- info, mount options and specifications for the Ext2 filesystem.
ext3.txt
- info, mount options and specifications for the Ext3 filesystem.
+ext4.txt
+ - info, mount options and specifications for the Ext4 filesystem.
files.txt
- info on file management in the Linux kernel.
fuse.txt
--- /dev/null
+
+Ext4 Filesystem
+===============
+
+This is a development version of the ext4 filesystem, an advanced level
+of the ext3 filesystem which incorporates scalability and reliability
+enhancements for supporting large filesystems (64 bit) in keeping with
+increasing disk capacities and state-of-the-art feature requirements.
+
+Mailing list: linux-ext4@vger.kernel.org
+
+
+1. Quick usage instructions:
+===========================
+
+ - Grab updated e2fsprogs from
+ ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs-interim/
+ This is a patchset on top of e2fsprogs-1.39, which can be found at
+ ftp://ftp.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
+
+ - It's still mke2fs -j /dev/hda1
+
+ - mount /dev/hda1 /wherever -t ext4dev
+
+ - To enable extents,
+
+ mount /dev/hda1 /wherever -t ext4dev -o extents
+
+ - The filesystem is compatible with the ext3 driver until you add a file
+ which has extents (ie: `mount -o extents', then create a file).
+
+ NOTE: The "extents" mount flag is temporary. It will soon go away and
+ extents will be enabled by the "-o extents" flag to mke2fs or tune2fs
+
+ - When comparing performance with other filesystems, remember that
+ ext3/4 by default offers higher data integrity guarantees than most. So
+ when comparing with a metadata-only journalling filesystem, use `mount -o
+ data=writeback'. And you might as well use `mount -o nobh' too along
+ with it. Making the journal larger than the mke2fs default often helps
+ performance with metadata-intensive workloads.
+
+2. Features
+===========
+
+2.1 Currently available
+
+* ability to use filesystems > 16TB
+* extent format reduces metadata overhead (RAM, IO for access, transactions)
+* extent format more robust in face of on-disk corruption due to magics,
+* internal redunancy in tree
+
+2.1 Previously available, soon to be enabled by default by "mkefs.ext4":
+
+* dir_index and resize inode will be on by default
+* large inodes will be used by default for fast EAs, nsec timestamps, etc
+
+2.2 Candidate features for future inclusion
+
+There are several under discussion, whether they all make it in is
+partly a function of how much time everyone has to work on them:
+
+* improved file allocation (multi-block alloc, delayed alloc; basically done)
+* fix 32000 subdirectory limit (patch exists, needs some e2fsck work)
+* nsec timestamps for mtime, atime, ctime, create time (patch exists,
+ needs some e2fsck work)
+* inode version field on disk (NFSv4, Lustre; prototype exists)
+* reduced mke2fs/e2fsck time via uninitialized groups (prototype exists)
+* journal checksumming for robustness, performance (prototype exists)
+* persistent file preallocation (e.g for streaming media, databases)
+
+Features like metadata checksumming have been discussed and planned for
+a bit but no patches exist yet so I'm not sure they're in the near-term
+roadmap.
+
+The big performance win will come with mballoc and delalloc. CFS has
+been using mballoc for a few years already with Lustre, and IBM + Bull
+did a lot of benchmarking on it. The reason it isn't in the first set of
+patches is partly a manageability issue, and partly because it doesn't
+directly affect the on-disk format (outside of much better allocation)
+so it isn't critical to get into the first round of changes. I believe
+Alex is working on a new set of patches right now.
+
+3. Options
+==========
+
+When mounting an ext4 filesystem, the following option are accepted:
+(*) == default
+
+extents ext4 will use extents to address file data. The
+ file system will no longer be mountable by ext3.
+
+journal=update Update the ext4 file system's journal to the current
+ format.
+
+journal=inum When a journal already exists, this option is ignored.
+ Otherwise, it specifies the number of the inode which
+ will represent the ext4 file system's journal file.
+
+journal_dev=devnum When the external journal device's major/minor numbers
+ have changed, this option allows the user to specify
+ the new journal location. The journal device is
+ identified through its new major/minor numbers encoded
+ in devnum.
+
+noload Don't load the journal on mounting.
+
+data=journal All data are committed into the journal prior to being
+ written into the main file system.
+
+data=ordered (*) All data are forced directly out to the main file
+ system prior to its metadata being committed to the
+ journal.
+
+data=writeback Data ordering is not preserved, data may be written
+ into the main file system after its metadata has been
+ committed to the journal.
+
+commit=nrsec (*) Ext4 can be told to sync all its data and metadata
+ every 'nrsec' seconds. The default value is 5 seconds.
+ This means that if you lose your power, you will lose
+ as much as the latest 5 seconds of work (your
+ filesystem will not be damaged though, thanks to the
+ journaling). This default value (or any low value)
+ will hurt performance, but it's good for data-safety.
+ Setting it to 0 will have the same effect as leaving
+ it at the default (5 seconds).
+ Setting it to very large values will improve
+ performance.
+
+barrier=1 This enables/disables barriers. barrier=0 disables
+ it, barrier=1 enables it.
+
+orlov (*) This enables the new Orlov block allocator. It is
+ enabled by default.
+
+oldalloc This disables the Orlov block allocator and enables
+ the old block allocator. Orlov should have better
+ performance - we'd like to get some feedback if it's
+ the contrary for you.
+
+user_xattr Enables Extended User Attributes. Additionally, you
+ need to have extended attribute support enabled in the
+ kernel configuration (CONFIG_EXT4_FS_XATTR). See the
+ attr(5) manual page and http://acl.bestbits.at/ to
+ learn more about extended attributes.
+
+nouser_xattr Disables Extended User Attributes.
+
+acl Enables POSIX Access Control Lists support.
+ Additionally, you need to have ACL support enabled in
+ the kernel configuration (CONFIG_EXT4_FS_POSIX_ACL).
+ See the acl(5) manual page and http://acl.bestbits.at/
+ for more information.
+
+noacl This option disables POSIX Access Control List
+ support.
+
+reservation
+
+noreservation
+
+bsddf (*) Make 'df' act like BSD.
+minixdf Make 'df' act like Minix.
+
+check=none Don't do extra checking of bitmaps on mount.
+nocheck
+
+debug Extra debugging information is sent to syslog.
+
+errors=remount-ro(*) Remount the filesystem read-only on an error.
+errors=continue Keep going on a filesystem error.
+errors=panic Panic and halt the machine if an error occurs.
+
+grpid Give objects the same group ID as their creator.
+bsdgroups
+
+nogrpid (*) New objects have the group ID of their creator.
+sysvgroups
+
+resgid=n The group ID which may use the reserved blocks.
+
+resuid=n The user ID which may use the reserved blocks.
+
+sb=n Use alternate superblock at this location.
+
+quota
+noquota
+grpquota
+usrquota
+
+bh (*) ext4 associates buffer heads to data pages to
+nobh (a) cache disk block mapping information
+ (b) link pages into transaction to provide
+ ordering guarantees.
+ "bh" option forces use of buffer heads.
+ "nobh" option tries to avoid associating buffer
+ heads (supported only for "writeback" mode).
+
+
+Data Mode
+---------
+There are 3 different data modes:
+
+* writeback mode
+In data=writeback mode, ext4 does not journal data at all. This mode provides
+a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
+mode - metadata journaling. A crash+recovery can cause incorrect data to
+appear in files which were written shortly before the crash. This mode will
+typically provide the best ext4 performance.
+
+* ordered mode
+In data=ordered mode, ext4 only officially journals metadata, but it logically
+groups metadata and data blocks into a single unit called a transaction. When
+it's time to write the new metadata out to disk, the associated data blocks
+are written first. In general, this mode performs slightly slower than
+writeback but significantly faster than journal mode.
+
+* journal mode
+data=journal mode provides full data and metadata journaling. All new data is
+written to the journal first, and then to its final location.
+In the event of a crash, the journal can be replayed, bringing both data and
+metadata into a consistent state. This mode is the slowest except when data
+needs to be read from and written to disk at the same time where it
+outperforms all others modes.
+
+References
+==========
+
+kernel source: <file:fs/ext4/>
+ <file:fs/jbd2/>
+
+programs: http://e2fsprogs.sourceforge.net/
+ http://ext2resize.sourceforge.net
+
+useful links: http://fedoraproject.org/wiki/ext3-devel
+ http://www.bullopensource.org/ext4/
- ACPI sounds
- temperature sensors
- Experimental: embedded controller register dump
- - Experimental: LCD brightness control
- - Experimental: volume control
+ - LCD brightness control
+ - Volume control
- Experimental: fan speed, fan enable/disable
+ - Experimental: WAN enable and disable
A compatibility table by model and feature is maintained on the web
site, http://ibm-acpi.sf.net/. I appreciate any success or failure
If you are compiling this driver as included in the Linux kernel
sources, simply enable the CONFIG_ACPI_IBM option (Power Management /
-ACPI / IBM ThinkPad Laptop Extras). The rest of this section describes
-how to install this driver when downloaded from the web site.
-
-First, you need to get a kernel with ACPI support up and running.
-Please refer to http://acpi.sourceforge.net/ for help with this
-step. How successful you will be depends a lot on you ThinkPad model,
-the kernel you are using and any additional patches applied. The
-kernel provided with your distribution may not be good enough. I
-needed to compile a 2.6.7 kernel with the 20040715 ACPI patch to get
-ACPI working reliably on my ThinkPad X40. Old ThinkPad models may not
-be supported at all.
-
-Assuming you have the basic ACPI support working (e.g. you can see the
-/proc/acpi directory), follow the following steps to install this
-driver:
-
- - unpack the archive:
-
- tar xzvf ibm-acpi-x.y.tar.gz; cd ibm-acpi-x.y
-
- - compile the driver:
-
- make
-
- - install the module in your kernel modules directory:
-
- make install
-
- - load the module:
-
- modprobe ibm_acpi
-
-After loading the module, check the "dmesg" output for any error messages.
-
+ACPI / IBM ThinkPad Laptop Extras).
Features
--------
with this, do send me your results (including some complete dumps with
a description of the conditions when they were taken.)
-EXPERIMENTAL: LCD brightness control -- /proc/acpi/ibm/brightness
------------------------------------------------------------------
-
-This feature is marked EXPERIMENTAL because the implementation
-directly accesses hardware registers and may not work as expected. USE
-WITH CAUTION! To use this feature, you need to supply the
-experimental=1 parameter when loading the module.
+LCD brightness control -- /proc/acpi/ibm/brightness
+---------------------------------------------------
This feature allows software control of the LCD brightness on ThinkPad
models which don't have a hardware brightness slider. The available
The <level> number range is 0 to 7, although not all of them may be
distinct. The current brightness level is shown in the file.
-EXPERIMENTAL: Volume control -- /proc/acpi/ibm/volume
------------------------------------------------------
-
-This feature is marked EXPERIMENTAL because the implementation
-directly accesses hardware registers and may not work as expected. USE
-WITH CAUTION! To use this feature, you need to supply the
-experimental=1 parameter when loading the module.
+Volume control -- /proc/acpi/ibm/volume
+---------------------------------------
This feature allows volume control on ThinkPad models which don't have
a hardware volume knob. The available commands are:
echo 'level <level>' > /proc/acpi/ibm/thermal
+EXPERIMENTAL: WAN -- /proc/acpi/ibm/wan
+---------------------------------------
+
+This feature is marked EXPERIMENTAL because the implementation
+directly accesses hardware registers and may not work as expected. USE
+WITH CAUTION! To use this feature, you need to supply the
+experimental=1 parameter when loading the module.
+
+This feature shows the presence and current state of a WAN (Sierra
+Wireless EV-DO) device. If WAN is installed, the following commands can
+be used:
+
+ echo enable > /proc/acpi/ibm/wan
+ echo disable > /proc/acpi/ibm/wan
+
+It was tested on a Lenovo Thinkpad X60. It should probably work on other
+Thinkpad models which come with this module installed.
Multiple Commands, Module Parameters
------------------------------------
softirq-read respectively, and the character displayed in each
indicates:
- '.' acquired while irqs enabled
+ '.' acquired while irqs disabled
'+' acquired in irq context
- '-' acquired in process context with irqs disabled
- '?' read-acquired both with irqs enabled and in irq context
+ '-' acquired with irqs enabled
+ '?' read acquired in irq context with irqs enabled.
Unused mutexes cannot be part of the cause of an error.
core_pattern:
core_pattern is used to specify a core dumpfile pattern name.
-. max length 64 characters; default value is "core"
+. max length 128 characters; default value is "core"
. core_pattern is used as a pattern template for the output filename;
certain string patterns (beginning with '%') are substituted with
their actual values.
%h hostname
%e executable filename
%<OTHER> both are dropped
+. If the first character of the pattern is a '|', the kernel will treat
+ the rest of the pattern as a command to run. The core dump will be
+ written to the standard input of that program instead of to a file.
==============================================================
50 -> NPG Tech Real TV FM Top 10 [14f1:0842]
51 -> WinFast DTV2000 H [107d:665e]
52 -> Geniatech DVB-S [14f1:0084]
- 53 -> Hauppauge WinTV-HVR3000 TriMode Analog/DVB-S/DVB-T [0070:1404]
+ 53 -> Hauppauge WinTV-HVR3000 TriMode Analog/DVB-S/DVB-T [0070:1404,0070:1400,0070:1401,0070:1402]
54 -> Norwood Micro TV Tuner
55 -> Shenzhen Tungsten Ages Tech TE-DTV-250 / Swann OEM [c180:c980]
56 -> Hauppauge WinTV-HVR1300 DVB-T/Hybrid MPEG Encoder [0070:9600,0070:9601,0070:9602]
M: teigland@redhat.com
L: cluster-devel@redhat.com
W: http://sources.redhat.com/cluster/
-T: git kernel.org:/pub/scm/linux/kernel/git/steve/gfs-2.6.git
+T: git kernel.org:/pub/scm/linux/kernel/git/steve/gfs2-2.6-fixes.git
+T: git kernel.org:/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw.git
S: Supported
DAVICOM FAST ETHERNET (DMFE) NETWORK DRIVER
M: swhiteho@redhat.com
L: cluster-devel@redhat.com
W: http://sources.redhat.com/cluster/
-T: git kernel.org:/pub/scm/linux/kernel/git/steve/gfs-2.6.git
+T: git kernel.org:/pub/scm/linux/kernel/git/steve/gfs2-2.6-fixes.git
+T: git kernel.org:/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw.git
S: Supported
GIGASET ISDN DRIVERS
L: linux-kernel@vger.kernel.org
S: Maintained
+MSI LAPTOP SUPPORT
+P: Lennart Poettering
+M: mzxreary@0pointer.de
+L: https://tango.0pointer.de/mailman/listinfo/s270-linux
+W: http://0pointer.de/lennart/tchibo.html
+S: Maintained
+
MTRR AND SIMILAR SUPPORT [i386]
P: Richard Gooch
M: rgooch@atnf.csiro.au
W: http://www.atnf.csiro.au/~rgooch/linux/kernel-patches.html
S: Maintained
-MULTIMEDIA CARD (MMC) SUBSYSTEM
-S: Orphan
+MULTIMEDIA CARD (MMC) AND SECURE DIGITAL (SD) SUBSYSTEM
+P: Pierre Ossman
+M: drzeus-mmc@drzeus.cx
+L: linux-kernel@vger.kernel.org
+S: Maintained
MULTISOUND SOUND DRIVER
P: Andrew Veliath
P: James Morris
P: Harald Welte
P: Jozsef Kadlecsik
-M: coreteam@netfilter.org
+P: Patrick McHardy
+M: kaber@trash.net
+L: netfilter-devel@lists.netfilter.org
+L: netfilter@lists.netfilter.org
+L: coreteam@netfilter.org
W: http://www.netfilter.org/
W: http://www.iptables.org/
-L: netfilter@lists.netfilter.org
-L: netfilter-devel@lists.netfilter.org
S: Supported
NETLABEL
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 19
-EXTRAVERSION =-rc1
+EXTRAVERSION =-rc2
NAME=Avast! A bilge rat!
# *DOCUMENTATION*
# vmlinux image - including updated kernel symbols
vmlinux: $(vmlinux-lds) $(vmlinux-init) $(vmlinux-main) $(kallsyms.o) FORCE
+ifdef CONFIG_HEADERS_CHECK
+ $(Q)$(MAKE) -f $(srctree)/Makefile headers_check
+endif
$(call if_changed_rule,vmlinux__)
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost $@
$(Q)rm -f .old_version
PHONY += headers_install
headers_install: include/linux/version.h scripts_basic FORCE
- @if [ ! -r include/asm-$(ARCH)/Kbuild ]; then \
+ @if [ ! -r $(srctree)/include/asm-$(ARCH)/Kbuild ]; then \
echo '*** Error: Headers not exportable for this architecture ($(ARCH))'; \
exit 1 ; fi
$(Q)$(MAKE) $(build)=scripts scripts/unifdef
$(all-sources) | xargs $1 -a \
-I __initdata,__exitdata,__acquires,__releases \
-I EXPORT_SYMBOL,EXPORT_SYMBOL_GPL \
- --extra=+f --c-kinds=+px; \
+ --extra=+f --c-kinds=+px \
+ --regex-asm='/ENTRY\(([^)]*)\).*/\1/'; \
$(all-kconfigs) | xargs $1 -a \
--langdef=kconfig \
--language-force=kconfig \
*/
#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/user.h>
-#include <linux/elfcore.h>
-#include <linux/socket.h>
-#include <linux/syscalls.h>
-#include <linux/in.h>
-#include <linux/in6.h>
-#include <linux/pci.h>
-#include <linux/screen_info.h>
-#include <linux/tty.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/dma-mapping.h>
-
-#include <asm/io.h>
#include <asm/console.h>
-#include <asm/hwrpb.h>
#include <asm/uaccess.h>
-#include <asm/processor.h>
#include <asm/checksum.h>
-#include <linux/interrupt.h>
#include <asm/fpu.h>
-#include <asm/irq.h>
#include <asm/machvec.h>
-#include <asm/pgalloc.h>
-#include <asm/semaphore.h>
-#include <asm/tlbflush.h>
-#include <asm/cacheflush.h>
-#include <asm/vga.h>
-#include <asm/unistd.h>
-
-extern struct hwrpb_struct *hwrpb;
-extern spinlock_t rtc_lock;
+#include <linux/syscalls.h>
/* these are C runtime functions with special calling conventions: */
extern void __divl (void);
extern void __remqu (void);
EXPORT_SYMBOL(alpha_mv);
-EXPORT_SYMBOL(screen_info);
-EXPORT_SYMBOL(perf_irq);
EXPORT_SYMBOL(callback_getenv);
EXPORT_SYMBOL(callback_setenv);
EXPORT_SYMBOL(callback_save_env);
-#ifdef CONFIG_ALPHA_GENERIC
-EXPORT_SYMBOL(alpha_using_srm);
-#endif /* CONFIG_ALPHA_GENERIC */
/* platform dependent support */
EXPORT_SYMBOL(strcat);
EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(clear_page);
-EXPORT_SYMBOL(__direct_map_base);
-EXPORT_SYMBOL(__direct_map_size);
-
-#ifdef CONFIG_PCI
-EXPORT_SYMBOL(pci_alloc_consistent);
-EXPORT_SYMBOL(pci_free_consistent);
-EXPORT_SYMBOL(pci_map_single);
-EXPORT_SYMBOL(pci_map_page);
-EXPORT_SYMBOL(pci_unmap_single);
-EXPORT_SYMBOL(pci_unmap_page);
-EXPORT_SYMBOL(pci_map_sg);
-EXPORT_SYMBOL(pci_unmap_sg);
-EXPORT_SYMBOL(pci_dma_supported);
-EXPORT_SYMBOL(pci_dac_dma_supported);
-EXPORT_SYMBOL(pci_dac_page_to_dma);
-EXPORT_SYMBOL(pci_dac_dma_to_page);
-EXPORT_SYMBOL(pci_dac_dma_to_offset);
-EXPORT_SYMBOL(alpha_gendev_to_pci);
-#endif
-EXPORT_SYMBOL(dma_set_mask);
-
-EXPORT_SYMBOL(dump_thread);
-EXPORT_SYMBOL(dump_elf_thread);
-EXPORT_SYMBOL(dump_elf_task);
-EXPORT_SYMBOL(dump_elf_task_fp);
-EXPORT_SYMBOL(hwrpb);
-EXPORT_SYMBOL(start_thread);
EXPORT_SYMBOL(alpha_read_fp_reg);
EXPORT_SYMBOL(alpha_read_fp_reg_s);
EXPORT_SYMBOL(alpha_write_fp_reg);
EXPORT_SYMBOL(alpha_write_fp_reg_s);
-/* In-kernel system calls. */
+/* entry.S */
EXPORT_SYMBOL(kernel_thread);
-EXPORT_SYMBOL(sys_dup);
-EXPORT_SYMBOL(sys_exit);
-EXPORT_SYMBOL(sys_write);
-EXPORT_SYMBOL(sys_lseek);
EXPORT_SYMBOL(kernel_execve);
-EXPORT_SYMBOL(sys_setsid);
-EXPORT_SYMBOL(sys_wait4);
/* Networking helper routines. */
EXPORT_SYMBOL(csum_tcpudp_magic);
EXPORT_SYMBOL(alpha_fp_emul);
#endif
-#ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK
-EXPORT_SYMBOL(__min_ipl);
-#endif
-
/*
* The following are specially called from the uaccess assembly stubs.
*/
*/
#ifdef CONFIG_SMP
-EXPORT_SYMBOL(flush_tlb_mm);
-EXPORT_SYMBOL(flush_tlb_range);
-EXPORT_SYMBOL(flush_tlb_page);
-EXPORT_SYMBOL(smp_imb);
-EXPORT_SYMBOL(cpu_data);
-EXPORT_SYMBOL(smp_num_cpus);
-EXPORT_SYMBOL(smp_call_function);
-EXPORT_SYMBOL(smp_call_function_on_cpu);
EXPORT_SYMBOL(_atomic_dec_and_lock);
#endif /* CONFIG_SMP */
-/*
- * NUMA specific symbols
- */
-#ifdef CONFIG_DISCONTIGMEM
-EXPORT_SYMBOL(node_data);
-#endif /* CONFIG_DISCONTIGMEM */
-
-EXPORT_SYMBOL(rtc_lock);
-
/*
* The following are special because they're not called
* explicitly (the C compiler or assembler generates them in
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memchr);
-
-#ifdef CONFIG_ALPHA_IRONGATE
-EXPORT_SYMBOL(irongate_ioremap);
-EXPORT_SYMBOL(irongate_iounmap);
-#endif
#endif
return (void __iomem *)vaddr;
}
+EXPORT_SYMBOL(irongate_ioremap);
void
irongate_iounmap(volatile void __iomem *xaddr)
if (addr)
return vfree((void *)(PAGE_MASK & addr));
}
+EXPORT_SYMBOL(irongate_iounmap);
#include <linux/sched.h>
#include <linux/irq.h>
#include <linux/kernel_stat.h>
+#include <linux/module.h>
#include <asm/machvec.h>
#include <asm/dma.h>
/* Hack minimum IPL during interrupt processing for broken hardware. */
#ifdef CONFIG_ALPHA_BROKEN_IRQ_MASK
int __min_ipl;
+EXPORT_SYMBOL(__min_ipl);
#endif
/*
}
void (*perf_irq)(unsigned long, struct pt_regs *) = dummy_perf;
+EXPORT_SYMBOL(perf_irq);
/*
* The main interrupt entry point.
return 0;
}
+EXPORT_SYMBOL(dma_set_mask);
void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
{
dac_allowed = pdev ? pci_dac_dma_supported(pdev, pdev->dma_mask) : 0;
return pci_map_single_1(pdev, cpu_addr, size, dac_allowed);
}
+EXPORT_SYMBOL(pci_map_single);
dma_addr_t
pci_map_page(struct pci_dev *pdev, struct page *page, unsigned long offset,
return pci_map_single_1(pdev, (char *)page_address(page) + offset,
size, dac_allowed);
}
+EXPORT_SYMBOL(pci_map_page);
/* Unmap a single streaming mode DMA translation. The DMA_ADDR and
SIZE must match what was provided for in a previous pci_map_single
DBGA2("pci_unmap_single: sg [%lx,%lx] np %ld from %p\n",
dma_addr, size, npages, __builtin_return_address(0));
}
+EXPORT_SYMBOL(pci_unmap_single);
void
pci_unmap_page(struct pci_dev *pdev, dma_addr_t dma_addr,
{
pci_unmap_single(pdev, dma_addr, size, direction);
}
+EXPORT_SYMBOL(pci_unmap_page);
/* Allocate and map kernel buffer using consistent mode DMA for PCI
device. Returns non-NULL cpu-view pointer to the buffer if
return cpu_addr;
}
+EXPORT_SYMBOL(pci_alloc_consistent);
/* Free and unmap a consistent DMA buffer. CPU_ADDR and DMA_ADDR must
be values that were returned from pci_alloc_consistent. SIZE must
DBGA2("pci_free_consistent: [%x,%lx] from %p\n",
dma_addr, size, __builtin_return_address(0));
}
-
+EXPORT_SYMBOL(pci_free_consistent);
/* Classify the elements of the scatterlist. Write dma_address
of each element with:
pci_unmap_sg(pdev, start, out - start, direction);
return 0;
}
+EXPORT_SYMBOL(pci_map_sg);
/* Unmap a set of streaming mode DMA translations. Again, cpu read
rules concerning calls here are the same as for pci_unmap_single()
DBGA("pci_unmap_sg: %ld entries\n", nents - (end - sg));
}
+EXPORT_SYMBOL(pci_unmap_sg);
/* Return whether the given PCI device DMA address mask can be
return 0;
}
+EXPORT_SYMBOL(pci_dma_supported);
\f
/*
return ok;
}
+EXPORT_SYMBOL(pci_dac_dma_supported);
dma64_addr_t
pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page,
+ __pa(page_address(page))
+ (dma64_addr_t) offset);
}
+EXPORT_SYMBOL(pci_dac_page_to_dma);
struct page *
pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr)
unsigned long paddr = (dma_addr & PAGE_MASK) - alpha_mv.pci_dac_offset;
return virt_to_page(__va(paddr));
}
+EXPORT_SYMBOL(pci_dac_dma_to_page);
unsigned long
pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr)
{
return (dma_addr & ~PAGE_MASK);
}
-
+EXPORT_SYMBOL(pci_dac_dma_to_offset);
/* Helper for generic DMA-mapping functions. */
/* This assumes ISA bus master with dma_mask 0xffffff. */
return NULL;
}
+EXPORT_SYMBOL(alpha_gendev_to_pci);
int
dma_set_mask(struct device *dev, u64 mask)
return 0;
}
+EXPORT_SYMBOL(dma_set_mask);
regs->ps = 8;
wrusp(sp);
}
+EXPORT_SYMBOL(start_thread);
/*
* Free current thread data structures etc..
dump->regs[EF_A2] = pt->r18;
memcpy((char *)dump->regs + EF_SIZE, sw->fp, 32 * 8);
}
+EXPORT_SYMBOL(dump_thread);
/*
* Fill in the user structure for a ELF core dump.
useful value of the thread's UNIQUE field. */
dest[32] = ti->pcb.unique;
}
+EXPORT_SYMBOL(dump_elf_thread);
int
dump_elf_task(elf_greg_t *dest, struct task_struct *task)
dump_elf_thread(dest, task_pt_regs(task), task_thread_info(task));
return 1;
}
+EXPORT_SYMBOL(dump_elf_task);
int
dump_elf_task_fp(elf_fpreg_t *dest, struct task_struct *task)
memcpy(dest, sw->fp, 32 * 8);
return 1;
}
+EXPORT_SYMBOL(dump_elf_task_fp);
/*
* sys_execve() executes a new program.
struct hwrpb_struct *hwrpb;
+EXPORT_SYMBOL(hwrpb);
unsigned long srm_hae;
int alpha_l1i_cacheshape;
#ifdef CONFIG_ALPHA_GENERIC
struct alpha_machine_vector alpha_mv;
int alpha_using_srm;
+EXPORT_SYMBOL(alpha_using_srm);
#endif
static struct alpha_machine_vector *get_sysvec(unsigned long, unsigned long,
.orig_video_points = 16
};
+EXPORT_SYMBOL(screen_info);
+
/*
* The direct map I/O window, if any. This should be the same
* for all busses, since it's used by virt_to_bus.
unsigned long __direct_map_base;
unsigned long __direct_map_size;
+EXPORT_SYMBOL(__direct_map_base);
+EXPORT_SYMBOL(__direct_map_size);
/*
* Declare all of the machine vectors.
/* A collection of per-processor data. */
struct cpuinfo_alpha cpu_data[NR_CPUS];
+EXPORT_SYMBOL(cpu_data);
/* A collection of single bit ipi messages. */
static struct {
int smp_num_probed; /* Internal processor count */
int smp_num_cpus = 1; /* Number that came online. */
+EXPORT_SYMBOL(smp_num_cpus);
extern void calibrate_delay(void);
return 0;
}
+EXPORT_SYMBOL(smp_call_function_on_cpu);
int
smp_call_function (void (*func) (void *info), void *info, int retry, int wait)
return smp_call_function_on_cpu (func, info, retry, wait,
cpu_online_map);
}
+EXPORT_SYMBOL(smp_call_function);
static void
ipi_imb(void *ignored)
if (on_each_cpu(ipi_imb, NULL, 1, 1))
printk(KERN_CRIT "smp_imb: timed out\n");
}
+EXPORT_SYMBOL(smp_imb);
static void
ipi_flush_tlb_all(void *ignored)
preempt_enable();
}
+EXPORT_SYMBOL(flush_tlb_mm);
struct flush_tlb_page_struct {
struct vm_area_struct *vma;
preempt_enable();
}
+EXPORT_SYMBOL(flush_tlb_page);
void
flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
/* On the Alpha we always flush the whole user tlb. */
flush_tlb_mm(vma->vm_mm);
}
+EXPORT_SYMBOL(flush_tlb_range);
static void
ipi_flush_icache_page(void *x)
static int set_rtc_mmss(unsigned long);
DEFINE_SPINLOCK(rtc_lock);
+EXPORT_SYMBOL(rtc_lock);
#define TICK_SIZE (tick_nsec / 1000)
#include <linux/swap.h>
#include <linux/initrd.h>
#include <linux/pfn.h>
+#include <linux/module.h>
#include <asm/hwrpb.h>
#include <asm/pgalloc.h>
pg_data_t node_data[MAX_NUMNODES];
bootmem_data_t node_bdata[MAX_NUMNODES];
+EXPORT_SYMBOL(node_data);
#undef DEBUG_DISCONTIG
#ifdef DEBUG_DISCONTIG
EXPORT_SYMBOL(_find_first_bit_be);
EXPORT_SYMBOL(_find_next_bit_be);
#endif
-
- /* syscalls */
-EXPORT_SYMBOL(sys_write);
-EXPORT_SYMBOL(sys_lseek);
-EXPORT_SYMBOL(sys_exit);
-EXPORT_SYMBOL(sys_wait4);
.length = SZ_4K,
.type = MT_DEVICE
}, {
- .virtual = VERSATILE_PCI_VIRT_BASE,
+ .virtual = (unsigned long)VERSATILE_PCI_VIRT_BASE,
.pfn = __phys_to_pfn(VERSATILE_PCI_BASE),
.length = VERSATILE_PCI_BASE_SIZE,
.type = MT_DEVICE
}, {
- .virtual = VERSATILE_PCI_CFG_VIRT_BASE,
+ .virtual = (unsigned long)VERSATILE_PCI_CFG_VIRT_BASE,
.pfn = __phys_to_pfn(VERSATILE_PCI_CFG_BASE),
.length = VERSATILE_PCI_CFG_BASE_SIZE,
.type = MT_DEVICE
* Cfg 42000000 - 42FFFFFF PCI config
*
*/
-#define SYS_PCICTL IO_ADDRESS(VERSATILE_SYS_PCICTL)
-#define PCI_IMAP0 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0)
-#define PCI_IMAP1 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4)
-#define PCI_IMAP2 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8)
-#define PCI_SMAP0 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10)
-#define PCI_SMAP1 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
-#define PCI_SMAP2 IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
-#define PCI_SELFID IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc)
+#define __IO_ADDRESS(n) ((void __iomem *)(unsigned long)IO_ADDRESS(n))
+#define SYS_PCICTL __IO_ADDRESS(VERSATILE_SYS_PCICTL)
+#define PCI_IMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0)
+#define PCI_IMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4)
+#define PCI_IMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8)
+#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10)
+#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
+#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SELFID __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc)
#define DEVICE_ID_OFFSET 0x00
#define CSR_OFFSET 0x04
__setup("pci_slot_ignore=", versatile_pci_slot_ignore);
-static unsigned long __pci_addr(struct pci_bus *bus,
+static void __iomem *__pci_addr(struct pci_bus *bus,
unsigned int devfn, int offset)
{
unsigned int busnr = bus->number;
if (devfn > 255)
BUG();
- return (VERSATILE_PCI_CFG_VIRT_BASE | (busnr << 16) |
+ return VERSATILE_PCI_CFG_VIRT_BASE + ((busnr << 16) |
(PCI_SLOT(devfn) << 11) | (PCI_FUNC(devfn) << 8) | offset);
}
static int versatile_read_config(struct pci_bus *bus, unsigned int devfn, int where,
int size, u32 *val)
{
- unsigned long addr = __pci_addr(bus, devfn, where);
+ void __iomem *addr = __pci_addr(bus, devfn, where & ~3);
u32 v;
int slot = PCI_SLOT(devfn);
break;
case 2:
- v = __raw_readl(addr & ~3);
- if (addr & 2) v >>= 16;
+ v = __raw_readl(addr);
+ if (where & 2) v >>= 16;
v &= 0xffff;
break;
default:
- addr &= ~3;
v = __raw_readl(addr);
break;
}
static int versatile_write_config(struct pci_bus *bus, unsigned int devfn, int where,
int size, u32 val)
{
- unsigned long addr = __pci_addr(bus, devfn, where);
+ void __iomem *addr = __pci_addr(bus, devfn, where);
int slot = PCI_SLOT(devfn);
if (pci_slot_ignore & (1 << slot)) {
printk("PCI core found (slot %d)\n",myslot);
__raw_writel(myslot, PCI_SELFID);
- local_pci_cfg_base = (void *) VERSATILE_PCI_CFG_VIRT_BASE + (myslot << 11);
+ local_pci_cfg_base = VERSATILE_PCI_CFG_VIRT_BASE + (myslot << 11);
val = __raw_readl(local_pci_cfg_base + CSR_OFFSET);
val |= PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER | PCI_COMMAND_INVALIDATE;
info.si_signo = SIGFPE;
info.si_code = sicode;
- info.si_addr = (void *)(instruction_pointer(regs) - 4);
+ info.si_addr = (void __user *)(instruction_pointer(regs) - 4);
/*
* This is the same as NWFPE, because it's not clear what
EXPORT_SYMBOL(elf_platform);
EXPORT_SYMBOL(elf_hwcap);
- /* syscalls */
-EXPORT_SYMBOL(sys_write);
-EXPORT_SYMBOL(sys_read);
-EXPORT_SYMBOL(sys_lseek);
-EXPORT_SYMBOL(sys_open);
-EXPORT_SYMBOL(sys_exit);
-EXPORT_SYMBOL(sys_wait4);
-
#ifdef CONFIG_PREEMPT
EXPORT_SYMBOL(kernel_flag);
#endif
*
* In UP mode, it is invoked from the (global) timer_interrupt.
*/
-static void local_timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static void local_timer_interrupt(int irq, void *dev_id)
{
if (current->pid)
- profile_tick(CPU_PROFILING, regs);
- update_process_times(user_mode(regs));
+ profile_tick(CPU_PROFILING);
+ update_process_times(user_mode(get_irq_regs()));
}
static irqreturn_t
-timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+timer_interrupt(int irq, void *dev_id)
{
unsigned int count;
*
* SMP is not supported yet.
*/
- local_timer_interrupt(irq, dev_id, regs);
+ local_timer_interrupt(irq, dev_id);
return IRQ_HANDLED;
}
.set_type = eim_set_irq_type,
};
-static void demux_eim_irq(unsigned int irq, struct irq_desc *desc,
- struct pt_regs *regs)
+static void demux_eim_irq(unsigned int irq, struct irq_desc *desc)
{
struct at32_sm *sm = desc->handler_data;
struct irq_desc *ext_desc;
ext_irq = i + sm->eim_first_irq;
ext_desc = irq_desc + ext_irq;
- ext_desc->handle_irq(ext_irq, ext_desc, regs);
+ ext_desc->handle_irq(ext_irq, ext_desc);
}
spin_unlock(&sm->lock);
asmlinkage void do_IRQ(int level, struct pt_regs *regs)
{
struct irq_desc *desc;
+ struct pt_regs *old_regs;
unsigned int irq;
unsigned long status_reg;
local_irq_disable();
+ old_regs = set_irq_regs(regs);
+
irq_enter();
irq = intc_readl(&intc0, INTCAUSE0 - 4 * level);
desc = irq_desc + irq;
- desc->handle_irq(irq, desc, regs);
+ desc->handle_irq(irq, desc);
/*
* Clear all interrupt level masks so that we may handle
sysreg_write(SR, status_reg);
irq_exit();
+
+ set_irq_regs(old_regs);
}
void __init init_IRQ(void)
config M386
bool "386"
+ depends on !UML
---help---
This is the processor type of your CPU. This information is used for
optimizing purposes. In order to compile a kernel that can run on
config X86_USE_3DNOW
bool
- depends on MCYRIXIII || MK7 || MGEODE_LX
+ depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
default y
config X86_OOSTORE
/*
* Parse Interrupt Source Override for the ACPI SCI
*/
-static void acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger)
+static void acpi_sci_ioapic_setup(u32 bus_irq, u32 gsi, u16 polarity, u16 trigger)
{
if (trigger == 0) /* compatible SCI trigger is level */
trigger = 3;
* If GSI is < 16, this will update its flags,
* else it will create a new mp_irqs[] entry.
*/
- mp_override_legacy_irq(gsi, polarity, trigger, gsi);
+ mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
/*
* stash over-ride to indicate we've been here
* and for later update of acpi_fadt
*/
- acpi_sci_override_gsi = gsi;
+ acpi_sci_override_gsi = bus_irq;
return;
}
acpi_table_print_madt_entry(header);
if (intsrc->bus_irq == acpi_fadt.sci_int) {
- acpi_sci_ioapic_setup(intsrc->global_irq,
+ acpi_sci_ioapic_setup(intsrc->bus_irq, intsrc->global_irq,
intsrc->flags.polarity,
intsrc->flags.trigger);
return 0;
* pretend we got one so we can set the SCI flags.
*/
if (!acpi_sci_override_gsi)
- acpi_sci_ioapic_setup(acpi_fadt.sci_int, 0, 0);
+ acpi_sci_ioapic_setup(acpi_fadt.sci_int, acpi_fadt.sci_int, 0, 0);
/* Fill in identity legacy mapings where no override */
mp_config_acpi_legacy_irqs();
#include <linux/module.h>
#include <linux/init.h>
#include <linux/acpi.h>
+#include <linux/cpu.h>
#include <acpi/processor.h>
#include <asm/acpi.h>
flags->bm_check = 1;
}
}
-
EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
+
+/* The code below handles cstate entry with monitor-mwait pair on Intel*/
+
+struct cstate_entry_s {
+ struct {
+ unsigned int eax;
+ unsigned int ecx;
+ } states[ACPI_PROCESSOR_MAX_POWER];
+};
+static struct cstate_entry_s *cpu_cstate_entry; /* per CPU ptr */
+
+static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
+
+#define MWAIT_SUBSTATE_MASK (0xf)
+#define MWAIT_SUBSTATE_SIZE (4)
+
+#define CPUID_MWAIT_LEAF (5)
+#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
+#define CPUID5_ECX_INTERRUPT_BREAK (0x2)
+
+#define MWAIT_ECX_INTERRUPT_BREAK (0x1)
+
+#define NATIVE_CSTATE_BEYOND_HALT (2)
+
+int acpi_processor_ffh_cstate_probe(unsigned int cpu,
+ struct acpi_processor_cx *cx, struct acpi_power_register *reg)
+{
+ struct cstate_entry_s *percpu_entry;
+ struct cpuinfo_x86 *c = cpu_data + cpu;
+
+ cpumask_t saved_mask;
+ int retval;
+ unsigned int eax, ebx, ecx, edx;
+ unsigned int edx_part;
+ unsigned int cstate_type; /* C-state type and not ACPI C-state type */
+ unsigned int num_cstate_subtype;
+
+ if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF )
+ return -1;
+
+ if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT)
+ return -1;
+
+ percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+ percpu_entry->states[cx->index].eax = 0;
+ percpu_entry->states[cx->index].ecx = 0;
+
+ /* Make sure we are running on right CPU */
+ saved_mask = current->cpus_allowed;
+ retval = set_cpus_allowed(current, cpumask_of_cpu(cpu));
+ if (retval)
+ return -1;
+
+ cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
+
+ /* Check whether this particular cx_type (in CST) is supported or not */
+ cstate_type = (cx->address >> MWAIT_SUBSTATE_SIZE) + 1;
+ edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE);
+ num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
+
+ retval = 0;
+ if (num_cstate_subtype < (cx->address & MWAIT_SUBSTATE_MASK)) {
+ retval = -1;
+ goto out;
+ }
+
+ /* mwait ecx extensions INTERRUPT_BREAK should be supported for C2/C3 */
+ if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
+ !(ecx & CPUID5_ECX_INTERRUPT_BREAK)) {
+ retval = -1;
+ goto out;
+ }
+ percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK;
+
+ /* Use the hint in CST */
+ percpu_entry->states[cx->index].eax = cx->address;
+
+ if (!mwait_supported[cstate_type]) {
+ mwait_supported[cstate_type] = 1;
+ printk(KERN_DEBUG "Monitor-Mwait will be used to enter C-%d "
+ "state\n", cx->type);
+ }
+
+out:
+ set_cpus_allowed(current, saved_mask);
+ return retval;
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
+
+void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
+{
+ unsigned int cpu = smp_processor_id();
+ struct cstate_entry_s *percpu_entry;
+
+ percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+ mwait_idle_with_hints(percpu_entry->states[cx->index].eax,
+ percpu_entry->states[cx->index].ecx);
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_enter);
+
+static int __init ffh_cstate_init(void)
+{
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+ if (c->x86_vendor != X86_VENDOR_INTEL)
+ return -1;
+
+ cpu_cstate_entry = alloc_percpu(struct cstate_entry_s);
+ return 0;
+}
+
+static void __exit ffh_cstate_exit(void)
+{
+ if (cpu_cstate_entry) {
+ free_percpu(cpu_cstate_entry);
+ cpu_cstate_entry = NULL;
+ }
+}
+
+arch_initcall(ffh_cstate_init);
+__exitcall(ffh_cstate_exit);
* Also, we KNOW that for the non error case of apm_bios_call, there
* is no useful data returned in the low order 8 bits of eax.
*/
-#define APM_DO_CLI \
- if (apm_info.allow_ints) \
- local_irq_enable(); \
- else \
+
+static inline unsigned long __apm_irq_save(void)
+{
+ unsigned long flags;
+ local_save_flags(flags);
+ if (apm_info.allow_ints) {
+ if (irqs_disabled_flags(flags))
+ local_irq_enable();
+ } else
+ local_irq_disable();
+
+ return flags;
+}
+
+#define apm_irq_save(flags) \
+ do { flags = __apm_irq_save(); } while (0)
+
+static inline void apm_irq_restore(unsigned long flags)
+{
+ if (irqs_disabled_flags(flags))
local_irq_disable();
+ else if (irqs_disabled())
+ local_irq_enable();
+}
#ifdef APM_ZERO_SEGS
# define APM_DECL_SEGS \
save_desc_40 = gdt[0x40 / 8];
gdt[0x40 / 8] = bad_bios_desc;
- local_save_flags(flags);
- APM_DO_CLI;
+ apm_irq_save(flags);
APM_DO_SAVE_SEGS;
apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi);
APM_DO_RESTORE_SEGS;
- local_irq_restore(flags);
+ apm_irq_restore(flags);
gdt[0x40 / 8] = save_desc_40;
put_cpu();
apm_restore_cpus(cpus);
save_desc_40 = gdt[0x40 / 8];
gdt[0x40 / 8] = bad_bios_desc;
- local_save_flags(flags);
- APM_DO_CLI;
+ apm_irq_save(flags);
APM_DO_SAVE_SEGS;
error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax);
APM_DO_RESTORE_SEGS;
- local_irq_restore(flags);
+ apm_irq_restore(flags);
gdt[0x40 / 8] = save_desc_40;
put_cpu();
apm_restore_cpus(cpus);
#ifdef CONFIG_SYSFS
/* Add/Remove thermal_throttle interface for CPU device */
-static __cpuinit int thermal_throttle_add_dev(struct sys_device * sys_dev)
+static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
{
- sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group);
- return 0;
+ return sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group);
}
#ifdef CONFIG_HOTPLUG_CPU
-static __cpuinit int thermal_throttle_remove_dev(struct sys_device * sys_dev)
+static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev)
{
- sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
- return 0;
+ return sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
}
/* Mutex protecting device creation against CPU hotplug */
{
unsigned int cpu = (unsigned long)hcpu;
struct sys_device *sys_dev;
+ int err;
sys_dev = get_cpu_sysdev(cpu);
mutex_lock(&therm_cpu_lock);
switch (action) {
case CPU_ONLINE:
- thermal_throttle_add_dev(sys_dev);
+ err = thermal_throttle_add_dev(sys_dev);
+ WARN_ON(err);
break;
case CPU_DEAD:
thermal_throttle_remove_dev(sys_dev);
static __init int thermal_throttle_init_device(void)
{
unsigned int cpu = 0;
+ int err;
if (!atomic_read(&therm_throt_en))
return 0;
mutex_lock(&therm_cpu_lock);
#endif
/* connect live CPUs to sysfs */
- for_each_online_cpu(cpu)
- thermal_throttle_add_dev(get_cpu_sysdev(cpu));
+ for_each_online_cpu(cpu) {
+ err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
+ WARN_ON(err);
+ }
#ifdef CONFIG_HOTPLUG_CPU
mutex_unlock(&therm_cpu_lock);
#endif
static int __init init_pit_clocksource(void)
{
- if (num_possible_cpus() > 4) /* PIT does not scale! */
+ if (num_possible_cpus() > 1) /* PIT does not scale! */
return 0;
clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, 20);
{
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
- set_irq_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
+ set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
+ "XT");
enable_irq(irq);
}
/*
* 16 old-style INTA-cycle interrupts:
*/
- set_irq_chip_and_handler(i, &i8259A_chip,
- handle_level_irq);
+ set_irq_chip_and_handler_name(i, &i8259A_chip,
+ handle_level_irq, "XT");
} else {
/*
* 'high' PCI IRQs filled in on demand
{
if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
trigger == IOAPIC_LEVEL)
- set_irq_chip_and_handler(irq, &ioapic_chip,
- handle_fasteoi_irq);
+ set_irq_chip_and_handler_name(irq, &ioapic_chip,
+ handle_fasteoi_irq, "fasteoi");
else
- set_irq_chip_and_handler(irq, &ioapic_chip,
- handle_edge_irq);
+ set_irq_chip_and_handler_name(irq, &ioapic_chip,
+ handle_edge_irq, "edge");
set_intr_gate(vector, interrupt[irq]);
}
printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
disable_8259A_irq(0);
- set_irq_chip_and_handler(0, &lapic_chip, handle_fasteoi_irq);
+ set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
+ "fasteio");
apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
enable_8259A_irq(0);
write_msi_msg(irq, &msg);
- set_irq_chip_and_handler(irq, &msi_chip, handle_edge_irq);
+ set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq,
+ "edge");
return 0;
}
}
#endif
-static struct hw_interrupt_type ht_irq_chip = {
+static struct irq_chip ht_irq_chip = {
.name = "PCI-HT",
.mask = mask_ht_irq,
.unmask = unmask_ht_irq,
write_ht_irq_low(irq, low);
write_ht_irq_high(irq, high);
- set_irq_chip_and_handler(irq, &ht_irq_chip, handle_edge_irq);
+ set_irq_chip_and_handler_name(irq, &ht_irq_chip,
+ handle_edge_irq, "edge");
}
return vector;
}
seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
#endif
seq_printf(p, " %8s", irq_desc[i].chip->name);
- seq_printf(p, "-%s", handle_irq_name(irq_desc[i].handle_irq));
+ seq_printf(p, "-%-8s", irq_desc[i].name);
seq_printf(p, " %s", action->name);
for (action=action->next; action; action = action->next)
static int mc_sysdev_add(struct sys_device *sys_dev)
{
- int cpu = sys_dev->id;
+ int err, cpu = sys_dev->id;
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
if (!cpu_online(cpu))
return 0;
+
pr_debug("Microcode:CPU %d added\n", cpu);
memset(uci, 0, sizeof(*uci));
- sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
+
+ err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
+ if (err)
+ return err;
microcode_init_cpu(cpu);
return 0;
* We execute MONITOR against need_resched and enter optimized wait state
* through MWAIT. Whenever someone changes need_resched, we would be woken
* up from MWAIT (without an IPI).
+ *
+ * New with Core Duo processors, MWAIT can take some hints based on CPU
+ * capability.
*/
-static void mwait_idle(void)
+void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
{
- local_irq_enable();
-
- while (!need_resched()) {
+ if (!need_resched()) {
__monitor((void *)¤t_thread_info()->flags, 0, 0);
smp_mb();
- if (need_resched())
- break;
- __mwait(0, 0);
+ if (!need_resched())
+ __mwait(eax, ecx);
}
}
+/* Default MONITOR/MWAIT with no hints, used for default C1 state */
+static void mwait_idle(void)
+{
+ local_irq_enable();
+ while (!need_resched())
+ mwait_idle_with_hints(0, 0);
+}
+
void __devinit select_idle_routine(const struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_MWAIT)) {
void __init zone_sizes_init(void)
{
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+ max_zone_pfns[ZONE_DMA] =
+ virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+ max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
#ifdef CONFIG_HIGHMEM
- unsigned long max_zone_pfns[MAX_NR_ZONES] = {
- virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT,
- max_low_pfn,
- highend_pfn};
+ max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
add_active_range(0, 0, highend_pfn);
#else
- unsigned long max_zone_pfns[MAX_NR_ZONES] = {
- virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT,
- max_low_pfn};
add_active_range(0, 0, max_low_pfn);
#endif
.long sys_vmsplice
.long sys_move_pages
.long sys_getcpu
+ .long sys_epoll_pwait
int change = 0;
/* check to see if we should switch to the safe clocksource: */
- if (clocksource_tsc.rating != 50 && check_tsc_unstable()) {
- clocksource_tsc.rating = 50;
+ if (clocksource_tsc.rating != 0 && check_tsc_unstable()) {
+ clocksource_tsc.rating = 0;
clocksource_reselect();
change = 1;
}
clocksource_tsc.shift);
/* lower the rating if we already know its unstable: */
if (check_tsc_unstable())
- clocksource_tsc.rating = 50;
+ clocksource_tsc.rating = 0;
init_timer(&verify_tsc_freq_timer);
verify_tsc_freq_timer.function = verify_tsc_freq;
EXPORT_SYMBOL(__clear_user);
/**
- * strlen_user: - Get the size of a string in user space.
+ * strnlen_user: - Get the size of a string in user space.
* @s: The string to measure.
