf_wq, &adapter->watchdog_task.work);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
return 0;
}
return -ENOMEM;
adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES;
if (CLIENT_ENABLED(adapter))
adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN;
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
}
/**
adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES;
}
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
}
/**
if (aq_required) {
adapter->aq_required |= aq_required;
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
}
}
goto restart_watchdog;
}
+ if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) &&
+ adapter->netdev_registered &&
+ !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) &&
+ rtnl_trylock()) {
+ netdev_update_features(adapter->netdev);
+ rtnl_unlock();
+ adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES;
+ }
+
if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
iavf_change_state(adapter, __IAVF_COMM_FAILED);
adapter->aq_required = 0;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
mutex_unlock(&adapter->crit_lock);
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
return;
}
case __IAVF_STARTUP:
iavf_startup(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(30));
return;
case __IAVF_INIT_VERSION_CHECK:
iavf_init_version_check(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(30));
return;
case __IAVF_INIT_GET_RESOURCES:
iavf_init_get_resources(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(1));
return;
case __IAVF_INIT_EXTENDED_CAPS:
iavf_init_process_extended_caps(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(1));
return;
case __IAVF_INIT_CONFIG_ADAPTER:
iavf_init_config_adapter(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(1));
return;
case __IAVF_INIT_FAILED:
adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
iavf_shutdown_adminq(hw);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq,
+ queue_delayed_work(adapter->wq,
&adapter->watchdog_task, (5 * HZ));
return;
}
/* Try again from failed step*/
iavf_change_state(adapter, adapter->last_state);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ);
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ);
return;
case __IAVF_COMM_FAILED:
if (test_bit(__IAVF_IN_REMOVE_TASK,
adapter->aq_required = 0;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq,
+ queue_delayed_work(adapter->wq,
&adapter->watchdog_task,
msecs_to_jiffies(10));
return;
case __IAVF_RESETTING:
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+ HZ * 2);
return;
case __IAVF_DOWN:
case __IAVF_DOWN_PENDING:
adapter->aq_required = 0;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq,
+ queue_delayed_work(adapter->wq,
&adapter->watchdog_task, HZ * 2);
return;
}
mutex_unlock(&adapter->crit_lock);
restart_watchdog:
if (adapter->state >= __IAVF_DOWN)
- queue_work(iavf_wq, &adapter->adminq_task);
+ queue_work(adapter->wq, &adapter->adminq_task);
if (adapter->aq_required)
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(20));
else
- queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+ HZ * 2);
}
/**
*/
if (!mutex_trylock(&adapter->crit_lock)) {
if (adapter->state != __IAVF_REMOVE)
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
goto reset_finish;
}
bitmap_clear(adapter->vsi.active_cvlans, 0, VLAN_N_VID);
bitmap_clear(adapter->vsi.active_svlans, 0, VLAN_N_VID);
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 2);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 2);
/* We were running when the reset started, so we need to restore some
* state here.
if (adapter->state == __IAVF_REMOVE)
return;
- queue_work(iavf_wq, &adapter->adminq_task);
+ queue_work(adapter->wq, &adapter->adminq_task);
goto out;
}
} while (pending);
mutex_unlock(&adapter->crit_lock);
- if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES)) {
- if (adapter->netdev_registered ||
- !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) {
- struct net_device *netdev = adapter->netdev;
-
- rtnl_lock();
- netdev_update_features(netdev);
- rtnl_unlock();
- /* Request VLAN offload settings */
- if (VLAN_V2_ALLOWED(adapter))
- iavf_set_vlan_offload_features
- (adapter, 0, netdev->features);
-
- iavf_set_queue_vlan_tag_loc(adapter);
- }
-
- adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES;
- }
if ((adapter->flags &
(IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) ||
adapter->state == __IAVF_RESETTING)
field_flags |= IAVF_CLOUD_FIELD_IIP;
} else {
dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n",
- be32_to_cpu(match.mask->dst));
+ be32_to_cpu(match.mask->src));
return -EINVAL;
}
}
if (netif_running(netdev)) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
return 0;
hw = &adapter->hw;
hw->back = adapter;
+ adapter->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
+ iavf_driver_name);
+ if (!adapter->wq) {
+ err = -ENOMEM;
+ goto err_alloc_wq;
+ }
+
adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1;
iavf_change_state(adapter, __IAVF_STARTUP);
INIT_WORK(&adapter->adminq_task, iavf_adminq_task);
INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task);
INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
/* Setup the wait queue for indicating transition to down status */
return 0;
err_ioremap:
+ destroy_workqueue(adapter->wq);
+err_alloc_wq:
free_netdev(netdev);
err_alloc_etherdev:
pci_disable_pcie_error_reporting(pdev);
return err;
}
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
netif_device_attach(adapter->netdev);
}
spin_unlock_bh(&adapter->adv_rss_lock);
+ destroy_workqueue(adapter->wq);
+
free_netdev(netdev);
pci_disable_pcie_error_reporting(pdev);
**/
static int __init iavf_init_module(void)
{
- int ret;
-
pr_info("iavf: %s\n", iavf_driver_string);
pr_info("%s\n", iavf_copyright);
- iavf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1,
- iavf_driver_name);
- if (!iavf_wq) {
- pr_err("%s: Failed to create workqueue\n", iavf_driver_name);
- return -ENOMEM;
- }
-
- ret = pci_register_driver(&iavf_driver);
- if (ret)
- destroy_workqueue(iavf_wq);
-
- return ret;
+ return pci_register_driver(&iavf_driver);
}
module_init(iavf_init_module);
static void __exit iavf_exit_module(void)
{
pci_unregister_driver(&iavf_driver);
- destroy_workqueue(iavf_wq);
}
module_exit(iavf_exit_module);
if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) {
adapter->flags |= IAVF_FLAG_RESET_PENDING;
dev_info(&adapter->pdev->dev, "Scheduling reset task\n");
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
break;
default:
iavf_process_config(adapter);
adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES;
+
+ /* Request VLAN offload settings */
+ if (VLAN_V2_ALLOWED(adapter))
+ iavf_set_vlan_offload_features(adapter, 0,
+ netdev->features);
+
+ iavf_set_queue_vlan_tag_loc(adapter);
+
was_mac_changed = !ether_addr_equal(netdev->dev_addr,
adapter->hw.mac.addr);
void ice_set_ethtool_safe_mode_ops(struct net_device *netdev);
u16 ice_get_avail_txq_count(struct ice_pf *pf);
u16 ice_get_avail_rxq_count(struct ice_pf *pf);
-int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx);
+int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked);
void ice_update_vsi_stats(struct ice_vsi *vsi);
void ice_update_pf_stats(struct ice_pf *pf);
void
* returned by the firmware is a 16 bit * value, but is indexed
* by [fls(speed) - 1]
*/
-static const u32 ice_aq_to_link_speed[15] = {
+static const u32 ice_aq_to_link_speed[] = {
SPEED_10, /* BIT(0) */
SPEED_100,
SPEED_1000,
SPEED_40000,
SPEED_50000,
SPEED_100000, /* BIT(10) */
- 0,
- 0,
- 0,
- 0 /* BIT(14) */
};
/**
*/
u32 ice_get_link_speed(u16 index)
{
+ if (index >= ARRAY_SIZE(ice_aq_to_link_speed))
+ return 0;
+
return ice_aq_to_link_speed[index];
}
goto out;
}
- ice_pf_dcb_recfg(pf);
+ ice_pf_dcb_recfg(pf, false);
out:
/* enable previously downed VSIs */
/**
* ice_pf_dcb_recfg - Reconfigure all VEBs and VSIs
* @pf: pointer to the PF struct
+ * @locked: is adev device lock held
*
* Assumed caller has already disabled all VSIs before
* calling this function. Reconfiguring DCB based on
* local_dcbx_cfg.
*/
-void ice_pf_dcb_recfg(struct ice_pf *pf)
+void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked)
{
struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg;
struct iidc_event *event;
if (vsi->type == ICE_VSI_PF)
ice_dcbnl_set_all(vsi);
}
- /* Notify the AUX drivers that TC change is finished */
- event = kzalloc(sizeof(*event), GFP_KERNEL);
- if (!event)
- return;
+ if (!locked) {
+ /* Notify the AUX drivers that TC change is finished */
+ event = kzalloc(sizeof(*event), GFP_KERNEL);
+ if (!event)
+ return;
- set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type);
- ice_send_event_to_aux(pf, event);
- kfree(event);
+ set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type);
+ ice_send_event_to_aux(pf, event);
+ kfree(event);
+ }
}
/**
}
/* changes in configuration update VSI */
- ice_pf_dcb_recfg(pf);
+ ice_pf_dcb_recfg(pf, false);
/* enable previously downed VSIs */
ice_dcb_ena_dis_vsi(pf, true, true);
int
ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked);
int ice_dcb_bwchk(struct ice_pf *pf, struct ice_dcbx_cfg *dcbcfg);
-void ice_pf_dcb_recfg(struct ice_pf *pf);
+void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked);
void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi);
int ice_init_pf_dcb(struct ice_pf *pf, bool locked);
void ice_update_dcb_stats(struct ice_pf *pf);
return 0;
}
-static inline void ice_pf_dcb_recfg(struct ice_pf *pf) { }
+static inline void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { }
static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { }
static inline void ice_update_dcb_stats(struct ice_pf *pf) { }
static inline void
{
int status;
- if (node->tx_priority >= 8) {
+ if (priority >= 8) {
NL_SET_ERR_MSG_MOD(extack, "Priority should be less than 8");
return -EINVAL;
}
{
int status;
- if (node->tx_weight > 200 || node->tx_weight < 1) {
+ if (weight > 200 || weight < 1) {
NL_SET_ERR_MSG_MOD(extack, "Weight must be between 1 and 200");
return -EINVAL;
}
struct ice_vsi *vsi = np->vsi;
struct ice_pf *pf = vsi->back;
int new_rx = 0, new_tx = 0;
+ bool locked = false;
u32 curr_combined;
+ int ret = 0;
/* do not support changing channels in Safe Mode */
if (ice_is_safe_mode(pf)) {
return -EINVAL;
}
- ice_vsi_recfg_qs(vsi, new_rx, new_tx);
+ if (pf->adev) {
+ mutex_lock(&pf->adev_mutex);
+ device_lock(&pf->adev->dev);
+ locked = true;
+ if (pf->adev->dev.driver) {
+ netdev_err(dev, "Cannot change channels when RDMA is active\n");
+ ret = -EBUSY;
+ goto adev_unlock;
+ }
+ }
+
+ ice_vsi_recfg_qs(vsi, new_rx, new_tx, locked);
- if (!netif_is_rxfh_configured(dev))
- return ice_vsi_set_dflt_rss_lut(vsi, new_rx);
+ if (!netif_is_rxfh_configured(dev)) {
+ ret = ice_vsi_set_dflt_rss_lut(vsi, new_rx);
+ goto adev_unlock;
+ }
/* Update rss_size due to change in Rx queues */
vsi->rss_size = ice_get_valid_rss_size(&pf->hw, new_rx);
- return 0;
+adev_unlock:
+ if (locked) {
+ device_unlock(&pf->adev->dev);
+ mutex_unlock(&pf->adev_mutex);
+ }
+ return ret;
}
/**
/* Send the data out to a hardware port */
write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL);
if (!write_buf) {
+ kfree(cmd_buf);
err = -ENOMEM;
goto exit;
}
for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) {
pf->gnss_tty_port[i] = kzalloc(sizeof(*pf->gnss_tty_port[i]),
GFP_KERNEL);
+ if (!pf->gnss_tty_port[i])
+ goto err_out;
+
pf->gnss_serial[i] = NULL;
tty_port_init(pf->gnss_tty_port[i]);
err = tty_register_driver(tty_driver);
if (err) {
dev_err(dev, "Failed to register TTY driver err=%d\n", err);
-
- for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) {
- tty_port_destroy(pf->gnss_tty_port[i]);
- kfree(pf->gnss_tty_port[i]);
- }
- kfree(ttydrv_name);
- tty_driver_kref_put(pf->ice_gnss_tty_driver);
-
- return NULL;
+ goto err_out;
}
for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++)
dev_info(dev, "%s%d registered\n", ttydrv_name, i);
return tty_driver;
+
+err_out:
+ while (i--) {
+ tty_port_destroy(pf->gnss_tty_port[i]);
+ kfree(pf->gnss_tty_port[i]);
+ }
+ kfree(ttydrv_name);
+ tty_driver_kref_put(pf->ice_gnss_tty_driver);
+
+ return NULL;
}
/**
}
}
- if (vsi->type == ICE_VSI_PF)
- ice_devlink_destroy_pf_port(pf);
-
if (vsi->type == ICE_VSI_VF &&
vsi->agg_node && vsi->agg_node->valid)
vsi->agg_node->num_vsis--;
if (status && status != -EEXIST)
return status;
+ netdev_dbg(vsi->netdev, "set promisc filter bits for VSI %i: 0x%x\n",
+ vsi->vsi_num, promisc_m);
return 0;
}
promisc_m, 0);
}
+ netdev_dbg(vsi->netdev, "clear promisc filter bits for VSI %i: 0x%x\n",
+ vsi->vsi_num, promisc_m);
return status;
}
}
err = 0;
vlan_ops->dis_rx_filtering(vsi);
+
+ /* promiscuous mode implies allmulticast so
+ * that VSIs that are in promiscuous mode are
+ * subscribed to multicast packets coming to
+ * the port
+ */
+ err = ice_set_promisc(vsi,
+ ICE_MCAST_PROMISC_BITS);
+ if (err)
+ goto out_promisc;
}
} else {
/* Clear Rx filter to remove traffic from wire */
NETIF_F_HW_VLAN_CTAG_FILTER)
vlan_ops->ena_rx_filtering(vsi);
}
+
+ /* disable allmulti here, but only if allmulti is not
+ * still enabled for the netdev
+ */
+ if (!(vsi->current_netdev_flags & IFF_ALLMULTI)) {
+ err = ice_clear_promisc(vsi,
+ ICE_MCAST_PROMISC_BITS);
+ if (err) {
+ netdev_err(netdev, "Error %d clearing multicast promiscuous on VSI %i\n",
+ err, vsi->vsi_num);
+ }
+ }
}
}
goto exit;
* @vsi: VSI being changed
* @new_rx: new number of Rx queues
* @new_tx: new number of Tx queues
+ * @locked: is adev device_lock held
*
* Only change the number of queues if new_tx, or new_rx is non-0.
*
* Returns 0 on success.
*/
-int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx)
+int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
{
struct ice_pf *pf = vsi->back;
int err = 0, timeout = 50;
ice_vsi_close(vsi);
ice_vsi_rebuild(vsi, false);
- ice_pf_dcb_recfg(pf);
+ ice_pf_dcb_recfg(pf, locked);
ice_vsi_open(vsi);
done:
clear_bit(ICE_CFG_BUSY, pf->state);
}
/**
- * ice_register_netdev - register netdev and devlink port
+ * ice_register_netdev - register netdev
* @pf: pointer to the PF struct
*/
static int ice_register_netdev(struct ice_pf *pf)
if (!vsi || !vsi->netdev)
return -EIO;
- err = ice_devlink_create_pf_port(pf);
- if (err)
- goto err_devlink_create;
-
- SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
err = register_netdev(vsi->netdev);
if (err)
goto err_register_netdev;
return 0;
err_register_netdev:
- ice_devlink_destroy_pf_port(pf);
-err_devlink_create:
free_netdev(vsi->netdev);
vsi->netdev = NULL;
clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
{
struct device *dev = &pdev->dev;
+ struct ice_vsi *vsi;
struct ice_pf *pf;
struct ice_hw *hw;
int i, err;
pcie_print_link_status(pf->pdev);
probe_done:
+ err = ice_devlink_create_pf_port(pf);
+ if (err)
+ goto err_create_pf_port;
+
+ vsi = ice_get_main_vsi(pf);
+ if (!vsi || !vsi->netdev) {
+ err = -EINVAL;
+ goto err_netdev_reg;
+ }
+
+ SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
+
err = ice_register_netdev(pf);
if (err)
goto err_netdev_reg;
err_devlink_reg_param:
ice_devlink_unregister_params(pf);
err_netdev_reg:
+ ice_devlink_destroy_pf_port(pf);
+err_create_pf_port:
err_send_version_unroll:
ice_vsi_release_all(pf);
err_alloc_sw_unroll:
ice_setup_mc_magic_wake(pf);
ice_vsi_release_all(pf);
mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
+ ice_devlink_destroy_pf_port(pf);
ice_set_wake(pf);
ice_free_irq_msix_misc(pf);
ice_for_each_vsi(pf, i) {
pr_info("%s\n", ice_driver_string);
pr_info("%s\n", ice_copyright);
- ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME);
+ ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME);
if (!ice_wq) {
pr_err("Failed to create workqueue\n");
return -ENOMEM;
*/
status = ice_add_special_words(rinfo, lkup_exts, ice_is_dvm_ena(hw));
if (status)
- goto err_free_lkup_exts;
+ goto err_unroll;
/* Group match words into recipes using preferred recipe grouping
* criteria.
struct ice_vsi *ch_vsi = NULL;
u16 queue = act->rx_queue;
- if (queue > vsi->num_rxq) {
+ if (queue >= vsi->num_rxq) {
NL_SET_ERR_MSG_MOD(fltr->extack,
"Unable to add filter because specified queue is invalid");
return -EINVAL;
return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd);
}
-static const u32 ice_legacy_aq_to_vc_speed[15] = {
+static const u32 ice_legacy_aq_to_vc_speed[] = {
VIRTCHNL_LINK_SPEED_100MB, /* BIT(0) */
VIRTCHNL_LINK_SPEED_100MB,
VIRTCHNL_LINK_SPEED_1GB,
VIRTCHNL_LINK_SPEED_40GB,
VIRTCHNL_LINK_SPEED_40GB,
VIRTCHNL_LINK_SPEED_40GB,
- VIRTCHNL_LINK_SPEED_UNKNOWN,
- VIRTCHNL_LINK_SPEED_UNKNOWN,
- VIRTCHNL_LINK_SPEED_UNKNOWN,
- VIRTCHNL_LINK_SPEED_UNKNOWN /* BIT(14) */
};
/**
*/
u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed)
{
- u32 speed;
+ /* convert a BIT() value into an array index */
+ u32 index = fls(link_speed) - 1;
- if (adv_link_support) {
- /* convert a BIT() value into an array index */
- speed = ice_get_link_speed(fls(link_speed) - 1);
- } else {
+ if (adv_link_support)
+ return ice_get_link_speed(index);
+ else if (index < ARRAY_SIZE(ice_legacy_aq_to_vc_speed))
/* Virtchnl speeds are not defined for every speed supported in
* the hardware. To maintain compatibility with older AVF
* drivers, while reporting the speed the new speed values are
* resolved to the closest known virtchnl speeds
*/
- speed = ice_legacy_aq_to_vc_speed[fls(link_speed) - 1];
- }
+ return ice_legacy_aq_to_vc_speed[index];
- return speed;
+ return VIRTCHNL_LINK_SPEED_UNKNOWN;
}
/* The mailbox overflow detection algorithm helps to check if there
/* outer VLAN ops regardless of port VLAN config */
vlan_ops->add_vlan = ice_vsi_add_vlan;
- vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering;
vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering;
vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering;
if (ice_vf_is_port_vlan_ena(vf)) {
/* setup outer VLAN ops */
vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan;
+ /* all Rx traffic should be in the domain of the
+ * assigned port VLAN, so prevent disabling Rx VLAN
+ * filtering
+ */
+ vlan_ops->dis_rx_filtering = noop_vlan;
vlan_ops->ena_rx_filtering =
ice_vsi_ena_rx_vlan_filtering;
vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion;
vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion;
} else {
+ vlan_ops->dis_rx_filtering =
+ ice_vsi_dis_rx_vlan_filtering;
+
if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags))
vlan_ops->ena_rx_filtering = noop_vlan;
else
vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan;
vlan_ops->ena_rx_filtering =
ice_vsi_ena_rx_vlan_filtering;
+ /* all Rx traffic should be in the domain of the
+ * assigned port VLAN, so prevent disabling Rx VLAN
+ * filtering
+ */
+ vlan_ops->dis_rx_filtering = noop_vlan;
} else {
+ vlan_ops->dis_rx_filtering =
+ ice_vsi_dis_rx_vlan_filtering;
if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags))
vlan_ops->ena_rx_filtering = noop_vlan;
else
static void
ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
{
- xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf);
+ page_frag_free(tx_buf->raw_buf);
xdp_ring->xdp_tx_active--;
dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
struct ice_tx_desc *tx_desc;
u16 cnt = xdp_ring->count;
struct ice_tx_buf *tx_buf;
+ u16 completed_frames = 0;
u16 xsk_frames = 0;
u16 last_rs;
int i;
if ((tx_desc->cmd_type_offset_bsz &
cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) {
if (last_rs >= ntc)
- xsk_frames = last_rs - ntc + 1;
+ completed_frames = last_rs - ntc + 1;
else
- xsk_frames = last_rs + cnt - ntc + 1;
+ completed_frames = last_rs + cnt - ntc + 1;
}
- if (!xsk_frames)
+ if (!completed_frames)
return;
- if (likely(!xdp_ring->xdp_tx_active))
+ if (likely(!xdp_ring->xdp_tx_active)) {
+ xsk_frames = completed_frames;
goto skip;
+ }
ntc = xdp_ring->next_to_clean;
- for (i = 0; i < xsk_frames; i++) {
+ for (i = 0; i < completed_frames; i++) {
tx_buf = &xdp_ring->tx_buf[ntc];
if (tx_buf->raw_buf) {
}
skip:
tx_desc->cmd_type_offset_bsz = 0;
- xdp_ring->next_to_clean += xsk_frames;
+ xdp_ring->next_to_clean += completed_frames;
if (xdp_ring->next_to_clean >= cnt)
xdp_ring->next_to_clean -= cnt;
if (xsk_frames)
}
}
+#ifdef CONFIG_IGB_HWMON
+/**
+ * igb_set_i2c_bb - Init I2C interface
+ * @hw: pointer to hardware structure
+ **/
+static void igb_set_i2c_bb(struct e1000_hw *hw)
+{
+ u32 ctrl_ext;
+ s32 i2cctl;
+
+ ctrl_ext = rd32(E1000_CTRL_EXT);
+ ctrl_ext |= E1000_CTRL_I2C_ENA;
+ wr32(E1000_CTRL_EXT, ctrl_ext);
+ wrfl();
+
+ i2cctl = rd32(E1000_I2CPARAMS);
+ i2cctl |= E1000_I2CBB_EN
+ | E1000_I2C_CLK_OE_N
+ | E1000_I2C_DATA_OE_N;
+ wr32(E1000_I2CPARAMS, i2cctl);
+ wrfl();
+}
+#endif
+
void igb_reset(struct igb_adapter *adapter)
{
struct pci_dev *pdev = adapter->pdev;
* interface.
*/
if (adapter->ets)
- mac->ops.init_thermal_sensor_thresh(hw);
+ igb_set_i2c_bb(hw);
+ mac->ops.init_thermal_sensor_thresh(hw);
}
}
#endif
**/
static s32 igb_init_i2c(struct igb_adapter *adapter)
{
- struct e1000_hw *hw = &adapter->hw;
s32 status = 0;
- s32 i2cctl;
/* I2C interface supported on i350 devices */
if (adapter->hw.mac.type != e1000_i350)
return 0;
- i2cctl = rd32(E1000_I2CPARAMS);
- i2cctl |= E1000_I2CBB_EN
- | E1000_I2C_CLK_OUT | E1000_I2C_CLK_OE_N
- | E1000_I2C_DATA_OUT | E1000_I2C_DATA_OE_N;
- wr32(E1000_I2CPARAMS, i2cctl);
- wrfl();
-
/* Initialize the i2c bus which is controlled by the registers.
* This bus will use the i2c_algo_bit structure that implements
* the protocol through toggling of the 4 bits in the register.
adapter->ets = true;
else
adapter->ets = false;
+ /* Only enable I2C bit banging if an external thermal
+ * sensor is supported.
+ */
+ if (adapter->ets)
+ igb_set_i2c_bb(hw);
+ hw->mac.ops.init_thermal_sensor_thresh(hw);
if (igb_sysfs_init(adapter))
dev_err(&pdev->dev,
"failed to allocate sysfs resources\n");
struct timespec64 ts;
u32 tsauxc;
- if (pin < 0 || pin >= IGB_N_PEROUT)
+ if (pin < 0 || pin >= IGB_N_SDP)
return;
spin_lock(&adapter->tmreg_lock);
if (hw->mac.type == e1000_82580 ||
hw->mac.type == e1000_i354 ||
hw->mac.type == e1000_i350) {
- s64 ns = timespec64_to_ns(&adapter->perout[pin].period);
+ s64 ns = timespec64_to_ns(&adapter->perout[tsintr_tt].period);
u32 systiml, systimh, level_mask, level, rem;
u64 systim, now;
ts.tv_nsec = (u32)systim;
ts.tv_sec = ((u32)(systim >> 32)) & 0xFF;
} else {
- ts = timespec64_add(adapter->perout[pin].start,
- adapter->perout[pin].period);
+ ts = timespec64_add(adapter->perout[tsintr_tt].start,
+ adapter->perout[tsintr_tt].period);
}
/* u32 conversion of tv_sec is safe until y2106 */
tsauxc = rd32(E1000_TSAUXC);
tsauxc |= TSAUXC_EN_TT0;
wr32(E1000_TSAUXC, tsauxc);
- adapter->perout[pin].start = ts;
+ adapter->perout[tsintr_tt].start = ts;
spin_unlock(&adapter->tmreg_lock);
}
struct ptp_clock_event event;
struct timespec64 ts;
- if (pin < 0 || pin >= IGB_N_EXTTS)
+ if (pin < 0 || pin >= IGB_N_SDP)
return;
if (hw->mac.type == e1000_82580 ||
#define IGC_TSAUXC_EN_TT0 BIT(0) /* Enable target time 0. */
#define IGC_TSAUXC_EN_TT1 BIT(1) /* Enable target time 1. */
#define IGC_TSAUXC_EN_CLK0 BIT(2) /* Enable Configurable Frequency Clock 0. */
+#define IGC_TSAUXC_ST0 BIT(4) /* Start Clock 0 Toggle on Target Time 0. */
#define IGC_TSAUXC_EN_CLK1 BIT(5) /* Enable Configurable Frequency Clock 1. */
+#define IGC_TSAUXC_ST1 BIT(7) /* Start Clock 1 Toggle on Target Time 1. */
#define IGC_TSAUXC_EN_TS0 BIT(8) /* Enable hardware timestamp 0. */
#define IGC_TSAUXC_AUTT0 BIT(9) /* Auxiliary Timestamp Taken. */
#define IGC_TSAUXC_EN_TS1 BIT(10) /* Enable hardware timestamp 0. */
if (tx_buffer->next_to_watch &&
time_after(jiffies, tx_buffer->time_stamp +
(adapter->tx_timeout_factor * HZ)) &&
- !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) {
+ !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) &&
+ (rd32(IGC_TDH(tx_ring->reg_idx)) !=
+ readl(tx_ring->tail))) {
/* detected Tx unit hang */
netdev_err(tx_ring->netdev,
"Detected Tx Unit Hang\n"
return 0;
}
+/**
+ * igc_tx_timeout - Respond to a Tx Hang
+ * @netdev: network interface device structure
+ * @txqueue: queue number that timed out
+ **/
+static void igc_tx_timeout(struct net_device *netdev,
+ unsigned int __always_unused txqueue)
+{
+ struct igc_adapter *adapter = netdev_priv(netdev);
+ struct igc_hw *hw = &adapter->hw;
+
+ /* Do the reset outside of interrupt context */
+ adapter->tx_timeout_count++;
+ schedule_work(&adapter->reset_task);
+ wr32(IGC_EICS,
+ (adapter->eims_enable_mask & ~adapter->eims_other));
+}
+
/**
* igc_get_stats64 - Get System Network Statistics
* @netdev: network interface device structure
case SPEED_100:
case SPEED_1000:
case SPEED_2500:
- adapter->tx_timeout_factor = 7;
+ adapter->tx_timeout_factor = 1;
break;
}
.ndo_set_rx_mode = igc_set_rx_mode,
.ndo_set_mac_address = igc_set_mac,
.ndo_change_mtu = igc_change_mtu,
+ .ndo_tx_timeout = igc_tx_timeout,
.ndo_get_stats64 = igc_get_stats64,
.ndo_fix_features = igc_fix_features,
.ndo_set_features = igc_set_features,
ts = ns_to_timespec64(ns);
if (rq->perout.index == 1) {
if (use_freq) {
- tsauxc_mask = IGC_TSAUXC_EN_CLK1;
+ tsauxc_mask = IGC_TSAUXC_EN_CLK1 | IGC_TSAUXC_ST1;
tsim_mask = 0;
} else {
tsauxc_mask = IGC_TSAUXC_EN_TT1;
freqout = IGC_FREQOUT1;
} else {
if (use_freq) {
- tsauxc_mask = IGC_TSAUXC_EN_CLK0;
+ tsauxc_mask = IGC_TSAUXC_EN_CLK0 | IGC_TSAUXC_ST0;
tsim_mask = 0;
} else {
tsauxc_mask = IGC_TSAUXC_EN_TT0;
tsauxc = rd32(IGC_TSAUXC);
tsim = rd32(IGC_TSIM);
if (rq->perout.index == 1) {
- tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1);
+ tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1 |
+ IGC_TSAUXC_ST1);
tsim &= ~IGC_TSICR_TT1;
} else {
- tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0);
+ tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0 |
+ IGC_TSAUXC_ST0);
tsim &= ~IGC_TSICR_TT0;
}
if (on) {
*
* We need to convert the system time value stored in the RX/TXSTMP registers
* into a hwtstamp which can be used by the upper level timestamping functions.
+ *
+ * Returns 0 on success.
**/
-static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter,
- struct skb_shared_hwtstamps *hwtstamps,
- u64 systim)
+static int igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter,
+ struct skb_shared_hwtstamps *hwtstamps,
+ u64 systim)
{
switch (adapter->hw.mac.type) {
case igc_i225:
systim & 0xFFFFFFFF);
break;
default:
- break;
+ return -EINVAL;
}
+ return 0;
}
/**
regval = rd32(IGC_TXSTMPL);
regval |= (u64)rd32(IGC_TXSTMPH) << 32;
- igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
+ if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval))
+ return;
switch (adapter->link_speed) {
case SPEED_10:
#define IXGBE_RXBUFFER_4K 4096
#define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */
+#define IXGBE_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))
+
/* Attempt to maximize the headroom available for incoming frames. We
* use a 2K buffer for receives and need 1536/1534 to store the data for
* the frame. This leaves us with 512 bytes of room. From that we need
ixgbe_free_rx_resources(adapter->rx_ring[i]);
}
+/**
+ * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP
+ * @adapter: device handle, pointer to adapter
+ */
+static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter)
+{
+ if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
+ return IXGBE_RXBUFFER_2K;
+ else
+ return IXGBE_RXBUFFER_3K;
+}
+
/**
* ixgbe_change_mtu - Change the Maximum Transfer Unit
* @netdev: network interface device structure
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
- if (adapter->xdp_prog) {
- int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN +
- VLAN_HLEN;
- int i;
-
- for (i = 0; i < adapter->num_rx_queues; i++) {
- struct ixgbe_ring *ring = adapter->rx_ring[i];
+ if (ixgbe_enabled_xdp_adapter(adapter)) {
+ int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD;
- if (new_frame_size > ixgbe_rx_bufsz(ring)) {
- e_warn(probe, "Requested MTU size is not supported with XDP\n");
- return -EINVAL;
- }
+ if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) {
+ e_warn(probe, "Requested MTU size is not supported with XDP\n");
+ return -EINVAL;
}
}
rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn);
if (rp_pdev && rp_pdev->subordinate) {
bus = rp_pdev->subordinate->number;
+ pci_dev_put(rp_pdev);
return pci_get_domain_bus_and_slot(0, bus, 0);
}
+ pci_dev_put(rp_pdev);
return NULL;
}
struct ixgbe_adapter *adapter = hw->back;
struct pci_dev *pdev = adapter->pdev;
struct pci_dev *func0_pdev;
+ bool has_mii = false;
/* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices
* are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0
func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0));
if (func0_pdev) {
if (func0_pdev == pdev)
- return true;
- else
- return false;
+ has_mii = true;
+ goto out;
}
func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0));
if (func0_pdev == pdev)
- return true;
+ has_mii = true;
- return false;
+out:
+ pci_dev_put(func0_pdev);
+ return has_mii;
}
/**
cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG);
if (enable)
- cfg |= CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN;
+ cfg |= DATA_PKT_RX_EN | DATA_PKT_TX_EN;
else
- cfg &= ~(CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN);
+ cfg &= ~(DATA_PKT_RX_EN | DATA_PKT_TX_EN);
cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg);
return 0;
}
#define CMR_P2X_SEL_SHIFT 59ULL
#define CMR_P2X_SEL_NIX0 1ULL
#define CMR_P2X_SEL_NIX1 2ULL
-#define CMR_EN BIT_ULL(55)
#define DATA_PKT_TX_EN BIT_ULL(53)
#define DATA_PKT_RX_EN BIT_ULL(54)
#define CGX_LMAC_TYPE_SHIFT 40
u16 pcifunc = req->hdr.pcifunc;
struct mcs_rsrc_map *map;
struct mcs *mcs;
- int rc;
+ int rc = 0;
if (req->mcs_id >= rvu->mcs_blk_cnt)
return MCS_AF_ERR_INVALID_MCSID;
BIT(DEVLINK_PARAM_CMODE_RUNTIME),
rvu_af_dl_dwrr_mtu_get, rvu_af_dl_dwrr_mtu_set,
rvu_af_dl_dwrr_mtu_validate),
+};
+
+static const struct devlink_param rvu_af_dl_param_exact_match[] = {
DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE,
"npc_exact_feature_disable", DEVLINK_PARAM_TYPE_STRING,
BIT(DEVLINK_PARAM_CMODE_RUNTIME),
{
struct rvu_devlink *rvu_dl;
struct devlink *dl;
- size_t size;
int err;
dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink),
goto err_dl_health;
}
+ err = devlink_params_register(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params));
+ if (err) {
+ dev_err(rvu->dev,
+ "devlink params register failed with error %d", err);
+ goto err_dl_health;
+ }
+
/* Register exact match devlink only for CN10K-B */
- size = ARRAY_SIZE(rvu_af_dl_params);
if (!rvu_npc_exact_has_match_table(rvu))
- size -= 1;
+ goto done;
- err = devlink_params_register(dl, rvu_af_dl_params, size);
+ err = devlink_params_register(dl, rvu_af_dl_param_exact_match,
+ ARRAY_SIZE(rvu_af_dl_param_exact_match));
if (err) {
dev_err(rvu->dev,
- "devlink params register failed with error %d", err);
- goto err_dl_health;
+ "devlink exact match params register failed with error %d", err);
+ goto err_dl_exact_match;
}
+done:
devlink_register(dl);
return 0;
+err_dl_exact_match:
+ devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params));
+
err_dl_health:
rvu_health_reporters_destroy(rvu);
devlink_free(dl);
struct devlink *dl = rvu_dl->dl;
devlink_unregister(dl);
- devlink_params_unregister(dl, rvu_af_dl_params,
- ARRAY_SIZE(rvu_af_dl_params));
+
+ devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params));
+
+ /* Unregister exact match devlink only for CN10K-B */
+ if (rvu_npc_exact_has_match_table(rvu))
+ devlink_params_unregister(dl, rvu_af_dl_param_exact_match,
+ ARRAY_SIZE(rvu_af_dl_param_exact_match));
+
rvu_health_reporters_destroy(rvu);
devlink_free(dl);
}
sq = &qset->sq[qidx];
sq->sqb_count = 0;
sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(*sq->sqb_ptrs), GFP_KERNEL);
- if (!sq->sqb_ptrs)
- return -ENOMEM;
+ if (!sq->sqb_ptrs) {
+ err = -ENOMEM;
+ goto err_mem;
+ }
for (ptr = 0; ptr < num_sqbs; ptr++) {
- if (otx2_alloc_rbuf(pfvf, pool, &bufptr))
- return -ENOMEM;
+ err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+ if (err)
+ goto err_mem;
pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
}
}
- return 0;
+err_mem:
+ return err ? -ENOMEM : 0;
+
fail:
otx2_mbox_reset(&pfvf->mbox.mbox, 0);
otx2_aura_pool_free(pfvf);
for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
pool = &pfvf->qset.pool[pool_id];
for (ptr = 0; ptr < num_ptrs; ptr++) {
- if (otx2_alloc_rbuf(pfvf, pool, &bufptr))
+ err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+ if (err)
return -ENOMEM;
pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
bufptr + OTX2_HEAD_ROOM);
}
}
-
return 0;
fail:
otx2_mbox_reset(&pfvf->mbox.mbox, 0);
u64 ptrs[2];
ptrs[1] = buf;
+ get_cpu();
/* Free only one buffer at time during init and teardown */
__cn10k_aura_freeptr(pfvf, aura, ptrs, 2);
+ put_cpu();
}
/* Alloc pointer from pool/aura */
if (vf->otx2_wq)
destroy_workqueue(vf->otx2_wq);
otx2_ptp_destroy(vf);
+ otx2_mcam_flow_del(vf);
+ otx2_shutdown_tc(vf);
otx2vf_disable_mbox_intr(vf);
otx2_detach_resources(&vf->mbox);
if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
if (IS_ERR(pp))
return pp;
- err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, eth->rx_napi.napi_id,
- id, PAGE_SIZE);
+ err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, id,
+ eth->rx_napi.napi_id, PAGE_SIZE);
if (err < 0)
goto err_free_pp;
while (done < budget) {
unsigned int pktlen, *rxdcsum;
+ bool has_hwaccel_tag = false;
struct net_device *netdev;
+ u16 vlan_proto, vlan_tci;
dma_addr_t dma_addr;
u32 hash, reason;
int mac = 0;
if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) {
if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) {
- if (trxd.rxd3 & RX_DMA_VTAG_V2)
- __vlan_hwaccel_put_tag(skb,
- htons(RX_DMA_VPID(trxd.rxd4)),
- RX_DMA_VID(trxd.rxd4));
+ if (trxd.rxd3 & RX_DMA_VTAG_V2) {
+ vlan_proto = RX_DMA_VPID(trxd.rxd4);
+ vlan_tci = RX_DMA_VID(trxd.rxd4);
+ has_hwaccel_tag = true;
+ }
} else if (trxd.rxd2 & RX_DMA_VTAG) {
- __vlan_hwaccel_put_tag(skb, htons(RX_DMA_VPID(trxd.rxd3)),
- RX_DMA_VID(trxd.rxd3));
+ vlan_proto = RX_DMA_VPID(trxd.rxd3);
+ vlan_tci = RX_DMA_VID(trxd.rxd3);
+ has_hwaccel_tag = true;
}
}
/* When using VLAN untagging in combination with DSA, the
* hardware treats the MTK special tag as a VLAN and untags it.
*/
- if (skb_vlan_tag_present(skb) && netdev_uses_dsa(netdev)) {
- unsigned int port = ntohs(skb->vlan_proto) & GENMASK(2, 0);
+ if (has_hwaccel_tag && netdev_uses_dsa(netdev)) {
+ unsigned int port = vlan_proto & GENMASK(2, 0);
if (port < ARRAY_SIZE(eth->dsa_meta) &&
eth->dsa_meta[port])
skb_dst_set_noref(skb, ð->dsa_meta[port]->dst);
-
- __vlan_hwaccel_clear_tag(skb);
+ } else if (has_hwaccel_tag) {
+ __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan_tci);
}
skb_record_rx_queue(skb, 0);
val |= config;
- if (!i && eth->netdev[0] && netdev_uses_dsa(eth->netdev[0]))
+ if (eth->netdev[i] && netdev_uses_dsa(eth->netdev[i]))
val |= MTK_GDMA_SPECIAL_TAG;
mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i));
#define SGMII_SPEED_10 FIELD_PREP(SGMII_SPEED_MASK, 0)
#define SGMII_SPEED_100 FIELD_PREP(SGMII_SPEED_MASK, 1)
#define SGMII_SPEED_1000 FIELD_PREP(SGMII_SPEED_MASK, 2)
-#define SGMII_DUPLEX_FULL BIT(4)
+#define SGMII_DUPLEX_HALF BIT(4)
#define SGMII_IF_MODE_BIT5 BIT(5)
#define SGMII_REMOTE_FAULT_DIS BIT(8)
#define SGMII_CODE_SYNC_SET_VAL BIT(9)
* @regmap: The register map pointing at the range used to setup
* SGMII modes
* @ana_rgc3: The offset refers to register ANA_RGC3 related to regmap
+ * @interface: Currently configured interface mode
* @pcs: Phylink PCS structure
*/
struct mtk_pcs {
struct regmap *regmap;
u32 ana_rgc3;
+ phy_interface_t interface;
struct phylink_pcs pcs;
};
u32 ib1_mask = mtk_get_ib1_pkt_type_mask(ppe->eth) | MTK_FOE_IB1_UDP;
int type;
- flow_info = kzalloc(offsetof(struct mtk_flow_entry, l2_data.end),
- GFP_ATOMIC);
+ flow_info = kzalloc(sizeof(*flow_info), GFP_ATOMIC);
if (!flow_info)
return;
struct {
struct mtk_flow_entry *base_flow;
struct hlist_node list;
- struct {} end;
} l2_data;
};
struct rhash_head node;
int advertise, link_timer;
bool changed, use_an;
- if (interface == PHY_INTERFACE_MODE_2500BASEX)
- rgc3 = RG_PHY_SPEED_3_125G;
- else
- rgc3 = 0;
-
advertise = phylink_mii_c22_pcs_encode_advertisement(interface,
advertising);
if (advertise < 0)
bmcr = 0;
}
- /* Configure the underlying interface speed */
- regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3,
- RG_PHY_SPEED_3_125G, rgc3);
+ if (mpcs->interface != interface) {
+ /* PHYA power down */
+ regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL,
+ SGMII_PHYA_PWD, SGMII_PHYA_PWD);
+
+ if (interface == PHY_INTERFACE_MODE_2500BASEX)
+ rgc3 = RG_PHY_SPEED_3_125G;
+ else
+ rgc3 = 0;
+
+ /* Configure the underlying interface speed */
+ regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3,
+ RG_PHY_SPEED_3_125G, rgc3);
+
+ mpcs->interface = interface;
+ }
/* Update the advertisement, noting whether it has changed */
regmap_update_bits_check(mpcs->regmap, SGMSYS_PCS_ADVERTISE,
regmap_update_bits(mpcs->regmap, SGMSYS_PCS_CONTROL_1,
SGMII_AN_RESTART | SGMII_AN_ENABLE, bmcr);
- /* Release PHYA power down state */
- regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL,
- SGMII_PHYA_PWD, 0);
+ /* Release PHYA power down state
+ * Only removing bit SGMII_PHYA_PWD isn't enough.
+ * There are cases when the SGMII_PHYA_PWD register contains 0x9 which
+ * prevents SGMII from working. The SGMII still shows link but no traffic
+ * can flow. Writing 0x0 to the PHYA_PWD register fix the issue. 0x0 was
+ * taken from a good working state of the SGMII interface.
+ * Unknown how much the QPHY needs but it is racy without a sleep.
+ * Tested on mt7622 & mt7986.
+ */
+ usleep_range(50, 100);
+ regmap_write(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, 0);
return changed;
}
else
sgm_mode = SGMII_SPEED_1000;
- if (duplex == DUPLEX_FULL)
- sgm_mode |= SGMII_DUPLEX_FULL;
+ if (duplex != DUPLEX_FULL)
+ sgm_mode |= SGMII_DUPLEX_HALF;
regmap_update_bits(mpcs->regmap, SGMSYS_SGMII_MODE,
- SGMII_DUPLEX_FULL | SGMII_SPEED_MASK,
+ SGMII_DUPLEX_HALF | SGMII_SPEED_MASK,
sgm_mode);
}
}
return PTR_ERR(ss->pcs[i].regmap);
ss->pcs[i].pcs.ops = &mtk_pcs_ops;
+ ss->pcs[i].pcs.poll = true;
+ ss->pcs[i].interface = PHY_INTERFACE_MODE_NA;
}
return 0;
return -EINVAL;
}
- cmd->stats = kvcalloc(MLX5_CMD_OP_MAX, sizeof(*cmd->stats), GFP_KERNEL);
- if (!cmd->stats)
- return -ENOMEM;
-
cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
- if (!cmd->pool) {
- err = -ENOMEM;
- goto dma_pool_err;
- }
+ if (!cmd->pool)
+ return -ENOMEM;
err = alloc_cmd_page(dev, cmd);
if (err)
err_free_pool:
dma_pool_destroy(cmd->pool);
-dma_pool_err:
- kvfree(cmd->stats);
return err;
}
destroy_msg_cache(dev);
free_cmd_page(dev, cmd);
dma_pool_destroy(cmd->pool);
- kvfree(cmd->stats);
}
void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
pages = dev->priv.dbg.pages_debugfs;
debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages);
- debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.vfs_pages);
- debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.host_pf_pages);
+ debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.page_counters[MLX5_VF]);
+ debugfs_create_u32("fw_pages_sfs", 0400, pages, &dev->priv.page_counters[MLX5_SF]);
+ debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.page_counters[MLX5_HOST_PF]);
debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed);
debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped);
debugfs_create_u32("fw_pages_reclaim_discard", 0400, pages,
bool new_state = val.vbool;
if (new_state && !MLX5_CAP_GEN(dev, roce) &&
- !MLX5_CAP_GEN(dev, roce_rw_supported)) {
+ !(MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))) {
NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE");
return -EOPNOTSUPP;
}
union devlink_param_value val,
struct netlink_ext_ack *extack)
{
- return (val.vu16 >= 64 && val.vu16 <= 4096) ? 0 : -EINVAL;
+ return (val.vu32 >= 64 && val.vu32 <= 4096) ? 0 : -EINVAL;
}
static const struct devlink_param mlx5_devlink_params[] = {
MLX5_GET(mtrc_cap, out, num_string_trace);
tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db);
tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner);
+ tracer->str_db.loaded = false;
for (i = 0; i < tracer->str_db.num_string_db; i++) {
mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]);
if (err)
mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err);
+ tracer->buff.consumer_index = 0;
return err;
}
mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner);
if (tracer->owner) {
tracer->owner = false;
- tracer->buff.consumer_index = 0;
return;
}
mlx5_host_pf_cleanup(dev);
- err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages);
+ err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]);
if (err)
mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err);
}
if (child->bw_share == old_bw_share)
continue;
- err_one = mlx5_qos_update_node(htb->mdev, child->hw_id, child->bw_share,
+ err_one = mlx5_qos_update_node(htb->mdev, child->bw_share,
child->max_average_bw, child->hw_id);
if (!err && err_one) {
err = err_one;
mlx5e_htb_convert_rate(htb, rate, node->parent, &bw_share);
mlx5e_htb_convert_ceil(htb, ceil, &max_average_bw);
- err = mlx5_qos_update_node(htb->mdev, node->parent->hw_id, bw_share,
+ err = mlx5_qos_update_node(htb->mdev, bw_share,
max_average_bw, node->hw_id);
if (err) {
NL_SET_ERR_MSG_MOD(extack, "Firmware error when modifying a node.");
{
enum mlx5e_mpwrq_umr_mode umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk);
u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk);
- bool unaligned = xsk ? xsk->unaligned : false;
u16 max_mtu_pkts;
if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode))
* needed number of WQEs exceeds the maximum.
*/
max_mtu_pkts = min_t(u8, MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE,
- mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, unaligned));
+ mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, xsk->unaligned));
if (params->log_rq_mtu_frames > max_mtu_pkts) {
mlx5_core_err(mdev, "Current RQ length %d is too big for XSK with given frame size %u\n",
1 << params->log_rq_mtu_frames, xsk->chunk_size);
switch (event) {
case SWITCHDEV_FDB_ADD_TO_BRIDGE:
- /* only handle the event on native eswtich of representor */
- if (!mlx5_esw_bridge_is_local(dev, rep, esw))
- break;
-
fdb_info = container_of(info,
struct switchdev_notifier_fdb_info,
info);
goto unlock;
for (i = 0; i < priv->channels.num; i++) {
- struct mlx5e_rq *rq = &priv->channels.c[i]->rq;
+ struct mlx5e_channel *c = priv->channels.c[i];
+ struct mlx5e_rq *rq;
+
+ rq = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state) ?
+ &c->xskrq : &c->rq;
err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg);
if (err)
return -EOPNOTSUPP;
}
- if (act->police.rate_pkt_ps) {
- NL_SET_ERR_MSG_MOD(extack,
- "QoS offload not support packets per second");
- return -EOPNOTSUPP;
- }
-
return 0;
}
attr->counter = act_counter;
attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT;
+ attr->inner_match_level = MLX5_MATCH_NONE;
attr->outer_match_level = MLX5_MATCH_NONE;
attr->chain = 0;
attr->prio = 0;
struct mlx5e_sample_flow *sample_flow;
struct mlx5e_sample_attr *sample_attr;
struct mlx5_flow_attr *pre_attr;
- u32 tunnel_id = attr->tunnel_id;
struct mlx5_eswitch *esw;
u32 default_tbl_id;
u32 obj_id;
restore_obj.sample.group_id = sample_attr->group_num;
restore_obj.sample.rate = sample_attr->rate;
restore_obj.sample.trunc_size = sample_attr->trunc_size;
- restore_obj.sample.tunnel_id = tunnel_id;
+ restore_obj.sample.tunnel_id = attr->tunnel_id;
err = mapping_add(esw->offloads.reg_c0_obj_pool, &restore_obj, &obj_id);
if (err)
goto err_obj_id;
/* For decap action, do decap in the original flow table instead of the
* default flow table.
*/
- if (tunnel_id)
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
pre_attr->modify_hdr = sample_flow->restore->modify_hdr;
pre_attr->flags = MLX5_ATTR_FLAG_SAMPLE;
static void
mlx5_ct_tc_create_dbgfs(struct mlx5_tc_ct_priv *ct_priv)
{
- bool is_fdb = ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB;
struct mlx5_tc_ct_debugfs *ct_dbgfs = &ct_priv->debugfs;
- char dirname[16] = {};
- if (sscanf(dirname, "ct_%s", is_fdb ? "fdb" : "nic") < 0)
- return;
-
- ct_dbgfs->root = debugfs_create_dir(dirname, mlx5_debugfs_get_dev_root(ct_priv->dev));
+ ct_dbgfs->root = debugfs_create_dir("ct", mlx5_debugfs_get_dev_root(ct_priv->dev));
debugfs_create_atomic_t("offloaded", 0400, ct_dbgfs->root,
&ct_dbgfs->stats.offloaded);
debugfs_create_atomic_t("rx_dropped", 0400, ct_dbgfs->root,
int err;
list_for_each_entry(flow, flow_list, tmp_list) {
- if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW))
+ if (!mlx5e_is_offloaded_flow(flow))
continue;
attr = mlx5e_tc_get_encap_attr(flow);
esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL;
+ /* Clear pkt_reformat before checking slow path flag. Because
+ * in next iteration, the same flow is already set slow path
+ * flag, but still need to clear the pkt_reformat.
+ */
+ if (flow_flag_test(flow, SLOW))
+ continue;
+
/* update from encap rule to slow path rule */
spec = &flow->attr->parse_attr->spec;
rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec);
geneve_tlv_option_0_data, be32_to_cpu(opt_data_key));
MLX5_SET(fte_match_set_misc3, misc_3_c,
geneve_tlv_option_0_data, be32_to_cpu(opt_data_mask));
+ if (MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+ ft_field_support.geneve_tlv_option_0_exist)) {
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, geneve_tlv_option_0_exist);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc_v, geneve_tlv_option_0_exist);
+ }
spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3;
struct udphdr *udp = (struct udphdr *)(buf);
struct vxlanhdr *vxh;
+ if (tun_key->tun_flags & TUNNEL_VXLAN_OPT)
+ return -EOPNOTSUPP;
vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
*ip_proto = IPPROTO_UDP;
u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)];
dma_addr_t dma_addr;
struct mlx5_aso *aso;
- /* IPsec ASO caches data on every query call,
- * so in nested calls, we can use this boolean to save
- * recursive calls to mlx5e_ipsec_aso_query()
- */
- u8 use_cache : 1;
+ /* Protect ASO WQ access, as it is global to whole IPsec */
+ spinlock_t lock;
};
struct mlx5e_ipsec {
if (ret)
goto unlock;
- aso->use_cache = true;
if (attrs->esn_trigger &&
!MLX5_GET(ipsec_aso, aso->ctx, esn_event_arm)) {
u32 mode_param = MLX5_GET(ipsec_aso, aso->ctx, mode_parameter);
!MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm) ||
!MLX5_GET(ipsec_aso, aso->ctx, remove_flow_enable))
xfrm_state_check_expire(sa_entry->x);
- aso->use_cache = false;
unlock:
spin_unlock(&sa_entry->x->lock);
goto err_aso_create;
}
+ spin_lock_init(&aso->lock);
ipsec->nb.notifier_call = mlx5e_ipsec_event;
mlx5_notifier_register(mdev, &ipsec->nb);
struct mlx5e_hw_objs *res;
struct mlx5_aso_wqe *wqe;
u8 ds_cnt;
+ int ret;
lockdep_assert_held(&sa_entry->x->lock);
- if (aso->use_cache)
- return 0;
-
res = &mdev->mlx5e_res.hw_objs;
+ spin_lock_bh(&aso->lock);
memset(aso->ctx, 0, sizeof(aso->ctx));
wqe = mlx5_aso_get_wqe(aso->aso);
ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS);
mlx5e_ipsec_aso_copy(ctrl, data);
mlx5_aso_post_wqe(aso->aso, false, &wqe->ctrl);
- return mlx5_aso_poll_cq(aso->aso, false);
+ ret = mlx5_aso_poll_cq(aso->aso, false);
+ spin_unlock_bh(&aso->lock);
+ return ret;
}
void mlx5e_ipsec_aso_update_curlft(struct mlx5e_ipsec_sa_entry *sa_entry,
u32 enc_key_id;
u32 next_pn;
sci_t sci;
+ ssci_t ssci;
salt_t salt;
struct rhash_head hash;
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5_macsec_obj_attrs obj_attrs;
union mlx5e_macsec_rule *macsec_rule;
- struct macsec_key *key;
int err;
obj_attrs.next_pn = sa->next_pn;
obj_attrs.aso_pdn = macsec->aso.pdn;
obj_attrs.epn_state = sa->epn_state;
- key = (is_tx) ? &ctx->sa.tx_sa->key : &ctx->sa.rx_sa->key;
-
if (sa->epn_state.epn_enabled) {
- obj_attrs.ssci = (is_tx) ? cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci) :
- cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci);
-
- memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt));
+ obj_attrs.ssci = cpu_to_be32((__force u32)sa->ssci);
+ memcpy(&obj_attrs.salt, &sa->salt, sizeof(sa->salt));
}
obj_attrs.replay_window = ctx->secy->replay_window;
}
static void update_macsec_epn(struct mlx5e_macsec_sa *sa, const struct macsec_key *key,
- const pn_t *next_pn_halves)
+ const pn_t *next_pn_halves, ssci_t ssci)
{
struct mlx5e_macsec_epn_state *epn_state = &sa->epn_state;
+ sa->ssci = ssci;
sa->salt = key->salt;
epn_state->epn_enabled = 1;
epn_state->epn_msb = next_pn_halves->upper;
tx_sa->assoc_num = assoc_num;
if (secy->xpn)
- update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves);
+ update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves,
+ ctx_tx_sa->ssci);
err = mlx5_create_encryption_key(mdev, ctx->sa.key, secy->key_len,
MLX5_ACCEL_OBJ_MACSEC_KEY,
rx_sa->fs_id = rx_sc->sc_xarray_element->fs_id;
if (ctx->secy->xpn)
- update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves);
+ update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves,
+ ctx_rx_sa->ssci);
err = mlx5_create_encryption_key(mdev, ctx->sa.key, ctx->secy->key_len,
MLX5_ACCEL_OBJ_MACSEC_KEY,
void mlx5e_disable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc)
{
- if (fs->vlan->cvlan_filter_disabled)
+ if (!fs->vlan || fs->vlan->cvlan_filter_disabled)
return;
fs->vlan->cvlan_filter_disabled = true;
rq->ix = c->ix;
rq->channel = c;
rq->mdev = mdev;
- rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+ rq->hw_mtu =
+ MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN * !params->scatter_fcs_en;
rq->xdpsq = &c->rq_xdpsq;
rq->stats = &c->priv->channel_stats[c->ix]->rq;
rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev);
return mlx5e_rq_to_ready(rq, curr_state);
}
-static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable)
-{
- struct mlx5_core_dev *mdev = rq->mdev;
-
- void *in;
- void *rqc;
- int inlen;
- int err;
-
- inlen = MLX5_ST_SZ_BYTES(modify_rq_in);
- in = kvzalloc(inlen, GFP_KERNEL);
- if (!in)
- return -ENOMEM;
-
- rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
-
- MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY);
- MLX5_SET64(modify_rq_in, in, modify_bitmask,
- MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS);
- MLX5_SET(rqc, rqc, scatter_fcs, enable);
- MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY);
-
- err = mlx5_core_modify_rq(mdev, rq->rqn, in);
-
- kvfree(in);
-
- return err;
-}
-
static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd)
{
struct mlx5_core_dev *mdev = rq->mdev;
sq->channel = c;
sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map;
sq->min_inline_mode = params->tx_min_inline_mode;
- sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+ sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
sq->xsk_pool = xsk_pool;
sq->stats = sq->xsk_pool ?
mlx5e_destroy_tises(priv);
}
-static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable)
-{
- int err = 0;
- int i;
-
- for (i = 0; i < chs->num; i++) {
- err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable);
- if (err)
- return err;
- }
-
- return 0;
-}
-
static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
{
int err;
return mlx5_set_ports_check(mdev, in, sizeof(in));
}
+static int mlx5e_set_rx_port_ts_wrap(struct mlx5e_priv *priv, void *ctx)
+{
+ struct mlx5_core_dev *mdev = priv->mdev;
+ bool enable = *(bool *)ctx;
+
+ return mlx5e_set_rx_port_ts(mdev, enable);
+}
+
static int set_feature_rx_fcs(struct net_device *netdev, bool enable)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5e_channels *chs = &priv->channels;
- struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5e_params new_params;
int err;
mutex_lock(&priv->state_lock);
- if (enable) {
- err = mlx5e_set_rx_port_ts(mdev, false);
- if (err)
- goto out;
-
- chs->params.scatter_fcs_en = true;
- err = mlx5e_modify_channels_scatter_fcs(chs, true);
- if (err) {
- chs->params.scatter_fcs_en = false;
- mlx5e_set_rx_port_ts(mdev, true);
- }
- } else {
- chs->params.scatter_fcs_en = false;
- err = mlx5e_modify_channels_scatter_fcs(chs, false);
- if (err) {
- chs->params.scatter_fcs_en = true;
- goto out;
- }
- err = mlx5e_set_rx_port_ts(mdev, true);
- if (err) {
- mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err);
- err = 0;
- }
- }
-
-out:
+ new_params = chs->params;
+ new_params.scatter_fcs_en = enable;
+ err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_set_rx_port_ts_wrap,
+ &new_params.scatter_fcs_en, true);
mutex_unlock(&priv->state_lock);
return err;
}
if (netdev->features & NETIF_F_GRO_HW)
netdev_warn(netdev, "Disabling HW_GRO, not supported in switchdev mode\n");
+ features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
+ if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
+ netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n");
+
return features;
}
struct mlx5e_vlan_table *vlan;
struct mlx5e_params *params;
+ if (!netif_device_present(netdev))
+ return features;
+
vlan = mlx5e_fs_get_vlan(priv->fs);
mutex_lock(&priv->state_lock);
params = &priv->channels.params;
if (err) {
netdev_warn(priv->netdev, "vport %d error %d reading stats\n",
rep->vport, err);
- return;
+ goto out;
}
#define MLX5_GET_CTR(p, x) \
rep_stats->tx_vport_rdma_multicast_bytes =
MLX5_GET_CTR(out, received_ib_multicast.octets);
+out:
kvfree(out);
}
priv = mlx5i_epriv(netdev);
tstamp = &priv->tstamp;
- stats = rq->stats;
+ stats = &priv->channel_stats[rq->ix]->rq;
flags_rqpn = be32_to_cpu(cqe->flags_rqpn);
g = (flags_rqpn >> 28) & 3;
* it's different than the ht->mutex here.
*/
static struct lock_class_key tc_ht_lock_key;
+static struct lock_class_key tc_ht_wq_key;
static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow);
static void free_flow_post_acts(struct mlx5e_tc_flow *flow);
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
err = mlx5e_attach_mod_hdr(priv, flow, parse_attr);
- mlx5e_mod_hdr_dealloc(&parse_attr->mod_hdr_acts);
if (err)
return err;
}
}
mutex_unlock(&tc->t_lock);
- if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+ mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts);
mlx5e_detach_mod_hdr(priv, flow);
+ }
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
mlx5_fc_destroy(priv->mdev, attr->counter);
return err;
lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key);
+ lockdep_init_map(&tc->ht.run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0);
mapping_id = mlx5_query_nic_system_image_guid(dev);
return err;
lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key);
+ lockdep_init_map(&tc_ht->run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0);
return 0;
}
int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
struct mlx5_flow_destination drop_ctr_dst = {};
struct mlx5_flow_destination *dst = NULL;
struct mlx5_fc *drop_counter = NULL;
*/
int table_size = 2;
int dest_num = 0;
+ int actions_flag;
int err = 0;
if (vport->egress.legacy.drop_counter) {
vport->vport, vport->info.vlan, vport->info.qos);
/* Allowed vlan rule */
+ actions_flag = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ if (vst_mode_steering)
+ actions_flag |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
err = esw_egress_acl_vlan_create(esw, vport, NULL, vport->info.vlan,
- MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+ actions_flag);
if (err)
goto out;
int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
struct mlx5_flow_destination drop_ctr_dst = {};
struct mlx5_flow_destination *dst = NULL;
struct mlx5_flow_act flow_act = {};
struct mlx5_flow_spec *spec = NULL;
struct mlx5_fc *counter = NULL;
+ bool vst_check_cvlan = false;
+ bool vst_push_cvlan = false;
/* The ingress acl table contains 4 groups
* (2 active rules at the same time -
* 1 allow rule from one of the first 3 groups.
goto out;
}
- if (vport->info.vlan || vport->info.qos)
+ if ((vport->info.vlan || vport->info.qos)) {
+ if (vst_mode_steering)
+ vst_push_cvlan = true;
+ else if (!MLX5_CAP_ESW(esw->dev, vport_cvlan_insert_always))
+ vst_check_cvlan = true;
+ }
+
+ if (vst_check_cvlan || vport->info.spoofchk)
+ spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+
+ /* Create ingress allow rule */
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ if (vst_push_cvlan) {
+ flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+ flow_act.vlan[0].prio = vport->info.qos;
+ flow_act.vlan[0].vid = vport->info.vlan;
+ flow_act.vlan[0].ethtype = ETH_P_8021Q;
+ }
+
+ if (vst_check_cvlan)
MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
outer_headers.cvlan_tag);
ether_addr_copy(smac_v, vport->info.mac);
}
- /* Create ingress allow rule */
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec,
&flow_act, NULL, 0);
if (IS_ERR(vport->ingress.allow_rule)) {
goto out;
}
+ if (!vst_check_cvlan && !vport->info.spoofchk)
+ goto out;
+
memset(&flow_act, 0, sizeof(flow_act));
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
/* Attach drop flow counter */
return 0;
out:
- esw_acl_ingress_lgcy_cleanup(esw, vport);
+ if (err)
+ esw_acl_ingress_lgcy_cleanup(esw, vport);
kvfree(spec);
return err;
}
struct mlx5_esw_bridge *bridge;
port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
- if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER)
+ if (!port)
return;
bridge = port->bridge;
};
static int esw_qos_tsar_config(struct mlx5_core_dev *dev, u32 *sched_ctx,
- u32 parent_ix, u32 tsar_ix,
- u32 max_rate, u32 bw_share)
+ u32 tsar_ix, u32 max_rate, u32 bw_share)
{
u32 bitmask = 0;
if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
return -EOPNOTSUPP;
- MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_ix);
MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate);
MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
int err;
err = esw_qos_tsar_config(dev, sched_ctx,
- esw->qos.root_tsar_ix, group->tsar_ix,
+ group->tsar_ix,
max_rate, bw_share);
if (err)
NL_SET_ERR_MSG_MOD(extack, "E-Switch modify group TSAR element failed");
struct netlink_ext_ack *extack)
{
u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
- struct mlx5_esw_rate_group *group = vport->qos.group;
struct mlx5_core_dev *dev = esw->dev;
- u32 parent_tsar_ix;
- void *vport_elem;
int err;
if (!vport->qos.enabled)
return -EIO;
- parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
- MLX5_SET(scheduling_context, sched_ctx, element_type,
- SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
- vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
- element_attributes);
- MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
-
- err = esw_qos_tsar_config(dev, sched_ctx, parent_tsar_ix, vport->qos.esw_tsar_ix,
+ err = esw_qos_tsar_config(dev, sched_ctx, vport->qos.esw_tsar_ix,
max_rate, bw_share);
if (err) {
esw_warn(esw->dev,
esw_vport_context.vport_cvlan_strip, 1);
if (set_flags & SET_VLAN_INSERT) {
- /* insert only if no vlan in packet */
- MLX5_SET(modify_esw_vport_context_in, in,
- esw_vport_context.vport_cvlan_insert, 1);
-
+ if (MLX5_CAP_ESW(dev, vport_cvlan_insert_always)) {
+ /* insert either if vlan exist in packet or not */
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.vport_cvlan_insert,
+ MLX5_VPORT_CVLAN_INSERT_ALWAYS);
+ } else {
+ /* insert only if no vlan in packet */
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.vport_cvlan_insert,
+ MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN);
+ }
MLX5_SET(modify_esw_vport_context_in, in,
esw_vport_context.cvlan_pcp, qos);
MLX5_SET(modify_esw_vport_context_in, in,
static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
u16 vport_num = vport->vport;
int flags;
int err;
flags = (vport->info.vlan || vport->info.qos) ?
SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
- modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
- vport->info.qos, flags);
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering)
+ modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
+ vport->info.qos, flags);
return 0;
mlx5_lag_disable_change(esw->dev);
down_write(&esw->mode_lock);
mlx5_eswitch_disable_locked(esw);
+ esw->mode = MLX5_ESWITCH_LEGACY;
up_write(&esw->mode_lock);
mlx5_lag_enable_change(esw->dev);
}
u16 vport, u16 vlan, u8 qos, u8 set_flags)
{
struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
int err = 0;
if (IS_ERR(evport))
if (vlan > 4095 || qos > 7)
return -EINVAL;
- err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
- if (err)
- return err;
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering) {
+ err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
+ if (err)
+ return err;
+ }
evport->info.vlan = vlan;
evport->info.qos = qos;
int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
u16 vport, u16 vlan, u8 qos, u8 set_flags);
+static inline bool esw_vst_mode_is_steering(struct mlx5_eswitch *esw)
+{
+ return (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, pop_vlan) &&
+ MLX5_CAP_ESW_INGRESS_ACL(esw->dev, push_vlan));
+}
+
static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
u8 vlan_depth)
{
if (mlx5_esw_indir_table_decap_vport(attr))
vport = mlx5_esw_indir_table_decap_vport(attr);
- if (attr && !attr->chain && esw_attr->int_port)
+ if (!attr->chain && esw_attr && esw_attr->int_port)
metadata =
mlx5e_tc_int_port_get_metadata_for_match(esw_attr->int_port);
else
}
hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
- memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability),
- MLX5_UN_SZ_BYTES(hca_cap_union));
MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1);
err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport,
}
hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
- memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability),
- MLX5_UN_SZ_BYTES(hca_cap_union));
MLX5_SET(cmd_hca_cap, hca_caps, roce, enable);
err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport_num,
dev = container_of(priv, struct mlx5_core_dev, priv);
devlink = priv_to_devlink(dev);
+ mutex_lock(&dev->intf_state_mutex);
+ if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) {
+ mlx5_core_err(dev, "health works are not permitted at this stage\n");
+ mutex_unlock(&dev->intf_state_mutex);
+ return;
+ }
+ mutex_unlock(&dev->intf_state_mutex);
enter_error_state(dev, false);
if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {
devl_lock(devlink);
static int mlx5i_set_channels(struct net_device *dev,
struct ethtool_channels *ch)
{
- struct mlx5e_priv *priv = mlx5i_epriv(dev);
+ struct mlx5i_priv *ipriv = netdev_priv(dev);
+ struct mlx5e_priv *epriv = mlx5i_epriv(dev);
+
+ /* rtnl lock protects from race between this ethtool op and sub
+ * interface ndo_init/uninit.
+ */
+ ASSERT_RTNL();
+ if (ipriv->num_sub_interfaces > 0) {
+ mlx5_core_warn(epriv->mdev,
+ "can't change number of channels for interfaces with sub interfaces (%u)\n",
+ ipriv->num_sub_interfaces);
+ return -EINVAL;
+ }
- return mlx5e_ethtool_set_channels(priv, ch);
+ return mlx5e_ethtool_set_channels(epriv, ch);
}
static void mlx5i_get_channels(struct net_device *dev,
}
}
-static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper)
+static u32 mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper)
{
int rate, width;
rate = mlx5_ptys_rate_enum_to_int(ib_proto_oper);
if (rate < 0)
- return -EINVAL;
+ return SPEED_UNKNOWN;
width = mlx5_ptys_width_enum_to_int(ib_link_width_oper);
if (width < 0)
- return -EINVAL;
+ return SPEED_UNKNOWN;
return rate * width;
}
ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
speed = mlx5i_get_speed_settings(ib_link_width_oper, ib_proto_oper);
- if (speed < 0)
- return -EINVAL;
+ link_ksettings->base.speed = speed;
+ link_ksettings->base.duplex = speed == SPEED_UNKNOWN ? DUPLEX_UNKNOWN : DUPLEX_FULL;
- link_ksettings->base.duplex = DUPLEX_FULL;
link_ksettings->base.port = PORT_OTHER;
link_ksettings->base.autoneg = AUTONEG_DISABLE;
- link_ksettings->base.speed = speed;
-
return 0;
}
params->packet_merge.type = MLX5E_PACKET_MERGE_NONE;
params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
params->tunneled_offload_en = false;
+
+ /* CQE compression is not supported for IPoIB */
+ params->rx_cqe_compress_def = false;
+ MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
}
/* Called directly after IPoIB netdevice was created to initialize SW structs */
stats->tx_dropped = sstats->tx_queue_dropped;
}
+struct net_device *mlx5i_parent_get(struct net_device *netdev)
+{
+ struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+ struct mlx5i_priv *ipriv, *parent_ipriv;
+ struct net_device *parent_dev;
+ int parent_ifindex;
+
+ ipriv = priv->ppriv;
+
+ parent_ifindex = netdev->netdev_ops->ndo_get_iflink(netdev);
+ parent_dev = dev_get_by_index(dev_net(netdev), parent_ifindex);
+ if (!parent_dev)
+ return NULL;
+
+ parent_ipriv = netdev_priv(parent_dev);
+
+ ASSERT_RTNL();
+ parent_ipriv->num_sub_interfaces++;
+
+ ipriv->parent_dev = parent_dev;
+
+ return parent_dev;
+}
+
+void mlx5i_parent_put(struct net_device *netdev)
+{
+ struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+ struct mlx5i_priv *ipriv, *parent_ipriv;
+
+ ipriv = priv->ppriv;
+ parent_ipriv = netdev_priv(ipriv->parent_dev);
+
+ ASSERT_RTNL();
+ parent_ipriv->num_sub_interfaces--;
+
+ dev_put(ipriv->parent_dev);
+}
+
int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
{
struct mlx5_core_dev *mdev = priv->mdev;
struct rdma_netdev rn; /* keep this first */
u32 qpn;
bool sub_interface;
+ u32 num_sub_interfaces;
u32 qkey;
u16 pkey_index;
struct mlx5i_pkey_qpn_ht *qpn_htbl;
+ struct net_device *parent_dev;
char *mlx5e_priv[];
};
struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more);
void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
+/* Reference management for child to parent interfaces. */
+struct net_device *mlx5i_parent_get(struct net_device *netdev);
+void mlx5i_parent_put(struct net_device *netdev);
+
#endif /* CONFIG_MLX5_CORE_IPOIB */
#endif /* __MLX5E_IPOB_H__ */
struct mlx5e_priv *priv = mlx5i_epriv(dev);
struct mlx5i_priv *ipriv, *parent_ipriv;
struct net_device *parent_dev;
- int parent_ifindex;
ipriv = priv->ppriv;
- /* Get QPN to netdevice hash table from parent */
- parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev);
- parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex);
+ /* Link to parent */
+ parent_dev = mlx5i_parent_get(dev);
if (!parent_dev) {
mlx5_core_warn(priv->mdev, "failed to get parent device\n");
return -EINVAL;
}
+ if (dev->num_rx_queues < parent_dev->real_num_rx_queues) {
+ mlx5_core_warn(priv->mdev,
+ "failed to create child device with rx queues [%d] less than parent's [%d]\n",
+ dev->num_rx_queues,
+ parent_dev->real_num_rx_queues);
+ mlx5i_parent_put(dev);
+ return -EINVAL;
+ }
+
+ /* Get QPN to netdevice hash table from parent */
parent_ipriv = netdev_priv(parent_dev);
ipriv->qpn_htbl = parent_ipriv->qpn_htbl;
- dev_put(parent_dev);
return mlx5i_dev_init(dev);
}
static void mlx5i_pkey_dev_cleanup(struct net_device *netdev)
{
+ mlx5i_parent_put(netdev);
return mlx5i_dev_cleanup(netdev);
}
if (ldev->nb.notifier_call)
unregister_netdevice_notifier_net(&init_net, &ldev->nb);
mlx5_lag_mp_cleanup(ldev);
+ cancel_delayed_work_sync(&ldev->bond_work);
destroy_workqueue(ldev->wq);
mlx5_lag_mpesw_cleanup(ldev);
mutex_destroy(&ldev->lock);
static const struct ptp_clock_info mlx5_ptp_clock_info = {
.owner = THIS_MODULE,
.name = "mlx5_ptp",
- .max_adj = 100000000,
+ .max_adj = 50000000,
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 0,
MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix,
MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
- if (MLX5_CAP_GEN(dev, roce_rw_supported))
+ if (MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))
MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
mlx5_is_roce_on(dev));
err_tables_cleanup:
mlx5_geneve_destroy(dev->geneve);
mlx5_vxlan_destroy(dev->vxlan);
+ mlx5_cleanup_clock(dev);
+ mlx5_cleanup_reserved_gids(dev);
mlx5_cq_debugfs_cleanup(dev);
mlx5_fw_reset_cleanup(dev);
err_events_cleanup:
}
}
-static int __init init(void)
+static int __init mlx5_init(void)
{
int err;
mlx5_core_verify_params();
mlx5_register_debugfs();
- err = pci_register_driver(&mlx5_core_driver);
+ err = mlx5e_init();
if (err)
goto err_debug;
if (err)
goto err_sf;
- err = mlx5e_init();
+ err = pci_register_driver(&mlx5_core_driver);
if (err)
- goto err_en;
+ goto err_pci;
return 0;
-err_en:
+err_pci:
mlx5_sf_driver_unregister();
err_sf:
- pci_unregister_driver(&mlx5_core_driver);
+ mlx5e_cleanup();
err_debug:
mlx5_unregister_debugfs();
return err;
}
-static void __exit cleanup(void)
+static void __exit mlx5_cleanup(void)
{
- mlx5e_cleanup();
- mlx5_sf_driver_unregister();
pci_unregister_driver(&mlx5_core_driver);
+ mlx5_sf_driver_unregister();
+ mlx5e_cleanup();
mlx5_unregister_debugfs();
}
-module_init(init);
-module_exit(cleanup);
+module_init(mlx5_init);
+module_exit(mlx5_cleanup);
return (u32)func_id | (ec_function << 16);
}
+static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_function)
+{
+ if (!func_id)
+ return mlx5_core_is_ecpf(dev) && !ec_function ? MLX5_HOST_PF : MLX5_PF;
+
+ return func_id <= mlx5_core_max_vfs(dev) ? MLX5_VF : MLX5_SF;
+}
+
static struct rb_root *page_root_per_function(struct mlx5_core_dev *dev, u32 function)
{
struct rb_root *root;
u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
int inlen = MLX5_ST_SZ_BYTES(manage_pages_in);
int notify_fail = event;
+ u16 func_type;
u64 addr;
int err;
u32 *in;
goto out_dropped;
}
+ func_type = func_id_to_type(dev, func_id, ec_function);
+ dev->priv.page_counters[func_type] += npages;
dev->priv.fw_pages += npages;
- if (func_id)
- dev->priv.vfs_pages += npages;
- else if (mlx5_core_is_ecpf(dev) && !ec_function)
- dev->priv.host_pf_pages += npages;
mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n",
npages, ec_function, func_id, err);
struct rb_root *root;
struct rb_node *p;
int npages = 0;
+ u16 func_type;
root = xa_load(&dev->priv.page_root_xa, function);
if (WARN_ON_ONCE(!root))
free_fwp(dev, fwp, fwp->free_count);
}
+ func_type = func_id_to_type(dev, func_id, ec_function);
+ dev->priv.page_counters[func_type] -= npages;
dev->priv.fw_pages -= npages;
- if (func_id)
- dev->priv.vfs_pages -= npages;
- else if (mlx5_core_is_ecpf(dev) && !ec_function)
- dev->priv.host_pf_pages -= npages;
mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n",
npages, ec_function, func_id);
int outlen = MLX5_ST_SZ_BYTES(manage_pages_out);
u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {};
int num_claimed;
+ u16 func_type;
u32 *out;
int err;
int i;
if (nclaimed)
*nclaimed = num_claimed;
+ func_type = func_id_to_type(dev, func_id, ec_function);
+ dev->priv.page_counters[func_type] -= num_claimed;
dev->priv.fw_pages -= num_claimed;
- if (func_id)
- dev->priv.vfs_pages -= num_claimed;
- else if (mlx5_core_is_ecpf(dev) && !ec_function)
- dev->priv.host_pf_pages -= num_claimed;
out_free:
kvfree(out);
WARN(dev->priv.fw_pages,
"FW pages counter is %d after reclaiming all pages\n",
dev->priv.fw_pages);
- WARN(dev->priv.vfs_pages,
+ WARN(dev->priv.page_counters[MLX5_VF],
"VFs FW pages counter is %d after reclaiming all pages\n",
- dev->priv.vfs_pages);
- WARN(dev->priv.host_pf_pages,
+ dev->priv.page_counters[MLX5_VF]);
+ WARN(dev->priv.page_counters[MLX5_HOST_PF],
"External host PF FW pages counter is %d after reclaiming all pages\n",
- dev->priv.host_pf_pages);
+ dev->priv.page_counters[MLX5_HOST_PF]);
return 0;
}
return mlx5_qos_create_inner_node(mdev, MLX5_QOS_DEFAULT_DWRR_UID, 0, 0, id);
}
-int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id,
+int mlx5_qos_update_node(struct mlx5_core_dev *mdev,
u32 bw_share, u32 max_avg_bw, u32 id)
{
u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
u32 bitmask = 0;
- MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id);
MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_avg_bw);
int mlx5_qos_create_inner_node(struct mlx5_core_dev *mdev, u32 parent_id,
u32 bw_share, u32 max_avg_bw, u32 *id);
int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id);
-int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id, u32 bw_share,
+int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 bw_share,
u32 max_avg_bw, u32 id);
int mlx5_qos_destroy_node(struct mlx5_core_dev *mdev, u32 id);
mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf);
- if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages))
+ if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF]))
mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
}
#include "dr_types.h"
+#if defined(CONFIG_FRAME_WARN) && (CONFIG_FRAME_WARN < 2048)
+/* don't try to optimize STE allocation if the stack is too constaraining */
+#define DR_RULE_MAX_STES_OPTIMIZED 0
+#else
#define DR_RULE_MAX_STES_OPTIMIZED 5
+#endif
#define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES)
static int dr_rule_append_to_miss_list(struct mlx5dr_domain *dmn,
rule->flow_source))
return 0;
+ mlx5dr_domain_nic_lock(nic_dmn);
+
ret = mlx5dr_matcher_select_builders(matcher,
nic_matcher,
dr_rule_get_ipv(¶m->outer),
dr_rule_get_ipv(¶m->inner));
if (ret)
- return ret;
+ goto err_unlock;
hw_ste_arr_is_opt = nic_matcher->num_of_builders <= DR_RULE_MAX_STES_OPTIMIZED;
if (likely(hw_ste_arr_is_opt)) {
hw_ste_arr = kzalloc((nic_matcher->num_of_builders + DR_ACTION_MAX_STES) *
DR_STE_SIZE, GFP_KERNEL);
- if (!hw_ste_arr)
- return -ENOMEM;
+ if (!hw_ste_arr) {
+ ret = -ENOMEM;
+ goto err_unlock;
+ }
}
- mlx5dr_domain_nic_lock(nic_dmn);
-
ret = mlx5dr_matcher_add_to_tbl_nic(dmn, nic_matcher);
if (ret)
goto free_hw_ste;
mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher);
free_hw_ste:
- mlx5dr_domain_nic_unlock(nic_dmn);
-
- if (unlikely(!hw_ste_arr_is_opt))
+ if (!hw_ste_arr_is_opt)
kfree(hw_ste_arr);
+err_unlock:
+ mlx5dr_domain_nic_unlock(nic_dmn);
+
return ret;
}
gateway:1, /* routes using the group use a gateway */
is_resilient:1;
struct list_head list; /* member in nh_res_grp_list */
- struct mlxsw_sp_nexthop nexthops[0];
+ struct mlxsw_sp_nexthop nexthops[];
#define nh_rif nexthops[0].rif
};
lan966x_fdma_rx_reload(rx);
}
- if (counter < weight && napi_complete_done(napi, counter))
- lan_wr(0xff, lan966x, FDMA_INTR_DB_ENA);
-
if (redirect)
xdp_do_flush();
+ if (counter < weight && napi_complete_done(napi, counter))
+ lan_wr(0xff, lan966x, FDMA_INTR_DB_ENA);
+
return counter;
}
lan966x->base_mac[5] &= 0xf0;
}
- ports = device_get_named_child_node(&pdev->dev, "ethernet-ports");
- if (!ports)
- return dev_err_probe(&pdev->dev, -ENODEV,
- "no ethernet-ports child found\n");
-
err = lan966x_create_targets(pdev, lan966x);
if (err)
return dev_err_probe(&pdev->dev, err,
}
}
+ ports = device_get_named_child_node(&pdev->dev, "ethernet-ports");
+ if (!ports)
+ return dev_err_probe(&pdev->dev, -ENODEV,
+ "no ethernet-ports child found\n");
+
/* init switch */
lan966x_init(lan966x);
lan966x_stats_init(lan966x);
goto cleanup_ports;
}
+ fwnode_handle_put(ports);
+
lan966x_mdb_init(lan966x);
err = lan966x_fdb_init(lan966x);
if (err)
lan966x_fdb_deinit(lan966x);
cleanup_ports:
+ fwnode_handle_put(ports);
fwnode_handle_put(portnp);
lan966x_cleanup_ports(lan966x);
}
/* Take PCS out of reset */
- lan_rmw(DEV_CLOCK_CFG_LINK_SPEED_SET(2) |
+ lan_rmw(DEV_CLOCK_CFG_LINK_SPEED_SET(LAN966X_SPEED_1000) |
DEV_CLOCK_CFG_PCS_RX_RST_SET(0) |
DEV_CLOCK_CFG_PCS_TX_RST_SET(0),
DEV_CLOCK_CFG_LINK_SPEED |
struct lan966x_port *port;
int i;
+ if (!lan966x->ptp)
+ return;
+
for (i = 0; i < lan966x->num_phys_ports; i++) {
port = lan966x->ports[i];
if (!port)
bool found = false;
u32 val;
- /* Check if the port keyset selection is enabled */
val = lan_rd(lan966x, ANA_VCAP_S2_CFG(port->chip_port));
- if (!ANA_VCAP_S2_CFG_ENA_GET(val))
- return -ENOENT;
/* Collect all keysets for the port in a list */
if (l3_proto == ETH_P_ALL)
if (err)
goto cleanup_config;
- if (!of_get_mac_address(np, sparx5->base_mac)) {
+ if (of_get_mac_address(np, sparx5->base_mac)) {
dev_info(sparx5->dev, "MAC addr was not set, use random MAC\n");
eth_random_addr(sparx5->base_mac);
sparx5->base_mac[5] = 0;
/* Enable master counters */
spx5_wr(PTP_PTP_DOM_CFG_PTP_ENA_SET(0x7), sparx5, PTP_PTP_DOM_CFG);
- for (i = 0; i < sparx5->port_count; i++) {
+ for (i = 0; i < SPX5_PORTS; i++) {
port = sparx5->ports[i];
if (!port)
continue;
struct sparx5_port *port;
int i;
- for (i = 0; i < sparx5->port_count; i++) {
+ for (i = 0; i < SPX5_PORTS; i++) {
port = sparx5->ports[i];
if (!port)
continue;
unsigned int max_queues_per_port = num_online_cpus();
struct gdma_context *gc = pci_get_drvdata(pdev);
struct gdma_irq_context *gic;
- unsigned int max_irqs;
- u16 *cpus;
- cpumask_var_t req_mask;
+ unsigned int max_irqs, cpu;
int nvec, irq;
int err, i = 0, j;
goto free_irq_vector;
}
- if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) {
- err = -ENOMEM;
- goto free_irq;
- }
-
- cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL);
- if (!cpus) {
- err = -ENOMEM;
- goto free_mask;
- }
- for (i = 0; i < nvec; i++)
- cpus[i] = cpumask_local_spread(i, gc->numa_node);
-
for (i = 0; i < nvec; i++) {
- cpumask_set_cpu(cpus[i], req_mask);
gic = &gc->irq_contexts[i];
gic->handler = NULL;
gic->arg = NULL;
+ if (!i)
+ snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_hwc@pci:%s",
+ pci_name(pdev));
+ else
+ snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s",
+ i - 1, pci_name(pdev));
+
irq = pci_irq_vector(pdev, i);
if (irq < 0) {
err = irq;
- goto free_mask;
+ goto free_irq;
}
- err = request_irq(irq, mana_gd_intr, 0, "mana_intr", gic);
+ err = request_irq(irq, mana_gd_intr, 0, gic->name, gic);
if (err)
- goto free_mask;
- irq_set_affinity_and_hint(irq, req_mask);
- cpumask_clear(req_mask);
+ goto free_irq;
+
+ cpu = cpumask_local_spread(i, gc->numa_node);
+ irq_set_affinity_and_hint(irq, cpumask_of(cpu));
}
- free_cpumask_var(req_mask);
- kfree(cpus);
err = mana_gd_alloc_res_map(nvec, &gc->msix_resource);
if (err)
return 0;
-free_mask:
- free_cpumask_var(req_mask);
- kfree(cpus);
free_irq:
for (j = i - 1; j >= 0; j--) {
irq = pci_irq_vector(pdev, j);
gic = &gc->irq_contexts[j];
+
+ irq_update_affinity_hint(irq, NULL);
free_irq(irq, gic);
}
continue;
gic = &gc->irq_contexts[i];
+
+ /* Need to clear the hint before free_irq */
+ irq_update_affinity_hint(irq, NULL);
free_irq(irq, gic);
}
flow_rule_match_control(rule, &match);
}
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_match_vlan match;
+
+ flow_rule_match_vlan(rule, &match);
+ filter->key_type = OCELOT_VCAP_KEY_ANY;
+ filter->vlan.vid.value = match.key->vlan_id;
+ filter->vlan.vid.mask = match.mask->vlan_id;
+ filter->vlan.pcp.value[0] = match.key->vlan_priority;
+ filter->vlan.pcp.mask[0] = match.mask->vlan_priority;
+ match_protocol = false;
+ }
+
if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
struct flow_match_eth_addrs match;
match_protocol = false;
}
- if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
- struct flow_match_vlan match;
-
- flow_rule_match_vlan(rule, &match);
- filter->key_type = OCELOT_VCAP_KEY_ANY;
- filter->vlan.vid.value = match.key->vlan_id;
- filter->vlan.vid.mask = match.mask->vlan_id;
- filter->vlan.pcp.value[0] = match.key->vlan_priority;
- filter->vlan.pcp.mask[0] = match.mask->vlan_priority;
- match_protocol = false;
- }
-
finished_key_parsing:
if (match_protocol && proto != ETH_P_ALL) {
if (filter->block_id == VCAP_ES0) {
ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap)
{
trap->key_type = OCELOT_VCAP_KEY_IPV6;
- trap->key.ipv4.proto.value[0] = IPPROTO_UDP;
- trap->key.ipv4.proto.mask[0] = 0xff;
+ trap->key.ipv6.proto.value[0] = IPPROTO_UDP;
+ trap->key.ipv6.proto.mask[0] = 0xff;
trap->key.ipv6.dport.value = PTP_EV_PORT;
trap->key.ipv6.dport.mask = 0xffff;
}
ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap)
{
trap->key_type = OCELOT_VCAP_KEY_IPV6;
- trap->key.ipv4.proto.value[0] = IPPROTO_UDP;
- trap->key.ipv4.proto.mask[0] = 0xff;
+ trap->key.ipv6.proto.value[0] = IPPROTO_UDP;
+ trap->key.ipv6.proto.mask[0] = 0xff;
trap->key.ipv6.dport.value = PTP_GEN_PORT;
trap->key.ipv6.dport.mask = 0xffff;
}
};
};
-static int nfp_ipsec_cfg_cmd_issue(struct nfp_net *nn, int type, int saidx,
- struct nfp_ipsec_cfg_mssg *msg)
+static int nfp_net_ipsec_cfg(struct nfp_net *nn, struct nfp_mbox_amsg_entry *entry)
{
+ unsigned int offset = nn->tlv_caps.mbox_off + NFP_NET_CFG_MBOX_SIMPLE_VAL;
+ struct nfp_ipsec_cfg_mssg *msg = (struct nfp_ipsec_cfg_mssg *)entry->msg;
int i, msg_size, ret;
- msg->cmd = type;
- msg->sa_idx = saidx;
- msg->rsp = 0;
- msg_size = ARRAY_SIZE(msg->raw);
+ ret = nfp_net_mbox_lock(nn, sizeof(*msg));
+ if (ret)
+ return ret;
+ msg_size = ARRAY_SIZE(msg->raw);
for (i = 0; i < msg_size; i++)
- nn_writel(nn, NFP_NET_CFG_MBOX_VAL + 4 * i, msg->raw[i]);
+ nn_writel(nn, offset + 4 * i, msg->raw[i]);
- ret = nfp_net_mbox_reconfig(nn, NFP_NET_CFG_MBOX_CMD_IPSEC);
- if (ret < 0)
+ ret = nfp_net_mbox_reconfig(nn, entry->cmd);
+ if (ret < 0) {
+ nn_ctrl_bar_unlock(nn);
return ret;
+ }
/* For now we always read the whole message response back */
for (i = 0; i < msg_size; i++)
- msg->raw[i] = nn_readl(nn, NFP_NET_CFG_MBOX_VAL + 4 * i);
+ msg->raw[i] = nn_readl(nn, offset + 4 * i);
+
+ nn_ctrl_bar_unlock(nn);
switch (msg->rsp) {
case NFP_IPSEC_CFG_MSSG_OK:
}
/* Allocate saidx and commit the SA */
- err = nfp_ipsec_cfg_cmd_issue(nn, NFP_IPSEC_CFG_MSSG_ADD_SA, saidx, &msg);
+ msg.cmd = NFP_IPSEC_CFG_MSSG_ADD_SA;
+ msg.sa_idx = saidx;
+ err = nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_IPSEC, &msg,
+ sizeof(msg), nfp_net_ipsec_cfg);
if (err) {
xa_erase(&nn->xa_ipsec, saidx);
nn_err(nn, "Failed to issue IPsec command err ret=%d\n", err);
static void nfp_net_xfrm_del_state(struct xfrm_state *x)
{
+ struct nfp_ipsec_cfg_mssg msg = {
+ .cmd = NFP_IPSEC_CFG_MSSG_INV_SA,
+ .sa_idx = x->xso.offload_handle - 1,
+ };
struct net_device *netdev = x->xso.dev;
- struct nfp_ipsec_cfg_mssg msg;
struct nfp_net *nn;
int err;
nn = netdev_priv(netdev);
- err = nfp_ipsec_cfg_cmd_issue(nn, NFP_IPSEC_CFG_MSSG_INV_SA,
- x->xso.offload_handle - 1, &msg);
+ err = nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_IPSEC, &msg,
+ sizeof(msg), nfp_net_ipsec_cfg);
if (err)
nn_warn(nn, "Failed to invalidate SA in hardware\n");
sizeof(struct nfp_tun_neigh_v4);
unsigned long cookie = (unsigned long)neigh;
struct nfp_flower_priv *priv = app->priv;
+ struct nfp_tun_neigh_lag lag_info;
struct nfp_neigh_entry *nn_entry;
u32 port_id;
u8 mtype;
if (!port_id)
return;
+ if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT) {
+ memset(&lag_info, 0, sizeof(struct nfp_tun_neigh_lag));
+ nfp_flower_lag_get_info_from_netdev(app, netdev, &lag_info);
+ }
+
spin_lock_bh(&priv->predt_lock);
nn_entry = rhashtable_lookup_fast(&priv->neigh_table, &cookie,
neigh_table_params);
neigh_ha_snapshot(common->dst_addr, neigh, netdev);
if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT)
- nfp_flower_lag_get_info_from_netdev(app, netdev, lag);
+ memcpy(lag, &lag_info, sizeof(struct nfp_tun_neigh_lag));
common->port_id = cpu_to_be32(port_id);
if (rhashtable_insert_fast(&priv->neigh_table,
* @vnic_no_name: For non-port PF vNIC make ndo_get_phys_port_name return
* -EOPNOTSUPP to keep backwards compatibility (set by app)
* @port: Pointer to nfp_port structure if vNIC is a port
+ * @mbox_amsg: Asynchronously processed message via mailbox
+ * @mbox_amsg.lock: Protect message list
+ * @mbox_amsg.list: List of message to process
+ * @mbox_amsg.work: Work to process message asynchronously
* @app_priv: APP private data for this vNIC
*/
struct nfp_net {
struct nfp_port *port;
+ struct {
+ spinlock_t lock;
+ struct list_head list;
+ struct work_struct work;
+ } mbox_amsg;
+
void *app_priv;
};
+struct nfp_mbox_amsg_entry {
+ struct list_head list;
+ int (*cfg)(struct nfp_net *nn, struct nfp_mbox_amsg_entry *entry);
+ u32 cmd;
+ char msg[];
+};
+
+int nfp_net_sched_mbox_amsg_work(struct nfp_net *nn, u32 cmd, const void *data, size_t len,
+ int (*cb)(struct nfp_net *, struct nfp_mbox_amsg_entry *));
+
/* Functions to read/write from/to a BAR
* Performs any endian conversion necessary.
*/
return err;
}
-static int nfp_net_mc_cfg(struct net_device *netdev, const unsigned char *addr, const u32 cmd)
+int nfp_net_sched_mbox_amsg_work(struct nfp_net *nn, u32 cmd, const void *data, size_t len,
+ int (*cb)(struct nfp_net *, struct nfp_mbox_amsg_entry *))
{
- struct nfp_net *nn = netdev_priv(netdev);
+ struct nfp_mbox_amsg_entry *entry;
+
+ entry = kmalloc(sizeof(*entry) + len, GFP_ATOMIC);
+ if (!entry)
+ return -ENOMEM;
+
+ memcpy(entry->msg, data, len);
+ entry->cmd = cmd;
+ entry->cfg = cb;
+
+ spin_lock_bh(&nn->mbox_amsg.lock);
+ list_add_tail(&entry->list, &nn->mbox_amsg.list);
+ spin_unlock_bh(&nn->mbox_amsg.lock);
+
+ schedule_work(&nn->mbox_amsg.work);
+
+ return 0;
+}
+
+static void nfp_net_mbox_amsg_work(struct work_struct *work)
+{
+ struct nfp_net *nn = container_of(work, struct nfp_net, mbox_amsg.work);
+ struct nfp_mbox_amsg_entry *entry, *tmp;
+ struct list_head tmp_list;
+
+ INIT_LIST_HEAD(&tmp_list);
+
+ spin_lock_bh(&nn->mbox_amsg.lock);
+ list_splice_init(&nn->mbox_amsg.list, &tmp_list);
+ spin_unlock_bh(&nn->mbox_amsg.lock);
+
+ list_for_each_entry_safe(entry, tmp, &tmp_list, list) {
+ int err = entry->cfg(nn, entry);
+
+ if (err)
+ nn_err(nn, "Config cmd %d to HW failed %d.\n", entry->cmd, err);
+
+ list_del(&entry->list);
+ kfree(entry);
+ }
+}
+
+static int nfp_net_mc_cfg(struct nfp_net *nn, struct nfp_mbox_amsg_entry *entry)
+{
+ unsigned char *addr = entry->msg;
int ret;
ret = nfp_net_mbox_lock(nn, NFP_NET_CFG_MULTICAST_SZ);
nn_writew(nn, nn->tlv_caps.mbox_off + NFP_NET_CFG_MULTICAST_MAC_LO,
get_unaligned_be16(addr + 4));
- return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
+ return nfp_net_mbox_reconfig_and_unlock(nn, entry->cmd);
}
static int nfp_net_mc_sync(struct net_device *netdev, const unsigned char *addr)
return -EINVAL;
}
- return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD);
+ return nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD, addr,
+ NFP_NET_CFG_MULTICAST_SZ, nfp_net_mc_cfg);
}
static int nfp_net_mc_unsync(struct net_device *netdev, const unsigned char *addr)
{
- return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL);
+ struct nfp_net *nn = netdev_priv(netdev);
+
+ return nfp_net_sched_mbox_amsg_work(nn, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL, addr,
+ NFP_NET_CFG_MULTICAST_SZ, nfp_net_mc_cfg);
}
static void nfp_net_set_rx_mode(struct net_device *netdev)
if (!nn->dp.netdev)
return 0;
+
+ spin_lock_init(&nn->mbox_amsg.lock);
+ INIT_LIST_HEAD(&nn->mbox_amsg.list);
+ INIT_WORK(&nn->mbox_amsg.work, nfp_net_mbox_amsg_work);
+
return register_netdev(nn->dp.netdev);
err_clean_mbox:
unregister_netdev(nn->dp.netdev);
nfp_net_ipsec_clean(nn);
nfp_ccm_mbox_clean(nn);
+ flush_work(&nn->mbox_amsg.work);
nfp_net_reconfig_wait_posted(nn);
}
*/
#define NFP_NET_CFG_MBOX_BASE 0x1800
#define NFP_NET_CFG_MBOX_VAL_MAX_SZ 0x1F8
-#define NFP_NET_CFG_MBOX_VAL 0x1808
#define NFP_NET_CFG_MBOX_SIMPLE_CMD 0x0
#define NFP_NET_CFG_MBOX_SIMPLE_RET 0x4
#define NFP_NET_CFG_MBOX_SIMPLE_VAL 0x8
}
}
-static const u16 nfp_eth_media_table[] = {
- [NFP_MEDIA_1000BASE_CX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
- [NFP_MEDIA_1000BASE_KX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
- [NFP_MEDIA_10GBASE_KX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
- [NFP_MEDIA_10GBASE_KR] = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
- [NFP_MEDIA_10GBASE_CX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
- [NFP_MEDIA_10GBASE_CR] = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
- [NFP_MEDIA_10GBASE_SR] = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
- [NFP_MEDIA_10GBASE_ER] = ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
- [NFP_MEDIA_25GBASE_KR] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
- [NFP_MEDIA_25GBASE_KR_S] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
- [NFP_MEDIA_25GBASE_CR] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
- [NFP_MEDIA_25GBASE_CR_S] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
- [NFP_MEDIA_25GBASE_SR] = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
- [NFP_MEDIA_40GBASE_CR4] = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
- [NFP_MEDIA_40GBASE_KR4] = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
- [NFP_MEDIA_40GBASE_SR4] = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
- [NFP_MEDIA_40GBASE_LR4] = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
- [NFP_MEDIA_50GBASE_KR] = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
- [NFP_MEDIA_50GBASE_SR] = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
- [NFP_MEDIA_50GBASE_CR] = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
- [NFP_MEDIA_50GBASE_LR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
- [NFP_MEDIA_50GBASE_ER] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
- [NFP_MEDIA_50GBASE_FR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
- [NFP_MEDIA_100GBASE_KR4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
- [NFP_MEDIA_100GBASE_SR4] = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
- [NFP_MEDIA_100GBASE_CR4] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
- [NFP_MEDIA_100GBASE_KP4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
- [NFP_MEDIA_100GBASE_CR10] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+static const struct nfp_eth_media_link_mode {
+ u16 ethtool_link_mode;
+ u16 speed;
+} nfp_eth_media_table[NFP_MEDIA_LINK_MODES_NUMBER] = {
+ [NFP_MEDIA_1000BASE_CX] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+ .speed = NFP_SPEED_1G,
+ },
+ [NFP_MEDIA_1000BASE_KX] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+ .speed = NFP_SPEED_1G,
+ },
+ [NFP_MEDIA_10GBASE_KX4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+ .speed = NFP_SPEED_10G,
+ },
+ [NFP_MEDIA_10GBASE_KR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+ .speed = NFP_SPEED_10G,
+ },
+ [NFP_MEDIA_10GBASE_CX4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+ .speed = NFP_SPEED_10G,
+ },
+ [NFP_MEDIA_10GBASE_CR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
+ .speed = NFP_SPEED_10G,
+ },
+ [NFP_MEDIA_10GBASE_SR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+ .speed = NFP_SPEED_10G,
+ },
+ [NFP_MEDIA_10GBASE_ER] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
+ .speed = NFP_SPEED_10G,
+ },
+ [NFP_MEDIA_25GBASE_KR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+ .speed = NFP_SPEED_25G,
+ },
+ [NFP_MEDIA_25GBASE_KR_S] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+ .speed = NFP_SPEED_25G,
+ },
+ [NFP_MEDIA_25GBASE_CR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+ .speed = NFP_SPEED_25G,
+ },
+ [NFP_MEDIA_25GBASE_CR_S] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+ .speed = NFP_SPEED_25G,
+ },
+ [NFP_MEDIA_25GBASE_SR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+ .speed = NFP_SPEED_25G,
+ },
+ [NFP_MEDIA_40GBASE_CR4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+ .speed = NFP_SPEED_40G,
+ },
+ [NFP_MEDIA_40GBASE_KR4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+ .speed = NFP_SPEED_40G,
+ },
+ [NFP_MEDIA_40GBASE_SR4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+ .speed = NFP_SPEED_40G,
+ },
+ [NFP_MEDIA_40GBASE_LR4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
+ .speed = NFP_SPEED_40G,
+ },
+ [NFP_MEDIA_50GBASE_KR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
+ .speed = NFP_SPEED_50G,
+ },
+ [NFP_MEDIA_50GBASE_SR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
+ .speed = NFP_SPEED_50G,
+ },
+ [NFP_MEDIA_50GBASE_CR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
+ .speed = NFP_SPEED_50G,
+ },
+ [NFP_MEDIA_50GBASE_LR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+ .speed = NFP_SPEED_50G,
+ },
+ [NFP_MEDIA_50GBASE_ER] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+ .speed = NFP_SPEED_50G,
+ },
+ [NFP_MEDIA_50GBASE_FR] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+ .speed = NFP_SPEED_50G,
+ },
+ [NFP_MEDIA_100GBASE_KR4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+ .speed = NFP_SPEED_100G,
+ },
+ [NFP_MEDIA_100GBASE_SR4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+ .speed = NFP_SPEED_100G,
+ },
+ [NFP_MEDIA_100GBASE_CR4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+ .speed = NFP_SPEED_100G,
+ },
+ [NFP_MEDIA_100GBASE_KP4] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+ .speed = NFP_SPEED_100G,
+ },
+ [NFP_MEDIA_100GBASE_CR10] = {
+ .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+ .speed = NFP_SPEED_100G,
+ },
+};
+
+static const unsigned int nfp_eth_speed_map[NFP_SUP_SPEED_NUMBER] = {
+ [NFP_SPEED_1G] = SPEED_1000,
+ [NFP_SPEED_10G] = SPEED_10000,
+ [NFP_SPEED_25G] = SPEED_25000,
+ [NFP_SPEED_40G] = SPEED_40000,
+ [NFP_SPEED_50G] = SPEED_50000,
+ [NFP_SPEED_100G] = SPEED_100000,
};
static void nfp_add_media_link_mode(struct nfp_port *port,
};
struct nfp_cpp *cpp = port->app->cpp;
- if (nfp_eth_read_media(cpp, ðm))
+ if (nfp_eth_read_media(cpp, ðm)) {
+ bitmap_fill(port->speed_bitmap, NFP_SUP_SPEED_NUMBER);
return;
+ }
+
+ bitmap_zero(port->speed_bitmap, NFP_SUP_SPEED_NUMBER);
for (u32 i = 0; i < 2; i++) {
supported_modes[i] = le64_to_cpu(ethm.supported_modes[i]);
for (u32 i = 0; i < NFP_MEDIA_LINK_MODES_NUMBER; i++) {
if (i < 64) {
- if (supported_modes[0] & BIT_ULL(i))
- __set_bit(nfp_eth_media_table[i],
+ if (supported_modes[0] & BIT_ULL(i)) {
+ __set_bit(nfp_eth_media_table[i].ethtool_link_mode,
cmd->link_modes.supported);
+ __set_bit(nfp_eth_media_table[i].speed,
+ port->speed_bitmap);
+ }
if (advertised_modes[0] & BIT_ULL(i))
- __set_bit(nfp_eth_media_table[i],
+ __set_bit(nfp_eth_media_table[i].ethtool_link_mode,
cmd->link_modes.advertising);
} else {
- if (supported_modes[1] & BIT_ULL(i - 64))
- __set_bit(nfp_eth_media_table[i],
+ if (supported_modes[1] & BIT_ULL(i - 64)) {
+ __set_bit(nfp_eth_media_table[i].ethtool_link_mode,
cmd->link_modes.supported);
+ __set_bit(nfp_eth_media_table[i].speed,
+ port->speed_bitmap);
+ }
if (advertised_modes[1] & BIT_ULL(i - 64))
- __set_bit(nfp_eth_media_table[i],
+ __set_bit(nfp_eth_media_table[i].ethtool_link_mode,
cmd->link_modes.advertising);
}
}
if (cmd->base.speed != SPEED_UNKNOWN) {
u32 speed = cmd->base.speed / eth_port->lanes;
+ bool is_supported = false;
+
+ for (u32 i = 0; i < NFP_SUP_SPEED_NUMBER; i++) {
+ if (cmd->base.speed == nfp_eth_speed_map[i] &&
+ test_bit(i, port->speed_bitmap)) {
+ is_supported = true;
+ break;
+ }
+ }
+
+ if (!is_supported) {
+ netdev_err(netdev, "Speed %u is not supported.\n",
+ cmd->base.speed);
+ err = -EINVAL;
+ goto err_bad_set;
+ }
if (req_aneg) {
netdev_err(netdev, "Speed changing is not allowed when working on autoneg mode.\n");
NFP_PORT_CHANGED = 0,
};
+enum {
+ NFP_SPEED_1G,
+ NFP_SPEED_10G,
+ NFP_SPEED_25G,
+ NFP_SPEED_40G,
+ NFP_SPEED_50G,
+ NFP_SPEED_100G,
+ NFP_SUP_SPEED_NUMBER
+};
+
/**
* struct nfp_port - structure representing NFP port
* @netdev: backpointer to associated netdev
* @eth_forced: for %NFP_PORT_PHYS_PORT port is forced UP or DOWN, don't change
* @eth_port: for %NFP_PORT_PHYS_PORT translated ETH Table port entry
* @eth_stats: for %NFP_PORT_PHYS_PORT MAC stats if available
+ * @speed_bitmap: for %NFP_PORT_PHYS_PORT supported speed bitmap
* @pf_id: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT ID of the PCI PF (0-3)
* @vf_id: for %NFP_PORT_VF_PORT ID of the PCI VF within @pf_id
* @pf_split: for %NFP_PORT_PF_PORT %true if PCI PF has more than one vNIC
bool eth_forced;
struct nfp_eth_table_port *eth_port;
u8 __iomem *eth_stats;
+ DECLARE_BITMAP(speed_bitmap, NFP_SUP_SPEED_NUMBER);
};
/* NFP_PORT_PF_PORT, NFP_PORT_VF_PORT */
struct {
q->lif->index, q->name, q->hw_type, q->hw_index,
q->head_idx, ring_doorbell);
- if (ring_doorbell)
+ if (ring_doorbell) {
ionic_dbell_ring(lif->kern_dbpage, q->hw_type,
q->dbval | q->head_idx);
+
+ q->dbell_jiffies = jiffies;
+
+ if (q_to_qcq(q)->napi_qcq)
+ mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline,
+ jiffies + IONIC_NAPI_DEADLINE);
+ }
}
static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos)
#define IONIC_DEV_INFO_REG_COUNT 32
#define IONIC_DEV_CMD_REG_COUNT 32
+#define IONIC_NAPI_DEADLINE (HZ / 200) /* 5ms */
+#define IONIC_ADMIN_DOORBELL_DEADLINE (HZ / 2) /* 500ms */
+#define IONIC_TX_DOORBELL_DEADLINE (HZ / 100) /* 10ms */
+#define IONIC_RX_MIN_DOORBELL_DEADLINE (HZ / 100) /* 10ms */
+#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 5) /* 5s */
+
struct ionic_dev_bar {
void __iomem *vaddr;
phys_addr_t bus_addr;
struct ionic_lif *lif;
struct ionic_desc_info *info;
u64 dbval;
+ unsigned long dbell_deadline;
+ unsigned long dbell_jiffies;
u16 head_idx;
u16 tail_idx;
unsigned int index;
int ionic_heartbeat_check(struct ionic *ionic);
bool ionic_is_fw_running(struct ionic_dev *idev);
+bool ionic_adminq_poke_doorbell(struct ionic_queue *q);
+bool ionic_txq_poke_doorbell(struct ionic_queue *q);
+bool ionic_rxq_poke_doorbell(struct ionic_queue *q);
+
#endif /* _IONIC_DEV_H_ */
#include "ionic.h"
#include "ionic_bus.h"
+#include "ionic_dev.h"
#include "ionic_lif.h"
#include "ionic_txrx.h"
#include "ionic_ethtool.h"
}
}
+static void ionic_napi_deadline(struct timer_list *timer)
+{
+ struct ionic_qcq *qcq = container_of(timer, struct ionic_qcq, napi_deadline);
+
+ napi_schedule(&qcq->napi);
+}
+
static irqreturn_t ionic_isr(int irq, void *data)
{
struct napi_struct *napi = data;
.oper = IONIC_Q_ENABLE,
},
};
+ int ret;
idev = &lif->ionic->idev;
dev = lif->ionic->dev;
dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n",
ctx.cmd.q_control.index, ctx.cmd.q_control.type);
+ if (qcq->flags & IONIC_QCQ_F_INTR)
+ ionic_intr_clean(idev->intr_ctrl, qcq->intr.index);
+
+ ret = ionic_adminq_post_wait(lif, &ctx);
+ if (ret)
+ return ret;
+
+ if (qcq->napi.poll)
+ napi_enable(&qcq->napi);
+
if (qcq->flags & IONIC_QCQ_F_INTR) {
irq_set_affinity_hint(qcq->intr.vector,
&qcq->intr.affinity_mask);
- napi_enable(&qcq->napi);
- ionic_intr_clean(idev->intr_ctrl, qcq->intr.index);
ionic_intr_mask(idev->intr_ctrl, qcq->intr.index,
IONIC_INTR_MASK_CLEAR);
}
- return ionic_adminq_post_wait(lif, &ctx);
+ return 0;
}
static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int fw_err)
synchronize_irq(qcq->intr.vector);
irq_set_affinity_hint(qcq->intr.vector, NULL);
napi_disable(&qcq->napi);
+ del_timer_sync(&qcq->napi_deadline);
}
/* If there was a previous fw communcation error, don't bother with
n_qcq->intr.vector = src_qcq->intr.vector;
n_qcq->intr.index = src_qcq->intr.index;
+ n_qcq->napi_qcq = src_qcq->napi_qcq;
}
static int ionic_alloc_qcq_interrupt(struct ionic_lif *lif, struct ionic_qcq *qcq)
}
if (flags & IONIC_QCQ_F_NOTIFYQ) {
- int q_size, cq_size;
+ int q_size;
- /* q & cq need to be contiguous in case of notifyq */
+ /* q & cq need to be contiguous in NotifyQ, so alloc it all in q
+ * and don't alloc qc. We leave new->qc_size and new->qc_base
+ * as 0 to be sure we don't try to free it later.
+ */
q_size = ALIGN(num_descs * desc_size, PAGE_SIZE);
- cq_size = ALIGN(num_descs * cq_desc_size, PAGE_SIZE);
-
- new->q_size = PAGE_SIZE + q_size + cq_size;
+ new->q_size = PAGE_SIZE + q_size +
+ ALIGN(num_descs * cq_desc_size, PAGE_SIZE);
new->q_base = dma_alloc_coherent(dev, new->q_size,
&new->q_base_pa, GFP_KERNEL);
if (!new->q_base) {
dev_dbg(dev, "txq->hw_type %d\n", q->hw_type);
dev_dbg(dev, "txq->hw_index %d\n", q->hw_index);
- if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state))
+ q->dbell_deadline = IONIC_TX_DOORBELL_DEADLINE;
+ q->dbell_jiffies = jiffies;
+
+ if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) {
netif_napi_add(lif->netdev, &qcq->napi, ionic_tx_napi);
+ qcq->napi_qcq = qcq;
+ timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0);
+ }
qcq->flags |= IONIC_QCQ_F_INITED;
dev_dbg(dev, "rxq->hw_type %d\n", q->hw_type);
dev_dbg(dev, "rxq->hw_index %d\n", q->hw_index);
+ q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE;
+ q->dbell_jiffies = jiffies;
+
if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state))
netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi);
else
netif_napi_add(lif->netdev, &qcq->napi, ionic_txrx_napi);
+ qcq->napi_qcq = qcq;
+ timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0);
+
qcq->flags |= IONIC_QCQ_F_INITED;
return 0;
struct ionic_dev *idev = &lif->ionic->idev;
unsigned long irqflags;
unsigned int flags = 0;
+ bool resched = false;
int rx_work = 0;
int tx_work = 0;
int n_work = 0;
ionic_intr_credits(idev->intr_ctrl, intr->index, credits, flags);
}
+ if (!a_work && ionic_adminq_poke_doorbell(&lif->adminqcq->q))
+ resched = true;
+ if (lif->hwstamp_rxq && !rx_work && ionic_rxq_poke_doorbell(&lif->hwstamp_rxq->q))
+ resched = true;
+ if (lif->hwstamp_txq && !tx_work && ionic_txq_poke_doorbell(&lif->hwstamp_txq->q))
+ resched = true;
+ if (resched)
+ mod_timer(&lif->adminqcq->napi_deadline,
+ jiffies + IONIC_NAPI_DEADLINE);
+
return work_done;
}
dev_dbg(dev, "adminq->hw_type %d\n", q->hw_type);
dev_dbg(dev, "adminq->hw_index %d\n", q->hw_index);
+ q->dbell_deadline = IONIC_ADMIN_DOORBELL_DEADLINE;
+ q->dbell_jiffies = jiffies;
+
netif_napi_add(lif->netdev, &qcq->napi, ionic_adminq_napi);
+ qcq->napi_qcq = qcq;
+ timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0);
+
napi_enable(&qcq->napi);
if (qcq->flags & IONIC_QCQ_F_INTR)
struct ionic_queue q;
struct ionic_cq cq;
struct ionic_intr_info intr;
+ struct timer_list napi_deadline;
struct napi_struct napi;
unsigned int flags;
+ struct ionic_qcq *napi_qcq;
struct dentry *dentry;
};
complete_all(&ctx->work);
}
+bool ionic_adminq_poke_doorbell(struct ionic_queue *q)
+{
+ struct ionic_lif *lif = q->lif;
+ unsigned long now, then, dif;
+ unsigned long irqflags;
+
+ spin_lock_irqsave(&lif->adminq_lock, irqflags);
+
+ if (q->tail_idx == q->head_idx) {
+ spin_unlock_irqrestore(&lif->adminq_lock, irqflags);
+ return false;
+ }
+
+ now = READ_ONCE(jiffies);
+ then = q->dbell_jiffies;
+ dif = now - then;
+
+ if (dif > q->dbell_deadline) {
+ ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type,
+ q->dbval | q->head_idx);
+
+ q->dbell_jiffies = now;
+ }
+
+ spin_unlock_irqrestore(&lif->adminq_lock, irqflags);
+
+ return true;
+}
+
int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx)
{
struct ionic_desc_info *desc_info;
ionic_q_post(q, ring_dbell, cb_func, cb_arg);
}
+bool ionic_txq_poke_doorbell(struct ionic_queue *q)
+{
+ unsigned long now, then, dif;
+ struct netdev_queue *netdev_txq;
+ struct net_device *netdev;
+
+ netdev = q->lif->netdev;
+ netdev_txq = netdev_get_tx_queue(netdev, q->index);
+
+ HARD_TX_LOCK(netdev, netdev_txq, smp_processor_id());
+
+ if (q->tail_idx == q->head_idx) {
+ HARD_TX_UNLOCK(netdev, netdev_txq);
+ return false;
+ }
+
+ now = READ_ONCE(jiffies);
+ then = q->dbell_jiffies;
+ dif = now - then;
+
+ if (dif > q->dbell_deadline) {
+ ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type,
+ q->dbval | q->head_idx);
+
+ q->dbell_jiffies = now;
+ }
+
+ HARD_TX_UNLOCK(netdev, netdev_txq);
+
+ return true;
+}
+
+bool ionic_rxq_poke_doorbell(struct ionic_queue *q)
+{
+ unsigned long now, then, dif;
+
+ /* no lock, called from rx napi or txrx napi, nothing else can fill */
+
+ if (q->tail_idx == q->head_idx)
+ return false;
+
+ now = READ_ONCE(jiffies);
+ then = q->dbell_jiffies;
+ dif = now - then;
+
+ if (dif > q->dbell_deadline) {
+ ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type,
+ q->dbval | q->head_idx);
+
+ q->dbell_jiffies = now;
+
+ dif = 2 * q->dbell_deadline;
+ if (dif > IONIC_RX_MAX_DOORBELL_DEADLINE)
+ dif = IONIC_RX_MAX_DOORBELL_DEADLINE;
+
+ q->dbell_deadline = dif;
+ }
+
+ return true;
+}
+
static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q)
{
return netdev_get_tx_queue(q->lif->netdev, q->index);
ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type,
q->dbval | q->head_idx);
+
+ q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE;
+ q->dbell_jiffies = jiffies;
+
+ mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline,
+ jiffies + IONIC_NAPI_DEADLINE);
}
void ionic_rx_empty(struct ionic_queue *q)
work_done, flags);
}
+ if (!work_done && ionic_txq_poke_doorbell(&qcq->q))
+ mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE);
+
return work_done;
}
work_done, flags);
}
+ if (!work_done && ionic_rxq_poke_doorbell(&qcq->q))
+ mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE);
+
return work_done;
}
int ionic_txrx_napi(struct napi_struct *napi, int budget)
{
- struct ionic_qcq *qcq = napi_to_qcq(napi);
+ struct ionic_qcq *rxqcq = napi_to_qcq(napi);
struct ionic_cq *rxcq = napi_to_cq(napi);
unsigned int qi = rxcq->bound_q->index;
+ struct ionic_qcq *txqcq;
struct ionic_dev *idev;
struct ionic_lif *lif;
struct ionic_cq *txcq;
+ bool resched = false;
u32 rx_work_done = 0;
u32 tx_work_done = 0;
u32 flags = 0;
lif = rxcq->bound_q->lif;
idev = &lif->ionic->idev;
+ txqcq = lif->txqcqs[qi];
txcq = &lif->txqcqs[qi]->cq;
tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT,
ionic_rx_fill(rxcq->bound_q);
if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) {
- ionic_dim_update(qcq, 0);
+ ionic_dim_update(rxqcq, 0);
flags |= IONIC_INTR_CRED_UNMASK;
rxcq->bound_intr->rearm_count++;
}
tx_work_done + rx_work_done, flags);
}
+ if (!rx_work_done && ionic_rxq_poke_doorbell(&rxqcq->q))
+ resched = true;
+ if (!tx_work_done && ionic_txq_poke_doorbell(&txqcq->q))
+ resched = true;
+ if (resched)
+ mod_timer(&rxqcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE);
+
return rx_work_done;
}
struct qed_ptt *p_ptt,
u32 image_type,
u32 *nvram_offset_bytes,
- u32 *nvram_size_bytes)
+ u32 *nvram_size_bytes,
+ bool b_can_sleep)
{
u32 ret_mcp_resp, ret_mcp_param, ret_txn_size;
struct mcp_file_att file_att;
&ret_mcp_resp,
&ret_mcp_param,
&ret_txn_size,
- (u32 *)&file_att, false);
+ (u32 *)&file_att,
+ b_can_sleep);
/* Check response */
if (nvm_result || (ret_mcp_resp & FW_MSG_CODE_MASK) !=
static enum dbg_status qed_nvram_read(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
u32 nvram_offset_bytes,
- u32 nvram_size_bytes, u32 *ret_buf)
+ u32 nvram_size_bytes,
+ u32 *ret_buf,
+ bool b_can_sleep)
{
u32 ret_mcp_resp, ret_mcp_param, ret_read_size, bytes_to_copy;
s32 bytes_left = nvram_size_bytes;
&ret_mcp_resp,
&ret_mcp_param, &ret_read_size,
(u32 *)((u8 *)ret_buf + read_offset),
- false))
+ b_can_sleep))
return DBG_STATUS_NVRAM_READ_FAILED;
/* Check response */
p_ptt,
NVM_TYPE_HW_DUMP_OUT,
&hw_dump_offset_bytes,
- &hw_dump_size_bytes);
+ &hw_dump_size_bytes,
+ false);
if (status != DBG_STATUS_OK)
return 0;
status = qed_nvram_read(p_hwfn,
p_ptt,
hw_dump_offset_bytes,
- hw_dump_size_bytes, dump_buf + offset);
+ hw_dump_size_bytes,
+ dump_buf + offset,
+ false);
if (status != DBG_STATUS_OK) {
DP_NOTICE(p_hwfn,
"Failed to read MCP HW Dump image from NVRAM\n");
return qed_find_nvram_image(p_hwfn,
p_ptt,
nvram_image_type,
- trace_meta_offset, trace_meta_size);
+ trace_meta_offset,
+ trace_meta_size,
+ true);
}
/* Reads the MCP Trace meta data from NVRAM into the specified buffer */
/* Read meta data from NVRAM */
status = qed_nvram_read(p_hwfn,
p_ptt,
- nvram_offset_in_bytes, size_in_bytes, buf);
+ nvram_offset_in_bytes,
+ size_in_bytes,
+ buf,
+ true);
if (status != DBG_STATUS_OK)
return status;
rx_work_done = (likely(fp->type & QEDE_FASTPATH_RX) &&
qede_has_rx_work(fp->rxq)) ?
qede_rx_int(fp, budget) : 0;
+
+ if (fp->xdp_xmit & QEDE_XDP_REDIRECT)
+ xdp_do_flush();
+
/* Handle case where we are called by netpoll with a budget of 0 */
if (rx_work_done < budget || !budget) {
if (!qede_poll_is_more_work(fp)) {
qede_update_tx_producer(fp->xdp_tx);
}
- if (fp->xdp_xmit & QEDE_XDP_REDIRECT)
- xdp_do_flush_map();
-
return rx_work_done;
}
goto disable_mbx_intr;
qlcnic_83xx_clear_function_resources(adapter);
- qlcnic_dcb_enable(adapter->dcb);
+
+ err = qlcnic_dcb_enable(adapter->dcb);
+ if (err) {
+ qlcnic_dcb_free(adapter->dcb);
+ goto disable_mbx_intr;
+ }
+
qlcnic_83xx_initialize_nic(adapter, 1);
qlcnic_dcb_get_info(adapter->dcb);
unsigned long state;
};
-static inline void qlcnic_clear_dcb_ops(struct qlcnic_dcb *dcb)
-{
- kfree(dcb);
-}
-
static inline int qlcnic_dcb_get_hw_capability(struct qlcnic_dcb *dcb)
{
if (dcb && dcb->ops->get_hw_capability)
dcb->ops->init_dcbnl_ops(dcb);
}
-static inline void qlcnic_dcb_enable(struct qlcnic_dcb *dcb)
+static inline int qlcnic_dcb_enable(struct qlcnic_dcb *dcb)
{
- if (dcb && qlcnic_dcb_attach(dcb))
- qlcnic_clear_dcb_ops(dcb);
+ return dcb ? qlcnic_dcb_attach(dcb) : 0;
}
#endif
"Device does not support MSI interrupts\n");
if (qlcnic_82xx_check(adapter)) {
- qlcnic_dcb_enable(adapter->dcb);
+ err = qlcnic_dcb_enable(adapter->dcb);
+ if (err) {
+ qlcnic_dcb_free(adapter->dcb);
+ dev_err(&pdev->dev, "Failed to enable DCB\n");
+ goto err_out_free_hw;
+ }
+
qlcnic_dcb_get_info(adapter->dcb);
err = qlcnic_setup_intr(adapter);
/* 8168F family. */
{ 0x7c8, 0x488, RTL_GIGA_MAC_VER_38 },
- /* It seems this chip version never made it to
- * the wild. Let's disable detection.
- * { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 },
- */
+ { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 },
{ 0x7cf, 0x480, RTL_GIGA_MAC_VER_35 },
/* 8168E family. */
return 0;
}
-static void rtl_wol_enable_rx(struct rtl8169_private *tp)
-{
- if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
- RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
- AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
-}
-
-static void rtl_prepare_power_down(struct rtl8169_private *tp)
-{
- if (tp->dash_type != RTL_DASH_NONE)
- return;
-
- if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
- tp->mac_version == RTL_GIGA_MAC_VER_33)
- rtl_ephy_write(tp, 0x19, 0xff64);
-
- if (device_may_wakeup(tp_to_dev(tp))) {
- phy_speed_down(tp->phydev, false);
- rtl_wol_enable_rx(tp);
- }
-}
-
static void rtl_init_rxcfg(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
rtl_wait_txrx_fifo_empty(tp);
}
+static void rtl_wol_enable_rx(struct rtl8169_private *tp)
+{
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
+ RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
+ AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
+
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_40)
+ rtl_disable_rxdvgate(tp);
+}
+
+static void rtl_prepare_power_down(struct rtl8169_private *tp)
+{
+ if (tp->dash_type != RTL_DASH_NONE)
+ return;
+
+ if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_33)
+ rtl_ephy_write(tp, 0x19, 0xff64);
+
+ if (device_may_wakeup(tp_to_dev(tp))) {
+ phy_speed_down(tp->phydev, false);
+ rtl_wol_enable_rx(tp);
+ }
+}
+
static void rtl_set_tx_config_registers(struct rtl8169_private *tp)
{
u32 val = TX_DMA_BURST << TxDMAShift |
netdev_reset_queue(tp->dev);
}
-static void rtl8169_cleanup(struct rtl8169_private *tp, bool going_down)
+static void rtl8169_cleanup(struct rtl8169_private *tp)
{
napi_disable(&tp->napi);
rtl_rx_close(tp);
- if (going_down && tp->dev->wol_enabled)
- goto no_reset;
-
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_28:
case RTL_GIGA_MAC_VER_31:
}
rtl_hw_reset(tp);
-no_reset:
+
rtl8169_tx_clear(tp);
rtl8169_init_ring_indexes(tp);
}
netif_stop_queue(tp->dev);
- rtl8169_cleanup(tp, false);
+ rtl8169_cleanup(tp);
for (i = 0; i < NUM_RX_DESC; i++)
rtl8169_mark_to_asic(tp->RxDescArray + i);
pci_clear_master(tp->pci_dev);
rtl_pci_commit(tp);
- rtl8169_cleanup(tp, true);
+ rtl8169_cleanup(tp);
rtl_disable_exit_l1(tp);
rtl_prepare_power_down(tp);
}
ravb_write(ndev, ~(EIS_QFS | EIS_RESERVED), EIS);
if (eis & EIS_QFS) {
ris2 = ravb_read(ndev, RIS2);
- ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF | RIS2_RESERVED),
+ ravb_write(ndev, ~(RIS2_QFF0 | RIS2_QFF1 | RIS2_RFFF | RIS2_RESERVED),
RIS2);
/* Receive Descriptor Empty int */
if (ris2 & RIS2_QFF0)
priv->stats[RAVB_BE].rx_over_errors++;
- /* Receive Descriptor Empty int */
+ /* Receive Descriptor Empty int */
if (ris2 & RIS2_QFF1)
priv->stats[RAVB_NC].rx_over_errors++;
else
ret = ravb_close(ndev);
+ if (priv->info->ccc_gac)
+ ravb_ptp_stop(ndev);
+
return ret;
}
/* Restore descriptor base address table */
ravb_write(ndev, priv->desc_bat_dma, DBAT);
+ if (priv->info->ccc_gac)
+ ravb_ptp_init(ndev, priv->pdev);
+
if (netif_running(ndev)) {
if (priv->wol_enabled) {
ret = ravb_wol_restore(ndev);
port = NULL;
goto out;
}
- if (index == rdev->etha->index)
+ if (index == rdev->etha->index) {
+ if (!of_device_is_available(port))
+ port = NULL;
break;
+ }
}
out:
port = rswitch_get_port_node(rdev);
if (!port)
- return -ENODEV;
+ return 0; /* ignored */
err = of_get_phy_mode(port, &rdev->etha->phy_interface);
of_node_put(port);
{
int i, err;
- for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
+ rswitch_for_each_enabled_port(priv, i) {
err = rswitch_ether_port_init_one(priv->rdev[i]);
if (err)
goto err_init_one;
}
- for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
+ rswitch_for_each_enabled_port(priv, i) {
err = rswitch_serdes_init(priv->rdev[i]);
if (err)
goto err_serdes;
return 0;
err_serdes:
- for (i--; i >= 0; i--)
+ rswitch_for_each_enabled_port_continue_reverse(priv, i)
rswitch_serdes_deinit(priv->rdev[i]);
i = RSWITCH_NUM_PORTS;
err_init_one:
- for (i--; i >= 0; i--)
+ rswitch_for_each_enabled_port_continue_reverse(priv, i)
rswitch_ether_port_deinit_one(priv->rdev[i]);
return err;
{
struct platform_device *pdev = priv->pdev;
struct rswitch_device *rdev;
+ struct device_node *port;
struct net_device *ndev;
int err;
netif_napi_add(ndev, &rdev->napi, rswitch_poll);
- err = of_get_ethdev_address(pdev->dev.of_node, ndev);
+ port = rswitch_get_port_node(rdev);
+ rdev->disabled = !port;
+ err = of_get_ethdev_address(port, ndev);
+ of_node_put(port);
if (err) {
if (is_valid_ether_addr(rdev->etha->mac_addr))
eth_hw_addr_set(ndev, rdev->etha->mac_addr);
if (err)
goto err_ether_port_init_all;
- for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
+ rswitch_for_each_enabled_port(priv, i) {
err = register_netdev(priv->rdev[i]->ndev);
if (err) {
- for (i--; i >= 0; i--)
+ rswitch_for_each_enabled_port_continue_reverse(priv, i)
unregister_netdev(priv->rdev[i]->ndev);
goto err_register_netdev;
}
}
- for (i = 0; i < RSWITCH_NUM_PORTS; i++)
+ rswitch_for_each_enabled_port(priv, i)
netdev_info(priv->rdev[i]->ndev, "MAC address %pM\n",
priv->rdev[i]->ndev->dev_addr);
pm_runtime_get_sync(&pdev->dev);
ret = rswitch_init(priv);
+ if (ret < 0) {
+ pm_runtime_put(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+ return ret;
+ }
device_set_wakeup_capable(&pdev->dev, 1);
#define RSWITCH_MAX_NUM_QUEUES 128
#define RSWITCH_NUM_PORTS 3
+#define rswitch_for_each_enabled_port(priv, i) \
+ for (i = 0; i < RSWITCH_NUM_PORTS; i++) \
+ if (priv->rdev[i]->disabled) \
+ continue; \
+ else
+
+#define rswitch_for_each_enabled_port_continue_reverse(priv, i) \
+ for (i--; i >= 0; i--) \
+ if (priv->rdev[i]->disabled) \
+ continue; \
+ else
#define TX_RING_SIZE 1024
#define RX_RING_SIZE 1024
struct rswitch_gwca_queue *tx_queue;
struct rswitch_gwca_queue *rx_queue;
u8 ts_tag;
+ bool disabled;
int port;
struct rswitch_etha *etha;
/* Determine netdevice features */
net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_RXALL);
- if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
+ if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) {
net_dev->features |= NETIF_F_TSO6;
+ if (efx_has_cap(efx, TX_TSO_V2_ENCAP))
+ net_dev->hw_enc_features |= NETIF_F_TSO6;
+ }
/* Check whether device supports TSO */
if (!efx->type->tso_versions || !efx->type->tso_versions(efx))
net_dev->features &= ~NETIF_F_ALL_TSO;
struct mediatek_dwmac_variant {
int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat);
int (*dwmac_set_delay)(struct mediatek_dwmac_plat_data *plat);
- void (*dwmac_fix_mac_speed)(void *priv, unsigned int speed);
/* clock ids to be requested */
const char * const *clk_list;
return 0;
}
-static void mt8195_fix_mac_speed(void *priv, unsigned int speed)
-{
- struct mediatek_dwmac_plat_data *priv_plat = priv;
-
- if ((phy_interface_mode_is_rgmii(priv_plat->phy_mode))) {
- /* prefer 2ns fixed delay which is controlled by TXC_PHASE_CTRL,
- * when link speed is 1Gbps with RGMII interface,
- * Fall back to delay macro circuit for 10/100Mbps link speed.
- */
- if (speed == SPEED_1000)
- regmap_update_bits(priv_plat->peri_regmap,
- MT8195_PERI_ETH_CTRL0,
- MT8195_RGMII_TXC_PHASE_CTRL |
- MT8195_DLY_GTXC_ENABLE |
- MT8195_DLY_GTXC_INV |
- MT8195_DLY_GTXC_STAGES,
- MT8195_RGMII_TXC_PHASE_CTRL);
- else
- mt8195_set_delay(priv_plat);
- }
-}
-
static const struct mediatek_dwmac_variant mt8195_gmac_variant = {
.dwmac_set_phy_interface = mt8195_set_interface,
.dwmac_set_delay = mt8195_set_delay,
- .dwmac_fix_mac_speed = mt8195_fix_mac_speed,
.clk_list = mt8195_dwmac_clk_l,
.num_clks = ARRAY_SIZE(mt8195_dwmac_clk_l),
.dma_bit_mask = 35,
plat->bsp_priv = priv_plat;
plat->init = mediatek_dwmac_init;
plat->clks_config = mediatek_dwmac_clks_config;
- if (priv_plat->variant->dwmac_fix_mac_speed)
- plat->fix_mac_speed = priv_plat->variant->dwmac_fix_mac_speed;
plat->safety_feat_cfg = devm_kzalloc(&pdev->dev,
sizeof(*plat->safety_feat_cfg),
plat_dat->has_gmac4 = 1;
plat_dat->pmt = 1;
plat_dat->tso_en = of_property_read_bool(np, "snps,tso");
+ if (of_device_is_compatible(np, "qcom,qcs404-ethqos"))
+ plat_dat->rx_clk_runs_in_lpi = 1;
ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
if (ret)
int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
struct stmmac_safety_feature_cfg *safety_feat_cfg)
{
+ struct stmmac_safety_feature_cfg all_safety_feats = {
+ .tsoee = 1,
+ .mrxpee = 1,
+ .mestee = 1,
+ .mrxee = 1,
+ .mtxee = 1,
+ .epsi = 1,
+ .edpp = 1,
+ .prtyen = 1,
+ .tmouten = 1,
+ };
u32 value;
if (!asp)
return -EINVAL;
+ if (!safety_feat_cfg)
+ safety_feat_cfg = &all_safety_feats;
+
/* 1. Enable Safety Features */
value = readl(ioaddr + MTL_ECC_CONTROL);
value |= MEEAO; /* MTL ECC Error Addr Status Override */
return 0;
}
- val |= PPSCMDx(index, 0x2);
val |= TRGTMODSELx(index, 0x2);
val |= PPSEN0;
+ writel(val, ioaddr + MAC_PPS_CONTROL);
writel(cfg->start.tv_sec, ioaddr + MAC_PPSx_TARGET_TIME_SEC(index));
writel(period - 1, ioaddr + MAC_PPSx_WIDTH(index));
/* Finally, activate it */
+ val |= PPSCMDx(index, 0x2);
writel(val, ioaddr + MAC_PPS_CONTROL);
return 0;
}
p = (char *)priv + offsetof(struct stmmac_priv,
xstats.txq_stats[q].tx_pkt_n);
for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
- *data++ = (*(u64 *)p);
- p += sizeof(u64 *);
+ *data++ = (*(unsigned long *)p);
+ p += sizeof(unsigned long);
}
}
for (q = 0; q < rx_cnt; q++) {
p = (char *)priv + offsetof(struct stmmac_priv,
xstats.rxq_stats[q].rx_pkt_n);
for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
- *data++ = (*(u64 *)p);
- p += sizeof(u64 *);
+ *data++ = (*(unsigned long *)p);
+ p += sizeof(unsigned long);
}
}
}
stmmac_mac_set(priv, priv->ioaddr, true);
if (phy && priv->dma_cap.eee) {
- priv->eee_active = phy_init_eee(phy, 1) >= 0;
+ priv->eee_active =
+ phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0;
priv->eee_enabled = stmmac_eee_init(priv);
priv->tx_lpi_enabled = priv->eee_enabled;
stmmac_set_eee_pls(priv, priv->hw, true);
int addr = priv->plat->phy_addr;
struct phy_device *phydev;
+ if (addr < 0) {
+ netdev_err(priv->dev, "no phy found\n");
+ return -ENODEV;
+ }
+
phydev = mdiobus_get_phy(priv->mii, addr);
if (!phydev) {
netdev_err(priv->dev, "no phy at addr %d\n", addr);
dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst");
plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode");
- if (plat->force_thresh_dma_mode) {
+ if (plat->force_thresh_dma_mode && plat->force_sf_dma_mode) {
plat->force_sf_dma_mode = 0;
dev_warn(&pdev->dev,
"force_sf_dma_mode is ignored if force_thresh_dma_mode is set.\n");
}
writel(acr_value, ptpaddr + PTP_ACR);
mutex_unlock(&priv->aux_ts_lock);
- ret = 0;
+ /* wait for auxts fifo clear to finish */
+ ret = readl_poll_timeout(ptpaddr + PTP_ACR, acr_value,
+ !(acr_value & PTP_ACR_ATSFC),
+ 10, 10000);
break;
default:
k3_udma_glue_disable_tx_chn(common->tx_chns[i].tx_chn);
}
+ reinit_completion(&common->tdown_complete);
k3_udma_glue_tdown_rx_chn(common->rx_chns.rx_chn, true);
+
+ if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) {
+ i = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000));
+ if (!i)
+ dev_err(common->dev, "rx teardown timeout\n");
+ }
+
napi_disable(&common->napi_rx);
for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++)
if (cppi5_desc_is_tdcm(desc_dma)) {
dev_dbg(dev, "%s RX tdown flow: %u\n", __func__, flow_idx);
+ if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ)
+ complete(&common->tdown_complete);
return 0;
}
};
static const struct am65_cpsw_pdata am64x_cpswxg_pdata = {
- .quirks = 0,
+ .quirks = AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ,
.ale_dev_id = "am64-cpswxg",
.fdqring_mode = K3_RINGACC_RING_MODE_RING,
};
};
#define AM65_CPSW_QUIRK_I2027_NO_TX_CSUM BIT(0)
+#define AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ BIT(1)
struct am65_cpsw_pdata {
u32 quirks;
void netvsc_dma_unmap(struct hv_device *hv_dev,
struct hv_netvsc_packet *packet)
{
- u32 page_count = packet->cp_partial ?
- packet->page_buf_cnt - packet->rmsg_pgcnt :
- packet->page_buf_cnt;
int i;
if (!hv_is_isolation_supported())
if (!packet->dma_range)
return;
- for (i = 0; i < page_count; i++)
+ for (i = 0; i < packet->page_buf_cnt; i++)
dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma,
packet->dma_range[i].mapping_size,
DMA_TO_DEVICE);
struct hv_netvsc_packet *packet,
struct hv_page_buffer *pb)
{
- u32 page_count = packet->cp_partial ?
- packet->page_buf_cnt - packet->rmsg_pgcnt :
- packet->page_buf_cnt;
+ u32 page_count = packet->page_buf_cnt;
dma_addr_t dma;
int i;
packet->dma_range = kcalloc(page_count,
sizeof(*packet->dma_range),
- GFP_KERNEL);
+ GFP_ATOMIC);
if (!packet->dma_range)
return -ENOMEM;
static const struct ipa_mem_data ipa_mem_data = {
.local_count = ARRAY_SIZE(ipa_mem_local_data),
.local = ipa_mem_local_data,
- .imem_addr = 0x146a9000,
+ .imem_addr = 0x146a8000,
.imem_size = 0x00002000,
.smem_id = 497,
.smem_size = 0x00009000,
return IRQ_HANDLED;
}
+void ipa_interrupt_irq_disable(struct ipa *ipa)
+{
+ disable_irq(ipa->interrupt->irq);
+}
+
+void ipa_interrupt_irq_enable(struct ipa *ipa)
+{
+ enable_irq(ipa->interrupt->irq);
+}
+
/* Common function used to enable/disable TX_SUSPEND for an endpoint */
static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt,
u32 endpoint_id, bool enable)
{
struct ipa *ipa = interrupt->ipa;
+ u32 mask = BIT(endpoint_id % 32);
u32 unit = endpoint_id / 32;
const struct ipa_reg *reg;
u32 offset;
- u32 mask;
u32 val;
WARN_ON(!test_bit(endpoint_id, ipa->available));
offset = ipa_reg_n_offset(reg, unit);
val = ioread32(ipa->reg_virt + offset);
- mask = BIT(endpoint_id);
if (enable)
val |= mask;
else
*/
void ipa_interrupt_simulate_suspend(struct ipa_interrupt *interrupt);
+/**
+ * ipa_interrupt_irq_enable() - Enable IPA interrupts
+ * @ipa: IPA pointer
+ *
+ * This enables the IPA interrupt line
+ */
+void ipa_interrupt_irq_enable(struct ipa *ipa);
+
+/**
+ * ipa_interrupt_irq_disable() - Disable IPA interrupts
+ * @ipa: IPA pointer
+ *
+ * This disables the IPA interrupt line
+ */
+void ipa_interrupt_irq_disable(struct ipa *ipa);
+
/**
* ipa_interrupt_config() - Configure the IPA interrupt framework
* @ipa: IPA pointer
__set_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags);
+ /* Increment the disable depth to ensure that the IRQ won't
+ * be re-enabled until the matching _enable call in
+ * ipa_resume(). We do this to ensure that the interrupt
+ * handler won't run whilst PM runtime is disabled.
+ *
+ * Note that disabling the IRQ is NOT the same as disabling
+ * irq wake. If wakeup is enabled for the IPA then the IRQ
+ * will still cause the system to wake up, see irq_set_irq_wake().
+ */
+ ipa_interrupt_irq_disable(ipa);
+
return pm_runtime_force_suspend(dev);
}
__clear_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags);
+ /* Now that PM runtime is enabled again it's safe
+ * to turn the IRQ back on and process any data
+ * that was received during suspend.
+ */
+ ipa_interrupt_irq_enable(ipa);
+
return ret;
}
*/
#include <linux/bitfield.h>
+#include <linux/delay.h>
#include <linux/clk.h>
#include <linux/clk-provider.h>
#include <linux/device.h>
static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv)
{
+ u32 value;
int ret;
/* Enable the phy clock */
/* Initialize ephy control */
writel(EPHY_G12A_ID, priv->regs + ETH_PHY_CNTL0);
- writel(FIELD_PREP(PHY_CNTL1_ST_MODE, 3) |
- FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) |
- FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) |
- PHY_CNTL1_CLK_EN |
- PHY_CNTL1_CLKFREQ |
- PHY_CNTL1_PHY_ENB,
- priv->regs + ETH_PHY_CNTL1);
+
+ /* Make sure we get a 0 -> 1 transition on the enable bit */
+ value = FIELD_PREP(PHY_CNTL1_ST_MODE, 3) |
+ FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) |
+ FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) |
+ PHY_CNTL1_CLK_EN |
+ PHY_CNTL1_CLKFREQ;
+ writel(value, priv->regs + ETH_PHY_CNTL1);
writel(PHY_CNTL2_USE_INTERNAL |
PHY_CNTL2_SMI_SRC_MAC |
PHY_CNTL2_RX_CLK_EPHY,
priv->regs + ETH_PHY_CNTL2);
+ value |= PHY_CNTL1_PHY_ENB;
+ writel(value, priv->regs + ETH_PHY_CNTL1);
+
+ /* The phy needs a bit of time to power up */
+ mdelay(10);
+
return 0;
}
DP83822_ENERGY_DET_INT_EN |
DP83822_LINK_QUAL_INT_EN);
- if (!dp83822->fx_enabled)
+ /* Private data pointer is NULL on DP83825/26 */
+ if (!dp83822 || !dp83822->fx_enabled)
misr_status |= DP83822_ANEG_COMPLETE_INT_EN |
DP83822_DUP_MODE_CHANGE_INT_EN |
DP83822_SPEED_CHANGED_INT_EN;
DP83822_PAGE_RX_INT_EN |
DP83822_EEE_ERROR_CHANGE_INT_EN);
- if (!dp83822->fx_enabled)
+ /* Private data pointer is NULL on DP83825/26 */
+ if (!dp83822 || !dp83822->fx_enabled)
misr_status |= DP83822_ANEG_ERR_INT_EN |
DP83822_WOL_PKT_INT_EN;
struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr)
{
- struct mdio_device *mdiodev = bus->mdio_map[addr];
+ struct mdio_device *mdiodev;
+
+ if (addr < 0 || addr >= ARRAY_SIZE(bus->mdio_map))
+ return NULL;
+
+ mdiodev = bus->mdio_map[addr];
if (!mdiodev)
return NULL;
.handle_interrupt = meson_gxl_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
+ .read_mmd = genphy_read_mmd_unsupported,
+ .write_mmd = genphy_write_mmd_unsupported,
}, {
PHY_ID_MATCH_EXACT(0x01803301),
.name = "Meson G12A Internal PHY",
.handle_interrupt = meson_gxl_handle_interrupt,
.suspend = genphy_suspend,
.resume = genphy_resume,
+ .read_mmd = genphy_read_mmd_unsupported,
+ .write_mmd = genphy_write_mmd_unsupported,
},
};
* another mac interface, so we should create a device link between
* phy dev and mac dev.
