Daniel Borkmann says:
====================
pull-request: bpf-next 2023-11-30
We've added 30 non-merge commits during the last 7 day(s) which contain
a total of 58 files changed, 1598 insertions(+), 154 deletions(-).
The main changes are:
1) Add initial TX metadata implementation for AF_XDP with support in mlx5
and stmmac drivers. Two types of offloads are supported right now, that
is, TX timestamp and TX checksum offload, from Stanislav Fomichev with
stmmac implementation from Song Yoong Siang.
2) Change BPF verifier logic to validate global subprograms lazily instead
of unconditionally before the main program, so they can be guarded using
BPF CO-RE techniques, from Andrii Nakryiko.
3) Add BPF link_info support for uprobe multi link along with bpftool
integration for the latter, from Jiri Olsa.
4) Use pkg-config in BPF selftests to determine ld flags which is
in particular needed for linking statically, from Akihiko Odaki.
5) Fix a few BPF selftest failures to adapt to the upcoming LLVM18,
from Yonghong Song.
* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (30 commits)
bpf/tests: Remove duplicate JSGT tests
selftests/bpf: Add TX side to xdp_hw_metadata
selftests/bpf: Convert xdp_hw_metadata to XDP_USE_NEED_WAKEUP
selftests/bpf: Add TX side to xdp_metadata
selftests/bpf: Add csum helpers
selftests/xsk: Support tx_metadata_len
xsk: Add option to calculate TX checksum in SW
xsk: Validate xsk_tx_metadata flags
xsk: Document tx_metadata_len layout
net: stmmac: Add Tx HWTS support to XDP ZC
net/mlx5e: Implement AF_XDP TX timestamp and checksum offload
tools: ynl: Print xsk-features from the sample
xsk: Add TX timestamp and TX checksum offload support
xsk: Support tx_metadata_len
selftests/bpf: Use pkg-config for libelf
selftests/bpf: Override PKG_CONFIG for static builds
selftests/bpf: Choose pkg-config for the target
bpftool: Add support to display uprobe_multi links
selftests/bpf: Add link_info test for uprobe_multi link
selftests/bpf: Use bpf_link__destroy in fill_link_info tests
...
====================
Conflicts:
Documentation/netlink/specs/netdev.yaml:
839ff60df3ab ("net: page_pool: add nlspec for basic access to page pools")
48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
https://lore.kernel.org/all/
20231201094705.
1ee3cab8@canb.auug.org.au/
While at it also regen, tree is dirty after:
48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
looks like code wasn't re-rendered after "render-max" was removed.
Link: https://lore.kernel.org/r/20231130145708.32573-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
See Documentation/networking/xdp-rx-metadata.rst for more details.
type: u64
enum: xdp-rx-metadata
+ -
+ name: xsk-features
+ doc: Bitmask of enabled AF_XDP features.
+ type: u64
+ enum: xsk-flags
+ -
+ name: page-pool
+ attributes:
+ -
+ name: id
+ doc: Unique ID of a Page Pool instance.
+ type: uint
+ checks:
+ min: 1
+ max: u32-max
+ -
+ name: ifindex
+ doc: |
+ ifindex of the netdev to which the pool belongs.
+ May be reported as 0 if the page pool was allocated for a netdev
+ which got destroyed already (page pools may outlast their netdevs
+ because they wait for all memory to be returned).
+ type: u32
+ checks:
+ min: 1
+ max: s32-max
+ -
+ name: napi-id
+ doc: Id of NAPI using this Page Pool instance.
+ type: uint
+ checks:
+ min: 1
+ max: u32-max
+ -
+ name: inflight
+ type: uint
+ doc: |
+ Number of outstanding references to this page pool (allocated
+ but yet to be freed pages). Allocated pages may be held in
+ socket receive queues, driver receive ring, page pool recycling
+ ring, the page pool cache, etc.
+ -
+ name: inflight-mem
+ type: uint
+ doc: |
+ Amount of memory held by inflight pages.
+ -
+ name: detach-time
+ type: uint
+ doc: |
+ Seconds in CLOCK_BOOTTIME of when Page Pool was detached by
+ the driver. Once detached Page Pool can no longer be used to
+ allocate memory.