* @n: The maximum valid length
*
#ifdef CONFIG_SMP
static void
-voyager_dump(int dummy1, struct pt_regs *dummy2, struct tty_struct *dummy3)
+voyager_dump(int dummy1, struct tty_struct *dummy3)
{
/* get here via a sysrq */
voyager_smp_dump();
* off the timer tick to the SMP code, since the VIC doesn't have an
* internal timer (The QIC does, but that's another story). */
void
-voyager_timer_interrupt(struct pt_regs *regs)
+voyager_timer_interrupt(void)
{
if((jiffies & 0x3ff) == 0) {
}
}
#ifdef CONFIG_SMP
- smp_vic_timer_interrupt(regs);
+ smp_vic_timer_interrupt();
#endif
}
static void ack_special_QIC_CPI(__u8 cpi);
static void ack_VIC_CPI(__u8 cpi);
static void send_CPI_allbutself(__u8 cpi);
-static void enable_vic_irq(unsigned int irq);
-static void disable_vic_irq(unsigned int irq);
+static void mask_vic_irq(unsigned int irq);
+static void unmask_vic_irq(unsigned int irq);
static unsigned int startup_vic_irq(unsigned int irq);
static void enable_local_vic_irq(unsigned int irq);
static void disable_local_vic_irq(unsigned int irq);
/* The VIC IRQ descriptors -- these look almost identical to the
* 8259 IRQs except that masks and things must be kept per processor
*/
-static struct hw_interrupt_type vic_irq_type = {
- .typename = "VIC-level",
- .startup = startup_vic_irq,
- .shutdown = disable_vic_irq,
- .enable = enable_vic_irq,
- .disable = disable_vic_irq,
- .ack = before_handle_vic_irq,
- .end = after_handle_vic_irq,
- .set_affinity = set_vic_irq_affinity,
+static struct irq_chip vic_chip = {
+ .name = "VIC",
+ .startup = startup_vic_irq,
+ .mask = mask_vic_irq,
+ .unmask = unmask_vic_irq,
+ .set_affinity = set_vic_irq_affinity,
};
/* used to count up as CPUs are brought on line (starts at 0) */
fastcall void
smp_qic_timer_interrupt(struct pt_regs *regs)
{
- ack_QIC_CPI(QIC_TIMER_CPI);
struct pt_regs *old_regs = set_irq_regs(regs);
- wrapper_smp_local_timer_interrupt(void);
+ ack_QIC_CPI(QIC_TIMER_CPI);
+ wrapper_smp_local_timer_interrupt();
set_irq_regs(old_regs);
}
/* this function is triggered in time.c when a clock tick fires
* we need to re-broadcast the tick to all CPUs */
void
-smp_vic_timer_interrupt(struct pt_regs *regs)
+smp_vic_timer_interrupt(void)
{
- struct pt_regs *old_regs = set_irq_regs(regs);
send_CPI_allbutself(VIC_TIMER_CPI);
smp_local_timer_interrupt();
- set_irq_regs(old_regs);
}
/* local (per CPU) timer interrupt. It does both profiling and
per_cpu(prof_counter, cpu);
}
- update_process_times(user_mode_vm(irq_regs));
+ update_process_times(user_mode_vm(get_irq_regs()));
}
if( ((1<<cpu) & voyager_extended_vic_processors) == 0)
return 0;
}
+/* This is a bit of a mess, but forced on us by the genirq changes
+ * there's no genirq handler that really does what voyager wants
+ * so hack it up with the simple IRQ handler */
+static void fastcall
+handle_vic_irq(unsigned int irq, struct irq_desc *desc)
+{
+ before_handle_vic_irq(irq);
+ handle_simple_irq(irq, desc);
+ after_handle_vic_irq(irq);
+}
+
/* The CPIs are handled in the per cpu 8259s, so they must be
* enabled to be received: FIX: enabling the CPIs in the early
* This is for later: first 16 correspond to PC IRQs; next 16
* are Primary MC IRQs and final 16 are Secondary MC IRQs */
for(i = 0; i < 48; i++)
- irq_desc[i].chip = &vic_irq_type;
+ set_irq_chip_and_handler(i, &vic_chip, handle_vic_irq);
}
/* send a CPI at level cpi to a set of cpus in cpuset (set 1 bit per
static unsigned int
startup_vic_irq(unsigned int irq)
{
- enable_vic_irq(irq);
+ unmask_vic_irq(irq);
return 0;
}
* adjust their masks accordingly. */
static void
-enable_vic_irq(unsigned int irq)
+unmask_vic_irq(unsigned int irq)
{
/* linux doesn't to processor-irq affinity, so enable on
* all CPUs we know about */
__u32 processorList = 0;
unsigned long flags;
- VDEBUG(("VOYAGER: enable_vic_irq(%d) CPU%d affinity 0x%lx\n",
+ VDEBUG(("VOYAGER: unmask_vic_irq(%d) CPU%d affinity 0x%lx\n",
irq, cpu, cpu_irq_affinity[cpu]));
spin_lock_irqsave(&vic_irq_lock, flags);
for_each_online_cpu(real_cpu) {
}
static void
-disable_vic_irq(unsigned int irq)
+mask_vic_irq(unsigned int irq)
{
/* lazy disable, do nothing */
}
* disabled again as it comes in (voyager lazy disable). If
* the affinity map is tightened to disable the interrupt on a
* cpu, it will be pushed off when it comes in */
- enable_vic_irq(irq);
+ unmask_vic_irq(irq);
}
static void
void __init zone_sizes_init(void)
{
int nid;
- unsigned long max_zone_pfns[MAX_NR_ZONES] = {
- virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT,
- max_low_pfn,
- highend_pfn
- };
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+ max_zone_pfns[ZONE_DMA] =
+ virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+ max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+ max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
/* If SRAT has not registered memory, register it now */
if (find_max_pfn_with_active_regions() == 0) {
efi_memmap_walk(count_pages, &num_physpages);
max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = max_dma;
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
max_pfn = mem_data[node].max_pfn;
}
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = max_dma;
max_zone_pfns[ZONE_NORMAL] = max_pfn;
free_area_init_nodes(max_zone_pfns);
}
struct seq_operations cpuinfo_op = {
- start: c_start,
- next: c_next,
- stop: c_stop,
- show: show_cpuinfo,
+ .start = c_start,
+ .next = c_next,
+ .stop = c_stop,
+ .show = show_cpuinfo,
};
#endif /* CONFIG_PROC_FS */
/* INT0 : LAN controller (RTL8019AS) */
irq_desc[M32R_IRQ_INT0].status = IRQ_DISABLED;
irq_desc[M32R_IRQ_INT0].chip = &mappi_irq_type;
- irq_desc[M32R_IRQ_INT0].action = 0;
+ irq_desc[M32R_IRQ_INT0].action = NULL;
irq_desc[M32R_IRQ_INT0].depth = 1;
icu_data[M32R_IRQ_INT0].icucr = M32R_ICUCR_IEN|M32R_ICUCR_ISMOD10;
disable_mappi_irq(M32R_IRQ_INT0);
/* MFT2 : system timer */
irq_desc[M32R_IRQ_MFT2].status = IRQ_DISABLED;
irq_desc[M32R_IRQ_MFT2].chip = &mappi_irq_type;
- irq_desc[M32R_IRQ_MFT2].action = 0;
+ irq_desc[M32R_IRQ_MFT2].action = NULL;
irq_desc[M32R_IRQ_MFT2].depth = 1;
icu_data[M32R_IRQ_MFT2].icucr = M32R_ICUCR_IEN;
disable_mappi_irq(M32R_IRQ_MFT2);
/* SIO0_R : uart receive data */
irq_desc[M32R_IRQ_SIO0_R].status = IRQ_DISABLED;
irq_desc[M32R_IRQ_SIO0_R].chip = &mappi_irq_type;
- irq_desc[M32R_IRQ_SIO0_R].action = 0;
+ irq_desc[M32R_IRQ_SIO0_R].action = NULL;
irq_desc[M32R_IRQ_SIO0_R].depth = 1;
icu_data[M32R_IRQ_SIO0_R].icucr = 0;
disable_mappi_irq(M32R_IRQ_SIO0_R);
/* SIO0_S : uart send data */
irq_desc[M32R_IRQ_SIO0_S].status = IRQ_DISABLED;
irq_desc[M32R_IRQ_SIO0_S].chip = &mappi_irq_type;
- irq_desc[M32R_IRQ_SIO0_S].action = 0;
+ irq_desc[M32R_IRQ_SIO0_S].action = NULL;
irq_desc[M32R_IRQ_SIO0_S].depth = 1;
icu_data[M32R_IRQ_SIO0_S].icucr = 0;
disable_mappi_irq(M32R_IRQ_SIO0_S);
/* SIO1_R : uart receive data */
irq_desc[M32R_IRQ_SIO1_R].status = IRQ_DISABLED;
irq_desc[M32R_IRQ_SIO1_R].chip = &mappi_irq_type;
- irq_desc[M32R_IRQ_SIO1_R].action = 0;
+ irq_desc[M32R_IRQ_SIO1_R].action = NULL;
irq_desc[M32R_IRQ_SIO1_R].depth = 1;
icu_data[M32R_IRQ_SIO1_R].icucr = 0;
disable_mappi_irq(M32R_IRQ_SIO1_R);
/* SIO1_S : uart send data */
irq_desc[M32R_IRQ_SIO1_S].status = IRQ_DISABLED;
irq_desc[M32R_IRQ_SIO1_S].chip = &mappi_irq_type;
- irq_desc[M32R_IRQ_SIO1_S].action = 0;
+ irq_desc[M32R_IRQ_SIO1_S].action = NULL;
irq_desc[M32R_IRQ_SIO1_S].depth = 1;
icu_data[M32R_IRQ_SIO1_S].icucr = 0;
disable_mappi_irq(M32R_IRQ_SIO1_S);
/* INT1 : pccard0 interrupt */
irq_desc[M32R_IRQ_INT1].status = IRQ_DISABLED;
irq_desc[M32R_IRQ_INT1].chip = &mappi_irq_type;
- irq_desc[M32R_IRQ_INT1].action = 0;
+ irq_desc[M32R_IRQ_INT1].action = NULL;
irq_desc[M32R_IRQ_INT1].depth = 1;
icu_data[M32R_IRQ_INT1].icucr = M32R_ICUCR_IEN | M32R_ICUCR_ISMOD00;
disable_mappi_irq(M32R_IRQ_INT1);
/* INT2 : pccard1 interrupt */
irq_desc[M32R_IRQ_INT2].status = IRQ_DISABLED;
irq_desc[M32R_IRQ_INT2].chip = &mappi_irq_type;
- irq_desc[M32R_IRQ_INT2].action = 0;
+ irq_desc[M32R_IRQ_INT2].action = NULL;
irq_desc[M32R_IRQ_INT2].depth = 1;
icu_data[M32R_IRQ_INT2].icucr = M32R_ICUCR_IEN | M32R_ICUCR_ISMOD00;
disable_mappi_irq(M32R_IRQ_INT2);
int do_signal(struct pt_regs *, sigset_t *);
asmlinkage int
-sys_rt_sigsuspend(sigset_t *unewset, size_t sigsetsize,
+sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize,
unsigned long r2, unsigned long r3, unsigned long r4,
unsigned long r5, unsigned long r6, struct pt_regs *regs)
{
struct rt_sigframe
{
int sig;
- struct siginfo *pinfo;
- void *puc;
+ struct siginfo __user *pinfo;
+ void __user *puc;
struct siginfo info;
struct ucontext uc;
// struct _fpstate fpstate;
local_irq_save(flags);
__flush_tlb_all();
local_irq_restore(flags);
- smp_call_function(flush_tlb_all_ipi, 0, 1, 1);
+ smp_call_function(flush_tlb_all_ipi, NULL, 1, 1);
preempt_enable();
}
/*
* sys_tas() - test-and-set
*/
-asmlinkage int sys_tas(int *addr)
+asmlinkage int sys_tas(int __user *addr)
{
int oldval;
error = do_pipe(fd);
if (!error) {
- if (copy_to_user((void *)r0, (void *)fd, 2*sizeof(int)))
+ if (copy_to_user((void __user *)r0, fd, 2*sizeof(int)))
error = -EFAULT;
}
return error;
}
}
-asmlinkage int sys_uname(struct old_utsname * name)
+asmlinkage int sys_uname(struct old_utsname __user * name)
{
int err;
if (!name)
#define DO_ERROR(trapnr, signr, str, name) \
asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
{ \
- do_trap(trapnr, signr, 0, regs, error_code, NULL); \
+ do_trap(trapnr, signr, NULL, regs, error_code, NULL); \
}
#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
#include <linux/module.h>
-#include <linux/linkage.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/user.h>
-#include <linux/elfcore.h>
-#include <linux/in6.h>
-#include <linux/interrupt.h>
-
-#include <asm/setup.h>
-#include <asm/machdep.h>
-#include <asm/pgalloc.h>
-#include <asm/irq.h>
-#include <asm/io.h>
#include <asm/semaphore.h>
-#include <asm/checksum.h>
asmlinkage long long __ashldi3 (long long, int);
asmlinkage long long __ashrdi3 (long long, int);
asmlinkage long long __lshrdi3 (long long, int);
asmlinkage long long __muldi3 (long long, long long);
-extern char m68k_debug_device[];
-
-/* platform dependent support */
-
-EXPORT_SYMBOL(m68k_machtype);
-EXPORT_SYMBOL(m68k_cputype);
-EXPORT_SYMBOL(m68k_is040or060);
-EXPORT_SYMBOL(m68k_realnum_memory);
-EXPORT_SYMBOL(m68k_memory);
-#ifndef CONFIG_SUN3
-EXPORT_SYMBOL(cache_push);
-EXPORT_SYMBOL(cache_clear);
-#ifndef CONFIG_SINGLE_MEMORY_CHUNK
-EXPORT_SYMBOL(mm_vtop);
-EXPORT_SYMBOL(mm_ptov);
-EXPORT_SYMBOL(mm_end_of_chunk);
-#else
-EXPORT_SYMBOL(m68k_memoffset);
-#endif /* !CONFIG_SINGLE_MEMORY_CHUNK */
-EXPORT_SYMBOL(__ioremap);
-EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(kernel_set_cachemode);
-#endif /* !CONFIG_SUN3 */
-EXPORT_SYMBOL(m68k_debug_device);
-EXPORT_SYMBOL(mach_hwclk);
-EXPORT_SYMBOL(mach_get_ss);
-EXPORT_SYMBOL(mach_get_rtc_pll);
-EXPORT_SYMBOL(mach_set_rtc_pll);
-#ifdef CONFIG_INPUT_M68K_BEEP_MODULE
-EXPORT_SYMBOL(mach_beep);
-#endif
-EXPORT_SYMBOL(dump_fpu);
-EXPORT_SYMBOL(dump_thread);
-EXPORT_SYMBOL(kernel_thread);
-#ifdef CONFIG_VME
-EXPORT_SYMBOL(vme_brdtype);
-#endif
/* The following are special because they're not called
explicitly (the C compiler generates them). Fortunately,
set_fs (fs);
return pid;
}
+EXPORT_SYMBOL(kernel_thread);
void flush_thread(void)
{
{
unsigned long clone_flags;
unsigned long newsp;
- int *parent_tidptr, *child_tidptr;
+ int __user *parent_tidptr, *child_tidptr;
/* syscall2 puts clone_flags in d1 and usp in d2 */
clone_flags = regs->d1;
newsp = regs->d2;
- parent_tidptr = (int *)regs->d3;
- child_tidptr = (int *)regs->d4;
+ parent_tidptr = (int __user *)regs->d3;
+ child_tidptr = (int __user *)regs->d4;
if (!newsp)
newsp = rdusp();
return do_fork(clone_flags, newsp, regs, 0,
: "memory");
return 1;
}
+EXPORT_SYMBOL(dump_fpu);
/*
* fill in the user structure for a core dump..
/* dump floating point stuff */
dump->u_fpvalid = dump_fpu (regs, &dump->m68kfp);
}
+EXPORT_SYMBOL(dump_thread);
/*
* sys_execve() executes a new program.
*/
-asmlinkage int sys_execve(char *name, char **argv, char **envp)
+asmlinkage int sys_execve(char __user *name, char __user * __user *argv, char __user * __user *envp)
{
int error;
char * filename;
unsigned long m68k_machtype;
unsigned long m68k_cputype;
+EXPORT_SYMBOL(m68k_machtype);
+EXPORT_SYMBOL(m68k_cputype);
unsigned long m68k_fputype;
unsigned long m68k_mmutype;
#ifdef CONFIG_VME
unsigned long vme_brdtype;
+EXPORT_SYMBOL(vme_brdtype);
#endif
int m68k_is040or060;
+EXPORT_SYMBOL(m68k_is040or060);
extern int end;
extern unsigned long availmem;
int m68k_num_memory;
int m68k_realnum_memory;
+EXPORT_SYMBOL(m68k_realnum_memory);
+#ifdef CONFIG_SINGLE_MEMORY_CHUNK
unsigned long m68k_memoffset;
+EXPORT_SYMBOL(m68k_memoffset);
+#endif
struct mem_info m68k_memory[NUM_MEMINFO];
+EXPORT_SYMBOL(m68k_memory);
static struct mem_info m68k_ramdisk;
static char m68k_command_line[CL_SIZE];
char m68k_debug_device[6] = "";
+EXPORT_SYMBOL(m68k_debug_device);
void (*mach_sched_init) (irq_handler_t handler) __initdata = NULL;
/* machine dependent irq functions */
/* machine dependent timer functions */
unsigned long (*mach_gettimeoffset) (void);
int (*mach_hwclk) (int, struct rtc_time*);
+EXPORT_SYMBOL(mach_hwclk);
int (*mach_set_clock_mmss) (unsigned long);
unsigned int (*mach_get_ss)(void);
int (*mach_get_rtc_pll)(struct rtc_pll_info *);
int (*mach_set_rtc_pll)(struct rtc_pll_info *);
+EXPORT_SYMBOL(mach_get_ss);
+EXPORT_SYMBOL(mach_get_rtc_pll);
+EXPORT_SYMBOL(mach_set_rtc_pll);
void (*mach_reset)( void );
void (*mach_halt)( void );
void (*mach_power_off)( void );
#endif
#if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE)
void (*mach_beep)(unsigned int, unsigned int);
+EXPORT_SYMBOL(mach_beep);
#endif
#if defined(CONFIG_ISA) && defined(MULTI_ISA)
int isa_type;
switch (wbs & WBSIZ_040) {
case BA_SIZE_BYTE:
- res = put_user(wbd & 0xff, (char *)wba);
+ res = put_user(wbd & 0xff, (char __user *)wba);
break;
case BA_SIZE_WORD:
- res = put_user(wbd & 0xffff, (short *)wba);
+ res = put_user(wbd & 0xffff, (short __user *)wba);
break;
case BA_SIZE_LONG:
- res = put_user(wbd, (int *)wba);
+ res = put_user(wbd, (int __user *)wba);
break;
}
* used by other architectures /Roman Zippel
*/
+#include <linux/module.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/string.h>
return (void __iomem *)retaddr;
}
+EXPORT_SYMBOL(__ioremap);
/*
* Unmap a ioremap()ed region again
free_io_area((__force void *)addr);
#endif
}
+EXPORT_SYMBOL(iounmap);
/*
* __iounmap unmaps nearly everything, so be careful
flush_tlb_all();
}
+EXPORT_SYMBOL(kernel_set_cachemode);
* Copyright (C) 1995 Hamish Macdonald
*/
+#include <linux/module.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/string.h>
return -1;
}
-#endif
+EXPORT_SYMBOL(mm_vtop);
-#ifndef CONFIG_SINGLE_MEMORY_CHUNK
unsigned long mm_ptov (unsigned long paddr)
{
int i = 0;
#endif
return -1;
}
+EXPORT_SYMBOL(mm_ptov);
#endif
/* invalidate page in both caches */
mach_l2_flush(0);
#endif
}
+EXPORT_SYMBOL(cache_clear); /* probably can be unexported */
/*
mach_l2_flush(1);
#endif
}
+EXPORT_SYMBOL(cache_push); /* probably can be unexported */
#ifndef CONFIG_SINGLE_MEMORY_CHUNK
int mm_end_of_chunk (unsigned long addr, int len)
return 1;
return 0;
}
+EXPORT_SYMBOL(mm_end_of_chunk);
#endif
* for more details.
*/
+#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
}
}
-void *sun3_ioremap(unsigned long phys, unsigned long size,
+void __iomem *sun3_ioremap(unsigned long phys, unsigned long size,
unsigned long type)
{
struct vm_struct *area;
virt += seg_pages * PAGE_SIZE;
}
- return (void *)ret;
+ return (void __iomem *)ret;
}
-void *__ioremap(unsigned long phys, unsigned long size, int cache)
+void __iomem *__ioremap(unsigned long phys, unsigned long size, int cache)
{
return sun3_ioremap(phys, size, SUN3_PAGE_TYPE_IO);
}
+EXPORT_SYMBOL(__ioremap);
-void iounmap(void *addr)
+void iounmap(void __iomem *addr)
{
vfree((void *)(PAGE_MASK & (unsigned long)addr));
}
+EXPORT_SYMBOL(iounmap);
/* sun3_map_test(addr, val) -- Reads a byte from addr, storing to val,
* trapping the potential read fault. Returns 0 if the access faulted,
# Makefile for Linux arch/m68k/sun3 source directory
#
-obj-y := sun3_ksyms.o sun3ints.o sun3dvma.o sbus.o idprom.o
+obj-y := sun3ints.o sun3dvma.o sbus.o idprom.o
obj-$(CONFIG_SUN3) += config.o mmu_emu.o leds.o dvma.o intersil.o
* Sun3/3x models added by David Monro (davidm@psrg.cs.usyd.edu.au)
*/
+#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
#include <asm/machines.h> /* Fun with Sun released architectures. */
struct idprom *idprom;
+EXPORT_SYMBOL(idprom);
+
static struct idprom idprom_buffer;
/* Here is the master table of Sun machines which use some implementation
+++ /dev/null
-#include <linux/module.h>
-#include <linux/types.h>
-#include <asm/dvma.h>
-#include <asm/idprom.h>
-
-/*
- * Add things here when you find the need for it.
- */
-EXPORT_SYMBOL(dvma_map_align);
-EXPORT_SYMBOL(dvma_unmap);
-EXPORT_SYMBOL(dvma_malloc_align);
-EXPORT_SYMBOL(dvma_free);
-EXPORT_SYMBOL(idprom);
* Contains common routines for sun3/sun3x DVMA management.
*/
+#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/list.h>
BUG();
return 0;
}
+EXPORT_SYMBOL(dvma_map_align);
void dvma_unmap(void *baddr)
{
return;
}
-
+EXPORT_SYMBOL(dvma_unmap);
void *dvma_malloc_align(unsigned long len, unsigned long align)
{
return (void *)vaddr;
}
+EXPORT_SYMBOL(dvma_malloc_align);
void dvma_free(void *vaddr)
{
return;
}
+EXPORT_SYMBOL(dvma_free);
.long sys_mq_notify /* 275 */
.long sys_mq_getsetattr
.long sys_waitid
- .long sys_ni_syscall /* sys_setaltroot */
- .long sys_ni_syscall /* sys_add_key */
- .long sys_ni_syscall /* 280 */ /* sys_request_key */
- .long sys_ni_syscall /* sys_keyctl */
+ .long sys_ni_syscall /* for sys_vserver */
+ .long sys_add_key
+ .long sys_request_key /* 280 */
+ .long sys_keyctl
+ .long sys_ioprio_set
+ .long sys_ioprio_get
+ .long sys_inotify_init
+ .long sys_inotify_add_watch /* 285 */
+ .long sys_inotify_rm_watch
+ .long sys_migrate_pages
+ .long sys_openat
+ .long sys_mkdirat
+ .long sys_mknodat /* 290 */
+ .long sys_fchownat
+ .long sys_futimesat
+ .long sys_fstatat64
+ .long sys_unlinkat
+ .long sys_renameat /* 295 */
+ .long sys_linkat
+ .long sys_symlinkat
+ .long sys_readlinkat
+ .long sys_fchmodat
+ .long sys_faccessat /* 300 */
+ .long sys_ni_syscall /* Reserved for pselect6 */
+ .long sys_ni_syscall /* Reserved for ppoll */
+ .long sys_unshare
+ .long sys_set_robust_list
+ .long sys_get_robust_list /* 305 */
+ .long sys_splice
+ .long sys_sync_file_range
+ .long sys_tee
+ .long sys_vmsplice
+ .long sys_move_pages /* 310 */
.rept NR_syscalls-(.-sys_call_table)/4
.long sys_ni_syscall
# carefully avoid to add it redundantly because gcc 3.3/3.4 complains
# when fed the toolchain default!
#
-cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' && echo -EB -D__MIPSEB__)
-cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' || echo -EL -D__MIPSEL__)
+# Certain gcc versions upto gcc 4.1.1 (probably 4.2-subversion as of
+# 2006-10-10 don't properly change the the predefined symbols if -EB / -EL
+# are used, so we kludge that here. A bug has been filed at
+# http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29413.
+#
+undef-all += -UMIPSEB -U_MIPSEB -U__MIPSEB -U__MIPSEB__
+undef-all += -UMIPSEL -U_MIPSEL -U__MIPSEL -U__MIPSEL__
+predef-be += -DMIPSEB -D_MIPSEB -D__MIPSEB -D__MIPSEB__
+predef-le += -DMIPSEL -D_MIPSEL -D__MIPSEL -D__MIPSEL__
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' && echo -EB $(undef-all) $(predef-be))
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' || echo -EL $(undef-all) $(predef-le))
cflags-$(CONFIG_SB1XXX_CORELIS) += $(call cc-option,-mno-sched-prolog) \
-fno-omit-frame-pointer
#
# Automatically generated make config: don't edit
-# Linux kernel version: 2.6.18-rc1
-# Thu Jul 6 10:02:58 2006
+# Linux kernel version: 2.6.19-rc1
+# Wed Oct 11 01:41:41 2006
#
CONFIG_MIPS=y
# CONFIG_MIPS_COBALT is not set
# CONFIG_MACH_DECSTATION is not set
# CONFIG_MIPS_EV64120 is not set
-# CONFIG_MIPS_IVR is not set
-# CONFIG_MIPS_ITE8172 is not set
# CONFIG_MACH_JAZZ is not set
# CONFIG_LASAT is not set
# CONFIG_MIPS_ATLAS is not set
CONFIG_GENERIC_FIND_NEXT_BIT=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_TIME=y
CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
CONFIG_DMA_COHERENT=y
CONFIG_CPU_BIG_ENDIAN=y
# CONFIG_PAGE_SIZE_64KB is not set
# CONFIG_SIBYTE_DMA_PAGEOPS is not set
CONFIG_MIPS_MT_DISABLED=y
-# CONFIG_MIPS_MT_SMTC is not set
# CONFIG_MIPS_MT_SMP is not set
+# CONFIG_MIPS_MT_SMTC is not set
# CONFIG_MIPS_VPE_LOADER is not set
CONFIG_CPU_HAS_LLSC=y
CONFIG_CPU_HAS_SYNC=y
CONFIG_LOCALVERSION_AUTO=y
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
+# CONFIG_IPC_NS is not set
# CONFIG_POSIX_MQUEUE is not set
# CONFIG_BSD_PROCESS_ACCT is not set
-CONFIG_SYSCTL=y
+# CONFIG_TASKSTATS is not set
+# CONFIG_UTS_NS is not set
# CONFIG_AUDIT is not set
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
# CONFIG_RELAY is not set
CONFIG_INITRAMFS_SOURCE=""
# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SYSCTL=y
CONFIG_EMBEDDED=y
+# CONFIG_SYSCTL_SYSCALL is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
# CONFIG_KALLSYMS_EXTRA_PASS is not set
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_BASE_FULL=y
-CONFIG_RT_MUTEXES=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SHMEM=y
CONFIG_SLAB=y
CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_RT_MUTEXES=y
# CONFIG_TINY_SHMEM is not set
CONFIG_BASE_SMALL=0
# CONFIG_SLOB is not set
#
# Block layer
#
+CONFIG_BLOCK=y
# CONFIG_BLK_DEV_IO_TRACE is not set
#
CONFIG_HW_HAS_PCI=y
CONFIG_PCI=y
CONFIG_PCI_DOMAINS=y
+# CONFIG_PCI_MULTITHREAD_PROBE is not set
CONFIG_PCI_DEBUG=y
CONFIG_MMU=y
#
# PCCARD (PCMCIA/CardBus) support
#
-# CONFIG_PCCARD is not set
#
# PCI Hotplug Support
#
-# CONFIG_HOTPLUG_PCI is not set
#
# Executable file formats
CONFIG_MIPS32_COMPAT=y
CONFIG_COMPAT=y
CONFIG_MIPS32_O32=y
-# CONFIG_MIPS32_N32 is not set
+CONFIG_MIPS32_N32=y
CONFIG_BINFMT_ELF32=y
#
CONFIG_UNIX=y
CONFIG_XFRM=y
CONFIG_XFRM_USER=m
+# CONFIG_XFRM_SUB_POLICY is not set
CONFIG_NET_KEY=y
CONFIG_INET=y
# CONFIG_IP_MULTICAST is not set
# CONFIG_INET_TUNNEL is not set
CONFIG_INET_XFRM_MODE_TRANSPORT=m
CONFIG_INET_XFRM_MODE_TUNNEL=m
+CONFIG_INET_XFRM_MODE_BEET=y
CONFIG_INET_DIAG=y
CONFIG_INET_TCP_DIAG=y
# CONFIG_TCP_CONG_ADVANCED is not set
-CONFIG_TCP_CONG_BIC=y
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
# CONFIG_IPV6 is not set
# CONFIG_INET6_XFRM_TUNNEL is not set
# CONFIG_INET6_TUNNEL is not set
# CONFIG_ATALK is not set
# CONFIG_X25 is not set
# CONFIG_LAPB is not set
-# CONFIG_NET_DIVERT is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set
#
CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
-# CONFIG_FW_LOADER is not set
# CONFIG_DEBUG_DRIVER is not set
# CONFIG_SYS_HYPERVISOR is not set
CONFIG_BLK_DEV_NBD=m
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_RAM is not set
-# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_BLK_DEV_INITRD=y
# CONFIG_CDROM_PKTCDVD is not set
# CONFIG_ATA_OVER_ETH is not set
# ATA/ATAPI/MFM/RLL support
#
CONFIG_IDE=y
+CONFIG_IDE_MAX_HWIFS=4
CONFIG_BLK_DEV_IDE=y
#
# IDE chipset support/bugfixes
#
CONFIG_IDE_GENERIC=y
-# CONFIG_BLK_DEV_IDEPCI is not set
+CONFIG_BLK_DEV_IDEPCI=y
+# CONFIG_IDEPCI_SHARE_IRQ is not set
+# CONFIG_BLK_DEV_OFFBOARD is not set
+CONFIG_BLK_DEV_GENERIC=y
+# CONFIG_BLK_DEV_OPTI621 is not set
+CONFIG_BLK_DEV_IDEDMA_PCI=y
+# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
+# CONFIG_IDEDMA_PCI_AUTO is not set
+# CONFIG_BLK_DEV_AEC62XX is not set
+# CONFIG_BLK_DEV_ALI15X3 is not set
+# CONFIG_BLK_DEV_AMD74XX is not set
+CONFIG_BLK_DEV_CMD64X=y
+# CONFIG_BLK_DEV_TRIFLEX is not set
+# CONFIG_BLK_DEV_CY82C693 is not set
+# CONFIG_BLK_DEV_CS5520 is not set
+# CONFIG_BLK_DEV_CS5530 is not set
+# CONFIG_BLK_DEV_HPT34X is not set
+# CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_JMICRON is not set
+# CONFIG_BLK_DEV_SC1200 is not set
+# CONFIG_BLK_DEV_PIIX is not set
+# CONFIG_BLK_DEV_IT821X is not set
+# CONFIG_BLK_DEV_NS87415 is not set
+# CONFIG_BLK_DEV_PDC202XX_OLD is not set
+# CONFIG_BLK_DEV_PDC202XX_NEW is not set
+# CONFIG_BLK_DEV_SVWKS is not set
+# CONFIG_BLK_DEV_SIIMAGE is not set
+# CONFIG_BLK_DEV_SLC90E66 is not set
+# CONFIG_BLK_DEV_TRM290 is not set
+# CONFIG_BLK_DEV_VIA82CXXX is not set
# CONFIG_BLK_DEV_IDE_SWARM is not set
# CONFIG_IDE_ARM is not set
-# CONFIG_BLK_DEV_IDEDMA is not set
+CONFIG_BLK_DEV_IDEDMA=y
+# CONFIG_IDEDMA_IVB is not set
# CONFIG_IDEDMA_AUTO is not set
# CONFIG_BLK_DEV_HD is not set
#
# CONFIG_RAID_ATTRS is not set
# CONFIG_SCSI is not set
+# CONFIG_SCSI_NETLINK is not set
+
+#
+# Serial ATA (prod) and Parallel ATA (experimental) drivers
+#
+# CONFIG_ATA is not set
#
# Multi-device support (RAID and LVM)
# CONFIG_SK98LIN is not set
# CONFIG_TIGON3 is not set
# CONFIG_BNX2 is not set
+# CONFIG_QLA3XXX is not set
#
# Ethernet (10000 Mbit)
# CONFIG_I2C_ALGOBIT is not set
# CONFIG_I2C_ALGOPCF is not set
# CONFIG_I2C_ALGOPCA is not set
-CONFIG_I2C_ALGO_SIBYTE=y
#
# I2C Hardware Bus support
#
# Misc devices
#
+# CONFIG_TIFM_CORE is not set
#
# Multimedia devices
#
# CONFIG_VIDEO_DEV is not set
-CONFIG_VIDEO_V4L2=y
#
# Digital Video Broadcasting Devices
#
# CONFIG_FIRMWARE_EDID is not set
# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
#
# Sound
# CONFIG_JFS_FS is not set
CONFIG_FS_POSIX_ACL=y
# CONFIG_XFS_FS is not set
+# CONFIG_GFS2_FS is not set
# CONFIG_OCFS2_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_ROMFS_FS is not set
#
CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
+CONFIG_PROC_SYSCTL=y
CONFIG_SYSFS=y
-# CONFIG_TMPFS is not set
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
# CONFIG_HUGETLB_PAGE is not set
CONFIG_RAMFS=y
# CONFIG_CONFIGFS_FS is not set
#
# CONFIG_ADFS_FS is not set
# CONFIG_AFFS_FS is not set
+# CONFIG_ECRYPT_FS is not set
# CONFIG_HFS_FS is not set
# CONFIG_HFSPLUS_FS is not set
# CONFIG_BEFS_FS is not set
# CONFIG_RPCSEC_GSS_SPKM3 is not set
# CONFIG_SMB_FS is not set
# CONFIG_CIFS is not set
-# CONFIG_CIFS_DEBUG2 is not set
# CONFIG_NCP_FS is not set
# CONFIG_CODA_FS is not set
# CONFIG_AFS_FS is not set
#
# CONFIG_NLS is not set
+#
+# Distributed Lock Manager
+#
+
#
# Profiling support
#
# Kernel hacking
#
CONFIG_TRACE_IRQFLAGS_SUPPORT=y
-CONFIG_PRINTK_TIME=y
+# CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_MUST_CHECK=y
CONFIG_MAGIC_SYSRQ=y
# CONFIG_UNUSED_SYMBOLS is not set
CONFIG_DEBUG_KERNEL=y
# CONFIG_DEBUG_SPINLOCK is not set
CONFIG_DEBUG_MUTEXES=y
# CONFIG_DEBUG_RWSEMS is not set
+# CONFIG_DEBUG_LOCK_ALLOC is not set
+# CONFIG_PROVE_LOCKING is not set
# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
# CONFIG_DEBUG_KOBJECT is not set
# CONFIG_DEBUG_INFO is not set
# CONFIG_DEBUG_FS is not set
# CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_LIST is not set
CONFIG_FORCED_INLINING=y
# CONFIG_RCU_TORTURE_TEST is not set
CONFIG_CROSSCOMPILE=y
# Cryptographic options
#
CONFIG_CRYPTO=y
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_BLKCIPHER=m
+CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_MANAGER=m
CONFIG_CRYPTO_HMAC=y
CONFIG_CRYPTO_NULL=y
CONFIG_CRYPTO_MD4=y
CONFIG_CRYPTO_SHA512=y
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_TGR192=m
+CONFIG_CRYPTO_ECB=m
+CONFIG_CRYPTO_CBC=m
CONFIG_CRYPTO_DES=y
CONFIG_CRYPTO_BLOWFISH=y
CONFIG_CRYPTO_TWOFISH=y
+CONFIG_CRYPTO_TWOFISH_COMMON=y
CONFIG_CRYPTO_SERPENT=y
CONFIG_CRYPTO_AES=m
# CONFIG_CRYPTO_CAST5 is not set
extern void jazz_machine_halt(void);
extern void jazz_machine_power_off(void);
-void __init plat_time_init(struct irqaction *irq)
+void __init plat_timer_setup(struct irqaction *irq)
{
/* set the clock to 100 Hz */
r4030_write_reg32(JAZZ_TIMER_INTERVAL, 9);
void flush_tlb_all(void)
{
- on_each_cpu(flush_tlb_all_ipi, 0, 1, 1);
+ on_each_cpu(flush_tlb_all_ipi, NULL, 1, 1);
}
static void flush_tlb_mm_ipi(void *mm)
* kernel. For example, we should never put a copy on a headless node,
* and we should respect the topology of the machine.
*/
-void __init setup_replication_mask()
+void __init setup_replication_mask(void)
{
cnodeid_t cnode;
* independent of board/firmware
*/
-static void *mailbox_0_set_regs[] = {
+static volatile void *mailbox_0_set_regs[] = {
IOADDR(A_BCM1480_IMR_CPU0_BASE + R_BCM1480_IMR_MAILBOX_0_SET_CPU),
IOADDR(A_BCM1480_IMR_CPU1_BASE + R_BCM1480_IMR_MAILBOX_0_SET_CPU),
IOADDR(A_BCM1480_IMR_CPU2_BASE + R_BCM1480_IMR_MAILBOX_0_SET_CPU),
IOADDR(A_BCM1480_IMR_CPU3_BASE + R_BCM1480_IMR_MAILBOX_0_SET_CPU),
};
-static void *mailbox_0_clear_regs[] = {
+static volatile void *mailbox_0_clear_regs[] = {
IOADDR(A_BCM1480_IMR_CPU0_BASE + R_BCM1480_IMR_MAILBOX_0_CLR_CPU),
IOADDR(A_BCM1480_IMR_CPU1_BASE + R_BCM1480_IMR_MAILBOX_0_CLR_CPU),
IOADDR(A_BCM1480_IMR_CPU2_BASE + R_BCM1480_IMR_MAILBOX_0_CLR_CPU),
IOADDR(A_BCM1480_IMR_CPU3_BASE + R_BCM1480_IMR_MAILBOX_0_CLR_CPU),
};
-static void *mailbox_0_regs[] = {
+static volatile void *mailbox_0_regs[] = {
IOADDR(A_BCM1480_IMR_CPU0_BASE + R_BCM1480_IMR_MAILBOX_0_CPU),
IOADDR(A_BCM1480_IMR_CPU1_BASE + R_BCM1480_IMR_MAILBOX_0_CPU),
IOADDR(A_BCM1480_IMR_CPU2_BASE + R_BCM1480_IMR_MAILBOX_0_CPU),
EXPORT_SYMBOL(memcpy_fromio);
EXPORT_SYMBOL(memset_io);
-#include <asm/unistd.h>
-EXPORT_SYMBOL(sys_lseek);
-EXPORT_SYMBOL(sys_write);
-
#include <asm/semaphore.h>
EXPORT_SYMBOL(__up);
EXPORT_SYMBOL(__down_interruptible);
# CONFIG_AMIGA_PARTITION is not set
# CONFIG_ATARI_PARTITION is not set
# CONFIG_MAC_PARTITION is not set
-# CONFIG_MSDOS_PARTITION is not set
+CONFIG_MSDOS_PARTITION=y
# CONFIG_LDM_PARTITION is not set
# CONFIG_SGI_PARTITION is not set
# CONFIG_ULTRIX_PARTITION is not set
.cpu_user_features = COMMON_USER_POWER6,
.icache_bsize = 128,
.dcache_bsize = 128,
- .num_pmcs = 8,
+ .num_pmcs = 6,
.oprofile_cpu_type = "ppc64/power6",
.oprofile_type = PPC_OPROFILE_POWER4,
.oprofile_mmcra_sihv = POWER6_MMCRA_SIHV,
end = res->end - off;
io_base_lo = (start >> 8) & PCI_IO_RANGE_MASK;
io_limit_lo = (end >> 8) & PCI_IO_RANGE_MASK;
- if (end > 0xffff) {
- pci_write_config_word(dev, PCI_IO_BASE_UPPER16,
- start >> 16);
- pci_write_config_word(dev, PCI_IO_LIMIT_UPPER16,
- end >> 16);
+ if (end > 0xffff)
io_base_lo |= PCI_IO_RANGE_TYPE_32;
- } else
+ else
io_base_lo |= PCI_IO_RANGE_TYPE_16;
+ pci_write_config_word(dev, PCI_IO_BASE_UPPER16,
+ start >> 16);
+ pci_write_config_word(dev, PCI_IO_LIMIT_UPPER16,
+ end >> 16);
pci_write_config_byte(dev, PCI_IO_BASE, io_base_lo);
pci_write_config_byte(dev, PCI_IO_LIMIT, io_limit_lo);
pci_setup_pci_controller(phb);
phb->arch_data = dev;
phb->is_dynamic = mem_init_done;
- if (dev)
- PHB_SET_NODE(phb, of_node_to_nid(dev));
+ if (dev) {
+ int nid = of_node_to_nid(dev);
+
+ if (nid < 0 || !node_online(nid))
+ nid = -1;
+
+ PHB_SET_NODE(phb, nid);
+ }
return phb;
}
static int instructions_to_print = 16;
-#ifdef CONFIG_PPC64
-#define BAD_PC(pc) ((REGION_ID(pc) != KERNEL_REGION_ID) && \
- (REGION_ID(pc) != VMALLOC_REGION_ID))
-#else
-#define BAD_PC(pc) ((pc) < KERNELBASE)
-#endif
-
static void show_instructions(struct pt_regs *regs)
{
int i;
* bad address because the pc *should* only be a
* kernel address.
*/
- if (BAD_PC(pc) || __get_user(instr, (unsigned int __user *)pc)) {
+ if (!__kernel_text_address(pc) ||
+ __get_user(instr, (unsigned int __user *)pc)) {
printk("XXXXXXXX ");
} else {
if (regs->nip == pc)
void altivec_unavailable_exception(struct pt_regs *regs)
{
-#if !defined(CONFIG_ALTIVEC)
if (user_mode(regs)) {
/* A user program has executed an altivec instruction,
but this kernel doesn't support altivec. */
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
return;
}
-#endif
+
printk(KERN_EMERG "Unrecoverable VMX/Altivec Unavailable Exception "
"%lx at %lx\n", regs->trap, regs->nip);
die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
top_of_ram, total_ram);
printk(KERN_DEBUG "Memory hole size: %ldMB\n",
(top_of_ram - total_ram) >> 20);
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
#ifdef CONFIG_HIGHMEM
- max_zone_pfns[0] = total_lowmem >> PAGE_SHIFT;
- max_zone_pfns[1] = top_of_ram >> PAGE_SHIFT;
+ max_zone_pfns[ZONE_DMA] = total_lowmem >> PAGE_SHIFT;
+ max_zone_pfns[ZONE_HIGHMEM] = top_of_ram >> PAGE_SHIFT;
#else
- max_zone_pfns[0] = top_of_ram >> PAGE_SHIFT;
+ max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
#endif
free_area_init_nodes(max_zone_pfns);
}
void __init paging_init(void)
{
- unsigned long max_zone_pfns[MAX_NR_ZONES] = {
- lmb_end_of_DRAM() >> PAGE_SHIFT
- };
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+ max_zone_pfns[ZONE_DMA] = lmb_end_of_DRAM() >> PAGE_SHIFT;
free_area_init_nodes(max_zone_pfns);
}
Be aware that PCI initialization is the bootloader's
responsiblilty.
+config MPC8360E_PB
+ bool "Freescale MPC8360E PB"
+ select DEFAULT_UIMAGE
+ select QUICC_ENGINE
+ help
+ This option enables support for the MPC836x EMDS Processor Board.
+
endchoice
config PPC_MPC832x
select PPC_INDIRECT_PCI
default y if MPC834x_SYS || MPC834x_ITX
+config PPC_MPC836x
+ bool
+ select PPC_UDBG_16550
+ select PPC_INDIRECT_PCI
+ default y if MPC8360E_PB
+
endmenu
obj-$(CONFIG_PCI) += pci.o
obj-$(CONFIG_MPC834x_SYS) += mpc834x_sys.o
obj-$(CONFIG_MPC834x_ITX) += mpc834x_itx.o
+obj-$(CONFIG_MPC8360E_PB) += mpc8360e_pb.o
+obj-$(CONFIG_MPC832x_MDS) += mpc832x_mds.o
#include <linux/root_dev.h>
#include <linux/initrd.h>
+#include <asm/of_device.h>
#include <asm/system.h>
#include <asm/atomic.h>
#include <asm/time.h>
#endif
}
+static int __init mpc8360_declare_of_platform_devices(void)
+{
+ struct device_node *np;
+
+ for (np = NULL; (np = of_find_compatible_node(np, "network",
+ "ucc_geth")) != NULL;) {
+ int ucc_num;
+ char bus_id[BUS_ID_SIZE];
+
+ ucc_num = *((uint *) get_property(np, "device-id", NULL)) - 1;
+ snprintf(bus_id, BUS_ID_SIZE, "ucc_geth.%u", ucc_num);
+ of_platform_device_create(np, bus_id, NULL);
+ }
+
+ return 0;
+}
+device_initcall(mpc8360_declare_of_platform_devices);
+
void __init mpc8360_sys_init_IRQ(void)
{
if (!spu)
goto out;
+ spu->node = find_spu_node_id(spe);
+ if (spu->node >= MAX_NUMNODES) {
+ printk(KERN_WARNING "SPE %s on node %d ignored,"
+ " node number too big\n", spe->full_name, spu->node);
+ printk(KERN_WARNING "Check if CONFIG_NUMA is enabled.\n");
+ return -ENODEV;
+ }
+ spu->nid = of_node_to_nid(spe);
+ if (spu->nid == -1)
+ spu->nid = 0;
+
ret = spu_map_device(spu, spe);
/* try old method */
if (ret)
if (ret)
goto out_free;
- spu->node = find_spu_node_id(spe);
- spu->nid = of_node_to_nid(spe);
- if (spu->nid == -1)
- spu->nid = 0;
ret = spu_map_interrupts(spu, spe);
if (ret)
ret = spu_map_interrupts_old(spu, spe);
static struct file_operations spufs_cntl_fops = {
.open = spufs_cntl_open,
+ .release = simple_attr_close,
.read = simple_attr_read,
.write = simple_attr_write,
.mmap = spufs_cntl_mmap,
#include <asm/cache.h>
#include <asm/8xx_immap.h>
#include <asm/machdep.h>
+#include <asm/irq_regs.h>
#include <asm/time.h>
*/
void timer_interrupt(struct pt_regs * regs)
{
+ struct pt_regs *old_regs;
int next_dec;
unsigned long cpu = smp_processor_id();
unsigned jiffy_stamp = last_jiffy_stamp(cpu);
if (atomic_read(&ppc_n_lost_interrupts) != 0)
do_IRQ(regs);
+ old_regs = set_irq_regs(regs);
irq_enter();
while ((next_dec = tb_ticks_per_jiffy - tb_delta(&jiffy_stamp)) <= 0) {
ppc_md.heartbeat();
irq_exit();
+ set_irq_regs(old_regs);
}
/*
end_pfn = start_pfn + (total_memory >> PAGE_SHIFT);
add_active_range(0, start_pfn, end_pfn);
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
#ifdef CONFIG_HIGHMEM
- max_zone_pfns[0] = total_lowmem >> PAGE_SHIFT;
- max_zone_pfns[1] = total_memory >> PAGE_SHIFT;
+ max_zone_pfns[ZONE_DMA] = total_lowmem >> PAGE_SHIFT;
+ max_zone_pfns[ZONE_HIGHMEM] = total_memory >> PAGE_SHIFT;
#else
- max_zone_pfns[0] = total_memory >> PAGE_SHIFT;
+ max_zone_pfns[ZONE_DMA] = total_memory >> PAGE_SHIFT;
#endif /* CONFIG_HIGHMEM */
free_area_init_nodes(max_zone_pfns);
}
bd_t* bi = (void*)__res;
int fs_no = fsid_fcc1+pdev->id-1;
- if(fs_no > ARRAY_SIZE(mpc82xx_enet_pdata)) {
+ if(fs_no >= ARRAY_SIZE(mpc82xx_enet_pdata)) {
return;
}
int id = fs_uart_id_scc2fsid(idx);
/* no need to alter anything if console */
- if ((id <= num) && (!pdev->dev.platform_data)) {
+ if ((id < num) && (!pdev->dev.platform_data)) {
pinfo = &mpc8272_uart_pdata[id];
pinfo->uart_clk = bd->bi_intfreq;
pdev->dev.platform_data = pinfo;
/* Get pointer to Communication Processor */
cp = cpmp;
- if(fs_no > ARRAY_SIZE(mpc8xx_enet_pdata)) {
+ if(fs_no >= ARRAY_SIZE(mpc8xx_enet_pdata)) {
printk(KERN_ERR"No network-suitable #%d device on bus", fs_no);
return;
}
int id = fs_uart_id_smc2fsid(idx);
/* no need to alter anything if console */
- if ((id <= num) && (!pdev->dev.platform_data)) {
+ if ((id < num) && (!pdev->dev.platform_data)) {
pinfo = &mpc866_uart_pdata[id];
pinfo->uart_clk = bd->bi_intfreq;
pdev->dev.platform_data = pinfo;
char *e;
int i;
- if(fs_no > ARRAY_SIZE(mpc8xx_enet_pdata)) {
+ if(fs_no >= ARRAY_SIZE(mpc8xx_enet_pdata)) {
printk(KERN_ERR"No network-suitable #%d device on bus", fs_no);
return;
}
int id = fs_uart_id_smc2fsid(idx);
/* no need to alter anything if console */
- if ((id <= num) && (!pdev->dev.platform_data)) {
+ if ((id < num) && (!pdev->dev.platform_data)) {
pinfo = &mpc885_uart_pdata[id];
pinfo->uart_clk = bd->bi_intfreq;
pdev->dev.platform_data = pinfo;
*
* schedule work and reschedule timer
*/
-static void appldata_timer_function(unsigned long data, struct pt_regs *regs)
+static void appldata_timer_function(unsigned long data)
{
P_DEBUG(" -= Timer =-\n");
P_DEBUG("CPU: %i, expire_count: %i\n", smp_processor_id(),
int index;
struct pt_regs *old_regs;
- irq_enter();
old_regs = set_irq_regs(regs);
+ irq_enter();
asm volatile ("mc 0,0");
if (S390_lowcore.int_clock >= S390_lowcore.jiffy_timer)
/**
p->handler(code);
}
}
- set_irq_regs(old_regs);
irq_exit();
+ set_irq_regs(old_regs);
}
EXPORT_SYMBOL(register_external_interrupt);
EXPORT_SYMBOL(console_mode);
EXPORT_SYMBOL(console_devno);
EXPORT_SYMBOL(console_irq);
-EXPORT_SYMBOL(sys_wait4);
void save_stack_trace(struct stack_trace *trace, struct task_struct *task)
{
register unsigned long sp asm ("15");
- unsigned long orig_sp;
+ unsigned long orig_sp, new_sp;
- sp &= PSW_ADDR_INSN;
- orig_sp = sp;
+ orig_sp = sp & PSW_ADDR_INSN;
- sp = save_context_stack(trace, &trace->skip, sp,
+ new_sp = save_context_stack(trace, &trace->skip, orig_sp,
S390_lowcore.panic_stack - PAGE_SIZE,
S390_lowcore.panic_stack);
- if ((sp != orig_sp) && !trace->all_contexts)
+ if ((new_sp != orig_sp) && !trace->all_contexts)
return;
- sp = save_context_stack(trace, &trace->skip, sp,
+ new_sp = save_context_stack(trace, &trace->skip, new_sp,
S390_lowcore.async_stack - ASYNC_SIZE,
S390_lowcore.async_stack);
- if ((sp != orig_sp) && !trace->all_contexts)
+ if ((new_sp != orig_sp) && !trace->all_contexts)
return;
if (task)
- save_context_stack(trace, &trace->skip, sp,
+ save_context_stack(trace, &trace->skip, new_sp,
(unsigned long) task_stack_page(task),
(unsigned long) task_stack_page(task) + THREAD_SIZE);
else
- save_context_stack(trace, &trace->skip, sp,
+ save_context_stack(trace, &trace->skip, new_sp,
S390_lowcore.thread_info,
S390_lowcore.thread_info + THREAD_SIZE);
return;
* Do the callback functions of expired vtimer events.
* Called from within the interrupt handler.
*/
-static void do_callbacks(struct list_head *cb_list, struct pt_regs *regs)
+static void do_callbacks(struct list_head *cb_list)
{
struct vtimer_queue *vt_list;
struct vtimer_list *event, *tmp;
- void (*fn)(unsigned long, struct pt_regs*);
+ void (*fn)(unsigned long);
unsigned long data;
if (list_empty(cb_list))
list_for_each_entry_safe(event, tmp, cb_list, entry) {
fn = event->function;
data = event->data;
- fn(data, regs);
+ fn(data);
if (!event->interval)
/* delete one shot timer */
list_move_tail(&event->entry, &cb_list);
}
spin_unlock(&vt_list->lock);
- do_callbacks(&cb_list, get_irq_regs());
+ do_callbacks(&cb_list);
/* next event is first in list */
spin_lock(&vt_list->lock);
config GENERIC_IOMAP
bool
+config GENERIC_TIME
+ def_bool n
+
config ARCH_MAY_HAVE_PC_FDC
bool
endmenu
menu "Timer support"
+depends on !GENERIC_TIME
config SH_TMU
bool "TMU timer support"
return p - buf;
}
-static irqreturn_t hp6x0_apm_interrupt(int irq, void *dev, struct pt_regs *regs)
+static irqreturn_t hp6x0_apm_interrupt(int irq, void *dev)
{
if (!apm_suspended)
apm_queue_event(APM_USER_SUSPEND);
int ret;
ret = request_irq(HP680_BTN_IRQ, hp6x0_apm_interrupt,
- SA_INTERRUPT, MODNAME, 0);
+ IRQF_DISABLED, MODNAME, 0);
if (unlikely(ret < 0)) {
printk(KERN_ERR MODNAME ": IRQ %d request failed\n",
HP680_BTN_IRQ);
return count;
}
-static irqreturn_t sw_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t sw_interrupt(int irq, void *dev_id)
{
landisk_btn = (0x0ff & (~ctrl_inb(PA_STATUS)));
disable_irq(IRQ_BUTTON);
static unsigned char m_irq_mask = 0xfb;
static unsigned char s_irq_mask = 0xff;
-volatile unsigned long irq_err_count;
static void disable_mpc1211_irq(unsigned int irq)
{
if(irq < 8) {
if(m_irq_mask & (1<<irq)){
if(!mpc1211_irq_real(irq)){
- irq_err_count++;
+ atomic_inc(&irq_err_count)
printk("spurious 8259A interrupt: IRQ %x\n",irq);
}
} else {
} else {
if(s_irq_mask & (1<<(irq - 8))){
if(!mpc1211_irq_real(irq)){
- irq_err_count++;
+ atomic_inc(&irq_err_count);
printk("spurious 8259A interrupt: IRQ %x\n",irq);
}
} else {
/*
- * linux/arch/sh/boards/renesas/r7780rp/irq.c
- *
- * Copyright (C) 2000 Kazumoto Kojima
- *
* Renesas Solutions Highlander R7780RP-1 Support.
*
- * Modified for R7780RP-1 by
- * Atom Create Engineering Co., Ltd. 2002.
+ * Copyright (C) 2002 Atom Create Engineering Co., Ltd.
+ * Copyright (C) 2006 Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
*/
#include <linux/init.h>
#include <linux/irq.h>
#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/r7780rp/r7780rp.h>
#ifdef CONFIG_SH_R7780MP
static int mask_pos[] = {12, 11, 9, 14, 15, 8, 13, 6, 5, 4, 3, 2, 0, 0, 1, 0};
static int mask_pos[] = {15, 14, 13, 12, 11, 10, 9, 8, 7, 5, 6, 4, 0, 1, 2, 0};
#endif
-static void enable_r7780rp_irq(unsigned int irq);
-static void disable_r7780rp_irq(unsigned int irq);
-
-/* shutdown is same as "disable" */
-#define shutdown_r7780rp_irq disable_r7780rp_irq
-
-static void ack_r7780rp_irq(unsigned int irq);
-static void end_r7780rp_irq(unsigned int irq);
-
-static unsigned int startup_r7780rp_irq(unsigned int irq)
-{
- enable_r7780rp_irq(irq);
- return 0; /* never anything pending */
-}
-
-static void disable_r7780rp_irq(unsigned int irq)
-{
- unsigned short val;
- unsigned short mask = 0xffff ^ (0x0001 << mask_pos[irq]);
-
- /* Set the priority in IPR to 0 */
- val = ctrl_inw(IRLCNTR1);
- val &= mask;
- ctrl_outw(val, IRLCNTR1);
-}
-
static void enable_r7780rp_irq(unsigned int irq)
{
- unsigned short val;
- unsigned short value = (0x0001 << mask_pos[irq]);
-
/* Set priority in IPR back to original value */
- val = ctrl_inw(IRLCNTR1);
- val |= value;
- ctrl_outw(val, IRLCNTR1);
-}
-
-static void ack_r7780rp_irq(unsigned int irq)
-{
- disable_r7780rp_irq(irq);
+ ctrl_outw(ctrl_inw(IRLCNTR1) | (1 << mask_pos[irq]), IRLCNTR1);
}
-static void end_r7780rp_irq(unsigned int irq)
+static void disable_r7780rp_irq(unsigned int irq)
{
- if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS)))
- enable_r7780rp_irq(irq);
+ /* Set the priority in IPR to 0 */
+ ctrl_outw(ctrl_inw(IRLCNTR1) & (0xffff ^ (1 << mask_pos[irq])),
+ IRLCNTR1);
}
-static struct hw_interrupt_type r7780rp_irq_type = {
- .typename = "R7780RP-IRQ",
- .startup = startup_r7780rp_irq,
- .shutdown = shutdown_r7780rp_irq,
- .enable = enable_r7780rp_irq,
- .disable = disable_r7780rp_irq,
- .ack = ack_r7780rp_irq,
- .end = end_r7780rp_irq,
+static struct irq_chip r7780rp_irq_chip __read_mostly = {
+ .name = "r7780rp",
+ .mask = disable_r7780rp_irq,
+ .unmask = enable_r7780rp_irq,
+ .mask_ack = disable_r7780rp_irq,
};
-static void make_r7780rp_irq(unsigned int irq)
-{
- disable_irq_nosync(irq);
- irq_desc[irq].chip = &r7780rp_irq_type;
- disable_r7780rp_irq(irq);
-}
-
/*
* Initialize IRQ setting
*/
{
int i;
- /* IRL0=PCI Slot #A
- * IRL1=PCI Slot #B
- * IRL2=PCI Slot #C
- * IRL3=PCI Slot #D
- * IRL4=CF Card
- * IRL5=CF Card Insert
- * IRL6=M66596
- * IRL7=SD Card
- * IRL8=Touch Panel
- * IRL9=SCI
- * IRL10=Serial
- * IRL11=Extention #A
- * IRL11=Extention #B
- * IRL12=Debug LAN
- * IRL13=Push Switch
- * IRL14=ZiggBee IO
- */
-
- for (i=0; i<15; i++)
- make_r7780rp_irq(i);
+ for (i = 0; i < 15; i++) {
+ disable_irq_nosync(i);
+ set_irq_chip_and_handler(i, &r7780rp_irq_chip,
+ handle_level_irq);
+ enable_r7780rp_irq(i);
+ }
}
* EraseConfig handling functions
*/
-static irqreturn_t eraseconfig_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t eraseconfig_interrupt(int irq, void *dev_id)
{
volatile char dummy __attribute__((unused)) = * (volatile char *) 0xb8000000;
.end = end_hd64461_irq,
};
-static irqreturn_t hd64461_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t hd64461_interrupt(int irq, void *dev_id)
{
printk(KERN_INFO
"HD64461: spurious interrupt, nirr: 0x%x nimr: 0x%x\n",
void *dev;
} handlers[GPIO_NPORTS * 8];
-static irqreturn_t hd64465_gpio_interrupt(int irq, void *dev, struct pt_regs *regs)
+static irqreturn_t hd64465_gpio_interrupt(int irq, void *dev)
{
unsigned short port, pin, isr, mask, portpin;
};
-static irqreturn_t hd64465_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t hd64465_interrupt(int irq, void *dev_id)
{
printk(KERN_INFO
"HD64465: spurious interrupt, nirr: 0x%x nimr: 0x%x\n",
.end = end_voyagergx_irq,
};
-static irqreturn_t voyagergx_interrupt(int irq, void *dev_id,
- struct pt_regs *regs)
+static irqreturn_t voyagergx_interrupt(int irq, void *dev_id)
{
printk(KERN_INFO
"VoyagerGX: spurious interrupt, status: 0x%x\n",
((g2_dma->channel[i].size - \
g2_dma->status[i].size) & 0x0fffffff)
-static irqreturn_t g2_dma_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t g2_dma_interrupt(int irq, void *dev_id)
{
int i;
static unsigned int xfer_complete;
static int count;
-static irqreturn_t pvr2_dma_interrupt(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t pvr2_dma_interrupt(int irq, void *dev_id)
{
if (get_dma_residue(PVR2_CASCADE_CHAN)) {
printk(KERN_WARNING "DMA: SH DMAC did not complete transfer "
* Besides that it needs to waken any waiting process, which should handle
* setting up the next transfer.