*/
- if (phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent)
+ if (dev && phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent)
phydev->devlink = device_link_add(dev->dev.parent, &phydev->mdio.dev,
DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
ret = phy_attach_direct(pl->netdev, phy_dev, flags,
pl->link_interface);
- if (ret) {
- phy_device_free(phy_dev);
+ phy_device_free(phy_dev);
+ if (ret)
return ret;
- }
ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface);
if (ret)
if (!priv->phy_dev->drv) {
dev_info(dev, "Attached phy not ready\n");
+ put_device(&priv->phy_dev->mdio.dev);
return -EPROBE_DEFER;
}
goto err_port_enter;
}
}
- port->dev->priv_flags |= IFF_NO_ADDRCONF;
return 0;
{
if (team->ops.port_leave)
team->ops.port_leave(team, port);
- port->dev->priv_flags &= ~IFF_NO_ADDRCONF;
dev_put(team->dev);
}
USB_CDC_SUBCLASS_ETHERNET,
USB_CDC_PROTO_NONE),
.driver_info = (unsigned long)&wwan_info,
+}, {
+ /* Cinterion PLS62-W modem by GEMALTO/THALES */
+ USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x005b, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET,
+ USB_CDC_PROTO_NONE),
+ .driver_info = (unsigned long)&wwan_info,
}, {
/* Cinterion PLS83/PLS63 modem by GEMALTO/THALES */
USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0069, USB_CLASS_COMM,
init_msg, init_msg_len, &act_len, KALMIA_USB_TIMEOUT);
if (status != 0) {
netdev_err(dev->net,
- "Error sending init packet. Status %i, length %i\n",
- status, act_len);
+ "Error sending init packet. Status %i\n",
+ status);
return status;
}
else if (act_len != init_msg_len) {
if (status != 0)
netdev_err(dev->net,
- "Error receiving init result. Status %i, length %i\n",
- status, act_len);
+ "Error receiving init result. Status %i\n",
+ status);
else if (act_len != expected_len)
netdev_err(dev->net, "Unexpected init result length: %i\n",
act_len);
static inline int
pl_vendor_req(struct usbnet *dev, u8 req, u8 val, u8 index)
{
- return usbnet_read_cmd(dev, req,
- USB_DIR_IN | USB_TYPE_VENDOR |
- USB_RECIP_DEVICE,
+ return usbnet_write_cmd(dev, req, USB_TYPE_VENDOR | USB_RECIP_DEVICE,
val, index, NULL, 0);
}
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab),
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6),
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927),
+ REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e),
REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101),
REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f),
REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3054),
off = le32_to_cpu(u.get_c->offset);
len = le32_to_cpu(u.get_c->len);
- if (unlikely((8 + off + len) > CONTROL_BUFFER_SIZE))
+ if (unlikely((off > CONTROL_BUFFER_SIZE - 8) ||
+ (len > CONTROL_BUFFER_SIZE - 8 - off)))
goto response_error;
if (*reply_len != -1 && len != *reply_len)
/* ignore the CRC length */
len = (skb->data[1] | (skb->data[2] << 8)) - 4;
- if (len > ETH_FRAME_LEN || len > skb->len)
+ if (len > ETH_FRAME_LEN || len > skb->len || len < 0)
return 0;
/* the last packet of current skb */
xdp_set_return_frame_no_direct();
done = veth_xdp_rcv(rq, budget, &bq, &stats);
+ if (stats.xdp_redirect > 0)
+ xdp_do_flush();
+
if (done < budget && napi_complete_done(napi, done)) {
/* Write rx_notify_masked before reading ptr_ring */
smp_store_mb(rq->rx_notify_masked, false);
if (stats.xdp_tx > 0)
veth_xdp_flush(rq, &bq);
- if (stats.xdp_redirect > 0)
- xdp_do_flush();
xdp_clear_return_frame_no_direct();
return done;
received = virtnet_receive(rq, budget, &xdp_xmit);
+ if (xdp_xmit & VIRTIO_XDP_REDIR)
+ xdp_do_flush();
+
/* Out of packets? */
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
- if (xdp_xmit & VIRTIO_XDP_REDIR)
- xdp_do_flush();
-
if (xdp_xmit & VIRTIO_XDP_TX) {
sq = virtnet_xdp_get_sq(vi);
if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
*/
if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
netif_stop_subqueue(dev, qnum);
- if (!use_napi &&
- unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
+ if (use_napi) {
+ if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
+ virtqueue_napi_schedule(&sq->napi, sq->vq);
+ } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
/* More just got used, free them then recheck. */
free_old_xmit_skbs(sq, false);
if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
cancel_delayed_work_sync(&vi->refill);
for (i = 0; i < vi->max_queue_pairs; i++) {
- xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
napi_disable(&vi->rq[i].napi);
+ xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
virtnet_napi_tx_disable(&vi->sq[i].napi);
}
(le32_to_cpu(gdesc->dword[3]) &
VMXNET3_RCD_CSUM_OK) == VMXNET3_RCD_CSUM_OK) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if ((le32_to_cpu(gdesc->dword[0]) &
+ (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) {
+ skb->csum_level = 1;
+ }
WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
!(le32_to_cpu(gdesc->dword[0]) &
(1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
} else if (gdesc->rcd.v6 && (le32_to_cpu(gdesc->dword[3]) &
(1 << VMXNET3_RCD_TUC_SHIFT))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if ((le32_to_cpu(gdesc->dword[0]) &
+ (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) {
+ skb->csum_level = 1;
+ }
WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
!(le32_to_cpu(gdesc->dword[0]) &
(1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
rxd->len = rbi->len;
}
-#ifdef VMXNET3_RSS
- if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE &&
- (adapter->netdev->features & NETIF_F_RXHASH)) {
- enum pkt_hash_types hash_type;
-
- switch (rcd->rssType) {
- case VMXNET3_RCD_RSS_TYPE_IPV4:
- case VMXNET3_RCD_RSS_TYPE_IPV6:
- hash_type = PKT_HASH_TYPE_L3;
- break;
- case VMXNET3_RCD_RSS_TYPE_TCPIPV4:
- case VMXNET3_RCD_RSS_TYPE_TCPIPV6:
- case VMXNET3_RCD_RSS_TYPE_UDPIPV4:
- case VMXNET3_RCD_RSS_TYPE_UDPIPV6:
- hash_type = PKT_HASH_TYPE_L4;
- break;
- default:
- hash_type = PKT_HASH_TYPE_L3;
- break;
- }
- skb_set_hash(ctx->skb,
- le32_to_cpu(rcd->rssHash),
- hash_type);
- }
-#endif
skb_record_rx_queue(ctx->skb, rq->qid);
skb_put(ctx->skb, rcd->len);
u32 mtu = adapter->netdev->mtu;
skb->len += skb->data_len;
+#ifdef VMXNET3_RSS
+ if (rcd->rssType != VMXNET3_RCD_RSS_TYPE_NONE &&
+ (adapter->netdev->features & NETIF_F_RXHASH)) {
+ enum pkt_hash_types hash_type;
+
+ switch (rcd->rssType) {
+ case VMXNET3_RCD_RSS_TYPE_IPV4:
+ case VMXNET3_RCD_RSS_TYPE_IPV6:
+ hash_type = PKT_HASH_TYPE_L3;
+ break;
+ case VMXNET3_RCD_RSS_TYPE_TCPIPV4:
+ case VMXNET3_RCD_RSS_TYPE_TCPIPV6:
+ case VMXNET3_RCD_RSS_TYPE_UDPIPV4:
+ case VMXNET3_RCD_RSS_TYPE_UDPIPV6:
+ hash_type = PKT_HASH_TYPE_L4;
+ break;
+ default:
+ hash_type = PKT_HASH_TYPE_L3;
+ break;
+ }
+ skb_set_hash(skb,
+ le32_to_cpu(rcd->rssHash),
+ hash_type);
+ }
+#endif
vmxnet3_rx_csum(adapter, skb,
(union Vmxnet3_GenericDesc *)rcd);
skb->protocol = eth_type_trans(skb, adapter->netdev);
/* loopback, multicast & non-ND link-local traffic; do not push through
* packet taps again. Reset pkt_type for upper layers to process skb.
- * For strict packets with a source LLA, determine the dst using the
- * original ifindex.
+ * For non-loopback strict packets, determine the dst using the original
+ * ifindex.
*/
if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) {
skb->dev = vrf_dev;
if (skb->pkt_type == PACKET_LOOPBACK)
skb->pkt_type = PACKET_HOST;
- else if (ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)
+ else
vrf_ip6_input_dst(skb, vrf_dev, orig_iif);
goto out;
vxlan_vnigroup_init(vxlan);
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!dev->tstats)
- return -ENOMEM;
+ if (!dev->tstats) {
+ err = -ENOMEM;
+ goto err_vnigroup_uninit;
+ }
err = gro_cells_init(&vxlan->gro_cells, dev);
- if (err) {
- free_percpu(dev->tstats);
- return err;
- }
+ if (err)
+ goto err_free_percpu;
return 0;
+
+err_free_percpu:
+ free_percpu(dev->tstats);
+err_vnigroup_uninit:
+ if (vxlan->cfg.flags & VXLAN_F_VNIFILTER)
+ vxlan_vnigroup_uninit(vxlan);
+ return err;
}
static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
free_dev:
free_netdev(dev);
undo_uhdlc_init:
- iounmap(utdm->siram);
+ if (utdm)
+ iounmap(utdm->siram);
unmap_si_regs:
- iounmap(utdm->si_regs);
+ if (utdm)
+ iounmap(utdm->si_regs);
free_utdm:
if (uhdlc_priv->tsa)
kfree(utdm);
}
#ifdef CONFIG_ATH9K_HTC_DEBUGFS
-#define __STAT_SAFE(hif_dev, expr) ((hif_dev)->htc_handle->drv_priv ? (expr) : 0)
-#define CAB_STAT_INC(priv) ((priv)->debug.tx_stats.cab_queued++)
-#define TX_QSTAT_INC(priv, q) ((priv)->debug.tx_stats.queue_stats[q]++)
+#define __STAT_SAFE(hif_dev, expr) do { ((hif_dev)->htc_handle->drv_priv ? (expr) : 0); } while (0)
+#define CAB_STAT_INC(priv) do { ((priv)->debug.tx_stats.cab_queued++); } while (0)
+#define TX_QSTAT_INC(priv, q) do { ((priv)->debug.tx_stats.queue_stats[q]++); } while (0)
#define TX_STAT_INC(hif_dev, c) \
__STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.tx_stats.c++)
struct ethtool_stats *stats, u64 *data);
#else
-#define TX_STAT_INC(hif_dev, c)
-#define TX_STAT_ADD(hif_dev, c, a)
-#define RX_STAT_INC(hif_dev, c)
-#define RX_STAT_ADD(hif_dev, c, a)
+#define TX_STAT_INC(hif_dev, c) do { } while (0)
+#define TX_STAT_ADD(hif_dev, c, a) do { } while (0)
+#define RX_STAT_INC(hif_dev, c) do { } while (0)
+#define RX_STAT_ADD(hif_dev, c, a) do { } while (0)
#define CAB_STAT_INC(priv)
#define TX_QSTAT_INC(priv, c)
struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg));
+ if (chan->flags & IEEE80211_CHAN_DISABLED)
+ return -EINVAL;
+
/* set_channel */
chspec = channel_to_chanspec(&cfg->d11inf, chan);
if (chspec != INVCHANSPEC) {
struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg));
struct brcmf_dump_survey survey = {};
struct ieee80211_supported_band *band;
- struct ieee80211_channel *chan;
+ enum nl80211_band band_id;
struct cca_msrmnt_query req;
u32 noise;
int err;
return -EBUSY;
}
- band = wiphy->bands[NL80211_BAND_2GHZ];
- if (band && idx >= band->n_channels) {
- idx -= band->n_channels;
- band = NULL;
- }
+ for (band_id = 0; band_id < NUM_NL80211_BANDS; band_id++) {
+ band = wiphy->bands[band_id];
+ if (!band)
+ continue;
+ if (idx >= band->n_channels) {
+ idx -= band->n_channels;
+ continue;
+ }
- if (!band || idx >= band->n_channels) {
- band = wiphy->bands[NL80211_BAND_5GHZ];
- if (idx >= band->n_channels)
- return -ENOENT;
+ info->channel = &band->channels[idx];
+ break;
}
+ if (band_id == NUM_NL80211_BANDS)
+ return -ENOENT;
/* Setting current channel to the requested channel */
- chan = &band->channels[idx];
- err = cfg80211_set_channel(wiphy, ndev, chan, NL80211_CHAN_HT20);
- if (err) {
- info->channel = chan;
- info->filled = 0;
+ info->filled = 0;
+ if (cfg80211_set_channel(wiphy, ndev, info->channel, NL80211_CHAN_HT20))
return 0;
- }
/* Disable mpc */
brcmf_set_mpc(ifp, 0);
if (err)
goto exit;
- info->channel = chan;
info->noise = noise;
info->time = ACS_MSRMNT_DELAY;
info->time_busy = ACS_MSRMNT_DELAY - survey.idle;
SURVEY_INFO_TIME_TX;
brcmf_dbg(INFO, "OBSS dump: channel %d: survey duration %d\n",
- ieee80211_frequency_to_channel(chan->center_freq),
+ ieee80211_frequency_to_channel(info->channel->center_freq),
ACS_MSRMNT_DELAY);
brcmf_dbg(INFO, "noise(%d) busy(%llu) rx(%llu) tx(%llu)\n",
info->noise, info->time_busy, info->time_rx, info->time_tx);
/* Apple ARM64 platforms have their own idea of board type, passed in
* via the device tree. They also have an antenna SKU parameter
*/
- if (!of_property_read_string(np, "brcm,board-type", &prop))
+ err = of_property_read_string(np, "brcm,board-type", &prop);
+ if (!err)
settings->board_type = prop;
if (!of_property_read_string(np, "apple,antenna-sku", &prop))
/* Set board-type to the first string of the machine compatible prop */
root = of_find_node_by_path("/");
- if (root && !settings->board_type) {
+ if (root && err) {
char *board_type;
const char *tmp;
BRCMF_NROF_H2D_COMMON_MSGRINGS;
max_completionrings = BRCMF_NROF_D2H_COMMON_MSGRINGS;
}
- if (max_flowrings > 256) {
+ if (max_flowrings > 512) {
brcmf_err(bus, "invalid max_flowrings(%d)\n", max_flowrings);
return -EIO;
}
int i, j, num_sub_bands;
s8 *gain;
+ /* many firmware images for JF lie about this */
+ if (CSR_HW_RFID_TYPE(fwrt->trans->hw_rf_id) ==
+ CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_JF))
+ return -EOPNOTSUPP;
+
if (!fw_has_capa(&fwrt->fw->ucode_capa, IWL_UCODE_TLV_CAPA_SET_PPAG)) {
IWL_DEBUG_RADIO(fwrt,
"PPAG capability not supported by FW, command not sent.\n");
mt76_dma_sync_idx(dev, q);
}
+static int
+mt76_dma_add_rx_buf(struct mt76_dev *dev, struct mt76_queue *q,
+ struct mt76_queue_buf *buf, void *data)
+{
+ struct mt76_desc *desc = &q->desc[q->head];
+ struct mt76_queue_entry *entry = &q->entry[q->head];
+ struct mt76_txwi_cache *txwi = NULL;
+ u32 buf1 = 0, ctrl;
+ int idx = q->head;
+ int rx_token;
+
+ ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
+
+ if ((q->flags & MT_QFLAG_WED) &&
+ FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) {
+ txwi = mt76_get_rxwi(dev);
+ if (!txwi)
+ return -ENOMEM;
+
+ rx_token = mt76_rx_token_consume(dev, data, txwi, buf->addr);
+ if (rx_token < 0) {
+ mt76_put_rxwi(dev, txwi);
+ return -ENOMEM;
+ }
+
+ buf1 |= FIELD_PREP(MT_DMA_CTL_TOKEN, rx_token);
+ ctrl |= MT_DMA_CTL_TO_HOST;
+ }
+
+ WRITE_ONCE(desc->buf0, cpu_to_le32(buf->addr));
+ WRITE_ONCE(desc->buf1, cpu_to_le32(buf1));
+ WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl));
+ WRITE_ONCE(desc->info, 0);
+
+ entry->dma_addr[0] = buf->addr;
+ entry->dma_len[0] = buf->len;
+ entry->txwi = txwi;
+ entry->buf = data;
+ entry->wcid = 0xffff;
+ entry->skip_buf1 = true;
+ q->head = (q->head + 1) % q->ndesc;
+ q->queued++;
+
+ return idx;
+}
+
static int
mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
struct mt76_queue_buf *buf, int nbufs, u32 info,
{
struct mt76_queue_entry *entry;
struct mt76_desc *desc;
- u32 ctrl;
int i, idx = -1;
+ u32 ctrl, next;
+
+ if (txwi) {
+ q->entry[q->head].txwi = DMA_DUMMY_DATA;
+ q->entry[q->head].skip_buf0 = true;
+ }
for (i = 0; i < nbufs; i += 2, buf += 2) {
u32 buf0 = buf[0].addr, buf1 = 0;
idx = q->head;
- q->head = (q->head + 1) % q->ndesc;
+ next = (q->head + 1) % q->ndesc;
desc = &q->desc[idx];
entry = &q->entry[idx];
- if ((q->flags & MT_QFLAG_WED) &&
- FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) {
- struct mt76_txwi_cache *t = txwi;
- int rx_token;
-
- if (!t)
- return -ENOMEM;
-
- rx_token = mt76_rx_token_consume(dev, (void *)skb, t,
- buf[0].addr);
- buf1 |= FIELD_PREP(MT_DMA_CTL_TOKEN, rx_token);
- ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len) |
- MT_DMA_CTL_TO_HOST;
- } else {
- if (txwi) {
- q->entry[q->head].txwi = DMA_DUMMY_DATA;
- q->entry[q->head].skip_buf0 = true;
- }
-
- if (buf[0].skip_unmap)
- entry->skip_buf0 = true;
- entry->skip_buf1 = i == nbufs - 1;
-
- entry->dma_addr[0] = buf[0].addr;
- entry->dma_len[0] = buf[0].len;
-
- ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
- if (i < nbufs - 1) {
- entry->dma_addr[1] = buf[1].addr;
- entry->dma_len[1] = buf[1].len;
- buf1 = buf[1].addr;
- ctrl |= FIELD_PREP(MT_DMA_CTL_SD_LEN1, buf[1].len);
- if (buf[1].skip_unmap)
- entry->skip_buf1 = true;
- }
-
- if (i == nbufs - 1)
- ctrl |= MT_DMA_CTL_LAST_SEC0;
- else if (i == nbufs - 2)
- ctrl |= MT_DMA_CTL_LAST_SEC1;
+ if (buf[0].skip_unmap)
+ entry->skip_buf0 = true;
+ entry->skip_buf1 = i == nbufs - 1;
+
+ entry->dma_addr[0] = buf[0].addr;
+ entry->dma_len[0] = buf[0].len;
+
+ ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
+ if (i < nbufs - 1) {
+ entry->dma_addr[1] = buf[1].addr;
+ entry->dma_len[1] = buf[1].len;
+ buf1 = buf[1].addr;
+ ctrl |= FIELD_PREP(MT_DMA_CTL_SD_LEN1, buf[1].len);
+ if (buf[1].skip_unmap)
+ entry->skip_buf1 = true;
}
+ if (i == nbufs - 1)
+ ctrl |= MT_DMA_CTL_LAST_SEC0;
+ else if (i == nbufs - 2)
+ ctrl |= MT_DMA_CTL_LAST_SEC1;
+
WRITE_ONCE(desc->buf0, cpu_to_le32(buf0));
WRITE_ONCE(desc->buf1, cpu_to_le32(buf1));
WRITE_ONCE(desc->info, cpu_to_le32(info));
WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl));
+ q->head = next;
q->queued++;
}
spin_lock_bh(&q->lock);
while (q->queued < q->ndesc - 1) {
- struct mt76_txwi_cache *t = NULL;
struct mt76_queue_buf qbuf;
void *buf = NULL;
- if ((q->flags & MT_QFLAG_WED) &&
- FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) {
- t = mt76_get_rxwi(dev);
- if (!t)
- break;
- }
-
buf = page_frag_alloc(rx_page, q->buf_size, GFP_ATOMIC);
if (!buf)
break;
qbuf.addr = addr + offset;
qbuf.len = len - offset;
qbuf.skip_unmap = false;
- mt76_dma_add_buf(dev, q, &qbuf, 1, 0, buf, t);
+ if (mt76_dma_add_rx_buf(dev, q, &qbuf, buf) < 0) {
+ dma_unmap_single(dev->dma_dev, addr, len,
+ DMA_FROM_DEVICE);
+ skb_free_frag(buf);
+ break;
+ }
frames++;
}
desc->buf0 = cpu_to_le32(phy_addr);
token = mt76_rx_token_consume(&dev->mt76, ptr, t, phy_addr);
+ if (token < 0) {
+ dma_unmap_single(dev->mt76.dma_dev, phy_addr,
+ wed->wlan.rx_size, DMA_TO_DEVICE);
+ skb_free_frag(ptr);
+ goto unmap;
+ }
+
desc->token |= cpu_to_le32(FIELD_PREP(MT_DMA_CTL_TOKEN,
token));
desc++;
config MT7996E
tristate "MediaTek MT7996 (PCIe) support"
select MT76_CONNAC_LIB
+ select RELAY
depends on MAC80211
depends on PCI
help
spin_lock_bh(&dev->rx_token_lock);
token = idr_alloc(&dev->rx_token, t, 0, dev->rx_token_size,
GFP_ATOMIC);
+ if (token >= 0) {
+ t->ptr = ptr;
+ t->dma_addr = phys;
+ }
spin_unlock_bh(&dev->rx_token_lock);
- t->ptr = ptr;
- t->dma_addr = phys;
-
return token;
}
EXPORT_SYMBOL_GPL(mt76_rx_token_consume);
struct rndis_query *get;
struct rndis_query_c *get_c;
} u;
- int ret, buflen;
- int resplen, respoffs, copylen;
+ int ret;
+ size_t buflen, resplen, respoffs, copylen;
buflen = *len + sizeof(*u.get);
if (buflen < CONTROL_BUFFER_SIZE)
if (respoffs > buflen) {
/* Device returned data offset outside buffer, error. */
- netdev_dbg(dev->net, "%s(%s): received invalid "
- "data offset: %d > %d\n", __func__,
- oid_to_string(oid), respoffs, buflen);
+ netdev_dbg(dev->net,
+ "%s(%s): received invalid data offset: %zu > %zu\n",
+ __func__, oid_to_string(oid), respoffs, buflen);
ret = -EINVAL;
goto exit_unlock;
}
- if ((resplen + respoffs) > buflen) {
- /* Device would have returned more data if buffer would
- * have been big enough. Copy just the bits that we got.
- */
- copylen = buflen - respoffs;
- } else {
- copylen = resplen;
- }
+ copylen = min(resplen, buflen - respoffs);
if (copylen > *len)
copylen = *len;
obj-$(CONFIG_WL12XX) += wl12xx/
obj-$(CONFIG_WL1251) += wl1251/
obj-$(CONFIG_WL18XX) += wl18xx/
-
-# small builtin driver bit
-obj-$(CONFIG_WILINK_PLATFORM_DATA) += wilink_platform_data.o
}
t7xx_pcie_mac_clear_int(dpmaif_ctrl->t7xx_dev, isr_para->pcie_int);
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t t7xx_dpmaif_isr_thread(int irq, void *data)
+{
+ struct dpmaif_isr_para *isr_para = data;
+ struct dpmaif_ctrl *dpmaif_ctrl = isr_para->dpmaif_ctrl;
+
t7xx_dpmaif_irq_cb(isr_para);
t7xx_pcie_mac_set_int(dpmaif_ctrl->t7xx_dev, isr_para->pcie_int);
return IRQ_HANDLED;
t7xx_pcie_mac_clear_int(t7xx_dev, int_type);
t7xx_dev->intr_handler[int_type] = t7xx_dpmaif_isr_handler;
- t7xx_dev->intr_thread[int_type] = NULL;
+ t7xx_dev->intr_thread[int_type] = t7xx_dpmaif_isr_thread;
t7xx_dev->callback_param[int_type] = isr_para;
t7xx_pcie_mac_clear_int_status(t7xx_dev, int_type);
if (!rxq->que_started) {
atomic_set(&rxq->rx_processing, 0);
+ pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev);
dev_err(rxq->dpmaif_ctrl->dev, "Work RXQ: %d has not been started\n", rxq->index);
return work_done;
}
- if (!rxq->sleep_lock_pending) {
- pm_runtime_get_noresume(rxq->dpmaif_ctrl->dev);
+ if (!rxq->sleep_lock_pending)
t7xx_pci_disable_sleep(t7xx_dev);
- }
ret = try_wait_for_completion(&t7xx_dev->sleep_lock_acquire);
if (!ret) {
napi_complete_done(napi, work_done);
t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info);
t7xx_dpmaif_dlq_unmask_rx_done(&rxq->dpmaif_ctrl->hw_info, rxq->index);
+ t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev);
+ pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev);
+ pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev);
+ atomic_set(&rxq->rx_processing, 0);
} else {
t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info);
}
- t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev);
- pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev);
- pm_runtime_put_noidle(rxq->dpmaif_ctrl->dev);
- atomic_set(&rxq->rx_processing, 0);
-
return work_done;
}
void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int que_mask)
{
struct dpmaif_rx_queue *rxq;
- int qno;
+ struct dpmaif_ctrl *ctrl;
+ int qno, ret;
qno = ffs(que_mask) - 1;
if (qno < 0 || qno > DPMAIF_RXQ_NUM - 1) {
}
rxq = &dpmaif_ctrl->rxq[qno];
+ ctrl = rxq->dpmaif_ctrl;
+ /* We need to make sure that the modem has been resumed before
+ * calling napi. This can't be done inside the polling function
+ * as we could be blocked waiting for device to be resumed,
+ * which can't be done from softirq context the poll function
+ * is running in.
+ */
+ ret = pm_runtime_resume_and_get(ctrl->dev);
+ if (ret < 0 && ret != -EACCES) {
+ dev_err(ctrl->dev, "Failed to resume device: %d\n", ret);
+ return;
+ }
napi_schedule(&rxq->napi);
}
#include <linux/list.h>
#include <linux/netdev_features.h>
#include <linux/netdevice.h>
+#include <linux/pm_runtime.h>
#include <linux/skbuff.h>
#include <linux/types.h>
#include <linux/wwan.h>
static void t7xx_ccmni_enable_napi(struct t7xx_ccmni_ctrl *ctlb)
{
- int i;
+ struct dpmaif_ctrl *ctrl;
+ int i, ret;
+
+ ctrl = ctlb->hif_ctrl;
if (ctlb->is_napi_en)
return;
for (i = 0; i < RXQ_NUM; i++) {
+ /* The usage count has to be bumped every time before calling
+ * napi_schedule. It will be decresed in the poll routine,
+ * right after napi_complete_done is called.
+ */
+ ret = pm_runtime_resume_and_get(ctrl->dev);
+ if (ret < 0) {
+ dev_err(ctrl->dev, "Failed to resume device: %d\n",
+ ret);
+ return;
+ }
napi_enable(ctlb->napi[i]);
napi_schedule(ctlb->napi[i]);
}
iowrite32(T7XX_L1_BIT(0), IREG_BASE(t7xx_dev) + ENABLE_ASPM_LOWPWR);
atomic_set(&t7xx_dev->md_pm_state, MTK_PM_RESUMED);
+ pm_runtime_mark_last_busy(&t7xx_dev->pdev->dev);
+ pm_runtime_allow(&t7xx_dev->pdev->dev);
pm_runtime_put_noidle(&t7xx_dev->pdev->dev);
}
return 0;
}
-static int netback_remove(struct xenbus_device *dev)
+static void netback_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
kfree(be->hotplug_script);
kfree(be);
dev_set_drvdata(&dev->dev, NULL);
- return 0;
}
/*
} while (!ret);
}
-static int xennet_remove(struct xenbus_device *dev)
+static void xennet_remove(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
rtnl_unlock();
}
xennet_free_netdev(info->netdev);
-
- return 0;
}
static const struct xenbus_device_id netfront_ids[] = {
return usb_submit_urb(phy->ack_urb, flags);
}
+struct pn533_out_arg {
+ struct pn533_usb_phy *phy;
+ struct completion done;
+};
+
static int pn533_usb_send_frame(struct pn533 *dev,
struct sk_buff *out)
{
struct pn533_usb_phy *phy = dev->phy;
+ struct pn533_out_arg arg;
+ void *cntx;
int rc;
if (phy->priv == NULL)
print_hex_dump_debug("PN533 TX: ", DUMP_PREFIX_NONE, 16, 1,
out->data, out->len, false);
+ init_completion(&arg.done);
+ cntx = phy->out_urb->context;
+ phy->out_urb->context = &arg;
+
rc = usb_submit_urb(phy->out_urb, GFP_KERNEL);
if (rc)
return rc;
+ wait_for_completion(&arg.done);
+ phy->out_urb->context = cntx;
+
if (dev->protocol_type == PN533_PROTO_REQ_RESP) {
/* request for response for sent packet directly */
rc = pn533_submit_urb_for_response(phy, GFP_KERNEL);
return arg.rc;
}
-static void pn533_send_complete(struct urb *urb)
+static void pn533_out_complete(struct urb *urb)
+{
+ struct pn533_out_arg *arg = urb->context;
+ struct pn533_usb_phy *phy = arg->phy;
+
+ switch (urb->status) {
+ case 0:
+ break; /* success */
+ case -ECONNRESET:
+ case -ENOENT:
+ dev_dbg(&phy->udev->dev,
+ "The urb has been stopped (status %d)\n",
+ urb->status);
+ break;
+ case -ESHUTDOWN:
+ default:
+ nfc_err(&phy->udev->dev,
+ "Urb failure (status %d)\n",
+ urb->status);
+ }
+
+ complete(&arg->done);
+}
+
+static void pn533_ack_complete(struct urb *urb)
{
struct pn533_usb_phy *phy = urb->context;
usb_fill_bulk_urb(phy->out_urb, phy->udev,
usb_sndbulkpipe(phy->udev, out_endpoint),
- NULL, 0, pn533_send_complete, phy);
+ NULL, 0, pn533_out_complete, phy);
usb_fill_bulk_urb(phy->ack_urb, phy->udev,
usb_sndbulkpipe(phy->udev, out_endpoint),
- NULL, 0, pn533_send_complete, phy);
+ NULL, 0, pn533_ack_complete, phy);
switch (id->driver_info) {
case PN533_DEVICE_STD:
depends on ENCRYPTED_KEYS
depends on (LIBNVDIMM=ENCRYPTED_KEYS) || LIBNVDIMM=m
+config NVDIMM_KMSAN
+ bool
+ depends on KMSAN
+ help
+ KMSAN, and other memory debug facilities, increase the size of
+ 'struct page' to contain extra metadata. This collides with
+ the NVDIMM capability to store a potentially
+ larger-than-"System RAM" size 'struct page' array in a
+ reservation of persistent memory rather than limited /
+ precious DRAM. However, that reservation needs to persist for
+ the life of the given NVDIMM namespace. If you are using KMSAN
+ to debug an issue unrelated to NVDIMMs or DAX then say N to this
+ option. Otherwise, say Y but understand that any namespaces
+ (with the page array stored pmem) created with this build of
+ the kernel will permanently reserve and strand excess
+ capacity compared to the CONFIG_KMSAN=n case.
+
+ Select N if unsure.
+
config NVDIMM_TEST_BUILD
tristate "Build the unit test core"
depends on m
struct nd_namespace_common *ndns);
#if IS_ENABLED(CONFIG_ND_CLAIM)
/* max struct page size independent of kernel config */
-#define MAX_STRUCT_PAGE_SIZE 128
+#define MAX_STRUCT_PAGE_SIZE 64
int nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap);
#else
static inline int nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
#include "pfn.h"
#include "nd.h"
+static const bool page_struct_override = IS_ENABLED(CONFIG_NVDIMM_KMSAN);
+
static void nd_pfn_release(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
return -ENXIO;
}
- /*
- * Note, we use 64 here for the standard size of struct page,
- * debugging options may cause it to be larger in which case the
- * implementation will limit the pfns advertised through
- * ->direct_access() to those that are included in the memmap.
- */
start = nsio->res.start;
size = resource_size(&nsio->res);
npfns = PHYS_PFN(size - SZ_8K);
}
end_trunc = start + size - ALIGN_DOWN(start + size, align);
if (nd_pfn->mode == PFN_MODE_PMEM) {
+ unsigned long page_map_size = MAX_STRUCT_PAGE_SIZE * npfns;
+
/*
* The altmap should be padded out to the block size used
* when populating the vmemmap. This *should* be equal to
* PMD_SIZE for most architectures.
*
- * Also make sure size of struct page is less than 128. We
- * want to make sure we use large enough size here so that
- * we don't have a dynamic reserve space depending on
- * struct page size. But we also want to make sure we notice
- * when we end up adding new elements to struct page.
+ * Also make sure size of struct page is less than
+ * MAX_STRUCT_PAGE_SIZE. The goal here is compatibility in the
+ * face of production kernel configurations that reduce the
+ * 'struct page' size below MAX_STRUCT_PAGE_SIZE. For debug
+ * kernel configurations that increase the 'struct page' size
+ * above MAX_STRUCT_PAGE_SIZE, the page_struct_override allows
+ * for continuing with the capacity that will be wasted when
+ * reverting to a production kernel configuration. Otherwise,
+ * those configurations are blocked by default.
*/
- BUILD_BUG_ON(sizeof(struct page) > MAX_STRUCT_PAGE_SIZE);
- offset = ALIGN(start + SZ_8K + MAX_STRUCT_PAGE_SIZE * npfns, align)
- - start;
+ if (sizeof(struct page) > MAX_STRUCT_PAGE_SIZE) {
+ if (page_struct_override)
+ page_map_size = sizeof(struct page) * npfns;
+ else {
+ dev_err(&nd_pfn->dev,
+ "Memory debug options prevent using pmem for the page map\n");
+ return -EINVAL;
+ }
+ }
+ offset = ALIGN(start + SZ_8K + page_map_size, align) - start;
} else if (nd_pfn->mode == PFN_MODE_RAM)
offset = ALIGN(start + SZ_8K, align) - start;
else
pfn_sb->version_minor = cpu_to_le16(4);
pfn_sb->end_trunc = cpu_to_le32(end_trunc);
pfn_sb->align = cpu_to_le32(nd_pfn->align);
- pfn_sb->page_struct_size = cpu_to_le16(MAX_STRUCT_PAGE_SIZE);
+ if (sizeof(struct page) > MAX_STRUCT_PAGE_SIZE && page_struct_override)
+ pfn_sb->page_struct_size = cpu_to_le16(sizeof(struct page));
+ else
+ pfn_sb->page_struct_size = cpu_to_le16(MAX_STRUCT_PAGE_SIZE);
pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
pfn_sb->checksum = cpu_to_le64(checksum);
apple_nvme_remove_cq(anv);
}
- nvme_disable_ctrl(&anv->ctrl, shutdown);
+ /*
+ * Always disable the NVMe controller after shutdown.
+ * We need to do this to bring it back up later anyway, and we
+ * can't do it while the firmware is not running (e.g. in the
+ * resume reset path before RTKit is initialized), so for Apple
+ * controllers it makes sense to unconditionally do it here.
+ * Additionally, this sequence of events is reliable, while
+ * others (like disabling after bringing back the firmware on
+ * resume) seem to run into trouble under some circumstances.
+ *
+ * Both U-Boot and m1n1 also use this convention (i.e. an ANS
+ * NVMe controller is handed off with firmware shut down, in an
+ * NVMe disabled state, after a clean shutdown).
+ */
+ if (shutdown)
+ nvme_disable_ctrl(&anv->ctrl, shutdown);
+ nvme_disable_ctrl(&anv->ctrl, false);
}
WRITE_ONCE(anv->ioq.enabled, false);
goto out;
}
- if (anv->ctrl.ctrl_config & NVME_CC_ENABLE)
- apple_nvme_disable(anv, false);
-
/* RTKit must be shut down cleanly for the (soft)-reset to work */
if (apple_rtkit_is_running(anv->rtk)) {
+ /* reset the controller if it is enabled */
+ if (anv->ctrl.ctrl_config & NVME_CC_ENABLE)
+ apple_nvme_disable(anv, false);
dev_dbg(anv->dev, "Trying to shut down RTKit before reset.");
ret = apple_rtkit_shutdown(anv->rtk);
if (ret)
}
ret = nvme_init_ctrl(&anv->ctrl, anv->dev, &nvme_ctrl_ops,
- NVME_QUIRK_SKIP_CID_GEN);
+ NVME_QUIRK_SKIP_CID_GEN | NVME_QUIRK_IDENTIFY_CNS);
if (ret) {
dev_err_probe(dev, ret, "Failed to initialize nvme_ctrl");
goto put_dev;
int sess_key_len;
};
+static struct workqueue_struct *nvme_auth_wq;
+
#define nvme_auth_flags_from_qid(qid) \
(qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED
#define nvme_auth_queue_from_qid(ctrl, qid) \
chap = &ctrl->dhchap_ctxs[qid];
cancel_work_sync(&chap->auth_work);
- queue_work(nvme_wq, &chap->auth_work);
+ queue_work(nvme_auth_wq, &chap->auth_work);
return 0;
}
EXPORT_SYMBOL_GPL(nvme_auth_negotiate);
goto err_free_dhchap_secret;
if (!ctrl->opts->dhchap_secret && !ctrl->opts->dhchap_ctrl_secret)
- return ret;
+ return 0;
ctrl->dhchap_ctxs = kvcalloc(ctrl_max_dhchaps(ctrl),
sizeof(*chap), GFP_KERNEL);
int __init nvme_init_auth(void)
{
+ nvme_auth_wq = alloc_workqueue("nvme-auth-wq",
+ WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
+ if (!nvme_auth_wq)
+ return -ENOMEM;
+
nvme_chap_buf_cache = kmem_cache_create("nvme-chap-buf-cache",
CHAP_BUF_SIZE, 0, SLAB_HWCACHE_ALIGN, NULL);
if (!nvme_chap_buf_cache)
- return -ENOMEM;
+ goto err_destroy_workqueue;
nvme_chap_buf_pool = mempool_create(16, mempool_alloc_slab,
mempool_free_slab, nvme_chap_buf_cache);
return 0;
err_destroy_chap_buf_cache:
kmem_cache_destroy(nvme_chap_buf_cache);
+err_destroy_workqueue:
+ destroy_workqueue(nvme_auth_wq);
return -ENOMEM;
}
{
mempool_destroy(nvme_chap_buf_pool);
kmem_cache_destroy(nvme_chap_buf_cache);
+ destroy_workqueue(nvme_auth_wq);
}
return 0;
}
+static u32 nvme_known_nvm_effects(u8 opcode)
+{
+ switch (opcode) {
+ case nvme_cmd_write:
+ case nvme_cmd_write_zeroes:
+ case nvme_cmd_write_uncor:
+ return NVME_CMD_EFFECTS_LBCC;
+ default:
+ return 0;
+ }
+}
+
u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
{
u32 effects = 0;
if (ns) {
if (ns->head->effects)
effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
+ if (ns->head->ids.csi == NVME_CSI_NVM)
+ effects |= nvme_known_nvm_effects(opcode);
if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
dev_warn_once(ctrl->device,
- "IO command:%02x has unhandled effects:%08x\n",
+ "IO command:%02x has unusual effects:%08x\n",
opcode, effects);
- return 0;
- }
- if (ctrl->effects)
- effects = le32_to_cpu(ctrl->effects->acs[opcode]);
- effects |= nvme_known_admin_effects(opcode);
+ /*
+ * NVME_CMD_EFFECTS_CSE_MASK causes a freeze all I/O queues,
+ * which would deadlock when done on an I/O command. Note that
+ * We already warn about an unusual effect above.
+ */
+ effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
+ } else {
+ if (ctrl->effects)
+ effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+ effects |= nvme_known_admin_effects(opcode);
+ }
return effects;
}
blk_mq_destroy_queue(ctrl->admin_q);
blk_put_queue(ctrl->admin_q);
out_free_tagset:
- blk_mq_free_tag_set(ctrl->admin_tagset);
+ blk_mq_free_tag_set(set);
+ ctrl->admin_q = NULL;
+ ctrl->fabrics_q = NULL;
return ret;
}
EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set);
memset(set, 0, sizeof(*set));
set->ops = ops;
- set->queue_depth = ctrl->sqsize + 1;
+ set->queue_depth = min_t(unsigned, ctrl->sqsize, BLK_MQ_MAX_DEPTH - 1);
/*
* Some Apple controllers requires tags to be unique across admin and
* the (only) I/O queue, so reserve the first 32 tags of the I/O queue.
out_free_tag_set:
blk_mq_free_tag_set(set);
+ ctrl->connect_q = NULL;
return ret;
}
EXPORT_SYMBOL_GPL(nvme_alloc_io_tag_set);
nvme_fc_init_queue(ctrl, 0);
- ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set,
- &nvme_fc_admin_mq_ops,
- struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv,
- ctrl->lport->ops->fcprqst_priv_sz));
- if (ret)
- goto out_free_queues;
-
/*
* Would have been nice to init io queues tag set as well.
* However, we require interaction from the controller
ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
if (ret)
- goto out_cleanup_tagset;
+ goto out_free_queues;
/* at this point, teardown path changes to ref counting on nvme ctrl */
+ ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set,
+ &nvme_fc_admin_mq_ops,
+ struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv,
+ ctrl->lport->ops->fcprqst_priv_sz));
+ if (ret)
+ goto fail_ctrl;
+
spin_lock_irqsave(&rport->lock, flags);
list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
spin_unlock_irqrestore(&rport->lock, flags);
return ERR_PTR(-EIO);
-out_cleanup_tagset:
- nvme_remove_admin_tag_set(&ctrl->ctrl);
out_free_queues:
kfree(ctrl->queues);
out_free_ida:
#include <linux/io_uring.h>
#include "nvme.h"
+enum {
+ NVME_IOCTL_VEC = (1 << 0),
+ NVME_IOCTL_PARTITION = (1 << 1),
+};
+
static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
- fmode_t mode)
+ unsigned int flags, fmode_t mode)
{
+ u32 effects;
+
if (capable(CAP_SYS_ADMIN))
return true;
+ /*
+ * Do not allow unprivileged passthrough on partitions, as that allows an
+ * escape from the containment of the partition.
+ */
+ if (flags & NVME_IOCTL_PARTITION)
+ return false;
+
/*
* Do not allow unprivileged processes to send vendor specific or fabrics
* commands as we can't be sure about their effects.
}
/*
- * Only allow I/O commands that transfer data to the controller if the
- * special file is open for writing, but always allow I/O commands that
- * transfer data from the controller.
+ * Check if the controller provides a Commands Supported and Effects log
+ * and marks this command as supported. If not reject unprivileged
+ * passthrough.
+ */
+ effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode);
+ if (!(effects & NVME_CMD_EFFECTS_CSUPP))
+ return false;
+
+ /*
+ * Don't allow passthrough for command that have intrusive (or unknown)
+ * effects.
+ */
+ if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
+ NVME_CMD_EFFECTS_UUID_SEL |
+ NVME_CMD_EFFECTS_SCOPE_MASK))
+ return false;
+
+ /*
+ * Only allow I/O commands that transfer data to the controller or that
+ * change the logical block contents if the file descriptor is open for
+ * writing.
*/
- if (nvme_is_write(c))
+ if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC))
return mode & FMODE_WRITE;
return true;
}
static int nvme_map_user_request(struct request *req, u64 ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd,
- bool vec)
+ unsigned int flags)
{
struct request_queue *q = req->q;
struct nvme_ns *ns = q->queuedata;
struct iov_iter iter;
/* fixedbufs is only for non-vectored io */
- if (WARN_ON_ONCE(vec))
+ if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC))
return -EINVAL;
ret = io_uring_cmd_import_fixed(ubuffer, bufflen,
rq_data_dir(req), &iter, ioucmd);
ret = blk_rq_map_user_iov(q, req, NULL, &iter, GFP_KERNEL);
} else {
ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer),
- bufflen, GFP_KERNEL, vec, 0, 0,
- rq_data_dir(req));
+ bufflen, GFP_KERNEL, flags & NVME_IOCTL_VEC, 0,
+ 0, rq_data_dir(req));
}
if (ret)
}
static int nvme_submit_user_cmd(struct request_queue *q,
- struct nvme_command *cmd, u64 ubuffer,
- unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
- u32 meta_seed, u64 *result, unsigned timeout, bool vec)
+ struct nvme_command *cmd, u64 ubuffer, unsigned bufflen,
+ void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
+ u64 *result, unsigned timeout, unsigned int flags)
{
struct nvme_ctrl *ctrl;
struct request *req;
req->timeout = timeout;
if (ubuffer && bufflen) {
ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
- meta_len, meta_seed, &meta, NULL, vec);
+ meta_len, meta_seed, &meta, NULL, flags);
if (ret)
return ret;
}
c.rw.apptag = cpu_to_le16(io.apptag);
c.rw.appmask = cpu_to_le16(io.appmask);
- return nvme_submit_user_cmd(ns->queue, &c,
- io.addr, length,
- metadata, meta_len, lower_32_bits(io.slba), NULL, 0,
- false);
+ return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata,
+ meta_len, lower_32_bits(io.slba), NULL, 0, 0);
}
static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
}
static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
- struct nvme_passthru_cmd __user *ucmd, fmode_t mode)
+ struct nvme_passthru_cmd __user *ucmd, unsigned int flags,
+ fmode_t mode)
{
struct nvme_passthru_cmd cmd;
struct nvme_command c;
c.common.cdw14 = cpu_to_le32(cmd.cdw14);
c.common.cdw15 = cpu_to_le32(cmd.cdw15);
- if (!nvme_cmd_allowed(ns, &c, mode))
+ if (!nvme_cmd_allowed(ns, &c, 0, mode))
return -EACCES;
if (cmd.timeout_ms)
timeout = msecs_to_jiffies(cmd.timeout_ms);
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
- cmd.addr, cmd.data_len,
- nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
- 0, &result, timeout, false);
+ cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
+ cmd.metadata_len, 0, &result, timeout, 0);
if (status >= 0) {
if (put_user(result, &ucmd->result))
}
static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
- struct nvme_passthru_cmd64 __user *ucmd, bool vec,
- fmode_t mode)
+ struct nvme_passthru_cmd64 __user *ucmd, unsigned int flags,
+ fmode_t mode)
{
struct nvme_passthru_cmd64 cmd;
struct nvme_command c;
c.common.cdw14 = cpu_to_le32(cmd.cdw14);
c.common.cdw15 = cpu_to_le32(cmd.cdw15);
- if (!nvme_cmd_allowed(ns, &c, mode))
+ if (!nvme_cmd_allowed(ns, &c, flags, mode))
return -EACCES;
if (cmd.timeout_ms)
timeout = msecs_to_jiffies(cmd.timeout_ms);
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
- cmd.addr, cmd.data_len,
- nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
- 0, &cmd.result, timeout, vec);
+ cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
+ cmd.metadata_len, 0, &cmd.result, timeout, flags);
if (status >= 0) {
if (put_user(cmd.result, &ucmd->result))
c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14));
c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15));
- if (!nvme_cmd_allowed(ns, &c, ioucmd->file->f_mode))
+ if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode))
return -EACCES;
d.metadata = READ_ONCE(cmd->metadata);
{
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(ctrl, NULL, argp, mode);
+ return nvme_user_cmd(ctrl, NULL, argp, 0, mode);
case NVME_IOCTL_ADMIN64_CMD:
- return nvme_user_cmd64(ctrl, NULL, argp, false, mode);
+ return nvme_user_cmd64(ctrl, NULL, argp, 0, mode);
default:
return sed_ioctl(ctrl->opal_dev, cmd, argp);
}
#endif /* COMPAT_FOR_U64_ALIGNMENT */
static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
- void __user *argp, fmode_t mode)
+ void __user *argp, unsigned int flags, fmode_t mode)
{
switch (cmd) {
case NVME_IOCTL_ID:
force_successful_syscall_return();
return ns->head->ns_id;
case NVME_IOCTL_IO_CMD:
- return nvme_user_cmd(ns->ctrl, ns, argp, mode);
+ return nvme_user_cmd(ns->ctrl, ns, argp, flags, mode);
/*
* struct nvme_user_io can have different padding on some 32-bit ABIs.
* Just accept the compat version as all fields that are used are the
#endif
case NVME_IOCTL_SUBMIT_IO:
return nvme_submit_io(ns, argp);
- case NVME_IOCTL_IO64_CMD:
- return nvme_user_cmd64(ns->ctrl, ns, argp, false, mode);
case NVME_IOCTL_IO64_CMD_VEC:
- return nvme_user_cmd64(ns->ctrl, ns, argp, true, mode);
+ flags |= NVME_IOCTL_VEC;
+ fallthrough;
+ case NVME_IOCTL_IO64_CMD:
+ return nvme_user_cmd64(ns->ctrl, ns, argp, flags, mode);
default:
return -ENOTTY;
}
}
-static int __nvme_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *arg,
- fmode_t mode)
-{
- if (is_ctrl_ioctl(cmd))
- return nvme_ctrl_ioctl(ns->ctrl, cmd, arg, mode);
- return nvme_ns_ioctl(ns, cmd, arg, mode);
-}
-
int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct nvme_ns *ns = bdev->bd_disk->private_data;
+ void __user *argp = (void __user *)arg;
+ unsigned int flags = 0;
+
+ if (bdev_is_partition(bdev))
+ flags |= NVME_IOCTL_PARTITION;
- return __nvme_ioctl(ns, cmd, (void __user *)arg, mode);
+ if (is_ctrl_ioctl(cmd))
+ return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode);
+ return nvme_ns_ioctl(ns, cmd, argp, flags, mode);
}
long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct nvme_ns *ns =
container_of(file_inode(file)->i_cdev, struct nvme_ns, cdev);
+ void __user *argp = (void __user *)arg;
- return __nvme_ioctl(ns, cmd, (void __user *)arg, file->f_mode);
+ if (is_ctrl_ioctl(cmd))
+ return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, file->f_mode);
+ return nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode);
}
static int nvme_uring_cmd_checks(unsigned int issue_flags)
void __user *argp = (void __user *)arg;
struct nvme_ns *ns;
int srcu_idx, ret = -EWOULDBLOCK;
+ unsigned int flags = 0;
+
+ if (bdev_is_partition(bdev))
+ flags |= NVME_IOCTL_PARTITION;
srcu_idx = srcu_read_lock(&head->srcu);
ns = nvme_find_path(head);
return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx,
mode);
- ret = nvme_ns_ioctl(ns, cmd, argp, mode);
+ ret = nvme_ns_ioctl(ns, cmd, argp, flags, mode);
out_unlock:
srcu_read_unlock(&head->srcu, srcu_idx);
return ret;
return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx,
file->f_mode);
- ret = nvme_ns_ioctl(ns, cmd, argp, file->f_mode);
+ ret = nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode);
out_unlock:
srcu_read_unlock(&head->srcu, srcu_idx);
return ret;
kref_get(&ns->kref);
up_read(&ctrl->namespaces_rwsem);
- ret = nvme_user_cmd(ctrl, ns, argp, mode);
+ ret = nvme_user_cmd(ctrl, ns, argp, 0, mode);
nvme_put_ns(ns);
return ret;
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(ctrl, NULL, argp, file->f_mode);
+ return nvme_user_cmd(ctrl, NULL, argp, 0, file->f_mode);
case NVME_IOCTL_ADMIN64_CMD:
- return nvme_user_cmd64(ctrl, NULL, argp, false, file->f_mode);
+ return nvme_user_cmd64(ctrl, NULL, argp, 0, file->f_mode);
case NVME_IOCTL_IO_CMD:
return nvme_dev_user_cmd(ctrl, argp, file->f_mode);
case NVME_IOCTL_RESET:
* pool from the original queue to allocate the bvecs from.
*/
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
srcu_idx = srcu_read_lock(&head->srcu);
ns = nvme_find_path(head);
{
struct nvme_ns *ns = req->q->queuedata;
- if (req->cmd_flags & REQ_NVME_MPATH)
+ if ((req->cmd_flags & REQ_NVME_MPATH) && req->bio)
trace_block_bio_complete(ns->head->disk->queue, req->bio);
}
#define SQ_SIZE(q) ((q)->q_depth << (q)->sqes)
#define CQ_SIZE(q) ((q)->q_depth * sizeof(struct nvme_completion))
-#define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+#define SGES_PER_PAGE (NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc))
/*
* These can be higher, but we need to ensure that any command doesn't
static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown);
static void nvme_delete_io_queues(struct nvme_dev *dev);
+static void nvme_update_attrs(struct nvme_dev *dev);
/*
* Represents an NVM Express device. Each nvme_dev is a PCI function.
mempool_t *iod_mempool;
/* shadow doorbell buffer support: */
- u32 *dbbuf_dbs;
+ __le32 *dbbuf_dbs;
dma_addr_t dbbuf_dbs_dma_addr;
- u32 *dbbuf_eis;
+ __le32 *dbbuf_eis;
dma_addr_t dbbuf_eis_dma_addr;
/* host memory buffer support: */
#define NVMEQ_SQ_CMB 1
#define NVMEQ_DELETE_ERROR 2
#define NVMEQ_POLLED 3
- u32 *dbbuf_sq_db;
- u32 *dbbuf_cq_db;
- u32 *dbbuf_sq_ei;
- u32 *dbbuf_cq_ei;
+ __le32 *dbbuf_sq_db;
+ __le32 *dbbuf_cq_db;
+ __le32 *dbbuf_sq_ei;
+ __le32 *dbbuf_cq_ei;
struct completion delete_done;
};
}
/* Update dbbuf and return true if an MMIO is required */
-static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
- volatile u32 *dbbuf_ei)
+static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
+ volatile __le32 *dbbuf_ei)
{
if (dbbuf_db) {
- u16 old_value;
+ u16 old_value, event_idx;
/*
* Ensure that the queue is written before updating
*/
wmb();
- old_value = *dbbuf_db;
- *dbbuf_db = value;
+ old_value = le32_to_cpu(*dbbuf_db);
+ *dbbuf_db = cpu_to_le32(value);
/*
* Ensure that the doorbell is updated before reading the event
*/
mb();
- if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
+ event_idx = le32_to_cpu(*dbbuf_ei);
+ if (!nvme_dbbuf_need_event(event_idx, value, old_value))
return false;
}
*/
static int nvme_pci_npages_prp(void)
{
- unsigned nprps = DIV_ROUND_UP(NVME_MAX_KB_SZ + NVME_CTRL_PAGE_SIZE,
- NVME_CTRL_PAGE_SIZE);
- return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+ unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
+ unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
+ return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8);
}
/*
static int nvme_pci_npages_sgl(void)
{
return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc),
- PAGE_SIZE);
+ NVME_CTRL_PAGE_SIZE);
}
static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
sge->length = cpu_to_le32(entries * sizeof(*sge));
sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4;
} else {
- sge->length = cpu_to_le32(PAGE_SIZE);
+ sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE);
sge->type = NVME_SGL_FMT_SEG_DESC << 4;
}
}
else
nvme_poll_irqdisable(nvmeq);
- if (blk_mq_request_completed(req)) {
+ if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
dev_warn(dev->ctrl.device,
"I/O %d QID %d timeout, completion polled\n",
req->tag, nvmeq->qid);
if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) ==
(NVME_CMBSZ_WDS | NVME_CMBSZ_RDS))
pci_p2pmem_publish(pdev, true);
+
+ nvme_update_attrs(dev);
}
static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
NULL,
};
+static void nvme_update_attrs(struct nvme_dev *dev)
+{
+ sysfs_update_group(&dev->ctrl.device->kobj, &nvme_pci_dev_attrs_group);
+}
+
/*
* nirqs is the number of interrupts available for write and read
* queues. The core already reserved an interrupt for the admin queue.
if (dev->cmb_use_sqes) {
result = nvme_cmb_qdepth(dev, nr_io_queues,
sizeof(struct nvme_command));
- if (result > 0)
+ if (result > 0) {
dev->q_depth = result;
- else
+ dev->ctrl.sqsize = result - 1;
+ } else {
dev->cmb_use_sqes = false;
+ }
}
do {
{
int result = -ENOMEM;
struct pci_dev *pdev = to_pci_dev(dev->dev);
- int dma_address_bits = 64;
if (pci_enable_device_mem(pdev))
return result;
pci_set_master(pdev);
- if (dev->ctrl.quirks & NVME_QUIRK_DMA_ADDRESS_BITS_48)
- dma_address_bits = 48;
- if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(dma_address_bits)))
- goto disable;
-
if (readl(dev->bar + NVME_REG_CSTS) == -1) {
result = -ENODEV;
goto disable;
*/
result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (result < 0)
- return result;
+ goto disable;
dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
io_queue_depth);
- dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
dev->dbs = dev->bar + 4096;
dev_warn(dev->ctrl.device, "IO queue depth clamped to %d\n",
dev->q_depth);
}
-
+ dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
nvme_map_cmb(dev);
pci_enable_pcie_error_reporting(pdev);
pci_save_state(pdev);
- return nvme_pci_configure_admin_queue(dev);
+ result = nvme_pci_configure_admin_queue(dev);
+ if (result)
+ goto free_irq;
+ return result;
+ free_irq:
+ pci_free_irq_vectors(pdev);
disable:
pci_disable_device(pdev);
return result;
dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
if (!dev)
- return NULL;
+ return ERR_PTR(-ENOMEM);
INIT_WORK(&dev->ctrl.reset_work, nvme_reset_work);
mutex_init(&dev->shutdown_lock);
quirks);
if (ret)
goto out_put_device;
-
+
+ if (dev->ctrl.quirks & NVME_QUIRK_DMA_ADDRESS_BITS_48)
+ dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
+ else
+ dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
dma_set_min_align_mask(&pdev->dev, NVME_CTRL_PAGE_SIZE - 1);
dma_set_max_seg_size(&pdev->dev, 0xffffffff);
int result = -ENOMEM;
dev = nvme_pci_alloc_dev(pdev, id);
- if (!dev)
- return -ENOMEM;
+ if (IS_ERR(dev))
+ return PTR_ERR(dev);
result = nvme_dev_map(dev);
if (result)
nvme_start_ctrl(&dev->ctrl);
nvme_put_ctrl(&dev->ctrl);
+ flush_work(&dev->ctrl.scan_work);
return 0;
out_disable:
{ PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
NVME_QUIRK_BOGUS_NID, },
+ { PCI_DEVICE(0x10ec, 0x5763), /* ADATA SX6000PNP */
+ .driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */
.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
.driver_data = NVME_QUIRK_SINGLE_VECTOR |
NVME_QUIRK_128_BYTES_SQES |
NVME_QUIRK_SHARED_TAGS |
- NVME_QUIRK_SKIP_CID_GEN },
+ NVME_QUIRK_SKIP_CID_GEN |
+ NVME_QUIRK_IDENTIFY_CNS },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ 0, }
};
static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
{
- log->acs[nvme_admin_get_log_page] = cpu_to_le32(1 << 0);
- log->acs[nvme_admin_identify] = cpu_to_le32(1 << 0);
- log->acs[nvme_admin_abort_cmd] = cpu_to_le32(1 << 0);
- log->acs[nvme_admin_set_features] = cpu_to_le32(1 << 0);
- log->acs[nvme_admin_get_features] = cpu_to_le32(1 << 0);
- log->acs[nvme_admin_async_event] = cpu_to_le32(1 << 0);
- log->acs[nvme_admin_keep_alive] = cpu_to_le32(1 << 0);
-
- log->iocs[nvme_cmd_read] = cpu_to_le32(1 << 0);
- log->iocs[nvme_cmd_write] = cpu_to_le32(1 << 0);
- log->iocs[nvme_cmd_flush] = cpu_to_le32(1 << 0);
- log->iocs[nvme_cmd_dsm] = cpu_to_le32(1 << 0);
- log->iocs[nvme_cmd_write_zeroes] = cpu_to_le32(1 << 0);
+ log->acs[nvme_admin_get_log_page] =
+ log->acs[nvme_admin_identify] =
+ log->acs[nvme_admin_abort_cmd] =
+ log->acs[nvme_admin_set_features] =
+ log->acs[nvme_admin_get_features] =
+ log->acs[nvme_admin_async_event] =
+ log->acs[nvme_admin_keep_alive] =
+ cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
+
+ log->iocs[nvme_cmd_read] =
+ log->iocs[nvme_cmd_flush] =
+ log->iocs[nvme_cmd_dsm] =
+ cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
+ log->iocs[nvme_cmd_write] =
+ log->iocs[nvme_cmd_write_zeroes] =
+ cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC);
}
static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log)
{
- log->iocs[nvme_cmd_zone_append] = cpu_to_le32(1 << 0);
- log->iocs[nvme_cmd_zone_mgmt_send] = cpu_to_le32(1 << 0);
- log->iocs[nvme_cmd_zone_mgmt_recv] = cpu_to_le32(1 << 0);
+ log->iocs[nvme_cmd_zone_append] =
+ log->iocs[nvme_cmd_zone_mgmt_send] =
+ cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC);
+ log->iocs[nvme_cmd_zone_mgmt_recv] =
+ cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
}
static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
else {
queue = nvmet_fc_alloc_target_queue(iod->assoc, 0,
be16_to_cpu(rqst->assoc_cmd.sqsize));
- if (!queue)
+ if (!queue) {
ret = VERR_QUEUE_ALLOC_FAIL;
+ nvmet_fc_tgt_a_put(iod->assoc);
+ }
}
}
}
/*
- * If there are effects for the command we are about to execute, or
- * an end_req function we need to use nvme_execute_passthru_rq()
- * synchronously in a work item seeing the end_req function and
- * nvme_passthru_end() can't be called in the request done callback
- * which is typically in interrupt context.
+ * If a command needs post-execution fixups, or there are any
+ * non-trivial effects, make sure to execute the command synchronously
+ * in a workqueue so that nvme_passthru_end gets called.
*/
effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode);
- if (req->p.use_workqueue || effects) {
+ if (req->p.use_workqueue ||
+ (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))) {
INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work);
req->p.rq = rq;
queue_work(nvmet_wq, &req->p.work);
len = le32_to_cpu(header.len);
data = kzalloc(len, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
memcpy_fromio(data, priv->base, len);
data[len - 1] = '\0';
return ERR_PTR(rval);
}
- if (config->wp_gpio)
- nvmem->wp_gpio = config->wp_gpio;
- else if (!config->ignore_wp)
+ nvmem->id = rval;
+
+ nvmem->dev.type = &nvmem_provider_type;
+ nvmem->dev.bus = &nvmem_bus_type;
+ nvmem->dev.parent = config->dev;
+
+ device_initialize(&nvmem->dev);
+
+ if (!config->ignore_wp)
nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp",
GPIOD_OUT_HIGH);
if (IS_ERR(nvmem->wp_gpio)) {
- ida_free(&nvmem_ida, nvmem->id);
rval = PTR_ERR(nvmem->wp_gpio);
- kfree(nvmem);
- return ERR_PTR(rval);
+ nvmem->wp_gpio = NULL;
+ goto err_put_device;
}
kref_init(&nvmem->refcnt);
INIT_LIST_HEAD(&nvmem->cells);
- nvmem->id = rval;
nvmem->owner = config->owner;
if (!nvmem->owner && config->dev->driver)
nvmem->owner = config->dev->driver->owner;
nvmem->stride = config->stride ?: 1;
nvmem->word_size = config->word_size ?: 1;
nvmem->size = config->size;
- nvmem->dev.type = &nvmem_provider_type;
- nvmem->dev.bus = &nvmem_bus_type;
- nvmem->dev.parent = config->dev;
nvmem->root_only = config->root_only;
nvmem->priv = config->priv;
nvmem->type = config->type;
break;
}
- if (rval) {
- ida_free(&nvmem_ida, nvmem->id);
- kfree(nvmem);
- return ERR_PTR(rval);
- }
+ if (rval)
+ goto err_put_device;
nvmem->read_only = device_property_present(config->dev, "read-only") ||
config->read_only || !nvmem->reg_write;
nvmem->dev.groups = nvmem_dev_groups;
#endif
- dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
-
- rval = device_register(&nvmem->dev);
- if (rval)
- goto err_put_device;
-
if (nvmem->nkeepout) {
rval = nvmem_validate_keepouts(nvmem);
if (rval)
- goto err_device_del;
+ goto err_put_device;
}
if (config->compat) {
rval = nvmem_sysfs_setup_compat(nvmem, config);
if (rval)
- goto err_device_del;
+ goto err_put_device;
}
if (config->cells) {
rval = nvmem_add_cells(nvmem, config->cells, config->ncells);
if (rval)
- goto err_teardown_compat;
+ goto err_remove_cells;
}
rval = nvmem_add_cells_from_table(nvmem);
if (rval)
goto err_remove_cells;
+ dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
+
+ rval = device_add(&nvmem->dev);
+ if (rval)
+ goto err_remove_cells;
+
blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem);
return nvmem;
err_remove_cells:
nvmem_device_remove_all_cells(nvmem);
-err_teardown_compat:
if (config->compat)
nvmem_sysfs_remove_compat(nvmem, config);
-err_device_del:
- device_del(&nvmem->dev);
err_put_device:
put_device(&nvmem->dev);
if (!cell_np)
return ERR_PTR(-ENOENT);
- nvmem_np = of_get_next_parent(cell_np);
- if (!nvmem_np)
+ nvmem_np = of_get_parent(cell_np);
+ if (!nvmem_np) {
+ of_node_put(cell_np);
return ERR_PTR(-EINVAL);
+ }
nvmem = __nvmem_device_get(nvmem_np, device_match_of_node);
of_node_put(nvmem_np);
- if (IS_ERR(nvmem))
+ if (IS_ERR(nvmem)) {
+ of_node_put(cell_np);
return ERR_CAST(nvmem);
+ }
cell_entry = nvmem_find_cell_entry_by_node(nvmem, cell_np);
+ of_node_put(cell_np);
if (!cell_entry) {
__nvmem_device_put(nvmem);
return ERR_PTR(-ENOENT);
{ .compatible = "qcom,spmi-sdam" },
{},
};
+MODULE_DEVICE_TABLE(of, sdam_match_table);
static struct platform_driver sdam_driver = {
.driver = {
void *val, size_t bytes)
{
struct sunxi_sid *sid = context;
+ u32 word;
+
+ /* .stride = 4 so offset is guaranteed to be aligned */
+ __ioread32_copy(val, sid->base + sid->value_offset + offset, bytes / 4);
- memcpy_fromio(val, sid->base + sid->value_offset + offset, bytes);
+ val += round_down(bytes, 4);
+ offset += round_down(bytes, 4);
+ bytes = bytes % 4;
+
+ if (!bytes)
+ return 0;
+
+ /* Handle any trailing bytes */
+ word = readl_relaxed(sid->base + sid->value_offset + offset);
+ memcpy(val, &word, bytes);
return 0;
}
}
of_dma_range_parser_init(&parser, node);
- for_each_of_range(&parser, &range)
+ for_each_of_range(&parser, &range) {
+ if (range.cpu_addr == OF_BAD_ADDR) {
+ pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
+ range.bus_addr, node);
+ continue;
+ }
num_ranges++;
+ }
+
+ if (!num_ranges) {
+ ret = -EINVAL;
+ goto out;
+ }
r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL);
if (!r) {
}
/*
- * Record all info in the generic DMA ranges array for struct device.
+ * Record all info in the generic DMA ranges array for struct device,
+ * returning an error if we don't find any parsable ranges.
*/
*map = r;
of_dma_range_parser_init(&parser, node);
for_each_of_range(&parser, &range) {
pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n",
range.bus_addr, range.cpu_addr, range.size);
- if (range.cpu_addr == OF_BAD_ADDR) {
- pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n",
- range.bus_addr, node);
+ if (range.cpu_addr == OF_BAD_ADDR)
continue;
- }
r->cpu_start = range.cpu_addr;
r->dma_start = range.bus_addr;
r->size = range.size;
#include <linux/serial_core.h>
#include <linux/sysfs.h>
#include <linux/random.h>
-#include <linux/kmemleak.h>
#include <asm/setup.h> /* for COMMAND_LINE_SIZE */
#include <asm/page.h>
size = dt_mem_next_cell(dt_root_size_cells, &prop);
if (size &&
- early_init_dt_reserve_memory(base, size, nomap) == 0) {
+ early_init_dt_reserve_memory(base, size, nomap) == 0)
pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n",
uname, &base, (unsigned long)(size / SZ_1M));
- if (!nomap)
- kmemleak_alloc_phys(base, size, 0);
- }
else
pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n",
uname, &base, (unsigned long)(size / SZ_1M));
*/
int __init early_init_dt_scan_memory(void)
{
- int node;
+ int node, found_memory = 0;
const void *fdt = initial_boot_params;
fdt_for_each_subnode(node, fdt, 0) {
early_init_dt_add_memory_arch(base, size);
+ found_memory = 1;
+
if (!hotpluggable)
continue;
base, base + size);
}
}
- return 0;
+ return found_memory;
}
int __init early_init_dt_scan_chosen(char *cmdline)
if (node < 0)
node = fdt_path_offset(fdt, "/chosen@0");
if (node < 0)
- return -ENOENT;
+ /* Handle the cmdline config options even if no /chosen node */
+ goto handle_cmdline;
chosen_node_offset = node;
early_init_dt_check_for_initrd(node);
early_init_dt_check_for_elfcorehdr(node);
- /* Retrieve command line */
- p = of_get_flat_dt_prop(node, "bootargs", &l);
- if (p != NULL && l > 0)
- strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE));
-
rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l);
if (rng_seed && l > 0) {
add_bootloader_randomness(rng_seed, l);
fdt_totalsize(initial_boot_params));
}
+ /* Retrieve command line */
+ p = of_get_flat_dt_prop(node, "bootargs", &l);
+ if (p != NULL && l > 0)
+ strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE));
+
+handle_cmdline:
+ /*
+ * CONFIG_CMDLINE is meant to be a default in case nothing else
+ * managed to set the command line, unless CONFIG_CMDLINE_FORCE
+ * is set in which case we override whatever was found earlier.
+ */
+#ifdef CONFIG_CMDLINE
+#if defined(CONFIG_CMDLINE_EXTEND)
+ strlcat(cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#elif defined(CONFIG_CMDLINE_FORCE)
+ strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#else
+ /* No arguments from boot loader, use kernel's cmdl*/
+ if (!((char *)cmdline)[0])
+ strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#endif
+#endif /* CONFIG_CMDLINE */
+
+ pr_debug("Command line is: %s\n", (char *)cmdline);
+
return 0;
}
if (rc)
pr_warn("No chosen node found, continuing without\n");
- /*
- * CONFIG_CMDLINE is meant to be a default in case nothing else
- * managed to set the command line, unless CONFIG_CMDLINE_FORCE
- * is set in which case we override whatever was found earlier.
- */
-#ifdef CONFIG_CMDLINE
-#if defined(CONFIG_CMDLINE_EXTEND)
- strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
- strlcat(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#elif defined(CONFIG_CMDLINE_FORCE)
- strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#else
- /* No arguments from boot loader, use kernel's cmdl */
- if (!boot_command_line[0])
- strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif
-#endif /* CONFIG_CMDLINE */
-
- pr_debug("Command line is: %s\n", boot_command_line);
-
/* Setup memory, calling early_init_dt_add_memory_arch */
early_init_dt_scan_memory();
err = memblock_mark_nomap(base, size);
if (err)
memblock_phys_free(base, size);
- kmemleak_ignore_phys(base);
}
+ kmemleak_ignore_phys(base);
+
return err;
}
if (IS_ENABLED(CONFIG_PPC)) {
struct device_node *boot_display = NULL;
struct platform_device *dev;
+ int display_number = 0;
int ret;
/* Check if we have a MacOS display without a node spec */
if (!of_get_property(node, "linux,opened", NULL) ||
!of_get_property(node, "linux,boot-display", NULL))
continue;
- dev = of_platform_device_create(node, "of-display", NULL);
+ dev = of_platform_device_create(node, "of-display.0", NULL);
+ of_node_put(node);
if (WARN_ON(!dev))
return -ENOMEM;
boot_display = node;
+ display_number++;
break;
}
for_each_node_by_type(node, "display") {
+ char buf[14];
+ const char *of_display_format = "of-display.%d";
+
if (!of_get_property(node, "linux,opened", NULL) || node == boot_display)
continue;
- of_platform_device_create(node, "of-display", NULL);
+ ret = snprintf(buf, sizeof(buf), of_display_format, display_number++);
+ if (ret < sizeof(buf))
+ of_platform_device_create(node, buf, NULL);
}
} else {
/* We'll use a local copy of buf */
count = min_t(size_t, count, sizeof(in)-1);
- strncpy(in, buf, count);
- in[count] = '\0';
+ strscpy(in, buf, count + 1);
/* Let's clean up the target. 0xff is a blank pattern */
memset(&hwpath, 0xff, sizeof(hwpath));
/* We'll use a local copy of buf */
count = min_t(size_t, count, sizeof(in)-1);
- strncpy(in, buf, count);
- in[count] = '\0';
+ strscpy(in, buf, count + 1);
/* Let's clean up the target. 0 is a blank pattern */
memset(&layers, 0, sizeof(layers));
/* We'll use a local copy of buf */
count = min_t(size_t, count, sizeof(in)-1);
- strncpy(in, buf, count);
- in[count] = '\0';
+ strscpy(in, buf, count + 1);
/* Current flags are stored in primary boot path entry */
pathentry = &pdcspath_entry_primary;
config PCIE_BT1
tristate "Baikal-T1 PCIe controller"
depends on MIPS_BAIKAL_T1 || COMPILE_TEST
- depends on PCI_MSI_IRQ_DOMAIN
+ depends on PCI_MSI
select PCIE_DW_HOST
help
Enables support for the PCIe controller in the Baikal-T1 SoC to work
return i;
pci_save_ltr_state(dev);
- pci_save_aspm_l1ss_state(dev);
pci_save_dpc_state(dev);
pci_save_aer_state(dev);
pci_save_ptm_state(dev);
* LTR itself (in the PCIe capability).
*/
pci_restore_ltr_state(dev);
- pci_restore_aspm_l1ss_state(dev);
pci_restore_pcie_state(dev);
pci_restore_pasid_state(dev);
if (error)
pci_err(dev, "unable to allocate suspend buffer for LTR\n");
- error = pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_L1SS,
- 2 * sizeof(u32));
- if (error)
- pci_err(dev, "unable to allocate suspend buffer for ASPM-L1SS\n");
-
pci_allocate_vc_save_buffers(dev);
}
void pcie_aspm_init_link_state(struct pci_dev *pdev);
void pcie_aspm_exit_link_state(struct pci_dev *pdev);
void pcie_aspm_powersave_config_link(struct pci_dev *pdev);
-void pci_save_aspm_l1ss_state(struct pci_dev *dev);
-void pci_restore_aspm_l1ss_state(struct pci_dev *dev);
#else
static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { }
static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { }
static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { }
-static inline void pci_save_aspm_l1ss_state(struct pci_dev *dev) { }
-static inline void pci_restore_aspm_l1ss_state(struct pci_dev *dev) { }
#endif
#ifdef CONFIG_PCIE_ECRC
pci_write_config_dword(pdev, pos, val);
}
-static void aspm_program_l1ss(struct pci_dev *dev, u32 ctl1, u32 ctl2)
-{
- u16 l1ss = dev->l1ss;
- u32 l1_2_enable;
-
- /*
- * Per PCIe r6.0, sec 5.5.4, T_POWER_ON in PCI_L1SS_CTL2 must be
- * programmed prior to setting the L1.2 enable bits in PCI_L1SS_CTL1.
- */
- pci_write_config_dword(dev, l1ss + PCI_L1SS_CTL2, ctl2);
-
- /*
- * In addition, Common_Mode_Restore_Time and LTR_L1.2_THRESHOLD in
- * PCI_L1SS_CTL1 must be programmed *before* setting the L1.2
- * enable bits, even though they're all in PCI_L1SS_CTL1.
- */
- l1_2_enable = ctl1 & PCI_L1SS_CTL1_L1_2_MASK;
- ctl1 &= ~PCI_L1SS_CTL1_L1_2_MASK;
-
- pci_write_config_dword(dev, l1ss + PCI_L1SS_CTL1, ctl1);
- if (l1_2_enable)
- pci_write_config_dword(dev, l1ss + PCI_L1SS_CTL1,
- ctl1 | l1_2_enable);
-}
-
/* Calculate L1.2 PM substate timing parameters */
static void aspm_calc_l1ss_info(struct pcie_link_state *link,
u32 parent_l1ss_cap, u32 child_l1ss_cap)
u32 t_common_mode, t_power_on, l1_2_threshold, scale, value;
u32 ctl1 = 0, ctl2 = 0;
u32 pctl1, pctl2, cctl1, cctl2;
+ u32 pl1_2_enables, cl1_2_enables;
if (!(link->aspm_support & ASPM_STATE_L1_2_MASK))
return;
ctl2 == pctl2 && ctl2 == cctl2)
return;
- pctl1 &= ~(PCI_L1SS_CTL1_CM_RESTORE_TIME |
- PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
- PCI_L1SS_CTL1_LTR_L12_TH_SCALE);
- pctl1 |= (ctl1 & (PCI_L1SS_CTL1_CM_RESTORE_TIME |
- PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
- PCI_L1SS_CTL1_LTR_L12_TH_SCALE));
- aspm_program_l1ss(parent, pctl1, ctl2);
-
- cctl1 &= ~(PCI_L1SS_CTL1_CM_RESTORE_TIME |
- PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
- PCI_L1SS_CTL1_LTR_L12_TH_SCALE);
- cctl1 |= (ctl1 & (PCI_L1SS_CTL1_CM_RESTORE_TIME |
- PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
- PCI_L1SS_CTL1_LTR_L12_TH_SCALE));
- aspm_program_l1ss(child, cctl1, ctl2);
+ /* Disable L1.2 while updating. See PCIe r5.0, sec 5.5.4, 7.8.3.3 */
+ pl1_2_enables = pctl1 & PCI_L1SS_CTL1_L1_2_MASK;
+ cl1_2_enables = cctl1 & PCI_L1SS_CTL1_L1_2_MASK;
+
+ if (pl1_2_enables || cl1_2_enables) {
+ pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
+ PCI_L1SS_CTL1_L1_2_MASK, 0);
+ pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+ PCI_L1SS_CTL1_L1_2_MASK, 0);
+ }
+
+ /* Program T_POWER_ON times in both ports */
+ pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, ctl2);
+ pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2, ctl2);
+
+ /* Program Common_Mode_Restore_Time in upstream device */
+ pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+ PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
+
+ /* Program LTR_L1.2_THRESHOLD time in both ports */
+ pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+ PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+ PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
+ pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
+ PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+ PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
+
+ if (pl1_2_enables || cl1_2_enables) {
+ pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1, 0,
+ pl1_2_enables);
+ pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1, 0,
+ cl1_2_enables);
+ }
}
static void aspm_l1ss_init(struct pcie_link_state *link)
PCI_L1SS_CTL1_L1SS_MASK, val);
}
-void pci_save_aspm_l1ss_state(struct pci_dev *dev)
-{
- struct pci_cap_saved_state *save_state;
- u16 l1ss = dev->l1ss;
- u32 *cap;
-
- if (!l1ss)
- return;
-
- save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_L1SS);
- if (!save_state)
- return;
-
- cap = (u32 *)&save_state->cap.data[0];
- pci_read_config_dword(dev, l1ss + PCI_L1SS_CTL2, cap++);
- pci_read_config_dword(dev, l1ss + PCI_L1SS_CTL1, cap++);
-}
-
-void pci_restore_aspm_l1ss_state(struct pci_dev *dev)
-{
- struct pci_cap_saved_state *save_state;
- u32 *cap, ctl1, ctl2;
- u16 l1ss = dev->l1ss;
-
- if (!l1ss)
- return;
-
- save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_L1SS);
- if (!save_state)
- return;
-
- cap = (u32 *)&save_state->cap.data[0];
- ctl2 = *cap++;
- ctl1 = *cap;
- aspm_program_l1ss(dev, ctl1, ctl2);
-}
-
static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)
{
pcie_capability_clear_and_set_word(pdev, PCI_EXP_LNKCTL,
return err;
}
-static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+static void pcifront_xenbus_remove(struct xenbus_device *xdev)
{
struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
if (pdev)
free_pdev(pdev);
-
- return 0;
}
static const struct xenbus_device_id xenpci_ids[] = {
hw->dn++;
continue;
}
- hw->dtcs_used |= arm_cmn_node_to_xp(cmn, dn)->dtc;
hw->num_dns++;
if (bynodeid)
break;
nodeid, nid.x, nid.y, nid.port, nid.dev, type);
return -EINVAL;
}
+ /*
+ * Keep assuming non-cycles events count in all DTC domains; turns out
+ * it's hard to make a worthwhile optimisation around this, short of
+ * going all-in with domain-local counter allocation as well.
+ */
+ hw->dtcs_used = (1U << cmn->num_dtcs) - 1;
return arm_cmn_validate_group(cmn, event);
}
static bool armpmu_filter(struct pmu *pmu, int cpu)
{
struct arm_pmu *armpmu = to_arm_pmu(pmu);
- bool ret;
-
- ret = cpumask_test_cpu(cpu, &armpmu->supported_cpus);
- if (ret && armpmu->filter)
- return armpmu->filter(pmu, cpu);
-
- return ret;
+ return !cpumask_test_cpu(cpu, &armpmu->supported_cpus);
}
static ssize_t cpus_show(struct device *dev,
imx8_phy->perst =
devm_reset_control_get_exclusive(dev, "perst");
if (IS_ERR(imx8_phy->perst))
- dev_err_probe(dev, PTR_ERR(imx8_phy->perst),
+ return dev_err_probe(dev, PTR_ERR(imx8_phy->perst),
"Failed to get PCIE PHY PERST control\n");
}
struct gpio_desc *standby_gpio;
struct gpio_desc *enable_gpio;
u32 max_bitrate = 0;
+ int err;
can_transceiver_phy = devm_kzalloc(dev, sizeof(struct can_transceiver_phy), GFP_KERNEL);
if (!can_transceiver_phy)
return PTR_ERR(phy);
}
- device_property_read_u32(dev, "max-bitrate", &max_bitrate);
- if (!max_bitrate)
+ err = device_property_read_u32(dev, "max-bitrate", &max_bitrate);
+ if ((err != -EINVAL) && !max_bitrate)
dev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit\n");
phy->attrs.max_link_rate = max_bitrate;
HSPHY_INIT_CFG(0x90, 0x60, 0),
};
-static const struct hsphy_init_seq init_seq_mdm9607[] = {
- HSPHY_INIT_CFG(0x80, 0x44, 0),
- HSPHY_INIT_CFG(0x81, 0x38, 0),
- HSPHY_INIT_CFG(0x82, 0x24, 0),
- HSPHY_INIT_CFG(0x83, 0x13, 0),
-};
-
static const struct hsphy_data hsphy_data_femtophy = {
.init_seq = init_seq_femtophy,
.init_seq_num = ARRAY_SIZE(init_seq_femtophy),
};
-static const struct hsphy_data hsphy_data_mdm9607 = {
- .init_seq = init_seq_mdm9607,
- .init_seq_num = ARRAY_SIZE(init_seq_mdm9607),
-};
-
static const struct of_device_id qcom_snps_hsphy_match[] = {
{ .compatible = "qcom,usb-hs-28nm-femtophy", .data = &hsphy_data_femtophy, },
- { .compatible = "qcom,usb-hs-28nm-mdm9607", .data = &hsphy_data_mdm9607, },
{ },
};
MODULE_DEVICE_TABLE(of, qcom_snps_hsphy_match);
r8a779f0_eth_serdes_write32(channel->addr, 0x0160, 0x180, 0x0007);
r8a779f0_eth_serdes_write32(channel->addr, 0x01ac, 0x180, 0x0000);
r8a779f0_eth_serdes_write32(channel->addr, 0x00c4, 0x180, 0x0310);
- r8a779f0_eth_serdes_write32(channel->addr, 0x00c8, 0x380, 0x0101);
+ r8a779f0_eth_serdes_write32(channel->addr, 0x00c8, 0x180, 0x0101);
ret = r8a779f0_eth_serdes_reg_wait(channel, 0x00c8, 0x0180, BIT(0), 0);
if (ret)
return ret;
return ret;
ret = property_enable(base, &rport->port_cfg->phy_sus, false);
- if (ret)
+ if (ret) {
+ clk_disable_unprepare(rphy->clk480m);
return ret;
+ }
/* waiting for the utmi_clk to become stable */
usleep_range(1500, 2000);
return PTR_ERR(usbphy->phy_regs);
usbphy->moon4_res_mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, "moon4");
+ if (!usbphy->moon4_res_mem)
+ return -EINVAL;
+
usbphy->moon4_regs = devm_ioremap(&pdev->dev, usbphy->moon4_res_mem->start,
resource_size(usbphy->moon4_res_mem));
if (!usbphy->moon4_regs)
config PHY_AM654_SERDES
tristate "TI AM654 SERDES support"
- depends on OF && ARCH_K3 || COMPILE_TEST
+ depends on OF && (ARCH_K3 || COMPILE_TEST)
depends on COMMON_CLK
select GENERIC_PHY
select MULTIPLEXER
config PHY_J721E_WIZ
tristate "TI J721E WIZ (SERDES Wrapper) support"
- depends on OF && ARCH_K3 || COMPILE_TEST
+ depends on OF && (ARCH_K3 || COMPILE_TEST)
depends on HAS_IOMEM && OF_ADDRESS
depends on COMMON_CLK
select GENERIC_PHY
static int aspeed_sig_expr_disable(struct aspeed_pinmux_data *ctx,
const struct aspeed_sig_expr *expr)
{
+ int ret;
+
pr_debug("Disabling signal %s for %s\n", expr->signal,
expr->function);
- return aspeed_sig_expr_set(ctx, expr, false);
+ ret = aspeed_sig_expr_eval(ctx, expr, true);
+ if (ret < 0)
+ return ret;
+
+ if (ret)
+ return aspeed_sig_expr_set(ctx, expr, false);
+
+ return 0;
}
/**
int ret = 0;
if (!exprs)
- return true;
+ return -EINVAL;
while (*exprs && !ret) {
ret = aspeed_sig_expr_disable(ctx, *exprs);
EXPORT_SYMBOL_GPL(intel_pinctrl_get_soc_data);
#ifdef CONFIG_PM_SLEEP
+static bool __intel_gpio_is_direct_irq(u32 value)
+{
+ return (value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) &&
+ (__intel_gpio_get_gpio_mode(value) == PADCFG0_PMODE_GPIO);
+}
+
static bool intel_pinctrl_should_save(struct intel_pinctrl *pctrl, unsigned int pin)
{
const struct pin_desc *pd = pin_desc_get(pctrl->pctldev, pin);
* See https://bugzilla.kernel.org/show_bug.cgi?id=214749.
*/
value = readl(intel_get_padcfg(pctrl, pin, PADCFG0));
- if ((value & PADCFG0_GPIROUTIOXAPIC) && (value & PADCFG0_GPIOTXDIS) &&
- (__intel_gpio_get_gpio_mode(value) == PADCFG0_PMODE_GPIO))
+ if (__intel_gpio_is_direct_irq(value))
return true;
return false;
for (i = 0; i < pctrl->soc->npins; i++) {
const struct pinctrl_pin_desc *desc = &pctrl->soc->pins[i];
- if (!intel_pinctrl_should_save(pctrl, desc->number))
+ if (!(intel_pinctrl_should_save(pctrl, desc->number) ||
+ /*
+ * If the firmware mangled the register contents too much,
+ * check the saved value for the Direct IRQ mode.
+ */
+ __intel_gpio_is_direct_irq(pads[i].padcfg0)))
continue;
intel_restore_padcfg(pctrl, desc->number, PADCFG0, pads[i].padcfg0);
PIN_FIELD_BASE(10, 10, 4, 0x010, 0x10, 9, 3),
PIN_FIELD_BASE(11, 11, 4, 0x000, 0x10, 24, 3),
PIN_FIELD_BASE(12, 12, 4, 0x010, 0x10, 12, 3),
- PIN_FIELD_BASE(13, 13, 4, 0x010, 0x10, 27, 3),
+ PIN_FIELD_BASE(13, 13, 4, 0x000, 0x10, 27, 3),
PIN_FIELD_BASE(14, 14, 4, 0x010, 0x10, 15, 3),
PIN_FIELD_BASE(15, 15, 4, 0x010, 0x10, 0, 3),
PIN_FIELD_BASE(16, 16, 4, 0x010, 0x10, 18, 3),
PIN_FIELD_BASE(78, 78, 3, 0x000, 0x10, 15, 3),
PIN_FIELD_BASE(79, 79, 3, 0x000, 0x10, 18, 3),
PIN_FIELD_BASE(80, 80, 3, 0x000, 0x10, 21, 3),
- PIN_FIELD_BASE(81, 81, 3, 0x000, 0x10, 28, 3),
+ PIN_FIELD_BASE(81, 81, 3, 0x000, 0x10, 24, 3),
PIN_FIELD_BASE(82, 82, 3, 0x000, 0x10, 27, 3),
PIN_FIELD_BASE(83, 83, 3, 0x010, 0x10, 0, 3),
PIN_FIELD_BASE(84, 84, 3, 0x010, 0x10, 3, 3),
*/
#include <linux/kernel.h>
-#include <linux/gpio/driver.h>
#include <linux/pinctrl/pinctrl.h>
+
#include <linux/mfd/abx500/ab8500.h>
+
#include "pinctrl-abx500.h"
/* All the pins that can be used for GPIO and some other functions */
*/
#include <linux/kernel.h>
-#include <linux/gpio/driver.h>
#include <linux/pinctrl/pinctrl.h>
+
#include <linux/mfd/abx500/ab8500.h>
+
#include "pinctrl-abx500.h"
/* All the pins that can be used for GPIO and some other functions */
*
* Driver allows to use AxB5xx unused pins to be used as GPIO
*/
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/init.h>
+#include <linux/bitops.h>
#include <linux/err.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
#include <linux/gpio/driver.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
-#include <linux/interrupt.h>
-#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
#include <linux/mfd/abx500.h>
#include <linux/mfd/abx500/ab8500.h>
-#include <linux/pinctrl/pinctrl.h>
+
#include <linux/pinctrl/consumer.h>
-#include <linux/pinctrl/pinmux.h>
-#include <linux/pinctrl/pinconf.h>
-#include <linux/pinctrl/pinconf-generic.h>
#include <linux/pinctrl/machine.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
-#include "pinctrl-abx500.h"
#include "../core.h"
#include "../pinconf.h"
#include "../pinctrl-utils.h"
+#include "pinctrl-abx500.h"
+
/*
* GPIO registers offset
* Bank: 0x10
#ifndef PINCTRL_PINCTRL_ABx500_H
#define PINCTRL_PINCTRL_ABx500_H
+#include <linux/types.h>
+
+struct pinctrl_pin_desc;
+
/* Package definitions */
#define PINCTRL_AB8500 0
#define PINCTRL_AB8505 1
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
+#include <linux/types.h>
+
#include <linux/pinctrl/pinctrl.h>
+
#include "pinctrl-nomadik.h"
/* All the pins that can be used for GPIO and some other functions */
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
+#include <linux/types.h>
+
#include <linux/pinctrl/pinctrl.h>
+
#include "pinctrl-nomadik.h"
/* All the pins that can be used for GPIO and some other functions */
* Rewritten based on work by Prafulla WADASKAR <prafulla.wadaskar@st.com>
* Copyright (C) 2011-2013 Linus Walleij <linus.walleij@linaro.org>
*/
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
+#include <linux/bitops.h>
#include <linux/clk.h>
+#include <linux/device.h>
#include <linux/err.h>
#include <linux/gpio/driver.h>
-#include <linux/spinlock.h>
+#include <linux/init.h>
#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/of_device.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
#include <linux/of_address.h>
-#include <linux/bitops.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+/* Since we request GPIOs from ourself */
+#include <linux/pinctrl/consumer.h>
#include <linux/pinctrl/machine.h>
+#include <linux/pinctrl/pinconf.h>
#include <linux/pinctrl/pinctrl.h>
#include <linux/pinctrl/pinmux.h>
-#include <linux/pinctrl/pinconf.h>
-/* Since we request GPIOs from ourself */
-#include <linux/pinctrl/consumer.h>
-#include "pinctrl-nomadik.h"
+
#include "../core.h"
#include "../pinctrl-utils.h"
+#include "pinctrl-nomadik.h"
+
/*
* The GPIO module in the Nomadik family of Systems-on-Chip is an
* AMBA device, managing 32 pins and alternate functions. The logic block
return (afunc ? NMK_GPIO_ALT_A : 0) | (bfunc ? NMK_GPIO_ALT_B : 0);
}
-#include <linux/seq_file.h>
-
static void nmk_gpio_dbg_show_one(struct seq_file *s,
struct pinctrl_dev *pctldev, struct gpio_chip *chip,
unsigned offset, unsigned gpio)
#ifndef PINCTRL_PINCTRL_NOMADIK_H
#define PINCTRL_PINCTRL_NOMADIK_H
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include <linux/pinctrl/pinctrl.h>
+
/* Package definitions */
#define PINCTRL_NMK_STN8815 0
#define PINCTRL_NMK_DB8500 1
} else {
debounce_enable = " ∅";
+ time = 0;
}
snprintf(debounce_value, sizeof(debounce_value), "%u", time * unit);
seq_printf(s, "debounce %s (🕑 %sus)| ", debounce_enable, debounce_value);
RK_MUXROUTE_PMU(0, RK_PB5, 4, 0x0110, WRITE_MASK_VAL(3, 2, 1)), /* PWM1 IO mux M1 */
RK_MUXROUTE_PMU(0, RK_PC1, 1, 0x0110, WRITE_MASK_VAL(5, 4, 0)), /* PWM2 IO mux M0 */
RK_MUXROUTE_PMU(0, RK_PB6, 4, 0x0110, WRITE_MASK_VAL(5, 4, 1)), /* PWM2 IO mux M1 */
- RK_MUXROUTE_PMU(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PA1, 4, 0x0300, WRITE_MASK_VAL(0, 0, 1)), /* CAN0 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PA1, 3, 0x0300, WRITE_MASK_VAL(2, 2, 0)), /* CAN1 IO mux M0 */
RK_MUXROUTE_GRF(4, RK_PC3, 3, 0x0300, WRITE_MASK_VAL(2, 2, 1)), /* CAN1 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PB5, 3, 0x0300, WRITE_MASK_VAL(4, 4, 0)), /* CAN2 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PB2, 4, 0x0300, WRITE_MASK_VAL(4, 4, 1)), /* CAN2 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PC4, 1, 0x0300, WRITE_MASK_VAL(6, 6, 0)), /* HPDIN IO mux M0 */
- RK_MUXROUTE_PMU(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */
+ RK_MUXROUTE_GRF(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */
RK_MUXROUTE_GRF(3, RK_PB1, 3, 0x0300, WRITE_MASK_VAL(8, 8, 0)), /* GMAC1 IO mux M0 */
RK_MUXROUTE_GRF(4, RK_PA7, 3, 0x0300, WRITE_MASK_VAL(8, 8, 1)), /* GMAC1 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PD1, 1, 0x0300, WRITE_MASK_VAL(10, 10, 0)), /* HDMITX IO mux M0 */
- RK_MUXROUTE_PMU(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */
- RK_MUXROUTE_PMU(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */
+ RK_MUXROUTE_GRF(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */
RK_MUXROUTE_GRF(4, RK_PB4, 1, 0x0300, WRITE_MASK_VAL(14, 14, 1)), /* I2C2 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PA0, 1, 0x0304, WRITE_MASK_VAL(0, 0, 0)), /* I2C3 IO mux M0 */
RK_MUXROUTE_GRF(3, RK_PB6, 4, 0x0304, WRITE_MASK_VAL(0, 0, 1)), /* I2C3 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PC3, 1, 0x0308, WRITE_MASK_VAL(12, 12, 1)), /* PWM15 IO mux M1 */
RK_MUXROUTE_GRF(3, RK_PD2, 3, 0x0308, WRITE_MASK_VAL(14, 14, 0)), /* SDMMC2 IO mux M0 */
RK_MUXROUTE_GRF(3, RK_PA5, 5, 0x0308, WRITE_MASK_VAL(14, 14, 1)), /* SDMMC2 IO mux M1 */
- RK_MUXROUTE_PMU(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PD3, 3, 0x030c, WRITE_MASK_VAL(0, 0, 1)), /* SPI0 IO mux M1 */
RK_MUXROUTE_GRF(2, RK_PB5, 3, 0x030c, WRITE_MASK_VAL(2, 2, 0)), /* SPI1 IO mux M0 */
RK_MUXROUTE_GRF(3, RK_PC3, 3, 0x030c, WRITE_MASK_VAL(2, 2, 1)), /* SPI1 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PB3, 4, 0x030c, WRITE_MASK_VAL(6, 6, 0)), /* SPI3 IO mux M0 */
RK_MUXROUTE_GRF(4, RK_PC2, 2, 0x030c, WRITE_MASK_VAL(6, 6, 1)), /* SPI3 IO mux M1 */
RK_MUXROUTE_GRF(2, RK_PB4, 2, 0x030c, WRITE_MASK_VAL(8, 8, 0)), /* UART1 IO mux M0 */
- RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */
- RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */
+ RK_MUXROUTE_GRF(3, RK_PD6, 4, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */
+ RK_MUXROUTE_GRF(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */
RK_MUXROUTE_GRF(1, RK_PD5, 2, 0x030c, WRITE_MASK_VAL(10, 10, 1)), /* UART2 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PA1, 2, 0x030c, WRITE_MASK_VAL(12, 12, 0)), /* UART3 IO mux M0 */
RK_MUXROUTE_GRF(3, RK_PB7, 4, 0x030c, WRITE_MASK_VAL(12, 12, 1)), /* UART3 IO mux M1 */
RK_MUXROUTE_GRF(3, RK_PD6, 5, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PA0, 4, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */
RK_MUXROUTE_GRF(3, RK_PC4, 5, 0x0314, WRITE_MASK_VAL(1, 0, 2)), /* PDM IO mux M2 */
- RK_MUXROUTE_PMU(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PD0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 1)), /* PCIE20 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PB0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 2)), /* PCIE20 IO mux M2 */
- RK_MUXROUTE_PMU(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PD2, 4, 0x0314, WRITE_MASK_VAL(5, 4, 1)), /* PCIE30X1 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PA5, 4, 0x0314, WRITE_MASK_VAL(5, 4, 2)), /* PCIE30X1 IO mux M2 */
- RK_MUXROUTE_PMU(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PD4, 4, 0x0314, WRITE_MASK_VAL(7, 6, 1)), /* PCIE30X2 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PC2, 4, 0x0314, WRITE_MASK_VAL(7, 6, 2)), /* PCIE30X2 IO mux M2 */
};
case RK3308:
case RK3368:
case RK3399:
+ case RK3568:
case RK3588:
pull_type = bank->pull_type[pin_num / 8];
data >>= bit;
data &= (1 << RK3188_PULL_BITS_PER_PIN) - 1;
+ /*
+ * In the TRM, pull-up being 1 for everything except the GPIO0_D3-D6,
+ * where that pull up value becomes 3.
+ */
+ if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) {
+ if (data == 3)
+ data = 1;
+ }
return rockchip_pull_list[pull_type][data];
default:
}
}
/*
- * In the TRM, pull-up being 1 for everything except the GPIO0_D0-D6,
+ * In the TRM, pull-up being 1 for everything except the GPIO0_D3-D6,
* where that pull up value becomes 3.
*/
if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) {
if (!pcs->fmask)
return 0;
function = pinmux_generic_get_function(pctldev, fselector);
+ if (!function)
+ return -EINVAL;
func = function->data;
if (!func)
return -EINVAL;
static const char * const swr_tx_clk_groups[] = { "gpio0" };
static const char * const swr_tx_data_groups[] = { "gpio1", "gpio2", "gpio14" };
static const char * const swr_rx_clk_groups[] = { "gpio3" };
-static const char * const swr_rx_data_groups[] = { "gpio4", "gpio5", "gpio15" };
+static const char * const swr_rx_data_groups[] = { "gpio4", "gpio5" };
static const char * const dmic1_clk_groups[] = { "gpio6" };
static const char * const dmic1_data_groups[] = { "gpio7" };
static const char * const dmic2_clk_groups[] = { "gpio8" };
return 0;
}
-#ifdef CONFIG_DEBUG_FS
static void sppctl_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
{
const char *label;
seq_puts(s, "\n");
}
}
-#endif
static int sppctl_gpio_new(struct platform_device *pdev, struct sppctl_pdata *pctl)
{
gchip->get = sppctl_gpio_get;
gchip->set = sppctl_gpio_set;
gchip->set_config = sppctl_gpio_set_config;
-#ifdef CONFIG_DEBUG_FS
- gchip->dbg_show = sppctl_gpio_dbg_show;
-#endif
+ gchip->dbg_show = IS_ENABLED(CONFIG_DEBUG_FS) ?
+ sppctl_gpio_dbg_show : NULL;
gchip->base = -1;
gchip->ngpio = sppctl_gpio_list_sz;
gchip->names = sppctl_gpio_list_s;
return status;
status = ssam_request_sync_init(rqst, spec->flags);
- if (status)
+ if (status) {
+ ssam_request_sync_free(rqst);
return status;
+ }
ssam_request_sync_set_resp(rqst, rsp);
if (sshp_parse_command(dev, data, &command, &command_data))
return;
+ /*
+ * Check if the message was intended for us. If not, drop it.
+ *
+ * Note: We will need to change this to handle debug messages. On newer
+ * generation devices, these seem to be sent to tid_out=0x03. We as
+ * host can still receive them as they can be forwarded via an override
+ * option on SAM, but doing so does not change tid_out=0x00.
+ */
+ if (command->tid_out != 0x00) {
+ rtl_warn(rtl, "rtl: dropping message not intended for us (tid = %#04x)\n",
+ command->tid_out);
+ return;
+ }
+
if (ssh_rqid_is_event(get_unaligned_le16(&command->rqid)))
ssh_rtl_rx_event(rtl, command, &command_data);
else
config AMD_PMC
tristate "AMD SoC PMC driver"
depends on ACPI && PCI && RTC_CLASS
+ select SERIO
help
The driver provides support for AMD Power Management Controller
primarily responsible for S2Idle transactions that are driven from
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/rtc.h>
+#include <linux/serio.h>
#include <linux/suspend.h>
#include <linux/seq_file.h>
#include <linux/uaccess.h>
module_param(enable_stb, bool, 0644);
MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism");
+static bool disable_workarounds;
+module_param(disable_workarounds, bool, 0644);
+MODULE_PARM_DESC(disable_workarounds, "Disable workarounds for platform bugs");
+
static struct amd_pmc_dev pmc;
static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret);
static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf);
return -EINVAL;
}
+static int amd_pmc_czn_wa_irq1(struct amd_pmc_dev *pdev)
+{
+ struct device *d;
+ int rc;
+
+ if (!pdev->major) {
+ rc = amd_pmc_get_smu_version(pdev);
+ if (rc)
+ return rc;
+ }
+
+ if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65))
+ return 0;
+
+ d = bus_find_device_by_name(&serio_bus, NULL, "serio0");
+ if (!d)
+ return 0;
+ if (device_may_wakeup(d)) {
+ dev_info_once(d, "Disabling IRQ1 wakeup source to avoid platform firmware bug\n");
+ disable_irq_wake(1);
+ device_set_wakeup_enable(d, false);
+ }
+ put_device(d);
+
+ return 0;
+}
+
static int amd_pmc_verify_czn_rtc(struct amd_pmc_dev *pdev, u32 *arg)
{
struct rtc_device *rtc_device;
/* Reset and Start SMU logging - to monitor the s0i3 stats */
amd_pmc_setup_smu_logging(pdev);
- /* Activate CZN specific RTC functionality */
- if (pdev->cpu_id == AMD_CPU_ID_CZN) {
+ /* Activate CZN specific platform bug workarounds */
+ if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) {
rc = amd_pmc_verify_czn_rtc(pdev, &arg);
if (rc) {
dev_err(pdev->dev, "failed to set RTC: %d\n", rc);
.check = amd_pmc_s2idle_check,
.restore = amd_pmc_s2idle_restore,
};
+
+static int __maybe_unused amd_pmc_suspend_handler(struct device *dev)
+{
+ struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
+
+ if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) {
+ int rc = amd_pmc_czn_wa_irq1(pdev);
+
+ if (rc) {
+ dev_err(pdev->dev, "failed to adjust keyboard wakeup: %d\n", rc);
+ return rc;
+ }
+ }
+
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL);
+
#endif
static const struct pci_device_id pmc_pci_ids[] = {
if (enable_stb && (dev->cpu_id == AMD_CPU_ID_YC || dev->cpu_id == AMD_CPU_ID_CB)) {
err = amd_pmc_s2d_init(dev);
if (err)
- return err;
+ goto err_pci_dev_put;
}
platform_set_drvdata(pdev, dev);
.name = "amd_pmc",
.acpi_match_table = amd_pmc_acpi_ids,
.dev_groups = pmc_groups,
+#ifdef CONFIG_SUSPEND
+ .pm = &amd_pmc_pm,
+#endif
},
.probe = amd_pmc_probe,
.remove = amd_pmc_remove,
*/
if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) {
- int mode = amd_pmf_get_pprof_modes(dev);
-
- if (mode < 0)
- return mode;
-
dev_dbg(dev->dev, "resetting AMT thermals\n");
- amd_pmf_update_slider(dev, SLIDER_OP_SET, mode, NULL);
+ amd_pmf_set_sps_power_limits(dev);
}
return 0;
}
void amd_pmf_init_auto_mode(struct amd_pmf_dev *dev)
{
amd_pmf_load_defaults_auto_mode(dev);
- /* update the thermal limits for Automode */
- amd_pmf_set_automode(dev, config_store.current_mode, NULL);
amd_pmf_init_metrics_table(dev);
}
src = amd_pmf_cnqf_get_power_source(dev);
- if (dev->current_profile == PLATFORM_PROFILE_BALANCED) {
+ if (is_pprof_balanced(dev)) {
amd_pmf_set_cnqf(dev, src, config_store.current_mode, NULL);
} else {
/*
const char *buf, size_t count)
{
struct amd_pmf_dev *pdev = dev_get_drvdata(dev);
- int mode, result, src;
+ int result, src;
bool input;
- mode = amd_pmf_get_pprof_modes(pdev);
- if (mode < 0)
- return mode;
-
result = kstrtobool(buf, &input);
if (result)
return result;
src = amd_pmf_cnqf_get_power_source(pdev);
pdev->cnqf_enabled = input;
- if (pdev->cnqf_enabled && pdev->current_profile == PLATFORM_PROFILE_BALANCED) {
+ if (pdev->cnqf_enabled && is_pprof_balanced(pdev)) {
amd_pmf_set_cnqf(pdev, src, config_store.current_mode, NULL);
} else {
if (is_apmf_func_supported(pdev, APMF_FUNC_STATIC_SLIDER_GRANULAR))
- amd_pmf_update_slider(pdev, SLIDER_OP_SET, mode, NULL);
+ amd_pmf_set_sps_power_limits(pdev);
}
dev_dbg(pdev->dev, "Received CnQF %s\n", input ? "on" : "off");
dev->cnqf_enabled = amd_pmf_check_flags(dev);
/* update the thermal for CnQF */
- if (dev->cnqf_enabled && dev->current_profile == PLATFORM_PROFILE_BALANCED) {
+ if (dev->cnqf_enabled && is_pprof_balanced(dev)) {
src = amd_pmf_cnqf_get_power_source(dev);
amd_pmf_set_cnqf(dev, src, config_store.current_mode, NULL);
}
module_param(force_load, bool, 0444);
MODULE_PARM_DESC(force_load, "Force load this driver on supported older platforms (experimental)");
+static int amd_pmf_pwr_src_notify_call(struct notifier_block *nb, unsigned long event, void *data)
+{
+ struct amd_pmf_dev *pmf = container_of(nb, struct amd_pmf_dev, pwr_src_notifier);
+
+ if (event != PSY_EVENT_PROP_CHANGED)
+ return NOTIFY_OK;
+
+ if (is_apmf_func_supported(pmf, APMF_FUNC_AUTO_MODE) ||
+ is_apmf_func_supported(pmf, APMF_FUNC_DYN_SLIDER_DC) ||
+ is_apmf_func_supported(pmf, APMF_FUNC_DYN_SLIDER_AC)) {
+ if ((pmf->amt_enabled || pmf->cnqf_enabled) && is_pprof_balanced(pmf))
+ return NOTIFY_DONE;
+ }
+
+ amd_pmf_set_sps_power_limits(pmf);
+
+ return NOTIFY_OK;
+}
+
static int current_power_limits_show(struct seq_file *seq, void *unused)
{
struct amd_pmf_dev *dev = seq->private;
if (!dev->regbase)
return -ENOMEM;
+ mutex_init(&dev->lock);
+ mutex_init(&dev->update_mutex);
+
apmf_acpi_init(dev);
platform_set_drvdata(pdev, dev);
amd_pmf_init_features(dev);
apmf_install_handler(dev);
amd_pmf_dbgfs_register(dev);
- mutex_init(&dev->lock);
- mutex_init(&dev->update_mutex);
+ dev->pwr_src_notifier.notifier_call = amd_pmf_pwr_src_notify_call;
+ power_supply_reg_notifier(&dev->pwr_src_notifier);
+
dev_info(dev->dev, "registered PMF device successfully\n");
return 0;
{
struct amd_pmf_dev *dev = platform_get_drvdata(pdev);
- mutex_destroy(&dev->lock);
- mutex_destroy(&dev->update_mutex);
+ power_supply_unreg_notifier(&dev->pwr_src_notifier);
amd_pmf_deinit_features(dev);
apmf_acpi_deinit(dev);
amd_pmf_dbgfs_unregister(dev);
+ mutex_destroy(&dev->lock);
+ mutex_destroy(&dev->update_mutex);
kfree(dev->buf);
return 0;
}
struct mutex update_mutex; /* protects race between ACPI handler and metrics thread */
bool cnqf_enabled;
bool cnqf_supported;
+ struct notifier_block pwr_src_notifier;
};
struct apmf_sps_prop_granular {
void amd_pmf_deinit_sps(struct amd_pmf_dev *dev);
int apmf_get_static_slider_granular(struct amd_pmf_dev *pdev,
struct apmf_static_slider_granular_output *output);
+bool is_pprof_balanced(struct amd_pmf_dev *pmf);
int apmf_update_fan_idx(struct amd_pmf_dev *pdev, bool manual, u32 idx);
+int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf);
/* Auto Mode Layer */
int apmf_get_auto_mode_def(struct amd_pmf_dev *pdev, struct apmf_auto_mode *data);
}
}
+int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf)
+{
+ int mode;
+
+ mode = amd_pmf_get_pprof_modes(pmf);
+ if (mode < 0)
+ return mode;
+
+ amd_pmf_update_slider(pmf, SLIDER_OP_SET, mode, NULL);
+
+ return 0;
+}
+
+bool is_pprof_balanced(struct amd_pmf_dev *pmf)
+{
+ return (pmf->current_profile == PLATFORM_PROFILE_BALANCED) ? true : false;
+}
+
static int amd_pmf_profile_get(struct platform_profile_handler *pprof,
enum platform_profile_option *profile)
{
enum platform_profile_option profile)
{
struct amd_pmf_dev *pmf = container_of(pprof, struct amd_pmf_dev, pprof);
- int mode;
pmf->current_profile = profile;
- mode = amd_pmf_get_pprof_modes(pmf);
- if (mode < 0)
- return mode;
- amd_pmf_update_slider(pmf, SLIDER_OP_SET, mode, NULL);
- return 0;
+ return amd_pmf_set_sps_power_limits(pmf);
}
int amd_pmf_init_sps(struct amd_pmf_dev *dev)
dev->current_profile = PLATFORM_PROFILE_BALANCED;
amd_pmf_load_defaults_sps(dev);
+ /* update SPS balanced power mode thermals */
+ amd_pmf_set_sps_power_limits(dev);
+
dev->pprof.profile_get = amd_pmf_profile_get;
dev->pprof.profile_set = amd_pmf_profile_set;
static struct apple_gmux_data *apple_gmux_data;
-/*
- * gmux port offsets. Many of these are not yet used, but may be in the
- * future, and it's useful to have them documented here anyhow.
- */
-#define GMUX_PORT_VERSION_MAJOR 0x04
-#define GMUX_PORT_VERSION_MINOR 0x05
-#define GMUX_PORT_VERSION_RELEASE 0x06
-#define GMUX_PORT_SWITCH_DISPLAY 0x10
-#define GMUX_PORT_SWITCH_GET_DISPLAY 0x11
-#define GMUX_PORT_INTERRUPT_ENABLE 0x14
-#define GMUX_PORT_INTERRUPT_STATUS 0x16
-#define GMUX_PORT_SWITCH_DDC 0x28
-#define GMUX_PORT_SWITCH_EXTERNAL 0x40
-#define GMUX_PORT_SWITCH_GET_EXTERNAL 0x41
-#define GMUX_PORT_DISCRETE_POWER 0x50
-#define GMUX_PORT_MAX_BRIGHTNESS 0x70
-#define GMUX_PORT_BRIGHTNESS 0x74
-#define GMUX_PORT_VALUE 0xc2
-#define GMUX_PORT_READ 0xd0
-#define GMUX_PORT_WRITE 0xd4
-
-#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4)
-
#define GMUX_INTERRUPT_ENABLE 0xff
#define GMUX_INTERRUPT_DISABLE 0x00
gmux_pio_write32(gmux_data, port, val);
}
-static bool gmux_is_indexed(struct apple_gmux_data *gmux_data)
-{
- u16 val;
-
- outb(0xaa, gmux_data->iostart + 0xcc);
- outb(0x55, gmux_data->iostart + 0xcd);
- outb(0x00, gmux_data->iostart + 0xce);
-
- val = inb(gmux_data->iostart + 0xcc) |
- (inb(gmux_data->iostart + 0xcd) << 8);
-
- if (val == 0x55aa)
- return true;
-
- return false;
-}
-
/**
* DOC: Backlight control
*
int ret = -ENXIO;
acpi_status status;
unsigned long long gpe;
+ bool indexed = false;
+ u32 version;
if (apple_gmux_data)
return -EBUSY;
+ if (!apple_gmux_detect(pnp, &indexed)) {
+ pr_info("gmux device not present\n");
+ return -ENODEV;
+ }
+
gmux_data = kzalloc(sizeof(*gmux_data), GFP_KERNEL);
if (!gmux_data)
return -ENOMEM;
pnp_set_drvdata(pnp, gmux_data);
res = pnp_get_resource(pnp, IORESOURCE_IO, 0);
- if (!res) {
- pr_err("Failed to find gmux I/O resource\n");
- goto err_free;
- }
-
gmux_data->iostart = res->start;
gmux_data->iolen = resource_size(res);
- if (gmux_data->iolen < GMUX_MIN_IO_LEN) {
- pr_err("gmux I/O region too small (%lu < %u)\n",
- gmux_data->iolen, GMUX_MIN_IO_LEN);
- goto err_free;
- }
-
if (!request_region(gmux_data->iostart, gmux_data->iolen,
"Apple gmux")) {
pr_err("gmux I/O already in use\n");
goto err_free;
}
- /*
- * Invalid version information may indicate either that the gmux
- * device isn't present or that it's a new one that uses indexed
- * io
- */
-
- ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR);
- ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR);
- ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE);
- if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) {
- if (gmux_is_indexed(gmux_data)) {
- u32 version;
- mutex_init(&gmux_data->index_lock);
- gmux_data->indexed = true;
- version = gmux_read32(gmux_data,
- GMUX_PORT_VERSION_MAJOR);
- ver_major = (version >> 24) & 0xff;
- ver_minor = (version >> 16) & 0xff;
- ver_release = (version >> 8) & 0xff;
- } else {
- pr_info("gmux device not present\n");
- ret = -ENODEV;
- goto err_release;
- }
+ if (indexed) {
+ mutex_init(&gmux_data->index_lock);
+ gmux_data->indexed = true;
+ version = gmux_read32(gmux_data, GMUX_PORT_VERSION_MAJOR);
+ ver_major = (version >> 24) & 0xff;
+ ver_minor = (version >> 16) & 0xff;
+ ver_release = (version >> 8) & 0xff;
+ } else {
+ ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR);
+ ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR);
+ ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE);
}
pr_info("Found gmux version %d.%d.%d [%s]\n", ver_major, ver_minor,
ver_release, (gmux_data->indexed ? "indexed" : "classic"));
.tablet_switch_mode = asus_wmi_lid_flip_rog_devid,
};
+static struct quirk_entry quirk_asus_ignore_fan = {
+ .wmi_ignore_fan = true,
+};
+
static int dmi_matched(const struct dmi_system_id *dmi)
{
pr_info("Identified laptop model '%s'\n", dmi->ident);
},
.driver_data = &quirk_asus_tablet_mode,
},
+ {
+ .callback = dmi_matched,
+ .ident = "ASUS VivoBook E410MA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "E410MA"),
+ },
+ .driver_data = &quirk_asus_ignore_fan,
+ },
{},
};
{ KE_KEY, 0x30, { KEY_VOLUMEUP } },
{ KE_KEY, 0x31, { KEY_VOLUMEDOWN } },
{ KE_KEY, 0x32, { KEY_MUTE } },
+ { KE_KEY, 0x33, { KEY_SCREENLOCK } },
{ KE_KEY, 0x35, { KEY_SCREENLOCK } },
{ KE_KEY, 0x38, { KEY_PROG3 } }, /* Armoury Crate */
{ KE_KEY, 0x40, { KEY_PREVIOUSSONG } },
{ KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */
{ KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */
{ KE_KEY, 0x82, { KEY_CAMERA } },
+ { KE_KEY, 0x85, { KEY_CAMERA } },
{ KE_KEY, 0x86, { KEY_PROG1 } }, /* MyASUS Key */
{ KE_KEY, 0x88, { KEY_RFKILL } }, /* Radio Toggle Key */
{ KE_KEY, 0x8A, { KEY_PROG1 } }, /* Color enhancement mode */
int tablet_switch_event_code;
u32 tablet_switch_dev_id;
+ bool tablet_switch_inverted;
enum fan_type fan_type;
enum fan_type gpu_fan_type;
}
/* Input **********************************************************************/
+static void asus_wmi_tablet_sw_report(struct asus_wmi *asus, bool value)
+{
+ input_report_switch(asus->inputdev, SW_TABLET_MODE,
+ asus->tablet_switch_inverted ? !value : value);
+ input_sync(asus->inputdev);
+}
+
static void asus_wmi_tablet_sw_init(struct asus_wmi *asus, u32 dev_id, int event_code)
{
struct device *dev = &asus->platform_device->dev;
result = asus_wmi_get_devstate_simple(asus, dev_id);
if (result >= 0) {
input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE);
- input_report_switch(asus->inputdev, SW_TABLET_MODE, result);
+ asus_wmi_tablet_sw_report(asus, result);
asus->tablet_switch_dev_id = dev_id;
asus->tablet_switch_event_code = event_code;
} else if (result == -ENODEV) {
case asus_wmi_no_tablet_switch:
break;
case asus_wmi_kbd_dock_devid:
+ asus->tablet_switch_inverted = true;
asus_wmi_tablet_sw_init(asus, ASUS_WMI_DEVID_KBD_DOCK, NOTIFY_KBD_DOCK_CHANGE);
break;
case asus_wmi_lid_flip_devid:
return;
result = asus_wmi_get_devstate_simple(asus, asus->tablet_switch_dev_id);
- if (result >= 0) {
- input_report_switch(asus->inputdev, SW_TABLET_MODE, result);
- input_sync(asus->inputdev);
- }
+ if (result >= 0)
+ asus_wmi_tablet_sw_report(asus, result);
}
/* dGPU ********************************************************************/
asus->fan_type = FAN_TYPE_NONE;
asus->agfn_pwm = -1;
- if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL))
+ if (asus->driver->quirks->wmi_ignore_fan)
+ asus->fan_type = FAN_TYPE_NONE;
+ else if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL))
asus->fan_type = FAN_TYPE_SPEC83;
else if (asus_wmi_has_agfn_fan(asus))
asus->fan_type = FAN_TYPE_AGFN;
*available = false;
+ if (asus->fan_type == FAN_TYPE_NONE)
+ return 0;
+
err = fan_curve_get_factory_default(asus, fan_dev);
if (err) {
return 0;
bool store_backlight_power;
bool wmi_backlight_set_devstate;
bool wmi_force_als_set;
+ bool wmi_ignore_fan;
enum asus_wmi_tablet_switch_mode tablet_switch_mode;
int wapf;
/*
{ KE_KEY, 0x57, { KEY_BRIGHTNESSDOWN } },
{ KE_KEY, 0x58, { KEY_BRIGHTNESSUP } },
+ /*Speaker Mute*/
+ { KE_KEY, 0x109, { KEY_MUTE} },
+
/* Mic mute */
{ KE_KEY, 0x150, { KEY_MICMUTE } },
/* privacy mic mute */
{ KE_KEY, 0x0001, { KEY_MICMUTE } },
/* privacy camera mute */
- { KE_SW, 0x0002, { SW_CAMERA_LENS_COVER } },
+ { KE_VSW, 0x0002, { SW_CAMERA_LENS_COVER } },
{ KE_END, 0},
};
switch (code) {
case DELL_PRIVACY_AUDIO_EVENT: /* Mic mute */
- case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */
priv->last_status = status;
sparse_keymap_report_entry(priv->input_dev, key, 1, true);
ret = true;
break;
+ case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */
+ priv->last_status = status;
+ sparse_keymap_report_entry(priv->input_dev, key, !(status & CAMERA_STATUS), false);
+ ret = true;
+ break;
default:
dev_dbg(&priv->wdev->dev, "unknown event type 0x%04x 0x%04x\n", type, code);
}
{
struct privacy_wmi_data *priv;
struct key_entry *keymap;
- int ret, i;
+ int ret, i, j;
ret = wmi_has_guid(DELL_PRIVACY_GUID);
if (!ret)
dev_set_drvdata(&wdev->dev, priv);
priv->wdev = wdev;
+
+ ret = get_current_status(priv->wdev);
+ if (ret)
+ return ret;
+
/* create evdev passing interface */
priv->input_dev = devm_input_allocate_device(&wdev->dev);
if (!priv->input_dev)
/* remap the keymap code with Dell privacy key type 0x12 as prefix
* KEY_MICMUTE scancode will be reported as 0x120001
*/
- for (i = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) {
- keymap[i] = dell_wmi_keymap_type_0012[i];
- keymap[i].code |= (0x0012 << 16);
+ for (i = 0, j = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) {
+ /*
+ * Unlike keys where only presses matter, userspace may act
+ * on switches in both of their positions. Only register
+ * SW_CAMERA_LENS_COVER if it is actually there.
+ */
+ if (dell_wmi_keymap_type_0012[i].type == KE_VSW &&
+ dell_wmi_keymap_type_0012[i].sw.code == SW_CAMERA_LENS_COVER &&
+ !(priv->features_present & BIT(DELL_PRIVACY_TYPE_CAMERA)))
+ continue;
+
+ keymap[j] = dell_wmi_keymap_type_0012[i];
+ keymap[j].code |= (0x0012 << 16);
+ j++;
}
ret = sparse_keymap_setup(priv->input_dev, keymap, NULL);
kfree(keymap);
priv->input_dev->name = "Dell Privacy Driver";
priv->input_dev->id.bustype = BUS_HOST;
- ret = input_register_device(priv->input_dev);
- if (ret)
- return ret;
+ /* Report initial camera-cover status */
+ if (priv->features_present & BIT(DELL_PRIVACY_TYPE_CAMERA))
+ input_report_switch(priv->input_dev, SW_CAMERA_LENS_COVER,
+ !(priv->last_status & CAMERA_STATUS));
- ret = get_current_status(priv->wdev);
+ ret = input_register_device(priv->input_dev);
if (ret)
return ret;
static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = {
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H-CF"),
+ DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H WIFI-CF"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE AX V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"),
HPWMI_PEAKSHIFT_PERIOD = 0x0F,
HPWMI_BATTERY_CHARGE_PERIOD = 0x10,
HPWMI_SANITIZATION_MODE = 0x17,
+ HPWMI_OMEN_KEY = 0x1D,
HPWMI_SMART_EXPERIENCE_APP = 0x21,
};
{ KE_KEY, 0x213b, { KEY_INFO } },
{ KE_KEY, 0x2169, { KEY_ROTATE_DISPLAY } },
{ KE_KEY, 0x216a, { KEY_SETUP } },
+ { KE_KEY, 0x21a5, { KEY_PROG2 } }, /* HP Omen Key */
+ { KE_KEY, 0x21a7, { KEY_FN_ESC } },
{ KE_KEY, 0x21a9, { KEY_TOUCHPAD_OFF } },
{ KE_KEY, 0x121a9, { KEY_TOUCHPAD_ON } },
{ KE_KEY, 0x231b, { KEY_HELP } },
static int hp_wmi_set_block(void *data, bool blocked)
{
- enum hp_wmi_radio r = (enum hp_wmi_radio) data;
+ enum hp_wmi_radio r = (long)data;
int query = BIT(r + 8) | ((!blocked) << r);
int ret;
case HPWMI_SMART_ADAPTER:
break;
case HPWMI_BEZEL_BUTTON:
+ case HPWMI_OMEN_KEY:
key_code = hp_wmi_read_int(HPWMI_HOTKEY_QUERY);
if (key_code < 0)
break;
DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion R7000P2020H"),
}
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion 5 15ARH05"),
+ }
+ },
{}
};
return PTR_ERR(int3472->regulator.gpio);
}
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->regulator.gpio, 0);
+
cfg.dev = &int3472->adev->dev;
cfg.init_data = &init_data;
cfg.ena_gpiod = int3472->regulator.gpio;
return (PTR_ERR(gpio));
int3472->clock.ena_gpio = gpio;
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->clock.ena_gpio, 0);
break;
case INT3472_GPIO_TYPE_PRIVACY_LED:
gpio = acpi_get_and_request_gpiod(path, pin, "int3472,privacy-led");
return (PTR_ERR(gpio));
int3472->clock.led_gpio = gpio;
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->clock.led_gpio, 0);
break;
default:
dev_err(int3472->dev, "Invalid GPIO type 0x%02x for clock\n", type);
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, adl_core_init),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, adl_core_init),
X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, mtl_core_init),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, mtl_core_init),
{}
};
.quirks = VSEC_QUIRK_NO_DVSEC | VSEC_QUIRK_EARLY_HW,
};
+/* MTL info */
+static const struct intel_vsec_platform_info mtl_info = {
+ .quirks = VSEC_QUIRK_NO_WATCHER | VSEC_QUIRK_NO_CRASHLOG,
+};
+
#define PCI_DEVICE_ID_INTEL_VSEC_ADL 0x467d
#define PCI_DEVICE_ID_INTEL_VSEC_DG1 0x490e
+#define PCI_DEVICE_ID_INTEL_VSEC_MTL_M 0x7d0d
+#define PCI_DEVICE_ID_INTEL_VSEC_MTL_S 0xad0d
#define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM 0x09a7
#define PCI_DEVICE_ID_INTEL_VSEC_RPL 0xa77d
#define PCI_DEVICE_ID_INTEL_VSEC_TGL 0x9a0d
static const struct pci_device_id intel_vsec_pci_ids[] = {
{ PCI_DEVICE_DATA(INTEL, VSEC_ADL, &tgl_info) },
{ PCI_DEVICE_DATA(INTEL, VSEC_DG1, &dg1_info) },
+ { PCI_DEVICE_DATA(INTEL, VSEC_MTL_M, &mtl_info) },
+ { PCI_DEVICE_DATA(INTEL, VSEC_MTL_S, &mtl_info) },
{ PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM, &(struct intel_vsec_platform_info) {}) },
{ PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) },
{ PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) },
{SIMATIC_IPC_IPC427D, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_NONE},
{SIMATIC_IPC_IPC427E, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_427E},
{SIMATIC_IPC_IPC477E, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_427E},
- {SIMATIC_IPC_IPC427G, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G},
+ {SIMATIC_IPC_IPCBX_39A, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G},
+ {SIMATIC_IPC_IPCPX_39A, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_227G},
};
static int register_platform_devices(u32 station_id)
break;
}
- ret = sony_call_snc_handle(handle, probe_base, &result);
- if (ret)
- return ret;
+ /*
+ * Only probe if there is a separate probe_base, otherwise the probe call
+ * is equivalent to __sony_nc_kbd_backlight_mode_set(0), resulting in
+ * the keyboard backlight being turned off.
+ */
+ if (probe_base) {
+ ret = sony_call_snc_handle(handle, probe_base, &result);
+ if (ret)
+ return ret;
- if ((handle == 0x0137 && !(result & 0x02)) ||
- !(result & 0x01)) {
- dprintk("no backlight keyboard found\n");
- return 0;
+ if ((handle == 0x0137 && !(result & 0x02)) ||
+ !(result & 0x01)) {
+ dprintk("no backlight keyboard found\n");
+ return 0;
+ }
}
kbdbl_ctl = kzalloc(sizeof(*kbdbl_ctl), GFP_KERNEL);
static enum led_brightness light_sysfs_get(struct led_classdev *led_cdev)
{
- return (light_get_status() == 1) ? LED_FULL : LED_OFF;
+ return (light_get_status() == 1) ? LED_ON : LED_OFF;
}
static struct tpacpi_led_classdev tpacpi_led_thinklight = {
static int dytc_capabilities;
static bool dytc_mmc_get_available;
-static int convert_dytc_to_profile(int dytcmode, enum platform_profile_option *profile)
+static int convert_dytc_to_profile(int funcmode, int dytcmode,
+ enum platform_profile_option *profile)
{
- if (dytc_capabilities & BIT(DYTC_FC_MMC)) {
+ switch (funcmode) {
+ case DYTC_FUNCTION_MMC:
switch (dytcmode) {
case DYTC_MODE_MMC_LOWPOWER:
*profile = PLATFORM_PROFILE_LOW_POWER;
return -EINVAL;
}
return 0;
- }
- if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
+ case DYTC_FUNCTION_PSC:
switch (dytcmode) {
case DYTC_MODE_PSC_LOWPOWER:
*profile = PLATFORM_PROFILE_LOW_POWER;
default: /* Unknown mode */
return -EINVAL;
}
+ return 0;
+ case DYTC_FUNCTION_AMT:
+ /* For now return balanced. It's the closest we have to 'auto' */
+ *profile = PLATFORM_PROFILE_BALANCED;
+ return 0;
+ default:
+ /* Unknown function */
+ return -EOPNOTSUPP;
}
return 0;
}
if (err)
goto unlock;
}
- }
- if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
+ } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
err = dytc_command(DYTC_SET_COMMAND(DYTC_FUNCTION_PSC, perfmode, 1), &output);
if (err)
goto unlock;
+
/* system supports AMT, activate it when on balanced */
if (dytc_capabilities & BIT(DYTC_FC_AMT))
dytc_control_amt(profile == PLATFORM_PROFILE_BALANCED);
{
enum platform_profile_option profile;
int output, err = 0;
- int perfmode;
+ int perfmode, funcmode;
mutex_lock(&dytc_mutex);
if (dytc_capabilities & BIT(DYTC_FC_MMC)) {
err = dytc_command(DYTC_CMD_MMC_GET, &output);
else
err = dytc_cql_command(DYTC_CMD_GET, &output);
- } else if (dytc_capabilities & BIT(DYTC_FC_PSC))
+ funcmode = DYTC_FUNCTION_MMC;
+ } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
err = dytc_command(DYTC_CMD_GET, &output);
-
+ /* Check if we are PSC mode, or have AMT enabled */
+ funcmode = (output >> DYTC_GET_FUNCTION_BIT) & 0xF;
+ }
mutex_unlock(&dytc_mutex);
if (err)
return;
perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF;
- convert_dytc_to_profile(perfmode, &profile);
+ convert_dytc_to_profile(funcmode, perfmode, &profile);
if (profile != dytc_current_profile) {
dytc_current_profile = profile;
platform_profile_notify();
.properties = connect_tablet9_props,
};
+static const struct property_entry csl_panther_tab_hd_props[] = {
+ PROPERTY_ENTRY_U32("touchscreen-min-x", 1),
+ PROPERTY_ENTRY_U32("touchscreen-min-y", 20),
+ PROPERTY_ENTRY_U32("touchscreen-size-x", 1980),
+ PROPERTY_ENTRY_U32("touchscreen-size-y", 1526),
+ PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+ PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"),
+ PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-csl-panther-tab-hd.fw"),
+ PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+ { }
+};
+
+static const struct ts_dmi_data csl_panther_tab_hd_data = {
+ .acpi_name = "MSSL1680:00",
+ .properties = csl_panther_tab_hd_props,
+};
+
static const struct property_entry cube_iwork8_air_props[] = {
PROPERTY_ENTRY_U32("touchscreen-min-x", 1),
PROPERTY_ENTRY_U32("touchscreen-min-y", 3),
DMI_MATCH(DMI_BIOS_DATE, "05/07/2016"),
},
},
+ {
+ /* Chuwi Vi8 (CWI501) */
+ .driver_data = (void *)&chuwi_vi8_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "i86"),
+ DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.W86JLBNR01"),
+ },
+ },
{
/* Chuwi Vi8 (CWI506) */
.driver_data = (void *)&chuwi_vi8_data,
DMI_MATCH(DMI_PRODUCT_NAME, "Tablet 9"),
},
},
+ {
+ /* CSL Panther Tab HD */
+ .driver_data = (void *)&csl_panther_tab_hd_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "CSL Computer GmbH & Co. KG"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "CSL Panther Tab HD"),
+ },
+ },
{
/* CUBE iwork8 Air */
.driver_data = (void *)&cube_iwork8_air_data,
chip->chip_irq = i2c->irq;
+ ret = da9211_regulator_init(chip);
+ if (ret < 0) {
+ dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret);
+ return ret;
+ }
+
if (chip->chip_irq != 0) {
ret = devm_request_threaded_irq(chip->dev, chip->chip_irq, NULL,
da9211_irq_handler,
dev_warn(chip->dev, "No IRQ configured\n");
}
- ret = da9211_regulator_init(chip);
-
- if (ret < 0)
- dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret);
-
return ret;
}
RPMH_VREG("ldo8", "ldo%s8", &pmic5_pldo_lv, "vdd-l8-l9"),
RPMH_VREG("ldo9", "ldo%s9", &pmic5_pldo, "vdd-l8-l9"),
RPMH_VREG("ldo10", "ldo%s10", &pmic5_nldo, "vdd-l1-l4-l10"),
- RPMH_VREG("ldo11", "ldo%s11", &pmic5_pldo, "vdd-l11"),
+ RPMH_VREG("ldo11", "ldo%s11", &pmic5_nldo, "vdd-l11"),
RPMH_VREG("ldo12", "ldo%s12", &pmic5_pldo, "vdd-l12"),
RPMH_VREG("ldo13", "ldo%s13", &pmic5_pldo, "vdd-l2-l13-l14"),
RPMH_VREG("ldo14", "ldo%s14", &pmic5_pldo, "vdd-l2-l13-l14"),
config RESET_TI_SCI
tristate "TI System Control Interface (TI-SCI) reset driver"
- depends on TI_SCI_PROTOCOL || COMPILE_TEST
+ depends on TI_SCI_PROTOCOL || (COMPILE_TEST && TI_SCI_PROTOCOL=n)
help
This enables the reset driver support over TI System Control Interface
available on some new TI's SoCs. If you wish to use reset resources
struct device *dev = &pdev->dev;
struct uniphier_glue_reset_priv *priv;
struct resource *res;
- resource_size_t size;
int i, ret;
priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
return -EINVAL;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- size = resource_size(res);
priv->rdata.membase = devm_ioremap_resource(dev, res);
if (IS_ERR(priv->rdata.membase))
return PTR_ERR(priv->rdata.membase);
spin_lock_init(&priv->rdata.lock);
priv->rdata.rcdev.owner = THIS_MODULE;
- priv->rdata.rcdev.nr_resets = size * BITS_PER_BYTE;
+ priv->rdata.rcdev.nr_resets = resource_size(res) * BITS_PER_BYTE;
priv->rdata.rcdev.ops = &reset_simple_ops;
priv->rdata.rcdev.of_node = dev->of_node;
priv->rdata.active_low = true;
static int efi_procfs(struct device *dev, struct seq_file *seq)
{
- efi_time_t eft, alm;
- efi_time_cap_t cap;
- efi_bool_t enabled, pending;
+ efi_time_t eft, alm;
+ efi_time_cap_t cap;
+ efi_bool_t enabled, pending;
+ struct rtc_device *rtc = dev_get_drvdata(dev);
memset(&eft, 0, sizeof(eft));
memset(&alm, 0, sizeof(alm));
/* XXX fixme: convert to string? */
seq_printf(seq, "Timezone\t: %u\n", eft.timezone);
- seq_printf(seq,
- "Alarm Time\t: %u:%u:%u.%09u\n"
- "Alarm Date\t: %u-%u-%u\n"
- "Alarm Daylight\t: %u\n"
- "Enabled\t\t: %s\n"
- "Pending\t\t: %s\n",
- alm.hour, alm.minute, alm.second, alm.nanosecond,
- alm.year, alm.month, alm.day,
- alm.daylight,
- enabled == 1 ? "yes" : "no",
- pending == 1 ? "yes" : "no");
-
- if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE)
- seq_puts(seq, "Timezone\t: unspecified\n");
- else
- /* XXX fixme: convert to string? */
- seq_printf(seq, "Timezone\t: %u\n", alm.timezone);
+ if (test_bit(RTC_FEATURE_ALARM, rtc->features)) {
+ seq_printf(seq,
+ "Alarm Time\t: %u:%u:%u.%09u\n"
+ "Alarm Date\t: %u-%u-%u\n"
+ "Alarm Daylight\t: %u\n"
+ "Enabled\t\t: %s\n"
+ "Pending\t\t: %s\n",
+ alm.hour, alm.minute, alm.second, alm.nanosecond,
+ alm.year, alm.month, alm.day,
+ alm.daylight,
+ enabled == 1 ? "yes" : "no",
+ pending == 1 ? "yes" : "no");
+
+ if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE)
+ seq_puts(seq, "Timezone\t: unspecified\n");
+ else
+ /* XXX fixme: convert to string? */
+ seq_printf(seq, "Timezone\t: %u\n", alm.timezone);
+ }
/*
* now prints the capabilities
rtc->ops = &efi_rtc_ops;
clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features);
- set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features);
+ if (efi_rt_services_supported(EFI_RT_SUPPORTED_WAKEUP_SERVICES))
+ set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features);
+ else
+ clear_bit(RTC_FEATURE_ALARM, rtc->features);
device_init_wakeup(&dev->dev, true);
if (IS_ERR(sp_rtc->reg_base))
return dev_err_probe(&plat_dev->dev, PTR_ERR(sp_rtc->reg_base),
"%s devm_ioremap_resource fail\n", RTC_REG_NAME);
- dev_dbg(&plat_dev->dev, "res = 0x%x, reg_base = 0x%lx\n",
- sp_rtc->res->start, (unsigned long)sp_rtc->reg_base);
+ dev_dbg(&plat_dev->dev, "res = %pR, reg_base = %p\n",
+ sp_rtc->res, sp_rtc->reg_base);
sp_rtc->irq = platform_get_irq(plat_dev, 0);
if (sp_rtc->irq < 0)
unsigned long bytes_done;
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
bytes_done = 0;
dev_info = bio->bi_bdev->bd_disk->private_data;
switch (card->options.isolation) {
case ISOLATION_MODE_NONE:
- return snprintf(buf, 6, "%s\n", ATTR_QETH_ISOLATION_NONE);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_NONE);
case ISOLATION_MODE_FWD:
- return snprintf(buf, 9, "%s\n", ATTR_QETH_ISOLATION_FWD);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_FWD);
case ISOLATION_MODE_DROP:
- return snprintf(buf, 6, "%s\n", ATTR_QETH_ISOLATION_DROP);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_DROP);
default:
- return snprintf(buf, 5, "%s\n", "N/A");
+ return sysfs_emit(buf, "%s\n", "N/A");
}
}
struct qeth_card *card = dev_get_drvdata(dev);
if (card->info.hwtrap)
- return snprintf(buf, 5, "arm\n");
+ return sysfs_emit(buf, "arm\n");
else
- return snprintf(buf, 8, "disarm\n");
+ return sysfs_emit(buf, "disarm\n");
}
static ssize_t qeth_hw_trap_store(struct device *dev,
*
* Returns true if and only if alua_rtpg_work() will be called asynchronously.
* That function is responsible for calling @qdata->fn().
+ *
+ * Context: may be called from atomic context (alua_check()) only if the caller
+ * holds an sdev reference.
*/
static bool alua_rtpg_queue(struct alua_port_group *pg,
struct scsi_device *sdev,
int start_queue = 0;
unsigned long flags;
- might_sleep();
-
if (WARN_ON_ONCE(!pg) || scsi_device_get(sdev))
return false;
static void hisi_sas_slot_index_free(struct hisi_hba *hisi_hba, int slot_idx)
{
if (hisi_hba->hw->slot_index_alloc ||
- slot_idx >= HISI_SAS_UNRESERVED_IPTT) {
+ slot_idx < HISI_SAS_RESERVED_IPTT) {
spin_lock(&hisi_hba->lock);
hisi_sas_slot_index_clear(hisi_hba, slot_idx);
spin_unlock(&hisi_hba->lock);
int_to_scsilun(0, &lun);
while (retry-- > 0) {
- rc = sas_clear_task_set(device, lun.scsi_lun);
+ rc = sas_abort_task_set(device, lun.scsi_lun);
if (rc == TMF_RESP_FUNC_COMPLETE) {
hisi_sas_release_task(hisi_hba, device);
break;
device->linkrate = phy->sas_phy.linkrate;
hisi_hba->hw->setup_itct(hisi_hba, sas_dev);
- } else
+ } else if (!port->port_attached)
port->id = 0xff;
}
}
{
struct Scsi_Host *sh;
- sh = scsi_host_alloc(&hpsa_driver_template, sizeof(h));
+ sh = scsi_host_alloc(&hpsa_driver_template, sizeof(struct ctlr_info));
if (sh == NULL) {
dev_err(&h->pdev->dev, "scsi_host_alloc failed\n");
return -ENOMEM;
enum iscsi_host_param param, char *buf)
{
struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(shost);
- struct iscsi_session *session = tcp_sw_host->session;
+ struct iscsi_session *session;
struct iscsi_conn *conn;
struct iscsi_tcp_conn *tcp_conn;
struct iscsi_sw_tcp_conn *tcp_sw_conn;
switch (param) {
case ISCSI_HOST_PARAM_IPADDRESS:
+ session = tcp_sw_host->session;
if (!session)
return -ENOTCONN;
if (!cls_session)
goto remove_host;
session = cls_session->dd_data;
- tcp_sw_host = iscsi_host_priv(shost);
- tcp_sw_host->session = session;
if (iscsi_tcp_r2tpool_alloc(session))
goto remove_session;
+
+ /* We are now fully setup so expose the session to sysfs. */
+ tcp_sw_host = iscsi_host_priv(shost);
+ tcp_sw_host->session = session;
return cls_session;
remove_session:
if (WARN_ON_ONCE(session->leadconn))
return;
+ iscsi_session_remove(cls_session);
+ /*
+ * Our get_host_param needs to access the session, so remove the
+ * host from sysfs before freeing the session to make sure userspace
+ * is no longer accessing the callout.
+ */
+ iscsi_host_remove(shost, false);
+
iscsi_tcp_r2tpool_free(cls_session->dd_data);
- iscsi_session_teardown(cls_session);
- iscsi_host_remove(shost, false);
+ iscsi_session_free(cls_session);
iscsi_host_free(shost);
}
}
EXPORT_SYMBOL_GPL(iscsi_session_setup);
-/**
- * iscsi_session_teardown - destroy session, host, and cls_session
- * @cls_session: iscsi session
+/*
+ * issi_session_remove - Remove session from iSCSI class.
*/
-void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
+void iscsi_session_remove(struct iscsi_cls_session *cls_session)
{
struct iscsi_session *session = cls_session->dd_data;
- struct module *owner = cls_session->transport->owner;
struct Scsi_Host *shost = session->host;
iscsi_remove_session(cls_session);
+ /*
+ * host removal only has to wait for its children to be removed from
+ * sysfs, and iscsi_tcp needs to do iscsi_host_remove before freeing
+ * the session, so drop the session count here.
+ */
+ iscsi_host_dec_session_cnt(shost);
+}
+EXPORT_SYMBOL_GPL(iscsi_session_remove);
+
+/**
+ * iscsi_session_free - Free iscsi session and it's resources
+ * @cls_session: iscsi session
+ */
+void iscsi_session_free(struct iscsi_cls_session *cls_session)
+{
+ struct iscsi_session *session = cls_session->dd_data;
+ struct module *owner = cls_session->transport->owner;
iscsi_pool_free(&session->cmdpool);
kfree(session->password);
kfree(session->discovery_parent_type);
iscsi_free_session(cls_session);
-
- iscsi_host_dec_session_cnt(shost);
module_put(owner);
}
+EXPORT_SYMBOL_GPL(iscsi_session_free);
+
+/**
+ * iscsi_session_teardown - destroy session and cls_session
+ * @cls_session: iscsi session
+ */
+void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
+{
+ iscsi_session_remove(cls_session);
+ iscsi_session_free(cls_session);
+}
EXPORT_SYMBOL_GPL(iscsi_session_teardown);
/**
{
struct ata_port *ap = device->sata_dev.ap;
struct ata_link *link = &ap->link;
+ unsigned long flags;
+ spin_lock_irqsave(ap->lock, flags);
device->sata_dev.fis[2] = ATA_ERR | ATA_DRDY; /* tf status */
device->sata_dev.fis[3] = ATA_ABORTED; /* tf error */
if (force_reset)
link->eh_info.action |= ATA_EH_RESET;
ata_link_abort(link);
+ spin_unlock_irqrestore(ap->lock, flags);
}
EXPORT_SYMBOL_GPL(sas_ata_device_link_abort);
# mpi3mr makefile
-obj-m += mpi3mr.o
+obj-$(CONFIG_SCSI_MPI3MR) += mpi3mr.o
mpi3mr-y += mpi3mr_os.o \
mpi3mr_fw.o \
mpi3mr_app.o \
int i, retval = 0, capb = 0;
u16 message_control;
u64 dma_mask = mrioc->dma_mask ? mrioc->dma_mask :
- (((dma_get_required_mask(&pdev->dev) > DMA_BIT_MASK(32)) &&
- (sizeof(dma_addr_t) > 4)) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32));
+ ((sizeof(dma_addr_t) > 4) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32));
if (pci_enable_device_mem(pdev)) {
ioc_err(mrioc, "pci_enable_device_mem: failed\n");
struct sysinfo s;
u64 coherent_dma_mask, dma_mask;
- if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 ||
- dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) {
+ if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4) {
ioc->dma_mask = 32;
coherent_dma_mask = dma_mask = DMA_BIT_MASK(32);
/* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */
{
struct module *mod = sdev->host->hostt->module;
- might_sleep();
-
put_device(&sdev->sdev_gendev);
module_put(mod);
}
put_unaligned_be64(sdebug_write_same_length, &arr[32]);
return 0x3c; /* Mandatory page length for Logical Block Provisioning */
-
- return sizeof(vpdb0_data);
}
/* Block device characteristics VPD page (SBC-3) */
struct Scsi_Host *shost = sdev->host;
unsigned long flags;
+ if (!shost->hostt->eh_abort_handler) {
+ /* No abort handler, fail command directly */
+ return FAILED;
+ }
+
if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) {
/*
* Retry after abort failed, escalate to next level.
* that no LUN is present, so don't add sdev in these cases.
* Two specific examples are:
* 1) NetApp targets: return PQ=1, PDT=0x1f
- * 2) IBM/2145 targets: return PQ=1, PDT=0
- * 3) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved"
+ * 2) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved"
* in the UFI 1.0 spec (we cannot rely on reserved bits).
*
* References:
* PDT=00h Direct-access device (floppy)
* PDT=1Fh none (no FDD connected to the requested logical unit)
*/
- if (((result[0] >> 5) == 1 ||
- (starget->pdt_1f_for_no_lun && (result[0] & 0x1f) == 0x1f)) &&
+ if (((result[0] >> 5) == 1 || starget->pdt_1f_for_no_lun) &&
+ (result[0] & 0x1f) == 0x1f &&
!scsi_is_wlun(lun)) {
SCSI_LOG_SCAN_BUS(3, sdev_printk(KERN_INFO, sdev,
"scsi scan: peripheral device type"
struct scsi_vpd *vpd_pgb0 = NULL, *vpd_pgb1 = NULL, *vpd_pgb2 = NULL;
unsigned long flags;
+ might_sleep();
+
scsi_dh_release_device(sdev);
parent = sdev->sdev_gendev.parent;
return name;
}
+static char *iscsi_session_target_state_name[] = {
+ [ISCSI_SESSION_TARGET_UNBOUND] = "UNBOUND",
+ [ISCSI_SESSION_TARGET_ALLOCATED] = "ALLOCATED",
+ [ISCSI_SESSION_TARGET_SCANNED] = "SCANNED",
+ [ISCSI_SESSION_TARGET_UNBINDING] = "UNBINDING",
+};
+
int iscsi_session_chkready(struct iscsi_cls_session *session)
{
int err;
if ((scan_data->channel == SCAN_WILD_CARD ||
scan_data->channel == 0) &&
(scan_data->id == SCAN_WILD_CARD ||
- scan_data->id == id))
+ scan_data->id == id)) {
scsi_scan_target(&session->dev, 0, id,
scan_data->lun, scan_data->rescan);
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_SCANNED;
+ spin_unlock_irqrestore(&session->lock, flags);
+ }
}
user_scan_exit:
struct iscsi_cls_host *ihost = shost->shost_data;
unsigned long flags;
unsigned int target_id;
+ bool remove_target = true;
ISCSI_DBG_TRANS_SESSION(session, "Unbinding session\n");
/* Prevent new scans and make sure scanning is not in progress */
mutex_lock(&ihost->mutex);
spin_lock_irqsave(&session->lock, flags);
- if (session->target_id == ISCSI_MAX_TARGET) {
+ if (session->target_state == ISCSI_SESSION_TARGET_ALLOCATED) {
+ remove_target = false;
+ } else if (session->target_state != ISCSI_SESSION_TARGET_SCANNED) {
spin_unlock_irqrestore(&session->lock, flags);
mutex_unlock(&ihost->mutex);
- goto unbind_session_exit;
+ ISCSI_DBG_TRANS_SESSION(session,
+ "Skipping target unbinding: Session is unbound/unbinding.\n");
+ return;
}
+ session->target_state = ISCSI_SESSION_TARGET_UNBINDING;
target_id = session->target_id;
session->target_id = ISCSI_MAX_TARGET;
spin_unlock_irqrestore(&session->lock, flags);
mutex_unlock(&ihost->mutex);
- scsi_remove_target(&session->dev);
+ if (remove_target)
+ scsi_remove_target(&session->dev);
if (session->ida_used)
ida_free(&iscsi_sess_ida, target_id);
-unbind_session_exit:
iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION);
ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n");
+
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_UNBOUND;
+ spin_unlock_irqrestore(&session->lock, flags);
}
static void __iscsi_destroy_session(struct work_struct *work)
session->ida_used = true;
} else
session->target_id = target_id;
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_ALLOCATED;
+ spin_unlock_irqrestore(&session->lock, flags);
dev_set_name(&session->dev, "session%u", session->sid);
err = device_add(&session->dev);
iscsi_session_attr(discovery_parent_idx, ISCSI_PARAM_DISCOVERY_PARENT_IDX, 0);
iscsi_session_attr(discovery_parent_type, ISCSI_PARAM_DISCOVERY_PARENT_TYPE, 0);
+static ssize_t
+show_priv_session_target_state(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct iscsi_cls_session *session = iscsi_dev_to_session(dev->parent);
+
+ return sysfs_emit(buf, "%s\n",
+ iscsi_session_target_state_name[session->target_state]);
+}
+
+static ISCSI_CLASS_ATTR(priv_sess, target_state, S_IRUGO,
+ show_priv_session_target_state, NULL);
+
static ssize_t
show_priv_session_state(struct device *dev, struct device_attribute *attr,
char *buf)
&dev_attr_sess_boot_target.attr,
&dev_attr_priv_sess_recovery_tmo.attr,
&dev_attr_priv_sess_state.attr,
+ &dev_attr_priv_sess_target_state.attr,
&dev_attr_priv_sess_creator.attr,
&dev_attr_sess_chap_out_idx.attr,
&dev_attr_sess_chap_in_idx.attr,
return S_IRUGO | S_IWUSR;
else if (attr == &dev_attr_priv_sess_state.attr)
return S_IRUGO;
+ else if (attr == &dev_attr_priv_sess_target_state.attr)
+ return S_IRUGO;
else if (attr == &dev_attr_priv_sess_creator.attr)
return S_IRUGO;
else if (attr == &dev_attr_priv_sess_target_id.attr)
ret = storvsc_do_io(dev, cmd_request, get_cpu());
put_cpu();
+ if (ret)
+ scsi_dma_unmap(scmnd);
+
if (ret == -EAGAIN) {
/* no more space */
ret = SCSI_MLQUEUE_DEVICE_BUSY;
return err;
}
-static int scsifront_remove(struct xenbus_device *dev)
+static void scsifront_remove(struct xenbus_device *dev)
{
struct vscsifrnt_info *info = dev_get_drvdata(&dev->dev);
scsifront_free_ring(info);
scsi_host_put(info->host);
-
- return 0;
}
static void scsifront_disconnect(struct vscsifrnt_info *info)
break;
case IMX8MP_HDMIBLK_PD_LCDIF:
regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0,
- BIT(7) | BIT(16) | BIT(17) | BIT(18) |
+ BIT(16) | BIT(17) | BIT(18) |
BIT(19) | BIT(20));
regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(11));
regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0,
regmap_set_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(1));
break;
case IMX8MP_HDMIBLK_PD_HDMI_TX_PHY:
+ regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(7));
regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(22) | BIT(24));
regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(12));
regmap_clear_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(3));
BIT(4) | BIT(5) | BIT(6));
regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(11));
regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0,
- BIT(7) | BIT(16) | BIT(17) | BIT(18) |
+ BIT(16) | BIT(17) | BIT(18) |
BIT(19) | BIT(20));
break;
case IMX8MP_HDMIBLK_PD_PAI:
case IMX8MP_HDMIBLK_PD_HDMI_TX_PHY:
regmap_set_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(3));
regmap_clear_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(12));
+ regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(7));
regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(22) | BIT(24));
break;
case IMX8MP_HDMIBLK_PD_HDCP:
ret = PTR_ERR(domain->power_dev);
goto cleanup_pds;
}
- dev_set_name(domain->power_dev, "%s", data->name);
domain->genpd.name = data->name;
domain->genpd.power_on = imx8mp_blk_ctrl_power_on;
ocotp_base = of_iomap(np, 0);
WARN_ON(!ocotp_base);
clk = of_clk_get_by_name(np, NULL);
- if (!clk) {
- WARN_ON(!clk);
+ if (IS_ERR(clk)) {
+ WARN_ON(IS_ERR(clk));
return 0;
}
goto out;
}
+ /* Protection domain is optional, it does not exist on older platforms */
ret = of_property_read_string_index(np, "qcom,protection-domain",
1, &adev->service_path);
- if (ret < 0) {
+ if (ret < 0 && ret != -EINVAL) {
dev_err(dev, "Failed to read second value of qcom,protection-domain\n");
goto out;
}
ret = of_genpd_add_provider_simple(dev->of_node, &drv->pd);
if (ret)
- return ret;
+ goto err_remove_genpd;
platform_set_drvdata(pdev, drv);
cpr_debugfs_init(drv);
return 0;
+
+err_remove_genpd:
+ pm_genpd_remove(&drv->pd);
+ return ret;
}
static int cpr_remove(struct platform_device *pdev)
#define CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op) ( \
FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_DCNT_H, \
((op)->data.nbytes >> 16) & 0xffff) | \
- FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, (op)->dummy.nbytes * 8))
+ FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, \
+ (op)->dummy.buswidth != 0 ? \
+ (((op)->dummy.nbytes * 8) / (op)->dummy.buswidth) : \
+ 0))
#define CDNS_XSPI_CMD_FLD_DSEQ_CMD_4(op, chipsel) ( \
FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R4_BANK, chipsel) | \
* will be adjusted at the final stage of the IRQ-based SPI transfer
* execution so not to lose the leftover of the incoming data.