+ Page Pools wait for all the memory allocated from them to be freed
+ before truly disappearing. "Detached" Page Pools cannot be
+ "re-attached", they are just waiting to disappear.
+ Attribute is absent if Page Pool has not been detached, and
+ can still be used to allocate new memory.
+ -
+ name: page-pool-info
+ subset-of: page-pool
+ attributes:
+ -
+ name: id
+ -
+ name: ifindex
+ -
+ name: page-pool-stats
+ doc: |
+ Page pool statistics, see docs for struct page_pool_stats
+ for information about individual statistics.
+ attributes:
+ -
+ name: info
+ doc: Page pool identifying information.
+ type: nest
+ nested-attributes: page-pool-info
+ -
+ name: alloc-fast
+ type: uint
+ value: 8 # reserve some attr ids in case we need more metadata later
+ -
+ name: alloc-slow
+ type: uint
+ -
+ name: alloc-slow-high-order
+ type: uint
+ -
+ name: alloc-empty
+ type: uint
+ -
+ name: alloc-refill
+ type: uint
+ -
+ name: alloc-waive
+ type: uint
+ -
+ name: recycle-cached
+ type: uint
+ -
+ name: recycle-cache-full
+ type: uint
+ -
+ name: recycle-ring
+ type: uint
+ -
+ name: recycle-ring-full
+ type: uint
+ -
+ name: recycle-released-refcnt
+ type: uint
operations:
list:
enum netdev_xdp_rx_metadata {
NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
NETDEV_XDP_RX_METADATA_HASH = 2,
-
- /* private: */
- NETDEV_XDP_RX_METADATA_MASK = 3,
+ };
- /* private: */
- NETDEV_XDP_RX_METADATA_MASK = 3,
+ /**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ * by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ * driver.
+ */
+ enum netdev_xsk_flags {
+ NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+ NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
-
- /* private: */
- NETDEV_XSK_FLAGS_MASK = 3,
};
enum {
enum netdev_xdp_rx_metadata {
NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
NETDEV_XDP_RX_METADATA_HASH = 2,
-
- /* private: */
- NETDEV_XDP_RX_METADATA_MASK = 3,
+ };
- /* private: */
- NETDEV_XDP_RX_METADATA_MASK = 3,
+ /**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ * by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ * driver.
+ */
+ enum netdev_xsk_flags {
+ NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+ NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
-
- /* private: */
- NETDEV_XSK_FLAGS_MASK = 3,
};
enum {
return netdev_xdp_rx_metadata_strmap[value];
}
+ static const char * const netdev_xsk_flags_strmap[] = {
+ [0] = "tx-timestamp",
+ [1] = "tx-checksum",
+ };
+
+ const char *netdev_xsk_flags_str(enum netdev_xsk_flags value)
+ {
+ value = ffs(value) - 1;
+ if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xsk_flags_strmap))
+ return NULL;
+ return netdev_xsk_flags_strmap[value];
+ }
+
/* Policies */
+struct ynl_policy_attr netdev_page_pool_info_policy[NETDEV_A_PAGE_POOL_MAX + 1] = {
+ [NETDEV_A_PAGE_POOL_ID] = { .name = "id", .type = YNL_PT_UINT, },
+ [NETDEV_A_PAGE_POOL_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
+};
+
+struct ynl_policy_nest netdev_page_pool_info_nest = {
+ .max_attr = NETDEV_A_PAGE_POOL_MAX,
+ .table = netdev_page_pool_info_policy,
+};
+
struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = {
[NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, },
[NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, },
const char *netdev_op_str(int op);
const char *netdev_xdp_act_str(enum netdev_xdp_act value);
const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value);
+ const char *netdev_xsk_flags_str(enum netdev_xsk_flags value);
/* Common nested types */
+struct netdev_page_pool_info {
+ struct {
+ __u32 id:1;
+ __u32 ifindex:1;
+ } _present;
+
+ __u64 id;
+ __u32 ifindex;
+};
+
/* ============== NETDEV_CMD_DEV_GET ============== */
/* NETDEV_CMD_DEV_GET - do */
struct netdev_dev_get_req {