*/
-static irqreturn_t dma_tei(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t dma_tei(int irq, void *dev_id)
{
- struct dma_channel *chan = (struct dma_channel *)dev_id;
+ struct dma_channel *chan = dev_id;
u32 chcr;
chcr = ctrl_inl(CHCR[chan->chan]);
}
#if defined(CONFIG_CPU_SH4)
-static irqreturn_t dma_err(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t dma_err(int irq, void *dummy)
{
dmaor_reset();
disable_irq(irq);
*/
pr_debug("PCI: Mapping IO address 0x%x - 0x%x to base 0x%x\n",
PCIBIOS_MIN_IO, (64 << 10),
- SH4_PCI_IO_BASE + PCIBIOS_MIN_IO);
+ SH7751_PCI_IO_BASE + PCIBIOS_MIN_IO);
/*
* XXX: For now, leave this board-specific. In the event we have other
*/
#ifdef CONFIG_SH_BIGSUR
bigsur_port_map(PCIBIOS_MIN_IO, (64 << 10),
- SH4_PCI_IO_BASE + PCIBIOS_MIN_IO, 0);
+ SH7751_PCI_IO_BASE + PCIBIOS_MIN_IO, 0);
#endif
/* Make sure the MSB's of IO window are set to access PCI space
"Memory Write-and-Invalidate"
};
-static irqreturn_t st40_pci_irq(int irq, void *dev_instance, struct pt_regs *regs)
+static irqreturn_t st40_pci_irq(int irq, void *dev_instance)
{
unsigned pci_int, pci_air, pci_cir, pci_aint;
static int count=0;
* These are the "new Hitachi style" interrupts, as present on the
* Hitachi 7751, the STM ST40 STB1, SH7760, and SH7780.
*/
-
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/irq.h>
#include <asm/system.h>
#include <asm/io.h>
-#include <asm/machvec.h>
-
-struct intc2_data {
- unsigned char msk_offset;
- unsigned char msk_shift;
-
- int (*clear_irq) (int);
-};
-
-static struct intc2_data intc2_data[NR_INTC2_IRQS];
-
-static void enable_intc2_irq(unsigned int irq);
-static void disable_intc2_irq(unsigned int irq);
-
-/* shutdown is same as "disable" */
-#define shutdown_intc2_irq disable_intc2_irq
-
-static void mask_and_ack_intc2(unsigned int);
-static void end_intc2_irq(unsigned int irq);
-
-static unsigned int startup_intc2_irq(unsigned int irq)
-{
- enable_intc2_irq(irq);
- return 0; /* never anything pending */
-}
-
-static struct hw_interrupt_type intc2_irq_type = {
- .typename = "INTC2-IRQ",
- .startup = startup_intc2_irq,
- .shutdown = shutdown_intc2_irq,
- .enable = enable_intc2_irq,
- .disable = disable_intc2_irq,
- .ack = mask_and_ack_intc2,
- .end = end_intc2_irq
-};
static void disable_intc2_irq(unsigned int irq)
{
- int irq_offset = irq - INTC2_FIRST_IRQ;
- int msk_shift, msk_offset;
-
- /* Sanity check */
- if (unlikely(irq_offset < 0 || irq_offset >= NR_INTC2_IRQS))
- return;
-
- msk_shift = intc2_data[irq_offset].msk_shift;
- msk_offset = intc2_data[irq_offset].msk_offset;
-
- ctrl_outl(1 << msk_shift,
- INTC2_BASE + INTC2_INTMSK_OFFSET + msk_offset);
+ struct intc2_data *p = get_irq_chip_data(irq);
+ ctrl_outl(1 << p->msk_shift,
+ INTC2_BASE + INTC2_INTMSK_OFFSET + p->msk_offset);
}
static void enable_intc2_irq(unsigned int irq)
{
- int irq_offset = irq - INTC2_FIRST_IRQ;
- int msk_shift, msk_offset;
-
- /* Sanity check */
- if (unlikely(irq_offset < 0 || irq_offset >= NR_INTC2_IRQS))
- return;
-
- msk_shift = intc2_data[irq_offset].msk_shift;
- msk_offset = intc2_data[irq_offset].msk_offset;
-
- ctrl_outl(1 << msk_shift,
- INTC2_BASE + INTC2_INTMSKCLR_OFFSET + msk_offset);
-}
-
-static void mask_and_ack_intc2(unsigned int irq)
-{
- disable_intc2_irq(irq);
+ struct intc2_data *p = get_irq_chip_data(irq);
+ ctrl_outl(1 << p->msk_shift,
+ INTC2_BASE + INTC2_INTMSKCLR_OFFSET + p->msk_offset);
}
-static void end_intc2_irq(unsigned int irq)
-{
- if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS)))
- enable_intc2_irq(irq);
-
- if (unlikely(intc2_data[irq - INTC2_FIRST_IRQ].clear_irq))
- intc2_data[irq - INTC2_FIRST_IRQ].clear_irq(irq);
-}
+static struct irq_chip intc2_irq_chip = {
+ .typename = "intc2",
+ .mask = disable_intc2_irq,
+ .unmask = enable_intc2_irq,
+ .mask_ack = disable_intc2_irq,
+};
/*
* Setup an INTC2 style interrupt.
* | | | |
* make_intc2_irq(84, 0, 16, 0, 13);
*/
-void make_intc2_irq(unsigned int irq,
- unsigned int ipr_offset, unsigned int ipr_shift,
- unsigned int msk_offset, unsigned int msk_shift,
- unsigned int priority)
+void make_intc2_irq(struct intc2_data *p)
{
- int irq_offset = irq - INTC2_FIRST_IRQ;
unsigned int flags;
unsigned long ipr;
- if (unlikely(irq_offset < 0 || irq_offset >= NR_INTC2_IRQS))
- return;
-
- disable_irq_nosync(irq);
-
- /* Fill the data we need */
- intc2_data[irq_offset].msk_offset = msk_offset;
- intc2_data[irq_offset].msk_shift = msk_shift;
- intc2_data[irq_offset].clear_irq = NULL;
+ disable_irq_nosync(p->irq);
/* Set the priority level */
local_irq_save(flags);
- ipr = ctrl_inl(INTC2_BASE + INTC2_INTPRI_OFFSET + ipr_offset);
- ipr &= ~(0xf << ipr_shift);
- ipr |= priority << ipr_shift;
- ctrl_outl(ipr, INTC2_BASE + INTC2_INTPRI_OFFSET + ipr_offset);
+ ipr = ctrl_inl(INTC2_BASE + INTC2_INTPRI_OFFSET + p->ipr_offset);
+ ipr &= ~(0xf << p->ipr_shift);
+ ipr |= p->priority << p->ipr_shift;
+ ctrl_outl(ipr, INTC2_BASE + INTC2_INTPRI_OFFSET + p->ipr_offset);
local_irq_restore(flags);
- irq_desc[irq].chip = &intc2_irq_type;
+ set_irq_chip_and_handler(p->irq, &intc2_irq_chip, handle_level_irq);
+ set_irq_chip_data(p->irq, p);
- disable_intc2_irq(irq);
+ enable_intc2_irq(p->irq);
}
-static struct intc2_init {
- unsigned short irq;
- unsigned char ipr_offset, ipr_shift;
- unsigned char msk_offset, msk_shift;
- unsigned char priority;
-} intc2_init_data[] __initdata = {
+static struct intc2_data intc2_irq_table[] = {
#if defined(CONFIG_CPU_SUBTYPE_ST40)
{64, 0, 0, 0, 0, 13}, /* PCI serr */
{65, 0, 4, 0, 1, 13}, /* PCI err */
{
int i;
- for (i = 0; i < ARRAY_SIZE(intc2_init_data); i++) {
- struct intc2_init *p = intc2_init_data + i;
- make_intc2_irq(p->irq, p->ipr_offset, p->ipr_shift,
- p-> msk_offset, p->msk_shift, p->priority);
- }
-}
-
-/* Adds a termination callback to the interrupt */
-void intc2_add_clear_irq(int irq, int (*fn)(int))
-{
- if (unlikely(irq < INTC2_FIRST_IRQ))
- return;
-
- intc2_data[irq - INTC2_FIRST_IRQ].clear_irq = fn;
+ for (i = 0; i < ARRAY_SIZE(intc2_irq_table); i++)
+ make_intc2_irq(intc2_irq_table + i);
}
-
/*
- * arch/sh/kernel/cpu/irq/ipr.c
+ * Interrupt handling for IPR-based IRQ.
*
* Copyright (C) 1999 Niibe Yutaka & Takeshi Yaegashi
* Copyright (C) 2000 Kazumoto Kojima
- * Copyright (C) 2003 Takashi Kusuda <kusuda-takashi@hitachi-ul.co.jp>
- *
- * Interrupt handling for IPR-based IRQ.
+ * Copyright (C) 2003 Takashi Kusuda <kusuda-takashi@hitachi-ul.co.jp>
+ * Copyright (C) 2006 Paul Mundt
*
* Supported system:
* On-chip supporting modules (TMU, RTC, etc.).
* Hitachi SolutionEngine external I/O:
* MS7709SE01, MS7709ASE01, and MS7750SE01
*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
*/
-
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/module.h>
-
#include <asm/system.h>
#include <asm/io.h>
#include <asm/machvec.h>
int shift; /* Shifts of the 16-bit data */
int priority; /* The priority */
};
-static struct ipr_data ipr_data[NR_IRQS];
-
-static void enable_ipr_irq(unsigned int irq);
-static void disable_ipr_irq(unsigned int irq);
-
-/* shutdown is same as "disable" */
-#define shutdown_ipr_irq disable_ipr_irq
-
-static void mask_and_ack_ipr(unsigned int);
-static void end_ipr_irq(unsigned int irq);
-
-static unsigned int startup_ipr_irq(unsigned int irq)
-{
- enable_ipr_irq(irq);
- return 0; /* never anything pending */
-}
-
-static struct hw_interrupt_type ipr_irq_type = {
- .typename = "IPR-IRQ",
- .startup = startup_ipr_irq,
- .shutdown = shutdown_ipr_irq,
- .enable = enable_ipr_irq,
- .disable = disable_ipr_irq,
- .ack = mask_and_ack_ipr,
- .end = end_ipr_irq
-};
static void disable_ipr_irq(unsigned int irq)
{
- unsigned long val;
- unsigned int addr = ipr_data[irq].addr;
- unsigned short mask = 0xffff ^ (0x0f << ipr_data[irq].shift);
-
+ struct ipr_data *p = get_irq_chip_data(irq);
/* Set the priority in IPR to 0 */
- val = ctrl_inw(addr);
- val &= mask;
- ctrl_outw(val, addr);
+ ctrl_outw(ctrl_inw(p->addr) & (0xffff ^ (0xf << p->shift)), p->addr);
}
static void enable_ipr_irq(unsigned int irq)
{
- unsigned long val;
- unsigned int addr = ipr_data[irq].addr;
- int priority = ipr_data[irq].priority;
- unsigned short value = (priority << ipr_data[irq].shift);
-
+ struct ipr_data *p = get_irq_chip_data(irq);
/* Set priority in IPR back to original value */
- val = ctrl_inw(addr);
- val |= value;
- ctrl_outw(val, addr);
+ ctrl_outw(ctrl_inw(p->addr) | (p->priority << p->shift), p->addr);
}
-static void mask_and_ack_ipr(unsigned int irq)
-{
- disable_ipr_irq(irq);
-
-#if defined(CONFIG_CPU_SUBTYPE_SH7707) || defined(CONFIG_CPU_SUBTYPE_SH7709) || \
- defined(CONFIG_CPU_SUBTYPE_SH7706) || \
- defined(CONFIG_CPU_SUBTYPE_SH7300) || defined(CONFIG_CPU_SUBTYPE_SH7705)
- /* This is needed when we use edge triggered setting */
- /* XXX: Is it really needed? */
- if (IRQ0_IRQ <= irq && irq <= IRQ5_IRQ) {
- /* Clear external interrupt request */
- int a = ctrl_inb(INTC_IRR0);
- a &= ~(1 << (irq - IRQ0_IRQ));
- ctrl_outb(a, INTC_IRR0);
- }
-#endif
-}
-
-static void end_ipr_irq(unsigned int irq)
-{
- if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS)))
- enable_ipr_irq(irq);
-}
+static struct irq_chip ipr_irq_chip = {
+ .name = "ipr",
+ .mask = disable_ipr_irq,
+ .unmask = enable_ipr_irq,
+ .mask_ack = disable_ipr_irq,
+};
void make_ipr_irq(unsigned int irq, unsigned int addr, int pos, int priority)
{
+ struct ipr_data ipr_data;
+
disable_irq_nosync(irq);
- ipr_data[irq].addr = addr;
- ipr_data[irq].shift = pos*4; /* POSition (0-3) x 4 means shift */
- ipr_data[irq].priority = priority;
- irq_desc[irq].chip = &ipr_irq_type;
- disable_ipr_irq(irq);
+ ipr_data.addr = addr;
+ ipr_data.shift = pos*4; /* POSition (0-3) x 4 means shift */
+ ipr_data.priority = priority;
+
+ set_irq_chip_and_handler(irq, &ipr_irq_chip, handle_level_irq);
+ set_irq_chip_data(irq, &ipr_data);
+
+ enable_ipr_irq(irq);
}
+/* XXX: This needs to die a horrible death.. */
void __init init_IRQ(void)
{
#ifndef CONFIG_CPU_SUBTYPE_SH7780
#endif
ENTRY(user_break_point_trap)
.long break_point_trap /* 1E0 */
-ENTRY(interrupt_table)
- ! external hardware
- .long do_IRQ ! 0000 /* 200 */
- .long do_IRQ ! 0001
- .long do_IRQ ! 0010
- .long do_IRQ ! 0011
- .long do_IRQ ! 0100
- .long do_IRQ ! 0101
- .long do_IRQ ! 0110
- .long do_IRQ ! 0111
- .long do_IRQ ! 1000 /* 300 */
- .long do_IRQ ! 1001
- .long do_IRQ ! 1010
- .long do_IRQ ! 1011
- .long do_IRQ ! 1100
- .long do_IRQ ! 1101
- .long do_IRQ ! 1110
- .long exception_error
- ! Internal hardware
- .long do_IRQ ! TMU0 tuni0 /* 400 */
- .long do_IRQ ! TMU1 tuni1
- .long do_IRQ ! TMU2 tuni2
- .long do_IRQ ! ticpi2
- .long do_IRQ ! RTC ati
- .long do_IRQ ! pri
- .long do_IRQ ! cui
- .long do_IRQ ! SCI eri
- .long do_IRQ ! rxi /* 500 */
- .long do_IRQ ! txi
- .long do_IRQ ! tei
- .long do_IRQ ! WDT iti /* 560 */
- .long do_IRQ ! REF rcmi
- .long do_IRQ ! rovi
- .long do_IRQ
- .long do_IRQ /* 5E0 */
-#if defined(CONFIG_CPU_SUBTYPE_SH7707) || \
- defined(CONFIG_CPU_SUBTYPE_SH7709) || \
- defined(CONFIG_CPU_SUBTYPE_SH7706) || \
- defined(CONFIG_CPU_SUBTYPE_SH7300) || \
- defined(CONFIG_CPU_SUBTYPE_SH7705) || \
- defined(CONFIG_CPU_SUBTYPE_SH7710)
- .long do_IRQ ! 32 IRQ irq0 /* 600 */
- .long do_IRQ ! 33 irq1
- .long do_IRQ ! 34 irq2
- .long do_IRQ ! 35 irq3
- .long do_IRQ ! 36 irq4
- .long do_IRQ ! 37 irq5
- .long do_IRQ ! 38
- .long do_IRQ ! 39
- .long do_IRQ ! 40 PINT pint0-7 /* 700 */
- .long do_IRQ ! 41 pint8-15
- .long do_IRQ ! 42
- .long do_IRQ ! 43
- .long do_IRQ ! 44
- .long do_IRQ ! 45
- .long do_IRQ ! 46
- .long do_IRQ ! 47
- .long do_IRQ ! 48 DMAC dei0 /* 800 */
- .long do_IRQ ! 49 dei1
- .long do_IRQ ! 50 dei2
- .long do_IRQ ! 51 dei3
- .long do_IRQ ! 52 IrDA eri1
- .long do_IRQ ! 53 rxi1
- .long do_IRQ ! 54 bri1
- .long do_IRQ ! 55 txi1
- .long do_IRQ ! 56 SCIF eri2
- .long do_IRQ ! 57 rxi2
- .long do_IRQ ! 58 bri2
- .long do_IRQ ! 59 txi2
- .long do_IRQ ! 60 ADC adi /* 980 */
-#if defined(CONFIG_CPU_SUBTYPE_SH7705)
- .long exception_none ! 61 /* 9A0 */
- .long exception_none ! 62
- .long exception_none ! 63
- .long exception_none ! 64 /* A00 */
- .long do_IRQ ! 65 USB usi0
- .long do_IRQ ! 66 usi1
- .long exception_none ! 67
- .long exception_none ! 68
- .long exception_none ! 69
- .long exception_none ! 70
- .long exception_none ! 71
- .long exception_none ! 72 /* B00 */
- .long exception_none ! 73
- .long exception_none ! 74
- .long exception_none ! 75
- .long exception_none ! 76
- .long exception_none ! 77
- .long exception_none ! 78
- .long exception_none ! 79
- .long do_IRQ ! 80 TPU0 tpi0 /* C00 */
- .long do_IRQ ! 81 TPU1 tpi1
- .long exception_none ! 82
- .long exception_none ! 83
- .long do_IRQ ! 84 TPU2 tpi2
- .long do_IRQ ! 85 TPU3 tpi3 /* CA0 */
-#endif
-#if defined(CONFIG_CPU_SUBTYPE_SH7707) || defined(CONFIG_CPU_SUBTYPE_SH7300)
- .long do_IRQ ! 61 LCDC lcdi /* 9A0 */
- .long do_IRQ ! 62 PCC pcc0i
- .long do_IRQ ! 63 pcc1i /* 9E0 */
-#endif
-#if defined(CONFIG_CPU_SUBTYPE_SH7710)
- .long exception_none ! 61 /* 9A0 */
- .long exception_none ! 62
- .long exception_none ! 63
- .long exception_none ! 64 /* A00 */
- .long exception_none ! 65
- .long exception_none ! 66
- .long exception_none ! 67
- .long exception_none ! 68
- .long exception_none ! 69
- .long exception_none ! 70
- .long exception_none ! 71
- .long exception_none ! 72 /* B00 */
- .long exception_none ! 73
- .long exception_none ! 74
- .long exception_none ! 75
- .long do_IRQ ! 76 DMAC2 dei4 /* B80 */
- .long do_IRQ ! 77 DMAC2 dei5
- .long exception_none ! 78
- .long do_IRQ ! 79 IPSEC ipseci /* BE0 */
- .long do_IRQ ! 80 EDMAC eint0 /* C00 */
- .long do_IRQ ! 81 EDMAC eint1
- .long do_IRQ ! 82 EDMAC eint2
- .long exception_none ! 83 /* C60 */
- .long exception_none ! 84
- .long exception_none ! 85
- .long exception_none ! 86
- .long exception_none ! 87
- .long exception_none ! 88 /* D00 */
- .long exception_none ! 89
- .long exception_none ! 90
- .long exception_none ! 91
- .long exception_none ! 92
- .long exception_none ! 93
- .long exception_none ! 94
- .long exception_none ! 95
- .long do_IRQ ! 96 SIOF eri0 /* E00 */
- .long do_IRQ ! 97 txi0
- .long do_IRQ ! 98 rxi0
- .long do_IRQ ! 99 cci0
- .long do_IRQ ! 100 eri1 /* E80 */
- .long do_IRQ ! 101 txi1
- .long do_IRQ ! 102 rxi2
- .long do_IRQ ! 103 cci3
-#endif
-#if defined(CONFIG_CPU_SUBTYPE_SH7300)
- .long do_IRQ ! 64
- .long do_IRQ ! 65
- .long do_IRQ ! 66
- .long do_IRQ ! 67
- .long do_IRQ ! 68
- .long do_IRQ ! 69
- .long do_IRQ ! 70
- .long do_IRQ ! 71
- .long do_IRQ ! 72
- .long do_IRQ ! 73
- .long do_IRQ ! 74
- .long do_IRQ ! 75
- .long do_IRQ ! 76
- .long do_IRQ ! 77
- .long do_IRQ ! 78
- .long do_IRQ ! 79
- .long do_IRQ ! 80 SCIF0(SH7300)
- .long do_IRQ ! 81
- .long do_IRQ ! 82
- .long do_IRQ ! 83
- .long do_IRQ ! 84
- .long do_IRQ ! 85
- .long do_IRQ ! 86
- .long do_IRQ ! 87
- .long do_IRQ ! 88
- .long do_IRQ ! 89
- .long do_IRQ ! 90
- .long do_IRQ ! 91
- .long do_IRQ ! 92
- .long do_IRQ ! 93
- .long do_IRQ ! 94
- .long do_IRQ ! 95
- .long do_IRQ ! 96
- .long do_IRQ ! 97
- .long do_IRQ ! 98
- .long do_IRQ ! 99
- .long do_IRQ ! 100
- .long do_IRQ ! 101
- .long do_IRQ ! 102
- .long do_IRQ ! 103
- .long do_IRQ ! 104
- .long do_IRQ ! 105
- .long do_IRQ ! 106
- .long do_IRQ ! 107
- .long do_IRQ ! 108
-#endif
-#endif
#endif
ENTRY(user_break_point_trap)
.long break_point_trap /* 1E0 */
-ENTRY(interrupt_table)
- ! external hardware
- .long do_IRQ ! 0000 /* 200 */
- .long do_IRQ ! 0001
- .long do_IRQ ! 0010
- .long do_IRQ ! 0011
- .long do_IRQ ! 0100
- .long do_IRQ ! 0101
- .long do_IRQ ! 0110
- .long do_IRQ ! 0111
- .long do_IRQ ! 1000 /* 300 */
- .long do_IRQ ! 1001
- .long do_IRQ ! 1010
- .long do_IRQ ! 1011
- .long do_IRQ ! 1100
- .long do_IRQ ! 1101
- .long do_IRQ ! 1110
- .long exception_error
- ! Internal hardware
-#ifndef CONFIG_CPU_SUBTYPE_SH7780
- .long do_IRQ ! TMU0 tuni0 /* 400 */
- .long do_IRQ ! TMU1 tuni1
- .long do_IRQ ! TMU2 tuni2
- .long do_IRQ ! ticpi2
-#if defined(CONFIG_CPU_SUBTYPE_SH7760)
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error /* 500 */
- .long exception_error
- .long exception_error
-#else
- .long do_IRQ ! RTC ati
- .long do_IRQ ! pri
- .long do_IRQ ! cui
- .long do_IRQ ! SCI eri
- .long do_IRQ ! rxi /* 500 */
- .long do_IRQ ! txi
- .long do_IRQ ! tei
-#endif
- .long do_IRQ ! WDT iti /* 560 */
- .long do_IRQ ! REF rcmi
- .long do_IRQ ! rovi
- .long do_IRQ
- .long do_IRQ /* 5E0 */
- .long do_IRQ ! 32 Hitachi UDI /* 600 */
- .long do_IRQ ! 33 GPIO
- .long do_IRQ ! 34 DMAC dmte0
- .long do_IRQ ! 35 dmte1
- .long do_IRQ ! 36 dmte2
- .long do_IRQ ! 37 dmte3
- .long do_IRQ ! 38 dmae
- .long exception_error ! 39 /* 6E0 */
-#if defined(CONFIG_CPU_SUBTYPE_SH7760)
- .long exception_error /* 700 */
- .long exception_error
- .long exception_error
- .long exception_error /* 760 */
-#else
- .long do_IRQ ! 40 SCIF eri /* 700 */
- .long do_IRQ ! 41 rxi
- .long do_IRQ ! 42 bri
- .long do_IRQ ! 43 txi
-#endif
-#if CONFIG_NR_ONCHIP_DMA_CHANNELS == 8
- .long do_IRQ ! 44 DMAC dmte4 /* 780 */
- .long do_IRQ ! 45 dmte5
- .long do_IRQ ! 46 dmte6
- .long do_IRQ ! 47 dmte7 /* 7E0 */
-#elif defined(CONFIG_CPU_SUBTYPE_SH7343)
- .long do_IRQ ! 44 IIC1 ali /* 780 */
- .long do_IRQ ! 45 tacki
- .long do_IRQ ! 46 waiti
- .long do_IRQ ! 47 dtei /* 7E0 */
- .long do_IRQ ! 48 DMAC dei0 /* 800 */
- .long do_IRQ ! 49 dei1 /* 820 */
-#else
- .long exception_error ! 44 /* 780 */
- .long exception_error ! 45
- .long exception_error ! 46
- .long exception_error ! 47
-#endif
-#if defined(CONFIG_SH_FPU)
- .long do_fpu_state_restore ! 48 /* 800 */
- .long do_fpu_state_restore ! 49 /* 820 */
-#elif !defined(CONFIG_CPU_SUBTYPE_SH7343) && \
- !defined(CONFIG_CPU_SUBTYPE_SH73180)
- .long exception_error
- .long exception_error
-#endif
-#if defined(CONFIG_CPU_SUBTYPE_SH7751)
- .long exception_error /* 840 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error /* 900 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! PCI serr /* A00 */
- .long do_IRQ ! dma3
- .long do_IRQ ! dma2
- .long do_IRQ ! dma1
- .long do_IRQ ! dma0
- .long do_IRQ ! pwon
- .long do_IRQ ! pwdwn
- .long do_IRQ ! err
- .long do_IRQ ! TMU3 tuni3 /* B00 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! TMU4 tuni4 /* B80 */
-#elif defined(CONFIG_CPU_SUBTYPE_SH7760)
- .long do_IRQ ! IRQ irq6 /* 840 */
- .long do_IRQ ! irq7
- .long do_IRQ ! SCIF eri0
- .long do_IRQ ! rxi0
- .long do_IRQ ! bri0
- .long do_IRQ ! txi0
- .long do_IRQ ! HCAN2 cani0 /* 900 */
- .long do_IRQ ! cani1
- .long do_IRQ ! SSI ssii0
- .long do_IRQ ! ssii1
- .long do_IRQ ! HAC haci0
- .long do_IRQ ! haci1
- .long do_IRQ ! IIC iici0
- .long do_IRQ ! iici1
- .long do_IRQ ! USB usbi /* A00 */
- .long do_IRQ ! LCDC vint
- .long exception_error
- .long exception_error
- .long do_IRQ ! DMABRG dmabrgi0
- .long do_IRQ ! dmabrgi1
- .long do_IRQ ! dmabrgi2
- .long exception_error
- .long do_IRQ ! SCIF eri1 /* B00 */
- .long do_IRQ ! rxi1
- .long do_IRQ ! bri1
- .long do_IRQ ! txi1
- .long do_IRQ ! eri2
- .long do_IRQ ! rxi2
- .long do_IRQ ! bri2
- .long do_IRQ ! txi2
- .long do_IRQ ! SIM simeri /* C00 */
- .long do_IRQ ! simrxi
- .long do_IRQ ! simtxi
- .long do_IRQ ! simtei
- .long do_IRQ ! HSPI spii
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! MMCIF mmci0 /* D00 */
- .long do_IRQ ! mmci1
- .long do_IRQ ! mmci2
- .long do_IRQ ! mmci3
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error /* E00 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! MFI mfii
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error /* F00 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! ADC adi
- .long do_IRQ ! CMT cmti /* FA0 */
-#elif defined(CONFIG_CPU_SUBTYPE_SH73180) || defined(CONFIG_CPU_SUBTYPE_SH7343)
- .long do_IRQ ! 50 0x840
- .long do_IRQ ! 51 0x860
- .long do_IRQ ! 52 0x880
- .long do_IRQ ! 53 0x8a0
- .long do_IRQ ! 54 0x8c0
- .long do_IRQ ! 55 0x8e0
- .long do_IRQ ! 56 0x900
- .long do_IRQ ! 57 0x920
- .long do_IRQ ! 58 0x940
- .long do_IRQ ! 59 0x960
- .long do_IRQ ! 60 0x980
- .long do_IRQ ! 61 0x9a0
- .long do_IRQ ! 62 0x9c0
- .long do_IRQ ! 63 0x9e0
- .long do_IRQ ! 64 0xa00
- .long do_IRQ ! 65 0xa20
- .long do_IRQ ! 66 0xa40
- .long do_IRQ ! 67 0xa60
- .long do_IRQ ! 68 0xa80
- .long do_IRQ ! 69 0xaa0
- .long do_IRQ ! 70 0xac0
- .long do_IRQ ! 71 0xae0
- .long do_IRQ ! 72 0xb00
- .long do_IRQ ! 73 0xb20
- .long do_IRQ ! 74 0xb40
- .long do_IRQ ! 75 0xb60
- .long do_IRQ ! 76 0xb80
- .long do_IRQ ! 77 0xba0
- .long do_IRQ ! 78 0xbc0
- .long do_IRQ ! 79 0xbe0
- .long do_IRQ ! 80 0xc00
- .long do_IRQ ! 81 0xc20
- .long do_IRQ ! 82 0xc40
- .long do_IRQ ! 83 0xc60
- .long do_IRQ ! 84 0xc80
- .long do_IRQ ! 85 0xca0
- .long do_IRQ ! 86 0xcc0
- .long do_IRQ ! 87 0xce0
- .long do_IRQ ! 88 0xd00
- .long do_IRQ ! 89 0xd20
- .long do_IRQ ! 90 0xd40
- .long do_IRQ ! 91 0xd60
- .long do_IRQ ! 92 0xd80
- .long do_IRQ ! 93 0xda0
- .long do_IRQ ! 94 0xdc0
- .long do_IRQ ! 95 0xde0
- .long do_IRQ ! 96 0xe00
- .long do_IRQ ! 97 0xe20
- .long do_IRQ ! 98 0xe40
- .long do_IRQ ! 99 0xe60
- .long do_IRQ ! 100 0xe80
- .long do_IRQ ! 101 0xea0
- .long do_IRQ ! 102 0xec0
- .long do_IRQ ! 103 0xee0
- .long do_IRQ ! 104 0xf00
- .long do_IRQ ! 105 0xf20
- .long do_IRQ ! 106 0xf40
- .long do_IRQ ! 107 0xf60
- .long do_IRQ ! 108 0xf80
-#elif defined(CONFIG_CPU_SUBTYPE_ST40STB1)
- .long exception_error ! 50 0x840
- .long exception_error ! 51 0x860
- .long exception_error ! 52 0x880
- .long exception_error ! 53 0x8a0
- .long exception_error ! 54 0x8c0
- .long exception_error ! 55 0x8e0
- .long exception_error ! 56 0x900
- .long exception_error ! 57 0x920
- .long exception_error ! 58 0x940
- .long exception_error ! 59 0x960
- .long exception_error ! 60 0x980
- .long exception_error ! 61 0x9a0
- .long exception_error ! 62 0x9c0
- .long exception_error ! 63 0x9e0
- .long do_IRQ ! 64 0xa00 PCI serr
- .long do_IRQ ! 65 0xa20 err
- .long do_IRQ ! 66 0xa40 ad
- .long do_IRQ ! 67 0xa60 pwr_dwn
- .long exception_error ! 68 0xa80
- .long exception_error ! 69 0xaa0
- .long exception_error ! 70 0xac0
- .long exception_error ! 71 0xae0
- .long do_IRQ ! 72 0xb00 DMA INT0
- .long do_IRQ ! 73 0xb20 INT1
- .long do_IRQ ! 74 0xb40 INT2
- .long do_IRQ ! 75 0xb60 INT3
- .long do_IRQ ! 76 0xb80 INT4
- .long exception_error ! 77 0xba0
- .long do_IRQ ! 78 0xbc0 DMA ERR
- .long exception_error ! 79 0xbe0
- .long do_IRQ ! 80 0xc00 PIO0
- .long do_IRQ ! 81 0xc20 PIO1
- .long do_IRQ ! 82 0xc40 PIO2
- .long exception_error ! 83 0xc60
- .long exception_error ! 84 0xc80
- .long exception_error ! 85 0xca0
- .long exception_error ! 86 0xcc0
- .long exception_error ! 87 0xce0
- .long exception_error ! 88 0xd00
- .long exception_error ! 89 0xd20
- .long exception_error ! 90 0xd40
- .long exception_error ! 91 0xd60
- .long exception_error ! 92 0xd80
- .long exception_error ! 93 0xda0
- .long exception_error ! 94 0xdc0
- .long exception_error ! 95 0xde0
- .long exception_error ! 96 0xe00
- .long exception_error ! 97 0xe20
- .long exception_error ! 98 0xe40
- .long exception_error ! 99 0xe60
- .long exception_error ! 100 0xe80
- .long exception_error ! 101 0xea0
- .long exception_error ! 102 0xec0
- .long exception_error ! 103 0xee0
- .long exception_error ! 104 0xf00
- .long exception_error ! 105 0xf20
- .long exception_error ! 106 0xf40
- .long exception_error ! 107 0xf60
- .long exception_error ! 108 0xf80
- .long exception_error ! 109 0xfa0
- .long exception_error ! 110 0xfc0
- .long exception_error ! 111 0xfe0
- .long do_IRQ ! 112 0x1000 Mailbox
- .long exception_error ! 113 0x1020
- .long exception_error ! 114 0x1040
- .long exception_error ! 115 0x1060
- .long exception_error ! 116 0x1080
- .long exception_error ! 117 0x10a0
- .long exception_error ! 118 0x10c0
- .long exception_error ! 119 0x10e0
- .long exception_error ! 120 0x1100
- .long exception_error ! 121 0x1120
- .long exception_error ! 122 0x1140
- .long exception_error ! 123 0x1160
- .long exception_error ! 124 0x1180
- .long exception_error ! 125 0x11a0
- .long exception_error ! 126 0x11c0
- .long exception_error ! 127 0x11e0
- .long exception_error ! 128 0x1200
- .long exception_error ! 129 0x1220
- .long exception_error ! 130 0x1240
- .long exception_error ! 131 0x1260
- .long exception_error ! 132 0x1280
- .long exception_error ! 133 0x12a0
- .long exception_error ! 134 0x12c0
- .long exception_error ! 135 0x12e0
- .long exception_error ! 136 0x1300
- .long exception_error ! 137 0x1320
- .long exception_error ! 138 0x1340
- .long exception_error ! 139 0x1360
- .long do_IRQ ! 140 0x1380 EMPI INV_ADDR
- .long exception_error ! 141 0x13a0
- .long exception_error ! 142 0x13c0
- .long exception_error ! 143 0x13e0
-#elif defined(CONFIG_CPU_SUBTYPE_SH7770)
- .long do_IRQ ! 50 0x840
- .long do_IRQ ! 51 0x860
- .long do_IRQ ! 52 0x880
- .long do_IRQ ! 53 0x8a0
- .long do_IRQ ! 54 0x8c0
- .long do_IRQ ! 55 0x8e0
- .long do_IRQ ! 56 0x900
- .long do_IRQ ! 57 0x920
- .long do_IRQ ! 58 0x940
- .long do_IRQ ! 59 0x960
- .long do_IRQ ! 60 0x980
- .long do_IRQ ! 61 0x9a0
- .long do_IRQ ! 62 0x9c0
- .long do_IRQ ! 63 0x9e0
- .long do_IRQ ! 64 0xa00
- .long do_IRQ ! 65 0xa20
- .long do_IRQ ! 66 0xa4d
- .long do_IRQ ! 67 0xa60
- .long do_IRQ ! 68 0xa80
- .long do_IRQ ! 69 0xaa0
- .long do_IRQ ! 70 0xac0
- .long do_IRQ ! 71 0xae0
- .long do_IRQ ! 72 0xb00
- .long do_IRQ ! 73 0xb20
- .long do_IRQ ! 74 0xb40
- .long do_IRQ ! 75 0xb60
- .long do_IRQ ! 76 0xb80
- .long do_IRQ ! 77 0xba0
- .long do_IRQ ! 78 0xbc0
- .long do_IRQ ! 79 0xbe0
- .long do_IRQ ! 80 0xc00
- .long do_IRQ ! 81 0xc20
- .long do_IRQ ! 82 0xc40
- .long do_IRQ ! 83 0xc60
- .long do_IRQ ! 84 0xc80
- .long do_IRQ ! 85 0xca0
- .long do_IRQ ! 86 0xcc0
- .long do_IRQ ! 87 0xce0
- .long do_IRQ ! 88 0xd00
- .long do_IRQ ! 89 0xd20
- .long do_IRQ ! 90 0xd40
- .long do_IRQ ! 91 0xd60
- .long do_IRQ ! 92 0xd80
- .long do_IRQ ! 93 0xda0
- .long do_IRQ ! 94 0xdc0
- .long do_IRQ ! 95 0xde0
- .long do_IRQ ! 96 0xe00
- .long do_IRQ ! 97 0xe20
- .long do_IRQ ! 98 0xe40
- .long do_IRQ ! 99 0xe60
- .long do_IRQ ! 100 0xe80
- .long do_IRQ ! 101 0xea0
- .long do_IRQ ! 102 0xec0
- .long do_IRQ ! 103 0xee0
- .long do_IRQ ! 104 0xf00
- .long do_IRQ ! 105 0xf20
- .long do_IRQ ! 106 0xf40
- .long do_IRQ ! 107 0xf60
- .long do_IRQ ! 108 0xf80
-#endif
-#else
- .long exception_error /* 400 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! RTC ati
- .long do_IRQ ! pri
- .long do_IRQ ! cui
- .long exception_error
- .long exception_error /* 500 */
- .long exception_error
- .long exception_error
- .long do_IRQ ! WDT iti /* 560 */
- .long do_IRQ ! TMU-ch0
- .long do_IRQ ! TMU-ch1
- .long do_IRQ ! TMU-ch2
- .long do_IRQ ! ticpi2 /* 5E0 */
- .long do_IRQ ! 32 Hitachi UDI /* 600 */
- .long exception_error
- .long do_IRQ ! 34 DMAC dmte0
- .long do_IRQ ! 35 dmte1
- .long do_IRQ ! 36 dmte2
- .long do_IRQ ! 37 dmte3
- .long do_IRQ ! 38 dmae
- .long exception_error ! 39 /* 6E0 */
- .long do_IRQ ! 40 SCIF-ch0 eri /* 700 */
- .long do_IRQ ! 41 rxi
- .long do_IRQ ! 42 bri
- .long do_IRQ ! 43 txi
- .long do_IRQ ! 44 DMAC dmte4 /* 780 */
- .long do_IRQ ! 45 dmte5
- .long do_IRQ ! 46 dmte6
- .long do_IRQ ! 47 dmte7 /* 7E0 */
-#if defined(CONFIG_SH_FPU)
- .long do_fpu_state_restore ! 48 /* 800 */
- .long do_fpu_state_restore ! 49 /* 820 */
-#else
- .long exception_error
- .long exception_error
-#endif
- .long exception_error /* 840 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! 56 CMT /* 900 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! 60 HAC
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! PCI serr /* A00 */
- .long do_IRQ ! INTA
- .long do_IRQ ! INTB
- .long do_IRQ ! INTC
- .long do_IRQ ! INTD
- .long do_IRQ ! err
- .long do_IRQ ! pwd3
- .long do_IRQ ! pwd2
- .long do_IRQ ! pwd1 /* B00 */
- .long do_IRQ ! pwd0
- .long exception_error
- .long exception_error
- .long do_IRQ ! SCIF-ch1 eri /* B80 */
- .long do_IRQ ! rxi
- .long do_IRQ ! bri
- .long do_IRQ ! txi
- .long do_IRQ ! SIOF /* C00 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! HSPI /* C80 */
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! MMCIF fatat /* D00 */
- .long do_IRQ ! tran
- .long do_IRQ ! err
- .long do_IRQ ! frdy
- .long do_IRQ ! DMAC dmint8 /* D80 */
- .long do_IRQ ! dmint9
- .long do_IRQ ! dmint10
- .long do_IRQ ! dmint11
- .long do_IRQ ! TMU-ch3 /* E00 */
- .long do_IRQ ! TMU-ch4
- .long do_IRQ ! TMU-ch5
- .long exception_error
- .long do_IRQ ! SSI
- .long exception_error
- .long exception_error
- .long exception_error
- .long do_IRQ ! FLCTL flste /* F00 */
- .long do_IRQ ! fltend
- .long do_IRQ ! fltrq0
- .long do_IRQ ! fltrq1
- .long do_IRQ ! GPIO gpioi0 /* F80 */
- .long do_IRQ ! gpioi1
- .long do_IRQ ! gpioi2
- .long do_IRQ ! gpioi3
-#endif
-
-/* $Id: entry.S,v 1.37 2004/06/11 13:02:46 doyu Exp $
- *
+/*
* linux/arch/sh/entry.S
*
* Copyright (C) 1999, 2000, 2002 Niibe Yutaka
- * Copyright (C) 2003 Paul Mundt
+ * Copyright (C) 2003 - 2006 Paul Mundt
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
#define k3 r3
#define k4 r4
-#define k_ex_code r2_bank /* r2_bank1 */
#define g_imask r6 /* r6_bank1 */
#define k_g_imask r6_bank /* r6_bank1 */
#define current r7 /* r7_bank1 */
0:
#endif /* defined(CONFIG_KGDB_NMI) */
bra handle_exception
- mov.l @k2, k2
+ mov #-1, k2 ! interrupt exception marker
.align 2
1: .long EXPEVT
add current, k1
mov k1, r15 ! change to kernel stack
!
-1: mov #-1, k4
- mov.l 2f, k1
+1: mov.l 2f, k1
!
#ifdef CONFIG_SH_DSP
mov.l r2, @-r15 ! Save r2, we need another reg
#endif
! Save the user registers on the stack.
mov.l k2, @-r15 ! EXPEVT
+
+ mov #-1, k4
mov.l k4, @-r15 ! set TRA (default: -1)
!
sts.l macl, @-r15
mov.l r2, @-r15
mov.l r1, @-r15
mov.l r0, @-r15
- ! Then, dispatch to the handler, according to the exception code.
- stc k_ex_code, r8
+
+ /*
+ * This gets a bit tricky.. in the INTEVT case we don't want to use
+ * the VBR offset as a destination in the jump call table, since all
+ * of the destinations are the same. In this case, (interrupt) sets
+ * a marker in r2 (now r2_bank since SR.RB changed), which we check
+ * to determine the exception type. For all other exceptions, we
+ * forcibly read EXPEVT from memory and fix up the jump address, in
+ * the interrupt exception case we jump to do_IRQ() and defer the
+ * INTEVT read until there. As a bonus, we can also clean up the SR.RB
+ * checks that do_IRQ() was doing..
+ */
+ stc r2_bank, r8
+ cmp/pz r8
+ bf interrupt_exception
shlr2 r8
shlr r8
mov.l 4f, r9
mov.l @r9, r9
jmp @r9
nop
+ rts
+ nop
.align 2
1: .long 0x00001000 ! DSP=1
3: .long 0xcfffffff ! RB=0, BL=0
4: .long exception_handling_table
+interrupt_exception:
+ mov.l 1f, r9
+ jmp @r9
+ nop
+ rts
+ nop
+
+ .align 2
+1: .long do_IRQ
+
.align 2
ENTRY(exception_none)
rts
nop
-
#include <linux/module.h>
#include <linux/kernel_stat.h>
#include <linux/seq_file.h>
+#include <linux/io.h>
#include <asm/irq.h>
#include <asm/processor.h>
#include <asm/uaccess.h>
#include <asm/thread_info.h>
#include <asm/cpu/mmu_context.h>
+atomic_t irq_err_count;
+
/*
* 'what should we do if we get a hw irq event on an illegal vector'.
* each architecture has to answer this themselves, it doesn't deserve
*/
void ack_bad_irq(unsigned int irq)
{
+ atomic_inc(&irq_err_count);
printk("unexpected IRQ trap at vector %02x\n", irq);
}
if (!action)
goto unlock;
seq_printf(p, "%3d: ",i);
- seq_printf(p, "%10u ", kstat_irqs(i));
- seq_printf(p, " %14s", irq_desc[i].chip->typename);
+ for_each_online_cpu(j)
+ seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+ seq_printf(p, " %14s", irq_desc[i].chip->name);
+ seq_printf(p, "-%s", handle_irq_name(irq_desc[i].handle_irq));
seq_printf(p, " %s", action->name);
for (action=action->next; action; action = action->next)
seq_putc(p, '\n');
unlock:
spin_unlock_irqrestore(&irq_desc[i].lock, flags);
- }
+ } else if (i == NR_IRQS)
+ seq_printf(p, "Err: %10u\n", atomic_read(&irq_err_count));
+
return 0;
}
#endif
unsigned long r6, unsigned long r7,
struct pt_regs regs)
{
- int irq = r4;
+ struct pt_regs *old_regs = set_irq_regs(®s);
+ int irq;
#ifdef CONFIG_4KSTACKS
union irq_ctx *curctx, *irqctx;
#endif
#endif
#ifdef CONFIG_CPU_HAS_INTEVT
- __asm__ __volatile__ (
-#ifdef CONFIG_CPU_HAS_SR_RB
- "stc r2_bank, %0\n\t"
+ irq = (ctrl_inl(INTEVT) >> 5) - 16;
#else
- "mov.l @%1, %0\n\t"
-#endif
- "shlr2 %0\n\t"
- "shlr2 %0\n\t"
- "shlr %0\n\t"
- "add #-16, %0\n\t"
- : "=z" (irq), "=r" (r4)
- : "1" (INTEVT)
- : "memory"
- );
+ irq = r4;
#endif
irq = irq_demux(irq);
__asm__ __volatile__ (
"mov %0, r4 \n"
- "mov %1, r5 \n"
"mov r15, r9 \n"
- "jsr @%2 \n"
+ "jsr @%1 \n"
/* swith to the irq stack */
- " mov %3, r15 \n"
+ " mov %2, r15 \n"
/* restore the stack (ring zero) */
"mov r9, r15 \n"
: /* no outputs */
- : "r" (irq), "r" (®s), "r" (__do_IRQ), "r" (isp)
+ : "r" (irq), "r" (generic_handle_irq), "r" (isp)
/* XXX: A somewhat excessive clobber list? -PFM */
: "memory", "r0", "r1", "r2", "r3", "r4",
"r5", "r6", "r7", "r8", "t", "pr"
);
} else
#endif
- __do_IRQ(irq, ®s);
+ generic_handle_irq(irq);
irq_exit();
+ set_irq_regs(old_regs);
return 1;
}
* Copyright (C) 1995 Linus Torvalds
*
* SuperH version: Copyright (C) 1999, 2000 Niibe Yutaka & Kaz Kojima
+ * Copyright (C) 2006 Lineo Solutions Inc. support SH4A UBC
*/
/*
static void
ubc_set_tracing(int asid, unsigned long pc)
{
+#if defined(CONFIG_CPU_SH4A)
+ unsigned long val;
+
+ val = (UBC_CBR_ID_INST | UBC_CBR_RW_READ | UBC_CBR_CE);
+ val |= (UBC_CBR_AIE | UBC_CBR_AIV_SET(asid));
+
+ ctrl_outl(val, UBC_CBR0);
+ ctrl_outl(pc, UBC_CAR0);
+ ctrl_outl(0x0, UBC_CAMR0);
+ ctrl_outl(0x0, UBC_CBCR);
+
+ val = (UBC_CRR_RES | UBC_CRR_PCB | UBC_CRR_BIE);
+ ctrl_outl(val, UBC_CRR0);
+
+ /* Read UBC register that we writed last. For chekking UBC Register changed */
+ val = ctrl_inl(UBC_CRR0);
+
+#else /* CONFIG_CPU_SH4A */
ctrl_outl(pc, UBC_BARA);
#ifdef CONFIG_MMU
ctrl_outw(BBR_INST | BBR_READ, UBC_BBRA);
ctrl_outw(BRCR_PCBA, UBC_BRCR);
}
+#endif /* CONFIG_CPU_SH4A */
}
/*
#endif
ubc_set_tracing(asid, next->thread.ubc_pc);
} else {
+#if defined(CONFIG_CPU_SH4A)
+ ctrl_outl(UBC_CBR_INIT, UBC_CBR0);
+ ctrl_outl(UBC_CRR_INIT, UBC_CRR0);
+#else
ctrl_outw(0, UBC_BBRA);
ctrl_outw(0, UBC_BBRB);
+#endif
}
return prev;
struct pt_regs regs)
{
/* Clear tracing. */
+#if defined(CONFIG_CPU_SH4A)
+ ctrl_outl(UBC_CBR_INIT, UBC_CBR0);
+ ctrl_outl(UBC_CRR_INIT, UBC_CRR0);
+#else
ctrl_outw(0, UBC_BBRA);
ctrl_outw(0, UBC_BBRB);
+#endif
current->thread.ubc_pc = 0;
ubc_usercnt -= 1;
return (unsigned long long)jiffies * (1000000000 / HZ);
}
+#ifndef CONFIG_GENERIC_TIME
void do_gettimeofday(struct timeval *tv)
{
unsigned long seq;
return 0;
}
EXPORT_SYMBOL(do_settimeofday);
+#endif /* !CONFIG_GENERIC_TIME */
/* last time the RTC clock got updated */
static long last_rtc_update;
* handle_timer_tick() needs to keep up the real-time clock,
* as well as call the "do_timer()" routine every clocktick
*/
-void handle_timer_tick(struct pt_regs *regs)
+void handle_timer_tick(void)
{
do_timer(1);
#ifndef CONFIG_SMP
- update_process_times(user_mode(regs));
+ update_process_times(user_mode(get_irq_regs()));
#endif
- profile_tick(CPU_PROFILING, regs);
+ if (current->pid)
+ profile_tick(CPU_PROFILING);
#ifdef CONFIG_HEARTBEAT
if (sh_mv.mv_heartbeat != NULL)
return count;
}
-static irqreturn_t tmu_timer_interrupt(int irq, void *dev_id,
- struct pt_regs *regs)
+static irqreturn_t tmu_timer_interrupt(int irq, void *dummy)
{
unsigned long timer_status;
* locally disabled. -arca
*/
write_seqlock(&xtime_lock);
- handle_timer_tick(regs);
+ handle_timer_tick();
write_sequnlock(&xtime_lock);
return IRQ_HANDLED;
.mask = CPU_MASK_NONE,
};
-/*
- * Hah! We'll see if this works (switching from usecs to nsecs).
- */
-static unsigned long tmu_timer_get_frequency(void)
-{
- u32 freq;
- struct timespec ts1, ts2;
- unsigned long diff_nsec;
- unsigned long factor;
-
- /* Setup the timer: We don't want to generate interrupts, just
- * have it count down at its natural rate.
- */
- ctrl_outb(0, TMU_TSTR);
-#if !defined(CONFIG_CPU_SUBTYPE_SH7300) && !defined(CONFIG_CPU_SUBTYPE_SH7760)
- ctrl_outb(TMU_TOCR_INIT, TMU_TOCR);
-#endif
- ctrl_outw(TMU0_TCR_CALIB, TMU0_TCR);
- ctrl_outl(0xffffffff, TMU0_TCOR);
- ctrl_outl(0xffffffff, TMU0_TCNT);
-
- rtc_sh_get_time(&ts2);
-
- do {
- rtc_sh_get_time(&ts1);
- } while (ts1.tv_nsec == ts2.tv_nsec && ts1.tv_sec == ts2.tv_sec);
-
- /* actually start the timer */
- ctrl_outb(TMU_TSTR_INIT, TMU_TSTR);
-
- do {
- rtc_sh_get_time(&ts2);
- } while (ts1.tv_nsec == ts2.tv_nsec && ts1.tv_sec == ts2.tv_sec);
-
- freq = 0xffffffff - ctrl_inl(TMU0_TCNT);
- if (ts2.tv_nsec < ts1.tv_nsec) {
- ts2.tv_nsec += 1000000000;
- ts2.tv_sec--;
- }
-
- diff_nsec = (ts2.tv_sec - ts1.tv_sec) * 1000000000 + (ts2.tv_nsec - ts1.tv_nsec);
-
- /* this should work well if the RTC has a precision of n Hz, where
- * n is an integer. I don't think we have to worry about the other
- * cases. */
- factor = (1000000000 + diff_nsec/2) / diff_nsec;
-
- if (factor * diff_nsec > 1100000000 ||
- factor * diff_nsec < 900000000)
- panic("weird RTC (diff_nsec %ld)", diff_nsec);
-
- return freq * factor;
-}
-
static void tmu_clk_init(struct clk *clk)
{
u8 divisor = TMU0_TCR_INIT & 0x7;
.init = tmu_timer_init,
.start = tmu_timer_start,
.stop = tmu_timer_stop,
- .get_frequency = tmu_timer_get_frequency,
+#ifndef CONFIG_GENERIC_TIME
.get_offset = tmu_timer_get_offset,
+#endif
};
struct sys_timer tmu_timer = {
.name = "tmu",
.ops = &tmu_timer_ops,
};
-
split_page(page, order);
ret = page_address(page);
+ memset(ret, 0, size);
*handle = virt_to_phys(ret);
/*
#include <asm/pcic.h>
#include <asm/timer.h>
#include <asm/uaccess.h>
+#include <asm/irq_regs.h>
unsigned int pcic_pin_to_irq(unsigned int pin, char *name);
.index = -1,
};
-int obp_system_intr(void)
-{
- if (boot_flags & BOOTME_DEBUG) {
- printk("OBP: system interrupted\n");
- prom_halt();
- return 1;
- }
- return 0;
-}
-
/*
* Process kernel command line switches that are specific to the
* SPARC or that require special low-level processing.