*/
- level = min_t(u16, dws->fifo_len / 2, dws->tx_len);
+ level = min_t(unsigned int, dws->fifo_len / 2, dws->tx_len);
dw_writel(dws, DW_SPI_TXFTLR, level);
dw_writel(dws, DW_SPI_RXFTLR, level - 1);
dev_notice(dev, "SPI dma_set_mask(%d) failed, ret:%d\n",
addr_bits, ret);
+ ret = devm_request_irq(dev, irq, mtk_spi_interrupt,
+ IRQF_TRIGGER_NONE, dev_name(dev), master);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to register irq\n");
+
pm_runtime_enable(dev);
ret = devm_spi_register_master(dev, master);
return dev_err_probe(dev, ret, "failed to register master\n");
}
- ret = devm_request_irq(dev, irq, mtk_spi_interrupt,
- IRQF_TRIGGER_NONE, dev_name(dev), master);
- if (ret) {
- pm_runtime_disable(dev);
- return dev_err_probe(dev, ret, "failed to register irq\n");
- }
-
return 0;
}
/*-------------------------------------------------------------------------*/
#if defined(CONFIG_OF)
+static void of_spi_parse_dt_cs_delay(struct device_node *nc,
+ struct spi_delay *delay, const char *prop)
+{
+ u32 value;
+
+ if (!of_property_read_u32(nc, prop, &value)) {
+ if (value > U16_MAX) {
+ delay->value = DIV_ROUND_UP(value, 1000);
+ delay->unit = SPI_DELAY_UNIT_USECS;
+ } else {
+ delay->value = value;
+ delay->unit = SPI_DELAY_UNIT_NSECS;
+ }
+ }
+}
+
static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
struct device_node *nc)
{
u32 value;
- u16 cs_setup;
int rc;
/* Mode (clock phase/polarity/etc.) */
if (!of_property_read_u32(nc, "spi-max-frequency", &value))
spi->max_speed_hz = value;
- if (!of_property_read_u16(nc, "spi-cs-setup-ns", &cs_setup)) {
- spi->cs_setup.value = cs_setup;
- spi->cs_setup.unit = SPI_DELAY_UNIT_NSECS;
- }
+ /* Device CS delays */
+ of_spi_parse_dt_cs_delay(nc, &spi->cs_setup, "spi-cs-setup-delay-ns");
return 0;
}
struct spidev_data {
dev_t devt;
- spinlock_t spi_lock;
+ struct mutex spi_lock;
struct spi_device *spi;
struct list_head device_entry;
/*-------------------------------------------------------------------------*/
+static ssize_t
+spidev_sync_unlocked(struct spi_device *spi, struct spi_message *message)
+{
+ ssize_t status;
+
+ status = spi_sync(spi, message);
+ if (status == 0)
+ status = message->actual_length;
+
+ return status;
+}
+
static ssize_t
spidev_sync(struct spidev_data *spidev, struct spi_message *message)
{
- int status;
+ ssize_t status;
struct spi_device *spi;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spidev->spi;
- spin_unlock_irq(&spidev->spi_lock);
if (spi == NULL)
status = -ESHUTDOWN;
else
- status = spi_sync(spi, message);
+ status = spidev_sync_unlocked(spi, message);
- if (status == 0)
- status = message->actual_length;
+ mutex_unlock(&spidev->spi_lock);
return status;
}
spi_message_add_tail(k_tmp, &msg);
}
- status = spidev_sync(spidev, &msg);
+ status = spidev_sync_unlocked(spidev->spi, &msg);
if (status < 0)
goto done;
* we issue this ioctl.
*/
spidev = filp->private_data;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spi_dev_get(spidev->spi);
- spin_unlock_irq(&spidev->spi_lock);
-
- if (spi == NULL)
+ if (spi == NULL) {
+ mutex_unlock(&spidev->spi_lock);
return -ESHUTDOWN;
+ }
/* use the buffer lock here for triple duty:
* - prevent I/O (from us) so calling spi_setup() is safe;
mutex_unlock(&spidev->buf_lock);
spi_dev_put(spi);
+ mutex_unlock(&spidev->spi_lock);
return retval;
}
* we issue this ioctl.
*/
spidev = filp->private_data;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spi_dev_get(spidev->spi);
- spin_unlock_irq(&spidev->spi_lock);
-
- if (spi == NULL)
+ if (spi == NULL) {
+ mutex_unlock(&spidev->spi_lock);
return -ESHUTDOWN;
+ }
/* SPI_IOC_MESSAGE needs the buffer locked "normally" */
mutex_lock(&spidev->buf_lock);
done:
mutex_unlock(&spidev->buf_lock);
spi_dev_put(spi);
+ mutex_unlock(&spidev->spi_lock);
return retval;
}
if (!spidev->tx_buffer) {
spidev->tx_buffer = kmalloc(bufsiz, GFP_KERNEL);
if (!spidev->tx_buffer) {
- dev_dbg(&spidev->spi->dev, "open/ENOMEM\n");
status = -ENOMEM;
goto err_find_dev;
}
if (!spidev->rx_buffer) {
spidev->rx_buffer = kmalloc(bufsiz, GFP_KERNEL);
if (!spidev->rx_buffer) {
- dev_dbg(&spidev->spi->dev, "open/ENOMEM\n");
status = -ENOMEM;
goto err_alloc_rx_buf;
}
spidev = filp->private_data;
filp->private_data = NULL;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
/* ... after we unbound from the underlying device? */
dofree = (spidev->spi == NULL);
- spin_unlock_irq(&spidev->spi_lock);
+ mutex_unlock(&spidev->spi_lock);
/* last close? */
spidev->users--;
/* Initialize the driver data */
spidev->spi = spi;
- spin_lock_init(&spidev->spi_lock);
+ mutex_init(&spidev->spi_lock);
mutex_init(&spidev->buf_lock);
INIT_LIST_HEAD(&spidev->device_entry);
/* prevent new opens */
mutex_lock(&device_list_lock);
/* make sure ops on existing fds can abort cleanly */
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spidev->spi = NULL;
- spin_unlock_irq(&spidev->spi_lock);
+ mutex_unlock(&spidev->spi_lock);
list_del(&spidev->device_entry);
device_destroy(spidev_class, spidev->devt);
struct vchiq_instance;
-extern enum vchiq_status vchiq_initialise(struct vchiq_instance **pinstance);
+extern int vchiq_initialise(struct vchiq_instance **pinstance);
extern enum vchiq_status vchiq_shutdown(struct vchiq_instance *instance);
extern enum vchiq_status vchiq_connect(struct vchiq_instance *instance);
extern enum vchiq_status vchiq_open_service(struct vchiq_instance *instance,
extern void
vchiq_dump_service_use_state(struct vchiq_state *state);
-extern enum vchiq_status
+extern int
vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service,
enum USE_TYPE_E use_type);
-extern enum vchiq_status
+extern int
vchiq_release_internal(struct vchiq_state *state,
struct vchiq_service *service);
{
struct se_session *sess = se_cmd->se_sess;
- assert_spin_locked(&sess->sess_cmd_lock);
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_held(&sess->sess_cmd_lock);
+
/*
* If command already reached CMD_T_COMPLETE state within
* target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown,
int trip, int *temp)
{
struct int34x_thermal_zone *d = zone->devdata;
- int i;
+ int i, ret = 0;
if (d->override_ops && d->override_ops->get_trip_temp)
return d->override_ops->get_trip_temp(zone, trip, temp);
+ mutex_lock(&d->trip_mutex);
+
if (trip < d->aux_trip_nr)
*temp = d->aux_trips[trip];
else if (trip == d->crt_trip_id)
}
}
if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT)
- return -EINVAL;
+ ret = -EINVAL;
}
- return 0;
+ mutex_unlock(&d->trip_mutex);
+
+ return ret;
}
static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone,
enum thermal_trip_type *type)
{
struct int34x_thermal_zone *d = zone->devdata;
- int i;
+ int i, ret = 0;
if (d->override_ops && d->override_ops->get_trip_type)
return d->override_ops->get_trip_type(zone, trip, type);
+ mutex_lock(&d->trip_mutex);
+
if (trip < d->aux_trip_nr)
*type = THERMAL_TRIP_PASSIVE;
else if (trip == d->crt_trip_id)
}
}
if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT)
- return -EINVAL;
+ ret = -EINVAL;
}
- return 0;
+ mutex_unlock(&d->trip_mutex);
+
+ return ret;
}
static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone,
int trip_cnt = int34x_zone->aux_trip_nr;
int i;
+ mutex_lock(&int34x_zone->trip_mutex);
+
int34x_zone->crt_trip_id = -1;
if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_CRT",
&int34x_zone->crt_temp))
int34x_zone->act_trips[i].valid = true;
}
+ mutex_unlock(&int34x_zone->trip_mutex);
+
return trip_cnt;
}
EXPORT_SYMBOL_GPL(int340x_thermal_read_trips);
if (!int34x_thermal_zone)
return ERR_PTR(-ENOMEM);
+ mutex_init(&int34x_thermal_zone->trip_mutex);
+
int34x_thermal_zone->adev = adev;
int34x_thermal_zone->override_ops = override_ops;
acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
kfree(int34x_thermal_zone->aux_trips);
err_trip_alloc:
+ mutex_destroy(&int34x_thermal_zone->trip_mutex);
kfree(int34x_thermal_zone);
return ERR_PTR(ret);
}
thermal_zone_device_unregister(int34x_thermal_zone->zone);
acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
kfree(int34x_thermal_zone->aux_trips);
+ mutex_destroy(&int34x_thermal_zone->trip_mutex);
kfree(int34x_thermal_zone);
}
EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove);
struct thermal_zone_device_ops *override_ops;
void *priv_data;
struct acpi_lpat_conversion_table *lpat_table;
+ struct mutex trip_mutex;
};
struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *,
RFIM_SHOW(rfi_restriction_run_busy, 1)
RFIM_SHOW(rfi_restriction_err_code, 1)
RFIM_SHOW(rfi_restriction_data_rate, 1)
+RFIM_SHOW(rfi_restriction_data_rate_base, 1)
RFIM_SHOW(ddr_data_rate_point_0, 1)
RFIM_SHOW(ddr_data_rate_point_1, 1)
RFIM_SHOW(ddr_data_rate_point_2, 1)
RFIM_STORE(rfi_restriction_run_busy, 1)
RFIM_STORE(rfi_restriction_err_code, 1)
RFIM_STORE(rfi_restriction_data_rate, 1)
+RFIM_STORE(rfi_restriction_data_rate_base, 1)
RFIM_STORE(rfi_disable, 1)
static DEVICE_ATTR_RW(rfi_restriction_run_busy);
static DEVICE_ATTR_RW(rfi_restriction_err_code);
static DEVICE_ATTR_RW(rfi_restriction_data_rate);
+static DEVICE_ATTR_RW(rfi_restriction_data_rate_base);
static DEVICE_ATTR_RO(ddr_data_rate_point_0);
static DEVICE_ATTR_RO(ddr_data_rate_point_1);
static DEVICE_ATTR_RO(ddr_data_rate_point_2);
&dev_attr_rfi_restriction_run_busy.attr,
&dev_attr_rfi_restriction_err_code.attr,
&dev_attr_rfi_restriction_data_rate.attr,
+ &dev_attr_rfi_restriction_data_rate_base.attr,
&dev_attr_ddr_data_rate_point_0.attr,
&dev_attr_ddr_data_rate_point_1.attr,
&dev_attr_ddr_data_rate_point_2.attr,
cdev->devdata = devdata;
ret = cdev->ops->get_max_state(cdev, &cdev->max_state);
- if (ret)
- goto out_kfree_type;
+ if (ret) {
+ kfree(cdev->type);
+ goto out_ida_remove;
+ }
thermal_cooling_device_setup_sysfs(cdev);
+
ret = dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
if (ret) {
+ kfree(cdev->type);
thermal_cooling_device_destroy_sysfs(cdev);
- goto out_kfree_type;
+ goto out_ida_remove;
}
+
ret = device_register(&cdev->device);
if (ret)
goto out_kfree_type;
thermal_cooling_device_destroy_sysfs(cdev);
kfree(cdev->type);
put_device(&cdev->device);
+
+ /* thermal_release() takes care of the rest */
cdev = NULL;
out_ida_remove:
ida_free(&thermal_cdev_ida, id);
{
u32 status[TB_MAX_RETIMER_INDEX + 1] = {};
int ret, i, last_idx = 0;
- struct usb4_port *usb4;
-
- usb4 = port->usb4;
- if (!usb4)
- return 0;
-
- pm_runtime_get_sync(&usb4->dev);
/*
* Send broadcast RT to make sure retimer indices facing this
*/
ret = usb4_port_enumerate_retimers(port);
if (ret)
- goto out;
+ return ret;
/*
* Enable sideband channel for each retimer. We can do this
break;
}
- if (!last_idx) {
- ret = 0;
- goto out;
- }
+ if (!last_idx)
+ return 0;
/* Add on-board retimers if they do not exist already */
+ ret = 0;
for (i = 1; i <= last_idx; i++) {
struct tb_retimer *rt;
}
}
-out:
- pm_runtime_mark_last_busy(&usb4->dev);
- pm_runtime_put_autosuspend(&usb4->dev);
-
return ret;
}
* Downstream switch is reachable through two ports.
* Only scan on the primary port (link_nr == 0).
*/
+
+ if (port->usb4)
+ pm_runtime_get_sync(&port->usb4->dev);
+
if (tb_wait_for_port(port, false) <= 0)
- return;
+ goto out_rpm_put;
if (port->remote) {
tb_port_dbg(port, "port already has a remote\n");
- return;
+ goto out_rpm_put;
}
tb_retimer_scan(port, true);
*/
if (PTR_ERR(sw) == -EIO || PTR_ERR(sw) == -EADDRNOTAVAIL)
tb_scan_xdomain(port);
- return;
+ goto out_rpm_put;
}
if (tb_switch_configure(sw)) {
tb_switch_put(sw);
- return;
+ goto out_rpm_put;
}
/*
if (tb_switch_add(sw)) {
tb_switch_put(sw);
- return;
+ goto out_rpm_put;
}
/* Link the switches using both links if available */
tb_add_dp_resources(sw);
tb_scan_switch(sw);
+
+out_rpm_put:
+ if (port->usb4) {
+ pm_runtime_mark_last_busy(&port->usb4->dev);
+ pm_runtime_put_autosuspend(&port->usb4->dev);
+ }
}
static void tb_deactivate_and_free_tunnel(struct tb_tunnel *tunnel)
return;
} else if (!ret) {
/* Use maximum link rate if the link valid is not set */
- ret = usb4_usb3_port_max_link_rate(tunnel->src_port);
+ ret = tb_usb3_max_link_rate(tunnel->dst_port, tunnel->src_port);
if (ret < 0) {
tb_tunnel_warn(tunnel, "failed to read maximum link rate\n");
return;
* registered, we notify the userspace that it has changed.
*/
if (!update) {
- struct tb_port *port;
+ /*
+ * Now disable lane 1 if bonding was not enabled. Do
+ * this only if bonding was possible at the beginning
+ * (that is we are the connection manager and there are
+ * two lanes).
+ */
+ if (xd->bonding_possible) {
+ struct tb_port *port;
- /* Now disable lane 1 if bonding was not enabled */
- port = tb_port_at(xd->route, tb_xdomain_parent(xd));
- if (!port->bonded)
- tb_port_disable(port->dual_link_port);
+ port = tb_port_at(xd->route, tb_xdomain_parent(xd));
+ if (!port->bonded)
+ tb_port_disable(port->dual_link_port);
+ }
if (device_add(&xd->dev)) {
dev_err(&xd->dev, "failed to add XDomain device\n");
static struct xencons_info *vtermno_to_xencons(int vtermno)
{
- struct xencons_info *entry, *n, *ret = NULL;
+ struct xencons_info *entry, *ret = NULL;
+ unsigned long flags;
- if (list_empty(&xenconsoles))
- return NULL;
+ spin_lock_irqsave(&xencons_lock, flags);
+ if (list_empty(&xenconsoles)) {
+ spin_unlock_irqrestore(&xencons_lock, flags);
+ return NULL;
+ }
- list_for_each_entry_safe(entry, n, &xenconsoles, list) {
+ list_for_each_entry(entry, &xenconsoles, list) {
if (entry->vtermno == vtermno) {
ret = entry;
break;
}
}
+ spin_unlock_irqrestore(&xencons_lock, flags);
return ret;
}
{
int r;
uint64_t v = 0;
- unsigned long gfn;
+ unsigned long gfn, flags;
struct xencons_info *info;
if (!xen_hvm_domain())
goto err;
info->vtermno = HVC_COOKIE;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
err:
static int xen_pv_console_init(void)
{
struct xencons_info *info;
+ unsigned long flags;
if (!xen_pv_domain())
return -ENODEV;
/* already configured */
return 0;
}
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
xencons_info_pv_init(info, HVC_COOKIE);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
}
static int xen_initial_domain_console_init(void)
{
struct xencons_info *info;
+ unsigned long flags;
if (!xen_initial_domain())
return -ENODEV;
info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false);
info->vtermno = HVC_COOKIE;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
}
static int xen_console_remove(struct xencons_info *info)
{
+ unsigned long flags;
+
xencons_disconnect_backend(info);
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_del(&info->list);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
if (info->xbdev != NULL)
xencons_free(info);
else {
return 0;
}
-static int xencons_remove(struct xenbus_device *dev)
+static void xencons_remove(struct xenbus_device *dev)
{
- return xen_console_remove(dev_get_drvdata(&dev->dev));
+ xen_console_remove(dev_get_drvdata(&dev->dev));
}
static int xencons_connect_backend(struct xenbus_device *dev,
{
int ret, devid;
struct xencons_info *info;
+ unsigned long flags;
devid = dev->nodename[strlen(dev->nodename) - 1] - '0';
if (devid == 0)
ret = xencons_connect_backend(dev, info);
if (ret < 0)
goto error;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
info->hvc = hvc_alloc(HVC_COOKIE, info->irq, ops, 256);
if (IS_ERR(info->hvc)) {
+ unsigned long flags;
+
r = PTR_ERR(info->hvc);
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_del(&info->list);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
if (info->irq)
unbind_from_irqhandler(info->irq, NULL);
kfree(info);
struct uart_8250_dma *dma = p->dma;
struct tty_port *tty_port = &p->port.state->port;
struct dma_tx_state state;
+ enum dma_status dma_status;
int count;
- dma->rx_running = 0;
- dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state);
+ /*
+ * New DMA Rx can be started during the completion handler before it
+ * could acquire port's lock and it might still be ongoing. Don't to
+ * anything in such case.
+ */
+ dma_status = dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state);
+ if (dma_status == DMA_IN_PROGRESS)
+ return;
count = dma->rx_size - state.residue;
tty_insert_flip_string(tty_port, dma->rx_buf, count);
p->port.icount.rx += count;
+ dma->rx_running = 0;
tty_flip_buffer_push(tty_port);
}
struct uart_8250_dma *dma = p->dma;
unsigned long flags;
- __dma_rx_complete(p);
-
spin_lock_irqsave(&p->port.lock, flags);
+ if (dma->rx_running)
+ __dma_rx_complete(p);
+
+ /*
+ * Cannot be combined with the previous check because __dma_rx_complete()
+ * changes dma->rx_running.
+ */
if (!dma->rx_running && (serial_lsr_in(p) & UART_LSR_DR))
p->dma->rx_dma(p);
spin_unlock_irqrestore(&p->port.lock, flags);
#define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358
#define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358
+#define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001
+#define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002
+#define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004
+#define PCI_DEVICE_ID_SEALEVEL_780xC 0x1008
+#define PCI_DEVICE_ID_SEALEVEL_716xC 0x1010
+
#define UART_EXAR_INT0 0x80
#define UART_EXAR_8XMODE 0x88 /* 8X sampling rate select */
#define UART_EXAR_SLEEP 0x8b /* Sleep mode */
nr_ports = BIT(((pcidev->device & 0x38) >> 3) - 1);
else if (board->num_ports)
nr_ports = board->num_ports;
+ else if (pcidev->vendor == PCI_VENDOR_ID_SEALEVEL)
+ nr_ports = pcidev->device & 0xff;
else
nr_ports = pcidev->device & 0x0f;
EXAR_DEVICE(COMMTECH, 4224PCI335, pbn_fastcom335_4),
EXAR_DEVICE(COMMTECH, 2324PCI335, pbn_fastcom335_4),
EXAR_DEVICE(COMMTECH, 2328PCI335, pbn_fastcom335_8),
+
+ EXAR_DEVICE(SEALEVEL, 710xC, pbn_exar_XR17V35x),
+ EXAR_DEVICE(SEALEVEL, 720xC, pbn_exar_XR17V35x),
+ EXAR_DEVICE(SEALEVEL, 740xC, pbn_exar_XR17V35x),
+ EXAR_DEVICE(SEALEVEL, 780xC, pbn_exar_XR17V35x),
+ EXAR_DEVICE(SEALEVEL, 716xC, pbn_exar_XR17V35x),
{ 0, }
};
MODULE_DEVICE_TABLE(pci, exar_pci_tbl);
struct circ_buf *xmit = &uap->port.state->xmit;
int count = uap->fifosize >> 1;
+ if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
+ !uap->rs485_tx_started)
+ pl011_rs485_tx_start(uap);
+
if (uap->port.x_char) {
if (!pl011_tx_char(uap, uap->port.x_char, from_irq))
return true;
return false;
}
- if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
- !uap->rs485_tx_started)
- pl011_rs485_tx_start(uap);
-
/* If we are using DMA mode, try to send some characters. */
if (pl011_dma_tx_irq(uap))
return true;
else if (mr == ATMEL_US_PAR_ODD)
*parity = 'o';
- /*
- * The serial core only rounds down when matching this to a
- * supported baud rate. Make sure we don't end up slightly
- * lower than one of those, as it would make us fall through
- * to a much lower baud rate than we really want.
- */
- *baud = port->uartclk / (16 * (quot - 1));
+ *baud = port->uartclk / (16 * quot);
}
static int __init atmel_console_setup(struct console *co, char *options)
int err = -ENODEV;
char *cptr = config;
struct console *cons;
+ int cookie;
if (!strlen(config) || isspace(config[0])) {
err = 0;
if (kgdboc_register_kbd(&cptr))
goto do_register;
- /*
- * tty_find_polling_driver() can call uart_set_options()
- * (via poll_init) to configure the uart. Take the console_list_lock
- * in order to synchronize against register_console(), which can also
- * configure the uart via uart_set_options(). This also allows safe
- * traversal of the console list.
- */
- console_list_lock();
-
p = tty_find_polling_driver(cptr, &tty_line);
- if (!p) {
- console_list_unlock();
+ if (!p)
goto noconfig;
- }
/*
* Take console_lock to serialize device() callback with
*/
console_lock();
- for_each_console(cons) {
+ cookie = console_srcu_read_lock();
+ for_each_console_srcu(cons) {
int idx;
if (cons->device && cons->device(cons, &idx) == p &&
idx == tty_line) {
break;
}
}
+ console_srcu_read_unlock(cookie);
console_unlock();
- console_list_unlock();
-
kgdb_tty_driver = p;
kgdb_tty_line = tty_line;
uart_xmit_advance(port, sg_dma_len(sg));
async_tx_ack(priv->desc_tx);
- dma_unmap_sg(port->dev, sg, priv->orig_nent, DMA_TO_DEVICE);
+ dma_unmap_sg(port->dev, priv->sg_tx_p, priv->orig_nent, DMA_TO_DEVICE);
priv->tx_dma_use = 0;
priv->nent = 0;
priv->orig_nent = 0;
return IRQ_HANDLED;
}
-static void get_tx_fifo_size(struct qcom_geni_serial_port *port)
+static int setup_fifos(struct qcom_geni_serial_port *port)
{
struct uart_port *uport;
+ u32 old_rx_fifo_depth = port->rx_fifo_depth;
uport = &port->uport;
port->tx_fifo_depth = geni_se_get_tx_fifo_depth(&port->se);
port->rx_fifo_depth = geni_se_get_rx_fifo_depth(&port->se);
uport->fifosize =
(port->tx_fifo_depth * port->tx_fifo_width) / BITS_PER_BYTE;
+
+ if (port->rx_fifo && (old_rx_fifo_depth != port->rx_fifo_depth) && port->rx_fifo_depth) {
+ port->rx_fifo = devm_krealloc(uport->dev, port->rx_fifo,
+ port->rx_fifo_depth * sizeof(u32),
+ GFP_KERNEL);
+ if (!port->rx_fifo)
+ return -ENOMEM;
+ }
+
+ return 0;
}
u32 rxstale = DEFAULT_BITS_PER_CHAR * STALE_TIMEOUT;
u32 proto;
u32 pin_swap;
+ int ret;
proto = geni_se_read_proto(&port->se);
if (proto != GENI_SE_UART) {
qcom_geni_serial_stop_rx(uport);
- get_tx_fifo_size(port);
+ ret = setup_fifos(port);
+ if (ret)
+ return ret;
writel(rxstale, uport->membase + SE_UART_RX_STALE_CNT);
return 0;
}
-static int __maybe_unused qcom_geni_serial_sys_suspend(struct device *dev)
+static int qcom_geni_serial_sys_suspend(struct device *dev)
{
struct qcom_geni_serial_port *port = dev_get_drvdata(dev);
struct uart_port *uport = &port->uport;
return uart_suspend_port(private_data->drv, uport);
}
-static int __maybe_unused qcom_geni_serial_sys_resume(struct device *dev)
+static int qcom_geni_serial_sys_resume(struct device *dev)
{
int ret;
struct qcom_geni_serial_port *port = dev_get_drvdata(dev);
}
static const struct dev_pm_ops qcom_geni_serial_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(qcom_geni_serial_sys_suspend,
- qcom_geni_serial_sys_resume)
- .restore = qcom_geni_serial_sys_hib_resume,
- .thaw = qcom_geni_serial_sys_hib_resume,
+ .suspend = pm_sleep_ptr(qcom_geni_serial_sys_suspend),
+ .resume = pm_sleep_ptr(qcom_geni_serial_sys_resume),
+ .freeze = pm_sleep_ptr(qcom_geni_serial_sys_suspend),
+ .poweroff = pm_sleep_ptr(qcom_geni_serial_sys_suspend),
+ .restore = pm_sleep_ptr(qcom_geni_serial_sys_hib_resume),
+ .thaw = pm_sleep_ptr(qcom_geni_serial_sys_hib_resume),
};
static const struct of_device_id qcom_geni_serial_match_table[] = {
* @parity: parity character - 'n' (none), 'o' (odd), 'e' (even)
* @bits: number of data bits
* @flow: flow control character - 'r' (rts)
+ *
+ * Locking: Caller must hold console_list_lock in order to serialize
+ * early initialization of the serial-console lock.
*/
int
uart_set_options(struct uart_port *port, struct console *co,
if (!ret && options) {
uart_parse_options(options, &baud, &parity, &bits, &flow);
+ console_list_lock();
ret = uart_set_options(port, NULL, baud, parity, bits, flow);
+ console_list_unlock();
}
out:
mutex_unlock(&tport->mutex);
spin_unlock(&port->lock);
}
- if (stm32_usart_rx_dma_enabled(port))
- return IRQ_WAKE_THREAD;
- else
- return IRQ_HANDLED;
-}
-
-static irqreturn_t stm32_usart_threaded_interrupt(int irq, void *ptr)
-{
- struct uart_port *port = ptr;
- struct tty_port *tport = &port->state->port;
- struct stm32_port *stm32_port = to_stm32_port(port);
- unsigned int size;
- unsigned long flags;
-
/* Receiver timeout irq for DMA RX */
- if (!stm32_port->throttled) {
- spin_lock_irqsave(&port->lock, flags);
+ if (stm32_usart_rx_dma_enabled(port) && !stm32_port->throttled) {
+ spin_lock(&port->lock);
size = stm32_usart_receive_chars(port, false);
- uart_unlock_and_check_sysrq_irqrestore(port, flags);
+ uart_unlock_and_check_sysrq(port);
if (size)
tty_flip_buffer_push(tport);
}
u32 val;
int ret;
- ret = request_threaded_irq(port->irq, stm32_usart_interrupt,
- stm32_usart_threaded_interrupt,
- IRQF_ONESHOT | IRQF_NO_SUSPEND,
- name, port);
+ ret = request_irq(port->irq, stm32_usart_interrupt,
+ IRQF_NO_SUSPEND, name, port);
if (ret)
return ret;
struct dma_slave_config config;
int ret;
- /*
- * Using DMA and threaded handler for the console could lead to
- * deadlocks.
- */
- if (uart_console(port))
- return -ENODEV;
-
stm32port->rx_buf = dma_alloc_coherent(dev, RX_BUF_L,
&stm32port->rx_dma_buf,
GFP_KERNEL);
uni_mode = use_unicode(inode);
attr = use_attributes(inode);
- ret = -ENXIO;
- vc = vcs_vc(inode, &viewed);
- if (!vc)
- goto unlock_out;
ret = -EINVAL;
if (pos < 0)
unsigned int this_round, skip = 0;
int size;
+ ret = -ENXIO;
+ vc = vcs_vc(inode, &viewed);
+ if (!vc)
+ goto unlock_out;
+
/* Check whether we are above size each round,
* as copy_to_user at the end of this loop
* could sleep.
* clock scaling is in progress
*/
ufshcd_scsi_block_requests(hba);
+ mutex_lock(&hba->wb_mutex);
down_write(&hba->clk_scaling_lock);
if (!hba->clk_scaling.is_allowed ||
ufshcd_wait_for_doorbell_clr(hba, DOORBELL_CLR_TOUT_US)) {
ret = -EBUSY;
up_write(&hba->clk_scaling_lock);
+ mutex_unlock(&hba->wb_mutex);
ufshcd_scsi_unblock_requests(hba);
goto out;
}
return ret;
}
-static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, bool writelock)
+static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err, bool scale_up)
{
- if (writelock)
- up_write(&hba->clk_scaling_lock);
- else
- up_read(&hba->clk_scaling_lock);
+ up_write(&hba->clk_scaling_lock);
+
+ /* Enable Write Booster if we have scaled up else disable it */
+ if (ufshcd_enable_wb_if_scaling_up(hba) && !err)
+ ufshcd_wb_toggle(hba, scale_up);
+
+ mutex_unlock(&hba->wb_mutex);
+
ufshcd_scsi_unblock_requests(hba);
ufshcd_release(hba);
}
static int ufshcd_devfreq_scale(struct ufs_hba *hba, bool scale_up)
{
int ret = 0;
- bool is_writelock = true;
ret = ufshcd_clock_scaling_prepare(hba);
if (ret)
}
}
- /* Enable Write Booster if we have scaled up else disable it */
- if (ufshcd_enable_wb_if_scaling_up(hba)) {
- downgrade_write(&hba->clk_scaling_lock);
- is_writelock = false;
- ufshcd_wb_toggle(hba, scale_up);
- }
-
out_unprepare:
- ufshcd_clock_scaling_unprepare(hba, is_writelock);
+ ufshcd_clock_scaling_unprepare(hba, ret, scale_up);
return ret;
}
}
}
+static void ufshcd_force_error_recovery(struct ufs_hba *hba)
+{
+ spin_lock_irq(hba->host->host_lock);
+ hba->force_reset = true;
+ ufshcd_schedule_eh_work(hba);
+ spin_unlock_irq(hba->host->host_lock);
+}
+
static void ufshcd_clk_scaling_allow(struct ufs_hba *hba, bool allow)
{
+ mutex_lock(&hba->wb_mutex);
down_write(&hba->clk_scaling_lock);
hba->clk_scaling.is_allowed = allow;
up_write(&hba->clk_scaling_lock);
+ mutex_unlock(&hba->wb_mutex);
}
static void ufshcd_clk_scaling_suspend(struct ufs_hba *hba, bool suspend)
if (!hba->dev_info.b_rpm_dev_flush_capable) {
ret = ufshcd_set_dev_pwr_mode(hba, req_dev_pwr_mode);
+ if (ret && pm_op != UFS_SHUTDOWN_PM) {
+ /*
+ * If return err in suspend flow, IO will hang.
+ * Trigger error handler and break suspend for
+ * error recovery.
+ */
+ ufshcd_force_error_recovery(hba);
+ ret = -EBUSY;
+ }
if (ret)
goto enable_scaling;
}
*/
check_for_bkops = !ufshcd_is_ufs_dev_deepsleep(hba);
ret = ufshcd_link_state_transition(hba, req_link_state, check_for_bkops);
+ if (ret && pm_op != UFS_SHUTDOWN_PM) {
+ /*
+ * If return err in suspend flow, IO will hang.
+ * Trigger error handler and break suspend for
+ * error recovery.
+ */
+ ufshcd_force_error_recovery(hba);
+ ret = -EBUSY;
+ }
if (ret)
goto set_dev_active;
/* Initialize mutex for exception event control */
mutex_init(&hba->ee_ctrl_mutex);
+ mutex_init(&hba->wb_mutex);
init_rwsem(&hba->clk_scaling_lock);
ufshcd_init_clk_gating(hba);
u8 req_on_hw_ring = 0;
unsigned long flags;
int ret = 0;
+ int val;
if (!ep || !request || !ep->desc)
return -EINVAL;
/* Update ring only if removed request is on pending_req_list list */
if (req_on_hw_ring && link_trb) {
+ /* Stop DMA */
+ writel(EP_CMD_DFLUSH, &priv_dev->regs->ep_cmd);
+
+ /* wait for DFLUSH cleared */
+ readl_poll_timeout_atomic(&priv_dev->regs->ep_cmd, val,
+ !(val & EP_CMD_DFLUSH), 1, 1000);
+
link_trb->buffer = cpu_to_le32(TRB_BUFFER(priv_ep->trb_pool_dma +
((priv_req->end_trb + 1) * TRB_SIZE)));
link_trb->control = cpu_to_le32((le32_to_cpu(link_trb->control) & TRB_CYCLE) |
cdns3_gadget_giveback(priv_ep, priv_req, -ECONNRESET);
+ req = cdns3_next_request(&priv_ep->pending_req_list);
+ if (req)
+ cdns3_rearm_transfer(priv_ep, 1);
+
not_found:
spin_unlock_irqrestore(&priv_dev->lock, flags);
return ret;
cable_id = &ci->platdata->id_extcon;
cable_vbus = &ci->platdata->vbus_extcon;
- if ((!IS_ERR(cable_id->edev) || !IS_ERR(ci->role_switch))
+ if ((!IS_ERR(cable_id->edev) || ci->role_switch)
&& ci->is_otg &&
(otgsc & OTGSC_IDIE) && (otgsc & OTGSC_IDIS))
ci_irq(ci);
- if ((!IS_ERR(cable_vbus->edev) || !IS_ERR(ci->role_switch))
+ if ((!IS_ERR(cable_vbus->edev) || ci->role_switch)
&& ci->is_otg &&
(otgsc & OTGSC_BSVIE) && (otgsc & OTGSC_BSVIS))
ci_irq(ci);
/* Test the interface */
ret = ulpi_write(ulpi, ULPI_SCRATCH, 0xaa);
if (ret < 0)
- return ret;
+ goto err;
ret = ulpi_read(ulpi, ULPI_SCRATCH);
if (ret < 0)
#define USB_PRODUCT_USB5534B 0x5534
#define USB_VENDOR_CYPRESS 0x04b4
#define USB_PRODUCT_CY7C65632 0x6570
+#define USB_VENDOR_TEXAS_INSTRUMENTS 0x0451
+#define USB_PRODUCT_TUSB8041_USB3 0x8140
+#define USB_PRODUCT_TUSB8041_USB2 0x8142
#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01
#define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02
.idVendor = USB_VENDOR_GENESYS_LOGIC,
.bInterfaceClass = USB_CLASS_HUB,
.driver_info = HUB_QUIRK_CHECK_PORT_AUTOSUSPEND},
+ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+ | USB_DEVICE_ID_MATCH_PRODUCT,
+ .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS,
+ .idProduct = USB_PRODUCT_TUSB8041_USB2,
+ .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
+ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+ | USB_DEVICE_ID_MATCH_PRODUCT,
+ .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS,
+ .idProduct = USB_PRODUCT_TUSB8041_USB3,
+ .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
{ .match_flags = USB_DEVICE_ID_MATCH_DEV_CLASS,
.bDeviceClass = USB_CLASS_HUB},
{ .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS,
/* DJI CineSSD */
{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
+ /* Alcor Link AK9563 SC Reader used in 2022 Lenovo ThinkPads */
+ { USB_DEVICE(0x2ce3, 0x9563), .driver_info = USB_QUIRK_NO_LPM },
+
/* DELL USB GEN2 */
{ USB_DEVICE(0x413c, 0xb062), .driver_info = USB_QUIRK_NO_LPM | USB_QUIRK_RESET_RESUME },
}
EXPORT_SYMBOL_GPL(usb_acpi_power_manageable);
+#define UUID_USB_CONTROLLER_DSM "ce2ee385-00e6-48cb-9f05-2edb927c4899"
+#define USB_DSM_DISABLE_U1_U2_FOR_PORT 5
+
+/**
+ * usb_acpi_port_lpm_incapable - check if lpm should be disabled for a port.
+ * @hdev: USB device belonging to the usb hub
+ * @index: zero based port index
+ *
+ * Some USB3 ports may not support USB3 link power management U1/U2 states
+ * due to different retimer setup. ACPI provides _DSM method which returns 0x01
+ * if U1 and U2 states should be disabled. Evaluate _DSM with:
+ * Arg0: UUID = ce2ee385-00e6-48cb-9f05-2edb927c4899
+ * Arg1: Revision ID = 0
+ * Arg2: Function Index = 5
+ * Arg3: (empty)
+ *
+ * Return 1 if USB3 port is LPM incapable, negative on error, otherwise 0
+ */
+
+int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index)
+{
+ union acpi_object *obj;
+ acpi_handle port_handle;
+ int port1 = index + 1;
+ guid_t guid;
+ int ret;
+
+ ret = guid_parse(UUID_USB_CONTROLLER_DSM, &guid);
+ if (ret)
+ return ret;
+
+ port_handle = usb_get_hub_port_acpi_handle(hdev, port1);
+ if (!port_handle) {
+ dev_dbg(&hdev->dev, "port-%d no acpi handle\n", port1);
+ return -ENODEV;
+ }
+
+ if (!acpi_check_dsm(port_handle, &guid, 0,
+ BIT(USB_DSM_DISABLE_U1_U2_FOR_PORT))) {
+ dev_dbg(&hdev->dev, "port-%d no _DSM function %d\n",
+ port1, USB_DSM_DISABLE_U1_U2_FOR_PORT);
+ return -ENODEV;
+ }
+
+ obj = acpi_evaluate_dsm(port_handle, &guid, 0,
+ USB_DSM_DISABLE_U1_U2_FOR_PORT, NULL);
+
+ if (!obj)
+ return -ENODEV;
+
+ if (obj->type != ACPI_TYPE_INTEGER) {
+ dev_dbg(&hdev->dev, "evaluate port-%d _DSM failed\n", port1);
+ ACPI_FREE(obj);
+ return -EINVAL;
+ }
+
+ if (obj->integer.value == 0x01)
+ ret = 1;
+
+ ACPI_FREE(obj);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(usb_acpi_port_lpm_incapable);
+
/**
* usb_acpi_set_power_state - control usb port's power via acpi power
* resource
config USB_DWC3
tristate "DesignWare USB3 DRD Core Support"
depends on (USB || USB_GADGET) && HAS_DMA
+ depends on (EXTCON || EXTCON=n)
select USB_XHCI_PLATFORM if USB_XHCI_HCD
select USB_ROLE_SWITCH if USB_DWC3_DUAL_ROLE
help
config USB_DWC3_DUAL_ROLE
bool "Dual Role mode"
depends on ((USB=y || USB=USB_DWC3) && (USB_GADGET=y || USB_GADGET=USB_DWC3))
- depends on (EXTCON=y || EXTCON=USB_DWC3)
help
This is the default mode of working of DWC3 controller where
both host and gadget features are enabled.
qcom->mode = usb_get_dr_mode(&qcom->dwc3->dev);
/* enable vbus override for device mode */
- if (qcom->mode == USB_DR_MODE_PERIPHERAL)
+ if (qcom->mode != USB_DR_MODE_HOST)
dwc3_qcom_vbus_override_enable(qcom, true);
/* register extcon to override sw_vbus on Vbus change later */
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
+#include <linux/gpio/consumer.h>
#include <linux/of_gpio.h>
#include <linux/of_platform.h>
#include <linux/pm_runtime.h>
else if (!ret)
dep->flags |= DWC3_EP_END_TRANSFER_PENDING;
+ dep->flags &= ~DWC3_EP_DELAY_STOP;
return ret;
}
if (dep->number <= 1 && dwc->ep0state != EP0_DATA_PHASE)
return;
+ if (interrupt && (dep->flags & DWC3_EP_DELAY_STOP))
+ return;
+
if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) ||
- (dep->flags & DWC3_EP_DELAY_STOP) ||
(dep->flags & DWC3_EP_END_TRANSFER_PENDING))
return;
static int __init fotg210_init(void)
{
- if (usb_disabled())
- return -ENODEV;
-
- if (IS_ENABLED(CONFIG_USB_FOTG210_HCD))
+ if (IS_ENABLED(CONFIG_USB_FOTG210_HCD) && !usb_disabled())
fotg210_hcd_init();
return platform_driver_register(&fotg210_driver);
}
int ret;
/* hook up the driver */
- driver->driver.bus = NULL;
fotg210->driver = driver;
if (!IS_ERR_OR_NULL(fotg210->phy)) {
dev_info(dev, "found and initialized PHY\n");
}
+ ret = -ENOMEM;
+
for (i = 0; i < FOTG210_MAX_NUM_EP; i++) {
fotg210->ep[i] = kzalloc(sizeof(struct fotg210_ep), GFP_KERNEL);
if (!fotg210->ep[i])
WARN_ON(!list_empty(&gi->string_list));
WARN_ON(!list_empty(&gi->available_func));
kfree(gi->composite.gadget_driver.function);
+ kfree(gi->composite.gadget_driver.driver.name);
kfree(gi);
}
.max_speed = USB_SPEED_SUPER_PLUS,
.driver = {
.owner = THIS_MODULE,
- .name = "configfs-gadget",
},
.match_existing_only = 1,
};
gi->composite.gadget_driver = configfs_driver_template;
+ gi->composite.gadget_driver.driver.name = kasprintf(GFP_KERNEL,
+ "configfs-gadget.%s", name);
+ if (!gi->composite.gadget_driver.driver.name)
+ goto err;
+
gi->composite.gadget_driver.function = kstrdup(name, GFP_KERNEL);
gi->composite.name = gi->composite.gadget_driver.function;
if (!gi->composite.gadget_driver.function)
- goto err;
+ goto out_free_driver_name;
return &gi->group;
+
+out_free_driver_name:
+ kfree(gi->composite.gadget_driver.driver.name);
err:
kfree(gi);
return ERR_PTR(-ENOMEM);
struct usb_request *req = ffs->ep0req;
int ret;
+ if (!req) {
+ spin_unlock_irq(&ffs->ev.waitq.lock);
+ return -EINVAL;
+ }
+
req->zero = len < le16_to_cpu(ffs->ev.setup.wLength);
spin_unlock_irq(&ffs->ev.waitq.lock);
ENTER();
if (!WARN_ON(!ffs->gadget)) {
+ /* dequeue before freeing ep0req */
+ usb_ep_dequeue(ffs->gadget->ep0, ffs->ep0req);
+ mutex_lock(&ffs->mutex);
usb_ep_free_request(ffs->gadget->ep0, ffs->ep0req);
ffs->ep0req = NULL;
ffs->gadget = NULL;
clear_bit(FFS_FL_BOUND, &ffs->flags);
+ mutex_unlock(&ffs->mutex);
ffs_data_put(ffs);
}
}
/* peak (theoretical) bulk transfer rate in bits-per-second */
static inline unsigned ncm_bitrate(struct usb_gadget *g)
{
- if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS)
+ if (!g)
+ return 0;
+ else if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS)
return 4250000000U;
else if (gadget_is_superspeed(g) && g->speed == USB_SPEED_SUPER)
return 3750000000U;
}
std_as_out_if0_desc.bInterfaceNumber = ret;
std_as_out_if1_desc.bInterfaceNumber = ret;
+ std_as_out_if1_desc.bNumEndpoints = 1;
uac2->as_out_intf = ret;
uac2->as_out_alt = 0;
net->max_mtu = GETHER_MAX_MTU_SIZE;
dev->gadget = g;
+ SET_NETDEV_DEV(net, &g->dev);
SET_NETDEV_DEVTYPE(net, &gadget_type);
status = register_netdev(net);
struct usb_gadget *g;
int status;
+ if (!net->dev.parent)
+ return -EINVAL;
dev = netdev_priv(net);
g = dev->gadget;
dev = netdev_priv(net);
dev->gadget = g;
+ SET_NETDEV_DEV(net, &g->dev);
}
EXPORT_SYMBOL_GPL(gether_set_gadget);
*/
static const char *CHIP;
+static DEFINE_MUTEX(sb_mutex); /* Serialize superblock operations */
/*----------------------------------------------------------------------*/
{
struct inode *inode;
struct dev_data *dev;
+ int rc;
- if (the_device)
- return -ESRCH;
+ mutex_lock(&sb_mutex);
+
+ if (the_device) {
+ rc = -ESRCH;
+ goto Done;
+ }
CHIP = usb_get_gadget_udc_name();
- if (!CHIP)
- return -ENODEV;
+ if (!CHIP) {
+ rc = -ENODEV;
+ goto Done;
+ }
/* superblock */
sb->s_blocksize = PAGE_SIZE;
* from binding to a controller.
*/
the_device = dev;
- return 0;
+ rc = 0;
+ goto Done;
-Enomem:
+ Enomem:
kfree(CHIP);
CHIP = NULL;
+ rc = -ENOMEM;
- return -ENOMEM;
+ Done:
+ mutex_unlock(&sb_mutex);
+ return rc;
}
/* "mount -t gadgetfs path /dev/gadget" ends up here */
static void
gadgetfs_kill_sb (struct super_block *sb)
{
+ mutex_lock(&sb_mutex);
kill_litter_super (sb);
if (the_device) {
put_dev (the_device);
}
kfree(CHIP);
CHIP = NULL;
+ mutex_unlock(&sb_mutex);
}
/*----------------------------------------------------------------------*/
(const struct uvc_descriptor_header *) &uvc_format_yuv,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
+ (const struct uvc_descriptor_header *) &uvc_color_matching,
(const struct uvc_descriptor_header *) &uvc_format_mjpg,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
(const struct uvc_descriptor_header *) &uvc_format_yuv,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
+ (const struct uvc_descriptor_header *) &uvc_color_matching,
(const struct uvc_descriptor_header *) &uvc_format_mjpg,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
(const struct uvc_descriptor_header *) &uvc_format_yuv,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
+ (const struct uvc_descriptor_header *) &uvc_color_matching,
(const struct uvc_descriptor_header *) &uvc_format_mjpg,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
bcm63xx_select_phy_mode(udc, true);
udc->driver = driver;
- driver->driver.bus = NULL;
udc->gadget.dev.of_node = udc->dev->of_node;
spin_unlock_irqrestore(&udc->lock, flags);
/* lock is needed but whether should use this lock or another */
spin_lock_irqsave(&udc->lock, flags);
- driver->driver.bus = NULL;
/* hook up the driver */
udc->driver = driver;
udc->gadget.speed = driver->max_speed;
/* lock is needed but whether should use this lock or another */
spin_lock_irqsave(&udc_controller->lock, flags);
- driver->driver.bus = NULL;
/* hook up the driver */
udc_controller->driver = driver;
spin_unlock_irqrestore(&udc_controller->lock, flags);
struct fusb300 *fusb300 = to_fusb300(g);
/* hook up the driver */
- driver->driver.bus = NULL;
fusb300->driver = driver;
return 0;
struct goku_udc *dev = to_goku_udc(g);
/* hook up the driver */
- driver->driver.bus = NULL;
dev->driver = driver;
/*
spin_lock(&dev->lock);
/* Hook up the driver */
- driver->driver.bus = NULL;
dev->driver = driver;
/* Get ready for host detection */
struct m66592 *m66592 = to_m66592(g);
/* hook up the driver */
- driver->driver.bus = NULL;
m66592->driver = driver;
m66592_bset(m66592, M66592_VBSE | M66592_URST, M66592_INTENB0);
spin_lock_irqsave(&udc->lock, flags);
/* hook up the driver */
- driver->driver.bus = NULL;
udc->driver = driver;
udc->gadget.speed = USB_SPEED_FULL;
}
/* hook up the driver ... */
- driver->driver.bus = NULL;
u3d->driver = driver;
u3d->ep0_dir = USB_DIR_OUT;
spin_lock_irqsave(&udc->lock, flags);
/* hook up the driver ... */
- driver->driver.bus = NULL;
udc->driver = driver;
udc->usb_state = USB_STATE_ATTACHED;
dev->ep[i].irqs = 0;
/* hook up the driver ... */
dev->softconnect = 1;
- driver->driver.bus = NULL;
dev->driver = driver;
/* ... then enable host detection and ep0; and we're ready
dev->ep[i].irqs = 0;
/* hook up the driver ... */
- driver->driver.bus = NULL;
dev->driver = driver;
retval = device_create_file(&dev->pdev->dev, &dev_attr_function);
udc->softconnect = 1;
/* hook up the driver */
- driver->driver.bus = NULL;
udc->driver = driver;
spin_unlock_irqrestore(&udc->lock, flags);
{
struct pch_udc_dev *dev = to_pch_udc(g);
- driver->driver.bus = NULL;
dev->driver = driver;
/* get ready for ep0 traffic */
struct udc *dev = to_amd5536_udc(g);
u32 tmp;
- driver->driver.bus = NULL;
dev->driver = driver;
/* Some gadget drivers use both ep0 directions.
#include "ehci-fsl.h"
#define DRIVER_DESC "Freescale EHCI Host controller driver"
-#define DRV_NAME "ehci-fsl"
+#define DRV_NAME "fsl-ehci"
static struct hc_driver __read_mostly fsl_ehci_hc_driver;
}
}
-static int xenhcd_remove(struct xenbus_device *dev)
+static void xenhcd_remove(struct xenbus_device *dev)
{
struct xenhcd_info *info = dev_get_drvdata(&dev->dev);
struct usb_hcd *hcd = xenhcd_info_to_hcd(info);
xenhcd_destroy_rings(info);
usb_put_hcd(hcd);
-
- return 0;
}
static int xenhcd_probe(struct xenbus_device *dev,
static struct hc_driver __read_mostly xhci_pci_hc_driver;
static int xhci_pci_setup(struct usb_hcd *hcd);
+static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
+ struct usb_tt *tt, gfp_t mem_flags);
static const struct xhci_driver_overrides xhci_pci_overrides __initconst = {
.reset = xhci_pci_setup,
+ .update_hub_device = xhci_pci_update_hub_device,
};
/* called after powerup, by probe or system-pm "wakeup" */
NULL);
ACPI_FREE(obj);
}
+
+static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev)
+{
+ struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+ struct xhci_hub *rhub = &xhci->usb3_rhub;
+ int ret;
+ int i;
+
+ /* This is not the usb3 roothub we are looking for */
+ if (hcd != rhub->hcd)
+ return;
+
+ if (hdev->maxchild > rhub->num_ports) {
+ dev_err(&hdev->dev, "USB3 roothub port number mismatch\n");
+ return;
+ }
+
+ for (i = 0; i < hdev->maxchild; i++) {
+ ret = usb_acpi_port_lpm_incapable(hdev, i);
+
+ dev_dbg(&hdev->dev, "port-%d disable U1/U2 _DSM: %d\n", i + 1, ret);
+
+ if (ret >= 0) {
+ rhub->ports[i]->lpm_incapable = ret;
+ continue;
+ }
+ }
+}
+
#else
static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { }
+static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev) { }
#endif /* CONFIG_ACPI */
/* called during probe() after chip reset completes */
return xhci_pci_reinit(xhci, pdev);
}
+static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
+ struct usb_tt *tt, gfp_t mem_flags)
+{
+ /* Check if acpi claims some USB3 roothub ports are lpm incapable */
+ if (!hdev->parent)
+ xhci_find_lpm_incapable_ports(hcd, hdev);
+
+ return xhci_update_hub_device(hcd, hdev, tt, mem_flags);
+}
+
/*
* We need to register our own PCI probe function (instead of the USB core's
* function) in order to create a second roothub under xHCI.
if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW)
pm_runtime_allow(&dev->dev);
+ dma_set_max_seg_size(&dev->dev, UINT_MAX);
+
return 0;
put_usb3_hcd:
struct xhci_virt_ep *ep;
struct xhci_ring *ring;
- ep = &xhci->devs[slot_id]->eps[ep_index];
+ ep = xhci_get_virt_ep(xhci, slot_id, ep_index);
+ if (!ep)
+ return;
+
if ((ep->ep_state & EP_HAS_STREAMS) ||
(ep->ep_state & EP_GETTING_NO_STREAMS)) {
int stream_id;
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
struct xhci_virt_device *virt_dev;
struct xhci_slot_ctx *slot_ctx;
+ unsigned long flags;
int i, ret;
/*
virt_dev->eps[i].ep_state &= ~EP_STOP_CMD_PENDING;
virt_dev->udev = NULL;
xhci_disable_slot(xhci, udev->slot_id);
+
+ spin_lock_irqsave(&xhci->lock, flags);
xhci_free_virt_device(xhci, udev->slot_id);
+ spin_unlock_irqrestore(&xhci->lock, flags);
+
}
int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
struct usb_device *udev, enum usb3_link_state state)
{
struct xhci_hcd *xhci;
+ struct xhci_port *port;
u16 hub_encoded_timeout;
int mel;
int ret;
if (xhci_check_tier_policy(xhci, udev, state) < 0)
return USB3_LPM_DISABLED;
+ /* If connected to root port then check port can handle lpm */
+ if (udev->parent && !udev->parent->parent) {
+ port = xhci->usb3_rhub.ports[udev->portnum - 1];
+ if (port->lpm_incapable)
+ return USB3_LPM_DISABLED;
+ }
+
hub_encoded_timeout = xhci_calculate_lpm_timeout(hcd, udev, state);
mel = calculate_max_exit_latency(udev, state, hub_encoded_timeout);
if (mel < 0) {
/* Once a hub descriptor is fetched for a device, we need to update the xHC's
* internal data structures for the device.
*/
-static int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
+int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
struct usb_tt *tt, gfp_t mem_flags)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
xhci_free_command(xhci, config_cmd);
return ret;
}
+EXPORT_SYMBOL_GPL(xhci_update_hub_device);
static int xhci_get_frame(struct usb_hcd *hcd)
{
drv->check_bandwidth = over->check_bandwidth;
if (over->reset_bandwidth)
drv->reset_bandwidth = over->reset_bandwidth;
+ if (over->update_hub_device)
+ drv->update_hub_device = over->update_hub_device;
}
}
EXPORT_SYMBOL_GPL(xhci_init_driver);
int hcd_portnum;
struct xhci_hub *rhub;
struct xhci_port_cap *port_cap;
+ unsigned int lpm_incapable:1;
};
struct xhci_hub {
struct usb_host_endpoint *ep);
int (*check_bandwidth)(struct usb_hcd *, struct usb_device *);
void (*reset_bandwidth)(struct usb_hcd *, struct usb_device *);
+ int (*update_hub_device)(struct usb_hcd *hcd, struct usb_device *hdev,
+ struct usb_tt *tt, gfp_t mem_flags);
};
#define XHCI_CFC_DELAY 10
struct usb_host_endpoint *ep);
int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev);
void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev);
+int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
+ struct usb_tt *tt, gfp_t mem_flags);
int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id);
int xhci_ext_cap_init(struct xhci_hcd *xhci);
break;
case USB_DEVICE_ID_CODEMERCS_IOW100:
- dev->report_size = 13;
+ dev->report_size = 12;
break;
}
}
#include "onboard_usb_hub.h"
+static void onboard_hub_attach_usb_driver(struct work_struct *work);
+
static struct usb_device_driver onboard_hub_usbdev_driver;
+static DECLARE_WORK(attach_usb_driver_work, onboard_hub_attach_usb_driver);
/************************** Platform driver **************************/
bool is_powered_on;
bool going_away;
struct list_head udev_list;
- struct work_struct attach_usb_driver_work;
struct mutex lock;
};
* This needs to be done deferred to avoid self-deadlocks on systems
* with nested onboard hubs.
*/
- INIT_WORK(&hub->attach_usb_driver_work, onboard_hub_attach_usb_driver);
- schedule_work(&hub->attach_usb_driver_work);
+ schedule_work(&attach_usb_driver_work);
return 0;
}
hub->going_away = true;
- if (&hub->attach_usb_driver_work != current_work())
- cancel_work_sync(&hub->attach_usb_driver_work);
-
mutex_lock(&hub->lock);
/* unbind the USB devices to avoid dangling references to this device */
{
int ret;
- ret = platform_driver_register(&onboard_hub_driver);
+ ret = usb_register_device_driver(&onboard_hub_usbdev_driver, THIS_MODULE);
if (ret)
return ret;
- ret = usb_register_device_driver(&onboard_hub_usbdev_driver, THIS_MODULE);
+ ret = platform_driver_register(&onboard_hub_driver);
if (ret)
- platform_driver_unregister(&onboard_hub_driver);
+ usb_deregister_device_driver(&onboard_hub_usbdev_driver);
return ret;
}
{
usb_deregister_device_driver(&onboard_hub_usbdev_driver);
platform_driver_unregister(&onboard_hub_driver);
+
+ cancel_work_sync(&attach_usb_driver_work);
}
module_exit(onboard_hub_exit);
memset(musb_res, 0, sizeof(*musb_res) * ARRAY_SIZE(musb_res));
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
+ if (!res) {
+ ret = -EINVAL;
goto err2;
+ }
musb_res[i].start = res->start;
musb_res[i].end = res->end;
{ USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */
{ USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */
{ USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */
+ { USB_DEVICE(0x0908, 0x0070) }, /* Siemens SCALANCE LPE-9000 USB Serial Console */
{ USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */
{ USB_DEVICE(0x0988, 0x0578) }, /* Teraoka AD2000 */
{ USB_DEVICE(0x0B00, 0x3070) }, /* Ingenico 3070 */
#define QUECTEL_PRODUCT_EP06 0x0306
#define QUECTEL_PRODUCT_EM05G 0x030a
#define QUECTEL_PRODUCT_EM060K 0x030b
+#define QUECTEL_PRODUCT_EM05G_CS 0x030c
+#define QUECTEL_PRODUCT_EM05CN_SG 0x0310
#define QUECTEL_PRODUCT_EM05G_SG 0x0311
+#define QUECTEL_PRODUCT_EM05CN 0x0312
+#define QUECTEL_PRODUCT_EM05G_GR 0x0313
+#define QUECTEL_PRODUCT_EM05G_RS 0x0314
#define QUECTEL_PRODUCT_EM12 0x0512
#define QUECTEL_PRODUCT_RM500Q 0x0800
#define QUECTEL_PRODUCT_RM520N 0x0801
+#define QUECTEL_PRODUCT_EC200U 0x0901
#define QUECTEL_PRODUCT_EC200S_CN 0x6002
#define QUECTEL_PRODUCT_EC200T 0x6026
#define QUECTEL_PRODUCT_RM500K 0x7001
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN, 0xff),
+ .driver_info = RSVD(6) | ZLP },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN_SG, 0xff),
+ .driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff),
.driver_info = RSVD(6) | ZLP },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff),
+ .driver_info = RSVD(6) | ZLP },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff),
+ .driver_info = RSVD(6) | ZLP },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_RS, 0xff),
+ .driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff),
.driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) },
if (le16_to_cpu(udev->descriptor.idVendor) == 0x0bc2)
flags |= US_FL_NO_ATA_1X;
+ /*
+ * RTL9210-based enclosure from HIKSEMI, MD202 reportedly have issues
+ * with UAS. This isn't distinguishable with just idVendor and
+ * idProduct, use manufacturer and product too.
+ *
+ * Reported-by: Hongling Zeng <zenghongling@kylinos.cn>
+ */
+ if (le16_to_cpu(udev->descriptor.idVendor) == 0x0bda &&
+ le16_to_cpu(udev->descriptor.idProduct) == 0x9210 &&
+ (udev->manufacturer && !strcmp(udev->manufacturer, "HIKSEMI")) &&
+ (udev->product && !strcmp(udev->product, "MD202")))
+ flags |= US_FL_IGNORE_UAS;
+
usb_stor_adjust_quirks(udev, &flags);
if (flags & US_FL_IGNORE_UAS) {
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_NO_REPORT_LUNS),
-/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */
-UNUSUAL_DEV(0x0bda, 0x9210, 0x0000, 0x9999,
- "Hiksemi",
- "External HDD",
- USB_SC_DEVICE, USB_PR_DEVICE, NULL,
- US_FL_IGNORE_UAS),
-
/* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
"Initio Corporation",
[DP_PIN_ASSIGN_F] = "F",
};
+/*
+ * Helper function to extract a peripheral's currently supported
+ * Pin Assignments from its DisplayPort alternate mode state.
+ */
+static u8 get_current_pin_assignments(struct dp_altmode *dp)
+{
+ if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_UFP_U_AS_DFP_D)
+ return DP_CAP_PIN_ASSIGN_DFP_D(dp->alt->vdo);
+ else
+ return DP_CAP_PIN_ASSIGN_UFP_D(dp->alt->vdo);
+}
+
static ssize_t
pin_assignment_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t size)
goto out_unlock;
}
- if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D)
- assignments = DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo);
- else
- assignments = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo);
+ assignments = get_current_pin_assignments(dp);
if (!(DP_CONF_GET_PIN_ASSIGN(conf) & assignments)) {
ret = -EINVAL;
cur = get_count_order(DP_CONF_GET_PIN_ASSIGN(dp->data.conf));
- if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D)
- assignments = DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo);
- else
- assignments = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo);
+ assignments = get_current_pin_assignments(dp);
for (i = 0; assignments; assignments >>= 1, i++) {
if (assignments & 1) {
/* FIXME: Port can only be DFP_U. */
/* Make sure we have compatiple pin configurations */
- if (!(DP_CAP_DFP_D_PIN_ASSIGN(port->vdo) &
- DP_CAP_UFP_D_PIN_ASSIGN(alt->vdo)) &&
- !(DP_CAP_UFP_D_PIN_ASSIGN(port->vdo) &
- DP_CAP_DFP_D_PIN_ASSIGN(alt->vdo)))
+ if (!(DP_CAP_PIN_ASSIGN_DFP_D(port->vdo) &
+ DP_CAP_PIN_ASSIGN_UFP_D(alt->vdo)) &&
+ !(DP_CAP_PIN_ASSIGN_UFP_D(port->vdo) &
+ DP_CAP_PIN_ASSIGN_DFP_D(alt->vdo)))
return -ENODEV;
ret = sysfs_create_group(&alt->dev.kobj, &dp_altmode_group);
tcpm_set_state(port, ready_state(port), 0);
break;
case DR_SWAP_CHANGE_DR:
- if (port->data_role == TYPEC_HOST) {
- tcpm_unregister_altmodes(port);
+ tcpm_unregister_altmodes(port);
+ if (port->data_role == TYPEC_HOST)
tcpm_set_roles(port, true, port->pwr_role,
TYPEC_DEVICE);
- } else {
+ else
tcpm_set_roles(port, true, port->pwr_role,
TYPEC_HOST);
- }
tcpm_ams_finish(port);
tcpm_set_state(port, ready_state(port), 0);
break;
struct ucsi_work {
struct delayed_work work;
+ struct list_head node;
unsigned long delay;
unsigned int count;
struct ucsi_connector *con;
mutex_lock(&con->lock);
if (!con->partner) {
+ list_del(&uwork->node);
mutex_unlock(&con->lock);
kfree(uwork);
return;
ret = uwork->cb(con);
- if (uwork->count-- && (ret == -EBUSY || ret == -ETIMEDOUT))
+ if (uwork->count-- && (ret == -EBUSY || ret == -ETIMEDOUT)) {
queue_delayed_work(con->wq, &uwork->work, uwork->delay);
- else
+ } else {
+ list_del(&uwork->node);
kfree(uwork);
+ }
mutex_unlock(&con->lock);
}
uwork->con = con;
uwork->cb = cb;
+ list_add_tail(&uwork->node, &con->partner_tasks);
queue_delayed_work(con->wq, &uwork->work, delay);
return 0;
INIT_WORK(&con->work, ucsi_handle_connector_change);
init_completion(&con->complete);
mutex_init(&con->lock);
+ INIT_LIST_HEAD(&con->partner_tasks);
con->num = index + 1;
con->ucsi = ucsi;
con->port = NULL;
}
+ kfree(ucsi->connector);
+ ucsi->connector = NULL;
+
err_reset:
memset(&ucsi->cap, 0, sizeof(ucsi->cap));
ucsi_reset_ppm(ucsi);
int ucsi_resume(struct ucsi *ucsi)
{
- queue_work(system_long_wq, &ucsi->resume_work);
+ if (ucsi->connector)
+ queue_work(system_long_wq, &ucsi->resume_work);
return 0;
}
EXPORT_SYMBOL_GPL(ucsi_resume);
/* Disable notifications */
ucsi->ops->async_write(ucsi, UCSI_CONTROL, &cmd, sizeof(cmd));
+ if (!ucsi->connector)
+ return;
+
for (i = 0; i < ucsi->cap.num_connectors; i++) {
cancel_work_sync(&ucsi->connector[i].work);
ucsi_unregister_partner(&ucsi->connector[i]);
ucsi_unregister_altmodes(&ucsi->connector[i],
UCSI_RECIPIENT_CON);
ucsi_unregister_port_psy(&ucsi->connector[i]);
- if (ucsi->connector[i].wq)
+
+ if (ucsi->connector[i].wq) {
+ struct ucsi_work *uwork;
+
+ mutex_lock(&ucsi->connector[i].lock);
+ /*
+ * queue delayed items immediately so they can execute
+ * and free themselves before the wq is destroyed
+ */
+ list_for_each_entry(uwork, &ucsi->connector[i].partner_tasks, node)
+ mod_delayed_work(ucsi->connector[i].wq, &uwork->work, 0);
+ mutex_unlock(&ucsi->connector[i].lock);
destroy_workqueue(ucsi->connector[i].wq);
+ }
typec_unregister_port(ucsi->connector[i].port);
}
struct work_struct work;
struct completion complete;
struct workqueue_struct *wq;
+ struct list_head partner_tasks;
struct typec_port *port;
struct typec_partner *partner;
ret = ifcvf_init_hw(vf, pdev);
if (ret) {
IFCVF_ERR(pdev, "Failed to init IFCVF hw\n");
- return ret;
+ goto err;
}
for (i = 0; i < vf->nr_vring; i++)
int inlen);
int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey);
int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
- bool *change_map);
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb);
+ bool *change_map, unsigned int asid);
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid);
void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
#define mlx5_vdpa_warn(__dev, format, ...) \
u64 st;
u64 sz;
int err;
- int i = 0;
st = start;
while (size) {
mr->num_directs++;
mr->num_klms++;
st += sz;
- i++;
}
list_splice_tail(&tmp, &mr->head);
return 0;
mutex_unlock(&mr->mkey_mtx);
}
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb, unsigned int asid)
{
struct mlx5_vdpa_mr *mr = &mvdev->mr;
int err;
if (mr->initialized)
return 0;
- if (iotlb)
- err = create_user_mr(mvdev, iotlb);
- else
- err = create_dma_mr(mvdev, mr);
+ if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+ if (iotlb)
+ err = create_user_mr(mvdev, iotlb);
+ else
+ err = create_dma_mr(mvdev, mr);
- if (err)
- return err;
+ if (err)
+ return err;
+ }
- err = dup_iotlb(mvdev, iotlb);
- if (err)
- goto out_err;
+ if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) {
+ err = dup_iotlb(mvdev, iotlb);
+ if (err)
+ goto out_err;
+ }
mr->initialized = true;
return 0;
out_err:
- if (iotlb)
- destroy_user_mr(mvdev, mr);
- else
- destroy_dma_mr(mvdev, mr);
+ if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+ if (iotlb)
+ destroy_user_mr(mvdev, mr);
+ else
+ destroy_dma_mr(mvdev, mr);
+ }
return err;
}
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid)
{
int err;
mutex_lock(&mvdev->mr.mkey_mtx);
- err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
mutex_unlock(&mvdev->mr.mkey_mtx);
return err;
}
int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
- bool *change_map)
+ bool *change_map, unsigned int asid)
{
struct mlx5_vdpa_mr *mr = &mvdev->mr;
int err = 0;
*change_map = true;
}
if (!*change_map)
- err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
mutex_unlock(&mr->mkey_mtx);
return err;
dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16);
eth_broadcast_addr(dmac_c);
ether_addr_copy(dmac_v, mac);
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+ if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)) {
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+ MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
+ }
if (tagged) {
MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
- MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, vid);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, vid);
}
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
/* Need recreate the flow table entry, so that the packet could forward back
*/
- mac_vlan_del(ndev, ndev->config.mac, 0, false);
+ mac_vlan_del(ndev, mac_back, 0, false);
if (mac_vlan_add(ndev, ndev->config.mac, 0, false)) {
mlx5_vdpa_warn(mvdev, "failed to insert forward rules, try to restore\n");
size_t read;
u16 id;
+ if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)))
+ return status;
+
switch (cmd) {
case VIRTIO_NET_CTRL_VLAN_ADD:
read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, &vlan, sizeof(vlan));
}
}
-static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb, unsigned int asid)
{
struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
int err;
teardown_driver(ndev);
mlx5_vdpa_destroy_mr(mvdev);
- err = mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = mlx5_vdpa_create_mr(mvdev, iotlb, asid);
if (err)
goto err_mr;
++mvdev->generation;
if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
- if (mlx5_vdpa_create_mr(mvdev, NULL))
+ if (mlx5_vdpa_create_mr(mvdev, NULL, 0))
mlx5_vdpa_warn(mvdev, "create MR failed\n");
}
up_write(&ndev->reslock);
return mvdev->generation;
}
-static int set_map_control(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
-{
- u64 start = 0ULL, last = 0ULL - 1;
- struct vhost_iotlb_map *map;
- int err = 0;
-
- spin_lock(&mvdev->cvq.iommu_lock);
- vhost_iotlb_reset(mvdev->cvq.iotlb);
-
- for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
- map = vhost_iotlb_itree_next(map, start, last)) {
- err = vhost_iotlb_add_range(mvdev->cvq.iotlb, map->start,
- map->last, map->addr, map->perm);
- if (err)
- goto out;
- }
-
-out:
- spin_unlock(&mvdev->cvq.iommu_lock);
- return err;
-}
-
-static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid)
{
bool change_map;
int err;
- err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map);
+ err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map, asid);
if (err) {
mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err);
return err;
}
if (change_map)
- err = mlx5_vdpa_change_map(mvdev, iotlb);
+ err = mlx5_vdpa_change_map(mvdev, iotlb, asid);
return err;
}
int err = -EINVAL;
down_write(&ndev->reslock);
- if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
- err = set_map_data(mvdev, iotlb);
- if (err)
- goto out;
- }
-
- if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid)
- err = set_map_control(mvdev, iotlb);
-
-out:
+ err = set_map_data(mvdev, iotlb, asid);
up_write(&ndev->reslock);
return err;
}
int i;
down_write(&ndev->reslock);
- mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
ndev->nb_registered = false;
+ mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
flush_workqueue(ndev->mvdev.wq);
for (i = 0; i < ndev->cur_num_vqs; i++) {
mvq = &ndev->vqs[i];
else
ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
- if (ndev->config_cb.callback)
+ if (ndev->nb_registered && ndev->config_cb.callback)
ndev->config_cb.callback(ndev->config_cb.private);
kfree(wqent);
switch (eqe->sub_type) {
case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
- down_read(&ndev->reslock);
- if (!ndev->nb_registered) {
- up_read(&ndev->reslock);
- return NOTIFY_DONE;
- }
wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
- if (!wqent) {
- up_read(&ndev->reslock);
+ if (!wqent)
return NOTIFY_DONE;
- }
wqent->mvdev = &ndev->mvdev;
INIT_WORK(&wqent->work, update_carrier);
queue_work(ndev->mvdev.wq, &wqent->work);
- up_read(&ndev->reslock);
ret = NOTIFY_OK;
break;
default:
goto err_mpfs;
if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
- err = mlx5_vdpa_create_mr(mvdev, NULL);
+ err = mlx5_vdpa_create_mr(mvdev, NULL, 0);
if (err)
goto err_res;
}
struct workqueue_struct *wq;
if (ndev->nb_registered) {
- mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
ndev->nb_registered = false;
+ mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
}
wq = mvdev->wq;
mvdev->wq = NULL;
features_device = vdev->config->get_device_features(vdev);
- if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device,
+ if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_FEATURES, features_device,
VDPA_ATTR_PAD))
return -EMSGSIZE;
{
struct virtio_net_config config = {};
u64 features;
- u16 max_vqp;
u8 status;
int err;
}
vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
- max_vqp = __virtio16_to_cpu(true, config.max_virtqueue_pairs);
- if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp))
- return -EMSGSIZE;
-
features = vdev->config->get_driver_features(vdev);
if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES,
features, VDPA_ATTR_PAD))
return -EMSGSIZE;
+ err = vdpa_dev_net_mq_config_fill(msg, features, &config);
+ if (err)
+ return err;
+
if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index))
return -EMSGSIZE;
{
struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
- vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
- VDPASIM_QUEUE_MAX, false,
+ vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false,
(struct vring_desc *)(uintptr_t)vq->desc_addr,
(struct vring_avail *)
(uintptr_t)vq->driver_addr,
}
kvfree(vdpasim->buffer);
- vhost_iotlb_free(vdpasim->iommu);
+ for (i = 0; i < vdpasim->dev_attr.nas; i++)
+ vhost_iotlb_reset(&vdpasim->iommu[i]);
+ kfree(vdpasim->iommu);
kfree(vdpasim->vqs);
kfree(vdpasim->config);
}
int ret;
ret = device_register(&vdpasim_blk_mgmtdev);
- if (ret)
+ if (ret) {
+ put_device(&vdpasim_blk_mgmtdev);
return ret;
+ }
ret = vdpa_mgmtdev_register(&mgmt_dev);
if (ret)
if (len < ETH_ALEN + hdr_len)
return false;
+ if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) ||
+ is_multicast_ether_addr(vdpasim->buffer + hdr_len))
+ return true;
if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN))
return true;
int ret;
ret = device_register(&vdpasim_net_mgmtdev);
- if (ret)
+ if (ret) {
+ put_device(&vdpasim_net_mgmtdev);
return ret;
+ }
ret = vdpa_mgmtdev_register(&mgmt_dev);
if (ret)
if (config->config_size > PAGE_SIZE)
return false;
+ if (config->vq_num > 0xffff)
+ return false;
+
if (!device_is_allowed(config->device_id))
return false;
mdev = vp_vdpa_mgtdev->mdev;
vp_modern_remove(mdev);
vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev);
- kfree(&vp_vdpa_mgtdev->mgtdev.id_table);
+ kfree(vp_vdpa_mgtdev->mgtdev.id_table);
kfree(mdev);
kfree(vp_vdpa_mgtdev);
}
* significantly boosts non-hugetlbfs mappings and doesn't seem to hurt when
* hugetlbfs is in use.
*/
-static void vfio_test_domain_fgsp(struct vfio_domain *domain)
+static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head *regions)
{
- struct page *pages;
int ret, order = get_order(PAGE_SIZE * 2);
+ struct vfio_iova *region;
+ struct page *pages;
+ dma_addr_t start;
pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
if (!pages)
return;
- ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2,
- IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
- if (!ret) {
- size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE);
+ list_for_each_entry(region, regions, list) {
+ start = ALIGN(region->start, PAGE_SIZE * 2);
+ if (start >= region->end || (region->end - start < PAGE_SIZE * 2))
+ continue;
- if (unmapped == PAGE_SIZE)
- iommu_unmap(domain->domain, PAGE_SIZE, PAGE_SIZE);
- else
- domain->fgsp = true;
+ ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2,
+ IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
+ if (!ret) {
+ size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE);
+
+ if (unmapped == PAGE_SIZE)
+ iommu_unmap(domain->domain, start + PAGE_SIZE, PAGE_SIZE);
+ else
+ domain->fgsp = true;
+ }
+ break;
}
__free_pages(pages, order);
}
}
- vfio_test_domain_fgsp(domain);
+ vfio_test_domain_fgsp(domain, &iova_copy);
/* replay mappings on new domains */
ret = vfio_iommu_replay(iommu, domain);
nvq = &n->vqs[index];
mutex_lock(&vq->mutex);
+ if (fd == -1)
+ vhost_clear_msg(&n->dev);
+
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(vq)) {
r = -EFAULT;
struct scatterlist *tvc_prot_sgl;
struct page **tvc_upages;
/* Pointer to response header iovec */
- struct iovec tvc_resp_iov;
+ struct iovec *tvc_resp_iov;
/* Pointer to vhost_scsi for our device */
struct vhost_scsi *tvc_vhost;
/* Pointer to vhost_virtqueue for the cmd */
memcpy(v_rsp.sense, cmd->tvc_sense_buf,
se_cmd->scsi_sense_length);
- iov_iter_init(&iov_iter, ITER_DEST, &cmd->tvc_resp_iov,
+ iov_iter_init(&iov_iter, ITER_DEST, cmd->tvc_resp_iov,
cmd->tvc_in_iovs, sizeof(v_rsp));
ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
if (likely(ret == sizeof(v_rsp))) {
struct vhost_scsi_cmd *cmd;
struct vhost_scsi_nexus *tv_nexus;
struct scatterlist *sg, *prot_sg;
+ struct iovec *tvc_resp_iov;
struct page **pages;
int tag;
sg = cmd->tvc_sgl;
prot_sg = cmd->tvc_prot_sgl;
pages = cmd->tvc_upages;
+ tvc_resp_iov = cmd->tvc_resp_iov;
memset(cmd, 0, sizeof(*cmd));
cmd->tvc_sgl = sg;
cmd->tvc_prot_sgl = prot_sg;
cmd->tvc_data_direction = data_direction;
cmd->tvc_nexus = tv_nexus;
cmd->inflight = vhost_scsi_get_inflight(vq);
+ cmd->tvc_resp_iov = tvc_resp_iov;
memcpy(cmd->tvc_cdb, cdb, VHOST_SCSI_MAX_CDB_SIZE);
struct iov_iter in_iter, prot_iter, data_iter;
u64 tag;
u32 exp_data_len, data_direction;
- int ret, prot_bytes, c = 0;
+ int ret, prot_bytes, i, c = 0;
u16 lun;
u8 task_attr;
bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI);
}
cmd->tvc_vhost = vs;
cmd->tvc_vq = vq;
- cmd->tvc_resp_iov = vq->iov[vc.out];
+ for (i = 0; i < vc.in ; i++)
+ cmd->tvc_resp_iov[i] = vq->iov[vc.out + i];
cmd->tvc_in_iovs = vc.in;
pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
kfree(tv_cmd->tvc_sgl);
kfree(tv_cmd->tvc_prot_sgl);
kfree(tv_cmd->tvc_upages);
+ kfree(tv_cmd->tvc_resp_iov);
}
sbitmap_free(&svq->scsi_tags);
goto out;
}
+ tv_cmd->tvc_resp_iov = kcalloc(UIO_MAXIOV,
+ sizeof(struct iovec),
+ GFP_KERNEL);
+ if (!tv_cmd->tvc_resp_iov) {
+ pr_err("Unable to allocate tv_cmd->tvc_resp_iov\n");
+ goto out;
+ }
+
tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS,
sizeof(struct scatterlist),
GFP_KERNEL);
static dev_t vhost_vdpa_major;
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
+ struct vhost_iotlb *iotlb, u64 start,
+ u64 last, u32 asid);
+
static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
{
struct vhost_vdpa_as *as = container_of(iotlb, struct
return -EINVAL;
hlist_del(&as->hash_link);
- vhost_iotlb_reset(&as->iotlb);
+ vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1, asid);
kfree(as);
return 0;
mutex_unlock(&d->mutex);
return r;
}
+static void vhost_vdpa_general_unmap(struct vhost_vdpa *v,
+ struct vhost_iotlb_map *map, u32 asid)
+{
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+ if (ops->dma_map) {
+ ops->dma_unmap(vdpa, asid, map->start, map->size);
+ } else if (ops->set_map == NULL) {
+ iommu_unmap(v->domain, map->start, map->size);
+ }
+}
-static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+ u64 start, u64 last, u32 asid)
{
struct vhost_dev *dev = &v->vdev;
struct vhost_iotlb_map *map;
unpin_user_page(page);
}
atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm);
+ vhost_vdpa_general_unmap(v, map, asid);
vhost_iotlb_map_free(iotlb, map);
}
}
-static void vhost_vdpa_va_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+ u64 start, u64 last, u32 asid)
{
struct vhost_iotlb_map *map;
struct vdpa_map_file *map_file;
map_file = (struct vdpa_map_file *)map->opaque;
fput(map_file->file);
kfree(map_file);
+ vhost_vdpa_general_unmap(v, map, asid);
vhost_iotlb_map_free(iotlb, map);
}
}
static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+ struct vhost_iotlb *iotlb, u64 start,
+ u64 last, u32 asid)
{
struct vdpa_device *vdpa = v->vdpa;
if (vdpa->use_va)
- return vhost_vdpa_va_unmap(v, iotlb, start, last);
+ return vhost_vdpa_va_unmap(v, iotlb, start, last, asid);
- return vhost_vdpa_pa_unmap(v, iotlb, start, last);
+ return vhost_vdpa_pa_unmap(v, iotlb, start, last, asid);
}
static int perm_to_iommu_flags(u32 perm)
const struct vdpa_config_ops *ops = vdpa->config;
u32 asid = iotlb_to_asid(iotlb);
- vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
+ vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1, asid);
- if (ops->dma_map) {
- ops->dma_unmap(vdpa, asid, iova, size);
- } else if (ops->set_map) {
+ if (ops->set_map) {
if (!v->in_batch)
ops->set_map(vdpa, asid, iotlb);
- } else {
- iommu_unmap(v->domain, iova, size);
}
-
/* If we are in the middle of batch processing, delay the free
* of AS until BATCH_END.
*/
struct vhost_vdpa_as *as;
u32 asid;
- vhost_dev_cleanup(&v->vdev);
- kfree(v->vdev.vqs);
-
for (asid = 0; asid < v->vdpa->nas; asid++) {
as = asid_to_as(v, asid);
if (as)
vhost_vdpa_remove_as(v, asid);
}
+
+ vhost_dev_cleanup(&v->vdev);
+ kfree(v->vdev.vqs);
}
static int vhost_vdpa_open(struct inode *inode, struct file *filep)
}
EXPORT_SYMBOL_GPL(vhost_dev_stop);
-static void vhost_clear_msg(struct vhost_dev *dev)
+void vhost_clear_msg(struct vhost_dev *dev)
{
struct vhost_msg_node *node, *n;
spin_unlock(&dev->iotlb_lock);
}
+EXPORT_SYMBOL_GPL(vhost_clear_msg);
void vhost_dev_cleanup(struct vhost_dev *dev)
{
struct vhost_dev *dev = vq->dev;
struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem;
struct iovec *_iov;
- u64 s = 0;
+ u64 s = 0, last = addr + len - 1;
int ret = 0;
while ((u64)len > s) {
break;
}
- map = vhost_iotlb_itree_first(umem, addr, addr + len - 1);
+ map = vhost_iotlb_itree_first(umem, addr, last);
if (map == NULL || map->start > addr) {
if (umem != dev->iotlb) {
ret = -EFAULT;
long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp);
bool vhost_vq_access_ok(struct vhost_virtqueue *vq);
bool vhost_log_access_ok(struct vhost_dev *);
+void vhost_clear_msg(struct vhost_dev *dev);
int vhost_get_vq_desc(struct vhost_virtqueue *,
struct iovec iov[], unsigned int iov_count,
struct vhost_iotlb_map *map;
struct vhost_iotlb *iotlb = vrh->iotlb;
int ret = 0;
- u64 s = 0;
+ u64 s = 0, last = addr + len - 1;
spin_lock(vrh->iotlb_lock);
break;
}
- map = vhost_iotlb_itree_first(iotlb, addr,
- addr + len - 1);
+ map = vhost_iotlb_itree_first(iotlb, addr, last);
if (!map || map->start > addr) {
ret = -EINVAL;
break;
VSOCK_TRANSPORT_F_H2G);
if (ret < 0)
return ret;
- return misc_register(&vhost_vsock_misc);
+
+ ret = misc_register(&vhost_vsock_misc);
+ if (ret) {
+ vsock_core_unregister(&vhost_transport.transport);
+ return ret;
+ }
+
+ return 0;
};
static void __exit vhost_vsock_exit(void)
chipset found in Ataris.
config FB_OF
- bool "Open Firmware frame buffer device support"
- depends on (FB = y) && PPC && (!PPC_PSERIES || PCI)
+ tristate "Open Firmware frame buffer device support"
+ depends on FB && PPC && (!PPC_PSERIES || PCI)
depends on !DRM_OFDRM
select APERTURE_HELPERS
select FB_CFB_FILLRECT
struct clk *lcdc_clk;
struct backlight_device *backlight;
- u8 bl_power;
u8 saved_lcdcon;
u32 pseudo_palette[16];
static int atmel_bl_update_status(struct backlight_device *bl)
{
struct atmel_lcdfb_info *sinfo = bl_get_data(bl);
- int power = sinfo->bl_power;
- int brightness = bl->props.brightness;
-
- /* REVISIT there may be a meaningful difference between
- * fb_blank and power ... there seem to be some cases
- * this doesn't handle correctly.
- */
- if (bl->props.fb_blank != sinfo->bl_power)
- power = bl->props.fb_blank;
- else if (bl->props.power != sinfo->bl_power)
- power = bl->props.power;
-
- if (brightness < 0 && power == FB_BLANK_UNBLANK)
- brightness = lcdc_readl(sinfo, ATMEL_LCDC_CONTRAST_VAL);
- else if (power != FB_BLANK_UNBLANK)
- brightness = 0;
+ int brightness = backlight_get_brightness(bl);
lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_VAL, brightness);
if (contrast_ctr & ATMEL_LCDC_POL_POSITIVE)
else
lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, contrast_ctr);
- bl->props.fb_blank = bl->props.power = sinfo->bl_power = power;
-
return 0;
}
struct backlight_properties props;
struct backlight_device *bl;
- sinfo->bl_power = FB_BLANK_UNBLANK;
-
if (sinfo->backlight)
return;
unsigned int reg = aty_ld_le32(LVDS_GEN_CNTL);
int level;
- if (bd->props.power != FB_BLANK_UNBLANK ||
- bd->props.fb_blank != FB_BLANK_UNBLANK ||
- !par->lcd_on)
+ if (!par->lcd_on)
level = 0;
else
- level = bd->props.brightness;
+ level = backlight_get_brightness(bd);
reg |= LVDS_BL_MOD_EN | LVDS_BLON;
if (level > 0) {
{
struct atyfb_par *par = bl_get_data(bd);
unsigned int reg = aty_ld_lcd(LCD_MISC_CNTL, par);
- int level;
-
- if (bd->props.power != FB_BLANK_UNBLANK ||
- bd->props.fb_blank != FB_BLANK_UNBLANK)
- level = 0;
- else
- level = bd->props.brightness;
+ int level = backlight_get_brightness(bd);
reg |= (BLMOD_EN | BIASMOD_EN);
if (level > 0) {
* which we print to the screen.
*/
id = *(u8 *)par->lcd_table;
- strncpy(model, (char *)par->lcd_table+1, 24);
- model[23] = 0;
+ strscpy(model, (char *)par->lcd_table+1, sizeof(model));
width = par->lcd_width = *(u16 *)(par->lcd_table+25);
height = par->lcd_height = *(u16 *)(par->lcd_table+27);
* backlight. This provides some greater power saving and the display
* is useless without backlight anyway.
*/
- if (bd->props.power != FB_BLANK_UNBLANK ||
- bd->props.fb_blank != FB_BLANK_UNBLANK)
- level = 0;
- else
- level = bd->props.brightness;
+ level = backlight_get_brightness(bd);
del_timer_sync(&rinfo->lvds_timer);
radeon_engine_idle();
}
EXPORT_SYMBOL_GPL(fb_deferred_io_open);
-void fb_deferred_io_cleanup(struct fb_info *info)
+void fb_deferred_io_release(struct fb_info *info)
{
struct fb_deferred_io *fbdefio = info->fbdefio;
struct page *page;
page = fb_deferred_io_page(info, i);
page->mapping = NULL;
}
+}
+EXPORT_SYMBOL_GPL(fb_deferred_io_release);
+
+void fb_deferred_io_cleanup(struct fb_info *info)
+{
+ struct fb_deferred_io *fbdefio = info->fbdefio;
+
+ fb_deferred_io_release(info);
kvfree(info->pagerefs);
mutex_destroy(&fbdefio->lock);
h > FBCON_SWAP(info->var.rotate, info->var.yres, info->var.xres))
return -EINVAL;
+ if (font->width > 32 || font->height > 32)
+ return -EINVAL;
+
/* Make sure drawing engine can handle the font */
- if (!(info->pixmap.blit_x & (1 << (font->width - 1))) ||
- !(info->pixmap.blit_y & (1 << (font->height - 1))))
+ if (!(info->pixmap.blit_x & BIT(font->width - 1)) ||
+ !(info->pixmap.blit_y & BIT(font->height - 1)))
return -EINVAL;
/* Make sure driver can handle the font length */
struct fb_info * const info = file->private_data;
lock_fb_info(info);
+#if IS_ENABLED(CONFIG_FB_DEFERRED_IO)
+ if (info->fbdefio)
+ fb_deferred_io_release(info);
+#endif
if (info->fbops->fb_release)
info->fbops->fb_release(info,1);
module_put(info->fbops->owner);
}
/**
- * fb_get_hblank_by_freq - get horizontal blank time given hfreq
+ * fb_get_hblank_by_hfreq - get horizontal blank time given hfreq
* @hfreq: horizontal freq
* @xres: horizontal resolution in pixels
*
.lowlevel = &matrox_G100
};
static struct video_board vbG200eW = {
- .maxvram = 0x100000,
- .maxdisplayable = 0x800000,
+ .maxvram = 0x1000000,
+ .maxdisplayable = 0x0800000,
.accelID = FB_ACCEL_MATROX_MGAG200,
.lowlevel = &matrox_G100
};
static int mx3fb_bl_update_status(struct backlight_device *bl)
{
struct mx3fb_data *fbd = bl_get_data(bl);
- int brightness = bl->props.brightness;
-
- if (bl->props.power != FB_BLANK_UNBLANK)
- brightness = 0;
- if (bl->props.fb_blank != FB_BLANK_UNBLANK)
- brightness = 0;
+ int brightness = backlight_get_brightness(bl);
fbd->backlight_level = (fbd->backlight_level & ~0xFF) | brightness;
{
struct nvidia_par *par = bl_get_data(bd);
u32 tmp_pcrt, tmp_pmc, fpcontrol;
- int level;
+ int level = backlight_get_brightness(bd);
if (!par->FlatPanel)
return 0;
- if (bd->props.power != FB_BLANK_UNBLANK ||
- bd->props.fb_blank != FB_BLANK_UNBLANK)
- level = 0;
- else
- level = bd->props.brightness;
-
tmp_pmc = NV_RD32(par->PMC, 0x10F0) & 0x0000FFFF;
tmp_pcrt = NV_RD32(par->PCRTC0, 0x081C) & 0xFFFFFFFC;
fpcontrol = NV_RD32(par->PRAMDAC, 0x0848) & 0xCFFFFFCC;
return nvidiafb_check_var(&info->var, info);
}
-static u32 nvidia_get_chipset(struct fb_info *info)
+static u32 nvidia_get_chipset(struct pci_dev *pci_dev,
+ volatile u32 __iomem *REGS)
{
- struct nvidia_par *par = info->par;
- u32 id = (par->pci_dev->vendor << 16) | par->pci_dev->device;
+ u32 id = (pci_dev->vendor << 16) | pci_dev->device;
printk(KERN_INFO PFX "Device ID: %x \n", id);
if ((id & 0xfff0) == 0x00f0 ||
(id & 0xfff0) == 0x02e0) {
/* pci-e */
- id = NV_RD32(par->REGS, 0x1800);
+ id = NV_RD32(REGS, 0x1800);
if ((id & 0x0000ffff) == 0x000010DE)
id = 0x10DE0000 | (id >> 16);
return id;
}
-static u32 nvidia_get_arch(struct fb_info *info)
+static u32 nvidia_get_arch(u32 Chipset)
{
- struct nvidia_par *par = info->par;
u32 arch = 0;
- switch (par->Chipset & 0x0ff0) {
+ switch (Chipset & 0x0ff0) {
case 0x0100: /* GeForce 256 */
case 0x0110: /* GeForce2 MX */
case 0x0150: /* GeForce2 */
struct fb_info *info;
unsigned short cmd;
int ret;
+ volatile u32 __iomem *REGS;
+ int Chipset;
+ u32 Architecture;
NVTRACE_ENTER();
assert(pd != NULL);
+ if (pci_enable_device(pd)) {
+ printk(KERN_ERR PFX "cannot enable PCI device\n");
+ return -ENODEV;
+ }
+
+ /* enable IO and mem if not already done */
+ pci_read_config_word(pd, PCI_COMMAND, &cmd);
+ cmd |= (PCI_COMMAND_IO | PCI_COMMAND_MEMORY);
+ pci_write_config_word(pd, PCI_COMMAND, cmd);
+
+ nvidiafb_fix.mmio_start = pci_resource_start(pd, 0);
+ nvidiafb_fix.mmio_len = pci_resource_len(pd, 0);
+
+ REGS = ioremap(nvidiafb_fix.mmio_start, nvidiafb_fix.mmio_len);
+ if (!REGS) {
+ printk(KERN_ERR PFX "cannot ioremap MMIO base\n");
+ return -ENODEV;
+ }
+
+ Chipset = nvidia_get_chipset(pd, REGS);
+ Architecture = nvidia_get_arch(Chipset);
+ if (Architecture == 0) {
+ printk(KERN_ERR PFX "unknown NV_ARCH\n");
+ goto err_out;
+ }
+
ret = aperture_remove_conflicting_pci_devices(pd, "nvidiafb");
if (ret)
- return ret;
+ goto err_out;
info = framebuffer_alloc(sizeof(struct nvidia_par), &pd->dev);
-
if (!info)
goto err_out;
if (info->pixmap.addr == NULL)
goto err_out_kfree;
- if (pci_enable_device(pd)) {
- printk(KERN_ERR PFX "cannot enable PCI device\n");
- goto err_out_enable;
- }
-
if (pci_request_regions(pd, "nvidiafb")) {
printk(KERN_ERR PFX "cannot request PCI regions\n");
goto err_out_enable;
par->paneltweak = paneltweak;
par->reverse_i2c = reverse_i2c;
- /* enable IO and mem if not already done */
- pci_read_config_word(pd, PCI_COMMAND, &cmd);
- cmd |= (PCI_COMMAND_IO | PCI_COMMAND_MEMORY);
- pci_write_config_word(pd, PCI_COMMAND, cmd);
-
- nvidiafb_fix.mmio_start = pci_resource_start(pd, 0);
nvidiafb_fix.smem_start = pci_resource_start(pd, 1);
- nvidiafb_fix.mmio_len = pci_resource_len(pd, 0);
-
- par->REGS = ioremap(nvidiafb_fix.mmio_start, nvidiafb_fix.mmio_len);
- if (!par->REGS) {
- printk(KERN_ERR PFX "cannot ioremap MMIO base\n");
- goto err_out_free_base0;
- }
+ par->REGS = REGS;
- par->Chipset = nvidia_get_chipset(info);
- par->Architecture = nvidia_get_arch(info);
-
- if (par->Architecture == 0) {
- printk(KERN_ERR PFX "unknown NV_ARCH\n");
- goto err_out_arch;
- }
+ par->Chipset = Chipset;
+ par->Architecture = Architecture;
sprintf(nvidiafb_fix.id, "NV%x", (pd->device & 0x0ff0) >> 4);
if (NVCommonSetup(info))
- goto err_out_arch;
+ goto err_out_free_base0;
par->FbAddress = nvidiafb_fix.smem_start;
par->FbMapSize = par->RamAmountKBytes * 1024;
goto err_out_iounmap_fb;
}
-
printk(KERN_INFO PFX
"PCI nVidia %s framebuffer (%dMB @ 0x%lX)\n",
info->fix.id,
err_out_free_base1:
fb_destroy_modedb(info->monspecs.modedb);
nvidia_delete_i2c_busses(par);
-err_out_arch:
- iounmap(par->REGS);
- err_out_free_base0:
+err_out_free_base0:
pci_release_regions(pd);
err_out_enable:
kfree(info->pixmap.addr);
err_out_kfree:
framebuffer_release(info);
err_out:
+ iounmap(REGS);
return -ENODEV;
}
info->fbops = &omapfb_ops;
info->flags = FBINFO_FLAG_DEFAULT;
- strncpy(fix->id, MODULE_NAME, sizeof(fix->id));
+ strscpy(fix->id, MODULE_NAME, sizeof(fix->id));
info->pseudo_palette = fbdev->pseudo_palette;
fbdev->ctrl = NULL;
- strncpy(name, conf->lcd.ctrl_name, sizeof(name) - 1);
- name[sizeof(name) - 1] = '\0';
+ strscpy(name, conf->lcd.ctrl_name, sizeof(name));
if (strcmp(name, "internal") == 0) {
fbdev->ctrl = fbdev->int_ctrl;
struct panel_drv_data *ddata = dev_get_drvdata(&dev->dev);
struct omap_dss_device *in = ddata->in;
int r;
- int level;
-
- if (dev->props.fb_blank == FB_BLANK_UNBLANK &&
- dev->props.power == FB_BLANK_UNBLANK)
- level = dev->props.brightness;
- else
- level = 0;
+ int level = backlight_get_brightness(dev);
dev_dbg(&ddata->pdev->dev, "update brightness to %d\n", level);
#define DSS_SUBSYS_NAME "DISPLAY"
#include <linux/kernel.h>
+#include <linux/kstrtox.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/sysfs.h>
int r;
bool enable;
- r = strtobool(buf, &enable);
+ r = kstrtobool(buf, &enable);
if (r)
return r;
if (!dssdev->driver->enable_te || !dssdev->driver->get_te)
return -ENOENT;
- r = strtobool(buf, &te);
+ r = kstrtobool(buf, &te);
if (r)
return r;
if (!dssdev->driver->set_mirror || !dssdev->driver->get_mirror)
return -ENOENT;
- r = strtobool(buf, &mirror);
+ r = kstrtobool(buf, &mirror);
if (r)
return r;
{
struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
unsigned long flags;
- struct dsi_irq_stats stats;
+ struct dsi_irq_stats *stats;
+
+ stats = kzalloc(sizeof(*stats), GFP_KERNEL);
+ if (!stats) {
+ seq_printf(s, "out of memory\n");
+ return;
+ }
spin_lock_irqsave(&dsi->irq_stats_lock, flags);
- stats = dsi->irq_stats;
+ *stats = dsi->irq_stats;
memset(&dsi->irq_stats, 0, sizeof(dsi->irq_stats));
dsi->irq_stats.last_reset = jiffies;
spin_unlock_irqrestore(&dsi->irq_stats_lock, flags);
seq_printf(s, "period %u ms\n",
- jiffies_to_msecs(jiffies - stats.last_reset));
+ jiffies_to_msecs(jiffies - stats->last_reset));
- seq_printf(s, "irqs %d\n", stats.irq_count);
+ seq_printf(s, "irqs %d\n", stats->irq_count);
#define PIS(x) \
- seq_printf(s, "%-20s %10d\n", #x, stats.dsi_irqs[ffs(DSI_IRQ_##x)-1])
+ seq_printf(s, "%-20s %10d\n", #x, stats->dsi_irqs[ffs(DSI_IRQ_##x)-1])
seq_printf(s, "-- DSI%d interrupts --\n", dsi->module_id + 1);
PIS(VC0);
#define PIS(x) \
seq_printf(s, "%-20s %10d %10d %10d %10d\n", #x, \
- stats.vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]);
+ stats->vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]);
seq_printf(s, "-- VC interrupts --\n");
PIS(CS);
#define PIS(x) \
seq_printf(s, "%-20s %10d\n", #x, \
- stats.cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]);
+ stats->cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]);
seq_printf(s, "-- CIO interrupts --\n");
PIS(ERRSYNCESC1);
PIS(ULPSACTIVENOT_ALL0);
PIS(ULPSACTIVENOT_ALL1);
#undef PIS
+
+ kfree(stats);
}
static void dsi1_dump_irqs(struct seq_file *s)
#define DSS_SUBSYS_NAME "MANAGER"
#include <linux/kernel.h>
+#include <linux/kstrtox.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/platform_device.h>
bool enable;
int r;
- r = strtobool(buf, &enable);
+ r = kstrtobool(buf, &enable);
if (r)
return r;
if(!dss_has_feature(FEAT_ALPHA_FIXED_ZORDER))
return -ENODEV;
- r = strtobool(buf, &enable);
+ r = kstrtobool(buf, &enable);
if (r)
return r;
if (!dss_has_feature(FEAT_CPR))
return -ENODEV;
- r = strtobool(buf, &enable);
+ r = kstrtobool(buf, &enable);
if (r)
return r;
#include <linux/err.h>
#include <linux/sysfs.h>
#include <linux/kobject.h>
+#include <linux/kstrtox.h>
#include <linux/platform_device.h>
#include <video/omapfb_dss.h>
int r;
bool enable;
- r = strtobool(buf, &enable);
+ r = kstrtobool(buf, &enable);
if (r)
return r;
#include <linux/uaccess.h>
#include <linux/platform_device.h>
#include <linux/kernel.h>
+#include <linux/kstrtox.h>
#include <linux/mm.h>
#include <linux/omapfb.h>
int r;
struct fb_var_screeninfo new_var;
- r = strtobool(buf, &mirror);
+ r = kstrtobool(buf, &mirror);
if (r)
return r;
{
struct riva_par *par = bl_get_data(bd);
U032 tmp_pcrt, tmp_pmc;
- int level;
-
- if (bd->props.power != FB_BLANK_UNBLANK ||
- bd->props.fb_blank != FB_BLANK_UNBLANK)
- level = 0;
- else
- level = bd->props.brightness;
+ int level = backlight_get_brightness(bd);
tmp_pmc = NV_RD32(par->riva.PMC, 0x10F0) & 0x0000FFFF;
tmp_pcrt = NV_RD32(par->riva.PCRTC0, 0x081C) & 0xFFFFFFFC;
"Video memory size in MB, width, height in pixels (default 2,800,600)");
static void xenfb_make_preferred_console(void);
-static int xenfb_remove(struct xenbus_device *);
+static void xenfb_remove(struct xenbus_device *);
static void xenfb_init_shared_page(struct xenfb_info *, struct fb_info *);
static int xenfb_connect_backend(struct xenbus_device *, struct xenfb_info *);
static void xenfb_disconnect_backend(struct xenfb_info *);
return xenfb_connect_backend(dev, info);
}
-static int xenfb_remove(struct xenbus_device *dev)
+static void xenfb_remove(struct xenbus_device *dev)
{
struct xenfb_info *info = dev_get_drvdata(&dev->dev);
vfree(info->gfns);
vfree(info->fb);
kfree(info);
-
- return 0;
}
static unsigned long vmalloc_to_gfn(void *address)
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%04x\n", dev->id.device);
+ return sysfs_emit(buf, "0x%04x\n", dev->id.device);
}
static DEVICE_ATTR_RO(device);
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
+ return sysfs_emit(buf, "0x%04x\n", dev->id.vendor);
}
static DEVICE_ATTR_RO(vendor);
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
+ return sysfs_emit(buf, "0x%08x\n", dev->config->get_status(dev));
}
static DEVICE_ATTR_RO(status);
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "virtio:d%08Xv%08X\n",
+ return sysfs_emit(buf, "virtio:d%08Xv%08X\n",
dev->id.device, dev->id.vendor);
}
static DEVICE_ATTR_RO(modalias);
/* We actually represent this as a bitstring, as it could be
* arbitrary length in future. */
for (i = 0; i < sizeof(dev->features)*8; i++)
- len += sprintf(buf+len, "%c",
+ len += sysfs_emit_at(buf, len, "%c",
__virtio_test_bit(dev, i) ? '1' : '0');
- len += sprintf(buf+len, "\n");
+ len += sysfs_emit_at(buf, len, "\n");
return len;
}
static DEVICE_ATTR_RO(features);
int err;
if (index >= vp_modern_get_num_queues(mdev))
- return ERR_PTR(-ENOENT);
+ return ERR_PTR(-EINVAL);
/* Check if queue is either not available or already active. */
num = vp_modern_get_queue_size(mdev, index);
if (!num || vp_modern_get_queue_enable(mdev, index))
return ERR_PTR(-ENOENT);
- if (num & (num - 1)) {
+ if (!is_power_of_2(num)) {
dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
return ERR_PTR(-EINVAL);
}
dma_addr_t dma_addr;
/* We assume num is a power of 2. */
- if (num & (num - 1)) {
+ if (!is_power_of_2(num)) {
dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
return -EINVAL;
}
/* remainder if it woke up early */
unsigned long jremain = 0;
+ atomic_inc(&dev->refcnt);
+
for (;;) {
if (!jremain && dev->search_count) {
*/
mutex_unlock(&dev->list_mutex);
- if (kthread_should_stop())
+ if (kthread_should_stop()) {
+ __set_current_state(TASK_RUNNING);
break;
+ }
/* Only sleep when the search is active. */
if (dev->search_count) {
dev->search_count = w1_search_count;
dev->enable_pullup = w1_enable_pullup;
- /* 1 for w1_process to decrement
- * 1 for __w1_remove_master_device to decrement
+ /* For __w1_remove_master_device to decrement
*/
- atomic_set(&dev->refcnt, 2);
+ atomic_set(&dev->refcnt, 1);
INIT_LIST_HEAD(&dev->slist);
INIT_LIST_HEAD(&dev->async_list);
"1:\n"
EX_TABLE(0b, 1b)
: "+d" (err) : "d"(__func), "d"(__timeout),
- "d"(__action), "d"(__len) : "1", "cc");
+ "d"(__action), "d"(__len) : "1", "cc", "memory");
return err;
}
char ebc_begin[] = {
194, 197, 199, 201, 213
};
+ char *ebc_cmd;
watchdog_set_nowayout(&wdt_dev, nowayout_info);
if (MACHINE_IS_VM) {
- if (__diag288_vm(WDT_FUNC_INIT, 15,
- ebc_begin, sizeof(ebc_begin)) != 0) {
+ ebc_cmd = kmalloc(sizeof(ebc_begin), GFP_KERNEL);
+ if (!ebc_cmd) {
+ pr_err("The watchdog cannot be initialized\n");
+ return -ENOMEM;
+ }
+ memcpy(ebc_cmd, ebc_begin, sizeof(ebc_begin));
+ ret = __diag288_vm(WDT_FUNC_INIT, 15,
+ ebc_cmd, sizeof(ebc_begin));
+ kfree(ebc_cmd);
+ if (ret != 0) {
pr_err("The watchdog cannot be initialized\n");
return -EINVAL;
}
}
}
-static int pvcalls_back_remove(struct xenbus_device *dev)
+static void pvcalls_back_remove(struct xenbus_device *dev)
{
- return 0;
}
static int pvcalls_back_uevent(struct xenbus_device *xdev,
return IRQ_HANDLED;
}
+static void free_active_ring(struct sock_mapping *map);
+
static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
struct sock_mapping *map)
{
for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
gnttab_end_foreign_access(map->active.ring->ref[i], NULL);
gnttab_end_foreign_access(map->active.ref, NULL);
- free_page((unsigned long)map->active.ring);
+ free_active_ring(map);
kfree(map);
}
{ "" }
};
-static int pvcalls_front_remove(struct xenbus_device *dev)
+static void pvcalls_front_remove(struct xenbus_device *dev)
{
struct pvcalls_bedata *bedata;
struct sock_mapping *map = NULL, *n;
kfree(bedata->ring.sring);
kfree(bedata);
xenbus_switch_state(dev, XenbusStateClosed);
- return 0;
}
static int pvcalls_front_probe(struct xenbus_device *dev,
return err;
}
-static int xen_pcibk_xenbus_remove(struct xenbus_device *dev)
+static void xen_pcibk_xenbus_remove(struct xenbus_device *dev)
{
struct xen_pcibk_device *pdev = dev_get_drvdata(&dev->dev);
if (pdev != NULL)
free_pdev(pdev);
-
- return 0;
}
static const struct xenbus_device_id xen_pcibk_ids[] = {
spin_unlock_irqrestore(&info->v2p_lock, flags);
}
-static int scsiback_remove(struct xenbus_device *dev)
+static void scsiback_remove(struct xenbus_device *dev)
{
struct vscsibk_info *info = dev_get_drvdata(&dev->dev);
gnttab_page_cache_shrink(&info->free_pages, 0);
dev_set_drvdata(&dev->dev, NULL);
-
- return 0;
}
static int scsiback_probe(struct xenbus_device *dev,
if (inode->i_size > AFFS_I(inode)->mmu_private) {
struct address_space *mapping = inode->i_mapping;
struct page *page;
- void *fsdata;
+ void *fsdata = NULL;
loff_t isize = inode->i_size;
int res;
#include "internal.h"
#include "afs_cm.h"
#include "protocol_yfs.h"
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
static int afs_deliver_cb_init_call_back_state(struct afs_call *);
static int afs_deliver_cb_init_call_back_state3(struct afs_call *);
* Abort a service call from within an action function.
*/
static void afs_abort_service_call(struct afs_call *call, u32 abort_code, int error,
- const char *why)
+ enum rxrpc_abort_reason why)
{
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
abort_code, error, why);
if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0)
afs_send_empty_reply(call);
else
- afs_abort_service_call(call, 1, 1, "K-1");
+ afs_abort_service_call(call, 1, 1, afs_abort_probeuuid_negative);
afs_put_call(call);
_leave("");
#include "internal.h"
#include "afs_cm.h"
#include "protocol_yfs.h"
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
struct workqueue_struct *afs_async_calls;
error_do_abort:
if (ret != -ECONNABORTED) {
rxrpc_kernel_abort_call(call->net->socket, rxcall,
- RX_USER_ABORT, ret, "KSD");
+ RX_USER_ABORT, ret,
+ afs_abort_send_data_error);
} else {
len = 0;
iov_iter_kvec(&msg.msg_iter, ITER_DEST, NULL, 0, 0);
case -ENOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KIV");
+ abort_code, ret,
+ afs_abort_op_not_supported);
goto local_abort;
case -EIO:
pr_err("kAFS: Call %u in bad state %u\n",
if (state != AFS_CALL_CL_AWAIT_REPLY)
abort_code = RXGEN_SS_UNMARSHAL;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KUM");
+ abort_code, ret,
+ afs_abort_unmarshal_error);
goto local_abort;
default:
abort_code = RX_CALL_DEAD;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KER");
+ abort_code, ret,
+ afs_abort_general_error);
goto local_abort;
}
}
/* Kill off the call if it's still live. */
_debug("call interrupted");
if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- RX_USER_ABORT, -EINTR, "KWI"))
+ RX_USER_ABORT, -EINTR,
+ afs_abort_interrupted))
afs_set_call_complete(call, -EINTR, 0);
}
}
case -ENOMEM:
_debug("oom");
rxrpc_kernel_abort_call(net->socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "KOO");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ afs_abort_oom);
fallthrough;
default:
_leave(" [error]");
if (n == -ENOMEM) {
_debug("oom");
rxrpc_kernel_abort_call(net->socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "KOO");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ afs_abort_oom);
}
_leave(" [error]");
}
ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter,
&call->iov_len, want_more, &remote_abort,
&call->service_id);
+ trace_afs_receive_data(call, call->iter, want_more, ret);
if (ret == 0 || ret == -EAGAIN)
return ret;
spin_lock(&mm->ioctx_lock);
rcu_read_lock();
table = rcu_dereference(mm->ioctx_table);
+ if (!table)
+ goto out_unlock;
+
for (i = 0; i < table->nr; i++) {
struct kioctx *ctx;
}
}
+out_unlock:
rcu_read_unlock();
spin_unlock(&mm->ioctx_lock);
return res;
* The number of segs are recored into ELF header as 16bit value.
* Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
*/
- segs = cprm->vma_count + elf_core_extra_phdrs();
+ segs = cprm->vma_count + elf_core_extra_phdrs(cprm);
/* for notes section */
segs++;
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
offset += cprm->vma_data_size;
- offset += elf_core_extra_data_size();
+ offset += elf_core_extra_data_size(cprm);
e_shoff = offset;
if (e_phnum == PN_XNUM) {
tmp->next = thread_list;
thread_list = tmp;
- segs = cprm->vma_count + elf_core_extra_phdrs();
+ segs = cprm->vma_count + elf_core_extra_phdrs(cprm);
/* for notes section */
segs++;
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
offset += cprm->vma_data_size;
- offset += elf_core_extra_data_size();
+ offset += elf_core_extra_data_size(cprm);
e_shoff = offset;
if (e_phnum == PN_XNUM) {
u64 wanted_disk_byte = ref->wanted_disk_byte;
u64 count = 0;
u64 data_offset;
+ u8 type;
if (level != 0) {
eb = path->nodes[level];
continue;
}
fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(eb, fi);
+ if (type == BTRFS_FILE_EXTENT_INLINE)
+ goto next;
disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
data_offset = btrfs_file_extent_offset(eb, fi);
&map_length, &bioc, mirror_num);
if (ret)
goto out_counter_dec;
- BUG_ON(mirror_num != bioc->mirror_num);
+ /*
+ * This happens when dev-replace is also running, and the
+ * mirror_num indicates the dev-replace target.
+ *
+ * In this case, we don't need to do anything, as the read
+ * error just means the replace progress hasn't reached our
+ * read range, and later replace routine would handle it well.
+ */
+ if (mirror_num != bioc->mirror_num)
+ goto out_counter_dec;
}
sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
goto out;
path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
level = btrfs_header_level(root->node);
btrfs_print_tree(eb, 0);
btrfs_err(fs_info, "block=%llu write time tree block corruption detected",
eb->start);
- WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+ /*
+ * Be noisy if this is an extent buffer from a log tree. We don't abort
+ * a transaction in case there's a bad log tree extent buffer, we just
+ * fallback to a transaction commit. Still we want to know when there is
+ * a bad log tree extent buffer, as that may signal a bug somewhere.
+ */
+ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) ||
+ btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID);
return ret;
}
}
if (found_level != check->level) {
+ btrfs_err(fs_info,
+ "level verify failed on logical %llu mirror %u wanted %u found %u",
+ eb->start, eb->read_mirror, check->level, found_level);
ret = -EIO;
goto out;
}
/*
* Do various sanity and dependency checks of different features.
*
+ * @is_rw_mount: If the mount is read-write.
+ *
* This is the place for less strict checks (like for subpage or artificial
* feature dependencies).
*
* (space cache related) can modify on-disk format like free space tree and
* screw up certain feature dependencies.
*/
-int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb)
+int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
{
struct btrfs_super_block *disk_super = fs_info->super_copy;
u64 incompat = btrfs_super_incompat_flags(disk_super);
if (btrfs_super_nodesize(disk_super) > PAGE_SIZE)
incompat |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
- if (compat_ro_unsupp && !sb_rdonly(sb)) {
+ if (compat_ro_unsupp && is_rw_mount) {
btrfs_err(fs_info,
"cannot mount read-write because of unknown compat_ro features (0x%llx)",
compat_ro);
goto fail_alloc;
}
- ret = btrfs_check_features(fs_info, sb);
+ ret = btrfs_check_features(fs_info, !sb_rdonly(sb));
if (ret < 0) {
err = ret;
goto fail_alloc;
void __cold close_ctree(struct btrfs_fs_info *fs_info);
int btrfs_validate_super(struct btrfs_fs_info *fs_info,
struct btrfs_super_block *sb, int mirror_num);
-int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb);
+int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount);
int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev);
struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
u64 last = 0;
int found = 0;
- if (WARN_ON(search_end <= cur_start))
+ if (WARN_ON(search_end < cur_start))
return 0;
spin_lock(&tree->lock);
BUG();
if (ret && insert_reserved)
btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+ if (ret < 0)
+ btrfs_err(trans->fs_info,
+"failed to run delayed ref for logical %llu num_bytes %llu type %u action %u ref_mod %d: %d",
+ node->bytenr, node->num_bytes, node->type,
+ node->action, node->ref_mod, ret);
return ret;
}
if (ret) {
unselect_delayed_ref_head(delayed_refs, locked_ref);
btrfs_put_delayed_ref(ref);
- btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
- ret);
return ret;
}
u32 len_to_oe_boundary;
btrfs_bio_end_io_t end_io_func;
+ /*
+ * This is for metadata read, to provide the extra needed verification
+ * info. This has to be provided for submit_one_bio(), as
+ * submit_one_bio() can submit a bio if it ends at stripe boundary. If
+ * no such parent_check is provided, the metadata can hit false alert at
+ * endio time.
+ */
+ struct btrfs_tree_parent_check *parent_check;
+
/*
* Tell writepage not to lock the state bits for this range, it still
* does the unlocking.
btrfs_bio(bio)->file_offset = page_offset(bv->bv_page) + bv->bv_offset;
- if (!is_data_inode(&inode->vfs_inode))
+ if (!is_data_inode(&inode->vfs_inode)) {
+ if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
+ /*
+ * For metadata read, we should have the parent_check,
+ * and copy it to bbio for metadata verification.
+ */
+ ASSERT(bio_ctrl->parent_check);
+ memcpy(&btrfs_bio(bio)->parent_check,
+ bio_ctrl->parent_check,
+ sizeof(struct btrfs_tree_parent_check));
+ }
btrfs_submit_metadata_bio(inode, bio, mirror_num);
- else if (btrfs_op(bio) == BTRFS_MAP_WRITE)
+ } else if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
btrfs_submit_data_write_bio(inode, bio, mirror_num);
- else
+ } else {
btrfs_submit_data_read_bio(inode, bio, mirror_num,
bio_ctrl->compress_type);
+ }
/* The bio is owned by the end_io handler now */
bio_ctrl->bio = NULL;
lockend = round_up(start + len, inode->root->fs_info->sectorsize);
prev_extent_end = lockstart;
+ btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end);
out_unlock:
unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
out:
free_extent_state(delalloc_cached_state);
btrfs_free_backref_share_ctx(backref_ctx);
struct extent_state *cached_state = NULL;
struct btrfs_bio_ctrl bio_ctrl = {
.mirror_num = mirror_num,
+ .parent_check = check,
};
int ret = 0;
*/
atomic_dec(&eb->io_pages);
}
- memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
submit_one_bio(&bio_ctrl);
if (ret || wait != WAIT_COMPLETE) {
free_extent_state(cached_state);
unsigned long num_reads = 0;
struct btrfs_bio_ctrl bio_ctrl = {
.mirror_num = mirror_num,
+ .parent_check = check,
};
if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
}
}
- memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
submit_one_bio(&bio_ctrl);
if (ret || wait != WAIT_COMPLETE)
bool search_io_tree = true;
bool ret = false;
- while (cur_offset < end) {
+ while (cur_offset <= end) {
u64 delalloc_start;
u64 delalloc_end;
bool delalloc;
struct extent_buffer *leaf = path->nodes[0];
struct btrfs_file_extent_item *extent;
u64 extent_end;
+ u8 type;
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
ret = btrfs_next_leaf(root, path);
extent = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(leaf, extent);
- if (btrfs_file_extent_disk_bytenr(leaf, extent) == 0 ||
- btrfs_file_extent_type(leaf, extent) ==
- BTRFS_FILE_EXTENT_PREALLOC) {
+ /*
+ * Can't access the extent's disk_bytenr field if this is an
+ * inline extent, since at that offset, it's where the extent
+ * data starts.
+ */
+ if (type == BTRFS_FILE_EXTENT_PREALLOC ||
+ (type == BTRFS_FILE_EXTENT_REG &&
+ btrfs_file_extent_disk_bytenr(leaf, extent) == 0)) {
/*
* Explicit hole or prealloc extent, search for delalloc.
* A prealloc extent is treated like a hole.
/* Indicate that we want to commit the transaction. */
BTRFS_FS_NEED_TRANS_COMMIT,
+ /*
+ * Indicate metadata over-commit is disabled. This is set when active
+ * zone tracking is needed.
+ */
+ BTRFS_FS_NO_OVERCOMMIT,
+
#if BITS_PER_LONG == 32
/* Indicate if we have error/warn message printed on 32bit systems */
BTRFS_FS_32BIT_ERROR,
* Other members are not utilized for inline extents.
*/
ASSERT(em->block_start == EXTENT_MAP_INLINE);
- ASSERT(em->len = fs_info->sectorsize);
+ ASSERT(em->len == fs_info->sectorsize);
ret = read_inline_extent(inode, path, page);
if (ret < 0)
if (flags & RENAME_WHITEOUT) {
whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir);
- if (!whiteout_args.inode)
- return -ENOMEM;
+ if (!whiteout_args.inode) {
+ ret = -ENOMEM;
+ goto out_fscrypt_names;
+ }
ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items);
if (ret)
goto out_whiteout_inode;
/*
* Old roots should be searched when inserting qgroup
- * extent record
+ * extent record.
+ *
+ * But for INCONSISTENT (NO_ACCOUNTING) -> rescan case,
+ * we may have some record inserted during
+ * NO_ACCOUNTING (thus no old_roots populated), but
+ * later we start rescan, which clears NO_ACCOUNTING,
+ * leaving some inserted records without old_roots
+ * populated.
+ *
+ * Those cases are rare and should not cause too much
+ * time spent during commit_transaction().
*/
- if (WARN_ON(!record->old_roots)) {
+ if (!record->old_roots) {
/* Search commit root to find old_roots */
ret = btrfs_find_all_roots(&ctx, false);
if (ret < 0)
* current root. It's safe inside commit_transaction().
*/
ctx.trans = trans;
+ ctx.time_seq = BTRFS_SEQ_LAST;
ret = btrfs_find_all_roots(&ctx, false);
if (ret < 0)
goto cleanup;
int err = -ENOMEM;
int ret = 0;
bool stopped = false;
+ bool did_leaf_rescans = false;
path = btrfs_alloc_path();
if (!path)
}
err = qgroup_rescan_leaf(trans, path);
+ did_leaf_rescans = true;
if (err > 0)
btrfs_commit_transaction(trans);
mutex_unlock(&fs_info->qgroup_rescan_lock);
/*
- * only update status, since the previous part has already updated the
- * qgroup info.
+ * Only update status, since the previous part has already updated the
+ * qgroup info, and only if we did any actual work. This also prevents
+ * race with a concurrent quota disable, which has already set
+ * fs_info->quota_root to NULL and cleared BTRFS_FS_QUOTA_ENABLED at
+ * btrfs_quota_disable().
*/
- trans = btrfs_start_transaction(fs_info->quota_root, 1);
- if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
+ if (did_leaf_rescans) {
+ trans = btrfs_start_transaction(fs_info->quota_root, 1);
+ if (IS_ERR(trans)) {
+ err = PTR_ERR(trans);
+ trans = NULL;
+ btrfs_err(fs_info,
+ "fail to start transaction for status update: %d",
+ err);
+ }
+ } else {
trans = NULL;
- btrfs_err(fs_info,
- "fail to start transaction for status update: %d",
- err);
}
mutex_lock(&fs_info->qgroup_rescan_lock);
u32 bio_size = 0;
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
+ int i;
bio_for_each_segment_all(bvec, bio, iter_all)
bio_size += bvec->bv_len;
- bitmap_set(rbio->error_bitmap, total_sector_nr,
- bio_size >> rbio->bioc->fs_info->sectorsize_bits);
+ /*
+ * Since we can have multiple bios touching the error_bitmap, we cannot
+ * call bitmap_set() without protection.
+ *
+ * Instead use set_bit() for each bit, as set_bit() itself is atomic.
+ */
+ for (i = total_sector_nr; i < total_sector_nr +
+ (bio_size >> rbio->bioc->fs_info->sectorsize_bits); i++)
+ set_bit(i, rbio->error_bitmap);
}
/* Verify the data sectors at read time. */
sector->uptodate = 1;
}
if (failb >= 0) {
- ret = verify_one_sector(rbio, faila, sector_nr);
+ ret = verify_one_sector(rbio, failb, sector_nr);
if (ret < 0)
goto cleanup;
void **pointers = NULL;
void **unmap_array = NULL;
int sector_nr;
- int ret;
+ int ret = 0;
/*
* @pointers array stores the pointer for each sector.
/*
* Check that we don't overflow at later allocations, we request
* clone_sources_count + 1 items, and compare to unsigned long inside
- * access_ok.
+ * access_ok. Also set an upper limit for allocation size so this can't
+ * easily exhaust memory. Max number of clone sources is about 200K.
*/
- if (arg->clone_sources_count >
- ULONG_MAX / sizeof(struct clone_root) - 1) {
+ if (arg->clone_sources_count > SZ_8M / sizeof(struct clone_root)) {
ret = -EINVAL;
goto out;
}
return 0;
used = btrfs_space_info_used(space_info, true);
- if (btrfs_is_zoned(fs_info) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
+ if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) &&
+ (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
avail = 0;
else
avail = calc_available_free_space(fs_info, space_info, flush);
if (ret)
goto restore;
- ret = btrfs_check_features(fs_info, sb);
+ ret = btrfs_check_features(fs_info, !(*flags & SB_RDONLY));
if (ret < 0)
goto restore;
static void __exit exit_btrfs_fs(void)
{
btrfs_exit_btrfs_fs();
+ btrfs_cleanup_fs_uuids();
}
static int __init init_btrfs_fs(void)
ret = 0;
if (ret) {
blk_finish_plug(&plug);
- btrfs_abort_transaction(trans, ret);
btrfs_set_log_full_commit(trans);
mutex_unlock(&root->log_mutex);
goto out;
blk_finish_plug(&plug);
btrfs_set_log_full_commit(trans);
-
- if (ret != -ENOSPC) {
- btrfs_abort_transaction(trans, ret);
- mutex_unlock(&log_root_tree->log_mutex);
- goto out;
- }
+ if (ret != -ENOSPC)
+ btrfs_err(fs_info,
+ "failed to update log for root %llu ret %d",
+ root->root_key.objectid, ret);
btrfs_wait_tree_log_extents(log, mark);
mutex_unlock(&log_root_tree->log_mutex);
- ret = BTRFS_LOG_FORCE_COMMIT;
goto out;
}
goto out_wake_log_root;
} else if (ret) {
btrfs_set_log_full_commit(trans);
- btrfs_abort_transaction(trans, ret);
mutex_unlock(&log_root_tree->log_mutex);
goto out_wake_log_root;
}
}
static int flush_dir_items_batch(struct btrfs_trans_handle *trans,
- struct btrfs_root *log,
+ struct btrfs_inode *inode,
struct extent_buffer *src,
struct btrfs_path *dst_path,
int start_slot,
int count)
{
+ struct btrfs_root *log = inode->root->log_root;
char *ins_data = NULL;
struct btrfs_item_batch batch;
struct extent_buffer *dst;
unsigned long src_offset;
unsigned long dst_offset;
+ u64 last_index;
struct btrfs_key key;
u32 item_size;
int ret;
src_offset = btrfs_item_ptr_offset(src, start_slot + count - 1);
copy_extent_buffer(dst, src, dst_offset, src_offset, batch.total_data_size);
btrfs_release_path(dst_path);
+
+ last_index = batch.keys[count - 1].offset;
+ ASSERT(last_index > inode->last_dir_index_offset);
+
+ /*
+ * If for some unexpected reason the last item's index is not greater
+ * than the last index we logged, warn and return an error to fallback
+ * to a transaction commit.
+ */
+ if (WARN_ON(last_index <= inode->last_dir_index_offset))
+ ret = -EUCLEAN;
+ else
+ inode->last_dir_index_offset = last_index;
out:
kfree(ins_data);
}
di = btrfs_item_ptr(src, i, struct btrfs_dir_item);
- ctx->last_dir_item_offset = key.offset;
/*
* Skip ranges of items that consist only of dir item keys created
if (batch_size > 0) {
int ret;
- ret = flush_dir_items_batch(trans, log, src, dst_path,
+ ret = flush_dir_items_batch(trans, inode, src, dst_path,
batch_start, batch_size);
if (ret < 0)
return ret;
path->slots[0]);
if (tmp.type == BTRFS_DIR_INDEX_KEY)
last_old_dentry_offset = tmp.offset;
+ } else if (ret < 0) {
+ err = ret;
}
+
goto done;
}
*/
if (tmp.type == BTRFS_DIR_INDEX_KEY)
last_old_dentry_offset = tmp.offset;
+ } else if (ret < 0) {
+ err = ret;
+ goto done;
}
+
btrfs_release_path(path);
/*
- * Find the first key from this transaction again. See the note for
- * log_new_dir_dentries, if we're logging a directory recursively we
- * won't be holding its i_mutex, which means we can modify the directory
- * while we're logging it. If we remove an entry between our first
- * search and this search we'll not find the key again and can just
- * bail.
+ * Find the first key from this transaction again or the one we were at
+ * in the loop below in case we had to reschedule. We may be logging the
+ * directory without holding its VFS lock, which happen when logging new
+ * dentries (through log_new_dir_dentries()) or in some cases when we
+ * need to log the parent directory of an inode. This means a dir index
+ * key might be deleted from the inode's root, and therefore we may not
+ * find it anymore. If we can't find it, just move to the next key. We
+ * can not bail out and ignore, because if we do that we will simply
+ * not log dir index keys that come after the one that was just deleted
+ * and we can end up logging a dir index range that ends at (u64)-1
+ * (@last_offset is initialized to that), resulting in removing dir
+ * entries we should not remove at log replay time.
*/
search:
ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
+ if (ret > 0)
+ ret = btrfs_next_item(root, path);
+ if (ret < 0)
+ err = ret;
+ /* If ret is 1, there are no more keys in the inode's root. */
if (ret != 0)
goto done;
min_key = BTRFS_DIR_START_INDEX;
max_key = 0;
- ctx->last_dir_item_offset = inode->last_dir_index_offset;
while (1) {
ret = log_dir_items(trans, inode, path, dst_path,
min_key = max_key + 1;
}
- inode->last_dir_index_offset = ctx->last_dir_item_offset;
-
return 0;
}
* LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction
* commits.
*/
- if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES)
+ if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) {
+ btrfs_set_log_full_commit(trans);
return BTRFS_LOG_FORCE_COMMIT;
+ }
inode = btrfs_iget(root->fs_info->sb, ino, root);
/*
* not fail, but if it does, it's not serious, just bail out and
* mark the log for a full commit.
*/
- if (WARN_ON_ONCE(ret < 0))
+ if (WARN_ON_ONCE(ret < 0)) {
+ fscrypt_free_filename(&fname);
goto out;
+ }
+
log_pinned = true;
path = btrfs_alloc_path();
bool logging_new_delayed_dentries;
/* Indicate if the inode being logged was logged before. */
bool logged_before;
- /* Tracks the last logged dir item/index key offset. */
- u64 last_dir_item_offset;
struct inode *inode;
struct list_head list;
/* Only used for fast fsyncs. */
static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
{
struct btrfs_device *device;
+
WARN_ON(fs_devices->opened);
while (!list_empty(&fs_devices->devices)) {
device = list_entry(fs_devices->devices.next,
BTRFS_SUPER_FLAG_CHANGING_FSID_V2);
error = lookup_bdev(path, &path_devt);
- if (error)
+ if (error) {
+ btrfs_err(NULL, "failed to lookup block device for path %s: %d",
+ path, error);
return ERR_PTR(error);
+ }
if (fsid_change_in_progress) {
if (!has_metadata_uuid)
unsigned int nofs_flag;
if (fs_devices->opened) {
+ btrfs_err(NULL,
+ "device %s belongs to fsid %pU, and the fs is already mounted",
+ path, fs_devices->fsid);
mutex_unlock(&fs_devices->device_list_mutex);
return ERR_PTR(-EBUSY);
}
* generation are equal.
*/
mutex_unlock(&fs_devices->device_list_mutex);
+ btrfs_err(NULL,
+"device %s already registered with a higher generation, found %llu expect %llu",
+ path, found_transid, device->generation);
return ERR_PTR(-EEXIST);
}
mutex_lock(&uuid_mutex);
close_fs_devices(fs_devices);
- if (!fs_devices->opened)
+ if (!fs_devices->opened) {
list_splice_init(&fs_devices->seed_list, &list);
+ /*
+ * If the struct btrfs_fs_devices is not assembled with any
+ * other device, it can be re-initialized during the next mount
+ * without the needing device-scan step. Therefore, it can be
+ * fully freed.
+ */
+ if (fs_devices->num_devices == 1) {
+ list_del(&fs_devices->fs_list);
+ free_fs_devices(fs_devices);
+ }
+ }
+
+
list_for_each_entry_safe(fs_devices, tmp, &list, seed_list) {
close_fs_devices(fs_devices);
list_del(&fs_devices->seed_list);
if (ret < 0)
goto out;
- while (1) {
+ while (search_start < search_end) {
l = path->nodes[0];
slot = path->slots[0];
if (slot >= btrfs_header_nritems(l)) {
if (key.type != BTRFS_DEV_EXTENT_KEY)
goto next;
+ if (key.offset > search_end)
+ break;
+
if (key.offset > search_start) {
hole_size = key.offset - search_start;
dev_extent_hole_check(device, &search_start, &hole_size,
else
ret = 0;
+ ASSERT(max_hole_start + max_hole_size <= search_end);
out:
btrfs_free_path(path);
*start = max_hole_start;
return num_devices;
}
+static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info,
+ struct block_device *bdev, int copy_num)
+{
+ struct btrfs_super_block *disk_super;
+ const size_t len = sizeof(disk_super->magic);
+ const u64 bytenr = btrfs_sb_offset(copy_num);
+ int ret;
+
+ disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr);
+ if (IS_ERR(disk_super))
+ return;
+
+ memset(&disk_super->magic, 0, len);
+ folio_mark_dirty(virt_to_folio(disk_super));
+ btrfs_release_disk_super(disk_super);
+
+ ret = sync_blockdev_range(bdev, bytenr, bytenr + len - 1);
+ if (ret)
+ btrfs_warn(fs_info, "error clearing superblock number %d (%d)",
+ copy_num, ret);
+}
+
void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
struct block_device *bdev,
const char *device_path)
{
- struct btrfs_super_block *disk_super;
int copy_num;
if (!bdev)
return;
for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX; copy_num++) {
- struct page *page;
- int ret;
-
- disk_super = btrfs_read_dev_one_super(bdev, copy_num, false);
- if (IS_ERR(disk_super))
- continue;
-
- if (bdev_is_zoned(bdev)) {
+ if (bdev_is_zoned(bdev))
btrfs_reset_sb_log_zones(bdev, copy_num);
- continue;
- }
-
- memset(&disk_super->magic, 0, sizeof(disk_super->magic));
-
- page = virt_to_page(disk_super);
- set_page_dirty(page);
- lock_page(page);
- /* write_on_page() unlocks the page */
- ret = write_one_page(page);
- if (ret)
- btrfs_warn(fs_info,
- "error clearing superblock number %d (%d)",
- copy_num, ret);
- btrfs_release_disk_super(disk_super);
-
+ else
+ btrfs_scratch_superblock(fs_info, bdev, copy_num);
}
/* Notify udev that device has changed */
workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL),
zlib_inflate_workspacesize());
- workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL);
+ workspace->strm.workspace = kvzalloc(workspacesize, GFP_KERNEL);
workspace->level = level;
workspace->buf = NULL;
/*
}
atomic_set(&zone_info->active_zones_left,
max_active_zones - nactive);
+ /* Overcommit does not work well with active zone tacking. */
+ set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags);
}
/* Validate superblock log */
struct inode *inode = rreq->inode;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
- struct ceph_osd_request *req;
+ struct ceph_osd_request *req = NULL;
struct ceph_vino vino = ceph_vino(inode);
struct iov_iter iter;
struct page **pages;
int err = 0;
u64 len = subreq->len;
+ if (ceph_inode_is_shutdown(inode)) {
+ err = -EIO;
+ goto out;
+ }
+
if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq))
return;
dout("writepage %p idx %lu\n", page, page->index);
+ if (ceph_inode_is_shutdown(inode))
+ return -EIO;
+
/* verify this is a writeable snap context */
snapc = page_snap_context(page);
if (!snapc) {
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_osd_request *req = NULL;
- struct ceph_cap_flush *prealloc_cf;
+ struct ceph_cap_flush *prealloc_cf = NULL;
struct folio *folio = NULL;
u64 inline_version = CEPH_INLINE_NONE;
struct page *pages[1];
dout("uninline_data %p %llx.%llx inline_version %llu\n",
inode, ceph_vinop(inode), inline_version);
+ if (ceph_inode_is_shutdown(inode)) {
+ err = -EIO;
+ goto out;
+ }
+
if (inline_version == CEPH_INLINE_NONE)
return 0;
while (true) {
flags &= CEPH_FILE_MODE_MASK;
- if (atomic_read(&fi->num_locks))
+ if (vfs_inode_has_locks(inode))
flags |= CHECK_FILELOCK;
_got = 0;
ret = try_get_cap_refs(inode, need, want, endoff,
void *p, *end;
struct cap_extra_info extra_info = {};
bool queue_trunc;
+ bool close_sessions = false;
dout("handle_caps from mds%d\n", session->s_mds);
realm = NULL;
if (snaptrace_len) {
down_write(&mdsc->snap_rwsem);
- ceph_update_snap_trace(mdsc, snaptrace,
- snaptrace + snaptrace_len,
- false, &realm);
+ if (ceph_update_snap_trace(mdsc, snaptrace,
+ snaptrace + snaptrace_len,
+ false, &realm)) {
+ up_write(&mdsc->snap_rwsem);
+ close_sessions = true;
+ goto done;
+ }
downgrade_write(&mdsc->snap_rwsem);
} else {
down_read(&mdsc->snap_rwsem);
iput(inode);
out:
ceph_put_string(extra_info.pool_ns);
+
+ /* Defer closing the sessions after s_mutex lock being released */
+ if (close_sessions)
+ ceph_mdsc_close_sessions(mdsc);
+
return;
flush_cap_releases:
loff_t zero = 0;
int op;
+ if (ceph_inode_is_shutdown(inode))
+ return -EIO;
+
if (!length) {
op = offset ? CEPH_OSD_OP_DELETE : CEPH_OSD_OP_TRUNCATE;
length = &zero;
static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
{
- struct ceph_file_info *fi = dst->fl_file->private_data;
struct inode *inode = file_inode(dst->fl_file);
atomic_inc(&ceph_inode(inode)->i_filelock_ref);
- atomic_inc(&fi->num_locks);
+ dst->fl_u.ceph.inode = igrab(inode);
}
+/*
+ * Do not use the 'fl->fl_file' in release function, which
+ * is possibly already released by another thread.
+ */
static void ceph_fl_release_lock(struct file_lock *fl)
{
- struct ceph_file_info *fi = fl->fl_file->private_data;
- struct inode *inode = file_inode(fl->fl_file);
- struct ceph_inode_info *ci = ceph_inode(inode);
- atomic_dec(&fi->num_locks);
+ struct inode *inode = fl->fl_u.ceph.inode;
+ struct ceph_inode_info *ci;
+
+ /*
+ * If inode is NULL it should be a request file_lock,
+ * nothing we can do.
+ */
+ if (!inode)
+ return;
+
+ ci = ceph_inode(inode);
if (atomic_dec_and_test(&ci->i_filelock_ref)) {
/* clear error when all locks are released */
spin_lock(&ci->i_ceph_lock);
ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK;
spin_unlock(&ci->i_ceph_lock);
}
+ fl->fl_u.ceph.inode = NULL;
+ iput(inode);
}
static const struct file_lock_operations ceph_fl_lock_ops = {
{
struct ceph_mds_session *s;
+ if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO)
+ return ERR_PTR(-EIO);
+
if (mds >= mdsc->mdsmap->possible_max_rank)
return ERR_PTR(-EINVAL);
int mstate;
int mds = session->s_mds;
+ if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO)
+ return -EIO;
+
/* wait for mds to go active? */
mstate = ceph_mdsmap_get_state(mdsc->mdsmap, mds);
dout("open_session to mds%d (%s)\n", mds,
return;
}
+ if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) {
+ dout("do_request metadata corrupted\n");
+ err = -EIO;
+ goto finish;
+ }
if (req->r_timeout &&
time_after_eq(jiffies, req->r_started + req->r_timeout)) {
dout("do_request timed out\n");
u64 tid;
int err, result;
int mds = session->s_mds;
+ bool close_sessions = false;
if (msg->front.iov_len < sizeof(*head)) {
pr_err("mdsc_handle_reply got corrupt (short) reply\n");
realm = NULL;
if (rinfo->snapblob_len) {
down_write(&mdsc->snap_rwsem);
- ceph_update_snap_trace(mdsc, rinfo->snapblob,
+ err = ceph_update_snap_trace(mdsc, rinfo->snapblob,
rinfo->snapblob + rinfo->snapblob_len,
le32_to_cpu(head->op) == CEPH_MDS_OP_RMSNAP,
&realm);
+ if (err) {
+ up_write(&mdsc->snap_rwsem);
+ close_sessions = true;
+ if (err == -EIO)
+ ceph_msg_dump(msg);
+ goto out_err;
+ }
downgrade_write(&mdsc->snap_rwsem);
} else {
down_read(&mdsc->snap_rwsem);
req->r_end_latency, err);
out:
ceph_mdsc_put_request(req);
+
+ /* Defer closing the sessions after s_mutex lock being released */
+ if (close_sessions)
+ ceph_mdsc_close_sessions(mdsc);
return;
}
break;
case CEPH_SESSION_FLUSHMSG:
+ /* flush cap releases */
+ spin_lock(&session->s_cap_lock);
+ if (session->s_num_cap_releases)
+ ceph_flush_cap_releases(mdsc, session);
+ spin_unlock(&session->s_cap_lock);
+
send_flushmsg_ack(mdsc, session, seq);
break;
}
/*
- * called after sb is ro.
+ * called after sb is ro or when metadata corrupted.
*/
void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
{
struct ceph_mds_client *mdsc = s->s_mdsc;
pr_warn("mds%d closed our session\n", s->s_mds);
- send_mds_reconnect(mdsc, s);
+ if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO)
+ send_mds_reconnect(mdsc, s);
}
static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
+#include <linux/fs.h>
#include <linux/sort.h>
#include <linux/slab.h>
#include <linux/iversion.h>
struct ceph_snap_realm *realm;
struct ceph_snap_realm *first_realm = NULL;
struct ceph_snap_realm *realm_to_rebuild = NULL;
+ struct ceph_client *client = mdsc->fsc->client;
int rebuild_snapcs;
int err = -ENOMEM;
+ int ret;
LIST_HEAD(dirty_realms);
lockdep_assert_held_write(&mdsc->snap_rwsem);
if (first_realm)
ceph_put_snap_realm(mdsc, first_realm);
pr_err("%s error %d\n", __func__, err);
+
+ /*
+ * When receiving a corrupted snap trace we don't know what
+ * exactly has happened in MDS side. And we shouldn't continue
+ * writing to OSD, which may corrupt the snapshot contents.
+ *
+ * Just try to blocklist this kclient and then this kclient
+ * must be remounted to continue after the corrupted metadata
+ * fixed in the MDS side.
+ */
+ WRITE_ONCE(mdsc->fsc->mount_state, CEPH_MOUNT_FENCE_IO);
+ ret = ceph_monc_blocklist_add(&client->monc, &client->msgr.inst.addr);
+ if (ret)
+ pr_err("%s failed to blocklist %s: %d\n", __func__,
+ ceph_pr_addr(&client->msgr.inst.addr), ret);
+
+ WARN(1, "%s: %s%sdo remount to continue%s",
+ __func__, ret ? "" : ceph_pr_addr(&client->msgr.inst.addr),
+ ret ? "" : " was blocklisted, ",
+ err == -EIO ? " after corrupted snaptrace is fixed" : "");
+
return err;
}
__le64 *split_inos = NULL, *split_realms = NULL;
int i;
int locked_rwsem = 0;
+ bool close_sessions = false;
/* decode */
if (msg->front.iov_len < sizeof(*h))
* update using the provided snap trace. if we are deleting a
* snap, we can avoid queueing cap_snaps.
*/
- ceph_update_snap_trace(mdsc, p, e,
- op == CEPH_SNAP_OP_DESTROY, NULL);
+ if (ceph_update_snap_trace(mdsc, p, e,
+ op == CEPH_SNAP_OP_DESTROY,
+ NULL)) {
+ close_sessions = true;
+ goto bad;
+ }
if (op == CEPH_SNAP_OP_SPLIT)
/* we took a reference when we created the realm, above */
out:
if (locked_rwsem)
up_write(&mdsc->snap_rwsem);
+
+ if (close_sessions)
+ ceph_mdsc_close_sessions(mdsc);
return;
}
char *mon_addr;
};
+/* mount state */
+enum {
+ CEPH_MOUNT_MOUNTING,
+ CEPH_MOUNT_MOUNTED,
+ CEPH_MOUNT_UNMOUNTING,
+ CEPH_MOUNT_UNMOUNTED,
+ CEPH_MOUNT_SHUTDOWN,
+ CEPH_MOUNT_RECOVER,
+ CEPH_MOUNT_FENCE_IO,
+};
+
#define CEPH_ASYNC_CREATE_CONFLICT_BITS 8
struct ceph_fs_client {
struct list_head rw_contexts;
u32 filp_gen;
- atomic_t num_locks;
};
struct ceph_dir_file_info {
* ( for NTLMSSP_AV_NB_DOMAIN_NAME followed by NTLMSSP_AV_EOL ) +
* unicode length of a netbios domain name
*/
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.len = size + 2 * dlen;
ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL);
if (!ses->auth_key.response) {
INIT_LIST_HEAD(&tcon->pending_opens);
tcon->status = TID_GOOD;
- /* schedule query interfaces poll */
INIT_DELAYED_WORK(&tcon->query_interfaces,
smb2_query_server_interfaces);
- queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
- (SMB_INTERFACE_POLL_INTERVAL * HZ));
+ if (ses->server->dialect >= SMB30_PROT_ID &&
+ (ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
+ /* schedule query interfaces poll */
+ queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
+ (SMB_INTERFACE_POLL_INTERVAL * HZ));
+ }
spin_lock(&cifs_tcp_ses_lock);
list_add(&tcon->tcon_list, &ses->tcon_list);
return rc;
}
-static int target_share_matches_server(struct TCP_Server_Info *server, const char *tcp_host,
- size_t tcp_host_len, char *share, bool *target_match)
+static int target_share_matches_server(struct TCP_Server_Info *server, char *share,
+ bool *target_match)
{
int rc = 0;
const char *dfs_host;
extract_unc_hostname(share, &dfs_host, &dfs_host_len);
/* Check if hostnames or addresses match */
- if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) {
- cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len,
- dfs_host, (int)tcp_host_len, tcp_host);
+ cifs_server_lock(server);
+ if (dfs_host_len != strlen(server->hostname) ||
+ strncasecmp(dfs_host, server->hostname, dfs_host_len)) {
+ cifs_dbg(FYI, "%s: %.*s doesn't match %s\n", __func__,
+ (int)dfs_host_len, dfs_host, server->hostname);
rc = match_target_ip(server, dfs_host, dfs_host_len, target_match);
if (rc)
cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc);
}
+ cifs_server_unlock(server);
return rc;
}
struct cifs_ses *root_ses = CIFS_DFS_ROOT_SES(tcon->ses);
struct cifs_tcon *ipc = root_ses->tcon_ipc;
char *share = NULL, *prefix = NULL;
- const char *tcp_host;
- size_t tcp_host_len;
struct dfs_cache_tgt_iterator *tit;
bool target_match;
- extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len);
-
tit = dfs_cache_get_tgt_iterator(tl);
if (!tit) {
rc = -ENOENT;
break;
}
- rc = target_share_matches_server(server, tcp_host, tcp_host_len, share,
- &target_match);
+ rc = target_share_matches_server(server, share, &target_match);
if (rc)
break;
if (!target_match) {
if (ipc->need_reconnect) {
scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls);
- if (rc)
- break;
+ cifs_dbg(FYI, "%s: reconnect ipc: %d\n", __func__, rc);
}
scnprintf(tree, MAX_TREE_SIZE, "\\%s", share);
}
if (tcon->ipc) {
+ cifs_server_lock(server);
scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
+ cifs_server_unlock(server);
rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
goto out;
}
list_for_each_entry(t, &ce->tlist, list) {
seq_printf(m, " %s%s\n",
t->name,
- ce->tgthint == t ? " (target hint)" : "");
+ READ_ONCE(ce->tgthint) == t ? " (target hint)" : "");
}
}
}
cifs_dbg(FYI, "target list:\n");
list_for_each_entry(t, &ce->tlist, list) {
cifs_dbg(FYI, " %s%s\n", t->name,
- ce->tgthint == t ? " (target hint)" : "");
+ READ_ONCE(ce->tgthint) == t ? " (target hint)" : "");
}
}
/* Return target hint of a DFS cache entry */
static inline char *get_tgt_name(const struct cache_entry *ce)
{
- struct cache_dfs_tgt *t = ce->tgthint;
+ struct cache_dfs_tgt *t = READ_ONCE(ce->tgthint);
return t ? t->name : ERR_PTR(-ENOENT);
}
static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs,
struct cache_entry *ce, const char *tgthint)
{
+ struct cache_dfs_tgt *target;
int i;
ce->ttl = max_t(int, refs[0].ttl, CACHE_MIN_TTL);
ce->numtgts++;
}
- ce->tgthint = list_first_entry_or_null(&ce->tlist,
- struct cache_dfs_tgt, list);
+ target = list_first_entry_or_null(&ce->tlist, struct cache_dfs_tgt,
+ list);
+ WRITE_ONCE(ce->tgthint, target);
return 0;
}
}
/* Add a new DFS cache entry */
-static int add_cache_entry_locked(struct dfs_info3_param *refs, int numrefs)
+static struct cache_entry *add_cache_entry_locked(struct dfs_info3_param *refs,
+ int numrefs)
{
int rc;
struct cache_entry *ce;
rc = cache_entry_hash(refs[0].path_name, strlen(refs[0].path_name), &hash);
if (rc)
- return rc;
+ return ERR_PTR(rc);
ce = alloc_cache_entry(refs, numrefs);
if (IS_ERR(ce))
- return PTR_ERR(ce);
+ return ce;
spin_lock(&cache_ttl_lock);
if (!cache_ttl) {
atomic_inc(&cache_count);
- return 0;
+ return ce;
}
/* Check if two DFS paths are equal. @s1 and @s2 are expected to be in @cache_cp's charset */
*
* Use whole path components in the match. Must be called with htable_rw_lock held.