. = ALIGN(4096);
__init_begin = .;
+ _sinittext = .;
.init.text : {
- _sinittext = .;
*(.init.text)
- _einittext = .;
}
+ _einittext = .;
__init_text_end = .;
.init.data : { *(.init.data) }
. = ALIGN(16);
srmmu_nocache_end = SRMMU_NOCACHE_VADDR + srmmu_nocache_size;
}
-void srmmu_nocache_init(void)
+void __init srmmu_nocache_init(void)
{
unsigned int bitmap_bits;
pgd_t *pgd;
{
}
-int obp_system_intr(void)
-{
- if (boot_flags & BOOTME_DEBUG) {
- printk("OBP: system interrupted\n");
- prom_halt();
- return 1;
- }
- return 0;
-}
-
/*
* Process kernel command line switches that are specific to the
* SPARC or that require special low-level processing.
config PCMCIA
bool
+# Yet to do!
+config TRACE_IRQFLAGS_SUPPORT
+ bool
+ default n
+
+config LOCKDEP_SUPPORT
+ bool
+ default y
+
+config STACKTRACE_SUPPORT
+ bool
+ default y
+
config GENERIC_CALIBRATE_DELAY
bool
default y
menu "UML-specific options"
config MODE_TT
- bool "Tracing thread support"
+ bool "Tracing thread support (DEPRECATED)"
default n
help
This option controls whether tracing thread support is compiled
- into UML. This option is largely obsolete, given that skas0 provides
+ into UML. This option is largely obsolete, given that skas0 provides
skas security and performance without needing to patch the host.
- It is safe to say 'N' here.
+ It is safe to say 'N' here; saying 'Y' may cause additional problems
+ with the resulting binary even if you run UML in SKAS mode, and running
+ in TT mode is strongly *NOT RECOMMENDED*.
config STATIC_LINK
bool "Force a static link"
for use in a chroot jail. So, if you intend to run UML inside a
chroot, and you disable CONFIG_MODE_TT, you probably want to say Y
here.
+ Additionally, this option enables using higher memory spaces (up to
+ 2.75G) for UML - disabling CONFIG_MODE_TT and enabling this option leads
+ to best results for this.
config KERNEL_HALF_GIGS
int "Kernel address space size (in .5G units)"
default y
help
This option controls whether skas (separate kernel address space)
- support is compiled in. If you have applied the skas patch to the
- host, then you certainly want to say Y here (and consider saying N
- to CONFIG_MODE_TT). Otherwise, it is safe to say Y. Disabling this
- option will shrink the UML binary slightly.
+ support is compiled in.
+ Unless you have specific needs to use TT mode (which applies almost only
+ to developers), you should say Y here.
+ SKAS mode will make use of the SKAS3 patch if it is applied on the host
+ (and your UML will run in SKAS3 mode), but if no SKAS patch is applied
+ on the host it will run in SKAS0 mode, which is anyway faster than TT
+ mode.
source "arch/um/Kconfig.arch"
source "mm/Kconfig"
bool
default y
-config HOST_2G_2G
- bool "2G/2G host address space split"
- default n
- help
- This is needed when the host on which you run has a 2G/2G memory
- split, instead of the customary 3G/1G.
-
- Note that to enable such a host
- configuration, which makes sense only in some cases, you need special
- host patches.
-
- So, if you do not know what to do here, say 'N'.
+choice
+ prompt "Host memory split"
+ default HOST_VMSPLIT_3G
+ ---help---
+ This is needed when the host kernel on which you run has a non-default
+ (like 2G/2G) memory split, instead of the customary 3G/1G. If you did
+ not recompile your own kernel but use the default distro's one, you can
+ safely accept the "Default split" option.
+
+ It can be enabled on recent (>=2.6.16-rc2) vanilla kernels via
+ CONFIG_VM_SPLIT_*, or on previous kernels with special patches (-ck
+ patchset by Con Kolivas, or other ones) - option names match closely the
+ host CONFIG_VM_SPLIT_* ones.
+
+ A lower setting (where 1G/3G is lowest and 3G/1G is higher) will
+ tolerate even more "normal" host kernels, but an higher setting will be
+ stricter.
+
+ So, if you do not know what to do here, say 'Default split'.
+
+ config HOST_VMSPLIT_3G
+ bool "Default split (3G/1G user/kernel host split)"
+ config HOST_VMSPLIT_3G_OPT
+ bool "3G/1G user/kernel host split (for full 1G low memory)"
+ config HOST_VMSPLIT_2G
+ bool "2G/2G user/kernel host split"
+ config HOST_VMSPLIT_1G
+ bool "1G/3G user/kernel host split"
+endchoice
config TOP_ADDR
- hex
- default 0xc0000000 if !HOST_2G_2G
- default 0x80000000 if HOST_2G_2G
+ hex
+ default 0xB0000000 if HOST_VMSPLIT_3G_OPT
+ default 0x78000000 if HOST_VMSPLIT_2G
+ default 0x40000000 if HOST_VMSPLIT_1G
+ default 0xC0000000
config 3_LEVEL_PGTABLES
bool "Three-level pagetables (EXPERIMENTAL)"
# Copyright 2003 - 2004 Pathscale, Inc
# Released under the GPL
-core-y += arch/um/sys-x86_64/
+core-y += arch/um/sys-x86_64/ arch/x86_64/crypto/
START := 0x60000000
-_extra_flags_ = -fno-builtin -m64 -mcmodel=kernel
+_extra_flags_ = -fno-builtin -m64
#We #undef __x86_64__ for kernelspace, not for userspace where
#it's needed for headers to work!
/* for use by sys-$SUBARCH/kernel-offsets.c */
+DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
+#ifdef CONFIG_MODE_TT
+OFFSET(HOST_TASK_EXTERN_PID, task_struct, thread.mode.tt.extern_pid);
+#endif
+
OFFSET(HOST_TASK_REGS, task_struct, thread.regs);
OFFSET(HOST_TASK_PID, task_struct, pid);
+
DEFINE(UM_KERN_PAGE_SIZE, PAGE_SIZE);
DEFINE(UM_NSEC_PER_SEC, NSEC_PER_SEC);
+
DEFINE_STR(UM_KERN_EMERG, KERN_EMERG);
DEFINE_STR(UM_KERN_ALERT, KERN_ALERT);
DEFINE_STR(UM_KERN_CRIT, KERN_CRIT);
DEFINE_STR(UM_KERN_NOTICE, KERN_NOTICE);
DEFINE_STR(UM_KERN_INFO, KERN_INFO);
DEFINE_STR(UM_KERN_DEBUG, KERN_DEBUG);
+
DEFINE(UM_ELF_CLASS, ELF_CLASS);
DEFINE(UM_ELFCLASS32, ELFCLASS32);
DEFINE(UM_ELFCLASS64, ELFCLASS64);
+
+/* For crypto assembler code. */
+DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx));
#ifndef __KERN_UTIL_H__
#define __KERN_UTIL_H__
-#include "linux/threads.h"
#include "sysdep/ptrace.h"
#include "sysdep/faultinfo.h"
} while(0)
#define UML_SETJMP(buf) ({ \
- int n, enable; \
+ int n; \
+ volatile int enable; \
enable = get_signals(); \
n = setjmp(*buf); \
if(n != 0) \
#ifdef UML_CONFIG_MODE_TT
extern void init_new_thread_stack(void *sig_stack, void (*usr1_handler)(int));
+extern void stop(void);
#endif
extern void init_new_thread_signals(void);
extern int run_kernel_thread(int (*fn)(void *), void *arg, void **jmp_ptr);
#include <linux/stddef.h>
#include <linux/sched.h>
#include <linux/elf.h>
+#include <linux/crypto.h>
#include <asm/mman.h>
#define DEFINE(sym, val) \
void foo(void)
{
OFFSET(HOST_TASK_DEBUGREGS, task_struct, thread.arch.debugregs);
- DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
-#ifdef CONFIG_MODE_TT
- OFFSET(HOST_TASK_EXTERN_PID, task_struct, thread.mode.tt.extern_pid);
-#endif
#include <common-offsets.h>
}
#include <linux/sched.h>
#include <linux/time.h>
#include <linux/elf.h>
+#include <linux/crypto.h>
#include <asm/page.h>
#include <asm/mman.h>
void foo(void)
{
- DEFINE(KERNEL_MADV_REMOVE, MADV_REMOVE);
-#ifdef CONFIG_MODE_TT
- OFFSET(HOST_TASK_EXTERN_PID, task_struct, thread.mode.tt.extern_pid);
-#endif
#include <common-offsets.h>
}
#endif
*pte = mk_pte(virt_to_page(kernel), __pgprot(_PAGE_PRESENT));
- /* This is wrong for the code page, but it doesn't matter since the
- * stub is mapped by hand with the correct permissions.
- */
- *pte = pte_mkwrite(*pte);
+ *pte = pte_mkread(*pte);
return(0);
out_pmd:
* Licensed under the GPL
*/
-#include <setjmp.h>
#include <string.h>
#include "user_util.h"
#include "uml_uaccess.h"
#include "task.h"
#include "kern_util.h"
#include "os.h"
+#include "longjmp.h"
int __do_copy_from_user(void *to, const void *from, int n,
void **fault_addr, void **fault_catcher)
struct tt_regs save = TASK_REGS(get_current())->tt;
int ret;
unsigned long *faddrp = (unsigned long *)fault_addr;
- sigjmp_buf jbuf;
+ jmp_buf jbuf;
*fault_catcher = &jbuf;
- if(sigsetjmp(jbuf, 1) == 0)
+ if(UML_SETJMP(&jbuf) == 0)
ret = strlen(str) + 1;
else ret = *faddrp - (unsigned long) str;
#include <errno.h>
#include <stdarg.h>
#include <stdlib.h>
-#include <setjmp.h>
#include <sys/time.h>
#include <sys/ptrace.h>
#include <linux/ptrace.h>
struct utsname host;
uname(&host);
-#if defined(UML_CONFIG_UML_X86) && !defined(UML_CONFIG_64BIT)
+#ifdef UML_CONFIG_UML_X86
+# ifndef UML_CONFIG_64BIT
if (!strcmp(host.machine, "x86_64")) {
strcpy(machine_out, "i686");
return;
}
+# else
+ if (!strcmp(host.machine, "i686")) {
+ strcpy(machine_out, "x86_64");
+ return;
+ }
+# endif
#endif
strcpy(machine_out, host.machine);
}
/*XXX: we need them because they would be exported by x86_64 */
EXPORT_SYMBOL(__memcpy);
-
-/* Networking helper routines. */
-EXPORT_SYMBOL(ip_compute_csum);
#include <stddef.h>
#include <signal.h>
-#include <linux/compiler.h>
#include <asm/unistd.h>
#include "uml-config.h"
#include "sysdep/sigcontext.h"
{
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
- set_irq_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
+ set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
+ "XT");
enable_irq(irq);
}
/*
* 16 old-style INTA-cycle interrupts:
*/
- set_irq_chip_and_handler(i, &i8259A_chip,
- handle_level_irq);
+ set_irq_chip_and_handler_name(i, &i8259A_chip,
+ handle_level_irq, "XT");
} else {
/*
* 'high' PCI IRQs filled in on demand
}
if (old_vector >= 0) {
int old_cpu;
- for_each_cpu_mask(old_cpu, domain)
+ for_each_cpu_mask(old_cpu, irq_domain[irq])
per_cpu(vector_irq, old_cpu)[old_vector] = -1;
}
for_each_cpu_mask(new_cpu, domain)
{
if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
trigger == IOAPIC_LEVEL)
- set_irq_chip_and_handler(irq, &ioapic_chip,
- handle_fasteoi_irq);
+ set_irq_chip_and_handler_name(irq, &ioapic_chip,
+ handle_fasteoi_irq, "fasteoi");
else
- set_irq_chip_and_handler(irq, &ioapic_chip,
- handle_edge_irq);
+ set_irq_chip_and_handler_name(irq, &ioapic_chip,
+ handle_edge_irq, "edge");
}
static void __init setup_IO_APIC_irqs(void)
* The timer IRQ doesn't have to know that behind the
* scene we have a 8259A-master in AEOI mode ...
*/
- set_irq_chip_and_handler(0, &ioapic_chip, handle_edge_irq);
+ set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
/*
* Add it to the IO-APIC irq-routing table:
write_msi_msg(irq, &msg);
- set_irq_chip_and_handler(irq, &msi_chip, handle_edge_irq);
+ set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
return 0;
}
}
#endif
-static struct hw_interrupt_type ht_irq_chip = {
+static struct irq_chip ht_irq_chip = {
.name = "PCI-HT",
.mask = mask_ht_irq,
.unmask = unmask_ht_irq,
write_ht_irq_low(irq, low);
write_ht_irq_high(irq, high);
- set_irq_chip_and_handler(irq, &ht_irq_chip, handle_edge_irq);
+ set_irq_chip_and_handler_name(irq, &ht_irq_chip,
+ handle_edge_irq, "edge");
}
return vector;
}
seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
#endif
seq_printf(p, " %8s", irq_desc[i].chip->name);
- seq_printf(p, "-%s", handle_irq_name(irq_desc[i].handle_irq));
+ seq_printf(p, "-%-8s", irq_desc[i].name);
seq_printf(p, " %s", action->name);
for (action=action->next; action; action = action->next)
* We execute MONITOR against need_resched and enter optimized wait state
* through MWAIT. Whenever someone changes need_resched, we would be woken
* up from MWAIT (without an IPI).
+ *
+ * New with Core Duo processors, MWAIT can take some hints based on CPU
+ * capability.
*/
-static void mwait_idle(void)
+void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
{
- local_irq_enable();
-
- while (!need_resched()) {
+ if (!need_resched()) {
__monitor((void *)¤t_thread_info()->flags, 0, 0);
smp_mb();
- if (need_resched())
- break;
- __mwait(0, 0);
+ if (!need_resched())
+ __mwait(eax, ecx);
}
}
+/* Default MONITOR/MWAIT with no hints, used for default C1 state */
+static void mwait_idle(void)
+{
+ local_irq_enable();
+ while (!need_resched())
+ mwait_idle_with_hints(0,0);
+}
+
void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
static int printed;
#include <linux/pci_ids.h>
#include <linux/pci_regs.h>
#include <asm/pci-direct.h>
+#include <asm/io.h>
static int __init vsmp_init(void)
{
#ifndef CONFIG_NUMA
void __init paging_init(void)
{
- unsigned long max_zone_pfns[MAX_NR_ZONES] = {MAX_DMA_PFN,
- MAX_DMA32_PFN,
- end_pfn};
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+ max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
+ max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
+ max_zone_pfns[ZONE_NORMAL] = end_pfn;
+
memory_present(0, 0, end_pfn);
sparse_init();
free_area_init_nodes(max_zone_pfns);
void __init paging_init(void)
{
int i;
- unsigned long max_zone_pfns[MAX_NR_ZONES] = { MAX_DMA_PFN,
- MAX_DMA32_PFN,
- end_pfn};
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+ max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
+ max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
+ max_zone_pfns[ZONE_NORMAL] = end_pfn;
arch_sparse_init();
static struct elevator_type *elevator_find(const char *name)
{
- struct elevator_type *e = NULL;
+ struct elevator_type *e;
struct list_head *entry;
list_for_each(entry, &elv_list) {
- struct elevator_type *__e;
- __e = list_entry(entry, struct elevator_type, list);
+ e = list_entry(entry, struct elevator_type, list);
- if (!strcmp(__e->elevator_name, name)) {
- e = __e;
- break;
- }
+ if (!strcmp(e->elevator_name, name))
+ return e;
}
- return e;
+ return NULL;
}
static void elevator_put(struct elevator_type *e)
struct list_head *entry;
int len = 0;
- spin_lock_irq(q->queue_lock);
+ spin_lock_irq(&elv_list_lock);
list_for_each(entry, &elv_list) {
struct elevator_type *__e;
else
len += sprintf(name+len, "%s ", __e->elevator_name);
}
- spin_unlock_irq(q->queue_lock);
+ spin_unlock_irq(&elv_list_lock);
len += sprintf(len+name, "\n");
return len;
source "drivers/block/Kconfig"
+# misc before ide - BLK_DEV_SGIIOC4 depends on SGI_IOC4
+
+source "drivers/misc/Kconfig"
+
source "drivers/ide/Kconfig"
source "drivers/scsi/Kconfig"
source "drivers/hwmon/Kconfig"
-source "drivers/misc/Kconfig"
-
source "drivers/mfd/Kconfig"
source "drivers/media/Kconfig"
S2x, //S200 (J1 reported), Victor MP-XP7210
W1N, //W1000N
W5A, //W5A
+ W3V, //W3030V
xxN, //M2400N, M3700N, M5200N, M6800N, S1300N, S5200N
//(Centrino)
END_MODEL
.display_get = "\\ADVG"},
{
+ .name = "W3V",
+ .mt_mled = "MLED",
+ .mt_wled = "WLED",
+ .mt_lcd_switch = xxN_PREFIX "_Q10",
+ .lcd_status = "\\BKLT",
+ .brightness_set = "SPLV",
+ .brightness_get = "GPLV",
+ .display_set = "SDSP",
+ .display_get = "\\INFB"},
+
+ {
.name = "xxN",
.mt_mled = "MLED",
/* WLED present, but not controlled by ACPI */
write_led(const char __user * buffer, unsigned long count,
char *ledname, int ledmask, int invert)
{
- int value;
+ int rv, value;
int led_out = 0;
- count = parse_arg(buffer, count, &value);
- if (count > 0)
+ rv = parse_arg(buffer, count, &value);
+ if (rv > 0)
led_out = value ? 1 : 0;
hotk->status =
printk(KERN_WARNING "Asus ACPI: LED (%s) write failed\n",
ledname);
- return count;
+ return rv;
}
/*
proc_write_ledd(struct file *file, const char __user * buffer,
unsigned long count, void *data)
{
- int value;
+ int rv, value;
- count = parse_arg(buffer, count, &value);
- if (count > 0) {
+ rv = parse_arg(buffer, count, &value);
+ if (rv > 0) {
if (!write_acpi_int
(hotk->handle, hotk->methods->mt_ledd, value, NULL))
printk(KERN_WARNING
"Asus ACPI: LED display write failed\n");
else
hotk->ledd_status = (u32) value;
- } else if (count < 0)
- printk(KERN_WARNING "Asus ACPI: Error reading user input\n");
-
- return count;
+ }
+ return rv;
}
/*
proc_write_lcd(struct file *file, const char __user * buffer,
unsigned long count, void *data)
{
- int value;
+ int rv, value;
- count = parse_arg(buffer, count, &value);
- if (count > 0)
+ rv = parse_arg(buffer, count, &value);
+ if (rv > 0)
set_lcd_state(value);
- return count;
+ return rv;
}
static int read_brightness(void)
proc_write_brn(struct file *file, const char __user * buffer,
unsigned long count, void *data)
{
- int value;
+ int rv, value;
- count = parse_arg(buffer, count, &value);
- if (count > 0) {
+ rv = parse_arg(buffer, count, &value);
+ if (rv > 0) {
value = (0 < value) ? ((15 < value) ? 15 : value) : 0;
/* 0 <= value <= 15 */
set_brightness(value);
- } else if (count < 0) {
- printk(KERN_WARNING "Asus ACPI: Error reading user input\n");
}
-
- return count;
+ return rv;
}
static void set_display(int value)
proc_write_disp(struct file *file, const char __user * buffer,
unsigned long count, void *data)
{
- int value;
+ int rv, value;
- count = parse_arg(buffer, count, &value);
- if (count > 0)
+ rv = parse_arg(buffer, count, &value);
+ if (rv > 0)
set_display(value);
- else if (count < 0)
- printk(KERN_WARNING "Asus ACPI: Error reading user input\n");
-
- return count;
+ return rv;
}
typedef int (proc_readfunc) (char *page, char **start, off_t off, int count,
return A4G;
else if (strncmp(model, "W1N", 3) == 0)
return W1N;
+ else if (strncmp(model, "W3V", 3) == 0)
+ return W3V;
else if (strncmp(model, "W5A", 3) == 0)
return W5A;
else
hotk->methods->mt_wled = NULL;
/* L5D's WLED is not controlled by ACPI */
else if (strncmp(string, "M2N", 3) == 0 ||
+ strncmp(string, "W3V", 3) == 0 ||
strncmp(string, "S1N", 3) == 0)
hotk->methods->mt_wled = "WLED";
- /* M2N and S1N have a usable WLED */
+ /* M2N, S1N and W3V have a usable WLED */
else if (asus_info) {
if (strncmp(asus_info->oem_table_id, "L1", 2) == 0)
hotk->methods->mled_status = NULL;
static int acpi_battery_add(struct acpi_device *device);
static int acpi_battery_remove(struct acpi_device *device, int type);
+static int acpi_battery_resume(struct acpi_device *device, int status);
static struct acpi_driver acpi_battery_driver = {
.name = ACPI_BATTERY_DRIVER_NAME,
.ids = ACPI_BATTERY_HID,
.ops = {
.add = acpi_battery_add,
+ .resume = acpi_battery_resume,
.remove = acpi_battery_remove,
},
};
return 0;
}
+/* this is needed to learn about changes made in suspended state */
+static int acpi_battery_resume(struct acpi_device *device, int state)
+{
+ struct acpi_battery *battery;
+
+ if (!device)
+ return -EINVAL;
+
+ battery = device->driver_data;
+ return acpi_battery_check(battery);
+}
+
static int __init acpi_battery_init(void)
{
int result;
#define ACPI_EC_DRIVER_NAME "ACPI Embedded Controller Driver"
#define ACPI_EC_DEVICE_NAME "Embedded Controller"
#define ACPI_EC_FILE_INFO "info"
+
+/* EC status register */
#define ACPI_EC_FLAG_OBF 0x01 /* Output buffer full */
#define ACPI_EC_FLAG_IBF 0x02 /* Input buffer full */
#define ACPI_EC_FLAG_BURST 0x10 /* burst mode */
#define ACPI_EC_FLAG_SCI 0x20 /* EC-SCI occurred */
-#define ACPI_EC_EVENT_OBF 0x01 /* Output buffer full */
-#define ACPI_EC_EVENT_IBE 0x02 /* Input buffer empty */
-#define ACPI_EC_DELAY 50 /* Wait 50ms max. during EC ops */
-#define ACPI_EC_UDELAY_GLK 1000 /* Wait 1ms max. to get global lock */
-#define ACPI_EC_UDELAY 100 /* Poll @ 100us increments */
-#define ACPI_EC_UDELAY_COUNT 1000 /* Wait 10ms max. during EC ops */
+
+/* EC commands */
#define ACPI_EC_COMMAND_READ 0x80
#define ACPI_EC_COMMAND_WRITE 0x81
#define ACPI_EC_BURST_ENABLE 0x82
#define ACPI_EC_BURST_DISABLE 0x83
#define ACPI_EC_COMMAND_QUERY 0x84
-#define EC_POLL 0xFF
-#define EC_INTR 0x00
+
+/* EC events */
+enum {
+ ACPI_EC_EVENT_OBF_1 = 1, /* Output buffer full */
+ ACPI_EC_EVENT_IBF_0, /* Input buffer empty */
+};
+
+#define ACPI_EC_DELAY 50 /* Wait 50ms max. during EC ops */
+#define ACPI_EC_UDELAY_GLK 1000 /* Wait 1ms max. to get global lock */
+#define ACPI_EC_UDELAY 100 /* Poll @ 100us increments */
+#define ACPI_EC_UDELAY_COUNT 1000 /* Wait 10ms max. during EC ops */
+
+enum {
+ EC_INTR = 1, /* Output buffer full */
+ EC_POLL, /* Input buffer empty */
+};
+
static int acpi_ec_remove(struct acpi_device *device, int type);
static int acpi_ec_start(struct acpi_device *device);
static int acpi_ec_stop(struct acpi_device *device, int type);
-static int acpi_ec_intr_add(struct acpi_device *device);
-static int acpi_ec_poll_add(struct acpi_device *device);
+static int acpi_ec_add(struct acpi_device *device);
static struct acpi_driver acpi_ec_driver = {
.name = ACPI_EC_DRIVER_NAME,
.class = ACPI_EC_CLASS,
.ids = ACPI_EC_HID,
.ops = {
- .add = acpi_ec_intr_add,
+ .add = acpi_ec_add,
.remove = acpi_ec_remove,
.start = acpi_ec_start,
.stop = acpi_ec_stop,
},
};
-union acpi_ec {
- struct {
- u32 mode;
- acpi_handle handle;
- unsigned long uid;
- unsigned long gpe_bit;
- struct acpi_generic_address status_addr;
- struct acpi_generic_address command_addr;
- struct acpi_generic_address data_addr;
- unsigned long global_lock;
- } common;
-
- struct {
- u32 mode;
- acpi_handle handle;
- unsigned long uid;
- unsigned long gpe_bit;
- struct acpi_generic_address status_addr;
- struct acpi_generic_address command_addr;
- struct acpi_generic_address data_addr;
- unsigned long global_lock;
- unsigned int expect_event;
- atomic_t leaving_burst; /* 0 : No, 1 : Yes, 2: abort */
- atomic_t pending_gpe;
- struct semaphore sem;
- wait_queue_head_t wait;
- } intr;
-
- struct {
- u32 mode;
- acpi_handle handle;
- unsigned long uid;
- unsigned long gpe_bit;
- struct acpi_generic_address status_addr;
- struct acpi_generic_address command_addr;
- struct acpi_generic_address data_addr;
- unsigned long global_lock;
- struct semaphore sem;
- } poll;
-};
-static int acpi_ec_poll_wait(union acpi_ec *ec, u8 event);
-static int acpi_ec_intr_wait(union acpi_ec *ec, unsigned int event);
-static int acpi_ec_poll_read(union acpi_ec *ec, u8 address, u32 * data);
-static int acpi_ec_intr_read(union acpi_ec *ec, u8 address, u32 * data);
-static int acpi_ec_poll_write(union acpi_ec *ec, u8 address, u8 data);
-static int acpi_ec_intr_write(union acpi_ec *ec, u8 address, u8 data);
-static int acpi_ec_poll_query(union acpi_ec *ec, u32 * data);
-static int acpi_ec_intr_query(union acpi_ec *ec, u32 * data);
-static void acpi_ec_gpe_poll_query(void *ec_cxt);
-static void acpi_ec_gpe_intr_query(void *ec_cxt);
-static u32 acpi_ec_gpe_poll_handler(void *data);
-static u32 acpi_ec_gpe_intr_handler(void *data);
-static acpi_status __init
-acpi_fake_ecdt_poll_callback(acpi_handle handle,
- u32 Level, void *context, void **retval);
-
-static acpi_status __init
-acpi_fake_ecdt_intr_callback(acpi_handle handle,
- u32 Level, void *context, void **retval);
-
-static int __init acpi_ec_poll_get_real_ecdt(void);
-static int __init acpi_ec_intr_get_real_ecdt(void);
/* If we find an EC via the ECDT, we need to keep a ptr to its context */
-static union acpi_ec *ec_ecdt;
+struct acpi_ec {
+ acpi_handle handle;
+ unsigned long uid;
+ unsigned long gpe_bit;
+ unsigned long command_addr;
+ unsigned long data_addr;
+ unsigned long global_lock;
+ struct semaphore sem;
+ unsigned int expect_event;
+ atomic_t leaving_burst; /* 0 : No, 1 : Yes, 2: abort */
+ wait_queue_head_t wait;
+} *ec_ecdt;
/* External interfaces use first EC only, so remember */
static struct acpi_device *first_ec;
-static int acpi_ec_poll_mode = EC_INTR;
+static int acpi_ec_mode = EC_INTR;
/* --------------------------------------------------------------------------
Transaction Management
-------------------------------------------------------------------------- */
-static u32 acpi_ec_read_status(union acpi_ec *ec)
+static inline u8 acpi_ec_read_status(struct acpi_ec *ec)
{
- u32 status = 0;
-
- acpi_hw_low_level_read(8, &status, &ec->common.status_addr);
- return status;
+ return inb(ec->command_addr);
}
-static int acpi_ec_wait(union acpi_ec *ec, u8 event)
+static inline u8 acpi_ec_read_data(struct acpi_ec *ec)
{
- if (acpi_ec_poll_mode)
- return acpi_ec_poll_wait(ec, event);
- else
- return acpi_ec_intr_wait(ec, event);
+ return inb(ec->data_addr);
}
-static int acpi_ec_poll_wait(union acpi_ec *ec, u8 event)
+static inline void acpi_ec_write_cmd(struct acpi_ec *ec, u8 command)
{
- u32 acpi_ec_status = 0;
- u32 i = ACPI_EC_UDELAY_COUNT;
+ outb(command, ec->command_addr);
+}
- if (!ec)
- return -EINVAL;
+static inline void acpi_ec_write_data(struct acpi_ec *ec, u8 data)
+{
+ outb(data, ec->data_addr);
+}
- /* Poll the EC status register waiting for the event to occur. */
+static int acpi_ec_check_status(u8 status, u8 event)
+{
switch (event) {
- case ACPI_EC_EVENT_OBF:
- do {
- acpi_hw_low_level_read(8, &acpi_ec_status,
- &ec->common.status_addr);
- if (acpi_ec_status & ACPI_EC_FLAG_OBF)
- return 0;
- udelay(ACPI_EC_UDELAY);
- } while (--i > 0);
+ case ACPI_EC_EVENT_OBF_1:
+ if (status & ACPI_EC_FLAG_OBF)
+ return 1;
break;
- case ACPI_EC_EVENT_IBE:
- do {
- acpi_hw_low_level_read(8, &acpi_ec_status,
- &ec->common.status_addr);
- if (!(acpi_ec_status & ACPI_EC_FLAG_IBF))
- return 0;
- udelay(ACPI_EC_UDELAY);
- } while (--i > 0);
+ case ACPI_EC_EVENT_IBF_0:
+ if (!(status & ACPI_EC_FLAG_IBF))
+ return 1;
break;
default:
- return -EINVAL;
+ break;
}
- return -ETIME;
+ return 0;
}
-static int acpi_ec_intr_wait(union acpi_ec *ec, unsigned int event)
-{
- int result = 0;
-
- ec->intr.expect_event = event;
- smp_mb();
+static int acpi_ec_wait(struct acpi_ec *ec, u8 event)
+{
+ int i = (acpi_ec_mode == EC_POLL) ? ACPI_EC_UDELAY_COUNT : 0;
+ long time_left;
- switch (event) {
- case ACPI_EC_EVENT_IBE:
- if (~acpi_ec_read_status(ec) & ACPI_EC_FLAG_IBF) {
- ec->intr.expect_event = 0;
- return 0;
- }
- break;
- default:
- break;
+ ec->expect_event = event;
+ if (acpi_ec_check_status(acpi_ec_read_status(ec), event)) {
+ ec->expect_event = 0;
+ return 0;
}
- result = wait_event_timeout(ec->intr.wait,
- !ec->intr.expect_event,
+ do {
+ if (acpi_ec_mode == EC_POLL) {
+ udelay(ACPI_EC_UDELAY);
+ } else {
+ time_left = wait_event_timeout(ec->wait,
+ !ec->expect_event,
msecs_to_jiffies(ACPI_EC_DELAY));
-
- ec->intr.expect_event = 0;
- smp_mb();
-
- /*
- * Verify that the event in question has actually happened by
- * querying EC status. Do the check even if operation timed-out
- * to make sure that we did not miss interrupt.
- */
- switch (event) {
- case ACPI_EC_EVENT_OBF:
- if (acpi_ec_read_status(ec) & ACPI_EC_FLAG_OBF)
+ if (time_left > 0) {
+ ec->expect_event = 0;
+ return 0;
+ }
+ }
+ if (acpi_ec_check_status(acpi_ec_read_status(ec), event)) {
+ ec->expect_event = 0;
return 0;
- break;
+ }
+ } while (--i > 0);
- case ACPI_EC_EVENT_IBE:
- if (~acpi_ec_read_status(ec) & ACPI_EC_FLAG_IBF)
- return 0;
- break;
- }
+ ec->expect_event = 0;
return -ETIME;
}
* Note: samsung nv5000 doesn't work with ec burst mode.
* http://bugzilla.kernel.org/show_bug.cgi?id=4980
*/
-int acpi_ec_enter_burst_mode(union acpi_ec *ec)
+int acpi_ec_enter_burst_mode(struct acpi_ec *ec)
{
- u32 tmp = 0;
- int status = 0;
+ u8 tmp = 0;
+ u8 status = 0;
status = acpi_ec_read_status(ec);
if (status != -EINVAL && !(status & ACPI_EC_FLAG_BURST)) {
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
+ status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBF_0);
if (status)
goto end;
- acpi_hw_low_level_write(8, ACPI_EC_BURST_ENABLE,
- &ec->common.command_addr);
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_OBF);
- acpi_hw_low_level_read(8, &tmp, &ec->common.data_addr);
+ acpi_ec_write_cmd(ec, ACPI_EC_BURST_ENABLE);
+ status = acpi_ec_wait(ec, ACPI_EC_EVENT_OBF_1);
+ tmp = acpi_ec_read_data(ec);
if (tmp != 0x90) { /* Burst ACK byte */
return -EINVAL;
}
}
- atomic_set(&ec->intr.leaving_burst, 0);
+ atomic_set(&ec->leaving_burst, 0);
return 0;
- end:
- ACPI_EXCEPTION ((AE_INFO, status, "EC wait, burst mode");
+ end:
+ ACPI_EXCEPTION((AE_INFO, status, "EC wait, burst mode"));
return -1;
}
-int acpi_ec_leave_burst_mode(union acpi_ec *ec)
+int acpi_ec_leave_burst_mode(struct acpi_ec *ec)
{
- int status = 0;
+ u8 status = 0;
status = acpi_ec_read_status(ec);
if (status != -EINVAL && (status & ACPI_EC_FLAG_BURST)){
- status = acpi_ec_wait(ec, ACPI_EC_FLAG_IBF);
+ status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBF_0);
if(status)
goto end;
- acpi_hw_low_level_write(8, ACPI_EC_BURST_DISABLE, &ec->common.command_addr);
- acpi_ec_wait(ec, ACPI_EC_FLAG_IBF);
- }
- atomic_set(&ec->intr.leaving_burst, 1);
+ acpi_ec_write_cmd(ec, ACPI_EC_BURST_DISABLE);
+ acpi_ec_wait(ec, ACPI_EC_EVENT_IBF_0);
+ }
+ atomic_set(&ec->leaving_burst, 1);
return 0;
-end:
- ACPI_EXCEPTION((AE_INFO, status, "EC leave burst mode");
+ end:
+ ACPI_EXCEPTION((AE_INFO, status, "EC leave burst mode"));
return -1;
}
#endif /* ACPI_FUTURE_USAGE */
-static int acpi_ec_read(union acpi_ec *ec, u8 address, u32 * data)
-{
- if (acpi_ec_poll_mode)
- return acpi_ec_poll_read(ec, address, data);
- else
- return acpi_ec_intr_read(ec, address, data);
-}
-static int acpi_ec_write(union acpi_ec *ec, u8 address, u8 data)
-{
- if (acpi_ec_poll_mode)
- return acpi_ec_poll_write(ec, address, data);
- else
- return acpi_ec_intr_write(ec, address, data);
-}
-static int acpi_ec_poll_read(union acpi_ec *ec, u8 address, u32 * data)
+static int acpi_ec_transaction_unlocked(struct acpi_ec *ec, u8 command,
+ const u8 *wdata, unsigned wdata_len,
+ u8 *rdata, unsigned rdata_len)
{
- acpi_status status = AE_OK;
- int result = 0;
- u32 glk = 0;
+ int result;
+ acpi_ec_write_cmd(ec, command);
- if (!ec || !data)
- return -EINVAL;
-
- *data = 0;
-
- if (ec->common.global_lock) {
- status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
- if (ACPI_FAILURE(status))
- return -ENODEV;
+ for (; wdata_len > 0; wdata_len --) {
+ result = acpi_ec_wait(ec, ACPI_EC_EVENT_IBF_0);
+ if (result)
+ return result;
+ acpi_ec_write_data(ec, *(wdata++));
}
- if (down_interruptible(&ec->poll.sem)) {
- result = -ERESTARTSYS;
- goto end_nosem;
+ if (command == ACPI_EC_COMMAND_WRITE) {
+ result = acpi_ec_wait(ec, ACPI_EC_EVENT_IBF_0);
+ if (result)
+ return result;
}
-
- acpi_hw_low_level_write(8, ACPI_EC_COMMAND_READ,
- &ec->common.command_addr);
- result = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (result)
- goto end;
-
- acpi_hw_low_level_write(8, address, &ec->common.data_addr);
- result = acpi_ec_wait(ec, ACPI_EC_EVENT_OBF);
- if (result)
- goto end;
-
- acpi_hw_low_level_read(8, data, &ec->common.data_addr);
-
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Read [%02x] from address [%02x]\n",
- *data, address));
-
- end:
- up(&ec->poll.sem);
-end_nosem:
- if (ec->common.global_lock)
- acpi_release_global_lock(glk);
-
- return result;
-}
-
-static int acpi_ec_poll_write(union acpi_ec *ec, u8 address, u8 data)
-{
- int result = 0;
- acpi_status status = AE_OK;
- u32 glk = 0;
+ for (; rdata_len > 0; rdata_len --) {
+ result = acpi_ec_wait(ec, ACPI_EC_EVENT_OBF_1);
+ if (result)
+ return result;
- if (!ec)
- return -EINVAL;
-
- if (ec->common.global_lock) {
- status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
- if (ACPI_FAILURE(status))
- return -ENODEV;
- }
-
- if (down_interruptible(&ec->poll.sem)) {
- result = -ERESTARTSYS;
- goto end_nosem;
+ *(rdata++) = acpi_ec_read_data(ec);
}
-
- acpi_hw_low_level_write(8, ACPI_EC_COMMAND_WRITE,
- &ec->common.command_addr);
- result = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (result)
- goto end;
-
- acpi_hw_low_level_write(8, address, &ec->common.data_addr);
- result = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (result)
- goto end;
-
- acpi_hw_low_level_write(8, data, &ec->common.data_addr);
- result = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (result)
- goto end;
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Wrote [%02x] to address [%02x]\n",
- data, address));
-
- end:
- up(&ec->poll.sem);
-end_nosem:
- if (ec->common.global_lock)
- acpi_release_global_lock(glk);
-
- return result;
+ return 0;
}
-static int acpi_ec_intr_read(union acpi_ec *ec, u8 address, u32 * data)
+static int acpi_ec_transaction(struct acpi_ec *ec, u8 command,
+ const u8 *wdata, unsigned wdata_len,
+ u8 *rdata, unsigned rdata_len)
{
- int status = 0;
+ int status;
u32 glk;
-
- if (!ec || !data)
+ if (!ec || (wdata_len && !wdata) || (rdata_len && !rdata))
return -EINVAL;
- *data = 0;
+ if (rdata)
+ memset(rdata, 0, rdata_len);
- if (ec->common.global_lock) {
+ if (ec->global_lock) {
status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
if (ACPI_FAILURE(status))
return -ENODEV;
}
+ down(&ec->sem);
- WARN_ON(in_interrupt());
- down(&ec->intr.sem);
-
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
+ status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBF_0);
if (status) {
printk(KERN_DEBUG PREFIX "read EC, IB not empty\n");
goto end;
}
- acpi_hw_low_level_write(8, ACPI_EC_COMMAND_READ,
- &ec->common.command_addr);
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (status) {
- printk(KERN_DEBUG PREFIX "read EC, IB not empty\n");
- }
- acpi_hw_low_level_write(8, address, &ec->common.data_addr);
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_OBF);
- if (status) {
- printk(KERN_DEBUG PREFIX "read EC, OB not full\n");
- goto end;
- }
- acpi_hw_low_level_read(8, data, &ec->common.data_addr);
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Read [%02x] from address [%02x]\n",
- *data, address));
+ status = acpi_ec_transaction_unlocked(ec, command,
+ wdata, wdata_len,
+ rdata, rdata_len);
- end:
- up(&ec->intr.sem);
+end:
+ up(&ec->sem);
- if (ec->common.global_lock)
+ if (ec->global_lock)
acpi_release_global_lock(glk);
return status;
}
-static int acpi_ec_intr_write(union acpi_ec *ec, u8 address, u8 data)
+static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data)
{
- int status = 0;
- u32 glk;
-
-
- if (!ec)
- return -EINVAL;
-
- if (ec->common.global_lock) {
- status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
- if (ACPI_FAILURE(status))
- return -ENODEV;
- }
-
- WARN_ON(in_interrupt());
- down(&ec->intr.sem);
-
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (status) {
- printk(KERN_DEBUG PREFIX "write EC, IB not empty\n");
- }
- acpi_hw_low_level_write(8, ACPI_EC_COMMAND_WRITE,
- &ec->common.command_addr);
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (status) {
- printk(KERN_DEBUG PREFIX "write EC, IB not empty\n");
- }
-
- acpi_hw_low_level_write(8, address, &ec->common.data_addr);
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (status) {
- printk(KERN_DEBUG PREFIX "write EC, IB not empty\n");
- }
-
- acpi_hw_low_level_write(8, data, &ec->common.data_addr);
+ int result;
+ u8 d;
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Wrote [%02x] to address [%02x]\n",
- data, address));
-
- up(&ec->intr.sem);
-
- if (ec->common.global_lock)
- acpi_release_global_lock(glk);
+ result = acpi_ec_transaction(ec, ACPI_EC_COMMAND_READ,
+ &address, 1, &d, 1);
+ *data = d;
+ return result;
+}
- return status;
+static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data)
+{
+ u8 wdata[2] = { address, data };
+ return acpi_ec_transaction(ec, ACPI_EC_COMMAND_WRITE,
+ wdata, 2, NULL, 0);
}
/*
* Externally callable EC access functions. For now, assume 1 EC only
*/
-int ec_read(u8 addr, u8 * val)
+int ec_read(u8 addr, u8 *val)
{
- union acpi_ec *ec;
+ struct acpi_ec *ec;
int err;
- u32 temp_data;
+ u8 temp_data;
if (!first_ec)
return -ENODEV;
int ec_write(u8 addr, u8 val)
{
- union acpi_ec *ec;
+ struct acpi_ec *ec;
int err;
if (!first_ec)
EXPORT_SYMBOL(ec_write);
-static int acpi_ec_query(union acpi_ec *ec, u32 * data)
-{
- if (acpi_ec_poll_mode)
- return acpi_ec_poll_query(ec, data);
- else
- return acpi_ec_intr_query(ec, data);
-}
-static int acpi_ec_poll_query(union acpi_ec *ec, u32 * data)
+extern int ec_transaction(u8 command,
+ const u8 *wdata, unsigned wdata_len,
+ u8 *rdata, unsigned rdata_len)
{
- int result = 0;
- acpi_status status = AE_OK;
- u32 glk = 0;
-
-
- if (!ec || !data)
- return -EINVAL;
-
- *data = 0;
-
- if (ec->common.global_lock) {
- status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
- if (ACPI_FAILURE(status))
- return -ENODEV;
- }
+ struct acpi_ec *ec;
- /*
- * Query the EC to find out which _Qxx method we need to evaluate.
- * Note that successful completion of the query causes the ACPI_EC_SCI
- * bit to be cleared (and thus clearing the interrupt source).
- */
- if (down_interruptible(&ec->poll.sem)) {
- result = -ERESTARTSYS;
- goto end_nosem;
- }
-
- acpi_hw_low_level_write(8, ACPI_EC_COMMAND_QUERY,
- &ec->common.command_addr);
- result = acpi_ec_wait(ec, ACPI_EC_EVENT_OBF);
- if (result)
- goto end;
-
- acpi_hw_low_level_read(8, data, &ec->common.data_addr);
- if (!*data)
- result = -ENODATA;
+ if (!first_ec)
+ return -ENODEV;
- end:
- up(&ec->poll.sem);
-end_nosem:
- if (ec->common.global_lock)
- acpi_release_global_lock(glk);
+ ec = acpi_driver_data(first_ec);
- return result;
+ return acpi_ec_transaction(ec, command, wdata,
+ wdata_len, rdata, rdata_len);
}
-static int acpi_ec_intr_query(union acpi_ec *ec, u32 * data)
-{
- int status = 0;
- u32 glk;
-
- if (!ec || !data)
- return -EINVAL;
- *data = 0;
-
- if (ec->common.global_lock) {
- status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
- if (ACPI_FAILURE(status))
- return -ENODEV;
- }
+EXPORT_SYMBOL(ec_transaction);
- down(&ec->intr.sem);
+static int acpi_ec_query(struct acpi_ec *ec, u8 *data)
+{
+ int result;
+ u8 d;
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_IBE);
- if (status) {
- printk(KERN_DEBUG PREFIX "query EC, IB not empty\n");
- goto end;
- }
- /*
- * Query the EC to find out which _Qxx method we need to evaluate.
- * Note that successful completion of the query causes the ACPI_EC_SCI
- * bit to be cleared (and thus clearing the interrupt source).
- */
- acpi_hw_low_level_write(8, ACPI_EC_COMMAND_QUERY,
- &ec->common.command_addr);
- status = acpi_ec_wait(ec, ACPI_EC_EVENT_OBF);
- if (status) {
- printk(KERN_DEBUG PREFIX "query EC, OB not full\n");
- goto end;
- }
+ if (!ec || !data)
+ return -EINVAL;
- acpi_hw_low_level_read(8, data, &ec->common.data_addr);
- if (!*data)
- status = -ENODATA;
+ /*
+ * Query the EC to find out which _Qxx method we need to evaluate.
+ * Note that successful completion of the query causes the ACPI_EC_SCI
+ * bit to be cleared (and thus clearing the interrupt source).
+ */
- end:
- up(&ec->intr.sem);
+ result = acpi_ec_transaction(ec, ACPI_EC_COMMAND_QUERY, NULL, 0, &d, 1);
+ if (result)
+ return result;
- if (ec->common.global_lock)
- acpi_release_global_lock(glk);
+ if (!d)
+ return -ENODATA;
- return status;
+ *data = d;
+ return 0;
}
/* --------------------------------------------------------------------------
Event Management
-------------------------------------------------------------------------- */
-union acpi_ec_query_data {
+struct acpi_ec_query_data {
acpi_handle handle;
u8 data;
};
static void acpi_ec_gpe_query(void *ec_cxt)
{
- if (acpi_ec_poll_mode)
- acpi_ec_gpe_poll_query(ec_cxt);
- else
- acpi_ec_gpe_intr_query(ec_cxt);
-}
-
-static void acpi_ec_gpe_poll_query(void *ec_cxt)
-{
- union acpi_ec *ec = (union acpi_ec *)ec_cxt;
- u32 value = 0;
- static char object_name[5] = { '_', 'Q', '0', '0', '\0' };
- const char hex[] = { '0', '1', '2', '3', '4', '5', '6', '7',
- '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'
- };
-
+ struct acpi_ec *ec = (struct acpi_ec *)ec_cxt;
+ u8 value = 0;
+ static char object_name[8];
- if (!ec_cxt)
+ if (!ec)
goto end;
- if (down_interruptible (&ec->poll.sem)) {
- return;
- }
- acpi_hw_low_level_read(8, &value, &ec->common.command_addr);
- up(&ec->poll.sem);
-
- /* TBD: Implement asynch events!
- * NOTE: All we care about are EC-SCI's. Other EC events are
- * handled via polling (yuck!). This is because some systems
- * treat EC-SCIs as level (versus EDGE!) triggered, preventing
- * a purely interrupt-driven approach (grumble, grumble).
- */
+ value = acpi_ec_read_status(ec);
+
if (!(value & ACPI_EC_FLAG_SCI))
goto end;
if (acpi_ec_query(ec, &value))
goto end;
- object_name[2] = hex[((value >> 4) & 0x0F)];
- object_name[3] = hex[(value & 0x0F)];
-
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Evaluating %s\n", object_name));
+ snprintf(object_name, 8, "_Q%2.2X", value);
- acpi_evaluate_object(ec->common.handle, object_name, NULL, NULL);
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Evaluating %s", object_name));
- end:
- acpi_enable_gpe(NULL, ec->common.gpe_bit, ACPI_NOT_ISR);
-}
-static void acpi_ec_gpe_intr_query(void *ec_cxt)
-{
- union acpi_ec *ec = (union acpi_ec *)ec_cxt;
- u32 value;
- int result = -ENODATA;
- static char object_name[5] = { '_', 'Q', '0', '0', '\0' };
- const char hex[] = { '0', '1', '2', '3', '4', '5', '6', '7',
- '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'
- };
+ acpi_evaluate_object(ec->handle, object_name, NULL, NULL);
-
- if (acpi_ec_read_status(ec) & ACPI_EC_FLAG_SCI)
- result = acpi_ec_query(ec, &value);
-
- if (result)
- goto end;
-
- object_name[2] = hex[((value >> 4) & 0x0F)];
- object_name[3] = hex[(value & 0x0F)];
-
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Evaluating %s\n", object_name));
-
- acpi_evaluate_object(ec->common.handle, object_name, NULL, NULL);
end:
- atomic_dec(&ec->intr.pending_gpe);
- return;
+ acpi_enable_gpe(NULL, ec->gpe_bit, ACPI_NOT_ISR);
}
static u32 acpi_ec_gpe_handler(void *data)
-{
- if (acpi_ec_poll_mode)
- return acpi_ec_gpe_poll_handler(data);
- else
- return acpi_ec_gpe_intr_handler(data);
-}
-static u32 acpi_ec_gpe_poll_handler(void *data)
{
acpi_status status = AE_OK;
- union acpi_ec *ec = (union acpi_ec *)data;
-
- if (!ec)
- return ACPI_INTERRUPT_NOT_HANDLED;
-
- acpi_disable_gpe(NULL, ec->common.gpe_bit, ACPI_ISR);
-
- status = acpi_os_execute(OSL_EC_POLL_HANDLER, acpi_ec_gpe_query, ec);
-
- if (status == AE_OK)
- return ACPI_INTERRUPT_HANDLED;
- else
- return ACPI_INTERRUPT_NOT_HANDLED;
-}
-static u32 acpi_ec_gpe_intr_handler(void *data)
-{
- acpi_status status = AE_OK;
- u32 value;
- union acpi_ec *ec = (union acpi_ec *)data;
-
- if (!ec)
- return ACPI_INTERRUPT_NOT_HANDLED;
+ u8 value;
+ struct acpi_ec *ec = (struct acpi_ec *)data;
- acpi_clear_gpe(NULL, ec->common.gpe_bit, ACPI_ISR);
+ acpi_clear_gpe(NULL, ec->gpe_bit, ACPI_ISR);
value = acpi_ec_read_status(ec);
- switch (ec->intr.expect_event) {
- case ACPI_EC_EVENT_OBF:
- if (!(value & ACPI_EC_FLAG_OBF))
- break;
- ec->intr.expect_event = 0;
- wake_up(&ec->intr.wait);
- break;
- case ACPI_EC_EVENT_IBE:
- if ((value & ACPI_EC_FLAG_IBF))
- break;
- ec->intr.expect_event = 0;
- wake_up(&ec->intr.wait);
- break;
- default:
- break;
+ if (acpi_ec_mode == EC_INTR) {
+ if (acpi_ec_check_status(value, ec->expect_event)) {
+ ec->expect_event = 0;
+ wake_up(&ec->wait);
+ }
}
if (value & ACPI_EC_FLAG_SCI) {
- atomic_add(1, &ec->intr.pending_gpe);
- status = acpi_os_execute(OSL_EC_BURST_HANDLER,
- acpi_ec_gpe_query, ec);
+ status = acpi_os_execute(OSL_EC_BURST_HANDLER, acpi_ec_gpe_query, ec);
return status == AE_OK ?
ACPI_INTERRUPT_HANDLED : ACPI_INTERRUPT_NOT_HANDLED;
}
- acpi_enable_gpe(NULL, ec->common.gpe_bit, ACPI_ISR);
+ acpi_enable_gpe(NULL, ec->gpe_bit, ACPI_ISR);
return status == AE_OK ?
ACPI_INTERRUPT_HANDLED : ACPI_INTERRUPT_NOT_HANDLED;
}
void *handler_context, void *region_context)
{
int result = 0;
- union acpi_ec *ec = NULL;
+ struct acpi_ec *ec = NULL;
u64 temp = *value;
acpi_integer f_v = 0;
int i = 0;
return AE_BAD_PARAMETER;
if (bit_width != 8 && acpi_strict) {
- printk(KERN_WARNING PREFIX
- "acpi_ec_space_handler: bit_width should be 8\n");
return AE_BAD_PARAMETER;
}
- ec = (union acpi_ec *)handler_context;
+ ec = (struct acpi_ec *)handler_context;
next_byte:
switch (function) {
case ACPI_READ:
temp = 0;
- result = acpi_ec_read(ec, (u8) address, (u32 *) & temp);
+ result = acpi_ec_read(ec, (u8) address, (u8 *) &temp);
break;
case ACPI_WRITE:
result = acpi_ec_write(ec, (u8) address, (u8) temp);
static int acpi_ec_read_info(struct seq_file *seq, void *offset)
{
- union acpi_ec *ec = (union acpi_ec *)seq->private;
+ struct acpi_ec *ec = (struct acpi_ec *)seq->private;
if (!ec)
goto end;
seq_printf(seq, "gpe bit: 0x%02x\n",
- (u32) ec->common.gpe_bit);
+ (u32) ec->gpe_bit);
seq_printf(seq, "ports: 0x%02x, 0x%02x\n",
- (u32) ec->common.status_addr.address,
- (u32) ec->common.data_addr.address);
+ (u32) ec->command_addr,
+ (u32) ec->data_addr);
seq_printf(seq, "use global lock: %s\n",
- ec->common.global_lock ? "yes" : "no");
- acpi_enable_gpe(NULL, ec->common.gpe_bit, ACPI_NOT_ISR);
+ ec->global_lock ? "yes" : "no");
+ acpi_enable_gpe(NULL, ec->gpe_bit, ACPI_NOT_ISR);
end:
return 0;
return single_open(file, acpi_ec_read_info, PDE(inode)->data);
}
-static const struct file_operations acpi_ec_info_ops = {
+static struct file_operations acpi_ec_info_ops = {
.open = acpi_ec_info_open_fs,
.read = seq_read,
.llseek = seq_lseek,
Driver Interface
-------------------------------------------------------------------------- */
-static int acpi_ec_poll_add(struct acpi_device *device)
+static int acpi_ec_add(struct acpi_device *device)
{
int result = 0;
acpi_status status = AE_OK;
- union acpi_ec *ec = NULL;
+ struct acpi_ec *ec = NULL;
if (!device)
return -EINVAL;
- ec = kmalloc(sizeof(union acpi_ec), GFP_KERNEL);
+ ec = kmalloc(sizeof(struct acpi_ec), GFP_KERNEL);
if (!ec)
return -ENOMEM;
- memset(ec, 0, sizeof(union acpi_ec));
-
- ec->common.handle = device->handle;
- ec->common.uid = -1;
- init_MUTEX(&ec->poll.sem);
- strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME);
- strcpy(acpi_device_class(device), ACPI_EC_CLASS);
- acpi_driver_data(device) = ec;
-
- /* Use the global lock for all EC transactions? */
- acpi_evaluate_integer(ec->common.handle, "_GLK", NULL,
- &ec->common.global_lock);
-
- /* XXX we don't test uids, because on some boxes ecdt uid = 0, see:
- http://bugzilla.kernel.org/show_bug.cgi?id=6111 */
- if (ec_ecdt) {
- acpi_remove_address_space_handler(ACPI_ROOT_OBJECT,
- ACPI_ADR_SPACE_EC,
- &acpi_ec_space_handler);
-
- acpi_remove_gpe_handler(NULL, ec_ecdt->common.gpe_bit,
- &acpi_ec_gpe_handler);
-
- kfree(ec_ecdt);
+ memset(ec, 0, sizeof(struct acpi_ec));
+
+ ec->handle = device->handle;
+ ec->uid = -1;
+ init_MUTEX(&ec->sem);
+ if (acpi_ec_mode == EC_INTR) {
+ atomic_set(&ec->leaving_burst, 1);
+ init_waitqueue_head(&ec->wait);
}
-
- /* Get GPE bit assignment (EC events). */
- /* TODO: Add support for _GPE returning a package */
- status =
- acpi_evaluate_integer(ec->common.handle, "_GPE", NULL,
- &ec->common.gpe_bit);
- if (ACPI_FAILURE(status)) {
- ACPI_EXCEPTION((AE_INFO, status, "Obtaining GPE bit"));
- result = -ENODEV;
- goto end;
- }
-
- result = acpi_ec_add_fs(device);
- if (result)
- goto end;
-
- printk(KERN_INFO PREFIX "%s [%s] (gpe %d) polling mode.\n",
- acpi_device_name(device), acpi_device_bid(device),
- (u32) ec->common.gpe_bit);
-
- if (!first_ec)
- first_ec = device;
-
- end:
- if (result)
- kfree(ec);
-
- return result;
-}
-static int acpi_ec_intr_add(struct acpi_device *device)
-{
- int result = 0;
- acpi_status status = AE_OK;
- union acpi_ec *ec = NULL;
-
-
- if (!device)
- return -EINVAL;
-
- ec = kmalloc(sizeof(union acpi_ec), GFP_KERNEL);
- if (!ec)
- return -ENOMEM;
- memset(ec, 0, sizeof(union acpi_ec));
-
- ec->common.handle = device->handle;
- ec->common.uid = -1;
- atomic_set(&ec->intr.pending_gpe, 0);
- atomic_set(&ec->intr.leaving_burst, 1);
- init_MUTEX(&ec->intr.sem);
- init_waitqueue_head(&ec->intr.wait);
strcpy(acpi_device_name(device), ACPI_EC_DEVICE_NAME);
strcpy(acpi_device_class(device), ACPI_EC_CLASS);
acpi_driver_data(device) = ec;
/* Use the global lock for all EC transactions? */
- acpi_evaluate_integer(ec->common.handle, "_GLK", NULL,
- &ec->common.global_lock);
+ acpi_evaluate_integer(ec->handle, "_GLK", NULL,
+ &ec->global_lock);
/* XXX we don't test uids, because on some boxes ecdt uid = 0, see:
http://bugzilla.kernel.org/show_bug.cgi?id=6111 */
ACPI_ADR_SPACE_EC,
&acpi_ec_space_handler);
- acpi_remove_gpe_handler(NULL, ec_ecdt->common.gpe_bit,
+ acpi_remove_gpe_handler(NULL, ec_ecdt->gpe_bit,
&acpi_ec_gpe_handler);
kfree(ec_ecdt);
/* Get GPE bit assignment (EC events). */
/* TODO: Add support for _GPE returning a package */
status =
- acpi_evaluate_integer(ec->common.handle, "_GPE", NULL,
- &ec->common.gpe_bit);
+ acpi_evaluate_integer(ec->handle, "_GPE", NULL,
+ &ec->gpe_bit);
if (ACPI_FAILURE(status)) {
- printk(KERN_ERR PREFIX "Obtaining GPE bit assignment\n");
+ ACPI_EXCEPTION((AE_INFO, status, "Obtaining GPE bit assignment"));
result = -ENODEV;
goto end;
}
if (result)
goto end;
- printk(KERN_INFO PREFIX "%s [%s] (gpe %d) interrupt mode.\n",
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "%s [%s] (gpe %d) interrupt mode.",
acpi_device_name(device), acpi_device_bid(device),
- (u32) ec->common.gpe_bit);
+ (u32) ec->gpe_bit));
if (!first_ec)
first_ec = device;
- end:
+ end:
if (result)
kfree(ec);
static int acpi_ec_remove(struct acpi_device *device, int type)
{
- union acpi_ec *ec = NULL;
+ struct acpi_ec *ec = NULL;
if (!device)
static acpi_status
acpi_ec_io_ports(struct acpi_resource *resource, void *context)
{
- union acpi_ec *ec = (union acpi_ec *)context;
- struct acpi_generic_address *addr;
+ struct acpi_ec *ec = (struct acpi_ec *)context;
if (resource->type != ACPI_RESOURCE_TYPE_IO) {
return AE_OK;
* the second address region returned is the status/command
* port.
*/
- if (ec->common.data_addr.register_bit_width == 0) {
- addr = &ec->common.data_addr;
- } else if (ec->common.command_addr.register_bit_width == 0) {
- addr = &ec->common.command_addr;
+ if (ec->data_addr == 0) {
+ ec->data_addr = resource->data.io.minimum;
+ } else if (ec->command_addr == 0) {
+ ec->command_addr = resource->data.io.minimum;
} else {
return AE_CTRL_TERMINATE;
}
- addr->address_space_id = ACPI_ADR_SPACE_SYSTEM_IO;
- addr->register_bit_width = 8;
- addr->register_bit_offset = 0;
- addr->address = resource->data.io.minimum;
-
return AE_OK;
}
static int acpi_ec_start(struct acpi_device *device)
{
acpi_status status = AE_OK;
- union acpi_ec *ec = NULL;
+ struct acpi_ec *ec = NULL;
if (!device)
/*
* Get I/O port addresses. Convert to GAS format.
*/
- status = acpi_walk_resources(ec->common.handle, METHOD_NAME__CRS,
+ status = acpi_walk_resources(ec->handle, METHOD_NAME__CRS,
acpi_ec_io_ports, ec);
- if (ACPI_FAILURE(status)
- || ec->common.command_addr.register_bit_width == 0) {
- printk(KERN_ERR PREFIX "Error getting I/O port addresses\n");
+ if (ACPI_FAILURE(status) || ec->command_addr == 0) {
+ ACPI_EXCEPTION((AE_INFO, status,
+ "Error getting I/O port addresses"));
return -ENODEV;
}
- ec->common.status_addr = ec->common.command_addr;
-
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "gpe=0x%02x, ports=0x%2x,0x%2x\n",
- (u32) ec->common.gpe_bit,
- (u32) ec->common.command_addr.address,
- (u32) ec->common.data_addr.address));
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "gpe=0x%02lx, ports=0x%2lx,0x%2lx",
+ ec->gpe_bit, ec->command_addr, ec->data_addr));
/*
* Install GPE handler
*/
- status = acpi_install_gpe_handler(NULL, ec->common.gpe_bit,
+ status = acpi_install_gpe_handler(NULL, ec->gpe_bit,
ACPI_GPE_EDGE_TRIGGERED,
&acpi_ec_gpe_handler, ec);
if (ACPI_FAILURE(status)) {
return -ENODEV;
}
- acpi_set_gpe_type(NULL, ec->common.gpe_bit, ACPI_GPE_TYPE_RUNTIME);
- acpi_enable_gpe(NULL, ec->common.gpe_bit, ACPI_NOT_ISR);
+ acpi_set_gpe_type(NULL, ec->gpe_bit, ACPI_GPE_TYPE_RUNTIME);
+ acpi_enable_gpe(NULL, ec->gpe_bit, ACPI_NOT_ISR);
- status = acpi_install_address_space_handler(ec->common.handle,
+ status = acpi_install_address_space_handler(ec->handle,
ACPI_ADR_SPACE_EC,
&acpi_ec_space_handler,
&acpi_ec_space_setup, ec);
if (ACPI_FAILURE(status)) {
- acpi_remove_gpe_handler(NULL, ec->common.gpe_bit,
+ acpi_remove_gpe_handler(NULL, ec->gpe_bit,
&acpi_ec_gpe_handler);
return -ENODEV;
}
static int acpi_ec_stop(struct acpi_device *device, int type)
{
acpi_status status = AE_OK;
- union acpi_ec *ec = NULL;
+ struct acpi_ec *ec = NULL;
if (!device)
ec = acpi_driver_data(device);
- status = acpi_remove_address_space_handler(ec->common.handle,
+ status = acpi_remove_address_space_handler(ec->handle,
ACPI_ADR_SPACE_EC,
&acpi_ec_space_handler);
if (ACPI_FAILURE(status))
return -ENODEV;
status =
- acpi_remove_gpe_handler(NULL, ec->common.gpe_bit,
+ acpi_remove_gpe_handler(NULL, ec->gpe_bit,
&acpi_ec_gpe_handler);
if (ACPI_FAILURE(status))
return -ENODEV;
acpi_fake_ecdt_callback(acpi_handle handle,
u32 Level, void *context, void **retval)
{
-
- if (acpi_ec_poll_mode)
- return acpi_fake_ecdt_poll_callback(handle,
- Level, context, retval);
- else
- return acpi_fake_ecdt_intr_callback(handle,
- Level, context, retval);
-}
-
-static acpi_status __init
-acpi_fake_ecdt_poll_callback(acpi_handle handle,
- u32 Level, void *context, void **retval)
-{
- acpi_status status;
-
- status = acpi_walk_resources(handle, METHOD_NAME__CRS,
- acpi_ec_io_ports, ec_ecdt);
- if (ACPI_FAILURE(status))
- return status;
- ec_ecdt->common.status_addr = ec_ecdt->common.command_addr;
-
- ec_ecdt->common.uid = -1;
- acpi_evaluate_integer(handle, "_UID", NULL, &ec_ecdt->common.uid);
-
- status =
- acpi_evaluate_integer(handle, "_GPE", NULL,
- &ec_ecdt->common.gpe_bit);
- if (ACPI_FAILURE(status))
- return status;
- init_MUTEX(&ec_ecdt->poll.sem);
- ec_ecdt->common.global_lock = TRUE;
- ec_ecdt->common.handle = handle;
-
- printk(KERN_INFO PREFIX "GPE=0x%02x, ports=0x%2x, 0x%2x\n",
- (u32) ec_ecdt->common.gpe_bit,
- (u32) ec_ecdt->common.command_addr.address,
- (u32) ec_ecdt->common.data_addr.address);
-
- return AE_CTRL_TERMINATE;
-}
-
-static acpi_status __init
-acpi_fake_ecdt_intr_callback(acpi_handle handle,
- u32 Level, void *context, void **retval)
-{
acpi_status status;
- init_MUTEX(&ec_ecdt->intr.sem);
- init_waitqueue_head(&ec_ecdt->intr.wait);
+ init_MUTEX(&ec_ecdt->sem);
+ if (acpi_ec_mode == EC_INTR) {
+ init_waitqueue_head(&ec_ecdt->wait);
+ }
status = acpi_walk_resources(handle, METHOD_NAME__CRS,
acpi_ec_io_ports, ec_ecdt);
if (ACPI_FAILURE(status))
return status;
- ec_ecdt->common.status_addr = ec_ecdt->common.command_addr;
- ec_ecdt->common.uid = -1;
- acpi_evaluate_integer(handle, "_UID", NULL, &ec_ecdt->common.uid);
+ ec_ecdt->uid = -1;
+ acpi_evaluate_integer(handle, "_UID", NULL, &ec_ecdt->uid);
status =
acpi_evaluate_integer(handle, "_GPE", NULL,
- &ec_ecdt->common.gpe_bit);
+ &ec_ecdt->gpe_bit);
if (ACPI_FAILURE(status))
return status;
- ec_ecdt->common.global_lock = TRUE;
- ec_ecdt->common.handle = handle;
+ ec_ecdt->global_lock = TRUE;
+ ec_ecdt->handle = handle;
- printk(KERN_INFO PREFIX "GPE=0x%02x, ports=0x%2x, 0x%2x\n",
- (u32) ec_ecdt->common.gpe_bit,
- (u32) ec_ecdt->common.command_addr.address,
- (u32) ec_ecdt->common.data_addr.address);
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "GPE=0x%02lx, ports=0x%2lx, 0x%2lx",
+ ec_ecdt->gpe_bit, ec_ecdt->command_addr, ec_ecdt->data_addr));
return AE_CTRL_TERMINATE;
}
acpi_status status;
int ret = 0;
- printk(KERN_INFO PREFIX "Try to make an fake ECDT\n");
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Try to make an fake ECDT"));
- ec_ecdt = kmalloc(sizeof(union acpi_ec), GFP_KERNEL);
+ ec_ecdt = kmalloc(sizeof(struct acpi_ec), GFP_KERNEL);
if (!ec_ecdt) {
ret = -ENOMEM;
goto error;
}
- memset(ec_ecdt, 0, sizeof(union acpi_ec));
+ memset(ec_ecdt, 0, sizeof(struct acpi_ec));
status = acpi_get_devices(ACPI_EC_HID,
acpi_fake_ecdt_callback, NULL, NULL);
kfree(ec_ecdt);
ec_ecdt = NULL;
ret = -ENODEV;
+ ACPI_EXCEPTION((AE_INFO, status, "Can't make an fake ECDT"));
goto error;
}
return 0;
- error:
- printk(KERN_ERR PREFIX "Can't make an fake ECDT\n");
+ error:
return ret;
}
static int __init acpi_ec_get_real_ecdt(void)
-{
- if (acpi_ec_poll_mode)
- return acpi_ec_poll_get_real_ecdt();
- else
- return acpi_ec_intr_get_real_ecdt();
-}
-
-static int __init acpi_ec_poll_get_real_ecdt(void)
{
acpi_status status;
struct acpi_table_ecdt *ecdt_ptr;
if (ACPI_FAILURE(status))
return -ENODEV;
- printk(KERN_INFO PREFIX "Found ECDT\n");
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Found ECDT"));
/*
* Generate a temporary ec context to use until the namespace is scanned
*/
- ec_ecdt = kmalloc(sizeof(union acpi_ec), GFP_KERNEL);
+ ec_ecdt = kmalloc(sizeof(struct acpi_ec), GFP_KERNEL);
if (!ec_ecdt)
return -ENOMEM;
- memset(ec_ecdt, 0, sizeof(union acpi_ec));
-
- ec_ecdt->common.command_addr = ecdt_ptr->ec_control;
- ec_ecdt->common.status_addr = ecdt_ptr->ec_control;
- ec_ecdt->common.data_addr = ecdt_ptr->ec_data;
- ec_ecdt->common.gpe_bit = ecdt_ptr->gpe_bit;
- init_MUTEX(&ec_ecdt->poll.sem);
- /* use the GL just to be safe */
- ec_ecdt->common.global_lock = TRUE;
- ec_ecdt->common.uid = ecdt_ptr->uid;
+ memset(ec_ecdt, 0, sizeof(struct acpi_ec));
- status =
- acpi_get_handle(NULL, ecdt_ptr->ec_id, &ec_ecdt->common.handle);
- if (ACPI_FAILURE(status)) {
- goto error;
+ init_MUTEX(&ec_ecdt->sem);
+ if (acpi_ec_mode == EC_INTR) {
+ init_waitqueue_head(&ec_ecdt->wait);
}
-
- return 0;
- error:
- printk(KERN_ERR PREFIX "Could not use ECDT\n");
- kfree(ec_ecdt);
- ec_ecdt = NULL;
-
- return -ENODEV;
-}
-
-static int __init acpi_ec_intr_get_real_ecdt(void)
-{
- acpi_status status;
- struct acpi_table_ecdt *ecdt_ptr;
-
- status = acpi_get_firmware_table("ECDT", 1, ACPI_LOGICAL_ADDRESSING,
- (struct acpi_table_header **)
- &ecdt_ptr);
- if (ACPI_FAILURE(status))
- return -ENODEV;
-
- printk(KERN_INFO PREFIX "Found ECDT\n");
-
- /*
- * Generate a temporary ec context to use until the namespace is scanned
- */
- ec_ecdt = kmalloc(sizeof(union acpi_ec), GFP_KERNEL);
- if (!ec_ecdt)
- return -ENOMEM;
- memset(ec_ecdt, 0, sizeof(union acpi_ec));
-
- init_MUTEX(&ec_ecdt->intr.sem);
- init_waitqueue_head(&ec_ecdt->intr.wait);
- ec_ecdt->common.command_addr = ecdt_ptr->ec_control;
- ec_ecdt->common.status_addr = ecdt_ptr->ec_control;
- ec_ecdt->common.data_addr = ecdt_ptr->ec_data;
- ec_ecdt->common.gpe_bit = ecdt_ptr->gpe_bit;
+ ec_ecdt->command_addr = ecdt_ptr->ec_control.address;
+ ec_ecdt->data_addr = ecdt_ptr->ec_data.address;
+ ec_ecdt->gpe_bit = ecdt_ptr->gpe_bit;
/* use the GL just to be safe */
- ec_ecdt->common.global_lock = TRUE;
- ec_ecdt->common.uid = ecdt_ptr->uid;
+ ec_ecdt->global_lock = TRUE;
+ ec_ecdt->uid = ecdt_ptr->uid;
status =
- acpi_get_handle(NULL, ecdt_ptr->ec_id, &ec_ecdt->common.handle);
+ acpi_get_handle(NULL, ecdt_ptr->ec_id, &ec_ecdt->handle);
if (ACPI_FAILURE(status)) {
goto error;
}
return 0;
- error:
- printk(KERN_ERR PREFIX "Could not use ECDT\n");
+ error:
+ ACPI_EXCEPTION((AE_INFO, status, "Could not use ECDT"));
kfree(ec_ecdt);
ec_ecdt = NULL;
/*
* Install GPE handler
*/
- status = acpi_install_gpe_handler(NULL, ec_ecdt->common.gpe_bit,
+ status = acpi_install_gpe_handler(NULL, ec_ecdt->gpe_bit,
ACPI_GPE_EDGE_TRIGGERED,
&acpi_ec_gpe_handler, ec_ecdt);
if (ACPI_FAILURE(status)) {
goto error;
}
- acpi_set_gpe_type(NULL, ec_ecdt->common.gpe_bit, ACPI_GPE_TYPE_RUNTIME);
- acpi_enable_gpe(NULL, ec_ecdt->common.gpe_bit, ACPI_NOT_ISR);
+ acpi_set_gpe_type(NULL, ec_ecdt->gpe_bit, ACPI_GPE_TYPE_RUNTIME);
+ acpi_enable_gpe(NULL, ec_ecdt->gpe_bit, ACPI_NOT_ISR);
status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT,
ACPI_ADR_SPACE_EC,
&acpi_ec_space_setup,
ec_ecdt);
if (ACPI_FAILURE(status)) {
- acpi_remove_gpe_handler(NULL, ec_ecdt->common.gpe_bit,
+ acpi_remove_gpe_handler(NULL, ec_ecdt->gpe_bit,
&acpi_ec_gpe_handler);
goto error;
}
return 0;
error:
- printk(KERN_ERR PREFIX "Could not use ECDT\n");
+ ACPI_EXCEPTION((AE_INFO, status, "Could not use ECDT"));
kfree(ec_ecdt);
ec_ecdt = NULL;
return 0;
if (intr) {
- acpi_ec_poll_mode = EC_INTR;
- acpi_ec_driver.ops.add = acpi_ec_intr_add;
+ acpi_ec_mode = EC_INTR;
} else {
- acpi_ec_poll_mode = EC_POLL;
- acpi_ec_driver.ops.add = acpi_ec_poll_add;
+ acpi_ec_mode = EC_POLL;
}
- printk(KERN_INFO PREFIX "EC %s mode.\n", intr ? "interrupt" : "polling");
+ acpi_ec_driver.ops.add = acpi_ec_add;
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "EC %s mode.\n", intr ? "interrupt" : "polling"));
+
return 1;
}
if (acquired) {
/* Got the lock, now wake all threads waiting for it */
-
acpi_gbl_global_lock_acquired = TRUE;
-
- /* Run the Global Lock thread which will signal all waiting threads */
-
- status =
- acpi_os_execute(OSL_GLOBAL_LOCK_HANDLER,
- acpi_ev_global_lock_thread, context);
- if (ACPI_FAILURE(status)) {
- ACPI_EXCEPTION((AE_INFO, status,
- "Could not queue Global Lock thread"));
-
- return (ACPI_INTERRUPT_NOT_HANDLED);
- }
+ acpi_ev_global_lock_thread(context);
}
return (ACPI_INTERRUPT_HANDLED);
if (!
(ACPI_STRNCMP
(object_hID.value, PCI_ROOT_HID_STRING,
- sizeof(PCI_ROOT_HID_STRING))
- ||
- !(ACPI_STRNCMP
- (object_hID.value,
- PCI_EXPRESS_ROOT_HID_STRING,
- sizeof(PCI_EXPRESS_ROOT_HID_STRING)))))
- {
+ sizeof(PCI_ROOT_HID_STRING)))
+ ||
+ !(ACPI_STRNCMP
+ (object_hID.value,
+ PCI_EXPRESS_ROOT_HID_STRING,
+ sizeof(PCI_EXPRESS_ROOT_HID_STRING)))) {
/* Install a handler for this PCI root bridge */
.name = "brightness",
.read = brightness_read,
.write = brightness_write,
- .experimental = 1,
},
{
.name = "volume",
.read = volume_read,
.write = volume_write,
- .experimental = 1,
},
{
.name = "fan",
* the io ports if they really know they can use it, while
* still preventing hotplug PCI devices from using it.
*/
+
+/*
+ * When CONFIG_PNP is enabled, pnp/system.c binds to PNP0C01
+ * and PNP0C02, redundant with acpi_reserve_io_ranges().
+ * But acpi_reserve_io_ranges() is necessary for !CONFIG_PNP.
+ */
static acpi_status acpi_reserve_io_ranges(struct acpi_resource *res, void *data)
{
struct resource *requested_res = NULL;
static acpi_osd_handler acpi_irq_handler;
static void *acpi_irq_context;
static struct workqueue_struct *kacpid_wq;
+static struct workqueue_struct *kacpi_notify_wq;
acpi_status acpi_os_initialize(void)
{
return AE_NULL_ENTRY;
}
kacpid_wq = create_singlethread_workqueue("kacpid");
+ kacpi_notify_wq = create_singlethread_workqueue("kacpi_notify");
BUG_ON(!kacpid_wq);
-
+ BUG_ON(!kacpi_notify_wq);
return AE_OK;
}
}
destroy_workqueue(kacpid_wq);
+ destroy_workqueue(kacpi_notify_wq);
return AE_OK;
}
static void acpi_os_execute_deferred(void *context)
{
- struct acpi_os_dpc *dpc = NULL;
-
-
- dpc = (struct acpi_os_dpc *)context;
+ struct acpi_os_dpc *dpc = (struct acpi_os_dpc *)context;
if (!dpc) {
printk(KERN_ERR PREFIX "Invalid (NULL) context\n");
return;
struct acpi_os_dpc *dpc;
struct work_struct *task;
- ACPI_FUNCTION_TRACE("os_queue_for_execution");
-
ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
"Scheduling function [%p(%p)] for deferred execution.\n",
function, context));
if (!function)
- return_ACPI_STATUS(AE_BAD_PARAMETER);
+ return AE_BAD_PARAMETER;
/*
* Allocate/initialize DPC structure. Note that this memory will be
* from the same memory.
*/
- dpc =
- kmalloc(sizeof(struct acpi_os_dpc) + sizeof(struct work_struct),
- GFP_ATOMIC);
+ dpc = kmalloc(sizeof(struct acpi_os_dpc) +
+ sizeof(struct work_struct), GFP_ATOMIC);
if (!dpc)
- return_ACPI_STATUS(AE_NO_MEMORY);
-
+ return AE_NO_MEMORY;
dpc->function = function;
dpc->context = context;
-
task = (void *)(dpc + 1);
INIT_WORK(task, acpi_os_execute_deferred, (void *)dpc);
-
- if (!queue_work(kacpid_wq, task)) {
- ACPI_DEBUG_PRINT((ACPI_DB_ERROR,
- "Call to queue_work() failed.\n"));
- kfree(dpc);
+ if (!queue_work((type == OSL_NOTIFY_HANDLER)?
+ kacpi_notify_wq : kacpid_wq, task)) {
status = AE_ERROR;
+ kfree(dpc);
}
-
- return_ACPI_STATUS(status);
+ return status;
}
EXPORT_SYMBOL(acpi_os_execute);
if (!link || !irq)
return -EINVAL;
- resource = kmalloc(sizeof(*resource) + 1, GFP_ATOMIC);
+ resource = kmalloc(sizeof(*resource) + 1, irqs_disabled() ? GFP_ATOMIC: GFP_KERNEL);
if (!resource)
return -ENOMEM;
{
int result = 0;
acpi_status status = AE_OK;
- struct acpi_device *device = NULL;
struct acpi_power_resource *resource = NULL;
-
result = acpi_power_get_context(handle, &resource);
if (result)
return result;
if (resource->references) {
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"Resource [%s] is still in use, dereferencing\n",
- device->pnp.bus_id));
+ resource->device->pnp.bus_id));
return 0;
}
if (resource->state == ACPI_POWER_RESOURCE_STATE_OFF) {
ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Resource [%s] already off\n",
- device->pnp.bus_id));
+ resource->device->pnp.bus_id));
return 0;
}
return -ENOEXEC;
/* Update the power resource's _device_ power state */
- device = resource->device;
- device->power.state = ACPI_STATE_D3;
+ resource->device->power.state = ACPI_STATE_D3;
ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Resource [%s] turned off\n",
resource->name));
static void *processor_device_array[NR_CPUS];
-static int acpi_processor_start(struct acpi_device *device)
+static int __cpuinit acpi_processor_start(struct acpi_device *device)
{
int result = 0;
acpi_status status = AE_OK;
static atomic_t c3_cpu_count;
+/* Common C-state entry for C2, C3, .. */
+static void acpi_cstate_enter(struct acpi_processor_cx *cstate)
+{
+ if (cstate->space_id == ACPI_CSTATE_FFH) {
+ /* Call into architectural FFH based C-state */
+ acpi_processor_ffh_cstate_enter(cstate);
+ } else {
+ int unused;
+ /* IO port based C-state */
+ inb(cstate->address);
+ /* Dummy wait op - must do something useless after P_LVL2 read
+ because chipsets cannot guarantee that STPCLK# signal
+ gets asserted in time to freeze execution properly. */
+ unused = inl(acpi_fadt.xpm_tmr_blk.address);
+ }
+}
+
static void acpi_processor_idle(void)
{
struct acpi_processor *pr = NULL;
/* Get start time (ticks) */
t1 = inl(acpi_fadt.xpm_tmr_blk.address);
/* Invoke C2 */
- inb(cx->address);
- /* Dummy wait op - must do something useless after P_LVL2 read
- because chipsets cannot guarantee that STPCLK# signal
- gets asserted in time to freeze execution properly. */
- t2 = inl(acpi_fadt.xpm_tmr_blk.address);
+ acpi_cstate_enter(cx);
/* Get end time (ticks) */
t2 = inl(acpi_fadt.xpm_tmr_blk.address);
/* Get start time (ticks) */
t1 = inl(acpi_fadt.xpm_tmr_blk.address);
/* Invoke C3 */
- inb(cx->address);
- /* Dummy wait op (see above) */
- t2 = inl(acpi_fadt.xpm_tmr_blk.address);
+ acpi_cstate_enter(cx);
/* Get end time (ticks) */
t2 = inl(acpi_fadt.xpm_tmr_blk.address);
if (pr->flags.bm_check) {
return 0;
}
-static int acpi_processor_get_power_info_default_c1(struct acpi_processor *pr)
+static int acpi_processor_get_power_info_default(struct acpi_processor *pr)
{
-
- /* Zero initialize all the C-states info. */
- memset(pr->power.states, 0, sizeof(pr->power.states));
-
- /* set the first C-State to C1 */
- pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1;
-
- /* the C0 state only exists as a filler in our array,
- * and all processors need to support C1 */
+ if (!pr->power.states[ACPI_STATE_C1].valid) {
+ /* set the first C-State to C1 */
+ /* all processors need to support C1 */
+ pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1;
+ pr->power.states[ACPI_STATE_C1].valid = 1;
+ }
+ /* the C0 state only exists as a filler in our array */
pr->power.states[ACPI_STATE_C0].valid = 1;
- pr->power.states[ACPI_STATE_C1].valid = 1;
-
return 0;
}
if (nocst)
return -ENODEV;
- current_count = 1;
-
- /* Zero initialize C2 onwards and prepare for fresh CST lookup */
- for (i = 2; i < ACPI_PROCESSOR_MAX_POWER; i++)
- memset(&(pr->power.states[i]), 0,
- sizeof(struct acpi_processor_cx));
+ current_count = 0;
status = acpi_evaluate_object(pr->handle, "_CST", NULL, &buffer);
if (ACPI_FAILURE(status)) {
(reg->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE))
continue;
- cx.address = (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) ?
- 0 : reg->address;
-
/* There should be an easy way to extract an integer... */
obj = (union acpi_object *)&(element->package.elements[1]);
if (obj->type != ACPI_TYPE_INTEGER)
continue;
cx.type = obj->integer.value;
-
- if ((cx.type != ACPI_STATE_C1) &&
- (reg->space_id != ACPI_ADR_SPACE_SYSTEM_IO))
- continue;
-
- if ((cx.type < ACPI_STATE_C2) || (cx.type > ACPI_STATE_C3))
- continue;
+ /*
+ * Some buggy BIOSes won't list C1 in _CST -
+ * Let acpi_processor_get_power_info_default() handle them later
+ */
+ if (i == 1 && cx.type != ACPI_STATE_C1)
+ current_count++;
+
+ cx.address = reg->address;
+ cx.index = current_count + 1;
+
+ cx.space_id = ACPI_CSTATE_SYSTEMIO;
+ if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) {
+ if (acpi_processor_ffh_cstate_probe
+ (pr->id, &cx, reg) == 0) {
+ cx.space_id = ACPI_CSTATE_FFH;
+ } else if (cx.type != ACPI_STATE_C1) {
+ /*
+ * C1 is a special case where FIXED_HARDWARE
+ * can be handled in non-MWAIT way as well.
+ * In that case, save this _CST entry info.
+ * That is, we retain space_id of SYSTEM_IO for
+ * halt based C1.
+ * Otherwise, ignore this info and continue.
+ */
+ continue;
+ }
+ }
obj = (union acpi_object *)&(element->package.elements[2]);
if (obj->type != ACPI_TYPE_INTEGER)
/* NOTE: the idle thread may not be running while calling
* this function */
- /* Adding C1 state */
- acpi_processor_get_power_info_default_c1(pr);
+ /* Zero initialize all the C-states info. */
+ memset(pr->power.states, 0, sizeof(pr->power.states));
+
result = acpi_processor_get_power_info_cst(pr);
if (result == -ENODEV)
acpi_processor_get_power_info_fadt(pr);
+ if (result)
+ return result;
+
+ acpi_processor_get_power_info_default(pr);
+
pr->power.count = acpi_processor_power_verify(pr);
/*
.release = single_release,
};
+#ifdef CONFIG_SMP
static void smp_callback(void *v)
{
/* we already woke the CPU up, nothing more to do */
static struct notifier_block acpi_processor_latency_notifier = {
.notifier_call = acpi_processor_latency_notify,
};
+#endif
-int acpi_processor_power_init(struct acpi_processor *pr,
+int __cpuinit acpi_processor_power_init(struct acpi_processor *pr,
struct acpi_device *device)
{
acpi_status status = 0;
"ACPI: processor limited to max C-state %d\n",
max_cstate);
first_run++;
+#ifdef CONFIG_SMP
register_latency_notifier(&acpi_processor_latency_notifier);
+#endif
}
if (!pr)
* copies of pm_idle before proceeding.
*/
cpu_idle_wait();
+#ifdef CONFIG_SMP
unregister_latency_notifier(&acpi_processor_latency_notifier);
+#endif
}
return 0;
static int update_time = UPDATE_TIME;
static int update_time2 = UPDATE_TIME2;
-module_param(capacity_mode, int, CAPACITY_UNIT);
-module_param(update_mode, int, UPDATE_MODE);
-module_param(update_info_mode, int, UPDATE_INFO_MODE);
-module_param(update_time, int, UPDATE_TIME);
-module_param(update_time2, int, UPDATE_TIME2);
+module_param(capacity_mode, int, 0);
+module_param(update_mode, int, 0);
+module_param(update_info_mode, int, 0);
+module_param(update_time, int, 0);
+module_param(update_time2, int, 0);
static int acpi_sbs_add(struct acpi_device *device);
static int acpi_sbs_remove(struct acpi_device *device, int type);
int acpi_sbs_remove(struct acpi_device *device, int type)
{
- struct acpi_sbs *sbs = (struct acpi_sbs *)acpi_driver_data(device);
+ struct acpi_sbs *sbs = NULL;
int id;
- if (!device || !sbs) {
+ if (!device) {
+ return -EINVAL;
+ }
+
+ sbs = (struct acpi_sbs *)acpi_driver_data(device);
+
+ if (!sbs) {
return -EINVAL;
}
if (header->length < sizeof(struct acpi_table_header)) {
ACPI_ERROR((AE_INFO,
- "Table length (%X) is smaller than minimum (%X)",
+ "Table length (%X) is smaller than minimum (%zX)",
header->length, sizeof(struct acpi_table_header)));
return_ACPI_STATUS(AE_INVALID_TABLE_LENGTH);
if (table_ptr->length < sizeof(struct acpi_table_header)) {
ACPI_ERROR((AE_INFO,
- "RSDT/XSDT length (%X) is smaller than minimum (%X)",
+ "RSDT/XSDT length (%X) is smaller than minimum (%zX)",
table_ptr->length,
sizeof(struct acpi_table_header)));
* the PIO timing number for the maximum. Turn it into
* a mask.
*/
- pio_mask = (2 << (id[ATA_ID_OLD_PIO_MODES] & 0xFF)) - 1 ;
+ u8 mode = id[ATA_ID_OLD_PIO_MODES] & 0xFF;
+ if (mode < 5) /* Valid PIO range */
+ pio_mask = (2 << mode) - 1;
+ else
+ pio_mask = 1;
/* But wait.. there's more. Design your standards by
* committee and you too can get a free iordy field to
{
int rc = 0;
u8 scsi_cmd[MAX_COMMAND_SIZE];
- u8 args[4], *argbuf = NULL;
+ u8 args[4], *argbuf = NULL, *sensebuf = NULL;
int argsize = 0;
- struct scsi_sense_hdr sshdr;
enum dma_data_direction data_dir;
+ int cmd_result;
if (arg == NULL)
return -EINVAL;
if (copy_from_user(args, arg, sizeof(args)))
return -EFAULT;
+ sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
+ if (!sensebuf)
+ return -ENOMEM;
+
memset(scsi_cmd, 0, sizeof(scsi_cmd));
if (args[3]) {
data_dir = DMA_FROM_DEVICE;
} else {
scsi_cmd[1] = (3 << 1); /* Non-data */
- /* scsi_cmd[2] is already 0 -- no off.line, cc, or data xfer */
+ scsi_cmd[2] = 0x20; /* cc but no off.line or data xfer */
data_dir = DMA_NONE;
}
/* Good values for timeout and retries? Values below
from scsi_ioctl_send_command() for default case... */
- if (scsi_execute_req(scsidev, scsi_cmd, data_dir, argbuf, argsize,
- &sshdr, (10*HZ), 5)) {
+ cmd_result = scsi_execute(scsidev, scsi_cmd, data_dir, argbuf, argsize,
+ sensebuf, (10*HZ), 5, 0);
+
+ if (driver_byte(cmd_result) == DRIVER_SENSE) {/* sense data available */
+ u8 *desc = sensebuf + 8;
+ cmd_result &= ~(0xFF<<24); /* DRIVER_SENSE is not an error */
+
+ /* If we set cc then ATA pass-through will cause a
+ * check condition even if no error. Filter that. */
+ if (cmd_result & SAM_STAT_CHECK_CONDITION) {
+ struct scsi_sense_hdr sshdr;
+ scsi_normalize_sense(sensebuf, SCSI_SENSE_BUFFERSIZE,
+ &sshdr);
+ if (sshdr.sense_key==0 &&
+ sshdr.asc==0 && sshdr.ascq==0)
+ cmd_result &= ~SAM_STAT_CHECK_CONDITION;
+ }
+
+ /* Send userspace a few ATA registers (same as drivers/ide) */
+ if (sensebuf[0] == 0x72 && /* format is "descriptor" */
+ desc[0] == 0x09 ) { /* code is "ATA Descriptor" */
+ args[0] = desc[13]; /* status */
+ args[1] = desc[3]; /* error */
+ args[2] = desc[5]; /* sector count (0:7) */
+ if (copy_to_user(arg, args, sizeof(args)))
+ rc = -EFAULT;
+ }
+ }
+
+
+ if (cmd_result) {
rc = -EIO;
goto error;
}
- /* Need code to retrieve data from check condition? */
-
if ((argbuf)
&& copy_to_user(arg + sizeof(args), argbuf, argsize))
rc = -EFAULT;
error:
+ kfree(sensebuf);
kfree(argbuf);
return rc;
}
memcpy(&pad, buf + buflen - slop, slop);
outl(le32_to_cpu(pad), ap->ioaddr.data_addr);
} else {
- pad = cpu_to_le16(inl(ap->ioaddr.data_addr));
+ pad = cpu_to_le32(inl(ap->ioaddr.data_addr));
memcpy(buf + buflen - slop, &pad, slop);
}
}
#if 0
{ PCI_VDEVICE(PROMISE, 0x3570), board_20771 },
#endif
+ { PCI_VDEVICE(PROMISE, 0x3577), board_20771 },
{ } /* terminate list */
};
static inline void DAC960_P_To_PD_TranslateDeviceState(void *DeviceState)
{
memcpy(DeviceState + 2, DeviceState + 3, 1);
- memcpy(DeviceState + 4, DeviceState + 5, 2);
- memcpy(DeviceState + 6, DeviceState + 8, 4);
+ memmove(DeviceState + 4, DeviceState + 5, 2);
+ memmove(DeviceState + 6, DeviceState + 8, 4);
}
static inline
return get_disk(unit[drive].gendisk);
}
-int __init amiga_floppy_init(void)
+static int __init amiga_floppy_init(void)
{
int i, ret;
+ if (!MACH_IS_AMIGA)
+ return -ENXIO;
+
if (!AMIGAHW_PRESENT(AMI_FLOPPY))
return -ENXIO;
return ret;
}
+module_init(amiga_floppy_init);
#ifdef MODULE
-int init_module(void)
-{
- if (!MACH_IS_AMIGA)
- return -ENXIO;
- return amiga_floppy_init();
-}
-
#if 0 /* not safe to unload */
void cleanup_module(void)
{
rd_disks[i] = alloc_disk(1);
if (!rd_disks[i])
goto out;
+
+ rd_queue[i] = blk_alloc_queue(GFP_KERNEL);
+ if (!rd_queue[i]) {
+ put_disk(rd_disks[i]);
+ goto out;
+ }
}
if (register_blkdev(RAMDISK_MAJOR, "ramdisk")) {
for (i = 0; i < CONFIG_BLK_DEV_RAM_COUNT; i++) {
struct gendisk *disk = rd_disks[i];
- rd_queue[i] = blk_alloc_queue(GFP_KERNEL);
- if (!rd_queue[i])
- goto out_queue;
-
blk_queue_make_request(rd_queue[i], &rd_make_request);
blk_queue_hardsect_size(rd_queue[i], rd_blocksize);
CONFIG_BLK_DEV_RAM_COUNT, rd_size, rd_blocksize);
return 0;
-out_queue:
- unregister_blkdev(RAMDISK_MAJOR, "ramdisk");
out:
while (i--) {
put_disk(rd_disks[i]);
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/delay.h>
+#include <linux/io.h>
#include <asm/system.h>
-#include <asm/io.h>
#include <asm/uaccess.h>
#include <asm/dma.h>
static struct request_queue *z2_queue;
-int __init
+static int __init
z2_init(void)
{
int ret;
return ret;
}
-#if defined(MODULE)
-
-MODULE_LICENSE("GPL");
-
-int
-init_module( void )
-{
- int error;
-
- error = z2_init();
- if ( error == 0 )
- {
- printk( KERN_INFO DEVICE_NAME ": loaded as module\n" );
- }
-
- return error;
-}
-
-void
-cleanup_module( void )
+static void __exit z2_exit(void)
{
int i, j;
blk_unregister_region(MKDEV(Z2RAM_MAJOR, 0), 256);
return;
}
-#endif
+
+module_init(z2_init);
+module_exit(z2_exit);
+MODULE_LICENSE("GPL");
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/errno.h>
-#include <linux/timer.h>
#include <linux/device.h>
#include <linux/firmware.h>
#define BT_DBG(D...)
#endif
-#define VERSION "1.0"
+#define VERSION "1.1"
static int ignore = 0;
unsigned long state;
- struct timer_list timer;
+ struct work_struct work;
struct urb *urb;
unsigned char *buffer;
data->state = BCM203X_SELECT_MEMORY;
- mod_timer(&data->timer, jiffies + (HZ / 10));
+ schedule_work(&data->work);
break;
case BCM203X_SELECT_MEMORY:
}
}
-static void bcm203x_timer(unsigned long user_data)
+static void bcm203x_work(void *user_data)
{
- struct bcm203x_data *data = (struct bcm203x_data *) user_data;
+ struct bcm203x_data *data = user_data;
if (usb_submit_urb(data->urb, GFP_ATOMIC) < 0)
BT_ERR("Can't submit URB");
release_firmware(firmware);
- init_timer(&data->timer);
- data->timer.function = bcm203x_timer;
- data->timer.data = (unsigned long) data;
+ INIT_WORK(&data->work, bcm203x_work, (void *) data);
usb_set_intfdata(intf, data);
- mod_timer(&data->timer, jiffies + HZ);
+ schedule_work(&data->work);
return 0;
}
config TELCLOCK
tristate "Telecom clock driver for MPBL0010 ATCA SBC"
- depends on EXPERIMENTAL
+ depends on EXPERIMENTAL && X86
default n
help
The telecom clock device is specific to the MPBL0010 ATCA computer and
int crd;
struct board_info *bd;
unsigned char board_id = 0;
+ int err = -ENOMEM;
int pci_boards_found, pci_count;
pc_driver = alloc_tty_driver(MAX_ALLOC);
if (!pc_driver)
- return -ENOMEM;
+ goto out1;
pc_info = alloc_tty_driver(MAX_ALLOC);
- if (!pc_info) {
- put_tty_driver(pc_driver);
- return -ENOMEM;
- }
+ if (!pc_info)
+ goto out2;
/* -----------------------------------------------------------------------
If epca_setup has not been ran by LILO set num_cards to defaults; copy
} /* End for each card */
- if (tty_register_driver(pc_driver))
- panic("Couldn't register Digi PC/ driver");
+ err = tty_register_driver(pc_driver);
+ if (err) {
+ printk(KERN_ERR "Couldn't register Digi PC/ driver");
+ goto out3;
+ }
- if (tty_register_driver(pc_info))
- panic("Couldn't register Digi PC/ info ");
+ err = tty_register_driver(pc_info);
+ if (err) {
+ printk(KERN_ERR "Couldn't register Digi PC/ info ");
+ goto out4;
+ }
/* -------------------------------------------------------------------
Start up the poller to check for events on all enabled boards
mod_timer(&epca_timer, jiffies + HZ/25);
return 0;
+out4:
+ tty_unregister_driver(pc_driver);
+out3:
+ put_tty_driver(pc_info);
+out2:
+ put_tty_driver(pc_driver);
+out1:
+ return err;
+
} /* End pc_init */
/* ------------------ Begin post_fep_init ---------------------- */
// applications that one cannot break out of.
//******************************************************************************
static int
-i2Output(i2ChanStrPtr pCh, const char *pSource, int count, int user )
+i2Output(i2ChanStrPtr pCh, const char *pSource, int count)
{
i2eBordStrPtr pB;
unsigned char *pInsert;
int bailout = 10;
- ip2trace (CHANN, ITRC_OUTPUT, ITRC_ENTER, 2, count, user );
+ ip2trace (CHANN, ITRC_OUTPUT, ITRC_ENTER, 2, count, 0 );
// Ensure channel structure seems real
if ( !i2Validate ( pCh ) )
DATA_COUNT_OF(pInsert) = amountToMove;
// Move the data
- if ( user ) {
- rc = copy_from_user((char*)(DATA_OF(pInsert)), pSource,
- amountToMove );
- } else {
- memcpy( (char*)(DATA_OF(pInsert)), pSource, amountToMove );
- }
+ memcpy( (char*)(DATA_OF(pInsert)), pSource, amountToMove );
// Adjust pointers and indices
pSource += amountToMove;
pCh->Obuf_char_count += amountToMove;
static int i2GetStatus(i2ChanStrPtr, int);
static int i2Input(i2ChanStrPtr);
static int i2InputFlush(i2ChanStrPtr);
-static int i2Output(i2ChanStrPtr, const char *, int, int);
+static int i2Output(i2ChanStrPtr, const char *, int);
static int i2OutputFree(i2ChanStrPtr);
static int i2ServiceBoard(i2eBordStrPtr);
static void i2DrainOutput(i2ChanStrPtr, int);
/* This is the actual move bit. Make sure it does what we need!!!!! */
WRITE_LOCK_IRQSAVE(&pCh->Pbuf_spinlock,flags);
- bytesSent = i2Output( pCh, pData, count, 0 );
+ bytesSent = i2Output( pCh, pData, count);
WRITE_UNLOCK_IRQRESTORE(&pCh->Pbuf_spinlock,flags);
ip2trace (CHANN, ITRC_WRITE, ITRC_RETURN, 1, bytesSent );
//
// We may need to restart i2Output if it does not fullfill this request
//
- strip = i2Output( pCh, pCh->Pbuf, pCh->Pbuf_stuff, 0 );
+ strip = i2Output( pCh, pCh->Pbuf, pCh->Pbuf_stuff);
if ( strip != pCh->Pbuf_stuff ) {
memmove( pCh->Pbuf, &pCh->Pbuf[strip], pCh->Pbuf_stuff - strip );
}
(long long) bmc->guid[8]);
}
-static void
-cleanup_bmc_device(struct kref *ref)
+static void remove_files(struct bmc_device *bmc)
{
- struct bmc_device *bmc;
-
- bmc = container_of(ref, struct bmc_device, refcount);
-
device_remove_file(&bmc->dev->dev,
&bmc->device_id_attr);
device_remove_file(&bmc->dev->dev,
&bmc->manufacturer_id_attr);
device_remove_file(&bmc->dev->dev,
&bmc->product_id_attr);
+
if (bmc->id.aux_firmware_revision_set)
device_remove_file(&bmc->dev->dev,
&bmc->aux_firmware_rev_attr);
if (bmc->guid_set)
device_remove_file(&bmc->dev->dev,
&bmc->guid_attr);
+}
+
+static void
+cleanup_bmc_device(struct kref *ref)
+{
+ struct bmc_device *bmc;
+
+ bmc = container_of(ref, struct bmc_device, refcount);
+
+ remove_files(bmc);
platform_device_unregister(bmc->dev);
kfree(bmc);
}
mutex_unlock(&ipmidriver_mutex);
}
+static int create_files(struct bmc_device *bmc)
+{
+ int err;
+
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->device_id_attr);
+ if (err) goto out;
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->provides_dev_sdrs_attr);
+ if (err) goto out_devid;
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->revision_attr);
+ if (err) goto out_sdrs;
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->firmware_rev_attr);
+ if (err) goto out_rev;
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->version_attr);
+ if (err) goto out_firm;
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->add_dev_support_attr);
+ if (err) goto out_version;
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->manufacturer_id_attr);
+ if (err) goto out_add_dev;
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->product_id_attr);
+ if (err) goto out_manu;
+ if (bmc->id.aux_firmware_revision_set) {
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->aux_firmware_rev_attr);
+ if (err) goto out_prod_id;
+ }
+ if (bmc->guid_set) {
+ err = device_create_file(&bmc->dev->dev,
+ &bmc->guid_attr);
+ if (err) goto out_aux_firm;
+ }
+
+ return 0;
+
+out_aux_firm:
+ if (bmc->id.aux_firmware_revision_set)
+ device_remove_file(&bmc->dev->dev,
+ &bmc->aux_firmware_rev_attr);
+out_prod_id:
+ device_remove_file(&bmc->dev->dev,
+ &bmc->product_id_attr);
+out_manu:
+ device_remove_file(&bmc->dev->dev,
+ &bmc->manufacturer_id_attr);
+out_add_dev:
+ device_remove_file(&bmc->dev->dev,
+ &bmc->add_dev_support_attr);
+out_version:
+ device_remove_file(&bmc->dev->dev,
+ &bmc->version_attr);
+out_firm:
+ device_remove_file(&bmc->dev->dev,
+ &bmc->firmware_rev_attr);
+out_rev:
+ device_remove_file(&bmc->dev->dev,
+ &bmc->revision_attr);
+out_sdrs:
+ device_remove_file(&bmc->dev->dev,
+ &bmc->provides_dev_sdrs_attr);
+out_devid:
+ device_remove_file(&bmc->dev->dev,
+ &bmc->device_id_attr);
+out:
+ return err;
+}
+
static int ipmi_bmc_register(ipmi_smi_t intf)
{
int rv;
bmc->provides_dev_sdrs_attr.attr.mode = S_IRUGO;
bmc->provides_dev_sdrs_attr.show = provides_dev_sdrs_show;
-
bmc->revision_attr.attr.name = "revision";
bmc->revision_attr.attr.owner = THIS_MODULE;
bmc->revision_attr.attr.mode = S_IRUGO;
bmc->aux_firmware_rev_attr.attr.mode = S_IRUGO;
bmc->aux_firmware_rev_attr.show = aux_firmware_rev_show;
- device_create_file(&bmc->dev->dev,
- &bmc->device_id_attr);
- device_create_file(&bmc->dev->dev,
- &bmc->provides_dev_sdrs_attr);
- device_create_file(&bmc->dev->dev,
- &bmc->revision_attr);
- device_create_file(&bmc->dev->dev,
- &bmc->firmware_rev_attr);
- device_create_file(&bmc->dev->dev,
- &bmc->version_attr);
- device_create_file(&bmc->dev->dev,
- &bmc->add_dev_support_attr);
- device_create_file(&bmc->dev->dev,
- &bmc->manufacturer_id_attr);
- device_create_file(&bmc->dev->dev,
- &bmc->product_id_attr);
- if (bmc->id.aux_firmware_revision_set)
- device_create_file(&bmc->dev->dev,
- &bmc->aux_firmware_rev_attr);
- if (bmc->guid_set)
- device_create_file(&bmc->dev->dev,
- &bmc->guid_attr);
+ rv = create_files(bmc);
+ if (rv) {
+ mutex_lock(&ipmidriver_mutex);
+ platform_device_unregister(bmc->dev);
+ mutex_unlock(&ipmidriver_mutex);
+
+ return rv;
+ }
printk(KERN_INFO
"ipmi: Found new BMC (man_id: 0x%6.6x, "
#include <linux/backing-dev.h>
#include <linux/bootmem.h>
#include <linux/pipe_fs_i.h>
+#include <linux/pfn.h>
#include <asm/uaccess.h>
#include <asm/io.h>
{
unsigned long pfn;
- /* Turn a kernel-virtual address into a physical page frame */
- pfn = __pa((u64)vma->vm_pgoff << PAGE_SHIFT) >> PAGE_SHIFT;
+ /* Turn a pfn offset into an absolute pfn */
+ pfn = PFN_DOWN(virt_to_phys((void *)PAGE_OFFSET)) + vma->vm_pgoff;
/*
* RED-PEN: on some architectures there is more mapped memory
p->RIOError.Error = COPYIN_FAILED;
return -EFAULT;
}
- if (portStats.port >= RIO_PORTS) {
+ if (portStats.port < 0 || portStats.port >= RIO_PORTS) {
p->RIOError.Error = PORT_NUMBER_OUT_OF_RANGE;
return -ENXIO;
}
p->RIOError.Error = COPYIN_FAILED;
return -EFAULT;
}
- if (portStats.port >= RIO_PORTS) {
+ if (portStats.port < 0 || portStats.port >= RIO_PORTS) {
p->RIOError.Error = PORT_NUMBER_OUT_OF_RANGE;
return -ENXIO;
}
local_irq_save(flags);
if (info->xmit_buf){
free_page((unsigned long) info->xmit_buf);
- info->xmit_buf = 0;
+ info->xmit_buf = NULL;
}
base_addr[CyCAR] = (u_char)channel;
static int
get_serial_info(struct cyclades_port * info,
- struct serial_struct * retinfo)
+ struct serial_struct __user * retinfo)
{
struct serial_struct tmp;
static int
set_serial_info(struct cyclades_port * info,
- struct serial_struct * new_info)
+ struct serial_struct __user * new_info)
{
struct serial_struct new_serial;
struct cyclades_port old_info;
} /* send_break */
static int
-get_mon_info(struct cyclades_port * info, struct cyclades_monitor * mon)
+get_mon_info(struct cyclades_port * info, struct cyclades_monitor __user * mon)
{
if (copy_to_user(mon, &info->mon, sizeof(struct cyclades_monitor)))
}
static int
-set_threshold(struct cyclades_port * info, unsigned long *arg)
+set_threshold(struct cyclades_port * info, unsigned long __user *arg)
{
volatile unsigned char *base_addr = (u_char *)BASE_ADDR;
unsigned long value;
}
static int
-get_threshold(struct cyclades_port * info, unsigned long *value)
+get_threshold(struct cyclades_port * info, unsigned long __user *value)
{
volatile unsigned char *base_addr = (u_char *)BASE_ADDR;
int channel;
}
static int
-set_default_threshold(struct cyclades_port * info, unsigned long *arg)
+set_default_threshold(struct cyclades_port * info, unsigned long __user *arg)
{
unsigned long value;
}
static int
-get_default_threshold(struct cyclades_port * info, unsigned long *value)
+get_default_threshold(struct cyclades_port * info, unsigned long __user *value)
{
return put_user(info->default_threshold,value);
}
static int
-set_timeout(struct cyclades_port * info, unsigned long *arg)
+set_timeout(struct cyclades_port * info, unsigned long __user *arg)
{
volatile unsigned char *base_addr = (u_char *)BASE_ADDR;
int channel;
}
static int
-get_timeout(struct cyclades_port * info, unsigned long *value)
+get_timeout(struct cyclades_port * info, unsigned long __user *value)
{
volatile unsigned char *base_addr = (u_char *)BASE_ADDR;
int channel;
}
static int
-get_default_timeout(struct cyclades_port * info, unsigned long *value)
+get_default_timeout(struct cyclades_port * info, unsigned long __user *value)
{
return put_user(info->default_timeout,value);
}
unsigned long val;
struct cyclades_port * info = (struct cyclades_port *)tty->driver_data;
int ret_val = 0;
+ void __user *argp = (void __user *)arg;
#ifdef SERIAL_DEBUG_OTHER
printk("cy_ioctl %s, cmd = %x arg = %lx\n", tty->name, cmd, arg); /* */
switch (cmd) {
case CYGETMON:
- ret_val = get_mon_info(info, (struct cyclades_monitor *)arg);
+ ret_val = get_mon_info(info, argp);
break;
case CYGETTHRESH:
- ret_val = get_threshold(info, (unsigned long *)arg);
+ ret_val = get_threshold(info, argp);
break;
case CYSETTHRESH:
- ret_val = set_threshold(info, (unsigned long *)arg);
+ ret_val = set_threshold(info, argp);
break;
case CYGETDEFTHRESH:
- ret_val = get_default_threshold(info, (unsigned long *)arg);
+ ret_val = get_default_threshold(info, argp);
break;
case CYSETDEFTHRESH:
- ret_val = set_default_threshold(info, (unsigned long *)arg);
+ ret_val = set_default_threshold(info, argp);
break;
case CYGETTIMEOUT:
- ret_val = get_timeout(info, (unsigned long *)arg);
+ ret_val = get_timeout(info, argp);
break;
case CYSETTIMEOUT:
- ret_val = set_timeout(info, (unsigned long *)arg);
+ ret_val = set_timeout(info, argp);
break;
case CYGETDEFTIMEOUT:
- ret_val = get_default_timeout(info, (unsigned long *)arg);
+ ret_val = get_default_timeout(info, argp);
break;
case CYSETDEFTIMEOUT:
ret_val = set_default_timeout(info, (unsigned long)arg);
/* The following commands are incompletely implemented!!! */
case TIOCGSOFTCAR:
- ret_val = put_user(C_CLOCAL(tty) ? 1 : 0, (unsigned long *) arg);
+ ret_val = put_user(C_CLOCAL(tty) ? 1 : 0, (unsigned long __user *) argp);
break;
case TIOCSSOFTCAR:
- ret_val = get_user(val, (unsigned long *) arg);
+ ret_val = get_user(val, (unsigned long __user *) argp);
if (ret_val)
break;
tty->termios->c_cflag =
((tty->termios->c_cflag & ~CLOCAL) | (val ? CLOCAL : 0));
break;
case TIOCGSERIAL:
- ret_val = get_serial_info(info, (struct serial_struct *) arg);
+ ret_val = get_serial_info(info, argp);
break;
case TIOCSSERIAL:
- ret_val = set_serial_info(info,
- (struct serial_struct *) arg);
+ ret_val = set_serial_info(info, argp);
break;
default:
ret_val = -ENOIOCTLCMD;
tty->driver->flush_buffer(tty);
tty_ldisc_flush(tty);
info->event = 0;
- info->tty = 0;
+ info->tty = NULL;
if (info->blocked_open) {
if (info->close_delay) {
msleep_interruptible(jiffies_to_msecs(info->close_delay));
info->card = index;
info->line = port_num;
info->flags = STD_COM_FLAGS;
- info->tty = 0;
+ info->tty = NULL;
info->xmit_fifo_size = 12;
info->cor1 = CyPARITY_NONE|Cy_8_BITS;
info->cor2 = CyETC;
static struct tty_driver *specialix_driver;
-static unsigned long baud_table[] = {
- 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800,
- 9600, 19200, 38400, 57600, 115200, 0,
-};
-
static struct specialix_board sx_board[SX_NBOARD] = {
{ 0, SX_IOBASE1, 9, },
{ 0, SX_IOBASE2, 11, },
if (baud == 38400) {
if ((port->flags & ASYNC_SPD_MASK) == ASYNC_SPD_HI)
- baud ++;
+ baud = 57600;
if ((port->flags & ASYNC_SPD_MASK) == ASYNC_SPD_VHI)
- baud += 2;
+ baud = 115200;
}
if (!baud) {
sx_out(bp, CD186x_RBPRL, tmp & 0xff);
sx_out(bp, CD186x_TBPRL, tmp & 0xff);
spin_unlock_irqrestore(&bp->lock, flags);
- if (port->custom_divisor) {
+ if (port->custom_divisor)
baud = (SX_OSCFREQ + port->custom_divisor/2) / port->custom_divisor;
- baud = ( baud + 5 ) / 10;
- } else
- baud = (baud_table[baud] + 5) / 10; /* Estimated CPS */
+ baud = (baud + 5) / 10; /* Estimated CPS */
/* Two timer ticks seems enough to wakeup something like SLIP driver */
tmp = ((baud + HZ/2) / HZ) * 2 - CD186x_NFIFO;
}
}
if (misc_deregister(&sx_fw_device) < 0) {
- printk (KERN_INFO "sx: couldn't deregister firmware loader devic\n");
+ printk (KERN_INFO "sx: couldn't deregister firmware loader device\n");
}
sx_dprintk (SX_DEBUG_CLEANUP, "Cleaning up drivers (%d)\n", sx_initialized);
if (sx_initialized)
};
#define SHARED_MEM_ADDRESS_SIZE 0x40000
-#define BUFFERLISTSIZE (PAGE_SIZE)
-#define DMABUFFERSIZE (PAGE_SIZE)
+#define BUFFERLISTSIZE 4096
+#define DMABUFFERSIZE 4096
#define MAXRXFRAMES 7
typedef struct _DMABUFFERENTRY
spin_unlock(&driver_lock);
- sysfs_create_group(&dev->kobj, chip->vendor.attr_group);
+ if (sysfs_create_group(&dev->kobj, chip->vendor.attr_group)) {
+ list_del(&chip->list);
+ put_device(dev);
+ clear_bit(chip->dev_num, dev_mask);
+ kfree(chip);
+ kfree(devname);
+ return NULL;
+ }
chip->bios_dir = tpm_bios_log_setup(devname);
unsigned long base;
struct tpm_chip *chip;
- driver_register(&atml_drv);
+ rc = driver_register(&atml_drv);
+ if (rc)
+ return rc;
if ((iobase = atmel_get_base_addr(&base, ®ion_size)) == NULL) {
rc = -ENODEV;
(atmel_request_region
(tpm_atmel.base, region_size, "tpm_atmel0") == NULL) ? 0 : 1;
-
- if (IS_ERR
- (pdev =
- platform_device_register_simple("tpm_atmel", -1, NULL, 0))) {
+ pdev = platform_device_register_simple("tpm_atmel", -1, NULL, 0);
+ if (IS_ERR(pdev)) {
rc = PTR_ERR(pdev);
goto err_rel_reg;
}
static int __init init_nsc(void)
{
int rc = 0;
- int lo, hi;
+ int lo, hi, err;
int nscAddrBase = TPM_ADDR;
struct tpm_chip *chip;
unsigned long base;
return -ENODEV;
}
- driver_register(&nsc_drv);
+ err = driver_register(&nsc_drv);
+ if (err)
+ return err;
hi = tpm_read_index(nscAddrBase, TPM_NSC_BASE0_HI);
lo = tpm_read_index(nscAddrBase, TPM_NSC_BASE0_LO);
static int __init eisa_register_device (struct eisa_device *edev)
{
- if (device_register (&edev->dev))
- return -1;
+ int rc = device_register (&edev->dev);
+ if (rc)
+ return rc;
- device_create_file (&edev->dev, &dev_attr_signature);
- device_create_file (&edev->dev, &dev_attr_enabled);
- device_create_file (&edev->dev, &dev_attr_modalias);
+ rc = device_create_file (&edev->dev, &dev_attr_signature);
+ if (rc) goto err_devreg;
+ rc = device_create_file (&edev->dev, &dev_attr_enabled);
+ if (rc) goto err_sig;
+ rc = device_create_file (&edev->dev, &dev_attr_modalias);
+ if (rc) goto err_enab;
return 0;
+
+err_enab:
+ device_remove_file (&edev->dev, &dev_attr_enabled);
+err_sig:
+ device_remove_file (&edev->dev, &dev_attr_signature);
+err_devreg:
+ device_unregister(&edev->dev);
+ return rc;
}
static int __init eisa_request_resources (struct eisa_root_device *root,
if ((rc = create_packet(temp, packet_length)))
return rc;
- pr_debug("%p:%lu\n", temp, (end - temp));
+ pr_debug("%p:%td\n", temp, (end - temp));
temp += packet_length;
}
return -EIO;
}
- sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_data_attr);
- sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_image_type_attr);
- sysfs_create_bin_file(&rbu_device->dev.kobj,
+ rc = sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_data_attr);
+ if (rc)
+ goto out_devreg;
+ rc = sysfs_create_bin_file(&rbu_device->dev.kobj, &rbu_image_type_attr);
+ if (rc)
+ goto out_data;
+ rc = sysfs_create_bin_file(&rbu_device->dev.kobj,
&rbu_packet_size_attr);
+ if (rc)
+ goto out_imtype;
rbu_data.entry_created = 0;
- return rc;
+ return 0;
+out_imtype:
+ sysfs_remove_bin_file(&rbu_device->dev.kobj, &rbu_image_type_attr);
+out_data:
+ sysfs_remove_bin_file(&rbu_device->dev.kobj, &rbu_data_attr);
+out_devreg:
+ platform_device_unregister(rbu_device);
+ return rc;
}
static __exit void dcdrbu_exit(void)
kobject_set_name(&new_efivar->kobj, "%s", short_name);
kobj_set_kset_s(new_efivar, vars_subsys);
- kobject_register(&new_efivar->kobj);
+ i = kobject_register(&new_efivar->kobj);
+ if (i) {
+ kfree(short_name);
+ kfree(new_efivar);
+ return 1;
+ }
kfree(short_name);
short_name = NULL;
struct cdrom_info *cd = drive->driver_data;
ide_init_drive_cmd(rq);
- rq->cmd_type = REQ_TYPE_BLOCK_PC;
+ rq->cmd_type = REQ_TYPE_ATA_PC;
rq->rq_disk = cd->disk;
}
ide_error(drive, "request sense failure", stat);
return 1;
- } else if (blk_pc_request(rq)) {
+ } else if (blk_pc_request(rq) || rq->cmd_type == REQ_TYPE_ATA_PC) {
/* All other functions, except for READ. */
unsigned long flags;
}
info->last_block = block;
return action;
- } else if (rq->cmd_type == REQ_TYPE_SENSE) {
+ } else if (rq->cmd_type == REQ_TYPE_SENSE ||
+ rq->cmd_type == REQ_TYPE_ATA_PC) {
return cdrom_do_packet_command(drive);
} else if (blk_pc_request(rq)) {
return cdrom_do_block_pc(drive, rq);
task_ioreg_t *hobsptr = args.hobRegister;
int err = 0;
int tasksize = sizeof(struct ide_task_request_s);
- int taskin = 0;
- int taskout = 0;
+ unsigned int taskin = 0;
+ unsigned int taskout = 0;
u8 io_32bit = drive->io_32bit;
char __user *buf = (char __user *)arg;
return -EFAULT;
}
- taskout = (int) req_task->out_size;
- taskin = (int) req_task->in_size;
+ taskout = req_task->out_size;
+ taskin = req_task->in_size;
+
+ if (taskin > 65536 || taskout > 65536) {
+ err = -EINVAL;
+ goto abort;
+ }
if (taskout) {
int outtotal = tasksize;
if (dev->vendor == PCI_VENDOR_ID_JMICRON && PCI_FUNC(dev->devfn) != 1)
goto out;
- pci_read_config_word(dev, PCI_COMMAND, &command);
- if (!(command & PCI_COMMAND_IO)) {
- printk(KERN_INFO "Skipping disabled %s IDE controller.\n", d->name);
- goto out;
+ if (dev->vendor != PCI_VENDOR_ID_JMICRON) {
+ pci_read_config_word(dev, PCI_COMMAND, &command);
+ if (!(command & PCI_COMMAND_IO)) {
+ printk(KERN_INFO "Skipping disabled %s IDE controller.\n", d->name);
+ goto out;
+ }
}
ret = ide_setup_pci_device(dev, d);
out:
ioc4_unregister_submodule(&ioc4_ide_submodule);
}
-module_init(ioc4_ide_init);
+late_initcall(ioc4_ide_init); /* Call only after IDE init is done */
module_exit(ioc4_ide_exit);
MODULE_AUTHOR("Aniket Malatpure/Jeremy Higdon");
static DECLARE_WAIT_QUEUE_HEAD(hp_sdc_rtc_wait);
-static ssize_t hp_sdc_rtc_read(struct file *file, char *buf,
+static ssize_t hp_sdc_rtc_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos);
static int hp_sdc_rtc_ioctl(struct inode *inode, struct file *file,
return 0;
}
-static ssize_t hp_sdc_rtc_read(struct file *file, char *buf,
+static ssize_t hp_sdc_rtc_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos) {
ssize_t retval;
if (count < sizeof(unsigned long))
return -EINVAL;
- retval = put_user(68, (unsigned long *)buf);
+ retval = put_user(68, (unsigned long __user *)buf);
return retval;
}
if ((ret = hp_sdc_request_timer_irq(&hp_sdc_rtc_isr)))
return ret;
misc_register(&hp_sdc_rtc_dev);
- create_proc_read_entry ("driver/rtc", 0, 0,
+ create_proc_read_entry ("driver/rtc", 0, NULL,
hp_sdc_rtc_read_proc, NULL);
printk(KERN_INFO "HP i8042 SDC + MSM-58321 RTC support loaded "
* with this program; if not, write to the Free Software Foundation, Inc.,
* 59 Temple Place Suite 330, Boston, MA 02111-1307, USA.