*
+ * Return cached entry if successful.
* Return ERR_PTR(-ENOENT) if the entry is not found.
+ * Return error ptr otherwise.
*/
static struct cache_entry *lookup_cache_entry(const char *path)
{
static int update_cache_entry_locked(struct cache_entry *ce, const struct dfs_info3_param *refs,
int numrefs)
{
+ struct cache_dfs_tgt *target;
+ char *th = NULL;
int rc;
- char *s, *th = NULL;
WARN_ON(!rwsem_is_locked(&htable_rw_lock));
- if (ce->tgthint) {
- s = ce->tgthint->name;
- th = kstrdup(s, GFP_ATOMIC);
+ target = READ_ONCE(ce->tgthint);
+ if (target) {
+ th = kstrdup(target->name, GFP_ATOMIC);
if (!th)
return -ENOMEM;
}
*
* For interlinks, cifs_mount() and expand_dfs_referral() are supposed to
* handle them properly.
+ *
+ * On success, return entry with acquired lock for reading, otherwise error ptr.
*/
-static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, const char *path)
+static struct cache_entry *cache_refresh_path(const unsigned int xid,
+ struct cifs_ses *ses,
+ const char *path,
+ bool force_refresh)
{
- int rc;
- struct cache_entry *ce;
struct dfs_info3_param *refs = NULL;
+ struct cache_entry *ce;
int numrefs = 0;
- bool newent = false;
+ int rc;
cifs_dbg(FYI, "%s: search path: %s\n", __func__, path);
- down_write(&htable_rw_lock);
+ down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
if (!IS_ERR(ce)) {
- if (!cache_entry_expired(ce)) {
- dump_ce(ce);
- up_write(&htable_rw_lock);
- return 0;
- }
- } else {
- newent = true;
+ if (!force_refresh && !cache_entry_expired(ce))
+ return ce;
+ } else if (PTR_ERR(ce) != -ENOENT) {
+ up_read(&htable_rw_lock);
+ return ce;
}
/*
- * Either the entry was not found, or it is expired.
+ * Unlock shared access as we don't want to hold any locks while getting
+ * a new referral. The @ses used for performing the I/O could be
+ * reconnecting and it acquires @htable_rw_lock to look up the dfs cache
+ * in order to failover -- if necessary.
+ */
+ up_read(&htable_rw_lock);
+
+ /*
+ * Either the entry was not found, or it is expired, or it is a forced
+ * refresh.
* Request a new DFS referral in order to create or update a cache entry.
*/
rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
- if (rc)
- goto out_unlock;
+ if (rc) {
+ ce = ERR_PTR(rc);
+ goto out;
+ }
dump_refs(refs, numrefs);
- if (!newent) {
- rc = update_cache_entry_locked(ce, refs, numrefs);
- goto out_unlock;
+ down_write(&htable_rw_lock);
+ /* Re-check as another task might have it added or refreshed already */
+ ce = lookup_cache_entry(path);
+ if (!IS_ERR(ce)) {
+ if (force_refresh || cache_entry_expired(ce)) {
+ rc = update_cache_entry_locked(ce, refs, numrefs);
+ if (rc)
+ ce = ERR_PTR(rc);
+ }
+ } else if (PTR_ERR(ce) == -ENOENT) {
+ ce = add_cache_entry_locked(refs, numrefs);
}
- rc = add_cache_entry_locked(refs, numrefs);
+ if (IS_ERR(ce)) {
+ up_write(&htable_rw_lock);
+ goto out;
+ }
-out_unlock:
- up_write(&htable_rw_lock);
+ downgrade_write(&htable_rw_lock);
+out:
free_dfs_info_array(refs, numrefs);
- return rc;
+ return ce;
}
/*
}
it->it_path_consumed = t->path_consumed;
- if (ce->tgthint == t)
+ if (READ_ONCE(ce->tgthint) == t)
list_add(&it->it_list, head);
else
list_add_tail(&it->it_list, head);
if (IS_ERR(npath))
return PTR_ERR(npath);
- rc = cache_refresh_path(xid, ses, npath);
- if (rc)
- goto out_free_path;
-
- down_read(&htable_rw_lock);
-
- ce = lookup_cache_entry(npath);
+ ce = cache_refresh_path(xid, ses, npath, false);
if (IS_ERR(ce)) {
- up_read(&htable_rw_lock);
rc = PTR_ERR(ce);
goto out_free_path;
}
return rc;
}
-/**
- * dfs_cache_update_tgthint - update target hint of a DFS cache entry
- *
- * If it doesn't find the cache entry, then it will get a DFS referral for @path
- * and create a new entry.
- *
- * In case the cache entry exists but expired, it will get a DFS referral
- * for @path and then update the respective cache entry.
- *
- * @xid: syscall id
- * @ses: smb session
- * @cp: codepage
- * @remap: type of character remapping for paths
- * @path: path to lookup in DFS referral cache
- * @it: DFS target iterator
- *
- * Return zero if the target hint was updated successfully, otherwise non-zero.
- */
-int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
- const struct nls_table *cp, int remap, const char *path,
- const struct dfs_cache_tgt_iterator *it)
-{
- int rc;
- const char *npath;
- struct cache_entry *ce;
- struct cache_dfs_tgt *t;
-
- npath = dfs_cache_canonical_path(path, cp, remap);
- if (IS_ERR(npath))
- return PTR_ERR(npath);
-
- cifs_dbg(FYI, "%s: update target hint - path: %s\n", __func__, npath);
-
- rc = cache_refresh_path(xid, ses, npath);
- if (rc)
- goto out_free_path;
-
- down_write(&htable_rw_lock);
-
- ce = lookup_cache_entry(npath);
- if (IS_ERR(ce)) {
- rc = PTR_ERR(ce);
- goto out_unlock;
- }
-
- t = ce->tgthint;
-
- if (likely(!strcasecmp(it->it_name, t->name)))
- goto out_unlock;
-
- list_for_each_entry(t, &ce->tlist, list) {
- if (!strcasecmp(t->name, it->it_name)) {
- ce->tgthint = t;
- cifs_dbg(FYI, "%s: new target hint: %s\n", __func__,
- it->it_name);
- break;
- }
- }
-
-out_unlock:
- up_write(&htable_rw_lock);
-out_free_path:
- kfree(npath);
- return rc;
-}
-
/**
* dfs_cache_noreq_update_tgthint - update target hint of a DFS cache entry
* without sending any requests to the currently connected server.
cifs_dbg(FYI, "%s: path: %s\n", __func__, path);
- if (!down_write_trylock(&htable_rw_lock))
- return;
+ down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
if (IS_ERR(ce))
goto out_unlock;
- t = ce->tgthint;
+ t = READ_ONCE(ce->tgthint);
if (unlikely(!strcasecmp(it->it_name, t->name)))
goto out_unlock;
list_for_each_entry(t, &ce->tlist, list) {
if (!strcasecmp(t->name, it->it_name)) {
- ce->tgthint = t;
+ WRITE_ONCE(ce->tgthint, t);
cifs_dbg(FYI, "%s: new target hint: %s\n", __func__,
it->it_name);
break;
}
out_unlock:
- up_write(&htable_rw_lock);
+ up_read(&htable_rw_lock);
}
/**
* Resolve share's hostname and check if server address matches. Otherwise just ignore it
* as we could not have upcall to resolve hostname or failed to convert ip address.
*/
- match = true;
extract_unc_hostname(s1, &host, &hostlen);
scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host);
* Mark dfs tcon for reconnecting when the currently connected tcon does not match any of the new
* target shares in @refs.
*/
-static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cache_tgt_list *tl,
- const struct dfs_info3_param *refs, int numrefs)
+static void mark_for_reconnect_if_needed(struct TCP_Server_Info *server,
+ struct dfs_cache_tgt_list *old_tl,
+ struct dfs_cache_tgt_list *new_tl)
{
- struct dfs_cache_tgt_iterator *it;
- int i;
-
- for (it = dfs_cache_get_tgt_iterator(tl); it; it = dfs_cache_get_next_tgt(tl, it)) {
- for (i = 0; i < numrefs; i++) {
- if (target_share_equal(tcon->ses->server, dfs_cache_get_tgt_name(it),
- refs[i].node_name))
+ struct dfs_cache_tgt_iterator *oit, *nit;
+
+ for (oit = dfs_cache_get_tgt_iterator(old_tl); oit;
+ oit = dfs_cache_get_next_tgt(old_tl, oit)) {
+ for (nit = dfs_cache_get_tgt_iterator(new_tl); nit;
+ nit = dfs_cache_get_next_tgt(new_tl, nit)) {
+ if (target_share_equal(server,
+ dfs_cache_get_tgt_name(oit),
+ dfs_cache_get_tgt_name(nit)))
return;
}
}
cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__);
- cifs_signal_cifsd_for_reconnect(tcon->ses->server, true);
+ cifs_signal_cifsd_for_reconnect(server, true);
}
/* Refresh dfs referral of tcon and mark it for reconnect if needed */
static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_refresh)
{
- struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl);
+ struct dfs_cache_tgt_list old_tl = DFS_CACHE_TGT_LIST_INIT(old_tl);
+ struct dfs_cache_tgt_list new_tl = DFS_CACHE_TGT_LIST_INIT(new_tl);
struct cifs_ses *ses = CIFS_DFS_ROOT_SES(tcon->ses);
struct cifs_tcon *ipc = ses->tcon_ipc;
- struct dfs_info3_param *refs = NULL;
bool needs_refresh = false;
struct cache_entry *ce;
unsigned int xid;
- int numrefs = 0;
int rc = 0;
xid = get_xid();
ce = lookup_cache_entry(path);
needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce);
if (!IS_ERR(ce)) {
- rc = get_targets(ce, &tl);
- if (rc)
- cifs_dbg(FYI, "%s: could not get dfs targets: %d\n", __func__, rc);
+ rc = get_targets(ce, &old_tl);
+ cifs_dbg(FYI, "%s: get_targets: %d\n", __func__, rc);
}
up_read(&htable_rw_lock);
}
spin_unlock(&ipc->tc_lock);
- rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
- if (!rc) {
- /* Create or update a cache entry with the new referral */
- dump_refs(refs, numrefs);
-
- down_write(&htable_rw_lock);
- ce = lookup_cache_entry(path);
- if (IS_ERR(ce))
- add_cache_entry_locked(refs, numrefs);
- else if (force_refresh || cache_entry_expired(ce))
- update_cache_entry_locked(ce, refs, numrefs);
- up_write(&htable_rw_lock);
-
- mark_for_reconnect_if_needed(tcon, &tl, refs, numrefs);
+ ce = cache_refresh_path(xid, ses, path, true);
+ if (!IS_ERR(ce)) {
+ rc = get_targets(ce, &new_tl);
+ up_read(&htable_rw_lock);
+ cifs_dbg(FYI, "%s: get_targets: %d\n", __func__, rc);
+ mark_for_reconnect_if_needed(tcon->ses->server, &old_tl, &new_tl);
}
out:
free_xid(xid);
- dfs_cache_free_tgts(&tl);
- free_dfs_info_array(refs, numrefs);
+ dfs_cache_free_tgts(&old_tl);
+ dfs_cache_free_tgts(&new_tl);
return rc;
}
struct dfs_cache_tgt_list *tgt_list);
int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref,
struct dfs_cache_tgt_list *tgt_list);
-int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
- const struct nls_table *cp, int remap, const char *path,
- const struct dfs_cache_tgt_iterator *it);
void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt_iterator *it);
int dfs_cache_get_tgt_referral(const char *path, const struct dfs_cache_tgt_iterator *it,
struct dfs_info3_param *ref);
rdata->got_bytes += result;
}
- return rdata->got_bytes > 0 && result != -ECONNABORTED ?
+ return result != -ECONNABORTED && rdata->got_bytes > 0 ?
rdata->got_bytes : result;
}
rdata->got_bytes += result;
}
- return rdata->got_bytes > 0 && result != -ECONNABORTED ?
+ return result != -ECONNABORTED && rdata->got_bytes > 0 ?
rdata->got_bytes : result;
}
oparms.disposition = FILE_CREATE;
oparms.fid = &fid;
oparms.reconnect = false;
+ oparms.mode = 0644;
rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL,
NULL, NULL);
if (rc < 0)
return rc;
+ spin_lock(&server->srv_lock);
*result = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss);
+ spin_unlock(&server->srv_lock);
cifs_dbg(FYI, "%s: ip addresses match: %u\n", __func__, *result);
return 0;
}
continue;
}
kref_get(&iface->refcount);
+ break;
}
- if (!list_entry_is_head(iface, &ses->iface_list, iface_head)) {
+ if (list_entry_is_head(iface, &ses->iface_list, iface_head)) {
rc = 1;
iface = NULL;
cifs_dbg(FYI, "unable to find a suitable iface\n");
return -EINVAL;
}
if (tilen) {
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(bcc_ptr + tioffset, tilen,
GFP_KERNEL);
if (!ses->auth_key.response) {
goto out_put_spnego_key;
}
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
GFP_KERNEL);
if (!ses->auth_key.response) {
if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) {
rc = SMBQueryInformation(xid, tcon, full_path, &fi, cifs_sb->local_nls,
cifs_remap(cifs_sb));
- if (!rc)
- move_cifs_info_to_smb2(&data->fi, &fi);
*adjustTZ = true;
}
- if (!rc && (le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) {
+ if (!rc) {
int tmprc;
int oplock = 0;
struct cifs_fid fid;
struct cifs_open_parms oparms;
+ move_cifs_info_to_smb2(&data->fi, &fi);
+
+ if (!(le32_to_cpu(fi.Attributes) & ATTR_REPARSE))
+ return 0;
+
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = FILE_READ_ATTRIBUTES;
static int cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock,
void *buf)
{
- FILE_ALL_INFO *fi = buf;
+ struct cifs_open_info_data *data = buf;
+ FILE_ALL_INFO fi = {};
+ int rc;
if (!(oparms->tcon->ses->capabilities & CAP_NT_SMBS))
- return SMBLegacyOpen(xid, oparms->tcon, oparms->path,
- oparms->disposition,
- oparms->desired_access,
- oparms->create_options,
- &oparms->fid->netfid, oplock, fi,
- oparms->cifs_sb->local_nls,
- cifs_remap(oparms->cifs_sb));
- return CIFS_open(xid, oparms, oplock, fi);
+ rc = SMBLegacyOpen(xid, oparms->tcon, oparms->path,
+ oparms->disposition,
+ oparms->desired_access,
+ oparms->create_options,
+ &oparms->fid->netfid, oplock, &fi,
+ oparms->cifs_sb->local_nls,
+ cifs_remap(oparms->cifs_sb));
+ else
+ rc = CIFS_open(xid, oparms, oplock, &fi);
+
+ if (!rc && data)
+ move_cifs_info_to_smb2(&data->fi, &fi);
+
+ return rc;
}
static void
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct inode *newinode = NULL;
int rc = -EPERM;
- FILE_ALL_INFO *buf = NULL;
+ struct cifs_open_info_data buf = {};
struct cifs_io_parms io_parms;
__u32 oplock = 0;
struct cifs_fid fid;
cifs_sb->local_nls,
cifs_remap(cifs_sb));
if (rc)
- goto out;
+ return rc;
rc = cifs_get_inode_info_unix(&newinode, full_path,
inode->i_sb, xid);
if (rc == 0)
d_instantiate(dentry, newinode);
- goto out;
+ return rc;
}
/*
* support block and char device (no socket & fifo)
*/
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
- goto out;
+ return rc;
if (!S_ISCHR(mode) && !S_ISBLK(mode))
- goto out;
+ return rc;
cifs_dbg(FYI, "sfu compat create special file\n");
- buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
- if (buf == NULL) {
- rc = -ENOMEM;
- goto out;
- }
-
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = GENERIC_WRITE;
oplock = REQ_OPLOCK;
else
oplock = 0;
- rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf);
+ rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf);
if (rc)
- goto out;
+ return rc;
/*
* BB Do not bother to decode buf since no local inode yet to put
* timestamps in, but we can reuse it safely.
*/
- pdev = (struct win_dev *)buf;
+ pdev = (struct win_dev *)&buf.fi;
io_parms.pid = current->tgid;
io_parms.tcon = tcon;
io_parms.offset = 0;
io_parms.length = sizeof(struct win_dev);
- iov[1].iov_base = buf;
+ iov[1].iov_base = &buf.fi;
iov[1].iov_len = sizeof(struct win_dev);
if (S_ISCHR(mode)) {
memcpy(pdev->type, "IntxCHR", 8);
d_drop(dentry);
/* FIXME: add code here to set EAs */
-out:
- kfree(buf);
+
+ cifs_free_open_info(&buf);
return rc;
}
p = buf;
spin_lock(&ses->iface_lock);
- ses->iface_count = 0;
/*
* Go through iface_list and do kref_put to remove
* any unused ifaces. ifaces in use will be removed
iface_head) {
iface->is_active = 0;
kref_put(&iface->refcount, release_iface);
+ ses->iface_count--;
}
spin_unlock(&ses->iface_lock);
/* just get a ref so that it doesn't get picked/freed */
iface->is_active = 1;
kref_get(&iface->refcount);
+ ses->iface_count++;
spin_unlock(&ses->iface_lock);
goto next_iface;
} else if (ret < 0) {
/* copy pages form the old */
for (j = 0; j < npages; j++) {
- char *dst, *src;
unsigned int offset, len;
rqst_page_get_length(new, j, &len, &offset);
- dst = kmap_local_page(new->rq_pages[j]) + offset;
- src = kmap_local_page(old->rq_pages[j]) + offset;
-
- memcpy(dst, src, len);
- kunmap(new->rq_pages[j]);
- kunmap(old->rq_pages[j]);
+ memcpy_page(new->rq_pages[j], offset,
+ old->rq_pages[j], offset, len);
}
}
assemble_neg_contexts(struct smb2_negotiate_req *req,
struct TCP_Server_Info *server, unsigned int *total_len)
{
- char *pneg_ctxt;
- char *hostname = NULL;
unsigned int ctxt_len, neg_context_count;
+ struct TCP_Server_Info *pserver;
+ char *pneg_ctxt;
+ char *hostname;
if (*total_len > 200) {
/* In case length corrupted don't want to overrun smb buffer */
* secondary channels don't have the hostname field populated
* use the hostname field in the primary channel instead
*/
- hostname = CIFS_SERVER_IS_CHAN(server) ?
- server->primary_server->hostname : server->hostname;
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+ cifs_server_lock(pserver);
+ hostname = pserver->hostname;
if (hostname && (hostname[0] != 0)) {
ctxt_len = build_netname_ctxt((struct smb2_netname_neg_context *)pneg_ctxt,
hostname);
neg_context_count = 3;
} else
neg_context_count = 2;
+ cifs_server_unlock(pserver);
build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt);
*total_len += sizeof(struct smb2_posix_neg_context);
/* keep session key if binding */
if (!is_binding) {
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
GFP_KERNEL);
if (!ses->auth_key.response) {
out_put_spnego_key:
key_invalidate(spnego_key);
key_put(spnego_key);
- if (rc)
+ if (rc) {
kfree_sensitive(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ ses->auth_key.len = 0;
+ }
out:
sess_data->result = rc;
sess_data->func = NULL;
(struct smb2_hdr *)rdata->iov[0].iov_base;
struct cifs_credits credits = { .value = 0, .instance = 0 };
struct smb_rqst rqst = { .rq_iov = &rdata->iov[1],
- .rq_nvec = 1,
- .rq_pages = rdata->pages,
- .rq_offset = rdata->page_offset,
- .rq_npages = rdata->nr_pages,
- .rq_pagesz = rdata->pagesz,
- .rq_tailsz = rdata->tailsz };
+ .rq_nvec = 1, };
+
+ if (rdata->got_bytes) {
+ rqst.rq_pages = rdata->pages;
+ rqst.rq_offset = rdata->page_offset;
+ rqst.rq_npages = rdata->nr_pages;
+ rqst.rq_pagesz = rdata->pagesz;
+ rqst.rq_tailsz = rdata->tailsz;
+ }
WARN_ONCE(rdata->server != mid->server,
"rdata server %p != mid server %p",
destroy_workqueue(info->workqueue);
log_rdma_event(INFO, "rdma session destroyed\n");
kfree(info);
+ server->smbd_conn = NULL;
}
/*
}
}
+int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
+{
+ if (cprm->to_skip) {
+ if (!__dump_skip(cprm, cprm->to_skip))
+ return 0;
+ cprm->to_skip = 0;
+ }
+ return __dump_emit(cprm, addr, nr);
+}
+EXPORT_SYMBOL(dump_emit);
+
+void dump_skip_to(struct coredump_params *cprm, unsigned long pos)
+{
+ cprm->to_skip = pos - cprm->pos;
+}
+EXPORT_SYMBOL(dump_skip_to);
+
+void dump_skip(struct coredump_params *cprm, size_t nr)
+{
+ cprm->to_skip += nr;
+}
+EXPORT_SYMBOL(dump_skip);
+
+#ifdef CONFIG_ELF_CORE
static int dump_emit_page(struct coredump_params *cprm, struct page *page)
{
struct bio_vec bvec = {
return 1;
}
-int dump_emit(struct coredump_params *cprm, const void *addr, int nr)
-{
- if (cprm->to_skip) {
- if (!__dump_skip(cprm, cprm->to_skip))
- return 0;
- cprm->to_skip = 0;
- }
- return __dump_emit(cprm, addr, nr);
-}
-EXPORT_SYMBOL(dump_emit);
-
-void dump_skip_to(struct coredump_params *cprm, unsigned long pos)
-{
- cprm->to_skip = pos - cprm->pos;
-}
-EXPORT_SYMBOL(dump_skip_to);
-
-void dump_skip(struct coredump_params *cprm, size_t nr)
-{
- cprm->to_skip += nr;
-}
-EXPORT_SYMBOL(dump_skip);
-
-#ifdef CONFIG_ELF_CORE
int dump_user_range(struct coredump_params *cprm, unsigned long start,
unsigned long len)
{
if (ret < 0)
goto out_unlock;
- ret = copy_mc_to_kernel(daddr, saddr, length);
- if (ret)
+ if (copy_mc_to_kernel(daddr, saddr, length) == 0)
+ ret = length;
+ else
ret = -EIO;
out_unlock:
}
++ctx->devs->extra_devices;
break;
- case Opt_fsid:
#ifdef CONFIG_EROFS_FS_ONDEMAND
+ case Opt_fsid:
kfree(ctx->fsid);
ctx->fsid = kstrdup(param->string, GFP_KERNEL);
if (!ctx->fsid)
return -ENOMEM;
-#else
- errorfc(fc, "fsid option not supported");
-#endif
break;
case Opt_domain_id:
-#ifdef CONFIG_EROFS_FS_ONDEMAND
kfree(ctx->domain_id);
ctx->domain_id = kstrdup(param->string, GFP_KERNEL);
if (!ctx->domain_id)
return -ENOMEM;
+ break;
#else
- errorfc(fc, "domain_id option not supported");
-#endif
+ case Opt_fsid:
+ case Opt_domain_id:
+ errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
break;
+#endif
default:
return -ENOPARAM;
}
if (!be->decompressed_pages)
be->decompressed_pages =
- kvcalloc(be->nr_pages, sizeof(struct page *),
- GFP_KERNEL | __GFP_NOFAIL);
+ kcalloc(be->nr_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
if (!be->compressed_pages)
be->compressed_pages =
- kvcalloc(pclusterpages, sizeof(struct page *),
- GFP_KERNEL | __GFP_NOFAIL);
+ kcalloc(pclusterpages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
z_erofs_parse_out_bvecs(be);
err2 = z_erofs_parse_in_bvecs(be, &overlapped);
}
if (be->compressed_pages < be->onstack_pages ||
be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES)
- kvfree(be->compressed_pages);
+ kfree(be->compressed_pages);
z_erofs_fill_other_copies(be, err);
for (i = 0; i < be->nr_pages; ++i) {
}
if (be->decompressed_pages != be->onstack_pages)
- kvfree(be->decompressed_pages);
+ kfree(be->decompressed_pages);
pcl->length = 0;
pcl->partial = true;
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
/*
- * No strict rule how to describe extents for post EOF, yet
- * we need do like below. Otherwise, iomap itself will get
+ * No strict rule on how to describe extents for post EOF, yet
+ * we need to do like below. Otherwise, iomap itself will get
* into an endless loop on post EOF.
+ *
+ * Calculate the effective offset by subtracting extent start
+ * (map.m_la) from the requested offset, and add it to length.
+ * (NB: offset >= map.m_la always)
*/
if (iomap->offset >= inode->i_size)
- iomap->length = length + map.m_la - offset;
+ iomap->length = length + offset - map.m_la;
}
iomap->flags = 0;
return 0;
struct mb_cache_entry **);
static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value,
size_t value_count);
+static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value,
+ size_t value_count);
static void ext4_xattr_rehash(struct ext4_xattr_header *);
static const struct xattr_handler * const ext4_xattr_handler_map[] = {
tmp_data = cpu_to_le32(hash);
e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len,
&tmp_data, 1);
+ /* All good? */
+ if (e_hash == entry->e_hash)
+ return 0;
+
+ /*
+ * Not good. Maybe the entry hash was calculated
+ * using the buggy signed char version?
+ */
+ e_hash = ext4_xattr_hash_entry_signed(entry->e_name, entry->e_name_len,
+ &tmp_data, 1);
+ /* Still no match - bad */
if (e_hash != entry->e_hash)
return -EFSCORRUPTED;
+
+ /* Let people know about old hash */
+ pr_warn_once("ext4: filesystem with signed xattr name hash");
}
return 0;
}
while (name_len--) {
hash = (hash << NAME_HASH_SHIFT) ^
(hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
- *name++;
+ (unsigned char)*name++;
+ }
+ while (value_count--) {
+ hash = (hash << VALUE_HASH_SHIFT) ^
+ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
+ le32_to_cpu(*value++);
+ }
+ return cpu_to_le32(hash);
+}
+
+/*
+ * ext4_xattr_hash_entry_signed()
+ *
+ * Compute the hash of an extended attribute incorrectly.
+ */
+static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, size_t value_count)
+{
+ __u32 hash = 0;
+
+ while (name_len--) {
+ hash = (hash << NAME_HASH_SHIFT) ^
+ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
+ (signed char)*name++;
}
while (value_count--) {
hash = (hash << VALUE_HASH_SHIFT) ^
sector_t last_block_in_file;
const unsigned blocksize = blks_to_bytes(inode, 1);
struct decompress_io_ctx *dic = NULL;
- struct extent_info ei = {0, };
+ struct extent_info ei = {};
bool from_dnode = true;
int i;
int ret = 0;
struct extent_node *en;
bool ret = false;
- f2fs_bug_on(sbi, !et);
+ if (!et)
+ return false;
trace_f2fs_lookup_extent_tree_start(inode, pgofs, type);
}
/* This returns a new age and allocated blocks in ei */
-static int __get_new_block_age(struct inode *inode, struct extent_info *ei)
+static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
+ block_t blkaddr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t f_size = i_size_read(inode);
unsigned long long cur_blocks =
atomic64_read(&sbi->allocated_data_blocks);
+ struct extent_info tei = *ei; /* only fofs and len are valid */
/*
* When I/O is not aligned to a PAGE_SIZE, update will happen to the last
* block here.
*/
if ((f_size >> PAGE_SHIFT) == ei->fofs && f_size & (PAGE_SIZE - 1) &&
- ei->blk == NEW_ADDR)
+ blkaddr == NEW_ADDR)
return -EINVAL;
- if (__lookup_extent_tree(inode, ei->fofs, ei, EX_BLOCK_AGE)) {
+ if (__lookup_extent_tree(inode, ei->fofs, &tei, EX_BLOCK_AGE)) {
unsigned long long cur_age;
- if (cur_blocks >= ei->last_blocks)
- cur_age = cur_blocks - ei->last_blocks;
+ if (cur_blocks >= tei.last_blocks)
+ cur_age = cur_blocks - tei.last_blocks;
else
/* allocated_data_blocks overflow */
- cur_age = ULLONG_MAX - ei->last_blocks + cur_blocks;
+ cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks;
- if (ei->age)
- ei->age = __calculate_block_age(cur_age, ei->age);
+ if (tei.age)
+ ei->age = __calculate_block_age(cur_age, tei.age);
else
ei->age = cur_age;
ei->last_blocks = cur_blocks;
return 0;
}
- f2fs_bug_on(sbi, ei->blk == NULL_ADDR);
+ f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
/* the data block was allocated for the first time */
- if (ei->blk == NEW_ADDR)
+ if (blkaddr == NEW_ADDR)
goto out;
- if (__is_valid_data_blkaddr(ei->blk) &&
- !f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE)) {
+ if (__is_valid_data_blkaddr(blkaddr) &&
+ !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
f2fs_bug_on(sbi, 1);
return -EINVAL;
}
static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type type)
{
- struct extent_info ei;
+ struct extent_info ei = {};
if (!__may_extent_tree(dn->inode, type))
return;
else
ei.blk = dn->data_blkaddr;
} else if (type == EX_BLOCK_AGE) {
- ei.blk = dn->data_blkaddr;
- if (__get_new_block_age(dn->inode, &ei))
+ if (__get_new_block_age(dn->inode, &ei, dn->data_blkaddr))
return;
}
__update_extent_tree_range(dn->inode, &ei, type);
struct f2fs_map_blocks map = { .m_next_extent = NULL,
.m_seg_type = NO_CHECK_TYPE,
.m_may_create = false };
- struct extent_info ei = {0, };
+ struct extent_info ei = {};
pgoff_t pg_start, pg_end, next_pgofs;
unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
if (IS_ERR(fcc->f2fs_issue_flush)) {
int err = PTR_ERR(fcc->f2fs_issue_flush);
- kfree(fcc);
- SM_I(sbi)->fcc_info = NULL;
+ fcc->f2fs_issue_flush = NULL;
return err;
}
static int __get_age_segment_type(struct inode *inode, pgoff_t pgofs)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct extent_info ei;
+ struct extent_info ei = {};
if (f2fs_lookup_age_extent_cache(inode, pgofs, &ei)) {
if (!ei.age)
init_f2fs_rwsem(&sm_info->curseg_lock);
- if (!f2fs_readonly(sbi->sb)) {
- err = f2fs_create_flush_cmd_control(sbi);
- if (err)
- return err;
- }
+ err = f2fs_create_flush_cmd_control(sbi);
+ if (err)
+ return err;
err = create_discard_cmd_control(sbi);
if (err)
of SCO UnixWare (and possibly others) and optionally available
for Sunsoft Solaris, HP-UX and many other operating systems. However
these particular OS implementations of vxfs may differ in on-disk
- data endianess and/or superblock offset. The vxfs module has been
+ data endianness and/or superblock offset. The vxfs module has been
tested with SCO UnixWare and HP-UX B.10.20 (pa-risc 1.1 arch.)
Currently only readonly access is supported and VxFX versions
2, 3 and 4. Tests were performed with HP-UX VxFS version 3.
static void fscache_wait_on_volume_collision(struct fscache_volume *candidate,
unsigned int collidee_debug_id)
{
- wait_var_event_timeout(&candidate->flags,
- !fscache_is_acquire_pending(candidate), 20 * HZ);
+ wait_on_bit_timeout(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING,
+ TASK_UNINTERRUPTIBLE, 20 * HZ);
if (fscache_is_acquire_pending(candidate)) {
pr_notice("Potential volume collision new=%08x old=%08x",
candidate->debug_id, collidee_debug_id);
fscache_stat(&fscache_n_volumes_collision);
- wait_var_event(&candidate->flags, !fscache_is_acquire_pending(candidate));
+ wait_on_bit(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING,
+ TASK_UNINTERRUPTIBLE);
}
}
fscache_end_cache_access(volume->cache,
fscache_access_acquire_volume_end);
- clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags);
- wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING);
+ clear_and_wake_up_bit(FSCACHE_VOLUME_CREATING, &volume->flags);
fscache_put_volume(volume, fscache_volume_put_create_work);
}
hlist_bl_for_each_entry(cursor, p, h, hash_link) {
if (fscache_volume_same(cursor, volume)) {
fscache_see_volume(cursor, fscache_volume_see_hash_wake);
- clear_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags);
- wake_up_bit(&cursor->flags, FSCACHE_VOLUME_ACQUIRE_PENDING);
+ clear_and_wake_up_bit(FSCACHE_VOLUME_ACQUIRE_PENDING,
+ &cursor->flags);
return;
}
}
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
-struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu)
+static struct posix_acl *__fuse_get_acl(struct fuse_conn *fc,
+ struct user_namespace *mnt_userns,
+ struct inode *inode, int type, bool rcu)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
int size;
const char *name;
void *value = NULL;
if (fuse_is_bad(inode))
return ERR_PTR(-EIO);
- if (!fc->posix_acl || fc->no_getxattr)
+ if (fc->no_getxattr)
return NULL;
if (type == ACL_TYPE_ACCESS)
return acl;
}
+static inline bool fuse_no_acl(const struct fuse_conn *fc,
+ const struct inode *inode)
+{
+ /*
+ * Refuse interacting with POSIX ACLs for daemons that
+ * don't support FUSE_POSIX_ACL and are not mounted on
+ * the host to retain backwards compatibility.
+ */
+ return !fc->posix_acl && (i_user_ns(inode) != &init_user_ns);
+}
+
+struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, int type)
+{
+ struct inode *inode = d_inode(dentry);
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ if (fuse_no_acl(fc, inode))
+ return ERR_PTR(-EOPNOTSUPP);
+
+ return __fuse_get_acl(fc, mnt_userns, inode, type, false);
+}
+
+struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ /*
+ * FUSE daemons before FUSE_POSIX_ACL was introduced could get and set
+ * POSIX ACLs without them being used for permission checking by the
+ * vfs. Retain that behavior for backwards compatibility as there are
+ * filesystems that do all permission checking for acls in the daemon
+ * and not in the kernel.
+ */
+ if (!fc->posix_acl)
+ return NULL;
+
+ return __fuse_get_acl(fc, &init_user_ns, inode, type, rcu);
+}
+
int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
struct posix_acl *acl, int type)
{
if (fuse_is_bad(inode))
return -EIO;
- if (!fc->posix_acl || fc->no_setxattr)
+ if (fc->no_setxattr || fuse_no_acl(fc, inode))
return -EOPNOTSUPP;
if (type == ACL_TYPE_ACCESS)
return ret;
}
- if (!vfsgid_in_group_p(i_gid_into_vfsgid(&init_user_ns, inode)) &&
+ /*
+ * Fuse daemons without FUSE_POSIX_ACL never changed the passed
+ * through POSIX ACLs. Such daemons don't expect setgid bits to
+ * be stripped.
+ */
+ if (fc->posix_acl &&
+ !vfsgid_in_group_p(i_gid_into_vfsgid(&init_user_ns, inode)) &&
!capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID))
extra_flags |= FUSE_SETXATTR_ACL_KILL_SGID;
} else {
ret = fuse_removexattr(inode, name);
}
- forget_all_cached_acls(inode);
- fuse_invalidate_attr(inode);
+
+ if (fc->posix_acl) {
+ /*
+ * Fuse daemons without FUSE_POSIX_ACL never cached POSIX ACLs
+ * and didn't invalidate attributes. Retain that behavior.
+ */
+ forget_all_cached_acls(inode);
+ fuse_invalidate_attr(inode);
+ }
return ret;
}
.permission = fuse_permission,
.getattr = fuse_getattr,
.listxattr = fuse_listxattr,
- .get_inode_acl = fuse_get_acl,
+ .get_inode_acl = fuse_get_inode_acl,
+ .get_acl = fuse_get_acl,
.set_acl = fuse_set_acl,
.fileattr_get = fuse_fileattr_get,
.fileattr_set = fuse_fileattr_set,
.permission = fuse_permission,
.getattr = fuse_getattr,
.listxattr = fuse_listxattr,
- .get_inode_acl = fuse_get_acl,
+ .get_inode_acl = fuse_get_inode_acl,
+ .get_acl = fuse_get_acl,
.set_acl = fuse_set_acl,
.fileattr_get = fuse_fileattr_get,
.fileattr_set = fuse_fileattr_set,
ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size);
int fuse_removexattr(struct inode *inode, const char *name);
extern const struct xattr_handler *fuse_xattr_handlers[];
-extern const struct xattr_handler *fuse_acl_xattr_handlers[];
-extern const struct xattr_handler *fuse_no_acl_xattr_handlers[];
struct posix_acl;
-struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu);
+struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu);
+struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, int type);
int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
struct posix_acl *acl, int type);
fuse_dax_dontcache(inode, attr->flags);
}
-static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
+static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr,
+ struct fuse_conn *fc)
{
inode->i_mode = attr->mode & S_IFMT;
inode->i_size = attr->size;
new_decode_dev(attr->rdev));
} else
BUG();
+ /*
+ * Ensure that we don't cache acls for daemons without FUSE_POSIX_ACL
+ * so they see the exact same behavior as before.
+ */
+ if (!fc->posix_acl)
+ inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
}
static int fuse_inode_eq(struct inode *inode, void *_nodeidp)
if (!inode)
return NULL;
- fuse_init_inode(inode, attr);
+ fuse_init_inode(inode, attr, fc);
get_fuse_inode(inode)->nodeid = nodeid;
inode->i_flags |= S_AUTOMOUNT;
goto done;
if (!fc->writeback_cache || !S_ISREG(attr->mode))
inode->i_flags |= S_NOCMTIME;
inode->i_generation = generation;
- fuse_init_inode(inode, attr);
+ fuse_init_inode(inode, attr, fc);
unlock_new_inode(inode);
} else if (fuse_stale_inode(inode, generation, attr)) {
/* nodeid was reused, any I/O on the old inode should fail */
if ((flags & FUSE_POSIX_ACL)) {
fc->default_permissions = 1;
fc->posix_acl = 1;
- fm->sb->s_xattr = fuse_acl_xattr_handlers;
}
if (flags & FUSE_CACHE_SYMLINKS)
fc->cache_symlinks = 1;
if (sb->s_user_ns != &init_user_ns)
sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER;
sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION);
-
- /*
- * If we are not in the initial user namespace posix
- * acls must be translated.
- */
- if (sb->s_user_ns != &init_user_ns)
- sb->s_xattr = fuse_no_acl_xattr_handlers;
}
static int fuse_fill_super_submount(struct super_block *sb,
return fuse_setxattr(inode, name, value, size, flags, 0);
}
-static bool no_xattr_list(struct dentry *dentry)
-{
- return false;
-}
-
-static int no_xattr_get(const struct xattr_handler *handler,
- struct dentry *dentry, struct inode *inode,
- const char *name, void *value, size_t size)
-{
- return -EOPNOTSUPP;
-}
-
-static int no_xattr_set(const struct xattr_handler *handler,
- struct user_namespace *mnt_userns,
- struct dentry *dentry, struct inode *nodee,
- const char *name, const void *value,
- size_t size, int flags)
-{
- return -EOPNOTSUPP;
-}
-
static const struct xattr_handler fuse_xattr_handler = {
.prefix = "",
.get = fuse_xattr_get,
&fuse_xattr_handler,
NULL
};
-
-const struct xattr_handler *fuse_acl_xattr_handlers[] = {
- &posix_acl_access_xattr_handler,
- &posix_acl_default_xattr_handler,
- &fuse_xattr_handler,
- NULL
-};
-
-static const struct xattr_handler fuse_no_acl_access_xattr_handler = {
- .name = XATTR_NAME_POSIX_ACL_ACCESS,
- .flags = ACL_TYPE_ACCESS,
- .list = no_xattr_list,
- .get = no_xattr_get,
- .set = no_xattr_set,
-};
-
-static const struct xattr_handler fuse_no_acl_default_xattr_handler = {
- .name = XATTR_NAME_POSIX_ACL_DEFAULT,
- .flags = ACL_TYPE_ACCESS,
- .list = no_xattr_list,
- .get = no_xattr_get,
- .set = no_xattr_set,
-};
-
-const struct xattr_handler *fuse_no_acl_xattr_handlers[] = {
- &fuse_no_acl_access_xattr_handler,
- &fuse_no_acl_default_xattr_handler,
- &fuse_xattr_handler,
- NULL
-};
brelse(bd->bd_bh);
}
+static int __gfs2_writepage(struct page *page, struct writeback_control *wbc,
+ void *data)
+{
+ struct address_space *mapping = data;
+ int ret = mapping->a_ops->writepage(page, wbc);
+ mapping_set_error(mapping, ret);
+ return ret;
+}
+
/**
* gfs2_ail1_start_one - Start I/O on a transaction
* @sdp: The superblock
if (!mapping)
continue;
spin_unlock(&sdp->sd_ail_lock);
- ret = filemap_fdatawrite_wbc(mapping, wbc);
+ ret = write_cache_pages(mapping, wbc, __gfs2_writepage, mapping);
if (need_resched()) {
blk_finish_plug(plug);
cond_resched();
/* panic? */
return -EIO;
+ res = -EIO;
if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN)
- return -EIO;
+ goto out;
fd.search_key->cat = HFS_I(main_inode)->cat_key;
if (hfs_brec_find(&fd))
- /* panic? */
goto out;
if (S_ISDIR(main_inode->i_mode)) {
- WARN_ON(fd.entrylength < sizeof(struct hfs_cat_dir));
+ if (fd.entrylength < sizeof(struct hfs_cat_dir))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_dir));
if (rec.type != HFS_CDR_DIR ||
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_dir));
} else if (HFS_IS_RSRC(inode)) {
+ if (fd.entrylength < sizeof(struct hfs_cat_file))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
hfs_inode_write_fork(inode, rec.file.RExtRec,
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
} else {
- WARN_ON(fd.entrylength < sizeof(struct hfs_cat_file));
+ if (fd.entrylength < sizeof(struct hfs_cat_file))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
if (rec.type != HFS_CDR_FIL ||
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
}
+ res = 0;
out:
hfs_find_exit(&fd);
- return 0;
+ return res;
}
static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
dn_off = le32_to_cpu(authblob->DomainName.BufferOffset);
dn_len = le16_to_cpu(authblob->DomainName.Length);
- if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len)
+ if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len ||
+ nt_len < CIFS_ENCPWD_SIZE)
return -EINVAL;
/* TODO : use domain name that imported from configuration file */
{
struct ksmbd_conn *conn = (struct ksmbd_conn *)p;
struct ksmbd_transport *t = conn->transport;
- unsigned int pdu_size;
+ unsigned int pdu_size, max_allowed_pdu_size;
char hdr_buf[4] = {0,};
int size;
pdu_size = get_rfc1002_len(hdr_buf);
ksmbd_debug(CONN, "RFC1002 header %u bytes\n", pdu_size);
+ if (conn->status == KSMBD_SESS_GOOD)
+ max_allowed_pdu_size =
+ SMB3_MAX_MSGSIZE + conn->vals->max_write_size;
+ else
+ max_allowed_pdu_size = SMB3_MAX_MSGSIZE;
+
+ if (pdu_size > max_allowed_pdu_size) {
+ pr_err_ratelimited("PDU length(%u) excceed maximum allowed pdu size(%u) on connection(%d)\n",
+ pdu_size, max_allowed_pdu_size,
+ conn->status);
+ break;
+ }
+
/*
* Check if pdu size is valid (min : smb header size,
* max : 0x00FFFFFF).
*/
if (pdu_size < __SMB2_HEADER_STRUCTURE_SIZE ||
pdu_size > MAX_STREAM_PROT_LEN) {
- continue;
+ break;
}
/* 4 for rfc1002 length field */
size = pdu_size + 4;
- conn->request_buf = kvmalloc(size, GFP_KERNEL);
+ conn->request_buf = kvmalloc(size,
+ GFP_KERNEL |
+ __GFP_NOWARN |
+ __GFP_NORETRY);
if (!conn->request_buf)
- continue;
+ break;
memcpy(conn->request_buf, hdr_buf, sizeof(hdr_buf));
if (!ksmbd_smb_request(conn))
__u32 sub_auth[3]; /* Subauth value for Security ID */
__u32 smb2_max_credits; /* MAX credits */
__u32 smbd_max_io_size; /* smbd read write size */
- __u32 reserved[127]; /* Reserved room */
+ __u32 max_connections; /* Number of maximum simultaneous connections */
+ __u32 reserved[126]; /* Reserved room */
__u32 ifc_list_sz; /* interfaces list size */
__s8 ____payload[];
};
return ret;
if (da->version != 3 && da->version != 4) {
- pr_err("v%d version is not supported\n", da->version);
+ ksmbd_debug(VFS, "v%d version is not supported\n", da->version);
return -EINVAL;
}
return ret;
if (da->version != version2) {
- pr_err("ndr version mismatched(version: %d, version2: %d)\n",
+ ksmbd_debug(VFS, "ndr version mismatched(version: %d, version2: %d)\n",
da->version, version2);
return -EINVAL;
}
if (ret)
return ret;
if (acl->version != 4) {
- pr_err("v%d version is not supported\n", acl->version);
+ ksmbd_debug(VFS, "v%d version is not supported\n", acl->version);
return -EINVAL;
}
if (ret)
return ret;
if (acl->version != version2) {
- pr_err("ndr version mismatched(version: %d, version2: %d)\n",
+ ksmbd_debug(VFS, "ndr version mismatched(version: %d, version2: %d)\n",
acl->version, version2);
return -EINVAL;
}
unsigned int share_fake_fscaps;
struct smb_sid domain_sid;
unsigned int auth_mechs;
+ unsigned int max_connections;
char *conf[SERVER_CONF_WORK_GROUP + 1];
};
if (conn->posix_ext_supported)
status.tree_conn->posix_extensions = true;
-out_err1:
rsp->StructureSize = cpu_to_le16(16);
+ inc_rfc1001_len(work->response_buf, 16);
+out_err1:
rsp->Capabilities = 0;
rsp->Reserved = 0;
/* default manual caching */
rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING;
- inc_rfc1001_len(work->response_buf, 16);
if (!IS_ERR(treename))
kfree(treename);
rsp->hdr.Status = STATUS_ACCESS_DENIED;
}
+ if (status.ret != KSMBD_TREE_CONN_STATUS_OK)
+ smb2_set_err_rsp(work);
+
return rc;
}
bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work)
{
struct ksmbd_conn *conn = work->conn;
+ struct ksmbd_session *sess = work->sess;
struct smb2_hdr *rsp = smb2_get_msg(work->response_buf);
if (conn->dialect < SMB30_PROT_ID)
rsp = ksmbd_resp_buf_next(work);
if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE &&
+ sess->user && !user_guest(sess->user) &&
rsp->Status == STATUS_SUCCESS)
return true;
return false;
#define SMB21_DEFAULT_IOSIZE (1024 * 1024)
#define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024)
-#define SMB3_MIN_IOSIZE (64 * 1024)
-#define SMB3_MAX_IOSIZE (8 * 1024 * 1024)
+#define SMB3_MIN_IOSIZE (64 * 1024)
+#define SMB3_MAX_IOSIZE (8 * 1024 * 1024)
+#define SMB3_MAX_MSGSIZE (4 * 4096)
/*
* Definitions for SMB2 Protocol Data Units (network frames)
if (req->smbd_max_io_size)
init_smbd_max_io_size(req->smbd_max_io_size);
+ if (req->max_connections)
+ server_conf.max_connections = req->max_connections;
+
ret = ksmbd_set_netbios_name(req->netbios_name);
ret |= ksmbd_set_server_string(req->server_string);
ret |= ksmbd_set_work_group(req->work_group);
#define IFACE_STATE_DOWN BIT(0)
#define IFACE_STATE_CONFIGURED BIT(1)
+static atomic_t active_num_conn;
+
struct interface {
struct task_struct *ksmbd_kthread;
struct socket *ksmbd_socket;
struct tcp_transport *t;
t = alloc_transport(client_sk);
- if (!t)
+ if (!t) {
+ sock_release(client_sk);
return -ENOMEM;
+ }
csin = KSMBD_TCP_PEER_SOCKADDR(KSMBD_TRANS(t)->conn);
if (kernel_getpeername(client_sk, csin) < 0) {
continue;
}
+ if (server_conf.max_connections &&
+ atomic_inc_return(&active_num_conn) >= server_conf.max_connections) {
+ pr_info_ratelimited("Limit the maximum number of connections(%u)\n",
+ atomic_read(&active_num_conn));
+ atomic_dec(&active_num_conn);
+ sock_release(client_sk);
+ continue;
+ }
+
ksmbd_debug(CONN, "connect success: accepted new connection\n");
client_sk->sk->sk_rcvtimeo = KSMBD_TCP_RECV_TIMEOUT;
client_sk->sk->sk_sndtimeo = KSMBD_TCP_SEND_TIMEOUT;
struct msghdr ksmbd_msg;
struct kvec *iov;
struct ksmbd_conn *conn = KSMBD_TRANS(t)->conn;
+ int max_retry = 2;
iov = get_conn_iovec(t, nr_segs);
if (!iov)
} else if (conn->status == KSMBD_SESS_NEED_RECONNECT) {
total_read = -EAGAIN;
break;
- } else if (length == -ERESTARTSYS || length == -EAGAIN) {
+ } else if ((length == -ERESTARTSYS || length == -EAGAIN) &&
+ max_retry) {
usleep_range(1000, 2000);
length = 0;
+ max_retry--;
continue;
} else if (length <= 0) {
total_read = -EAGAIN;
static void ksmbd_tcp_disconnect(struct ksmbd_transport *t)
{
free_transport(TCP_TRANS(t));
+ if (server_conf.max_connections)
+ atomic_dec(&active_num_conn);
}
static void tcp_destroy_socket(struct socket *ksmbd_socket)
config NFS_V4_2_READ_PLUS
bool "NFS: Enable support for the NFSv4.2 READ_PLUS operation"
depends on NFS_V4_2
- default y
+ default n
help
- Choose Y here to enable the use of READ_PLUS over NFS v4.2. READ_PLUS
- attempts to improve read performance by compressing out sparse holes
- in the file contents.
+ This is intended for developers only. The READ_PLUS operation has
+ been shown to have issues under specific conditions and should not
+ be used in production.
const struct cred *cred)
{
const struct task_struct *parent;
+ const struct cred *pcred;
u64 ret;
rcu_read_lock();
for (;;) {
parent = rcu_dereference(task->real_parent);
- if (parent == task || cred_fscmp(parent->cred, cred) != 0)
+ pcred = rcu_dereference(parent->cred);
+ if (parent == task || cred_fscmp(pcred, cred) != 0)
break;
task = parent;
}
* but do it without locking.
*/
struct nfs_inode *nfsi = NFS_I(inode);
+ u64 login_time = nfs_access_login_time(current, cred);
struct nfs_access_entry *cache;
int err = -ECHILD;
struct list_head *lh;
cache = NULL;
if (cache == NULL)
goto out;
+ if ((s64)(login_time - cache->timestamp) > 0)
+ goto out;
if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
goto out;
*mask = cache->mask;
return &fl->generic_hdr;
}
+static bool
+filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg)
+{
+ return flseg->num_fh > 1;
+}
+
/*
* filelayout_pg_test(). Called by nfs_can_coalesce_requests()
*
size = pnfs_generic_pg_test(pgio, prev, req);
if (!size)
return 0;
+ else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg)))
+ return size;
/* see if req and prev are in the same stripe */
if (prev) {
.seeks = 1,
};
+/**
+ * nfsd_file_cond_queue - conditionally unhash and queue a nfsd_file
+ * @nf: nfsd_file to attempt to queue
+ * @dispose: private list to queue successfully-put objects
+ *
+ * Unhash an nfsd_file, try to get a reference to it, and then put that
+ * reference. If it's the last reference, queue it to the dispose list.
+ */
+static void
+nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose)
+ __must_hold(RCU)
+{
+ int decrement = 1;
+
+ /* If we raced with someone else unhashing, ignore it */
+ if (!nfsd_file_unhash(nf))
+ return;
+
+ /* If we can't get a reference, ignore it */
+ if (!nfsd_file_get(nf))
+ return;
+
+ /* Extra decrement if we remove from the LRU */
+ if (nfsd_file_lru_remove(nf))
+ ++decrement;
+
+ /* If refcount goes to 0, then put on the dispose list */
+ if (refcount_sub_and_test(decrement, &nf->nf_ref)) {
+ list_add(&nf->nf_lru, dispose);
+ trace_nfsd_file_closing(nf);
+ }
+}
+
/**
* nfsd_file_queue_for_close: try to close out any open nfsd_files for an inode
* @inode: inode on which to close out nfsd_files
rcu_read_lock();
do {
- int decrement = 1;
-
nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key,
nfsd_file_rhash_params);
if (!nf)
break;
-
- /* If we raced with someone else unhashing, ignore it */
- if (!nfsd_file_unhash(nf))
- continue;
-
- /* If we can't get a reference, ignore it */
- if (!nfsd_file_get(nf))
- continue;
-
- /* Extra decrement if we remove from the LRU */
- if (nfsd_file_lru_remove(nf))
- ++decrement;
-
- /* If refcount goes to 0, then put on the dispose list */
- if (refcount_sub_and_test(decrement, &nf->nf_ref)) {
- list_add(&nf->nf_lru, dispose);
- trace_nfsd_file_closing(nf);
- }
+ nfsd_file_cond_queue(nf, dispose);
} while (1);
rcu_read_unlock();
}
nf = rhashtable_walk_next(&iter);
while (!IS_ERR_OR_NULL(nf)) {
- if (!net || nf->nf_net == net) {
- nfsd_file_unhash(nf);
- nfsd_file_lru_remove(nf);
- list_add(&nf->nf_lru, &dispose);
- }
+ if (!net || nf->nf_net == net)
+ nfsd_file_cond_queue(nf, &dispose);
nf = rhashtable_walk_next(&iter);
}
static __be32
nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **pnf,
- bool open, bool want_gc)
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **pnf, bool want_gc)
{
struct nfsd_file_lookup_key key = {
.type = NFSD_FILE_KEY_FULL,
status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags));
out:
if (status == nfs_ok) {
- if (open)
- this_cpu_inc(nfsd_file_acquisitions);
+ this_cpu_inc(nfsd_file_acquisitions);
*pnf = nf;
} else {
if (refcount_dec_and_test(&nf->nf_ref))
out_status:
put_cred(key.cred);
- if (open)
- trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
+ trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
return status;
open_file:
trace_nfsd_file_alloc(nf);
nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode);
if (nf->nf_mark) {
- if (open) {
+ if (file) {
+ get_file(file);
+ nf->nf_file = file;
+ status = nfs_ok;
+ trace_nfsd_file_opened(nf, status);
+ } else {
status = nfsd_open_verified(rqstp, fhp, may_flags,
&nf->nf_file);
trace_nfsd_file_open(nf, status);
- } else
- status = nfs_ok;
+ }
} else
status = nfserr_jukebox;
/*
nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, true);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true);
}
/**
nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false);
}
/**
- * nfsd_file_create - Get a struct nfsd_file, do not open
+ * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file
* @rqstp: the RPC transaction being executed
* @fhp: the NFS filehandle of the file just created
* @may_flags: NFSD_MAY_ settings for the file
+ * @file: cached, already-open file (may be NULL)
* @pnf: OUT: new or found "struct nfsd_file" object
*
- * The nfsd_file_object returned by this API is reference-counted
- * but not garbage-collected. The object is released immediately
- * one RCU grace period after the final nfsd_file_put().
+ * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist,
+ * and @file is non-NULL, use it to instantiate a new nfsd_file instead of
+ * opening a new one.
*
* Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
* network byte order is returned.
*/
__be32
-nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **pnf)
+nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false);
}
/*
unsigned int may_flags, struct nfsd_file **nfp);
__be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **nfp);
-__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **nfp);
+__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **nfp);
int nfsd_file_cache_stats_show(struct seq_file *m, void *v);
#endif /* _FS_NFSD_FILECACHE_H */
atomic_t nfsd_courtesy_clients;
struct shrinker nfsd_client_shrinker;
- struct delayed_work nfsd_shrinker_work;
+ struct work_struct nfsd_shrinker_work;
};
/* Simple check to find out if a given net was properly initialized */
* the client wants us to do more in this compound:
*/
if (!nfsd4_last_compound_op(rqstp))
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* check stateid */
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
/* allow 20secs for mount/unmount for now - revisit */
if (signal_pending(current) ||
(schedule_timeout(20*HZ) == 0)) {
+ finish_wait(&nn->nfsd_ssc_waitq, &wait);
kfree(work);
return nfserr_eagain;
}
cstate->minorversion = args->minorversion;
fh_init(current_fh, NFS4_FHSIZE);
fh_init(save_fh, NFS4_FHSIZE);
-
/*
* Don't use the deferral mechanism for NFSv4; compounds make it
* too hard to avoid non-idempotency problems.
*/
- __clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
/*
* According to RFC3010, this takes precedence over all other errors.
out:
cstate->status = status;
/* Reset deferral mechanism for RPC deferrals */
- __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
return rpc_success;
}
if (!count)
count = atomic_long_read(&num_delegations);
if (count)
- mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
+ queue_work(laundry_wq, &nn->nfsd_shrinker_work);
return (unsigned long)count;
}
return SHRINK_STOP;
}
-int
+void
nfsd4_init_leases_net(struct nfsd_net *nn)
{
struct sysinfo si;
nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
atomic_set(&nn->nfsd_courtesy_clients, 0);
- nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
- nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
- nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
- return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
-}
-
-void
-nfsd4_leases_net_shutdown(struct nfsd_net *nn)
-{
- unregister_shrinker(&nn->nfsd_client_shrinker);
}
static void init_nfs4_replay(struct nfs4_replay *rp)
if (!fp->fi_fds[oflag]) {
spin_unlock(&fp->fi_lock);
- if (!open->op_filp) {
- status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
- if (status != nfs_ok)
- goto out_put_access;
- } else {
- status = nfsd_file_create(rqstp, cur_fh, access, &nf);
- if (status != nfs_ok)
- goto out_put_access;
- nf->nf_file = open->op_filp;
- open->op_filp = NULL;
- trace_nfsd_file_create(rqstp, access, nf);
- }
+ status = nfsd_file_acquire_opened(rqstp, cur_fh, access,
+ open->op_filp, &nf);
+ if (status != nfs_ok)
+ goto out_put_access;
spin_lock(&fp->fi_lock);
if (!fp->fi_fds[oflag]) {
static void
nfsd4_state_shrinker_worker(struct work_struct *work)
{
- struct delayed_work *dwork = to_delayed_work(work);
- struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+ struct nfsd_net *nn = container_of(work, struct nfsd_net,
nfsd_shrinker_work);
courtesy_client_reaper(nn);
INIT_LIST_HEAD(&nn->blocked_locks_lru);
INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
- INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
+ INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
get_net(net);
+ nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
+ nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
+ nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
+
+ if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"))
+ goto err_shrinker;
return 0;
+err_shrinker:
+ put_net(net);
+ kfree(nn->sessionid_hashtbl);
err_sessionid:
kfree(nn->unconf_id_hashtbl);
err_unconf_id:
struct list_head *pos, *next, reaplist;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ unregister_shrinker(&nn->nfsd_client_shrinker);
+ cancel_work(&nn->nfsd_shrinker_work);
cancel_delayed_work_sync(&nn->laundromat_work);
locks_end_grace(&nn->nfsd4_manager);
nfsd4_client_tracking_exit(net);
nfs4_state_destroy_net(net);
- rhltable_destroy(&nfs4_file_rhltable);
#ifdef CONFIG_NFSD_V4_2_INTER_SSC
nfsd4_ssc_shutdown_umount(nn);
#endif
nfs4_state_shutdown(void)
{
nfsd4_destroy_callback_queue();
+ rhltable_destroy(&nfs4_file_rhltable);
}
static void
argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
- __clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
return true;
}
case nfserr_noent:
xdr_truncate_encode(xdr, start_offset);
goto skip_entry;
+ case nfserr_jukebox:
+ /*
+ * The pseudoroot should only display dentries that lead to
+ * exports. If we get EJUKEBOX here, then we can't tell whether
+ * this entry should be included. Just fail the whole READDIR
+ * with NFS4ERR_DELAY in that case, and hope that the situation
+ * will resolve itself by the client's next attempt.
+ */
+ if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT)
+ goto fail;
+ fallthrough;
default:
/*
* If the client requested the RDATTR_ERROR attribute,
goto out_idmap_error;
nn->nfsd_versions = NULL;
nn->nfsd4_minorversions = NULL;
- retval = nfsd4_init_leases_net(nn);
- if (retval)
- goto out_drc_error;
+ nfsd4_init_leases_net(nn);
retval = nfsd_reply_cache_init(nn);
if (retval)
goto out_cache_error;
return 0;
out_cache_error:
- nfsd4_leases_net_shutdown(nn);
-out_drc_error:
nfsd_idmap_shutdown(net);
out_idmap_error:
nfsd_export_shutdown(net);
nfsd_idmap_shutdown(net);
nfsd_export_shutdown(net);
nfsd_netns_free_versions(net_generic(net, nfsd_net_id));
- nfsd4_leases_net_shutdown(nn);
}
static struct pernet_operations nfsd_net_ops = {
extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn);
#endif
-extern int nfsd4_init_leases_net(struct nfsd_net *nn);
-extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn);
+extern void nfsd4_init_leases_net(struct nfsd_net *nn);
#else /* CONFIG_NFSD_V4 */
static inline int nfsd4_is_junction(struct dentry *dentry)
return 0;
}
-static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; };
-static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {};
+static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { };
#define register_cld_notifier() 0
#define unregister_cld_notifier() do { } while(0)
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
return rpc_success;
}
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
return rpc_success;
}
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- nfsd_file_cache_shutdown_net(net);
nfs4_state_shutdown_net(net);
+ nfsd_file_cache_shutdown_net(net);
if (nn->lockd_up) {
lockd_down(net);
nn->lockd_up = false;
)
);
-TRACE_EVENT(nfsd_file_create,
- TP_PROTO(
- const struct svc_rqst *rqstp,
- unsigned int may_flags,
- const struct nfsd_file *nf
- ),
-
- TP_ARGS(rqstp, may_flags, nf),
-
- TP_STRUCT__entry(
- __field(const void *, nf_inode)
- __field(const void *, nf_file)
- __field(unsigned long, may_flags)
- __field(unsigned long, nf_flags)
- __field(unsigned long, nf_may)
- __field(unsigned int, nf_ref)
- __field(u32, xid)
- ),
-
- TP_fast_assign(
- __entry->nf_inode = nf->nf_inode;
- __entry->nf_file = nf->nf_file;
- __entry->may_flags = may_flags;
- __entry->nf_flags = nf->nf_flags;
- __entry->nf_may = nf->nf_may;
- __entry->nf_ref = refcount_read(&nf->nf_ref);
- __entry->xid = be32_to_cpu(rqstp->rq_xid);
- ),
-
- TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p",
- __entry->xid, __entry->nf_inode,
- show_nfsd_may_flags(__entry->may_flags),
- __entry->nf_ref, show_nf_flags(__entry->nf_flags),
- show_nfsd_may_flags(__entry->nf_may), __entry->nf_file
- )
-);
-
TRACE_EVENT(nfsd_file_insert_err,
TP_PROTO(
const struct svc_rqst *rqstp,
)
);
-TRACE_EVENT(nfsd_file_open,
- TP_PROTO(struct nfsd_file *nf, __be32 status),
+DECLARE_EVENT_CLASS(nfsd_file_open_class,
+ TP_PROTO(const struct nfsd_file *nf, __be32 status),
TP_ARGS(nf, status),
TP_STRUCT__entry(
__field(void *, nf_inode) /* cannot be dereferenced */
__entry->nf_file)
)
+#define DEFINE_NFSD_FILE_OPEN_EVENT(name) \
+DEFINE_EVENT(nfsd_file_open_class, name, \
+ TP_PROTO( \
+ const struct nfsd_file *nf, \
+ __be32 status \
+ ), \
+ TP_ARGS(nf, status))
+
+DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_open);
+DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_opened);
+
TRACE_EVENT(nfsd_file_is_cached,
TP_PROTO(
const struct inode *inode,
ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh,
&submit_ptr);
if (ret) {
- if (ret != -EEXIST)
- return ret;
- goto out_check;
+ if (likely(ret == -EEXIST))
+ goto out_check;
+ if (ret == -ENOENT) {
+ /*
+ * Block address translation failed due to invalid
+ * value of 'ptr'. In this case, return internal code
+ * -EINVAL (broken bmap) to notify bmap layer of fatal
+ * metadata corruption.
+ */
+ ret = -EINVAL;
+ }
+ return ret;
}
if (ra) {
minseg = range[0] + segbytes - 1;
do_div(minseg, segbytes);
+
+ if (range[1] < 4096)
+ goto out;
+
maxseg = NILFS_SB2_OFFSET_BYTES(range[1]);
+ if (maxseg < segbytes)
+ goto out;
+
do_div(maxseg, segbytes);
maxseg--;
if (newsize > devsize)
goto out;
+ /*
+ * Prevent underflow in second superblock position calculation.
+ * The exact minimum size check is done in nilfs_sufile_resize().
+ */
+ if (newsize < 4096) {
+ ret = -ENOSPC;
+ goto out;
+ }
+
/*
* Write lock is required to protect some functions depending
* on the number of segments, the number of reserved segments,
{
struct nilfs_super_block **sbp = nilfs->ns_sbp;
struct buffer_head **sbh = nilfs->ns_sbh;
- u64 sb2off = NILFS_SB2_OFFSET_BYTES(bdev_nr_bytes(nilfs->ns_bdev));
+ u64 sb2off, devsize = bdev_nr_bytes(nilfs->ns_bdev);
int valid[2], swp = 0;
+ if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) {
+ nilfs_err(sb, "device size too small");
+ return -EINVAL;
+ }
+ sb2off = NILFS_SB2_OFFSET_BYTES(devsize);
+
sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize,
&sbh[0]);
sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]);
new_valid = ntfs_up_block(sb, min_t(u64, ni->i_valid, new_size));
- ni_lock(ni);
-
truncate_setsize(inode, new_size);
+ ni_lock(ni);
+
down_write(&ni->file.run_lock);
err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_size,
&new_valid, ni->mi.sbi->options->prealloc, NULL);
if (!c->metacopy && c->stat.size) {
err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size);
if (err)
- return err;
+ goto out_fput;
}
err = ovl_copy_up_metadata(c, temp);
if (err)
return err;
+ if (!kuid_has_mapping(current_user_ns(), ctx.stat.uid) ||
+ !kgid_has_mapping(current_user_ns(), ctx.stat.gid))
+ return -EOVERFLOW;
+
ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags);
if (parent) {
page = pfn_swap_entry_to_page(swpent);
}
if (page) {
- int mapcount = page_mapcount(page);
-
- if (mapcount >= 2)
+ if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte))
mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
else
mss->private_hugetlb += huge_page_size(hstate_vma(vma));
#define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\
sizeof(u64))
/* xattr id lookup table defines */
-#define SQUASHFS_XATTR_BYTES(A) ((A) * sizeof(struct squashfs_xattr_id))
+#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id))
#define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \
SQUASHFS_METADATA_SIZE)
long long bytes_used;
unsigned int inodes;
unsigned int fragments;
- int xattr_ids;
+ unsigned int xattr_ids;
unsigned int ids;
bool panic_on_errors;
const struct squashfs_decompressor_thread_ops *thread_ops;
#ifdef CONFIG_SQUASHFS_XATTR
extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64,
- u64 *, int *);
+ u64 *, unsigned int *);
extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *,
unsigned int *, unsigned long long *);
#else
static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb,
- u64 start, u64 *xattr_table_start, int *xattr_ids)
+ u64 start, u64 *xattr_table_start, unsigned int *xattr_ids)
{
struct squashfs_xattr_id_table *id_table;
* Read uncompressed xattr id lookup table indexes from disk into memory
*/
__le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
- u64 *xattr_table_start, int *xattr_ids)
+ u64 *xattr_table_start, unsigned int *xattr_ids)
{
struct squashfs_sb_info *msblk = sb->s_fs_info;
unsigned int len, indexes;
*/
if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK))
return;
- added_bytes = (last_ext->extLength & UDF_EXTENT_LENGTH_MASK) - new_elen;
+ added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
last_ext->extLength += added_bytes;
UDF_I(inode)->i_lenExtents += added_bytes;
struct kernel_lb_addr eloc, tmpeloc;
int c = 1;
loff_t lbcount = 0, b_off = 0;
- udf_pblk_t newblocknum, newblock;
+ udf_pblk_t newblocknum, newblock = 0;
sector_t offset = 0;
int8_t etype;
struct udf_inode_info *iinfo = UDF_I(inode);
ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len);
if (ret < 0) {
*err = ret;
- newblock = 0;
goto out_free;
}
c = 0;
goal, err);
if (!newblocknum) {
*err = -ENOSPC;
- newblock = 0;
goto out_free;
}
if (isBeyondEOF)
return ctx->features & UFFD_FEATURE_INITIALIZED;
}
+static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP;
+
+ vma->vm_flags = flags;
+ /*
+ * For shared mappings, we want to enable writenotify while
+ * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply
+ * recalculate vma->vm_page_prot whenever userfaultfd-wp changes.
+ */
+ if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed)
+ vma_set_page_prot(vma);
+}
+
static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
int wake_flags, void *key)
{
for_each_vma(vmi, vma) {
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma,
+ vma->vm_flags & ~__VM_UFFD_FLAGS);
}
}
mmap_write_unlock(mm);
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
return 0;
}
} else {
/* Drop uffd context if remap feature not enabled */
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
}
}
prev = vma;
}
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
mmap_write_unlock(mm);
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx.ctx = ctx;
if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
skip:
const unsigned int *limits,
unsigned long long leaf_blocks)
{
- unsigned long long node_blocks = limits[1];
+ /*
+ * The root btree block can have fewer than minrecs pointers in it
+ * because the tree might not be big enough to require that amount of
+ * fanout. Hence it has a minimum size of 2 pointers, not limits[1].
+ */
+ unsigned long long node_blocks = 2;
unsigned long long blocks_left = leaf_blocks - 1;
unsigned int height = 1;
*
*/
busyp->bno = fend;
+ busyp->length = bend - fend;
} else if (bbno < fbno) {
/*
* Case 8:
struct xfs_inodegc, work);
struct llist_node *node = llist_del_all(&gc->list);
struct xfs_inode *ip, *n;
+ unsigned int nofs_flag;
WRITE_ONCE(gc->items, 0);
if (!node)
return;
+ /*
+ * We can allocate memory here while doing writeback on behalf of
+ * memory reclaim. To avoid memory allocation deadlocks set the
+ * task-wide nofs context for the following operations.
+ */
+ nofs_flag = memalloc_nofs_save();
+
ip = llist_entry(node, struct xfs_inode, i_gclist);
trace_xfs_inodegc_worker(ip->i_mount, READ_ONCE(gc->shrinker_hits));
xfs_iflags_set(ip, XFS_INACTIVATING);
xfs_inodegc_inactivate(ip);
}
+
+ memalloc_nofs_restore(nofs_flag);
}
/*
static int
xfs_bulk_ireq_setup(
struct xfs_mount *mp,
- struct xfs_bulk_ireq *hdr,
+ const struct xfs_bulk_ireq *hdr,
struct xfs_ibulk *breq,
void __user *ubuffer)
{
switch (hdr->ino) {
case XFS_BULK_IREQ_SPECIAL_ROOT:
- hdr->ino = mp->m_sb.sb_rootino;
+ breq->startino = mp->m_sb.sb_rootino;
break;
default:
return -EINVAL;
return true;
}
-const struct iomap_page_ops xfs_iomap_page_ops = {
+static const struct iomap_page_ops xfs_iomap_page_ops = {
.iomap_valid = xfs_iomap_valid,
};
while (1) {
struct xfs_dquot *batch[XFS_DQ_LOOKUP_BATCH];
- int error = 0;
+ int error;
int i;
mutex_lock(&qi->qi_tree_lock);
goto convert;
}
- ASSERT(cmap->br_startoff > imap->br_startoff);
-
/* Allocate the entire reservation as unwritten blocks. */
nimaps = 1;
error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
data_size = zonefs_check_zone_condition(inode, zone,
false, false);
}
+ } else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO &&
+ data_size > isize) {
+ /* Do not expose garbage data */
+ data_size = isize;
}
/*
ret = submit_bio_wait(bio);
+ /*
+ * If the file zone was written underneath the file system, the zone
+ * write pointer may not be where we expect it to be, but the zone
+ * append write can still succeed. So check manually that we wrote where
+ * we intended to, that is, at zi->i_wpoffset.
+ */
+ if (!ret) {
+ sector_t wpsector =
+ zi->i_zsector + (zi->i_wpoffset >> SECTOR_SHIFT);
+
+ if (bio->bi_iter.bi_sector != wpsector) {
+ zonefs_warn(inode->i_sb,
+ "Corrupted write pointer %llu for zone at %llu\n",
+ wpsector, zi->i_zsector);
+ ret = -EIO;
+ }
+ }
+
zonefs_file_write_dio_end_io(iocb, size, ret, 0);
trace_zonefs_file_dio_append(inode, size, ret);
u32 hardware_id:1;
u32 bus_address:1;
u32 platform_id:1;
- u32 reserved:29;
+ u32 backlight:1;
+ u32 reserved:28;
};
struct acpi_device_pnp {
};
#if IS_ENABLED(CONFIG_ACPI_VIDEO)
+extern void acpi_video_report_nolcd(void);
extern int acpi_video_register(void);
extern void acpi_video_unregister(void);
extern void acpi_video_register_backlight(void);
struct acpi_video_device_brightness **dev_br,
int *pmax_level);
#else
+static inline void acpi_video_report_nolcd(void) { return; };
static inline int acpi_video_register(void) { return -ENODEV; }
static inline void acpi_video_unregister(void) { return; }
static inline void acpi_video_register_backlight(void) { return; }
#define PRINTK_INDEX
#endif
+/*
+ * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler.
+ * Otherwise, the type of .notes section would become PROGBITS instead of NOTES.
+ */
#define NOTES \
+ /DISCARD/ : { *(.note.GNU-stack) } \
.notes : AT(ADDR(.notes) - LOAD_OFFSET) { \
BOUNDED_SECTION_BY(.note.*, _notes) \
} NOTES_HEADERS \
*/
struct drm_client_dev *client;
- /**
- * @handle: Buffer handle
- */
- u32 handle;
-
/**
* @pitch: Buffer pitch
*/
* the smem_start field should always be cleared to zero.
*/
bool hint_leak_smem_start;
+
+#ifdef CONFIG_FB_DEFERRED_IO
+ /**
+ * @fbdefio:
+ *
+ * Temporary storage for the driver's FB deferred I/O handler. If the
+ * driver uses the DRM fbdev emulation layer, this is set by the core
+ * to a generic deferred I/O handler if a driver is preferring to use
+ * a shadow buffer.
+ */
+ struct fb_deferred_io fbdefio;
+#endif
};
static inline struct drm_fb_helper *
#include <linux/types.h>
+struct drm_atomic_state;
struct drm_crtc;
struct drm_framebuffer;
struct drm_modeset_acquire_ctx;
struct drm_vma_offset_node *node);
int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag);
+int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag);
void drm_vma_node_revoke(struct drm_vma_offset_node *node,
struct drm_file *tag);
bool drm_vma_node_is_allowed(struct drm_vma_offset_node *node,
*/
#define kunit_test_init_section_suites(__suites...) \
__kunit_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe), \
- CONCATENATE(__UNIQUE_ID(suites), _probe), \
##__suites)
#define kunit_test_init_section_suite(suite) \
.right_text = #right, \
}; \
\
- if (likely(memcmp(__left, __right, __size) op 0)) \
- break; \
+ if (likely(__left && __right)) \
+ if (likely(memcmp(__left, __right, __size) op 0)) \
+ break; \
\
_KUNIT_FAILED(test, \
assert_type, \
struct vgic_io_device dist_iodev;
bool has_its;
- bool save_its_tables_in_progress;
+ bool table_write_in_progress;
/*
* Contains the attributes and gpa of the LPI configuration table.
#define LINUX_APPLE_GMUX_H
#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/pnp.h>
#define GMUX_ACPI_HID "APP000B"
+/*
+ * gmux port offsets. Many of these are not yet used, but may be in the
+ * future, and it's useful to have them documented here anyhow.
+ */
+#define GMUX_PORT_VERSION_MAJOR 0x04
+#define GMUX_PORT_VERSION_MINOR 0x05
+#define GMUX_PORT_VERSION_RELEASE 0x06
+#define GMUX_PORT_SWITCH_DISPLAY 0x10
+#define GMUX_PORT_SWITCH_GET_DISPLAY 0x11
+#define GMUX_PORT_INTERRUPT_ENABLE 0x14
+#define GMUX_PORT_INTERRUPT_STATUS 0x16
+#define GMUX_PORT_SWITCH_DDC 0x28
+#define GMUX_PORT_SWITCH_EXTERNAL 0x40
+#define GMUX_PORT_SWITCH_GET_EXTERNAL 0x41
+#define GMUX_PORT_DISCRETE_POWER 0x50
+#define GMUX_PORT_MAX_BRIGHTNESS 0x70
+#define GMUX_PORT_BRIGHTNESS 0x74
+#define GMUX_PORT_VALUE 0xc2
+#define GMUX_PORT_READ 0xd0
+#define GMUX_PORT_WRITE 0xd4
+
+#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4)
+
#if IS_ENABLED(CONFIG_APPLE_GMUX)
+static inline bool apple_gmux_is_indexed(unsigned long iostart)
+{
+ u16 val;
+
+ outb(0xaa, iostart + 0xcc);
+ outb(0x55, iostart + 0xcd);
+ outb(0x00, iostart + 0xce);
+
+ val = inb(iostart + 0xcc) | (inb(iostart + 0xcd) << 8);
+ if (val == 0x55aa)
+ return true;
+
+ return false;
+}
/**
- * apple_gmux_present() - detect if gmux is built into the machine
+ * apple_gmux_detect() - detect if gmux is built into the machine
+ *
+ * @pnp_dev: Device to probe or NULL to use the first matching device
+ * @indexed_ret: Returns (by reference) if the gmux is indexed or not
+ *
+ * Detect if a supported gmux device is present by actually probing it.
+ * This avoids the false positives returned on some models by
+ * apple_gmux_present().
+ *
+ * Return: %true if a supported gmux ACPI device is detected and the kernel
+ * was configured with CONFIG_APPLE_GMUX, %false otherwise.
+ */
+static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret)
+{
+ u8 ver_major, ver_minor, ver_release;
+ struct device *dev = NULL;
+ struct acpi_device *adev;
+ struct resource *res;
+ bool indexed = false;
+ bool ret = false;
+
+ if (!pnp_dev) {
+ adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1);
+ if (!adev)
+ return false;
+
+ dev = get_device(acpi_get_first_physical_node(adev));
+ acpi_dev_put(adev);
+ if (!dev)
+ return false;
+
+ pnp_dev = to_pnp_dev(dev);
+ }
+
+ res = pnp_get_resource(pnp_dev, IORESOURCE_IO, 0);
+ if (!res || resource_size(res) < GMUX_MIN_IO_LEN)
+ goto out;
+
+ /*
+ * Invalid version information may indicate either that the gmux
+ * device isn't present or that it's a new one that uses indexed io.
+ */
+ ver_major = inb(res->start + GMUX_PORT_VERSION_MAJOR);
+ ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR);
+ ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE);
+ if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) {
+ indexed = apple_gmux_is_indexed(res->start);
+ if (!indexed)
+ goto out;
+ }
+
+ if (indexed_ret)
+ *indexed_ret = indexed;
+
+ ret = true;
+out:
+ put_device(dev);
+ return ret;
+}
+
+/**
+ * apple_gmux_present() - check if gmux ACPI device is present
*
* Drivers may use this to activate quirks specific to dual GPU MacBook Pros
* and Mac Pros, e.g. for deferred probing, runtime pm and backlight.
*
- * Return: %true if gmux is present and the kernel was configured
+ * Return: %true if gmux ACPI device is present and the kernel was configured
* with CONFIG_APPLE_GMUX, %false otherwise.
*/
static inline bool apple_gmux_present(void)
return false;
}
+static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret)
+{
+ return false;
+}
+
#endif /* !CONFIG_APPLE_GMUX */
#endif /* LINUX_APPLE_GMUX_H */
extern void bio_set_pages_dirty(struct bio *bio);
extern void bio_check_pages_dirty(struct bio *bio);
+extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+ struct bio *src, struct bvec_iter *src_iter);
extern void bio_copy_data(struct bio *dst, struct bio *src);
extern void bio_free_pages(struct bio *bio);
void guard_bio_eod(struct bio *bio);
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
int (*report_zones)(struct gendisk *, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
+ char *(*devnode)(struct gendisk *disk, umode_t *mode);
/* returns the length of the identifier or a negative errno: */
int (*get_unique_id)(struct gendisk *disk, u8 id[16],
enum blk_unique_id id_type);
struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
void bpf_prog_put(struct bpf_prog *prog);
-void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
+void bpf_prog_free_id(struct bpf_prog *prog);
void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
struct btf_field *btf_record_find(const struct btf_record *rec,
#define CEPH_AUTH_NAME_DEFAULT "guest"
-/* mount state */
-enum {
- CEPH_MOUNT_MOUNTING,
- CEPH_MOUNT_MOUNTED,
- CEPH_MOUNT_UNMOUNTING,
- CEPH_MOUNT_UNMOUNTED,
- CEPH_MOUNT_SHUTDOWN,
- CEPH_MOUNT_RECOVER,
-};
-
static inline unsigned long ceph_timeout_jiffies(unsigned long timeout)
{
return timeout ?: MAX_SCHEDULE_TIMEOUT;
QCA_HDR_MGMT_COMMAND_LEN + \
QCA_HDR_MGMT_DATA1_LEN)
-#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */
-#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */
+#define QCA_HDR_MGMT_DATA2_LEN 28 /* Other 28 byte for the mdio data */
+#define QCA_HDR_MGMT_PADDING_LEN 18 /* Padding to reach the min Ethernet packet */
#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \
QCA_HDR_LEN + \
#define EFI_RT_SUPPORTED_ALL 0x3fff
-#define EFI_RT_SUPPORTED_TIME_SERVICES 0x000f
+#define EFI_RT_SUPPORTED_TIME_SERVICES 0x0003
+#define EFI_RT_SUPPORTED_WAKEUP_SERVICES 0x000c
#define EFI_RT_SUPPORTED_VARIABLE_SERVICES 0x0070
extern struct mm_struct efi_mm;
* Dumping its extra ELF program headers includes all the other information
* a debugger needs to easily find how the gate DSO was being used.
*/
-extern Elf_Half elf_core_extra_phdrs(void);
+extern Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm);
extern int
elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset);
extern int
elf_core_write_extra_data(struct coredump_params *cprm);
-extern size_t elf_core_extra_data_size(void);
+extern size_t elf_core_extra_data_size(struct coredump_params *cprm);
#else
-static inline Elf_Half elf_core_extra_phdrs(void)
+static inline Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return 0;
}
return 1;
}
-static inline size_t elf_core_extra_data_size(void)
+static inline size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
return 0;
}
extern void fb_deferred_io_open(struct fb_info *info,
struct inode *inode,
struct file *file);
+extern void fb_deferred_io_release(struct fb_info *info);
extern void fb_deferred_io_cleanup(struct fb_info *info);
extern int fb_deferred_io_fsync(struct file *file, loff_t start,
loff_t end, int datasync);
const u64 address,
const enum zynqmp_pm_request_ack ack);
int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode);
-int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1);
-int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1);
+int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode);
+int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode);
int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value);
int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config,
u32 value);
return -ENODEV;
}
-static inline int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1)
+static inline int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode)
{
return -ENODEV;
}
-static inline int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1)
+static inline int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode)
{
return -ENODEV;
}
int state; /* state of grant or error if -ve */
unsigned int debug_id;
} afs;
+ struct {
+ struct inode *inode;
+ } ceph;
} fl_u;
} __randomize_layout;
static inline void __kunmap_local(const void *addr)
{
#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
- kunmap_flush_on_unmap(addr);
+ kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE));
#endif
}
static inline void __kunmap_atomic(const void *addr)
{
#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
- kunmap_flush_on_unmap(addr);
+ kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE));
#endif
pagefault_enable();
if (IS_ENABLED(CONFIG_PREEMPT_RT))
#include <linux/fs.h>
#include <linux/hugetlb_inline.h>
#include <linux/cgroup.h>
+#include <linux/page_ref.h>
#include <linux/list.h>
#include <linux/kref.h>
#include <linux/pgtable.h>
if (!page_size_log)
return &default_hstate;
- return size_to_hstate(1UL << page_size_log);
+ if (page_size_log < BITS_PER_LONG)
+ return size_to_hstate(1UL << page_size_log);
+
+ return NULL;
}
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
}
#endif
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+static inline bool hugetlb_pmd_shared(pte_t *pte)
+{
+ return page_count(virt_to_page(pte)) > 1;
+}
+#else
+static inline bool hugetlb_pmd_shared(pte_t *pte)
+{
+ return false;
+}
+#endif
+
bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr);
#ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
struct {
spinlock_t completion_lock;
+ bool poll_multi_queue;
+
/*
* ->iopoll_list is protected by the ctx->uring_lock for
* io_uring instances that don't use IORING_SETUP_SQPOLL.
*/
struct io_wq_work_list iopoll_list;
struct io_hash_table cancel_table;
- bool poll_multi_queue;
struct llist_head work_llist;
static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
struct bdi_writeback *wb)
{
+ struct mem_cgroup *memcg;
+
if (mem_cgroup_disabled())
return;
- if (unlikely(&folio_memcg(folio)->css != wb->memcg_css))
+ memcg = folio_memcg(folio);
+ if (unlikely(memcg && &memcg->css != wb->memcg_css))
mem_cgroup_track_foreign_dirty_slowpath(folio, wb);
}
MLX5_VPORT_ADMIN_STATE_AUTO = 0x2,
};
+enum {
+ MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN = 0x1,
+ MLX5_VPORT_CVLAN_INSERT_ALWAYS = 0x3,
+};
+
enum {
MLX5_L3_PROT_TYPE_IPV4 = 0,
MLX5_L3_PROT_TYPE_IPV6 = 1,
struct mlx5_cmd_debug dbg;
struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES];
int checksum_disabled;
- struct mlx5_cmd_stats *stats;
+ struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX];
};
struct mlx5_cmd_mailbox {
struct dentry *lag_debugfs;
};
+enum mlx5_func_type {
+ MLX5_PF,
+ MLX5_VF,
+ MLX5_SF,
+ MLX5_HOST_PF,
+ MLX5_FUNC_TYPE_NUM,
+};
+
struct mlx5_ft_pool;
struct mlx5_priv {
/* IRQ table valid only for real pci devices PF or VF */
struct mlx5_nb pg_nb;
struct workqueue_struct *pg_wq;
struct xarray page_root_xa;
- u32 fw_pages;
atomic_t reg_pages;
struct list_head free_list;
- u32 vfs_pages;
- u32 host_pf_pages;
+ u32 fw_pages;
+ u32 page_counters[MLX5_FUNC_TYPE_NUM];
u32 fw_pages_alloc_failed;
u32 give_pages_dropped;
u32 reclaim_pages_discard;
u8 vport_svlan_insert[0x1];
u8 vport_cvlan_insert_if_not_exist[0x1];
u8 vport_cvlan_insert_overwrite[0x1];
- u8 reserved_at_5[0x2];
+ u8 reserved_at_5[0x1];
+ u8 vport_cvlan_insert_always[0x1];
u8 esw_shared_ingress_acl[0x1];
u8 esw_uplink_ingress_acl[0x1];
u8 root_ft_on_other_esw[0x1];
* define their own version of this macro in <asm/pgtable.h>
*/
#if BITS_PER_LONG == 64
-/* This function must be updated when the size of struct page grows above 80
+/* This function must be updated when the size of struct page grows above 96
* or reduces below 56. The idea that compiler optimizes out switch()
* statement, and only leaves move/store instructions. Also the compiler can
* combine write statements if they are both assignments and can be reordered,
{
unsigned long *_pp = (void *)page;
- /* Check that struct page is either 56, 64, 72, or 80 bytes */
+ /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */
BUILD_BUG_ON(sizeof(struct page) & 7);
BUILD_BUG_ON(sizeof(struct page) < 56);
- BUILD_BUG_ON(sizeof(struct page) > 80);
+ BUILD_BUG_ON(sizeof(struct page) > 96);
switch (sizeof(struct page)) {
+ case 96:
+ _pp[11] = 0;
+ fallthrough;
+ case 88:
+ _pp[10] = 0;
+ fallthrough;
case 80:
_pp[9] = 0;
fallthrough;
__folio_put(folio);
}
-/**
- * release_pages - release an array of pages or folios
+/*
+ * union release_pages_arg - an array of pages or folios
*
- * This just releases a simple array of multiple pages, and
+ * release_pages() releases a simple array of multiple pages, and
* accepts various different forms of said page array: either
* a regular old boring array of pages, an array of folios, or
* an array of encoded page pointers.
* Not using anon_vma_name because it generates a warning if mmap_lock
* is not held, which might be the case here.
*/
- if (!vma->vm_file)
- anon_vma_name_put(vma->anon_name);
+ anon_vma_name_put(vma->anon_name);
}
static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
/*
* For private and shared anonymous mappings, a pointer to a null
* terminated string containing the name given to the vma, or NULL if
- * unnamed. Serialized by mmap_sem. Use anon_vma_name to access.
+ * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
*/
struct anon_vma_name *anon_name;
#endif
#define __LINUX_MTD_SPI_NOR_H
#include <linux/bitops.h>
-#include <linux/mtd/cfi.h>
#include <linux/mtd/mtd.h>
#include <linux/spi/spi-mem.h>
int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb);
int unregister_netdevice_notifier_net(struct net *net,
struct notifier_block *nb);
-void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net,
- struct notifier_block *nb);
int register_netdevice_notifier_dev_net(struct net_device *dev,
struct notifier_block *nb,
struct netdev_net_notifier *nn);
};
/* Max range where every element is added/deleted in one step */
-#define IPSET_MAX_RANGE (1<<20)
+#define IPSET_MAX_RANGE (1<<14)
/* The max revision number supported by any set type + 1 */
#define IPSET_REVISION_MAX 9
#ifndef _LINUX_NVME_H
#define _LINUX_NVME_H
+#include <linux/bits.h>
#include <linux/types.h>
#include <linux/uuid.h>
NVME_CMD_EFFECTS_NCC = 1 << 2,
NVME_CMD_EFFECTS_NIC = 1 << 3,
NVME_CMD_EFFECTS_CCC = 1 << 4,
- NVME_CMD_EFFECTS_CSE_MASK = 3 << 16,
+ NVME_CMD_EFFECTS_CSE_MASK = GENMASK(18, 16),
NVME_CMD_EFFECTS_UUID_SEL = 1 << 19,
+ NVME_CMD_EFFECTS_SCOPE_MASK = GENMASK(31, 20),
};
struct nvme_effects_log {
* @word_size: Minimum read/write access granularity.
* @stride: Minimum read/write access stride.
* @priv: User context passed to read/write callbacks.
- * @wp-gpio: Write protect pin
* @ignore_wp: Write Protect pin is managed by the provider.
*
* Note: A default "nvmem<id>" name will be assigned to the device if
const char *name;
int id;
struct module *owner;
- struct gpio_desc *wp_gpio;
const struct nvmem_cell_info *cells;
int ncells;
const struct nvmem_keepout *keepout;
*
* You can also use this function if you're holding a lock that prevents
* pages being frozen & removed; eg the i_pages lock for the page cache
- * or the mmap_sem or page table lock for page tables. In this case,
+ * or the mmap_lock or page table lock for page tables. In this case,
* it will always succeed, and you could have used a plain folio_get(),
* but it's sometimes more convenient to have a common function called
* from both locked and RCU-protected contexts.
flags, NULL);
}
+static inline struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index,
+ const struct irq_affinity_desc *affdesc)
+{
+ struct msi_map map = { .index = -ENOSYS, };
+
+ return map;
+}
+
+static inline void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map)
+{
+}
+
static inline void pci_free_irq_vectors(struct pci_dev *dev)
{
}
void (*stop)(struct arm_pmu *);
void (*reset)(void *);
int (*map_event)(struct perf_event *event);
- bool (*filter)(struct pmu *pmu, int cpu);
int num_events;
bool secure_access; /* 32-bit ARM only */
#define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40
* whether to advertise lower-speed modes for that interface. It is
* assumed that if a rate matching mode is supported on an interface,
* then that interface's rate can be adapted to all slower link speeds
- * supported by the phy. If iface is %PHY_INTERFACE_MODE_NA, and the phy
- * supports any kind of rate matching for any interface, then it must
- * return that rate matching mode (preferring %RATE_MATCH_PAUSE to
- * %RATE_MATCH_CRS). If the interface is not supported, this should
+ * supported by the phy. If the interface is not supported, this should
* return %RATE_MATCH_NONE.
*/
int (*get_rate_matching)(struct phy_device *phydev,
--- /dev/null
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
+ * DVD-RW devices.
+ *
+ */
+#ifndef __PKTCDVD_H
+#define __PKTCDVD_H
+
+#include <linux/blkdev.h>
+#include <linux/completion.h>
+#include <linux/cdrom.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/mempool.h>
+#include <uapi/linux/pktcdvd.h>
+
+/* default bio write queue congestion marks */
+#define PKT_WRITE_CONGESTION_ON 10000
+#define PKT_WRITE_CONGESTION_OFF 9000
+
+
+struct packet_settings
+{
+ __u32 size; /* packet size in (512 byte) sectors */
+ __u8 fp; /* fixed packets */
+ __u8 link_loss; /* the rest is specified
+ * as per Mt Fuji */
+ __u8 write_type;
+ __u8 track_mode;
+ __u8 block_mode;
+};
+
+/*
+ * Very crude stats for now
+ */
+struct packet_stats
+{
+ unsigned long pkt_started;
+ unsigned long pkt_ended;
+ unsigned long secs_w;
+ unsigned long secs_rg;
+ unsigned long secs_r;
+};
+
+struct packet_cdrw
+{
+ struct list_head pkt_free_list;
+ struct list_head pkt_active_list;
+ spinlock_t active_list_lock; /* Serialize access to pkt_active_list */
+ struct task_struct *thread;
+ atomic_t pending_bios;
+};
+
+/*
+ * Switch to high speed reading after reading this many kilobytes
+ * with no interspersed writes.
+ */
+#define HI_SPEED_SWITCH 512
+
+struct packet_iosched
+{
+ atomic_t attention; /* Set to non-zero when queue processing is needed */
+ int writing; /* Non-zero when writing, zero when reading */
+ spinlock_t lock; /* Protecting read/write queue manipulations */
+ struct bio_list read_queue;
+ struct bio_list write_queue;
+ sector_t last_write; /* The sector where the last write ended */
+ int successive_reads;
+};
+
+/*
+ * 32 buffers of 2048 bytes
+ */
+#if (PAGE_SIZE % CD_FRAMESIZE) != 0
+#error "PAGE_SIZE must be a multiple of CD_FRAMESIZE"
+#endif
+#define PACKET_MAX_SIZE 128
+#define FRAMES_PER_PAGE (PAGE_SIZE / CD_FRAMESIZE)
+#define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9)
+
+enum packet_data_state {
+ PACKET_IDLE_STATE, /* Not used at the moment */
+ PACKET_WAITING_STATE, /* Waiting for more bios to arrive, so */
+ /* we don't have to do as much */
+ /* data gathering */
+ PACKET_READ_WAIT_STATE, /* Waiting for reads to fill in holes */
+ PACKET_WRITE_WAIT_STATE, /* Waiting for the write to complete */
+ PACKET_RECOVERY_STATE, /* Recover after read/write errors */
+ PACKET_FINISHED_STATE, /* After write has finished */
+
+ PACKET_NUM_STATES /* Number of possible states */
+};
+
+/*
+ * Information needed for writing a single packet
+ */
+struct pktcdvd_device;
+
+struct packet_data
+{
+ struct list_head list;
+
+ spinlock_t lock; /* Lock protecting state transitions and */
+ /* orig_bios list */
+
+ struct bio_list orig_bios; /* Original bios passed to pkt_make_request */
+ /* that will be handled by this packet */
+ int write_size; /* Total size of all bios in the orig_bios */
+ /* list, measured in number of frames */
+
+ struct bio *w_bio; /* The bio we will send to the real CD */
+ /* device once we have all data for the */
+ /* packet we are going to write */
+ sector_t sector; /* First sector in this packet */
+ int frames; /* Number of frames in this packet */
+
+ enum packet_data_state state; /* Current state */
+ atomic_t run_sm; /* Incremented whenever the state */
+ /* machine needs to be run */
+ long sleep_time; /* Set this to non-zero to make the state */
+ /* machine run after this many jiffies. */
+
+ atomic_t io_wait; /* Number of pending IO operations */
+ atomic_t io_errors; /* Number of read/write errors during IO */
+
+ struct bio *r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */
+ struct page *pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE];
+
+ int cache_valid; /* If non-zero, the data for the zone defined */
+ /* by the sector variable is completely cached */
+ /* in the pages[] vector. */
+
+ int id; /* ID number for debugging */
+ struct pktcdvd_device *pd;
+};
+
+struct pkt_rb_node {
+ struct rb_node rb_node;
+ struct bio *bio;
+};
+
+struct packet_stacked_data
+{
+ struct bio *bio; /* Original read request bio */
+ struct pktcdvd_device *pd;
+};
+#define PSD_POOL_SIZE 64
+
+struct pktcdvd_device
+{
+ struct block_device *bdev; /* dev attached */
+ dev_t pkt_dev; /* our dev */
+ char name[20];
+ struct packet_settings settings;
+ struct packet_stats stats;
+ int refcnt; /* Open count */
+ int write_speed; /* current write speed, kB/s */
+ int read_speed; /* current read speed, kB/s */
+ unsigned long offset; /* start offset */
+ __u8 mode_offset; /* 0 / 8 */
+ __u8 type;
+ unsigned long flags;
+ __u16 mmc3_profile;
+ __u32 nwa; /* next writable address */
+ __u32 lra; /* last recorded address */
+ struct packet_cdrw cdrw;
+ wait_queue_head_t wqueue;
+
+ spinlock_t lock; /* Serialize access to bio_queue */
+ struct rb_root bio_queue; /* Work queue of bios we need to handle */
+ int bio_queue_size; /* Number of nodes in bio_queue */
+ bool congested; /* Someone is waiting for bio_queue_size
+ * to drop. */
+ sector_t current_sector; /* Keep track of where the elevator is */
+ atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */
+ /* needs to be run. */
+ mempool_t rb_pool; /* mempool for pkt_rb_node allocations */
+
+ struct packet_iosched iosched;
+ struct gendisk *disk;
+
+ int write_congestion_off;
+ int write_congestion_on;
+
+ struct device *dev; /* sysfs pktcdvd[0-7] dev */
+
+ struct dentry *dfs_d_root; /* debugfs: devname directory */
+ struct dentry *dfs_f_info; /* debugfs: info file */
+};
+
+#endif /* __PKTCDVD_H */
SIMATIC_IPC_IPC477E = 0x00000A02,
SIMATIC_IPC_IPC127E = 0x00000D01,
SIMATIC_IPC_IPC227G = 0x00000F01,
- SIMATIC_IPC_IPC427G = 0x00001001,
+ SIMATIC_IPC_IPCBX_39A = 0x00001001,
+ SIMATIC_IPC_IPCPX_39A = 0x00001002,
};
static inline u32 simatic_ipc_get_station_id(u8 *data, int max_len)
#ifdef CONFIG_SHRINKER_DEBUG
extern int shrinker_debugfs_add(struct shrinker *shrinker);
-extern void shrinker_debugfs_remove(struct shrinker *shrinker);
+extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker);
extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker,
const char *fmt, ...);
#else /* CONFIG_SHRINKER_DEBUG */
{
return 0;
}
-static inline void shrinker_debugfs_remove(struct shrinker *shrinker)
+static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker)
{
+ return NULL;
}
static inline __printf(2, 3)
int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
#ifndef __ASSEMBLER__
#include <linux/types.h>
-#ifdef CONFIG_ARCH_OMAP1_ANY
+#ifdef CONFIG_ARCH_OMAP1
/*
* NOTE: Please use ioremap + __raw_read/write where possible instead of these
*/
extern void omap_writeb(u8 v, u32 pa);
extern void omap_writew(u16 v, u32 pa);
extern void omap_writel(u32 v, u32 pa);
-#else
+#elif defined(CONFIG_COMPILE_TEST)
static inline u8 omap_readb(u32 pa) { return 0; }
static inline u16 omap_readw(u32 pa) { return 0; }
static inline u32 omap_readl(u32 pa) { return 0; }
#define atomic_dec_and_lock_irqsave(atomic, lock, flags) \
__cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags)))
+extern int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock);
+#define atomic_dec_and_raw_lock(atomic, lock) \
+ __cond_lock(lock, _atomic_dec_and_raw_lock(atomic, lock))
+
+extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock,
+ unsigned long *flags);
+#define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) \
+ __cond_lock(lock, _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags)))
+
int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask,
size_t max_size, unsigned int cpu_mult,
gfp_t gfp, const char *name,
int rss_en;
int mac_port_sel_speed;
bool en_tx_lpi_clockgating;
+ bool rx_clk_runs_in_lpi;
int has_xgmac;
bool vlan_fail_q_en;
u8 vlan_fail_q;
char __user *, size_t);
extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *);
+/* returns true if the msg is in-flight, i.e., already eaten by the peer */
+static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) {
+ return (msg->copied != 0 && list_empty(&msg->list));
+}
+
struct rpc_clnt;
extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
extern int rpc_remove_client_dir(struct rpc_clnt *);
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
- unsigned int reclaim_options,
- nodemask_t *nodemask);
+ unsigned int reclaim_options);
extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
pg_data_t *pgdat,
* The loop below will unmap these fields if the log is larger than
* one page, so save them here for reference:
*/
- count = READ_ONCE(event->count);
- event_type = READ_ONCE(event->event_type);
+ count = event->count;
+ event_type = event->event_type;
/* Verify that it's the log header */
if (event_header->pcr_idx != 0 ||
const int align;
const int is_signed;
const int filter_type;
+ const int len;
};
int (*define_fields)(struct trace_event_call *);
};
}
/**
- * usb_set_intfdata() - associate driver-specific data with the interface
- * @intf: the usb interface
- * @data: pointer to the device priv structure or %NULL
+ * usb_set_intfdata() - associate driver-specific data with an interface
+ * @intf: USB interface
+ * @data: driver data
*
- * Drivers should use this function in their probe() to associate their
- * driver-specific data with the usb interface.
+ * Drivers can use this function in their probe() callbacks to associate
+ * driver-specific data with an interface.
*
- * When disconnecting, the core will take care of setting @intf back to %NULL,
- * so no actions are needed on the driver side. The interface should not be set
- * to %NULL before all actions completed (e.g. no outsanding URB remaining).
+ * Note that there is generally no need to clear the driver-data pointer even
+ * if some drivers do so for historical or implementation-specific reasons.
*/
static inline void usb_set_intfdata(struct usb_interface *intf, void *data)
{
extern int usb_acpi_set_power_state(struct usb_device *hdev, int index,
bool enable);
extern bool usb_acpi_power_manageable(struct usb_device *hdev, int index);
+extern int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index);
#else
static inline int usb_acpi_set_power_state(struct usb_device *hdev, int index,
bool enable) { return 0; }
static inline bool usb_acpi_power_manageable(struct usb_device *hdev, int index)
{ return true; }
+static inline int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index)
+ { return 0; }
#endif
/* USB autosuspend and autoresume */
*/
#define find_closest_descending(x, a, as) __find_closest(x, a, as, >=)
+/**
+ * is_insidevar - check if the @ptr points inside the @var memory range.
+ * @ptr: the pointer to a memory address.
+ * @var: the variable which address and size identify the memory range.
+ *
+ * Evaluates to true if the address in @ptr lies within the memory
+ * range allocated to @var.
+ */
+#define is_insidevar(ptr, var) \
+ ((uintptr_t)(ptr) >= (uintptr_t)(var) && \
+ (uintptr_t)(ptr) < (uintptr_t)(var) + sizeof(var))
+
#endif
struct sock;
struct socket;
struct rxrpc_call;
+enum rxrpc_abort_reason;
enum rxrpc_interruptibility {
RXRPC_INTERRUPTIBLE, /* Call is interruptible */
int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
struct iov_iter *, size_t *, bool, u32 *, u16 *);
bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
- u32, int, const char *);
+ u32, int, enum rxrpc_abort_reason);
void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
struct sockaddr_rxrpc *);
struct hlist_node node;
/* List of sockets hashed to this bucket */
struct hlist_head owners;
+ /* bhash has twsk in owners, but bhash2 has twsk in
+ * deathrow not to add a member in struct sock_common.
+ */
+ struct hlist_head deathrow;
};
static inline struct net *ib_net(const struct inet_bind_bucket *ib)
u32 tw_priority;
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
+ struct inet_bind2_bucket *tw_tb2;
+ struct hlist_node tw_bind2_node;
};
#define tw_tclass tw_tos
+#define twsk_for_each_bound_bhash2(__tw, list) \
+ hlist_for_each_entry(__tw, list, tw_bind2_node)
+
static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
{
return (struct inet_timewait_sock *)sk;
* @drv_priv: data area for driver use, will always be aligned to
* sizeof(void \*).
* @txq: the multicast data TX queue
- * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped,
- * protected by fq->lock.
* @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see
* &enum ieee80211_offload_flags.
* @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled.
bool probe_req_reg;
bool rx_mcast_action_reg;
- bool txqs_stopped[IEEE80211_NUM_ACS];
-
struct ieee80211_vif *mbssid_tx_vif;
/* must be last */
};
};
+#define MANA_IRQ_NAME_SZ 32
+
struct gdma_irq_context {
void (*handler)(void *arg);
void *arg;
+ char name[MANA_IRQ_NAME_SZ];
};
struct gdma_context {
/**
* struct nft_set_desc - description of set elements
*
+ * @ktype: key type
* @klen: key length
+ * @dtype: data type
* @dlen: data length
+ * @objtype: object type
+ * @flags: flags
* @size: number of set elements
+ * @policy: set policy
+ * @gc_int: garbage collector interval
* @field_len: length of each field in concatenation, bytes
* @field_count: number of concatenated fields in element
* @expr: set must support for expressions
*/
struct nft_set_desc {
+ u32 ktype;
unsigned int klen;
+ u32 dtype;
unsigned int dlen;
+ u32 objtype;
unsigned int size;
+ u32 policy;
+ u32 gc_int;
+ u64 timeout;
u8 field_len[NFT_REG32_COUNT];
u8 field_count;
bool expr;
static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
{
- return set->gc_int ? msecs_to_jiffies(set->gc_int) : HZ;
+ u32 gc_int = READ_ONCE(set->gc_int);
+
+ return gc_int ? msecs_to_jiffies(gc_int) : HZ;
}
/**
struct nft_trans_set {
struct nft_set *set;
u32 set_id;
+ u32 gc_int;
+ u64 timeout;
+ bool update;
bool bound;
};
(((struct nft_trans_set *)trans->data)->set_id)
#define nft_trans_set_bound(trans) \
(((struct nft_trans_set *)trans->data)->bound)
+#define nft_trans_set_update(trans) \
+ (((struct nft_trans_set *)trans->data)->update)
+#define nft_trans_set_timeout(trans) \
+ (((struct nft_trans_set *)trans->data)->timeout)
+#define nft_trans_set_gc_int(trans) \
+ (((struct nft_trans_set *)trans->data)->gc_int)
struct nft_trans_chain {
bool update;
int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
+/* Make sure qdisc is no longer in SCHED state. */
+static inline void qdisc_synchronize(const struct Qdisc *q)
+{
+ while (test_bit(__QDISC_STATE_SCHED, &q->state))
+ msleep(1);
+}
+
#endif
return false;
}
+static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk)
+{
+ skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
+ if (skb) {
+ if (sk_rmem_schedule(sk, skb, skb->truesize)) {
+ skb_set_owner_r(skb, sk);
+ return skb;
+ }
+ __kfree_skb(skb);
+ }
+ return NULL;
+}
+
static inline void skb_prepare_for_gro(struct sk_buff *skb)
{
if (skb->destructor != sock_wfree) {
return tp->classify(skb, tp, res);
}
+#endif /* CONFIG_NET_CLS */
+
static inline void tc_wrapper_init(void)
{
#ifdef CONFIG_X86
#endif
}
-#endif /* CONFIG_NET_CLS */
-
#else
#define TC_INDIRECT_SCOPE static
extern struct iscsi_cls_session *
iscsi_session_setup(struct iscsi_transport *, struct Scsi_Host *shost,
uint16_t, int, int, uint32_t, unsigned int);
+void iscsi_session_remove(struct iscsi_cls_session *cls_session);
+void iscsi_session_free(struct iscsi_cls_session *cls_session);
extern void iscsi_session_teardown(struct iscsi_cls_session *);
extern void iscsi_session_recovery_timedout(struct iscsi_cls_session *);
extern int iscsi_set_param(struct iscsi_cls_conn *cls_conn,
ISCSI_SESSION_FREE,
};
+enum {
+ ISCSI_SESSION_TARGET_UNBOUND,
+ ISCSI_SESSION_TARGET_ALLOCATED,
+ ISCSI_SESSION_TARGET_SCANNED,
+ ISCSI_SESSION_TARGET_UNBINDING,
+ ISCSI_SESSION_TARGET_MAX,
+};
+
#define ISCSI_MAX_TARGET -1
struct iscsi_cls_session {
*/
pid_t creator;
int state;
+ int target_state; /* session target bind state */
int sid; /* session id */
void *dd_data; /* LLD private data */
struct device dev; /* sysfs transport/container device */
#define RPI_FIRMWARE_CLK_RATE_REQUEST(_id) \
{ \
- .id = _id, \
+ .id = cpu_to_le32(_id), \
}
#if IS_ENABLED(CONFIG_RASPBERRYPI_FIRMWARE)
EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \
EM( FLUSH_DELALLOC_FULL, "FLUSH_DELALLOC_FULL") \
EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \
- EM( FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS") \
+ EM( FLUSH_DELAYED_REFS, "FLUSH_DELAYED_REFS") \
EM( ALLOC_CHUNK, "ALLOC_CHUNK") \
EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \
EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \
/*
* Declare tracing information enums and their string mappings for display.
*/
+#define rxrpc_abort_reasons \
+ /* AFS errors */ \
+ EM(afs_abort_general_error, "afs-error") \
+ EM(afs_abort_interrupted, "afs-intr") \
+ EM(afs_abort_oom, "afs-oom") \
+ EM(afs_abort_op_not_supported, "afs-op-notsupp") \
+ EM(afs_abort_probeuuid_negative, "afs-probeuuid-neg") \
+ EM(afs_abort_send_data_error, "afs-send-data") \
+ EM(afs_abort_unmarshal_error, "afs-unmarshal") \
+ /* rxperf errors */ \
+ EM(rxperf_abort_general_error, "rxperf-error") \
+ EM(rxperf_abort_oom, "rxperf-oom") \
+ EM(rxperf_abort_op_not_supported, "rxperf-op-notsupp") \
+ EM(rxperf_abort_unmarshal_error, "rxperf-unmarshal") \
+ /* RxKAD security errors */ \
+ EM(rxkad_abort_1_short_check, "rxkad1-short-check") \
+ EM(rxkad_abort_1_short_data, "rxkad1-short-data") \
+ EM(rxkad_abort_1_short_encdata, "rxkad1-short-encdata") \
+ EM(rxkad_abort_1_short_header, "rxkad1-short-hdr") \
+ EM(rxkad_abort_2_short_check, "rxkad2-short-check") \
+ EM(rxkad_abort_2_short_data, "rxkad2-short-data") \
+ EM(rxkad_abort_2_short_header, "rxkad2-short-hdr") \
+ EM(rxkad_abort_2_short_len, "rxkad2-short-len") \
+ EM(rxkad_abort_bad_checksum, "rxkad2-bad-cksum") \
+ EM(rxkad_abort_chall_key_expired, "rxkad-chall-key-exp") \
+ EM(rxkad_abort_chall_level, "rxkad-chall-level") \
+ EM(rxkad_abort_chall_no_key, "rxkad-chall-nokey") \
+ EM(rxkad_abort_chall_short, "rxkad-chall-short") \
+ EM(rxkad_abort_chall_version, "rxkad-chall-version") \
+ EM(rxkad_abort_resp_bad_callid, "rxkad-resp-bad-callid") \
+ EM(rxkad_abort_resp_bad_checksum, "rxkad-resp-bad-cksum") \
+ EM(rxkad_abort_resp_bad_param, "rxkad-resp-bad-param") \
+ EM(rxkad_abort_resp_call_ctr, "rxkad-resp-call-ctr") \
+ EM(rxkad_abort_resp_call_state, "rxkad-resp-call-state") \
+ EM(rxkad_abort_resp_key_expired, "rxkad-resp-key-exp") \
+ EM(rxkad_abort_resp_key_rejected, "rxkad-resp-key-rej") \
+ EM(rxkad_abort_resp_level, "rxkad-resp-level") \
+ EM(rxkad_abort_resp_nokey, "rxkad-resp-nokey") \
+ EM(rxkad_abort_resp_ooseq, "rxkad-resp-ooseq") \
+ EM(rxkad_abort_resp_short, "rxkad-resp-short") \
+ EM(rxkad_abort_resp_short_tkt, "rxkad-resp-short-tkt") \
+ EM(rxkad_abort_resp_tkt_aname, "rxkad-resp-tk-aname") \
+ EM(rxkad_abort_resp_tkt_expired, "rxkad-resp-tk-exp") \
+ EM(rxkad_abort_resp_tkt_future, "rxkad-resp-tk-future") \
+ EM(rxkad_abort_resp_tkt_inst, "rxkad-resp-tk-inst") \
+ EM(rxkad_abort_resp_tkt_len, "rxkad-resp-tk-len") \
+ EM(rxkad_abort_resp_tkt_realm, "rxkad-resp-tk-realm") \
+ EM(rxkad_abort_resp_tkt_short, "rxkad-resp-tk-short") \
+ EM(rxkad_abort_resp_tkt_sinst, "rxkad-resp-tk-sinst") \
+ EM(rxkad_abort_resp_tkt_sname, "rxkad-resp-tk-sname") \
+ EM(rxkad_abort_resp_unknown_tkt, "rxkad-resp-unknown-tkt") \
+ EM(rxkad_abort_resp_version, "rxkad-resp-version") \
+ /* rxrpc errors */ \
+ EM(rxrpc_abort_call_improper_term, "call-improper-term") \
+ EM(rxrpc_abort_call_reset, "call-reset") \
+ EM(rxrpc_abort_call_sendmsg, "call-sendmsg") \
+ EM(rxrpc_abort_call_sock_release, "call-sock-rel") \
+ EM(rxrpc_abort_call_sock_release_tba, "call-sock-rel-tba") \
+ EM(rxrpc_abort_call_timeout, "call-timeout") \
+ EM(rxrpc_abort_no_service_key, "no-serv-key") \
+ EM(rxrpc_abort_nomem, "nomem") \
+ EM(rxrpc_abort_service_not_offered, "serv-not-offered") \
+ EM(rxrpc_abort_shut_down, "shut-down") \
+ EM(rxrpc_abort_unsupported_security, "unsup-sec") \
+ EM(rxrpc_badmsg_bad_abort, "bad-abort") \
+ EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \
+ EM(rxrpc_badmsg_short_ack, "short-ack") \
+ EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \
+ EM(rxrpc_badmsg_short_hdr, "short-hdr") \
+ EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \
+ EM(rxrpc_badmsg_zero_call, "zero-call") \
+ EM(rxrpc_badmsg_zero_seq, "zero-seq") \
+ EM(rxrpc_badmsg_zero_service, "zero-service") \
+ EM(rxrpc_eproto_ackr_outside_window, "ackr-out-win") \
+ EM(rxrpc_eproto_ackr_sack_overflow, "ackr-sack-over") \
+ EM(rxrpc_eproto_ackr_short_sack, "ackr-short-sack") \
+ EM(rxrpc_eproto_ackr_zero, "ackr-zero") \
+ EM(rxrpc_eproto_bad_upgrade, "bad-upgrade") \
+ EM(rxrpc_eproto_data_after_last, "data-after-last") \
+ EM(rxrpc_eproto_different_last, "diff-last") \
+ EM(rxrpc_eproto_early_reply, "early-reply") \
+ EM(rxrpc_eproto_improper_term, "improper-term") \
+ EM(rxrpc_eproto_no_client_call, "no-cl-call") \
+ EM(rxrpc_eproto_no_client_conn, "no-cl-conn") \
+ EM(rxrpc_eproto_no_service_call, "no-sv-call") \
+ EM(rxrpc_eproto_reupgrade, "re-upgrade") \
+ EM(rxrpc_eproto_rxnull_challenge, "rxnull-chall") \
+ EM(rxrpc_eproto_rxnull_response, "rxnull-resp") \
+ EM(rxrpc_eproto_tx_rot_last, "tx-rot-last") \
+ EM(rxrpc_eproto_unexpected_ack, "unex-ack") \
+ EM(rxrpc_eproto_unexpected_ackall, "unex-ackall") \
+ EM(rxrpc_eproto_unexpected_implicit_end, "unex-impl-end") \
+ EM(rxrpc_eproto_unexpected_reply, "unex-reply") \
+ EM(rxrpc_eproto_wrong_security, "wrong-sec") \
+ EM(rxrpc_recvmsg_excess_data, "recvmsg-excess") \
+ EM(rxrpc_recvmsg_short_data, "recvmsg-short") \
+ E_(rxrpc_sendmsg_late_send, "sendmsg-late")
+
#define rxrpc_call_poke_traces \
+ EM(rxrpc_call_poke_abort, "Abort") \
+ EM(rxrpc_call_poke_complete, "Compl") \
EM(rxrpc_call_poke_error, "Error") \
EM(rxrpc_call_poke_idle, "Idle") \
EM(rxrpc_call_poke_start, "Start") \
#define rxrpc_skb_traces \
EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \
EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \
+ EM(rxrpc_skb_get_conn_secured, "GET conn-secd") \
EM(rxrpc_skb_get_conn_work, "GET conn-work") \
EM(rxrpc_skb_get_local_work, "GET locl-work") \
EM(rxrpc_skb_get_reject_work, "GET rej-work ") \
EM(rxrpc_skb_new_error_report, "NEW error-rpt") \
EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \
EM(rxrpc_skb_new_unshared, "NEW unshared ") \
+ EM(rxrpc_skb_put_conn_secured, "PUT conn-secd") \
EM(rxrpc_skb_put_conn_work, "PUT conn-work") \
EM(rxrpc_skb_put_error_report, "PUT error-rep") \
EM(rxrpc_skb_put_input, "PUT input ") \
#define rxrpc_peer_traces \
EM(rxrpc_peer_free, "FREE ") \
EM(rxrpc_peer_get_accept, "GET accept ") \
- EM(rxrpc_peer_get_activate_call, "GET act-call") \
EM(rxrpc_peer_get_bundle, "GET bundle ") \
EM(rxrpc_peer_get_client_conn, "GET cln-conn") \
EM(rxrpc_peer_get_input, "GET input ") \
EM(rxrpc_peer_put_bundle, "PUT bundle ") \
EM(rxrpc_peer_put_call, "PUT call ") \
EM(rxrpc_peer_put_conn, "PUT conn ") \
- EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \
EM(rxrpc_peer_put_input, "PUT input ") \
EM(rxrpc_peer_put_input_error, "PUT inpt-err") \
E_(rxrpc_peer_put_keepalive, "PUT keepaliv")
EM(rxrpc_bundle_get_client_call, "GET clt-call") \
EM(rxrpc_bundle_get_client_conn, "GET clt-conn") \
EM(rxrpc_bundle_get_service_conn, "GET svc-conn") \
+ EM(rxrpc_bundle_put_call, "PUT call ") \
EM(rxrpc_bundle_put_conn, "PUT conn ") \
EM(rxrpc_bundle_put_discard, "PUT discard ") \
E_(rxrpc_bundle_new, "NEW ")
EM(rxrpc_conn_get_call_input, "GET inp-call") \
EM(rxrpc_conn_get_conn_input, "GET inp-conn") \
EM(rxrpc_conn_get_idle, "GET idle ") \
- EM(rxrpc_conn_get_poke, "GET poke ") \
+ EM(rxrpc_conn_get_poke_abort, "GET pk-abort") \
+ EM(rxrpc_conn_get_poke_timer, "GET poke ") \
EM(rxrpc_conn_get_service_conn, "GET svc-conn") \
EM(rxrpc_conn_new_client, "NEW client ") \
EM(rxrpc_conn_new_service, "NEW service ") \
EM(rxrpc_conn_put_call, "PUT call ") \
EM(rxrpc_conn_put_call_input, "PUT inp-call") \
EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \
- EM(rxrpc_conn_put_discard, "PUT discard ") \
EM(rxrpc_conn_put_discard_idle, "PUT disc-idl") \
EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \
EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \
EM(rxrpc_conn_put_service_reaped, "PUT svc-reap") \
EM(rxrpc_conn_put_unbundle, "PUT unbundle") \
EM(rxrpc_conn_put_unidle, "PUT unidle ") \
+ EM(rxrpc_conn_put_work, "PUT work ") \
EM(rxrpc_conn_queue_challenge, "QUE chall ") \
EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \
EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \
- EM(rxrpc_conn_queue_timer, "QUE timer ") \
EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \
EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \
E_(rxrpc_conn_see_work, "SEE work ")
EM(rxrpc_client_chan_activate, "ChActv") \
EM(rxrpc_client_chan_disconnect, "ChDisc") \
EM(rxrpc_client_chan_pass, "ChPass") \
- EM(rxrpc_client_chan_wait_failed, "ChWtFl") \
EM(rxrpc_client_cleanup, "Clean ") \
EM(rxrpc_client_discard, "Discar") \
- EM(rxrpc_client_duplicate, "Duplic") \
EM(rxrpc_client_exposed, "Expose") \
EM(rxrpc_client_replace, "Replac") \
+ EM(rxrpc_client_queue_new_call, "Q-Call") \
EM(rxrpc_client_to_active, "->Actv") \
E_(rxrpc_client_to_idle, "->Idle")
#define rxrpc_call_traces \
+ EM(rxrpc_call_get_io_thread, "GET iothread") \
EM(rxrpc_call_get_input, "GET input ") \
EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \
EM(rxrpc_call_get_notify_socket, "GET notify ") \
EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \
EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \
EM(rxrpc_call_put_discard_error, "PUT disc-err") \
+ EM(rxrpc_call_put_io_thread, "PUT iothread") \
EM(rxrpc_call_put_input, "PUT input ") \
EM(rxrpc_call_put_kernel, "PUT kernel ") \
EM(rxrpc_call_put_poke, "PUT poke ") \
EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \
EM(rxrpc_call_put_unnotify, "PUT unnotify") \
EM(rxrpc_call_put_userid_exists, "PUT u-exists") \
+ EM(rxrpc_call_put_userid, "PUT user-id ") \
EM(rxrpc_call_see_accept, "SEE accept ") \
EM(rxrpc_call_see_activate_client, "SEE act-clnt") \
EM(rxrpc_call_see_connect_failed, "SEE con-fail") \
EM(rxrpc_call_see_connected, "SEE connect ") \
+ EM(rxrpc_call_see_disconnected, "SEE disconn ") \
EM(rxrpc_call_see_distribute_error, "SEE dist-err") \
EM(rxrpc_call_see_input, "SEE input ") \
EM(rxrpc_call_see_release, "SEE release ") \
#define EM(a, b) a,
#define E_(a, b) a
+enum rxrpc_abort_reason { rxrpc_abort_reasons } __mode(byte);
enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte);
enum rxrpc_call_poke_trace { rxrpc_call_poke_traces } __mode(byte);
enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte);
*/
#undef EM
#undef E_
+
+#ifndef RXRPC_TRACE_ONLY_DEFINE_ENUMS
+
#define EM(a, b) TRACE_DEFINE_ENUM(a);
#define E_(a, b) TRACE_DEFINE_ENUM(a);
+rxrpc_abort_reasons;
rxrpc_bundle_traces;
rxrpc_call_poke_traces;
rxrpc_call_traces;
);
TRACE_EVENT(rxrpc_abort,
- TP_PROTO(unsigned int call_nr, const char *why, u32 cid, u32 call_id,
- rxrpc_seq_t seq, int abort_code, int error),
+ TP_PROTO(unsigned int call_nr, enum rxrpc_abort_reason why,
+ u32 cid, u32 call_id, rxrpc_seq_t seq, int abort_code, int error),
TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error),
TP_STRUCT__entry(
__field(unsigned int, call_nr )
- __array(char, why, 4 )
+ __field(enum rxrpc_abort_reason, why )
__field(u32, cid )
__field(u32, call_id )
__field(rxrpc_seq_t, seq )
),
TP_fast_assign(
- memcpy(__entry->why, why, 4);
__entry->call_nr = call_nr;
+ __entry->why = why;
__entry->cid = cid;
__entry->call_id = call_id;
__entry->abort_code = abort_code;
TP_printk("c=%08x %08x:%08x s=%u a=%d e=%d %s",
__entry->call_nr,
__entry->cid, __entry->call_id, __entry->seq,
- __entry->abort_code, __entry->error, __entry->why)
+ __entry->abort_code, __entry->error,
+ __print_symbolic(__entry->why, rxrpc_abort_reasons))
);
TRACE_EVENT(rxrpc_call_complete,
);
TRACE_EVENT(rxrpc_recvmsg,
- TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why,
+ TP_PROTO(unsigned int call_debug_id, enum rxrpc_recvmsg_trace why,
int ret),
- TP_ARGS(call, why, ret),
+ TP_ARGS(call_debug_id, why, ret),
TP_STRUCT__entry(
__field(unsigned int, call )
),
TP_fast_assign(
- __entry->call = call ? call->debug_id : 0;
+ __entry->call = call_debug_id;
__entry->why = why;
__entry->ret = ret;
),
__entry->abort_code)
);
-TRACE_EVENT(rxrpc_rx_eproto,
- TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
- const char *why),
-
- TP_ARGS(call, serial, why),
-
- TP_STRUCT__entry(
- __field(unsigned int, call )
- __field(rxrpc_serial_t, serial )
- __field(const char *, why )
- ),
-
- TP_fast_assign(
- __entry->call = call ? call->debug_id : 0;
- __entry->serial = serial;
- __entry->why = why;
- ),
-
- TP_printk("c=%08x EPROTO %08x %s",
- __entry->call,
- __entry->serial,
- __entry->why)
- );
-
TRACE_EVENT(rxrpc_connect_call,
TP_PROTO(struct rxrpc_call *call),
#undef EM
#undef E_
+
+#endif /* RXRPC_TRACE_ONLY_DEFINE_ENUMS */
#endif /* _TRACE_RXRPC_H */
/* This part must be outside protection */
#define __array(_type, _item, _len) { \
.type = #_type"["__stringify(_len)"]", .name = #_item, \
.size = sizeof(_type[_len]), .align = ALIGN_STRUCTFIELD(_type), \
- .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER },
+ .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER,\
+ .len = _len },
#undef __dynamic_array
#define __dynamic_array(_type, _item, _len) { \
__u32 pad;
};
+/* fence_fd is modified on success if VIRTGPU_EXECBUF_FENCE_FD_OUT flag is set. */
struct drm_virtgpu_execbuffer {
__u32 flags;
__u32 size;
*/
#define BR2684_ENCAPS_VC (0) /* VC-mux */
#define BR2684_ENCAPS_LLC (1)
-#define BR2684_ENCAPS_AUTODETECT (2) /* Unsuported */
+#define BR2684_ENCAPS_AUTODETECT (2) /* Unsupported */
/*
* Is this VC bridged or routed?
#include <linux/fs.h>
#include <linux/types.h>
+/*
+ * this file is shared with liburing and that has to autodetect
+ * if linux/time_types.h is available or not, it can
+ * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+ * if linux/time_types.h is not available
+ */
+#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
#include <linux/time_types.h>
+#endif
#ifdef __cplusplus
extern "C" {
#ifndef _UAPI_LINUX_IP_H
#define _UAPI_LINUX_IP_H
#include <linux/types.h>
+#include <linux/stddef.h>
#include <asm/byteorder.h>
#define IPTOS_TOS_MASK 0x1E
#include <linux/libc-compat.h>
#include <linux/types.h>
+#include <linux/stddef.h>
#include <linux/in6.h>
#include <asm/byteorder.h>
__u8 runstate_update_flag;
struct {
__u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
} shared_info;
struct {
__u32 send_port;
} u;
};
+
/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
__u16 pad[3];
union {
__u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
__u64 pad[8];
struct {
__u64 state;
SCTP_CONNTRACK_SHUTDOWN_RECD,
SCTP_CONNTRACK_SHUTDOWN_ACK_SENT,
SCTP_CONNTRACK_HEARTBEAT_SENT,
- SCTP_CONNTRACK_HEARTBEAT_ACKED,
- SCTP_CONNTRACK_DATA_SENT,
+ SCTP_CONNTRACK_HEARTBEAT_ACKED, /* no longer used */
SCTP_CONNTRACK_MAX
};
CTA_TIMEOUT_SCTP_SHUTDOWN_RECD,
CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
CTA_TIMEOUT_SCTP_HEARTBEAT_SENT,
- CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED,
- CTA_TIMEOUT_SCTP_DATA_SENT,
+ CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, /* no longer used */
__CTA_TIMEOUT_SCTP_MAX
};
#define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1)
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
+ * DVD-RW devices.
+ *
+ */
+#ifndef _UAPI__PKTCDVD_H
+#define _UAPI__PKTCDVD_H
+
+#include <linux/types.h>
+
+/*
+ * 1 for normal debug messages, 2 is very verbose. 0 to turn it off.
+ */
+#define PACKET_DEBUG 1
+
+#define MAX_WRITERS 8
+
+#define PKT_RB_POOL_SIZE 512
+
+/*
+ * How long we should hold a non-full packet before starting data gathering.
+ */
+#define PACKET_WAIT_TIME (HZ * 5 / 1000)
+
+/*
+ * use drive write caching -- we need deferred error handling to be
+ * able to successfully recover with this option (drive will return good
+ * status as soon as the cdb is validated).
+ */
+#if defined(CONFIG_CDROM_PKTCDVD_WCACHE)
+#define USE_WCACHING 1
+#else
+#define USE_WCACHING 0
+#endif
+
+/*
+ * No user-servicable parts beyond this point ->
+ */
+
+/*
+ * device types
+ */
+#define PACKET_CDR 1
+#define PACKET_CDRW 2
+#define PACKET_DVDR 3
+#define PACKET_DVDRW 4
+
+/*
+ * flags
+ */
+#define PACKET_WRITABLE 1 /* pd is writable */
+#define PACKET_NWA_VALID 2 /* next writable address valid */
+#define PACKET_LRA_VALID 3 /* last recorded address valid */
+#define PACKET_MERGE_SEGS 4 /* perform segment merging to keep */
+ /* underlying cdrom device happy */
+
+/*
+ * Disc status -- from READ_DISC_INFO
+ */
+#define PACKET_DISC_EMPTY 0
+#define PACKET_DISC_INCOMPLETE 1
+#define PACKET_DISC_COMPLETE 2
+#define PACKET_DISC_OTHER 3
+
+/*
+ * write type, and corresponding data block type
+ */
+#define PACKET_MODE1 1
+#define PACKET_MODE2 2
+#define PACKET_BLOCK_MODE1 8
+#define PACKET_BLOCK_MODE2 10
+
+/*
+ * Last session/border status
+ */
+#define PACKET_SESSION_EMPTY 0
+#define PACKET_SESSION_INCOMPLETE 1
+#define PACKET_SESSION_RESERVED 2
+#define PACKET_SESSION_COMPLETE 3
+
+#define PACKET_MCN "4a656e734178626f65323030300000"
+
+#undef PACKET_USE_LS
+
+#define PKT_CTRL_CMD_SETUP 0
+#define PKT_CTRL_CMD_TEARDOWN 1
+#define PKT_CTRL_CMD_STATUS 2
+
+struct pkt_ctrl_command {
+ __u32 command; /* in: Setup, teardown, status */
+ __u32 dev_index; /* in/out: Device index */
+ __u32 dev; /* in/out: Device nr for cdrw device */
+ __u32 pkt_dev; /* in/out: Device nr for packet device */
+ __u32 num_devices; /* out: Largest device index + 1 */
+ __u32 padding; /* Not used */
+};
+
+/*
+ * packet ioctls
+ */
+#define PACKET_IOCTL_MAGIC ('X')
+#define PACKET_CTRL_CMD _IOWR(PACKET_IOCTL_MAGIC, 1, struct pkt_ctrl_command)
+
+
+#endif /* _UAPI__PKTCDVD_H */
#define PSCI_1_1_FN_SYSTEM_RESET2 PSCI_0_2_FN(18)
#define PSCI_1_1_FN_MEM_PROTECT PSCI_0_2_FN(19)
-#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(19)
+#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(20)
#define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND PSCI_0_2_FN64(12)
#define PSCI_1_0_FN64_NODE_HW_STATE PSCI_0_2_FN64(13)
#define PSCI_1_0_FN64_STAT_COUNT PSCI_0_2_FN64(17)
#define PSCI_1_1_FN64_SYSTEM_RESET2 PSCI_0_2_FN64(18)
-#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(19)
+#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(20)
/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
#define PSCI_0_2_POWER_STATE_ID_MASK 0xffff
VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */
VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */
+ /* virtio features that are provisioned to the vDPA device */
VDPA_ATTR_DEV_FEATURES, /* u64 */
- /* virtio features that are supported by the vDPA device */
- VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, /* u64 */
-
/* new attributes must be added above here */
VDPA_ATTR_MAX,
};
* @urgent_bkops_lvl: keeps track of urgent bkops level for device
* @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for
* device is known or not.
+ * @wb_mutex: used to serialize devfreq and sysfs write booster toggling
* @clk_scaling_lock: used to serialize device commands and clock scaling
* @desc_size: descriptor sizes reported by device
* @scsi_block_reqs_cnt: reference counting for scsi block requests
enum bkops_status urgent_bkops_lvl;
bool is_urgent_bkops_lvl_checked;
+ struct mutex wb_mutex;
struct rw_semaphore clk_scaling_lock;
unsigned char desc_size[QUERY_DESC_IDN_MAX];
atomic_t scsi_block_reqs_cnt;
const struct xenbus_device_id *id);
void (*otherend_changed)(struct xenbus_device *dev,
enum xenbus_state backend_state);
- int (*remove)(struct xenbus_device *dev);
+ void (*remove)(struct xenbus_device *dev);
int (*suspend)(struct xenbus_device *dev);
int (*resume)(struct xenbus_device *dev);
int (*uevent)(struct xenbus_device *, struct kobj_uevent_env *);
appended after any matching localversion* files, and after the value
set in CONFIG_LOCALVERSION.
- (The actual string used here is the first eight characters produced
+ (The actual string used here is the first 12 characters produced
by running the command:
$ git rev-parse --verify HEAD
depends on PRINTK
help
Select the size of an alternate printk per-CPU buffer where messages
- printed from usafe contexts are temporary stored. One example would
+ printed from unsafe contexts are temporary stored. One example would
be NMI messages, another one - printk recursion. The messages are
copied to the main log buffer in a safe context to avoid a deadlock.
The value defines the size as a power of 2.
default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5)
default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough)
-# Currently, disable gcc-12 array-bounds globally.
+# Currently, disable gcc-11,12 array-bounds globally.
# We may want to target only particular configurations some day.
+config GCC11_NO_ARRAY_BOUNDS
+ def_bool y
+
config GCC12_NO_ARRAY_BOUNDS
def_bool y
config CC_NO_ARRAY_BOUNDS
bool
+ default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_ARRAY_BOUNDS
default y if CC_IS_GCC && GCC_VERSION >= 120000 && GCC_VERSION < 130000 && GCC12_NO_ARRAY_BOUNDS
#
$(obj)/version-timestamp.o: include/generated/utsversion.h
CFLAGS_version-timestamp.o := -include include/generated/utsversion.h
+KASAN_SANITIZE_version-timestamp.o := n
#include <generated/compile.h>
#include <generated/utsrelease.h>
-#include <linux/version.h>
#include <linux/proc_ns.h>
#include <linux/refcount.h>
#include <linux/uts.h>
ret = __io_sync_cancel(current->io_uring, &cd, sc.fd);
+ mutex_unlock(&ctx->uring_lock);
if (ret != -EALREADY)
break;
- mutex_unlock(&ctx->uring_lock);
ret = io_run_task_work_sig(ctx);
- if (ret < 0) {
- mutex_lock(&ctx->uring_lock);
+ if (ret < 0)
break;
- }
ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS);
- mutex_lock(&ctx->uring_lock);
if (!ret) {
ret = -ETIME;
break;
}
+ mutex_lock(&ctx->uring_lock);
} while (1);
finish_wait(&ctx->cq_wait, &wait);
+ mutex_lock(&ctx->uring_lock);
if (ret == -ENOENT || ret > 0)
ret = 0;
xa_for_each(&ctx->personalities, index, cred)
io_uring_show_cred(m, index, cred);
}
- if (has_lock)
- mutex_unlock(&ctx->uring_lock);
seq_puts(m, "PollList:\n");
for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) {
struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
+ struct io_hash_bucket *hbl = &ctx->cancel_table_locked.hbs[i];
struct io_kiocb *req;
spin_lock(&hb->lock);
seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
task_work_pending(req->task));
spin_unlock(&hb->lock);
+
+ if (!has_lock)
+ continue;
+ hlist_for_each_entry(req, &hbl->list, hash_node)
+ seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
+ task_work_pending(req->task));
}
+ if (has_lock)
+ mutex_unlock(&ctx->uring_lock);
+
seq_puts(m, "CqOverflowList:\n");
spin_lock(&ctx->completion_lock);
list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
worker = container_of(cb, struct io_worker, create_work);
io_worker_cancel_cb(worker);
+ /*
+ * Only the worker continuation helper has worker allocated and
+ * hence needs freeing.
+ */
+ if (cb->func == create_worker_cont)
+ kfree(worker);
}
}
io_cq_unlock_post(ctx);
}
+static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx)
+{
+ /* iopoll syncs against uring_lock, not completion_lock */
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_lock(&ctx->uring_lock);
+ __io_cqring_overflow_flush(ctx);
+ if (ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_unlock(&ctx->uring_lock);
+}
+
static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
{
- if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
- /* iopoll syncs against uring_lock, not completion_lock */
- if (ctx->flags & IORING_SETUP_IOPOLL)
- mutex_lock(&ctx->uring_lock);
- __io_cqring_overflow_flush(ctx);
- if (ctx->flags & IORING_SETUP_IOPOLL)
- mutex_unlock(&ctx->uring_lock);
- }
+ if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
+ io_cqring_do_overflow_flush(ctx);
}
void __io_put_task(struct task_struct *task, int nr)
size_t ocq_size = sizeof(struct io_overflow_cqe);
bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
+ lockdep_assert_held(&ctx->completion_lock);
+
if (is_cqe32)
ocq_size += sizeof(struct io_uring_cqe);
{
struct io_uring_cqe *cqe;
- if (!ctx->task_complete)
- lockdep_assert_held(&ctx->completion_lock);
-
ctx->cq_extra++;
/*
{
struct io_ring_ctx *ctx = req->ctx;
- if (!llist_add(&req->io_task_work.node, &ctx->work_llist))
+ percpu_ref_get(&ctx->refs);
+
+ if (!llist_add(&req->io_task_work.node, &ctx->work_llist)) {
+ percpu_ref_put(&ctx->refs);
return;
+ }
/* need it for the following io_cqring_wake() */
smp_mb__after_atomic();
if (unlikely(atomic_read(&req->task->io_uring->in_idle))) {
io_move_task_work_from_local(ctx);
+ percpu_ref_put(&ctx->refs);
return;
}
if (ctx->has_evfd)
io_eventfd_signal(ctx);
__io_cqring_wake(ctx);
+ percpu_ref_put(&ctx->refs);
}
void __io_req_task_work_add(struct io_kiocb *req, bool allow_local)
}
spin_unlock(&ctx->completion_lock);
- ret = io_req_prep_async(req);
- if (ret) {
-fail:
- io_req_defer_failed(req, ret);
- return;
- }
io_prep_async_link(req);
de = kmalloc(sizeof(*de), GFP_KERNEL);
if (!de) {
ret = -ENOMEM;
- goto fail;
+ io_req_defer_failed(req, ret);
+ return;
}
spin_lock(&ctx->completion_lock);
req->flags &= ~REQ_F_HARDLINK;
req->flags |= REQ_F_LINK;
io_req_defer_failed(req, req->cqe.res);
- } else if (unlikely(req->ctx->drain_active)) {
- io_drain_req(req);
} else {
int ret = io_req_prep_async(req);
- if (unlikely(ret))
+ if (unlikely(ret)) {
io_req_defer_failed(req, ret);
+ return;
+ }
+
+ if (unlikely(req->ctx->drain_active))
+ io_drain_req(req);
else
io_queue_iowq(req, NULL);
}
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
- ktime_t timeout)
+ ktime_t *timeout)
{
int ret;
unsigned long check_cq;
if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
return -EBADR;
}
- if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
+ if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
return -ETIME;
/*
trace_io_uring_cqring_wait(ctx, min_events);
do {
- io_cqring_overflow_flush(ctx);
+ if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
+ finish_wait(&ctx->cq_wait, &iowq.wq);
+ io_cqring_do_overflow_flush(ctx);
+ }
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
- ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
+ ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
if (__io_cqring_events_user(ctx) >= min_events)
break;
cond_resched();
if (ctx->flags & IORING_SETUP_SINGLE_ISSUER
&& !(ctx->flags & IORING_SETUP_R_DISABLED))
- ctx->submitter_task = get_task_struct(current);
+ WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
file = io_uring_get_file(ctx);
if (IS_ERR(file)) {
return -EBADFD;
if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task)
- ctx->submitter_task = get_task_struct(current);
+ WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
if (ctx->restrictions.registered)
ctx->restricted = 1;
return -EEXIST;
if (ctx->restricted) {
- if (opcode >= IORING_REGISTER_LAST)
- return -EINVAL;
opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
if (!test_bit(opcode, ctx->restrictions.register_op))
return -EACCES;
long ret = -EBADF;
struct fd f;
+ if (opcode >= IORING_REGISTER_LAST)
+ return -EINVAL;
+
f = fdget(fd);
if (!f.file)
return -EBADF;
bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all);
+#define io_lockdep_assert_cq_locked(ctx) \
+ do { \
+ if (ctx->flags & IORING_SETUP_IOPOLL) { \
+ lockdep_assert_held(&ctx->uring_lock); \
+ } else if (!ctx->task_complete) { \
+ lockdep_assert_held(&ctx->completion_lock); \
+ } else if (ctx->submitter_task->flags & PF_EXITING) { \
+ lockdep_assert(current_work()); \
+ } else { \
+ lockdep_assert(current == ctx->submitter_task); \
+ } \
+ } while (0)
+
static inline void io_req_task_work_add(struct io_kiocb *req)
{
__io_req_task_work_add(req, true);
static inline struct io_uring_cqe *io_get_cqe_overflow(struct io_ring_ctx *ctx,
bool overflow)
{
+ io_lockdep_assert_cq_locked(ctx);
+
if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
struct io_uring_cqe *cqe = ctx->cqe_cached;
u32 flags;
};
+static void io_double_unlock_ctx(struct io_ring_ctx *octx)
+{
+ mutex_unlock(&octx->uring_lock);
+}
+
+static int io_double_lock_ctx(struct io_ring_ctx *octx,
+ unsigned int issue_flags)
+{
+ /*
+ * To ensure proper ordering between the two ctxs, we can only
+ * attempt a trylock on the target. If that fails and we already have
+ * the source ctx lock, punt to io-wq.
+ */
+ if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+ if (!mutex_trylock(&octx->uring_lock))
+ return -EAGAIN;
+ return 0;
+ }
+ mutex_lock(&octx->uring_lock);
+ return 0;
+}
+
void io_msg_ring_cleanup(struct io_kiocb *req)
{
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
msg->src_file = NULL;
}
+static inline bool io_msg_need_remote(struct io_ring_ctx *target_ctx)
+{
+ if (!target_ctx->task_complete)
+ return false;
+ return current != target_ctx->submitter_task;
+}
+
+static int io_msg_exec_remote(struct io_kiocb *req, task_work_func_t func)
+{
+ struct io_ring_ctx *ctx = req->file->private_data;
+ struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
+ struct task_struct *task = READ_ONCE(ctx->submitter_task);
+
+ if (unlikely(!task))
+ return -EOWNERDEAD;
+
+ init_task_work(&msg->tw, func);
+ if (task_work_add(ctx->submitter_task, &msg->tw, TWA_SIGNAL))
+ return -EOWNERDEAD;
+
+ return IOU_ISSUE_SKIP_COMPLETE;
+}
+
static void io_msg_tw_complete(struct callback_head *head)
{
struct io_msg *msg = container_of(head, struct io_msg, tw);
struct io_ring_ctx *target_ctx = req->file->private_data;
int ret = 0;
- if (current->flags & PF_EXITING)
+ if (current->flags & PF_EXITING) {
ret = -EOWNERDEAD;
- else if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
- ret = -EOVERFLOW;
+ } else {
+ /*
+ * If the target ring is using IOPOLL mode, then we need to be
+ * holding the uring_lock for posting completions. Other ring
+ * types rely on the regular completion locking, which is
+ * handled while posting.
+ */
+ if (target_ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_lock(&target_ctx->uring_lock);
+ if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+ ret = -EOVERFLOW;
+ if (target_ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_unlock(&target_ctx->uring_lock);
+ }
if (ret < 0)
req_set_fail(req);
io_req_queue_tw_complete(req, ret);
}
-static int io_msg_ring_data(struct io_kiocb *req)
+static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *target_ctx = req->file->private_data;
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
+ int ret;
if (msg->src_fd || msg->dst_fd || msg->flags)
return -EINVAL;
+ if (target_ctx->flags & IORING_SETUP_R_DISABLED)
+ return -EBADFD;
- if (target_ctx->task_complete && current != target_ctx->submitter_task) {
- init_task_work(&msg->tw, io_msg_tw_complete);
- if (task_work_add(target_ctx->submitter_task, &msg->tw,
- TWA_SIGNAL_NO_IPI))
- return -EOWNERDEAD;
-
- atomic_or(IORING_SQ_TASKRUN, &target_ctx->rings->sq_flags);
- return IOU_ISSUE_SKIP_COMPLETE;
- }
-
- if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
- return 0;
+ if (io_msg_need_remote(target_ctx))
+ return io_msg_exec_remote(req, io_msg_tw_complete);
- return -EOVERFLOW;
-}
-
-static void io_double_unlock_ctx(struct io_ring_ctx *octx,
- unsigned int issue_flags)
-{
- mutex_unlock(&octx->uring_lock);
-}
-
-static int io_double_lock_ctx(struct io_ring_ctx *octx,
- unsigned int issue_flags)
-{
- /*
- * To ensure proper ordering between the two ctxs, we can only
- * attempt a trylock on the target. If that fails and we already have
- * the source ctx lock, punt to io-wq.
- */
- if (!(issue_flags & IO_URING_F_UNLOCKED)) {
- if (!mutex_trylock(&octx->uring_lock))
+ ret = -EOVERFLOW;
+ if (target_ctx->flags & IORING_SETUP_IOPOLL) {
+ if (unlikely(io_double_lock_ctx(target_ctx, issue_flags)))
return -EAGAIN;
- return 0;
+ if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+ ret = 0;
+ io_double_unlock_ctx(target_ctx);
+ } else {
+ if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+ ret = 0;
}
- mutex_lock(&octx->uring_lock);
- return 0;
+ return ret;
}
static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags)
if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
ret = -EOVERFLOW;
out_unlock:
- io_double_unlock_ctx(target_ctx, issue_flags);
+ io_double_unlock_ctx(target_ctx);
return ret;
}
if (target_ctx == ctx)
return -EINVAL;
+ if (target_ctx->flags & IORING_SETUP_R_DISABLED)
+ return -EBADFD;
if (!src_file) {
src_file = io_msg_grab_file(req, issue_flags);
if (!src_file)
req->flags |= REQ_F_NEED_CLEANUP;
}
- if (target_ctx->task_complete && current != target_ctx->submitter_task) {
- init_task_work(&msg->tw, io_msg_tw_fd_complete);
- if (task_work_add(target_ctx->submitter_task, &msg->tw,
- TWA_SIGNAL))
- return -EOWNERDEAD;
-
- return IOU_ISSUE_SKIP_COMPLETE;
- }
+ if (io_msg_need_remote(target_ctx))
+ return io_msg_exec_remote(req, io_msg_tw_fd_complete);
return io_msg_install_complete(req, issue_flags);
}
switch (msg->cmd) {
case IORING_MSG_DATA:
- ret = io_msg_ring_data(req);
+ ret = io_msg_ring_data(req, issue_flags);
break;
case IORING_MSG_SEND_FD:
ret = io_msg_send_fd(req, issue_flags);
u16 flags;
/* initialised and used only by !msg send variants */
u16 addr_len;
+ u16 buf_group;
void __user *addr;
/* used only for send zerocopy */
struct io_kiocb *notif;
if (req->opcode == IORING_OP_RECV && sr->len)
return -EINVAL;
req->flags |= REQ_F_APOLL_MULTISHOT;
+ /*
+ * Store the buffer group for this multishot receive separately,
+ * as if we end up doing an io-wq based issue that selects a
+ * buffer, it has to be committed immediately and that will
+ * clear ->buf_list. This means we lose the link to the buffer
+ * list, and the eventual buffer put on completion then cannot
+ * restore it.
+ */
+ sr->buf_group = req->buf_index;
}
#ifdef CONFIG_COMPAT
sr->done_io = 0;
sr->len = 0; /* get from the provided buffer */
+ req->buf_index = sr->buf_group;
}
/*
IOU_POLL_DONE = 0,
IOU_POLL_NO_ACTION = 1,
IOU_POLL_REMOVE_POLL_USE_RES = 2,
+ IOU_POLL_REISSUE = 3,
};
/*
* All poll tw should go through this. Checks for poll events, manages
* references, does rewait, etc.
*
- * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action require,
- * which is either spurious wakeup or multishot CQE is served.
- * IOU_POLL_DONE when it's done with the request, then the mask is stored in req->cqe.res.
- * IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot poll and that the result
- * is stored in req->cqe.
+ * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action
+ * require, which is either spurious wakeup or multishot CQE is served.
+ * IOU_POLL_DONE when it's done with the request, then the mask is stored in
+ * req->cqe.res. IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot
+ * poll and that the result is stored in req->cqe.
*/
static int io_poll_check_events(struct io_kiocb *req, bool *locked)
{
- int v, ret;
+ int v;
/* req->task == current here, checking PF_EXITING is safe */
if (unlikely(req->task->flags & PF_EXITING))
if (!req->cqe.res) {
struct poll_table_struct pt = { ._key = req->apoll_events };
req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events;
+ /*
+ * We got woken with a mask, but someone else got to
+ * it first. The above vfs_poll() doesn't add us back
+ * to the waitqueue, so if we get nothing back, we
+ * should be safe and attempt a reissue.
+ */
+ if (unlikely(!req->cqe.res)) {
+ /* Multishot armed need not reissue */
+ if (!(req->apoll_events & EPOLLONESHOT))
+ continue;
+ return IOU_POLL_REISSUE;
+ }
}
-
- if ((unlikely(!req->cqe.res)))
- continue;
if (req->apoll_events & EPOLLONESHOT)
return IOU_POLL_DONE;
return IOU_POLL_REMOVE_POLL_USE_RES;
}
} else {
- ret = io_poll_issue(req, locked);
+ int ret = io_poll_issue(req, locked);
if (ret == IOU_STOP_MULTISHOT)
return IOU_POLL_REMOVE_POLL_USE_RES;
if (ret < 0)
poll = io_kiocb_to_cmd(req, struct io_poll);
req->cqe.res = mangle_poll(req->cqe.res & poll->events);
+ } else if (ret == IOU_POLL_REISSUE) {
+ io_req_task_submit(req, locked);
+ return;
} else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) {
req->cqe.res = ret;
req_set_fail(req);
if (ret == IOU_POLL_REMOVE_POLL_USE_RES)
io_req_task_complete(req, locked);
- else if (ret == IOU_POLL_DONE)
+ else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE)
io_req_task_submit(req, locked);
else
io_req_defer_failed(req, ret);
return pt->owning || io_poll_get_ownership(req);
}
+static void io_poll_add_hash(struct io_kiocb *req)
+{
+ if (req->flags & REQ_F_HASH_LOCKED)
+ io_poll_req_insert_locked(req);
+ else
+ io_poll_req_insert(req);
+}
+
/*
* Returns 0 when it's handed over for polling. The caller owns the requests if
* it returns non-zero, but otherwise should not touch it. Negative values
if (mask &&
((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) {
- if (!io_poll_can_finish_inline(req, ipt))
+ if (!io_poll_can_finish_inline(req, ipt)) {
+ io_poll_add_hash(req);
return 0;
+ }
io_poll_remove_entries(req);
ipt->result_mask = mask;
/* no one else has access to the req, forget about the ref */
return 1;
}
- if (req->flags & REQ_F_HASH_LOCKED)
- io_poll_req_insert_locked(req);
- else
- io_poll_req_insert(req);
+ io_poll_add_hash(req);
if (mask && (poll->events & EPOLLET) &&
io_poll_can_finish_inline(req, ipt)) {
continue;
req->cqe.flags = io_put_kbuf(req, 0);
- io_fill_cqe_req(req->ctx, req);
+ if (unlikely(!__io_fill_cqe_req(ctx, req))) {
+ spin_lock(&ctx->completion_lock);
+ io_req_cqe_overflow(req);
+ spin_unlock(&ctx->completion_lock);
+ }
}
if (unlikely(!nr_events))
*/
BTF_SET_START(bpf_lsm_locked_sockopt_hooks)
#ifdef CONFIG_SECURITY_NETWORK
-BTF_ID(func, bpf_lsm_socket_sock_rcv_skb)
BTF_ID(func, bpf_lsm_sock_graft)
BTF_ID(func, bpf_lsm_inet_csk_clone)
BTF_ID(func, bpf_lsm_inet_conn_established)
BTF_ID(func, bpf_lsm_bpf_prog_free_security)
BTF_ID(func, bpf_lsm_file_alloc_security)
BTF_ID(func, bpf_lsm_file_free_security)
+#ifdef CONFIG_SECURITY_NETWORK
BTF_ID(func, bpf_lsm_sk_alloc_security)
BTF_ID(func, bpf_lsm_sk_free_security)
+#endif /* CONFIG_SECURITY_NETWORK */
BTF_ID(func, bpf_lsm_task_free)
BTF_SET_END(untrusted_lsm_hooks)
sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL);
- return 0;
end:
- btf_free_dtor_kfunc_tab(btf);
+ if (ret)
+ btf_free_dtor_kfunc_tab(btf);
btf_put(btf);
return ret;
}
{
unsigned long flags;
- hash = hash & HASHTAB_MAP_LOCK_MASK;
+ hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
preempt_disable();
if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
struct bucket *b, u32 hash,
unsigned long flags)
{
- hash = hash & HASHTAB_MAP_LOCK_MASK;
+ hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
raw_spin_unlock_irqrestore(&b->raw_lock, flags);
__this_cpu_dec(*(htab->map_locked[hash]));
preempt_enable();
if (size <= 192)
return size_index[(size - 1) / 8] - 1;
- return fls(size - 1) - 1;
+ return fls(size - 1) - 2;
}
#define NUM_CACHES 11
if (offload->dev_state)
offload->offdev->ops->destroy(prog);
- /* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
- bpf_prog_free_id(prog, true);
-
list_del_init(&offload->offloads);
kfree(offload);
prog->aux->offload = NULL;
return;
if (audit_enabled == AUDIT_OFF)
return;
- if (op == BPF_AUDIT_LOAD)
+ if (!in_irq() && !irqs_disabled())
ctx = audit_context();
ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF);
if (unlikely(!ab))
return id > 0 ? 0 : id;
}
-void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
+void bpf_prog_free_id(struct bpf_prog *prog)
{
unsigned long flags;
if (!prog->aux->id)
return;
- if (do_idr_lock)
- spin_lock_irqsave(&prog_idr_lock, flags);
- else
- __acquire(&prog_idr_lock);
-
+ spin_lock_irqsave(&prog_idr_lock, flags);
idr_remove(&prog_idr, prog->aux->id);
prog->aux->id = 0;
-
- if (do_idr_lock)
- spin_unlock_irqrestore(&prog_idr_lock, flags);
- else
- __release(&prog_idr_lock);
+ spin_unlock_irqrestore(&prog_idr_lock, flags);
}
static void __bpf_prog_put_rcu(struct rcu_head *rcu)
prog = aux->prog;
perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
bpf_audit_prog(prog, BPF_AUDIT_UNLOAD);
+ bpf_prog_free_id(prog);
__bpf_prog_put_noref(prog, true);
}
-static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
+static void __bpf_prog_put(struct bpf_prog *prog)
{
struct bpf_prog_aux *aux = prog->aux;
if (atomic64_dec_and_test(&aux->refcnt)) {
- /* bpf_prog_free_id() must be called first */
- bpf_prog_free_id(prog, do_idr_lock);
-
if (in_irq() || irqs_disabled()) {
INIT_WORK(&aux->work, bpf_prog_put_deferred);
schedule_work(&aux->work);
void bpf_prog_put(struct bpf_prog *prog)
{
- __bpf_prog_put(prog, true);
+ __bpf_prog_put(prog);
}
EXPORT_SYMBOL_GPL(bpf_prog_put);
*/
struct bpf_iter_seq_task_common common;
struct task_struct *task;
+ struct mm_struct *mm;
struct vm_area_struct *vma;
u32 tid;
unsigned long prev_vm_start;
enum bpf_task_vma_iter_find_op op;
struct vm_area_struct *curr_vma;
struct task_struct *curr_task;
+ struct mm_struct *curr_mm;
u32 saved_tid = info->tid;
/* If this function returns a non-NULL vma, it holds a reference to
- * the task_struct, and holds read lock on vma->mm->mmap_lock.
+ * the task_struct, holds a refcount on mm->mm_users, and holds
+ * read lock on vma->mm->mmap_lock.
* If this function returns NULL, it does not hold any reference or
* lock.
*/
if (info->task) {
curr_task = info->task;
curr_vma = info->vma;
+ curr_mm = info->mm;
/* In case of lock contention, drop mmap_lock to unblock
* the writer.
*
* 4.2) VMA2 and VMA2' covers different ranges, process
* VMA2'.
*/
- if (mmap_lock_is_contended(curr_task->mm)) {
+ if (mmap_lock_is_contended(curr_mm)) {
info->prev_vm_start = curr_vma->vm_start;
info->prev_vm_end = curr_vma->vm_end;
op = task_vma_iter_find_vma;
- mmap_read_unlock(curr_task->mm);
- if (mmap_read_lock_killable(curr_task->mm))
+ mmap_read_unlock(curr_mm);
+ if (mmap_read_lock_killable(curr_mm)) {
+ mmput(curr_mm);
goto finish;
+ }
} else {
op = task_vma_iter_next_vma;
}
op = task_vma_iter_find_vma;
}
- if (!curr_task->mm)
+ curr_mm = get_task_mm(curr_task);
+ if (!curr_mm)
goto next_task;
- if (mmap_read_lock_killable(curr_task->mm))
+ if (mmap_read_lock_killable(curr_mm)) {
+ mmput(curr_mm);
goto finish;
+ }
}
switch (op) {
case task_vma_iter_first_vma:
- curr_vma = find_vma(curr_task->mm, 0);
+ curr_vma = find_vma(curr_mm, 0);
break;
case task_vma_iter_next_vma:
- curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+ curr_vma = find_vma(curr_mm, curr_vma->vm_end);
break;
case task_vma_iter_find_vma:
/* We dropped mmap_lock so it is necessary to use find_vma
* to find the next vma. This is similar to the mechanism
* in show_smaps_rollup().
*/
- curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
+ curr_vma = find_vma(curr_mm, info->prev_vm_end - 1);
/* case 1) and 4.2) above just use curr_vma */
/* check for case 2) or case 4.1) above */
if (curr_vma &&
curr_vma->vm_start == info->prev_vm_start &&
curr_vma->vm_end == info->prev_vm_end)
- curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+ curr_vma = find_vma(curr_mm, curr_vma->vm_end);
break;
}
if (!curr_vma) {
/* case 3) above, or case 2) 4.1) with vma->next == NULL */
- mmap_read_unlock(curr_task->mm);
+ mmap_read_unlock(curr_mm);
+ mmput(curr_mm);
goto next_task;
}
info->task = curr_task;
info->vma = curr_vma;
+ info->mm = curr_mm;
return curr_vma;
next_task:
put_task_struct(curr_task);
info->task = NULL;
+ info->mm = NULL;
info->tid++;
goto again;
put_task_struct(curr_task);
info->task = NULL;
info->vma = NULL;
+ info->mm = NULL;
return NULL;
}
*/
info->prev_vm_start = ~0UL;
info->prev_vm_end = info->vma->vm_end;
- mmap_read_unlock(info->task->mm);
+ mmap_read_unlock(info->mm);
+ mmput(info->mm);
+ info->mm = NULL;
put_task_struct(info->task);
info->task = NULL;
}
/* reset fops->func and fops->trampoline for re-register */
tr->fops->func = NULL;
tr->fops->trampoline = 0;
+
+ /* reset im->image memory attr for arch_prepare_bpf_trampoline */
+ set_memory_nx((long)im->image, 1);
+ set_memory_rw((long)im->image, 1);
goto again;
}
#endif
*/
static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags)
{
+ size_t alloc_bytes;
+ void *orig = dst;
size_t bytes;
if (ZERO_OR_NULL_PTR(src))
if (unlikely(check_mul_overflow(n, size, &bytes)))
return NULL;
- if (ksize(dst) < ksize(src)) {
- kfree(dst);
- dst = kmalloc_track_caller(kmalloc_size_roundup(bytes), flags);
- if (!dst)
- return NULL;
+ alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes));
+ dst = krealloc(orig, alloc_bytes, flags);
+ if (!dst) {
+ kfree(orig);
+ return NULL;
}
memcpy(dst, src, bytes);
*/
if (insn->src_reg == 0 && is_callback_calling_function(insn->imm))
return -ENOTSUPP;
+ /* kfunc with imm==0 is invalid and fixup_kfunc_call will
+ * catch this error later. Make backtracking conservative
+ * with ENOTSUPP.
+ */
+ if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0)
+ return -ENOTSUPP;
/* regular helper call sets R0 */
*reg_mask &= ~1;
if (*reg_mask & 0x3f) {
return reg->type != SCALAR_VALUE;
}
+/* Copy src state preserving dst->parent and dst->live fields */
+static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src)
+{
+ struct bpf_reg_state *parent = dst->parent;
+ enum bpf_reg_liveness live = dst->live;
+
+ *dst = *src;
+ dst->parent = parent;
+ dst->live = live;
+}
+
static void save_register_state(struct bpf_func_state *state,
int spi, struct bpf_reg_state *reg,
int size)
{
int i;
- state->stack[spi].spilled_ptr = *reg;
+ copy_register_state(&state->stack[spi].spilled_ptr, reg);
if (size == BPF_REG_SIZE)
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
bool sanitize = reg && is_spillable_regtype(reg->type);
for (i = 0; i < size; i++) {
- if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+ u8 type = state->stack[spi].slot_type[i];
+
+ if (type != STACK_MISC && type != STACK_ZERO) {
sanitize = true;
break;
}
*/
s32 subreg_def = state->regs[dst_regno].subreg_def;
- state->regs[dst_regno] = *reg;
+ copy_register_state(&state->regs[dst_regno], reg);
state->regs[dst_regno].subreg_def = subreg_def;
} else {
for (i = 0; i < size; i++) {
if (dst_regno >= 0) {
/* restore register state from stack */
- state->regs[dst_regno] = *reg;
+ copy_register_state(&state->regs[dst_regno], reg);
/* mark reg as written since spilled pointer state likely
* has its liveness marks cleared by is_state_visited()
* which resets stack/reg liveness for state transitions
*/
if (!ptr_is_dst_reg) {
tmp = *dst_reg;
- *dst_reg = *ptr_reg;
+ copy_register_state(dst_reg, ptr_reg);
}
ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1,
env->insn_idx);
* to propagate min/max range.
*/
src_reg->id = ++env->id_gen;
- *dst_reg = *src_reg;
+ copy_register_state(dst_reg, src_reg);
dst_reg->live |= REG_LIVE_WRITTEN;
dst_reg->subreg_def = DEF_NOT_SUBREG;
} else {
insn->src_reg);
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
- *dst_reg = *src_reg;
+ copy_register_state(dst_reg, src_reg);
/* Make sure ID is cleared otherwise
* dst_reg min/max could be incorrectly
* propagated into src_reg by find_equal_scalars()
bpf_for_each_reg_in_vstate(vstate, state, reg, ({
if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
- *reg = *known_reg;
+ copy_register_state(reg, known_reg);
}));
}
* register B - not null
* for JNE A, B, ... - A is not null in the false branch;
* for JEQ A, B, ... - A is not null in the true branch.
+ *
+ * Since PTR_TO_BTF_ID points to a kernel struct that does
+ * not need to be null checked by the BPF program, i.e.,
+ * could be null even without PTR_MAYBE_NULL marking, so
+ * only propagate nullness when neither reg is that type.
*/
if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X &&
__is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) &&
- type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type)) {
+ type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) &&
+ base_type(src_reg->type) != PTR_TO_BTF_ID &&
+ base_type(dst_reg->type) != PTR_TO_BTF_ID) {
eq_branch_regs = NULL;
switch (opcode) {
case BPF_JEQ:
/**
* update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
* @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
+ * @new_cpus: the temp variable for the new effective_cpus mask
*
* Iterate through each task of @cs updating its cpus_allowed to the
* effective cpuset's. As this function is called with cpuset_rwsem held,
* cpuset membership stays stable.
*/
-static void update_tasks_cpumask(struct cpuset *cs)
+static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
{
struct css_task_iter it;
struct task_struct *task;
if (top_cs && (task->flags & PF_KTHREAD) &&
kthread_is_per_cpu(task))
continue;
- set_cpus_allowed_ptr(task, cs->effective_cpus);
+
+ cpumask_and(new_cpus, cs->effective_cpus,
+ task_cpu_possible_mask(task));
+ set_cpus_allowed_ptr(task, new_cpus);
}
css_task_iter_end(&it);
}
* A parent can be left with no CPU as long as there is no
* task directly associated with the parent partition.
*/
- if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) &&
+ if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) &&
partition_is_populated(parent, cs))
return PERR_NOCPUS;
spin_unlock_irq(&callback_lock);
if (adding || deleting)
- update_tasks_cpumask(parent);
+ update_tasks_cpumask(parent, tmp->new_cpus);
/*
* Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
WARN_ON(!is_in_v2_mode() &&
!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
- update_tasks_cpumask(cp);
+ update_tasks_cpumask(cp, tmp->new_cpus);
/*
* On legacy hierarchy, if the effective cpumask of any non-
}
}
- update_tasks_cpumask(parent);
+ update_tasks_cpumask(parent, tmpmask.new_cpus);
if (parent->child_ecpus_count)
update_sibling_cpumasks(parent, cs, &tmpmask);
new_prs = -new_prs;
spin_lock_irq(&callback_lock);
cs->partition_root_state = new_prs;
+ WRITE_ONCE(cs->prs_err, err);
spin_unlock_irq(&callback_lock);
/*
* Update child cpusets, if present.
* as the tasks will be migrated to an ancestor.
*/
if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
- update_tasks_cpumask(cs);
+ update_tasks_cpumask(cs, new_cpus);
if (mems_updated && !nodes_empty(cs->mems_allowed))
update_tasks_nodemask(cs);
spin_unlock_irq(&callback_lock);
if (cpus_updated)
- update_tasks_cpumask(cs);
+ update_tasks_cpumask(cs, new_cpus);
if (mems_updated)
update_tasks_nodemask(cs);
}
* Description: Returns the cpumask_var_t cpus_allowed of the cpuset
* attached to the specified @tsk. Guaranteed to return some non-empty
* subset of cpu_online_mask, even if this means going outside the
- * tasks cpuset.
+ * tasks cpuset, except when the task is in the top cpuset.
**/
void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
{
unsigned long flags;
+ struct cpuset *cs;
spin_lock_irqsave(&callback_lock, flags);
- guarantee_online_cpus(tsk, pmask);
+ rcu_read_lock();
+
+ cs = task_cs(tsk);
+ if (cs != &top_cpuset)
+ guarantee_online_cpus(tsk, pmask);
+ /*
+ * Tasks in the top cpuset won't get update to their cpumasks
+ * when a hotplug online/offline event happens. So we include all
+ * offline cpus in the allowed cpu list.
+ */
+ if ((cs == &top_cpuset) || cpumask_empty(pmask)) {
+ const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+
+ /*
+ * We first exclude cpus allocated to partitions. If there is no
+ * allowable online cpu left, we fall back to all possible cpus.
+ */
+ cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus);
+ if (!cpumask_intersects(pmask, cpu_online_mask))
+ cpumask_copy(pmask, possible_mask);
+ }
+
+ rcu_read_unlock();
spin_unlock_irqrestore(&callback_lock, flags);
}
/*
* perf_sched_events : >0 events exist
- * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
*/
static void perf_sched_delayed(struct work_struct *work);
static DEFINE_MUTEX(perf_sched_mutex);
static atomic_t perf_sched_count;
-static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
static atomic_t nr_mmap_events __read_mostly;
struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
struct perf_cgroup *cgrp;
- cgrp = perf_cgroup_from_task(task, NULL);
+ /*
+ * cpuctx->cgrp is set when the first cgroup event enabled,
+ * and is cleared when the last cgroup event disabled.
+ */
+ if (READ_ONCE(cpuctx->cgrp) == NULL)
+ return;
WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+
+ cgrp = perf_cgroup_from_task(task, NULL);
if (READ_ONCE(cpuctx->cgrp) == cgrp)
return;
* to check if we have to switch out PMU state.
* cgroup event are system-wide mode only
*/
- if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
- perf_cgroup_switch(next);
+ perf_cgroup_switch(next);
}
static bool perf_less_group_idx(const void *l, const void *r)
cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu);
epc = &cpc->epc;
-
+ raw_spin_lock_irq(&ctx->lock);
if (!epc->ctx) {
atomic_set(&epc->refcount, 1);
epc->embedded = 1;
- raw_spin_lock_irq(&ctx->lock);
list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
epc->ctx = ctx;
- raw_spin_unlock_irq(&ctx->lock);
} else {
WARN_ON_ONCE(epc->ctx != ctx);
atomic_inc(&epc->refcount);
}
-
+ raw_spin_unlock_irq(&ctx->lock);
return epc;
}
static void put_pmu_ctx(struct perf_event_pmu_context *epc)
{
+ struct perf_event_context *ctx = epc->ctx;
unsigned long flags;
- if (!atomic_dec_and_test(&epc->refcount))
+ /*
+ * XXX
+ *
+ * lockdep_assert_held(&ctx->mutex);
+ *
+ * can't because of the call-site in _free_event()/put_event()
+ * which isn't always called under ctx->mutex.
+ */
+ if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags))
return;
- if (epc->ctx) {
- struct perf_event_context *ctx = epc->ctx;
-
- /*
- * XXX
- *
- * lockdep_assert_held(&ctx->mutex);
- *
- * can't because of the call-site in _free_event()/put_event()
- * which isn't always called under ctx->mutex.
- */
+ WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
- WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry));
- raw_spin_lock_irqsave(&ctx->lock, flags);
- list_del_init(&epc->pmu_ctx_entry);
- epc->ctx = NULL;
- raw_spin_unlock_irqrestore(&ctx->lock, flags);
- }
+ list_del_init(&epc->pmu_ctx_entry);
+ epc->ctx = NULL;
WARN_ON_ONCE(!list_empty(&epc->pinned_active));
WARN_ON_ONCE(!list_empty(&epc->flexible_active));
+ raw_spin_unlock_irqrestore(&ctx->lock, flags);
+
if (epc->embedded)
return;
detach_sb_event(event);
}
-static void unaccount_event_cpu(struct perf_event *event, int cpu)
-{
- if (event->parent)
- return;
-
- if (is_cgroup_event(event))
- atomic_dec(&per_cpu(perf_cgroup_events, cpu));
-}
-
#ifdef CONFIG_NO_HZ_FULL
static DEFINE_SPINLOCK(nr_freq_lock);
#endif
schedule_delayed_work(&perf_sched_work, HZ);
}
- unaccount_event_cpu(event, event->cpu);
-
unaccount_pmu_sb_event(event);
}
attach_sb_event(event);
}
-static void account_event_cpu(struct perf_event *event, int cpu)
-{
- if (event->parent)
- return;
-
- if (is_cgroup_event(event))
- atomic_inc(&per_cpu(perf_cgroup_events, cpu));
-}
-
/* Freq events need the tick to stay alive (see perf_event_task_tick). */
static void account_freq_event_nohz(void)
{
}
enabled:
- account_event_cpu(event, event->cpu);
-
account_pmu_sb_event(event);
}
if (flags & ~PERF_FLAG_ALL)
return -EINVAL;
- /* Do we allow access to perf_event_open(2) ? */
- err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
+ err = perf_copy_attr(attr_uptr, &attr);
if (err)
return err;
- err = perf_copy_attr(attr_uptr, &attr);
+ /* Do we allow access to perf_event_open(2) ? */
+ err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
if (err)
return err;
return event_fd;
err_context:
- /* event->pmu_ctx freed by free_event() */
+ put_pmu_ctx(event->pmu_ctx);
+ event->pmu_ctx = NULL; /* _free_event() */
err_locked:
mutex_unlock(&ctx->mutex);
perf_unpin_context(ctx);
err_pmu_ctx:
put_pmu_ctx(pmu_ctx);
+ event->pmu_ctx = NULL; /* _free_event() */
err_unlock:
mutex_unlock(&ctx->mutex);
perf_unpin_context(ctx);
perf_event_groups_for_cpu_pmu(event, groups, cpu, pmu) {
perf_remove_from_context(event, 0);
- unaccount_event_cpu(event, cpu);
put_pmu_ctx(event->pmu_ctx);
list_add(&event->migrate_entry, events);
for_each_sibling_event(sibling, event) {
perf_remove_from_context(sibling, 0);
- unaccount_event_cpu(sibling, cpu);
put_pmu_ctx(sibling->pmu_ctx);
list_add(&sibling->migrate_entry, events);
}
if (event->state >= PERF_EVENT_STATE_OFF)
event->state = PERF_EVENT_STATE_INACTIVE;
- account_event_cpu(event, cpu);
perf_install_in_context(ctx, event, cpu);
}
pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
if (IS_ERR(pmu_ctx)) {
free_event(child_event);
- return NULL;
+ return ERR_CAST(pmu_ctx);
}
child_event->pmu_ctx = pmu_ctx;
struct task_struct *task = info;
preempt_disable();
- if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
- perf_cgroup_switch(task);
+ perf_cgroup_switch(task);
preempt_enable();
return 0;
}
futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL);
- if (!futexv)
- return -ENOMEM;
+ if (!futexv) {
+ ret = -ENOMEM;
+ goto destroy_timer;
+ }
ret = futex_parse_waitv(futexv, waiters, nr_futexes);
if (!ret)
ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL);
+ kfree(futexv);
+
+destroy_timer:
if (timeout) {
hrtimer_cancel(&to.timer);
destroy_hrtimer_on_stack(&to.timer);
}
-
- kfree(futexv);
return ret;
}
arch/$SRCARCH/include/
"
+type cpio > /dev/null
+
# Support incremental builds by skipping archive generation
# if timestamps of files being archived are not changed.
{
struct irqchip_fwid *fwid;
- if (WARN_ON(!is_fwnode_irqchip(fwnode)))
+ if (!fwnode || WARN_ON(!is_fwnode_irqchip(fwnode)))
return;
fwid = container_of(fwnode, struct irqchip_fwid, fwnode);
static void debugfs_remove_domain_dir(struct irq_domain *d)
{
- debugfs_remove(debugfs_lookup(d->name, domain_dir));
+ debugfs_lookup_and_remove(d->name, domain_dir);
}
void __init irq_domain_debugfs_init(struct dentry *root)
fail:
msi_unlock_descs(dev);
free_fwnode:
- kfree(fwnode);
+ irq_domain_free_fwnode(fwnode);
free_bundle:
kfree(bundle);
return false;
*/
void msi_remove_device_irq_domain(struct device *dev, unsigned int domid)
{
+ struct fwnode_handle *fwnode = NULL;
struct msi_domain_info *info;
struct irq_domain *domain;
dev->msi.data->__domains[domid].domain = NULL;
info = domain->host_data;
+ if (irq_domain_is_msi_device(domain))
+ fwnode = domain->fwnode;
irq_domain_remove(domain);
+ irq_domain_free_fwnode(fwnode);
kfree(container_of(info, struct msi_domain_template, info));
unlock:
static int lookup_name(void *data, const char *name, struct module *mod, unsigned long addr)
{
u64 t0, t1, t;
- unsigned long flags;
struct test_stat *stat = (struct test_stat *)data;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
(void)kallsyms_lookup_name(name);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
t = t1 - t0;
if (t < stat->min)
static void test_perf_kallsyms_on_each_symbol(void)
{
u64 t0, t1;
- unsigned long flags;
struct test_stat stat;
memset(&stat, 0, sizeof(stat));
stat.max = INT_MAX;
stat.name = stub_name;
stat.perf = 1;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
kallsyms_on_each_symbol(find_symbol, &stat);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
pr_info("kallsyms_on_each_symbol() traverse all: %lld ns\n", t1 - t0);
}
static void test_perf_kallsyms_on_each_match_symbol(void)
{
u64 t0, t1;
- unsigned long flags;
struct test_stat stat;
memset(&stat, 0, sizeof(stat));
stat.max = INT_MAX;
stat.name = stub_name;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
kallsyms_on_each_match_symbol(match_symbol, stat.name, &stat);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
pr_info("kallsyms_on_each_match_symbol() traverse all: %lld ns\n", t1 - t0);
}
const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT;
bool ret = false;
unsigned long flags;
- typeof(observed.lines) expect;
+ typeof(*observed.lines) *expect;
const char *end;
char *cur;
int i;
if (!report_available())
return false;
+ expect = kmalloc(sizeof(observed.lines), GFP_KERNEL);
+ if (WARN_ON(!expect))
+ return false;
+
/* Generate expected report contents. */
/* Title */
strstr(observed.lines[2], expect[1])));
out:
spin_unlock_irqrestore(&observed.lock, flags);
+ kfree(expect);
return ret;
}
* set this bit before looking at the lock.
*/
-static __always_inline void
-rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner)
+static __always_inline struct task_struct *
+rt_mutex_owner_encode(struct rt_mutex_base *lock, struct task_struct *owner)
{
unsigned long val = (unsigned long)owner;
if (rt_mutex_has_waiters(lock))
val |= RT_MUTEX_HAS_WAITERS;
- WRITE_ONCE(lock->owner, (struct task_struct *)val);
+ return (struct task_struct *)val;
+}
+
+static __always_inline void
+rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner)
+{
+ /*
+ * lock->wait_lock is held but explicit acquire semantics are needed
+ * for a new lock owner so WRITE_ONCE is insufficient.
+ */
+ xchg_acquire(&lock->owner, rt_mutex_owner_encode(lock, owner));
+}
+
+static __always_inline void rt_mutex_clear_owner(struct rt_mutex_base *lock)
+{
+ /* lock->wait_lock is held so the unlock provides release semantics. */
+ WRITE_ONCE(lock->owner, rt_mutex_owner_encode(lock, NULL));
}
static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock)
((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
}
-static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock)
+static __always_inline void
+fixup_rt_mutex_waiters(struct rt_mutex_base *lock, bool acquire_lock)
{
unsigned long owner, *p = (unsigned long *) &lock->owner;
* still set.
*/
owner = READ_ONCE(*p);
- if (owner & RT_MUTEX_HAS_WAITERS)
- WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
+ if (owner & RT_MUTEX_HAS_WAITERS) {
+ /*
+ * See rt_mutex_set_owner() and rt_mutex_clear_owner() on
+ * why xchg_acquire() is used for updating owner for
+ * locking and WRITE_ONCE() for unlocking.
+ *
+ * WRITE_ONCE() would work for the acquire case too, but
+ * in case that the lock acquisition failed it might
+ * force other lockers into the slow path unnecessarily.
+ */
+ if (acquire_lock)
+ xchg_acquire(p, owner & ~RT_MUTEX_HAS_WAITERS);
+ else
+ WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
+ }
}
/*
owner = *p;
} while (cmpxchg_relaxed(p, owner,
owner | RT_MUTEX_HAS_WAITERS) != owner);
+
+ /*
+ * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE
+ * operations in the event of contention. Ensure the successful
+ * cmpxchg is visible.
+ */
+ smp_mb__after_atomic();
}
/*
* then we need to wake the new top waiter up to try
* to get the lock.
*/
- if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
- wake_up_state(waiter->task, waiter->wake_state);
+ top_waiter = rt_mutex_top_waiter(lock);
+ if (prerequeue_top_waiter != top_waiter)
+ wake_up_state(top_waiter->task, top_waiter->wake_state);
raw_spin_unlock_irq(&lock->wait_lock);
return 0;
}
* try_to_take_rt_mutex() sets the lock waiters bit
* unconditionally. Clean this up.
*/
- fixup_rt_mutex_waiters(lock);
+ fixup_rt_mutex_waiters(lock, true);
return ret;
}
* try_to_take_rt_mutex() sets the waiter bit
* unconditionally. We might have to fix that up.
*/
- fixup_rt_mutex_waiters(lock);
+ fixup_rt_mutex_waiters(lock, true);
trace_contention_end(lock, ret);
* try_to_take_rt_mutex() sets the waiter bit unconditionally.
* We might have to fix that up:
*/
- fixup_rt_mutex_waiters(lock);
+ fixup_rt_mutex_waiters(lock, true);
debug_rt_mutex_free_waiter(&waiter);
trace_contention_end(lock, 0);
void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock)
{
debug_rt_mutex_proxy_unlock(lock);
- rt_mutex_set_owner(lock, NULL);
+ rt_mutex_clear_owner(lock);
}
/**
* try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
* have to fix that up.
*/
- fixup_rt_mutex_waiters(lock);
+ fixup_rt_mutex_waiters(lock, true);
raw_spin_unlock_irq(&lock->wait_lock);
return ret;
* try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
* have to fix that up.
*/
- fixup_rt_mutex_waiters(lock);
+ fixup_rt_mutex_waiters(lock, false);
raw_spin_unlock_irq(&lock->wait_lock);
sched_annotate_sleep();
mutex_lock(&module_mutex);
mod = find_module_all(name, strlen(name), true);
- ret = !mod || mod->state == MODULE_STATE_LIVE;
+ ret = !mod || mod->state == MODULE_STATE_LIVE
+ || mod->state == MODULE_STATE_GOING;
mutex_unlock(&module_mutex);
return ret;
mod->state = MODULE_STATE_UNFORMED;
-again:
mutex_lock(&module_mutex);
old = find_module_all(mod->name, strlen(mod->name), true);
if (old != NULL) {
- if (old->state != MODULE_STATE_LIVE) {
+ if (old->state == MODULE_STATE_COMING
+ || old->state == MODULE_STATE_UNFORMED) {
/* Wait in case it fails to load. */
mutex_unlock(&module_mutex);
err = wait_event_interruptible(module_wq,
finished_loading(mod->name));
if (err)
goto out_unlocked;
- goto again;
+
+ /* The module might have gone in the meantime. */
+ mutex_lock(&module_mutex);
+ old = find_module_all(mod->name, strlen(mod->name),
+ true);
}
- err = -EEXIST;
+
+ /*
+ * We are here only when the same module was being loaded. Do
+ * not try to load it again right now. It prevents long delays
+ * caused by serialized module load failures. It might happen
+ * when more devices of the same type trigger load of
+ * a particular module.
+ */
+ if (old && old->state == MODULE_STATE_LIVE)
+ err = -EEXIST;
+ else
+ err = -EBUSY;
goto out;
}
mod_update_bounds(mod);
{
return srcu_read_lock_held(&console_srcu);
}
+EXPORT_SYMBOL(console_srcu_read_lock_is_held);
#endif
enum devkmsg_log_bits {
/**
* console_lock_spinning_disable_and_check - mark end of code where another
* thread was able to busy wait and check if there is a waiter
+ * @cookie: cookie returned from console_srcu_read_lock()
*
* This is called at the end of the section where spinning is allowed.
* It has two functions. First, it is a signal that it is no longer
.user_mask = NULL,
.flags = SCA_USER, /* clear the user requested mask */
};
+ union cpumask_rcuhead {
+ cpumask_t cpumask;
+ struct rcu_head rcu;
+ };
__do_set_cpus_allowed(p, &ac);
- kfree(ac.user_mask);
+
+ /*
+ * Because this is called with p->pi_lock held, it is not possible
+ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
+ * kfree_rcu().
+ */
+ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
+}
+
+static cpumask_t *alloc_user_cpus_ptr(int node)
+{
+ /*
+ * See do_set_cpus_allowed() above for the rcu_head usage.
+ */
+ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+
+ return kmalloc_node(size, GFP_KERNEL, node);
}
int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
int node)
{
+ cpumask_t *user_mask;
unsigned long flags;
- if (!src->user_cpus_ptr)
+ /*
+ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
+ * may differ by now due to racing.
+ */
+ dst->user_cpus_ptr = NULL;
+
+ /*
+ * This check is racy and losing the race is a valid situation.
+ * It is not worth the extra overhead of taking the pi_lock on
+ * every fork/clone.
+ */
+ if (data_race(!src->user_cpus_ptr))
return 0;
- dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
- if (!dst->user_cpus_ptr)
+ user_mask = alloc_user_cpus_ptr(node);
+ if (!user_mask)
return -ENOMEM;
- /* Use pi_lock to protect content of user_cpus_ptr */
+ /*
+ * Use pi_lock to protect content of user_cpus_ptr
+ *
+ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
+ * do_set_cpus_allowed().
+ */
raw_spin_lock_irqsave(&src->pi_lock, flags);
- cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ if (src->user_cpus_ptr) {
+ swap(dst->user_cpus_ptr, user_mask);
+ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ }
raw_spin_unlock_irqrestore(&src->pi_lock, flags);
+
+ if (unlikely(user_mask))
+ kfree(user_mask);
+
return 0;
}
}
if (!(ctx->flags & SCA_MIGRATE_ENABLE)) {
- if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
+ if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) {
+ if (ctx->flags & SCA_USER)
+ swap(p->user_cpus_ptr, ctx->user_mask);
goto out;
+ }
if (WARN_ON_ONCE(p == current &&
is_migration_disabled(p) &&
return false;
}
+static inline cpumask_t *alloc_user_cpus_ptr(int node)
+{
+ return NULL;
+}
+
#endif /* !CONFIG_SMP */
static void
unsigned long thermal_pressure;
u64 resched_latency;
- arch_scale_freq_tick();
+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
+ arch_scale_freq_tick();
+
sched_clock_tick();
rq_lock(rq, &rf);
if (retval)
goto out_put_task;
- user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
- if (!user_mask) {
+ /*
+ * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
+ * alloc_user_cpus_ptr() returns NULL.
+ */
+ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
+ if (user_mask) {
+ cpumask_copy(user_mask, in_mask);
+ } else if (IS_ENABLED(CONFIG_SMP)) {
retval = -ENOMEM;
goto out_put_task;
}
- cpumask_copy(user_mask, in_mask);
+
ac = (struct affinity_context){
.new_mask = in_mask,
.user_mask = user_mask,
eenv_task_busy_time(&eenv, p, prev_cpu);
for (; pd; pd = pd->next) {
+ unsigned long util_min = p_util_min, util_max = p_util_max;
unsigned long cpu_cap, cpu_thermal_cap, util;
unsigned long cur_delta, max_spare_cap = 0;
unsigned long rq_util_min, rq_util_max;
- unsigned long util_min, util_max;
unsigned long prev_spare_cap = 0;
int max_spare_cap_cpu = -1;
unsigned long base_energy;
eenv.pd_cap = 0;
for_each_cpu(cpu, cpus) {
+ struct rq *rq = cpu_rq(cpu);
+
eenv.pd_cap += cpu_thermal_cap;
if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
* much capacity we can get out of the CPU; this is
* aligned with sched_cpu_util().
*/
- if (uclamp_is_used()) {
- if (uclamp_rq_is_idle(cpu_rq(cpu))) {
- util_min = p_util_min;
- util_max = p_util_max;
- } else {
- /*
- * Open code uclamp_rq_util_with() except for
- * the clamp() part. Ie: apply max aggregation
- * only. util_fits_cpu() logic requires to
- * operate on non clamped util but must use the
- * max-aggregated uclamp_{min, max}.
- */
- rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
- rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
-
- util_min = max(rq_util_min, p_util_min);
- util_max = max(rq_util_max, p_util_max);
- }
+ if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) {
+ /*
+ * Open code uclamp_rq_util_with() except for
+ * the clamp() part. Ie: apply max aggregation
+ * only. util_fits_cpu() logic requires to
+ * operate on non clamped util but must use the
+ * max-aggregated uclamp_{min, max}.
+ */
+ rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN);
+ rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX);
+
+ util_min = max(rq_util_min, p_util_min);
+ util_max = max(rq_util_max, p_util_max);
}
if (!util_fits_cpu(util, util_min, util_max, cpu))
continue;
* * Thermal pressure will impact all cpus in this perf domain
* equally.
*/
- if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+ if (sched_energy_enabled()) {
unsigned long inv_cap = capacity_orig - thermal_load_avg(rq);
- struct perf_domain *pd = rcu_dereference(rq->rd->pd);
+ struct perf_domain *pd;
+ rcu_read_lock();
+
+ pd = rcu_dereference(rq->rd->pd);
rq->cpu_capacity_inverted = 0;
for (; pd; pd = pd->next) {
struct cpumask *pd_span = perf_domain_span(pd);
unsigned long pd_cap_orig, pd_cap;
+ /* We can't be inverted against our own pd */
+ if (cpumask_test_cpu(cpu_of(rq), pd_span))
+ continue;
+
cpu = cpumask_any(pd_span);
pd_cap_orig = arch_scale_cpu_capacity(cpu);
break;
}
}
+
+ rcu_read_unlock();
}
trace_sched_cpu_capacity_tp(rq);
group = t->group;
/*
- * Wakeup waiters to stop polling. Can happen if cgroup is deleted
- * from under a polling process.
+ * Wakeup waiters to stop polling and clear the queue to prevent it from
+ * being accessed later. Can happen if cgroup is deleted from under a
+ * polling process.
*/
- wake_up_interruptible(&t->event_wait);
+ wake_up_pollfree(&t->event_wait);
mutex_lock(&group->trigger_lock);
if (resource >= RLIM_NLIMITS)
return -EINVAL;
+ resource = array_index_nospec(resource, RLIM_NLIMITS);
+
if (new_rlim) {
if (new_rlim->rlim_cur > new_rlim->rlim_max)
return -EINVAL;
}
EXPORT_SYMBOL_GPL(alarm_forward);
-u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle)
{
struct alarm_base *base = &alarm_bases[alarm->type];
+ ktime_t now = base->get_ktime();
+
+ if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) {
+ /*
+ * Same issue as with posix_timer_fn(). Timers which are
+ * periodic but the signal is ignored can starve the system
+ * with a very small interval. The real fix which was
+ * promised in the context of posix_timer_fn() never
+ * materialized, but someone should really work on it.
+ *
+ * To prevent DOS fake @now to be 1 jiffie out which keeps
+ * the overrun accounting correct but creates an
+ * inconsistency vs. timer_gettime(2).
+ */
+ ktime_t kj = NSEC_PER_SEC / HZ;
+
+ if (interval < kj)
+ now = ktime_add(now, kj);
+ }
+
+ return alarm_forward(alarm, now, interval);
+}
- return alarm_forward(alarm, base->get_ktime(), interval);
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+ return __alarm_forward_now(alarm, interval, false);
}
EXPORT_SYMBOL_GPL(alarm_forward_now);
if (posix_timer_event(ptr, si_private) && ptr->it_interval) {
/*
* Handle ignored signals and rearm the timer. This will go
- * away once we handle ignored signals proper.
+ * away once we handle ignored signals proper. Ensure that
+ * small intervals cannot starve the system.
*/
- ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval);
+ ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true);
++ptr->it_requeue_pending;
ptr->it_active = 1;
result = ALARMTIMER_RESTART;
#include "tick-internal.h"
/**
- * tick_program_event
+ * tick_program_event - program the CPU local timer device for the next event
*/
int tick_program_event(ktime_t expires, int force)
{
}
/**
- * tick_check_oneshot_mode - check whether the system is in oneshot mode
+ * tick_oneshot_mode_active - check whether the system is in oneshot mode
*
* returns 1 when either nohz or highres are enabled. otherwise 0.
*/
EXPORT_SYMBOL(ns_to_kernel_old_timeval);
/**
- * set_normalized_timespec - set timespec sec and nsec parts and normalize
+ * set_normalized_timespec64 - set timespec sec and nsec parts and normalize
*
* @ts: pointer to timespec variable to be set
* @sec: seconds to set
EXPORT_SYMBOL(ns_to_timespec64);
/**
- * msecs_to_jiffies: - convert milliseconds to jiffies
+ * __msecs_to_jiffies: - convert milliseconds to jiffies
* @m: time in milliseconds
*
* conversion is done as follows:
* handling any 32-bit overflows.
* for the details see __msecs_to_jiffies()
*
- * msecs_to_jiffies() checks for the passed in value being a constant
+ * __msecs_to_jiffies() checks for the passed in value being a constant
* via __builtin_constant_p() allowing gcc to eliminate most of the
* code, __msecs_to_jiffies() is called if the value passed does not
* allow constant folding and the actual conversion must be done at
* runtime.
- * the _msecs_to_jiffies helpers are the HZ dependent conversion
+ * The _msecs_to_jiffies helpers are the HZ dependent conversion
* routines found in include/linux/jiffies.h
*/
unsigned long __msecs_to_jiffies(const unsigned int m)
/**
* read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
* from the boot.
+ * @wall_time: current time as returned by persistent clock
+ * @boot_offset: offset that is defined as wall_time - boot_time
*
* Weak dummy function for arches that do not yet support it.
- * @wall_time: - current time as returned by persistent clock
- * @boot_offset: - offset that is defined as wall_time - boot_time
*
* The default function calculates offset based on the current value of
* local_clock(). This way architectures that support sched_clock() but don't
}
#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE)
-/**
+/*
* We have three kinds of time sources to use for sleep time
* injection, the preference order is:
* 1) non-stop clocksource
return !suspend_timing_needed;
}
-/**
+/*
* 1) can be determined whether to use or not only when doing
* timekeeping_resume() which is invoked after rtc_suspend(),
* so we can't skip rtc_suspend() surely if system has 1).
default y
help
The ring buffer has its own internal recursion. Although when
- recursion happens it wont cause harm because of the protection,
- but it does cause an unwanted overhead. Enabling this option will
+ recursion happens it won't cause harm because of the protection,
+ but it does cause unwanted overhead. Enabling this option will
place where recursion was detected into the ftrace "recursed_functions"
file.
The test runs for 10 seconds. This will slow your boot time
by at least 10 more seconds.
- At the end of the test, statics and more checks are done.
- It will output the stats of each per cpu buffer. What
+ At the end of the test, statistics and more checks are done.
+ It will output the stats of each per cpu buffer: What
was written, the sizes, what was read, what was lost, and
other similar details.
work = container_of(entry, struct send_signal_irq_work, irq_work);
group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type);
+ put_task_struct(work->task);
}
static int bpf_send_signal_common(u32 sig, enum pid_type type)
return -EPERM;
if (unlikely(!nmi_uaccess_okay()))
return -EPERM;
+ /* Task should not be pid=1 to avoid kernel panic. */
+ if (unlikely(is_global_init(current)))
+ return -EPERM;
if (irqs_disabled()) {
/* Do an early check on signal validity. Otherwise,
* to the irq_work. The current task may change when queued
* irq works get executed.
*/
- work->task = current;
+ work->task = get_task_struct(current);
work->sig = sig;
work->type = type;
irq_work_queue(&work->irq_work);
call_rcu(&hash->rcu, __free_ftrace_hash_rcu);
}
+/**
+ * ftrace_free_filter - remove all filters for an ftrace_ops
+ * @ops - the ops to remove the filters from
+ */
void ftrace_free_filter(struct ftrace_ops *ops)
{
ftrace_ops_init(ops);
free_ftrace_hash(ops->func_hash->filter_hash);
free_ftrace_hash(ops->func_hash->notrace_hash);
}
+EXPORT_SYMBOL_GPL(ftrace_free_filter);
static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
{
*
* Filters denote which functions should be enabled when tracing is enabled
* If @ip is NULL, it fails to update filter.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
*/
int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
int remove, int reset)
*
* Filters denote which functions should be enabled when tracing is enabled
* If @ips array or any ip specified within is NULL , it fails to update filter.
- */
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
+*/
int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips,
unsigned int cnt, int remove, int reset)
{
*
* Filters denote which functions should be enabled when tracing is enabled.
* If @buf is NULL and reset is set, all functions will be enabled for tracing.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
*/
int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset)
* Notrace Filters denote which functions should not be enabled when tracing
* is enabled. If @buf is NULL and reset is set, all functions will be enabled
* for tracing.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
*/
int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset)
struct rv_monitor_def *mdef;
int retval = -EINVAL;
bool enable = true;
- char *ptr = buff;
+ char *ptr;
int len;
if (count < 1 || count > MAX_RV_MONITOR_NAME_SIZE + 1)
if (val > 100)
return -EINVAL;
- if (!val)
- val = 1;
-
tr->buffer_percent = val;
(*ppos)++;
static_key_enable(&tracepoint_printk_key.key);
}
tracer_alloc_buffers();
+
+ init_events();
}
void __init trace_init(void)
int offset;
int size;
int is_signed;
+ int len;
};
struct prog_entry;
extern void trace_event_enable_tgid_record(bool enable);
extern int event_trace_init(void);
+extern int init_events(void);
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
extern int event_trace_del_tracer(struct trace_array *tr);
extern void __trace_early_add_events(struct trace_array *tr);
static int __trace_define_field(struct list_head *head, const char *type,
const char *name, int offset, int size,
- int is_signed, int filter_type)
+ int is_signed, int filter_type, int len)
{
struct ftrace_event_field *field;
field->offset = offset;
field->size = size;
field->is_signed = is_signed;
+ field->len = len;
list_add(&field->link, head);
head = trace_get_fields(call);
return __trace_define_field(head, type, name, offset, size,
- is_signed, filter_type);
+ is_signed, filter_type, 0);
}
EXPORT_SYMBOL_GPL(trace_define_field);
+static int trace_define_field_ext(struct trace_event_call *call, const char *type,
+ const char *name, int offset, int size, int is_signed,
+ int filter_type, int len)
+{
+ struct list_head *head;
+
+ if (WARN_ON(!call->class))
+ return 0;
+
+ head = trace_get_fields(call);
+ return __trace_define_field(head, type, name, offset, size,
+ is_signed, filter_type, len);
+}
+
#define __generic_field(type, item, filter_type) \
ret = __trace_define_field(&ftrace_generic_fields, #type, \
#item, 0, 0, is_signed_type(type), \
- filter_type); \
+ filter_type, 0); \
if (ret) \
return ret;
"common_" #item, \
offsetof(typeof(ent), item), \
sizeof(ent.item), \
- is_signed_type(type), FILTER_OTHER); \
+ is_signed_type(type), FILTER_OTHER, 0); \
if (ret) \
return ret;
seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
field->type, field->name, field->offset,
field->size, !!field->is_signed);
- else
- seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+ else if (field->len)
+ seq_printf(m, "\tfield:%.*s %s[%d];\toffset:%u;\tsize:%u;\tsigned:%d;\n",
(int)(array_descriptor - field->type),
field->type, field->name,
- array_descriptor, field->offset,
+ field->len, field->offset,
field->size, !!field->is_signed);
+ else
+ seq_printf(m, "\tfield:%.*s %s[];\toffset:%u;\tsize:%u;\tsigned:%d;\n",
+ (int)(array_descriptor - field->type),
+ field->type, field->name,
+ field->offset, field->size, !!field->is_signed);
return 0;
}
}
offset = ALIGN(offset, field->align);
- ret = trace_define_field(call, field->type, field->name,
+ ret = trace_define_field_ext(call, field->type, field->name,
offset, field->size,
- field->is_signed, field->filter_type);
+ field->is_signed, field->filter_type,
+ field->len);
if (WARN_ON_ONCE(ret)) {
pr_err("error code is %d\n", ret);
break;
}
/**
- * prog_entry - a singe entry in the filter program
+ * struct prog_entry - a singe entry in the filter program
* @target: Index to jump to on a branch (actually one minus the index)
* @when_to_branch: The value of the result of the predicate to do a branch
* @pred: The predicate to execute.
};
/**
- * update_preds- assign a program entry a label target
+ * update_preds - assign a program entry a label target
* @prog: The program array
* @N: The index of the current entry in @prog
- * @when_to_branch: What to assign a program entry for its branch condition
+ * @invert: What to assign a program entry for its branch condition
*
* The program entry at @N has a target that points to the index of a program
* entry that can have its target and when_to_branch fields updated.
* Update the current program entry denoted by index @N target field to be
* that of the updated entry. This will denote the entry to update if
- * we are processing an "||" after an "&&"
+ * we are processing an "||" after an "&&".
*/
static void update_preds(struct prog_entry *prog, int N, int invert)
{
hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 :
HIST_FIELD_FN_BUCKET;
hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
+ if (!hist_field->operands[0])
+ goto free;
hist_field->size = hist_field->operands[0]->size;
hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL);
if (!hist_field->type)
#define __array(_type, _item, _len) { \
.type = #_type"["__stringify(_len)"]", .name = #_item, \
.size = sizeof(_type[_len]), .align = __alignof__(_type), \
- is_signed_type(_type), .filter_type = FILTER_OTHER },
+ is_signed_type(_type), .filter_type = FILTER_OTHER, \
+ .len = _len },
#undef __array_desc
#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len)
* register/unregister serialization is provided by trace's
* trace_types_lock.
*/
- lockdep_assert_held(&trace_types_lock);
-
- list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+ list_for_each_entry_rcu(inst, &osnoise_instances, list,
+ lockdep_is_held(&trace_types_lock)) {
if (inst->tr == tr) {
list_del_rcu(&inst->list);
found = 1;
NULL
};
-__init static int init_events(void)
+__init int init_events(void)
{
struct trace_event *event;
int i, ret;
return 0;
}
-early_initcall(init_events);
if (wait == UMH_NO_WAIT) /* task has freed sub_info */
goto unlock;
- if (wait & UMH_KILLABLE)
- state |= TASK_KILLABLE;
-
if (wait & UMH_FREEZABLE)
state |= TASK_FREEZABLE;
- retval = wait_for_completion_state(&done, state);
- if (!retval)
- goto wait_done;
-
if (wait & UMH_KILLABLE) {
+ retval = wait_for_completion_state(&done, state | TASK_KILLABLE);
+ if (!retval)
+ goto wait_done;
+
/* umh_complete() will see NULL and free sub_info */
if (xchg(&sub_info->complete, NULL))
goto unlock;
+
+ /*
+ * fallthrough; in case of -ERESTARTSYS now do uninterruptible
+ * wait_for_completion_state(). Since umh_complete() shall call
+ * complete() in a moment if xchg() above returned NULL, this
+ * uninterruptible wait_for_completion_state() will not block
+ * SIGKILL'ed processes for long.
+ */
}
+ wait_for_completion_state(&done, state);
wait_done:
retval = sub_info->retval;
select KALLSYMS
select CRC32
select STACKDEPOT
+ select STACKDEPOT_ALWAYS_INIT if !DEBUG_KMEMLEAK_DEFAULT_OFF
help
Say Y here if you want to enable the memory leak
detector. The memory allocation/freeing is traced in a way
depends on DEBUG_KERNEL && PROC_FS
default y
help
- If you say Y here, the /proc/sched_debug file will be provided
+ If you say Y here, the /sys/kernel/debug/sched file will be provided
that can help debug the scheduler. The runtime overhead of this
option is minimal.
help
Add fault injections into various functions that are annotated with
ALLOW_ERROR_INJECTION() in the kernel. BPF may also modify the return
- value of theses functions. This is useful to test error paths of code.
+ value of these functions. This is useful to test error paths of code.
If unsure, say N
If unsure, say N.
+config MEMCPY_SLOW_KUNIT_TEST
+ bool "Include exhaustive memcpy tests"
+ depends on MEMCPY_KUNIT_TEST
+ default y
+ help
+ Some memcpy tests are quite exhaustive in checking for overlaps
+ and bit ranges. These can be very slow, so they are split out
+ as a separate config, in case they need to be disabled.
+
config IS_SIGNED_TYPE_KUNIT_TEST
tristate "Test is_signed_type() macro" if !KUNIT_ALL_TESTS
depends on KUNIT
Enable support for modeling a subset of weak memory, which allows
detecting a subset of data races due to missing memory barriers.
- Depends on KCSAN_STRICT, because the options strenghtening certain
+ Depends on KCSAN_STRICT, because the options strengthening certain
plain accesses by default (depending on !KCSAN_STRICT) reduce the
ability to detect any data races invoving reordered accesses, in
particular reordered writes.
return 0;
}
EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave);
+
+int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock)
+{
+ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+ if (atomic_add_unless(atomic, -1, 1))
+ return 0;
+
+ /* Otherwise do it the slow way */
+ raw_spin_lock(lock);
+ if (atomic_dec_and_test(atomic))
+ return 1;
+ raw_spin_unlock(lock);
+ return 0;
+}
+EXPORT_SYMBOL(_atomic_dec_and_raw_lock);
+
+int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock,
+ unsigned long *flags)
+{
+ /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+ if (atomic_add_unless(atomic, -1, 1))
+ return 0;
+
+ /* Otherwise do it the slow way */
+ raw_spin_lock_irqsave(lock, *flags);
+ if (atomic_dec_and_test(atomic))
+ return 1;
+ raw_spin_unlock_irqrestore(lock, *flags);
+ return 0;
+}
+EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave);
mem_assert = container_of(assert, struct kunit_mem_assert,
assert);
- string_stream_add(stream,
- KUNIT_SUBTEST_INDENT "Expected %s %s %s, but\n",
- mem_assert->text->left_text,
- mem_assert->text->operation,
- mem_assert->text->right_text);
+ if (!mem_assert->left_value) {
+ string_stream_add(stream,
+ KUNIT_SUBTEST_INDENT "Expected %s is not null, but is\n",
+ mem_assert->text->left_text);
+ } else if (!mem_assert->right_value) {
+ string_stream_add(stream,
+ KUNIT_SUBTEST_INDENT "Expected %s is not null, but is\n",
+ mem_assert->text->right_text);
+ } else {
+ string_stream_add(stream,
+ KUNIT_SUBTEST_INDENT "Expected %s %s %s, but\n",
+ mem_assert->text->left_text,
+ mem_assert->text->operation,
+ mem_assert->text->right_text);
- string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n",
- mem_assert->text->left_text);
- kunit_assert_hexdump(stream, mem_assert->left_value,
- mem_assert->right_value, mem_assert->size);
+ string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n",
+ mem_assert->text->left_text);
+ kunit_assert_hexdump(stream, mem_assert->left_value,
+ mem_assert->right_value, mem_assert->size);
- string_stream_add(stream, "\n");
+ string_stream_add(stream, "\n");
- string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n",
- mem_assert->text->right_text);
- kunit_assert_hexdump(stream, mem_assert->right_value,
- mem_assert->left_value, mem_assert->size);
+ string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n",
+ mem_assert->text->right_text);
+ kunit_assert_hexdump(stream, mem_assert->right_value,
+ mem_assert->left_value, mem_assert->size);
- kunit_assert_print_msg(message, stream);
+ kunit_assert_print_msg(message, stream);
+ }
}
EXPORT_SYMBOL_GPL(kunit_mem_assert_format);
return ERR_PTR(-ENOMEM);
frag->fragment = kunit_kmalloc(test, len, gfp);
- if (!frag->fragment)
+ if (!frag->fragment) {
+ kunit_kfree(test, frag);
return ERR_PTR(-ENOMEM);
+ }
return frag;
}
#include "try-catch-impl.h"
DEFINE_STATIC_KEY_FALSE(kunit_running);
+EXPORT_SYMBOL_GPL(kunit_running);
#if IS_BUILTIN(CONFIG_KUNIT)
/*
} \
if (!--retry) \
break; \
- cpu_relax(); \
} \
} while (0)
unsigned char piv)
{
struct maple_node *node = mte_to_node(mn);
+ enum maple_type type = mte_node_type(mn);
- if (piv >= mt_pivots[piv]) {
+ if (piv >= mt_pivots[type]) {
WARN_ON(1);
return 0;
}
- switch (mte_node_type(mn)) {
+ switch (type) {
case maple_arange_64:
return node->ma64.pivot[piv];
case maple_range_64:
unsigned long *pivots, *gaps;
void __rcu **slots;
unsigned long gap = 0;
- unsigned long max, min, index;
+ unsigned long max, min;
unsigned char offset;
if (unlikely(mas_is_err(mas)))
min = mas_safe_min(mas, pivots, --offset);
max = mas_safe_pivot(mas, pivots, offset, type);
- index = mas->index;
- while (index <= max) {
+ while (mas->index <= max) {
gap = 0;
if (gaps)
gap = gaps[offset];
min = mas_safe_min(mas, pivots, offset);
}
- if (unlikely(index > max)) {
- mas_set_err(mas, -EBUSY);
- return false;
- }
+ if (unlikely((mas->index > max) || (size - 1 > max - mas->index)))
+ goto no_space;
if (unlikely(ma_is_leaf(type))) {
mas->offset = offset;
return false;
ascend:
- if (mte_is_root(mas->node))
- mas_set_err(mas, -EBUSY);
+ if (!mte_is_root(mas->node))
+ return false;
+no_space:
+ mas_set_err(mas, -EBUSY);
return false;
}
static void init_large(struct kunit *test)
{
+ if (!IS_ENABLED(CONFIG_MEMCPY_SLOW_KUNIT_TEST))
+ kunit_skip(test, "Slow test skipped. Enable with CONFIG_MEMCPY_SLOW_KUNIT_TEST=y");
/* Get many bit patterns. */
get_random_bytes(large_src, ARRAY_SIZE(large_src));
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/jiffies.h>
+#include <linux/nospec.h>
#include <linux/skbuff.h>
#include <linux/string.h>
#include <linux/types.h>
if (type <= 0 || type > maxtype)
return 0;
+ type = array_index_nospec(type, maxtype + 1);
pt = &policy[type];
BUG_ON(pt->type > NLA_TYPE_MAX);
}
continue;
}
+ type = array_index_nospec(type, maxtype + 1);
if (policy) {
int err = validate_nla(nla, maxtype, policy,
validate, extack, depth);
#include <linux/slab.h>
#include <linux/string.h>
+/*
+ * max size needed by different bases to express U64
+ * HEX: "0xFFFFFFFFFFFFFFFF" --> 18
+ * DEC: "18446744073709551615" --> 20
+ * OCT: "01777777777777777777777" --> 23
+ * pick the max one to define NUMBER_BUF_LEN
+ */
+#define NUMBER_BUF_LEN 24
+
/**
* match_one - Determines if a string matches a simple pattern
* @s: the string to examine for presence of the pattern
static int match_number(substring_t *s, int *result, int base)
{
char *endp;
- char *buf;
+ char buf[NUMBER_BUF_LEN];
int ret;
long val;
- buf = match_strdup(s);
- if (!buf)
- return -ENOMEM;
-
+ if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN)
+ return -ERANGE;
ret = 0;
val = simple_strtol(buf, &endp, base);
if (endp == buf)
ret = -ERANGE;
else
*result = (int) val;
- kfree(buf);
return ret;
}
*/
static int match_u64int(substring_t *s, u64 *result, int base)
{
- char *buf;
+ char buf[NUMBER_BUF_LEN];
int ret;
u64 val;
- buf = match_strdup(s);
- if (!buf)
- return -ENOMEM;
-
+ if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN)
+ return -ERANGE;
ret = kstrtoull(buf, base, &val);
if (!ret)
*result = val;
- kfree(buf);
return ret;
}
*/
int match_uint(substring_t *s, unsigned int *result)
{
- int err = -ENOMEM;
- char *buf = match_strdup(s);
+ char buf[NUMBER_BUF_LEN];
- if (buf) {
- err = kstrtouint(buf, 10, result);
- kfree(buf);
- }
- return err;
+ if (match_strlcpy(buf, s, NUMBER_BUF_LEN) >= NUMBER_BUF_LEN)
+ return -ERANGE;
+
+ return kstrtouint(buf, 10, result);
}
EXPORT_SYMBOL(match_uint);
return -EOPNOTSUPP;
if (sgt_append->prv) {
+ unsigned long next_pfn = (page_to_phys(sg_page(sgt_append->prv)) +
+ sgt_append->prv->offset + sgt_append->prv->length) / PAGE_SIZE;
+
if (WARN_ON(offset))
return -EINVAL;
/* Merge contiguous pages into the last SG */
prv_len = sgt_append->prv->length;
- last_pg = sg_page(sgt_append->prv);
- while (n_pages && pages_are_mergeable(last_pg, pages[0])) {
- if (sgt_append->prv->length + PAGE_SIZE > max_segment)
- break;
- sgt_append->prv->length += PAGE_SIZE;
- last_pg = pages[0];
- pages++;
- n_pages--;
+ if (page_to_pfn(pages[0]) == next_pfn) {
+ last_pg = pfn_to_page(next_pfn - 1);
+ while (n_pages && pages_are_mergeable(pages[0], last_pg)) {
+ if (sgt_append->prv->length + PAGE_SIZE > max_segment)
+ break;
+ sgt_append->prv->length += PAGE_SIZE;
+ last_pg = pages[0];
+ pages++;
+ n_pages--;
+ }
+ if (!n_pages)
+ goto out;
}
- if (!n_pages)
- goto out;
}
/* compute number of contiguous chunks */
mt_set_non_kernel(0);
}
+static noinline void check_empty_area_window(struct maple_tree *mt)
+{
+ unsigned long i, nr_entries = 20;
+ MA_STATE(mas, mt, 0, 0);
+
+ for (i = 1; i <= nr_entries; i++)
+ mtree_store_range(mt, i*10, i*10 + 9,
+ xa_mk_value(i), GFP_KERNEL);
+
+ /* Create another hole besides the one at 0 */
+ mtree_store_range(mt, 160, 169, NULL, GFP_KERNEL);
+
+ /* Check lower bounds that don't fit */
+ rcu_read_lock();
+ MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 10) != -EBUSY);
+
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area_rev(&mas, 6, 90, 5) != -EBUSY);
+
+ /* Check lower bound that does fit */
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 5) != 0);
+ MT_BUG_ON(mt, mas.index != 5);
+ MT_BUG_ON(mt, mas.last != 9);
+ rcu_read_unlock();
+
+ /* Check one gap that doesn't fit and one that does */
+ rcu_read_lock();
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 217, 9) != 0);
+ MT_BUG_ON(mt, mas.index != 161);
+ MT_BUG_ON(mt, mas.last != 169);
+
+ /* Check one gap that does fit above the min */
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 3) != 0);
+ MT_BUG_ON(mt, mas.index != 216);
+ MT_BUG_ON(mt, mas.last != 218);
+
+ /* Check size that doesn't fit any gap */
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 16) != -EBUSY);
+
+ /*
+ * Check size that doesn't fit the lower end of the window but
+ * does fit the gap
+ */
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area_rev(&mas, 167, 200, 4) != -EBUSY);
+
+ /*
+ * Check size that doesn't fit the upper end of the window but
+ * does fit the gap
+ */
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 162, 4) != -EBUSY);
+
+ /* Check mas_empty_area forward */
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 9) != 0);
+ MT_BUG_ON(mt, mas.index != 0);
+ MT_BUG_ON(mt, mas.last != 8);
+
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 4) != 0);
+ MT_BUG_ON(mt, mas.index != 0);
+ MT_BUG_ON(mt, mas.last != 3);
+
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 11) != -EBUSY);
+
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area(&mas, 5, 100, 6) != -EBUSY);
+
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area(&mas, 0, 8, 10) != -EBUSY);
+
+ mas_reset(&mas);
+ mas_empty_area(&mas, 100, 165, 3);
+
+ mas_reset(&mas);
+ MT_BUG_ON(mt, mas_empty_area(&mas, 100, 163, 6) != -EBUSY);
+ rcu_read_unlock();
+}
+
static DEFINE_MTREE(tree);
static int maple_tree_seed(void)
{
check_bnode_min_spanning(&tree);
mtree_destroy(&tree);
+ mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
+ check_empty_area_window(&tree);
+ mtree_destroy(&tree);
+
#if defined(BENCH)
skip:
#endif
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* lib/minmax.c: windowed min/max tracker
*
* Kathleen Nichols' algorithm for tracking the minimum (or maximum)
pfn = cc->zone->zone_start_pfn;
cc->fast_search_fail = 0;
found_block = true;
+ set_pageblock_skip(freepage);
break;
}
}
struct folio *folio;
int err = 0;
+ /* "last_index" is the index of the page beyond the end of the read */
last_index = DIV_ROUND_UP(iocb->ki_pos + iter->count, PAGE_SIZE);
retry:
if (fatal_signal_pending(current))
return -EINTR;
- filemap_get_read_batch(mapping, index, last_index, fbatch);
+ filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
if (!folio_batch_count(fbatch)) {
if (iocb->ki_flags & IOCB_NOIO)
return -EAGAIN;
page_cache_sync_readahead(mapping, ra, filp, index,
last_index - index);
- filemap_get_read_batch(mapping, index, last_index, fbatch);
+ filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
}
if (!folio_batch_count(fbatch)) {
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
drain_allow = false;
}
- if (!folio_isolate_lru(folio))
+ if (folio_isolate_lru(folio))
continue;
list_add_tail(&folio->lru, movable_page_list);
pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot));
if (pmd_swp_soft_dirty(*pvmw->pmd))
pmde = pmd_mksoft_dirty(pmde);
- if (is_writable_migration_entry(entry))
- pmde = maybe_pmd_mkwrite(pmde, vma);
if (pmd_swp_uffd_wp(*pvmw->pmd))
pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde));
if (!is_migration_entry_young(entry))
/* NOTE: this may contain setting soft-dirty on some archs */
if (PageDirty(new) && is_migration_entry_dirty(entry))
pmde = pmd_mkdirty(pmde);
+ if (is_writable_migration_entry(entry))
+ pmde = maybe_pmd_mkwrite(pmde, vma);
+ else
+ pmde = pmd_wrprotect(pmde);
if (PageAnon(new)) {
rmap_t rmap_flags = RMAP_COMPOUND;
static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end);
static inline bool subpool_is_free(struct hugepage_subpool *spool)
{
/*
* Reset and decrement one ref on hugepage private reservation.
- * Called with mm->mmap_sem writer semaphore held.
+ * Called with mm->mmap_lock writer semaphore held.
* This function should be only used by move_vma() and operate on
* same sized vma. It should never come here with last ref on the
* reservation.
{
if (addr & ~(huge_page_mask(hstate_vma(vma))))
return -EINVAL;
+
+ /*
+ * PMD sharing is only possible for PUD_SIZE-aligned address ranges
+ * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this
+ * split, unshare PMDs in the PUD_SIZE interval surrounding addr now.
+ */
+ if (addr & ~PUD_MASK) {
+ /*
+ * hugetlb_vm_op_split is called right before we attempt to
+ * split the VMA. We will need to unshare PMDs in the old and
+ * new VMAs, so let's unshare before we split.
+ */
+ unsigned long floor = addr & PUD_MASK;
+ unsigned long ceil = floor + PUD_SIZE;
+
+ if (floor >= vma->vm_start && ceil <= vma->vm_end)
+ hugetlb_unshare_pmds(vma, floor, ceil);
+ }
+
return 0;
}
entry = huge_pte_clear_uffd_wp(entry);
set_huge_pte_at(dst, addr, dst_pte, entry);
} else if (unlikely(is_pte_marker(entry))) {
+ /* No swap on hugetlb */
+ WARN_ON_ONCE(
+ is_swapin_error_entry(pte_to_swp_entry(entry)));
/*
* We copy the pte marker only if the dst vma has
* uffd-wp enabled.
/*
* We don't have to worry about the ordering of src and dst ptlocks
- * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock.
+ * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock.
*/
if (src_ptl != dst_ptl)
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
spinlock_t *ptl;
ptep = huge_pte_offset(mm, address, psize);
if (!ptep) {
- address |= last_addr_mask;
- continue;
+ if (!uffd_wp) {
+ address |= last_addr_mask;
+ continue;
+ }
+ /*
+ * Userfaultfd wr-protect requires pgtable
+ * pre-allocations to install pte markers.
+ */
+ ptep = huge_pte_alloc(mm, vma, address, psize);
+ if (!ptep)
+ break;
}
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, vma, address, ptep)) {
}
pte = huge_ptep_get(ptep);
if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
- spin_unlock(ptl);
- continue;
- }
- if (unlikely(is_hugetlb_entry_migration(pte))) {
+ /* Nothing to do. */
+ } else if (unlikely(is_hugetlb_entry_migration(pte))) {
swp_entry_t entry = pte_to_swp_entry(pte);
struct page *page = pfn_swap_entry_to_page(entry);
+ pte_t newpte = pte;
- if (!is_readable_migration_entry(entry)) {
- pte_t newpte;
-
+ if (is_writable_migration_entry(entry)) {
if (PageAnon(page))
entry = make_readable_exclusive_migration_entry(
swp_offset(entry));
entry = make_readable_migration_entry(
swp_offset(entry));
newpte = swp_entry_to_pte(entry);
- if (uffd_wp)
- newpte = pte_swp_mkuffd_wp(newpte);
- else if (uffd_wp_resolve)
- newpte = pte_swp_clear_uffd_wp(newpte);
- set_huge_pte_at(mm, address, ptep, newpte);
pages++;
}
- spin_unlock(ptl);
- continue;
- }
- if (unlikely(pte_marker_uffd_wp(pte))) {
- /*
- * This is changing a non-present pte into a none pte,
- * no need for huge_ptep_modify_prot_start/commit().
- */
+
+ if (uffd_wp)
+ newpte = pte_swp_mkuffd_wp(newpte);
+ else if (uffd_wp_resolve)
+ newpte = pte_swp_clear_uffd_wp(newpte);
+ if (!pte_same(pte, newpte))
+ set_huge_pte_at(mm, address, ptep, newpte);
+ } else if (unlikely(is_pte_marker(pte))) {
+ /* No other markers apply for now. */
+ WARN_ON_ONCE(!pte_marker_uffd_wp(pte));
if (uffd_wp_resolve)
+ /* Safe to modify directly (non-present->none). */
huge_pte_clear(mm, address, ptep, psize);
- }
- if (!huge_pte_none(pte)) {
+ } else if (!huge_pte_none(pte)) {
pte_t old_pte;
unsigned int shift = huge_page_shift(hstate_vma(vma));
}
}
-/*
- * This function will unconditionally remove all the shared pmd pgtable entries
- * within the specific vma for a hugetlbfs memory range.
- */
-void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end)
{
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
struct mm_struct *mm = vma->vm_mm;
struct mmu_notifier_range range;
- unsigned long address, start, end;
+ unsigned long address;
spinlock_t *ptl;
pte_t *ptep;
if (!(vma->vm_flags & VM_MAYSHARE))
return;
- start = ALIGN(vma->vm_start, PUD_SIZE);
- end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
-
if (start >= end)
return;
mmu_notifier_invalidate_range_end(&range);
}
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+{
+ hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE),
+ ALIGN_DOWN(vma->vm_end, PUD_SIZE));
+}
+
#ifdef CONFIG_CMA
static bool cma_reserve_called __initdata;
static inline bool ____kasan_kfree_large(void *ptr, unsigned long ip)
{
+ if (!kasan_arch_is_ready())
+ return false;
+
if (ptr != page_address(virt_to_head_page(ptr))) {
kasan_report_invalid_free(ptr, ip, KASAN_REPORT_INVALID_FREE);
return true;
bool kasan_byte_accessible(const void *addr)
{
- s8 shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr));
+ s8 shadow_byte;
+
+ if (!kasan_arch_is_ready())
+ return true;
+
+ shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(addr));
return shadow_byte >= 0 && shadow_byte < KASAN_GRANULE_SIZE;
}
* Whether the KASAN KUnit test suite is currently being executed.
* Updated in kasan_test.c.
*/
-bool kasan_kunit_executing;
+static bool kasan_kunit_executing;
void kasan_kunit_test_suite_start(void)
{
unsigned long shadow_start, shadow_end;
int ret;
+ if (!kasan_arch_is_ready())
+ return 0;
+
if (!is_vmalloc_or_module_addr((void *)addr))
return 0;
unsigned long region_start, region_end;
unsigned long size;
+ if (!kasan_arch_is_ready())
+ return;
+
region_start = ALIGN(start, KASAN_MEMORY_PER_SHADOW_PAGE);
region_end = ALIGN_DOWN(end, KASAN_MEMORY_PER_SHADOW_PAGE);
* with setting memory tags, so the KASAN_VMALLOC_INIT flag is ignored.
*/
+ if (!kasan_arch_is_ready())
+ return (void *)start;
+
if (!is_vmalloc_or_module_addr(start))
return (void *)start;
*/
void __kasan_poison_vmalloc(const void *start, unsigned long size)
{
+ if (!kasan_arch_is_ready())
+ return;
+
if (!is_vmalloc_or_module_addr(start))
return;
return SCAN_SUCCEED;
}
+/*
+ * See pmd_trans_unstable() for how the result may change out from
+ * underneath us, even if we hold mmap_lock in read.
+ */
static int find_pmd_or_thp_or_none(struct mm_struct *mm,
unsigned long address,
pmd_t **pmd)
#endif
if (pmd_none(pmde))
return SCAN_PMD_NONE;
+ if (!pmd_present(pmde))
+ return SCAN_PMD_NULL;
if (pmd_trans_huge(pmde))
return SCAN_PMD_MAPPED;
+ if (pmd_devmap(pmde))
+ return SCAN_PMD_NULL;
if (pmd_bad(pmde))
return SCAN_PMD_NULL;
return SCAN_SUCCEED;
if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
return SCAN_VMA_CHECK;
- /*
- * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings
- * that got written to. Without this, we'd have to also lock the
- * anon_vma if one exists.
- */
- if (vma->anon_vma)
- return SCAN_VMA_CHECK;
-
/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
if (userfaultfd_wp(vma))
return SCAN_PTE_UFFD_WP;
}
/* step 4: remove pte entries */
+ /* we make no change to anon, but protect concurrent anon page lookup */
+ if (vma->anon_vma)
+ anon_vma_lock_write(vma->anon_vma);
+
collapse_and_free_pmd(mm, vma, haddr, pmd);
+ if (vma->anon_vma)
+ anon_vma_unlock_write(vma->anon_vma);
i_mmap_unlock_write(vma->vm_file->f_mapping);
maybe_install_pmd:
* has higher cost too. It would also probably require locking
* the anon_vma.
*/
- if (vma->anon_vma) {
+ if (READ_ONCE(vma->anon_vma)) {
result = SCAN_PAGE_ANON;
goto next;
}
result = SCAN_PTE_MAPPED_HUGEPAGE;
if ((cc->is_khugepaged || is_target) &&
mmap_write_trylock(mm)) {
+ /*
+ * Re-check whether we have an ->anon_vma, because
+ * collapse_and_free_pmd() requires that either no
+ * ->anon_vma exists or the anon_vma is locked.
+ * We already checked ->anon_vma above, but that check
+ * is racy because ->anon_vma can be populated under the
+ * mmap lock in read mode.
+ */
+ if (vma->anon_vma) {
+ result = SCAN_PAGE_ANON;
+ goto unlock_next;
+ }
/*
* When a vma is registered with uffd-wp, we can't
* recycle the pmd pgtable because there can be pte
case SCAN_CGROUP_CHARGE_FAIL:
return -EBUSY;
/* Resource temporary unavailable - trying again might succeed */
+ case SCAN_PAGE_COUNT:
case SCAN_PAGE_LOCK:
case SCAN_PAGE_LRU:
case SCAN_DEL_PAGE_LRU:
goto out_nolock;
}
- hend = vma->vm_end & HPAGE_PMD_MASK;
+ hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
}
mmap_assert_locked(mm);
memset(cc->node_load, 0, sizeof(cc->node_load));
return -EINVAL;
if (strcmp(str, "off") == 0)
kmemleak_disable();
- else if (strcmp(str, "on") == 0)
+ else if (strcmp(str, "on") == 0) {
kmemleak_skip_disable = 1;
+ stack_depot_want_early_init();
+ }
else
return -EINVAL;
return 0;
if (kmemleak_error)
return;
- stack_depot_init();
jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);
new_page = NULL;
}
if (new_page) {
- copy_user_highpage(new_page, page, address, vma);
-
+ if (copy_mc_user_highpage(new_page, page, address, vma)) {
+ put_page(new_page);
+ memory_failure_queue(page_to_pfn(page), 0);
+ return ERR_PTR(-EHWPOISON);
+ }
SetPageDirty(new_page);
__SetPageUptodate(new_page);
__SetPageLocked(new_page);
#endif /* CONFIG_ANON_VMA_NAME */
/*
* Update the vm_flags on region of a vma, splitting it or merging it as
- * necessary. Must be called with mmap_sem held for writing;
+ * necessary. Must be called with mmap_lock held for writing;
* Caller should ensure anon_name stability by raising its refcount even when
* anon_name belongs to a valid vma because this function might free that vma.
*/
* @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
- * Free boot memory block previously allocated by memblock_alloc_xx() API.
+ * Free boot memory block previously allocated by memblock_phys_alloc_xx() API.
* The freeing memory will not be released to the buddy allocator.
*/
int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size)
#include <linux/resume_user_mode.h>
#include <linux/psi.h>
#include <linux/seq_buf.h>
-#include <linux/parser.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
psi_memstall_enter(&pflags);
nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
gfp_mask,
- MEMCG_RECLAIM_MAY_SWAP,
- NULL);
+ MEMCG_RECLAIM_MAY_SWAP);
psi_memstall_leave(&pflags);
} while ((memcg = parent_mem_cgroup(memcg)) &&
!mem_cgroup_is_root(memcg));
psi_memstall_enter(&pflags);
nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
- gfp_mask, reclaim_options,
- NULL);
+ gfp_mask, reclaim_options);
psi_memstall_leave(&pflags);
if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
}
if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
- memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP,
- NULL)) {
+ memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) {
ret = -EBUSY;
break;
}
return -EINTR;
if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
- MEMCG_RECLAIM_MAY_SWAP,
- NULL))
+ MEMCG_RECLAIM_MAY_SWAP))
nr_retries--;
}
}
reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
- GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP,
- NULL);
+ GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP);
if (!reclaimed && !nr_retries--)
break;
if (nr_reclaims) {
if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max,
- GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP,
- NULL))
+ GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP))
nr_reclaims--;
continue;
}
return nbytes;
}
-enum {
- MEMORY_RECLAIM_NODES = 0,
- MEMORY_RECLAIM_NULL,
-};
-
-static const match_table_t if_tokens = {
- { MEMORY_RECLAIM_NODES, "nodes=%s" },
- { MEMORY_RECLAIM_NULL, NULL },
-};
-
static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
unsigned int nr_retries = MAX_RECLAIM_RETRIES;
unsigned long nr_to_reclaim, nr_reclaimed = 0;
- unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP |
- MEMCG_RECLAIM_PROACTIVE;
- char *old_buf, *start;
- substring_t args[MAX_OPT_ARGS];
- int token;
- char value[256];
- nodemask_t nodemask = NODE_MASK_ALL;
-
- buf = strstrip(buf);
-
- old_buf = buf;
- nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
- if (buf == old_buf)
- return -EINVAL;
+ unsigned int reclaim_options;
+ int err;
buf = strstrip(buf);
+ err = page_counter_memparse(buf, "", &nr_to_reclaim);
+ if (err)
+ return err;
- while ((start = strsep(&buf, " ")) != NULL) {
- if (!strlen(start))
- continue;
- token = match_token(start, if_tokens, args);
- match_strlcpy(value, args, sizeof(value));
- switch (token) {
- case MEMORY_RECLAIM_NODES:
- if (nodelist_parse(value, nodemask) < 0)
- return -EINVAL;
- break;
- default:
- return -EINVAL;
- }
- }
-
+ reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
while (nr_reclaimed < nr_to_reclaim) {
unsigned long reclaimed;
reclaimed = try_to_free_mem_cgroup_pages(memcg,
nr_to_reclaim - nr_reclaimed,
- GFP_KERNEL, reclaim_options,
- &nodemask);
+ GFP_KERNEL, reclaim_options);
if (!reclaimed && !nr_retries--)
return -EAGAIN;
return -EBUSY;
return -ENOENT;
} else if (is_pte_marker_entry(entry)) {
- /*
- * We're copying the pgtable should only because dst_vma has
- * uffd-wp enabled, do sanity check.
- */
- WARN_ON_ONCE(!userfaultfd_wp(dst_vma));
- set_pte_at(dst_mm, addr, dst_pte, pte);
+ if (is_swapin_error_entry(entry) || userfaultfd_wp(dst_vma))
+ set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
if (!userfaultfd_wp(dst_vma))
/*
* Be careful so that we will only recover a special uffd-wp pte into a
* none pte. Otherwise it means the pte could have changed, so retry.
+ *
+ * This should also cover the case where e.g. the pte changed
+ * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_SWAPIN_ERROR.
+ * So is_pte_marker() check is not enough to safely drop the pte.
*/
- if (is_pte_marker(*vmf->pte))
+ if (pte_same(vmf->orig_pte, *vmf->pte))
pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
if (unlikely(!page)) {
ret = VM_FAULT_OOM;
goto out_page;
+ } else if (unlikely(PTR_ERR(page) == -EHWPOISON)) {
+ ret = VM_FAULT_HWPOISON;
+ goto out_page;
}
folio = page_folio(page);
/* With MPOL_MF_MOVE, we migrate only unshared hugepage. */
if (flags & (MPOL_MF_MOVE_ALL) ||
- (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) {
+ (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 &&
+ !hugetlb_pmd_shared(pte))) {
if (isolate_hugetlb(page, qp->pagelist) &&
(flags & MPOL_MF_STRICT))
/*
pte = maybe_mkwrite(pte, vma);
else if (pte_swp_uffd_wp(*pvmw.pte))
pte = pte_mkuffd_wp(pte);
+ else
+ pte = pte_wrprotect(pte);
if (folio_test_anon(folio) && !is_readable_migration_entry(entry))
rmap_flags |= RMAP_EXCLUSIVE;
if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma))
return 1;
+ /* Do we need write faults for uffd-wp tracking? */
+ if (userfaultfd_wp(vma))
+ return 1;
+
/* Specialty mapping? */
if (vm_flags & VM_PFNMAP)
return 0;
* @start: The aligned start address to munmap.
* @end: The aligned end address to munmap.
* @uf: The userfaultfd list_head
- * @downgrade: Set to true to attempt a write downgrade of the mmap_sem
+ * @downgrade: Set to true to attempt a write downgrade of the mmap_lock
*
* If @downgrade is true, check return code for potential release of the lock.
*/
* @len: The length of the range to munmap
* @uf: The userfaultfd list_head
* @downgrade: set to true if the user wants to attempt to write_downgrade the
- * mmap_sem
+ * mmap_lock
*
* This function takes a @mas that is either pointing to the previous VMA or set
* to MA_START and sets it up to remove the mapping(s). The @len will be
newpte = pte_swp_mksoft_dirty(newpte);
if (pte_swp_uffd_wp(oldpte))
newpte = pte_swp_mkuffd_wp(newpte);
- } else if (pte_marker_entry_uffd_wp(entry)) {
+ } else if (is_pte_marker_entry(entry)) {
+ /*
+ * Ignore swapin errors unconditionally,
+ * because any access should sigbus anyway.
+ */
+ if (is_swapin_error_entry(entry))
+ continue;
/*
* If this is uffd-wp pte marker and we'd like
* to unprotect it, drop it; the next page
}
/*
- * Function vma_merge() is called on the extension we are adding to
- * the already existing vma, vma_merge() will merge this extension with
- * the already existing vma (expand operation itself) and possibly also
- * with the next vma if it becomes adjacent to the expanded vma and
- * otherwise compatible.
+ * Function vma_merge() is called on the extension we
+ * are adding to the already existing vma, vma_merge()
+ * will merge this extension with the already existing
+ * vma (expand operation itself) and possibly also with
+ * the next vma if it becomes adjacent to the expanded
+ * vma and otherwise compatible.
+ *
+ * However, vma_merge() can currently fail due to
+ * is_mergeable_vma() check for vm_ops->close (see the
+ * comment there). Yet this should not prevent vma
+ * expanding, so perform a simple expand for such vma.
+ * Ideally the check for close op should be only done
+ * when a vma would be actually removed due to a merge.
*/
- vma = vma_merge(mm, vma, extension_start, extension_end,
+ if (!vma->vm_ops || !vma->vm_ops->close) {
+ vma = vma_merge(mm, vma, extension_start, extension_end,
vma->vm_flags, vma->anon_vma, vma->vm_file,
extension_pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx, anon_vma_name(vma));
+ } else if (vma_adjust(vma, vma->vm_start, addr + new_len,
+ vma->vm_pgoff, NULL)) {
+ vma = NULL;
+ }
if (!vma) {
vm_unacct_memory(pages);
ret = -ENOMEM;
static void setup_vma_to_mm(struct vm_area_struct *vma, struct mm_struct *mm)
{
- mm->map_count++;
vma->vm_mm = mm;
/* add the VMA to the mapping */
BUG_ON(!vma->vm_region);
setup_vma_to_mm(vma, mm);
+ mm->map_count++;
/* add the VMA to the tree */
vma_mas_store(vma, mas);
error_just_free:
up_write(&nommu_region_sem);
error:
+ mas_destroy(&mas);
if (region->vm_file)
fput(region->vm_file);
kmem_cache_free(vm_region_jar, region);
sharing_violation:
up_write(&nommu_region_sem);
- mas_destroy(&mas);
pr_warn("Attempt to share mismatched mappings\n");
ret = -EINVAL;
goto error;
if (vma->vm_file)
return -ENOMEM;
+ mm = vma->vm_mm;
if (mm->map_count >= sysctl_max_map_count)
return -ENOMEM;
mas_set_range(&mas, vma->vm_start, vma->vm_end - 1);
mas_store(&mas, vma);
vma_mas_store(new, &mas);
+ mm->map_count++;
return 0;
err_mas_preallocate:
erase_whole_vma:
if (delete_vma_from_mm(vma))
ret = -ENOMEM;
- delete_vma(mm, vma);
+ else
+ delete_vma(mm, vma);
return ret;
}
*/
void __free_pages(struct page *page, unsigned int order)
{
+ /* get PageHead before we drop reference */
+ int head = PageHead(page);
+
if (put_page_testzero(page))
free_the_page(page, order);
- else if (!PageHead(page))
+ else if (!head)
while (order-- > 0)
free_the_page(page + (1 << order), order);
}
if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
return false;
- if (shmem_huge_force)
- return true;
- if (shmem_huge == SHMEM_HUGE_FORCE)
- return true;
if (shmem_huge == SHMEM_HUGE_DENY)
return false;
+ if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE)
+ return true;
switch (SHMEM_SB(inode->i_sb)->huge) {
case SHMEM_HUGE_ALWAYS:
}
EXPORT_SYMBOL(shrinker_debugfs_rename);
-void shrinker_debugfs_remove(struct shrinker *shrinker)
+struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker)
{
+ struct dentry *entry = shrinker->debugfs_entry;
+
lockdep_assert_held(&shrinker_rwsem);
kfree_const(shrinker->name);
shrinker->name = NULL;
- if (!shrinker->debugfs_entry)
- return;
+ if (entry) {
+ ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id);
+ shrinker->debugfs_entry = NULL;
+ }
- debugfs_remove_recursive(shrinker->debugfs_entry);
- ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id);
+ return entry;
}
static int __init shrinker_debugfs_init(void)
raw_spin_unlock_irq(&n->list_lock);
slab_destroy(cache, slab);
nr_freed++;
+
+ cond_resched();
}
out:
return nr_freed;
goto check_out;
pr_debug("scan_swap_map of si %d failed to find offset\n",
si->type);
+ cond_resched();
spin_lock(&swap_avail_lock);
nextsi:
struct page *swapcache;
spinlock_t *ptl;
pte_t *pte, new_pte;
+ bool hwposioned = false;
int ret = 1;
swapcache = page;
page = ksm_might_need_to_copy(page, vma, addr);
if (unlikely(!page))
return -ENOMEM;
+ else if (unlikely(PTR_ERR(page) == -EHWPOISON))
+ hwposioned = true;
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
goto out;
}
- if (unlikely(!PageUptodate(page))) {
- pte_t pteval;
+ if (unlikely(hwposioned || !PageUptodate(page))) {
+ swp_entry_t swp_entry;
dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
- pteval = swp_entry_to_pte(make_swapin_error_entry());
- set_pte_at(vma->vm_mm, addr, pte, pteval);
- swap_free(entry);
+ if (hwposioned) {
+ swp_entry = make_hwpoison_entry(swapcache);
+ page = swapcache;
+ } else {
+ swp_entry = make_swapin_error_entry();
+ }
+ new_pte = swp_entry_to_pte(swp_entry);
ret = 0;
- goto out;
+ goto setpte;
}
/* See do_swap_page() */
new_pte = pte_mksoft_dirty(new_pte);
if (pte_swp_uffd_wp(*pte))
new_pte = pte_mkuffd_wp(new_pte);
+setpte:
set_pte_at(vma->vm_mm, addr, pte, new_pte);
swap_free(entry);
out:
*/
void unregister_shrinker(struct shrinker *shrinker)
{
+ struct dentry *debugfs_entry;
+
if (!(shrinker->flags & SHRINKER_REGISTERED))
return;
shrinker->flags &= ~SHRINKER_REGISTERED;
if (shrinker->flags & SHRINKER_MEMCG_AWARE)
unregister_memcg_shrinker(shrinker);
- shrinker_debugfs_remove(shrinker);
+ debugfs_entry = shrinker_debugfs_remove(shrinker);
up_write(&shrinker_rwsem);
+ debugfs_remove_recursive(debugfs_entry);
+
kfree(shrinker->nr_deferred);
shrinker->nr_deferred = NULL;
}
if (mem_cgroup_disabled())
return;
+ /* migration can happen before addition */
+ if (!mm->lru_gen.memcg)
+ return;
+
rcu_read_lock();
memcg = mem_cgroup_from_task(task);
rcu_read_unlock();
if (memcg == mm->lru_gen.memcg)
return;
- VM_WARN_ON_ONCE(!mm->lru_gen.memcg);
VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list));
lru_gen_del_mm(mm);
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
- unsigned int reclaim_options,
- nodemask_t *nodemask)
+ unsigned int reclaim_options)
{
unsigned long nr_reclaimed;
unsigned int noreclaim_flag;
.may_unmap = 1,
.may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
.proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
- .nodemask = nodemask,
};
/*
* Traverse the ZONELIST_FALLBACK zonelist of the current node to put
* have room for two bit at least.
*/
#define OBJ_ALLOCATED_TAG 1
-#define OBJ_TAG_BITS 1
+
+#ifdef CONFIG_ZPOOL
+/*
+ * The second least-significant bit in the object's header identifies if the
+ * value stored at the header is a deferred handle from the last reclaim
+ * attempt.
+ *
+ * As noted above, this is valid because we have room for two bits.
+ */
+#define OBJ_DEFERRED_HANDLE_TAG 2
+#define OBJ_TAG_BITS 2
+#define OBJ_TAG_MASK (OBJ_ALLOCATED_TAG | OBJ_DEFERRED_HANDLE_TAG)
+#else
+#define OBJ_TAG_BITS 1
+#define OBJ_TAG_MASK OBJ_ALLOCATED_TAG
+#endif /* CONFIG_ZPOOL */
+
#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS)
#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
* Handle of allocated object.
*/
unsigned long handle;
+#ifdef CONFIG_ZPOOL
+ /*
+ * Deferred handle of a reclaimed object.
+ */
+ unsigned long deferred_handle;
+#endif
};
};
/* links the zspage to the lru list in the pool */
struct list_head lru;
bool under_reclaim;
- /* list of unfreed handles whose objects have been reclaimed */
- unsigned long *deferred_handles;
#endif
struct zs_pool *pool;
return *(unsigned long *)handle;
}
-static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle)
+static bool obj_tagged(struct page *page, void *obj, unsigned long *phandle,
+ int tag)
{
unsigned long handle;
struct zspage *zspage = get_zspage(page);
} else
handle = *(unsigned long *)obj;
- if (!(handle & OBJ_ALLOCATED_TAG))
+ if (!(handle & tag))
return false;
- *phandle = handle & ~OBJ_ALLOCATED_TAG;
+ /* Clear all tags before returning the handle */
+ *phandle = handle & ~OBJ_TAG_MASK;
return true;
}
+static inline bool obj_allocated(struct page *page, void *obj, unsigned long *phandle)
+{
+ return obj_tagged(page, obj, phandle, OBJ_ALLOCATED_TAG);
+}
+
+#ifdef CONFIG_ZPOOL
+static bool obj_stores_deferred_handle(struct page *page, void *obj,
+ unsigned long *phandle)
+{
+ return obj_tagged(page, obj, phandle, OBJ_DEFERRED_HANDLE_TAG);
+}
+#endif
+
static void reset_page(struct page *page)
{
__ClearPageMovable(page);
}
#ifdef CONFIG_ZPOOL
+static unsigned long find_deferred_handle_obj(struct size_class *class,
+ struct page *page, int *obj_idx);
+
/*
* Free all the deferred handles whose objects are freed in zs_free.
*/
-static void free_handles(struct zs_pool *pool, struct zspage *zspage)
+static void free_handles(struct zs_pool *pool, struct size_class *class,
+ struct zspage *zspage)
{
- unsigned long handle = (unsigned long)zspage->deferred_handles;
+ int obj_idx = 0;
+ struct page *page = get_first_page(zspage);
+ unsigned long handle;
- while (handle) {
- unsigned long nxt_handle = handle_to_obj(handle);
+ while (1) {
+ handle = find_deferred_handle_obj(class, page, &obj_idx);
+ if (!handle) {
+ page = get_next_page(page);
+ if (!page)
+ break;
+ obj_idx = 0;
+ continue;
+ }
cache_free_handle(pool, handle);
- handle = nxt_handle;
+ obj_idx++;
}
}
#else
-static inline void free_handles(struct zs_pool *pool, struct zspage *zspage) {}
+static inline void free_handles(struct zs_pool *pool, struct size_class *class,
+ struct zspage *zspage) {}
#endif
static void __free_zspage(struct zs_pool *pool, struct size_class *class,
VM_BUG_ON(fg != ZS_EMPTY);
/* Free all deferred handles from zs_free */
- free_handles(pool, zspage);
+ free_handles(pool, class, zspage);
next = page = get_first_page(zspage);
do {
#ifdef CONFIG_ZPOOL
INIT_LIST_HEAD(&zspage->lru);
zspage->under_reclaim = false;
- zspage->deferred_handles = NULL;
#endif
set_freeobj(zspage, 0);
}
EXPORT_SYMBOL_GPL(zs_malloc);
-static void obj_free(int class_size, unsigned long obj)
+static void obj_free(int class_size, unsigned long obj, unsigned long *handle)
{
struct link_free *link;
struct zspage *zspage;
zspage = get_zspage(f_page);
vaddr = kmap_atomic(f_page);
-
- /* Insert this object in containing zspage's freelist */
link = (struct link_free *)(vaddr + f_offset);
- if (likely(!ZsHugePage(zspage)))
- link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
- else
- f_page->index = 0;
+
+ if (handle) {
+#ifdef CONFIG_ZPOOL
+ /* Stores the (deferred) handle in the object's header */
+ *handle |= OBJ_DEFERRED_HANDLE_TAG;
+ *handle &= ~OBJ_ALLOCATED_TAG;
+
+ if (likely(!ZsHugePage(zspage)))
+ link->deferred_handle = *handle;
+ else
+ f_page->index = *handle;
+#endif
+ } else {
+ /* Insert this object in containing zspage's freelist */
+ if (likely(!ZsHugePage(zspage)))
+ link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
+ else
+ f_page->index = 0;
+ set_freeobj(zspage, f_objidx);
+ }
+
kunmap_atomic(vaddr);
- set_freeobj(zspage, f_objidx);
mod_zspage_inuse(zspage, -1);
}
zspage = get_zspage(f_page);
class = zspage_class(pool, zspage);
- obj_free(class->size, obj);
class_stat_dec(class, OBJ_USED, 1);
#ifdef CONFIG_ZPOOL
* Reclaim needs the handles during writeback. It'll free
* them along with the zspage when it's done with them.
*
- * Record current deferred handle at the memory location
- * whose address is given by handle.
+ * Record current deferred handle in the object's header.
*/
- record_obj(handle, (unsigned long)zspage->deferred_handles);
- zspage->deferred_handles = (unsigned long *)handle;
+ obj_free(class->size, obj, &handle);
spin_unlock(&pool->lock);
return;
}
#endif
+ obj_free(class->size, obj, NULL);
+
fullness = fix_fullness_group(class, zspage);
if (fullness == ZS_EMPTY)
free_zspage(pool, class, zspage);
}
/*
- * Find alloced object in zspage from index object and
+ * Find object with a certain tag in zspage from index object and
* return handle.
*/
-static unsigned long find_alloced_obj(struct size_class *class,
- struct page *page, int *obj_idx)
+static unsigned long find_tagged_obj(struct size_class *class,
+ struct page *page, int *obj_idx, int tag)
{
unsigned int offset;
int index = *obj_idx;
offset += class->size * index;
while (offset < PAGE_SIZE) {
- if (obj_allocated(page, addr + offset, &handle))
+ if (obj_tagged(page, addr + offset, &handle, tag))
break;
offset += class->size;
return handle;
}
+/*
+ * Find alloced object in zspage from index object and
+ * return handle.
+ */
+static unsigned long find_alloced_obj(struct size_class *class,
+ struct page *page, int *obj_idx)
+{
+ return find_tagged_obj(class, page, obj_idx, OBJ_ALLOCATED_TAG);
+}
+
+#ifdef CONFIG_ZPOOL
+/*
+ * Find object storing a deferred handle in header in zspage from index object
+ * and return handle.
+ */
+static unsigned long find_deferred_handle_obj(struct size_class *class,
+ struct page *page, int *obj_idx)
+{
+ return find_tagged_obj(class, page, obj_idx, OBJ_DEFERRED_HANDLE_TAG);
+}
+#endif
+
struct zs_compact_control {
/* Source spage for migration which could be a subpage of zspage */
struct page *s_page;
zs_object_copy(class, free_obj, used_obj);
obj_idx++;
record_obj(handle, free_obj);
- obj_free(class->size, used_obj);
+ obj_free(class->size, used_obj, NULL);
}
/* Remember last position in this iteration */
EXPORT_SYMBOL_GPL(zs_destroy_pool);
#ifdef CONFIG_ZPOOL
+static void restore_freelist(struct zs_pool *pool, struct size_class *class,
+ struct zspage *zspage)
+{
+ unsigned int obj_idx = 0;
+ unsigned long handle, off = 0; /* off is within-page offset */
+ struct page *page = get_first_page(zspage);
+ struct link_free *prev_free = NULL;
+ void *prev_page_vaddr = NULL;
+
+ /* in case no free object found */
+ set_freeobj(zspage, (unsigned int)(-1UL));
+
+ while (page) {
+ void *vaddr = kmap_atomic(page);
+ struct page *next_page;
+
+ while (off < PAGE_SIZE) {
+ void *obj_addr = vaddr + off;
+
+ /* skip allocated object */
+ if (obj_allocated(page, obj_addr, &handle)) {
+ obj_idx++;
+ off += class->size;
+ continue;
+ }
+
+ /* free deferred handle from reclaim attempt */
+ if (obj_stores_deferred_handle(page, obj_addr, &handle))
+ cache_free_handle(pool, handle);
+
+ if (prev_free)
+ prev_free->next = obj_idx << OBJ_TAG_BITS;
+ else /* first free object found */
+ set_freeobj(zspage, obj_idx);
+
+ prev_free = (struct link_free *)vaddr + off / sizeof(*prev_free);
+ /* if last free object in a previous page, need to unmap */
+ if (prev_page_vaddr) {
+ kunmap_atomic(prev_page_vaddr);
+ prev_page_vaddr = NULL;
+ }
+
+ obj_idx++;
+ off += class->size;
+ }
+
+ /*
+ * Handle the last (full or partial) object on this page.
+ */
+ next_page = get_next_page(page);
+ if (next_page) {
+ if (!prev_free || prev_page_vaddr) {
+ /*
+ * There is no free object in this page, so we can safely
+ * unmap it.
+ */
+ kunmap_atomic(vaddr);
+ } else {
+ /* update prev_page_vaddr since prev_free is on this page */
+ prev_page_vaddr = vaddr;
+ }
+ } else { /* this is the last page */
+ if (prev_free) {
+ /*
+ * Reset OBJ_TAG_BITS bit to last link to tell
+ * whether it's allocated object or not.
+ */
+ prev_free->next = -1UL << OBJ_TAG_BITS;
+ }
+
+ /* unmap previous page (if not done yet) */
+ if (prev_page_vaddr) {
+ kunmap_atomic(prev_page_vaddr);
+ prev_page_vaddr = NULL;
+ }
+
+ kunmap_atomic(vaddr);
+ }
+
+ page = next_page;
+ off %= PAGE_SIZE;
+ }
+}
+
static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries)
{
int i, obj_idx, ret = 0;
return 0;
}
+ /*
+ * Eviction fails on one of the handles, so we need to restore zspage.
+ * We need to rebuild its freelist (and free stored deferred handles),
+ * put it back to the correct size class, and add it to the LRU list.
+ */
+ restore_freelist(pool, class, zspage);
putback_zspage(class, zspage);
list_add(&zspage->lru, &pool->lru);
unlock_zspage(zspage);
kfree(priv);
}
-static int xen_9pfs_front_remove(struct xenbus_device *dev)
+static void xen_9pfs_front_remove(struct xenbus_device *dev)
{
struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev);
dev_set_drvdata(&dev->dev, NULL);
xen_9pfs_front_free(priv);
- return 0;
}
static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev,
static int hci_le_terminate_big(struct hci_dev *hdev, u8 big, u8 bis)
{
struct iso_list_data *d;
+ int ret;
bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", big, bis);
d->big = big;
d->bis = bis;
- return hci_cmd_sync_queue(hdev, terminate_big_sync, d,
- terminate_big_destroy);
+ ret = hci_cmd_sync_queue(hdev, terminate_big_sync, d,
+ terminate_big_destroy);
+ if (ret)
+ kfree(d);
+
+ return ret;
}
static int big_terminate_sync(struct hci_dev *hdev, void *data)
static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle)
{
struct iso_list_data *d;
+ int ret;
bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, sync_handle);
d->big = big;
d->sync_handle = sync_handle;
- return hci_cmd_sync_queue(hdev, big_terminate_sync, d,
- terminate_big_destroy);
+ ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d,
+ terminate_big_destroy);
+ if (ret)
+ kfree(d);
+
+ return ret;
}
/* Cleanup BIS connection
conn->handle, conn->link);
/* Create CIS if LE is already connected */
- if (conn->link && conn->link->state == BT_CONNECTED)
+ if (conn->link && conn->link->state == BT_CONNECTED) {
+ rcu_read_unlock();
hci_le_create_cis(conn->link);
+ rcu_read_lock();
+ }
if (i == rp->num_handles)
break;
static int hci_le_read_buffer_size_sync(struct hci_dev *hdev)
{
/* Use Read LE Buffer Size V2 if supported */
- if (hdev->commands[41] & 0x20)
+ if (iso_capable(hdev) && hdev->commands[41] & 0x20)
return __hci_cmd_sync_status(hdev,
HCI_OP_LE_READ_BUFFER_SIZE_V2,
0, NULL, HCI_CMD_TIMEOUT);
/* LE Controller init stage 2 command sequence */
static const struct hci_init_stage le_init2[] = {
- /* HCI_OP_LE_READ_BUFFER_SIZE */
- HCI_INIT(hci_le_read_buffer_size_sync),
/* HCI_OP_LE_READ_LOCAL_FEATURES */
HCI_INIT(hci_le_read_local_features_sync),
+ /* HCI_OP_LE_READ_BUFFER_SIZE */
+ HCI_INIT(hci_le_read_buffer_size_sync),
/* HCI_OP_LE_READ_SUPPORTED_STATES */
HCI_INIT(hci_le_read_supported_states_sync),
{}
static int _update_adv_data_sync(struct hci_dev *hdev, void *data)
{
- u8 instance = *(u8 *)data;
-
- kfree(data);
+ u8 instance = PTR_ERR(data);
return hci_update_adv_data_sync(hdev, instance);
}
int hci_update_adv_data(struct hci_dev *hdev, u8 instance)
{
- u8 *inst_ptr = kmalloc(1, GFP_KERNEL);
-
- if (!inst_ptr)
- return -ENOMEM;
-
- *inst_ptr = instance;
- return hci_cmd_sync_queue(hdev, _update_adv_data_sync, inst_ptr, NULL);
+ return hci_cmd_sync_queue(hdev, _update_adv_data_sync,
+ ERR_PTR(instance), NULL);
}
hci_dev_unlock(hdev);
hci_dev_put(hdev);
+ err = iso_chan_add(conn, sk, NULL);
+ if (err)
+ return err;
+
lock_sock(sk);
/* Update source addr of the socket */
bacpy(&iso_pi(sk)->src, &hcon->src);
- err = iso_chan_add(conn, sk, NULL);
- if (err)
- goto release;
-
if (hcon->state == BT_CONNECTED) {
iso_sock_clear_timer(sk);
sk->sk_state = BT_CONNECTED;
iso_sock_set_timer(sk, sk->sk_sndtimeo);
}
-release:
release_sock(sk);
return err;
hci_dev_unlock(hdev);
hci_dev_put(hdev);
+ err = iso_chan_add(conn, sk, NULL);
+ if (err)
+ return err;
+
lock_sock(sk);
/* Update source addr of the socket */
bacpy(&iso_pi(sk)->src, &hcon->src);
- err = iso_chan_add(conn, sk, NULL);
- if (err)
- goto release;
-
if (hcon->state == BT_CONNECTED) {
iso_sock_clear_timer(sk);
sk->sk_state = BT_CONNECTED;
iso_sock_set_timer(sk, sk->sk_sndtimeo);
}
-release:
release_sock(sk);
return err;
if (!hdev)
return -EHOSTUNREACH;
- hci_dev_lock(hdev);
-
err = hci_pa_create_sync(hdev, &iso_pi(sk)->dst,
le_addr_type(iso_pi(sk)->dst_type),
iso_pi(sk)->bc_sid);
- hci_dev_unlock(hdev);
hci_dev_put(hdev);
return err;
struct sock *parent;
struct sock *sk = conn->sk;
struct hci_ev_le_big_sync_estabilished *ev;
+ struct hci_conn *hcon;
BT_DBG("conn %p", conn);
if (sk) {
iso_sock_ready(conn->sk);
} else {
- iso_conn_lock(conn);
-
- if (!conn->hcon) {
- iso_conn_unlock(conn);
+ hcon = conn->hcon;
+ if (!hcon)
return;
- }
- ev = hci_recv_event_data(conn->hcon->hdev,
+ ev = hci_recv_event_data(hcon->hdev,
HCI_EVT_LE_BIG_SYNC_ESTABILISHED);
if (ev)
- parent = iso_get_sock_listen(&conn->hcon->src,
- &conn->hcon->dst,
+ parent = iso_get_sock_listen(&hcon->src,
+ &hcon->dst,
iso_match_big, ev);
else
- parent = iso_get_sock_listen(&conn->hcon->src,
+ parent = iso_get_sock_listen(&hcon->src,
BDADDR_ANY, NULL, NULL);
- if (!parent) {
- iso_conn_unlock(conn);
+ if (!parent)
return;
- }
lock_sock(parent);
BTPROTO_ISO, GFP_ATOMIC, 0);
if (!sk) {
release_sock(parent);
- iso_conn_unlock(conn);
return;
}
iso_sock_init(sk, parent);
- bacpy(&iso_pi(sk)->src, &conn->hcon->src);
- iso_pi(sk)->src_type = conn->hcon->src_type;
+ bacpy(&iso_pi(sk)->src, &hcon->src);
+ iso_pi(sk)->src_type = hcon->src_type;
/* If hcon has no destination address (BDADDR_ANY) it means it
* was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED so we need to
* initialize using the parent socket destination address.
*/
- if (!bacmp(&conn->hcon->dst, BDADDR_ANY)) {
- bacpy(&conn->hcon->dst, &iso_pi(parent)->dst);
- conn->hcon->dst_type = iso_pi(parent)->dst_type;
- conn->hcon->sync_handle = iso_pi(parent)->sync_handle;
+ if (!bacmp(&hcon->dst, BDADDR_ANY)) {
+ bacpy(&hcon->dst, &iso_pi(parent)->dst);
+ hcon->dst_type = iso_pi(parent)->dst_type;
+ hcon->sync_handle = iso_pi(parent)->sync_handle;
}
- bacpy(&iso_pi(sk)->dst, &conn->hcon->dst);
- iso_pi(sk)->dst_type = conn->hcon->dst_type;
+ bacpy(&iso_pi(sk)->dst, &hcon->dst);
+ iso_pi(sk)->dst_type = hcon->dst_type;
- hci_conn_hold(conn->hcon);
- __iso_chan_add(conn, sk, parent);
+ hci_conn_hold(hcon);
+ iso_chan_add(conn, sk, parent);
if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags))
sk->sk_state = BT_CONNECT2;
parent->sk_data_ready(parent);
release_sock(parent);
-
- iso_conn_unlock(conn);
}
}
struct sock *sk;
u8 handle;
u8 instance;
- u8 param[sizeof(struct mgmt_cp_mesh_send) + 29];
+ u8 param[sizeof(struct mgmt_cp_mesh_send) + 31];
};
struct mgmt_pending_cmd {
addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ sock_hold(sk);
lock_sock(sk);
if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
d->sec_level = rfcomm_pi(sk)->sec_level;
d->role_switch = rfcomm_pi(sk)->role_switch;
+ /* Drop sock lock to avoid potential deadlock with the RFCOMM lock */
+ release_sock(sk);
err = rfcomm_dlc_open(d, &rfcomm_pi(sk)->src, &sa->rc_bdaddr,
sa->rc_channel);
- if (!err)
+ lock_sock(sk);
+ if (!err && !sock_flag(sk, SOCK_ZAPPED))
err = bt_sock_wait_state(sk, BT_CONNECTED,
sock_sndtimeo(sk, flags & O_NONBLOCK));
done:
release_sock(sk);
+ sock_put(sk);
return err;
}
if (nf_bridge && !nf_bridge->in_prerouting &&
!netif_is_l3_master(skb->dev) &&
!netif_is_l3_slave(skb->dev)) {
+ nf_bridge_info_free(skb);
state->okfn(state->net, state->sk, skb);
return NF_STOLEN;
}
return;
}
sk_stream_kill_queues(&cf_sk->sk);
+ WARN_ON_ONCE(sk->sk_forward_alloc);
caif_free_client(&cf_sk->layer);
}
default:
pr_warn("Request setup of bad link type = %d\n",
param->linktype);
+ cfpkt_destroy(pkt);
return -EINVAL;
}
req = kzalloc(sizeof(*req), GFP_KERNEL);
- if (!req)
+ if (!req) {
+ cfpkt_destroy(pkt);
return -ENOMEM;
+ }
+
req->client_layer = user_layer;
req->cmd = CFCTRL_CMD_LINK_SETUP;
req->param = *param;
canid_t rxid;
ktime_t tx_gap;
ktime_t lastrxcf_tstamp;
- struct hrtimer rxtimer, txtimer;
+ struct hrtimer rxtimer, txtimer, txfrtimer;
struct can_isotp_options opt;
struct can_isotp_fc_options rxfc, txfc;
struct can_isotp_ll_options ll;
}
/* start timer to send next consecutive frame with correct delay */
- hrtimer_start(&so->txtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT);
+ hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT);
}
static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer)
struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
txtimer);
struct sock *sk = &so->sk;
- enum hrtimer_restart restart = HRTIMER_NORESTART;
- switch (so->tx.state) {
- case ISOTP_SENDING:
-
- /* cfecho should be consumed by isotp_rcv_echo() here */
- if (!so->cfecho) {
- /* start timeout for unlikely lost echo skb */
- hrtimer_set_expires(&so->txtimer,
- ktime_add(ktime_get(),
- ktime_set(ISOTP_ECHO_TIMEOUT, 0)));
- restart = HRTIMER_RESTART;
+ /* don't handle timeouts in IDLE state */
+ if (so->tx.state == ISOTP_IDLE)
+ return HRTIMER_NORESTART;
- /* push out the next consecutive frame */
- isotp_send_cframe(so);
- break;
- }
+ /* we did not get any flow control or echo frame in time */
- /* cfecho has not been cleared in isotp_rcv_echo() */
- pr_notice_once("can-isotp: cfecho %08X timeout\n", so->cfecho);
- fallthrough;
+ /* report 'communication error on send' */
+ sk->sk_err = ECOMM;
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk_error_report(sk);
- case ISOTP_WAIT_FC:
- case ISOTP_WAIT_FIRST_FC:
+ /* reset tx state */
+ so->tx.state = ISOTP_IDLE;
+ wake_up_interruptible(&so->wait);
- /* we did not get any flow control frame in time */
+ return HRTIMER_NORESTART;
+}
- /* report 'communication error on send' */
- sk->sk_err = ECOMM;
- if (!sock_flag(sk, SOCK_DEAD))
- sk_error_report(sk);
+static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer)
+{
+ struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+ txfrtimer);
- /* reset tx state */
- so->tx.state = ISOTP_IDLE;
- wake_up_interruptible(&so->wait);
- break;
+ /* start echo timeout handling and cover below protocol error */
+ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0),
+ HRTIMER_MODE_REL_SOFT);
- default:
- WARN_ONCE(1, "can-isotp: tx timer state %08X cfecho %08X\n",
- so->tx.state, so->cfecho);
- }
+ /* cfecho should be consumed by isotp_rcv_echo() here */
+ if (so->tx.state == ISOTP_SENDING && !so->cfecho)
+ isotp_send_cframe(so);
- return restart;
+ return HRTIMER_NORESTART;
}
static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
/* wait for complete transmission of current pdu */
wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+ /* force state machines to be idle also when a signal occurred */
+ so->tx.state = ISOTP_IDLE;
+ so->rx.state = ISOTP_IDLE;
+
spin_lock(&isotp_notifier_lock);
while (isotp_busy_notifier == so) {
spin_unlock(&isotp_notifier_lock);
}
}
+ hrtimer_cancel(&so->txfrtimer);
hrtimer_cancel(&so->txtimer);
hrtimer_cancel(&so->rxtimer);
so->rxtimer.function = isotp_rx_timer_handler;
hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
so->txtimer.function = isotp_tx_timer_handler;
+ hrtimer_init(&so->txfrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+ so->txfrtimer.function = isotp_txfr_timer_handler;
init_waitqueue_head(&so->wait);
spin_lock_init(&so->rx_lock);
* leaving this function.
*/
ecu = j1939_ecu_get_by_name_locked(priv, name);
+
+ if (ecu && ecu->addr == skcb->addr.sa) {
+ /* The ISO 11783-5 standard, in "4.5.2 - Address claim
+ * requirements", states:
+ * d) No CF shall begin, or resume, transmission on the
+ * network until 250 ms after it has successfully claimed
+ * an address except when responding to a request for
+ * address-claimed.
+ *
+ * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim
+ * prioritization" show that the CF begins the transmission
+ * after 250 ms from the first AC (address-claimed) message
+ * even if it sends another AC message during that time window
+ * to resolve the address contention with another CF.
+ *
+ * As stated in "4.4.2.3 - Address-claimed message":
+ * In order to successfully claim an address, the CF sending
+ * an address claimed message shall not receive a contending
+ * claim from another CF for at least 250 ms.
+ *
+ * As stated in "4.4.3.2 - NAME management (NM) message":
+ * 1) A commanding CF can
+ * d) request that a CF with a specified NAME transmit
+ * the address-claimed message with its current NAME.
+ * 2) A target CF shall
+ * d) send an address-claimed message in response to a
+ * request for a matching NAME
+ *
+ * Taking the above arguments into account, the 250 ms wait is
+ * requested only during network initialization.
+ *
+ * Do not restart the timer on AC message if both the NAME and
+ * the address match and so if the address has already been
+ * claimed (timer has expired) or the AC message has been sent
+ * to resolve the contention with another CF (timer is still
+ * running).
+ */
+ goto out_ecu_put;
+ }
+
if (!ecu && j1939_address_is_unicast(skcb->addr.sa))
ecu = j1939_ecu_create_locked(priv, name);
bool active;
j1939_session_list_lock(priv);
- /* This function should be called with a session ref-count of at
- * least 2.
- */
- WARN_ON_ONCE(kref_read(&session->kref) < 2);
active = j1939_session_deactivate_locked(session);
j1939_session_list_unlock(priv);
return;
/* make sure to not pass oversized frames to the socket */
- if ((can_is_canfd_skb(oskb) && !ro->fd_frames && !ro->xl_frames) ||
- (can_is_canxl_skb(oskb) && !ro->xl_frames))
+ if ((!ro->fd_frames && can_is_canfd_skb(oskb)) ||
+ (!ro->xl_frames && can_is_canxl_skb(oskb)))
return;
/* eliminate multiple filter matches for the same skb */
if (copy_from_sockptr(&ro->fd_frames, optval, optlen))
return -EFAULT;
+ /* Enabling CAN XL includes CAN FD */
+ if (ro->xl_frames && !ro->fd_frames) {
+ ro->fd_frames = ro->xl_frames;
+ return -EINVAL;
+ }
break;
case CAN_RAW_XL_FRAMES:
if (copy_from_sockptr(&ro->xl_frames, optval, optlen))
return -EFAULT;
+ /* Enabling CAN XL includes CAN FD */
+ if (ro->xl_frames)
+ ro->fd_frames = ro->xl_frames;
break;
case CAN_RAW_JOIN_FILTERS:
return 0;
}
+static bool raw_bad_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu)
+{
+ /* Classical CAN -> no checks for flags and device capabilities */
+ if (can_is_can_skb(skb))
+ return false;
+
+ /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */
+ if (ro->fd_frames && can_is_canfd_skb(skb) &&
+ (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu)))
+ return false;
+
+ /* CAN XL -> needs to be enabled and a CAN XL device */
+ if (ro->xl_frames && can_is_canxl_skb(skb) &&
+ can_is_canxl_dev_mtu(mtu))
+ return false;
+
+ return true;
+}
+
static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
struct sock *sk = sock->sk;
goto free_skb;
err = -EINVAL;
- if (ro->xl_frames && can_is_canxl_dev_mtu(dev->mtu)) {
- /* CAN XL, CAN FD and Classical CAN */
- if (!can_is_canxl_skb(skb) && !can_is_canfd_skb(skb) &&
- !can_is_can_skb(skb))
- goto free_skb;
- } else if (ro->fd_frames && dev->mtu == CANFD_MTU) {
- /* CAN FD and Classical CAN */
- if (!can_is_canfd_skb(skb) && !can_is_can_skb(skb))
- goto free_skb;
- } else {
- /* Classical CAN */
- if (!can_is_can_skb(skb))
- goto free_skb;
- }
+ if (raw_bad_txframe(ro, skb, dev->mtu))
+ goto free_skb;
sockcm_init(&sockc, sk);
if (msg->msg_controllen) {
__register_netdevice_notifier_net(dst_net, nb, true);
}
-void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net,
- struct notifier_block *nb)
-{
- rtnl_lock();
- __move_netdevice_notifier_net(src_net, dst_net, nb);
- rtnl_unlock();
-}
-
int register_netdevice_notifier_dev_net(struct net_device *dev,
struct notifier_block *nb,
struct netdev_net_notifier *nn)
BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64));
for (i = 0; i < n; i++)
- dst[i] = atomic_long_read(&src[i]);
+ dst[i] = (unsigned long)atomic_long_read(&src[i]);
/* zero out counters that only exist in rtnl_link_stats64 */
memset((char *)stats64 + n * sizeof(u64), 0,
sizeof(*stats64) - n * sizeof(u64));
if (err)
return err;
- if (dest_net && !net_eq(dest_net, curr_net)) {
- move_netdevice_notifier_net(curr_net, dest_net,
- &devlink->netdevice_nb);
+ if (dest_net && !net_eq(dest_net, curr_net))
write_pnet(&devlink->_net, dest_net);
- }
err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack);
devlink_reload_failed_set(devlink, !!err);
goto err_xa_alloc;
devlink->netdevice_nb.notifier_call = devlink_netdevice_event;
- ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb);
+ ret = register_netdevice_notifier(&devlink->netdevice_nb);
if (ret)
goto err_register_netdevice_notifier;
xa_destroy(&devlink->snapshot_ids);
xa_destroy(&devlink->ports);
- WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink),
- &devlink->netdevice_nb));
+ WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb));
xa_erase(&devlinks, devlink->index);
break;
case NETDEV_REGISTER:
case NETDEV_CHANGENAME:
+ if (devlink_net(devlink) != dev_net(netdev))
+ return NOTIFY_OK;
/* Set the netdev on top of previously set type. Note this
* event happens also during net namespace change so here
* we take into account netdev pointer appearing in this
netdev);
break;
case NETDEV_UNREGISTER:
+ if (devlink_net(devlink) != dev_net(netdev))
+ return NOTIFY_OK;
/* Clear netdev pointer, but not the type. This event happens
* also during net namespace change so we need to clear
* pointer to netdev that is going to another net namespace.
static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
{
+ void *old_data;
+
/* skb_ensure_writable() is not needed here, as we're
* already working on an uncloned skb.
*/
if (unlikely(!pskb_may_pull(skb, off + len)))
return -ENOMEM;
- skb_postpull_rcsum(skb, skb->data + off, len);
- memmove(skb->data + len, skb->data, off);
+ old_data = skb->data;
__skb_pull(skb, len);
+ skb_postpull_rcsum(skb, old_data + off, len);
+ memmove(skb->data, old_data, off);
return 0;
}
struct sk_buff *lp;
int segs;
+ /* Do not splice page pool based packets w/ non-page pool
+ * packets. This can result in reference count issues as page
+ * pool pages will not decrement the reference count and will
+ * instead be immediately returned to the pool or have frag
+ * count decremented.
+ */
+ if (p->pp_recycle != skb->pp_recycle)
+ return -ETOOMANYREFS;
+
/* pairs with WRITE_ONCE() in netif_set_gro_max_size() */
gro_max_size = READ_ONCE(p->dev->gro_max_size);
NAPI_GRO_CB(skb)->count = 1;
if (unlikely(skb_is_gso(skb))) {
NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs;
- /* Only support TCP at the moment. */
- if (!skb_is_gso_tcp(skb))
+ /* Only support TCP and non DODGY users. */
+ if (!skb_is_gso_tcp(skb) ||
+ (skb_shinfo(skb)->gso_type & SKB_GSO_DODGY))
NAPI_GRO_CB(skb)->flush = 1;
}
(n->nud_state == NUD_NOARP) ||
(tbl->is_multicast &&
tbl->is_multicast(n->primary_key)) ||
- time_after(tref, n->updated))
+ !time_in_range(n->updated, tref, jiffies))
remove = true;
write_unlock(&n->lock);
static void neigh_add_timer(struct neighbour *n, unsigned long when)
{
+ /* Use safe distance from the jiffies - LONG_MAX point while timer
+ * is running in DELAY/PROBE state but still show to user space
+ * large times in the past.
+ */
+ unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ);
+
neigh_hold(n);
+ if (!time_in_range(n->confirmed, mint, jiffies))
+ n->confirmed = mint;
+ if (time_before(n->used, n->confirmed))
+ n->used = n->confirmed;
if (unlikely(mod_timer(&n->timer, when))) {
printk("NEIGH: BUG, double timer add, state is %x\n",
n->nud_state);
goto next_elt;
}
- if (time_before(n->used, n->confirmed))
+ if (time_before(n->used, n->confirmed) &&
+ time_is_before_eq_jiffies(n->confirmed))
n->used = n->confirmed;
if (refcount_read(&n->refcnt) == 1 &&
(state == NUD_FAILED ||
- time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
+ !time_in_range_open(jiffies, n->used,
+ n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
*np = n->next;
neigh_mark_dead(n);
write_unlock(&n->lock);
return 0;
if (ops->id && ops->size) {
-cleanup:
ng = rcu_dereference_protected(net->gen,
lockdep_is_held(&pernet_ops_rwsem));
ng->ptr[*ops->id] = NULL;
}
+cleanup:
kfree(data);
out:
}
EXPORT_SYMBOL_GPL(get_net_ns_by_id);
+/* init code that must occur even if setup_net() is not called. */
+static __net_init void preinit_net(struct net *net)
+{
+ ref_tracker_dir_init(&net->notrefcnt_tracker, 128);
+}
+
/*
* setup_net runs the initializers for the network namespace object.
*/
refcount_set(&net->ns.count, 1);
ref_tracker_dir_init(&net->refcnt_tracker, 128);
- ref_tracker_dir_init(&net->notrefcnt_tracker, 128);
refcount_set(&net->passive, 1);
get_random_bytes(&net->hash_mix, sizeof(u32));
rv = -ENOMEM;
goto dec_ucounts;
}
+
+ preinit_net(net);
refcount_set(&net->passive, 1);
net->ucounts = ucounts;
get_user_ns(user_ns);
init_net.key_domain = &init_net_key_domain;
#endif
down_write(&pernet_ops_rwsem);
+ preinit_net(&init_net);
if (setup_net(&init_net, &init_user_ns))
panic("Could not setup the initial network namespace");
skb_shinfo(skb)->frag_list = NULL;
- do {
+ while (list_skb) {
nskb = list_skb;
list_skb = list_skb->next;
if (skb_needs_linearize(nskb, features) &&
__skb_linearize(nskb))
goto err_linearize;
-
- } while (list_skb);
+ }
skb->truesize = skb->truesize - delta_truesize;
skb->data_len = skb->data_len - delta_len;
ret = -EINVAL;
break;
}
+ if ((u8)val == SOCK_TXREHASH_DEFAULT)
+ val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
/* Paired with READ_ONCE() in tcp_rtx_synack() */
WRITE_ONCE(sk->sk_txrehash, (u8)val);
break;
sk->sk_pacing_rate = ~0UL;
WRITE_ONCE(sk->sk_pacing_shift, 10);
sk->sk_incoming_cpu = -1;
- sk->sk_txrehash = SOCK_TXREHASH_DEFAULT;
sk_rx_queue_clear(sk);
/*
psock = sk_psock(sk);
if (unlikely(!psock)) {
rcu_read_unlock();
- if (sk->sk_prot->unhash)
- sk->sk_prot->unhash(sk);
- return;
+ saved_unhash = READ_ONCE(sk->sk_prot)->unhash;
+ } else {
+ saved_unhash = psock->saved_unhash;
+ sock_map_remove_links(sk, psock);
+ rcu_read_unlock();
}
-
- saved_unhash = psock->saved_unhash;
- sock_map_remove_links(sk, psock);
- rcu_read_unlock();
- saved_unhash(sk);
+ if (WARN_ON_ONCE(saved_unhash == sock_map_unhash))
+ return;
+ if (saved_unhash)
+ saved_unhash(sk);
}
EXPORT_SYMBOL_GPL(sock_map_unhash);
psock = sk_psock_get(sk);
if (unlikely(!psock)) {
rcu_read_unlock();
- if (sk->sk_prot->destroy)
- sk->sk_prot->destroy(sk);
- return;
+ saved_destroy = READ_ONCE(sk->sk_prot)->destroy;
+ } else {
+ saved_destroy = psock->saved_destroy;
+ sock_map_remove_links(sk, psock);
+ rcu_read_unlock();
+ sk_psock_stop(psock);
+ sk_psock_put(sk, psock);
}
-
- saved_destroy = psock->saved_destroy;
- sock_map_remove_links(sk, psock);
- rcu_read_unlock();
- sk_psock_stop(psock);
- sk_psock_put(sk, psock);
- saved_destroy(sk);
+ if (WARN_ON_ONCE(saved_destroy == sock_map_destroy))
+ return;
+ if (saved_destroy)
+ saved_destroy(sk);
}
EXPORT_SYMBOL_GPL(sock_map_destroy);
if (unlikely(!psock)) {
rcu_read_unlock();
release_sock(sk);
- return sk->sk_prot->close(sk, timeout);
+ saved_close = READ_ONCE(sk->sk_prot)->close;
+ } else {
+ saved_close = psock->saved_close;
+ sock_map_remove_links(sk, psock);
+ rcu_read_unlock();
+ sk_psock_stop(psock);
+ release_sock(sk);
+ cancel_work_sync(&psock->work);
+ sk_psock_put(sk, psock);
}
-
- saved_close = psock->saved_close;
- sock_map_remove_links(sk, psock);
- rcu_read_unlock();
- sk_psock_stop(psock);
- release_sock(sk);
- cancel_work_sync(&psock->work);
- sk_psock_put(sk, psock);
+ /* Make sure we do not recurse. This is a bug.
+ * Leak the socket instead of crashing on a stack overflow.
+ */
+ if (WARN_ON_ONCE(saved_close == sock_map_close))
+ return;
saved_close(sk, timeout);
}
EXPORT_SYMBOL_GPL(sock_map_close);
sk_mem_reclaim_final(sk);
WARN_ON_ONCE(sk->sk_wmem_queued);
- WARN_ON_ONCE(sk->sk_forward_alloc);
/* It is _impossible_ for the backlog to contain anything
* when we get here. All user references to this socket
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
/* Clone pktoptions received with SYN, if we own the req */
if (*own_req && ireq->pktopts) {
- newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
+ newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
- if (newnp->pktoptions)
- skb_set_owner_r(newnp->pktoptions, newsk);
}
return newsk;
--ANK (980728)
*/
if (np->rxopt.all)
- opt_skb = skb_clone(skb, GFP_ATOMIC);
+ opt_skb = skb_clone_and_charge_r(skb, sk);
if (sk->sk_state == DCCP_OPEN) { /* Fast path */
if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len))
np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb,
&DCCP_SKB_CB(opt_skb)->header.h6)) {
- skb_set_owner_r(opt_skb, sk);
memmove(IP6CB(opt_skb),
&DCCP_SKB_CB(opt_skb)->header.h6,
sizeof(struct inet6_skb_parm));
return ret;
}
-static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
+static int ethtool_vzalloc_stats_array(int n_stats, u64 **data)
{
+ if (n_stats < 0)
+ return n_stats;
+ if (n_stats > S32_MAX / sizeof(u64))
+ return -ENOMEM;
+ if (WARN_ON_ONCE(!n_stats))
+ return -EOPNOTSUPP;
+
+ *data = vzalloc(array_size(n_stats, sizeof(u64)));
+ if (!*data)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int ethtool_get_phy_stats_phydev(struct phy_device *phydev,
+ struct ethtool_stats *stats,
+ u64 **data)
+ {
const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
+ int n_stats, ret;
+
+ if (!phy_ops || !phy_ops->get_sset_count || !phy_ops->get_stats)
+ return -EOPNOTSUPP;
+
+ n_stats = phy_ops->get_sset_count(phydev);
+
+ ret = ethtool_vzalloc_stats_array(n_stats, data);
+ if (ret)
+ return ret;
+
+ stats->n_stats = n_stats;
+ return phy_ops->get_stats(phydev, stats, *data);
+}
+
+static int ethtool_get_phy_stats_ethtool(struct net_device *dev,
+ struct ethtool_stats *stats,
+ u64 **data)
+{
const struct ethtool_ops *ops = dev->ethtool_ops;
- struct phy_device *phydev = dev->phydev;
- struct ethtool_stats stats;
- u64 *data;
- int ret, n_stats;
+ int n_stats, ret;
- if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count))
+ if (!ops || !ops->get_sset_count || ops->get_ethtool_phy_stats)
return -EOPNOTSUPP;
- if (phydev && !ops->get_ethtool_phy_stats &&
- phy_ops && phy_ops->get_sset_count)
- n_stats = phy_ops->get_sset_count(phydev);
- else
- n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
- if (n_stats < 0)
- return n_stats;
- if (n_stats > S32_MAX / sizeof(u64))
- return -ENOMEM;
- WARN_ON_ONCE(!n_stats);
+ n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
+
+ ret = ethtool_vzalloc_stats_array(n_stats, data);
+ if (ret)
+ return ret;
+
+ stats->n_stats = n_stats;
+ ops->get_ethtool_phy_stats(dev, stats, *data);
+
+ return 0;
+}
+
+static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
+{
+ struct phy_device *phydev = dev->phydev;
+ struct ethtool_stats stats;
+ u64 *data = NULL;
+ int ret = -EOPNOTSUPP;
if (copy_from_user(&stats, useraddr, sizeof(stats)))
return -EFAULT;
- stats.n_stats = n_stats;
+ if (phydev)
+ ret = ethtool_get_phy_stats_phydev(phydev, &stats, &data);
- if (n_stats) {
- data = vzalloc(array_size(n_stats, sizeof(u64)));
- if (!data)
- return -ENOMEM;
+ if (ret == -EOPNOTSUPP)
+ ret = ethtool_get_phy_stats_ethtool(dev, &stats, &data);
- if (phydev && !ops->get_ethtool_phy_stats &&
- phy_ops && phy_ops->get_stats) {
- ret = phy_ops->get_stats(phydev, &stats, data);
- if (ret < 0)
- goto out;
- } else {
- ops->get_ethtool_phy_stats(dev, &stats, data);
- }
- } else {
- data = NULL;
- }
+ if (ret)
+ goto out;
- ret = -EFAULT;
- if (copy_to_user(useraddr, &stats, sizeof(stats)))
+ if (copy_to_user(useraddr, &stats, sizeof(stats))) {
+ ret = -EFAULT;
goto out;
+ }
+
useraddr += sizeof(stats);
- if (n_stats && copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64))))
- goto out;
- ret = 0;
+ if (copy_to_user(useraddr, data, array_size(stats.n_stats, sizeof(u64))))
+ ret = -EFAULT;
out:
vfree(data);
{
const struct rss_reply_data *data = RSS_REPDATA(reply_base);
- if (nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc) ||
- nla_put(skb, ETHTOOL_A_RSS_INDIR,
- sizeof(u32) * data->indir_size, data->indir_table) ||
- nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey))
+ if ((data->hfunc &&
+ nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||
+ (data->indir_size &&
+ nla_put(skb, ETHTOOL_A_RSS_INDIR,
+ sizeof(u32) * data->indir_size, data->indir_table)) ||
+ (data->hkey_size &&
+ nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey)))
return -EMSGSIZE;
return 0;
sk->sk_destruct = inet_sock_destruct;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
+ sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash);
inet->uc_ttl = -1;
inet->mc_loop = 1;
if (rc == 0) {
*sk = sock->sk;
(*sk)->sk_allocation = GFP_ATOMIC;
+ (*sk)->sk_use_task_frag = false;
/*
* Unhash it so that IP input processing does not even see it,
* we do not wish this socket to see incoming packets.
#include <linux/slab.h>
#include <linux/netlink.h>
#include <linux/hash.h>
+#include <linux/nospec.h>
#include <net/arp.h>
#include <net/inet_dscp.h>
if (type > RTAX_MAX)
return false;
+ type = array_index_nospec(type, RTAX_MAX + 1);
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
bool ecn_ca = false;
return false;
}
+static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
+ kuid_t sk_uid, bool relax,
+ bool reuseport_cb_ok, bool reuseport_ok)
+{
+ if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
+ return false;
+
+ return inet_bind_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok);
+}
+
static bool inet_bhash2_conflict(const struct sock *sk,
const struct inet_bind2_bucket *tb2,
kuid_t sk_uid,
bool relax, bool reuseport_cb_ok,
bool reuseport_ok)
{
+ struct inet_timewait_sock *tw2;
struct sock *sk2;
sk_for_each_bound_bhash2(sk2, &tb2->owners) {
- if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
- continue;
+ if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok))
+ return true;
+ }
+
+ twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
+ sk2 = (struct sock *)tw2;
- if (inet_bind_conflict(sk, sk2, sk_uid, relax,
- reuseport_cb_ok, reuseport_ok))
+ if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok))
return true;
}
+
return false;
}
}
EXPORT_SYMBOL(inet_csk_prepare_forced_close);
+static int inet_ulp_can_listen(const struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone)
+ return -EINVAL;
+
+ return 0;
+}
+
int inet_csk_listen_start(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
int err;
+ err = inet_ulp_can_listen(sk);
+ if (unlikely(err))
+ return err;
+
reqsk_queue_alloc(&icsk->icsk_accept_queue);
sk->sk_ack_backlog = 0;
inet_csk_delack_init(sk);
- if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT)
- sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
-
/* There is race window here: we announce ourselves listening,
* but this transition is still not validated by get_port().
* It is OK, because this socket enters to hash table only
#endif
tb->rcv_saddr = sk->sk_rcv_saddr;
INIT_HLIST_HEAD(&tb->owners);
+ INIT_HLIST_HEAD(&tb->deathrow);
hlist_add_head(&tb->node, &head->chain);
}
/* Caller must hold hashbucket lock for this tb with local BH disabled */
void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
{
- if (hlist_empty(&tb->owners)) {
+ if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
__hlist_del(&tb->node);
kmem_cache_free(cachep, tb);
}
spin_lock(lock);
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
- ret = sk_nulls_del_node_init_rcu(osk);
- } else if (found_dup_sk) {
+ ret = sk_hashed(osk);
+ if (ret) {
+ /* Before deleting the node, we insert a new one to make
+ * sure that the look-up-sk process would not miss either
+ * of them and that at least one node would exist in ehash
+ * table all the time. Otherwise there's a tiny chance
+ * that lookup process could find nothing in ehash table.
+ */
+ __sk_nulls_add_node_tail_rcu(sk, list);
+ sk_nulls_del_node_init_rcu(osk);
+ }
+ goto unlock;
+ }
+ if (found_dup_sk) {
*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
if (*found_dup_sk)
ret = false;
if (ret)
__sk_nulls_add_node_rcu(sk, list);
+unlock:
spin_unlock(lock);
return ret;
/* Head lock still held and bh's disabled */
inet_bind_hash(sk, tb, tb2, port);
- spin_unlock(&head2->lock);
-
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
+
+ spin_unlock(&head2->lock);
spin_unlock(&head->lock);
+
if (tw)
inet_twsk_deschedule_put(tw);
local_bh_enable();
void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo)
{
+ struct inet_bind2_bucket *tb2 = tw->tw_tb2;
struct inet_bind_bucket *tb = tw->tw_tb;
if (!tb)
__hlist_del(&tw->tw_bind_node);
tw->tw_tb = NULL;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+
+ __hlist_del(&tw->tw_bind2_node);
+ tw->tw_tb2 = NULL;
+ inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
+
__sock_put((struct sock *)tw);
}
{
struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
- struct inet_bind_hashbucket *bhead;
+ struct inet_bind_hashbucket *bhead, *bhead2;
spin_lock(lock);
sk_nulls_del_node_init_rcu((struct sock *)tw);
/* Disassociate with bind bucket. */
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
hashinfo->bhash_size)];
+ bhead2 = inet_bhashfn_portaddr(hashinfo, (struct sock *)tw,
+ twsk_net(tw), tw->tw_num);
spin_lock(&bhead->lock);
+ spin_lock(&bhead2->lock);
inet_twsk_bind_unhash(tw, hashinfo);
+ spin_unlock(&bhead2->lock);
spin_unlock(&bhead->lock);
refcount_dec(&tw->tw_dr->tw_refcount);
}
EXPORT_SYMBOL_GPL(inet_twsk_put);
-static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
- struct hlist_nulls_head *list)
+static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw,
+ struct hlist_nulls_head *list)
{
- hlist_nulls_add_head_rcu(&tw->tw_node, list);
+ hlist_nulls_add_tail_rcu(&tw->tw_node, list);
}
static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
hlist_add_head(&tw->tw_bind_node, list);
}
+static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw,
+ struct hlist_head *list)
+{
+ hlist_add_head(&tw->tw_bind2_node, list);
+}
+
/*
* Enter the time wait state. This is called with locally disabled BH.
* Essentially we whip up a timewait bucket, copy the relevant info into it
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
- struct inet_bind_hashbucket *bhead;
+ struct inet_bind_hashbucket *bhead, *bhead2;
+
/* Step 1: Put TW into bind hash. Original socket stays there too.
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
hashinfo->bhash_size)];
+ bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num);
+
spin_lock(&bhead->lock);
+ spin_lock(&bhead2->lock);
+
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
+
+ tw->tw_tb2 = icsk->icsk_bind2_hash;
+ WARN_ON(!icsk->icsk_bind2_hash);
+ inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow);
+
+ spin_unlock(&bhead2->lock);
spin_unlock(&bhead->lock);
spin_lock(lock);
- inet_twsk_add_node_rcu(tw, &ehead->chain);
+ inet_twsk_add_node_tail_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
if (__sk_nulls_del_node_init_rcu(sk))
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/netlink.h>
+#include <linux/nospec.h>
#include <linux/rtnetlink.h>
#include <linux/types.h>
#include <net/ip.h>
return -EINVAL;
}
+ type = array_index_nospec(type, RTAX_MAX + 1);
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
/* There's a bubble in the pipe until at least the first ACK. */
tp->app_limited = ~0U;
+ tp->rate_app_limited = 1;
/* See draft-stevens-tcpca-spec-01 for discussion of the
* initialization of these values.
tp->plb_rehash = 0;
/* There's a bubble in the pipe until at least the first ACK. */
tp->app_limited = ~0U;
+ tp->rate_app_limited = 1;
tp->rack.mstamp = 0;
tp->rack.advanced = 0;
tp->rack.reo_wnd_steps = 1;
#include <linux/bpf.h>
#include <linux/init.h>
#include <linux/wait.h>
+#include <linux/util_macros.h>
#include <net/inet_common.h>
#include <net/tls.h>
*/
void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
{
- int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
struct proto *prot = newsk->sk_prot;
- if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE])
+ if (is_insidevar(prot, tcp_bpf_prots))
newsk->sk_prot = sk->sk_prot_creator;
}
#endif /* CONFIG_BPF_SYSCALL */
if (sk->sk_socket)
clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
+ err = -ENOTCONN;
+ if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN)
+ goto out_err;
+
err = ulp_ops->init(sk);
if (err)
goto out_err;
offset = sizeof(struct in6_addr) - 4;
memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
- if (idev->dev->flags&IFF_POINTOPOINT) {
+ if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
+ scope = IPV6_ADDR_COMPATv4;
+ plen = 96;
+ pflags |= RTF_NONEXTHOP;
+ } else {
if (idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_NONE)
return;
addr.s6_addr32[0] = htonl(0xfe800000);
scope = IFA_LINK;
plen = 64;
- } else {
- scope = IPV6_ADDR_COMPATv4;
- plen = 96;
- pflags |= RTF_NONEXTHOP;
}
if (addr.s6_addr32[3]) {
}
#endif
+static void addrconf_init_auto_addrs(struct net_device *dev)
+{
+ switch (dev->type) {
+#if IS_ENABLED(CONFIG_IPV6_SIT)
+ case ARPHRD_SIT:
+ addrconf_sit_config(dev);
+ break;
+#endif
+#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE)
+ case ARPHRD_IP6GRE:
+ case ARPHRD_IPGRE:
+ addrconf_gre_config(dev);
+ break;
+#endif
+ case ARPHRD_LOOPBACK:
+ init_loopback(dev);
+ break;
+
+ default:
+ addrconf_dev_config(dev);
+ break;
+ }
+}
+
static int fixup_permanent_addr(struct net *net,
struct inet6_dev *idev,
struct inet6_ifaddr *ifp)
run_pending = 1;
}
- switch (dev->type) {
-#if IS_ENABLED(CONFIG_IPV6_SIT)
- case ARPHRD_SIT:
- addrconf_sit_config(dev);
- break;
-#endif
-#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE)
- case ARPHRD_IP6GRE:
- case ARPHRD_IPGRE:
- addrconf_gre_config(dev);
- break;
-#endif
- case ARPHRD_LOOPBACK:
- init_loopback(dev);
- break;
-
- default:
- addrconf_dev_config(dev);
- break;
- }
+ addrconf_init_auto_addrs(dev);
if (!IS_ERR_OR_NULL(idev)) {
if (run_pending)
if (idev->cnf.addr_gen_mode != new_val) {
idev->cnf.addr_gen_mode = new_val;
- addrconf_dev_config(idev->dev);
+ addrconf_init_auto_addrs(idev->dev);
}
} else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) {
struct net_device *dev;
if (idev &&
idev->cnf.addr_gen_mode != new_val) {
idev->cnf.addr_gen_mode = new_val;
- addrconf_dev_config(idev->dev);
+ addrconf_init_auto_addrs(idev->dev);
}
}
}
np->pmtudisc = IPV6_PMTUDISC_WANT;
np->repflow = net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED;
sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;
+ sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash);
/* Init the ipv4 part of the socket since we can have sockets
* using v6 API for ipv4.
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_dport = inet->inet_dport;
fl6->fl6_sport = inet->inet_sport;
- fl6->flowlabel = np->flow_label;
+ fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
fl6->flowi6_uid = sk->sk_uid;
if (!oif)
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
if (proxied > 0) {
- hdr->hop_limit--;
+ /* It's tempting to decrease the hop limit
+ * here by 1, as we do at the end of the
+ * function too.
+ *
+ * But that would be incorrect, as proxying is
+ * not forwarding. The ip6_input function
+ * will handle this packet locally, and it
+ * depends on the hop limit being unchanged.
+ *
+ * One example is the NDP hop limit, that
+ * always has to stay 255, but other would be
+ * similar checks around RA packets, where the
+ * user can even change the desired limit.