*/
-#include <asm/io.h>
+#include <linux/io.h>
#include <linux/dmi.h>
#include <linux/init.h>
#include <linux/input.h>
}
#define FUNC(funct, funct_arg, zero_rc, neg_rc, pos_rc) \
-{ HILSE_FUNC, { func: &funct }, funct_arg, zero_rc, neg_rc, pos_rc },
+{ HILSE_FUNC, { .func = funct }, funct_arg, zero_rc, neg_rc, pos_rc },
#define OUT(pack) \
-{ HILSE_OUT, { packet: pack }, 0, HILSEN_NEXT, HILSEN_DOZE, 0 },
+{ HILSE_OUT, { .packet = pack }, 0, HILSEN_NEXT, HILSEN_DOZE, 0 },
#define CTS \
-{ HILSE_CTS, { packet: 0 }, 0, HILSEN_NEXT | HILSEN_SCHED | HILSEN_BREAK, HILSEN_DOZE, 0 },
+{ HILSE_CTS, { .packet = 0 }, 0, HILSEN_NEXT | HILSEN_SCHED | HILSEN_BREAK, HILSEN_DOZE, 0 },
#define EXPECT(comp, to, got, got_wrong, timed_out) \
-{ HILSE_EXPECT, { packet: comp }, to, got, got_wrong, timed_out },
+{ HILSE_EXPECT, { .packet = comp }, to, got, got_wrong, timed_out },
#define EXPECT_LAST(comp, to, got, got_wrong, timed_out) \
-{ HILSE_EXPECT_LAST, { packet: comp }, to, got, got_wrong, timed_out },
+{ HILSE_EXPECT_LAST, { .packet = comp }, to, got, got_wrong, timed_out },
#define EXPECT_DISC(comp, to, got, got_wrong, timed_out) \
-{ HILSE_EXPECT_DISC, { packet: comp }, to, got, got_wrong, timed_out },
+{ HILSE_EXPECT_DISC, { .packet = comp }, to, got, got_wrong, timed_out },
#define IN(to, got, got_error, timed_out) \
-{ HILSE_IN, { packet: 0 }, to, got, got_error, timed_out },
+{ HILSE_IN, { .packet = 0 }, to, got, got_error, timed_out },
#define OUT_DISC(pack) \
-{ HILSE_OUT_DISC, { packet: pack }, 0, 0, 0, 0 },
+{ HILSE_OUT_DISC, { .packet = pack }, 0, 0, 0, 0 },
#define OUT_LAST(pack) \
-{ HILSE_OUT_LAST, { packet: pack }, 0, 0, 0, 0 },
+{ HILSE_OUT_LAST, { .packet = pack }, 0, 0, 0, 0 },
struct hilse_node hil_mlc_se[HILSEN_END] = {
* in tasklet/bh context.
*/
if (curr->act.irqhook)
- curr->act.irqhook(0, 0, 0, 0);
+ curr->act.irqhook(0, NULL, 0, 0);
}
curr->actidx = curr->idx;
curr->idx++;
up(curr->act.semaphore);
}
else if (act & HP_SDC_ACT_CALLBACK) {
- curr->act.irqhook(0,0,0,0);
+ curr->act.irqhook(0,NULL,0,0);
}
if (curr->idx >= curr->endidx) { /* This transaction is over. */
if (act & HP_SDC_ACT_DEALLOC) kfree(curr);
}
for (p=buf, count=0; count < len; p++, count++) {
- put_user(*card->q931_read++, p);
+ if (put_user(*card->q931_read++, p))
+ return -EFAULT;
if (card->q931_read > card->q931_end)
card->q931_read = card->q931_buf;
}
count = cs->status_end - cs->status_read + 1;
if (count >= len)
count = len;
- copy_to_user(p, cs->status_read, count);
+ if (copy_to_user(p, cs->status_read, count))
+ return -EFAULT;
cs->status_read += count;
if (cs->status_read > cs->status_end)
cs->status_read = cs->status_buf;
cnt = HISAX_STATUS_BUFSIZE;
else
cnt = count;
- copy_to_user(p, cs->status_read, cnt);
+ if (copy_to_user(p, cs->status_read, cnt))
+ return -EFAULT;
p += cnt;
cs->status_read += cnt % HISAX_STATUS_BUFSIZE;
count -= cnt;
if (!card->irq_enabled)
return IRQ_NONE; /* other device interrupting or irq switched off */
- save_flags(flags);
- cli(); /* no further irqs allowed */
+ spin_lock_irqsave(&card->hysdn_lock, flags); /* no further irqs allowed */
if (!(bytein(card->iobase + PCI9050_INTR_REG) & PCI9050_INTR_REG_STAT1)) {
- restore_flags(flags); /* restore old state */
+ spin_unlock_irqrestore(&card->hysdn_lock, flags); /* restore old state */
return IRQ_NONE; /* no interrupt requested by E1 */
}
/* clear any pending ints on the board */
/* start kernel task immediately after leaving all interrupts */
if (!card->hw_lock)
schedule_work(&card->irq_queue);
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
return IRQ_HANDLED;
} /* ergo_interrupt */
dpr = card->dpram; /* point to DPRAM */
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->hysdn_lock, flags);
if (card->hw_lock) {
- restore_flags(flags); /* hardware currently unavailable */
+ spin_unlock_irqrestore(&card->hysdn_lock, flags); /* hardware currently unavailable */
return;
}
card->hw_lock = 1; /* we now lock the hardware */
card->hw_lock = 0; /* free hardware again */
} while (again); /* until nothing more to do */
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
} /* ergo_irq_bh */
#ifdef CONFIG_HYSDN_CAPI
hycapi_capi_stop(card);
#endif /* CONFIG_HYSDN_CAPI */
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->hysdn_lock, flags);
val = bytein(card->iobase + PCI9050_INTR_REG); /* get actual value */
val &= ~(PCI9050_INTR_REG_ENPCI | PCI9050_INTR_REG_EN1); /* mask irq */
byteout(card->iobase + PCI9050_INTR_REG, val);
card->state = CARD_STATE_UNUSED;
card->err_log_state = ERRLOG_STATE_OFF; /* currently no log active */
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
} /* ergo_stopcard */
/**************************************************************************/
card->err_log_state = ERRLOG_STATE_OFF; /* must be off */
return;
}
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->hysdn_lock, flags);
if (((card->err_log_state == ERRLOG_STATE_OFF) && !on) ||
((card->err_log_state == ERRLOG_STATE_ON) && on)) {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
return; /* nothing to do */
}
if (on)
else
card->err_log_state = ERRLOG_STATE_STOP; /* request stop */
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
schedule_work(&card->irq_queue);
} /* ergo_set_errlog_state */
if (card->debug_flags & LOG_POF_RECORD)
hysdn_addlog(card, "ERGO: pof boot success");
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->hysdn_lock, flags);
card->state = CARD_STATE_RUN; /* now card is running */
/* enable the cards interrupt */
dpr->ToHyInt = 1;
dpr->ToPcInt = 1; /* interrupt to E1 for all cards */
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
if ((hynet_enable & (1 << card->myid))
&& (i = hysdn_net_create(card)))
{
card->waitpofready = ergo_waitpofready;
card->set_errlog_state = ergo_set_errlog_state;
INIT_WORK(&card->irq_queue, (void *) (void *) ergo_irq_bh, card);
+ card->hysdn_lock = SPIN_LOCK_UNLOCKED;
return (0);
} /* ergo_inithardware */
/* init and deinit stopcard for booting, too */
void (*stopcard) (struct HYSDN_CARD *);
void (*releasehardware) (struct HYSDN_CARD *);
+
+ spinlock_t hysdn_lock;
#ifdef CONFIG_HYSDN_CAPI
struct hycapictrl_info {
char cardname[32];
strcpy(ib->log_start, cp); /* set output string */
ib->next = NULL;
ib->proc_ctrl = pd; /* point to own control structure */
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->hysdn_lock, flags);
ib->usage_cnt = pd->if_used;
if (!pd->log_head)
pd->log_head = ib; /* new head */
pd->log_tail->next = ib; /* follows existing messages */
pd->log_tail = ib; /* new tail */
i = pd->del_lock++; /* get lock state */
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
/* delete old entrys */
if (!i)
} else if ((filep->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) {
/* read access -> log/debug read */
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->hysdn_lock, flags);
pd->if_used++;
if (pd->log_head)
filep->private_data = &pd->log_tail->next;
else
filep->private_data = &pd->log_head;
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
} else { /* simultaneous read/write access forbidden ! */
unlock_kernel();
return (-EPERM); /* no permission this time */
hysdn_card *card;
int retval = 0;
unsigned long flags;
-
+ spinlock_t hysdn_lock = SPIN_LOCK_UNLOCKED;
lock_kernel();
if ((filep->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_WRITE) {
/* read access -> log/debug read, mark one further file as closed */
pd = NULL;
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&hysdn_lock, flags);
inf = *((struct log_data **) filep->private_data); /* get first log entry */
if (inf)
pd = (struct procdata *) inf->proc_ctrl; /* still entries there */
inf->usage_cnt--; /* decrement usage count for buffers */
inf = inf->next;
}
- restore_flags(flags);
+ spin_unlock_irqrestore(&hysdn_lock, flags);
if (pd)
if (pd->if_used <= 0) /* delete buffers if last file closed */
if (card->debug_flags & LOG_SCHED_ASYN)
hysdn_addlog(card, "async tx-cfg chan=%d len=%d", chan, strlen(line) + 1);
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->hysdn_lock, flags);
while (card->async_busy) {
sti();
msleep_interruptible(20); /* Timeout 20ms */
if (!--cnt) {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
return (-ERR_ASYNC_TIME); /* timed out */
}
cli();
msleep_interruptible(20); /* Timeout 20ms */
if (!--cnt) {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
return (-ERR_ASYNC_TIME); /* timed out */
}
cli();
} /* wait for buffer to become free again */
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->hysdn_lock, flags);
if (card->debug_flags & LOG_SCHED_ASYN)
hysdn_addlog(card, "async tx-cfg data send");
if (dev->drv[drvidx]->interface->readstat) {
if (count > dev->drv[drvidx]->stavail)
count = dev->drv[drvidx]->stavail;
- len = dev->drv[drvidx]->interface->
- readstat(buf, count, drvidx,
- isdn_minor2chan(minor));
+ len = dev->drv[drvidx]->interface->readstat(buf, count,
+ drvidx, isdn_minor2chan(minor));
+ if (len < 0) {
+ retval = len;
+ goto out;
+ }
} else {
len = 0;
}
for (p = buf, count = 0; count < len; p++, count++) {
if (card->msg_buf_read == card->msg_buf_write)
return count;
- put_user(*card->msg_buf_read++, p);
+ if (put_user(*card->msg_buf_read++, p))
+ return -EFAULT;
if (card->msg_buf_read > card->msg_buf_end)
card->msg_buf_read = card->msg_buf;
}
isdnloop_bchan_send(card, 1);
if (card->flags & (ISDNLOOP_FLAGS_B1ACTIVE | ISDNLOOP_FLAGS_B2ACTIVE)) {
/* schedule b-channel polling again */
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
card->rb_timer.expires = jiffies + ISDNLOOP_TIMER_BCREAD;
add_timer(&card->rb_timer);
card->flags |= ISDNLOOP_FLAGS_RBTIMER;
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
} else
card->flags &= ~ISDNLOOP_FLAGS_RBTIMER;
}
{
ulong flags;
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
*card->msg_buf_write++ = (c == 0xff) ? '\n' : c;
if (card->msg_buf_write == card->msg_buf_read) {
if (++card->msg_buf_read > card->msg_buf_end)
}
if (card->msg_buf_write > card->msg_buf_end)
card->msg_buf_write = card->msg_buf;
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
}
/*
if (!(card->flags & ISDNLOOP_FLAGS_RBTIMER)) {
/* schedule b-channel polling */
card->flags |= ISDNLOOP_FLAGS_RBTIMER;
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
del_timer(&card->rb_timer);
card->rb_timer.function = isdnloop_pollbchan;
card->rb_timer.data = (unsigned long) card;
card->rb_timer.expires = jiffies + ISDNLOOP_TIMER_BCREAD;
add_timer(&card->rb_timer);
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
}
/* schedule again */
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
card->st_timer.expires = jiffies + ISDNLOOP_TIMER_DCREAD;
add_timer(&card->st_timer);
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
}
/*
return 0;
if (card->sndcount[channel] > ISDNLOOP_MAX_SQUEUE)
return 0;
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
nskb = dev_alloc_skb(skb->len);
if (nskb) {
memcpy(skb_put(nskb, len), skb->data, len);
} else
len = 0;
card->sndcount[channel] += len;
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
}
return len;
}
for (p = buf, count = 0; count < len; p++, count++) {
if (card->msg_buf_read == card->msg_buf_write)
return count;
- put_user(*card->msg_buf_read++, p);
+ if (put_user(*card->msg_buf_read++, p))
+ return -EFAULT;
if (card->msg_buf_read > card->msg_buf_end)
card->msg_buf_read = card->msg_buf;
}
unsigned long flags;
char buf[60];
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
if (card->rcard) {
isdnloop_fake(card->rcard[ch], "DDIS_I", card->rch[ch] + 1);
card->rcard[ch]->rcard[card->rch[ch]] = NULL;
/* No user responding */
sprintf(buf, "CAU%s", isdnloop_unicause(card, 1, 3));
isdnloop_fake(card, buf, ch + 1);
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
}
/*
{
unsigned long flags;
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
init_timer(&card->c_timer[ch]);
card->c_timer[ch].expires = jiffies + ISDNLOOP_TIMER_ALERTWAIT;
if (ch)
card->c_timer[ch].function = isdnloop_atimeout0;
card->c_timer[ch].data = (unsigned long) card;
add_timer(&card->c_timer[ch]);
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
}
/*
{
unsigned long flags;
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
del_timer(&card->c_timer[ch]);
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
}
static u_char si2bit[] =
}
}
if (num_match) {
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
/* channel idle? */
if (!(cc->rcard[ch])) {
/* Check SI */
if (!(si2bit[cmd->parm.setup.si1] & cc->sil[ch])) {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return 3;
}
/* ch is idle, si and number matches */
cc->rch[ch] = lch;
card->rcard[lch] = cc;
card->rch[lch] = ch;
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return 0;
} else {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
/* num matches, but busy */
if (ch == 1)
return 1;
unsigned long flags;
isdn_ctrl cmd;
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
if (card->flags & ISDNLOOP_FLAGS_RUNNING) {
card->flags &= ~ISDNLOOP_FLAGS_RUNNING;
del_timer(&card->st_timer);
cmd.driver = card->myid;
card->interface.statcallb(&cmd);
}
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
}
/*
return -EBUSY;
if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
return -EFAULT;
- save_flags(flags);
- cli();
+ spin_lock_irqsave(&card->isdnloop_lock, flags);
switch (sdef.ptype) {
case ISDN_PTYPE_EURO:
if (isdnloop_fake(card, "DRV1.23EC-Q.931-CAPI-CNS-BASIS-20.02.96",
-1)) {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return -ENOMEM;
}
card->sil[0] = card->sil[1] = 4;
if (isdnloop_fake(card, "TEI OK", 0)) {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return -ENOMEM;
}
for (i = 0; i < 3; i++)
case ISDN_PTYPE_1TR6:
if (isdnloop_fake(card, "DRV1.04TC-1TR6-CAPI-CNS-BASIS-29.11.95",
-1)) {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return -ENOMEM;
}
card->sil[0] = card->sil[1] = 4;
if (isdnloop_fake(card, "TEI OK", 0)) {
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return -ENOMEM;
}
strcpy(card->s0num[0], sdef.num[0]);
card->s0num[2][0] = '\0';
break;
default:
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
printk(KERN_WARNING "isdnloop: Illegal D-channel protocol %d\n",
sdef.ptype);
return -EINVAL;
card->st_timer.data = (unsigned long) card;
add_timer(&card->st_timer);
card->flags |= ISDNLOOP_FLAGS_RUNNING;
- restore_flags(flags);
+ spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return 0;
}
skb_queue_head_init(&card->bqueue[i]);
}
skb_queue_head_init(&card->dqueue);
+ card->isdnloop_lock = SPIN_LOCK_UNLOCKED;
card->next = cards;
cards = card;
if (!register_isdn(&card->interface)) {
struct sk_buff_head
bqueue[ISDNLOOP_BCH]; /* B-Channel queues */
struct sk_buff_head dqueue; /* D-Channel queue */
+ spinlock_t isdnloop_lock;
} isdnloop_card;
/*
if (stat_st < stat_end)
{
- copy_to_user(buf, statbuf + stat_st, len);
+ if (copy_to_user(buf, statbuf + stat_st, len))
+ return -EFAULT;
stat_st += len;
}
else
{
if (len > STATBUF_LEN - stat_st)
{
- copy_to_user(buf, statbuf + stat_st,
- STATBUF_LEN - stat_st);
- copy_to_user(buf, statbuf,
- len - (STATBUF_LEN - stat_st));
+ if (copy_to_user(buf, statbuf + stat_st,
+ STATBUF_LEN - stat_st))
+ return -EFAULT;
+ if (copy_to_user(buf, statbuf,
+ len - (STATBUF_LEN - stat_st)))
+ return -EFAULT;
stat_st = len - (STATBUF_LEN - stat_st);
}
else
{
- copy_to_user(buf, statbuf + stat_st, len);
+ if (copy_to_user(buf, statbuf + stat_st, len))
+ return -EFAULT;
stat_st += len;
dev->read_queue = frame->next;
spin_unlock_irqrestore(&dev->lock, flags);
+ msg = 0;
SET_MSG_CPU(msg, 0);
SET_MSG_PROC(msg, 0);
SET_MSG_CMD(msg, frame->skb->data[2]);
* Confirm the I/O Address with a test
*/
if(io[b] == 0) {
- pr_debug("I/O Address 0x%x is in use.\n");
+ pr_debug("I/O Address invalid.\n");
continue;
}
outb(0x18, io[b] + 0x400 * EXP_PAGE0);
if(inb(io[b] + 0x400 * EXP_PAGE0) != 0x18) {
- pr_debug("I/O Base 0x%x fails test\n");
+ pr_debug("I/O Base 0x%x fails test\n",
+ io[b] + 0x400 * EXP_PAGE0);
continue;
}
}
outb(0xFF, io[b] + RESET_OFFSET);
msleep_interruptible(10000);
}
- pr_debug("RAM Base for board %d is 0x%x, %s probe\n", b, ram[b],
- ram[b] == 0 ? "will" : "won't");
+ pr_debug("RAM Base for board %d is 0x%lx, %s probe\n", b,
+ ram[b], ram[b] == 0 ? "will" : "won't");
if(ram[b]) {
/*
* board model
*/
if(request_region(ram[b], SRAM_PAGESIZE, "sc test")) {
- pr_debug("request_region for RAM base 0x%x succeeded\n", ram[b]);
+ pr_debug("request_region for RAM base 0x%lx succeeded\n", ram[b]);
model = identify_board(ram[b], io[b]);
release_region(ram[b], SRAM_PAGESIZE);
}
* Nope, there was no place in RAM for the
* board, or it couldn't be identified
*/
- pr_debug("Failed to find an adapter at 0x%x\n", ram[b]);
+ pr_debug("Failed to find an adapter at 0x%lx\n", ram[b]);
continue;
}
HWConfig_pl hwci;
int x;
- pr_debug("Attempting to identify adapter @ 0x%x io 0x%x\n",
+ pr_debug("Attempting to identify adapter @ 0x%lx io 0x%x\n",
rambase, iobase);
/*
outb(PRI_BASEPG_VAL, pgport);
msleep_interruptible(1000);
sig = readl(rambase + SIG_OFFSET);
- pr_debug("Looking for a signature, got 0x%x\n", sig);
+ pr_debug("Looking for a signature, got 0x%lx\n", sig);
if(sig == SIGNATURE)
return PRI_BOARD;
outb(BRI_BASEPG_VAL, pgport);
msleep_interruptible(1000);
sig = readl(rambase + SIG_OFFSET);
- pr_debug("Looking for a signature, got 0x%x\n", sig);
+ pr_debug("Looking for a signature, got 0x%lx\n", sig);
if(sig == SIGNATURE)
return BRI_BOARD;
* Try to spot a card
*/
sig = readl(rambase + SIG_OFFSET);
- pr_debug("Looking for a signature, got 0x%x\n", sig);
+ pr_debug("Looking for a signature, got 0x%lx\n", sig);
if(sig != SIGNATURE)
return -1;
memcpy_fromio(&rcvmsg, &(dpm->rsp_queue[dpm->rsp_tail]), MSG_LEN);
pr_debug("Got HWConfig response, status = 0x%x\n", rcvmsg.rsp_status);
memcpy(&hwci, &(rcvmsg.msg_data.HWCresponse), sizeof(HWConfig_pl));
- pr_debug("Hardware Config: Interface: %s, RAM Size: %d, Serial: %s\n"
+ pr_debug("Hardware Config: Interface: %s, RAM Size: %ld, Serial: %s\n"
" Part: %s, Rev: %s\n",
hwci.st_u_sense ? "S/T" : "U", hwci.ram_size,
hwci.serial_no, hwci.part_no, hwci.rev_no);
return -ENODEV;
}
- pr_debug("%s: sndpkt: frst = 0x%x nxt = %d f = %d n = %d\n",
+ pr_debug("%s: sndpkt: frst = 0x%lx nxt = %d f = %d n = %d\n",
sc_adapter[card]->devicename,
sc_adapter[card]->channel[channel].first_sendbuf,
sc_adapter[card]->channel[channel].next_sendbuf,
ReqLnkWrite.buff_offset = sc_adapter[card]->channel[channel].next_sendbuf *
BUFFER_SIZE + sc_adapter[card]->channel[channel].first_sendbuf;
ReqLnkWrite.msg_len = data->len; /* sk_buff size */
- pr_debug("%s: writing %d bytes to buffer offset 0x%x\n",
+ pr_debug("%s: writing %d bytes to buffer offset 0x%lx\n",
sc_adapter[card]->devicename,
ReqLnkWrite.msg_len, ReqLnkWrite.buff_offset);
memcpy_toshmem(card, (char *)ReqLnkWrite.buff_offset, data->data, ReqLnkWrite.msg_len);
/*
* sendmessage
*/
- pr_debug("%s: sndpkt size=%d, buf_offset=0x%x buf_indx=%d\n",
+ pr_debug("%s: sndpkt size=%d, buf_offset=0x%lx buf_indx=%d\n",
sc_adapter[card]->devicename,
ReqLnkWrite.msg_len, ReqLnkWrite.buff_offset,
sc_adapter[card]->channel[channel].next_sendbuf);
return;
}
skb_put(skb, rcvmsg->msg_data.response.msg_len);
- pr_debug("%s: getting data from offset: 0x%x\n",
+ pr_debug("%s: getting data from offset: 0x%lx\n",
sc_adapter[card]->devicename,
rcvmsg->msg_data.response.buff_offset);
memcpy_fromshmem(card,
/* memset_shmem(card, rcvmsg->msg_data.response.buff_offset, 0, BUFFER_SIZE); */
newll.buff_offset = rcvmsg->msg_data.response.buff_offset;
newll.msg_len = BUFFER_SIZE;
- pr_debug("%s: recycled buffer at offset 0x%x size %d\n",
+ pr_debug("%s: recycled buffer at offset 0x%lx size %d\n",
sc_adapter[card]->devicename,
newll.buff_offset, newll.msg_len);
sendmessage(card, CEPID, ceReqTypeLnk, ceReqClass1, ceReqLnkRead,
sc_adapter[card]->channel[c-1].num_sendbufs = nBuffers / 2;
sc_adapter[card]->channel[c-1].free_sendbufs = nBuffers / 2;
sc_adapter[card]->channel[c-1].next_sendbuf = 0;
- pr_debug("%s: send buffer setup complete: first=0x%x n=%d f=%d, nxt=%d\n",
+ pr_debug("%s: send buffer setup complete: first=0x%lx n=%d f=%d, nxt=%d\n",
sc_adapter[card]->devicename,
sc_adapter[card]->channel[c-1].first_sendbuf,
sc_adapter[card]->channel[c-1].num_sendbufs,
((sc_adapter[card]->channel[c-1].first_sendbuf +
(nBuffers / 2) * buffer_size) + (buffer_size * i));
RcvBuffOffset.msg_len = buffer_size;
- pr_debug("%s: adding RcvBuffer #%d offset=0x%x sz=%d bufsz:%d\n",
+ pr_debug("%s: adding RcvBuffer #%d offset=0x%lx sz=%d bufsz:%d\n",
sc_adapter[card]->devicename,
i + 1, RcvBuffOffset.buff_offset,
RcvBuffOffset.msg_len,buffer_size);
spin_unlock_irqrestore(&sc_adapter[card]->lock, flags);
pr_debug("%s: set page to %#x\n",sc_adapter[card]->devicename,
((sc_adapter[card]->shmem_magic + ch * SRAM_PAGESIZE)>>14)|0x80);
- pr_debug("%s: copying %d bytes from %#x to %#x\n",
+ pr_debug("%s: copying %d bytes from %#lx to %#lx\n",
sc_adapter[card]->devicename, n,
(unsigned long) src,
sc_adapter[card]->rambase + ((unsigned long) dest %0x4000));
*/
int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
{
+ int rc;
+
led_cdev->class_dev = class_device_create(leds_class, NULL, 0,
parent, "%s", led_cdev->name);
if (unlikely(IS_ERR(led_cdev->class_dev)))
class_set_devdata(led_cdev->class_dev, led_cdev);
/* register the attributes */
- class_device_create_file(led_cdev->class_dev,
- &class_device_attr_brightness);
+ rc = class_device_create_file(led_cdev->class_dev,
+ &class_device_attr_brightness);
+ if (rc)
+ goto err_out;
/* add to the list of leds */
write_lock(&leds_list_lock);
#ifdef CONFIG_LEDS_TRIGGERS
rwlock_init(&led_cdev->trigger_lock);
- led_trigger_set_default(led_cdev);
+ rc = class_device_create_file(led_cdev->class_dev,
+ &class_device_attr_trigger);
+ if (rc)
+ goto err_out_led_list;
- class_device_create_file(led_cdev->class_dev,
- &class_device_attr_trigger);
+ led_trigger_set_default(led_cdev);
#endif
printk(KERN_INFO "Registered led device: %s\n",
led_cdev->class_dev->class_id);
return 0;
+
+#ifdef CONFIG_LEDS_TRIGGERS
+err_out_led_list:
+ class_device_remove_file(led_cdev->class_dev,
+ &class_device_attr_brightness);
+ list_del(&led_cdev->node);
+#endif
+err_out:
+ class_device_unregister(led_cdev->class_dev);
+ return rc;
}
EXPORT_SYMBOL_GPL(led_classdev_register);
static void timer_trig_activate(struct led_classdev *led_cdev)
{
struct timer_trig_data *timer_data;
+ int rc;
timer_data = kzalloc(sizeof(struct timer_trig_data), GFP_KERNEL);
if (!timer_data)
timer_data->timer.function = led_timer_function;
timer_data->timer.data = (unsigned long) led_cdev;
- class_device_create_file(led_cdev->class_dev,
+ rc = class_device_create_file(led_cdev->class_dev,
&class_device_attr_delay_on);
- class_device_create_file(led_cdev->class_dev,
+ if (rc) goto err_out;
+ rc = class_device_create_file(led_cdev->class_dev,
&class_device_attr_delay_off);
+ if (rc) goto err_out_delayon;
+
+ return;
+
+err_out_delayon:
+ class_device_remove_file(led_cdev->class_dev,
+ &class_device_attr_delay_on);
+err_out:
+ led_cdev->trigger_data = NULL;
+ kfree(timer_data);
}
static void timer_trig_deactivate(struct led_classdev *led_cdev)
int __init mca_register_device(int bus, struct mca_device *mca_dev)
{
struct mca_bus *mca_bus = mca_root_busses[bus];
+ int rc;
mca_dev->dev.parent = &mca_bus->dev;
mca_dev->dev.bus = &mca_bus_type;
mca_dev->dev.dma_mask = &mca_dev->dma_mask;
mca_dev->dev.coherent_dma_mask = mca_dev->dma_mask;
- if (device_register(&mca_dev->dev))
- return 0;
+ rc = device_register(&mca_dev->dev);
+ if (rc)
+ goto err_out;
- device_create_file(&mca_dev->dev, &dev_attr_id);
- device_create_file(&mca_dev->dev, &dev_attr_pos);
+ rc = device_create_file(&mca_dev->dev, &dev_attr_id);
+ if (rc) goto err_out_devreg;
+ rc = device_create_file(&mca_dev->dev, &dev_attr_pos);
+ if (rc) goto err_out_id;
return 1;
+
+err_out_id:
+ device_remove_file(&mca_dev->dev, &dev_attr_id);
+err_out_devreg:
+ device_unregister(&mca_dev->dev);
+err_out:
+ return 0;
}
/* */
return NULL;
}
- mca_bus = kmalloc(sizeof(struct mca_bus), GFP_KERNEL);
+ mca_bus = kzalloc(sizeof(struct mca_bus), GFP_KERNEL);
if (!mca_bus)
return NULL;
- memset(mca_bus, 0, sizeof(struct mca_bus));
+
sprintf(mca_bus->dev.bus_id,"mca%d",bus);
sprintf(mca_bus->name,"Host %s MCA Bridge", bus ? "Secondary" : "Primary");
- device_register(&mca_bus->dev);
+ if (device_register(&mca_bus->dev)) {
+ kfree(mca_bus);
+ return NULL;
+ }
mca_root_busses[bus] = mca_bus;
int err;
sector_t start;
- BUG_ON(sizeof(bitmap_super_t) != 256);
+ BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */
return 0;
}
static struct file_operations md_seq_fops = {
+ .owner = THIS_MODULE,
.open = md_seq_open,
.read = seq_read,
.llseek = seq_lseek,
case BTTV_BOARD_TWINHAN_DST:
/* DST is not a frontend driver !!! */
state = (struct dst_state *) kmalloc(sizeof (struct dst_state), GFP_KERNEL);
+ if (!state) {
+ printk("dvb_bt8xx: No memory\n");
+ break;
+ }
/* Setup the Card */
state->config = &dst_config;
state->i2c = card->i2c_adapter;
allow the card drivers to only load the frontend modules
they require. This saves several KBytes of memory.
- Note: You will need moudule-init-tools v3.2 or later for this feature.
+ Note: You will need module-init-tools v3.2 or later for this feature.
If unsure say Y.
// Config Adjacent channels Perf -cal22
static struct dibx000_agc_config dib3000p_mt2060_agc_config = {
.band_caps = BAND_VHF | BAND_UHF,
- .setup = (0 << 15) | (0 << 14) | (1 << 13) | (1 << 12) | (29 << 0),
+ .setup = (1 << 8) | (5 << 5) | (1 << 4) | (1 << 3) | (0 << 2) | (2 << 0),
.agc1_max = 48497,
.agc1_min = 23593,
.ln_adc_level = 0x1cc7,
.output_mpeg2_in_188_bytes = 1,
+
+ .agc_command1 = 1,
+ .agc_command2 = 1,
};
static struct dibx000_agc_config dib3000p_panasonic_agc_config = {
- .setup = (0 << 15) | (0 << 14) | (1 << 13) | (1 << 12) | (29 << 0),
+ .band_caps = BAND_VHF | BAND_UHF,
+ .setup = (1 << 8) | (5 << 5) | (1 << 4) | (1 << 3) | (0 << 2) | (2 << 0),
.agc1_max = 56361,
.agc1_min = 22282,
.ln_adc_level = 0x1cc7,
.output_mpeg2_in_188_bytes = 1,
+
+ .agc_command1 = 1,
+ .agc_command2 = 1,
};
int dibusb_dib3000mc_frontend_attach(struct dvb_usb_adapter *adap)
struct dibusb_state {
struct dib_fe_xfer_ops ops;
int mt2060_present;
+};
+struct dibusb_device_state {
/* for RC5 remote control */
int old_toggle;
int last_repeat_count;
u8 key[5],cmd[2] = { DIBUSB_REQ_POLL_REMOTE, 0x35 }, data,toggle,custom;
u16 raw;
int i;
- struct dibusb_state *st = d->priv;
+ struct dibusb_device_state *st = d->priv;
dvb_usb_generic_rw(d,cmd,2,key,5,0);
.size_of_priv = sizeof(struct dibusb_state),
}
},
+ .size_of_priv = sizeof(struct dibusb_device_state),
.power_ctrl = dibusb2_0_power_ctrl,
.read_mac_address = nova_t_read_mac_address,
/* agc */
dib3000mc_write_word(state, 36, state->cfg->max_time);
- dib3000mc_write_word(state, 37, agc->setup);
+ dib3000mc_write_word(state, 37, (state->cfg->agc_command1 << 13) | (state->cfg->agc_command2 << 12) | (0x1d << 0));
dib3000mc_write_word(state, 38, state->cfg->pwm3_value);
dib3000mc_write_word(state, 39, state->cfg->ln_adc_level);
u16 max_time;
u16 ln_adc_level;
+ u8 agc_command1 :1;
+ u8 agc_command2 :1;
+
u8 mobile_mode;
u8 output_mpeg2_in_188_bytes;
u8 invert;
};
+#if defined(CONFIG_DVB_TDA10086) || defined(CONFIG_DVB_TDA10086_MODULE)
extern struct dvb_frontend* tda10086_attach(const struct tda10086_config* config,
struct i2c_adapter* i2c);
+#else
+static inline struct dvb_frontend* tda10086_attach(const struct tda10086_config* config,
+ struct i2c_adapter* i2c)
+{
+ printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __FUNCTION__);
+ return NULL;
+}
+#endif // CONFIG_DVB_TDA10086
#endif // TDA10086_H
* @param has_loopthrough Set to 1 if the card has a loopthrough RF connector.
* @return FE pointer on success, NULL on failure.
*/
-extern struct dvb_frontend *tda826x_attach(struct dvb_frontend *fe, int addr, struct i2c_adapter *i2c, int has_loopthrough);
-
-#endif
+#if defined(CONFIG_DVB_TDA826X) || defined(CONFIG_DVB_TDA826X_MODULE)
+extern struct dvb_frontend* tda826x_attach(struct dvb_frontend *fe, int addr,
+ struct i2c_adapter *i2c,
+ int has_loopthrough);
+#else
+static inline struct dvb_frontend* tda826x_attach(struct dvb_frontend *fe,
+ int addr,
+ struct i2c_adapter *i2c,
+ int has_loopthrough)
+{
+ printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __FUNCTION__);
+ return NULL;
+}
+#endif // CONFIG_DVB_TDA826X
+
+#endif // __DVB_TDA826X_H__
menu "V4L USB devices"
depends on USB && VIDEO_DEV
+source "drivers/media/video/pvrusb2/Kconfig"
+
source "drivers/media/video/em28xx/Kconfig"
source "drivers/media/video/usbvideo/Kconfig"
0, 0, V4L2_SLICED_VPS, 0, 0, /* 9 */
0, 0, 0, 0
};
+ int is_pal = !(cx25840_get_v4lstd(client) & V4L2_STD_525_60);
int i;
fmt = arg;
if ((cx25840_read(client, 0x404) & 0x10) == 0)
break;
- for (i = 7; i <= 23; i++) {
- u8 v = cx25840_read(client, 0x424 + i - 7);
+ if (is_pal) {
+ for (i = 7; i <= 23; i++) {
+ u8 v = cx25840_read(client, 0x424 + i - 7);
+
+ svbi->service_lines[0][i] = lcr2vbi[v >> 4];
+ svbi->service_lines[1][i] = lcr2vbi[v & 0xf];
+ svbi->service_set |=
+ svbi->service_lines[0][i] | svbi->service_lines[1][i];
+ }
+ }
+ else {
+ for (i = 10; i <= 21; i++) {
+ u8 v = cx25840_read(client, 0x424 + i - 10);
- svbi->service_lines[0][i] = lcr2vbi[v >> 4];
- svbi->service_lines[1][i] = lcr2vbi[v & 0xf];
- svbi->service_set |=
- svbi->service_lines[0][i] | svbi->service_lines[1][i];
+ svbi->service_lines[0][i] = lcr2vbi[v >> 4];
+ svbi->service_lines[1][i] = lcr2vbi[v & 0xf];
+ svbi->service_set |=
+ svbi->service_lines[0][i] | svbi->service_lines[1][i];
+ }
}
break;
}
.vmux = 2,
.gpio0 = 0x84bf,
}},
+ .mpeg = CX88_MPEG_DVB,
},
[CX88_BOARD_NORWOOD_MICRO] = {
.name = "Norwood Micro TV Tuner",
.subvendor = 0x0070,
.subdevice = 0x9000,
.card = CX88_BOARD_HAUPPAUGE_DVB_T1,
+ },{
+ .subvendor = 0x0070,
+ .subdevice = 0x1400,
+ .card = CX88_BOARD_HAUPPAUGE_HVR3000,
+ },{
+ .subvendor = 0x0070,
+ .subdevice = 0x1401,
+ .card = CX88_BOARD_HAUPPAUGE_HVR3000,
+ },{
+ .subvendor = 0x0070,
+ .subdevice = 0x1402,
+ .card = CX88_BOARD_HAUPPAUGE_HVR3000,
},
};
const unsigned int cx88_idcount = ARRAY_SIZE(cx88_subids);
/* Make sure we support the board model */
switch (tv.model)
{
+ case 14009: /* WinTV-HVR3000 (Retail, IR, b/panel video, 3.5mm audio in) */
+ case 14019: /* WinTV-HVR3000 (Retail, IR Blaster, b/panel video, 3.5mm audio in) */
+ case 14029: /* WinTV-HVR3000 (Retail, IR, b/panel video, 3.5mm audio in - 880 bridge) */
+ case 14109: /* WinTV-HVR3000 (Retail, IR, b/panel video, 3.5mm audio in - low profile) */
+ case 14129: /* WinTV-HVR3000 (Retail, IR, b/panel video, 3.5mm audio in - 880 bridge - LP) */
+ case 14559: /* WinTV-HVR3000 (OEM, no IR, b/panel video, 3.5mm audio in) */
case 14569: /* WinTV-HVR3000 (OEM, no IR, no back panel video) */
+ case 14659: /* WinTV-HVR3000 (OEM, no IR, b/panel video, RCA audio in - Low profile) */
+ case 14669: /* WinTV-HVR3000 (OEM, no IR, no b/panel video - Low profile) */
case 28552: /* WinTV-PVR 'Roslyn' (No IR) */
case 34519: /* WinTV-PCI-FM */
case 90002: /* Nova-T-PCI (9002) */
.demod_address = 0x43,
.output_mode = CX22702_SERIAL_OUTPUT,
};
+
static struct cx22702_config hauppauge_hvr1100_config = {
.demod_address = 0x63,
.output_mode = CX22702_SERIAL_OUTPUT,
};
+
static struct cx22702_config hauppauge_hvr1300_config = {
.demod_address = 0x63,
.output_mode = CX22702_SERIAL_OUTPUT,
};
+static struct cx22702_config hauppauge_hvr3000_config = {
+ .demod_address = 0x63,
+ .output_mode = CX22702_SERIAL_OUTPUT,
+};
+
static int or51132_set_ts_param(struct dvb_frontend* fe,
int is_punctured)
{
&dvb_pll_fmd1216me);
}
break;
+ case CX88_BOARD_HAUPPAUGE_HVR3000:
+ dev->dvb.frontend = dvb_attach(cx22702_attach,
+ &hauppauge_hvr3000_config,
+ &dev->core->i2c_adap);
+ if (dev->dvb.frontend != NULL) {
+ dvb_attach(dvb_pll_attach, dev->dvb.frontend, 0x61,
+ &dev->core->i2c_adap,
+ &dvb_pll_fmd1216me);
+ }
+ break;
case CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_PLUS:
dev->dvb.frontend = dvb_attach(mt352_attach,
&dvico_fusionhdtv,
case CX88_BOARD_HAUPPAUGE_NOVASPLUS_S1:
case CX88_BOARD_HAUPPAUGE_HVR1100:
case CX88_BOARD_HAUPPAUGE_HVR1300:
+ case CX88_BOARD_HAUPPAUGE_HVR3000:
ir_codes = ir_codes_hauppauge_new;
ir_type = IR_TYPE_RC5;
ir->sampling = 1;
case CX88_BOARD_HAUPPAUGE_NOVASPLUS_S1:
case CX88_BOARD_HAUPPAUGE_HVR1100:
case CX88_BOARD_HAUPPAUGE_HVR1300:
+ case CX88_BOARD_HAUPPAUGE_HVR3000:
ircode = ir_decode_biphase(ir->samples, ir->scount, 5, 7);
ir_dprintk("biphase decoded: %x\n", ircode);
if ((ircode & 0xfffff000) != 0x3000)
et61x251_show_i2c_val, et61x251_store_i2c_val);
-static void et61x251_create_sysfs(struct et61x251_device* cam)
+static int et61x251_create_sysfs(struct et61x251_device* cam)
{
struct video_device *v4ldev = cam->v4ldev;
+ int rc;
- video_device_create_file(v4ldev, &class_device_attr_reg);
- video_device_create_file(v4ldev, &class_device_attr_val);
+ rc = video_device_create_file(v4ldev, &class_device_attr_reg);
+ if (rc) goto err;
+ rc = video_device_create_file(v4ldev, &class_device_attr_val);
+ if (rc) goto err_reg;
if (cam->sensor.sysfs_ops) {
- video_device_create_file(v4ldev, &class_device_attr_i2c_reg);
- video_device_create_file(v4ldev, &class_device_attr_i2c_val);
+ rc = video_device_create_file(v4ldev, &class_device_attr_i2c_reg);
+ if (rc) goto err_val;
+ rc = video_device_create_file(v4ldev, &class_device_attr_i2c_val);
+ if (rc) goto err_i2c_reg;
}
+
+ return 0;
+
+err_i2c_reg:
+ video_device_remove_file(v4ldev, &class_device_attr_i2c_reg);
+err_val:
+ video_device_remove_file(v4ldev, &class_device_attr_val);
+err_reg:
+ video_device_remove_file(v4ldev, &class_device_attr_reg);
+err:
+ return rc;
}
#endif /* CONFIG_VIDEO_ADV_DEBUG */
dev_nr = (dev_nr < ET61X251_MAX_DEVICES-1) ? dev_nr+1 : 0;
#ifdef CONFIG_VIDEO_ADV_DEBUG
- et61x251_create_sysfs(cam);
+ err = et61x251_create_sysfs(cam);
+ if (err)
+ goto fail2;
DBG(2, "Optional device control through 'sysfs' interface ready");
#endif
return 0;
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+fail2:
+ video_nr[dev_nr] = -1;
+ dev_nr = (dev_nr < ET61X251_MAX_DEVICES-1) ? dev_nr+1 : 0;
+ mutex_unlock(&cam->dev_mutex);
+ video_unregister_device(cam->v4ldev);
+#endif
fail:
if (cam) {
kfree(cam->control_buffer);
}
static CLASS_DEVICE_ATTR(exposure, S_IRUGO, show_exposure, NULL);
-static void ov_create_sysfs(struct video_device *vdev)
+static int ov_create_sysfs(struct video_device *vdev)
{
- video_device_create_file(vdev, &class_device_attr_custom_id);
- video_device_create_file(vdev, &class_device_attr_model);
- video_device_create_file(vdev, &class_device_attr_bridge);
- video_device_create_file(vdev, &class_device_attr_sensor);
- video_device_create_file(vdev, &class_device_attr_brightness);
- video_device_create_file(vdev, &class_device_attr_saturation);
- video_device_create_file(vdev, &class_device_attr_contrast);
- video_device_create_file(vdev, &class_device_attr_hue);
- video_device_create_file(vdev, &class_device_attr_exposure);
+ int rc;
+
+ rc = video_device_create_file(vdev, &class_device_attr_custom_id);
+ if (rc) goto err;
+ rc = video_device_create_file(vdev, &class_device_attr_model);
+ if (rc) goto err_id;
+ rc = video_device_create_file(vdev, &class_device_attr_bridge);
+ if (rc) goto err_model;
+ rc = video_device_create_file(vdev, &class_device_attr_sensor);
+ if (rc) goto err_bridge;
+ rc = video_device_create_file(vdev, &class_device_attr_brightness);
+ if (rc) goto err_sensor;
+ rc = video_device_create_file(vdev, &class_device_attr_saturation);
+ if (rc) goto err_bright;
+ rc = video_device_create_file(vdev, &class_device_attr_contrast);
+ if (rc) goto err_sat;
+ rc = video_device_create_file(vdev, &class_device_attr_hue);
+ if (rc) goto err_contrast;
+ rc = video_device_create_file(vdev, &class_device_attr_exposure);
+ if (rc) goto err_hue;
+
+ return 0;
+
+err_hue:
+ video_device_remove_file(vdev, &class_device_attr_hue);
+err_contrast:
+ video_device_remove_file(vdev, &class_device_attr_contrast);
+err_sat:
+ video_device_remove_file(vdev, &class_device_attr_saturation);
+err_bright:
+ video_device_remove_file(vdev, &class_device_attr_brightness);
+err_sensor:
+ video_device_remove_file(vdev, &class_device_attr_sensor);
+err_bridge:
+ video_device_remove_file(vdev, &class_device_attr_bridge);
+err_model:
+ video_device_remove_file(vdev, &class_device_attr_model);
+err_id:
+ video_device_remove_file(vdev, &class_device_attr_custom_id);
+err:
+ return rc;
}
/****************************************************************************
ov->vdev->minor);
usb_set_intfdata(intf, ov);
- ov_create_sysfs(ov->vdev);
+ if (ov_create_sysfs(ov->vdev)) {
+ err("ov_create_sysfs failed");
+ goto error;
+ }
+
return 0;
error:
static CLASS_DEVICE_ATTR(button, S_IRUGO | S_IWUSR, show_snapshot_button_status,
NULL);
-static void pwc_create_sysfs_files(struct video_device *vdev)
+static int pwc_create_sysfs_files(struct video_device *vdev)
{
struct pwc_device *pdev = video_get_drvdata(vdev);
- if (pdev->features & FEATURE_MOTOR_PANTILT)
- video_device_create_file(vdev, &class_device_attr_pan_tilt);
- video_device_create_file(vdev, &class_device_attr_button);
+ int rc;
+
+ rc = video_device_create_file(vdev, &class_device_attr_button);
+ if (rc)
+ goto err;
+ if (pdev->features & FEATURE_MOTOR_PANTILT) {
+ rc = video_device_create_file(vdev,&class_device_attr_pan_tilt);
+ if (rc) goto err_button;
+ }
+
+ return 0;
+
+err_button:
+ video_device_remove_file(vdev, &class_device_attr_button);
+err:
+ return rc;
}
static void pwc_remove_sysfs_files(struct video_device *vdev)
struct usb_device *udev = interface_to_usbdev(intf);
struct pwc_device *pdev = NULL;
int vendor_id, product_id, type_id;
- int i, hint;
+ int i, hint, rc;
int features = 0;
int video_nr = -1; /* default: use next available device */
char serial_number[30], *name;
i = video_register_device(pdev->vdev, VFL_TYPE_GRABBER, video_nr);
if (i < 0) {
PWC_ERROR("Failed to register as video device (%d).\n", i);
- video_device_release(pdev->vdev); /* Drip... drip... drip... */
- kfree(pdev); /* Oops, no memory leaks please */
- return -EIO;
+ rc = i;
+ goto err;
}
else {
PWC_INFO("Registered as /dev/video%d.\n", pdev->vdev->minor & 0x3F);
PWC_DEBUG_PROBE("probe() function returning struct at 0x%p.\n", pdev);
usb_set_intfdata (intf, pdev);
- pwc_create_sysfs_files(pdev->vdev);
+ rc = pwc_create_sysfs_files(pdev->vdev);
+ if (rc)
+ goto err_unreg;
/* Set the leds off */
pwc_set_leds(pdev, 0, 0);
pwc_camera_power(pdev, 0);
return 0;
+
+err_unreg:
+ if (hint < MAX_DEV_HINTS)
+ device_hint[hint].pdev = NULL;
+ video_unregister_device(pdev->vdev);
+err:
+ video_device_release(pdev->vdev); /* Drip... drip... drip... */
+ kfree(pdev); /* Oops, no memory leaks please */
+ return rc;
}
/* The user janked out the cable... */
reg |= 0x10;
} else if (std == V4L2_STD_NTSC_M_JP) {
reg |= 0x40;
+ } else if (std == V4L2_STD_SECAM) {
+ reg |= 0x50;
}
saa711x_write(client, R_0E_CHROMA_CNTL_1, reg);
} else {
t->type = V4L2_TUNER_RADIO;
saa7134_i2c_call_clients(dev, VIDIOC_G_TUNER, t);
-
+ if (dev->input->amux == TV) {
+ t->signal = 0xf800 - ((saa_readb(0x581) & 0x1f) << 11);
+ t->rxsubchans = (saa_readb(0x529) & 0x08) ?