+ */
return ip6_input(skb);
} else if (proxied < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
struct raw6_sock *rp)
{
+ struct ipv6_txoptions *opt;
struct sk_buff *skb;
int err = 0;
int offset;
offset = rp->offset;
total_len = inet_sk(sk)->cork.base.length;
+ opt = inet6_sk(sk)->cork.opt;
+ total_len -= opt ? opt->opt_flen : 0;
+
if (offset >= total_len - 1) {
err = -EINVAL;
ip6_flush_pending_frames(sk);
fl6.flowi6_proto = IPPROTO_TCP;
fl6.daddr = sk->sk_v6_daddr;
fl6.saddr = saddr ? *saddr : np->saddr;
+ fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_dport = usin->sin6_port;
/* Clone pktoptions received with SYN, if we own the req */
if (ireq->pktopts) {
- newnp->pktoptions = skb_clone(ireq->pktopts,
- sk_gfp_mask(sk, GFP_ATOMIC));
+ newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
consume_skb(ireq->pktopts);
ireq->pktopts = NULL;
- if (newnp->pktoptions) {
+ if (newnp->pktoptions)
tcp_v6_restore_cb(newnp->pktoptions);
- skb_set_owner_r(newnp->pktoptions, newsk);
- }
}
} else {
if (!req_unhash && found_dup_sk) {
--ANK (980728)
*/
if (np->rxopt.all)
- opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
+ opt_skb = skb_clone_and_charge_r(skb, sk);
reason = SKB_DROP_REASON_NOT_SPECIFIED;
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
if (np->repflow)
np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
- skb_set_owner_r(opt_skb, sk);
tcp_v6_restore_cb(opt_skb);
opt_skb = xchg(&np->pktoptions, opt_skb);
} else {
const struct sadb_x_nat_t_type* n_type;
struct xfrm_encap_tmpl *natt;
- x->encap = kmalloc(sizeof(*x->encap), GFP_KERNEL);
+ x->encap = kzalloc(sizeof(*x->encap), GFP_KERNEL);
if (!x->encap) {
err = -ENOMEM;
goto out;
/* per-net private data for this module */
static unsigned int l2tp_net_id;
struct l2tp_net {
- struct list_head l2tp_tunnel_list;
- /* Lock for write access to l2tp_tunnel_list */
- spinlock_t l2tp_tunnel_list_lock;
+ /* Lock for write access to l2tp_tunnel_idr */
+ spinlock_t l2tp_tunnel_idr_lock;
+ struct idr l2tp_tunnel_idr;
struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2];
/* Lock for write access to l2tp_session_hlist */
spinlock_t l2tp_session_hlist_lock;
struct l2tp_tunnel *tunnel;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (tunnel->tunnel_id == tunnel_id &&
- refcount_inc_not_zero(&tunnel->ref_count)) {
- rcu_read_unlock_bh();
-
- return tunnel;
- }
+ tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id);
+ if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) {
+ rcu_read_unlock_bh();
+ return tunnel;
}
rcu_read_unlock_bh();
struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
{
- const struct l2tp_net *pn = l2tp_pernet(net);
+ struct l2tp_net *pn = l2tp_pernet(net);
+ unsigned long tunnel_id, tmp;
struct l2tp_tunnel *tunnel;
int count = 0;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (++count > nth &&
+ idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
+ if (tunnel && ++count > nth &&
refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
nf_reset_ct(skb);
- bh_lock_sock(sk);
+ bh_lock_sock_nested(sk);
if (sock_owned_by_user(sk)) {
kfree_skb(skb);
ret = NET_XMIT_DROP;
l2tp_tunnel_delete(tunnel);
}
+static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel)
+{
+ struct l2tp_net *pn = l2tp_pernet(net);
+
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
+}
+
/* Workqueue tunnel deletion function */
static void l2tp_tunnel_del_work(struct work_struct *work)
{
del_work);
struct sock *sk = tunnel->sock;
struct socket *sock = sk->sk_socket;
- struct l2tp_net *pn;
l2tp_tunnel_closeall(tunnel);
}
}
- /* Remove the tunnel struct from the tunnel list */
- pn = l2tp_pernet(tunnel->l2tp_net);
- spin_lock_bh(&pn->l2tp_tunnel_list_lock);
- list_del_rcu(&tunnel->list);
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
-
+ l2tp_tunnel_remove(tunnel->l2tp_net, tunnel);
/* drop initial ref */
l2tp_tunnel_dec_refcount(tunnel);
return err;
}
-static struct lock_class_key l2tp_socket_class;
-
int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id,
struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp)
{
int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
struct l2tp_tunnel_cfg *cfg)
{
- struct l2tp_tunnel *tunnel_walk;
- struct l2tp_net *pn;
+ struct l2tp_net *pn = l2tp_pernet(net);
+ u32 tunnel_id = tunnel->tunnel_id;
struct socket *sock;
struct sock *sk;
int ret;
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id,
+ GFP_ATOMIC);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
+ if (ret)
+ return ret == -ENOSPC ? -EEXIST : ret;
+
if (tunnel->fd < 0) {
ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id,
tunnel->peer_tunnel_id, cfg,
}
sk = sock->sk;
+ lock_sock(sk);
write_lock_bh(&sk->sk_callback_lock);
ret = l2tp_validate_socket(sk, net, tunnel->encap);
if (ret < 0)
rcu_assign_sk_user_data(sk, tunnel);
write_unlock_bh(&sk->sk_callback_lock);
- tunnel->l2tp_net = net;
- pn = l2tp_pernet(net);
-
- sock_hold(sk);
- tunnel->sock = sk;
-
- spin_lock_bh(&pn->l2tp_tunnel_list_lock);
- list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) {
- if (tunnel_walk->tunnel_id == tunnel->tunnel_id) {
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
- sock_put(sk);
- ret = -EEXIST;
- goto err_sock;
- }
- }
- list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
-
if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
struct udp_tunnel_sock_cfg udp_cfg = {
.sk_user_data = tunnel,
tunnel->old_sk_destruct = sk->sk_destruct;
sk->sk_destruct = &l2tp_tunnel_destruct;
- lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class,
- "l2tp_sock");
sk->sk_allocation = GFP_ATOMIC;
+ release_sock(sk);
+
+ sock_hold(sk);
+ tunnel->sock = sk;
+ tunnel->l2tp_net = net;
+
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
trace_register_tunnel(tunnel);
return 0;
-err_sock:
- write_lock_bh(&sk->sk_callback_lock);
- rcu_assign_sk_user_data(sk, NULL);
err_inval_sock:
write_unlock_bh(&sk->sk_callback_lock);
+ release_sock(sk);
if (tunnel->fd < 0)
sock_release(sock);
else
sockfd_put(sock);
err:
+ l2tp_tunnel_remove(net, tunnel);
return ret;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_register);
struct l2tp_net *pn = net_generic(net, l2tp_net_id);
int hash;
- INIT_LIST_HEAD(&pn->l2tp_tunnel_list);
- spin_lock_init(&pn->l2tp_tunnel_list_lock);
+ idr_init(&pn->l2tp_tunnel_idr);
+ spin_lock_init(&pn->l2tp_tunnel_idr_lock);
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++)
INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]);
{
struct l2tp_net *pn = l2tp_pernet(net);
struct l2tp_tunnel *tunnel = NULL;
+ unsigned long tunnel_id, tmp;
int hash;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- l2tp_tunnel_delete(tunnel);
+ idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
+ if (tunnel)
+ l2tp_tunnel_delete(tunnel);
}
rcu_read_unlock_bh();
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++)
WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash]));
+ idr_destroy(&pn->l2tp_tunnel_idr);
}
static struct pernet_operations l2tp_net_ops = {
{
struct tid_ampdu_tx *tid_tx;
struct ieee80211_local *local = sta->local;
- struct ieee80211_sub_if_data *sdata = sta->sdata;
+ struct ieee80211_sub_if_data *sdata;
struct ieee80211_ampdu_params params = {
.sta = &sta->sta,
.action = IEEE80211_AMPDU_TX_START,
*/
clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state);
- ieee80211_agg_stop_txq(sta, tid);
-
/*
* Make sure no packets are being processed. This ensures that
* we have a valid starting sequence number and that in-flight
*/
synchronize_net();
+ sdata = sta->sdata;
params.ssn = sta->tid_seq[tid] >> 4;
ret = drv_ampdu_action(local, sdata, ¶ms);
tid_tx->ssn = params.ssn;
*/
set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state);
} else if (ret) {
+ if (!sdata)
+ return;
+
ht_dbg(sdata,
"BA request denied - HW unavailable for %pM tid %d\n",
sta->sta.addr, tid);
link_conf->bssid_index = 0;
link_conf->nontransmitted = false;
link_conf->ema_ap = false;
+ link_conf->bssid_indicator = 0;
if (sdata->vif.type != NL80211_IFTYPE_AP || !params.tx_wdev)
return -EINVAL;
kfree(link_conf->ftmr_params);
link_conf->ftmr_params = NULL;
+ sdata->vif.mbssid_tx_vif = NULL;
+ link_conf->bssid_index = 0;
+ link_conf->nontransmitted = false;
+ link_conf->ema_ap = false;
+ link_conf->bssid_indicator = 0;
+
__sta_info_flush(sdata, true);
ieee80211_free_keys(sdata, true);
continue;
txqi = to_txq_info(sta->sta.txq[i]);
p += scnprintf(p, bufsz + buf - p,
- "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n",
+ "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s%s)\n",
txqi->txq.tid,
txqi->txq.ac,
txqi->tin.backlog_bytes,
txqi->flags,
test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ? "STOP" : "RUN",
test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "",
- test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : "");
+ test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : "",
+ test_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) ? " DIRTY" : "");
}
rcu_read_unlock();
might_sleep();
+ if (!sdata)
+ return -EIO;
+
sdata = get_bss_sdata(sdata);
if (!check_sdata_in_driver(sdata))
return -EIO;
/* In reconfig don't transmit now, but mark for waking later */
if (local->in_reconfig) {
- set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txq->flags);
+ set_bit(IEEE80211_TXQ_DIRTY, &txq->flags);
return;
}
tid_tx = sta->ampdu_mlme.tid_start_tx[tid];
if (!blocked && tid_tx) {
+ struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
+ struct ieee80211_sub_if_data *sdata =
+ vif_to_sdata(txqi->txq.vif);
+ struct fq *fq = &sdata->local->fq;
+
+ spin_lock_bh(&fq->lock);
+
+ /* Allow only frags to be dequeued */
+ set_bit(IEEE80211_TXQ_STOP, &txqi->flags);
+
+ if (!skb_queue_empty(&txqi->frags)) {
+ /* Fragmented Tx is ongoing, wait for it to
+ * finish. Reschedule worker to retry later.
+ */
+
+ spin_unlock_bh(&fq->lock);
+ spin_unlock_bh(&sta->lock);
+
+ /* Give the task working on the txq a chance
+ * to send out the queued frags
+ */
+ synchronize_net();
+
+ mutex_unlock(&sta->ampdu_mlme.mtx);
+
+ ieee80211_queue_work(&sdata->local->hw, work);
+ return;
+ }
+
+ spin_unlock_bh(&fq->lock);
+
/*
* Assign it over to the normal tid_tx array
* where it "goes live".
IEEE80211_TXQ_STOP,
IEEE80211_TXQ_AMPDU,
IEEE80211_TXQ_NO_AMSDU,
- IEEE80211_TXQ_STOP_NETIF_TX,
+ IEEE80211_TXQ_DIRTY,
};
/**
/* No support for VLAN with MLO yet */
if (iftype == NL80211_IFTYPE_AP_VLAN &&
- nsdata->wdev.use_4addr)
+ sdata->wdev.use_4addr &&
+ nsdata->vif.type == NL80211_IFTYPE_AP &&
+ nsdata->vif.valid_links)
return -EOPNOTSUPP;
/*
ret = cfg80211_register_netdevice(ndev);
if (ret) {
- ieee80211_if_free(ndev);
free_netdev(ndev);
return ret;
}
#undef CALL_RXH
}
+static bool
+ieee80211_rx_is_valid_sta_link_id(struct ieee80211_sta *sta, u8 link_id)
+{
+ if (!sta->mlo)
+ return false;
+
+ return !!(sta->valid_links & BIT(link_id));
+}
+
+static bool ieee80211_rx_data_set_link(struct ieee80211_rx_data *rx,
+ u8 link_id)
+{
+ rx->link_id = link_id;
+ rx->link = rcu_dereference(rx->sdata->link[link_id]);
+
+ if (!rx->sta)
+ return rx->link;
+
+ if (!ieee80211_rx_is_valid_sta_link_id(&rx->sta->sta, link_id))
+ return false;
+
+ rx->link_sta = rcu_dereference(rx->sta->link[link_id]);
+
+ return rx->link && rx->link_sta;
+}
+
+static bool ieee80211_rx_data_set_sta(struct ieee80211_rx_data *rx,
+ struct ieee80211_sta *pubsta,
+ int link_id)
+{
+ struct sta_info *sta;
+
+ sta = container_of(pubsta, struct sta_info, sta);
+
+ rx->link_id = link_id;
+ rx->sta = sta;
+
+ if (sta) {
+ rx->local = sta->sdata->local;
+ if (!rx->sdata)
+ rx->sdata = sta->sdata;
+ rx->link_sta = &sta->deflink;
+ }
+
+ if (link_id < 0)
+ rx->link = &rx->sdata->deflink;
+ else if (!ieee80211_rx_data_set_link(rx, link_id))
+ return false;
+
+ return true;
+}
+
/*
* This function makes calls into the RX path, therefore
* it has to be invoked under RCU read lock.
{
struct sk_buff_head frames;
struct ieee80211_rx_data rx = {
- .sta = sta,
- .sdata = sta->sdata,
- .local = sta->local,
/* This is OK -- must be QoS data frame */
.security_idx = tid,
.seqno_idx = tid,
- .link_id = -1,
};
struct tid_ampdu_rx *tid_agg_rx;
- u8 link_id;
+ int link_id = -1;
+
+ /* FIXME: statistics won't be right with this */
+ if (sta->sta.valid_links)
+ link_id = ffs(sta->sta.valid_links) - 1;
+
+ if (!ieee80211_rx_data_set_sta(&rx, &sta->sta, link_id))
+ return;
tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]);
if (!tid_agg_rx)
};
drv_event_callback(rx.local, rx.sdata, &event);
}
- /* FIXME: statistics won't be right with this */
- link_id = sta->sta.valid_links ? ffs(sta->sta.valid_links) - 1 : 0;
- rx.link = rcu_dereference(sta->sdata->link[link_id]);
- rx.link_sta = rcu_dereference(sta->link[link_id]);
ieee80211_rx_handlers(&rx, &frames);
}
/* This is OK -- must be QoS data frame */
.security_idx = tid,
.seqno_idx = tid,
- .link_id = -1,
};
int i, diff;
sta = container_of(pubsta, struct sta_info, sta);
- rx.sta = sta;
- rx.sdata = sta->sdata;
- rx.link = &rx.sdata->deflink;
- rx.local = sta->local;
+ if (!ieee80211_rx_data_set_sta(&rx, pubsta, -1))
+ return;
rcu_read_lock();
tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]);
mutex_unlock(&local->sta_mtx);
}
-static bool
-ieee80211_rx_is_valid_sta_link_id(struct ieee80211_sta *sta, u8 link_id)
-{
- if (!sta->mlo)
- return false;
-
- return !!(sta->valid_links & BIT(link_id));
-}
-
static void ieee80211_rx_8023(struct ieee80211_rx_data *rx,
struct ieee80211_fast_rx *fast_rx,
int orig_len)
struct sk_buff *skb = rx->skb;
struct ieee80211_hdr *hdr = (void *)skb->data;
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
- struct sta_info *sta = rx->sta;
int orig_len = skb->len;
int hdrlen = ieee80211_hdrlen(hdr->frame_control);
int snap_offs = hdrlen;
u8 da[ETH_ALEN];
u8 sa[ETH_ALEN];
} addrs __aligned(2);
- struct link_sta_info *link_sta;
struct ieee80211_sta_rx_stats *stats;
/* for parallel-rx, we need to have DUP_VALIDATED, otherwise we write
drop:
dev_kfree_skb(skb);
- if (rx->link_id >= 0) {
- link_sta = rcu_dereference(sta->link[rx->link_id]);
- if (!link_sta)
- return true;
- } else {
- link_sta = &sta->deflink;
- }
-
if (fast_rx->uses_rss)
- stats = this_cpu_ptr(link_sta->pcpu_rx_stats);
+ stats = this_cpu_ptr(rx->link_sta->pcpu_rx_stats);
else
- stats = &link_sta->rx_stats;
+ stats = &rx->link_sta->rx_stats;
stats->dropped++;
return true;
struct ieee80211_local *local = rx->local;
struct ieee80211_sub_if_data *sdata = rx->sdata;
struct ieee80211_hdr *hdr = (void *)skb->data;
- struct link_sta_info *link_sta = NULL;
- struct ieee80211_link_data *link;
+ struct link_sta_info *link_sta = rx->link_sta;
+ struct ieee80211_link_data *link = rx->link;
rx->skb = skb;
if (!ieee80211_accept_frame(rx))
return false;
- if (rx->link_id >= 0) {
- link = rcu_dereference(rx->sdata->link[rx->link_id]);
-
- /* we might race link removal */
- if (!link)
- return true;
- rx->link = link;
-
- if (rx->sta) {
- rx->link_sta =
- rcu_dereference(rx->sta->link[rx->link_id]);
- if (!rx->link_sta)
- return true;
- }
- } else {
- if (rx->sta)
- rx->link_sta = &rx->sta->deflink;
-
- rx->link = &sdata->deflink;
- }
-
- if (unlikely(!is_multicast_ether_addr(hdr->addr1) &&
- rx->link_id >= 0 && rx->sta && rx->sta->sta.mlo)) {
- link_sta = rcu_dereference(rx->sta->link[rx->link_id]);
-
- if (WARN_ON_ONCE(!link_sta))
- return true;
- }
-
if (!consume) {
struct skb_shared_hwtstamps *shwt;
*/
shwt = skb_hwtstamps(rx->skb);
shwt->hwtstamp = skb_hwtstamps(skb)->hwtstamp;
+
+ /* Update the hdr pointer to the new skb for translation below */
+ hdr = (struct ieee80211_hdr *)rx->skb->data;
}
- if (unlikely(link_sta)) {
+ if (unlikely(rx->sta && rx->sta->sta.mlo)) {
/* translate to MLD addresses */
if (ether_addr_equal(link->conf->addr, hdr->addr1))
ether_addr_copy(hdr->addr1, rx->sdata->vif.addr);
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
struct ieee80211_fast_rx *fast_rx;
struct ieee80211_rx_data rx;
+ int link_id = -1;
memset(&rx, 0, sizeof(rx));
rx.skb = skb;
if (!pubsta)
goto drop;
- rx.sta = container_of(pubsta, struct sta_info, sta);
- rx.sdata = rx.sta->sdata;
-
- if (status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(pubsta, status->link_id))
- goto drop;
+ if (status->link_valid)
+ link_id = status->link_id;
/*
* TODO: Should the frame be dropped if the right link_id is not
* link_id is used only for stats purpose and updating the stats on
* the deflink is fine?
*/
- if (status->link_valid)
- rx.link_id = status->link_id;
-
- if (rx.link_id >= 0) {
- struct ieee80211_link_data *link;
-
- link = rcu_dereference(rx.sdata->link[rx.link_id]);
- if (!link)
- goto drop;
- rx.link = link;
- } else {
- rx.link = &rx.sdata->deflink;
- }
+ if (!ieee80211_rx_data_set_sta(&rx, pubsta, link_id))
+ goto drop;
fast_rx = rcu_dereference(rx.sta->fast_rx);
if (!fast_rx)
{
struct link_sta_info *link_sta;
struct ieee80211_hdr *hdr = (void *)skb->data;
+ struct sta_info *sta;
+ int link_id = -1;
/*
* Look up link station first, in case there's a
*/
link_sta = link_sta_info_get_bss(rx->sdata, hdr->addr2);
if (link_sta) {
- rx->sta = link_sta->sta;
- rx->link_id = link_sta->link_id;
+ sta = link_sta->sta;
+ link_id = link_sta->link_id;
} else {
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
- rx->sta = sta_info_get_bss(rx->sdata, hdr->addr2);
- if (rx->sta) {
- if (status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(&rx->sta->sta,
- status->link_id))
- return false;
-
- rx->link_id = status->link_valid ? status->link_id : -1;
- } else {
- rx->link_id = -1;
- }
+ sta = sta_info_get_bss(rx->sdata, hdr->addr2);
+ if (status->link_valid)
+ link_id = status->link_id;
}
+ if (!ieee80211_rx_data_set_sta(rx, &sta->sta, link_id))
+ return false;
+
return ieee80211_prepare_and_rx_handle(rx, skb, consume);
}
if (ieee80211_is_data(fc)) {
struct sta_info *sta, *prev_sta;
- u8 link_id = status->link_id;
+ int link_id = -1;
- if (pubsta) {
- rx.sta = container_of(pubsta, struct sta_info, sta);
- rx.sdata = rx.sta->sdata;
+ if (status->link_valid)
+ link_id = status->link_id;
- if (status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(pubsta, link_id))
+ if (pubsta) {
+ if (!ieee80211_rx_data_set_sta(&rx, pubsta, link_id))
goto out;
- if (status->link_valid)
- rx.link_id = status->link_id;
-
/*
* In MLO connection, fetch the link_id using addr2
* when the driver does not pass link_id in status.
if (!link_sta)
goto out;
- rx.link_id = link_sta->link_id;
+ ieee80211_rx_data_set_link(&rx, link_sta->link_id);
}
if (ieee80211_prepare_and_rx_handle(&rx, skb, true))
continue;
}
- if ((status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(&prev_sta->sta,
- link_id)) ||
- (!status->link_valid && prev_sta->sta.mlo))
+ rx.sdata = prev_sta->sdata;
+ if (!ieee80211_rx_data_set_sta(&rx, &prev_sta->sta,
+ link_id))
+ goto out;
+
+ if (!status->link_valid && prev_sta->sta.mlo)
continue;
- rx.link_id = status->link_valid ? link_id : -1;
- rx.sta = prev_sta;
- rx.sdata = prev_sta->sdata;
ieee80211_prepare_and_rx_handle(&rx, skb, false);
prev_sta = sta;
}
if (prev_sta) {
- if ((status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(&prev_sta->sta,
- link_id)) ||
- (!status->link_valid && prev_sta->sta.mlo))
+ rx.sdata = prev_sta->sdata;
+ if (!ieee80211_rx_data_set_sta(&rx, &prev_sta->sta,
+ link_id))
goto out;
- rx.link_id = status->link_valid ? link_id : -1;
- rx.sta = prev_sta;
- rx.sdata = prev_sta->sdata;
+ if (!status->link_valid && prev_sta->sta.mlo)
+ goto out;
if (ieee80211_prepare_and_rx_handle(&rx, skb, true))
return;
struct sk_buff *purge_skb = NULL;
if (test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) {
- info->flags |= IEEE80211_TX_CTL_AMPDU;
reset_agg_timer = true;
} else if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) {
/*
if (!tid_tx) {
/* do nothing, let packet pass through */
} else if (test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) {
- info->flags |= IEEE80211_TX_CTL_AMPDU;
reset_agg_timer = true;
} else {
queued = true;
info->band = fast_tx->band;
info->control.vif = &sdata->vif;
info->flags = IEEE80211_TX_CTL_FIRST_FRAGMENT |
- IEEE80211_TX_CTL_DONTFRAG |
- (ampdu ? IEEE80211_TX_CTL_AMPDU : 0);
+ IEEE80211_TX_CTL_DONTFRAG;
info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT |
u32_encode_bits(IEEE80211_LINK_UNSPECIFIED,
IEEE80211_TX_CTRL_MLO_LINK);
struct ieee80211_tx_data tx;
ieee80211_tx_result r;
struct ieee80211_vif *vif = txq->vif;
+ int q = vif->hw_queue[txq->ac];
+ bool q_stopped;
WARN_ON_ONCE(softirq_count() == 0);
return NULL;
begin:
- spin_lock_bh(&fq->lock);
-
- if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ||
- test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags))
- goto out;
+ spin_lock(&local->queue_stop_reason_lock);
+ q_stopped = local->queue_stop_reasons[q];
+ spin_unlock(&local->queue_stop_reason_lock);
- if (vif->txqs_stopped[txq->ac]) {
- set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags);
- goto out;
+ if (unlikely(q_stopped)) {
+ /* mark for waking later */
+ set_bit(IEEE80211_TXQ_DIRTY, &txqi->flags);
+ return NULL;
}
+ spin_lock_bh(&fq->lock);
+
/* Make sure fragments stay together. */
skb = __skb_dequeue(&txqi->frags);
if (unlikely(skb)) {
IEEE80211_SKB_CB(skb)->control.flags &=
~IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
} else {
+ if (unlikely(test_bit(IEEE80211_TXQ_STOP, &txqi->flags)))
+ goto out;
+
skb = fq_tin_dequeue(fq, tin, fq_tin_dequeue_func);
}
}
if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags))
- info->flags |= IEEE80211_TX_CTL_AMPDU;
- else
- info->flags &= ~IEEE80211_TX_CTL_AMPDU;
+ info->flags |= (IEEE80211_TX_CTL_AMPDU |
+ IEEE80211_TX_CTL_DONTFRAG);
if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
if (!ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) {
info = IEEE80211_SKB_CB(skb);
memset(info, 0, sizeof(*info));
- if (tid_tx)
- info->flags |= IEEE80211_TX_CTL_AMPDU;
info->hw_queue = sdata->vif.hw_queue[queue];
struct ieee80211_sub_if_data *sdata,
struct ieee80211_txq *queue)
{
- int q = sdata->vif.hw_queue[queue->ac];
struct ieee80211_tx_control control = {
.sta = queue->sta,
};
struct sk_buff *skb;
- unsigned long flags;
- bool q_stopped;
while (1) {
- spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
- q_stopped = local->queue_stop_reasons[q];
- spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
-
- if (q_stopped)
- break;
-
skb = ieee80211_tx_dequeue(&local->hw, queue);
if (!skb)
break;
local_bh_disable();
spin_lock(&fq->lock);
- sdata->vif.txqs_stopped[ac] = false;
-
if (!test_bit(SDATA_STATE_RUNNING, &sdata->state))
goto out;
if (ac != txq->ac)
continue;
- if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX,
+ if (!test_and_clear_bit(IEEE80211_TXQ_DIRTY,
&txqi->flags))
continue;
txqi = to_txq_info(vif->txq);
- if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags) ||
+ if (!test_and_clear_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) ||
(ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac)
goto out;
bool refcounted)
{
struct ieee80211_local *local = hw_to_local(hw);
- struct ieee80211_sub_if_data *sdata;
- int n_acs = IEEE80211_NUM_ACS;
trace_stop_queue(local, queue, reason);
else
local->q_stop_reasons[queue][reason]++;
- if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue]))
- return;
-
- if (local->hw.queues < IEEE80211_NUM_ACS)
- n_acs = 1;
-
- rcu_read_lock();
- list_for_each_entry_rcu(sdata, &local->interfaces, list) {
- int ac;
-
- if (!sdata->dev)
- continue;
-
- for (ac = 0; ac < n_acs; ac++) {
- if (sdata->vif.hw_queue[ac] == queue ||
- sdata->vif.cab_queue == queue) {
- spin_lock(&local->fq.lock);
- sdata->vif.txqs_stopped[ac] = true;
- spin_unlock(&local->fq.lock);
- }
- }
- }
- rcu_read_unlock();
+ set_bit(reason, &local->queue_stop_reasons[queue]);
}
void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue,
ret = ieee802154_parse_frame_start(skb, &hdr);
if (ret) {
pr_debug("got invalid frame\n");
- kfree_skb(skb);
return;
}
static void mctp_sk_close(struct sock *sk, long timeout)
{
- struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
-
- del_timer_sync(&msk->key_expiry);
sk_common_release(sk);
}
spin_lock_irqsave(&key->lock, fl2);
__mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED);
}
+ sock_set_flag(sk, SOCK_DEAD);
spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+ /* Since there are no more tag allocations (we have removed all of the
+ * keys), stop any pending expiry events. the timer cannot be re-queued
+ * as the sk is no longer observable
+ */
+ del_timer_sync(&msk->key_expiry);
+}
+
+static void mctp_sk_destruct(struct sock *sk)
+{
+ skb_queue_purge(&sk->sk_receive_queue);
}
static struct proto mctp_proto = {
return -ENOMEM;
sock_init_data(sock, sk);
+ sk->sk_destruct = mctp_sk_destruct;
rc = 0;
if (sk->sk_prot->init)
key->valid = true;
spin_lock_init(&key->lock);
refcount_set(&key->refs, 1);
+ sock_hold(key->sk);
return key;
}
mctp_dev_release_key(key->dev, key);
spin_unlock_irqrestore(&key->lock, flags);
+ sock_put(key->sk);
kfree(key);
}
spin_lock_irqsave(&net->mctp.keys_lock, flags);
+ if (sock_flag(&msk->sk, SOCK_DEAD)) {
+ rc = -EINVAL;
+ goto out_unlock;
+ }
+
hlist_for_each_entry(tmp, &net->mctp.keys, hlist) {
if (mctp_key_match(tmp, key->local_addr, key->peer_addr,
key->tag)) {
hlist_add_head(&key->sklist, &msk->keys);
}
+out_unlock:
spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
return rc;
static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
{
+ struct mctp_sk_key *key, *any_key = NULL;
struct net *net = dev_net(skb->dev);
- struct mctp_sk_key *key;
struct mctp_sock *msk;
struct mctp_hdr *mh;
unsigned long f;
* key for reassembly - we'll create a more specific
* one for future packets if required (ie, !EOM).
*/
- key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f);
- if (key) {
- msk = container_of(key->sk,
+ any_key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f);
+ if (any_key) {
+ msk = container_of(any_key->sk,
struct mctp_sock, sk);
- spin_unlock_irqrestore(&key->lock, f);
- mctp_key_unref(key);
- key = NULL;
+ spin_unlock_irqrestore(&any_key->lock, f);
}
}
* this function.
*/
rc = mctp_key_add(key, msk);
- if (rc) {
- kfree(key);
- } else {
+ if (!rc)
trace_mctp_key_acquire(key);
- /* we don't need to release key->lock on exit */
- mctp_key_unref(key);
- }
+ /* we don't need to release key->lock on exit, so
+ * clean up here and suppress the unlock via
+ * setting to NULL
+ */
+ mctp_key_unref(key);
key = NULL;
} else {
spin_unlock_irqrestore(&key->lock, f);
mctp_key_unref(key);
}
+ if (any_key)
+ mctp_key_unref(any_key);
out:
if (rc)
kfree_skb(skb);
free:
kfree(table);
out:
+ mdev->sysctl = NULL;
return -ENOBUFS;
}
struct net *net = dev_net(dev);
struct ctl_table *table;
+ if (!mdev->sysctl)
+ return;
+
table = mdev->sysctl->ctl_table_arg;
unregister_net_sysctl_table(mdev->sysctl);
kfree(table);
}
}
+/* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses,
+ * otherwise allow any matching local/remote pair
+ */
+bool mptcp_pm_addr_families_match(const struct sock *sk,
+ const struct mptcp_addr_info *loc,
+ const struct mptcp_addr_info *rem)
+{
+ bool mptcp_is_v4 = sk->sk_family == AF_INET;
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ bool loc_is_v4 = loc->family == AF_INET || ipv6_addr_v4mapped(&loc->addr6);
+ bool rem_is_v4 = rem->family == AF_INET || ipv6_addr_v4mapped(&rem->addr6);
+
+ if (mptcp_is_v4)
+ return loc_is_v4 && rem_is_v4;
+
+ if (ipv6_only_sock(sk))
+ return !loc_is_v4 && !rem_is_v4;
+
+ return loc_is_v4 == rem_is_v4;
+#else
+ return mptcp_is_v4 && loc->family == AF_INET && rem->family == AF_INET;
+#endif
+}
+
void mptcp_pm_data_reset(struct mptcp_sock *msk)
{
u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
{
int addrlen = sizeof(struct sockaddr_in);
struct sockaddr_storage addr;
- struct mptcp_sock *msk;
struct socket *ssock;
+ struct sock *newsk;
int backlog = 1024;
int err;
if (err)
return err;
- msk = mptcp_sk(entry->lsk->sk);
- if (!msk)
+ newsk = entry->lsk->sk;
+ if (!newsk)
return -EINVAL;
- ssock = __mptcp_nmpc_socket(msk);
+ lock_sock(newsk);
+ ssock = __mptcp_nmpc_socket(mptcp_sk(newsk));
+ release_sock(newsk);
if (!ssock)
return -EINVAL;
}
sk = (struct sock *)msk;
+
+ if (!mptcp_pm_addr_families_match(sk, &addr_l, &addr_r)) {
+ GENL_SET_ERR_MSG(info, "families mismatch");
+ err = -EINVAL;
+ goto create_err;
+ }
+
lock_sock(sk);
err = __mptcp_subflow_connect(sk, &addr_l, &addr_r);
struct socket *ssock;
int err;
- err = mptcp_subflow_create_socket(sk, &ssock);
+ err = mptcp_subflow_create_socket(sk, sk->sk_family, &ssock);
if (err)
return err;
set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
}
+static int mptcp_disconnect(struct sock *sk, int flags);
+
static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
size_t len, int *copied_syn)
{
lock_sock(ssk);
msg->msg_flags |= MSG_DONTWAIT;
msk->connect_flags = O_NONBLOCK;
- msk->is_sendmsg = 1;
+ msk->fastopening = 1;
ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
- msk->is_sendmsg = 0;
+ msk->fastopening = 0;
msg->msg_flags = saved_flags;
release_sock(ssk);
*/
if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
*copied_syn = 0;
+ } else if (ret && ret != -EINPROGRESS) {
+ mptcp_disconnect(sk, 0);
}
return ret;
/* otherwise tcp will dispose of the ssk and subflow ctx */
if (ssk->sk_state == TCP_LISTEN) {
tcp_set_state(ssk, TCP_CLOSE);
- mptcp_subflow_queue_clean(ssk);
+ mptcp_subflow_queue_clean(sk, ssk);
inet_csk_listen_stop(ssk);
mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
}
struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
bool do_cancel_work = false;
+ int subflows_alive = 0;
sk->sk_shutdown = SHUTDOWN_MASK;
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast_nested(ssk);
+ subflows_alive += ssk->sk_state != TCP_CLOSE;
+
/* since the close timeout takes precedence on the fail one,
* cancel the latter
*/
}
sock_orphan(sk);
+ /* all the subflows are closed, only timeout can change the msk
+ * state, let's not keep resources busy for no reasons
+ */
+ if (subflows_alive == 0)
+ inet_sk_state_store(sk, TCP_CLOSE);
+
sock_hold(sk);
pr_debug("msk=%p state=%d", sk, sk->sk_state);
if (msk->token)
{
struct mptcp_sock *msk = mptcp_sk(sk);
+ /* We are on the fastopen error path. We can't call straight into the
+ * subflows cleanup code due to lock nesting (we are already under
+ * msk->firstsocket lock). Do nothing and leave the cleanup to the
+ * caller.
+ */
+ if (msk->fastopening)
+ return 0;
+
inet_sk_state_store(sk, TCP_CLOSE);
mptcp_stop_timer(sk);
/* if reaching here via the fastopen/sendmsg path, the caller already
* acquired the subflow socket lock, too.
*/
- if (msk->is_sendmsg)
+ if (msk->fastopening)
err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
else
err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
u8 recvmsg_inq:1,
cork:1,
nodelay:1,
- is_sendmsg:1;
+ fastopening:1;
int connect_flags;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct mptcp_subflow_context *subflow);
void __mptcp_subflow_send_ack(struct sock *ssk);
void mptcp_subflow_reset(struct sock *ssk);
-void mptcp_subflow_queue_clean(struct sock *ssk);
+void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
bool __mptcp_close(struct sock *sk, long timeout);
/* called with sk socket lock held */
int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
const struct mptcp_addr_info *remote);
-int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
+int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
+ struct socket **new_sock);
void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
struct sockaddr_storage *addr,
unsigned short family);
int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
bool require_family,
struct mptcp_pm_addr_entry *entry);
+bool mptcp_pm_addr_families_match(const struct sock *sk,
+ const struct mptcp_addr_info *loc,
+ const struct mptcp_addr_info *rem);
void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
+ struct sock *sk = (struct sock *)msk;
struct socket *sock;
+ int ret = -EINVAL;
/* Limit to first subflow, before the connection establishment */
+ lock_sock(sk);
sock = __mptcp_nmpc_socket(msk);
if (!sock)
- return -EINVAL;
+ goto unlock;
- return tcp_setsockopt(sock->sk, level, optname, optval, optlen);
+ ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen);
+
+unlock:
+ release_sock(sk);
+ return ret;
}
static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
int err = sock_error(ssk);
+ int ssk_state;
if (!err)
continue;
if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk))
continue;
- inet_sk_state_store(sk, inet_sk_state_load(ssk));
+ /* We need to propagate only transition to CLOSE state.
+ * Orphaned socket will see such state change via
+ * subflow_sched_work_if_closed() and that path will properly
+ * destroy the msk as needed.
+ */
+ ssk_state = inet_sk_state_load(ssk);
+ if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
+ inet_sk_state_store(sk, ssk_state);
sk->sk_err = -err;
/* This barrier is coupled with smp_rmb() in mptcp_poll() */
if (!mptcp_is_fully_established(sk))
goto err_out;
- err = mptcp_subflow_create_socket(sk, &sf);
+ err = mptcp_subflow_create_socket(sk, loc->family, &sf);
if (err)
goto err_out;
#endif
ssk->sk_prot = &tcp_prot;
}
-int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
+
+int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
+ struct socket **new_sock)
{
struct mptcp_subflow_context *subflow;
struct net *net = sock_net(sk);
if (unlikely(!sk->sk_socket))
return -EINVAL;
- err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP,
- &sf);
+ err = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &sf);
if (err)
return err;
- lock_sock(sf->sk);
+ lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING);
/* the newly created socket has to be in the same cgroup as its parent */
mptcp_attach_cgroup(sk, sf->sk);
}
}
-void mptcp_subflow_queue_clean(struct sock *listener_ssk)
+void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
{
struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
struct mptcp_sock *msk, *next, *head = NULL;
do_cancel_work = __mptcp_close(sk, 0);
release_sock(sk);
- if (do_cancel_work)
+ if (do_cancel_work) {
+ /* lockdep will report a false positive ABBA deadlock
+ * between cancel_work_sync and the listener socket.
+ * The involved locks belong to different sockets WRT
+ * the existing AB chain.
+ * Using a per socket key is problematic as key
+ * deregistration requires process context and must be
+ * performed at socket disposal time, in atomic
+ * context.
+ * Just tell lockdep to consider the listener socket
+ * released here.
+ */
+ mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
mptcp_cancel_work(sk);
+ mutex_acquire(&listener_sk->sk_lock.dep_map,
+ SINGLE_DEPTH_NESTING, 0, _RET_IP_);
+ }
sock_put(sk);
}
return -IPSET_ERR_BITMAP_RANGE;
pr_debug("mask_bits %u, netmask %u\n", mask_bits, netmask);
- hosts = 2 << (32 - netmask - 1);
- elements = 2 << (netmask - mask_bits - 1);
+ hosts = 2U << (32 - netmask - 1);
+ elements = 2UL << (netmask - mask_bits - 1);
}
if (elements > IPSET_BITMAP_MAX_RANGE + 1)
return -IPSET_ERR_BITMAP_RANGE_SIZE;
ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried);
ip_set_unlock(set);
retried = true;
- } while (ret == -EAGAIN &&
- set->variant->resize &&
- (ret = set->variant->resize(set, retried)) == 0);
+ } while (ret == -ERANGE ||
+ (ret == -EAGAIN &&
+ set->variant->resize &&
+ (ret = set->variant->resize(set, retried)) == 0));
if (!ret || (ret == -IPSET_ERR_EXIST && eexist))
return 0;
hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ip4 *h = set->data;
+ struct hash_ip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip4_elem e = { 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, hosts;
+ u32 ip = 0, ip_to = 0, hosts, i = 0;
int ret = 0;
if (tb[IPSET_ATTR_LINENO])
hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1);
- /* 64bit division is not allowed on 32bit */
- if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
- for (; ip <= ip_to;) {
+ for (; ip <= ip_to; i++) {
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ip4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipmark4 *h = set->data;
+ struct hash_ipmark4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipmark4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0;
+ u32 ip, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
ip_set_mask_from_to(ip, ip_to, cidr);
}
- if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
- for (; ip <= ip_to; ip++) {
+ for (; ip <= ip_to; ip++, i++) {
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipmark4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipport4 *h = set->data;
+ struct hash_ipport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport4_elem e = { .ip = 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to, i = 0;
bool with_ports = false;
int ret;
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.ip = htonl(ip);
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipport4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportip4 *h = set->data;
+ struct hash_ipportip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip4_elem e = { .ip = 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to, i = 0;
bool with_ports = false;
int ret;
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.ip = htonl(ip);
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipportip4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportnet4 *h = set->data;
+ struct hash_ipportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0, p = 0, port, port_to;
- u32 ip2_from = 0, ip2_to = 0, ip2;
+ u32 ip2_from = 0, ip2_to = 0, ip2, i = 0;
bool with_ports = false;
u8 cidr;
int ret;
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
ip2_to = ip2_from;
if (tb[IPSET_ATTR_IP2_TO]) {
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
for (; p <= port_to; p++) {
e.port = htons(p);
do {
+ i++;
e.ip2 = htonl(ip2);
ip2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr);
e.cidr = cidr - 1;
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipportnet4_data_next(&h->next,
+ &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_net4 *h = set->data;
+ struct hash_net4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net4_elem e = { .cidr = HOST_MASK };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, ipn, n = 0;
+ u32 ip = 0, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
if (ip + UINT_MAX == ip_to)
return -IPSET_ERR_HASH_RANGE;
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried)
ip = ntohl(h->next.ip);
do {
+ i++;
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_net4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, ipn, n = 0;
+ u32 ip = 0, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
} else {
ip_set_mask_from_to(ip, ip_to, e.cidr);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried)
ip = ntohl(h->next.ip);
do {
+ i++;
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netiface4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
ret = adtfn(set, &e, &ext, &ext, flags);
hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netnet4 *h = set->data;
+ struct hash_netnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0;
- u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn;
- u64 n = 0, m = 0;
+ u32 ip2 = 0, ip2_from = 0, ip2_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
} else {
ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
- n++;
- } while (ipn++ < ip_to);
- ipn = ip2_from;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
- m++;
- } while (ipn++ < ip2_to);
-
- if (n*m > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip[0]);
e.ip[0] = htonl(ip);
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
do {
+ i++;
e.ip[1] = htonl(ip2);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netnet4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netport4 *h = set->data;
+ struct hash_netport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn;
- u64 n = 0;
+ u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0;
bool with_ports = false;
u8 cidr;
int ret;
} else {
ip_set_mask_from_to(ip, ip_to, e.cidr + 1);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip);
e.ip = htonl(ip);
ip = ip_set_range_to_cidr(ip, ip_to, &cidr);
e.cidr = cidr - 1;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netport4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
+static u32
+hash_netportnet4_range_to_cidr(u32 from, u32 to, u8 *cidr)
+{
+ if (from == 0 && to == UINT_MAX) {
+ *cidr = 0;
+ return to;
+ }
+ return ip_set_range_to_cidr(from, to, cidr);
+}
+
static int
hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netportnet4 *h = set->data;
+ struct hash_netportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netportnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0, p = 0, port, port_to;
- u32 ip2_from = 0, ip2_to = 0, ip2, ipn;
- u64 n = 0, m = 0;
+ u32 ip2_from = 0, ip2_to = 0, ip2, i = 0;
bool with_ports = false;
int ret;
} else {
ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
- n++;
- } while (ipn++ < ip_to);
- ipn = ip2_from;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
- m++;
- } while (ipn++ < ip2_to);
-
- if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip[0]);
do {
e.ip[0] = htonl(ip);
- ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
+ ip = hash_netportnet4_range_to_cidr(ip, ip_to, &e.cidr[0]);
for (; p <= port_to; p++) {
e.port = htons(p);
do {
+ i++;
e.ip[1] = htonl(ip2);
- ip2 = ip_set_range_to_cidr(ip2, ip2_to,
- &e.cidr[1]);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netportnet4_data_next(&h->next,
+ &e);
+ return -ERANGE;
+ }
+ ip2 = hash_netportnet4_range_to_cidr(ip2,
+ ip2_to, &e.cidr[1]);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
struct nf_conn *ct;
bool seqadj_needed;
__be16 frag_off;
+ int start;
u8 pnum;
ct = nf_ct_get(skb, &ctinfo);
break;
case NFPROTO_IPV6:
pnum = ipv6_hdr(skb)->nexthdr;
- protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off);
- if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
+ start = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off);
+ if (start < 0 || (frag_off & htons(~0x7)) != 0)
return nf_conntrack_confirm(skb);
+
+ protoff = start;
break;
default:
return nf_conntrack_confirm(skb);
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_conntrack_timeout.h>
-/* FIXME: Examine ipfilter's timeouts and conntrack transitions more
- closely. They're more complex. --RR
-
- And so for me for SCTP :D -Kiran */
-
static const char *const sctp_conntrack_names[] = {
- "NONE",
- "CLOSED",
- "COOKIE_WAIT",
- "COOKIE_ECHOED",
- "ESTABLISHED",
- "SHUTDOWN_SENT",
- "SHUTDOWN_RECD",
- "SHUTDOWN_ACK_SENT",
- "HEARTBEAT_SENT",
- "HEARTBEAT_ACKED",
+ [SCTP_CONNTRACK_NONE] = "NONE",
+ [SCTP_CONNTRACK_CLOSED] = "CLOSED",
+ [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT",
+ [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED",
+ [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED",
+ [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT",
+ [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD",
+ [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT",
+ [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT",
};
#define SECS * HZ
[SCTP_CONNTRACK_CLOSED] = 10 SECS,
[SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS,
[SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS,
- [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS,
+ [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS,
[SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000,
[SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000,
[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS,
[SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS,
- [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS,
- [SCTP_CONNTRACK_DATA_SENT] = 30 SECS,
};
#define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1
#define sSR SCTP_CONNTRACK_SHUTDOWN_RECD
#define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT
#define sHS SCTP_CONNTRACK_HEARTBEAT_SENT
-#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED
-#define sDS SCTP_CONNTRACK_DATA_SENT
#define sIV SCTP_CONNTRACK_MAX
/*
CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of
the SHUTDOWN chunk. Connection is closed.
HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow.
-HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK/DATA/SACK in the direction
- opposite to that of the HEARTBEAT/DATA chunk. Secondary connection
- is established.
-DATA_SENT - We have seen a DATA/SACK in a new flow.
*/
/* TODO
*/
/* SCTP conntrack state transitions */
-static const u8 sctp_conntracks[2][12][SCTP_CONNTRACK_MAX] = {
+static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
{
/* ORIGINAL */
-/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */
-/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA, sCW},
-/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},
-/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
-/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS, sCL},
-/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA, sSA},
-/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't have Stale cookie*/
-/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* 5.2.4 - Big TODO */
-/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't come in orig dir */
-/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA, sCL},
-/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS},
-/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS},
-/* data/sack */ {sDS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}
+/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
+/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW},
+/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},
+/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
+/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL},
+/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA},
+/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/
+/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */
+/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */
+/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL},
+/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
+/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
},
{
/* REPLY */
-/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */
-/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* INIT in sCL Big TODO */
-/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},
-/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL, sIV},
-/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR, sIV},
-/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA, sIV},
-/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA, sIV},
-/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* Can't come in reply dir */
-/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA, sIV},
-/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA, sIV},
-/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sHA},
-/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA},
-/* data/sack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA},
+/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
+/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */
+/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV},
+/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV},
+/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV},
+/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV},
+/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV},
+/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */
+/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV},
+/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV},
+/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
+/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES},
}
};
}
#endif
+/* do_basic_checks ensures sch->length > 0, do not use before */
#define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \
for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \
(offset) < (skb)->len && \
pr_debug("SCTP_CID_HEARTBEAT_ACK");
i = 10;
break;
- case SCTP_CID_DATA:
- case SCTP_CID_SACK:
- pr_debug("SCTP_CID_DATA/SACK");
- i = 11;
- break;
default:
/* Other chunks like DATA or SACK do not change the state */
pr_debug("Unknown chunk type, Will stay in %s\n",
ih->init_tag);
ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag;
- } else if (sch->type == SCTP_CID_HEARTBEAT ||
- sch->type == SCTP_CID_DATA ||
- sch->type == SCTP_CID_SACK) {
+ } else if (sch->type == SCTP_CID_HEARTBEAT) {
pr_debug("Setting vtag %x for secondary conntrack\n",
sh->vtag);
ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag;
if (!sctp_new(ct, skb, sh, dataoff))
return -NF_ACCEPT;
- } else {
- /* Check the verification tag (Sec 8.5) */
- if (!test_bit(SCTP_CID_INIT, map) &&
- !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) &&
- !test_bit(SCTP_CID_COOKIE_ECHO, map) &&
- !test_bit(SCTP_CID_ABORT, map) &&
- !test_bit(SCTP_CID_SHUTDOWN_ACK, map) &&
- !test_bit(SCTP_CID_HEARTBEAT, map) &&
- !test_bit(SCTP_CID_HEARTBEAT_ACK, map) &&
- sh->vtag != ct->proto.sctp.vtag[dir]) {
- pr_debug("Verification tag check failed\n");
- goto out;
- }
+ }
+
+ /* Check the verification tag (Sec 8.5) */
+ if (!test_bit(SCTP_CID_INIT, map) &&
+ !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) &&
+ !test_bit(SCTP_CID_COOKIE_ECHO, map) &&
+ !test_bit(SCTP_CID_ABORT, map) &&
+ !test_bit(SCTP_CID_SHUTDOWN_ACK, map) &&
+ !test_bit(SCTP_CID_HEARTBEAT, map) &&
+ !test_bit(SCTP_CID_HEARTBEAT_ACK, map) &&
+ sh->vtag != ct->proto.sctp.vtag[dir]) {
+ pr_debug("Verification tag check failed\n");
+ goto out;
}
old_state = new_state = SCTP_CONNTRACK_NONE;
for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) {
/* Special cases of Verification tag check (Sec 8.5.1) */
if (sch->type == SCTP_CID_INIT) {
- /* Sec 8.5.1 (A) */
+ /* (A) vtag MUST be zero */
if (sh->vtag != 0)
goto out_unlock;
} else if (sch->type == SCTP_CID_ABORT) {
- /* Sec 8.5.1 (B) */
- if (sh->vtag != ct->proto.sctp.vtag[dir] &&
- sh->vtag != ct->proto.sctp.vtag[!dir])
+ /* (B) vtag MUST match own vtag if T flag is unset OR
+ * MUST match peer's vtag if T flag is set
+ */
+ if ((!(sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[dir]) ||
+ ((sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[!dir]))
goto out_unlock;
} else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) {
- /* Sec 8.5.1 (C) */
- if (sh->vtag != ct->proto.sctp.vtag[dir] &&
- sh->vtag != ct->proto.sctp.vtag[!dir] &&
- sch->flags & SCTP_CHUNK_FLAG_T)
+ /* (C) vtag MUST match own vtag if T flag is unset OR
+ * MUST match peer's vtag if T flag is set
+ */
+ if ((!(sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[dir]) ||
+ ((sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[!dir]))
goto out_unlock;
} else if (sch->type == SCTP_CID_COOKIE_ECHO) {
- /* Sec 8.5.1 (D) */
+ /* (D) vtag must be same as init_vtag as found in INIT_ACK */
if (sh->vtag != ct->proto.sctp.vtag[dir])
goto out_unlock;
} else if (sch->type == SCTP_CID_HEARTBEAT) {
} else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) {
ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED;
}
- } else if (sch->type == SCTP_CID_DATA || sch->type == SCTP_CID_SACK) {
- if (ct->proto.sctp.vtag[dir] == 0) {
- pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir);
- ct->proto.sctp.vtag[dir] = sh->vtag;
- }
}
old_state = ct->proto.sctp.state;
}
ct->proto.sctp.state = new_state;
- if (old_state != new_state)
+ if (old_state != new_state) {
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
+ if (new_state == SCTP_CONNTRACK_ESTABLISHED &&
+ !test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
+ nf_conntrack_event_cache(IPCT_ASSURED, ct);
+ }
}
spin_unlock_bh(&ct->lock);
nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
- if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED &&
- dir == IP_CT_DIR_REPLY &&
- new_state == SCTP_CONNTRACK_ESTABLISHED) {
- pr_debug("Setting assured bit\n");
- set_bit(IPS_ASSURED_BIT, &ct->status);
- nf_conntrack_event_cache(IPCT_ASSURED, ct);
- }
-
return NF_ACCEPT;
out_unlock:
[CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 },
[CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 },
[CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 },
- [CTA_TIMEOUT_SCTP_DATA_SENT] = { .type = NLA_U32 },
};
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
ct->proto.tcp.last_flags |=
IP_CT_EXP_CHALLENGE_ACK;
}
+
+ /* possible challenge ack reply to syn */
+ if (old_state == TCP_CONNTRACK_SYN_SENT &&
+ index == TCP_ACK_SET &&
+ dir == IP_CT_DIR_REPLY)
+ ct->proto.tcp.last_ack = ntohl(th->ack_seq);
+
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, state,
"packet (index %d) in dir %d ignored, state %s",
* segments we ignored. */
goto in_window;
}
+
+ /* Reset in response to a challenge-ack we let through earlier */
+ if (old_state == TCP_CONNTRACK_SYN_SENT &&
+ ct->proto.tcp.last_index == TCP_ACK_SET &&
+ ct->proto.tcp.last_dir == IP_CT_DIR_REPLY &&
+ ntohl(th->seq) == ct->proto.tcp.last_ack)
+ goto in_window;
+
break;
default:
/* Keep compilers happy. */
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD,
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT,
- NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED,
- NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT,
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST,
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = {
- .procname = "nf_conntrack_sctp_timeout_heartbeat_acked",
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
- [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT] = {
- .procname = "nf_conntrack_sctp_timeout_data_sent",
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = {
XASSIGN(SHUTDOWN_RECD, sn);
XASSIGN(SHUTDOWN_ACK_SENT, sn);
XASSIGN(HEARTBEAT_SENT, sn);
- XASSIGN(HEARTBEAT_ACKED, sn);
- XASSIGN(DATA_SENT, sn);
#undef XASSIGN
#endif
}
return 0;
}
-static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
- struct nft_set *set)
+static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
+ struct nft_set *set,
+ const struct nft_set_desc *desc)
{
struct nft_trans *trans;
if (trans == NULL)
return -ENOMEM;
- if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) {
+ if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) {
nft_trans_set_id(trans) =
ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID]));
nft_activate_next(ctx->net, set);
}
nft_trans_set(trans) = set;
+ if (desc) {
+ nft_trans_set_update(trans) = true;
+ nft_trans_set_gc_int(trans) = desc->gc_int;
+ nft_trans_set_timeout(trans) = desc->timeout;
+ }
nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
}
+static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
+ struct nft_set *set)
+{
+ return __nft_trans_set_add(ctx, msg_type, set, NULL);
+}
+
static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
{
int err;
static const struct nft_set_ops *
nft_select_set_ops(const struct nft_ctx *ctx,
const struct nlattr * const nla[],
- const struct nft_set_desc *desc,
- enum nft_set_policies policy)
+ const struct nft_set_desc *desc)
{
struct nftables_pernet *nft_net = nft_pernet(ctx->net);
const struct nft_set_ops *ops, *bops;
if (!ops->estimate(desc, flags, &est))
continue;
- switch (policy) {
+ switch (desc->policy) {
case NFT_SET_POL_PERFORMANCE:
if (est.lookup < best.lookup)
break;
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
const struct nft_set *set, u16 event, u16 flags)
{
- struct nlmsghdr *nlh;
+ u64 timeout = READ_ONCE(set->timeout);
+ u32 gc_int = READ_ONCE(set->gc_int);
u32 portid = ctx->portid;
+ struct nlmsghdr *nlh;
struct nlattr *nest;
u32 seq = ctx->seq;
int i;
nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype)))
goto nla_put_failure;
- if (set->timeout &&
+ if (timeout &&
nla_put_be64(skb, NFTA_SET_TIMEOUT,
- nf_jiffies64_to_msecs(set->timeout),
+ nf_jiffies64_to_msecs(timeout),
NFTA_SET_PAD))
goto nla_put_failure;
- if (set->gc_int &&
- nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(set->gc_int)))
+ if (gc_int &&
+ nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(gc_int)))
goto nla_put_failure;
if (set->policy != NFT_SET_POL_PERFORMANCE) {
return err;
}
+static int nft_set_expr_alloc(struct nft_ctx *ctx, struct nft_set *set,
+ const struct nlattr * const *nla,
+ struct nft_expr **exprs, int *num_exprs,
+ u32 flags)
+{
+ struct nft_expr *expr;
+ int err, i;
+
+ if (nla[NFTA_SET_EXPR]) {
+ expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_EXPR]);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+ exprs[0] = expr;
+ (*num_exprs)++;
+ } else if (nla[NFTA_SET_EXPRESSIONS]) {
+ struct nlattr *tmp;
+ int left;
+
+ if (!(flags & NFT_SET_EXPR)) {
+ err = -EINVAL;
+ goto err_set_expr_alloc;
+ }
+ i = 0;
+ nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
+ if (i == NFT_SET_EXPR_MAX) {
+ err = -E2BIG;
+ goto err_set_expr_alloc;
+ }
+ if (nla_type(tmp) != NFTA_LIST_ELEM) {
+ err = -EINVAL;
+ goto err_set_expr_alloc;
+ }
+ expr = nft_set_elem_expr_alloc(ctx, set, tmp);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+ exprs[i++] = expr;
+ (*num_exprs)++;
+ }
+ }
+
+ return 0;
+
+err_set_expr_alloc:
+ for (i = 0; i < *num_exprs; i++)
+ nft_expr_destroy(ctx, exprs[i]);
+
+ return err;
+}
+
+static bool nft_set_is_same(const struct nft_set *set,
+ const struct nft_set_desc *desc,
+ struct nft_expr *exprs[], u32 num_exprs, u32 flags)
+{
+ int i;
+
+ if (set->ktype != desc->ktype ||
+ set->dtype != desc->dtype ||
+ set->flags != flags ||
+ set->klen != desc->klen ||
+ set->dlen != desc->dlen ||
+ set->field_count != desc->field_count ||
+ set->num_exprs != num_exprs)
+ return false;
+
+ for (i = 0; i < desc->field_count; i++) {
+ if (set->field_len[i] != desc->field_len[i])
+ return false;
+ }
+
+ for (i = 0; i < num_exprs; i++) {
+ if (set->exprs[i]->ops != exprs[i]->ops)
+ return false;
+ }
+
+ return true;
+}
+
static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
const struct nlattr * const nla[])
{
- u32 ktype, dtype, flags, policy, gc_int, objtype;
struct netlink_ext_ack *extack = info->extack;
u8 genmask = nft_genmask_next(info->net);
u8 family = info->nfmsg->nfgen_family;
const struct nft_set_ops *ops;
- struct nft_expr *expr = NULL;
struct net *net = info->net;
struct nft_set_desc desc;
struct nft_table *table;
struct nft_set *set;
struct nft_ctx ctx;
size_t alloc_size;
- u64 timeout;
+ int num_exprs = 0;
char *name;
int err, i;
u16 udlen;
+ u32 flags;
u64 size;
if (nla[NFTA_SET_TABLE] == NULL ||
memset(&desc, 0, sizeof(desc));
- ktype = NFT_DATA_VALUE;
+ desc.ktype = NFT_DATA_VALUE;
if (nla[NFTA_SET_KEY_TYPE] != NULL) {
- ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
- if ((ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
+ desc.ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
+ if ((desc.ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
return -EINVAL;
}
return -EOPNOTSUPP;
}
- dtype = 0;
+ desc.dtype = 0;
if (nla[NFTA_SET_DATA_TYPE] != NULL) {
if (!(flags & NFT_SET_MAP))
return -EINVAL;
- dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
- if ((dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
- dtype != NFT_DATA_VERDICT)
+ desc.dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
+ if ((desc.dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
+ desc.dtype != NFT_DATA_VERDICT)
return -EINVAL;
- if (dtype != NFT_DATA_VERDICT) {
+ if (desc.dtype != NFT_DATA_VERDICT) {
if (nla[NFTA_SET_DATA_LEN] == NULL)
return -EINVAL;
desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
if (!(flags & NFT_SET_OBJECT))
return -EINVAL;
- objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
- if (objtype == NFT_OBJECT_UNSPEC ||
- objtype > NFT_OBJECT_MAX)
+ desc.objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
+ if (desc.objtype == NFT_OBJECT_UNSPEC ||
+ desc.objtype > NFT_OBJECT_MAX)
return -EOPNOTSUPP;
} else if (flags & NFT_SET_OBJECT)
return -EINVAL;
else
- objtype = NFT_OBJECT_UNSPEC;
+ desc.objtype = NFT_OBJECT_UNSPEC;
- timeout = 0;
+ desc.timeout = 0;
if (nla[NFTA_SET_TIMEOUT] != NULL) {
if (!(flags & NFT_SET_TIMEOUT))
return -EINVAL;
- err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout);
+ err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout);
if (err)
return err;
}
- gc_int = 0;
+ desc.gc_int = 0;
if (nla[NFTA_SET_GC_INTERVAL] != NULL) {
if (!(flags & NFT_SET_TIMEOUT))
return -EINVAL;
- gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
+ desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
}
- policy = NFT_SET_POL_PERFORMANCE;
+ desc.policy = NFT_SET_POL_PERFORMANCE;
if (nla[NFTA_SET_POLICY] != NULL)
- policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+ desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
if (nla[NFTA_SET_DESC] != NULL) {
err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
return PTR_ERR(set);
}
} else {
+ struct nft_expr *exprs[NFT_SET_EXPR_MAX] = {};
+
if (info->nlh->nlmsg_flags & NLM_F_EXCL) {
NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
return -EEXIST;
if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
- return 0;
+ err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags);
+ if (err < 0)
+ return err;
+
+ err = 0;
+ if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
+ err = -EEXIST;
+ }
+
+ for (i = 0; i < num_exprs; i++)
+ nft_expr_destroy(&ctx, exprs[i]);
+
+ if (err < 0)
+ return err;
+
+ return __nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set, &desc);
}
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
return -ENOENT;
- ops = nft_select_set_ops(&ctx, nla, &desc, policy);
+ ops = nft_select_set_ops(&ctx, nla, &desc);
if (IS_ERR(ops))
return PTR_ERR(ops);
set->table = table;
write_pnet(&set->net, net);
set->ops = ops;
- set->ktype = ktype;
+ set->ktype = desc.ktype;
set->klen = desc.klen;
- set->dtype = dtype;
- set->objtype = objtype;
+ set->dtype = desc.dtype;
+ set->objtype = desc.objtype;
set->dlen = desc.dlen;
set->flags = flags;
set->size = desc.size;
- set->policy = policy;
+ set->policy = desc.policy;
set->udlen = udlen;
set->udata = udata;
- set->timeout = timeout;
- set->gc_int = gc_int;
+ set->timeout = desc.timeout;
+ set->gc_int = desc.gc_int;
set->field_count = desc.field_count;
for (i = 0; i < desc.field_count; i++)
if (err < 0)
goto err_set_init;
- if (nla[NFTA_SET_EXPR]) {
- expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_expr_alloc;
- }
- set->exprs[0] = expr;
- set->num_exprs++;
- } else if (nla[NFTA_SET_EXPRESSIONS]) {
- struct nft_expr *expr;
- struct nlattr *tmp;
- int left;
-
- if (!(flags & NFT_SET_EXPR)) {
- err = -EINVAL;
- goto err_set_expr_alloc;
- }
- i = 0;
- nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
- if (i == NFT_SET_EXPR_MAX) {
- err = -E2BIG;
- goto err_set_expr_alloc;
- }
- if (nla_type(tmp) != NFTA_LIST_ELEM) {
- err = -EINVAL;
- goto err_set_expr_alloc;
- }
- expr = nft_set_elem_expr_alloc(&ctx, set, tmp);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_expr_alloc;
- }
- set->exprs[i++] = expr;
- set->num_exprs++;
- }
- }
+ err = nft_set_expr_alloc(&ctx, set, nla, set->exprs, &num_exprs, flags);
+ if (err < 0)
+ goto err_set_destroy;
+ set->num_exprs = num_exprs;
set->handle = nf_tables_alloc_handle(table);
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
err_set_expr_alloc:
for (i = 0; i < set->num_exprs; i++)
nft_expr_destroy(&ctx, set->exprs[i]);
-
+err_set_destroy:
ops->destroy(set);
err_set_init:
kfree(set->name);
return err;
} else if (set->flags & NFT_SET_TIMEOUT &&
!(flags & NFT_SET_ELEM_INTERVAL_END)) {
- timeout = set->timeout;
+ timeout = READ_ONCE(set->timeout);
}
expiration = 0;
if (err < 0)
goto err_parse_key_end;
- if (timeout != set->timeout) {
+ if (timeout != READ_ONCE(set->timeout)) {
err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
if (err < 0)
goto err_parse_key_end;
nft_flow_rule_destroy(nft_trans_flow_rule(trans));
break;
case NFT_MSG_NEWSET:
- nft_clear(net, nft_trans_set(trans));
- /* This avoids hitting -EBUSY when deleting the table
- * from the transaction.
- */
- if (nft_set_is_anonymous(nft_trans_set(trans)) &&
- !list_empty(&nft_trans_set(trans)->bindings))
- trans->ctx.table->use--;
+ if (nft_trans_set_update(trans)) {
+ struct nft_set *set = nft_trans_set(trans);
+ WRITE_ONCE(set->timeout, nft_trans_set_timeout(trans));
+ WRITE_ONCE(set->gc_int, nft_trans_set_gc_int(trans));
+ } else {
+ nft_clear(net, nft_trans_set(trans));
+ /* This avoids hitting -EBUSY when deleting the table
+ * from the transaction.
+ */
+ if (nft_set_is_anonymous(nft_trans_set(trans)) &&
+ !list_empty(&nft_trans_set(trans)->bindings))
+ trans->ctx.table->use--;
+ }
nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
NFT_MSG_NEWSET, GFP_KERNEL);
nft_trans_destroy(trans);
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSET:
+ if (nft_trans_set_update(trans)) {
+ nft_trans_destroy(trans);
+ break;
+ }
trans->ctx.table->use--;
if (nft_trans_set_bound(trans)) {
nft_trans_destroy(trans);
return false;
if (offset + len > VLAN_ETH_HLEN + vlan_hlen)
- ethlen -= offset + len - VLAN_ETH_HLEN + vlan_hlen;
+ ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen;
memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen);
return !nft_rbtree_interval_end(rbe);
}
-static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
- const struct nft_rbtree_elem *interval)
+static int nft_rbtree_cmp(const struct nft_set *set,
+ const struct nft_rbtree_elem *e1,
+ const struct nft_rbtree_elem *e2)
{
- return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0;
+ return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext),
+ set->klen);
}
static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
const struct nft_rbtree_elem *rbe, *interval = NULL;
u8 genmask = nft_genmask_cur(net);
const struct rb_node *parent;
- const void *this;
int d;
parent = rcu_dereference_raw(priv->root.rb_node);
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
- this = nft_set_ext_key(&rbe->ext);
- d = memcmp(this, key, set->klen);
+ d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen);
if (d < 0) {
parent = rcu_dereference_raw(parent->rb_left);
if (interval &&
- nft_rbtree_equal(set, this, interval) &&
+ !nft_rbtree_cmp(set, rbe, interval) &&
nft_rbtree_interval_end(rbe) &&
nft_rbtree_interval_start(interval))
continue;
return rbe;
}
+static int nft_rbtree_gc_elem(const struct nft_set *__set,
+ struct nft_rbtree *priv,
+ struct nft_rbtree_elem *rbe)
+{
+ struct nft_set *set = (struct nft_set *)__set;
+ struct rb_node *prev = rb_prev(&rbe->node);
+ struct nft_rbtree_elem *rbe_prev;
+ struct nft_set_gc_batch *gcb;
+
+ gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC);
+ if (!gcb)
+ return -ENOMEM;
+
+ /* search for expired end interval coming before this element. */
+ do {
+ rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
+ if (nft_rbtree_interval_end(rbe_prev))
+ break;
+
+ prev = rb_prev(prev);
+ } while (prev != NULL);
+
+ rb_erase(&rbe_prev->node, &priv->root);
+ rb_erase(&rbe->node, &priv->root);
+ atomic_sub(2, &set->nelems);
+
+ nft_set_gc_batch_add(gcb, rbe);
+ nft_set_gc_batch_complete(gcb);
+
+ return 0;
+}
+
+static bool nft_rbtree_update_first(const struct nft_set *set,
+ struct nft_rbtree_elem *rbe,
+ struct rb_node *first)
+{
+ struct nft_rbtree_elem *first_elem;
+
+ first_elem = rb_entry(first, struct nft_rbtree_elem, node);
+ /* this element is closest to where the new element is to be inserted:
+ * update the first element for the node list path.
+ */
+ if (nft_rbtree_cmp(set, rbe, first_elem) < 0)
+ return true;
+
+ return false;
+}
+
static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
struct nft_rbtree_elem *new,
struct nft_set_ext **ext)
{
- bool overlap = false, dup_end_left = false, dup_end_right = false;
+ struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL;
+ struct rb_node *node, *parent, **p, *first = NULL;
struct nft_rbtree *priv = nft_set_priv(set);
u8 genmask = nft_genmask_next(net);
- struct nft_rbtree_elem *rbe;
- struct rb_node *parent, **p;
- int d;
+ int d, err;
- /* Detect overlaps as we descend the tree. Set the flag in these cases:
- *
- * a1. _ _ __>| ?_ _ __| (insert end before existing end)
- * a2. _ _ ___| ?_ _ _>| (insert end after existing end)
- * a3. _ _ ___? >|_ _ __| (insert start before existing end)
- *
- * and clear it later on, as we eventually reach the points indicated by
- * '?' above, in the cases described below. We'll always meet these
- * later, locally, due to tree ordering, and overlaps for the intervals
- * that are the closest together are always evaluated last.
- *
- * b1. _ _ __>| !_ _ __| (insert end before existing start)
- * b2. _ _ ___| !_ _ _>| (insert end after existing start)
- * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf)
- * '--' no nodes falling in this range
- * b4. >|_ _ ! (insert start before existing start)
- *
- * Case a3. resolves to b3.:
- * - if the inserted start element is the leftmost, because the '0'
- * element in the tree serves as end element
- * - otherwise, if an existing end is found immediately to the left. If
- * there are existing nodes in between, we need to further descend the
- * tree before we can conclude the new start isn't causing an overlap
- *
- * or to b4., which, preceded by a3., means we already traversed one or
- * more existing intervals entirely, from the right.
- *
- * For a new, rightmost pair of elements, we'll hit cases b3. and b2.,
- * in that order.
- *
- * The flag is also cleared in two special cases:
- *
- * b5. |__ _ _!|<_ _ _ (insert start right before existing end)
- * b6. |__ _ >|!__ _ _ (insert end right after existing start)
- *
- * which always happen as last step and imply that no further
- * overlapping is possible.
- *
- * Another special case comes from the fact that start elements matching
- * an already existing start element are allowed: insertion is not
- * performed but we return -EEXIST in that case, and the error will be
- * cleared by the caller if NLM_F_EXCL is not present in the request.
- * This way, request for insertion of an exact overlap isn't reported as
- * error to userspace if not desired.
- *
- * However, if the existing start matches a pre-existing start, but the
- * end element doesn't match the corresponding pre-existing end element,
- * we need to report a partial overlap. This is a local condition that
- * can be noticed without need for a tracking flag, by checking for a
- * local duplicated end for a corresponding start, from left and right,
- * separately.
+ /* Descend the tree to search for an existing element greater than the
+ * key value to insert that is greater than the new element. This is the
+ * first element to walk the ordered elements to find possible overlap.
*/
-
parent = NULL;
p = &priv->root.rb_node;
while (*p != NULL) {
parent = *p;
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
- d = memcmp(nft_set_ext_key(&rbe->ext),
- nft_set_ext_key(&new->ext),
- set->klen);
+ d = nft_rbtree_cmp(set, rbe, new);
+
if (d < 0) {
p = &parent->rb_left;
-
- if (nft_rbtree_interval_start(new)) {
- if (nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext) && !*p)
- overlap = false;
- } else {
- if (dup_end_left && !*p)
- return -ENOTEMPTY;
-
- overlap = nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext,
- genmask) &&
- !nft_set_elem_expired(&rbe->ext);
-
- if (overlap) {
- dup_end_right = true;
- continue;
- }
- }
} else if (d > 0) {
- p = &parent->rb_right;
+ if (!first ||
+ nft_rbtree_update_first(set, rbe, first))
+ first = &rbe->node;
- if (nft_rbtree_interval_end(new)) {
- if (dup_end_right && !*p)
- return -ENOTEMPTY;
-
- overlap = nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext,
- genmask) &&
- !nft_set_elem_expired(&rbe->ext);
-
- if (overlap) {
- dup_end_left = true;
- continue;
- }
- } else if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext)) {
- overlap = nft_rbtree_interval_end(rbe);
- }
+ p = &parent->rb_right;
} else {
- if (nft_rbtree_interval_end(rbe) &&
- nft_rbtree_interval_start(new)) {
+ if (nft_rbtree_interval_end(rbe))
p = &parent->rb_left;
-
- if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext))
- overlap = false;
- } else if (nft_rbtree_interval_start(rbe) &&
- nft_rbtree_interval_end(new)) {
+ else
p = &parent->rb_right;
+ }
+ }
+
+ if (!first)
+ first = rb_first(&priv->root);
+
+ /* Detect overlap by going through the list of valid tree nodes.
+ * Values stored in the tree are in reversed order, starting from
+ * highest to lowest value.
+ */
+ for (node = first; node != NULL; node = rb_next(node)) {
+ rbe = rb_entry(node, struct nft_rbtree_elem, node);
- if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext))
- overlap = false;
- } else if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext)) {
- *ext = &rbe->ext;
- return -EEXIST;
- } else {
- overlap = false;
- if (nft_rbtree_interval_end(rbe))
- p = &parent->rb_left;
- else
- p = &parent->rb_right;
+ if (!nft_set_elem_active(&rbe->ext, genmask))
+ continue;
+
+ /* perform garbage collection to avoid bogus overlap reports. */
+ if (nft_set_elem_expired(&rbe->ext)) {
+ err = nft_rbtree_gc_elem(set, priv, rbe);
+ if (err < 0)
+ return err;
+
+ continue;
+ }
+
+ d = nft_rbtree_cmp(set, rbe, new);
+ if (d == 0) {
+ /* Matching end element: no need to look for an
+ * overlapping greater or equal element.
+ */
+ if (nft_rbtree_interval_end(rbe)) {
+ rbe_le = rbe;
+ break;
+ }
+
+ /* first element that is greater or equal to key value. */
+ if (!rbe_ge) {
+ rbe_ge = rbe;
+ continue;
+ }
+
+ /* this is a closer more or equal element, update it. */
+ if (nft_rbtree_cmp(set, rbe_ge, new) != 0) {
+ rbe_ge = rbe;
+ continue;
+ }
+
+ /* element is equal to key value, make sure flags are
+ * the same, an existing more or equal start element
+ * must not be replaced by more or equal end element.
+ */
+ if ((nft_rbtree_interval_start(new) &&
+ nft_rbtree_interval_start(rbe_ge)) ||
+ (nft_rbtree_interval_end(new) &&
+ nft_rbtree_interval_end(rbe_ge))) {
+ rbe_ge = rbe;
+ continue;
}
+ } else if (d > 0) {
+ /* annotate element greater than the new element. */
+ rbe_ge = rbe;
+ continue;
+ } else if (d < 0) {
+ /* annotate element less than the new element. */
+ rbe_le = rbe;
+ break;
}
+ }
- dup_end_left = dup_end_right = false;
+ /* - new start element matching existing start element: full overlap
+ * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given.
+ */
+ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) &&
+ nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) {
+ *ext = &rbe_ge->ext;
+ return -EEXIST;
}
- if (overlap)
+ /* - new end element matching existing end element: full overlap
+ * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given.
+ */
+ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) &&
+ nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) {
+ *ext = &rbe_le->ext;
+ return -EEXIST;
+ }
+
+ /* - new start element with existing closest, less or equal key value
+ * being a start element: partial overlap, reported as -ENOTEMPTY.
+ * Anonymous sets allow for two consecutive start element since they
+ * are constant, skip them to avoid bogus overlap reports.
+ */
+ if (!nft_set_is_anonymous(set) && rbe_le &&
+ nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new))
+ return -ENOTEMPTY;
+
+ /* - new end element with existing closest, less or equal key value
+ * being a end element: partial overlap, reported as -ENOTEMPTY.
+ */
+ if (rbe_le &&
+ nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new))
return -ENOTEMPTY;
+ /* - new end element with existing closest, greater or equal key value
+ * being an end element: partial overlap, reported as -ENOTEMPTY
+ */
+ if (rbe_ge &&
+ nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new))
+ return -ENOTEMPTY;
+
+ /* Accepted element: pick insertion point depending on key value */
+ parent = NULL;
+ p = &priv->root.rb_node;
+ while (*p != NULL) {
+ parent = *p;
+ rbe = rb_entry(parent, struct nft_rbtree_elem, node);
+ d = nft_rbtree_cmp(set, rbe, new);
+
+ if (d < 0)
+ p = &parent->rb_left;
+ else if (d > 0)
+ p = &parent->rb_right;
+ else if (nft_rbtree_interval_end(rbe))
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
+ }
+
rb_link_node_rcu(&new->node, parent, p);
rb_insert_color(&new->node, &priv->root);
return 0;
struct nft_rbtree *priv;
struct rb_node *node;
struct nft_set *set;
+ struct net *net;
+ u8 genmask;
priv = container_of(work, struct nft_rbtree, gc_work.work);
set = nft_set_container_of(priv);
+ net = read_pnet(&set->net);
+ genmask = nft_genmask_cur(net);
write_lock_bh(&priv->lock);
write_seqcount_begin(&priv->count);
for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
rbe = rb_entry(node, struct nft_rbtree_elem, node);
+ if (!nft_set_elem_active(&rbe->ext, genmask))
+ continue;
+
+ /* elements are reversed in the rbtree for historical reasons,
+ * from highest to lowest value, that is why end element is
+ * always visited before the start element.
+ */
if (nft_rbtree_interval_end(rbe)) {
rbe_end = rbe;
continue;
}
if (!nft_set_elem_expired(&rbe->ext))
continue;
- if (nft_set_elem_mark_busy(&rbe->ext))
+
+ if (nft_set_elem_mark_busy(&rbe->ext)) {
+ rbe_end = NULL;
continue;
+ }
if (rbe_prev) {
rb_erase(&rbe_prev->node, &priv->root);
if (nlk_sk(sk)->bound)
goto err;
- nlk_sk(sk)->portid = portid;
+ /* portid can be read locklessly from netlink_getname(). */
+ WRITE_ONCE(nlk_sk(sk)->portid, portid);
+
sock_hold(sk);
err = __netlink_insert(table, sk);
return -EINVAL;
if (addr->sa_family == AF_UNSPEC) {
- sk->sk_state = NETLINK_UNCONNECTED;
- nlk->dst_portid = 0;
- nlk->dst_group = 0;
+ /* paired with READ_ONCE() in netlink_getsockbyportid() */
+ WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED);
+ /* dst_portid and dst_group can be read locklessly */
+ WRITE_ONCE(nlk->dst_portid, 0);
+ WRITE_ONCE(nlk->dst_group, 0);
return 0;
}
if (addr->sa_family != AF_NETLINK)
err = netlink_autobind(sock);
if (err == 0) {
- sk->sk_state = NETLINK_CONNECTED;
- nlk->dst_portid = nladdr->nl_pid;
- nlk->dst_group = ffs(nladdr->nl_groups);
+ /* paired with READ_ONCE() in netlink_getsockbyportid() */
+ WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED);
+ /* dst_portid and dst_group can be read locklessly */
+ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid);
+ WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups));
}
return err;
nladdr->nl_pad = 0;
if (peer) {
- nladdr->nl_pid = nlk->dst_portid;
- nladdr->nl_groups = netlink_group_mask(nlk->dst_group);
+ /* Paired with WRITE_ONCE() in netlink_connect() */
+ nladdr->nl_pid = READ_ONCE(nlk->dst_portid);
+ nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group));
} else {
- nladdr->nl_pid = nlk->portid;
+ /* Paired with WRITE_ONCE() in netlink_insert() */
+ nladdr->nl_pid = READ_ONCE(nlk->portid);
netlink_lock_table();
nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0;
netlink_unlock_table();
/* Don't bother queuing skb if kernel socket has no input function */
nlk = nlk_sk(sock);
- if (sock->sk_state == NETLINK_CONNECTED &&
- nlk->dst_portid != nlk_sk(ssk)->portid) {
+ /* dst_portid and sk_state can be changed in netlink_connect() */
+ if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED &&
+ READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) {
sock_put(sock);
return ERR_PTR(-ECONNREFUSED);
}
goto out;
netlink_skb_flags |= NETLINK_SKB_DST;
} else {
- dst_portid = nlk->dst_portid;
- dst_group = nlk->dst_group;
+ /* Paired with WRITE_ONCE() in netlink_connect() */
+ dst_portid = READ_ONCE(nlk->dst_portid);
+ dst_group = READ_ONCE(nlk->dst_group);
}
/* Paired with WRITE_ONCE() in netlink_insert() */
struct sock *sk = sock->sk;
lock_sock(sk);
+ if (sock->state != SS_UNCONNECTED) {
+ release_sock(sk);
+ return -EINVAL;
+ }
+
if (sk->sk_state != TCP_LISTEN) {
memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN);
sk->sk_max_ack_backlog = backlog;
is accepted() it isn't 'dead' so doesn't get removed. */
if (sock_flag(sk, SOCK_DESTROY) ||
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
+ sock_hold(sk);
bh_unlock_sock(sk);
nr_destroy_socket(sk);
goto out;
cancel_work_sync(&local->rx_work);
cancel_work_sync(&local->timeout_work);
kfree_skb(local->rx_pending);
+ local->rx_pending = NULL;
del_timer_sync(&local->sdreq_timer);
cancel_work_sync(&local->sdreq_timeout_work);
nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs);
u32 dev_idx, se_idx;
u8 *apdu;
size_t apdu_len;
+ int rc;
if (!info->attrs[NFC_ATTR_DEVICE_INDEX] ||
!info->attrs[NFC_ATTR_SE_INDEX] ||
if (!dev)
return -ENODEV;
- if (!dev->ops || !dev->ops->se_io)
- return -ENOTSUPP;
+ if (!dev->ops || !dev->ops->se_io) {
+ rc = -EOPNOTSUPP;
+ goto put_dev;
+ }
apdu_len = nla_len(info->attrs[NFC_ATTR_SE_APDU]);
- if (apdu_len == 0)
- return -EINVAL;
+ if (apdu_len == 0) {
+ rc = -EINVAL;
+ goto put_dev;
+ }
apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]);
- if (!apdu)
- return -EINVAL;
+ if (!apdu) {
+ rc = -EINVAL;
+ goto put_dev;
+ }
ctx = kzalloc(sizeof(struct se_io_ctx), GFP_KERNEL);
- if (!ctx)
- return -ENOMEM;
+ if (!ctx) {
+ rc = -ENOMEM;
+ goto put_dev;
+ }
ctx->dev_idx = dev_idx;
ctx->se_idx = se_idx;
- return nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+ rc = nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+
+put_dev:
+ nfc_put_device(dev);
+ return rc;
}
static int nfc_genl_vendor_cmd(struct sk_buff *skb,
subcmd = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_SUBCMD]);
dev = nfc_get_device(dev_idx);
- if (!dev || !dev->vendor_cmds || !dev->n_vendor_cmds)
+ if (!dev)
return -ENODEV;
+ if (!dev->vendor_cmds || !dev->n_vendor_cmds) {
+ err = -ENODEV;
+ goto put_dev;
+ }
+
if (info->attrs[NFC_ATTR_VENDOR_DATA]) {
data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]);
data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]);
- if (data_len == 0)
- return -EINVAL;
+ if (data_len == 0) {
+ err = -EINVAL;
+ goto put_dev;
+ }
} else {
data = NULL;
data_len = 0;
dev->cur_cmd_info = info;
err = cmd->doit(dev, data, data_len);
dev->cur_cmd_info = NULL;
- return err;
+ goto put_dev;
}
- return -EOPNOTSUPP;
+ err = -EOPNOTSUPP;
+
+put_dev:
+ nfc_put_device(dev);
+ return err;
}
/* message building helper */
key = kzalloc(sizeof(*key), GFP_KERNEL);
if (!key) {
error = -ENOMEM;
- goto err_kfree_key;
+ goto err_kfree_flow;
}
ovs_match_init(&match, key, false, &mask);
error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY],
a[OVS_FLOW_ATTR_MASK], log);
if (error)
- goto err_kfree_flow;
+ goto err_kfree_key;
ovs_flow_mask_key(&new_flow->key, key, true, &mask);
error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
key, log);
if (error)
- goto err_kfree_flow;
+ goto err_kfree_key;
/* Validate actions. */
error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS],
&new_flow->key, &acts, log);
if (error) {
OVS_NLERR(log, "Flow actions may not be safe on all matching packets.");
- goto err_kfree_flow;
+ goto err_kfree_key;
}
reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false,
kfree_skb(reply);
err_kfree_acts:
ovs_nla_free_flow_actions(acts);
-err_kfree_flow:
- ovs_flow_free(new_flow, false);
err_kfree_key:
kfree(key);
+err_kfree_flow:
+ ovs_flow_free(new_flow, false);
error:
return error;
}
vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
if (!vport->upcall_stats) {
err = -ENOMEM;
- goto err_destroy_portids;
+ goto err_destroy_vport;
}
err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
+err_destroy_vport:
+ ovs_dp_detach_port(vport);
err_destroy_portids:
kfree(rcu_dereference_raw(dp->upcall_portids));
err_unlock_and_destroy_meters:
vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
if (!vport->upcall_stats) {
err = -ENOMEM;
- goto exit_unlock_free;
+ goto exit_unlock_free_vport;
}
err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
ovs_notify(&dp_vport_genl_family, reply, info);
return 0;
+exit_unlock_free_vport:
+ ovs_dp_detach_port(vport);
exit_unlock_free:
ovs_unlock();
kfree_skb(reply);
err = attach_meter(meter_tbl, meter);
if (err)
- goto exit_unlock;
+ goto exit_free_old_meter;
ovs_unlock();
genlmsg_end(reply, ovs_reply_header);
return genlmsg_reply(reply, info);
+exit_free_old_meter:
+ ovs_meter_free(old_meter);
exit_unlock:
ovs_unlock();
nlmsg_free(reply);
node->id = node_id;
- radix_tree_insert(&nodes, node_id, node);
+ if (radix_tree_insert(&nodes, node_id, node)) {
+ kfree(node);
+ return NULL;
+ }
return node;
}
spin_lock_irqsave(&q->lock, flags);
head = &q->zcookie_head;
if (!list_empty(head)) {
- info = list_entry(head, struct rds_msg_zcopy_info,
- rs_zcookie_next);
- if (info && rds_zcookie_add(info, cookie)) {
+ info = list_first_entry(head, struct rds_msg_zcopy_info,
+ rs_zcookie_next);
+ if (rds_zcookie_add(info, cookie)) {
spin_unlock_irqrestore(&q->lock, flags);
kfree(rds_info_from_znotifier(znotif));
/* caller invokes rds_wake_sk_sleep() */
{
struct sock *sk = sock->sk;
+ lock_sock(sk);
+ if (sock->state != SS_UNCONNECTED) {
+ release_sock(sk);
+ return -EINVAL;
+ }
+
if (sk->sk_state != TCP_LISTEN) {
struct rose_sock *rose = rose_sk(sk);
memset(rose->dest_digis, 0, AX25_ADDR_LEN * ROSE_MAX_DIGIS);
sk->sk_max_ack_backlog = backlog;
sk->sk_state = TCP_LISTEN;
+ release_sock(sk);
return 0;
}
+ release_sock(sk);
return -EOPNOTSUPP;
}
call_accept.o \
call_event.o \
call_object.o \
+ call_state.o \
conn_client.o \
conn_event.o \
conn_object.o \
if (service_id) {
write_lock(&local->services_lock);
- if (rcu_access_pointer(local->service))
+ if (local->service)
goto service_in_use;
rx->local = local;
- rcu_assign_pointer(local->service, rx);
+ local->service = rx;
write_unlock(&local->services_lock);
rx->sk.sk_state = RXRPC_SERVER_BOUND;
mutex_unlock(&call->user_mutex);
}
- rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp);
_leave(" = %p", call);
return call;
}
* @sock: The socket the call is on
* @call: The call to check
*
- * Allow a kernel service to find out whether a call is still alive -
- * ie. whether it has completed.
+ * Allow a kernel service to find out whether a call is still alive - whether
+ * it has completed successfully and all received data has been consumed.
*/
bool rxrpc_kernel_check_life(const struct socket *sock,
const struct rxrpc_call *call)
{
- return call->state != RXRPC_CALL_COMPLETE;
+ if (!rxrpc_call_is_complete(call))
+ return true;
+ if (call->completion != RXRPC_CALL_SUCCEEDED)
+ return false;
+ return !skb_queue_empty(&call->recvmsg_queue);
}
EXPORT_SYMBOL(rxrpc_kernel_check_life);
sk->sk_state = RXRPC_CLOSE;
- if (rx->local && rcu_access_pointer(rx->local->service) == rx) {
+ if (rx->local && rx->local->service == rx) {
write_lock(&rx->local->services_lock);
- rcu_assign_pointer(rx->local->service, NULL);
+ rx->local->service = NULL;
write_unlock(&rx->local->services_lock);
}
static int __init af_rxrpc_init(void)
{
int ret = -1;
- unsigned int tmp;
BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb));
- get_random_bytes(&tmp, sizeof(tmp));
- tmp &= 0x3fffffff;
- if (tmp == 0)
- tmp = 1;
- idr_set_cursor(&rxrpc_client_conn_ids, tmp);
-
ret = -ENOMEM;
rxrpc_call_jar = kmem_cache_create(
"rxrpc_call_jar", sizeof(struct rxrpc_call), 0,
* are released.
*/
rcu_barrier();
- rxrpc_destroy_client_conn_ids();
destroy_workqueue(rxrpc_workqueue);
rxrpc_exit_security();
enum rxrpc_skb_mark {
RXRPC_SKB_MARK_PACKET, /* Received packet */
RXRPC_SKB_MARK_ERROR, /* Error notification */
+ RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */
RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */
RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */
};
bool live;
- bool kill_all_client_conns;
atomic_t nr_client_conns;
- spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */
- struct mutex client_conn_discard_lock; /* Prevent multiple discarders */
- struct list_head idle_client_conns;
- struct work_struct client_conn_reaper;
- struct timer_list client_conn_reap_timer;
struct hlist_head local_endpoints;
struct mutex local_mutex; /* Lock for ->local_endpoints */
* - max 48 bytes (struct sk_buff::cb)
*/
struct rxrpc_skb_priv {
+ struct rxrpc_connection *conn; /* Connection referred to (poke packet) */
u16 offset; /* Offset of data */
u16 len; /* Length of data */
u8 flags;
/* respond to a challenge */
int (*respond_to_challenge)(struct rxrpc_connection *,
- struct sk_buff *,
- u32 *);
+ struct sk_buff *);
/* verify a response */
int (*verify_response)(struct rxrpc_connection *,
- struct sk_buff *,
- u32 *);
+ struct sk_buff *);
/* clear connection security */
void (*clear)(struct rxrpc_connection *);
struct rcu_head rcu;
atomic_t active_users; /* Number of users of the local endpoint */
refcount_t ref; /* Number of references to the structure */
- struct rxrpc_net *rxnet; /* The network ns in which this resides */
+ struct net *net; /* The network namespace */
+ struct rxrpc_net *rxnet; /* Our bits in the network namespace */
struct hlist_node link;
struct socket *socket; /* my UDP socket */
struct task_struct *io_thread;
struct completion io_thread_ready; /* Indication that the I/O thread started */
- struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */
+ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */
struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */
struct sk_buff_head rx_queue; /* Received packets */
+ struct list_head conn_attend_q; /* Conns requiring immediate attention */
struct list_head call_attend_q; /* Calls requiring immediate attention */
+
struct rb_root client_bundles; /* Client connection bundles by socket params */
spinlock_t client_bundles_lock; /* Lock for client_bundles */
+ bool kill_all_client_conns;
+ struct list_head idle_client_conns;
+ struct timer_list client_conn_reap_timer;
+ unsigned long client_conn_flags;
+#define RXRPC_CLIENT_CONN_REAP_TIMER 0 /* The client conn reap timer expired */
+
spinlock_t lock; /* access lock */
rwlock_t services_lock; /* lock for services list */
int debug_id; /* debug ID for printks */
bool dead;
bool service_closed; /* Service socket closed */
+ struct idr conn_ids; /* List of connection IDs */
+ struct list_head new_client_calls; /* Newly created client calls need connection */
+ spinlock_t client_call_lock; /* Lock for ->new_client_calls */
struct sockaddr_rxrpc srx; /* local address */
};
struct rxrpc_conn_parameters {
struct rxrpc_local *local; /* Representation of local endpoint */
- struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* Security details */
bool exclusive; /* T if conn is exclusive */
bool upgrade; /* T if service ID can be upgraded */
u32 security_level; /* Security level selected */
};
+/*
+ * Call completion condition (state == RXRPC_CALL_COMPLETE).
+ */
+enum rxrpc_call_completion {
+ RXRPC_CALL_SUCCEEDED, /* - Normal termination */
+ RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */
+ RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */
+ RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */
+ RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */
+ NR__RXRPC_CALL_COMPLETIONS
+};
+
/*
* Bits in the connection flags.
*/
enum rxrpc_conn_flag {
- RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */
RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */
RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */
RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */
*/
enum rxrpc_conn_event {
RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */
+ RXRPC_CONN_EV_ABORT_CALLS, /* Abort attached calls */
};
/*
*/
enum rxrpc_conn_proto_state {
RXRPC_CONN_UNUSED, /* Connection not yet attempted */
+ RXRPC_CONN_CLIENT_UNSECURED, /* Client connection needs security init */
RXRPC_CONN_CLIENT, /* Client connection */
RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */
RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */
RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */
RXRPC_CONN_SERVICE, /* Service secured connection */
- RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */
- RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */
+ RXRPC_CONN_ABORTED, /* Conn aborted */
RXRPC_CONN__NR_STATES
};
struct rxrpc_local *local; /* Representation of local endpoint */
struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* Security details */
+ const struct rxrpc_security *security; /* applied security module */
refcount_t ref;
atomic_t active; /* Number of active users */
unsigned int debug_id;
u32 security_level; /* Security level selected */
u16 service_id; /* Service ID for this connection */
bool try_upgrade; /* True if the bundle is attempting upgrade */
- bool alloc_conn; /* True if someone's getting a conn */
bool exclusive; /* T if conn is exclusive */
bool upgrade; /* T if service ID can be upgraded */
- short alloc_error; /* Error from last conn allocation */
- spinlock_t channel_lock;
+ unsigned short alloc_error; /* Error from last conn allocation */
struct rb_node local_node; /* Node in local->client_conns */
struct list_head waiting_calls; /* Calls waiting for channels */
unsigned long avail_chans; /* Mask of available channels */
struct rxrpc_peer *peer; /* Remote endpoint */
struct rxrpc_net *rxnet; /* Network namespace to which call belongs */
struct key *key; /* Security details */
+ struct list_head attend_link; /* Link in local->conn_attend_q */
refcount_t ref;
atomic_t active; /* Active count for service conns */
unsigned char act_chans; /* Mask of active channels */
struct rxrpc_channel {
unsigned long final_ack_at; /* Time at which to issue final ACK */
- struct rxrpc_call __rcu *call; /* Active call */
+ struct rxrpc_call *call; /* Active call */
unsigned int call_debug_id; /* call->debug_id */
u32 call_id; /* ID of current call */
u32 call_counter; /* Call ID counter */
struct list_head link; /* link in master connection list */
struct sk_buff_head rx_queue; /* received conn-level packets */
+ struct mutex security_lock; /* Lock for security management */
const struct rxrpc_security *security; /* applied security module */
union {
struct {
unsigned long idle_timestamp; /* Time at which last became idle */
spinlock_t state_lock; /* state-change lock */
enum rxrpc_conn_proto_state state; /* current state of connection */
- u32 abort_code; /* Abort code of connection abort */
+ enum rxrpc_call_completion completion; /* Completion condition */
+ s32 abort_code; /* Abort code of connection abort */
int debug_id; /* debug ID for printks */
atomic_t serial; /* packet serial number counter */
unsigned int hi_serial; /* highest serial number received */
RXRPC_CALL_KERNEL, /* The call was made by the kernel */
RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */
RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */
- RXRPC_CALL_RX_IS_IDLE, /* Reception is idle - send an ACK */
+ RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */
+ RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */
};
/*
NR__RXRPC_CALL_STATES
};
-/*
- * Call completion condition (state == RXRPC_CALL_COMPLETE).
- */
-enum rxrpc_call_completion {
- RXRPC_CALL_SUCCEEDED, /* - Normal termination */
- RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */
- RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */
- RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */
- RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */
- NR__RXRPC_CALL_COMPLETIONS
-};
-
/*
* Call Tx congestion management modes.
*/
struct rxrpc_call {
struct rcu_head rcu;
struct rxrpc_connection *conn; /* connection carrying call */
+ struct rxrpc_bundle *bundle; /* Connection bundle to use */
struct rxrpc_peer *peer; /* Peer record for remote address */
struct rxrpc_local *local; /* Representation of local endpoint */
struct rxrpc_sock __rcu *socket; /* socket responsible */
struct work_struct destroyer; /* In-process-context destroyer */
rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */
struct list_head link; /* link in master call list */
- struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */
+ struct list_head wait_link; /* Link in local->new_client_calls */
struct hlist_node error_link; /* link in error distribution list */
struct list_head accept_link; /* Link in rx->acceptq */
struct list_head recvmsg_link; /* Link in rx->recvmsg_q */
unsigned long flags;
unsigned long events;
spinlock_t notify_lock; /* Kernel notification lock */
- rwlock_t state_lock; /* lock for state transition */
- u32 abort_code; /* Local/remote abort code */
+ unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */
+ s32 send_abort; /* Abort code to be sent */
+ short send_abort_err; /* Error to be associated with the abort */
+ rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */
+ s32 abort_code; /* Local/remote abort code */
int error; /* Local error incurred */
- enum rxrpc_call_state state; /* current state of call */
+ enum rxrpc_call_state _state; /* Current state of call (needs barrier) */
enum rxrpc_call_completion completion; /* Call completion condition */
refcount_t ref;
u8 security_ix; /* Security type */
*/
int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t);
void rxrpc_discard_prealloc(struct rxrpc_sock *);
-int rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_peer *,
- struct rxrpc_connection *, struct sockaddr_rxrpc *,
- struct sk_buff *);
+bool rxrpc_new_incoming_call(struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
+ struct rxrpc_connection *conn,
+ struct sockaddr_rxrpc *peer_srx,
+ struct sk_buff *skb);
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long);
unsigned long now,
enum rxrpc_timer_trace why);
-void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb);
+bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb);
/*
* call_object.c
struct sockaddr_rxrpc *,
struct rxrpc_call_params *, gfp_t,
unsigned int);
+void rxrpc_start_call_timer(struct rxrpc_call *call);
void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *,
struct sk_buff *);
void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *);
return !rxrpc_is_service_call(call);
}
+/*
+ * call_state.c
+ */
+bool rxrpc_set_call_completion(struct rxrpc_call *call,
+ enum rxrpc_call_completion compl,
+ u32 abort_code,
+ int error);
+bool rxrpc_call_completed(struct rxrpc_call *call);
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why);
+void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl,
+ int error);
+
+static inline void rxrpc_set_call_state(struct rxrpc_call *call,
+ enum rxrpc_call_state state)
+{
+ /* Order write of completion info before write of ->state. */
+ smp_store_release(&call->_state, state);
+ wake_up(&call->waitq);
+}
+
+static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call)
+{
+ return call->_state; /* Only inside I/O thread */
+}
+
+static inline bool __rxrpc_call_is_complete(const struct rxrpc_call *call)
+{
+ return __rxrpc_call_state(call) == RXRPC_CALL_COMPLETE;
+}
+
+static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call)
+{
+ /* Order read ->state before read of completion info. */
+ return smp_load_acquire(&call->_state);
+}
+
+static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call)
+{
+ return rxrpc_call_state(call) == RXRPC_CALL_COMPLETE;
+}
+
+static inline bool rxrpc_call_has_failed(const struct rxrpc_call *call)
+{
+ return rxrpc_call_is_complete(call) && call->completion != RXRPC_CALL_SUCCEEDED;
+}
+
/*
* conn_client.c
*/
extern unsigned int rxrpc_reap_client_connections;
extern unsigned long rxrpc_conn_idle_client_expiry;
extern unsigned long rxrpc_conn_idle_client_fast_expiry;
-extern struct idr rxrpc_client_conn_ids;
-void rxrpc_destroy_client_conn_ids(void);
+void rxrpc_purge_client_connections(struct rxrpc_local *local);
struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
-int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *,
- struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *,
- gfp_t);
+int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp);
+void rxrpc_connect_client_calls(struct rxrpc_local *local);
void rxrpc_expose_client_call(struct rxrpc_call *);
void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *);
+void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace);
-void rxrpc_discard_expired_client_conns(struct work_struct *);
-void rxrpc_destroy_all_client_connections(struct rxrpc_net *);
+void rxrpc_discard_expired_client_conns(struct rxrpc_local *local);
void rxrpc_clean_up_local_conns(struct rxrpc_local *);
/*
* conn_event.c
*/
+void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb,
+ unsigned int channel);
+int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err, enum rxrpc_abort_reason why);
void rxrpc_process_connection(struct work_struct *);
void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool);
-int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
+bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
+void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb);
+
+static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn)
+{
+ /* Order reading the abort info after the state check. */
+ return smp_load_acquire(&conn->state) == RXRPC_CONN_ABORTED;
+}
/*
* conn_object.c
extern unsigned int rxrpc_connection_expiry;
extern unsigned int rxrpc_closed_conn_expiry;
+void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why);
struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t);
struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *,
struct sockaddr_rxrpc *,
*/
int rxrpc_encap_rcv(struct sock *, struct sk_buff *);
void rxrpc_error_report(struct sock *);
+bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why,
+ s32 abort_code, int err);
int rxrpc_io_thread(void *data);
static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local)
{
wake_up_process(local->io_thread);
}
+static inline bool rxrpc_protocol_error(struct sk_buff *skb, enum rxrpc_abort_reason why)
+{
+ return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EPROTO);
+}
+
/*
* insecure.c
*/
int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb);
int rxrpc_send_abort_packet(struct rxrpc_call *);
int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *);
+void rxrpc_send_conn_abort(struct rxrpc_connection *conn);
void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb);
void rxrpc_send_keepalive(struct rxrpc_peer *);
void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb);
*/
struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
const struct sockaddr_rxrpc *);
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *,
- struct sockaddr_rxrpc *, gfp_t);
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
+ struct sockaddr_rxrpc *srx, gfp_t gfp);
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t,
enum rxrpc_peer_trace);
-void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *,
- struct rxrpc_peer *);
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer);
void rxrpc_destroy_all_peers(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace);
* recvmsg.c
*/
void rxrpc_notify_socket(struct rxrpc_call *);
-bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int);
-bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int);
-bool __rxrpc_call_completed(struct rxrpc_call *);
-bool rxrpc_call_completed(struct rxrpc_call *);
-bool __rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int);
-bool rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int);
int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
/*
* Abort a call due to a protocol error.
*/
-static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call,
- struct sk_buff *skb,
- const char *eproto_why,
- const char *why,
- u32 abort_code)
+static inline int rxrpc_abort_eproto(struct rxrpc_call *call,
+ struct sk_buff *skb,
+ s32 abort_code,
+ enum rxrpc_abort_reason why)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why);
- return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO);
+ rxrpc_abort_call(call, sp->hdr.seq, abort_code, -EPROTO, why);
+ return -EPROTO;
}
-#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \
- __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \
- (abort_why), (abort_code))
-
/*
* rtt.c
*/
/*
* sendmsg.c
*/
+bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
+ enum rxrpc_abort_reason why);
int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
/*
if (!call)
return -ENOMEM;
call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
- call->state = RXRPC_CALL_SERVER_PREALLOC;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_PREALLOC);
__set_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events);
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
(peer_tail + 1) &
(RXRPC_BACKLOG_MAX - 1));
- rxrpc_new_incoming_peer(rx, local, peer);
+ rxrpc_new_incoming_peer(local, peer);
}
/* Now allocate and set up the connection */
* If we want to report an error, we mark the skb with the packet type and
* abort code and return false.
*/
-int rxrpc_new_incoming_call(struct rxrpc_local *local,
- struct rxrpc_peer *peer,
- struct rxrpc_connection *conn,
- struct sockaddr_rxrpc *peer_srx,
- struct sk_buff *skb)
+bool rxrpc_new_incoming_call(struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
+ struct rxrpc_connection *conn,
+ struct sockaddr_rxrpc *peer_srx,
+ struct sk_buff *skb)
{
const struct rxrpc_security *sec = NULL;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
_enter("");
- /* Don't set up a call for anything other than the first DATA packet. */
- if (sp->hdr.seq != 1 ||
- sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
- return 0; /* Just discard */
+ /* Don't set up a call for anything other than a DATA packet. */
+ if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call);
- rcu_read_lock();
+ read_lock(&local->services_lock);
/* Weed out packets to services we're not offering. Packets that would
* begin a call are explicitly rejected and the rest are just
* discarded.
*/
- rx = rcu_dereference(local->service);
+ rx = local->service;
if (!rx || (sp->hdr.serviceId != rx->srx.srx_service &&
sp->hdr.serviceId != rx->second_service)
) {
if (!conn) {
sec = rxrpc_get_incoming_security(rx, skb);
if (!sec)
- goto reject;
+ goto unsupported_security;
}
spin_lock(&rx->incoming_lock);
if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
rx->sk.sk_state == RXRPC_CLOSE) {
- trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
- sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = RX_INVALID_OPERATION;
+ rxrpc_direct_abort(skb, rxrpc_abort_shut_down,
+ RX_INVALID_OPERATION, -ESHUTDOWN);
goto no_call;
}
spin_unlock(&conn->state_lock);
spin_unlock(&rx->incoming_lock);
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
if (hlist_unhashed(&call->error_link)) {
spin_lock(&call->peer->lock);
_leave(" = %p{%d}", call, call->debug_id);
rxrpc_input_call_event(call, skb);
rxrpc_put_call(call, rxrpc_call_put_input);
- return 0;
+ return true;
unsupported_service:
- trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EOPNOTSUPP);
- skb->priority = RX_INVALID_OPERATION;
- goto reject;
+ read_unlock(&local->services_lock);
+ return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered,
+ RX_INVALID_OPERATION, -EOPNOTSUPP);
+unsupported_security:
+ read_unlock(&local->services_lock);
+ return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered,
+ RX_INVALID_OPERATION, -EKEYREJECTED);
no_call:
spin_unlock(&rx->incoming_lock);
-reject:
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
_leave(" = f [%u]", skb->mark);
- return -EPROTO;
+ return false;
discard:
- rcu_read_unlock();
- return 0;
+ read_unlock(&local->services_lock);
+ return true;
}
/*
_leave("");
}
+/*
+ * Start transmitting the reply to a service. This cancels the need to ACK the
+ * request if we haven't yet done so.
+ */
+static void rxrpc_begin_service_reply(struct rxrpc_call *call)
+{
+ unsigned long now = jiffies;
+
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY);
+ WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
+ if (call->ackr_reason == RXRPC_ACK_DELAY)
+ call->ackr_reason = 0;
+ trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
+}
+
+/*
+ * Close the transmission phase. After this point there is no more data to be
+ * transmitted in the call.
+ */
+static void rxrpc_close_tx_phase(struct rxrpc_call *call)
+{
+ _debug("________awaiting reply/ACK__________");
+
+ switch (__rxrpc_call_state(call)) {
+ case RXRPC_CALL_CLIENT_SEND_REQUEST:
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY);
+ break;
+ case RXRPC_CALL_SERVER_SEND_REPLY:
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_AWAIT_ACK);
+ break;
+ default:
+ break;
+ }
+}
+
static bool rxrpc_tx_window_has_space(struct rxrpc_call *call)
{
unsigned int winsize = min_t(unsigned int, call->tx_winsize,
{
struct rxrpc_txbuf *txb;
- if (rxrpc_is_client_call(call) &&
- !test_bit(RXRPC_CALL_EXPOSED, &call->flags))
+ if (!test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
+ if (list_empty(&call->tx_sendmsg))
+ return;
rxrpc_expose_client_call(call);
+ }
while ((txb = list_first_entry_or_null(&call->tx_sendmsg,
struct rxrpc_txbuf, call_link))) {
call->tx_top = txb->seq;
list_add_tail(&txb->call_link, &call->tx_buffer);
+ if (txb->wire.flags & RXRPC_LAST_PACKET)
+ rxrpc_close_tx_phase(call);
+
rxrpc_transmit_one(call, txb);
if (!rxrpc_tx_window_has_space(call))
static void rxrpc_transmit_some_data(struct rxrpc_call *call)
{
- switch (call->state) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_SERVER_ACK_REQUEST:
if (list_empty(&call->tx_sendmsg))
return;
+ rxrpc_begin_service_reply(call);
fallthrough;
case RXRPC_CALL_SERVER_SEND_REPLY:
- case RXRPC_CALL_SERVER_AWAIT_ACK:
case RXRPC_CALL_CLIENT_SEND_REQUEST:
- case RXRPC_CALL_CLIENT_AWAIT_REPLY:
if (!rxrpc_tx_window_has_space(call))
return;
if (list_empty(&call->tx_sendmsg)) {
/*
* Handle retransmission and deferred ACK/abort generation.
*/
-void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
+bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
{
unsigned long now, next, t;
rxrpc_serial_t ackr_serial;
bool resend = false, expired = false;
+ s32 abort_code;
rxrpc_see_call(call, rxrpc_call_see_input);
//printk("\n--------------------\n");
_enter("{%d,%s,%lx}",
- call->debug_id, rxrpc_call_states[call->state], call->events);
+ call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)],
+ call->events);
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (__rxrpc_call_is_complete(call))
goto out;
+ /* Handle abort request locklessly, vs rxrpc_propose_abort(). */
+ abort_code = smp_load_acquire(&call->send_abort);
+ if (abort_code) {
+ rxrpc_abort_call(call, 0, call->send_abort, call->send_abort_err,
+ call->send_abort_why);
+ goto out;
+ }
+
if (skb && skb->mark == RXRPC_SKB_MARK_ERROR)
goto out;
}
t = READ_ONCE(call->expect_req_by);
- if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST &&
+ if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST &&
time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now);
expired = true;
if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) &&
(int)call->conn->hi_serial - (int)call->rx_serial > 0) {
trace_rxrpc_call_reset(call);
- rxrpc_abort_call("EXP", call, 0, RX_CALL_DEAD, -ECONNRESET);
+ rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_reset);
} else {
- rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME);
+ rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME,
+ rxrpc_abort_call_timeout);
}
- rxrpc_send_abort_packet(call);
goto out;
}
rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
rxrpc_propose_ack_ping_for_lost_ack);
- if (resend && call->state != RXRPC_CALL_CLIENT_RECV_REPLY)
+ if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY)
rxrpc_resend(call, NULL);
if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags))
rxrpc_propose_ack_input_data);
/* Make sure the timer is restarted */
- if (call->state != RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
next = call->expect_rx_by;
#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; }
}
out:
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (__rxrpc_call_is_complete(call)) {
del_timer_sync(&call->timer);
+ if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
+ rxrpc_disconnect_call(call);
+ if (call->security)
+ call->security->free_call_crypto(call);
+ }
if (call->acks_hard_ack != call->tx_bottom)
rxrpc_shrink_call_tx_buffer(call);
_leave("");
+ return true;
}
struct rxrpc_local *local = call->local;
bool busy;
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) {
spin_lock_bh(&local->lock);
busy = !list_empty(&call->attend_link);
trace_rxrpc_poke_call(call, busy, what);
_enter("%d", call->debug_id);
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
trace_rxrpc_timer_expired(call, jiffies);
rxrpc_poke_call(call, rxrpc_call_poke_timer);
}
timer_setup(&call->timer, rxrpc_call_timer_expired, 0);
INIT_WORK(&call->destroyer, rxrpc_destroy_call);
INIT_LIST_HEAD(&call->link);
- INIT_LIST_HEAD(&call->chan_wait_link);
+ INIT_LIST_HEAD(&call->wait_link);
INIT_LIST_HEAD(&call->accept_link);
INIT_LIST_HEAD(&call->recvmsg_link);
INIT_LIST_HEAD(&call->sock_link);
init_waitqueue_head(&call->waitq);
spin_lock_init(&call->notify_lock);
spin_lock_init(&call->tx_lock);
- rwlock_init(&call->state_lock);
refcount_set(&call->ref, 1);
call->debug_id = debug_id;
call->tx_total_len = -1;
now = ktime_get_real();
call->acks_latest_ts = now;
call->cong_tstamp = now;
- call->state = RXRPC_CALL_CLIENT_AWAIT_CONN;
call->dest_srx = *srx;
call->interruptibility = p->interruptibility;
call->tx_total_len = p->tx_total_len;
ret = rxrpc_init_client_call_security(call);
if (ret < 0) {
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret);
rxrpc_put_call(call, rxrpc_call_put_discard_error);
return ERR_PTR(ret);
}
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_CONN);
+
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
p->user_call_ID, rxrpc_call_new_client);
/*
* Initiate the call ack/resend/expiry timer.
*/
-static void rxrpc_start_call_timer(struct rxrpc_call *call)
+void rxrpc_start_call_timer(struct rxrpc_call *call)
{
unsigned long now = jiffies;
unsigned long j = now + MAX_JIFFY_OFFSET;
up(limiter);
}
+/*
+ * Start the process of connecting a call. We obtain a peer and a connection
+ * bundle, but the actual association of a call with a connection is offloaded
+ * to the I/O thread to simplify locking.
+ */
+static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
+{
+ struct rxrpc_local *local = call->local;
+ int ret = -ENOMEM;
+
+ _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
+
+ call->peer = rxrpc_lookup_peer(local, &call->dest_srx, gfp);
+ if (!call->peer)
+ goto error;
+
+ ret = rxrpc_look_up_bundle(call, gfp);
+ if (ret < 0)
+ goto error;
+
+ trace_rxrpc_client(NULL, -1, rxrpc_client_queue_new_call);
+ rxrpc_get_call(call, rxrpc_call_get_io_thread);
+ spin_lock(&local->client_call_lock);
+ list_add_tail(&call->wait_link, &local->new_client_calls);
+ spin_unlock(&local->client_call_lock);
+ rxrpc_wake_up_io_thread(local);
+ return 0;
+
+error:
+ __set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+ return ret;
+}
+
/*
* Set up a call for the given parameters.
* - Called with the socket lock held, which it must release.
/* Set up or get a connection record and set the protocol parameters,
* including channel number and call ID.
*/
- ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
+ ret = rxrpc_connect_call(call, gfp);
if (ret < 0)
goto error_attached_to_socket;
- rxrpc_see_call(call, rxrpc_call_see_connected);
-
- rxrpc_start_call_timer(call);
-
_leave(" = %p [new]", call);
return call;
error_dup_user_ID:
write_unlock(&rx->call_lock);
release_sock(&rx->sk);
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
- RX_CALL_DEAD, -EEXIST);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EEXIST);
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0,
rxrpc_call_see_userid_exists);
- rxrpc_release_call(rx, call);
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put_userid_exists);
_leave(" = -EEXIST");
return ERR_PTR(-EEXIST);
/* We got an error, but the call is attached to the socket and is in
- * need of release. However, we might now race with recvmsg() when
- * completing the call queues it. Return 0 from sys_sendmsg() and
+ * need of release. However, we might now race with recvmsg() when it
+ * completion notifies the socket. Return 0 from sys_sendmsg() and
* leave the error to recvmsg() to deal with.
*/
error_attached_to_socket:
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret,
rxrpc_call_see_connect_failed);
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
- RX_CALL_DEAD, ret);
+ rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
_leave(" = c=%08x [err]", call->debug_id);
return call;
}
call->call_id = sp->hdr.callNumber;
call->dest_srx.srx_service = sp->hdr.serviceId;
call->cid = sp->hdr.cid;
- call->state = RXRPC_CALL_SERVER_SECURING;
call->cong_tstamp = skb->tstamp;
+ __set_bit(RXRPC_CALL_EXPOSED, &call->flags);
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
+
spin_lock(&conn->state_lock);
switch (conn->state) {
case RXRPC_CONN_SERVICE_UNSECURED:
case RXRPC_CONN_SERVICE_CHALLENGING:
- call->state = RXRPC_CALL_SERVER_SECURING;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
break;
case RXRPC_CONN_SERVICE:
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
break;
- case RXRPC_CONN_REMOTELY_ABORTED:
- __rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
- conn->abort_code, conn->error);
- break;
- case RXRPC_CONN_LOCALLY_ABORTED:
- __rxrpc_abort_call("CON", call, 1,
- conn->abort_code, conn->error);
+ case RXRPC_CONN_ABORTED:
+ rxrpc_set_call_completion(call, conn->completion,
+ conn->abort_code, conn->error);
break;
default:
BUG();
}
+ rxrpc_get_call(call, rxrpc_call_get_io_thread);
+
/* Set the channel for this call. We don't get channel_lock as we're
* only defending against the data_ready handler (which we're called
* from) and the RESPONSE packet parser (which is only really
chan = sp->hdr.cid & RXRPC_CHANNELMASK;
conn->channels[chan].call_counter = call->call_id;
conn->channels[chan].call_id = call->call_id;
- rcu_assign_pointer(conn->channels[chan].call, call);
+ conn->channels[chan].call = call;
spin_unlock(&conn->state_lock);
spin_lock(&conn->peer->lock);
void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
{
struct rxrpc_connection *conn = call->conn;
- bool put = false;
+ bool put = false, putu = false;
_enter("{%d,%d}", call->debug_id, refcount_read(&call->ref));
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
call->flags, rxrpc_call_see_release);
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
-
if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags))
BUG();
rxrpc_put_call_slot(call);
- del_timer_sync(&call->timer);
/* Make sure we don't get any more notifications */
write_lock(&rx->recvmsg_lock);
if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
rb_erase(&call->sock_node, &rx->calls);
memset(&call->sock_node, 0xdd, sizeof(call->sock_node));
- rxrpc_put_call(call, rxrpc_call_put_userid_exists);
+ putu = true;
}
list_del(&call->sock_link);
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
- if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
- rxrpc_disconnect_call(call);
- if (call->security)
- call->security->free_call_crypto(call);
+ if (putu)
+ rxrpc_put_call(call, rxrpc_call_put_userid);
+
_leave("");
}
call = list_entry(rx->to_be_accepted.next,
struct rxrpc_call, accept_link);
list_del(&call->accept_link);
- rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET);
+ rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_sock_release_tba);
rxrpc_put_call(call, rxrpc_call_put_release_sock_tba);
}
call = list_entry(rx->sock_calls.next,
struct rxrpc_call, sock_link);
rxrpc_get_call(call, rxrpc_call_get_release_sock);
- rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET);
- rxrpc_send_abort_packet(call);
+ rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_sock_release);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put_release_sock);
}
dead = __refcount_dec_and_test(&call->ref, &r);
trace_rxrpc_call(debug_id, r - 1, 0, why);
if (dead) {
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
+ ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
if (!list_empty(&call->link)) {
spin_lock(&rxnet->call_lock);
rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned);
rxrpc_put_connection(call->conn, rxrpc_conn_put_call);
+ rxrpc_deactivate_bundle(call->bundle);
+ rxrpc_put_bundle(call->bundle, rxrpc_bundle_put_call);
rxrpc_put_peer(call->peer, rxrpc_peer_put_call);
rxrpc_put_local(call->local, rxrpc_local_put_call);
call_rcu(&call->rcu, rxrpc_rcu_free_call);
{
memset(&call->sock_node, 0xcd, sizeof(call->sock_node));
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
+ ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
del_timer(&call->timer);
pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
call, refcount_read(&call->ref),
- rxrpc_call_states[call->state],
+ rxrpc_call_states[__rxrpc_call_state(call)],
call->flags, call->events);
spin_unlock(&rxnet->call_lock);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Call state changing functions.
+ *
+ * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include "ar-internal.h"
+
+/*
+ * Transition a call to the complete state.
+ */
+bool rxrpc_set_call_completion(struct rxrpc_call *call,
+ enum rxrpc_call_completion compl,
+ u32 abort_code,
+ int error)
+{
+ if (__rxrpc_call_state(call) == RXRPC_CALL_COMPLETE)
+ return false;
+
+ call->abort_code = abort_code;
+ call->error = error;
+ call->completion = compl;
+ /* Allow reader of completion state to operate locklessly */
+ rxrpc_set_call_state(call, RXRPC_CALL_COMPLETE);
+ trace_rxrpc_call_complete(call);
+ wake_up(&call->waitq);
+ rxrpc_notify_socket(call);
+ return true;
+}
+
+/*
+ * Record that a call successfully completed.
+ */
+bool rxrpc_call_completed(struct rxrpc_call *call)
+{
+ return rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
+}
+
+/*
+ * Record that a call is locally aborted.
+ */
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
+{
+ trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
+ abort_code, error);
+ if (!rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
+ abort_code, error))
+ return false;
+ if (test_bit(RXRPC_CALL_EXPOSED, &call->flags))
+ rxrpc_send_abort_packet(call);
+ return true;
+}
+
+/*
+ * Record that a call errored out before even getting off the ground, thereby
+ * setting the state to allow it to be destroyed.
+ */
+void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl,
+ int error)
+{
+ call->abort_code = RX_CALL_DEAD;
+ call->error = error;
+ call->completion = compl;
+ call->_state = RXRPC_CALL_COMPLETE;
+ trace_rxrpc_call_complete(call);
+ WARN_ON_ONCE(__test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags));
+}
__read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ;
__read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
-/*
- * We use machine-unique IDs for our client connections.
- */
-DEFINE_IDR(rxrpc_client_conn_ids);
-static DEFINE_SPINLOCK(rxrpc_conn_id_lock);
-
-static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
-
-/*
- * Get a connection ID and epoch for a client connection from the global pool.
- * The connection struct pointer is then recorded in the idr radix tree. The
- * epoch doesn't change until the client is rebooted (or, at least, unless the
- * module is unloaded).
- */
-static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn,
- gfp_t gfp)
+static void rxrpc_activate_bundle(struct rxrpc_bundle *bundle)
{
- struct rxrpc_net *rxnet = conn->rxnet;
- int id;
-
- _enter("");
-
- idr_preload(gfp);
- spin_lock(&rxrpc_conn_id_lock);
-
- id = idr_alloc_cyclic(&rxrpc_client_conn_ids, conn,
- 1, 0x40000000, GFP_NOWAIT);
- if (id < 0)
- goto error;
-
- spin_unlock(&rxrpc_conn_id_lock);
- idr_preload_end();
-
- conn->proto.epoch = rxnet->epoch;
- conn->proto.cid = id << RXRPC_CIDSHIFT;
- set_bit(RXRPC_CONN_HAS_IDR, &conn->flags);
- _leave(" [CID %x]", conn->proto.cid);
- return 0;
-
-error:
- spin_unlock(&rxrpc_conn_id_lock);
- idr_preload_end();
- _leave(" = %d", id);
- return id;
+ atomic_inc(&bundle->active);
}
/*
- * Release a connection ID for a client connection from the global pool.
+ * Release a connection ID for a client connection.
*/
-static void rxrpc_put_client_connection_id(struct rxrpc_connection *conn)
+static void rxrpc_put_client_connection_id(struct rxrpc_local *local,
+ struct rxrpc_connection *conn)
{
- if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) {
- spin_lock(&rxrpc_conn_id_lock);
- idr_remove(&rxrpc_client_conn_ids,
- conn->proto.cid >> RXRPC_CIDSHIFT);
- spin_unlock(&rxrpc_conn_id_lock);
- }
+ idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT);
}
/*
* Destroy the client connection ID tree.
*/
-void rxrpc_destroy_client_conn_ids(void)
+static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local)
{
struct rxrpc_connection *conn;
int id;
- if (!idr_is_empty(&rxrpc_client_conn_ids)) {
- idr_for_each_entry(&rxrpc_client_conn_ids, conn, id) {
+ if (!idr_is_empty(&local->conn_ids)) {
+ idr_for_each_entry(&local->conn_ids, conn, id) {
pr_err("AF_RXRPC: Leaked client conn %p {%d}\n",
conn, refcount_read(&conn->ref));
}
BUG();
}
- idr_destroy(&rxrpc_client_conn_ids);
+ idr_destroy(&local->conn_ids);
}
/*
* Allocate a connection bundle.
*/
-static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp,
+static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call,
gfp_t gfp)
{
struct rxrpc_bundle *bundle;
bundle = kzalloc(sizeof(*bundle), gfp);
if (bundle) {
- bundle->local = cp->local;
- bundle->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_bundle);
- bundle->key = cp->key;
- bundle->exclusive = cp->exclusive;
- bundle->upgrade = cp->upgrade;
- bundle->service_id = cp->service_id;
- bundle->security_level = cp->security_level;
+ bundle->local = call->local;
+ bundle->peer = rxrpc_get_peer(call->peer, rxrpc_peer_get_bundle);
+ bundle->key = key_get(call->key);
+ bundle->security = call->security;
+ bundle->exclusive = test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags);
+ bundle->upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags);
+ bundle->service_id = call->dest_srx.srx_service;
+ bundle->security_level = call->security_level;
refcount_set(&bundle->ref, 1);
atomic_set(&bundle->active, 1);
- spin_lock_init(&bundle->channel_lock);
INIT_LIST_HEAD(&bundle->waiting_calls);
trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new);
}
{
trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free);
rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle);
+ key_put(bundle->key);
kfree(bundle);
}
void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why)
{
- unsigned int id = bundle->debug_id;
+ unsigned int id;
bool dead;
int r;
- dead = __refcount_dec_and_test(&bundle->ref, &r);
- trace_rxrpc_bundle(id, r - 1, why);
- if (dead)
- rxrpc_free_bundle(bundle);
+ if (bundle) {
+ id = bundle->debug_id;
+ dead = __refcount_dec_and_test(&bundle->ref, &r);
+ trace_rxrpc_bundle(id, r - 1, why);
+ if (dead)
+ rxrpc_free_bundle(bundle);
+ }
+}
+
+/*
+ * Get rid of outstanding client connection preallocations when a local
+ * endpoint is destroyed.
+ */
+void rxrpc_purge_client_connections(struct rxrpc_local *local)
+{
+ rxrpc_destroy_client_conn_ids(local);
}
/*
* Allocate a client connection.
*/
static struct rxrpc_connection *
-rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp)
+rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle)
{
struct rxrpc_connection *conn;
- struct rxrpc_net *rxnet = bundle->local->rxnet;
- int ret;
+ struct rxrpc_local *local = bundle->local;
+ struct rxrpc_net *rxnet = local->rxnet;
+ int id;
_enter("");
- conn = rxrpc_alloc_connection(rxnet, gfp);
- if (!conn) {
- _leave(" = -ENOMEM");
+ conn = rxrpc_alloc_connection(rxnet, GFP_ATOMIC | __GFP_NOWARN);
+ if (!conn)
return ERR_PTR(-ENOMEM);
+
+ id = idr_alloc_cyclic(&local->conn_ids, conn, 1, 0x40000000,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (id < 0) {
+ kfree(conn);
+ return ERR_PTR(id);
}
refcount_set(&conn->ref, 1);
- conn->bundle = bundle;
- conn->local = bundle->local;
- conn->peer = bundle->peer;
- conn->key = bundle->key;
+ conn->proto.cid = id << RXRPC_CIDSHIFT;
+ conn->proto.epoch = local->rxnet->epoch;
+ conn->out_clientflag = RXRPC_CLIENT_INITIATED;
+ conn->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn);
+ conn->local = rxrpc_get_local(bundle->local, rxrpc_local_get_client_conn);
+ conn->peer = rxrpc_get_peer(bundle->peer, rxrpc_peer_get_client_conn);
+ conn->key = key_get(bundle->key);
+ conn->security = bundle->security;
conn->exclusive = bundle->exclusive;
conn->upgrade = bundle->upgrade;
conn->orig_service_id = bundle->service_id;
conn->security_level = bundle->security_level;
- conn->out_clientflag = RXRPC_CLIENT_INITIATED;
- conn->state = RXRPC_CONN_CLIENT;
+ conn->state = RXRPC_CONN_CLIENT_UNSECURED;
conn->service_id = conn->orig_service_id;
- ret = rxrpc_get_client_connection_id(conn, gfp);
- if (ret < 0)
- goto error_0;
-
- ret = rxrpc_init_client_conn_security(conn);
- if (ret < 0)
- goto error_1;
+ if (conn->security == &rxrpc_no_security)
+ conn->state = RXRPC_CONN_CLIENT;
atomic_inc(&rxnet->nr_conns);
write_lock(&rxnet->conn_lock);
list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
write_unlock(&rxnet->conn_lock);
- rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn);
- rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn);
- rxrpc_get_local(conn->local, rxrpc_local_get_client_conn);
- key_get(conn->key);
-
- trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref),
- rxrpc_conn_new_client);
+ rxrpc_see_connection(conn, rxrpc_conn_new_client);
atomic_inc(&rxnet->nr_client_conns);
trace_rxrpc_client(conn, -1, rxrpc_client_alloc);
- _leave(" = %p", conn);
return conn;
-
-error_1:
- rxrpc_put_client_connection_id(conn);
-error_0:
- kfree(conn);
- _leave(" = %d", ret);
- return ERR_PTR(ret);
}
/*
if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags))
goto dont_reuse;
- if (conn->state != RXRPC_CONN_CLIENT ||
+ if ((conn->state != RXRPC_CONN_CLIENT_UNSECURED &&
+ conn->state != RXRPC_CONN_CLIENT) ||
conn->proto.epoch != rxnet->epoch)
goto mark_dont_reuse;
* times the maximum number of client conns away from the current
* allocation point to try and keep the IDs concentrated.
*/
- id_cursor = idr_get_cursor(&rxrpc_client_conn_ids);
+ id_cursor = idr_get_cursor(&conn->local->conn_ids);
id = conn->proto.cid >> RXRPC_CIDSHIFT;
distance = id - id_cursor;
if (distance < 0)
* Look up the conn bundle that matches the connection parameters, adding it if
* it doesn't yet exist.
*/
-static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp,
- gfp_t gfp)
+int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
{
static atomic_t rxrpc_bundle_id;
struct rxrpc_bundle *bundle, *candidate;
- struct rxrpc_local *local = cp->local;
+ struct rxrpc_local *local = call->local;
struct rb_node *p, **pp, *parent;
long diff;
+ bool upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags);
_enter("{%px,%x,%u,%u}",
- cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade);
+ call->peer, key_serial(call->key), call->security_level,
+ upgrade);
- if (cp->exclusive)
- return rxrpc_alloc_bundle(cp, gfp);
+ if (test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags)) {
+ call->bundle = rxrpc_alloc_bundle(call, gfp);
+ return call->bundle ? 0 : -ENOMEM;
+ }
/* First, see if the bundle is already there. */
_debug("search 1");
while (p) {
bundle = rb_entry(p, struct rxrpc_bundle, local_node);
-#define cmp(X) ((long)bundle->X - (long)cp->X)
- diff = (cmp(peer) ?:
- cmp(key) ?:
- cmp(security_level) ?:
- cmp(upgrade));
+#define cmp(X, Y) ((long)(X) - (long)(Y))
+ diff = (cmp(bundle->peer, call->peer) ?:
+ cmp(bundle->key, call->key) ?:
+ cmp(bundle->security_level, call->security_level) ?:
+ cmp(bundle->upgrade, upgrade));
#undef cmp
if (diff < 0)
p = p->rb_left;
_debug("not found");
/* It wasn't. We need to add one. */
- candidate = rxrpc_alloc_bundle(cp, gfp);
+ candidate = rxrpc_alloc_bundle(call, gfp);
if (!candidate)
- return NULL;
+ return -ENOMEM;
_debug("search 2");
spin_lock(&local->client_bundles_lock);
parent = *pp;
bundle = rb_entry(parent, struct rxrpc_bundle, local_node);
-#define cmp(X) ((long)bundle->X - (long)cp->X)
- diff = (cmp(peer) ?:
- cmp(key) ?:
- cmp(security_level) ?:
- cmp(upgrade));
+#define cmp(X, Y) ((long)(X) - (long)(Y))
+ diff = (cmp(bundle->peer, call->peer) ?:
+ cmp(bundle->key, call->key) ?:
+ cmp(bundle->security_level, call->security_level) ?:
+ cmp(bundle->upgrade, upgrade));
#undef cmp
if (diff < 0)
pp = &(*pp)->rb_left;
candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id);
rb_link_node(&candidate->local_node, parent, pp);
rb_insert_color(&candidate->local_node, &local->client_bundles);
- rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
+ call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
spin_unlock(&local->client_bundles_lock);
- _leave(" = %u [new]", candidate->debug_id);
- return candidate;
+ _leave(" = B=%u [new]", call->bundle->debug_id);
+ return 0;
found_bundle_free:
rxrpc_free_bundle(candidate);
found_bundle:
- rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call);
- atomic_inc(&bundle->active);
+ call->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call);
+ rxrpc_activate_bundle(bundle);
spin_unlock(&local->client_bundles_lock);
- _leave(" = %u [found]", bundle->debug_id);
- return bundle;
-}
-
-/*
- * Create or find a client bundle to use for a call.
- *
- * If we return with a connection, the call will be on its waiting list. It's
- * left to the caller to assign a channel and wake up the call.
- */
-static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx,
- struct rxrpc_call *call,
- struct rxrpc_conn_parameters *cp,
- struct sockaddr_rxrpc *srx,
- gfp_t gfp)
-{
- struct rxrpc_bundle *bundle;
-
- _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
-
- cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
- if (!cp->peer)
- goto error;
-
- call->tx_last_sent = ktime_get_real();
- call->cong_ssthresh = cp->peer->cong_ssthresh;
- if (call->cong_cwnd >= call->cong_ssthresh)
- call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
- else
- call->cong_mode = RXRPC_CALL_SLOW_START;
- if (cp->upgrade)
- __set_bit(RXRPC_CALL_UPGRADE, &call->flags);
-
- /* Find the client connection bundle. */
- bundle = rxrpc_look_up_bundle(cp, gfp);
- if (!bundle)
- goto error;
-
- /* Get this call queued. Someone else may activate it whilst we're
- * lining up a new connection, but that's fine.
- */
- spin_lock(&bundle->channel_lock);
- list_add_tail(&call->chan_wait_link, &bundle->waiting_calls);
- spin_unlock(&bundle->channel_lock);
-
- _leave(" = [B=%x]", bundle->debug_id);
- return bundle;
-
-error:
- _leave(" = -ENOMEM");
- return ERR_PTR(-ENOMEM);
+ _leave(" = B=%u [found]", call->bundle->debug_id);
+ return 0;
}
/*
* Allocate a new connection and add it into a bundle.
*/
-static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp)
- __releases(bundle->channel_lock)
+static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle,
+ unsigned int slot)
{
- struct rxrpc_connection *candidate = NULL, *old = NULL;
- bool conflict;
- int i;
-
- _enter("");
-
- conflict = bundle->alloc_conn;
- if (!conflict)
- bundle->alloc_conn = true;
- spin_unlock(&bundle->channel_lock);
- if (conflict) {
- _leave(" [conf]");
- return;
- }
-
- candidate = rxrpc_alloc_client_connection(bundle, gfp);
-
- spin_lock(&bundle->channel_lock);
- bundle->alloc_conn = false;
-
- if (IS_ERR(candidate)) {
- bundle->alloc_error = PTR_ERR(candidate);
- spin_unlock(&bundle->channel_lock);
- _leave(" [err %ld]", PTR_ERR(candidate));
- return;
- }
-
- bundle->alloc_error = 0;
-
- for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) {
- unsigned int shift = i * RXRPC_MAXCALLS;
- int j;
-
- old = bundle->conns[i];
- if (!rxrpc_may_reuse_conn(old)) {
- if (old)
- trace_rxrpc_client(old, -1, rxrpc_client_replace);
- candidate->bundle_shift = shift;
- atomic_inc(&bundle->active);
- bundle->conns[i] = candidate;
- for (j = 0; j < RXRPC_MAXCALLS; j++)
- set_bit(shift + j, &bundle->avail_chans);
- candidate = NULL;
- break;
- }
+ struct rxrpc_connection *conn, *old;
+ unsigned int shift = slot * RXRPC_MAXCALLS;
+ unsigned int i;
- old = NULL;
+ old = bundle->conns[slot];
+ if (old) {
+ bundle->conns[slot] = NULL;
+ trace_rxrpc_client(old, -1, rxrpc_client_replace);
+ rxrpc_put_connection(old, rxrpc_conn_put_noreuse);
}
- spin_unlock(&bundle->channel_lock);
-
- if (candidate) {
- _debug("discard C=%x", candidate->debug_id);
- trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate);
- rxrpc_put_connection(candidate, rxrpc_conn_put_discard);
+ conn = rxrpc_alloc_client_connection(bundle);
+ if (IS_ERR(conn)) {
+ bundle->alloc_error = PTR_ERR(conn);
+ return false;
}
- rxrpc_put_connection(old, rxrpc_conn_put_noreuse);
- _leave("");
+ rxrpc_activate_bundle(bundle);
+ conn->bundle_shift = shift;
+ bundle->conns[slot] = conn;
+ for (i = 0; i < RXRPC_MAXCALLS; i++)
+ set_bit(shift + i, &bundle->avail_chans);
+ return true;
}
/*
* Add a connection to a bundle if there are no usable connections or we have
* connections waiting for extra capacity.
*/
-static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp)
+static bool rxrpc_bundle_has_space(struct rxrpc_bundle *bundle)
{
- struct rxrpc_call *call;
- int i, usable;
+ int slot = -1, i, usable;
_enter("");
- spin_lock(&bundle->channel_lock);
+ bundle->alloc_error = 0;
/* See if there are any usable connections. */
usable = 0;
- for (i = 0; i < ARRAY_SIZE(bundle->conns); i++)
+ for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) {
if (rxrpc_may_reuse_conn(bundle->conns[i]))
usable++;
-
- if (!usable && !list_empty(&bundle->waiting_calls)) {
- call = list_first_entry(&bundle->waiting_calls,
- struct rxrpc_call, chan_wait_link);
- if (test_bit(RXRPC_CALL_UPGRADE, &call->flags))
- bundle->try_upgrade = true;
+ else if (slot == -1)
+ slot = i;
}
+ if (!usable && bundle->upgrade)
+ bundle->try_upgrade = true;
+
if (!usable)
goto alloc_conn;
if (!bundle->avail_chans &&
!bundle->try_upgrade &&
- !list_empty(&bundle->waiting_calls) &&
usable < ARRAY_SIZE(bundle->conns))
goto alloc_conn;
- spin_unlock(&bundle->channel_lock);
_leave("");
- return;
+ return usable;
alloc_conn:
- return rxrpc_add_conn_to_bundle(bundle, gfp);
+ return slot >= 0 ? rxrpc_add_conn_to_bundle(bundle, slot) : false;
}
/*
struct rxrpc_channel *chan = &conn->channels[channel];
struct rxrpc_bundle *bundle = conn->bundle;
struct rxrpc_call *call = list_entry(bundle->waiting_calls.next,
- struct rxrpc_call, chan_wait_link);
+ struct rxrpc_call, wait_link);
u32 call_id = chan->call_counter + 1;
_enter("C=%x,%u", conn->debug_id, channel);
+ list_del_init(&call->wait_link);
+
trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate);
/* Cancel the final ACK on the previous call if it hasn't been sent yet
clear_bit(conn->bundle_shift + channel, &bundle->avail_chans);
rxrpc_see_call(call, rxrpc_call_see_activate_client);
- list_del_init(&call->chan_wait_link);
- call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call);
call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call);
call->cid = conn->proto.cid | channel;
call->call_id = call_id;
call->dest_srx.srx_service = conn->service_id;
-
- trace_rxrpc_connect_call(call);
-
- write_lock(&call->state_lock);
- call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
- write_unlock(&call->state_lock);
-
- /* Paired with the read barrier in rxrpc_connect_call(). This orders
- * cid and epoch in the connection wrt to call_id without the need to
- * take the channel_lock.
- *
- * We provisionally assign a callNumber at this point, but we don't
- * confirm it until the call is about to be exposed.
- *
- * TODO: Pair with a barrier in the data_ready handler when that looks
- * at the call ID through a connection channel.
- */
- smp_wmb();
+ call->cong_ssthresh = call->peer->cong_ssthresh;
+ if (call->cong_cwnd >= call->cong_ssthresh)
+ call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
+ else
+ call->cong_mode = RXRPC_CALL_SLOW_START;
chan->call_id = call_id;
chan->call_debug_id = call->debug_id;
- rcu_assign_pointer(chan->call, call);
+ chan->call = call;
+
+ rxrpc_see_call(call, rxrpc_call_see_connected);
+ trace_rxrpc_connect_call(call);
+ call->tx_last_sent = ktime_get_real();
+ rxrpc_start_call_timer(call);
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST);
wake_up(&call->waitq);
}
/*
* Remove a connection from the idle list if it's on it.
*/
-static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn)
+static void rxrpc_unidle_conn(struct rxrpc_connection *conn)
{
- struct rxrpc_net *rxnet = bundle->local->rxnet;
- bool drop_ref;
-
if (!list_empty(&conn->cache_link)) {
- drop_ref = false;
- spin_lock(&rxnet->client_conn_cache_lock);
- if (!list_empty(&conn->cache_link)) {
- list_del_init(&conn->cache_link);
- drop_ref = true;
- }
- spin_unlock(&rxnet->client_conn_cache_lock);
- if (drop_ref)
- rxrpc_put_connection(conn, rxrpc_conn_put_unidle);
+ list_del_init(&conn->cache_link);
+ rxrpc_put_connection(conn, rxrpc_conn_put_unidle);
}
}
/*
- * Assign channels and callNumbers to waiting calls with channel_lock
- * held by caller.
+ * Assign channels and callNumbers to waiting calls.
*/
-static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle)
+static void rxrpc_activate_channels(struct rxrpc_bundle *bundle)
{
struct rxrpc_connection *conn;
unsigned long avail, mask;
unsigned int channel, slot;
+ trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans);
+
if (bundle->try_upgrade)
mask = 1;
else
if (bundle->try_upgrade)
set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
- rxrpc_unidle_conn(bundle, conn);
+ rxrpc_unidle_conn(conn);
channel &= (RXRPC_MAXCALLS - 1);
conn->act_chans |= 1 << channel;
}
/*
- * Assign channels and callNumbers to waiting calls.
- */
-static void rxrpc_activate_channels(struct rxrpc_bundle *bundle)
-{
- _enter("B=%x", bundle->debug_id);
-
- trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans);
-
- if (!bundle->avail_chans)
- return;
-
- spin_lock(&bundle->channel_lock);
- rxrpc_activate_channels_locked(bundle);
- spin_unlock(&bundle->channel_lock);
- _leave("");
-}
-
-/*
- * Wait for a callNumber and a channel to be granted to a call.
- */
-static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle,
- struct rxrpc_call *call, gfp_t gfp)
-{
- DECLARE_WAITQUEUE(myself, current);
- int ret = 0;
-
- _enter("%d", call->debug_id);
-
- if (!gfpflags_allow_blocking(gfp)) {
- rxrpc_maybe_add_conn(bundle, gfp);
- rxrpc_activate_channels(bundle);
- ret = bundle->alloc_error ?: -EAGAIN;
- goto out;
- }
-
- add_wait_queue_exclusive(&call->waitq, &myself);
- for (;;) {
- rxrpc_maybe_add_conn(bundle, gfp);
- rxrpc_activate_channels(bundle);
- ret = bundle->alloc_error;
- if (ret < 0)
- break;
-
- switch (call->interruptibility) {
- case RXRPC_INTERRUPTIBLE:
- case RXRPC_PREINTERRUPTIBLE:
- set_current_state(TASK_INTERRUPTIBLE);
- break;
- case RXRPC_UNINTERRUPTIBLE:
- default:
- set_current_state(TASK_UNINTERRUPTIBLE);
- break;
- }
- if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN)
- break;
- if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
- call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
- signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
- schedule();
- }
- remove_wait_queue(&call->waitq, &myself);
- __set_current_state(TASK_RUNNING);
-
-out:
- _leave(" = %d", ret);
- return ret;
-}
-
-/*
- * find a connection for a call
- * - called in process context with IRQs enabled
+ * Connect waiting channels (called from the I/O thread).
*/
-int rxrpc_connect_call(struct rxrpc_sock *rx,
- struct rxrpc_call *call,
- struct rxrpc_conn_parameters *cp,
- struct sockaddr_rxrpc *srx,
- gfp_t gfp)
+void rxrpc_connect_client_calls(struct rxrpc_local *local)
{
- struct rxrpc_bundle *bundle;
- struct rxrpc_net *rxnet = cp->local->rxnet;
- int ret = 0;
-
- _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
-
- rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
+ struct rxrpc_call *call;
- bundle = rxrpc_prep_call(rx, call, cp, srx, gfp);
- if (IS_ERR(bundle)) {
- ret = PTR_ERR(bundle);
- goto out;
- }
+ while ((call = list_first_entry_or_null(&local->new_client_calls,
+ struct rxrpc_call, wait_link))
+ ) {
+ struct rxrpc_bundle *bundle = call->bundle;
- if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) {
- ret = rxrpc_wait_for_channel(bundle, call, gfp);
- if (ret < 0)
- goto wait_failed;
- }
+ spin_lock(&local->client_call_lock);
+ list_move_tail(&call->wait_link, &bundle->waiting_calls);
+ spin_unlock(&local->client_call_lock);
-granted_channel:
- /* Paired with the write barrier in rxrpc_activate_one_channel(). */
- smp_rmb();
-
-out_put_bundle:
- rxrpc_deactivate_bundle(bundle);
- rxrpc_put_bundle(bundle, rxrpc_bundle_get_client_call);
-out:
- _leave(" = %d", ret);
- return ret;
-
-wait_failed:
- spin_lock(&bundle->channel_lock);
- list_del_init(&call->chan_wait_link);
- spin_unlock(&bundle->channel_lock);
-
- if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) {
- ret = 0;
- goto granted_channel;
+ if (rxrpc_bundle_has_space(bundle))
+ rxrpc_activate_channels(bundle);
}
-
- trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed);
- rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
- rxrpc_disconnect_client_call(bundle, call);
- goto out_put_bundle;
}
/*
/*
* Set the reap timer.
*/
-static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet)
+static void rxrpc_set_client_reap_timer(struct rxrpc_local *local)
{
- if (!rxnet->kill_all_client_conns) {
+ if (!local->kill_all_client_conns) {
unsigned long now = jiffies;
unsigned long reap_at = now + rxrpc_conn_idle_client_expiry;
- if (rxnet->live)
- timer_reduce(&rxnet->client_conn_reap_timer, reap_at);
+ if (local->rxnet->live)
+ timer_reduce(&local->client_conn_reap_timer, reap_at);
}
}
{
struct rxrpc_connection *conn;
struct rxrpc_channel *chan = NULL;
- struct rxrpc_net *rxnet = bundle->local->rxnet;
+ struct rxrpc_local *local = bundle->local;
unsigned int channel;
bool may_reuse;
u32 cid;
_enter("c=%x", call->debug_id);
- spin_lock(&bundle->channel_lock);
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
-
/* Calls that have never actually been assigned a channel can simply be
* discarded.
*/
_debug("call is waiting");
ASSERTCMP(call->call_id, ==, 0);
ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags));
- list_del_init(&call->chan_wait_link);
- goto out;
+ list_del_init(&call->wait_link);
+ return;
}
cid = call->cid;
chan = &conn->channels[channel];
trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
- if (rcu_access_pointer(chan->call) != call) {
- spin_unlock(&bundle->channel_lock);
- BUG();
- }
+ if (WARN_ON(chan->call != call))
+ return;
may_reuse = rxrpc_may_reuse_conn(conn);
trace_rxrpc_client(conn, channel, rxrpc_client_to_active);
bundle->try_upgrade = false;
if (may_reuse)
- rxrpc_activate_channels_locked(bundle);
+ rxrpc_activate_channels(bundle);
}
-
}
/* See if we can pass the channel directly to another call. */
if (may_reuse && !list_empty(&bundle->waiting_calls)) {
trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass);
rxrpc_activate_one_channel(conn, channel);
- goto out;
+ return;
}
/* Schedule the final ACK to be transmitted in a short while so that it
}
/* Deactivate the channel. */
- rcu_assign_pointer(chan->call, NULL);
+ chan->call = NULL;
set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans);
conn->act_chans &= ~(1 << channel);
conn->idle_timestamp = jiffies;
rxrpc_get_connection(conn, rxrpc_conn_get_idle);
- spin_lock(&rxnet->client_conn_cache_lock);
- list_move_tail(&conn->cache_link, &rxnet->idle_client_conns);
- spin_unlock(&rxnet->client_conn_cache_lock);
+ list_move_tail(&conn->cache_link, &local->idle_client_conns);
- rxrpc_set_client_reap_timer(rxnet);
+ rxrpc_set_client_reap_timer(local);
}
-
-out:
- spin_unlock(&bundle->channel_lock);
- _leave("");
- return;
}
/*
{
struct rxrpc_bundle *bundle = conn->bundle;
unsigned int bindex;
- bool need_drop = false;
int i;
_enter("C=%x", conn->debug_id);
if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
rxrpc_process_delayed_final_acks(conn, true);
- spin_lock(&bundle->channel_lock);
bindex = conn->bundle_shift / RXRPC_MAXCALLS;
if (bundle->conns[bindex] == conn) {
_debug("clear slot %u", bindex);
bundle->conns[bindex] = NULL;
for (i = 0; i < RXRPC_MAXCALLS; i++)
clear_bit(conn->bundle_shift + i, &bundle->avail_chans);
- need_drop = true;
- }
- spin_unlock(&bundle->channel_lock);
-
- if (need_drop) {
+ rxrpc_put_client_connection_id(bundle->local, conn);
rxrpc_deactivate_bundle(bundle);
rxrpc_put_connection(conn, rxrpc_conn_put_unbundle);
}
/*
* Drop the active count on a bundle.
*/
-static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle)
+void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle)
{
- struct rxrpc_local *local = bundle->local;
+ struct rxrpc_local *local;
bool need_put = false;
+ if (!bundle)
+ return;
+
+ local = bundle->local;
if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) {
if (!bundle->exclusive) {
_debug("erase bundle");
trace_rxrpc_client(conn, -1, rxrpc_client_cleanup);
atomic_dec(&rxnet->nr_client_conns);
- rxrpc_put_client_connection_id(conn);
+ rxrpc_put_client_connection_id(local, conn);
}
/*
* This may be called from conn setup or from a work item so cannot be
* considered non-reentrant.
*/
-void rxrpc_discard_expired_client_conns(struct work_struct *work)
+void rxrpc_discard_expired_client_conns(struct rxrpc_local *local)
{
struct rxrpc_connection *conn;
- struct rxrpc_net *rxnet =
- container_of(work, struct rxrpc_net, client_conn_reaper);
unsigned long expiry, conn_expires_at, now;
unsigned int nr_conns;
_enter("");
- if (list_empty(&rxnet->idle_client_conns)) {
- _leave(" [empty]");
- return;
- }
-
- /* Don't double up on the discarding */
- if (!mutex_trylock(&rxnet->client_conn_discard_lock)) {
- _leave(" [already]");
- return;
- }
-
/* We keep an estimate of what the number of conns ought to be after
* we've discarded some so that we don't overdo the discarding.
*/
- nr_conns = atomic_read(&rxnet->nr_client_conns);
+ nr_conns = atomic_read(&local->rxnet->nr_client_conns);
next:
- spin_lock(&rxnet->client_conn_cache_lock);
-
- if (list_empty(&rxnet->idle_client_conns))
- goto out;
-
- conn = list_entry(rxnet->idle_client_conns.next,
- struct rxrpc_connection, cache_link);
+ conn = list_first_entry_or_null(&local->idle_client_conns,
+ struct rxrpc_connection, cache_link);
+ if (!conn)
+ return;
- if (!rxnet->kill_all_client_conns) {
+ if (!local->kill_all_client_conns) {
/* If the number of connections is over the reap limit, we
* expedite discard by reducing the expiry timeout. We must,
* however, have at least a short grace period to be able to do
trace_rxrpc_client(conn, -1, rxrpc_client_discard);
list_del_init(&conn->cache_link);
- spin_unlock(&rxnet->client_conn_cache_lock);
-
rxrpc_unbundle_conn(conn);
/* Drop the ->cache_link ref */
rxrpc_put_connection(conn, rxrpc_conn_put_discard_idle);
* then things get messier.
*/
_debug("not yet");
- if (!rxnet->kill_all_client_conns)
- timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at);
-
-out:
- spin_unlock(&rxnet->client_conn_cache_lock);
- mutex_unlock(&rxnet->client_conn_discard_lock);
- _leave("");
-}
-
-/*
- * Preemptively destroy all the client connection records rather than waiting
- * for them to time out
- */
-void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet)
-{
- _enter("");
-
- spin_lock(&rxnet->client_conn_cache_lock);
- rxnet->kill_all_client_conns = true;
- spin_unlock(&rxnet->client_conn_cache_lock);
-
- del_timer_sync(&rxnet->client_conn_reap_timer);
-
- if (!rxrpc_queue_work(&rxnet->client_conn_reaper))
- _debug("destroy: queue failed");
+ if (!local->kill_all_client_conns)
+ timer_reduce(&local->client_conn_reap_timer, conn_expires_at);
_leave("");
}
*/
void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
{
- struct rxrpc_connection *conn, *tmp;
- struct rxrpc_net *rxnet = local->rxnet;
- LIST_HEAD(graveyard);
+ struct rxrpc_connection *conn;
_enter("");
- spin_lock(&rxnet->client_conn_cache_lock);
-
- list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns,
- cache_link) {
- if (conn->local == local) {
- atomic_dec(&conn->active);
- trace_rxrpc_client(conn, -1, rxrpc_client_discard);
- list_move(&conn->cache_link, &graveyard);
- }
- }
+ local->kill_all_client_conns = true;
- spin_unlock(&rxnet->client_conn_cache_lock);
+ del_timer_sync(&local->client_conn_reap_timer);
- while (!list_empty(&graveyard)) {
- conn = list_entry(graveyard.next,
- struct rxrpc_connection, cache_link);
+ while ((conn = list_first_entry_or_null(&local->idle_client_conns,
+ struct rxrpc_connection, cache_link))) {
list_del_init(&conn->cache_link);
+ atomic_dec(&conn->active);
+ trace_rxrpc_client(conn, -1, rxrpc_client_discard);
rxrpc_unbundle_conn(conn);
rxrpc_put_connection(conn, rxrpc_conn_put_local_dead);
}
#include <net/ip.h>
#include "ar-internal.h"
+/*
+ * Set the completion state on an aborted connection.
+ */
+static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err,
+ enum rxrpc_call_completion compl)
+{
+ bool aborted = false;
+
+ if (conn->state != RXRPC_CONN_ABORTED) {
+ spin_lock(&conn->state_lock);
+ if (conn->state != RXRPC_CONN_ABORTED) {
+ conn->abort_code = abort_code;
+ conn->error = err;
+ conn->completion = compl;
+ /* Order the abort info before the state change. */
+ smp_store_release(&conn->state, RXRPC_CONN_ABORTED);
+ set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
+ set_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events);
+ aborted = true;
+ }
+ spin_unlock(&conn->state_lock);
+ }
+
+ return aborted;
+}
+
+/*
+ * Mark a socket buffer to indicate that the connection it's on should be aborted.
+ */
+int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err, enum rxrpc_abort_reason why)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ if (rxrpc_set_conn_aborted(conn, skb, abort_code, err,
+ RXRPC_CALL_LOCALLY_ABORTED)) {
+ trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber,
+ sp->hdr.seq, abort_code, err);
+ rxrpc_poke_conn(conn, rxrpc_conn_get_poke_abort);
+ }
+ return -EPROTO;
+}
+
+/*
+ * Mark a connection as being remotely aborted.
+ */
+static bool rxrpc_input_conn_abort(struct rxrpc_connection *conn,
+ struct sk_buff *skb)
+{
+ return rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED,
+ RXRPC_CALL_REMOTELY_ABORTED);
+}
+
/*
* Retransmit terminal ACK or ABORT of the previous call.
*/
-static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- unsigned int channel)
+void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
+ struct sk_buff *skb,
+ unsigned int channel)
{
struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL;
struct rxrpc_channel *chan;
/* If the last call got moved on whilst we were waiting to run, just
* ignore this packet.
*/
- call_id = READ_ONCE(chan->last_call);
- /* Sync with __rxrpc_disconnect_call() */
- smp_rmb();
+ call_id = chan->last_call;
if (skb && call_id != sp->hdr.callNumber)
return;
iov[2].iov_base = &ack_info;
iov[2].iov_len = sizeof(ack_info);
+ serial = atomic_inc_return(&conn->serial);
+
pkt.whdr.epoch = htonl(conn->proto.epoch);
pkt.whdr.cid = htonl(conn->proto.cid | channel);
pkt.whdr.callNumber = htonl(call_id);
+ pkt.whdr.serial = htonl(serial);
pkt.whdr.seq = 0;
pkt.whdr.type = chan->last_type;
pkt.whdr.flags = conn->out_clientflag;
iov[0].iov_len += sizeof(pkt.ack);
len += sizeof(pkt.ack) + 3 + sizeof(ack_info);
ioc = 3;
- break;
-
- default:
- return;
- }
-
- /* Resync with __rxrpc_disconnect_call() and check that the last call
- * didn't get advanced whilst we were filling out the packets.
- */
- smp_rmb();
- if (READ_ONCE(chan->last_call) != call_id)
- return;
-
- serial = atomic_inc_return(&conn->serial);
- pkt.whdr.serial = htonl(serial);
- switch (chan->last_type) {
- case RXRPC_PACKET_TYPE_ABORT:
- break;
- case RXRPC_PACKET_TYPE_ACK:
trace_rxrpc_tx_ack(chan->call_debug_id, serial,
ntohl(pkt.ack.firstPacket),
ntohl(pkt.ack.serial),
pkt.ack.reason, 0);
break;
+
+ default:
+ return;
}
ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len);
/*
* pass a connection-level abort onto all calls on that connection
*/
-static void rxrpc_abort_calls(struct rxrpc_connection *conn,
- enum rxrpc_call_completion compl,
- rxrpc_serial_t serial)
+static void rxrpc_abort_calls(struct rxrpc_connection *conn)
{
struct rxrpc_call *call;
int i;
_enter("{%d},%x", conn->debug_id, conn->abort_code);
- spin_lock(&conn->bundle->channel_lock);
-
for (i = 0; i < RXRPC_MAXCALLS; i++) {
- call = rcu_dereference_protected(
- conn->channels[i].call,
- lockdep_is_held(&conn->bundle->channel_lock));
- if (call) {
- if (compl == RXRPC_CALL_LOCALLY_ABORTED)
- trace_rxrpc_abort(call->debug_id,
- "CON", call->cid,
- call->call_id, 0,
+ call = conn->channels[i].call;
+ if (call)
+ rxrpc_set_call_completion(call,
+ conn->completion,
conn->abort_code,
conn->error);
- else
- trace_rxrpc_rx_abort(call, serial,
- conn->abort_code);
- rxrpc_set_call_completion(call, compl,
- conn->abort_code,
- conn->error);
- }
}
- spin_unlock(&conn->bundle->channel_lock);
_leave("");
}
-/*
- * generate a connection-level abort
- */
-static int rxrpc_abort_connection(struct rxrpc_connection *conn,
- int error, u32 abort_code)
-{
- struct rxrpc_wire_header whdr;
- struct msghdr msg;
- struct kvec iov[2];
- __be32 word;
- size_t len;
- u32 serial;
- int ret;
-
- _enter("%d,,%u,%u", conn->debug_id, error, abort_code);
-
- /* generate a connection-level abort */
- spin_lock(&conn->state_lock);
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- spin_unlock(&conn->state_lock);
- _leave(" = 0 [already dead]");
- return 0;
- }
-
- conn->error = error;
- conn->abort_code = abort_code;
- conn->state = RXRPC_CONN_LOCALLY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- spin_unlock(&conn->state_lock);
-
- msg.msg_name = &conn->peer->srx.transport;
- msg.msg_namelen = conn->peer->srx.transport_len;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- msg.msg_flags = 0;
-
- whdr.epoch = htonl(conn->proto.epoch);
- whdr.cid = htonl(conn->proto.cid);
- whdr.callNumber = 0;
- whdr.seq = 0;
- whdr.type = RXRPC_PACKET_TYPE_ABORT;
- whdr.flags = conn->out_clientflag;
- whdr.userStatus = 0;
- whdr.securityIndex = conn->security_ix;
- whdr._rsvd = 0;
- whdr.serviceId = htons(conn->service_id);
-
- word = htonl(conn->abort_code);
-
- iov[0].iov_base = &whdr;
- iov[0].iov_len = sizeof(whdr);
- iov[1].iov_base = &word;
- iov[1].iov_len = sizeof(word);
-
- len = iov[0].iov_len + iov[1].iov_len;
-
- serial = atomic_inc_return(&conn->serial);
- rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial);
- whdr.serial = htonl(serial);
-
- ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len);
- if (ret < 0) {
- trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
- rxrpc_tx_point_conn_abort);
- _debug("sendmsg failed: %d", ret);
- return -EAGAIN;
- }
-
- trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
-
- conn->peer->last_tx_at = ktime_get_seconds();
-
- _leave(" = 0");
- return 0;
-}
-
/*
* mark a call as being on a now-secured channel
* - must be called with BH's disabled.
*/
static void rxrpc_call_is_secure(struct rxrpc_call *call)
{
- _enter("%p", call);
- if (call) {
- write_lock(&call->state_lock);
- if (call->state == RXRPC_CALL_SERVER_SECURING) {
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
- rxrpc_notify_socket(call);
- }
- write_unlock(&call->state_lock);
+ if (call && __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SECURING) {
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
+ rxrpc_notify_socket(call);
}
}
* connection-level Rx packet processor
*/
static int rxrpc_process_event(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- int loop, ret;
+ int ret;
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- _leave(" = -ECONNABORTED [%u]", conn->state);
+ if (conn->state == RXRPC_CONN_ABORTED)
return -ECONNABORTED;
- }
_enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
switch (sp->hdr.type) {
- case RXRPC_PACKET_TYPE_DATA:
- case RXRPC_PACKET_TYPE_ACK:
- rxrpc_conn_retransmit_call(conn, skb,
- sp->hdr.cid & RXRPC_CHANNELMASK);
- return 0;
-
- case RXRPC_PACKET_TYPE_BUSY:
- /* Just ignore BUSY packets for now. */
- return 0;
-
- case RXRPC_PACKET_TYPE_ABORT:
- conn->error = -ECONNABORTED;
- conn->abort_code = skb->priority;
- conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
- return -ECONNABORTED;
-
case RXRPC_PACKET_TYPE_CHALLENGE:
- return conn->security->respond_to_challenge(conn, skb,
- _abort_code);
+ return conn->security->respond_to_challenge(conn, skb);
case RXRPC_PACKET_TYPE_RESPONSE:
- ret = conn->security->verify_response(conn, skb, _abort_code);
+ ret = conn->security->verify_response(conn, skb);
if (ret < 0)
return ret;
if (ret < 0)
return ret;
- spin_lock(&conn->bundle->channel_lock);
spin_lock(&conn->state_lock);
-
- if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
+ if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING)
conn->state = RXRPC_CONN_SERVICE;
- spin_unlock(&conn->state_lock);
- for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
- rxrpc_call_is_secure(
- rcu_dereference_protected(
- conn->channels[loop].call,
- lockdep_is_held(&conn->bundle->channel_lock)));
- } else {
- spin_unlock(&conn->state_lock);
- }
+ spin_unlock(&conn->state_lock);
- spin_unlock(&conn->bundle->channel_lock);
+ if (conn->state == RXRPC_CONN_SERVICE) {
+ /* Offload call state flipping to the I/O thread. As
+ * we've already received the packet, put it on the
+ * front of the queue.
+ */
+ skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED;
+ rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured);
+ skb_queue_head(&conn->local->rx_queue, skb);
+ rxrpc_wake_up_io_thread(conn->local);
+ }
return 0;
default:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_conn_pkt"));
+ WARN_ON_ONCE(1);
return -EPROTO;
}
}
*/
static void rxrpc_secure_connection(struct rxrpc_connection *conn)
{
- u32 abort_code;
- int ret;
-
- _enter("{%d}", conn->debug_id);
-
- ASSERT(conn->security_ix != 0);
-
- if (conn->security->issue_challenge(conn) < 0) {
- abort_code = RX_CALL_DEAD;
- ret = -ENOMEM;
- goto abort;
- }
-
- _leave("");
- return;
-
-abort:
- _debug("abort %d, %d", ret, abort_code);
- rxrpc_abort_connection(conn, ret, abort_code);
- _leave(" [aborted]");
+ if (conn->security->issue_challenge(conn) < 0)
+ rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM,
+ rxrpc_abort_nomem);
}
/*
if (!test_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags))
continue;
- smp_rmb(); /* vs rxrpc_disconnect_client_call */
- ack_at = READ_ONCE(chan->final_ack_at);
-
+ ack_at = chan->final_ack_at;
if (time_before(j, ack_at) && !force) {
if (time_before(ack_at, next_j)) {
next_j = ack_at;
static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
{
struct sk_buff *skb;
- u32 abort_code = RX_PROTOCOL_ERROR;
int ret;
if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
rxrpc_secure_connection(conn);
- /* Process delayed ACKs whose time has come. */
- if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
- rxrpc_process_delayed_final_acks(conn, false);
-
/* go through the conn-level event packets, releasing the ref on this
* connection that each one has when we've finished with it */
while ((skb = skb_dequeue(&conn->rx_queue))) {
rxrpc_see_skb(skb, rxrpc_skb_see_conn_work);
- ret = rxrpc_process_event(conn, skb, &abort_code);
+ ret = rxrpc_process_event(conn, skb);
switch (ret) {
- case -EPROTO:
- case -EKEYEXPIRED:
- case -EKEYREJECTED:
- goto protocol_error;
case -ENOMEM:
case -EAGAIN:
- goto requeue_and_leave;
- case -ECONNABORTED:
+ skb_queue_head(&conn->rx_queue, skb);
+ rxrpc_queue_conn(conn, rxrpc_conn_queue_retry_work);
+ break;
default:
rxrpc_free_skb(skb, rxrpc_skb_put_conn_work);
break;
}
}
-
- return;
-
-requeue_and_leave:
- skb_queue_head(&conn->rx_queue, skb);
- return;
-
-protocol_error:
- if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
- goto requeue_and_leave;
- rxrpc_free_skb(skb, rxrpc_skb_put_conn_work);
- return;
}
void rxrpc_process_connection(struct work_struct *work)
/*
* Input a connection-level packet.
*/
-int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
+bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- _leave(" = -ECONNABORTED [%u]", conn->state);
- return -ECONNABORTED;
- }
-
- _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
-
switch (sp->hdr.type) {
- case RXRPC_PACKET_TYPE_DATA:
- case RXRPC_PACKET_TYPE_ACK:
- rxrpc_conn_retransmit_call(conn, skb,
- sp->hdr.cid & RXRPC_CHANNELMASK);
- return 0;
-
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets for now. */
- return 0;
+ return true;
case RXRPC_PACKET_TYPE_ABORT:
- conn->error = -ECONNABORTED;
- conn->abort_code = skb->priority;
- conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
- return -ECONNABORTED;
+ if (rxrpc_is_conn_aborted(conn))
+ return true;
+ rxrpc_input_conn_abort(conn, skb);
+ rxrpc_abort_calls(conn);
+ return true;
case RXRPC_PACKET_TYPE_CHALLENGE:
case RXRPC_PACKET_TYPE_RESPONSE:
+ if (rxrpc_is_conn_aborted(conn)) {
+ if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED)
+ rxrpc_send_conn_abort(conn);
+ return true;
+ }
rxrpc_post_packet_to_conn(conn, skb);
- return 0;
+ return true;
default:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_conn_pkt"));
- return -EPROTO;
+ WARN_ON_ONCE(1);
+ return true;
}
}
+
+/*
+ * Input a connection event.
+ */
+void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
+{
+ unsigned int loop;
+
+ if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events))
+ rxrpc_abort_calls(conn);
+
+ switch (skb->mark) {
+ case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
+ if (conn->state != RXRPC_CONN_SERVICE)
+ break;
+
+ for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
+ rxrpc_call_is_secure(conn->channels[loop].call);
+ break;
+ }
+
+ /* Process delayed ACKs whose time has come. */
+ if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
+ rxrpc_process_delayed_final_acks(conn, false);
+}
static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet,
unsigned long reap_at);
+void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why)
+{
+ struct rxrpc_local *local = conn->local;
+ bool busy;
+
+ if (WARN_ON_ONCE(!local))
+ return;
+
+ spin_lock_bh(&local->lock);
+ busy = !list_empty(&conn->attend_link);
+ if (!busy) {
+ rxrpc_get_connection(conn, why);
+ list_add_tail(&conn->attend_link, &local->conn_attend_q);
+ }
+ spin_unlock_bh(&local->lock);
+ rxrpc_wake_up_io_thread(local);
+}
+
static void rxrpc_connection_timer(struct timer_list *timer)
{
struct rxrpc_connection *conn =
container_of(timer, struct rxrpc_connection, timer);
- rxrpc_queue_conn(conn, rxrpc_conn_queue_timer);
+ rxrpc_poke_conn(conn, rxrpc_conn_get_poke_timer);
}
/*
INIT_WORK(&conn->destructor, rxrpc_clean_up_connection);
INIT_LIST_HEAD(&conn->proc_link);
INIT_LIST_HEAD(&conn->link);
+ mutex_init(&conn->security_lock);
skb_queue_head_init(&conn->rx_queue);
conn->rxnet = rxnet;
conn->security = &rxrpc_no_security;
_enter(",%x", sp->hdr.cid & RXRPC_CIDMASK);
- /* Look up client connections by connection ID alone as their IDs are
- * unique for this machine.
+ /* Look up client connections by connection ID alone as their
+ * IDs are unique for this machine.
*/
- conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT);
+ conn = idr_find(&local->conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT);
if (!conn || refcount_read(&conn->ref) == 0) {
_debug("no conn");
goto not_found;
_enter("%d,%x", conn->debug_id, call->cid);
- if (rcu_access_pointer(chan->call) == call) {
+ if (chan->call == call) {
/* Save the result of the call so that we can repeat it if necessary
* through the channel, whilst disposing of the actual call record.
*/
break;
}
- /* Sync with rxrpc_conn_retransmit(). */
- smp_wmb();
chan->last_call = chan->call_id;
chan->call_id = chan->call_counter;
-
- rcu_assign_pointer(chan->call, NULL);
+ chan->call = NULL;
}
_leave("");
{
struct rxrpc_connection *conn = call->conn;
+ set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+ rxrpc_see_call(call, rxrpc_call_see_disconnected);
+
call->peer->cong_ssthresh = call->cong_ssthresh;
if (!hlist_unhashed(&call->error_link)) {
spin_unlock(&call->peer->lock);
}
- if (rxrpc_is_client_call(call))
- return rxrpc_disconnect_client_call(conn->bundle, call);
-
- spin_lock(&conn->bundle->channel_lock);
- __rxrpc_disconnect_call(conn, call);
- spin_unlock(&conn->bundle->channel_lock);
+ if (rxrpc_is_client_call(call)) {
+ rxrpc_disconnect_client_call(call->bundle, call);
+ } else {
+ __rxrpc_disconnect_call(conn, call);
+ conn->idle_timestamp = jiffies;
+ if (atomic_dec_and_test(&conn->active))
+ rxrpc_set_service_reap_timer(conn->rxnet,
+ jiffies + rxrpc_connection_expiry);
+ }
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
- conn->idle_timestamp = jiffies;
- if (atomic_dec_and_test(&conn->active))
- rxrpc_set_service_reap_timer(conn->rxnet,
- jiffies + rxrpc_connection_expiry);
+ rxrpc_put_call(call, rxrpc_call_put_io_thread);
}
/*
container_of(work, struct rxrpc_connection, destructor);
struct rxrpc_net *rxnet = conn->rxnet;
- ASSERT(!rcu_access_pointer(conn->channels[0].call) &&
- !rcu_access_pointer(conn->channels[1].call) &&
- !rcu_access_pointer(conn->channels[2].call) &&
- !rcu_access_pointer(conn->channels[3].call));
+ ASSERT(!conn->channels[0].call &&
+ !conn->channels[1].call &&
+ !conn->channels[2].call &&
+ !conn->channels[3].call);
ASSERT(list_empty(&conn->cache_link));
del_timer_sync(&conn->timer);
_enter("");
atomic_dec(&rxnet->nr_conns);
- rxrpc_destroy_all_client_connections(rxnet);
del_timer_sync(&rxnet->service_conn_reap_timer);
rxrpc_queue_work(&rxnet->service_conn_reaper);
static struct rxrpc_bundle rxrpc_service_dummy_bundle = {
.ref = REFCOUNT_INIT(1),
.debug_id = UINT_MAX,
- .channel_lock = __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock),
};
/*
#include "ar-internal.h"
-static void rxrpc_proto_abort(const char *why,
- struct rxrpc_call *call, rxrpc_seq_t seq)
+static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq,
+ enum rxrpc_abort_reason why)
{
- if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG))
- rxrpc_send_abort_packet(call);
+ rxrpc_abort_call(call, seq, RX_PROTOCOL_ERROR, -EBADMSG, why);
}
/*
if (call->cong_mode != RXRPC_CALL_SLOW_START &&
call->cong_mode != RXRPC_CALL_CONGEST_AVOIDANCE)
return;
- if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
+ if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY)
return;
rtt = ns_to_ktime(call->peer->srtt_us * (1000 / 8));
* This occurs when we get an ACKALL packet, the first DATA packet of a reply,
* or a final ACK packet.
*/
-static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
- const char *abort_why)
+static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
+ enum rxrpc_abort_reason abort_why)
{
- unsigned int state;
-
ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
- write_lock(&call->state_lock);
-
- state = call->state;
- switch (state) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
- if (reply_begun)
- call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY;
- else
- call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+ if (reply_begun) {
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_RECV_REPLY);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
+ break;
+ }
+
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply);
break;
case RXRPC_CALL_SERVER_AWAIT_ACK:
- __rxrpc_call_completed(call);
- state = call->state;
+ rxrpc_call_completed(call);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
break;
default:
- goto bad_state;
+ kdebug("end_tx %s", rxrpc_call_states[__rxrpc_call_state(call)]);
+ rxrpc_proto_abort(call, call->tx_top, abort_why);
+ break;
}
-
- write_unlock(&call->state_lock);
- if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
- trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply);
- else
- trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
- _leave(" = ok");
- return true;
-
-bad_state:
- write_unlock(&call->state_lock);
- kdebug("end_tx %s", rxrpc_call_states[call->state]);
- rxrpc_proto_abort(abort_why, call, call->tx_top);
- return false;
}
/*
if (call->ackr_reason) {
now = jiffies;
timo = now + MAX_JIFFY_OFFSET;
- WRITE_ONCE(call->resend_at, timo);
+
WRITE_ONCE(call->delay_ack_at, timo);
trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
}
if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
if (!rxrpc_rotate_tx_window(call, top, &summary)) {
- rxrpc_proto_abort("TXL", call, top);
+ rxrpc_proto_abort(call, top, rxrpc_eproto_early_reply);
return false;
}
}
- return rxrpc_end_tx_phase(call, true, "ETD");
+
+ rxrpc_end_tx_phase(call, true, rxrpc_eproto_unexpected_reply);
+ return true;
+}
+
+/*
+ * End the packet reception phase.
+ */
+static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
+{
+ rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq);
+
+ _enter("%d,%s", call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)]);
+
+ trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh);
+
+ switch (__rxrpc_call_state(call)) {
+ case RXRPC_CALL_CLIENT_RECV_REPLY:
+ rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
+ rxrpc_call_completed(call);
+ break;
+
+ case RXRPC_CALL_SERVER_RECV_REQUEST:
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST);
+ call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
+ rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op);
+ break;
+
+ default:
+ break;
+ }
}
static void rxrpc_input_update_ack_window(struct rxrpc_call *call,
__skb_queue_tail(&call->recvmsg_queue, skb);
rxrpc_input_update_ack_window(call, window, wtop);
-
trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq);
+ if (last)
+ rxrpc_end_rx_phase(call, sp->hdr.serial);
}
/*
if (last) {
if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- seq + 1 != wtop) {
- rxrpc_proto_abort("LSN", call, seq);
- return;
- }
+ seq + 1 != wtop)
+ return rxrpc_proto_abort(call, seq, rxrpc_eproto_different_last);
} else {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
after_eq(seq, wtop)) {
pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n",
call->debug_id, seq, window, wtop, wlimit);
- rxrpc_proto_abort("LSA", call, seq);
- return;
+ return rxrpc_proto_abort(call, seq, rxrpc_eproto_data_after_last);
}
}
static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- enum rxrpc_call_state state;
rxrpc_serial_t serial = sp->hdr.serial;
rxrpc_seq_t seq0 = sp->hdr.seq;
atomic64_read(&call->ackr_window), call->rx_highest_seq,
skb->len, seq0);
- state = READ_ONCE(call->state);
- if (state >= RXRPC_CALL_COMPLETE)
+ if (__rxrpc_call_is_complete(call))
return;
- if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+ switch (__rxrpc_call_state(call)) {
+ case RXRPC_CALL_CLIENT_SEND_REQUEST:
+ case RXRPC_CALL_CLIENT_AWAIT_REPLY:
+ /* Received data implicitly ACKs all of the request
+ * packets we sent when we're acting as a client.
+ */
+ if (!rxrpc_receiving_reply(call))
+ goto out_notify;
+ break;
+
+ case RXRPC_CALL_SERVER_RECV_REQUEST: {
unsigned long timo = READ_ONCE(call->next_req_timo);
unsigned long now, expect_req_by;
rxrpc_reduce_call_timer(call, expect_req_by, now,
rxrpc_timer_set_for_idle);
}
+ break;
}
- /* Received data implicitly ACKs all of the request packets we sent
- * when we're acting as a client.
- */
- if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
- state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
- !rxrpc_receiving_reply(call))
- goto out_notify;
+ default:
+ break;
+ }
if (!rxrpc_input_split_jumbo(call, skb)) {
- rxrpc_proto_abort("VLD", call, sp->hdr.seq);
+ rxrpc_proto_abort(call, sp->hdr.seq, rxrpc_badmsg_bad_jumbo);
goto out_notify;
}
skb = NULL;
offset = sizeof(struct rxrpc_wire_header);
if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0)
- return rxrpc_proto_abort("XAK", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack);
offset += sizeof(ack);
ack_serial = sp->hdr.serial;
ioffset = offset + nr_acks + 3;
if (skb->len >= ioffset + sizeof(info) &&
skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0)
- return rxrpc_proto_abort("XAI", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info);
if (nr_acks > 0)
skb_condense(skb);
rxrpc_input_ackinfo(call, skb, &info);
if (first_soft_ack == 0)
- return rxrpc_proto_abort("AK0", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero);
/* Ignore ACKs unless we are or have just been transmitting. */
- switch (READ_ONCE(call->state)) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
case RXRPC_CALL_SERVER_SEND_REPLY:
if (before(hard_ack, call->acks_hard_ack) ||
after(hard_ack, call->tx_top))
- return rxrpc_proto_abort("AKW", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_outside_window);
if (nr_acks > call->tx_top - hard_ack)
- return rxrpc_proto_abort("AKN", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_sack_overflow);
if (after(hard_ack, call->acks_hard_ack)) {
if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) {
- rxrpc_end_tx_phase(call, false, "ETA");
+ rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack);
return;
}
}
if (nr_acks > 0) {
if (offset > (int)skb->len - nr_acks)
- return rxrpc_proto_abort("XSA", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack);
rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack,
nr_acks, &summary);
}
struct rxrpc_ack_summary summary = { 0 };
if (rxrpc_rotate_tx_window(call, call->tx_top, &summary))
- rxrpc_end_tx_phase(call, false, "ETL");
+ rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ackall);
}
/*
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_DATA:
- rxrpc_input_data(call, skb);
- break;
+ return rxrpc_input_data(call, skb);
case RXRPC_PACKET_TYPE_ACK:
- rxrpc_input_ack(call, skb);
- break;
+ return rxrpc_input_ack(call, skb);
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets from the server; the retry and
* lifespan timers will take care of business. BUSY packets
* from the client don't make sense.
*/
- break;
+ return;
case RXRPC_PACKET_TYPE_ABORT:
- rxrpc_input_abort(call, skb);
- break;
+ return rxrpc_input_abort(call, skb);
case RXRPC_PACKET_TYPE_ACKALL:
- rxrpc_input_ackall(call, skb);
- break;
+ return rxrpc_input_ackall(call, skb);
default:
break;
*/
void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb)
{
- struct rxrpc_connection *conn = call->conn;
-
- switch (READ_ONCE(call->state)) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_SERVER_AWAIT_ACK:
rxrpc_call_completed(call);
fallthrough;
case RXRPC_CALL_COMPLETE:
break;
default:
- if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN))
- rxrpc_send_abort_packet(call);
+ rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ESHUTDOWN,
+ rxrpc_eproto_improper_term);
trace_rxrpc_improper_term(call);
break;
}
rxrpc_input_call_event(call, skb);
-
- spin_lock(&conn->bundle->channel_lock);
- __rxrpc_disconnect_call(conn, call);
- spin_unlock(&conn->bundle->channel_lock);
}
}
static int none_respond_to_challenge(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("chall_none"));
- return -EPROTO;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxrpc_eproto_rxnull_challenge);
}
static int none_verify_response(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("resp_none"));
- return -EPROTO;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxrpc_eproto_rxnull_response);
}
static void none_clear(struct rxrpc_connection *conn)
rcu_read_unlock();
}
+/*
+ * Directly produce an abort from a packet.
+ */
+bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why,
+ s32 abort_code, int err)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ abort_code, err);
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+ skb->priority = abort_code;
+ return false;
+}
+
+static bool rxrpc_bad_message(struct sk_buff *skb, enum rxrpc_abort_reason why)
+{
+ return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EBADMSG);
+}
+
+#define just_discard true
+
/*
* Process event packets targeted at a local endpoint.
*/
-static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb)
+static bool rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
char v;
if (v == 0)
rxrpc_send_version_request(local, &sp->hdr, skb);
}
+
+ return true;
}
/*
* Extract the wire header from a packet and translate the byte order.
*/
-static noinline
-int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
+static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp,
+ struct sk_buff *skb)
{
struct rxrpc_wire_header whdr;
/* dig out the RxRPC connection details */
- if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) {
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_hdr"));
- return -EBADMSG;
- }
+ if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_short_hdr);
memset(sp, 0, sizeof(*sp));
sp->hdr.epoch = ntohl(whdr.epoch);
sp->hdr.securityIndex = whdr.securityIndex;
sp->hdr._rsvd = ntohs(whdr._rsvd);
sp->hdr.serviceId = ntohs(whdr.serviceId);
- return 0;
+ return true;
}
/*
/*
* Process packets received on the local endpoint
*/
-static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
+static bool rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
{
struct rxrpc_connection *conn;
struct sockaddr_rxrpc peer_srx;
struct rxrpc_skb_priv *sp;
struct rxrpc_peer *peer = NULL;
struct sk_buff *skb = *_skb;
- int ret = 0;
+ bool ret = false;
skb_pull(skb, sizeof(struct udphdr));
sp = rxrpc_skb(skb);
/* dig out the RxRPC connection details */
- if (rxrpc_extract_header(sp, skb) < 0)
- goto bad_message;
+ if (!rxrpc_extract_header(sp, skb))
+ return just_discard;
if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) {
static int lose;
if ((lose++ & 7) == 7) {
trace_rxrpc_rx_lose(sp);
- return 0;
+ return just_discard;
}
}
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
if (rxrpc_to_client(sp))
- return 0;
- rxrpc_input_version(local, skb);
- return 0;
+ return just_discard;
+ return rxrpc_input_version(local, skb);
case RXRPC_PACKET_TYPE_BUSY:
if (rxrpc_to_server(sp))
- return 0;
+ return just_discard;
fallthrough;
case RXRPC_PACKET_TYPE_ACK:
case RXRPC_PACKET_TYPE_ACKALL:
if (sp->hdr.callNumber == 0)
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call);
break;
case RXRPC_PACKET_TYPE_ABORT:
if (!rxrpc_extract_abort(skb))
- return 0; /* Just discard if malformed */
+ return just_discard; /* Just discard if malformed */
break;
case RXRPC_PACKET_TYPE_DATA:
- if (sp->hdr.callNumber == 0 ||
- sp->hdr.seq == 0)
- goto bad_message;
+ if (sp->hdr.callNumber == 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call);
+ if (sp->hdr.seq == 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_seq);
/* Unshare the packet so that it can be modified for in-place
* decryption.
if (!skb) {
rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare_nomem);
*_skb = NULL;
- return 0;
+ return just_discard;
}
if (skb != *_skb) {
case RXRPC_PACKET_TYPE_CHALLENGE:
if (rxrpc_to_server(sp))
- return 0;
+ return just_discard;
break;
case RXRPC_PACKET_TYPE_RESPONSE:
if (rxrpc_to_client(sp))
- return 0;
+ return just_discard;
break;
/* Packet types 9-11 should just be ignored. */
case RXRPC_PACKET_TYPE_PARAMS:
case RXRPC_PACKET_TYPE_10:
case RXRPC_PACKET_TYPE_11:
- return 0;
+ return just_discard;
default:
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_unsupported_packet);
}
if (sp->hdr.serviceId == 0)
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_service);
if (WARN_ON_ONCE(rxrpc_extract_addr_from_skb(&peer_srx, skb) < 0))
- return true; /* Unsupported address type - discard. */
+ return just_discard; /* Unsupported address type. */
if (peer_srx.transport.family != local->srx.transport.family &&
(peer_srx.transport.family == AF_INET &&
pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
peer_srx.transport.family,
local->srx.transport.family);
- return true; /* Wrong address type - discard. */
+ return just_discard; /* Wrong address type. */
}
if (rxrpc_to_client(sp)) {
conn = rxrpc_find_client_connection_rcu(local, &peer_srx, skb);
conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input);
rcu_read_unlock();
- if (!conn) {
- trace_rxrpc_abort(0, "NCC", sp->hdr.cid,
- sp->hdr.callNumber, sp->hdr.seq,
- RXKADINCONSISTENCY, EBADMSG);
- goto protocol_error;
- }
+ if (!conn)
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_conn);
ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb);
rxrpc_put_connection(conn, rxrpc_conn_put_call_input);
ret = rxrpc_new_incoming_call(local, peer, NULL, &peer_srx, skb);
rxrpc_put_peer(peer, rxrpc_peer_put_input);
- if (ret < 0)
- goto reject_packet;
- return 0;
-
-bad_message:
- trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
-protocol_error:
- skb->priority = RX_PROTOCOL_ERROR;
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
-reject_packet:
- rxrpc_reject_packet(local, skb);
- return 0;
+ return ret;
}
/*
struct rxrpc_channel *chan;
struct rxrpc_call *call = NULL;
unsigned int channel;
+ bool ret;
if (sp->hdr.securityIndex != conn->security_ix)
- goto wrong_security;
+ return rxrpc_direct_abort(skb, rxrpc_eproto_wrong_security,
+ RXKADINCONSISTENCY, -EBADMSG);
if (sp->hdr.serviceId != conn->service_id) {
int old_id;
if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags))
- goto reupgrade;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_reupgrade);
+
old_id = cmpxchg(&conn->service_id, conn->orig_service_id,
sp->hdr.serviceId);
-
if (old_id != conn->orig_service_id &&
old_id != sp->hdr.serviceId)
- goto reupgrade;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_bad_upgrade);
}
if (after(sp->hdr.serial, conn->hi_serial))
/* Ignore really old calls */
if (sp->hdr.callNumber < chan->last_call)
- return 0;
+ return just_discard;
if (sp->hdr.callNumber == chan->last_call) {
if (chan->call ||
sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)
- return 0;
+ return just_discard;
/* For the previous service call, if completed successfully, we
* discard all further packets.
*/
if (rxrpc_conn_is_service(conn) &&
chan->last_type == RXRPC_PACKET_TYPE_ACK)
- return 0;
+ return just_discard;
/* But otherwise we need to retransmit the final packet from
* data cached in the connection record.
sp->hdr.seq,
sp->hdr.serial,
sp->hdr.flags);
- rxrpc_input_conn_packet(conn, skb);
- return 0;
+ rxrpc_conn_retransmit_call(conn, skb, channel);
+ return just_discard;
}
- rcu_read_lock();
- call = rxrpc_try_get_call(rcu_dereference(chan->call),
- rxrpc_call_get_input);
- rcu_read_unlock();
+ call = rxrpc_try_get_call(chan->call, rxrpc_call_get_input);
if (sp->hdr.callNumber > chan->call_id) {
if (rxrpc_to_client(sp)) {
rxrpc_put_call(call, rxrpc_call_put_input);
- goto reject_packet;
+ return rxrpc_protocol_error(skb,
+ rxrpc_eproto_unexpected_implicit_end);
}
if (call) {
if (!call) {
if (rxrpc_to_client(sp))
- goto bad_message;
- if (rxrpc_new_incoming_call(conn->local, conn->peer, conn,
- peer_srx, skb) == 0)
- return 0;
- goto reject_packet;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_call);
+ return rxrpc_new_incoming_call(conn->local, conn->peer, conn,
+ peer_srx, skb);
}
- rxrpc_input_call_event(call, skb);
+ ret = rxrpc_input_call_event(call, skb);
rxrpc_put_call(call, rxrpc_call_put_input);
- return 0;
-
-wrong_security:
- trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RXKADINCONSISTENCY, EBADMSG);
- skb->priority = RXKADINCONSISTENCY;
- goto post_abort;
-
-reupgrade:
- trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
- goto protocol_error;
-
-bad_message:
- trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
-protocol_error:
- skb->priority = RX_PROTOCOL_ERROR;
-post_abort:
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
-reject_packet:
- rxrpc_reject_packet(conn->local, skb);
- return 0;
+ return ret;
}
/*
*/
int rxrpc_io_thread(void *data)
{
+ struct rxrpc_connection *conn;
struct sk_buff_head rx_queue;
struct rxrpc_local *local = data;
struct rxrpc_call *call;
for (;;) {
rxrpc_inc_stat(local->rxnet, stat_io_loop);
+ /* Deal with connections that want immediate attention. */
+ conn = list_first_entry_or_null(&local->conn_attend_q,
+ struct rxrpc_connection,
+ attend_link);
+ if (conn) {
+ spin_lock_bh(&local->lock);
+ list_del_init(&conn->attend_link);
+ spin_unlock_bh(&local->lock);
+
+ rxrpc_input_conn_event(conn, NULL);
+ rxrpc_put_connection(conn, rxrpc_conn_put_poke);
+ continue;
+ }
+
+ if (test_and_clear_bit(RXRPC_CLIENT_CONN_REAP_TIMER,
+ &local->client_conn_flags))
+ rxrpc_discard_expired_client_conns(local);
+
/* Deal with calls that want immediate attention. */
if ((call = list_first_entry_or_null(&local->call_attend_q,
struct rxrpc_call,
continue;
}
+ if (!list_empty(&local->new_client_calls))
+ rxrpc_connect_client_calls(local);
+
/* Process received packets and errors. */
if ((skb = __skb_dequeue(&rx_queue))) {
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
switch (skb->mark) {
case RXRPC_SKB_MARK_PACKET:
skb->priority = 0;
- rxrpc_input_packet(local, &skb);
+ if (!rxrpc_input_packet(local, &skb))
+ rxrpc_reject_packet(local, skb);
trace_rxrpc_rx_done(skb->mark, skb->priority);
rxrpc_free_skb(skb, rxrpc_skb_put_input);
break;
rxrpc_input_error(local, skb);
rxrpc_free_skb(skb, rxrpc_skb_put_error_report);
break;
+ case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
+ rxrpc_input_conn_event(sp->conn, skb);
+ rxrpc_put_connection(sp->conn, rxrpc_conn_put_poke);
+ rxrpc_free_skb(skb, rxrpc_skb_put_conn_secured);
+ break;
default:
WARN_ON_ONCE(1);
rxrpc_free_skb(skb, rxrpc_skb_put_unknown);
set_current_state(TASK_INTERRUPTIBLE);
should_stop = kthread_should_stop();
if (!skb_queue_empty(&local->rx_queue) ||
- !list_empty(&local->call_attend_q)) {
+ !list_empty(&local->call_attend_q) ||
+ !list_empty(&local->conn_attend_q) ||
+ !list_empty(&local->new_client_calls) ||
+ test_bit(RXRPC_CLIENT_CONN_REAP_TIMER,
+ &local->client_conn_flags)) {
__set_current_state(TASK_RUNNING);
continue;
}
}
}
+static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
+{
+ struct rxrpc_local *local =
+ container_of(timer, struct rxrpc_local, client_conn_reap_timer);
+
+ if (local->kill_all_client_conns &&
+ test_and_set_bit(RXRPC_CLIENT_CONN_REAP_TIMER, &local->client_conn_flags))
+ rxrpc_wake_up_io_thread(local);
+}
+
/*
* Allocate a new local endpoint.
*/
-static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
+static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
const struct sockaddr_rxrpc *srx)
{
struct rxrpc_local *local;
+ u32 tmp;
local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
if (local) {
refcount_set(&local->ref, 1);
atomic_set(&local->active_users, 1);
- local->rxnet = rxnet;
+ local->net = net;
+ local->rxnet = rxrpc_net(net);
INIT_HLIST_NODE(&local->link);
init_rwsem(&local->defrag_sem);
init_completion(&local->io_thread_ready);
skb_queue_head_init(&local->rx_queue);
+ INIT_LIST_HEAD(&local->conn_attend_q);
INIT_LIST_HEAD(&local->call_attend_q);
+
local->client_bundles = RB_ROOT;
spin_lock_init(&local->client_bundles_lock);
+ local->kill_all_client_conns = false;
+ INIT_LIST_HEAD(&local->idle_client_conns);
+ timer_setup(&local->client_conn_reap_timer,
+ rxrpc_client_conn_reap_timeout, 0);
+
spin_lock_init(&local->lock);
rwlock_init(&local->services_lock);
local->debug_id = atomic_inc_return(&rxrpc_debug_id);
memcpy(&local->srx, srx, sizeof(*srx));
local->srx.srx_service = 0;
+ idr_init(&local->conn_ids);
+ get_random_bytes(&tmp, sizeof(tmp));
+ tmp &= 0x3fffffff;
+ if (tmp == 0)
+ tmp = 1;
+ idr_set_cursor(&local->conn_ids, tmp);
+ INIT_LIST_HEAD(&local->new_client_calls);
+ spin_lock_init(&local->client_call_lock);
+
trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1);
}
goto found;
}
- local = rxrpc_alloc_local(rxnet, srx);
+ local = rxrpc_alloc_local(net, srx);
if (!local)
goto nomem;
* local endpoint.
*/
rxrpc_purge_queue(&local->rx_queue);
+ rxrpc_purge_client_connections(local);
}
/*
unsigned int rxrpc_net_id;
-static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
-{
- struct rxrpc_net *rxnet =
- container_of(timer, struct rxrpc_net, client_conn_reap_timer);
-
- if (rxnet->live)
- rxrpc_queue_work(&rxnet->client_conn_reaper);
-}
-
static void rxrpc_service_conn_reap_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
rxrpc_service_conn_reap_timeout, 0);
atomic_set(&rxnet->nr_client_conns, 0);
- rxnet->kill_all_client_conns = false;
- spin_lock_init(&rxnet->client_conn_cache_lock);
- mutex_init(&rxnet->client_conn_discard_lock);
- INIT_LIST_HEAD(&rxnet->idle_client_conns);
- INIT_WORK(&rxnet->client_conn_reaper,
- rxrpc_discard_expired_client_conns);
- timer_setup(&rxnet->client_conn_reap_timer,
- rxrpc_client_conn_reap_timeout, 0);
INIT_HLIST_HEAD(&rxnet->local_endpoints);
mutex_init(&rxnet->local_mutex);
rxrpc_tx_point_call_ack);
rxrpc_tx_backoff(call, ret);
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
if (ret < 0)
rxrpc_cancel_rtt_probe(call, serial, rtt_slot);
rxrpc_set_keepalive(call);
goto done;
}
+/*
+ * Transmit a connection-level abort.
+ */
+void rxrpc_send_conn_abort(struct rxrpc_connection *conn)
+{
+ struct rxrpc_wire_header whdr;
+ struct msghdr msg;
+ struct kvec iov[2];
+ __be32 word;
+ size_t len;
+ u32 serial;
+ int ret;
+
+ msg.msg_name = &conn->peer->srx.transport;
+ msg.msg_namelen = conn->peer->srx.transport_len;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_flags = 0;
+
+ whdr.epoch = htonl(conn->proto.epoch);
+ whdr.cid = htonl(conn->proto.cid);
+ whdr.callNumber = 0;
+ whdr.seq = 0;
+ whdr.type = RXRPC_PACKET_TYPE_ABORT;
+ whdr.flags = conn->out_clientflag;
+ whdr.userStatus = 0;
+ whdr.securityIndex = conn->security_ix;
+ whdr._rsvd = 0;
+ whdr.serviceId = htons(conn->service_id);
+
+ word = htonl(conn->abort_code);
+
+ iov[0].iov_base = &whdr;
+ iov[0].iov_len = sizeof(whdr);
+ iov[1].iov_base = &word;
+ iov[1].iov_len = sizeof(word);
+
+ len = iov[0].iov_len + iov[1].iov_len;
+
+ serial = atomic_inc_return(&conn->serial);
+ whdr.serial = htonl(serial);
+
+ iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len);
+ ret = do_udp_sendmsg(conn->local->socket, &msg, len);
+ if (ret < 0) {
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_point_conn_abort);
+ _debug("sendmsg failed: %d", ret);
+ return;
+ }
+
+ trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
+
+ conn->peer->last_tx_at = ktime_get_seconds();
+}
+
/*
* Reject a packet through the local endpoint.
*/
static inline void rxrpc_instant_resend(struct rxrpc_call *call,
struct rxrpc_txbuf *txb)
{
- if (call->state < RXRPC_CALL_COMPLETE)
+ if (!__rxrpc_call_is_complete(call))
kdebug("resend");
}
* assess the MTU size for the network interface through which this peer is
* reached
*/
-static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx,
+static void rxrpc_assess_MTU_size(struct rxrpc_local *local,
struct rxrpc_peer *peer)
{
- struct net *net = sock_net(&rx->sk);
+ struct net *net = local->net;
struct dst_entry *dst;
struct rtable *rt;
struct flowi fl;
/*
* Initialise peer record.
*/
-static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer,
+static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer,
unsigned long hash_key)
{
peer->hash_key = hash_key;
- rxrpc_assess_MTU_size(rx, peer);
+ rxrpc_assess_MTU_size(local, peer);
peer->mtu = peer->if_mtu;
peer->rtt_last_req = ktime_get_real();
/*
* Set up a new peer.
*/
-static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
- struct rxrpc_local *local,
+static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
struct sockaddr_rxrpc *srx,
unsigned long hash_key,
gfp_t gfp)
peer = rxrpc_alloc_peer(local, gfp, rxrpc_peer_new_client);
if (peer) {
memcpy(&peer->srx, srx, sizeof(*srx));
- rxrpc_init_peer(rx, peer, hash_key);
+ rxrpc_init_peer(local, peer, hash_key);
}
_leave(" = %p", peer);
* since we've already done a search in the list from the non-reentrant context
* (the data_ready handler) that is the only place we can add new peers.
*/
-void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
- struct rxrpc_peer *peer)
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
{
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key;
hash_key = rxrpc_peer_hash_key(local, &peer->srx);
- rxrpc_init_peer(rx, peer, hash_key);
+ rxrpc_init_peer(local, peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
/*
* obtain a remote transport endpoint for the specified address
*/
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
- struct rxrpc_local *local,
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
struct sockaddr_rxrpc *srx, gfp_t gfp)
{
struct rxrpc_peer *peer, *candidate;
/* The peer is not yet present in hash - create a candidate
* for a new record and then redo the search.
*/
- candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp);
+ candidate = rxrpc_create_peer(local, srx, hash_key, gfp);
if (!candidate) {
_leave(" = NULL [nomem]");
return NULL;
static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
[RXRPC_CONN_UNUSED] = "Unused ",
+ [RXRPC_CONN_CLIENT_UNSECURED] = "ClUnsec ",
[RXRPC_CONN_CLIENT] = "Client ",
[RXRPC_CONN_SERVICE_PREALLOC] = "SvPrealc",
[RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ",
[RXRPC_CONN_SERVICE_CHALLENGING] = "SvChall ",
[RXRPC_CONN_SERVICE] = "SvSecure",
- [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort",
- [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort",
+ [RXRPC_CONN_ABORTED] = "Aborted ",
};
/*
struct rxrpc_local *local;
struct rxrpc_call *call;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+ enum rxrpc_call_state state;
unsigned long timeout = 0;
rxrpc_seq_t acks_hard_ack;
char lbuff[50], rbuff[50];
sprintf(rbuff, "%pISpc", &call->dest_srx.transport);
- if (call->state != RXRPC_CALL_SERVER_PREALLOC) {
+ state = rxrpc_call_state(call);
+ if (state != RXRPC_CALL_SERVER_PREALLOC) {
timeout = READ_ONCE(call->expect_rx_by);
timeout -= jiffies;
}
call->call_id,
rxrpc_is_service_call(call) ? "Svc" : "Clt",
refcount_read(&call->ref),
- rxrpc_call_states[call->state],
+ rxrpc_call_states[state],
call->abort_code,
call->debug_id,
acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack,
{
struct rxrpc_connection *conn;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+ const char *state;
char lbuff[50], rbuff[50];
if (v == &rxnet->conn_proc_list) {
}
sprintf(lbuff, "%pISpc", &conn->local->srx.transport);
-
sprintf(rbuff, "%pISpc", &conn->peer->srx.transport);
print:
+ state = rxrpc_is_conn_aborted(conn) ?
+ rxrpc_call_completions[conn->completion] :
+ rxrpc_conn_states[conn->state];
seq_printf(seq,
"UDP %-47.47s %-47.47s %4x %08x %s %3u %3d"
" %s %08x %08x %08x %08x %08x %08x %08x\n",
rxrpc_conn_is_service(conn) ? "Svc" : "Clt",
refcount_read(&conn->ref),
atomic_read(&conn->active),
- rxrpc_conn_states[conn->state],
+ state,
key_serial(conn->key),
atomic_read(&conn->serial),
conn->hi_serial,
_leave("");
}
-/*
- * Transition a call to the complete state.
- */
-bool __rxrpc_set_call_completion(struct rxrpc_call *call,
- enum rxrpc_call_completion compl,
- u32 abort_code,
- int error)
-{
- if (call->state < RXRPC_CALL_COMPLETE) {
- call->abort_code = abort_code;
- call->error = error;
- call->completion = compl;
- call->state = RXRPC_CALL_COMPLETE;
- trace_rxrpc_call_complete(call);
- wake_up(&call->waitq);
- rxrpc_notify_socket(call);
- return true;
- }
- return false;
-}
-
-bool rxrpc_set_call_completion(struct rxrpc_call *call,
- enum rxrpc_call_completion compl,
- u32 abort_code,
- int error)
-{
- bool ret = false;
-
- if (call->state < RXRPC_CALL_COMPLETE) {
- write_lock(&call->state_lock);
- ret = __rxrpc_set_call_completion(call, compl, abort_code, error);
- write_unlock(&call->state_lock);
- }
- return ret;
-}
-
-/*
- * Record that a call successfully completed.
- */
-bool __rxrpc_call_completed(struct rxrpc_call *call)
-{
- return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
-}
-
-bool rxrpc_call_completed(struct rxrpc_call *call)
-{
- bool ret = false;
-
- if (call->state < RXRPC_CALL_COMPLETE) {
- write_lock(&call->state_lock);
- ret = __rxrpc_call_completed(call);
- write_unlock(&call->state_lock);
- }
- return ret;
-}
-
-/*
- * Record that a call is locally aborted.
- */
-bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call,
- rxrpc_seq_t seq, u32 abort_code, int error)
-{
- trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
- abort_code, error);
- return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
- abort_code, error);
-}
-
-bool rxrpc_abort_call(const char *why, struct rxrpc_call *call,
- rxrpc_seq_t seq, u32 abort_code, int error)
-{
- bool ret;
-
- write_lock(&call->state_lock);
- ret = __rxrpc_abort_call(why, call, seq, abort_code, error);
- write_unlock(&call->state_lock);
- return ret;
-}
-
/*
* Pass a call terminating message to userspace.
*/
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp);
break;
default:
- pr_err("Invalid terminal call state %u\n", call->state);
+ pr_err("Invalid terminal call state %u\n", call->completion);
BUG();
break;
}
return ret;
}
-/*
- * End the packet reception phase.
- */
-static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
-{
- rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq);
-
- _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]);
-
- trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh);
-
- if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY)
- rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
-
- write_lock(&call->state_lock);
-
- switch (call->state) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- __rxrpc_call_completed(call);
- write_unlock(&call->state_lock);
- break;
-
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
- call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
- write_unlock(&call->state_lock);
- rxrpc_propose_delay_ACK(call, serial,
- rxrpc_propose_ack_processing_op);
- break;
- default:
- write_unlock(&call->state_lock);
- break;
- }
-}
-
/*
* Discard a packet we've used up and advance the Rx window by one.
*/
trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate,
serial, call->rx_consumed);
- if (last) {
- rxrpc_end_rx_phase(call, serial);
- return;
- }
+
+ if (last)
+ set_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags);
/* Check to see if there's an ACK that needs sending. */
acked = atomic_add_return(call->rx_consumed - old_consumed,
/*
* Deliver messages to a call. This keeps processing packets until the buffer
* is filled and we find either more DATA (returns 0) or the end of the DATA
- * (returns 1). If more packets are required, it returns -EAGAIN.
+ * (returns 1). If more packets are required, it returns -EAGAIN and if the
+ * call has failed it returns -EIO.
*/
static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
struct msghdr *msg, struct iov_iter *iter,
rx_pkt_offset = call->rx_pkt_offset;
rx_pkt_len = call->rx_pkt_len;
- if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) {
+ if (rxrpc_call_has_failed(call)) {
+ seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1;
+ ret = -EIO;
+ goto done;
+ }
+
+ if (test_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags)) {
seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1;
ret = 1;
goto done;
if (rx_pkt_offset == 0) {
ret2 = rxrpc_verify_data(call, skb);
- rx_pkt_offset = sp->offset;
- rx_pkt_len = sp->len;
trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq,
- rx_pkt_offset, rx_pkt_len, ret2);
+ sp->offset, sp->len, ret2);
if (ret2 < 0) {
+ kdebug("verify = %d", ret2);
ret = ret2;
goto out;
}
+ rx_pkt_offset = sp->offset;
+ rx_pkt_len = sp->len;
} else {
trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq,
rx_pkt_offset, rx_pkt_len, 0);
struct rxrpc_call *call;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
struct list_head *l;
+ unsigned int call_debug_id = 0;
size_t copied = 0;
long timeo;
int ret;
DEFINE_WAIT(wait);
- trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0);
+ trace_rxrpc_recvmsg(0, rxrpc_recvmsg_enter, 0);
if (flags & (MSG_OOB | MSG_TRUNC))
return -EOPNOTSUPP;
if (list_empty(&rx->recvmsg_q)) {
if (signal_pending(current))
goto wait_interrupted;
- trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, 0);
+ trace_rxrpc_recvmsg(0, rxrpc_recvmsg_wait, 0);
timeo = schedule_timeout(timeo);
}
finish_wait(sk_sleep(&rx->sk), &wait);
rxrpc_get_call(call, rxrpc_call_get_recvmsg);
write_unlock(&rx->recvmsg_lock);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0);
+ call_debug_id = call->debug_id;
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_dequeue, 0);
/* We're going to drop the socket lock, so we need to lock the call
* against interference by sendmsg.
msg->msg_namelen = len;
}
- switch (READ_ONCE(call->state)) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len,
- flags, &copied);
- if (ret == -EAGAIN)
- ret = 0;
-
- if (!skb_queue_empty(&call->recvmsg_queue))
- rxrpc_notify_socket(call);
- break;
- default:
+ ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len,
+ flags, &copied);
+ if (ret == -EAGAIN)
ret = 0;
- break;
- }
-
+ if (ret == -EIO)
+ goto call_failed;
if (ret < 0)
goto error_unlock_call;
- if (call->state == RXRPC_CALL_COMPLETE) {
- ret = rxrpc_recvmsg_term(call, msg);
- if (ret < 0)
- goto error_unlock_call;
- if (!(flags & MSG_PEEK))
- rxrpc_release_call(rx, call);
- msg->msg_flags |= MSG_EOR;
- ret = 1;
- }
+ if (rxrpc_call_is_complete(call) &&
+ skb_queue_empty(&call->recvmsg_queue))
+ goto call_complete;
+ if (rxrpc_call_has_failed(call))
+ goto call_failed;
+ rxrpc_notify_socket(call);
+ goto not_yet_complete;
+
+call_failed:
+ rxrpc_purge_queue(&call->recvmsg_queue);
+call_complete:
+ ret = rxrpc_recvmsg_term(call, msg);
+ if (ret < 0)
+ goto error_unlock_call;
+ if (!(flags & MSG_PEEK))
+ rxrpc_release_call(rx, call);
+ msg->msg_flags |= MSG_EOR;
+ ret = 1;
+
+not_yet_complete:
if (ret == 0)
msg->msg_flags |= MSG_MORE;
else
error_unlock_call:
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put_recvmsg);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_return, ret);
return ret;
error_requeue_call:
write_lock(&rx->recvmsg_lock);
list_add(&call->recvmsg_link, &rx->recvmsg_q);
write_unlock(&rx->recvmsg_lock);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0);
} else {
rxrpc_put_call(call, rxrpc_call_put_recvmsg);
}
error_no_call:
release_sock(&rx->sk);
error_trace:
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_return, ret);
return ret;
wait_interrupted:
size_t offset = 0;
int ret;
- _enter("{%d,%s},%zu,%d",
- call->debug_id, rxrpc_call_states[call->state],
- *_len, want_more);
-
- ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_SECURING);
+ _enter("{%d},%zu,%d", call->debug_id, *_len, want_more);
mutex_lock(&call->user_mutex);
- switch (READ_ONCE(call->state)) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- ret = rxrpc_recvmsg_data(sock, call, NULL, iter,
- *_len, 0, &offset);
- *_len -= offset;
- if (ret < 0)
- goto out;
-
- /* We can only reach here with a partially full buffer if we
- * have reached the end of the data. We must otherwise have a
- * full buffer or have been given -EAGAIN.
- */
- if (ret == 1) {
- if (iov_iter_count(iter) > 0)
- goto short_data;
- if (!want_more)
- goto read_phase_complete;
- ret = 0;
- goto out;
- }
-
- if (!want_more)
- goto excess_data;
+ ret = rxrpc_recvmsg_data(sock, call, NULL, iter, *_len, 0, &offset);
+ *_len -= offset;
+ if (ret == -EIO)
+ goto call_failed;
+ if (ret < 0)
goto out;
- case RXRPC_CALL_COMPLETE:
- goto call_complete;
-
- default:
- ret = -EINPROGRESS;
+ /* We can only reach here with a partially full buffer if we have
+ * reached the end of the data. We must otherwise have a full buffer
+ * or have been given -EAGAIN.
+ */
+ if (ret == 1) {
+ if (iov_iter_count(iter) > 0)
+ goto short_data;
+ if (!want_more)
+ goto read_phase_complete;
+ ret = 0;
goto out;
}
+ if (!want_more)
+ goto excess_data;
+ goto out;
+
read_phase_complete:
ret = 1;
out:
return ret;
short_data:
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("short_data"));
+ trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_short_data,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EBADMSG);
ret = -EBADMSG;
goto out;
excess_data:
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("excess_data"));
+ trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_excess_data,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EMSGSIZE);
ret = -EMSGSIZE;
goto out;
-call_complete:
+call_failed:
*_abort = call->abort_code;
ret = call->error;
if (call->completion == RXRPC_CALL_SUCCEEDED) {
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv;
struct scatterlist sg[16];
- bool aborted;
u32 data_size, buf;
u16 check;
int ret;
_enter("");
- if (sp->len < 8) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (sp->len < 8)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_1_short_header);
/* Decrypt the skbuff in-place. TODO: We really want to decrypt
* directly into the target buffer.
skcipher_request_zero(req);
/* Extract the decrypted packet length */
- if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_1_short_encdata);
sp->offset += sizeof(sechdr);
sp->len -= sizeof(sechdr);
check = buf >> 16;
check ^= seq ^ call->call_id;
check &= 0xffff;
- if (check != 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_check", "V1C",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
-
- if (data_size > sp->len) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (check != 0)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_1_short_check);
+ if (data_size > sp->len)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_1_short_data);
sp->len = data_size;
_leave(" = 0 [dlen=%x]", data_size);
return 0;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
}
/*
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv;
struct scatterlist _sg[4], *sg;
- bool aborted;
u32 data_size, buf;
u16 check;
int nsg, ret;
_enter(",{%d}", sp->len);
- if (sp->len < 8) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (sp->len < 8)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_2_short_header);
/* Decrypt the skbuff in-place. TODO: We really want to decrypt
* directly into the target buffer.
} else {
sg = kmalloc_array(nsg, sizeof(*sg), GFP_NOIO);
if (!sg)
- goto nomem;
+ return -ENOMEM;
}
sg_init_table(sg, nsg);
kfree(sg);
/* Extract the decrypted packet length */
- if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_2_short_len);
sp->offset += sizeof(sechdr);
sp->len -= sizeof(sechdr);
check = buf >> 16;
check ^= seq ^ call->call_id;
check &= 0xffff;
- if (check != 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_check", "V2C",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (check != 0)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_2_short_check);
- if (data_size > sp->len) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (data_size > sp->len)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_2_short_data);
sp->len = data_size;
_leave(" = 0 [dlen=%x]", data_size);
return 0;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
-
-nomem:
- _leave(" = -ENOMEM");
- return -ENOMEM;
}
/*
__be32 buf[2];
} crypto __aligned(8);
rxrpc_seq_t seq = sp->hdr.seq;
- bool aborted;
int ret;
u16 cksum;
u32 x, y;
cksum = 1; /* zero checksums are not permitted */
if (cksum != sp->hdr.cksum) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK",
- RXKADSEALEDINCON);
- goto protocol_error;
+ ret = rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_bad_checksum);
+ goto out;
}
switch (call->conn->security_level) {
break;
}
+out:
skcipher_request_free(req);
return ret;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
}
/*
* respond to a challenge packet
*/
static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
const struct rxrpc_key_token *token;
struct rxkad_challenge challenge;
struct rxkad_response *resp;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- const char *eproto;
- u32 version, nonce, min_level, abort_code;
- int ret;
+ u32 version, nonce, min_level;
+ int ret = -EPROTO;
_enter("{%d,%x}", conn->debug_id, key_serial(conn->key));
- eproto = tracepoint_string("chall_no_key");
- abort_code = RX_PROTOCOL_ERROR;
if (!conn->key)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxkad_abort_chall_no_key);
- abort_code = RXKADEXPIRED;
ret = key_validate(conn->key);
if (ret < 0)
- goto other_error;
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret,
+ rxkad_abort_chall_key_expired);
- eproto = tracepoint_string("chall_short");
- abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
&challenge, sizeof(challenge)) < 0)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_chall_short);
version = ntohl(challenge.version);
nonce = ntohl(challenge.nonce);
trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level);
- eproto = tracepoint_string("chall_ver");
- abort_code = RXKADINCONSISTENCY;
if (version != RXKAD_VERSION)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO,
+ rxkad_abort_chall_version);
- abort_code = RXKADLEVELFAIL;
- ret = -EACCES;
if (conn->security_level < min_level)
- goto other_error;
+ return rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES,
+ rxkad_abort_chall_level);
token = conn->key->payload.data[0];
ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad);
kfree(resp);
return ret;
-
-protocol_error:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
- ret = -EPROTO;
-other_error:
- *_abort_code = abort_code;
- return ret;
}
/*
struct sk_buff *skb,
void *ticket, size_t ticket_len,
struct rxrpc_crypt *_session_key,
- time64_t *_expiry,
- u32 *_abort_code)
+ time64_t *_expiry)
{
struct skcipher_request *req;
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv, key;
struct scatterlist sg[1];
struct in_addr addr;
unsigned int life;
- const char *eproto;
time64_t issue, now;
bool little_endian;
- int ret;
- u32 abort_code;
u8 *p, *q, *name, *end;
_enter("{%d},{%x}", conn->debug_id, key_serial(server_key));
memcpy(&iv, &server_key->payload.data[2], sizeof(iv));
- ret = -ENOMEM;
req = skcipher_request_alloc(server_key->payload.data[0], GFP_NOFS);
if (!req)
- goto temporary_error;
+ return -ENOMEM;
sg_init_one(&sg[0], ticket, ticket_len);
skcipher_request_set_callback(req, 0, NULL, NULL);
p = ticket;
end = p + ticket_len;
-#define Z(field) \
- ({ \
- u8 *__str = p; \
- eproto = tracepoint_string("rxkad_bad_"#field); \
- q = memchr(p, 0, end - p); \
- if (!q || q - p > (field##_SZ)) \
- goto bad_ticket; \
- for (; p < q; p++) \
- if (!isprint(*p)) \
- goto bad_ticket; \
- p++; \
- __str; \
+#define Z(field, fieldl) \
+ ({ \
+ u8 *__str = p; \
+ q = memchr(p, 0, end - p); \
+ if (!q || q - p > field##_SZ) \
+ return rxrpc_abort_conn( \
+ conn, skb, RXKADBADTICKET, -EPROTO, \
+ rxkad_abort_resp_tkt_##fieldl); \
+ for (; p < q; p++) \
+ if (!isprint(*p)) \
+ return rxrpc_abort_conn( \
+ conn, skb, RXKADBADTICKET, -EPROTO, \
+ rxkad_abort_resp_tkt_##fieldl); \
+ p++; \
+ __str; \
})
/* extract the ticket flags */
p++;
/* extract the authentication name */
- name = Z(ANAME);
+ name = Z(ANAME, aname);
_debug("KIV ANAME: %s", name);
/* extract the principal's instance */
- name = Z(INST);
+ name = Z(INST, inst);
_debug("KIV INST : %s", name);
/* extract the principal's authentication domain */
- name = Z(REALM);
+ name = Z(REALM, realm);
_debug("KIV REALM: %s", name);
- eproto = tracepoint_string("rxkad_bad_len");
if (end - p < 4 + 8 + 4 + 2)
- goto bad_ticket;
+ return rxrpc_abort_conn(conn, skb, RXKADBADTICKET, -EPROTO,
+ rxkad_abort_resp_tkt_short);
/* get the IPv4 address of the entity that requested the ticket */
memcpy(&addr, p, sizeof(addr));
_debug("KIV ISSUE: %llx [%llx]", issue, now);
/* check the ticket is in date */
- if (issue > now) {
- abort_code = RXKADNOAUTH;
- ret = -EKEYREJECTED;
- goto other_error;
- }
-
- if (issue < now - life) {
- abort_code = RXKADEXPIRED;
- ret = -EKEYEXPIRED;
- goto other_error;
- }
+ if (issue > now)
+ return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, -EKEYREJECTED,
+ rxkad_abort_resp_tkt_future);
+ if (issue < now - life)
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, -EKEYEXPIRED,
+ rxkad_abort_resp_tkt_expired);
*_expiry = issue + life;
/* get the service name */
- name = Z(SNAME);
+ name = Z(SNAME, sname);
_debug("KIV SNAME: %s", name);
/* get the service instance name */
- name = Z(INST);
+ name = Z(INST, sinst);
_debug("KIV SINST: %s", name);
return 0;
-
-bad_ticket:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
- abort_code = RXKADBADTICKET;
- ret = -EPROTO;
-other_error:
- *_abort_code = abort_code;
- return ret;
-temporary_error:
- return ret;
}
/*
* verify a response
*/
static int rxkad_verify_response(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
struct rxkad_response *response;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt session_key;
struct key *server_key;
- const char *eproto;
time64_t expiry;
void *ticket;
- u32 abort_code, version, kvno, ticket_len, level;
+ u32 version, kvno, ticket_len, level;
__be32 csum;
int ret, i;
server_key = rxrpc_look_up_server_security(conn, skb, 0, 0);
if (IS_ERR(server_key)) {
- switch (PTR_ERR(server_key)) {
+ ret = PTR_ERR(server_key);
+ switch (ret) {
case -ENOKEY:
- abort_code = RXKADUNKNOWNKEY;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, ret,
+ rxkad_abort_resp_nokey);
case -EKEYEXPIRED:
- abort_code = RXKADEXPIRED;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret,
+ rxkad_abort_resp_key_expired);
default:
- abort_code = RXKADNOAUTH;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, ret,
+ rxkad_abort_resp_key_rejected);
}
- trace_rxrpc_abort(0, "SVK",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- abort_code, PTR_ERR(server_key));
- *_abort_code = abort_code;
- return -EPROTO;
}
ret = -ENOMEM;
if (!response)
goto temporary_error;
- eproto = tracepoint_string("rxkad_rsp_short");
- abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
- response, sizeof(*response)) < 0)
+ response, sizeof(*response)) < 0) {
+ rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_resp_short);
goto protocol_error;
+ }
version = ntohl(response->version);
ticket_len = ntohl(response->ticket_len);
trace_rxrpc_rx_response(conn, sp->hdr.serial, version, kvno, ticket_len);
- eproto = tracepoint_string("rxkad_rsp_ver");
- abort_code = RXKADINCONSISTENCY;
- if (version != RXKAD_VERSION)
+ if (version != RXKAD_VERSION) {
+ rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO,
+ rxkad_abort_resp_version);
goto protocol_error;
+ }
- eproto = tracepoint_string("rxkad_rsp_tktlen");
- abort_code = RXKADTICKETLEN;
- if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN)
+ if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN) {
+ rxrpc_abort_conn(conn, skb, RXKADTICKETLEN, -EPROTO,
+ rxkad_abort_resp_tkt_len);
goto protocol_error;
+ }
- eproto = tracepoint_string("rxkad_rsp_unkkey");
- abort_code = RXKADUNKNOWNKEY;
- if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5)
+ if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5) {
+ rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, -EPROTO,
+ rxkad_abort_resp_unknown_tkt);
goto protocol_error;
+ }
/* extract the kerberos ticket and decrypt and decode it */
ret = -ENOMEM;
if (!ticket)
goto temporary_error_free_resp;
- eproto = tracepoint_string("rxkad_tkt_short");
- abort_code = RXKADPACKETSHORT;
- ret = skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response),
- ticket, ticket_len);
- if (ret < 0)
- goto temporary_error_free_ticket;
+ if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response),
+ ticket, ticket_len) < 0) {
+ rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_resp_short_tkt);
+ goto protocol_error;
+ }
ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len,
- &session_key, &expiry, _abort_code);
+ &session_key, &expiry);
if (ret < 0)
goto temporary_error_free_ticket;
* response */
rxkad_decrypt_response(conn, response, &session_key);
- eproto = tracepoint_string("rxkad_rsp_param");
- abort_code = RXKADSEALEDINCON;
- if (ntohl(response->encrypted.epoch) != conn->proto.epoch)
- goto protocol_error_free;
- if (ntohl(response->encrypted.cid) != conn->proto.cid)
- goto protocol_error_free;
- if (ntohl(response->encrypted.securityIndex) != conn->security_ix)
+ if (ntohl(response->encrypted.epoch) != conn->proto.epoch ||
+ ntohl(response->encrypted.cid) != conn->proto.cid ||
+ ntohl(response->encrypted.securityIndex) != conn->security_ix) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_param);
goto protocol_error_free;
+ }
+
csum = response->encrypted.checksum;
response->encrypted.checksum = 0;
rxkad_calc_response_checksum(response);
- eproto = tracepoint_string("rxkad_rsp_csum");
- if (response->encrypted.checksum != csum)
+ if (response->encrypted.checksum != csum) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_checksum);
goto protocol_error_free;
+ }
- spin_lock(&conn->bundle->channel_lock);
for (i = 0; i < RXRPC_MAXCALLS; i++) {
- struct rxrpc_call *call;
u32 call_id = ntohl(response->encrypted.call_id[i]);
+ u32 counter = READ_ONCE(conn->channels[i].call_counter);
+
+ if (call_id > INT_MAX) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_callid);
+ goto protocol_error_free;
+ }
- eproto = tracepoint_string("rxkad_rsp_callid");
- if (call_id > INT_MAX)
- goto protocol_error_unlock;
-
- eproto = tracepoint_string("rxkad_rsp_callctr");
- if (call_id < conn->channels[i].call_counter)
- goto protocol_error_unlock;
-
- eproto = tracepoint_string("rxkad_rsp_callst");
- if (call_id > conn->channels[i].call_counter) {
- call = rcu_dereference_protected(
- conn->channels[i].call,
- lockdep_is_held(&conn->bundle->channel_lock));
- if (call && call->state < RXRPC_CALL_COMPLETE)
- goto protocol_error_unlock;
+ if (call_id < counter) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_call_ctr);
+ goto protocol_error_free;
+ }
+
+ if (call_id > counter) {
+ if (conn->channels[i].call) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_call_state);
+ goto protocol_error_free;
+ }
conn->channels[i].call_counter = call_id;
}
}
- spin_unlock(&conn->bundle->channel_lock);
- eproto = tracepoint_string("rxkad_rsp_seq");
- abort_code = RXKADOUTOFSEQUENCE;
- if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1)
+ if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) {
+ rxrpc_abort_conn(conn, skb, RXKADOUTOFSEQUENCE, -EPROTO,
+ rxkad_abort_resp_ooseq);
goto protocol_error_free;
+ }
- eproto = tracepoint_string("rxkad_rsp_level");
- abort_code = RXKADLEVELFAIL;
level = ntohl(response->encrypted.level);
- if (level > RXRPC_SECURITY_ENCRYPT)
+ if (level > RXRPC_SECURITY_ENCRYPT) {
+ rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EPROTO,
+ rxkad_abort_resp_level);
goto protocol_error_free;
+ }
conn->security_level = level;
/* create a key to hold the security data and expiration time - after
_leave(" = 0");
return 0;
-protocol_error_unlock:
- spin_unlock(&conn->bundle->channel_lock);
protocol_error_free:
kfree(ticket);
protocol_error:
kfree(response);
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
key_put(server_key);
- *_abort_code = abort_code;
return -EPROTO;
temporary_error_free_ticket:
#include <linux/slab.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
MODULE_DESCRIPTION("rxperf test server (afs)");
MODULE_AUTHOR("Red Hat, Inc.");
case -EOPNOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- abort_code, ret, "GOP");
+ abort_code, ret,
+ rxperf_abort_op_not_supported);
goto call_complete;
case -ENOTSUPP:
abort_code = RX_USER_ABORT;
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- abort_code, ret, "GUA");
+ abort_code, ret,
+ rxperf_abort_op_not_supported);
goto call_complete;
case -EIO:
pr_err("Call %u in bad state %u\n",
case -ENOMEM:
case -EFAULT:
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RXGEN_SS_UNMARSHAL, ret, "GUM");
+ RXGEN_SS_UNMARSHAL, ret,
+ rxperf_abort_unmarshal_error);
goto call_complete;
default:
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RX_CALL_DEAD, ret, "GER");
+ RX_CALL_DEAD, ret,
+ rxperf_abort_general_error);
goto call_complete;
}
}
if (n == -ENOMEM)
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "GOM");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ rxperf_abort_oom);
return n;
}
*/
int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
{
- const struct rxrpc_security *sec;
struct rxrpc_key_token *token;
struct key *key = conn->key;
- int ret;
+ int ret = 0;
_enter("{%d},{%x}", conn->debug_id, key_serial(key));
- if (!key)
- return 0;
-
- ret = key_validate(key);
- if (ret < 0)
- return ret;
-
for (token = key->payload.data[0]; token; token = token->next) {
- sec = rxrpc_security_lookup(token->security_index);
- if (sec)
+ if (token->security_index == conn->security->security_index)
goto found;
}
return -EKEYREJECTED;
found:
- conn->security = sec;
-
- ret = conn->security->init_connection_security(conn, token);
- if (ret < 0) {
- conn->security = &rxrpc_no_security;
- return ret;
+ mutex_lock(&conn->security_lock);
+ if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) {
+ ret = conn->security->init_connection_security(conn, token);
+ if (ret == 0) {
+ spin_lock(&conn->state_lock);
+ if (conn->state == RXRPC_CONN_CLIENT_UNSECURED)
+ conn->state = RXRPC_CONN_CLIENT;
+ spin_unlock(&conn->state_lock);
+ }
}
-
- _leave(" = 0");
- return 0;
+ mutex_unlock(&conn->security_lock);
+ return ret;
}
/*
sec = rxrpc_security_lookup(sp->hdr.securityIndex);
if (!sec) {
- trace_rxrpc_abort(0, "SVS",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EKEYREJECTED);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = RX_INVALID_OPERATION;
+ rxrpc_direct_abort(skb, rxrpc_abort_unsupported_security,
+ RX_INVALID_OPERATION, -EKEYREJECTED);
return NULL;
}
if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE &&
!rx->securities) {
- trace_rxrpc_abort(0, "SVR",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EKEYREJECTED);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = sec->no_key_abort;
+ rxrpc_direct_abort(skb, rxrpc_abort_no_service_key,
+ sec->no_key_abort, -EKEYREJECTED);
return NULL;
}
sprintf(kdesc, "%u:%u",
sp->hdr.serviceId, sp->hdr.securityIndex);
- rcu_read_lock();
+ read_lock(&conn->local->services_lock);
- rx = rcu_dereference(conn->local->service);
+ rx = conn->local->service;
if (!rx)
goto out;
}
out:
- rcu_read_unlock();
+ read_unlock(&conn->local->services_lock);
return key;
}
#include <net/af_rxrpc.h>
#include "ar-internal.h"
+/*
+ * Propose an abort to be made in the I/O thread.
+ */
+bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
+ enum rxrpc_abort_reason why)
+{
+ _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
+
+ if (!call->send_abort && !rxrpc_call_is_complete(call)) {
+ call->send_abort_why = why;
+ call->send_abort_err = error;
+ call->send_abort_seq = 0;
+ /* Request abort locklessly vs rxrpc_input_call_event(). */
+ smp_store_release(&call->send_abort, abort_code);
+ rxrpc_poke_call(call, rxrpc_call_poke_abort);
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Wait for a call to become connected. Interruption here doesn't cause the
+ * call to be aborted.
+ */
+static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo)
+{
+ DECLARE_WAITQUEUE(myself, current);
+ int ret = 0;
+
+ _enter("%d", call->debug_id);
+
+ if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN)
+ return call->error;
+
+ add_wait_queue_exclusive(&call->waitq, &myself);
+
+ for (;;) {
+ ret = call->error;
+ if (ret < 0)
+ break;
+
+ switch (call->interruptibility) {
+ case RXRPC_INTERRUPTIBLE:
+ case RXRPC_PREINTERRUPTIBLE:
+ set_current_state(TASK_INTERRUPTIBLE);
+ break;
+ case RXRPC_UNINTERRUPTIBLE:
+ default:
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ break;
+ }
+ if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) {
+ ret = call->error;
+ break;
+ }
+ if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+ call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
+ signal_pending(current)) {
+ ret = sock_intr_errno(*timeo);
+ break;
+ }
+ *timeo = schedule_timeout(*timeo);
+ }
+
+ remove_wait_queue(&call->waitq, &myself);
+ __set_current_state(TASK_RUNNING);
+
+ if (ret == 0 && rxrpc_call_is_complete(call))
+ ret = call->error;
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
/*
* Return true if there's sufficient Tx queue space.
*/
if (rxrpc_check_tx_space(call, NULL))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
if (signal_pending(current))
if (rxrpc_check_tx_space(call, &tx_win))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
if (timeout == 0 &&
if (rxrpc_check_tx_space(call, NULL))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
trace_rxrpc_txqueue(call, rxrpc_txqueue_wait);
struct rxrpc_txbuf *txb,
rxrpc_notify_end_tx_t notify_end_tx)
{
- unsigned long now;
rxrpc_seq_t seq = txb->seq;
bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke;
poke = list_empty(&call->tx_sendmsg);
list_add_tail(&txb->call_link, &call->tx_sendmsg);
call->tx_prepared = seq;
+ if (last)
+ rxrpc_notify_end_tx(rx, call, notify_end_tx);
spin_unlock(&call->tx_lock);
- if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {
- _debug("________awaiting reply/ACK__________");
- write_lock(&call->state_lock);
- switch (call->state) {
- case RXRPC_CALL_CLIENT_SEND_REQUEST:
- call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
- rxrpc_notify_end_tx(rx, call, notify_end_tx);
- break;
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- call->state = RXRPC_CALL_SERVER_SEND_REPLY;
- now = jiffies;
- WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
- if (call->ackr_reason == RXRPC_ACK_DELAY)
- call->ackr_reason = 0;
- trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
- if (!last)
- break;
- fallthrough;
- case RXRPC_CALL_SERVER_SEND_REPLY:
- call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
- rxrpc_notify_end_tx(rx, call, notify_end_tx);
- break;
- default:
- break;
- }
- write_unlock(&call->state_lock);
- }
-
if (poke)
rxrpc_poke_call(call, rxrpc_call_poke_start);
}
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+ ret = rxrpc_wait_to_be_connected(call, &timeo);
+ if (ret < 0)
+ return ret;
+
+ if (call->conn->state == RXRPC_CONN_CLIENT_UNSECURED) {
+ ret = rxrpc_init_client_conn_security(call->conn);
+ if (ret < 0)
+ return ret;
+ }
+
/* this should be in poll */
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
ret = -EPIPE;
if (sk->sk_shutdown & SEND_SHUTDOWN)
goto maybe_error;
- state = READ_ONCE(call->state);
+ state = rxrpc_call_state(call);
ret = -ESHUTDOWN;
if (state >= RXRPC_CALL_COMPLETE)
goto maybe_error;
ret = -EPROTO;
if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
state != RXRPC_CALL_SERVER_ACK_REQUEST &&
- state != RXRPC_CALL_SERVER_SEND_REPLY)
+ state != RXRPC_CALL_SERVER_SEND_REPLY) {
+ /* Request phase complete for this client call */
+ trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EPROTO);
goto maybe_error;
+ }
ret = -EMSGSIZE;
if (call->tx_total_len != -1) {
/* check for the far side aborting the call or a network error
* occurring */
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
goto call_terminated;
/* add the packet to the send queue if it's now full */
success:
ret = copied;
- if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) {
- read_lock(&call->state_lock);
- if (call->error < 0)
- ret = call->error;
- read_unlock(&call->state_lock);
- }
+ if (rxrpc_call_is_complete(call) &&
+ call->error < 0)
+ ret = call->error;
out:
call->tx_pending = txb;
_leave(" = %d", ret);
atomic_inc_return(&rxrpc_debug_id));
/* The socket is now unlocked */
- rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp);
_leave(" = %p\n", call);
return call;
}
int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
__releases(&rx->sk.sk_lock.slock)
{
- enum rxrpc_call_state state;
struct rxrpc_call *call;
unsigned long now, j;
bool dropped_lock = false;
return PTR_ERR(call);
/* ... and we have the call lock. */
ret = 0;
- if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
goto out_put_unlock;
} else {
- switch (READ_ONCE(call->state)) {
+ switch (rxrpc_call_state(call)) {
case RXRPC_CALL_UNINITIALISED:
case RXRPC_CALL_CLIENT_AWAIT_CONN:
case RXRPC_CALL_SERVER_PREALLOC:
break;
}
- state = READ_ONCE(call->state);
- _debug("CALL %d USR %lx ST %d on CONN %p",
- call->debug_id, call->user_call_ID, state, call->conn);
-
- if (state >= RXRPC_CALL_COMPLETE) {
+ if (rxrpc_call_is_complete(call)) {
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (p.command == RXRPC_CMD_SEND_ABORT) {
+ rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED,
+ rxrpc_abort_call_sendmsg);
ret = 0;
- if (rxrpc_abort_call("CMD", call, 0, p.abort_code, -ECONNABORTED))
- ret = rxrpc_send_abort_packet(call);
} else if (p.command != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
} else {
bool dropped_lock = false;
int ret;
- _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
+ _enter("{%d},", call->debug_id);
ASSERTCMP(msg->msg_name, ==, NULL);
ASSERTCMP(msg->msg_control, ==, NULL);
mutex_lock(&call->user_mutex);
- _debug("CALL %d USR %lx ST %d on CONN %p",
- call->debug_id, call->user_call_ID, call->state, call->conn);
-
- switch (READ_ONCE(call->state)) {
- case RXRPC_CALL_CLIENT_SEND_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- case RXRPC_CALL_SERVER_SEND_REPLY:
- ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
- notify_end_tx, &dropped_lock);
- break;
- case RXRPC_CALL_COMPLETE:
- read_lock(&call->state_lock);
+ ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
+ notify_end_tx, &dropped_lock);
+ if (ret == -ESHUTDOWN)
ret = call->error;
- read_unlock(&call->state_lock);
- break;
- default:
- /* Request phase complete for this client call */
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send"));
- ret = -EPROTO;
- break;
- }
if (!dropped_lock)
mutex_unlock(&call->user_mutex);
* @call: The call to be aborted
* @abort_code: The abort code to stick into the ABORT packet
* @error: Local error value
- * @why: 3-char string indicating why.
+ * @why: Indication as to why.
*
* Allow a kernel service to abort a call, if it's still in an abortable state
* and return true if the call was aborted, false if it was already complete.
*/
bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
- u32 abort_code, int error, const char *why)
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
{
bool aborted;
- _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
+ _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
mutex_lock(&call->user_mutex);
-
- aborted = rxrpc_abort_call(why, call, 0, abort_code, error);
- if (aborted)
- rxrpc_send_abort_packet(call);
-
+ aborted = rxrpc_propose_abort(call, abort_code, error, why);
mutex_unlock(&call->user_mutex);
return aborted;
}
cp = rcu_dereference_bh(ca->params);
tcf_lastuse_update(&ca->tcf_tm);
- bstats_update(&ca->tcf_bstats, skb);
+ tcf_action_update_bstats(&ca->common, skb);
action = READ_ONCE(ca->tcf_action);
wlen = skb_network_offset(skb);
index = actparm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
- ret = tcf_idr_create(tn, index, est, a,
- &act_ctinfo_ops, bind, false, flags);
+ ret = tcf_idr_create_from_flags(tn, index, est, a,
+ &act_ctinfo_ops, bind, flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
{
const u32 *label = nla_data(attr);
+ if (nla_len(attr) != sizeof(*label)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length");
+ return -EINVAL;
+ }
+
if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) {
NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range");
return -EINVAL;
static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = {
[TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)),
[TCA_MPLS_PROTO] = { .type = NLA_U16 },
- [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label),
+ [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY,
+ valid_label),
[TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7),
[TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1),
[TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1),
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/refcount.h>
+#include <linux/rcupdate.h>
#include <net/act_api.h>
#include <net/netlink.h>
#include <net/pkt_cls.h>
struct tcindex_filter_result *r, struct nlattr **tb,
struct nlattr *est, u32 flags, struct netlink_ext_ack *extack)
{
- struct tcindex_filter_result new_filter_result, *old_r = r;
+ struct tcindex_filter_result new_filter_result;
struct tcindex_data *cp = NULL, *oldp;
struct tcindex_filter *f = NULL; /* make gcc behave */
struct tcf_result cr = {};
int err, balloc = 0;
struct tcf_exts e;
+ bool update_h = false;
err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
if (err < 0)
err = tcindex_filter_result_init(&new_filter_result, cp, net);
if (err < 0)
goto errout_alloc;
- if (old_r)
+ if (r)
cr = r->res;
err = -EBUSY;
}
}
- if (cp->perfect)
+ if (cp->perfect) {
r = cp->perfect + handle;
- else
- r = tcindex_lookup(cp, handle) ? : &new_filter_result;
+ } else {
+ /* imperfect area is updated in-place using rcu */
+ update_h = !!tcindex_lookup(cp, handle);
+ r = &new_filter_result;
+ }
if (r == &new_filter_result) {
f = kzalloc(sizeof(*f), GFP_KERNEL);
tcf_bind_filter(tp, &cr, base);
}
- if (old_r && old_r != r) {
- err = tcindex_filter_result_init(old_r, cp, net);
- if (err < 0) {
- kfree(f);
- goto errout_alloc;
- }
- }
-
oldp = p;
r->res = cr;
tcf_exts_change(&r->exts, &e);
rcu_assign_pointer(tp->root, cp);
- if (r == &new_filter_result) {
+ if (update_h) {
+ struct tcindex_filter __rcu **fp;
+ struct tcindex_filter *cf;
+
+ f->result.res = r->res;
+ tcf_exts_change(&f->result.exts, &r->exts);
+
+ /* imperfect area bucket */
+ fp = cp->h + (handle % cp->hash);
+
+ /* lookup the filter, guaranteed to exist */
+ for (cf = rcu_dereference_bh_rtnl(*fp); cf;
+ fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp))
+ if (cf->key == (u16)handle)
+ break;
+
+ f->next = cf->next;
+
+ cf = rcu_replace_pointer(*fp, f, 1);
+ tcf_exts_get_net(&cf->result.exts);
+ tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work);
+ } else if (r == &new_filter_result) {
struct tcindex_filter *nfp;
struct tcindex_filter __rcu **fp;
return -ENOENT;
}
+ if (new && new->ops == &noqueue_qdisc_ops) {
+ NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class");
+ return -EINVAL;
+ }
+
err = cops->graft(parent, cl, new, &old, extack);
if (err)
return err;
result = tcf_classify(skb, NULL, fl, &res, true);
if (result < 0)
continue;
+ if (result == TC_ACT_SHOT)
+ goto done;
+
flow = (struct atm_flow_data *)res.class;
if (!flow)
flow = lookup_flow(sch, res.classid);
- goto done;
+ goto drop;
}
}
flow = NULL;
result = tcf_classify(skb, NULL, fl, &res, true);
if (!fl || result < 0)
goto fallback;
+ if (result == TC_ACT_SHOT)
+ return NULL;
cl = (void *)res.class;
if (!cl) {
case TC_ACT_TRAP:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
fallthrough;
- case TC_ACT_SHOT:
- return NULL;
case TC_ACT_RECLASSIFY:
return cbq_reclassify(skb, cl);
}
/* Even if driver returns failure adjust the stats - in case offload
* ended but driver still wants to adjust the values.
*/
+ sch_tree_lock(sch);
for (i = 0; i < MAX_DPs; i++) {
if (!table->tab[i])
continue;
sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits;
}
_bstats_update(&sch->bstats, bytes, packets);
+ sch_tree_unlock(sch);
kfree(hw_stats);
return ret;
{
return (unsigned long)htb_find(handle, sch);
}
+
+#define HTB_DIRECT ((struct htb_class *)-1L)
+
/**
* htb_classify - classify a packet into class
+ * @skb: the socket buffer
+ * @sch: the active queue discipline
+ * @qerr: pointer for returned status code
*
* It returns NULL if the packet should be dropped or -1 if the packet
* should be passed directly thru. In all other cases leaf class is returned.
* have no valid leaf we try to use MAJOR:default leaf. It still unsuccessful
* then finish and return direct queue.
*/
-#define HTB_DIRECT ((struct htb_class *)-1L)
-
static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
{
while (cl->cmode == HTB_MAY_BORROW && p && mask) {
m = mask;
while (m) {
- int prio = ffz(~m);
+ unsigned int prio = ffz(~m);
+
+ if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio)))
+ break;
m &= ~(1 << prio);
if (p->inner.clprio[prio].feed.rb_node)
struct tc_htb_qopt_offload offload_opt;
struct netdev_queue *dev_queue;
struct Qdisc *q = cl->leaf.q;
- struct Qdisc *old = NULL;
+ struct Qdisc *old;
int err;
if (cl->level)
WARN_ON(!q);
dev_queue = htb_offload_get_queue(cl);
- old = htb_graft_helper(dev_queue, NULL);
- if (destroying)
- /* Before HTB is destroyed, the kernel grafts noop_qdisc to
- * all queues.
+ /* When destroying, caller qdisc_graft grafts the new qdisc and invokes
+ * qdisc_put for the qdisc being destroyed. htb_destroy_class_offload
+ * does not need to graft or qdisc_put the qdisc being destroyed.
+ */
+ if (!destroying) {
+ old = htb_graft_helper(dev_queue, NULL);
+ /* Last qdisc grafted should be the same as cl->leaf.q when
+ * calling htb_delete.
*/
- WARN_ON(!(old->flags & TCQ_F_BUILTIN));
- else
WARN_ON(old != q);
+ }
if (cl->parent) {
_bstats_update(&cl->parent->bstats_bias,
};
err = htb_offload(qdisc_dev(sch), &offload_opt);
- if (!err || destroying)
- qdisc_put(old);
- else
- htb_graft_helper(dev_queue, old);
+ if (!destroying) {
+ if (!err)
+ qdisc_put(old);
+ else
+ htb_graft_helper(dev_queue, old);
+ }
if (last_child)
return err;
int i;
hrtimer_cancel(&q->advance_timer);
+
if (q->qdiscs) {
for (i = 0; i < dev->num_tx_queues; i++)
if (q->qdiscs[i])
* happens in qdisc_create(), after taprio_init() has been called.
*/
hrtimer_cancel(&q->advance_timer);
+ qdisc_synchronize(sch);
taprio_disable_offload(dev, q, NULL);
}
}
+ /* If somehow no addresses were found that can be used with this
+ * scope, it's an error.
+ */
+ if (list_empty(&dest->address_list))
+ error = -ENETUNREACH;
+
out:
if (error)
sctp_bind_addr_clean(dest);
struct sctp_comm_param *commp = p;
struct sock *sk = ep->base.sk;
const struct inet_diag_req_v2 *r = commp->r;
- struct sctp_association *assoc =
- list_entry(ep->asocs.next, struct sctp_association, asocs);
/* find the ep only once through the transports by this condition */
- if (tsp->asoc != assoc)
+ if (!list_is_first(&tsp->asoc->asocs, &ep->asocs))
return 0;
if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family)
/* When a data chunk is sent, reset the heartbeat interval. */
expires = jiffies + sctp_transport_timeout(transport);
- if ((time_before(transport->hb_timer.expires, expires) ||
- !timer_pending(&transport->hb_timer)) &&
- !mod_timer(&transport->hb_timer,
+ if (!mod_timer(&transport->hb_timer,
expires + get_random_u32_below(transport->rto)))
sctp_transport_hold(transport);
}
static void sock_recv_mark(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb)
{
- if (sock_flag(sk, SOCK_RCVMARK) && skb)
- put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32),
- &skb->mark);
+ if (sock_flag(sk, SOCK_RCVMARK) && skb) {
+ /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */
+ __u32 mark = skb->mark;
+
+ put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32), &mark);
+ }
}
void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
list_for_each_entry(pos, &pipe->in_downcall, list) {
if (!uid_eq(pos->uid, uid))
continue;
- if (auth && pos->auth->service != auth->service)
+ if (pos->auth->service != auth->service)
continue;
refcount_inc(&pos->count);
return pos;
return err;
}
+static struct gss_upcall_msg *
+gss_find_downcall(struct rpc_pipe *pipe, kuid_t uid)
+{
+ struct gss_upcall_msg *pos;
+ list_for_each_entry(pos, &pipe->in_downcall, list) {
+ if (!uid_eq(pos->uid, uid))
+ continue;
+ if (!rpc_msg_is_inflight(&pos->msg))
+ continue;
+ refcount_inc(&pos->count);
+ return pos;
+ }
+ return NULL;
+}
+
#define MSG_BUF_MAXSIZE 1024
static ssize_t
err = -ENOENT;
/* Find a matching upcall */
spin_lock(&pipe->lock);
- gss_msg = __gss_find_upcall(pipe, uid, NULL);
+ gss_msg = gss_find_downcall(pipe, uid);
if (gss_msg == NULL) {
spin_unlock(&pipe->lock);
goto err_put_ctx;
* rejecting the server-computed MIC in this somewhat rare case,
* do not use splice with the GSS integrity service.
*/
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* Did we already verify the signature on the original pass through? */
if (rqstp->rq_deferred)
int pad, remaining_len, offset;
u32 rseqno;
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
priv_len = svc_getnl(&buf->head[0]);
if (rqstp->rq_deferred) {
goto err_short_len;
/* Will be turned off by GSS integrity and privacy services */
- __set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* Will be turned off only when NFSv4 Sessions are used */
- __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
- __clear_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ clear_bit(RQ_DROPME, &rqstp->rq_flags);
svc_putu32(resv, rqstp->rq_xid);
trace_svc_defer(rqstp);
svc_xprt_get(rqstp->rq_xprt);
dr->xprt = rqstp->rq_xprt;
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
dr->handle.revisit = svc_revisit;
return &dr->handle;
static void svc_sock_secure_port(struct svc_rqst *rqstp)
{
if (svc_port_is_privileged(svc_addr(rqstp)))
- __set_bit(RQ_SECURE, &rqstp->rq_flags);
+ set_bit(RQ_SECURE, &rqstp->rq_flags);
else
- __clear_bit(RQ_SECURE, &rqstp->rq_flags);
+ clear_bit(RQ_SECURE, &rqstp->rq_flags);
}
/*
rqstp->rq_xprt_ctxt = NULL;
rqstp->rq_prot = IPPROTO_TCP;
if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags))
- __set_bit(RQ_LOCAL, &rqstp->rq_flags);
+ set_bit(RQ_LOCAL, &rqstp->rq_flags);
else
- __clear_bit(RQ_LOCAL, &rqstp->rq_flags);
+ clear_bit(RQ_LOCAL, &rqstp->rq_flags);
p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
calldir = p[1];
static void svc_rdma_secure_port(struct svc_rqst *rqstp)
{
- __set_bit(RQ_SECURE, &rqstp->rq_flags);
+ set_bit(RQ_SECURE, &rqstp->rq_flags);
}
static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt)
bool addr_match = false;
bool sign_match = false;
bool link_up = false;
+ bool link_is_reset = false;
bool accept_addr = false;
- bool reset = true;
+ bool reset = false;
char *if_name;
unsigned long intv;
u16 session;
/* Prepare to validate requesting node's signature and media address */
l = le->link;
link_up = l && tipc_link_is_up(l);
+ link_is_reset = l && tipc_link_is_reset(l);
addr_match = l && !memcmp(&le->maddr, maddr, sizeof(*maddr));
sign_match = (signature == n->signature);
/* These three flags give us eight permutations: */
if (sign_match && addr_match && link_up) {
- /* All is fine. Do nothing. */
- reset = false;
+ /* All is fine. Ignore requests. */
/* Peer node is not a container/local namespace */
if (!n->peer_hash_mix)
n->peer_hash_mix = hash_mixes;
*/
accept_addr = true;
*respond = true;
+ reset = true;
} else if (!sign_match && addr_match && link_up) {
/* Peer node rebooted. Two possibilities:
* - Delayed re-discovery; this link endpoint has already
n->signature = signature;
accept_addr = true;
*respond = true;
+ reset = true;
}
if (!accept_addr)
tipc_link_fsm_evt(l, LINK_RESET_EVT);
if (n->state == NODE_FAILINGOVER)
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
+ link_is_reset = tipc_link_is_reset(l);
le->link = l;
n->link_cnt++;
tipc_node_calculate_timer(n, l);
memcpy(&le->maddr, maddr, sizeof(*maddr));
exit:
tipc_node_write_unlock(n);
- if (reset && l && !tipc_link_is_reset(l))
+ if (reset && !link_is_reset)
tipc_node_link_down(n, b->identity, false);
tipc_node_put(n);
}
/* Send a 'SYN-' to destination */
m.msg_name = dest;
m.msg_namelen = destlen;
+ iov_iter_kvec(&m.msg_iter, ITER_SOURCE, NULL, 0, 0);
/* If connect is in non-blocking case, set MSG_DONTWAIT to
* indicate send_msg() is never blocked.
__skb_queue_head(&new_sk->sk_receive_queue, buf);
skb_set_owner_r(buf, new_sk);
}
+ iov_iter_kvec(&m.msg_iter, ITER_SOURCE, NULL, 0, 0);
__tipc_sendstream(new_sock, &m, 0);
release_sock(new_sk);
exit:
{
struct tls_rec *rec;
- rec = list_first_entry(&ctx->tx_list, struct tls_rec, list);
+ rec = list_first_entry_or_null(&ctx->tx_list, struct tls_rec, list);
if (!rec)
return false;
int rc = -EOPNOTSUPP;
lock_sock(sk);
+ if (sock->state != SS_UNCONNECTED) {
+ rc = -EINVAL;
+ release_sock(sk);
+ return rc;
+ }
+
if (sk->sk_state != TCP_LISTEN) {
memset(&x25_sk(sk)->dest_addr, 0, X25_ADDR_LEN);
sk->sk_max_ack_backlog = backlog;
* Based on code and translator idea by: Florian Westphal <fw@strlen.de>
*/
#include <linux/compat.h>
+#include <linux/nospec.h>
#include <linux/xfrm.h>
#include <net/xfrm.h>
nla_for_each_attr(nla, attrs, len, remaining) {
int err;
- switch (type) {
+ switch (nlh_src->nlmsg_type) {
case XFRM_MSG_NEWSPDINFO:
err = xfrm_nla_cpy(dst, nla, nla_len(nla));
break;
NL_SET_ERR_MSG(extack, "Bad attribute");
return -EOPNOTSUPP;
}
+ type = array_index_nospec(type, XFRMA_MAX + 1);
if (nla_len(nla) < compat_policy[type].len) {
NL_SET_ERR_MSG(extack, "Attribute bad length");
return -EOPNOTSUPP;
goto out;
if (x->props.flags & XFRM_STATE_DECAP_DSCP)
- ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)),
- ipipv6_hdr(skb));
+ ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb));
if (!(x->props.flags & XFRM_STATE_NOECN))
ipip6_ecn_decapsulate(skb);
skb->mark = 0;
}
+static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type, unsigned short family)
+{
+ struct sec_path *sp;
+
+ sp = skb_sec_path(skb);
+ if (sp && (sp->len || sp->olen) &&
+ !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ goto discard;
+
+ XFRM_SPI_SKB_CB(skb)->family = family;
+ if (family == AF_INET) {
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
+ } else {
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL;
+ }
+
+ return xfrm_input(skb, nexthdr, spi, encap_type);
+discard:
+ kfree_skb(skb);
+ return 0;
+}
+
+static int xfrmi4_rcv(struct sk_buff *skb)
+{
+ return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET);
+}
+
+static int xfrmi6_rcv(struct sk_buff *skb)
+{
+ return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
+ 0, 0, AF_INET6);
+}
+
+static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+ return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET);
+}
+
+static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+{
+ return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6);
+}
+
static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
{
const struct xfrm_mode *inner_mode;
};
static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = {
- .handler = xfrm6_rcv,
- .input_handler = xfrm_input,
+ .handler = xfrmi6_rcv,
+ .input_handler = xfrmi6_input,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi6_err,
.priority = 10,
#endif
static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = {
- .handler = xfrm4_rcv,
- .input_handler = xfrm_input,
+ .handler = xfrmi4_rcv,
+ .input_handler = xfrmi4_input,
.cb_handler = xfrmi_rcv_cb,
.err_handler = xfrmi4_err,
.priority = 10,
}
if (xp->lft.hard_use_expires_seconds) {
time64_t tmo = xp->lft.hard_use_expires_seconds +
- (xp->curlft.use_time ? : xp->curlft.add_time) - now;
+ (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now;
if (tmo <= 0)
goto expired;
if (tmo < next)
}
if (xp->lft.soft_use_expires_seconds) {
time64_t tmo = xp->lft.soft_use_expires_seconds +
- (xp->curlft.use_time ? : xp->curlft.add_time) - now;
+ (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now;
if (tmo <= 0) {
warn = 1;
tmo = XFRM_KM_TIMEOUT;
return 1;
}
- pol->curlft.use_time = ktime_get_real_seconds();
+ /* This lockless write can happen from different cpus. */
+ WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds());
pols[0] = pol;
npols++;
xfrm_pol_put(pols[0]);
return 0;
}
- pols[1]->curlft.use_time = ktime_get_real_seconds();
+ /* This write can happen from different cpus. */
+ WRITE_ONCE(pols[1]->curlft.use_time,
+ ktime_get_real_seconds());
npols++;
}
}
goto reject;
}
+ if (if_id)
+ secpath_reset(skb);
+
xfrm_pols_put(pols, npols);
return 1;
}
if (x->km.state == XFRM_STATE_EXPIRED)
goto expired;
if (x->lft.hard_add_expires_seconds) {
- long tmo = x->lft.hard_add_expires_seconds +
+ time64_t tmo = x->lft.hard_add_expires_seconds +
x->curlft.add_time - now;
if (tmo <= 0) {
if (x->xflags & XFRM_SOFT_EXPIRE) {
next = tmo;
}
if (x->lft.hard_use_expires_seconds) {
- long tmo = x->lft.hard_use_expires_seconds +
- (x->curlft.use_time ? : now) - now;
+ time64_t tmo = x->lft.hard_use_expires_seconds +
+ (READ_ONCE(x->curlft.use_time) ? : now) - now;
if (tmo <= 0)
goto expired;
if (tmo < next)
if (x->km.dying)
goto resched;
if (x->lft.soft_add_expires_seconds) {
- long tmo = x->lft.soft_add_expires_seconds +
+ time64_t tmo = x->lft.soft_add_expires_seconds +
x->curlft.add_time - now;
if (tmo <= 0) {
warn = 1;
}
}
if (x->lft.soft_use_expires_seconds) {
- long tmo = x->lft.soft_use_expires_seconds +
- (x->curlft.use_time ? : now) - now;
+ time64_t tmo = x->lft.soft_use_expires_seconds +
+ (READ_ONCE(x->curlft.use_time) ? : now) - now;
if (tmo <= 0)
warn = 1;
else if (tmo < next)
hrtimer_start(&x1->mtimer, ktime_set(1, 0),
HRTIMER_MODE_REL_SOFT);
- if (x1->curlft.use_time)
+ if (READ_ONCE(x1->curlft.use_time))
xfrm_state_check_expire(x1);
if (x->props.smark.m || x->props.smark.v || x->if_id) {
{
xfrm_dev_state_update_curlft(x);
- if (!x->curlft.use_time)
- x->curlft.use_time = ktime_get_real_seconds();
+ if (!READ_ONCE(x->curlft.use_time))
+ WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds());
if (x->curlft.bytes >= x->lft.hard_byte_limit ||
x->curlft.packets >= x->lft.hard_packet_limit) {
macro_rules! print_macro (
// The non-continuation cases (most of them, e.g. `INFO`).
($format_string:path, false, $($arg:tt)+) => (
- // SAFETY: This hidden macro should only be called by the documented
- // printing macros which ensure the format string is one of the fixed
- // ones. All `__LOG_PREFIX`s are null-terminated as they are generated
- // by the `module!` proc macro or fixed values defined in a kernel
- // crate.
- unsafe {
- $crate::print::call_printk(
- &$format_string,
- crate::__LOG_PREFIX,
- format_args!($($arg)+),
- );
+ // To remain sound, `arg`s must be expanded outside the `unsafe` block.
+ // Typically one would use a `let` binding for that; however, `format_args!`
+ // takes borrows on the arguments, but does not extend the scope of temporaries.
+ // Therefore, a `match` expression is used to keep them around, since
+ // the scrutinee is kept until the end of the `match`.
+ match format_args!($($arg)+) {
+ // SAFETY: This hidden macro should only be called by the documented
+ // printing macros which ensure the format string is one of the fixed
+ // ones. All `__LOG_PREFIX`s are null-terminated as they are generated
+ // by the `module!` proc macro or fixed values defined in a kernel
+ // crate.
+ args => unsafe {
+ $crate::print::call_printk(
+ &$format_string,
+ crate::__LOG_PREFIX,
+ args,
+ );
+ }
}
);
{
kthread_stop(simple_tsk);
unregister_ftrace_direct_multi(&direct, my_tramp);
+ ftrace_free_filter(&direct);
}
module_init(ftrace_direct_multi_init);
static void __exit ftrace_direct_multi_exit(void)
{
unregister_ftrace_direct_multi(&direct, (unsigned long) my_tramp);
+ ftrace_free_filter(&direct);
}
module_init(ftrace_direct_multi_init);
# Don't stop modules_install even if we can't sign external modules.
#
ifeq ($(CONFIG_MODULE_SIG_ALL),y)
+ifeq ($(filter pkcs11:%, $(CONFIG_MODULE_SIG_KEY)),)
sig-key := $(if $(wildcard $(CONFIG_MODULE_SIG_KEY)),,$(srctree)/)$(CONFIG_MODULE_SIG_KEY)
+else
+sig-key := $(CONFIG_MODULE_SIG_KEY)
+endif
quiet_cmd_sign = SIGN $@
- cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(sig-key) certs/signing_key.x509 $@ \
+ cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \
$(if $(KBUILD_EXTMOD),|| true)
else
quiet_cmd_sign :=
$(if $(CONFIG_MODVERSIONS),-m) \
$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \
$(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \
+ $(if $(KBUILD_MODPOST_WARN),-w) \
$(if $(KBUILD_NSDEPS),-d $(MODULES_NSDEPS)) \
$(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N) \
-o $@
modpost-args += -n
endif
+# Read out modules.order to pass in modpost.
+# Otherwise, allmodconfig would fail with "Argument list too long".
+ifdef KBUILD_MODULES
+modpost-args += -T $(MODORDER)
+modpost-deps += $(MODORDER)
+endif
+
ifeq ($(KBUILD_EXTMOD),)
# Generate the list of in-tree objects in vmlinux
endif # ($(KBUILD_EXTMOD),)
-ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),)
+ifneq ($(missing-input),)
modpost-args += -w
endif
-ifdef KBUILD_MODULES
-modpost-args += -T $(MODORDER)
-modpost-deps += $(MODORDER)
-endif
-
-# Read out modules.order to pass in modpost.
-# Otherwise, allmodconfig would fail with "Argument list too long".
quiet_cmd_modpost = MODPOST $@
cmd_modpost = \
$(if $(missing-input), \
PHONY += help
help:
@echo ' rpm-pkg - Build both source and binary RPM kernel packages'
+ @echo ' srcrpm-pkg - Build only the source kernel RPM package'
@echo ' binrpm-pkg - Build only the binary kernel RPM package'
@echo ' deb-pkg - Build both source and binary deb kernel packages'
@echo ' bindeb-pkg - Build only the binary kernel deb package'
$(call if_changed_dep,cc_o_c)
ifdef CONFIG_MODULES
+KASAN_SANITIZE_.vmlinux.export.o := n
targets += .vmlinux.export.o
vmlinux: .vmlinux.export.o
endif
#include <unistd.h>
#include <fcntl.h>
#include <string.h>
-#include <stdarg.h>
#include <stdlib.h>
#include <stdio.h>
#include <ctype.h>
#include "varasm.h"
#include "stor-layout.h"
#include "internal-fn.h"
+#include "gimple.h"
#include "gimple-expr.h"
+#include "gimple-iterator.h"
#include "gimple-fold.h"
#include "context.h"
#include "tree-ssa-alias.h"
#include "tree-eh.h"
#include "stmt.h"
#include "gimplify.h"
-#include "gimple.h"
#include "tree-phinodes.h"
#include "tree-cfg.h"
-#include "gimple-iterator.h"
#include "gimple-ssa.h"
#include "ssa-iterators.h"
task_ptr_type = task_type.get_type().pointer()
if utils.is_target_arch("x86"):
- var_ptr = gdb.parse_and_eval("¤t_task")
+ var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task")
return per_cpu(var_ptr, cpu).dereference()
elif utils.is_target_arch("aarch64"):
current_task_addr = gdb.parse_and_eval("$SP_EL0")
# If the MAKEFLAGS variable contains multiple instances of the
# --jobserver-auth= option, the last one is relevant.
fds = opts[-1].split("=", 1)[1]
- reader, writer = [int(x) for x in fds.split(",", 1)]
- # Open a private copy of reader to avoid setting nonblocking
- # on an unexpecting process with the same reader fd.
- reader = os.open("/proc/self/fd/%d" % (reader),
- os.O_RDONLY | os.O_NONBLOCK)
+
+ # Starting with GNU Make 4.4, named pipes are used for reader and writer.
+ # Example argument: --jobserver-auth=fifo:/tmp/GMfifo8134
+ _, _, path = fds.partition('fifo:')
+
+ if path:
+ reader = os.open(path, os.O_RDONLY | os.O_NONBLOCK)
+ writer = os.open(path, os.O_WRONLY)
+ else:
+ reader, writer = [int(x) for x in fds.split(",", 1)]
+ # Open a private copy of reader to avoid setting nonblocking
+ # on an unexpecting process with the same reader fd.
+ reader = os.open("/proc/self/fd/%d" % (reader),
+ os.O_RDONLY | os.O_NONBLOCK)
# Read out as many jobserver slots as possible.
while True:
# SPDX-License-Identifier: GPL-2.0-only
/conf
/[gmnq]conf
+/[gmnq]conf-bin
/[gmnq]conf-cflags
/[gmnq]conf-libs
-/qconf-bin
/qconf-moc.cc
$(obj)/gconf.o: | $(obj)/gconf-cflags
# check if necessary packages are available, and configure build flags
-cmd_conf_cfg = $< $(addprefix $(obj)/$*conf-, cflags libs bin)
+cmd_conf_cfg = $< $(addprefix $(obj)/$*conf-, cflags libs bin); touch $(obj)/$*conf-bin
$(obj)/%conf-cflags $(obj)/%conf-libs $(obj)/%conf-bin: $(src)/%conf-cfg.sh
$(call cmd,conf_cfg)
"(especially with a larger number of unrolled categories) than the\n"
"default mode.\n"
"\n"
+
+"Search\n"
+"-------\n"
+"Pressing the forward-slash (/) anywhere brings up a search dialog box.\n"
+"\n"
+
"Different color themes available\n"
"--------------------------------\n"
"It is possible to select different color themes using the variable\n"
#!/bin/sh
#
# Output a simple RPM spec file.
-# This version assumes a minimum of RPM 4.0.3.
+# This version assumes a minimum of RPM 4.13
#
# The only gothic bit here is redefining install_post to avoid
# stripping the symbols from files in the kernel which we want
URL: https://www.kernel.org
$S Source: kernel-$__KERNELRELEASE.tar.gz
Provides: $PROVIDES
-$S BuildRequires: bc binutils bison dwarves elfutils-libelf-devel flex
+$S BuildRequires: bc binutils bison dwarves
+$S BuildRequires: (elfutils-libelf-devel or libelf-devel) flex
$S BuildRequires: gcc make openssl openssl-devel perl python3 rsync
# $UTS_MACHINE as a fallback of _arch in case
# (note, if this is a problem with function_graph tracing, then simply
# replace "function" with "function_graph" in the following steps).
#
-# # cd /sys/kernel/debug/tracing
+# # cd /sys/kernel/tracing
# # echo schedule > set_ftrace_filter
# # echo function > current_tracer
#
#
# # echo nop > current_tracer
#
-# # cat available_filter_functions > ~/full-file
+# Starting with v5.1 this can be done with numbers, making it much faster:
+#
+# The old (slow) way, for kernels before v5.1.
+#
+# [old-way] # cat available_filter_functions > ~/full-file
+#
+# [old-way] *** Note *** this process will take several minutes to update the
+# [old-way] filters. Setting multiple functions is an O(n^2) operation, and we
+# [old-way] are dealing with thousands of functions. So go have coffee, talk
+# [old-way] with your coworkers, read facebook. And eventually, this operation
+# [old-way] will end.
+#
+# The new way (using numbers) is an O(n) operation, and usually takes less than a second.
+#
+# seq `wc -l available_filter_functions | cut -d' ' -f1` > ~/full-file
+#
+# This will create a sequence of numbers that match the functions in
+# available_filter_functions, and when echoing in a number into the
+# set_ftrace_filter file, it will enable the corresponding function in
+# O(1) time. Making enabling all functions O(n) where n is the number of
+# functions to enable.
+#
+# For either the new or old way, the rest of the operations remain the same.
+#
# # ftrace-bisect ~/full-file ~/test-file ~/non-test-file
# # cat ~/test-file > set_ftrace_filter
#
-# *** Note *** this will take several minutes. Setting multiple functions is
-# an O(n^2) operation, and we are dealing with thousands of functions. So go
-# have coffee, talk with your coworkers, read facebook. And eventually, this
-# operation will end.
-#
# # echo function > current_tracer
#
# If it crashes, we know that ~/test-file has a bad function.
#
# Reboot back to test kernel.
#
-# # cd /sys/kernel/debug/tracing
+# # cd /sys/kernel/tracing
# # mv ~/test-file ~/full-file
#
# If it didn't crash.
if (!table)
return NULL;
- /* zero init so skip the trap state (state == 0) */
- for (state = 1; state < state_count; state++) {
+ for (state = 0; state < state_count; state++) {
table[state * 2] = compute_fperms_user(dfa, state);
table[state * 2 + 1] = compute_fperms_other(dfa, state);
}
select SECURITYFS
select SECURITY_PATH
select SECURITY_NETWORK
- select SRCU
- select BUILD_BIN2C
default n
help
This selects TOMOYO Linux, pathname-based access control.
Required userspace tools and further information may be
- found at <http://tomoyo.sourceforge.jp/>.
+ found at <https://tomoyo.osdn.jp/>.
If you are unsure how to answer this question, answer N.
config SECURITY_TOMOYO_MAX_ACCEPT_ENTRY
obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load_policy.o memory.o mount.o network.o realpath.o securityfs_if.o tomoyo.o util.o
targets += builtin-policy.h
-define do_policy
-echo "static char tomoyo_builtin_$(1)[] __initdata ="; \
-$(objtree)/scripts/bin2c <$(firstword $(wildcard $(obj)/policy/$(1).conf $(srctree)/$(src)/policy/$(1).conf.default) /dev/null); \
-echo ";"
-endef
-quiet_cmd_policy = POLICY $@
- cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@
-$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE
+quiet_cmd_policy = POLICY $@
+ cmd_policy = { \
+ $(foreach x, profile exception_policy domain_policy manager stat, \
+ printf 'static char tomoyo_builtin_$x[] __initdata =\n'; \
+ sed -e 's/\\/\\\\/g' -e 's/\"/\\"/g' -e 's/\(.*\)/\t"\1\\n"/' -- $(firstword $(filter %/$x.conf %/$x.conf.default, $^) /dev/null); \
+ printf '\t"";\n';) \
+ } > $@
+
+$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE
$(call if_changed,policy)
+ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
$(obj)/common.o: $(obj)/builtin-policy.h
+endif
const u32 pattern = 0xdeadbeef;
int ret;
+ down_read(&card->controls_rwsem);
kctl = snd_ctl_find_id(card, &control->id);
- if (kctl == NULL)
- return -ENOENT;
+ if (kctl == NULL) {
+ ret = -ENOENT;
+ goto unlock;
+ }
index_offset = snd_ctl_get_ioff(kctl, &control->id);
vd = &kctl->vd[index_offset];
- if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL)
- return -EPERM;
+ if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL) {
+ ret = -EPERM;
+ goto unlock;
+ }
snd_ctl_build_ioff(&control->id, kctl, index_offset);
info.id = control->id;
ret = __snd_ctl_elem_info(card, kctl, &info, NULL);
if (ret < 0)
- return ret;
+ goto unlock;
#endif
if (!snd_ctl_skip_validation(&info))
ret = kctl->get(kctl, control);
snd_power_unref(card);
if (ret < 0)
- return ret;
+ goto unlock;
if (!snd_ctl_skip_validation(&info) &&
sanity_check_elem_value(card, control, &info, pattern) < 0) {
dev_err(card->dev,
control->id.iface, control->id.device,
control->id.subdevice, control->id.name,
control->id.index);
- return -EINVAL;
+ ret = -EINVAL;
+ goto unlock;
}
+unlock:
+ up_read(&card->controls_rwsem);
return ret;
}
if (IS_ERR(control))
return PTR_ERR(control);
- down_read(&card->controls_rwsem);
result = snd_ctl_elem_read(card, control);
- up_read(&card->controls_rwsem);
if (result < 0)
goto error;
bool attach)
{
char buf2[256], *s, *os;
- size_t len = max(sizeof(s) - 1, count);
struct snd_ctl_elem_id id;
int err;
- strncpy(buf2, buf, len);
- buf2[len] = '\0';
+ if (strscpy(buf2, buf, sizeof(buf2)) < 0)
+ return -E2BIG;
memset(&id, 0, sizeof(id));
id.iface = SNDRV_CTL_ELEM_IFACE_MIXER;
s = buf2;
struct sg_table *sgt;
void *p;
+#ifdef CONFIG_SND_DMA_SGBUF
+ if (cpu_feature_enabled(X86_FEATURE_XENPV))
+ return snd_dma_sg_fallback_alloc(dmab, size);
+#endif
sgt = dma_alloc_noncontiguous(dmab->dev.dev, size, dmab->dev.dir,
DEFAULT_GFP, 0);
#ifdef CONFIG_SND_DMA_SGBUF
- if (!sgt && !get_dma_ops(dmab->dev.dev)) {
- if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG)
- dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK;
- else
- dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK;
+ if (!sgt && !get_dma_ops(dmab->dev.dev))
return snd_dma_sg_fallback_alloc(dmab, size);
- }
#endif
if (!sgt)
return NULL;
/* Fallback SG-buffer allocations for x86 */
struct snd_dma_sg_fallback {
+ bool use_dma_alloc_coherent;
size_t count;
struct page **pages;
+ /* DMA address array; the first page contains #pages in ~PAGE_MASK */
+ dma_addr_t *addrs;
};
static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab,
struct snd_dma_sg_fallback *sgbuf)
{
- bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK;
- size_t i;
-
- for (i = 0; i < sgbuf->count && sgbuf->pages[i]; i++)
- do_free_pages(page_address(sgbuf->pages[i]), PAGE_SIZE, wc);
+ size_t i, size;
+
+ if (sgbuf->pages && sgbuf->addrs) {
+ i = 0;
+ while (i < sgbuf->count) {
+ if (!sgbuf->pages[i] || !sgbuf->addrs[i])
+ break;
+ size = sgbuf->addrs[i] & ~PAGE_MASK;
+ if (WARN_ON(!size))
+ break;
+ if (sgbuf->use_dma_alloc_coherent)
+ dma_free_coherent(dmab->dev.dev, size << PAGE_SHIFT,
+ page_address(sgbuf->pages[i]),
+ sgbuf->addrs[i] & PAGE_MASK);
+ else
+ do_free_pages(page_address(sgbuf->pages[i]),
+ size << PAGE_SHIFT, false);
+ i += size;
+ }
+ }
kvfree(sgbuf->pages);
+ kvfree(sgbuf->addrs);
kfree(sgbuf);
}
struct snd_dma_sg_fallback *sgbuf;
struct page **pagep, *curp;
size_t chunk, npages;
+ dma_addr_t *addrp;
dma_addr_t addr;
void *p;
- bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK;
+
+ /* correct the type */
+ if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_SG)
+ dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK;
+ else if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG)
+ dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK;
sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL);
if (!sgbuf)
return NULL;
+ sgbuf->use_dma_alloc_coherent = cpu_feature_enabled(X86_FEATURE_XENPV);
size = PAGE_ALIGN(size);
sgbuf->count = size >> PAGE_SHIFT;
sgbuf->pages = kvcalloc(sgbuf->count, sizeof(*sgbuf->pages), GFP_KERNEL);
- if (!sgbuf->pages)
+ sgbuf->addrs = kvcalloc(sgbuf->count, sizeof(*sgbuf->addrs), GFP_KERNEL);
+ if (!sgbuf->pages || !sgbuf->addrs)
goto error;
pagep = sgbuf->pages;
- chunk = size;
+ addrp = sgbuf->addrs;
+ chunk = (PAGE_SIZE - 1) << PAGE_SHIFT; /* to fit in low bits in addrs */
while (size > 0) {
chunk = min(size, chunk);
- p = do_alloc_pages(dmab->dev.dev, chunk, &addr, wc);
+ if (sgbuf->use_dma_alloc_coherent)
+ p = dma_alloc_coherent(dmab->dev.dev, chunk, &addr, DEFAULT_GFP);
+ else
+ p = do_alloc_pages(dmab->dev.dev, chunk, &addr, false);
if (!p) {
if (chunk <= PAGE_SIZE)
goto error;
size -= chunk;
/* fill pages */
npages = chunk >> PAGE_SHIFT;
+ *addrp = npages; /* store in lower bits */
curp = virt_to_page(p);
- while (npages--)
+ while (npages--) {
*pagep++ = curp++;
+ *addrp++ |= addr;
+ addr += PAGE_SIZE;
+ }
}
p = vmap(sgbuf->pages, sgbuf->count, VM_MAP, PAGE_KERNEL);
if (!p)
goto error;
+
+ if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK)
+ set_pages_array_wc(sgbuf->pages, sgbuf->count);
+
dmab->private_data = sgbuf;
/* store the first page address for convenience */
- dmab->addr = snd_sgbuf_get_addr(dmab, 0);
+ dmab->addr = sgbuf->addrs[0] & PAGE_MASK;
return p;
error:
static void snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab)
{
+ struct snd_dma_sg_fallback *sgbuf = dmab->private_data;
+
+ if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK)
+ set_pages_array_wb(sgbuf->pages, sgbuf->count);
vunmap(dmab->area);
__snd_dma_sg_fallback_free(dmab, dmab->private_data);
}
+static dma_addr_t snd_dma_sg_fallback_get_addr(struct snd_dma_buffer *dmab,
+ size_t offset)
+{
+ struct snd_dma_sg_fallback *sgbuf = dmab->private_data;
+ size_t index = offset >> PAGE_SHIFT;
+
+ return (sgbuf->addrs[index] & PAGE_MASK) | (offset & ~PAGE_MASK);
+}
+
static int snd_dma_sg_fallback_mmap(struct snd_dma_buffer *dmab,
struct vm_area_struct *area)
{
.alloc = snd_dma_sg_fallback_alloc,
.free = snd_dma_sg_fallback_free,
.mmap = snd_dma_sg_fallback_mmap,
+ .get_addr = snd_dma_sg_fallback_get_addr,
/* reuse vmalloc helpers */
- .get_addr = snd_dma_vmalloc_get_addr,
.get_page = snd_dma_vmalloc_get_page,
.get_chunk_size = snd_dma_vmalloc_get_chunk_size,
};
return -EFAULT;
count = consumed;
+ } else {
+ spin_unlock_irq(&motu->lock);
+
+ count = 0;
}
return count;
dev_dbg(cs35l41->dev, "System Suspend\n");
if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) {
- dev_err(cs35l41->dev, "System Suspend not supported\n");
- return -EINVAL;
+ dev_err_once(cs35l41->dev, "System Suspend not supported\n");
+ return 0; /* don't block the whole system suspend */
}
ret = pm_runtime_force_suspend(dev);
dev_dbg(cs35l41->dev, "System Resume\n");
if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) {
- dev_err(cs35l41->dev, "System Resume not supported\n");
- return -EINVAL;
+ dev_err_once(cs35l41->dev, "System Resume not supported\n");
+ return 0; /* don't block the whole system resume */
}
if (cs35l41->reset_gpio) {
return ret;
}
+static int cs35l41_runtime_idle(struct device *dev)
+{
+ struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev);
+
+ if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH)
+ return -EBUSY; /* suspend not supported yet on this model */
+ return 0;
+}
+
static int cs35l41_runtime_suspend(struct device *dev)
{
struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev);
EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41);
const struct dev_pm_ops cs35l41_hda_pm_ops = {
- RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume, NULL)
+ RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume,
+ cs35l41_runtime_idle)
SYSTEM_SLEEP_PM_OPS(cs35l41_system_suspend, cs35l41_system_resume)
};
EXPORT_SYMBOL_NS_GPL(cs35l41_hda_pm_ops, SND_HDA_SCODEC_CS35L41);
error:
snd_hda_codec_cleanup_for_unbind(codec);
+ codec->preset = NULL;
return err;
}
if (codec->patch_ops.free)
codec->patch_ops.free(codec);
snd_hda_codec_cleanup_for_unbind(codec);
+ codec->preset = NULL;
module_put(dev->driver->owner);
return 0;
}
snd_array_free(&codec->cvt_setups);
snd_array_free(&codec->spdif_out);
snd_array_free(&codec->verbs);
- codec->preset = NULL;
codec->follower_dig_outs = NULL;
codec->spdif_status_reset = 0;
snd_array_free(&codec->mixers);
codec->depop_delay = -1;
codec->fixup_id = HDA_FIXUP_ID_NOT_SET;
codec->core.dev.release = snd_hda_codec_dev_release;
- codec->core.exec_verb = codec_exec_verb;
codec->core.type = HDA_DEV_LEGACY;
mutex_init(&codec->spdif_mutex);
if (snd_BUG_ON(codec_addr > HDA_MAX_CODEC_ADDRESS))
return -EINVAL;
+ codec->core.exec_verb = codec_exec_verb;
codec->card = card;
codec->addr = codec_addr;
HDA_CODEC_ENTRY(0x14f11f87, "SN6140", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f120d0, "CX11970", patch_conexant_auto),
+ HDA_CODEC_ENTRY(0x14f120d1, "SN6180", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto),
struct hdmi_ops ops;
bool dyn_pin_out;
+ bool static_pcm_mapping;
/* hdmi interrupt trigger control flag for Nvidia codec */
bool hdmi_intr_trig_ctrl;
bool nv_dp_workaround; /* workaround DP audio infoframe for Nvidia */
*/
pcm_jack = pin_idx_to_pcm_jack(codec, per_pin);
- if (eld->eld_valid) {
- hdmi_attach_hda_pcm(spec, per_pin);
- hdmi_pcm_setup_pin(spec, per_pin);
- } else {
- hdmi_pcm_reset_pin(spec, per_pin);
- hdmi_detach_hda_pcm(spec, per_pin);
+ if (!spec->static_pcm_mapping) {
+ if (eld->eld_valid) {
+ hdmi_attach_hda_pcm(spec, per_pin);
+ hdmi_pcm_setup_pin(spec, per_pin);
+ } else {
+ hdmi_pcm_reset_pin(spec, per_pin);
+ hdmi_detach_hda_pcm(spec, per_pin);
+ }
}
+
/* if pcm_idx == -1, it means this is in monitor connection event
* we can get the correct pcm_idx now.
*/
SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),
+ SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1),
SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1),
SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1),
{}
struct hdmi_spec *spec = codec->spec;
int idx, pcm_num;
- /* limit the PCM devices to the codec converters */
- pcm_num = spec->num_cvts;
+ /* limit the PCM devices to the codec converters or available PINs */
+ pcm_num = min(spec->num_cvts, spec->num_pins);
codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num);
for (idx = 0; idx < pcm_num; idx++) {
struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
struct hdmi_eld *pin_eld = &per_pin->sink_eld;
+ if (spec->static_pcm_mapping) {
+ hdmi_attach_hda_pcm(spec, per_pin);
+ hdmi_pcm_setup_pin(spec, per_pin);
+ }
+
pin_eld->eld_valid = false;
hdmi_present_sense(per_pin, 0);
}
spec = codec->spec;
+ spec->static_pcm_mapping = true;
+
spec->ops.pin_get_eld = atihdmi_pin_get_eld;
spec->ops.pin_setup_infoframe = atihdmi_pin_setup_infoframe;
spec->ops.pin_hbr_setup = atihdmi_pin_hbr_setup;
alc_setup_gpio(codec, 0x02);
break;
case 7:
- alc_setup_gpio(codec, 0x03);
+ alc_setup_gpio(codec, 0x04);
break;
case 5:
default:
hda_nid_t hp_pin = alc_get_hp_pin(spec);
bool hp_pin_sense;
+ if (spec->ultra_low_power) {
+ alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1);
+ alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2);
+ alc_update_coef_idx(codec, 0x08, 7<<4, 0);
+ alc_update_coef_idx(codec, 0x3b, 1<<15, 0);
+ alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
+ msleep(30);
+ }
+
if (!hp_pin)
hp_pin = 0x21;
msleep(2);
alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */
- if (spec->ultra_low_power) {
- alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1);
- alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2);
- alc_update_coef_idx(codec, 0x08, 7<<4, 0);
- alc_update_coef_idx(codec, 0x3b, 1<<15, 0);
- alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
- msleep(30);
- }
snd_hda_codec_write(codec, hp_pin, 0,
AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
hda_nid_t hp_pin = alc_get_hp_pin(spec);
bool hp1_pin_sense, hp2_pin_sense;
+ if (spec->ultra_low_power) {
+ alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2);
+ alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
+ alc_update_coef_idx(codec, 0x33, 1<<11, 0);
+ msleep(30);
+ }
+
if (spec->codec_variant != ALC269_TYPE_ALC287 &&
spec->codec_variant != ALC269_TYPE_ALC245)
/* required only at boot or S3 and S4 resume time */
msleep(2);
alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */
- if (spec->ultra_low_power) {
- alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2);
- alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
- alc_update_coef_idx(codec, 0x33, 1<<11, 0);
- msleep(30);
- }
if (hp1_pin_sense || spec->ultra_low_power)
snd_hda_codec_write(codec, hp_pin, 0,
}
}
+static void alc285_fixup_hp_gpio_micmute_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct alc_spec *spec = codec->spec;
+
+ if (action == HDA_FIXUP_ACT_PRE_PROBE)
+ spec->micmute_led_polarity = 1;
+ alc_fixup_hp_gpio_led(codec, action, 0, 0x04);
+}
+
static void alc236_fixup_hp_coef_micmute_led(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
alc285_fixup_hp_coef_micmute_led(codec, fix, action);
}
+static void alc285_fixup_hp_spectre_x360_mute_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ alc285_fixup_hp_mute_led_coefbit(codec, fix, action);
+ alc285_fixup_hp_gpio_micmute_led(codec, fix, action);
+}
+
static void alc236_fixup_hp_mute_led(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
ALC285_FIXUP_ASUS_G533Z_PINS,
ALC285_FIXUP_HP_GPIO_LED,
ALC285_FIXUP_HP_MUTE_LED,
+ ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED,
ALC236_FIXUP_HP_GPIO_LED,
ALC236_FIXUP_HP_MUTE_LED,
ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF,
ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK,
ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN,
ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS,
+ ALC236_FIXUP_DELL_DUAL_CODECS,
};
/* A special fixup for Lenovo C940 and Yoga Duet 7;
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_mute_led,
},
+ [ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_hp_spectre_x360_mute_led,
+ },
[ALC236_FIXUP_HP_GPIO_LED] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc236_fixup_hp_gpio_led,
.chained = true,
.chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
},
+ [ALC236_FIXUP_DELL_DUAL_CODECS] = {
+ .type = HDA_FIXUP_PINS,
+ .v.func = alc1220_fixup_gb_dual_codecs,
+ .chained = true,
+ .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1025, 0x142b, "Acer Swift SF314-42", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC),
+ SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X),
SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS),
SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK),
SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
+ SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
+ SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
+ SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
+ SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
+ SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
+ SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO),
SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
+ SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x89c3, "Zbook Studio G9", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+ SND_PCI_QUIRK(0x103c, 0x89d3, "HP EliteBook 645 G9 (MB 89D2)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x103c, 0x8aa0, "HP ProBook 440 G9 (MB 8A9E)", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b45, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b46, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+ SND_PCI_QUIRK(0x103c, 0x8b7a, "HP", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b7d, "HP", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b87, "HP", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b8a, "HP", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b8b, "HP", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b8d, "HP", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
+ SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_AMP),
SND_PCI_QUIRK(0x144d, 0xc830, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_AMP),
SND_PCI_QUIRK(0x144d, 0xc832, "Samsung Galaxy Book Flex Alpha (NP730QCJ)", ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET),
+ SND_PCI_QUIRK(0x144d, 0xca03, "Samsung Galaxy Book2 Pro 360 (NP930QED)", ALC298_FIXUP_SAMSUNG_AMP),
SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802),
SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X),
+ SND_PCI_QUIRK(0x1c6c, 0x1251, "Positivo N14KP6-TG", ALC288_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS),
SND_PCI_QUIRK(0x1d05, 0x1096, "TongFang GMxMRxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x1100, "TongFang GKxNRxx", ALC269_FIXUP_NO_SHUTUP),
return 0;
nums = snd_hda_get_connections(codec, spec->gen.mixer_nid, conn,
ARRAY_SIZE(conn) - 1);
+ if (nums < 0)
+ return nums;
+
for (i = 0; i < nums; i++) {
if (get_wcaps_type(get_wcaps(codec, conn[i])) == AC_WID_AUD_OUT)
return 0;
dev_dbg(chip->card->dev,
"CMD_08_ASK_BUFFERS: needed %d, freed %d\n",
*r_needed, *r_freed);
- for (i = 0; i < MAX_STREAM_BUFFER; ++i) {
- for (i = 0; i != chip->rmh.stat_len; ++i)
- dev_dbg(chip->card->dev,
- " stat[%d]: %x, %x\n", i,
- chip->rmh.stat[i],
- chip->rmh.stat[i] & MASK_DATA_SIZE);
+ for (i = 0; i < MAX_STREAM_BUFFER && i < chip->rmh.stat_len;
+ ++i) {
+ dev_dbg(chip->card->dev, " stat[%d]: %x, %x\n", i,
+ chip->rmh.stat[i],
+ chip->rmh.stat[i] & MASK_DATA_SIZE);
}
}
int ret;
adev = acpi_dev_get_first_match_dev("ESSX8336", NULL, -1);
- if (adev)
- put_device(&adev->dev);
+ if (!adev)
+ return -ENODEV;
+
codec_dev = acpi_get_first_physical_node(adev);
+ acpi_dev_put(adev);
if (!codec_dev)
dev_err(card->dev, "can not find codec dev\n");
DMI_MATCH(DMI_PRODUCT_NAME, "UM5302TA"),
}
},
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "M5402RA"),
+ }
+ },
{
.driver_data = &acp6x_card,
.matches = {
DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 14 2022"),
}
},
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "TIMI"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 15 2022"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Razer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Blade 14 (2022) - RZ09-0427"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "RB"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Swift SFA16-41"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "IRBIS"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "15NBC1011"),
+ }
+ },
{}
};
if (pdata) {
cs42l56->pdata = *pdata;
} else {
- pdata = devm_kzalloc(&i2c_client->dev, sizeof(*pdata),
- GFP_KERNEL);
- if (!pdata)
- return -ENOMEM;
-
if (i2c_client->dev.of_node) {
ret = cs42l56_handle_of_data(i2c_client,
&cs42l56->pdata);
if (ret != 0)
return ret;
}
- cs42l56->pdata = *pdata;
}
if (cs42l56->pdata.gpio_nreset) {
}
dev_dbg(component->dev, "jack-pol %x", es8326->jack_pol);
- ret = device_property_read_u8(component->dev, "everest,interrupt-src", &es8326->jack_pol);
+ ret = device_property_read_u8(component->dev, "everest,interrupt-src",
+ &es8326->interrupt_src);
if (ret != 0) {
dev_dbg(component->dev, "interrupt-src return %d", ret);
es8326->interrupt_src = ES8326_HP_DET_SRC_PIN9;
}
dev_dbg(component->dev, "interrupt-src %x", es8326->interrupt_src);
- ret = device_property_read_u8(component->dev, "everest,interrupt-clk", &es8326->jack_pol);
+ ret = device_property_read_u8(component->dev, "everest,interrupt-clk",
+ &es8326->interrupt_clk);
if (ret != 0) {
dev_dbg(component->dev, "interrupt-clk return %d", ret);
es8326->interrupt_clk = 0x45;
}
/* set the timeout values */
- prop->clk_stop_timeout = 20;
+ prop->clk_stop_timeout = 200;
return 0;
}
return 0;
}
+static int rt9120_codec_suspend(struct snd_soc_component *comp)
+{
+ return pm_runtime_force_suspend(comp->dev);
+}
+
+static int rt9120_codec_resume(struct snd_soc_component *comp)
+{
+ return pm_runtime_force_resume(comp->dev);
+}
+
static const struct snd_soc_component_driver rt9120_component_driver = {
.probe = rt9120_codec_probe,
+ .suspend = rt9120_codec_suspend,
+ .resume = rt9120_codec_resume,
.controls = rt9120_snd_controls,
.num_controls = ARRAY_SIZE(rt9120_snd_controls),
.dapm_widgets = rt9120_dapm_widgets,
#define TAS5805M_VOLUME_MIN 0
struct tas5805m_priv {
+ struct i2c_client *i2c;
struct regulator *pvdd;
struct gpio_desc *gpio_pdn_n;
int vol[2];
bool is_powered;
bool is_muted;
+
+ struct work_struct work;
+ struct mutex lock;
};
static void set_dsp_scale(struct regmap *rm, int offset, int vol)
regmap_bulk_write(rm, offset, v, ARRAY_SIZE(v));
}
-static void tas5805m_refresh(struct snd_soc_component *component)
+static void tas5805m_refresh(struct tas5805m_priv *tas5805m)
{
- struct tas5805m_priv *tas5805m =
- snd_soc_component_get_drvdata(component);
struct regmap *rm = tas5805m->regmap;
- dev_dbg(component->dev, "refresh: is_muted=%d, vol=%d/%d\n",
+ dev_dbg(&tas5805m->i2c->dev, "refresh: is_muted=%d, vol=%d/%d\n",
tas5805m->is_muted, tas5805m->vol[0], tas5805m->vol[1]);
regmap_write(rm, REG_PAGE, 0x00);
set_dsp_scale(rm, 0x24, tas5805m->vol[0]);
set_dsp_scale(rm, 0x28, tas5805m->vol[1]);
+ regmap_write(rm, REG_PAGE, 0x00);
+ regmap_write(rm, REG_BOOK, 0x00);
+
/* Set/clear digital soft-mute */
regmap_write(rm, REG_DEVICE_CTRL_2,
(tas5805m->is_muted ? DCTRL2_MUTE : 0) |
struct tas5805m_priv *tas5805m =
snd_soc_component_get_drvdata(component);
+ mutex_lock(&tas5805m->lock);
ucontrol->value.integer.value[0] = tas5805m->vol[0];
ucontrol->value.integer.value[1] = tas5805m->vol[1];
+ mutex_unlock(&tas5805m->lock);
+
return 0;
}
snd_soc_kcontrol_component(kcontrol);
struct tas5805m_priv *tas5805m =
snd_soc_component_get_drvdata(component);
+ int ret = 0;
if (!(volume_is_valid(ucontrol->value.integer.value[0]) &&
volume_is_valid(ucontrol->value.integer.value[1])))
return -EINVAL;
+ mutex_lock(&tas5805m->lock);
if (tas5805m->vol[0] != ucontrol->value.integer.value[0] ||
tas5805m->vol[1] != ucontrol->value.integer.value[1]) {
tas5805m->vol[0] = ucontrol->value.integer.value[0];
tas5805m->vol[0], tas5805m->vol[1],
tas5805m->is_powered);
if (tas5805m->is_powered)
- tas5805m_refresh(component);
- return 1;
+ tas5805m_refresh(tas5805m);
+ ret = 1;
}
+ mutex_unlock(&tas5805m->lock);
- return 0;
+ return ret;
}
static const struct snd_kcontrol_new tas5805m_snd_controls[] = {
struct snd_soc_component *component = dai->component;
struct tas5805m_priv *tas5805m =
snd_soc_component_get_drvdata(component);
- struct regmap *rm = tas5805m->regmap;
- unsigned int chan, global1, global2;
switch (cmd) {
case SNDRV_PCM_TRIGGER_START:
case SNDRV_PCM_TRIGGER_RESUME:
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
- dev_dbg(component->dev, "DSP startup\n");
-
- /* We mustn't issue any I2C transactions until the I2S
- * clock is stable. Furthermore, we must allow a 5ms
- * delay after the first set of register writes to
- * allow the DSP to boot before configuring it.
- */
- usleep_range(5000, 10000);
- send_cfg(rm, dsp_cfg_preboot,
- ARRAY_SIZE(dsp_cfg_preboot));
- usleep_range(5000, 15000);
- send_cfg(rm, tas5805m->dsp_cfg_data,
- tas5805m->dsp_cfg_len);
-
- tas5805m->is_powered = true;
- tas5805m_refresh(component);
+ dev_dbg(component->dev, "clock start\n");
+ schedule_work(&tas5805m->work);
break;
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
- dev_dbg(component->dev, "DSP shutdown\n");
+ break;
- tas5805m->is_powered = false;
+ default:
+ return -EINVAL;
+ }
- regmap_write(rm, REG_PAGE, 0x00);
- regmap_write(rm, REG_BOOK, 0x00);
+ return 0;
+}
- regmap_read(rm, REG_CHAN_FAULT, &chan);
- regmap_read(rm, REG_GLOBAL_FAULT1, &global1);
- regmap_read(rm, REG_GLOBAL_FAULT2, &global2);
+static void do_work(struct work_struct *work)
+{
+ struct tas5805m_priv *tas5805m =
+ container_of(work, struct tas5805m_priv, work);
+ struct regmap *rm = tas5805m->regmap;
- dev_dbg(component->dev,
- "fault regs: CHAN=%02x, GLOBAL1=%02x, GLOBAL2=%02x\n",
- chan, global1, global2);
+ dev_dbg(&tas5805m->i2c->dev, "DSP startup\n");
- regmap_write(rm, REG_DEVICE_CTRL_2, DCTRL2_MODE_HIZ);
- break;
+ mutex_lock(&tas5805m->lock);
+ /* We mustn't issue any I2C transactions until the I2S
+ * clock is stable. Furthermore, we must allow a 5ms
+ * delay after the first set of register writes to
+ * allow the DSP to boot before configuring it.