+ V4L2_TUNER_SUB_STEREO : V4L2_TUNER_SUB_MONO;
+ }
return 0;
}
case VIDIOC_S_TUNER:
sn9c102_show_frame_header, NULL);
-static void sn9c102_create_sysfs(struct sn9c102_device* cam)
+static int sn9c102_create_sysfs(struct sn9c102_device* cam)
{
struct video_device *v4ldev = cam->v4ldev;
+ int rc;
+
+ rc = video_device_create_file(v4ldev, &class_device_attr_reg);
+ if (rc) goto err;
+ rc = video_device_create_file(v4ldev, &class_device_attr_val);
+ if (rc) goto err_reg;
+ rc = video_device_create_file(v4ldev, &class_device_attr_frame_header);
+ if (rc) goto err_val;
- video_device_create_file(v4ldev, &class_device_attr_reg);
- video_device_create_file(v4ldev, &class_device_attr_val);
- video_device_create_file(v4ldev, &class_device_attr_frame_header);
- if (cam->bridge == BRIDGE_SN9C101 || cam->bridge == BRIDGE_SN9C102)
- video_device_create_file(v4ldev, &class_device_attr_green);
- else if (cam->bridge == BRIDGE_SN9C103) {
- video_device_create_file(v4ldev, &class_device_attr_blue);
- video_device_create_file(v4ldev, &class_device_attr_red);
- }
if (cam->sensor.sysfs_ops) {
- video_device_create_file(v4ldev, &class_device_attr_i2c_reg);
- video_device_create_file(v4ldev, &class_device_attr_i2c_val);
+ rc = video_device_create_file(v4ldev, &class_device_attr_i2c_reg);
+ if (rc) goto err_frhead;
+ rc = video_device_create_file(v4ldev, &class_device_attr_i2c_val);
+ if (rc) goto err_i2c_reg;
+ }
+
+ if (cam->bridge == BRIDGE_SN9C101 || cam->bridge == BRIDGE_SN9C102) {
+ rc = video_device_create_file(v4ldev, &class_device_attr_green);
+ if (rc) goto err_i2c_val;
+ } else if (cam->bridge == BRIDGE_SN9C103) {
+ rc = video_device_create_file(v4ldev, &class_device_attr_blue);
+ if (rc) goto err_i2c_val;
+ rc = video_device_create_file(v4ldev, &class_device_attr_red);
+ if (rc) goto err_blue;
}
+
+ return 0;
+
+err_blue:
+ video_device_remove_file(v4ldev, &class_device_attr_blue);
+err_i2c_val:
+ if (cam->sensor.sysfs_ops)
+ video_device_remove_file(v4ldev, &class_device_attr_i2c_val);
+err_i2c_reg:
+ if (cam->sensor.sysfs_ops)
+ video_device_remove_file(v4ldev, &class_device_attr_i2c_reg);
+err_frhead:
+ video_device_remove_file(v4ldev, &class_device_attr_frame_header);
+err_val:
+ video_device_remove_file(v4ldev, &class_device_attr_val);
+err_reg:
+ video_device_remove_file(v4ldev, &class_device_attr_reg);
+err:
+ return rc;
}
#endif /* CONFIG_VIDEO_ADV_DEBUG */
DBG(1, "V4L2 device registration failed");
if (err == -ENFILE && video_nr[dev_nr] == -1)
DBG(1, "Free /dev/videoX node not found");
- video_nr[dev_nr] = -1;
- dev_nr = (dev_nr < SN9C102_MAX_DEVICES-1) ? dev_nr+1 : 0;
- mutex_unlock(&cam->dev_mutex);
- goto fail;
+ goto fail2;
}
DBG(2, "V4L2 device registered as /dev/video%d", cam->v4ldev->minor);
dev_nr = (dev_nr < SN9C102_MAX_DEVICES-1) ? dev_nr+1 : 0;
#ifdef CONFIG_VIDEO_ADV_DEBUG
- sn9c102_create_sysfs(cam);
+ err = sn9c102_create_sysfs(cam);
+ if (err)
+ goto fail3;
DBG(2, "Optional device control through 'sysfs' interface ready");
#endif
return 0;
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+fail3:
+ video_unregister_device(cam->v4ldev);
+#endif
+fail2:
+ video_nr[dev_nr] = -1;
+ dev_nr = (dev_nr < SN9C102_MAX_DEVICES-1) ? dev_nr+1 : 0;
+ mutex_unlock(&cam->dev_mutex);
fail:
if (cam) {
kfree(cam->control_buffer);
stv680_file(packets_dropped, dropped, "%d\n");
stv680_file(decoding_errors, error, "%d\n");
-static void stv680_create_sysfs_files(struct video_device *vdev)
+static int stv680_create_sysfs_files(struct video_device *vdev)
{
- video_device_create_file(vdev, &class_device_attr_model);
- video_device_create_file(vdev, &class_device_attr_in_use);
- video_device_create_file(vdev, &class_device_attr_streaming);
- video_device_create_file(vdev, &class_device_attr_palette);
- video_device_create_file(vdev, &class_device_attr_frames_total);
- video_device_create_file(vdev, &class_device_attr_frames_read);
- video_device_create_file(vdev, &class_device_attr_packets_dropped);
- video_device_create_file(vdev, &class_device_attr_decoding_errors);
+ int rc;
+
+ rc = video_device_create_file(vdev, &class_device_attr_model);
+ if (rc) goto err;
+ rc = video_device_create_file(vdev, &class_device_attr_in_use);
+ if (rc) goto err_model;
+ rc = video_device_create_file(vdev, &class_device_attr_streaming);
+ if (rc) goto err_inuse;
+ rc = video_device_create_file(vdev, &class_device_attr_palette);
+ if (rc) goto err_stream;
+ rc = video_device_create_file(vdev, &class_device_attr_frames_total);
+ if (rc) goto err_pal;
+ rc = video_device_create_file(vdev, &class_device_attr_frames_read);
+ if (rc) goto err_framtot;
+ rc = video_device_create_file(vdev, &class_device_attr_packets_dropped);
+ if (rc) goto err_framread;
+ rc = video_device_create_file(vdev, &class_device_attr_decoding_errors);
+ if (rc) goto err_dropped;
+
+ return 0;
+
+err_dropped:
+ video_device_remove_file(vdev, &class_device_attr_packets_dropped);
+err_framread:
+ video_device_remove_file(vdev, &class_device_attr_frames_read);
+err_framtot:
+ video_device_remove_file(vdev, &class_device_attr_frames_total);
+err_pal:
+ video_device_remove_file(vdev, &class_device_attr_palette);
+err_stream:
+ video_device_remove_file(vdev, &class_device_attr_streaming);
+err_inuse:
+ video_device_remove_file(vdev, &class_device_attr_in_use);
+err_model:
+ video_device_remove_file(vdev, &class_device_attr_model);
+err:
+ return rc;
}
static void stv680_remove_sysfs_files(struct video_device *vdev)
PDEBUG (0, "STV(i): registered new video device: video%d", stv680->vdev->minor);
usb_set_intfdata (intf, stv680);
- stv680_create_sysfs_files(stv680->vdev);
+ retval = stv680_create_sysfs_files(stv680->vdev);
+ if (retval)
+ goto error_unreg;
return 0;
+error_unreg:
+ video_unregister_device(stv680->vdev);
error_vdev:
video_device_release(stv680->vdev);
error:
.type = TUNER_PARAM_TYPE_NTSC,
.ranges = tuner_samsung_tcpn_2121p30a_ntsc_ranges,
.count = ARRAY_SIZE(tuner_samsung_tcpn_2121p30a_ntsc_ranges),
- .has_tda9887 = 1,
},
};
*/
#define dbgarg(cmd, fmt, arg...) \
- if (vfd->debug & V4L2_DEBUG_IOCTL_ARG) \
+ if (vfd->debug & V4L2_DEBUG_IOCTL_ARG) { \
printk (KERN_DEBUG "%s: ", vfd->name); \
v4l_printk_ioctl(cmd); \
- printk (KERN_DEBUG "%s: " fmt, vfd->name, ## arg);
+ printk (KERN_DEBUG "%s: " fmt, vfd->name, ## arg); \
+ }
#define dbgarg2(fmt, arg...) \
if (vfd->debug & V4L2_DEBUG_IOCTL_ARG) \
ret=vfd->vidioc_g_parm(file, fh, p);
} else {
struct v4l2_standard s;
+ int i;
if (!vfd->tvnormsize) {
printk (KERN_WARNING "%s: no TV norms defined!\n",
if (p->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
return -EINVAL;
- v4l2_video_std_construct(&s, vfd->tvnorms[vfd->current_norm].id,
- vfd->tvnorms[vfd->current_norm].name);
+ for (i = 0; i < vfd->tvnormsize; i++)
+ if (vfd->tvnorms[i].id == vfd->current_norm)
+ break;
+ if (i >= vfd->tvnormsize)
+ return -EINVAL;
+
+ v4l2_video_std_construct(&s, vfd->current_norm,
+ vfd->tvnorms[i].name);
memset(p,0,sizeof(*p));
/* Get first addr pointed to pixel position */
oldpg=get_addr_pos(pos,pages,to_addr);
- pg=pfn_to_page(to_addr[oldpg].sg->dma_address >> PAGE_SHIFT);
+ pg=pfn_to_page(sg_dma_address(to_addr[oldpg].sg) >> PAGE_SHIFT);
basep = kmap_atomic(pg, KM_BOUNCE_READ)+to_addr[oldpg].sg->offset;
/* We will just duplicate the second pixel at the packet */
for (color=0;color<4;color++) {
pgpos=get_addr_pos(pos,pages,to_addr);
if (pgpos!=oldpg) {
- pg=pfn_to_page(to_addr[pgpos].sg->dma_address >> PAGE_SHIFT);
+ pg=pfn_to_page(sg_dma_address(to_addr[pgpos].sg) >> PAGE_SHIFT);
kunmap_atomic(basep, KM_BOUNCE_READ);
basep= kmap_atomic(pg, KM_BOUNCE_READ)+to_addr[pgpos].sg->offset;
oldpg=pgpos;
for (color=0;color<4;color++) {
pgpos=get_addr_pos(pos,pages,to_addr);
if (pgpos!=oldpg) {
- pg=pfn_to_page(to_addr[pgpos].
- sg->dma_address
+ pg=pfn_to_page(sg_dma_address(
+ to_addr[pgpos].sg)
>> PAGE_SHIFT);
kunmap_atomic(basep,
KM_BOUNCE_READ);
struct timeval ts;
/* Test if DMA mapping is ready */
- if (!vb->dma.sglist[0].dma_address)
+ if (!sg_dma_address(&vb->dma.sglist[0]))
return;
prep_to_addr(to_addr,vb);
for (i = 0; i < nents; i++ ) {
BUG_ON(!sg[i].page);
- sg[i].dma_address = page_to_phys(sg[i].page) + sg[i].offset;
+ sg_dma_address(&sg[i]) = page_to_phys(sg[i].page) + sg[i].offset;
}
return nents;
* @dev: device to verify if it is a I2O Bus Adapter device
*
* Because we want all Bus Adapters always return 0.
+ * Except when we fail. Then we are sad.
*
- * Returns 0.
+ * Returns 0, except when we fail to excel.
*/
static int i2o_bus_probe(struct device *dev)
{
struct i2o_device *i2o_dev = to_i2o_device(get_device(dev));
+ int rc;
- device_create_file(dev, &dev_attr_scan);
+ rc = device_create_file(dev, &dev_attr_scan);
+ if (rc)
+ goto err_out;
osm_info("device added (TID: %03x)\n", i2o_dev->lct_data.tid);
return 0;
+
+err_out:
+ put_device(dev);
+ return rc;
};
/**
static int i2o_exec_probe(struct device *dev)
{
struct i2o_device *i2o_dev = to_i2o_device(dev);
+ int rc;
- i2o_event_register(i2o_dev, &i2o_exec_driver, 0, 0xffffffff);
+ rc = i2o_event_register(i2o_dev, &i2o_exec_driver, 0, 0xffffffff);
+ if (rc) goto err_out;
- device_create_file(dev, &dev_attr_vendor_id);
- device_create_file(dev, &dev_attr_product_id);
+ rc = device_create_file(dev, &dev_attr_vendor_id);
+ if (rc) goto err_evtreg;
+ rc = device_create_file(dev, &dev_attr_product_id);
+ if (rc) goto err_vid;
return 0;
+
+err_vid:
+ device_remove_file(dev, &dev_attr_vendor_id);
+err_evtreg:
+ i2o_event_register(to_i2o_device(dev), &i2o_exec_driver, 0, 0);
+err_out:
+ return rc;
};
/**
If unsure, say N.
+config SGI_IOC4
+ tristate "SGI IOC4 Base IO support"
+ ---help---
+ This option enables basic support for the IOC4 chip on certain
+ SGI IO controller cards (IO9, IO10, and PCI-RT). This option
+ does not enable any specific functions on such a card, but provides
+ necessary infrastructure for other drivers to utilize.
+
+ If you have an SGI Altix with an IOC4-based card say Y.
+ Otherwise say N.
+
config TIFM_CORE
tristate "TI Flash Media interface support (EXPERIMENTAL)"
depends on EXPERIMENTAL
To compile this driver as a module, choose M here: the module will
be called tifm_7xx1.
+config MSI_LAPTOP
+ tristate "MSI Laptop Extras"
+ depends on X86
+ depends on ACPI_EC
+ depends on BACKLIGHT_CLASS_DEVICE
+ ---help---
+ This is a driver for laptops built by MSI (MICRO-STAR
+ INTERNATIONAL):
+
+ MSI MegaBook S270 (MS-1013)
+ Cytron/TCM/Medion/Tchibo MD96100/SAM2000
+
+ It adds support for Bluetooth, WLAN and LCD brightness control.
+
+ More information about this driver is available at
+ <http://0pointer.de/lennart/tchibo.html>.
+
+ If you have an MSI S270 laptop, say Y or M here.
+
endmenu
obj-$(CONFIG_IBM_ASM) += ibmasm/
obj-$(CONFIG_HDPU_FEATURES) += hdpuftrs/
+obj-$(CONFIG_MSI_LAPTOP) += msi-laptop.o
obj-$(CONFIG_LKDTM) += lkdtm.o
obj-$(CONFIG_TIFM_CORE) += tifm_core.o
obj-$(CONFIG_TIFM_7XX1) += tifm_7xx1.o
+obj-$(CONFIG_SGI_IOC4) += ioc4.o
--- /dev/null
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2005-2006 Silicon Graphics, Inc. All Rights Reserved.
+ */
+
+/* This file contains the master driver module for use by SGI IOC4 subdrivers.
+ *
+ * It allocates any resources shared between multiple subdevices, and
+ * provides accessor functions (where needed) and the like for those
+ * resources. It also provides a mechanism for the subdevice modules
+ * to support loading and unloading.
+ *
+ * Non-shared resources (e.g. external interrupt A_INT_OUT register page
+ * alias, serial port and UART registers) are handled by the subdevice
+ * modules themselves.
+ *
+ * This is all necessary because IOC4 is not implemented as a multi-function
+ * PCI device, but an amalgamation of disparate registers for several
+ * types of device (ATA, serial, external interrupts). The normal
+ * resource management in the kernel doesn't have quite the right interfaces
+ * to handle this situation (e.g. multiple modules can't claim the same
+ * PCI ID), thus this IOC4 master module.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/ioc4.h>
+#include <linux/ktime.h>
+#include <linux/mutex.h>
+#include <linux/time.h>
+
+/***************
+ * Definitions *
+ ***************/
+
+/* Tweakable values */
+
+/* PCI bus speed detection/calibration */
+#define IOC4_CALIBRATE_COUNT 63 /* Calibration cycle period */
+#define IOC4_CALIBRATE_CYCLES 256 /* Average over this many cycles */
+#define IOC4_CALIBRATE_DISCARD 2 /* Discard first few cycles */
+#define IOC4_CALIBRATE_LOW_MHZ 25 /* Lower bound on bus speed sanity */
+#define IOC4_CALIBRATE_HIGH_MHZ 75 /* Upper bound on bus speed sanity */
+#define IOC4_CALIBRATE_DEFAULT_MHZ 66 /* Assumed if sanity check fails */
+
+/************************
+ * Submodule management *
+ ************************/
+
+static DEFINE_MUTEX(ioc4_mutex);
+
+static LIST_HEAD(ioc4_devices);
+static LIST_HEAD(ioc4_submodules);
+
+/* Register an IOC4 submodule */
+int
+ioc4_register_submodule(struct ioc4_submodule *is)
+{
+ struct ioc4_driver_data *idd;
+
+ mutex_lock(&ioc4_mutex);
+ list_add(&is->is_list, &ioc4_submodules);
+
+ /* Initialize submodule for each IOC4 */
+ if (!is->is_probe)
+ goto out;
+
+ list_for_each_entry(idd, &ioc4_devices, idd_list) {
+ if (is->is_probe(idd)) {
+ printk(KERN_WARNING
+ "%s: IOC4 submodule %s probe failed "
+ "for pci_dev %s",
+ __FUNCTION__, module_name(is->is_owner),
+ pci_name(idd->idd_pdev));
+ }
+ }
+ out:
+ mutex_unlock(&ioc4_mutex);
+ return 0;
+}
+
+/* Unregister an IOC4 submodule */
+void
+ioc4_unregister_submodule(struct ioc4_submodule *is)
+{
+ struct ioc4_driver_data *idd;
+
+ mutex_lock(&ioc4_mutex);
+ list_del(&is->is_list);
+
+ /* Remove submodule for each IOC4 */
+ if (!is->is_remove)
+ goto out;
+
+ list_for_each_entry(idd, &ioc4_devices, idd_list) {
+ if (is->is_remove(idd)) {
+ printk(KERN_WARNING
+ "%s: IOC4 submodule %s remove failed "
+ "for pci_dev %s.\n",
+ __FUNCTION__, module_name(is->is_owner),
+ pci_name(idd->idd_pdev));
+ }
+ }
+ out:
+ mutex_unlock(&ioc4_mutex);
+}
+
+/*********************
+ * Device management *
+ *********************/
+
+#define IOC4_CALIBRATE_LOW_LIMIT \
+ (1000*IOC4_EXTINT_COUNT_DIVISOR/IOC4_CALIBRATE_LOW_MHZ)
+#define IOC4_CALIBRATE_HIGH_LIMIT \
+ (1000*IOC4_EXTINT_COUNT_DIVISOR/IOC4_CALIBRATE_HIGH_MHZ)
+#define IOC4_CALIBRATE_DEFAULT \
+ (1000*IOC4_EXTINT_COUNT_DIVISOR/IOC4_CALIBRATE_DEFAULT_MHZ)
+
+#define IOC4_CALIBRATE_END \
+ (IOC4_CALIBRATE_CYCLES + IOC4_CALIBRATE_DISCARD)
+
+#define IOC4_INT_OUT_MODE_TOGGLE 0x7 /* Toggle INT_OUT every COUNT+1 ticks */
+
+/* Determines external interrupt output clock period of the PCI bus an
+ * IOC4 is attached to. This value can be used to determine the PCI
+ * bus speed.
+ *
+ * IOC4 has a design feature that various internal timers are derived from
+ * the PCI bus clock. This causes IOC4 device drivers to need to take the
+ * bus speed into account when setting various register values (e.g. INT_OUT
+ * register COUNT field, UART divisors, etc). Since this information is
+ * needed by several subdrivers, it is determined by the main IOC4 driver,
+ * even though the following code utilizes external interrupt registers
+ * to perform the speed calculation.
+ */
+static void
+ioc4_clock_calibrate(struct ioc4_driver_data *idd)
+{
+ union ioc4_int_out int_out;
+ union ioc4_gpcr gpcr;
+ unsigned int state, last_state = 1;
+ struct timespec start_ts, end_ts;
+ uint64_t start, end, period;
+ unsigned int count = 0;
+
+ /* Enable output */
+ gpcr.raw = 0;
+ gpcr.fields.dir = IOC4_GPCR_DIR_0;
+ gpcr.fields.int_out_en = 1;
+ writel(gpcr.raw, &idd->idd_misc_regs->gpcr_s.raw);
+
+ /* Reset to power-on state */
+ writel(0, &idd->idd_misc_regs->int_out.raw);
+ mmiowb();
+
+ /* Set up square wave */
+ int_out.raw = 0;
+ int_out.fields.count = IOC4_CALIBRATE_COUNT;
+ int_out.fields.mode = IOC4_INT_OUT_MODE_TOGGLE;
+ int_out.fields.diag = 0;
+ writel(int_out.raw, &idd->idd_misc_regs->int_out.raw);
+ mmiowb();
+
+ /* Check square wave period averaged over some number of cycles */
+ do {
+ int_out.raw = readl(&idd->idd_misc_regs->int_out.raw);
+ state = int_out.fields.int_out;
+ if (!last_state && state) {
+ count++;
+ if (count == IOC4_CALIBRATE_END) {
+ ktime_get_ts(&end_ts);
+ break;
+ } else if (count == IOC4_CALIBRATE_DISCARD)
+ ktime_get_ts(&start_ts);
+ }
+ last_state = state;
+ } while (1);
+
+ /* Calculation rearranged to preserve intermediate precision.
+ * Logically:
+ * 1. "end - start" gives us the measurement period over all
+ * the square wave cycles.
+ * 2. Divide by number of square wave cycles to get the period
+ * of a square wave cycle.
+ * 3. Divide by 2*(int_out.fields.count+1), which is the formula
+ * by which the IOC4 generates the square wave, to get the
+ * period of an IOC4 INT_OUT count.
+ */
+ end = end_ts.tv_sec * NSEC_PER_SEC + end_ts.tv_nsec;
+ start = start_ts.tv_sec * NSEC_PER_SEC + start_ts.tv_nsec;
+ period = (end - start) /
+ (IOC4_CALIBRATE_CYCLES * 2 * (IOC4_CALIBRATE_COUNT + 1));
+
+ /* Bounds check the result. */
+ if (period > IOC4_CALIBRATE_LOW_LIMIT ||
+ period < IOC4_CALIBRATE_HIGH_LIMIT) {
+ printk(KERN_INFO
+ "IOC4 %s: Clock calibration failed. Assuming"
+ "PCI clock is %d ns.\n",
+ pci_name(idd->idd_pdev),
+ IOC4_CALIBRATE_DEFAULT / IOC4_EXTINT_COUNT_DIVISOR);
+ period = IOC4_CALIBRATE_DEFAULT;
+ } else {
+ u64 ns = period;
+
+ do_div(ns, IOC4_EXTINT_COUNT_DIVISOR);
+ printk(KERN_DEBUG
+ "IOC4 %s: PCI clock is %lld ns.\n",
+ pci_name(idd->idd_pdev), ns);
+ }
+
+ /* Remember results. We store the extint clock period rather
+ * than the PCI clock period so that greater precision is
+ * retained. Divide by IOC4_EXTINT_COUNT_DIVISOR to get
+ * PCI clock period.
+ */
+ idd->count_period = period;
+}
+
+/* There are three variants of IOC4 cards: IO9, IO10, and PCI-RT.
+ * Each brings out different combinations of IOC4 signals, thus.
+ * the IOC4 subdrivers need to know to which we're attached.
+ *
+ * We look for the presence of a SCSI (IO9) or SATA (IO10) controller
+ * on the same PCI bus at slot number 3 to differentiate IO9 from IO10.
+ * If neither is present, it's a PCI-RT.
+ */
+static unsigned int
+ioc4_variant(struct ioc4_driver_data *idd)
+{
+ struct pci_dev *pdev = NULL;
+ int found = 0;
+
+ /* IO9: Look for a QLogic ISP 12160 at the same bus and slot 3. */
+ do {
+ pdev = pci_get_device(PCI_VENDOR_ID_QLOGIC,
+ PCI_DEVICE_ID_QLOGIC_ISP12160, pdev);
+ if (pdev &&
+ idd->idd_pdev->bus->number == pdev->bus->number &&
+ 3 == PCI_SLOT(pdev->devfn))
+ found = 1;
+ pci_dev_put(pdev);
+ } while (pdev && !found);
+ if (NULL != pdev)
+ return IOC4_VARIANT_IO9;
+
+ /* IO10: Look for a Vitesse VSC 7174 at the same bus and slot 3. */
+ pdev = NULL;
+ do {
+ pdev = pci_get_device(PCI_VENDOR_ID_VITESSE,
+ PCI_DEVICE_ID_VITESSE_VSC7174, pdev);
+ if (pdev &&
+ idd->idd_pdev->bus->number == pdev->bus->number &&
+ 3 == PCI_SLOT(pdev->devfn))
+ found = 1;
+ pci_dev_put(pdev);
+ } while (pdev && !found);
+ if (NULL != pdev)
+ return IOC4_VARIANT_IO10;
+
+ /* PCI-RT: No SCSI/SATA controller will be present */
+ return IOC4_VARIANT_PCI_RT;
+}
+
+/* Adds a new instance of an IOC4 card */
+static int
+ioc4_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
+{
+ struct ioc4_driver_data *idd;
+ struct ioc4_submodule *is;
+ uint32_t pcmd;
+ int ret;
+
+ /* Enable IOC4 and take ownership of it */
+ if ((ret = pci_enable_device(pdev))) {
+ printk(KERN_WARNING
+ "%s: Failed to enable IOC4 device for pci_dev %s.\n",
+ __FUNCTION__, pci_name(pdev));
+ goto out;
+ }
+ pci_set_master(pdev);
+
+ /* Set up per-IOC4 data */
+ idd = kmalloc(sizeof(struct ioc4_driver_data), GFP_KERNEL);
+ if (!idd) {
+ printk(KERN_WARNING
+ "%s: Failed to allocate IOC4 data for pci_dev %s.\n",
+ __FUNCTION__, pci_name(pdev));
+ ret = -ENODEV;
+ goto out_idd;
+ }
+ idd->idd_pdev = pdev;
+ idd->idd_pci_id = pci_id;
+
+ /* Map IOC4 misc registers. These are shared between subdevices
+ * so the main IOC4 module manages them.
+ */
+ idd->idd_bar0 = pci_resource_start(idd->idd_pdev, 0);
+ if (!idd->idd_bar0) {
+ printk(KERN_WARNING
+ "%s: Unable to find IOC4 misc resource "
+ "for pci_dev %s.\n",
+ __FUNCTION__, pci_name(idd->idd_pdev));
+ ret = -ENODEV;
+ goto out_pci;
+ }
+ if (!request_region(idd->idd_bar0, sizeof(struct ioc4_misc_regs),
+ "ioc4_misc")) {
+ printk(KERN_WARNING
+ "%s: Unable to request IOC4 misc region "
+ "for pci_dev %s.\n",
+ __FUNCTION__, pci_name(idd->idd_pdev));
+ ret = -ENODEV;
+ goto out_pci;
+ }
+ idd->idd_misc_regs = ioremap(idd->idd_bar0,
+ sizeof(struct ioc4_misc_regs));
+ if (!idd->idd_misc_regs) {
+ printk(KERN_WARNING
+ "%s: Unable to remap IOC4 misc region "
+ "for pci_dev %s.\n",
+ __FUNCTION__, pci_name(idd->idd_pdev));
+ ret = -ENODEV;
+ goto out_misc_region;
+ }
+
+ /* Failsafe portion of per-IOC4 initialization */
+
+ /* Detect card variant */
+ idd->idd_variant = ioc4_variant(idd);
+ printk(KERN_INFO "IOC4 %s: %s card detected.\n", pci_name(pdev),
+ idd->idd_variant == IOC4_VARIANT_IO9 ? "IO9" :
+ idd->idd_variant == IOC4_VARIANT_PCI_RT ? "PCI-RT" :
+ idd->idd_variant == IOC4_VARIANT_IO10 ? "IO10" : "unknown");
+
+ /* Initialize IOC4 */
+ pci_read_config_dword(idd->idd_pdev, PCI_COMMAND, &pcmd);
+ pci_write_config_dword(idd->idd_pdev, PCI_COMMAND,
+ pcmd | PCI_COMMAND_PARITY | PCI_COMMAND_SERR);
+
+ /* Determine PCI clock */
+ ioc4_clock_calibrate(idd);
+
+ /* Disable/clear all interrupts. Need to do this here lest
+ * one submodule request the shared IOC4 IRQ, but interrupt
+ * is generated by a different subdevice.
+ */
+ /* Disable */
+ writel(~0, &idd->idd_misc_regs->other_iec.raw);
+ writel(~0, &idd->idd_misc_regs->sio_iec);
+ /* Clear (i.e. acknowledge) */
+ writel(~0, &idd->idd_misc_regs->other_ir.raw);
+ writel(~0, &idd->idd_misc_regs->sio_ir);
+
+ /* Track PCI-device specific data */
+ idd->idd_serial_data = NULL;
+ pci_set_drvdata(idd->idd_pdev, idd);
+
+ mutex_lock(&ioc4_mutex);
+ list_add_tail(&idd->idd_list, &ioc4_devices);
+
+ /* Add this IOC4 to all submodules */
+ list_for_each_entry(is, &ioc4_submodules, is_list) {
+ if (is->is_probe && is->is_probe(idd)) {
+ printk(KERN_WARNING
+ "%s: IOC4 submodule 0x%s probe failed "
+ "for pci_dev %s.\n",
+ __FUNCTION__, module_name(is->is_owner),
+ pci_name(idd->idd_pdev));
+ }
+ }
+ mutex_unlock(&ioc4_mutex);
+
+ return 0;
+
+out_misc_region:
+ release_region(idd->idd_bar0, sizeof(struct ioc4_misc_regs));
+out_pci:
+ kfree(idd);
+out_idd:
+ pci_disable_device(pdev);
+out:
+ return ret;
+}
+
+/* Removes a particular instance of an IOC4 card. */
+static void
+ioc4_remove(struct pci_dev *pdev)
+{
+ struct ioc4_submodule *is;
+ struct ioc4_driver_data *idd;
+
+ idd = pci_get_drvdata(pdev);
+
+ /* Remove this IOC4 from all submodules */
+ mutex_lock(&ioc4_mutex);
+ list_for_each_entry(is, &ioc4_submodules, is_list) {
+ if (is->is_remove && is->is_remove(idd)) {
+ printk(KERN_WARNING
+ "%s: IOC4 submodule 0x%s remove failed "
+ "for pci_dev %s.\n",
+ __FUNCTION__, module_name(is->is_owner),
+ pci_name(idd->idd_pdev));
+ }
+ }
+ mutex_unlock(&ioc4_mutex);
+
+ /* Release resources */
+ iounmap(idd->idd_misc_regs);
+ if (!idd->idd_bar0) {
+ printk(KERN_WARNING
+ "%s: Unable to get IOC4 misc mapping for pci_dev %s. "
+ "Device removal may be incomplete.\n",
+ __FUNCTION__, pci_name(idd->idd_pdev));
+ }
+ release_region(idd->idd_bar0, sizeof(struct ioc4_misc_regs));
+
+ /* Disable IOC4 and relinquish */
+ pci_disable_device(pdev);
+
+ /* Remove and free driver data */
+ mutex_lock(&ioc4_mutex);
+ list_del(&idd->idd_list);
+ mutex_unlock(&ioc4_mutex);
+ kfree(idd);
+}
+
+static struct pci_device_id ioc4_id_table[] = {
+ {PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC4, PCI_ANY_ID,
+ PCI_ANY_ID, 0x0b4000, 0xFFFFFF},
+ {0}
+};
+
+static struct pci_driver ioc4_driver = {
+ .name = "IOC4",
+ .id_table = ioc4_id_table,
+ .probe = ioc4_probe,
+ .remove = ioc4_remove,
+};
+
+MODULE_DEVICE_TABLE(pci, ioc4_id_table);
+
+/*********************
+ * Module management *
+ *********************/
+
+/* Module load */
+static int __devinit
+ioc4_init(void)
+{
+ return pci_register_driver(&ioc4_driver);
+}
+
+/* Module unload */
+static void __devexit
+ioc4_exit(void)
+{
+ pci_unregister_driver(&ioc4_driver);
+}
+
+module_init(ioc4_init);
+module_exit(ioc4_exit);
+
+MODULE_AUTHOR("Brent Casavant - Silicon Graphics, Inc. <bcasavan@sgi.com>");
+MODULE_DESCRIPTION("PCI driver master module for SGI IOC4 Base-IO Card");
+MODULE_LICENSE("GPL");
+
+EXPORT_SYMBOL(ioc4_register_submodule);
+EXPORT_SYMBOL(ioc4_unregister_submodule);
--- /dev/null
+/*-*-linux-c-*-*/
+
+/*
+ Copyright (C) 2006 Lennart Poettering <mzxreary (at) 0pointer (dot) de>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful, but
+ WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ 02110-1301, USA.
+ */
+
+/*
+ * msi-laptop.c - MSI S270 laptop support. This laptop is sold under
+ * various brands, including "Cytron/TCM/Medion/Tchibo MD96100".
+ *
+ * This driver exports a few files in /sys/devices/platform/msi-laptop-pf/:
+ *
+ * lcd_level - Screen brightness: contains a single integer in the
+ * range 0..8. (rw)
+ *
+ * auto_brightness - Enable automatic brightness control: contains
+ * either 0 or 1. If set to 1 the hardware adjusts the screen
+ * brightness automatically when the power cord is
+ * plugged/unplugged. (rw)
+ *
+ * wlan - WLAN subsystem enabled: contains either 0 or 1. (ro)
+ *
+ * bluetooth - Bluetooth subsystem enabled: contains either 0 or 1
+ * Please note that this file is constantly 0 if no Bluetooth
+ * hardware is available. (ro)
+ *
+ * In addition to these platform device attributes the driver
+ * registers itself in the Linux backlight control subsystem and is
+ * available to userspace under /sys/class/backlight/msi-laptop-bl/.
+ *
+ * This driver might work on other laptops produced by MSI. If you
+ * want to try it you can pass force=1 as argument to the module which
+ * will force it to load even when the DMI data doesn't identify the
+ * laptop as MSI S270. YMMV.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/dmi.h>
+#include <linux/backlight.h>
+#include <linux/platform_device.h>
+#include <linux/autoconf.h>
+
+#define MSI_DRIVER_VERSION "0.5"
+
+#define MSI_LCD_LEVEL_MAX 9
+
+#define MSI_EC_COMMAND_WIRELESS 0x10
+#define MSI_EC_COMMAND_LCD_LEVEL 0x11
+
+static int force;
+module_param(force, bool, 0);
+MODULE_PARM_DESC(force, "Force driver load, ignore DMI data");
+
+static int auto_brightness;
+module_param(auto_brightness, int, 0);
+MODULE_PARM_DESC(auto_brightness, "Enable automatic brightness control (0: disabled; 1: enabled; 2: don't touch)");
+
+/* Hardware access */
+
+static int set_lcd_level(int level)
+{
+ u8 buf[2];
+
+ if (level < 0 || level >= MSI_LCD_LEVEL_MAX)
+ return -EINVAL;
+
+ buf[0] = 0x80;
+ buf[1] = (u8) (level*31);
+
+ return ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, buf, sizeof(buf), NULL, 0);
+}
+
+static int get_lcd_level(void)
+{
+ u8 wdata = 0, rdata;
+ int result;
+
+ result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, &wdata, 1, &rdata, 1);
+ if (result < 0)
+ return result;
+
+ return (int) rdata / 31;
+}
+
+static int get_auto_brightness(void)
+{
+ u8 wdata = 4, rdata;
+ int result;
+
+ result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, &wdata, 1, &rdata, 1);
+ if (result < 0)
+ return result;
+
+ return !!(rdata & 8);
+}
+
+static int set_auto_brightness(int enable)
+{
+ u8 wdata[2], rdata;
+ int result;
+
+ wdata[0] = 4;
+
+ result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, wdata, 1, &rdata, 1);
+ if (result < 0)
+ return result;
+
+ wdata[0] = 0x84;
+ wdata[1] = (rdata & 0xF7) | (enable ? 8 : 0);
+
+ return ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, wdata, 2, NULL, 0);
+}
+
+static int get_wireless_state(int *wlan, int *bluetooth)
+{
+ u8 wdata = 0, rdata;
+ int result;
+
+ result = ec_transaction(MSI_EC_COMMAND_WIRELESS, &wdata, 1, &rdata, 1);
+ if (result < 0)
+ return -1;
+
+ if (wlan)
+ *wlan = !!(rdata & 8);
+
+ if (bluetooth)
+ *bluetooth = !!(rdata & 128);
+
+ return 0;
+}
+
+/* Backlight device stuff */
+
+static int bl_get_brightness(struct backlight_device *b)
+{
+ return get_lcd_level();
+}
+
+
+static int bl_update_status(struct backlight_device *b)
+{
+ return set_lcd_level(b->props->brightness);
+}
+
+static struct backlight_properties msibl_props = {
+ .owner = THIS_MODULE,
+ .get_brightness = bl_get_brightness,
+ .update_status = bl_update_status,
+ .max_brightness = MSI_LCD_LEVEL_MAX-1,
+};
+
+static struct backlight_device *msibl_device;
+
+/* Platform device */
+
+static ssize_t show_wlan(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+
+ int ret, enabled;
+
+ ret = get_wireless_state(&enabled, NULL);
+ if (ret < 0)
+ return ret;
+
+ return sprintf(buf, "%i\n", enabled);
+}
+
+static ssize_t show_bluetooth(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+
+ int ret, enabled;
+
+ ret = get_wireless_state(NULL, &enabled);
+ if (ret < 0)
+ return ret;
+
+ return sprintf(buf, "%i\n", enabled);
+}
+
+static ssize_t show_lcd_level(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+
+ int ret;
+
+ ret = get_lcd_level();
+ if (ret < 0)
+ return ret;
+
+ return sprintf(buf, "%i\n", ret);
+}
+
+static ssize_t store_lcd_level(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t count)
+{
+
+ int level, ret;
+
+ if (sscanf(buf, "%i", &level) != 1 || (level < 0 || level >= MSI_LCD_LEVEL_MAX))
+ return -EINVAL;
+
+ ret = set_lcd_level(level);
+ if (ret < 0)
+ return ret;
+
+ return count;
+}
+
+static ssize_t show_auto_brightness(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+
+ int ret;
+
+ ret = get_auto_brightness();
+ if (ret < 0)
+ return ret;
+
+ return sprintf(buf, "%i\n", ret);
+}
+
+static ssize_t store_auto_brightness(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t count)
+{
+
+ int enable, ret;
+
+ if (sscanf(buf, "%i", &enable) != 1 || (enable != (enable & 1)))
+ return -EINVAL;
+
+ ret = set_auto_brightness(enable);
+ if (ret < 0)
+ return ret;
+
+ return count;
+}
+
+static DEVICE_ATTR(lcd_level, 0644, show_lcd_level, store_lcd_level);
+static DEVICE_ATTR(auto_brightness, 0644, show_auto_brightness, store_auto_brightness);
+static DEVICE_ATTR(bluetooth, 0444, show_bluetooth, NULL);
+static DEVICE_ATTR(wlan, 0444, show_wlan, NULL);
+
+static struct attribute *msipf_attributes[] = {
+ &dev_attr_lcd_level.attr,
+ &dev_attr_auto_brightness.attr,
+ &dev_attr_bluetooth.attr,
+ &dev_attr_wlan.attr,
+ NULL
+};
+
+static struct attribute_group msipf_attribute_group = {
+ .attrs = msipf_attributes
+};
+
+static struct platform_driver msipf_driver = {
+ .driver = {
+ .name = "msi-laptop-pf",
+ .owner = THIS_MODULE,
+ }
+};
+
+static struct platform_device *msipf_device;
+
+/* Initialization */
+
+static struct dmi_system_id __initdata msi_dmi_table[] = {
+ {
+ .ident = "MSI S270",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "MICRO-STAR INT'L CO.,LTD"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MS-1013"),
+ }
+ },
+ {
+ .ident = "Medion MD96100",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "NOTEBOOK"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "SAM2000"),
+ }
+ },
+ { }
+};
+
+
+static int __init msi_init(void)
+{
+ int ret;
+
+ if (acpi_disabled)
+ return -ENODEV;
+
+ if (!force && !dmi_check_system(msi_dmi_table))
+ return -ENODEV;
+
+ if (auto_brightness < 0 || auto_brightness > 2)
+ return -EINVAL;
+
+ /* Register backlight stuff */
+
+ msibl_device = backlight_device_register("msi-laptop-bl", NULL, &msibl_props);
+ if (IS_ERR(msibl_device))
+ return PTR_ERR(msibl_device);
+
+ ret = platform_driver_register(&msipf_driver);
+ if (ret)
+ goto fail_backlight;
+
+ /* Register platform stuff */
+
+ msipf_device = platform_device_alloc("msi-laptop-pf", -1);
+ if (!msipf_device) {
+ ret = -ENOMEM;
+ goto fail_platform_driver;
+ }
+
+ ret = platform_device_add(msipf_device);
+ if (ret)
+ goto fail_platform_device1;
+
+ ret = sysfs_create_group(&msipf_device->dev.kobj, &msipf_attribute_group);
+ if (ret)
+ goto fail_platform_device2;
+
+ /* Disable automatic brightness control by default because
+ * this module was probably loaded to do brightness control in
+ * software. */
+
+ if (auto_brightness != 2)
+ set_auto_brightness(auto_brightness);
+
+ printk(KERN_INFO "msi-laptop: driver "MSI_DRIVER_VERSION" successfully loaded.\n");
+
+ return 0;
+
+fail_platform_device2:
+
+ platform_device_del(msipf_device);
+
+fail_platform_device1:
+
+ platform_device_put(msipf_device);
+
+fail_platform_driver:
+
+ platform_driver_unregister(&msipf_driver);
+
+fail_backlight:
+
+ backlight_device_unregister(msibl_device);
+
+ return ret;
+}
+
+static void __exit msi_cleanup(void)
+{
+
+ sysfs_remove_group(&msipf_device->dev.kobj, &msipf_attribute_group);
+ platform_device_unregister(msipf_device);
+ platform_driver_unregister(&msipf_driver);
+ backlight_device_unregister(msibl_device);
+
+ /* Enable automatic brightness control again */
+ if (auto_brightness != 2)
+ set_auto_brightness(1);
+
+ printk(KERN_INFO "msi-laptop: driver unloaded.\n");
+}
+
+module_init(msi_init);
+module_exit(msi_cleanup);
+
+MODULE_AUTHOR("Lennart Poettering");
+MODULE_DESCRIPTION("MSI Laptop Support");
+MODULE_VERSION(MSI_DRIVER_VERSION);
+MODULE_LICENSE("GPL");
__b44_set_mac_addr(bp);
- if (dev->flags & IFF_ALLMULTI)
+ if ((dev->flags & IFF_ALLMULTI) ||
+ (dev->mc_count > B44_MCAST_TABLE_SIZE))
val |= RXCONFIG_ALLMULTI;
else
i = __b44_load_mcast(bp, dev);
- for (; i < 64; i++) {
+ for (; i < 64; i++)
__b44_cam_write(bp, zero, i);
- }
+
bw32(bp, B44_RXCONFIG, val);
val = br32(bp, B44_CAM_CTRL);
bw32(bp, B44_CAM_CTRL, val | CAM_CTRL_ENABLE);
u16 *ptr = (u16 *) data;
for (i = 0; i < 128; i += 2)
- ptr[i / 2] = readw(bp->regs + 4096 + i);
+ ptr[i / 2] = cpu_to_le16(readw(bp->regs + 4096 + i));
return 0;
}
* write lock to protect from other code that also
* sets the promiscuity.