+ */
+ usleep_range(5000, 10000);
+ send_cfg(rm, dsp_cfg_preboot, ARRAY_SIZE(dsp_cfg_preboot));
+ usleep_range(5000, 15000);
+ send_cfg(rm, tas5805m->dsp_cfg_data, tas5805m->dsp_cfg_len);
+
+ tas5805m->is_powered = true;
+ tas5805m_refresh(tas5805m);
+ mutex_unlock(&tas5805m->lock);
+}
- default:
- return -EINVAL;
+static int tas5805m_dac_event(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+ struct tas5805m_priv *tas5805m =
+ snd_soc_component_get_drvdata(component);
+ struct regmap *rm = tas5805m->regmap;
+
+ if (event & SND_SOC_DAPM_PRE_PMD) {
+ unsigned int chan, global1, global2;
+
+ dev_dbg(component->dev, "DSP shutdown\n");
+ cancel_work_sync(&tas5805m->work);
+
+ mutex_lock(&tas5805m->lock);
+ if (tas5805m->is_powered) {
+ tas5805m->is_powered = false;
+
+ regmap_write(rm, REG_PAGE, 0x00);
+ regmap_write(rm, REG_BOOK, 0x00);
+
+ regmap_read(rm, REG_CHAN_FAULT, &chan);
+ regmap_read(rm, REG_GLOBAL_FAULT1, &global1);
+ regmap_read(rm, REG_GLOBAL_FAULT2, &global2);
+
+ dev_dbg(component->dev, "fault regs: CHAN=%02x, "
+ "GLOBAL1=%02x, GLOBAL2=%02x\n",
+ chan, global1, global2);
+
+ regmap_write(rm, REG_DEVICE_CTRL_2, DCTRL2_MODE_HIZ);
+ }
+ mutex_unlock(&tas5805m->lock);
}
return 0;
static const struct snd_soc_dapm_widget tas5805m_dapm_widgets[] = {
SND_SOC_DAPM_AIF_IN("DAC IN", "Playback", 0, SND_SOC_NOPM, 0, 0),
- SND_SOC_DAPM_DAC("DAC", NULL, SND_SOC_NOPM, 0, 0),
+ SND_SOC_DAPM_DAC_E("DAC", NULL, SND_SOC_NOPM, 0, 0,
+ tas5805m_dac_event, SND_SOC_DAPM_PRE_PMD),
SND_SOC_DAPM_OUTPUT("OUT")
};
struct tas5805m_priv *tas5805m =
snd_soc_component_get_drvdata(component);
+ mutex_lock(&tas5805m->lock);
dev_dbg(component->dev, "set mute=%d (is_powered=%d)\n",
mute, tas5805m->is_powered);
+
tas5805m->is_muted = mute;
if (tas5805m->is_powered)
- tas5805m_refresh(component);
+ tas5805m_refresh(tas5805m);
+ mutex_unlock(&tas5805m->lock);
return 0;
}
if (!tas5805m)
return -ENOMEM;
+ tas5805m->i2c = i2c;
tas5805m->pvdd = devm_regulator_get(dev, "pvdd");
if (IS_ERR(tas5805m->pvdd)) {
dev_err(dev, "failed to get pvdd supply: %ld\n",
gpiod_set_value(tas5805m->gpio_pdn_n, 1);
usleep_range(10000, 15000);
+ INIT_WORK(&tas5805m->work, do_work);
+ mutex_init(&tas5805m->lock);
+
/* Don't register through devm. We need to be able to unregister
* the component prior to deasserting PDN#
*/
struct device *dev = &i2c->dev;
struct tas5805m_priv *tas5805m = dev_get_drvdata(dev);
+ cancel_work_sync(&tas5805m->work);
snd_soc_unregister_component(dev);
gpiod_set_value(tas5805m->gpio_pdn_n, 0);
usleep_range(10000, 15000);
int dcs_mask;
int dcs_l, dcs_r;
int dcs_l_reg, dcs_r_reg;
+ int an_out_reg;
int timeout;
int pwr_reg;
dcs_mask = WM8904_DCS_ENA_CHAN_0 | WM8904_DCS_ENA_CHAN_1;
dcs_r_reg = WM8904_DC_SERVO_8;
dcs_l_reg = WM8904_DC_SERVO_9;
+ an_out_reg = WM8904_ANALOGUE_OUT1_LEFT;
dcs_l = 0;
dcs_r = 1;
break;
dcs_mask = WM8904_DCS_ENA_CHAN_2 | WM8904_DCS_ENA_CHAN_3;
dcs_r_reg = WM8904_DC_SERVO_6;
dcs_l_reg = WM8904_DC_SERVO_7;
+ an_out_reg = WM8904_ANALOGUE_OUT2_LEFT;
dcs_l = 2;
dcs_r = 3;
break;
snd_soc_component_update_bits(component, reg,
WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP,
WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP);
+
+ /* Update volume, requires PGA to be powered */
+ val = snd_soc_component_read(component, an_out_reg);
+ snd_soc_component_write(component, an_out_reg, val);
break;
case SND_SOC_DAPM_POST_PMU:
.stream_name = "SPKR Playback",
.rates = WSA883X_RATES | WSA883X_FRAC_RATES,
.formats = WSA883X_FORMATS,
- .rate_max = 8000,
- .rate_min = 352800,
+ .rate_min = 8000,
+ .rate_max = 352800,
.channels_min = 1,
.channels_max = 1,
},
static const struct snd_soc_dapm_route audio_map_ac97[] = {
/* 1st half -- Normal DAPM routes */
- {"Playback", NULL, "AC97 Playback"},
- {"AC97 Capture", NULL, "Capture"},
+ {"AC97 Playback", NULL, "CPU AC97 Playback"},
+ {"CPU AC97 Capture", NULL, "AC97 Capture"},
/* 2nd half -- ASRC DAPM routes */
- {"AC97 Playback", NULL, "ASRC-Playback"},
- {"ASRC-Capture", NULL, "AC97 Capture"},
+ {"CPU AC97 Playback", NULL, "ASRC-Playback"},
+ {"ASRC-Capture", NULL, "CPU AC97 Capture"},
};
static const struct snd_soc_dapm_route audio_map_tx[] = {
static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = {
SOC_SINGLE_SX_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(0), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(0), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(1), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(1), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH2 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(2), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(2), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH3 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(3), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(3), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH4 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(4), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(4), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH5 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(5), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(5), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH6 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(6), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(6), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(7), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(7), 0x8, 0xF, gain_tlv),
SOC_ENUM_EXT("MICFIL Quality Select",
fsl_micfil_quality_enum,
micfil_quality_get, micfil_quality_set),
sai->verid.version = val &
(FSL_SAI_VERID_MAJOR_MASK | FSL_SAI_VERID_MINOR_MASK);
+ sai->verid.version >>= FSL_SAI_VERID_MINOR_SHIFT;
sai->verid.feature = val & FSL_SAI_VERID_FEATURE_MASK;
ret = regmap_read(sai->regmap, FSL_SAI_PARAM, &val);
.symmetric_channels = 1,
.probe = fsl_ssi_dai_probe,
.playback = {
- .stream_name = "AC97 Playback",
+ .stream_name = "CPU AC97 Playback",
.channels_min = 2,
.channels_max = 2,
.rates = SNDRV_PCM_RATE_8000_48000,
.formats = SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S20,
},
.capture = {
- .stream_name = "AC97 Capture",
+ .stream_name = "CPU AC97 Capture",
.channels_min = 2,
.channels_max = 2,
.rates = SNDRV_PCM_RATE_48000,
return ret;
}
+static void avs_pci_shutdown(struct pci_dev *pci)
+{
+ struct hdac_bus *bus = pci_get_drvdata(pci);
+ struct avs_dev *adev = hdac_to_avs(bus);
+
+ cancel_work_sync(&adev->probe_work);
+ avs_ipc_block(adev->ipc);
+
+ snd_hdac_stop_streams(bus);
+ avs_dsp_op(adev, int_control, false);
+ snd_hdac_ext_bus_ppcap_int_enable(bus, false);
+ snd_hdac_ext_bus_link_power_down_all(bus);
+
+ snd_hdac_bus_stop_chip(bus);
+ snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false);
+
+ if (avs_platattr_test(adev, CLDMA))
+ pci_free_irq(pci, 0, &code_loader);
+ pci_free_irq(pci, 0, adev);
+ pci_free_irq(pci, 0, bus);
+ pci_free_irq_vectors(pci);
+}
+
static void avs_pci_remove(struct pci_dev *pci)
{
struct hdac_device *hdev, *save;
.id_table = avs_ids,
.probe = avs_pci_probe,
.remove = avs_pci_remove,
+ .shutdown = avs_pci_shutdown,
.driver = {
.pm = &avs_dev_pm,
},
select SND_SOC_RT1015P
select SND_SOC_MAX98373_I2C
select SND_SOC_MAX98357A
+ select SND_SOC_NAU8315
select SND_SOC_DMIC
select SND_SOC_HDAC_HDMI
select SND_SOC_INTEL_HDA_DSP_COMMON
select SND_SOC_INTEL_SOF_MAXIM_COMMON
+ select SND_SOC_INTEL_SOF_REALTEK_COMMON
help
This adds support for ASoC machine driver for SOF platforms
with nau8825 codec.
if (adev) {
snprintf(codec_name, sizeof(codec_name),
"i2c-%s", acpi_dev_name(adev));
- put_device(&adev->dev);
byt_cht_es8316_dais[dai_index].codecs->name = codec_name;
} else {
dev_err(dev, "Error cannot find '%s' dev\n", mach->id);
return -ENXIO;
}
+ codec_dev = acpi_get_first_physical_node(adev);
+ acpi_dev_put(adev);
+ if (!codec_dev)
+ return -EPROBE_DEFER;
+ priv->codec_dev = get_device(codec_dev);
+
/* override platform name, if required */
byt_cht_es8316_card.dev = dev;
platform_name = mach->mach_params.platform;
ret = snd_soc_fixup_dai_links_platform_name(&byt_cht_es8316_card,
platform_name);
- if (ret)
+ if (ret) {
+ put_device(codec_dev);
return ret;
+ }
/* Check for BYTCR or other platform and setup quirks */
dmi_id = dmi_first_match(byt_cht_es8316_quirk_table);
/* get the clock */
priv->mclk = devm_clk_get(dev, "pmc_plt_clk_3");
- if (IS_ERR(priv->mclk))
+ if (IS_ERR(priv->mclk)) {
+ put_device(codec_dev);
return dev_err_probe(dev, PTR_ERR(priv->mclk), "clk_get pmc_plt_clk_3 failed\n");
-
- codec_dev = acpi_get_first_physical_node(adev);
- if (!codec_dev)
- return -EPROBE_DEFER;
- priv->codec_dev = get_device(codec_dev);
+ }
if (quirk & BYT_CHT_ES8316_JD_INVERTED)
props[cnt++] = PROPERTY_ENTRY_BOOL("everest,jack-detect-inverted");
if (adev) {
snprintf(byt_rt5640_codec_name, sizeof(byt_rt5640_codec_name),
"i2c-%s", acpi_dev_name(adev));
- put_device(&adev->dev);
byt_rt5640_dais[dai_index].codecs->name = byt_rt5640_codec_name;
} else {
dev_err(dev, "Error cannot find '%s' dev\n", mach->id);
return -ENXIO;
}
+ codec_dev = acpi_get_first_physical_node(adev);
+ acpi_dev_put(adev);
+ if (!codec_dev)
+ return -EPROBE_DEFER;
+ priv->codec_dev = get_device(codec_dev);
+
/*
* swap SSP0 if bytcr is detected
* (will be overridden if DMI quirk is detected)
byt_rt5640_quirk = quirk_override;
}
- codec_dev = acpi_get_first_physical_node(adev);
- if (!codec_dev)
- return -EPROBE_DEFER;
- priv->codec_dev = get_device(codec_dev);
-
if (byt_rt5640_quirk & BYT_RT5640_JD_HP_ELITEP_1000G2) {
acpi_dev_add_driver_gpios(ACPI_COMPANION(priv->codec_dev),
byt_rt5640_hp_elitepad_1000g2_gpios);
if (adev) {
snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name),
"i2c-%s", acpi_dev_name(adev));
- put_device(&adev->dev);
byt_rt5651_dais[dai_index].codecs->name = byt_rt5651_codec_name;
} else {
dev_err(dev, "Error cannot find '%s' dev\n", mach->id);
}
codec_dev = acpi_get_first_physical_node(adev);
+ acpi_dev_put(adev);
if (!codec_dev)
return -EPROBE_DEFER;
priv->codec_dev = get_device(codec_dev);
return -ENOENT;
}
snprintf(codec_name, sizeof(codec_name), "spi-%s", acpi_dev_name(adev));
- put_device(&adev->dev);
codec_dev = bus_find_device_by_name(&spi_bus_type, NULL, codec_name);
+ acpi_dev_put(adev);
if (!codec_dev)
return -EPROBE_DEFER;
links[*id].platforms = platform_component;
links[*id].num_platforms = ARRAY_SIZE(platform_component);
links[*id].dpcm_playback = 1;
+ /* firmware-generated echo reference */
+ links[*id].dpcm_capture = 1;
+
links[*id].no_pcm = 1;
links[*id].cpus = &cpus[*id];
links[*id].num_cpus = 1;
if (adev) {
snprintf(codec_name, sizeof(codec_name),
"i2c-%s", acpi_dev_name(adev));
- put_device(&adev->dev);
dai_links[0].codecs->name = codec_name;
/* also fixup codec dai name if relevant */
return -ENXIO;
}
- ret = snd_soc_fixup_dai_links_platform_name(&sof_es8336_card,
- mach->mach_params.platform);
- if (ret)
- return ret;
-
codec_dev = acpi_get_first_physical_node(adev);
+ acpi_dev_put(adev);
if (!codec_dev)
return -EPROBE_DEFER;
priv->codec_dev = get_device(codec_dev);
+ ret = snd_soc_fixup_dai_links_platform_name(&sof_es8336_card,
+ mach->mach_params.platform);
+ if (ret) {
+ put_device(codec_dev);
+ return ret;
+ }
+
if (quirk & SOF_ES8336_JD_INVERTED)
props[cnt++] = PROPERTY_ENTRY_BOOL("everest,jack-detect-inverted");
#define SOF_MAX98373_SPEAKER_AMP_PRESENT BIT(15)
#define SOF_MAX98360A_SPEAKER_AMP_PRESENT BIT(16)
#define SOF_RT1015P_SPEAKER_AMP_PRESENT BIT(17)
+#define SOF_NAU8318_SPEAKER_AMP_PRESENT BIT(18)
static unsigned long sof_nau8825_quirk = SOF_NAU8825_SSP_CODEC(0);
}
};
+static struct snd_soc_dai_link_component nau8318_components[] = {
+ {
+ .name = "NVTN2012:00",
+ .dai_name = "nau8315-hifi",
+ }
+};
+
static struct snd_soc_dai_link_component dummy_component[] = {
{
.name = "snd-soc-dummy",
links[id].num_codecs = ARRAY_SIZE(max_98373_components);
links[id].init = max_98373_spk_codec_init;
links[id].ops = &max_98373_ops;
- /* feedback stream */
- links[id].dpcm_capture = 1;
} else if (sof_nau8825_quirk &
SOF_MAX98360A_SPEAKER_AMP_PRESENT) {
max_98360a_dai_link(&links[id]);
} else if (sof_nau8825_quirk & SOF_RT1015P_SPEAKER_AMP_PRESENT) {
sof_rt1015p_dai_link(&links[id]);
+ } else if (sof_nau8825_quirk &
+ SOF_NAU8318_SPEAKER_AMP_PRESENT) {
+ links[id].codecs = nau8318_components;
+ links[id].num_codecs = ARRAY_SIZE(nau8318_components);
+ links[id].init = speaker_codec_init;
} else {
goto devm_err;
}
links[id].platforms = platform_component;
links[id].num_platforms = ARRAY_SIZE(platform_component);
links[id].dpcm_playback = 1;
+ /* feedback stream or firmware-generated echo reference */
+ links[id].dpcm_capture = 1;
+
links[id].no_pcm = 1;
links[id].cpus = &cpus[id];
links[id].num_cpus = 1;
},
{
- .name = "adl_rt1019p_nau8825",
+ .name = "adl_rt1019p_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_RT1019P_SPEAKER_AMP_PRESENT |
SOF_NAU8825_NUM_HDMIDEV(4)),
},
{
- .name = "adl_max98373_nau8825",
+ .name = "adl_max98373_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_MAX98373_SPEAKER_AMP_PRESENT |
},
{
/* The limitation of length of char array, shorten the name */
- .name = "adl_mx98360a_nau8825",
+ .name = "adl_mx98360a_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_MAX98360A_SPEAKER_AMP_PRESENT |
},
{
- .name = "adl_rt1015p_nau8825",
+ .name = "adl_rt1015p_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_RT1015P_SPEAKER_AMP_PRESENT |
SOF_BT_OFFLOAD_SSP(2) |
SOF_SSP_BT_OFFLOAD_PRESENT),
},
+ {
+ .name = "adl_nau8318_8825",
+ .driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
+ SOF_SPEAKER_AMP_PRESENT |
+ SOF_NAU8318_SPEAKER_AMP_PRESENT |
+ SOF_NAU8825_SSP_AMP(1) |
+ SOF_NAU8825_NUM_HDMIDEV(4) |
+ SOF_BT_OFFLOAD_SSP(2) |
+ SOF_SSP_BT_OFFLOAD_PRESENT),
+ },
{ }
};
MODULE_DEVICE_TABLE(platform, board_ids);
links[id].num_codecs = ARRAY_SIZE(max_98373_components);
links[id].init = max_98373_spk_codec_init;
links[id].ops = &max_98373_ops;
- /* feedback stream */
- links[id].dpcm_capture = 1;
} else if (sof_rt5682_quirk &
SOF_MAX98360A_SPEAKER_AMP_PRESENT) {
max_98360a_dai_link(&links[id]);
links[id].platforms = platform_component;
links[id].num_platforms = ARRAY_SIZE(platform_component);
links[id].dpcm_playback = 1;
+ /* feedback stream or firmware-generated echo reference */
+ links[id].dpcm_capture = 1;
+
links[id].no_pcm = 1;
links[id].cpus = &cpus[id];
links[id].num_cpus = 1;
sof_rt1308_dai_link(&links[id]);
} else if (sof_ssp_amp_quirk & SOF_CS35L41_SPEAKER_AMP_PRESENT) {
cs35l41_set_dai_link(&links[id]);
-
- /* feedback from amplifier */
- links[id].dpcm_capture = 1;
}
links[id].platforms = platform_component;
links[id].num_platforms = ARRAY_SIZE(platform_component);
links[id].dpcm_playback = 1;
+ /* feedback from amplifier or firmware-generated echo reference */
+ links[id].dpcm_capture = 1;
links[id].no_pcm = 1;
links[id].cpus = &cpus[id];
links[id].num_cpus = 1;
.codecs = {"INTC10B0"}
};
+static const struct snd_soc_acpi_codecs adl_nau8318_amp = {
+ .num_codecs = 1,
+ .codecs = {"NVTN2012"}
+};
+
struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = {
{
.comp_ids = &adl_rt5682_rt5682s_hp,
},
{
.id = "10508825",
- .drv_name = "adl_rt1019p_nau8825",
+ .drv_name = "adl_rt1019p_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_rt1019p_amp,
.sof_tplg_filename = "sof-adl-rt1019-nau8825.tplg",
},
{
.id = "10508825",
- .drv_name = "adl_max98373_nau8825",
+ .drv_name = "adl_max98373_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_max98373_amp,
.sof_tplg_filename = "sof-adl-max98373-nau8825.tplg",
},
{
.id = "10508825",
- .drv_name = "adl_mx98360a_nau8825",
+ .drv_name = "adl_mx98360a_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_max98360a_amp,
.sof_tplg_filename = "sof-adl-max98360a-nau8825.tplg",
},
{
.id = "10508825",
- .drv_name = "adl_rt1015p_nau8825",
+ .drv_name = "adl_rt1015p_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_rt1015p_amp,
.sof_tplg_filename = "sof-adl-rt1015-nau8825.tplg",
},
+ {
+ .id = "10508825",
+ .drv_name = "adl_nau8318_8825",
+ .machine_quirk = snd_soc_acpi_codec_list,
+ .quirk_data = &adl_nau8318_amp,
+ .sof_tplg_filename = "sof-adl-nau8318-nau8825.tplg",
+ },
{
.id = "10508825",
.drv_name = "sof_nau8825",
{}
};
+static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link2_rt1316_link01[] = {
+ {
+ .mask = BIT(2),
+ .num_adr = ARRAY_SIZE(rt711_sdca_2_adr),
+ .adr_d = rt711_sdca_2_adr,
+ },
+ {
+ .mask = BIT(0),
+ .num_adr = ARRAY_SIZE(rt1316_0_group2_adr),
+ .adr_d = rt1316_0_group2_adr,
+ },
+ {
+ .mask = BIT(1),
+ .num_adr = ARRAY_SIZE(rt1316_1_group2_adr),
+ .adr_d = rt1316_1_group2_adr,
+ },
+ {}
+};
+
static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12_rt714_link3[] = {
{
.mask = BIT(0),
{}
};
+static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12[] = {
+ {
+ .mask = BIT(0),
+ .num_adr = ARRAY_SIZE(rt711_sdca_0_adr),
+ .adr_d = rt711_sdca_0_adr,
+ },
+ {
+ .mask = BIT(1),
+ .num_adr = ARRAY_SIZE(rt1318_1_group1_adr),
+ .adr_d = rt1318_1_group1_adr,
+ },
+ {
+ .mask = BIT(2),
+ .num_adr = ARRAY_SIZE(rt1318_2_group1_adr),
+ .adr_d = rt1318_2_group1_adr,
+ },
+ {}
+};
+
static const struct snd_soc_acpi_link_adr rpl_sdw_rt1316_link12_rt714_link0[] = {
{
.mask = BIT(1),
.drv_name = "sof_sdw",
.sof_tplg_filename = "sof-rpl-rt711-l0-rt1318-l12-rt714-l3.tplg",
},
+ {
+ .link_mask = 0x7, /* rt711 on link0 & two rt1318s on link1 and link2 */
+ .links = rpl_sdw_rt711_link0_rt1318_link12,
+ .drv_name = "sof_sdw",
+ .sof_tplg_filename = "sof-rpl-rt711-l0-rt1318-l12.tplg",
+ },
{
.link_mask = 0x7, /* rt714 on link0 & two rt1316s on link1 and link2 */
.links = rpl_sdw_rt1316_link12_rt714_link0,
.drv_name = "sof_sdw",
.sof_tplg_filename = "sof-rpl-rt1316-l12-rt714-l0.tplg",
},
+ {
+ .link_mask = 0x7, /* rt711 on link2 & two rt1316s on link0 and link1 */
+ .links = rpl_sdw_rt711_link2_rt1316_link01,
+ .drv_name = "sof_sdw",
+ .sof_tplg_filename = "sof-rpl-rt711-l2-rt1316-l01.tplg",
+ },
{
.link_mask = 0x1, /* link0 required */
.links = rpl_rvp,
If unsure select "N".
config SND_SOC_MT8186_MT6366_RT1019_RT5682S
- tristate "ASoC Audio driver for MT8186 with RT1019 RT5682S codec"
+ tristate "ASoC Audio driver for MT8186 with RT1019 RT5682S MAX98357A/MAX98360 codec"
depends on I2C && GPIOLIB
depends on SND_SOC_MT8186 && MTK_PMIC_WRAP
+ select SND_SOC_MAX98357A
select SND_SOC_MT6358
+ select SND_SOC_MAX98357A
select SND_SOC_RT1015P
select SND_SOC_RT5682S
select SND_SOC_BT_SCO
.num_configs = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_codec_conf),
};
+static struct snd_soc_card mt8186_mt6366_rt5682s_max98360_soc_card = {
+ .name = "mt8186_rt5682s_max98360",
+ .owner = THIS_MODULE,
+ .dai_link = mt8186_mt6366_rt1019_rt5682s_dai_links,
+ .num_links = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_dai_links),
+ .controls = mt8186_mt6366_rt1019_rt5682s_controls,
+ .num_controls = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_controls),
+ .dapm_widgets = mt8186_mt6366_rt1019_rt5682s_widgets,
+ .num_dapm_widgets = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_widgets),
+ .dapm_routes = mt8186_mt6366_rt1019_rt5682s_routes,
+ .num_dapm_routes = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_routes),
+ .codec_conf = mt8186_mt6366_rt1019_rt5682s_codec_conf,
+ .num_configs = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_codec_conf),
+};
+
static int mt8186_mt6366_rt1019_rt5682s_dev_probe(struct platform_device *pdev)
{
struct snd_soc_card *card;
#if IS_ENABLED(CONFIG_OF)
static const struct of_device_id mt8186_mt6366_rt1019_rt5682s_dt_match[] = {
- { .compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound",
+ {
+ .compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound",
.data = &mt8186_mt6366_rt1019_rt5682s_soc_card,
},
+ {
+ .compatible = "mediatek,mt8186-mt6366-rt5682s-max98360-sound",
+ .data = &mt8186_mt6366_rt5682s_max98360_soc_card,
+ },
{}
};
MODULE_DEVICE_TABLE(of, mt8186_mt6366_rt1019_rt5682s_dt_match);
menuconfig SND_SOC_QCOM
tristate "ASoC support for QCOM platforms"
depends on ARCH_QCOM || COMPILE_TEST
- imply SND_SOC_QCOM_COMMON
help
Say Y or M if you want to add support to use audio devices
in Qualcomm Technologies SOC-based platforms.
config SND_SOC_APQ8016_SBC
tristate "SoC Audio support for APQ8016 SBC platforms"
select SND_SOC_LPASS_APQ8016
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
help
Support for Qualcomm Technologies LPASS audio block in
APQ8016 SOC-based systems.
Say Y if you want to use audio devices on MI2S.
config SND_SOC_QCOM_COMMON
- depends on SOUNDWIRE
+ tristate
+
+config SND_SOC_QCOM_SDW
tristate
config SND_SOC_QDSP6_COMMON
depends on QCOM_APR
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
help
Support for Qualcomm Technologies LPASS audio block in
APQ8096 SoC-based systems.
depends on QCOM_APR && I2C && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_RT5663
select SND_SOC_MAX98927
imply SND_SOC_CROS_EC_CODEC
depends on QCOM_APR && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_SDW
help
To add support for audio on Qualcomm Technologies Inc.
SM8250 SoC-based systems.
depends on QCOM_APR && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_SDW
help
To add support for audio on Qualcomm Technologies Inc.
SC8280XP SoC-based systems.
tristate "SoC Machine driver for SC7180 boards"
depends on I2C && GPIOLIB
depends on SOUNDWIRE || SOUNDWIRE=n
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_LPASS_SC7180
select SND_SOC_MAX98357A
select SND_SOC_RT5682_I2C
config SND_SOC_SC7280
tristate "SoC Machine driver for SC7280 boards"
depends on I2C && SOUNDWIRE
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_LPASS_SC7280
select SND_SOC_MAX98357A
select SND_SOC_WCD938X_SDW
snd-soc-sm8250-objs := sm8250.o
snd-soc-sc8280xp-objs := sc8280xp.o
snd-soc-qcom-common-objs := common.o
+snd-soc-qcom-sdw-objs := sdw.o
obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o
obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o
obj-$(CONFIG_SND_SOC_SDM845) += snd-soc-sdm845.o
obj-$(CONFIG_SND_SOC_SM8250) += snd-soc-sm8250.o
obj-$(CONFIG_SND_SOC_QCOM_COMMON) += snd-soc-qcom-common.o
+obj-$(CONFIG_SND_SOC_QCOM_SDW) += snd-soc-qcom-sdw.o
#DSP lib
obj-$(CONFIG_SND_SOC_QDSP6) += qdsp6/
}
EXPORT_SYMBOL_GPL(qcom_snd_parse_of);
-int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime,
- bool *stream_prepared)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
- int ret;
-
- if (!sruntime)
- return 0;
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case WSA_CODEC_DMA_RX_1:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- break;
- default:
- return 0;
- }
-
- if (*stream_prepared) {
- sdw_disable_stream(sruntime);
- sdw_deprepare_stream(sruntime);
- *stream_prepared = false;
- }
-
- ret = sdw_prepare_stream(sruntime);
- if (ret)
- return ret;
-
- /**
- * NOTE: there is a strict hw requirement about the ordering of port
- * enables and actual WSA881x PA enable. PA enable should only happen
- * after soundwire ports are enabled if not DC on the line is
- * accumulated resulting in Click/Pop Noise
- * PA enable/mute are handled as part of codec DAPM and digital mute.
- */
-
- ret = sdw_enable_stream(sruntime);
- if (ret) {
- sdw_deprepare_stream(sruntime);
- return ret;
- }
- *stream_prepared = true;
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare);
-
-int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
- struct snd_pcm_hw_params *params,
- struct sdw_stream_runtime **psruntime)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *codec_dai;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
- struct sdw_stream_runtime *sruntime;
- int i;
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- for_each_rtd_codec_dais(rtd, i, codec_dai) {
- sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream);
- if (sruntime != ERR_PTR(-ENOTSUPP))
- *psruntime = sruntime;
- }
- break;
- }
-
- return 0;
-
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_params);
-
-int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime, bool *stream_prepared)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case WSA_CODEC_DMA_RX_1:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- if (sruntime && *stream_prepared) {
- sdw_disable_stream(sruntime);
- sdw_deprepare_stream(sruntime);
- *stream_prepared = false;
- }
- break;
- default:
- break;
- }
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free);
-
int qcom_snd_wcd_jack_setup(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_jack *jack, bool *jack_setup)
{
#define __QCOM_SND_COMMON_H__
#include <sound/soc.h>
-#include <linux/soundwire/sdw.h>
int qcom_snd_parse_of(struct snd_soc_card *card);
int qcom_snd_wcd_jack_setup(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_jack *jack, bool *jack_setup);
-int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *runtime,
- bool *stream_prepared);
-int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
- struct snd_pcm_hw_params *params,
- struct sdw_stream_runtime **psruntime);
-int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime,
- bool *stream_prepared);
#endif
struct lpass_data *data)
{
struct device_node *node;
- int ret, id;
+ int ret, i, id;
/* Allow all channels by default for backwards compatibility */
- for (id = 0; id < data->variant->num_dai; id++) {
+ for (i = 0; i < data->variant->num_dai; i++) {
+ id = data->variant->dai_driver[i].id;
data->mi2s_playback_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH;
data->mi2s_capture_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH;
}
#include <linux/input-event-codes.h>
#include "qdsp6/q6afe.h"
#include "common.h"
+#include "sdw.h"
#define DRIVER_NAME "sc8280xp"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, Linaro Limited.
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#include <linux/module.h>
+#include <sound/soc.h>
+#include "qdsp6/q6afe.h"
+#include "sdw.h"
+
+int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime,
+ bool *stream_prepared)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+ int ret;
+
+ if (!sruntime)
+ return 0;
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case WSA_CODEC_DMA_RX_1:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ break;
+ default:
+ return 0;
+ }
+
+ if (*stream_prepared) {
+ sdw_disable_stream(sruntime);
+ sdw_deprepare_stream(sruntime);
+ *stream_prepared = false;
+ }
+
+ ret = sdw_prepare_stream(sruntime);
+ if (ret)
+ return ret;
+
+ /**
+ * NOTE: there is a strict hw requirement about the ordering of port
+ * enables and actual WSA881x PA enable. PA enable should only happen
+ * after soundwire ports are enabled if not DC on the line is
+ * accumulated resulting in Click/Pop Noise
+ * PA enable/mute are handled as part of codec DAPM and digital mute.
+ */
+
+ ret = sdw_enable_stream(sruntime);
+ if (ret) {
+ sdw_deprepare_stream(sruntime);
+ return ret;
+ }
+ *stream_prepared = true;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare);
+
+int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct sdw_stream_runtime **psruntime)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *codec_dai;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+ struct sdw_stream_runtime *sruntime;
+ int i;
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ for_each_rtd_codec_dais(rtd, i, codec_dai) {
+ sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream);
+ if (sruntime != ERR_PTR(-ENOTSUPP))
+ *psruntime = sruntime;
+ }
+ break;
+ }
+
+ return 0;
+
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_params);
+
+int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime, bool *stream_prepared)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case WSA_CODEC_DMA_RX_1:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ if (sruntime && *stream_prepared) {
+ sdw_disable_stream(sruntime);
+ sdw_deprepare_stream(sruntime);
+ *stream_prepared = false;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free);
+MODULE_LICENSE("GPL v2");
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#ifndef __QCOM_SND_SDW_H__
+#define __QCOM_SND_SDW_H__
+
+#include <linux/soundwire/sdw.h>
+
+int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *runtime,
+ bool *stream_prepared);
+int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct sdw_stream_runtime **psruntime);
+int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime,
+ bool *stream_prepared);
+#endif
#include <linux/input-event-codes.h>
#include "qdsp6/q6afe.h"
#include "common.h"
+#include "sdw.h"
#define DRIVER_NAME "sm8250"
#define MI2S_BCLK_RATE 1536000
template.num_kcontrols = le32_to_cpu(w->num_kcontrols);
kc = devm_kcalloc(tplg->dev, le32_to_cpu(w->num_kcontrols), sizeof(*kc), GFP_KERNEL);
- if (!kc)
+ if (!kc) {
+ ret = -ENOMEM;
goto hdr_err;
+ }
kcontrol_type = devm_kcalloc(tplg->dev, le32_to_cpu(w->num_kcontrols), sizeof(unsigned int),
GFP_KERNEL);
- if (!kcontrol_type)
+ if (!kcontrol_type) {
+ ret = -ENOMEM;
goto hdr_err;
+ }
for (i = 0; i < le32_to_cpu(w->num_kcontrols); i++) {
control_hdr = (struct snd_soc_tplg_ctl_hdr *)tplg->pos;
{
struct snd_sof_dev *sdev = context;
const struct sof_amd_acp_desc *desc = get_chip_info(sdev->pdata);
- unsigned int base = desc->dsp_intr_base;
unsigned int val, count = ACP_HW_SEM_RETRY_COUNT;
val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->ext_intr_stat);
return IRQ_HANDLED;
}
- val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, base + DSP_SW_INTR_STAT_OFFSET);
- if (val & ACP_DSP_TO_HOST_IRQ) {
- while (snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset)) {
- /* Wait until acquired HW Semaphore lock or timeout */
- count--;
- if (!count) {
- dev_err(sdev->dev, "%s: Failed to acquire HW lock\n", __func__);
- return IRQ_NONE;
- }
+ while (snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset)) {
+ /* Wait until acquired HW Semaphore lock or timeout */
+ count--;
+ if (!count) {
+ dev_err(sdev->dev, "%s: Failed to acquire HW lock\n", __func__);
+ return IRQ_NONE;
}
-
- sof_ops(sdev)->irq_thread(irq, sdev);
- val |= ACP_DSP_TO_HOST_IRQ;
- snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + DSP_SW_INTR_STAT_OFFSET, val);
-
- /* Unlock or Release HW Semaphore */
- snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset, 0x0);
-
- return IRQ_HANDLED;
}
- return IRQ_NONE;
+ sof_ops(sdev)->irq_thread(irq, sdev);
+ /* Unlock or Release HW Semaphore */
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->hw_semaphore_offset, 0x0);
+
+ return IRQ_HANDLED;
};
static irqreturn_t acp_irq_handler(int irq, void *dev_id)
unsigned int val;
val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, base + DSP_SW_INTR_STAT_OFFSET);
- if (val)
+ if (val) {
+ val |= ACP_DSP_TO_HOST_IRQ;
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + DSP_SW_INTR_STAT_OFFSET, val);
return IRQ_WAKE_THREAD;
+ }
return IRQ_NONE;
}
return err;
}
- return 0;
+ return snd_sof_debugfs_buf_item(sdev, &sdev->fw_state,
+ sizeof(sdev->fw_state),
+ "fw_state", 0444);
}
EXPORT_SYMBOL_GPL(snd_sof_dbg_init);
sdev = snd_soc_component_get_drvdata(cpu_dai->component);
bus = sof_to_bus(sdev);
+ hlink = snd_hdac_ext_bus_get_hlink_by_name(bus, codec_dai->component->name);
+ if (!hlink)
+ return -EINVAL;
+
hext_stream = snd_soc_dai_get_dma_data(cpu_dai, substream);
if (!hext_stream) {
hext_stream = hda_link_stream_assign(bus, substream);
snd_soc_dai_set_dma_data(cpu_dai, substream, (void *)hext_stream);
}
- hlink = snd_hdac_ext_bus_get_hlink_by_name(bus, codec_dai->component->name);
- if (!hlink)
- return -EINVAL;
-
/* set the hdac_stream in the codec dai */
snd_soc_dai_set_stream(codec_dai, hdac_stream(hext_stream), substream->stream);
size_t count, loff_t *ppos)
{
struct sof_mtrace_priv *priv = file->private_data;
- int id, ret;
+ unsigned int id;
char *buf;
u32 mask;
+ int ret;
/*
* To update Nth mask entry, write:
if (IS_ERR(buf))
return PTR_ERR(buf);
- ret = sscanf(buf, "%d,0x%x", &id, &mask);
+ ret = sscanf(buf, "%u,0x%x", &id, &mask);
if (ret != 2) {
- ret = sscanf(buf, "%d,%x", &id, &mask);
+ ret = sscanf(buf, "%u,%x", &id, &mask);
if (ret != 2) {
ret = -EINVAL;
goto out;
}
static inline void snd_sof_dsp_update8(struct snd_sof_dev *sdev, u32 bar,
- u32 offset, u8 value, u8 mask)
+ u32 offset, u8 mask, u8 value)
{
u8 reg;
const struct sof_ipc_pm_ops *pm_ops = sdev->ipc->ops->pm;
const struct sof_ipc_tplg_ops *tplg_ops = sdev->ipc->ops->tplg;
pm_message_t pm_state;
- u32 target_state = 0;
+ u32 target_state = snd_sof_dsp_power_target(sdev);
int ret;
/* do nothing if dsp suspend callback is not set */
if (runtime_suspend && !sof_ops(sdev)->runtime_suspend)
return 0;
+ if (tplg_ops && tplg_ops->tear_down_all_pipelines)
+ tplg_ops->tear_down_all_pipelines(sdev, false);
+
if (sdev->fw_state != SOF_FW_BOOT_COMPLETE)
goto suspend;
}
}
- target_state = snd_sof_dsp_power_target(sdev);
pm_state.event = target_state;
/* Skip to platform-specific suspend if DSP is entering D0 */
goto suspend;
}
- if (tplg_ops->tear_down_all_pipelines)
- tplg_ops->tear_down_all_pipelines(sdev, false);
-
/* suspend DMA trace */
sof_fw_trace_suspend(sdev, pm_state);
struct snd_sof_widget *swidget = widget->dobj.private;
struct snd_soc_dapm_path *p;
- /* return if the widget is in use or if it is already unprepared */
- if (!swidget->prepared || swidget->use_count > 1)
- return;
+ /* skip if the widget is in use or if it is already unprepared */
+ if (!swidget || !swidget->prepared || swidget->use_count > 0)
+ goto sink_unprepare;
if (widget_ops[widget->id].ipc_unprepare)
/* unprepare the source widget */
swidget->prepared = false;
+sink_unprepare:
/* unprepare all widgets in the sink paths */
snd_soc_dapm_widget_for_each_sink_path(widget, p) {
if (!p->walking && p->sink->dobj.private) {
struct snd_soc_dapm_path *p;
int ret;
- if (!widget_ops[widget->id].ipc_prepare || swidget->prepared)
+ if (!swidget || !widget_ops[widget->id].ipc_prepare || swidget->prepared)
goto sink_prepare;
/* prepare the source widget */
p->walking = false;
if (ret < 0) {
/* unprepare the source widget */
- if (widget_ops[widget->id].ipc_unprepare && swidget->prepared) {
+ if (widget_ops[widget->id].ipc_unprepare &&
+ swidget && swidget->prepared) {
widget_ops[widget->id].ipc_unprepare(swidget);
swidget->prepared = false;
}
for_each_dapm_widgets(list, i, widget) {
/* starting widget for playback is AIF type */
- if (dir == SNDRV_PCM_STREAM_PLAYBACK && !WIDGET_IS_AIF(widget->id))
+ if (dir == SNDRV_PCM_STREAM_PLAYBACK && widget->id != snd_soc_dapm_aif_in)
continue;
/* starting widget for capture is DAI type */
- if (dir == SNDRV_PCM_STREAM_CAPTURE && !WIDGET_IS_DAI(widget->id))
+ if (dir == SNDRV_PCM_STREAM_CAPTURE && widget->id != snd_soc_dapm_dai_out)
continue;
switch (op) {
snd_emux_xg_control(struct snd_emux_port *port, struct snd_midi_channel *chan,
int param)
{
+ if (param >= ARRAY_SIZE(chan->control))
+ return -EINVAL;
+
return send_converted_effect(xg_effects, ARRAY_SIZE(xg_effects),
port, chan, param,
chan->control[param],
subs = find_matching_substream(chip, stream, target->sync_ep,
target->fmt_type);
if (!subs)
- return sync_fmt;
+ goto end;
high_score = 0;
list_for_each_entry(fp, &subs->fmt_list, list) {
}
}
+ end:
if (fixed_rate)
*fixed_rate = snd_usb_pcm_has_fixed_rate(subs);
return sync_fmt;
for (;;) {
done =
line6_midibuf_read(mb, line6->buffer_message,
- LINE6_MIDI_MESSAGE_MAXLEN);
+ LINE6_MIDI_MESSAGE_MAXLEN,
+ LINE6_MIDIBUF_READ_RX);
if (done <= 0)
break;
int req, done;
for (;;) {
- req = min(line6_midibuf_bytes_free(mb), line6->max_packet_size);
+ req = min3(line6_midibuf_bytes_free(mb), line6->max_packet_size,
+ LINE6_FALLBACK_MAXPACKETSIZE);
done = snd_rawmidi_transmit_peek(substream, chunk, req);
if (done == 0)
for (;;) {
done = line6_midibuf_read(mb, chunk,
- LINE6_FALLBACK_MAXPACKETSIZE);
+ LINE6_FALLBACK_MAXPACKETSIZE,
+ LINE6_MIDIBUF_READ_TX);
if (done == 0)
break;
#include "midibuf.h"
+
static int midibuf_message_length(unsigned char code)
{
int message_length;
message_length = length[(code >> 4) - 8];
} else {
- /*
- Note that according to the MIDI specification 0xf2 is
- the "Song Position Pointer", but this is used by Line 6
- to send sysex messages to the host.
- */
- static const int length[] = { -1, 2, -1, 2, -1, -1, 1, 1, 1, 1,
+ static const int length[] = { -1, 2, 2, 2, -1, -1, 1, 1, 1, -1,
1, 1, 1, -1, 1, 1
};
message_length = length[code & 0x0f];
}
int line6_midibuf_read(struct midi_buffer *this, unsigned char *data,
- int length)
+ int length, int read_type)
{
int bytes_used;
int length1, length2;
length1 = this->size - this->pos_read;
- /* check MIDI command length */
command = this->buf[this->pos_read];
+ /*
+ PODxt always has status byte lower nibble set to 0010,
+ when it means to send 0000, so we correct if here so
+ that control/program changes come on channel 1 and
+ sysex message status byte is correct
+ */
+ if (read_type == LINE6_MIDIBUF_READ_RX) {
+ if (command == 0xb2 || command == 0xc2 || command == 0xf2) {
+ unsigned char fixed = command & 0xf0;
+ this->buf[this->pos_read] = fixed;
+ command = fixed;
+ }
+ }
+ /* check MIDI command length */
if (command & 0x80) {
midi_length = midibuf_message_length(command);
this->command_prev = command;
#ifndef MIDIBUF_H
#define MIDIBUF_H
+#define LINE6_MIDIBUF_READ_TX 0
+#define LINE6_MIDIBUF_READ_RX 1
+
struct midi_buffer {
unsigned char *buf;
int size;
extern int line6_midibuf_ignore(struct midi_buffer *mb, int length);
extern int line6_midibuf_init(struct midi_buffer *mb, int size, int split);
extern int line6_midibuf_read(struct midi_buffer *mb, unsigned char *data,
- int length);
+ int length, int read_type);
extern void line6_midibuf_reset(struct midi_buffer *mb);
extern int line6_midibuf_write(struct midi_buffer *mb, unsigned char *data,
int length);
.bytes_per_channel = 3 /* SNDRV_PCM_FMTBIT_S24_3LE */
};
+
static const char pod_version_header[] = {
- 0xf2, 0x7e, 0x7f, 0x06, 0x02
+ 0xf0, 0x7e, 0x7f, 0x06, 0x02
};
static char *pod_alloc_sysex_buffer(struct usb_line6_pod *pod, int code,
bool snd_usb_pcm_has_fixed_rate(struct snd_usb_substream *subs)
{
const struct audioformat *fp;
- struct snd_usb_audio *chip = subs->stream->chip;
+ struct snd_usb_audio *chip;
int rate = -1;
+ if (!subs)
+ return false;
+ chip = subs->stream->chip;
if (!(chip->quirk_flags & QUIRK_FLAG_FIXED_RATE))
return false;
list_for_each_entry(fp, &subs->fmt_list, list) {
if (snd_usb_endpoint_compatible(chip, subs->data_endpoint,
fmt, hw_params))
goto unlock;
+ if (stop_endpoints(subs, false))
+ sync_pending_stops(subs);
close_endpoints(chip, subs);
}
return changed;
}
+/* get the specified endpoint object that is being used by other streams
+ * (i.e. the parameter is locked)
+ */
+static const struct snd_usb_endpoint *
+get_endpoint_in_use(struct snd_usb_audio *chip, int endpoint,
+ const struct snd_usb_endpoint *ref_ep)
+{
+ const struct snd_usb_endpoint *ep;
+
+ ep = snd_usb_get_endpoint(chip, endpoint);
+ if (ep && ep->cur_audiofmt && (ep != ref_ep || ep->opened > 1))
+ return ep;
+ return NULL;
+}
+
static int hw_rule_rate(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
struct snd_usb_audio *chip = subs->stream->chip;
+ const struct snd_usb_endpoint *ep;
const struct audioformat *fp;
struct snd_interval *it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
unsigned int rmin, rmax, r;
list_for_each_entry(fp, &subs->fmt_list, list) {
if (!hw_check_valid_format(subs, params, fp))
continue;
+
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("rate limit %d for ep#%x\n",
+ ep->cur_rate, fp->endpoint);
+ rmin = min(rmin, ep->cur_rate);
+ rmax = max(rmax, ep->cur_rate);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("rate limit %d for sync_ep#%x\n",
+ ep->cur_rate, fp->sync_ep);
+ rmin = min(rmin, ep->cur_rate);
+ rmax = max(rmax, ep->cur_rate);
+ continue;
+ }
+ }
+
r = snd_usb_endpoint_get_clock_rate(chip, fp->clock);
if (r > 0) {
if (!snd_interval_test(it, r))
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
+ struct snd_usb_audio *chip = subs->stream->chip;
+ const struct snd_usb_endpoint *ep;
const struct audioformat *fp;
struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
u64 fbits;
list_for_each_entry(fp, &subs->fmt_list, list) {
if (!hw_check_valid_format(subs, params, fp))
continue;
+
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("format limit %d for ep#%x\n",
+ ep->cur_format, fp->endpoint);
+ fbits |= pcm_format_to_bits(ep->cur_format);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("format limit %d for sync_ep#%x\n",
+ ep->cur_format, fp->sync_ep);
+ fbits |= pcm_format_to_bits(ep->cur_format);
+ continue;
+ }
+ }
+
fbits |= fp->formats;
}
return apply_hw_params_format_bits(fmt, fbits);
return apply_hw_params_minmax(it, pmin, UINT_MAX);
}
-/* get the EP or the sync EP for implicit fb when it's already set up */
-static const struct snd_usb_endpoint *
-get_sync_ep_from_substream(struct snd_usb_substream *subs)
-{
- struct snd_usb_audio *chip = subs->stream->chip;
- const struct audioformat *fp;
- const struct snd_usb_endpoint *ep;
-
- list_for_each_entry(fp, &subs->fmt_list, list) {
- ep = snd_usb_get_endpoint(chip, fp->endpoint);
- if (ep && ep->cur_audiofmt) {
- /* if EP is already opened solely for this substream,
- * we still allow us to change the parameter; otherwise
- * this substream has to follow the existing parameter
- */
- if (ep->cur_audiofmt != subs->cur_audiofmt || ep->opened > 1)
- return ep;
- }
- if (!fp->implicit_fb)
- continue;
- /* for the implicit fb, check the sync ep as well */
- ep = snd_usb_get_endpoint(chip, fp->sync_ep);
- if (ep && ep->cur_audiofmt)
- return ep;
- }
- return NULL;
-}
-
/* additional hw constraints for implicit feedback mode */
-static int hw_rule_format_implicit_fb(struct snd_pcm_hw_params *params,
- struct snd_pcm_hw_rule *rule)
-{
- struct snd_usb_substream *subs = rule->private;
- const struct snd_usb_endpoint *ep;
- struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
-
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
- return apply_hw_params_format_bits(fmt, pcm_format_to_bits(ep->cur_format));
-}
-
-static int hw_rule_rate_implicit_fb(struct snd_pcm_hw_params *params,
- struct snd_pcm_hw_rule *rule)
-{
- struct snd_usb_substream *subs = rule->private;
- const struct snd_usb_endpoint *ep;
- struct snd_interval *it;
-
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
- it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
- return apply_hw_params_minmax(it, ep->cur_rate, ep->cur_rate);
-}
-
static int hw_rule_period_size_implicit_fb(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
+ struct snd_usb_audio *chip = subs->stream->chip;
+ const struct audioformat *fp;
const struct snd_usb_endpoint *ep;
struct snd_interval *it;
+ unsigned int rmin, rmax;
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE);
- return apply_hw_params_minmax(it, ep->cur_period_frames,
- ep->cur_period_frames);
+ hwc_debug("hw_rule_period_size: (%u,%u)\n", it->min, it->max);
+ rmin = UINT_MAX;
+ rmax = 0;
+ list_for_each_entry(fp, &subs->fmt_list, list) {
+ if (!hw_check_valid_format(subs, params, fp))
+ continue;
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("period size limit %d for ep#%x\n",
+ ep->cur_period_frames, fp->endpoint);
+ rmin = min(rmin, ep->cur_period_frames);
+ rmax = max(rmax, ep->cur_period_frames);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("period size limit %d for sync_ep#%x\n",
+ ep->cur_period_frames, fp->sync_ep);
+ rmin = min(rmin, ep->cur_period_frames);
+ rmax = max(rmax, ep->cur_period_frames);
+ continue;
+ }
+ }
+ }
+
+ if (!rmax)
+ return 0; /* no limit by implicit fb */
+ return apply_hw_params_minmax(it, rmin, rmax);
}
static int hw_rule_periods_implicit_fb(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
+ struct snd_usb_audio *chip = subs->stream->chip;
+ const struct audioformat *fp;
const struct snd_usb_endpoint *ep;
struct snd_interval *it;
+ unsigned int rmin, rmax;
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIODS);
- return apply_hw_params_minmax(it, ep->cur_buffer_periods,
- ep->cur_buffer_periods);
+ hwc_debug("hw_rule_periods: (%u,%u)\n", it->min, it->max);
+ rmin = UINT_MAX;
+ rmax = 0;
+ list_for_each_entry(fp, &subs->fmt_list, list) {
+ if (!hw_check_valid_format(subs, params, fp))
+ continue;
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("periods limit %d for ep#%x\n",
+ ep->cur_buffer_periods, fp->endpoint);
+ rmin = min(rmin, ep->cur_buffer_periods);
+ rmax = max(rmax, ep->cur_buffer_periods);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("periods limit %d for sync_ep#%x\n",
+ ep->cur_buffer_periods, fp->sync_ep);
+ rmin = min(rmin, ep->cur_buffer_periods);
+ rmax = max(rmax, ep->cur_buffer_periods);
+ continue;
+ }
+ }
+ }
+
+ if (!rmax)
+ return 0; /* no limit by implicit fb */
+ return apply_hw_params_minmax(it, rmin, rmax);
}
/*
return err;
/* additional hw constraints for implicit fb */
- err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT,
- hw_rule_format_implicit_fb, subs,
- SNDRV_PCM_HW_PARAM_FORMAT, -1);
- if (err < 0)
- return err;
- err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
- hw_rule_rate_implicit_fb, subs,
- SNDRV_PCM_HW_PARAM_RATE, -1);
- if (err < 0)
- return err;
err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
hw_rule_period_size_implicit_fb, subs,
SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1);
QUIRK_FLAG_GENERIC_IMPLICIT_FB),
DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */
QUIRK_FLAG_IFACE_SKIP_CLOSE),
+ DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
+ QUIRK_FLAG_FIXED_RATE),
DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
QUIRK_FLAG_FIXED_RATE),
if (err < 0)
return err;
}
+
+ /* try to set the interface... */
+ usb_set_interface(chip->dev, iface_no, 0);
+ snd_usb_init_pitch(chip, fp);
+ snd_usb_init_sample_rate(chip, fp, fp->rate_max);
+ usb_set_interface(chip->dev, iface_no, altno);
}
return 0;
}
return xenbus_switch_state(xb_dev, XenbusStateInitialising);
}
-static int xen_drv_remove(struct xenbus_device *dev)
+static void xen_drv_remove(struct xenbus_device *dev)
{
struct xen_snd_front_info *front_info = dev_get_drvdata(&dev->dev);
int to = 100;
xen_snd_drv_fini(front_info);
xenbus_frontend_closed(dev);
- return 0;
}
static const struct xenbus_device_id xen_drv_ids[] = {
(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
#define MIDR_CPU_MODEL(imp, partnum) \
- (((imp) << MIDR_IMPLEMENTOR_SHIFT) | \
+ ((_AT(u32, imp) << MIDR_IMPLEMENTOR_SHIFT) | \
(0xf << MIDR_ARCHITECTURE_SHIFT) | \
((partnum) << MIDR_PARTNUM_SHIFT))
#define ARM_CPU_PART_CORTEX_X1 0xD44
#define ARM_CPU_PART_CORTEX_A510 0xD46
#define ARM_CPU_PART_CORTEX_A710 0xD47
+#define ARM_CPU_PART_CORTEX_A715 0xD4D
#define ARM_CPU_PART_CORTEX_X2 0xD48
#define ARM_CPU_PART_NEOVERSE_N2 0xD49
#define ARM_CPU_PART_CORTEX_A78C 0xD4B
#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025
#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028
#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029
+#define APPLE_CPU_PART_M2_BLIZZARD 0x032
+#define APPLE_CPU_PART_M2_AVALANCHE 0x033
#define AMPERE_CPU_PART_AMPERE1 0xAC3
#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
+#define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
#define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
#define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
+#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
#define __KVM_HAVE_VCPU_EVENTS
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
#define KVM_REG_SIZE(id) \
(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
struct kvm_msr_filter_range {
#define KVM_MSR_FILTER_READ (1 << 0)
#define KVM_MSR_FILTER_WRITE (1 << 1)
+#define KVM_MSR_FILTER_RANGE_VALID_MASK (KVM_MSR_FILTER_READ | \
+ KVM_MSR_FILTER_WRITE)
__u32 flags;
__u32 nmsrs; /* number of msrs in bitmap */
__u32 base; /* MSR index the bitmap starts at */
#define KVM_MSR_FILTER_MAX_RANGES 16
struct kvm_msr_filter {
+#ifndef __KERNEL__
#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#endif
#define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
+#define KVM_MSR_FILTER_VALID_MASK (KVM_MSR_FILTER_DEFAULT_DENY)
__u32 flags;
struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
};
LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
CFLAGS += $(shell $(LLVM_CONFIG) --cflags --libs $(LLVM_CONFIG_LIB_COMPONENTS))
LIBS += $(shell $(LLVM_CONFIG) --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ ifeq ($(shell $(LLVM_CONFIG) --shared-mode),static)
+ LIBS += $(shell $(LLVM_CONFIG) --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ LIBS += -lstdc++
+ endif
LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
else
# Fall back on libbfd
gpiotools_test_bit(values.bits, i));
}
+ i = 0;
while (1) {
struct gpio_v2_line_event event;
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
#endif // static_assert
+
+/*
+ * Compile time check that field has an expected offset
+ */
+#define ASSERT_STRUCT_OFFSET(type, field, expected_offset) \
+ BUILD_BUG_ON_MSG(offsetof(type, field) != (expected_offset), \
+ "Offset of " #field " in " #type " has changed.")
+
+
#endif /* _LINUX_BUILD_BUG_H */
__asm__ (".section .text\n"
".weak __start\n"
".set nomips16\n"
+ ".set push\n"
".set noreorder\n"
".option pic0\n"
".ent __start\n"
"li $v0, 4001\n" // NR_exit == 4001
"syscall\n"
".end __start\n"
+ ".set pop\n"
"");
#endif // _NOLIBC_ARCH_MIPS_H
#define O_RDONLY 0
#define O_WRONLY 1
#define O_RDWR 2
-#define O_CREAT 0x100
-#define O_EXCL 0x200
-#define O_NOCTTY 0x400
-#define O_TRUNC 0x1000
-#define O_APPEND 0x2000
-#define O_NONBLOCK 0x4000
-#define O_DIRECTORY 0x200000
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x10000
struct sys_stat_struct {
unsigned long st_dev; /* Device. */
return isgraph(c) && !isalnum(c);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_CTYPE_H */
*/
#define MAX_ERRNO 4095
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_ERRNO_H */
return sys_kill(sys_getpid(), signal);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_SIGNAL_H */
fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STDIO_H */
return itoa_buffer;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STDLIB_H */
{
char *p = dst;
- while (len--)
+ while (len--) {
+ /* prevent gcc from recognizing memset() here */
+ asm volatile("");
*(p++) = b;
+ }
return dst;
}
return (char *)ret;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STRING_H */
return ret;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
#endif /* _NOLIBC_SYS_H */
return tv.tv_sec;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_TIME_H */
#define S_IFSOCK 0140000
#define S_IFMT 0170000
-#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR)
-#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR)
-#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK)
-#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG)
-#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO)
-#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK)
-#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK)
+#define S_ISDIR(mode) (((mode) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(mode) (((mode) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(mode) (((mode) & S_IFMT) == S_IFBLK)
+#define S_ISREG(mode) (((mode) & S_IFMT) == S_IFREG)
+#define S_ISFIFO(mode) (((mode) & S_IFMT) == S_IFIFO)
+#define S_ISLNK(mode) (((mode) & S_IFMT) == S_IFLNK)
+#define S_ISSOCK(mode) (((mode) & S_IFMT) == S_IFSOCK)
/* dirent types */
#define DT_UNKNOWN 0x0
#define EXIT_SUCCESS 0
#define EXIT_FAILURE 1
+#define FD_SETIDXMASK (8 * sizeof(unsigned long))
+#define FD_SETBITMASK (8 * sizeof(unsigned long)-1)
+
/* for select() */
typedef struct {
- uint32_t fd32[(FD_SETSIZE + 31) / 32];
+ unsigned long fds[(FD_SETSIZE + FD_SETBITMASK) / FD_SETIDXMASK];
} fd_set;
-#define FD_CLR(fd, set) do { \
- fd_set *__set = (set); \
- int __fd = (fd); \
- if (__fd >= 0) \
- __set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \
+#define FD_CLR(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fds[__fd / FD_SETIDXMASK] &= \
+ ~(1U << (__fd & FX_SETBITMASK)); \
} while (0)
-#define FD_SET(fd, set) do { \
- fd_set *__set = (set); \
- int __fd = (fd); \
- if (__fd >= 0) \
- __set->fd32[__fd / 32] |= 1U << (__fd & 31); \
+#define FD_SET(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fds[__fd / FD_SETIDXMASK] |= \
+ 1 << (__fd & FD_SETBITMASK); \
} while (0)
-#define FD_ISSET(fd, set) ({ \
- fd_set *__set = (set); \
- int __fd = (fd); \
- int __r = 0; \
- if (__fd >= 0) \
- __r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \
- __r; \
+#define FD_ISSET(fd, set) ({ \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ int __r = 0; \
+ if (__fd >= 0) \
+ __r = !!(__set->fds[__fd / FD_SETIDXMASK] & \
+1U << (__fd & FD_SET_BITMASK)); \
+ __r; \
})
-#define FD_ZERO(set) do { \
- fd_set *__set = (set); \
- int __idx; \
- for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \
- __set->fd32[__idx] = 0; \
+#define FD_ZERO(set) do { \
+ fd_set *__set = (set); \
+ int __idx; \
+ int __size = (FD_SETSIZE+FD_SETBITMASK) / FD_SETIDXMASK;\
+ for (__idx = 0; __idx < __size; __idx++) \
+ __set->fds[__idx] = 0; \
} while (0)
/* for poll() */
})
#endif
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_TYPES_H */
return ioctl(fd, TIOCSPGRP, &pid);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_UNISTD_H */
__u8 runstate_update_flag;
struct {
__u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
} shared_info;
struct {
__u32 send_port;
} u;
};
+
/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
__u16 pad[3];
union {
__u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
__u64 pad[8];
struct {
__u64 state;
if (func->type != STT_NOTYPE && func->type != STT_FUNC)
continue;
+ if (func->offset == sec->sh.sh_size) {
+ /* Heuristic: likely an "end" symbol */
+ if (func->type == STT_NOTYPE)
+ continue;
+ WARN("%s(): STT_FUNC at end of section",
+ func->name);
+ return -1;
+ }
+
if (func->return_thunk || func->alias != func)
continue;
$(ASCIIDOC) -b docbook -d manpage \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
-aperf_date=$(shell git log -1 --pretty="format:%cd" \
- --date=short $<) \
+ --date=short --no-show-signature $<) \
-o $@+ $< && \
mv $@+ $@
$(call feature_check,libbpf-bpf_program__set_insns)
ifeq ($(feature-libbpf-bpf_program__set_insns), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
+ else
+ dummy := $(error Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources);
endif
$(call feature_check,libbpf-btf__raw_data)
ifeq ($(feature-libbpf-btf__raw_data), 1)
dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
endif
else
+ # Libbpf will be built as a static library from tools/lib/bpf.
+ LIBBPF_STATIC := 1
CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
export perfexec_instdir_SQ
-# If we install to $(HOME) we keep the traceevent default:
-# $(HOME)/.traceevent/plugins
-# Otherwise we install plugins into the global $(libdir).
-ifdef DESTDIR
-plugindir=$(libdir)/traceevent/plugins
-plugindir_SQ= $(subst ','\'',$(plugindir))
-endif
-
print_var = $(eval $(print_var_code)) $(info $(MSG))
define print_var_code
MSG = $(shell printf '...%40s: %s' $(1) $($(1)))
else
LIBBPF_OUTPUT = $(CURDIR)/libbpf
endif
-LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
-LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
-LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
-CFLAGS += -I$(LIBBPF_OUTPUT)/include
+ifdef LIBBPF_STATIC
+ LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
+ LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
+ LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
+ CFLAGS += -I$(LIBBPF_OUTPUT)/include
+endif
ifneq ($(OUTPUT),)
LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd
export PERL_PATH
PERFLIBS = $(LIBAPI) $(LIBPERF) $(LIBSUBCMD) $(LIBSYMBOL)
-ifndef NO_LIBBPF
- ifndef LIBBPF_DYNAMIC
- PERFLIBS += $(LIBBPF)
- endif
+ifdef LIBBPF_STATIC
+ PERFLIBS += $(LIBBPF)
endif
# We choose to avoid "if .. else if .. else .. endif endif"
$(arch_errno_name_array) \
$(sync_file_range_arrays) \
$(LIBAPI) \
- $(LIBBPF) \
$(LIBPERF) \
$(LIBSUBCMD) \
$(LIBSYMBOL) \
bpf-skel
+ifdef LIBBPF_STATIC
+prepare: $(LIBBPF)
+endif
+
$(OUTPUT)%.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(LIBAPI): FORCE | $(LIBAPI_OUTPUT)
$(Q)$(MAKE) -C $(LIBAPI_DIR) O=$(LIBAPI_OUTPUT) \
- DESTDIR=$(LIBAPI_DESTDIR) prefix= \
+ DESTDIR=$(LIBAPI_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBAPI)-clean:
$(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
$(Q)$(MAKE) -C $(LIBBPF_DIR) FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) \
- O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \
+ O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBBPF)-clean:
$(LIBPERF): FORCE | $(LIBPERF_OUTPUT)
$(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(LIBPERF_OUTPUT) \
- DESTDIR=$(LIBPERF_DESTDIR) prefix= \
+ DESTDIR=$(LIBPERF_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBPERF)-clean:
$(LIBSUBCMD): FORCE | $(LIBSUBCMD_OUTPUT)
$(Q)$(MAKE) -C $(LIBSUBCMD_DIR) O=$(LIBSUBCMD_OUTPUT) \
- DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= \
+ DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBSUBCMD)-clean:
$(LIBSYMBOL): FORCE | $(LIBSYMBOL_OUTPUT)
$(Q)$(MAKE) -C $(LIBSYMBOL_DIR) O=$(LIBSYMBOL_OUTPUT) \
- DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= \
+ DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBSYMBOL)-clean:
#include <elfutils/libdwfl.h>
#include "../../util/unwind-libdw.h"
#include "../../util/perf_regs.h"
-#include "../../util/event.h"
+#include "../../util/sample.h"
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
{
#include "util/string2.h"
#include <linux/kernel.h>
+#include <linux/numa.h>
#include <linux/rbtree.h>
#include <linux/string.h>
#include <linux/zalloc.h>
total_allocated += bytes_alloc;
nr_allocs++;
- return 0;
-}
-static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample)
-{
- int ret = evsel__process_alloc_event(evsel, sample);
+ /*
+ * Commit 11e9734bcb6a ("mm/slab_common: unify NUMA and UMA
+ * version of tracepoints") adds the field "node" into the
+ * tracepoints 'kmalloc' and 'kmem_cache_alloc'.
+ *
+ * The legacy tracepoints 'kmalloc_node' and 'kmem_cache_alloc_node'
+ * also contain the field "node".
+ *
+ * If the tracepoint contains the field "node" the tool stats the
+ * cross allocation.
+ */
+ if (evsel__field(evsel, "node")) {
+ int node1, node2;
- if (!ret) {
- int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}),
- node2 = evsel__intval(evsel, sample, "node");
+ node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu});
+ node2 = evsel__intval(evsel, sample, "node");
- if (node1 != node2)
+ /*
+ * If the field "node" is NUMA_NO_NODE (-1), we don't take it
+ * as a cross allocation.
+ */
+ if ((node2 != NUMA_NO_NODE) && (node1 != node2))
nr_cross_allocs++;
}
- return ret;
+ return 0;
}
static int ptr_cmp(void *, void *);
/* slab allocator */
{ "kmem:kmalloc", evsel__process_alloc_event, },
{ "kmem:kmem_cache_alloc", evsel__process_alloc_event, },
- { "kmem:kmalloc_node", evsel__process_alloc_node_event, },
- { "kmem:kmem_cache_alloc_node", evsel__process_alloc_node_event, },
+ { "kmem:kmalloc_node", evsel__process_alloc_event, },
+ { "kmem:kmem_cache_alloc_node", evsel__process_alloc_event, },
{ "kmem:kfree", evsel__process_free_event, },
{ "kmem:kmem_cache_free", evsel__process_free_event, },
/* page allocator */
return 0;
}
+static bool slab_legacy_tp_is_exposed(void)
+{
+ /*
+ * The tracepoints "kmem:kmalloc_node" and
+ * "kmem:kmem_cache_alloc_node" have been removed on the latest
+ * kernel, if the tracepoint "kmem:kmalloc_node" is existed it
+ * means the tool is running on an old kernel, we need to
+ * rollback to support these legacy tracepoints.
+ */
+ return IS_ERR(trace_event__tp_format("kmem", "kmalloc_node")) ?
+ false : true;
+}
+
static int __cmd_record(int argc, const char **argv)
{
const char * const record_args[] = {
};
const char * const slab_events[] = {
"-e", "kmem:kmalloc",
- "-e", "kmem:kmalloc_node",
"-e", "kmem:kfree",
"-e", "kmem:kmem_cache_alloc",
- "-e", "kmem:kmem_cache_alloc_node",
"-e", "kmem:kmem_cache_free",
};
+ const char * const slab_legacy_events[] = {
+ "-e", "kmem:kmalloc_node",
+ "-e", "kmem:kmem_cache_alloc_node",
+ };
const char * const page_events[] = {
"-e", "kmem:mm_page_alloc",
"-e", "kmem:mm_page_free",
};
unsigned int rec_argc, i, j;
const char **rec_argv;
+ unsigned int slab_legacy_tp_exposed = slab_legacy_tp_is_exposed();
rec_argc = ARRAY_SIZE(record_args) + argc - 1;
- if (kmem_slab)
+ if (kmem_slab) {
rec_argc += ARRAY_SIZE(slab_events);
+ if (slab_legacy_tp_exposed)
+ rec_argc += ARRAY_SIZE(slab_legacy_events);
+ }
if (kmem_page)
rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
if (kmem_slab) {
for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++)
rec_argv[i] = strdup(slab_events[j]);
+ if (slab_legacy_tp_exposed) {
+ for (j = 0; j < ARRAY_SIZE(slab_legacy_events); j++, i++)
+ rec_argv[i] = strdup(slab_legacy_events[j]);
+ }
}
if (kmem_page) {
rec_argv[i++] = strdup("-g");
/* for lock function check */
symbol_conf.sort_by_name = true;
+ symbol_conf.allow_aliases = true;
symbol__init(&session->header.env);
if (!data.is_pipe) {
/* for lock function check */
symbol_conf.sort_by_name = true;
+ symbol_conf.allow_aliases = true;
symbol__init(&session->header.env);
if (use_bpf) {
#include "util/record.h"
#include <api/fs/tracing_path.h>
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/bpf.h>
+#endif
#include "util/bpf_map.h"
#include "util/rlimit.h"
#include "builtin.h"
perf-inject mainporcelain common
perf-iostat mainporcelain common
perf-kallsyms mainporcelain common
-perf-kmem mainporcelain common
+perf-kmem mainporcelain traceevent
perf-kvm mainporcelain common
-perf-kwork mainporcelain common
+perf-kwork mainporcelain traceevent
perf-list mainporcelain common
-perf-lock mainporcelain common
+perf-lock mainporcelain traceevent
perf-mem mainporcelain common
perf-probe mainporcelain full
perf-record mainporcelain common
perf-report mainporcelain common
-perf-sched mainporcelain common
+perf-sched mainporcelain traceevent
perf-script mainporcelain common
perf-stat mainporcelain common
perf-test mainporcelain common
-perf-timechart mainporcelain common
+perf-timechart mainporcelain traceevent
perf-top mainporcelain common
perf-trace mainporcelain audit
perf-version mainporcelain common
# undef if
#endif
+typedef unsigned int __bitwise fmode_t;
+
#define FMODE_READ 0x1
#define FMODE_WRITE 0x2
installed_files_bin += etc/bash_completion.d/perf
installed_files_bin += libexec/perf-core/perf-archive
-installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
-
installed_files_all := $(installed_files_bin)
-installed_files_all += $(installed_files_plugins)
test_make_install := $(call test_dest_files,$(installed_files_all))
test_make_install_O := $(call test_dest_files,$(installed_files_all))
file=${build_id_dir}/.build-id/${id:0:2}/`readlink ${link}`/elf
echo "file: ${file}"
- if [ ! -x $file ]; then
+ # Check for file permission of original file
+ # in case of pe-file.exe file
+ echo $1 | grep ".exe"
+ if [ $? -eq 0 ]; then
+ if [ -x $1 -a ! -x $file ]; then
+ echo "failed: file ${file} executable does not exist"
+ exit 1
+ fi
+
+ if [ ! -x $file -a ! -e $file ]; then
+ echo "failed: file ${file} does not exist"
+ exit 1
+ fi
+ elif [ ! -x $file ]; then
echo "failed: file ${file} does not exist"
exit 1
fi
case "$(uname -m)" in
s390x)
eventattr='call-graph=dwarf,max-stack=4'
+ echo "text_to_binary_address.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
perf_data=`mktemp -u /tmp/perf.data.XXX`
perf_script=`mktemp -u /tmp/perf.script.XXX`
perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
- perf script -i $perf_data > $perf_script
+ perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script
exec 3<$perf_script
exec 4<$expected
struct sockaddr {
sa_family_t sa_family; /* address family, AF_xxx */
- char sa_data[14]; /* 14 bytes of protocol address */
+ union {
+ char sa_data_min[14]; /* Minimum 14 bytes of protocol address */
+ DECLARE_FLEX_ARRAY(char, sa_data);
+ };
};
struct linger {
if test -d ../../.git -o -f ../../.git
then
TAG=$(MAKEFLAGS= make -sC ../.. kernelversion)
- CID=$(git log -1 --abbrev=12 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
+ CID=$(git log -1 --abbrev=12 --pretty=format:"%h" --no-show-signature 2>/dev/null) && CID="-g$CID"
elif test -f ../../PERF-VERSION-FILE
then
TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')
*size = sym->start - *start;
if (idx > 0) {
if (*size)
- return 1;
+ return 0;
} else if (dso_sym_match(sym, sym_name, &cnt, idx)) {
print_duplicate_syms(dso, sym_name);
return -EINVAL;
#include <linux/list.h>
#include <sys/resource.h>
+
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/bpf.h>
#include <bpf/btf.h>
#include <bpf/libbpf.h>
+#endif
struct evsel;
struct target;
setrlimit(RLIMIT_MEMLOCK, &rinf);
}
+#ifdef HAVE_BPF_SKEL
+
static inline __u32 bpf_link_get_id(int fd)
{
struct bpf_link_info link_info = { .id = 0, };
return bpf_prog_test_run_opts(prog_fd, &opts);
}
+#endif /* HAVE_BPF_SKEL */
#endif /* __PERF_BPF_COUNTER_H */
/* open single copy of the events w/o cgroup */
err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1);
- if (err) {
- pr_err("Failed to open first cgroup events\n");
- goto out;
- }
+ if (err == 0)
+ evsel->supported = true;
map_fd = bpf_map__fd(skel->maps.events);
perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) {
int fd = FD(evsel, j);
__u32 idx = evsel->core.idx * total_cpus + cpu.cpu;
- err = bpf_map_update_elem(map_fd, &idx, &fd,
- BPF_ANY);
- if (err < 0) {
- pr_err("Failed to update perf_event fd\n");
- goto out;
- }
+ bpf_map_update_elem(map_fd, &idx, &fd, BPF_ANY);
}
evsel->cgrp = leader_cgrp;
}
- evsel->supported = true;
if (evsel->cgrp == cgrp)
continue;
} else if (nsi && nsinfo__need_setns(nsi)) {
if (copyfile_ns(name, filename, nsi))
goto out_free;
- } else if (link(realname, filename) && errno != EEXIST &&
- copyfile(name, filename))
- goto out_free;
+ } else if (link(realname, filename) && errno != EEXIST) {
+ struct stat f_stat;
+
+ if (!(stat(name, &f_stat) < 0) &&
+ copyfile_mode(name, filename, f_stat.st_mode))
+ goto out_free;
+ }
}
/* Some binaries are stripped, but have .debug files with their symbol
return 0;
}
+static int check_and_add_cgroup_name(const char *fpath)
+{
+ struct cgroup_name *cn;
+
+ list_for_each_entry(cn, &cgroup_list, list) {
+ if (!strcmp(cn->name, fpath))
+ return 0;
+ }
+
+ /* pretend if it's added by ftw() */
+ return add_cgroup_name(fpath, NULL, FTW_D, NULL);
+}
+
static void release_cgroup_list(void)
{
struct cgroup_name *cn;
struct cgroup_name *cn;
char *s;
- /* use given name as is - for testing purpose */
+ /* use given name as is when no regex is given */
for (;;) {
p = strchr(str, ',');
e = p ? p : eos;
s = strndup(str, e - str);
if (!s)
return -1;
- /* pretend if it's added by ftw() */
- ret = add_cgroup_name(s, NULL, FTW_D, NULL);
+
+ ret = check_and_add_cgroup_name(s);
free(s);
- if (ret)
+ if (ret < 0)
return -1;
} else {
- if (add_cgroup_name("", NULL, FTW_D, NULL) < 0)
+ if (check_and_add_cgroup_name("/") < 0)
return -1;
}
file->size = st.st_size;
}
+ closedir(dir);
if (!files)
return -EINVAL;
return 0;
out_err:
+ closedir(dir);
close_dir(files, nr);
return ret;
}
char *dst = str;
while (*str) {
- if (*str == '\\')
+ if (*str == '\\') {
*dst++ = *++str;
+ if (!*str)
+ break;
+ }
else if (*str == '?') {
char *paramval;
int i = 0;
done
echo "#endif /* HAVE_LIBELF_SUPPORT */"
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
+echo "#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT))"
sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt |
sort |
while read cmd
p
}' "Documentation/perf-$cmd.txt"
done
-echo "#endif /* HAVE_LIBELF_SUPPORT */"
+echo "#endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */"
+
+echo "#ifdef HAVE_LIBTRACEEVENT"
+sed -n -e 's/^perf-\([^ ]*\)[ ].* traceevent.*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+ sed -n '
+ /^NAME/,/perf-'"$cmd"'/H
+ ${
+ x
+ s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/
+ p
+ }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* HAVE_LIBTRACEEVENT */"
echo "};"
ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
goto out;
}
+#else
+ evlist__for_each_entry(evlist, evsel) {
+ if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
+ pr_err("%s %s", ret ? "," : "This perf binary isn't linked with libtraceevent, can't process", evsel__name(evsel));
+ ret = -ENOTSUP;
+ }
+ }
+
+ if (ret) {
+ pr_err("\n");
+ goto out;
+ }
#endif
evsel = find_evsel(evlist, event_name);
#include <stdbool.h>
#include <stdio.h>
+#include <sys/types.h>
#include <linux/types.h>
struct evlist;
main
memblock.c
linux/memblock.h
+asm/asm.h
asm/cmpxchg.h
@mkdir -p linux
test -L linux/memblock.h || ln -s ../../../../include/linux/memblock.h linux/memblock.h
+ test -L asm/asm.h || ln -s ../../../arch/x86/include/asm/asm.h asm/asm.h
test -L asm/cmpxchg.h || ln -s ../../../arch/x86/include/asm/cmpxchg.h asm/cmpxchg.h
memblock.c: $(EXTR_SRC)
test -L memblock.c || ln -s $(EXTR_SRC) memblock.c
clean:
- $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/cmpxchg.h
+ $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/asm.h asm/cmpxchg.h
help:
@echo 'Memblock simulator'
uname_M := $(shell uname -m 2>/dev/null || echo not)
ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-ifeq (x86,$(ARCH))
-TEST_GEN_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py
-TEST_GEN_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py
-endif
-
TEST_PROGS := run.sh
TEST_FILES := basic.sh tbench.sh gitsource.sh
*.lskel.h
/no_alu32
/bpf_gcc
+/host-tools
/tools
/runqslower
/bench
cgrp_local_storage # prog_attach unexpected error: -524 (trampoline)
core_read_macros # unknown func bpf_probe_read#4 (overlapping)
d_path # failed to auto-attach program 'prog_stat': -524 (trampoline)
+decap_sanity # JIT does not support calling kernel function (kfunc)
deny_namespace # failed to attach: ERROR: strerror_r(-524)=22 (trampoline)
dummy_st_ops # test_run unexpected error: -524 (errno 524) (trampoline)
fentry_fexit # fentry attach failed: -524 (trampoline)
bpf_iter_task_vma__destroy(skel);
}
+static void test_task_vma_dead_task(void)
+{
+ struct bpf_iter_task_vma *skel;
+ int wstatus, child_pid = -1;
+ time_t start_tm, cur_tm;
+ int err, iter_fd = -1;
+ int wait_sec = 3;
+
+ skel = bpf_iter_task_vma__open();
+ if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ err = bpf_iter_task_vma__load(skel);
+ if (!ASSERT_OK(err, "bpf_iter_task_vma__load"))
+ goto out;
+
+ skel->links.proc_maps = bpf_program__attach_iter(
+ skel->progs.proc_maps, NULL);
+
+ if (!ASSERT_OK_PTR(skel->links.proc_maps, "bpf_program__attach_iter")) {
+ skel->links.proc_maps = NULL;
+ goto out;
+ }
+
+ start_tm = time(NULL);
+ cur_tm = start_tm;
+
+ child_pid = fork();
+ if (child_pid == 0) {
+ /* Fork short-lived processes in the background. */
+ while (cur_tm < start_tm + wait_sec) {
+ system("echo > /dev/null");
+ cur_tm = time(NULL);
+ }
+ exit(0);
+ }
+
+ if (!ASSERT_GE(child_pid, 0, "fork_child"))
+ goto out;
+
+ while (cur_tm < start_tm + wait_sec) {
+ iter_fd = bpf_iter_create(bpf_link__fd(skel->links.proc_maps));
+ if (!ASSERT_GE(iter_fd, 0, "create_iter"))
+ goto out;
+
+ /* Drain all data from iter_fd. */
+ while (cur_tm < start_tm + wait_sec) {
+ err = read_fd_into_buffer(iter_fd, task_vma_output, CMP_BUFFER_SIZE);
+ if (!ASSERT_GE(err, 0, "read_iter_fd"))
+ goto out;
+
+ cur_tm = time(NULL);
+
+ if (err == 0)
+ break;
+ }
+
+ close(iter_fd);
+ iter_fd = -1;
+ }
+
+ check_bpf_link_info(skel->progs.proc_maps);
+
+out:
+ waitpid(child_pid, &wstatus, 0);
+ close(iter_fd);
+ bpf_iter_task_vma__destroy(skel);
+}
+
void test_bpf_sockmap_map_iter_fd(void)
{
struct bpf_iter_sockmap *skel;
test_task_file();
if (test__start_subtest("task_vma"))
test_task_vma();
+ if (test__start_subtest("task_vma_dead_task"))
+ test_task_vma_dead_task();
if (test__start_subtest("task_btf"))
test_task_btf();
if (test__start_subtest("tcp4"))
static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
char *str)
{
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if 0
TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
"int cpu_number = (int)100", 100);
#endif
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/in6.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "decap_sanity.skel.h"
+
+#define SYS(fmt, ...) \
+ ({ \
+ char cmd[1024]; \
+ snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \
+ if (!ASSERT_OK(system(cmd), cmd)) \
+ goto fail; \
+ })
+
+#define NS_TEST "decap_sanity_ns"
+#define IPV6_IFACE_ADDR "face::1"
+#define UDP_TEST_PORT 7777
+
+void test_decap_sanity(void)
+{
+ LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
+ LIBBPF_OPTS(bpf_tc_opts, tc_attach);
+ struct nstoken *nstoken = NULL;
+ struct decap_sanity *skel;
+ struct sockaddr_in6 addr;
+ socklen_t addrlen;
+ char buf[128] = {};
+ int sockfd, err;
+
+ skel = decap_sanity__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+ return;
+
+ SYS("ip netns add %s", NS_TEST);
+ SYS("ip -net %s -6 addr add %s/128 dev lo nodad", NS_TEST, IPV6_IFACE_ADDR);
+ SYS("ip -net %s link set dev lo up", NS_TEST);
+
+ nstoken = open_netns(NS_TEST);
+ if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+ goto fail;
+
+ qdisc_hook.ifindex = if_nametoindex("lo");
+ if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
+ goto fail;
+
+ err = bpf_tc_hook_create(&qdisc_hook);
+ if (!ASSERT_OK(err, "create qdisc hook"))
+ goto fail;
+
+ tc_attach.prog_fd = bpf_program__fd(skel->progs.decap_sanity);
+ err = bpf_tc_attach(&qdisc_hook, &tc_attach);
+ if (!ASSERT_OK(err, "attach filter"))
+ goto fail;
+
+ addrlen = sizeof(addr);
+ err = make_sockaddr(AF_INET6, IPV6_IFACE_ADDR, UDP_TEST_PORT,
+ (void *)&addr, &addrlen);
+ if (!ASSERT_OK(err, "make_sockaddr"))
+ goto fail;
+ sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+ if (!ASSERT_NEQ(sockfd, -1, "socket"))
+ goto fail;
+ err = sendto(sockfd, buf, sizeof(buf), 0, (void *)&addr, addrlen);
+ close(sockfd);
+ if (!ASSERT_EQ(err, sizeof(buf), "send"))
+ goto fail;
+
+ ASSERT_TRUE(skel->bss->init_csum_partial, "init_csum_partial");
+ ASSERT_TRUE(skel->bss->final_csum_none, "final_csum_none");
+ ASSERT_FALSE(skel->bss->broken_csum_start, "broken_csum_start");
+
+fail:
+ if (nstoken) {
+ bpf_tc_hook_destroy(&qdisc_hook);
+ close_netns(nstoken);
+ }
+ system("ip netns del " NS_TEST " >& /dev/null");
+ decap_sanity__destroy(skel);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "jeq_infer_not_null_fail.skel.h"
+
+void test_jeq_infer_not_null(void)
+{
+ RUN_TESTS(jeq_infer_not_null_fail);
+}
#define MAX_STRERR_LEN 256
#define MAX_TEST_NAME 80
+#define __always_unused __attribute__((__unused__))
+
#define _FAIL(errnum, fmt...) \
({ \
error_at_line(0, (errnum), __func__, __LINE__, fmt); \
return socket_loopback_reuseport(family, sotype, -1);
}
-static void test_insert_invalid(int family, int sotype, int mapfd)
+static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
u32 key = 0;
u64 value;
FAIL_ERRNO("map_update: expected EBADF");
}
-static void test_insert_opened(int family, int sotype, int mapfd)
+static void test_insert_opened(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
u32 key = 0;
u64 value;
xclose(s);
}
-static void test_insert_bound(int family, int sotype, int mapfd)
+static void test_insert_bound(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
struct sockaddr_storage addr;
socklen_t len;
xclose(s);
}
-static void test_insert(int family, int sotype, int mapfd)
+static void test_insert(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
u64 value;
u32 key;
xclose(s);
}
-static void test_delete_after_insert(int family, int sotype, int mapfd)
+static void test_delete_after_insert(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
u64 value;
u32 key;
xclose(s);
}
-static void test_delete_after_close(int family, int sotype, int mapfd)
+static void test_delete_after_close(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
int err, s;
u64 value;
FAIL_ERRNO("map_delete: expected EINVAL/EINVAL");
}
-static void test_lookup_after_insert(int family, int sotype, int mapfd)
+static void test_lookup_after_insert(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
u64 cookie, value;
socklen_t len;
xclose(s);
}
-static void test_lookup_after_delete(int family, int sotype, int mapfd)
+static void test_lookup_after_delete(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
int err, s;
u64 value;
xclose(s);
}
-static void test_lookup_32_bit_value(int family, int sotype, int mapfd)
+static void test_lookup_32_bit_value(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
u32 key, value32;
int err, s;
xclose(s);
}
-static void test_update_existing(int family, int sotype, int mapfd)
+static void test_update_existing(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
int s1, s2;
u64 value;
/* Exercise the code path where we destroy child sockets that never
* got accept()'ed, aka orphans, when parent socket gets closed.
*/
-static void test_destroy_orphan_child(int family, int sotype, int mapfd)
+static void do_destroy_orphan_child(int family, int sotype, int mapfd)
{
struct sockaddr_storage addr;
socklen_t len;
xclose(s);
}
+static void test_destroy_orphan_child(struct test_sockmap_listen *skel,
+ int family, int sotype, int mapfd)
+{
+ int msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+ int skb_verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ const struct test {
+ int progfd;
+ enum bpf_attach_type atype;
+ } tests[] = {
+ { -1, -1 },
+ { msg_verdict, BPF_SK_MSG_VERDICT },
+ { skb_verdict, BPF_SK_SKB_VERDICT },
+ };
+ const struct test *t;
+
+ for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+ if (t->progfd != -1 &&
+ xbpf_prog_attach(t->progfd, mapfd, t->atype, 0) != 0)
+ return;
+
+ do_destroy_orphan_child(family, sotype, mapfd);
+
+ if (t->progfd != -1)
+ xbpf_prog_detach2(t->progfd, mapfd, t->atype);
+ }
+}
+
/* Perform a passive open after removing listening socket from SOCKMAP
* to ensure that callbacks get restored properly.
*/
-static void test_clone_after_delete(int family, int sotype, int mapfd)
+static void test_clone_after_delete(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
struct sockaddr_storage addr;
socklen_t len;
* SOCKMAP, but got accept()'ed only after the parent has been removed
* from SOCKMAP, gets cloned without parent psock state or callbacks.
*/
-static void test_accept_after_delete(int family, int sotype, int mapfd)
+static void test_accept_after_delete(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
struct sockaddr_storage addr;
const u32 zero = 0;
/* Check that child socket that got created and accepted while parent
* was in a SOCKMAP is cloned without parent psock state or callbacks.
*/
-static void test_accept_before_delete(int family, int sotype, int mapfd)
+static void test_accept_before_delete(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
struct sockaddr_storage addr;
const u32 zero = 0, one = 1;
return NULL;
}
-static void test_syn_recv_insert_delete(int family, int sotype, int mapfd)
+static void test_syn_recv_insert_delete(struct test_sockmap_listen *skel __always_unused,
+ int family, int sotype, int mapfd)
{
struct connect_accept_ctx ctx = { 0 };
struct sockaddr_storage addr;
return NULL;
}
-static void test_race_insert_listen(int family, int socktype, int mapfd)
+static void test_race_insert_listen(struct test_sockmap_listen *skel __always_unused,
+ int family, int socktype, int mapfd)
{
struct connect_accept_ctx ctx = { 0 };
const u32 zero = 0;
int family, int sotype)
{
const struct op_test {
- void (*fn)(int family, int sotype, int mapfd);
+ void (*fn)(struct test_sockmap_listen *skel,
+ int family, int sotype, int mapfd);
const char *name;
int sotype;
} tests[] = {
if (!test__start_subtest(s))
continue;
- t->fn(family, sotype, map_fd);
+ t->fn(skel, family, sotype, map_fd);
test_ops_cleanup(map);
}
}
#define ICSK_TIME_LOSS_PROBE 5
#define ICSK_TIME_REO_TIMEOUT 6
+#define ETH_HLEN 14
+#define ETH_P_IPV6 0x86DD
+
+#define CHECKSUM_NONE 0
+#define CHECKSUM_PARTIAL 3
+
#define IFNAMSIZ 16
#define RTF_GATEWAY 0x0002
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define UDP_TEST_PORT 7777
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+bool init_csum_partial = false;
+bool final_csum_none = false;
+bool broken_csum_start = false;
+
+static unsigned int skb_headlen(const struct sk_buff *skb)
+{
+ return skb->len - skb->data_len;
+}
+
+static unsigned int skb_headroom(const struct sk_buff *skb)
+{
+ return skb->data - skb->head;
+}
+
+static int skb_checksum_start_offset(const struct sk_buff *skb)
+{
+ return skb->csum_start - skb_headroom(skb);
+}
+
+SEC("tc")
+int decap_sanity(struct __sk_buff *skb)
+{
+ struct sk_buff *kskb;
+ struct ipv6hdr ip6h;
+ struct udphdr udph;
+ int err;
+
+ if (skb->protocol != __bpf_constant_htons(ETH_P_IPV6))
+ return TC_ACT_SHOT;
+
+ if (bpf_skb_load_bytes(skb, ETH_HLEN, &ip6h, sizeof(ip6h)))
+ return TC_ACT_SHOT;
+
+ if (ip6h.nexthdr != IPPROTO_UDP)
+ return TC_ACT_SHOT;
+
+ if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(ip6h), &udph, sizeof(udph)))
+ return TC_ACT_SHOT;
+
+ if (udph.dest != __bpf_constant_htons(UDP_TEST_PORT))
+ return TC_ACT_SHOT;
+
+ kskb = bpf_cast_to_kern_ctx(skb);
+ init_csum_partial = (kskb->ip_summed == CHECKSUM_PARTIAL);
+ err = bpf_skb_adjust_room(skb, -(s32)(ETH_HLEN + sizeof(ip6h) + sizeof(udph)),
+ 1, BPF_F_ADJ_ROOM_FIXED_GSO);
+ if (err)
+ return TC_ACT_SHOT;
+ final_csum_none = (kskb->ip_summed == CHECKSUM_NONE);
+ if (kskb->ip_summed == CHECKSUM_PARTIAL &&
+ (unsigned int)skb_checksum_start_offset(kskb) >= skb_headlen(kskb))
+ broken_csum_start = true;
+
+ return TC_ACT_SHOT;
+}
+
+char __license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, u64);
+ __type(value, u64);
+} m_hash SEC(".maps");
+
+SEC("?raw_tp")
+__failure __msg("R8 invalid mem access 'map_value_or_null")
+int jeq_infer_not_null_ptr_to_btfid(void *ctx)
+{
+ struct bpf_map *map = (struct bpf_map *)&m_hash;
+ struct bpf_map *inner_map = map->inner_map_meta;
+ u64 key = 0, ret = 0, *val;
+
+ val = bpf_map_lookup_elem(map, &key);
+ /* Do not mark ptr as non-null if one of them is
+ * PTR_TO_BTF_ID (R9), reject because of invalid
+ * access to map value (R8).
+ *
+ * Here, we need to inline those insns to access
+ * R8 directly, since compiler may use other reg
+ * once it figures out val==inner_map.
+ */
+ asm volatile("r8 = %[val];\n"
+ "r9 = %[inner_map];\n"
+ "if r8 != r9 goto +1;\n"
+ "%[ret] = *(u64 *)(r8 +0);\n"
+ : [ret] "+r"(ret)
+ : [inner_map] "r"(inner_map), [val] "r"(val)
+ : "r8", "r9");
+
+ return ret;
+}
.result_unpriv = ACCEPT,
.insn_processed = 15,
},
+/* The test performs a conditional 64-bit write to a stack location
+ * fp[-8], this is followed by an unconditional 8-bit write to fp[-8],
+ * then data is read from fp[-8]. This sequence is unsafe.
+ *
+ * The test would be mistakenly marked as safe w/o dst register parent
+ * preservation in verifier.c:copy_register_state() function.
+ *
+ * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the
+ * checkpoint state after conditional 64-bit assignment.
+ */
+{
+ "write tracking and register parent chain bug",
+ .insns = {
+ /* r6 = ktime_get_ns() */
+ BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ /* r0 = ktime_get_ns() */
+ BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+ /* if r0 > r6 goto +1 */
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1),
+ /* *(u64 *)(r10 - 8) = 0xdeadbeef */
+ BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef),
+ /* r1 = 42 */
+ BPF_MOV64_IMM(BPF_REG_1, 42),
+ /* *(u8 *)(r10 - 8) = r1 */
+ BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8),
+ /* r2 = *(u64 *)(r10 - 8) */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8),
+ /* exit(0) */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .flags = BPF_F_TEST_STATE_FREQ,
+ .errstr = "invalid read from stack off -8+1 size 8",
+ .result = REJECT,
+},
# Taking away all CPUs from parent or itself if there are tasks
# will make the partition invalid.
" S+ C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3,A2:2-3 A1:P1,A2:P-1"
+ " S+ C3:P1:S+ C3 . . T P1 . . 0 A1:3,A2:3 A1:P1,A2:P-1"
" S+ $SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
" S+ $SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
bridge vlan add dev $swp2 vid 300
tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \
- protocol 802.1Q flower skip_sw vlan_id 200 \
+ protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \
action vlan modify id 300 \
action goto chain $(IS2 0 0)
# SPDX-License-Identifier: GPL-2.0-only
-/aarch64/aarch32_id_regs
-/aarch64/arch_timer
-/aarch64/debug-exceptions
-/aarch64/get-reg-list
-/aarch64/hypercalls
-/aarch64/page_fault_test
-/aarch64/psci_test
-/aarch64/vcpu_width_config
-/aarch64/vgic_init
-/aarch64/vgic_irq
-/s390x/memop
-/s390x/resets
-/s390x/sync_regs_test
-/s390x/tprot
-/x86_64/amx_test
-/x86_64/cpuid_test
-/x86_64/cr4_cpuid_sync_test
-/x86_64/debug_regs
-/x86_64/exit_on_emulation_failure_test
-/x86_64/fix_hypercall_test
-/x86_64/get_msr_index_features
-/x86_64/kvm_clock_test
-/x86_64/kvm_pv_test
-/x86_64/hyperv_clock
-/x86_64/hyperv_cpuid
-/x86_64/hyperv_evmcs
-/x86_64/hyperv_features
-/x86_64/hyperv_ipi
-/x86_64/hyperv_svm_test
-/x86_64/hyperv_tlb_flush
-/x86_64/max_vcpuid_cap_test
-/x86_64/mmio_warning_test
-/x86_64/monitor_mwait_test
-/x86_64/nested_exceptions_test
-/x86_64/nx_huge_pages_test
-/x86_64/platform_info_test
-/x86_64/pmu_event_filter_test
-/x86_64/set_boot_cpu_id
-/x86_64/set_sregs_test
-/x86_64/sev_migrate_tests
-/x86_64/smaller_maxphyaddr_emulation_test
-/x86_64/smm_test
-/x86_64/state_test
-/x86_64/svm_vmcall_test
-/x86_64/svm_int_ctl_test
-/x86_64/svm_nested_soft_inject_test
-/x86_64/svm_nested_shutdown_test
-/x86_64/sync_regs_test
-/x86_64/tsc_msrs_test
-/x86_64/tsc_scaling_sync
-/x86_64/ucna_injection_test
-/x86_64/userspace_io_test
-/x86_64/userspace_msr_exit_test
-/x86_64/vmx_apic_access_test
-/x86_64/vmx_close_while_nested_test
-/x86_64/vmx_dirty_log_test
-/x86_64/vmx_exception_with_invalid_guest_state
-/x86_64/vmx_invalid_nested_guest_state
-/x86_64/vmx_msrs_test
-/x86_64/vmx_preemption_timer_test
-/x86_64/vmx_set_nested_state_test
-/x86_64/vmx_tsc_adjust_test
-/x86_64/vmx_nested_tsc_scaling_test
-/x86_64/xapic_ipi_test
-/x86_64/xapic_state_test
-/x86_64/xen_shinfo_test
-/x86_64/xen_vmcall_test
-/x86_64/xss_msr_test
-/x86_64/vmx_pmu_caps_test
-/x86_64/triple_fault_event_test
-/access_tracking_perf_test
-/demand_paging_test
-/dirty_log_test
-/dirty_log_perf_test
-/hardware_disable_test
-/kvm_create_max_vcpus
-/kvm_page_table_test
-/max_guest_memory_test
-/memslot_modification_stress_test
-/memslot_perf_test
-/rseq_test
-/set_memory_region_test
-/steal_time
-/kvm_binary_stats_test
-/system_counter_offset_test
+*
+!/**/
+!*.c
+!*.h
+!*.S
+!*.sh
include $(top_srcdir)/scripts/subarch.include
ARCH ?= $(SUBARCH)
-# For cross-builds to work, UNAME_M has to map to ARCH and arch specific
-# directories and targets in this Makefile. "uname -m" doesn't map to
-# arch specific sub-directory names.
-#
-# UNAME_M variable to used to run the compiles pointing to the right arch
-# directories and build the right targets for these supported architectures.
-#
-# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable.
-# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable.
-#
-# x86_64 targets are named to include x86_64 as a suffix and directories
-# for includes are in x86_64 sub-directory. s390x and aarch64 follow the
-# same convention. "uname -m" doesn't result in the correct mapping for
-# s390x and aarch64.
-#
-# No change necessary for x86_64
-UNAME_M := $(shell uname -m)
-
-# Set UNAME_M for arm64 compile/install to work
-ifeq ($(ARCH),arm64)
- UNAME_M := aarch64
-endif
-# Set UNAME_M s390x compile/install to work
-ifeq ($(ARCH),s390)
- UNAME_M := s390x
-endif
-# Set UNAME_M riscv compile/install to work
-ifeq ($(ARCH),riscv)
- UNAME_M := riscv
+ifeq ($(ARCH),x86)
+ ARCH_DIR := x86_64
+else ifeq ($(ARCH),arm64)
+ ARCH_DIR := aarch64
+else ifeq ($(ARCH),s390)
+ ARCH_DIR := s390x
+else
+ ARCH_DIR := $(ARCH)
endif
LIBKVM += lib/assert.c
TEST_GEN_PROGS_riscv += set_memory_region_test
TEST_GEN_PROGS_riscv += kvm_binary_stats_test
-TEST_PROGS += $(TEST_PROGS_$(UNAME_M))
-TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
-TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(UNAME_M))
-LIBKVM += $(LIBKVM_$(UNAME_M))
+TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR))
+TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR))
+TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR))
+LIBKVM += $(LIBKVM_$(ARCH_DIR))
+
+# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most
+# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`,
+# which causes the environment variable to override the makefile).
+include ../lib.mk
INSTALL_HDR_PATH = $(top_srcdir)/usr
LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
endif
CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
+ -Wno-gnu-variable-sized-type-not-at-end \
+ -fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
- -I$(<D) -Iinclude/$(UNAME_M) -I ../rseq -I.. $(EXTRA_CFLAGS) \
+ -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \
$(KHDR_INCLUDES)
-no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
- $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)
+no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
+ $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
# On s390, build the testcases KVM-enabled
-pgste-option = $(call try-run, echo 'int main() { return 0; }' | \
+pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \
$(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste)
LDLIBS += -ldl
LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
-# After inclusion, $(OUTPUT) is defined and
-# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
-include ../lib.mk
-
LIBKVM_C := $(filter %.c,$(LIBKVM))
LIBKVM_S := $(filter %.S,$(LIBKVM))
LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
GUEST_ASSERT(guest_check_lse());
asm volatile(".arch_extension lse\n"
"casal %0, %1, [%2]\n"
- :: "r" (0), "r" (TEST_DATA), "r" (guest_test_memory));
+ :: "r" (0ul), "r" (TEST_DATA), "r" (guest_test_memory));
val = READ_ONCE(*guest_test_memory);
GUEST_ASSERT_EQ(val, TEST_DATA);
}
GUEST_SYNC(CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG);
}
+static void guest_check_no_s1ptw_wr_in_dirty_log(void)
+{
+ GUEST_SYNC(CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG);
+}
+
static void guest_exec(void)
{
int (*code)(void) = (int (*)(void))TEST_EXEC_GVA;
/* Returns true to continue the test, and false if it should be skipped. */
static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
- struct uffd_args *args, bool expect_write)
+ struct uffd_args *args)
{
uint64_t addr = msg->arg.pagefault.address;
uint64_t flags = msg->arg.pagefault.flags;
TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING,
"The only expected UFFD mode is MISSING");
- ASSERT_EQ(!!(flags & UFFD_PAGEFAULT_FLAG_WRITE), expect_write);
ASSERT_EQ(addr, (uint64_t)args->hva);
pr_debug("uffd fault: addr=%p write=%d\n",
return 0;
}
-static int uffd_pt_write_handler(int mode, int uffd, struct uffd_msg *msg)
-{
- return uffd_generic_handler(mode, uffd, msg, &pt_args, true);
-}
-
-static int uffd_data_write_handler(int mode, int uffd, struct uffd_msg *msg)
+static int uffd_pt_handler(int mode, int uffd, struct uffd_msg *msg)
{
- return uffd_generic_handler(mode, uffd, msg, &data_args, true);
+ return uffd_generic_handler(mode, uffd, msg, &pt_args);
}
-static int uffd_data_read_handler(int mode, int uffd, struct uffd_msg *msg)
+static int uffd_data_handler(int mode, int uffd, struct uffd_msg *msg)
{
- return uffd_generic_handler(mode, uffd, msg, &data_args, false);
+ return uffd_generic_handler(mode, uffd, msg, &data_args);
}
static void setup_uffd_args(struct userspace_mem_region *region,
{
struct userspace_mem_region *data_region, *pt_region;
bool continue_test = true;
+ uint64_t pte_gpa, pte_pg;
data_region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA);
pt_region = vm_get_mem_region(vm, MEM_REGION_PT);
+ pte_gpa = addr_hva2gpa(vm, virt_get_pte_hva(vm, TEST_GVA));
+ pte_pg = (pte_gpa - pt_region->region.guest_phys_addr) / getpagesize();
if (cmd == CMD_SKIP_TEST)
continue_test = false;
TEST_ASSERT(check_write_in_dirty_log(vm, data_region, 0),
"Missing write in dirty log");
if (cmd & CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG)
- TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, 0),
+ TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, pte_pg),
"Missing s1ptw write in dirty log");
if (cmd & CMD_CHECK_NO_WRITE_IN_DIRTY_LOG)
TEST_ASSERT(!check_write_in_dirty_log(vm, data_region, 0),
"Unexpected write in dirty log");
if (cmd & CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG)
- TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, 0),
+ TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, pte_pg),
"Unexpected s1ptw write in dirty log");
return continue_test;
.expected_events = { .uffd_faults = _uffd_faults, }, \
}
-#define TEST_DIRTY_LOG(_access, _with_af, _test_check) \
+#define TEST_DIRTY_LOG(_access, _with_af, _test_check, _pt_check) \
{ \
.name = SCAT3(dirty_log, _access, _with_af), \
.data_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \
.guest_prepare = { _PREPARE(_with_af), \
_PREPARE(_access) }, \
.guest_test = _access, \
- .guest_test_check = { _CHECK(_with_af), _test_check, \
- guest_check_s1ptw_wr_in_dirty_log}, \
+ .guest_test_check = { _CHECK(_with_af), _test_check, _pt_check }, \
.expected_events = { 0 }, \
}
#define TEST_UFFD_AND_DIRTY_LOG(_access, _with_af, _uffd_data_handler, \
- _uffd_faults, _test_check) \
+ _uffd_faults, _test_check, _pt_check) \
{ \
.name = SCAT3(uffd_and_dirty_log, _access, _with_af), \
.data_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \
_PREPARE(_access) }, \
.guest_test = _access, \
.mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \
- .guest_test_check = { _CHECK(_with_af), _test_check }, \
+ .guest_test_check = { _CHECK(_with_af), _test_check, _pt_check }, \
.uffd_data_handler = _uffd_data_handler, \
- .uffd_pt_handler = uffd_pt_write_handler, \
+ .uffd_pt_handler = uffd_pt_handler, \
.expected_events = { .uffd_faults = _uffd_faults, }, \
}
#define TEST_RO_MEMSLOT(_access, _mmio_handler, _mmio_exits) \
{ \
- .name = SCAT3(ro_memslot, _access, _with_af), \
+ .name = SCAT2(ro_memslot, _access), \
.data_memslot_flags = KVM_MEM_READONLY, \
+ .pt_memslot_flags = KVM_MEM_READONLY, \
.guest_prepare = { _PREPARE(_access) }, \
.guest_test = _access, \
.mmio_handler = _mmio_handler, \
{ \
.name = SCAT2(ro_memslot_no_syndrome, _access), \
.data_memslot_flags = KVM_MEM_READONLY, \
+ .pt_memslot_flags = KVM_MEM_READONLY, \
.guest_test = _access, \
.fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \
.expected_events = { .fail_vcpu_runs = 1 }, \
#define TEST_RO_MEMSLOT_AND_DIRTY_LOG(_access, _mmio_handler, _mmio_exits, \
_test_check) \
{ \
- .name = SCAT3(ro_memslot, _access, _with_af), \
+ .name = SCAT2(ro_memslot, _access), \
.data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \
- .pt_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \
+ .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \
.guest_prepare = { _PREPARE(_access) }, \
.guest_test = _access, \
.guest_test_check = { _test_check }, \
{ \
.name = SCAT2(ro_memslot_no_syn_and_dlog, _access), \
.data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \
- .pt_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \
+ .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \
.guest_test = _access, \
.guest_test_check = { _test_check }, \
.fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \
{ \
.name = SCAT2(ro_memslot_uffd, _access), \
.data_memslot_flags = KVM_MEM_READONLY, \
+ .pt_memslot_flags = KVM_MEM_READONLY, \
.mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \
.guest_prepare = { _PREPARE(_access) }, \
.guest_test = _access, \
.uffd_data_handler = _uffd_data_handler, \
- .uffd_pt_handler = uffd_pt_write_handler, \
+ .uffd_pt_handler = uffd_pt_handler, \
.mmio_handler = _mmio_handler, \
.expected_events = { .mmio_exits = _mmio_exits, \
.uffd_faults = _uffd_faults }, \
{ \
.name = SCAT2(ro_memslot_no_syndrome, _access), \
.data_memslot_flags = KVM_MEM_READONLY, \
+ .pt_memslot_flags = KVM_MEM_READONLY, \
.mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \
.guest_test = _access, \
.uffd_data_handler = _uffd_data_handler, \
- .uffd_pt_handler = uffd_pt_write_handler, \
+ .uffd_pt_handler = uffd_pt_handler, \
.fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \
.expected_events = { .fail_vcpu_runs = 1, \
.uffd_faults = _uffd_faults }, \
* (S1PTW).
*/
TEST_UFFD(guest_read64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_read_handler, uffd_pt_write_handler, 2),
- /* no_af should also lead to a PT write. */
+ uffd_data_handler, uffd_pt_handler, 2),
TEST_UFFD(guest_read64, no_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_read_handler, uffd_pt_write_handler, 2),
- /* Note how that cas invokes the read handler. */
+ uffd_data_handler, uffd_pt_handler, 2),
TEST_UFFD(guest_cas, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_read_handler, uffd_pt_write_handler, 2),
+ uffd_data_handler, uffd_pt_handler, 2),
/*
* Can't test guest_at with_af as it's IMPDEF whether the AF is set.
* The S1PTW fault should still be marked as a write.
*/
TEST_UFFD(guest_at, no_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_read_handler, uffd_pt_write_handler, 1),
+ uffd_no_handler, uffd_pt_handler, 1),
TEST_UFFD(guest_ld_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_read_handler, uffd_pt_write_handler, 2),
+ uffd_data_handler, uffd_pt_handler, 2),
TEST_UFFD(guest_write64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_write_handler, uffd_pt_write_handler, 2),
+ uffd_data_handler, uffd_pt_handler, 2),
TEST_UFFD(guest_dc_zva, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_write_handler, uffd_pt_write_handler, 2),
+ uffd_data_handler, uffd_pt_handler, 2),
TEST_UFFD(guest_st_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_write_handler, uffd_pt_write_handler, 2),
+ uffd_data_handler, uffd_pt_handler, 2),
TEST_UFFD(guest_exec, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
- uffd_data_read_handler, uffd_pt_write_handler, 2),
+ uffd_data_handler, uffd_pt_handler, 2),
/*
* Try accesses when the data and PT memory regions are both
* tracked for dirty logging.
*/
- TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log),
- /* no_af should also lead to a PT write. */
- TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log),
- TEST_DIRTY_LOG(guest_ld_preidx, with_af, guest_check_no_write_in_dirty_log),
- TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log),
- TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log),
- TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log),
- TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log),
- TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log),
- TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log),
+ TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log,
+ guest_check_no_s1ptw_wr_in_dirty_log),
+ TEST_DIRTY_LOG(guest_ld_preidx, with_af,
+ guest_check_no_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log,
+ guest_check_no_s1ptw_wr_in_dirty_log),
+ TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
/*
* Access when the data and PT memory regions are both marked for
* fault, and nothing in the dirty log. Any S1PTW should result in
* a write in the dirty log and a userfaultfd write.
*/
- TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, uffd_data_read_handler, 2,
- guest_check_no_write_in_dirty_log),
- /* no_af should also lead to a PT write. */
- TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, uffd_data_read_handler, 2,
- guest_check_no_write_in_dirty_log),
- TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, uffd_data_read_handler,
- 2, guest_check_no_write_in_dirty_log),
- TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, 0, 1,
- guest_check_no_write_in_dirty_log),
- TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, uffd_data_read_handler, 2,
- guest_check_no_write_in_dirty_log),
- TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, uffd_data_write_handler,
- 2, guest_check_write_in_dirty_log),
- TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, uffd_data_read_handler, 2,
- guest_check_write_in_dirty_log),
- TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, uffd_data_write_handler,
- 2, guest_check_write_in_dirty_log),
+ TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af,
+ uffd_data_handler, 2,
+ guest_check_no_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af,
+ uffd_data_handler, 2,
+ guest_check_no_write_in_dirty_log,
+ guest_check_no_s1ptw_wr_in_dirty_log),
+ TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af,
+ uffd_data_handler,
+ 2, guest_check_no_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, uffd_no_handler, 1,
+ guest_check_no_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af,
+ uffd_data_handler, 2,
+ guest_check_no_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af,
+ uffd_data_handler,
+ 2, guest_check_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af,
+ uffd_data_handler, 2,
+ guest_check_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
+ TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af,
+ uffd_data_handler,
+ 2, guest_check_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
TEST_UFFD_AND_DIRTY_LOG(guest_st_preidx, with_af,
- uffd_data_write_handler, 2,
- guest_check_write_in_dirty_log),
-
+ uffd_data_handler, 2,
+ guest_check_write_in_dirty_log,
+ guest_check_s1ptw_wr_in_dirty_log),
/*
- * Try accesses when the data memory region is marked read-only
+ * Access when both the PT and data regions are marked read-only
* (with KVM_MEM_READONLY). Writes with a syndrome result in an
* MMIO exit, writes with no syndrome (e.g., CAS) result in a
* failed vcpu run, and reads/execs with and without syndroms do
TEST_RO_MEMSLOT_NO_SYNDROME(guest_st_preidx),
/*
- * Access when both the data region is both read-only and marked
+ * The PT and data regions are both read-only and marked
* for dirty logging at the same time. The expected result is that
* for writes there should be no write in the dirty log. The
* readonly handling is the same as if the memslot was not marked
guest_check_no_write_in_dirty_log),
/*
- * Access when the data region is both read-only and punched with
+ * The PT and data regions are both read-only and punched with
* holes tracked with userfaultfd. The expected result is the
* union of both userfaultfd and read-only behaviors. For example,
* write accesses result in a userfaultfd write fault and an MMIO
* no userfaultfd write fault. Reads result in userfaultfd getting
* triggered.
*/
- TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0,
- uffd_data_read_handler, 2),
- TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0,
- uffd_data_read_handler, 2),
- TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0,
- uffd_no_handler, 1),
- TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0,
- uffd_data_read_handler, 2),
+ TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0, uffd_data_handler, 2),
+ TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0, uffd_data_handler, 2),
+ TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0, uffd_no_handler, 1),
+ TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0, uffd_data_handler, 2),
TEST_RO_MEMSLOT_AND_UFFD(guest_write64, mmio_on_test_gpa_handler, 1,
- uffd_data_write_handler, 2),
- TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas,
- uffd_data_read_handler, 2),
- TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva,
- uffd_no_handler, 1),
- TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx,
- uffd_no_handler, 1),
+ uffd_data_handler, 2),
+ TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas, uffd_data_handler, 2),
+ TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva, uffd_no_handler, 1),
+ TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx, uffd_no_handler, 1),
{ 0 }
};
void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
{
- virt_pg_map(vm, mmio_gpa, mmio_gpa);
+ vm_vaddr_t mmio_gva = vm_vaddr_unused_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR);
+
+ virt_map(vm, mmio_gva, mmio_gpa, 1);
vm->ucall_mmio_addr = mmio_gpa;
- write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gpa);
+ write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva);
}
void ucall_arch_do_ucall(vm_vaddr_t uc)
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
+/*
+ * Initializes vm->vpages_valid to match the canonical VA space of the
+ * architecture.
+ *
+ * The default implementation is valid for architectures which split the
+ * range addressed by a single page table into a low and high region
+ * based on the MSB of the VA. On architectures with this behavior
+ * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1].
+ */
__weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm)
{
sparsebit_set_num(vm->vpages_valid,
while (npages--) {
virt_pg_map(vm, vaddr, paddr);
+ sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
+
vaddr += page_size;
paddr += page_size;
-
- sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
}
}
#include "linux/bitmap.h"
#include "linux/atomic.h"
+#define GUEST_UCALL_FAILED -1
+
struct ucall_header {
DECLARE_BITMAP(in_use, KVM_MAX_VCPUS);
struct ucall ucalls[KVM_MAX_VCPUS];
struct ucall *uc;
int i;
- GUEST_ASSERT(ucall_pool);
+ if (!ucall_pool)
+ goto ucall_failed;
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
if (!test_and_set_bit(i, ucall_pool->in_use)) {
}
}
- GUEST_ASSERT(0);
+ucall_failed:
+ /*
+ * If the vCPU cannot grab a ucall structure, make a bare ucall with a
+ * magic value to signal to get_ucall() that things went sideways.
+ * GUEST_ASSERT() depends on ucall_alloc() and so cannot be used here.
+ */
+ ucall_arch_do_ucall(GUEST_UCALL_FAILED);
return NULL;
}
addr = ucall_arch_get_ucall(vcpu);
if (addr) {
+ TEST_ASSERT(addr != (void *)GUEST_UCALL_FAILED,
+ "Guest failed to allocate ucall struct");
+
memcpy(uc, addr, sizeof(*uc));
vcpu_run_complete_io(vcpu);
} else {
void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
{
if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) {
- *pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
+ *pa_bits = kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
*va_bits = 32;
} else {
*pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR);
slots = data->nslots;
while (--slots > 1) {
pages_per_slot = mempages / slots;
+ if (!pages_per_slot)
+ continue;
+
rempages = mempages % pages_per_slot;
if (check_slot_pages(host_page_size, guest_page_size,
pages_per_slot, rempages))
GUEST_SYNC(stage++);
/*
* 'XMM Fast' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL.
- * Nothing to write anything to XMM regs.
*/
+ ipi_ex->vp_set.valid_bank_mask = 0;
+ hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 2);
hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT,
IPI_VECTOR, HV_GENERIC_SET_ALL);
nop_loop();
while ((opt = getopt(argc, argv, "hp:t:r")) != -1) {
switch (opt) {
case 'p':
- reclaim_period_ms = atoi_non_negative("Reclaim period", optarg);
+ reclaim_period_ms = atoi_positive("Reclaim period", optarg);
break;
case 't':
token = atoi_paranoid(optarg);
static void l2_guest_code_int(void)
{
GUEST_ASSERT_1(int_fired == 1, int_fired);
- vmmcall();
- ud2();
+
+ /*
+ * Same as the vmmcall() function, but with a ud2 sneaked after the
+ * vmmcall. The caller injects an exception with the return address
+ * increased by 2, so the "pop rbp" must be after the ud2 and we cannot
+ * use vmmcall() directly.
+ */
+ __asm__ __volatile__("push %%rbp; vmmcall; ud2; pop %%rbp"
+ : : "a"(0xdeadbeef), "c"(0xbeefdead)
+ : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+ "r10", "r11", "r12", "r13", "r14", "r15");
GUEST_ASSERT_1(bp_fired == 1, bp_fired);
hlt();
NUM_VMX_PAGES,
};
-struct kvm_single_msr {
- struct kvm_msrs header;
- struct kvm_msr_entry entry;
-} __attribute__((packed));
-
/* The virtual machine object. */
static struct kvm_vm *vm;
int main(int argc, char *argv[])
{
struct timespec min_ts, max_ts, vm_ts;
+ struct kvm_xen_hvm_attr evt_reset;
struct kvm_vm *vm;
pthread_t thread;
bool verbose;
}
done:
+ evt_reset.type = KVM_XEN_ATTR_TYPE_EVTCHN;
+ evt_reset.u.evtchn.flags = KVM_XEN_EVTCHN_RESET;
+ vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
+
alarm(0);
clock_gettime(CLOCK_REALTIME, &max_ts);
ifeq ($(CROSS_COMPILE),)
ifeq ($(CLANG_TARGET_FLAGS),)
-$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk
+$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk)
else
CLANG_FLAGS += --target=$(CLANG_TARGET_FLAGS)
endif # CLANG_TARGET_FLAGS
# SPDX-License-Identifier: GPL-2.0-only
bind_bhash
+bind_timewait
csum
cmsg_sender
diag_uid
wait_for_signal(pipefd[0]);
if (connect(cfd, (struct sockaddr *)consumer_addr,
- sizeof(struct sockaddr)) != 0) {
+ sizeof(*consumer_addr)) != 0) {
perror("Connect failed");
kill(0, SIGTERM);
exit(1);
readonly V6_ADDR0=2001:db8:91::1
readonly V6_ADDR1=2001:db8:91::2
nsid=100
+ret=0
cleanup_v6()
{
ip netns del me
ip netns del peer
- sysctl -w net.ipv4.conf.veth0.ndisc_evict_nocarrier=1 >/dev/null 2>&1
- sysctl -w net.ipv4.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+ sysctl -w net.ipv6.conf.veth1.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+ sysctl -w net.ipv6.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
}
create_ns()
if [ $? -ne 0 ]; then
cleanup_v6
echo "failed"
- exit
+ exit 1
fi
# Set veth2 down, which will put veth1 in NOCARRIER state
if [ $? -ne 0 ]; then
cleanup_v4
echo "failed"
- exit
+ exit 1
fi
# Set veth1 down, which will put veth0 in NOCARRIER state
if [ $? -eq 0 ];then
echo "failed"
+ ret=1
else
echo "ok"
fi
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v4
if [ $? -eq 0 ];then
echo "failed"
+ ret=1
else
echo "ok"
fi
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v6
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v6
fi
run_all_tests
+exit $ret
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "../kselftest_harness.h"
+
+FIXTURE(bind_timewait)
+{
+ struct sockaddr_in addr;
+ socklen_t addrlen;
+};
+
+FIXTURE_VARIANT(bind_timewait)
+{
+ __u32 addr_const;
+};
+
+FIXTURE_VARIANT_ADD(bind_timewait, localhost)
+{
+ .addr_const = INADDR_LOOPBACK
+};
+
+FIXTURE_VARIANT_ADD(bind_timewait, addrany)
+{
+ .addr_const = INADDR_ANY
+};
+
+FIXTURE_SETUP(bind_timewait)
+{
+ self->addr.sin_family = AF_INET;
+ self->addr.sin_port = 0;
+ self->addr.sin_addr.s_addr = htonl(variant->addr_const);
+ self->addrlen = sizeof(self->addr);
+}
+
+FIXTURE_TEARDOWN(bind_timewait)
+{
+}
+
+void create_timewait_socket(struct __test_metadata *_metadata,
+ FIXTURE_DATA(bind_timewait) *self)
+{
+ int server_fd, client_fd, child_fd, ret;
+ struct sockaddr_in addr;
+ socklen_t addrlen;
+
+ server_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(server_fd, 0);
+
+ ret = bind(server_fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ ret = listen(server_fd, 1);
+ ASSERT_EQ(ret, 0);
+
+ ret = getsockname(server_fd, (struct sockaddr *)&self->addr, &self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ client_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(client_fd, 0);
+
+ ret = connect(client_fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ addrlen = sizeof(addr);
+ child_fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen);
+ ASSERT_GT(child_fd, 0);
+
+ close(child_fd);
+ close(client_fd);
+ close(server_fd);
+}
+
+TEST_F(bind_timewait, 1)
+{
+ int fd, ret;
+
+ create_timewait_socket(_metadata, self);
+
+ fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(fd, 0);
+
+ ret = bind(fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, -1);
+ ASSERT_EQ(errno, EADDRINUSE);
+
+ close(fd);
+}
+
+TEST_HARNESS_MAIN
NS=ns
IP6=2001:db8:1::1/64
TGT6=2001:db8:1::2
-TMPF=`mktemp`
+TMPF=$(mktemp --suffix ".pcap")
cleanup()
{
static void cs_parse_args(int argc, char *argv[])
{
- char o;
+ int o;
while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) {
switch (o) {
PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
IP="ip -netns testns"
+IP_PEER="ip -netns peerns"
RTABLE=100
+RTABLE_PEER=101
GW_IP4=192.51.100.2
SRC_IP=192.51.100.3
GW_IP6=2001:db8:1::2
DEV_ADDR=192.51.100.1
DEV_ADDR6=2001:db8:1::1
DEV=dummy0
-TESTS="fib_rule6 fib_rule4"
+TESTS="fib_rule6 fib_rule4 fib_rule6_connect fib_rule4_connect"
+
+SELFTEST_PATH=""
log_test()
{
echo "######################################################################"
}
+check_nettest()
+{
+ if which nettest > /dev/null 2>&1; then
+ return 0
+ fi
+
+ # Add the selftest directory to PATH if not already done
+ if [ "${SELFTEST_PATH}" = "" ]; then
+ SELFTEST_PATH="$(dirname $0)"
+ PATH="${PATH}:${SELFTEST_PATH}"
+
+ # Now retry with the new path
+ if which nettest > /dev/null 2>&1; then
+ return 0
+ fi
+
+ if [ "${ret}" -eq 0 ]; then
+ ret="${ksft_skip}"
+ fi
+ echo "nettest not found (try 'make -C ${SELFTEST_PATH} nettest')"
+ fi
+
+ return 1
+}
+
setup()
{
set -e
ip netns del testns
}
+setup_peer()
+{
+ set -e
+
+ ip netns add peerns
+ $IP_PEER link set dev lo up
+
+ ip link add name veth0 netns testns type veth \
+ peer name veth1 netns peerns
+ $IP link set dev veth0 up
+ $IP_PEER link set dev veth1 up
+
+ $IP address add 192.0.2.10 peer 192.0.2.11/32 dev veth0
+ $IP_PEER address add 192.0.2.11 peer 192.0.2.10/32 dev veth1
+
+ $IP address add 2001:db8::10 peer 2001:db8::11/128 dev veth0 nodad
+ $IP_PEER address add 2001:db8::11 peer 2001:db8::10/128 dev veth1 nodad
+
+ $IP_PEER address add 198.51.100.11/32 dev lo
+ $IP route add table $RTABLE_PEER 198.51.100.11/32 via 192.0.2.11
+
+ $IP_PEER address add 2001:db8::1:11/128 dev lo
+ $IP route add table $RTABLE_PEER 2001:db8::1:11/128 via 2001:db8::11
+
+ set +e
+}
+
+cleanup_peer()
+{
+ $IP link del dev veth0
+ ip netns del peerns
+}
+
fib_check_iproute_support()
{
ip rule help 2>&1 | grep -q $1
fi
}
+# Verify that the IPV6_TCLASS option of UDPv6 and TCPv6 sockets is properly
+# taken into account when connecting the socket and when sending packets.
+fib_rule6_connect_test()
+{
+ local dsfield
+
+ if ! check_nettest; then
+ echo "SKIP: Could not run test without nettest tool"
+ return
+ fi
+
+ setup_peer
+ $IP -6 rule add dsfield 0x04 table $RTABLE_PEER
+
+ # Combine the base DS Field value (0x04) with all possible ECN values
+ # (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3).
+ # The ECN bits shouldn't influence the result of the test.
+ for dsfield in 0x04 0x05 0x06 0x07; do
+ nettest -q -6 -B -t 5 -N testns -O peerns -U -D \
+ -Q "${dsfield}" -l 2001:db8::1:11 -r 2001:db8::1:11
+ log_test $? 0 "rule6 dsfield udp connect (dsfield ${dsfield})"
+
+ nettest -q -6 -B -t 5 -N testns -O peerns -Q "${dsfield}" \
+ -l 2001:db8::1:11 -r 2001:db8::1:11
+ log_test $? 0 "rule6 dsfield tcp connect (dsfield ${dsfield})"
+ done
+
+ $IP -6 rule del dsfield 0x04 table $RTABLE_PEER
+ cleanup_peer
+}
+
fib_rule4_del()
{
$IP rule del $1
fi
}
+# Verify that the IP_TOS option of UDPv4 and TCPv4 sockets is properly taken
+# into account when connecting the socket and when sending packets.
+fib_rule4_connect_test()
+{
+ local dsfield
+
+ if ! check_nettest; then
+ echo "SKIP: Could not run test without nettest tool"
+ return
+ fi
+
+ setup_peer
+ $IP -4 rule add dsfield 0x04 table $RTABLE_PEER
+
+ # Combine the base DS Field value (0x04) with all possible ECN values
+ # (Not-ECT: 0, ECT(1): 1, ECT(0): 2, CE: 3).
+ # The ECN bits shouldn't influence the result of the test.
+ for dsfield in 0x04 0x05 0x06 0x07; do
+ nettest -q -B -t 5 -N testns -O peerns -D -U -Q "${dsfield}" \
+ -l 198.51.100.11 -r 198.51.100.11
+ log_test $? 0 "rule4 dsfield udp connect (dsfield ${dsfield})"
+
+ nettest -q -B -t 5 -N testns -O peerns -Q "${dsfield}" \
+ -l 198.51.100.11 -r 198.51.100.11
+ log_test $? 0 "rule4 dsfield tcp connect (dsfield ${dsfield})"
+ done
+
+ $IP -4 rule del dsfield 0x04 table $RTABLE_PEER
+ cleanup_peer
+}
+
run_fibrule_tests()
{
log_section "IPv4 fib rule"
case $t in
fib_rule6_test|fib_rule6) fib_rule6_test;;
fib_rule4_test|fib_rule4) fib_rule4_test;;
+ fib_rule6_connect_test|fib_rule6_connect) fib_rule6_connect_test;;
+ fib_rule4_connect_test|fib_rule4_connect) fib_rule4_connect_test;;
help) echo "Test names: $TESTS"; exit 0;;
local value=$1; shift
SYSCTL_ORIG[$key]=$(sysctl -n $key)
- sysctl -qw $key=$value
+ sysctl -qw $key="$value"
}
sysctl_restore()
{
local key=$1; shift
- sysctl -qw $key=${SYSCTL_ORIG["$key"]}
+ sysctl -qw $key="${SYSCTL_ORIG[$key]}"
}
forwarding_enable()
# In addition this script also checks if forcing a specific field in the
# outer header is working.
+# Return 4 by default (Kselftest SKIP code)
+ERR=4
+
if [ "$(id -u)" != "0" ]; then
echo "Please run as root."
- exit 0
+ exit $ERR
fi
if ! which tcpdump > /dev/null 2>&1; then
echo "No tcpdump found. Required for this test."
- exit 0
+ exit $ERR
fi
expected_tos="0x00"
expected_ttl="0"
failed=false
+readonly NS0=$(mktemp -u ns0-XXXXXXXX)
+readonly NS1=$(mktemp -u ns1-XXXXXXXX)
+
+RUN_NS0="ip netns exec ${NS0}"
+
get_random_tos() {
# Get a random hex tos value between 0x00 and 0xfc, a multiple of 4
echo "0x$(tr -dc '0-9a-f' < /dev/urandom | head -c 1)\
local vlan="$5"
local test_tos="0x00"
local test_ttl="0"
- local ns="ip netns exec testing"
# We don't want a test-tos of 0x00,
# because this is the value that we get when no tos is set.
printf "│%7s │%6s │%6s │%13s │%13s │%6s │" \
"$type" "$outer" "$inner" "$tos" "$ttl" "$vlan"
- # Create 'testing' netns, veth pair and connect main ns with testing ns
- ip netns add testing
- ip link add type veth
- ip link set veth1 netns testing
- ip link set veth0 up
- $ns ip link set veth1 up
- ip addr flush dev veth0
- $ns ip addr flush dev veth1
+ # Create netns NS0 and NS1 and connect them with a veth pair
+ ip netns add "${NS0}"
+ ip netns add "${NS1}"
+ ip link add name veth0 netns "${NS0}" type veth \
+ peer name veth1 netns "${NS1}"
+ ip -netns "${NS0}" link set dev veth0 up
+ ip -netns "${NS1}" link set dev veth1 up
+ ip -netns "${NS0}" address flush dev veth0
+ ip -netns "${NS1}" address flush dev veth1
local local_addr1=""
local local_addr2=""
if [ "$type" = "gre" ]; then
type="gretap"
fi
- ip addr add 198.18.0.1/24 dev veth0
- $ns ip addr add 198.18.0.2/24 dev veth1
- ip link add name tep0 type $type $local_addr1 remote \
- 198.18.0.2 tos $test_tos ttl $test_ttl $vxlan $geneve
- $ns ip link add name tep1 type $type $local_addr2 remote \
- 198.18.0.1 tos $test_tos ttl $test_ttl $vxlan $geneve
+ ip -netns "${NS0}" address add 198.18.0.1/24 dev veth0
+ ip -netns "${NS1}" address add 198.18.0.2/24 dev veth1
+ ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \
+ remote 198.18.0.2 tos $test_tos ttl $test_ttl \
+ $vxlan $geneve
+ ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \
+ remote 198.18.0.1 tos $test_tos ttl $test_ttl \
+ $vxlan $geneve
elif [ "$outer" = "6" ]; then
if [ "$type" = "gre" ]; then
type="ip6gretap"
fi
- ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0
- $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1
- ip link add name tep0 type $type $local_addr1 \
- remote fdd1:ced0:5d88:3fce::2 tos $test_tos ttl $test_ttl \
- $vxlan $geneve
- $ns ip link add name tep1 type $type $local_addr2 \
- remote fdd1:ced0:5d88:3fce::1 tos $test_tos ttl $test_ttl \
- $vxlan $geneve
+ ip -netns "${NS0}" address add fdd1:ced0:5d88:3fce::1/64 \
+ dev veth0 nodad
+ ip -netns "${NS1}" address add fdd1:ced0:5d88:3fce::2/64 \
+ dev veth1 nodad
+ ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \
+ remote fdd1:ced0:5d88:3fce::2 tos $test_tos \
+ ttl $test_ttl $vxlan $geneve
+ ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \
+ remote fdd1:ced0:5d88:3fce::1 tos $test_tos \
+ ttl $test_ttl $vxlan $geneve
fi
# Bring L2-tunnel link up and create VLAN on top
- ip link set tep0 up
- $ns ip link set tep1 up
- ip addr flush dev tep0
- $ns ip addr flush dev tep1
+ ip -netns "${NS0}" link set tep0 up
+ ip -netns "${NS1}" link set tep1 up
+ ip -netns "${NS0}" address flush dev tep0
+ ip -netns "${NS1}" address flush dev tep1
local parent
if $vlan; then
parent="vlan99-"
- ip link add link tep0 name ${parent}0 type vlan id 99
- $ns ip link add link tep1 name ${parent}1 type vlan id 99
- ip link set ${parent}0 up
- $ns ip link set ${parent}1 up
- ip addr flush dev ${parent}0
- $ns ip addr flush dev ${parent}1
+ ip -netns "${NS0}" link add link tep0 name ${parent}0 \
+ type vlan id 99
+ ip -netns "${NS1}" link add link tep1 name ${parent}1 \
+ type vlan id 99
+ ip -netns "${NS0}" link set dev ${parent}0 up
+ ip -netns "${NS1}" link set dev ${parent}1 up
+ ip -netns "${NS0}" address flush dev ${parent}0
+ ip -netns "${NS1}" address flush dev ${parent}1
else
parent="tep"
fi
# Assign inner IPv4/IPv6 addresses
if [ "$inner" = "4" ] || [ "$inner" = "other" ]; then
- ip addr add 198.19.0.1/24 brd + dev ${parent}0
- $ns ip addr add 198.19.0.2/24 brd + dev ${parent}1
+ ip -netns "${NS0}" address add 198.19.0.1/24 brd + dev ${parent}0
+ ip -netns "${NS1}" address add 198.19.0.2/24 brd + dev ${parent}1
elif [ "$inner" = "6" ]; then
- ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0
- $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1
+ ip -netns "${NS0}" address add fdd4:96cf:4eae:443b::1/64 \
+ dev ${parent}0 nodad
+ ip -netns "${NS1}" address add fdd4:96cf:4eae:443b::2/64 \
+ dev ${parent}1 nodad
fi
}
ping_dst="198.19.0.3" # Generates ARPs which are not IPv4/IPv6
fi
if [ "$tos_ttl" = "inherit" ]; then
- ping -i 0.1 $ping_dst -Q "$expected_tos" -t "$expected_ttl" \
- 2>/dev/null 1>&2 & ping_pid="$!"
+ ${RUN_NS0} ping -i 0.1 $ping_dst -Q "$expected_tos" \
+ -t "$expected_ttl" 2>/dev/null 1>&2 & ping_pid="$!"
else
- ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!"
+ ${RUN_NS0} ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!"
fi
local tunnel_type_offset tunnel_type_proto req_proto_offset req_offset
if [ "$type" = "gre" ]; then
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x01 and \
- ip[$req_offset] = 0x08 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x01 and \
+ ip[$req_offset] = 0x08 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "6" ]; then
req_proto_offset="44"
req_offset="78"
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x3a and \
- ip[$req_offset] = 0x80 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x3a and \
+ ip[$req_offset] = 0x80 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "other" ]; then
req_proto_offset="36"
req_offset="45"
expected_tos="0x00"
expected_ttl="64"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x08 and \
- ip[$((req_proto_offset + 1))] = 0x06 and \
- ip[$req_offset] = 0x01 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x08 and \
+ ip[$((req_proto_offset + 1))] = 0x06 and \
+ ip[$req_offset] = 0x01 2>/dev/null \
+ | head -n 1)"
fi
elif [ "$outer" = "6" ]; then
if [ "$type" = "gre" ]; then
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x01 and \
- ip6[$req_offset] = 0x08 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x01 and \
+ ip6[$req_offset] = 0x08 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "6" ]; then
local req_proto_offset="72"
local req_offset="106"
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x3a and \
- ip6[$req_offset] = 0x80 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x3a and \
+ ip6[$req_offset] = 0x80 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "other" ]; then
local req_proto_offset="64"
local req_offset="73"
expected_tos="0x00"
expected_ttl="64"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x08 and \
- ip6[$((req_proto_offset + 1))] = 0x06 and \
- ip6[$req_offset] = 0x01 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x08 and \
+ ip6[$((req_proto_offset + 1))] = 0x06 and \
+ ip6[$req_offset] = 0x01 2>/dev/null \
+ | head -n 1)"
fi
fi
kill -9 $ping_pid
- wait $ping_pid 2>/dev/null
+ wait $ping_pid 2>/dev/null || true
result="FAIL"
if [ "$outer" = "4" ]; then
captured_ttl="$(get_field "ttl" "$out")"
}
cleanup() {
- ip link del veth0 2>/dev/null
- ip netns del testing 2>/dev/null
- ip link del tep0 2>/dev/null
+ ip netns del "${NS0}" 2>/dev/null
+ ip netns del "${NS1}" 2>/dev/null
}
+exit_handler() {
+ # Don't exit immediately if one of the intermediate commands fails.
+ # We might be called at the end of the script, when the network
+ # namespaces have already been deleted. So cleanup() may fail, but we
+ # still need to run until 'exit $ERR' or the script won't return the
+ # correct error code.
+ set +e
+
+ cleanup
+
+ exit $ERR
+}
+
+# Restore the default SIGINT handler (just in case) and exit.
+# The exit handler will take care of cleaning everything up.
+interrupted() {
+ trap - INT
+
+ exit $ERR
+}
+
+set -e
+trap exit_handler EXIT
+trap interrupted INT
+
printf "┌────────┬───────┬───────┬──────────────┬"
printf "──────────────┬───────┬────────┐\n"
for type in gre vxlan geneve; do
printf "└────────┴───────┴───────┴──────────────┴"
printf "──────────────┴───────┴────────┘\n"
+# All tests done.
+# Set ERR appropriately: it will be returned by the exit handler.
if $failed; then
- exit 1
+ ERR=1
+else
+ ERR=0
fi
kill_wait $evts_ns2_pid
}
+kill_tests_wait()
+{
+ kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1)
+ wait
+}
+
pm_nl_set_limits()
{
local ns=$1
local subflow_nr=$3
local cnt1
local cnt2
+ local dump_stats
if [ -n "${need_title}" ]; then
printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}"
echo "[ ok ]"
fi
- [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint )
+ if [ "${dump_stats}" = 1 ]; then
+ ss -N $ns1 -tOni
+ ss -N $ns1 -tOni | grep token
+ ip -n $ns1 mptcp endpoint
+ dump_stats
+ fi
}
chk_link_usage()
pm_nl_set_limits $ns1 2 2
pm_nl_set_limits $ns2 2 2
pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
- run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow &
+ run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null &
wait_mpj $ns1
pm_nl_check_endpoint 1 "creation" \
pm_nl_add_endpoint $ns2 10.0.2.2 flags signal
pm_nl_check_endpoint 0 "modif is allowed" \
$ns2 10.0.2.2 id 1 flags signal
- wait
+ kill_tests_wait
fi
if reset "delete and re-add"; then
pm_nl_set_limits $ns1 1 1
pm_nl_set_limits $ns2 1 1
pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
- run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow &
+ run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null &
wait_mpj $ns2
pm_nl_del_endpoint $ns2 2 10.0.2.2
pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
wait_mpj $ns2
chk_subflow_nr "" "after re-add" 2
- wait
+ kill_tests_wait
fi
}
"$server4_token" > /dev/null 2>&1
}
+test_subflows_v4_v6_mix()
+{
+ # Attempt to add a listener at 10.0.2.1:<subflow-port>
+ ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
+ $app6_port > /dev/null 2>&1 &
+ local listener_pid=$!
+
+ # ADD_ADDR4 from server to client machine reusing the subflow port on
+ # the established v6 connection
+ :>"$client_evts"
+ ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\
+ $server_addr_id dev ns1eth2 > /dev/null 2>&1
+ stdbuf -o0 -e0 printf "ADD_ADDR4 id:%d 10.0.2.1 (ns1) => ns2, reuse port\t\t" $server_addr_id
+ sleep 0.5
+ verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\
+ "$server_addr_id" "$app6_port"
+
+ # CREATE_SUBFLOW from client to server machine
+ :>"$client_evts"
+ ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
+ $app6_port token "$client6_token" > /dev/null 2>&1
+ sleep 0.5
+ verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\
+ "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
+ "$server_addr_id" "ns2" "ns1"
+
+ # Delete the listener from the server ns, if one was created
+ kill_wait $listener_pid
+
+ sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
+
+ # DESTROY_SUBFLOW from client to server machine
+ :>"$client_evts"
+ ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
+ $app6_port token "$client6_token" > /dev/null 2>&1
+ sleep 0.5
+ verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client6_token" \
+ "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
+ "$server_addr_id" "ns2" "ns1"
+
+ # RM_ADDR from server to client machine
+ ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
+ "$server6_token" > /dev/null 2>&1
+ sleep 0.5
+}
+
test_prio()
{
local count
test_announce
test_remove
test_subflows
+test_subflows_v4_v6_mix
test_prio
test_listener
int use_setsockopt;
int use_freebind;
int use_cmsg;
+ uint8_t dsfield;
const char *dev;
const char *server_dev;
int ifindex;
return rc;
}
+static int set_dsfield(int sd, int version, int dsfield)
+{
+ if (!dsfield)
+ return 0;
+
+ switch (version) {
+ case AF_INET:
+ if (setsockopt(sd, SOL_IP, IP_TOS, &dsfield,
+ sizeof(dsfield)) < 0) {
+ log_err_errno("setsockopt(IP_TOS)");
+ return -1;
+ }
+ break;
+
+ case AF_INET6:
+ if (setsockopt(sd, SOL_IPV6, IPV6_TCLASS, &dsfield,
+ sizeof(dsfield)) < 0) {
+ log_err_errno("setsockopt(IPV6_TCLASS)");
+ return -1;
+ }
+ break;
+
+ default:
+ log_error("Invalid address family\n");
+ return -1;
+ }
+
+ return 0;
+}
+
static int str_to_uint(const char *str, int min, int max, unsigned int *value)
{
int number;
(char *)&one, sizeof(one)) < 0)
log_err_errno("Setting SO_BROADCAST error");
+ if (set_dsfield(sd, AF_INET, args->dsfield) != 0)
+ goto out_err;
+
if (args->dev && bind_to_device(sd, args->dev) != 0)
goto out_err;
else if (args->use_setsockopt &&
if (set_reuseport(sd) != 0)
goto err;
+ if (set_dsfield(sd, args->version, args->dsfield) != 0)
+ goto err;
+
if (args->dev && bind_to_device(sd, args->dev) != 0)
goto err;
else if (args->use_setsockopt &&
if (set_reuseport(sd) != 0)
goto err;
+ if (set_dsfield(sd, args->version, args->dsfield) != 0)
+ goto err;
+
if (args->dev && bind_to_device(sd, args->dev) != 0)
goto err;
else if (args->use_setsockopt &&
return client_status;
}
-#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf"
+#define GETOPT_STR "sr:l:c:Q:p:t:g:P:DRn:M:X:m:d:I:BN:O:SUCi6xL:0:1:2:3:Fbqf"
#define OPT_FORCE_BIND_KEY_IFINDEX 1001
#define OPT_NO_BIND_KEY_IFINDEX 1002
" -D|R datagram (D) / raw (R) socket (default stream)\n"
" -l addr local address to bind to in server mode\n"
" -c addr local address to bind to in client mode\n"
+ " -Q dsfield DS Field value of the socket (the IP_TOS or\n"
+ " IPV6_TCLASS socket option)\n"
" -x configure XFRM policy on socket\n"
"\n"
" -d dev bind socket to given device name\n"
args.has_local_ip = 1;
args.client_local_addr_str = optarg;
break;
+ case 'Q':
+ if (str_to_uint(optarg, 0, 255, &tmp) != 0) {
+ fprintf(stderr, "Invalid DS Field\n");
+ return 1;
+ }
+ args.dsfield = tmp;
+ break;
case 'p':
if (str_to_uint(optarg, 1, 65535, &tmp) != 0) {
fprintf(stderr, "Invalid port\n");
elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then
# Add per vni group config with 'bridge vni' api
if [ -n "$group" ]; then
- if [ "$family" == "v4" ]; then
- if [ $mcast -eq 1 ]; then
- bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group
- else
- bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group
- fi
- else
- if [ $mcast -eq 1 ]; then
- bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group6 $group
- else
- bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote6 $group
- fi
- fi
+ if [ $mcast -eq 1 ]; then
+ bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group
+ else
+ bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group
+ fi
fi
fi
done
}
/* A single TPACKET_V3 block can hold multiple frames */
-static void recv_block(struct ring_state *ring)
+static bool recv_block(struct ring_state *ring)
{
struct tpacket_block_desc *block;
char *frame;
block = (void *)(ring->mmap + ring->idx * ring_block_sz);
if (!(block->hdr.bh1.block_status & TP_STATUS_USER))
- return;
+ return false;
frame = (char *)block;
frame += block->hdr.bh1.offset_to_first_pkt;
block->hdr.bh1.block_status = TP_STATUS_KERNEL;
ring->idx = (ring->idx + 1) % ring_block_nr;
+
+ return true;
}
/* simple test: sleep once unconditionally and then process all rings */
usleep(1000 * cfg_timeout_msec);
for (i = 0; i < num_cpus; i++)
- recv_block(&rings[i]);
+ do {} while (recv_block(&rings[i]));
fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n",
frames_received - frames_nohash - frames_error,
struct tpacket_req3 req3 = {0};
void *ring;
- req3.tp_retire_blk_tov = cfg_timeout_msec;
+ req3.tp_retire_blk_tov = cfg_timeout_msec / 8;
req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
req3.tp_frame_size = 2048;
req3.tp_frame_nr = 1 << 10;
- req3.tp_block_nr = 2;
+ req3.tp_block_nr = 16;
req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr;
req3.tp_block_size /= req3.tp_block_nr;
readonly YELLOW='\033[0;33m'
readonly RED='\033[0;31m'
readonly NC='\033[0m' # No Color
+readonly TESTPORT=8000
readonly KSFT_PASS=0
readonly KSFT_FAIL=1
run_one() {
local -r args=$@
+ local nr_socks=0
+ local i=0
+ local -r timeout=10
+
+ ./udpgso_bench_rx -p "$TESTPORT" &
+ ./udpgso_bench_rx -p "$TESTPORT" -t &
+
+ # Wait for the above test program to get ready to receive connections.
+ while [ "$i" -lt "$timeout" ]; do
+ nr_socks="$(ss -lnHi | grep -c "\*:${TESTPORT}")"
+ [ "$nr_socks" -eq 2 ] && break
+ i=$((i + 1))
+ sleep 1
+ done
+ if [ "$nr_socks" -ne 2 ]; then
+ echo "timed out while waiting for udpgso_bench_rx"
+ exit 1
+ fi
- ./udpgso_bench_rx &
- ./udpgso_bench_rx -t &
-
- ./udpgso_bench_tx ${args}
+ ./udpgso_bench_tx -p "$TESTPORT" ${args}
}
run_in_netns() {
static void do_flush_udp(int fd)
{
static char rbuf[ETH_MAX_MTU];
- int ret, len, gso_size, budget = 256;
+ int ret, len, gso_size = 0, budget = 256;
len = cfg_read_all ? sizeof(rbuf) : 0;
while (budget--) {
cfg_verify = true;
cfg_read_all = true;
break;
+ default:
+ exit(1);
}
}
static int cfg_port = 8000;
static int cfg_runtime_ms = -1;
static bool cfg_poll;
+static int cfg_poll_loop_timeout_ms = 2000;
static bool cfg_segment;
static bool cfg_sendmmsg;
static bool cfg_tcp;
}
}
-static void flush_errqueue(int fd, const bool do_poll)
+static void flush_errqueue(int fd, const bool do_poll,
+ unsigned long poll_timeout, const bool poll_err)
{
if (do_poll) {
struct pollfd fds = {0};
int ret;
fds.fd = fd;
- ret = poll(&fds, 1, 500);
+ ret = poll(&fds, 1, poll_timeout);
if (ret == 0) {
- if (cfg_verbose)
+ if ((cfg_verbose) && (poll_err))
fprintf(stderr, "poll timeout\n");
} else if (ret < 0) {
error(1, errno, "poll");
flush_errqueue_recv(fd);
}
+static void flush_errqueue_retry(int fd, unsigned long num_sends)
+{
+ unsigned long tnow, tstop;
+ bool first_try = true;
+
+ tnow = gettimeofday_ms();
+ tstop = tnow + cfg_poll_loop_timeout_ms;
+ do {
+ flush_errqueue(fd, true, tstop - tnow, first_try);
+ first_try = false;
+ tnow = gettimeofday_ms();
+ } while ((stat_zcopies != num_sends) && (tnow < tstop));
+}
+
static int send_tcp(int fd, char *data)
{
int ret, done = 0, count = 0;
static void usage(const char *filepath)
{
- error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
+ error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] "
+ "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
filepath);
}
int max_len, hdrlen;
int c;
- while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) {
+ while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) {
switch (c) {
case '4':
if (cfg_family != PF_UNSPEC)
case 'l':
cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
break;
+ case 'L':
+ cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000;
+ break;
case 'm':
cfg_sendmmsg = true;
break;
case 'z':
cfg_zerocopy = true;
break;
+ default:
+ exit(1);
}
}
num_sends += send_udp(fd, buf[i]);
num_msgs++;
if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp)
- flush_errqueue(fd, cfg_poll);
+ flush_errqueue(fd, cfg_poll, 500, true);
if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
break;
} while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
if (cfg_zerocopy || cfg_tx_tstamp)
- flush_errqueue(fd, true);
+ flush_errqueue_retry(fd, num_sends);
if (close(fd))
error(1, errno, "close");
ksft_skip=4
testns=testns-$(mktemp -u "XXXXXXXX")
+tmp=""
tables="foo bar baz quux"
global_ret=0
eret=0
lret=0
+cleanup() {
+ ip netns pids "$testns" | xargs kill 2>/dev/null
+ ip netns del "$testns"
+
+ rm -f "$tmp"
+}
+
check_result()
{
local r=$1
exit $ksft_skip
fi
+trap cleanup EXIT
tmp=$(mktemp)
for table in $tables; do
check_result $lret "add/delete with nftrace enabled"
-pkill -9 ping
-
-wait
-
-rm -f "$tmp"
-ip netns del "$testns"
-
exit $global_ret
--- /dev/null
+timeout=120
#undef NDEBUG
#include <assert.h>
#include <errno.h>
+#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
* 1: vsyscall VMA is --xp vsyscall=xonly
* 2: vsyscall VMA is r-xp vsyscall=emulate
*/
-static int g_vsyscall;
+static volatile int g_vsyscall;
static const char *g_proc_pid_maps_vsyscall;
static const char *g_proc_pid_smaps_vsyscall;
g_vsyscall = 0;
/* gettimeofday(NULL, NULL); */
+ uint64_t rax = 0xffffffffff600000;
asm volatile (
- "call %P0"
- :
- : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
- : "rax", "rcx", "r11"
+ "call *%[rax]"
+ : [rax] "+a" (rax)
+ : "D" (NULL), "S" (NULL)
+ : "rcx", "r11"
);
g_vsyscall = 1;
g_vsyscall = 0;
/* gettimeofday(NULL, NULL); */
+ uint64_t rax = 0xffffffffff600000;
asm volatile (
- "call %P0"
- :
- : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
- : "rax", "rcx", "r11"
+ "call *%[rax]"
+ : [rax] "+a" (rax)
+ : "D" (NULL), "S" (NULL)
+ : "rcx", "r11"
);
g_vsyscall = 1;
#include <stdio.h>
#include <unistd.h>
#include <sys/mman.h>
-#define __USE_GNU
#include <fcntl.h>
#define MIN_FREE_PAGES 20
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef BUG_H
-#define BUG_H
+#ifndef _LINUX_BUG_H
+#define _LINUX_BUG_H
#include <asm/bug.h>
#define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond))
-#define BUILD_BUG_ON(x)
-
#define BUG() abort()
-#endif /* BUG_H */
+#endif /* _LINUX_BUG_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BUILD_BUG_H
+#define _LINUX_BUILD_BUG_H
+
+#define BUILD_BUG_ON(x)
+
+#endif /* _LINUX_BUILD_BUG_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CPUMASK_H
+#define _LINUX_CPUMASK_H
+
+#include <linux/kernel.h>
+
+#endif /* _LINUX_CPUMASK_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_GFP_H
+#define __LINUX_GFP_H
+
+#include <linux/topology.h>
+
+#endif
#include <stdarg.h>
#include <linux/compiler.h>
+#include <linux/log2.h>
#include <linux/types.h>
#include <linux/overflow.h>
#include <linux/list.h>
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KMSAN_H
+#define _LINUX_KMSAN_H
+
+#include <linux/gfp.h>
+
+inline void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+ enum dma_data_direction dir)
+{
+}
+
+#endif /* _LINUX_KMSAN_H */
#ifndef SCATTERLIST_H
#define SCATTERLIST_H
#include <linux/kernel.h>
+#include <linux/bug.h>
struct scatterlist {
unsigned long page_link;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TOPOLOGY_H
+#define _LINUX_TOPOLOGY_H
+
+#include <linux/cpumask.h>
+
+#endif /* _LINUX_TOPOLOGY_H */
#define smp_wmb() smp_release()
#endif
-#ifdef __alpha__
-#define smp_read_barrier_depends() smp_acquire()
-#else
-#define smp_read_barrier_depends() do {} while(0)
-#endif
-
static __always_inline
void __read_once_size(const volatile void *p, void *res, int size)
{
- switch (size) { \
- case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break; \
- case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break; \
- case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break; \
- case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break; \
- default: \
- barrier(); \
- __builtin_memcpy((void *)res, (const void *)p, size); \
- barrier(); \
- } \
+ switch (size) {
+ case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break;
+ case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break;
+ case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break;
+ case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break;
+ default:
+ barrier();
+ __builtin_memcpy((void *)res, (const void *)p, size);
+ barrier();
+ }
}
static __always_inline void __write_once_size(volatile void *p, void *res, int size)
}
}
+#ifdef __alpha__
#define READ_ONCE(x) \
({ \
union { typeof(x) __val; char __c[1]; } __u; \
__read_once_size(&(x), __u.__c, sizeof(x)); \
- smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
+ smp_mb(); /* Enforce dependency ordering from x */ \
+ __u.__val; \
+})
+#else
+#define READ_ONCE(x) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u; \
+ __read_once_size(&(x), __u.__c, sizeof(x)); \
__u.__val; \
})
+#endif
#define WRITE_ONCE(x, val) \
({ \
if (ret)
break;
- };
+ }
return ret;
long started = 0, completed = 0, next_reset = reset_n;
long completed_before, started_before;
int r, test = 1;
- unsigned len;
+ unsigned int len;
long long spurious = 0;
const bool random_batch = batch == RANDOM_BATCH;
gvdev.vdev.features = features;
INIT_LIST_HEAD(&gvdev.vdev.vqs);
+ spin_lock_init(&gvdev.vdev.vqs_list_lock);
gvdev.to_host_fd = to_host[1];
gvdev.notifies = 0;
getrange = getrange_iov;
vdev.features = 0;
INIT_LIST_HEAD(&vdev.vqs);
+ spin_lock_init(&vdev.vqs_list_lock);
while (argv[1]) {
if (strcmp(argv[1], "--indirect") == 0)
}
mutex_lock(&kvm->lock);
+
+#ifdef CONFIG_LOCKDEP
+ /* Ensure that lockdep knows vcpu->mutex is taken *inside* kvm->lock */
+ mutex_lock(&vcpu->mutex);
+ mutex_unlock(&vcpu->mutex);
+#endif
+
if (kvm_get_vcpu_by_id(kvm, id)) {
r = -EEXIST;
goto unlock_vcpu_destroy;
#define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock)
#define KVM_MMU_LOCK(kvm) write_lock(&(kvm)->mmu_lock)
#define KVM_MMU_UNLOCK(kvm) write_unlock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_LOCK(kvm) read_lock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_UNLOCK(kvm) read_unlock(&(kvm)->mmu_lock)
#else
#define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock)
#define KVM_MMU_LOCK(kvm) spin_lock(&(kvm)->mmu_lock)
#define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_LOCK(kvm) spin_lock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock)
#endif /* KVM_HAVE_MMU_RWLOCK */
kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
return -ENXIO;
}
-static void kvm_vfio_destroy(struct kvm_device *dev)
+static void kvm_vfio_release(struct kvm_device *dev)
{
struct kvm_vfio *kv = dev->private;
struct kvm_vfio_group *kvg, *tmp;
kvm_vfio_update_coherency(dev);
kfree(kv);
- kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
+ kfree(dev); /* alloc by kvm_ioctl_create_device, free by .release */
}
static int kvm_vfio_create(struct kvm_device *dev, u32 type);
static struct kvm_device_ops kvm_vfio_ops = {
.name = "kvm-vfio",
.create = kvm_vfio_create,
- .destroy = kvm_vfio_destroy,
+ .release = kvm_vfio_release,
.set_attr = kvm_vfio_set_attr,
.has_attr = kvm_vfio_has_attr,
};