*/
- write_lock(&bond->curr_slave_lock);
+ write_lock_bh(&bond->curr_slave_lock);
if (bond_info->primary_is_promisc &&
(++bond_info->rlb_promisc_timeout_counter >= RLB_PROMISC_TIMEOUT)) {
bond_info->primary_is_promisc = 0;
}
- write_unlock(&bond->curr_slave_lock);
+ write_unlock_bh(&bond->curr_slave_lock);
if (bond_info->rlb_rebalance) {
bond_info->rlb_rebalance = 0;
#include <asm/io.h>
#define DRV_NAME "ehea"
-#define DRV_VERSION "EHEA_0028"
+#define DRV_VERSION "EHEA_0034"
#define EHEA_MSG_DEFAULT (NETIF_MSG_LINK | NETIF_MSG_TIMER \
| NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
#define EHEA_MAX_ENTRIES_SQ 32767
#define EHEA_MIN_ENTRIES_QP 127
+#define EHEA_SMALL_QUEUES
#define EHEA_NUM_TX_QP 1
#ifdef EHEA_SMALL_QUEUES
#define EHEA_DEF_ENTRIES_RQ2 1023
#define EHEA_DEF_ENTRIES_RQ3 1023
#else
-#define EHEA_MAX_CQE_COUNT 32000
-#define EHEA_DEF_ENTRIES_SQ 16000
-#define EHEA_DEF_ENTRIES_RQ1 32080
-#define EHEA_DEF_ENTRIES_RQ2 4020
-#define EHEA_DEF_ENTRIES_RQ3 4020
+#define EHEA_MAX_CQE_COUNT 4080
+#define EHEA_DEF_ENTRIES_SQ 4080
+#define EHEA_DEF_ENTRIES_RQ1 8160
+#define EHEA_DEF_ENTRIES_RQ2 2040
+#define EHEA_DEF_ENTRIES_RQ3 2040
#endif
#define EHEA_MAX_ENTRIES_EQ 20
if (EHEA_BMASK_GET(NEQE_PORT_UP, eqe)) {
if (!netif_carrier_ok(port->netdev)) {
ret = ehea_sense_port_attr(
- adapter->port[portnum]);
+ port);
if (ret) {
ehea_error("failed resensing port "
"attributes");
netif_stop_queue(port->netdev);
break;
default:
- ehea_error("unknown event code %x", ec);
+ ehea_error("unknown event code %x, eqe=0x%lX", ec, eqe);
break;
}
}
if (netif_msg_tx_queued(port)) {
ehea_info("post swqe on QP %d", pr->qp->init_attr.qp_nr);
- ehea_dump(swqe, sizeof(*swqe), "swqe");
+ ehea_dump(swqe, 512, "swqe");
}
ehea_post_swqe(pr->qp, swqe);
#define H_ALL_RES_TYPE_MR 5
#define H_ALL_RES_TYPE_MW 6
-static long ehea_hcall_9arg_9ret(unsigned long opcode,
- unsigned long arg1, unsigned long arg2,
- unsigned long arg3, unsigned long arg4,
- unsigned long arg5, unsigned long arg6,
- unsigned long arg7, unsigned long arg8,
- unsigned long arg9, unsigned long *out1,
- unsigned long *out2,unsigned long *out3,
- unsigned long *out4,unsigned long *out5,
- unsigned long *out6,unsigned long *out7,
- unsigned long *out8,unsigned long *out9)
+static long ehea_plpar_hcall_norets(unsigned long opcode,
+ unsigned long arg1,
+ unsigned long arg2,
+ unsigned long arg3,
+ unsigned long arg4,
+ unsigned long arg5,
+ unsigned long arg6,
+ unsigned long arg7)
{
- long hret;
+ long ret;
int i, sleep_msecs;
for (i = 0; i < 5; i++) {
- hret = plpar_hcall_9arg_9ret(opcode,arg1, arg2, arg3, arg4,
- arg5, arg6, arg7, arg8, arg9, out1,
- out2, out3, out4, out5, out6, out7,
- out8, out9);
- if (H_IS_LONG_BUSY(hret)) {
- sleep_msecs = get_longbusy_msecs(hret);
+ ret = plpar_hcall_norets(opcode, arg1, arg2, arg3, arg4,
+ arg5, arg6, arg7);
+
+ if (H_IS_LONG_BUSY(ret)) {
+ sleep_msecs = get_longbusy_msecs(ret);
msleep_interruptible(sleep_msecs);
continue;
}
- if (hret < H_SUCCESS)
- ehea_error("op=%lx hret=%lx "
- "i1=%lx i2=%lx i3=%lx i4=%lx i5=%lx i6=%lx "
- "i7=%lx i8=%lx i9=%lx "
- "o1=%lx o2=%lx o3=%lx o4=%lx o5=%lx o6=%lx "
- "o7=%lx o8=%lx o9=%lx",
- opcode, hret, arg1, arg2, arg3, arg4, arg5,
- arg6, arg7, arg8, arg9, *out1, *out2, *out3,
- *out4, *out5, *out6, *out7, *out8, *out9);
- return hret;
+ if (ret < H_SUCCESS)
+ ehea_error("opcode=%lx ret=%lx"
+ " arg1=%lx arg2=%lx arg3=%lx arg4=%lx"
+ " arg5=%lx arg6=%lx arg7=%lx ",
+ opcode, ret,
+ arg1, arg2, arg3, arg4, arg5,
+ arg6, arg7);
+
+ return ret;
}
+
return H_BUSY;
}
-u64 ehea_h_query_ehea_qp(const u64 adapter_handle, const u8 qp_category,
- const u64 qp_handle, const u64 sel_mask, void *cb_addr)
+static long ehea_plpar_hcall9(unsigned long opcode,
+ unsigned long *outs, /* array of 9 outputs */
+ unsigned long arg1,
+ unsigned long arg2,
+ unsigned long arg3,
+ unsigned long arg4,
+ unsigned long arg5,
+ unsigned long arg6,
+ unsigned long arg7,
+ unsigned long arg8,
+ unsigned long arg9)
{
- u64 dummy;
+ long ret;
+ int i, sleep_msecs;
- if ((((u64)cb_addr) & (PAGE_SIZE - 1)) != 0) {
- ehea_error("not on pageboundary");
- return H_PARAMETER;
+ for (i = 0; i < 5; i++) {
+ ret = plpar_hcall9(opcode, outs,
+ arg1, arg2, arg3, arg4, arg5,
+ arg6, arg7, arg8, arg9);
+
+ if (H_IS_LONG_BUSY(ret)) {
+ sleep_msecs = get_longbusy_msecs(ret);
+ msleep_interruptible(sleep_msecs);
+ continue;
+ }
+
+ if (ret < H_SUCCESS)
+ ehea_error("opcode=%lx ret=%lx"
+ " arg1=%lx arg2=%lx arg3=%lx arg4=%lx"
+ " arg5=%lx arg6=%lx arg7=%lx arg8=%lx"
+ " arg9=%lx"
+ " out1=%lx out2=%lx out3=%lx out4=%lx"
+ " out5=%lx out6=%lx out7=%lx out8=%lx"
+ " out9=%lx",
+ opcode, ret,
+ arg1, arg2, arg3, arg4, arg5,
+ arg6, arg7, arg8, arg9,
+ outs[0], outs[1], outs[2], outs[3],
+ outs[4], outs[5], outs[6], outs[7],
+ outs[8]);
+
+ return ret;
}
- return ehea_hcall_9arg_9ret(H_QUERY_HEA_QP,
- adapter_handle, /* R4 */
- qp_category, /* R5 */
- qp_handle, /* R6 */
- sel_mask, /* R7 */
- virt_to_abs(cb_addr), /* R8 */
- 0, 0, 0, 0, /* R9-R12 */
- &dummy, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
+ return H_BUSY;
+}
+
+u64 ehea_h_query_ehea_qp(const u64 adapter_handle, const u8 qp_category,
+ const u64 qp_handle, const u64 sel_mask, void *cb_addr)
+{
+ return ehea_plpar_hcall_norets(H_QUERY_HEA_QP,
+ adapter_handle, /* R4 */
+ qp_category, /* R5 */
+ qp_handle, /* R6 */
+ sel_mask, /* R7 */
+ virt_to_abs(cb_addr), /* R8 */
+ 0, 0);
}
/* input param R5 */
u64 *qp_handle, struct h_epas *h_epas)
{
u64 hret;
+ u64 outs[PLPAR_HCALL9_BUFSIZE];
u64 allocate_controls =
EHEA_BMASK_SET(H_ALL_RES_QP_EQPO, init_attr->low_lat_rq1 ? 1 : 0)
EHEA_BMASK_SET(H_ALL_RES_QP_TH_RQ2, init_attr->rq2_threshold)
| EHEA_BMASK_SET(H_ALL_RES_QP_TH_RQ3, init_attr->rq3_threshold);
- u64 r5_out = 0;
- u64 r6_out = 0;
- u64 r7_out = 0;
- u64 r8_out = 0;
- u64 r9_out = 0;
- u64 g_la_user_out = 0;
- u64 r11_out = 0;
- u64 r12_out = 0;
-
- hret = ehea_hcall_9arg_9ret(H_ALLOC_HEA_RESOURCE,
- adapter_handle, /* R4 */
- allocate_controls, /* R5 */
- init_attr->send_cq_handle, /* R6 */
- init_attr->recv_cq_handle, /* R7 */
- init_attr->aff_eq_handle, /* R8 */
- r9_reg, /* R9 */
- max_r10_reg, /* R10 */
- r11_in, /* R11 */
- threshold, /* R12 */
- qp_handle, /* R4 */
- &r5_out, /* R5 */
- &r6_out, /* R6 */
- &r7_out, /* R7 */
- &r8_out, /* R8 */
- &r9_out, /* R9 */
- &g_la_user_out, /* R10 */
- &r11_out, /* R11 */
- &r12_out); /* R12 */
-
- init_attr->qp_nr = (u32)r5_out;
+ hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE,
+ outs,
+ adapter_handle, /* R4 */
+ allocate_controls, /* R5 */
+ init_attr->send_cq_handle, /* R6 */
+ init_attr->recv_cq_handle, /* R7 */
+ init_attr->aff_eq_handle, /* R8 */
+ r9_reg, /* R9 */
+ max_r10_reg, /* R10 */
+ r11_in, /* R11 */
+ threshold); /* R12 */
+
+ *qp_handle = outs[0];
+ init_attr->qp_nr = (u32)outs[1];
init_attr->act_nr_send_wqes =
- (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_SWQE, r6_out);
+ (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_SWQE, outs[2]);
init_attr->act_nr_rwqes_rq1 =
- (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R1WQE, r6_out);
+ (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R1WQE, outs[2]);
init_attr->act_nr_rwqes_rq2 =
- (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R2WQE, r6_out);
+ (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R2WQE, outs[2]);
init_attr->act_nr_rwqes_rq3 =
- (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R3WQE, r6_out);
+ (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R3WQE, outs[2]);
init_attr->act_wqe_size_enc_sq = init_attr->wqe_size_enc_sq;
init_attr->act_wqe_size_enc_rq1 = init_attr->wqe_size_enc_rq1;
init_attr->act_wqe_size_enc_rq3 = init_attr->wqe_size_enc_rq3;
init_attr->nr_sq_pages =
- (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_SQ, r8_out);
+ (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_SQ, outs[4]);
init_attr->nr_rq1_pages =
- (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ1, r8_out);
+ (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ1, outs[4]);
init_attr->nr_rq2_pages =
- (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ2, r9_out);
+ (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ2, outs[5]);
init_attr->nr_rq3_pages =
- (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ3, r9_out);
+ (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ3, outs[5]);
init_attr->liobn_sq =
- (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_SQ, r11_out);
+ (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_SQ, outs[7]);
init_attr->liobn_rq1 =
- (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ1, r11_out);
+ (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ1, outs[7]);
init_attr->liobn_rq2 =
- (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ2, r12_out);
+ (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ2, outs[8]);
init_attr->liobn_rq3 =
- (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ3, r12_out);
+ (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ3, outs[8]);
if (!hret)
- hcp_epas_ctor(h_epas, g_la_user_out, g_la_user_out);
+ hcp_epas_ctor(h_epas, outs[6], outs[6]);
return hret;
}
struct ehea_cq_attr *cq_attr,
u64 *cq_handle, struct h_epas *epas)
{
- u64 hret, dummy, act_nr_of_cqes_out, act_pages_out;
- u64 g_la_privileged_out, g_la_user_out;
-
- hret = ehea_hcall_9arg_9ret(H_ALLOC_HEA_RESOURCE,
- adapter_handle, /* R4 */
- H_ALL_RES_TYPE_CQ, /* R5 */
- cq_attr->eq_handle, /* R6 */
- cq_attr->cq_token, /* R7 */
- cq_attr->max_nr_of_cqes, /* R8 */
- 0, 0, 0, 0, /* R9-R12 */
- cq_handle, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &act_nr_of_cqes_out, /* R7 */
- &act_pages_out, /* R8 */
- &g_la_privileged_out, /* R9 */
- &g_la_user_out, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
-
- cq_attr->act_nr_of_cqes = act_nr_of_cqes_out;
- cq_attr->nr_pages = act_pages_out;
+ u64 hret;
+ u64 outs[PLPAR_HCALL9_BUFSIZE];
+
+ hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE,
+ outs,
+ adapter_handle, /* R4 */
+ H_ALL_RES_TYPE_CQ, /* R5 */
+ cq_attr->eq_handle, /* R6 */
+ cq_attr->cq_token, /* R7 */
+ cq_attr->max_nr_of_cqes, /* R8 */
+ 0, 0, 0, 0); /* R9-R12 */
+
+ *cq_handle = outs[0];
+ cq_attr->act_nr_of_cqes = outs[3];
+ cq_attr->nr_pages = outs[4];
if (!hret)
- hcp_epas_ctor(epas, g_la_privileged_out, g_la_user_out);
+ hcp_epas_ctor(epas, outs[5], outs[6]);
return hret;
}
u64 ehea_h_alloc_resource_eq(const u64 adapter_handle,
struct ehea_eq_attr *eq_attr, u64 *eq_handle)
{
- u64 hret, dummy, eq_liobn, allocate_controls;
- u64 ist1_out, ist2_out, ist3_out, ist4_out;
- u64 act_nr_of_eqes_out, act_pages_out;
+ u64 hret, allocate_controls;
+ u64 outs[PLPAR_HCALL9_BUFSIZE];
/* resource type */
allocate_controls =
| EHEA_BMASK_SET(H_ALL_RES_EQ_INH_EQE_GEN, !eq_attr->eqe_gen)
| EHEA_BMASK_SET(H_ALL_RES_EQ_NON_NEQ_ISN, 1);
- hret = ehea_hcall_9arg_9ret(H_ALLOC_HEA_RESOURCE,
- adapter_handle, /* R4 */
- allocate_controls, /* R5 */
- eq_attr->max_nr_of_eqes, /* R6 */
- 0, 0, 0, 0, 0, 0, /* R7-R10 */
- eq_handle, /* R4 */
- &dummy, /* R5 */
- &eq_liobn, /* R6 */
- &act_nr_of_eqes_out, /* R7 */
- &act_pages_out, /* R8 */
- &ist1_out, /* R9 */
- &ist2_out, /* R10 */
- &ist3_out, /* R11 */
- &ist4_out); /* R12 */
-
- eq_attr->act_nr_of_eqes = act_nr_of_eqes_out;
- eq_attr->nr_pages = act_pages_out;
- eq_attr->ist1 = ist1_out;
- eq_attr->ist2 = ist2_out;
- eq_attr->ist3 = ist3_out;
- eq_attr->ist4 = ist4_out;
+ hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE,
+ outs,
+ adapter_handle, /* R4 */
+ allocate_controls, /* R5 */
+ eq_attr->max_nr_of_eqes, /* R6 */
+ 0, 0, 0, 0, 0, 0); /* R7-R10 */
+
+ *eq_handle = outs[0];
+ eq_attr->act_nr_of_eqes = outs[3];
+ eq_attr->nr_pages = outs[4];
+ eq_attr->ist1 = outs[5];
+ eq_attr->ist2 = outs[6];
+ eq_attr->ist3 = outs[7];
+ eq_attr->ist4 = outs[8];
return hret;
}
void *cb_addr, u64 *inv_attr_id, u64 *proc_mask,
u16 *out_swr, u16 *out_rwr)
{
- u64 hret, dummy, act_out_swr, act_out_rwr;
-
- if ((((u64)cb_addr) & (PAGE_SIZE - 1)) != 0) {
- ehea_error("not on page boundary");
- return H_PARAMETER;
- }
-
- hret = ehea_hcall_9arg_9ret(H_MODIFY_HEA_QP,
- adapter_handle, /* R4 */
- (u64) cat, /* R5 */
- qp_handle, /* R6 */
- sel_mask, /* R7 */
- virt_to_abs(cb_addr), /* R8 */
- 0, 0, 0, 0, /* R9-R12 */
- inv_attr_id, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &act_out_swr, /* R7 */
- &act_out_rwr, /* R8 */
- proc_mask, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
- *out_swr = act_out_swr;
- *out_rwr = act_out_rwr;
+ u64 hret;
+ u64 outs[PLPAR_HCALL9_BUFSIZE];
+
+ hret = ehea_plpar_hcall9(H_MODIFY_HEA_QP,
+ outs,
+ adapter_handle, /* R4 */
+ (u64) cat, /* R5 */
+ qp_handle, /* R6 */
+ sel_mask, /* R7 */
+ virt_to_abs(cb_addr), /* R8 */
+ 0, 0, 0, 0); /* R9-R12 */
+
+ *inv_attr_id = outs[0];
+ *out_swr = outs[3];
+ *out_rwr = outs[4];
+ *proc_mask = outs[5];
return hret;
}
const u8 queue_type, const u64 resource_handle,
const u64 log_pageaddr, u64 count)
{
- u64 dummy, reg_control;
+ u64 reg_control;
reg_control = EHEA_BMASK_SET(H_REG_RPAGE_PAGE_SIZE, pagesize)
| EHEA_BMASK_SET(H_REG_RPAGE_QT, queue_type);
- return ehea_hcall_9arg_9ret(H_REGISTER_HEA_RPAGES,
- adapter_handle, /* R4 */
- reg_control, /* R5 */
- resource_handle, /* R6 */
- log_pageaddr, /* R7 */
- count, /* R8 */
- 0, 0, 0, 0, /* R9-R12 */
- &dummy, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
+ return ehea_plpar_hcall_norets(H_REGISTER_HEA_RPAGES,
+ adapter_handle, /* R4 */
+ reg_control, /* R5 */
+ resource_handle, /* R6 */
+ log_pageaddr, /* R7 */
+ count, /* R8 */
+ 0, 0); /* R9-R10 */
}
u64 ehea_h_register_smr(const u64 adapter_handle, const u64 orig_mr_handle,
const u64 vaddr_in, const u32 access_ctrl, const u32 pd,
struct ehea_mr *mr)
{
- u64 hret, dummy, lkey_out;
-
- hret = ehea_hcall_9arg_9ret(H_REGISTER_SMR,
- adapter_handle , /* R4 */
- orig_mr_handle, /* R5 */
- vaddr_in, /* R6 */
- (((u64)access_ctrl) << 32ULL), /* R7 */
- pd, /* R8 */
- 0, 0, 0, 0, /* R9-R12 */
- &mr->handle, /* R4 */
- &dummy, /* R5 */
- &lkey_out, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
- mr->lkey = (u32)lkey_out;
+ u64 hret;
+ u64 outs[PLPAR_HCALL9_BUFSIZE];
+
+ hret = ehea_plpar_hcall9(H_REGISTER_SMR,
+ outs,
+ adapter_handle , /* R4 */
+ orig_mr_handle, /* R5 */
+ vaddr_in, /* R6 */
+ (((u64)access_ctrl) << 32ULL), /* R7 */
+ pd, /* R8 */
+ 0, 0, 0, 0); /* R9-R12 */
+
+ mr->handle = outs[0];
+ mr->lkey = (u32)outs[2];
return hret;
}
u64 ehea_h_disable_and_get_hea(const u64 adapter_handle, const u64 qp_handle)
{
- u64 hret, dummy, ladr_next_sq_wqe_out;
- u64 ladr_next_rq1_wqe_out, ladr_next_rq2_wqe_out, ladr_next_rq3_wqe_out;
-
- hret = ehea_hcall_9arg_9ret(H_DISABLE_AND_GET_HEA,
- adapter_handle, /* R4 */
- H_DISABLE_GET_EHEA_WQE_P, /* R5 */
- qp_handle, /* R6 */
- 0, 0, 0, 0, 0, 0, /* R7-R12 */
- &ladr_next_sq_wqe_out, /* R4 */
- &ladr_next_rq1_wqe_out, /* R5 */
- &ladr_next_rq2_wqe_out, /* R6 */
- &ladr_next_rq3_wqe_out, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
- return hret;
+ u64 outs[PLPAR_HCALL9_BUFSIZE];
+
+ return ehea_plpar_hcall9(H_DISABLE_AND_GET_HEA,
+ outs,
+ adapter_handle, /* R4 */
+ H_DISABLE_GET_EHEA_WQE_P, /* R5 */
+ qp_handle, /* R6 */
+ 0, 0, 0, 0, 0, 0); /* R7-R12 */
}
u64 ehea_h_free_resource(const u64 adapter_handle, const u64 res_handle)
{
- u64 dummy;
-
- return ehea_hcall_9arg_9ret(H_FREE_RESOURCE,
- adapter_handle, /* R4 */
- res_handle, /* R5 */
- 0, 0, 0, 0, 0, 0, 0, /* R6-R12 */
- &dummy, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
+ return ehea_plpar_hcall_norets(H_FREE_RESOURCE,
+ adapter_handle, /* R4 */
+ res_handle, /* R5 */
+ 0, 0, 0, 0, 0); /* R6-R10 */
}
u64 ehea_h_alloc_resource_mr(const u64 adapter_handle, const u64 vaddr,
const u64 length, const u32 access_ctrl,
const u32 pd, u64 *mr_handle, u32 *lkey)
{
- u64 hret, dummy, lkey_out;
-
- hret = ehea_hcall_9arg_9ret(H_ALLOC_HEA_RESOURCE,
- adapter_handle, /* R4 */
- 5, /* R5 */
- vaddr, /* R6 */
- length, /* R7 */
- (((u64) access_ctrl) << 32ULL),/* R8 */
- pd, /* R9 */
- 0, 0, 0, /* R10-R12 */
- mr_handle, /* R4 */
- &dummy, /* R5 */
- &lkey_out, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
- *lkey = (u32) lkey_out;
-
+ u64 hret;
+ u64 outs[PLPAR_HCALL9_BUFSIZE];
+
+ hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE,
+ outs,
+ adapter_handle, /* R4 */
+ 5, /* R5 */
+ vaddr, /* R6 */
+ length, /* R7 */
+ (((u64) access_ctrl) << 32ULL), /* R8 */
+ pd, /* R9 */
+ 0, 0, 0); /* R10-R12 */
+
+ *mr_handle = outs[0];
+ *lkey = (u32)outs[2];
return hret;
}
u64 ehea_h_query_ehea(const u64 adapter_handle, void *cb_addr)
{
- u64 hret, dummy, cb_logaddr;
+ u64 hret, cb_logaddr;
cb_logaddr = virt_to_abs(cb_addr);
- hret = ehea_hcall_9arg_9ret(H_QUERY_HEA,
- adapter_handle, /* R4 */
- cb_logaddr, /* R5 */
- 0, 0, 0, 0, 0, 0, 0, /* R6-R12 */
- &dummy, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
+ hret = ehea_plpar_hcall_norets(H_QUERY_HEA,
+ adapter_handle, /* R4 */
+ cb_logaddr, /* R5 */
+ 0, 0, 0, 0, 0); /* R6-R10 */
#ifdef DEBUG
ehea_dmp(cb_addr, sizeof(struct hcp_query_ehea), "hcp_query_ehea");
#endif
const u8 cb_cat, const u64 select_mask,
void *cb_addr)
{
- u64 port_info, dummy;
+ u64 port_info;
u64 cb_logaddr = virt_to_abs(cb_addr);
u64 arr_index = 0;
port_info = EHEA_BMASK_SET(H_MEHEAPORT_CAT, cb_cat)
| EHEA_BMASK_SET(H_MEHEAPORT_PN, port_num);
- return ehea_hcall_9arg_9ret(H_QUERY_HEA_PORT,
- adapter_handle, /* R4 */
- port_info, /* R5 */
- select_mask, /* R6 */
- arr_index, /* R7 */
- cb_logaddr, /* R8 */
- 0, 0, 0, 0, /* R9-R12 */
- &dummy, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
+ return ehea_plpar_hcall_norets(H_QUERY_HEA_PORT,
+ adapter_handle, /* R4 */
+ port_info, /* R5 */
+ select_mask, /* R6 */
+ arr_index, /* R7 */
+ cb_logaddr, /* R8 */
+ 0, 0); /* R9-R10 */
}
u64 ehea_h_modify_ehea_port(const u64 adapter_handle, const u16 port_num,
const u8 cb_cat, const u64 select_mask,
void *cb_addr)
{
- u64 port_info, dummy, inv_attr_ident, proc_mask;
+ u64 outs[PLPAR_HCALL9_BUFSIZE];
+ u64 port_info;
u64 arr_index = 0;
u64 cb_logaddr = virt_to_abs(cb_addr);
#ifdef DEBUG
ehea_dump(cb_addr, sizeof(struct hcp_ehea_port_cb0), "Before HCALL");
#endif
- return ehea_hcall_9arg_9ret(H_MODIFY_HEA_PORT,
- adapter_handle, /* R4 */
- port_info, /* R5 */
- select_mask, /* R6 */
- arr_index, /* R7 */
- cb_logaddr, /* R8 */
- 0, 0, 0, 0, /* R9-R12 */
- &inv_attr_ident, /* R4 */
- &proc_mask, /* R5 */
- &dummy, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
+ return ehea_plpar_hcall9(H_MODIFY_HEA_PORT,
+ outs,
+ adapter_handle, /* R4 */
+ port_info, /* R5 */
+ select_mask, /* R6 */
+ arr_index, /* R7 */
+ cb_logaddr, /* R8 */
+ 0, 0, 0, 0); /* R9-R12 */
}
u64 ehea_h_reg_dereg_bcmc(const u64 adapter_handle, const u16 port_num,
const u8 reg_type, const u64 mc_mac_addr,
const u16 vlan_id, const u32 hcall_id)
{
- u64 r5_port_num, r6_reg_type, r7_mc_mac_addr, r8_vlan_id, dummy;
+ u64 r5_port_num, r6_reg_type, r7_mc_mac_addr, r8_vlan_id;
u64 mac_addr = mc_mac_addr >> 16;
r5_port_num = EHEA_BMASK_SET(H_REGBCMC_PN, port_num);
r7_mc_mac_addr = EHEA_BMASK_SET(H_REGBCMC_MACADDR, mac_addr);
r8_vlan_id = EHEA_BMASK_SET(H_REGBCMC_VLANID, vlan_id);
- return ehea_hcall_9arg_9ret(hcall_id,
- adapter_handle, /* R4 */
- r5_port_num, /* R5 */
- r6_reg_type, /* R6 */
- r7_mc_mac_addr, /* R7 */
- r8_vlan_id, /* R8 */
- 0, 0, 0, 0, /* R9-R12 */
- &dummy, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
+ return ehea_plpar_hcall_norets(hcall_id,
+ adapter_handle, /* R4 */
+ r5_port_num, /* R5 */
+ r6_reg_type, /* R6 */
+ r7_mc_mac_addr, /* R7 */
+ r8_vlan_id, /* R8 */
+ 0, 0); /* R9-R12 */
}
u64 ehea_h_reset_events(const u64 adapter_handle, const u64 neq_handle,
const u64 event_mask)
{
- u64 dummy;
-
- return ehea_hcall_9arg_9ret(H_RESET_EVENTS,
- adapter_handle, /* R4 */
- neq_handle, /* R5 */
- event_mask, /* R6 */
- 0, 0, 0, 0, 0, 0, /* R7-R12 */
- &dummy, /* R4 */
- &dummy, /* R5 */
- &dummy, /* R6 */
- &dummy, /* R7 */
- &dummy, /* R8 */
- &dummy, /* R9 */
- &dummy, /* R10 */
- &dummy, /* R11 */
- &dummy); /* R12 */
+ return ehea_plpar_hcall_norets(H_RESET_EVENTS,
+ adapter_handle, /* R4 */
+ neq_handle, /* R5 */
+ event_mask, /* R6 */
+ 0, 0, 0, 0); /* R7-R12 */
}
#include <linux/skbuff.h>
#include <linux/bitops.h>
#include <linux/jiffies.h>
+#include <linux/io.h>
#include <asm/system.h>
-#include <asm/io.h>
#include <asm/dma.h>
u8 __iomem *base = get_hwbase(dev);
u32 events;
int i;
+ unsigned long flags;
dprintk(KERN_DEBUG "%s: nv_nic_irq_tx\n", dev->name);
if (!(events & np->irqmask))
break;
- spin_lock_irq(&np->lock);
+ spin_lock_irqsave(&np->lock, flags);
nv_tx_done(dev);
- spin_unlock_irq(&np->lock);
+ spin_unlock_irqrestore(&np->lock, flags);
if (events & (NVREG_IRQ_TX_ERR)) {
dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n",
dev->name, events);
}
if (i > max_interrupt_work) {
- spin_lock_irq(&np->lock);
+ spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_TX_ALL, base + NvRegIrqMask);
pci_push(base);
mod_timer(&np->nic_poll, jiffies + POLL_WAIT);
}
printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_tx.\n", dev->name, i);
- spin_unlock_irq(&np->lock);
+ spin_unlock_irqrestore(&np->lock, flags);
break;
}
u8 __iomem *base = get_hwbase(dev);
u32 events;
int i;
+ unsigned long flags;
dprintk(KERN_DEBUG "%s: nv_nic_irq_rx\n", dev->name);
nv_rx_process(dev, dev->weight);
if (nv_alloc_rx(dev)) {
- spin_lock_irq(&np->lock);
+ spin_lock_irqsave(&np->lock, flags);
if (!np->in_shutdown)
mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
- spin_unlock_irq(&np->lock);
+ spin_unlock_irqrestore(&np->lock, flags);
}
if (i > max_interrupt_work) {
- spin_lock_irq(&np->lock);
+ spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
pci_push(base);
mod_timer(&np->nic_poll, jiffies + POLL_WAIT);
}
printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_rx.\n", dev->name, i);
- spin_unlock_irq(&np->lock);
+ spin_unlock_irqrestore(&np->lock, flags);
break;
}
}
u8 __iomem *base = get_hwbase(dev);
u32 events;
int i;
+ unsigned long flags;
dprintk(KERN_DEBUG "%s: nv_nic_irq_other\n", dev->name);
break;
if (events & NVREG_IRQ_LINK) {
- spin_lock_irq(&np->lock);
+ spin_lock_irqsave(&np->lock, flags);
nv_link_irq(dev);
- spin_unlock_irq(&np->lock);
+ spin_unlock_irqrestore(&np->lock, flags);
}
if (np->need_linktimer && time_after(jiffies, np->link_timeout)) {
- spin_lock_irq(&np->lock);
+ spin_lock_irqsave(&np->lock, flags);
nv_linkchange(dev);
- spin_unlock_irq(&np->lock);
+ spin_unlock_irqrestore(&np->lock, flags);
np->link_timeout = jiffies + LINK_TIMEOUT;
}
if (events & (NVREG_IRQ_UNKNOWN)) {
dev->name, events);
}
if (i > max_interrupt_work) {
- spin_lock_irq(&np->lock);
+ spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_OTHER, base + NvRegIrqMask);
pci_push(base);
mod_timer(&np->nic_poll, jiffies + POLL_WAIT);
}
printk(KERN_DEBUG "%s: too many iterations (%d) in nv_nic_irq_other.\n", dev->name, i);
- spin_unlock_irq(&np->lock);
+ spin_unlock_irqrestore(&np->lock, flags);
break;
}
}
free_index = pool->consumer_index++ % pool->size;
+ pool->consumer_index = free_index;
index = pool->free_map[free_index];
ibmveth_assert(index != IBM_VETH_INVALID_MAP);
if(lpar_rc != H_SUCCESS) {
pool->free_map[free_index] = index;
pool->skbuff[index] = NULL;
- pool->consumer_index--;
+ if (pool->consumer_index == 0)
+ pool->consumer_index = pool->size - 1;
+ else
+ pool->consumer_index--;
dma_unmap_single(&adapter->vdev->dev,
pool->dma_addr[index], pool->buff_size,
DMA_FROM_DEVICE);
DMA_FROM_DEVICE);
free_index = adapter->rx_buff_pool[pool].producer_index++ % adapter->rx_buff_pool[pool].size;
+ adapter->rx_buff_pool[pool].producer_index = free_index;
adapter->rx_buff_pool[pool].free_map[free_index] = index;
mb();
&adapter->rx_buff_pool[i]);
}
+static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
+ union ibmveth_buf_desc rxq_desc, u64 mac_address)
+{
+ int rc, try_again = 1;
+
+ /* After a kexec the adapter will still be open, so our attempt to
+ * open it will fail. So if we get a failure we free the adapter and
+ * try again, but only once. */
+retry:
+ rc = h_register_logical_lan(adapter->vdev->unit_address,
+ adapter->buffer_list_dma, rxq_desc.desc,
+ adapter->filter_list_dma, mac_address);
+
+ if (rc != H_SUCCESS && try_again) {
+ do {
+ rc = h_free_logical_lan(adapter->vdev->unit_address);
+ } while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));
+
+ try_again = 0;
+ goto retry;
+ }
+
+ return rc;
+}
+
static int ibmveth_open(struct net_device *netdev)
{
struct ibmveth_adapter *adapter = netdev->priv;
ibmveth_debug_printk("filter list @ 0x%p\n", adapter->filter_list_addr);
ibmveth_debug_printk("receive q @ 0x%p\n", adapter->rx_queue.queue_addr);
+ h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE);
- lpar_rc = h_register_logical_lan(adapter->vdev->unit_address,
- adapter->buffer_list_dma,
- rxq_desc.desc,
- adapter->filter_list_dma,
- mac_address);
+ lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address);
if(lpar_rc != H_SUCCESS) {
ibmveth_error_printk("h_register_logical_lan failed with %ld\n", lpar_rc);
return -EINVAL;
}
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void ibmveth_poll_controller(struct net_device *dev)
+{
+ ibmveth_replenish_task(dev->priv);
+ ibmveth_interrupt(dev->irq, dev);
+}
+#endif
+
static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
{
int rc, i;
netdev->ethtool_ops = &netdev_ethtool_ops;
netdev->change_mtu = ibmveth_change_mtu;
SET_NETDEV_DEV(netdev, &dev->dev);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ netdev->poll_controller = ibmveth_poll_controller;
+#endif
netdev->features |= NETIF_F_LLTX;
spin_lock_init(&adapter->stats_lock);
{
struct proc_dir_entry *entry;
if (ibmveth_proc_dir) {
- entry = create_proc_entry(adapter->netdev->name, S_IFREG, ibmveth_proc_dir);
+ char u_addr[10];
+ sprintf(u_addr, "%x", adapter->vdev->unit_address);
+ entry = create_proc_entry(u_addr, S_IFREG, ibmveth_proc_dir);
if (!entry) {
ibmveth_error_printk("Cannot create adapter proc entry");
} else {
static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter)
{
if (ibmveth_proc_dir) {
- remove_proc_entry(adapter->netdev->name, ibmveth_proc_dir);
+ char u_addr[10];
+ sprintf(u_addr, "%x", adapter->vdev->unit_address);
+ remove_proc_entry(u_addr, ibmveth_proc_dir);
}
}
for (offset = ETH_MIB_BAD_OCTETS_RECEIVED;
offset <= ETH_MIB_FRAMES_1024_TO_MAX_OCTETS;
offset += 4)
- *(u32 *)((char *)p + offset) = read_mib(mp, offset);
+ *(u32 *)((char *)p + offset) += read_mib(mp, offset);
p->good_octets_sent += read_mib(mp, ETH_MIB_GOOD_OCTETS_SENT_LOW);
p->good_octets_sent +=
for (offset = ETH_MIB_GOOD_FRAMES_SENT;
offset <= ETH_MIB_LATE_COLLISION;
offset += 4)
- *(u32 *)((char *)p + offset) = read_mib(mp, offset);
+ *(u32 *)((char *)p + offset) += read_mib(mp, offset);
}
/*
#include "skge.h"
#define DRV_NAME "skge"
-#define DRV_VERSION "1.8"
+#define DRV_VERSION "1.9"
#define PFX DRV_NAME " "
#define DEFAULT_TX_RING_SIZE 128
else if (hw->chip_id == CHIP_ID_YUKON)
supported &= ~SUPPORTED_1000baseT_Half;
} else
- supported = SUPPORTED_1000baseT_Full | SUPPORTED_FIBRE
- | SUPPORTED_Autoneg;
+ supported = SUPPORTED_1000baseT_Full | SUPPORTED_1000baseT_Half
+ | SUPPORTED_FIBRE | SUPPORTED_Autoneg;
return supported;
}
{
struct skge_port *skge = netdev_priv(dev);
- ecmd->tx_pause = (skge->flow_control == FLOW_MODE_LOC_SEND)
- || (skge->flow_control == FLOW_MODE_SYMMETRIC);
- ecmd->rx_pause = (skge->flow_control == FLOW_MODE_REM_SEND)
- || (skge->flow_control == FLOW_MODE_SYMMETRIC);
+ ecmd->rx_pause = (skge->flow_control == FLOW_MODE_SYMMETRIC)
+ || (skge->flow_control == FLOW_MODE_SYM_OR_REM);
+ ecmd->tx_pause = ecmd->rx_pause || (skge->flow_control == FLOW_MODE_LOC_SEND);
- ecmd->autoneg = skge->autoneg;
+ ecmd->autoneg = ecmd->rx_pause || ecmd->tx_pause;
}
static int skge_set_pauseparam(struct net_device *dev,
struct ethtool_pauseparam *ecmd)
{
struct skge_port *skge = netdev_priv(dev);
+ struct ethtool_pauseparam old;
- skge->autoneg = ecmd->autoneg;
- if (ecmd->rx_pause && ecmd->tx_pause)
- skge->flow_control = FLOW_MODE_SYMMETRIC;
- else if (ecmd->rx_pause && !ecmd->tx_pause)
- skge->flow_control = FLOW_MODE_REM_SEND;
- else if (!ecmd->rx_pause && ecmd->tx_pause)
- skge->flow_control = FLOW_MODE_LOC_SEND;
- else
- skge->flow_control = FLOW_MODE_NONE;
+ skge_get_pauseparam(dev, &old);
+
+ if (ecmd->autoneg != old.autoneg)
+ skge->flow_control = ecmd->autoneg ? FLOW_MODE_NONE : FLOW_MODE_SYMMETRIC;
+ else {
+ if (ecmd->rx_pause && ecmd->tx_pause)
+ skge->flow_control = FLOW_MODE_SYMMETRIC;
+ else if (ecmd->rx_pause && !ecmd->tx_pause)
+ skge->flow_control = FLOW_MODE_SYM_OR_REM;
+ else if (!ecmd->rx_pause && ecmd->tx_pause)
+ skge->flow_control = FLOW_MODE_LOC_SEND;
+ else
+ skge->flow_control = FLOW_MODE_NONE;
+ }
if (netif_running(dev))
skge_phy_reset(skge);
+
return 0;
}
return 0;
}
+static const char *skge_pause(enum pause_status status)
+{
+ switch(status) {
+ case FLOW_STAT_NONE:
+ return "none";
+ case FLOW_STAT_REM_SEND:
+ return "rx only";
+ case FLOW_STAT_LOC_SEND:
+ return "tx_only";
+ case FLOW_STAT_SYMMETRIC: /* Both station may send PAUSE */
+ return "both";
+ default:
+ return "indeterminated";
+ }
+}
+
+
static void skge_link_up(struct skge_port *skge)
{
skge_write8(skge->hw, SK_REG(skge->port, LNK_LED_REG),
netif_carrier_on(skge->netdev);
netif_wake_queue(skge->netdev);
- if (netif_msg_link(skge))
+ if (netif_msg_link(skge)) {
printk(KERN_INFO PFX
"%s: Link is up at %d Mbps, %s duplex, flow control %s\n",
skge->netdev->name, skge->speed,
skge->duplex == DUPLEX_FULL ? "full" : "half",
- (skge->flow_control == FLOW_MODE_NONE) ? "none" :
- (skge->flow_control == FLOW_MODE_LOC_SEND) ? "tx only" :
- (skge->flow_control == FLOW_MODE_REM_SEND) ? "rx only" :
- (skge->flow_control == FLOW_MODE_SYMMETRIC) ? "tx and rx" :
- "unknown");
+ skge_pause(skge->flow_status));
+ }
}
static void skge_link_down(struct skge_port *skge)
printk(KERN_INFO PFX "%s: Link is down.\n", skge->netdev->name);
}
+
+static void xm_link_down(struct skge_hw *hw, int port)
+{
+ struct net_device *dev = hw->dev[port];
+ struct skge_port *skge = netdev_priv(dev);
+ u16 cmd, msk;
+
+ if (hw->phy_type == SK_PHY_XMAC) {
+ msk = xm_read16(hw, port, XM_IMSK);
+ msk |= XM_IS_INP_ASS | XM_IS_LIPA_RC | XM_IS_RX_PAGE | XM_IS_AND;
+ xm_write16(hw, port, XM_IMSK, msk);
+ }
+
+ cmd = xm_read16(hw, port, XM_MMU_CMD);
+ cmd &= ~(XM_MMU_ENA_RX | XM_MMU_ENA_TX);
+ xm_write16(hw, port, XM_MMU_CMD, cmd);
+ /* dummy read to ensure writing */
+ (void) xm_read16(hw, port, XM_MMU_CMD);
+
+ if (netif_carrier_ok(dev))
+ skge_link_down(skge);
+}
+
static int __xm_phy_read(struct skge_hw *hw, int port, u16 reg, u16 *val)
{
int i;
[FLOW_MODE_NONE] = 0,
[FLOW_MODE_LOC_SEND] = PHY_AN_PAUSE_ASYM,
[FLOW_MODE_SYMMETRIC] = PHY_AN_PAUSE_CAP,
- [FLOW_MODE_REM_SEND] = PHY_AN_PAUSE_CAP | PHY_AN_PAUSE_ASYM,
+ [FLOW_MODE_SYM_OR_REM] = PHY_AN_PAUSE_CAP | PHY_AN_PAUSE_ASYM,
+};
+
+/* special defines for FIBER (88E1011S only) */
+static const u16 fiber_pause_map[] = {
+ [FLOW_MODE_NONE] = PHY_X_P_NO_PAUSE,
+ [FLOW_MODE_LOC_SEND] = PHY_X_P_ASYM_MD,
+ [FLOW_MODE_SYMMETRIC] = PHY_X_P_SYM_MD,
+ [FLOW_MODE_SYM_OR_REM] = PHY_X_P_BOTH_MD,
};
status = xm_phy_read(hw, port, PHY_BCOM_STAT);
if ((status & PHY_ST_LSYNC) == 0) {
- u16 cmd = xm_read16(hw, port, XM_MMU_CMD);
- cmd &= ~(XM_MMU_ENA_RX | XM_MMU_ENA_TX);
- xm_write16(hw, port, XM_MMU_CMD, cmd);
- /* dummy read to ensure writing */
- (void) xm_read16(hw, port, XM_MMU_CMD);
-
- if (netif_carrier_ok(dev))
- skge_link_down(skge);
+ xm_link_down(hw, port);
return;
}
return;
}
-
/* We are using IEEE 802.3z/D5.0 Table 37-4 */
switch (aux & PHY_B_AS_PAUSE_MSK) {
case PHY_B_AS_PAUSE_MSK:
- skge->flow_control = FLOW_MODE_SYMMETRIC;
+ skge->flow_status = FLOW_STAT_SYMMETRIC;
break;
case PHY_B_AS_PRR:
- skge->flow_control = FLOW_MODE_REM_SEND;
+ skge->flow_status = FLOW_STAT_REM_SEND;
break;
case PHY_B_AS_PRT:
- skge->flow_control = FLOW_MODE_LOC_SEND;
+ skge->flow_status = FLOW_STAT_LOC_SEND;
break;
default:
- skge->flow_control = FLOW_MODE_NONE;
+ skge->flow_status = FLOW_STAT_NONE;
}
skge->speed = SPEED_1000;
}
if (skge->advertising & ADVERTISED_1000baseT_Full)
ctrl |= PHY_X_AN_FD;
- switch(skge->flow_control) {
- case FLOW_MODE_NONE:
- ctrl |= PHY_X_P_NO_PAUSE;
- break;
- case FLOW_MODE_LOC_SEND:
- ctrl |= PHY_X_P_ASYM_MD;
- break;
- case FLOW_MODE_SYMMETRIC:
- ctrl |= PHY_X_P_BOTH_MD;
- break;
- }
+ ctrl |= fiber_pause_map[skge->flow_control];
xm_phy_write(hw, port, PHY_XMAC_AUNE_ADV, ctrl);
status = xm_phy_read(hw, port, PHY_XMAC_STAT);
if ((status & PHY_ST_LSYNC) == 0) {
- u16 cmd = xm_read16(hw, port, XM_MMU_CMD);
- cmd &= ~(XM_MMU_ENA_RX | XM_MMU_ENA_TX);
- xm_write16(hw, port, XM_MMU_CMD, cmd);
- /* dummy read to ensure writing */
- (void) xm_read16(hw, port, XM_MMU_CMD);
-
- if (netif_carrier_ok(dev))
- skge_link_down(skge);
+ xm_link_down(hw, port);
return;
}
}
/* We are using IEEE 802.3z/D5.0 Table 37-4 */
- if (lpa & PHY_X_P_SYM_MD)
- skge->flow_control = FLOW_MODE_SYMMETRIC;
- else if ((lpa & PHY_X_RS_PAUSE) == PHY_X_P_ASYM_MD)
- skge->flow_control = FLOW_MODE_REM_SEND;
- else if ((lpa & PHY_X_RS_PAUSE) == PHY_X_P_BOTH_MD)
- skge->flow_control = FLOW_MODE_LOC_SEND;
+ if ((skge->flow_control == FLOW_MODE_SYMMETRIC ||
+ skge->flow_control == FLOW_MODE_SYM_OR_REM) &&
+ (lpa & PHY_X_P_SYM_MD))
+ skge->flow_status = FLOW_STAT_SYMMETRIC;
+ else if (skge->flow_control == FLOW_MODE_SYM_OR_REM &&
+ (lpa & PHY_X_RS_PAUSE) == PHY_X_P_ASYM_MD)
+ /* Enable PAUSE receive, disable PAUSE transmit */
+ skge->flow_status = FLOW_STAT_REM_SEND;
+ else if (skge->flow_control == FLOW_MODE_LOC_SEND &&
+ (lpa & PHY_X_RS_PAUSE) == PHY_X_P_BOTH_MD)
+ /* Disable PAUSE receive, enable PAUSE transmit */
+ skge->flow_status = FLOW_STAT_LOC_SEND;
else
- skge->flow_control = FLOW_MODE_NONE;
-
+ skge->flow_status = FLOW_STAT_NONE;
skge->speed = SPEED_1000;
}
printk(KERN_DEBUG PFX "%s: mac interrupt status 0x%x\n",
skge->netdev->name, status);
+ if (hw->phy_type == SK_PHY_XMAC &&
+ (status & (XM_IS_INP_ASS | XM_IS_LIPA_RC)))
+ xm_link_down(hw, port);
+
if (status & XM_IS_TXF_UR) {
xm_write32(hw, port, XM_MODE, XM_MD_FTF);
++skge->net_stats.tx_fifo_errors;
{
struct skge_hw *hw = skge->hw;
int port = skge->port;
- u16 cmd;
+ u16 cmd, msk;
u32 mode;
cmd = xm_read16(hw, port, XM_MMU_CMD);
* enabling pause frame reception is required for 1000BT
* because the XMAC is not reset if the link is going down
*/
- if (skge->flow_control == FLOW_MODE_NONE ||
- skge->flow_control == FLOW_MODE_LOC_SEND)
+ if (skge->flow_status == FLOW_STAT_NONE ||
+ skge->flow_status == FLOW_STAT_LOC_SEND)
/* Disable Pause Frame Reception */
cmd |= XM_MMU_IGN_PF;
else
xm_write16(hw, port, XM_MMU_CMD, cmd);
mode = xm_read32(hw, port, XM_MODE);
- if (skge->flow_control == FLOW_MODE_SYMMETRIC ||
- skge->flow_control == FLOW_MODE_LOC_SEND) {
+ if (skge->flow_status== FLOW_STAT_SYMMETRIC ||
+ skge->flow_status == FLOW_STAT_LOC_SEND) {
/*
* Configure Pause Frame Generation
* Use internal and external Pause Frame Generation.
}
xm_write32(hw, port, XM_MODE, mode);
- xm_write16(hw, port, XM_IMSK, XM_DEF_MSK);
+ msk = XM_DEF_MSK;
+ if (hw->phy_type != SK_PHY_XMAC)
+ msk |= XM_IS_INP_ASS; /* disable GP0 interrupt bit */
+
+ xm_write16(hw, port, XM_IMSK, msk);
xm_read16(hw, port, XM_ISRC);
/* get MMU Command Reg. */
adv |= PHY_M_AN_10_FD;
if (skge->advertising & ADVERTISED_10baseT_Half)
adv |= PHY_M_AN_10_HD;
- } else /* special defines for FIBER (88E1011S only) */
- adv |= PHY_M_AN_1000X_AHD | PHY_M_AN_1000X_AFD;
- /* Set Flow-control capabilities */
- adv |= phy_pause_map[skge->flow_control];
+ /* Set Flow-control capabilities */
+ adv |= phy_pause_map[skge->flow_control];
+ } else {
+ if (skge->advertising & ADVERTISED_1000baseT_Full)
+ adv |= PHY_M_AN_1000X_AFD;
+ if (skge->advertising & ADVERTISED_1000baseT_Half)
+ adv |= PHY_M_AN_1000X_AHD;
+
+ adv |= fiber_pause_map[skge->flow_control];
+ }
/* Restart Auto-negotiation */
ctrl |= PHY_CT_ANE | PHY_CT_RE_CFG;
case FLOW_MODE_LOC_SEND:
/* disable Rx flow-control */
reg |= GM_GPCR_FC_RX_DIS | GM_GPCR_AU_FCT_DIS;
+ break;
+ case FLOW_MODE_SYMMETRIC:
+ case FLOW_MODE_SYM_OR_REM:
+ /* enable Tx & Rx flow-control */
+ break;
}
gma_write16(hw, port, GM_GP_CTRL, reg);
ctrl &= ~(GM_GPCR_RX_ENA | GM_GPCR_TX_ENA);
gma_write16(hw, port, GM_GP_CTRL, ctrl);
- if (skge->flow_control == FLOW_MODE_REM_SEND) {
+ if (skge->flow_status == FLOW_STAT_REM_SEND) {
+ ctrl = gm_phy_read(hw, port, PHY_MARV_AUNE_ADV);
+ ctrl |= PHY_M_AN_ASP;
/* restore Asymmetric Pause bit */
- gm_phy_write(hw, port, PHY_MARV_AUNE_ADV,
- gm_phy_read(hw, port,
- PHY_MARV_AUNE_ADV)
- | PHY_M_AN_ASP);
-
+ gm_phy_write(hw, port, PHY_MARV_AUNE_ADV, ctrl);
}
yukon_reset(hw, port);
/* We are using IEEE 802.3z/D5.0 Table 37-4 */
switch (phystat & PHY_M_PS_PAUSE_MSK) {
case PHY_M_PS_PAUSE_MSK:
- skge->flow_control = FLOW_MODE_SYMMETRIC;
+ skge->flow_status = FLOW_STAT_SYMMETRIC;
break;
case PHY_M_PS_RX_P_EN:
- skge->flow_control = FLOW_MODE_REM_SEND;
+ skge->flow_status = FLOW_STAT_REM_SEND;
break;
case PHY_M_PS_TX_P_EN:
- skge->flow_control = FLOW_MODE_LOC_SEND;
+ skge->flow_status = FLOW_STAT_LOC_SEND;
break;
default:
- skge->flow_control = FLOW_MODE_NONE;
+ skge->flow_status = FLOW_STAT_NONE;
}
- if (skge->flow_control == FLOW_MODE_NONE ||
+ if (skge->flow_status == FLOW_STAT_NONE ||
(skge->speed < SPEED_1000 && skge->duplex == DUPLEX_HALF))
skge_write8(hw, SK_REG(port, GMAC_CTRL), GMC_PAUSE_OFF);
else
/* Auto speed and flow control */
skge->autoneg = AUTONEG_ENABLE;
- skge->flow_control = FLOW_MODE_SYMMETRIC;
+ skge->flow_control = FLOW_MODE_SYM_OR_REM;
skge->duplex = -1;
skge->speed = -1;
skge->advertising = skge_supported_modes(hw);
XM_IS_RX_COMP = 1<<0, /* Bit 0: Frame Rx Complete */
};
-#define XM_DEF_MSK (~(XM_IS_RXC_OV | XM_IS_TXC_OV | XM_IS_RXF_OV | XM_IS_TXF_UR))
+#define XM_DEF_MSK (~(XM_IS_INP_ASS | XM_IS_LIPA_RC | \
+ XM_IS_RXF_OV | XM_IS_TXF_UR))
/* XM_HW_CFG 16 bit r/w Hardware Config Register */
struct mutex phy_mutex;
};
-enum {
- FLOW_MODE_NONE = 0, /* No Flow-Control */
- FLOW_MODE_LOC_SEND = 1, /* Local station sends PAUSE */
- FLOW_MODE_REM_SEND = 2, /* Symmetric or just remote */
+enum pause_control {
+ FLOW_MODE_NONE = 1, /* No Flow-Control */
+ FLOW_MODE_LOC_SEND = 2, /* Local station sends PAUSE */
FLOW_MODE_SYMMETRIC = 3, /* Both stations may send PAUSE */
+ FLOW_MODE_SYM_OR_REM = 4, /* Both stations may send PAUSE or
+ * just the remote station may send PAUSE
+ */
+};
+
+enum pause_status {
+ FLOW_STAT_INDETERMINATED=0, /* indeterminated */
+ FLOW_STAT_NONE, /* No Flow Control */
+ FLOW_STAT_REM_SEND, /* Remote Station sends PAUSE */
+ FLOW_STAT_LOC_SEND, /* Local station sends PAUSE */
+ FLOW_STAT_SYMMETRIC, /* Both station may send PAUSE */
};
+
struct skge_port {
u32 msg_enable;
struct skge_hw *hw;
struct net_device_stats net_stats;
struct work_struct link_thread;
+ enum pause_control flow_control;
+ enum pause_status flow_status;
u8 rx_csum;
u8 blink_on;
- u8 flow_control;
u8 wol;
u8 autoneg; /* AUTONEG_ENABLE, AUTONEG_DISABLE */
u8 duplex; /* DUPLEX_HALF, DUPLEX_FULL */
sky2_write16(hw, SK_REG(port, TX_GMF_CTRL_T), GMF_OPER_ON);
if (hw->chip_id == CHIP_ID_YUKON_EC_U) {
- sky2_write8(hw, SK_REG(port, RX_GMF_LP_THR), 768/8);
+ sky2_write8(hw, SK_REG(port, RX_GMF_LP_THR), 512/8);
sky2_write8(hw, SK_REG(port, RX_GMF_UP_THR), 1024/8);
if (hw->dev[port]->mtu > ETH_DATA_LEN) {
/* set Tx GMAC FIFO Almost Empty Threshold */
pci_dma_sync_single_for_device(sky2->hw->pdev, re->data_addr,
length, PCI_DMA_FROMDEVICE);
re->skb->ip_summed = CHECKSUM_NONE;
- __skb_put(skb, length);
+ skb_put(skb, length);
}
return skb;
}
if (skb_shinfo(skb)->nr_frags)
skb_put_frags(skb, hdr_space, length);
else
- skb_put(skb, hdr_space);
+ skb_put(skb, length);
return skb;
}
/* PCI-Express uncorrectable Error occurred */
u32 pex_err;
- pex_err = sky2_pci_read32(hw,
- hw->err_cap + PCI_ERR_UNCOR_STATUS);
+ pex_err = sky2_pci_read32(hw, PEX_UNC_ERR_STAT);
if (net_ratelimit())
printk(KERN_ERR PFX "%s: pci express error (0x%x)\n",
/* clear the interrupt */
sky2_write32(hw, B2_TST_CTRL1, TST_CFG_WRITE_ON);
- sky2_pci_write32(hw,
- hw->err_cap + PCI_ERR_UNCOR_STATUS,
- 0xffffffffUL);
+ sky2_pci_write32(hw, PEX_UNC_ERR_STAT,
+ 0xffffffffUL);
sky2_write32(hw, B2_TST_CTRL1, TST_CFG_WRITE_OFF);
-
- /* In case of fatal error mask off to keep from getting stuck */
- if (pex_err & (PCI_ERR_UNC_POISON_TLP | PCI_ERR_UNC_FCP
- | PCI_ERR_UNC_DLP)) {
+ if (pex_err & PEX_FATAL_ERRORS) {
u32 hwmsk = sky2_read32(hw, B0_HWE_IMSK);
hwmsk &= ~Y2_IS_PCI_EXP;
sky2_write32(hw, B0_HWE_IMSK, hwmsk);
}
-
}
if (status & Y2_HWE_L1_MASK)
u16 status;
u8 t8;
int i;
- u32 msk;
sky2_write8(hw, B0_CTST, CS_RST_CLR);
sky2_write8(hw, B0_CTST, CS_MRST_CLR);
/* clear any PEX errors */
- if (pci_find_capability(hw->pdev, PCI_CAP_ID_EXP)) {
- hw->err_cap = pci_find_ext_capability(hw->pdev, PCI_EXT_CAP_ID_ERR);
- if (hw->err_cap)
- sky2_pci_write32(hw,
- hw->err_cap + PCI_ERR_UNCOR_STATUS,
- 0xffffffffUL);
- }
+ if (pci_find_capability(hw->pdev, PCI_CAP_ID_EXP))
+ sky2_pci_write32(hw, PEX_UNC_ERR_STAT, 0xffffffffUL);
+
hw->pmd_type = sky2_read8(hw, B2_PMD_TYP);
hw->ports = 1;
sky2_write8(hw, RAM_BUFFER(i, B3_RI_RTO_XS2), SK_RI_TO_53);
}
- msk = Y2_HWE_ALL_MASK;
- if (!hw->err_cap)
- msk &= ~Y2_IS_PCI_EXP;
- sky2_write32(hw, B0_HWE_IMSK, msk);
+ sky2_write32(hw, B0_HWE_IMSK, Y2_HWE_ALL_MASK);
for (i = 0; i < hw->ports; i++)
sky2_gmac_reset(hw, i);
#define ETH_JUMBO_MTU 9000 /* Maximum MTU supported */
-/* PCI device specific config registers */
+/* PCI config registers */
enum {
PCI_DEV_REG1 = 0x40,
PCI_DEV_REG2 = 0x44,
+ PCI_DEV_STATUS = 0x7c,
PCI_DEV_REG3 = 0x80,
PCI_DEV_REG4 = 0x84,
PCI_DEV_REG5 = 0x88,
};
+enum {
+ PEX_DEV_CAP = 0xe4,
+ PEX_DEV_CTRL = 0xe8,
+ PEX_DEV_STA = 0xea,
+ PEX_LNK_STAT = 0xf2,
+ PEX_UNC_ERR_STAT= 0x104,
+};
+
/* Yukon-2 */
enum pci_dev_reg_1 {
PCI_Y2_PIG_ENA = 1<<31, /* Enable Plug-in-Go (YUKON-2) */
PCI_STATUS_REC_MASTER_ABORT | \
PCI_STATUS_REC_TARGET_ABORT | \
PCI_STATUS_PARITY)
+
+enum pex_dev_ctrl {
+ PEX_DC_MAX_RRS_MSK = 7<<12, /* Bit 14..12: Max. Read Request Size */
+ PEX_DC_EN_NO_SNOOP = 1<<11,/* Enable No Snoop */
+ PEX_DC_EN_AUX_POW = 1<<10,/* Enable AUX Power */
+ PEX_DC_EN_PHANTOM = 1<<9, /* Enable Phantom Functions */
+ PEX_DC_EN_EXT_TAG = 1<<8, /* Enable Extended Tag Field */
+ PEX_DC_MAX_PLS_MSK = 7<<5, /* Bit 7.. 5: Max. Payload Size Mask */
+ PEX_DC_EN_REL_ORD = 1<<4, /* Enable Relaxed Ordering */
+ PEX_DC_EN_UNS_RQ_RP = 1<<3, /* Enable Unsupported Request Reporting */
+ PEX_DC_EN_FAT_ER_RP = 1<<2, /* Enable Fatal Error Reporting */
+ PEX_DC_EN_NFA_ER_RP = 1<<1, /* Enable Non-Fatal Error Reporting */
+ PEX_DC_EN_COR_ER_RP = 1<<0, /* Enable Correctable Error Reporting */
+};
+#define PEX_DC_MAX_RD_RQ_SIZE(x) (((x)<<12) & PEX_DC_MAX_RRS_MSK)
+
+/* PEX_UNC_ERR_STAT PEX Uncorrectable Errors Status Register (Yukon-2) */
+enum pex_err {
+ PEX_UNSUP_REQ = 1<<20, /* Unsupported Request Error */
+
+ PEX_MALFOR_TLP = 1<<18, /* Malformed TLP */
+
+ PEX_UNEXP_COMP = 1<<16, /* Unexpected Completion */
+
+ PEX_COMP_TO = 1<<14, /* Completion Timeout */
+ PEX_FLOW_CTRL_P = 1<<13, /* Flow Control Protocol Error */
+ PEX_POIS_TLP = 1<<12, /* Poisoned TLP */
+
+ PEX_DATA_LINK_P = 1<<4, /* Data Link Protocol Error */
+ PEX_FATAL_ERRORS= (PEX_MALFOR_TLP | PEX_FLOW_CTRL_P | PEX_DATA_LINK_P),
+};
+
+
enum csr_regs {
B0_RAP = 0x0000,
B0_CTST = 0x0004,
struct net_device *dev[2];
int pm_cap;
- int err_cap;
u8 chip_id;
u8 chip_rev;
u8 pmd_type;
#define SMC_IRQ_FLAGS (0)
+#elif defined(CONFIG_ARCH_VERSATILE)
+
+#define SMC_CAN_USE_8BIT 1
+#define SMC_CAN_USE_16BIT 1
+#define SMC_CAN_USE_32BIT 1
+#define SMC_NOWAIT 1
+
+#define SMC_inb(a, r) readb((a) + (r))
+#define SMC_inw(a, r) readw((a) + (r))
+#define SMC_inl(a, r) readl((a) + (r))
+#define SMC_outb(v, a, r) writeb(v, (a) + (r))
+#define SMC_outw(v, a, r) writew(v, (a) + (r))
+#define SMC_outl(v, a, r) writel(v, (a) + (r))
+#define SMC_insl(a, r, p, l) readsl((a) + (r), p, l)
+#define SMC_outsl(a, r, p, l) writesl((a) + (r), p, l)
+
+#define SMC_IRQ_FLAGS (0)
+
#else
#define SMC_CAN_USE_8BIT 1
"<Jens.Osterkamp@de.ibm.com>");
MODULE_DESCRIPTION("Spider Southbridge Gigabit Ethernet driver");
MODULE_LICENSE("GPL");
+MODULE_VERSION(VERSION);
static int rx_descriptors = SPIDER_NET_RX_DESCRIPTORS_DEFAULT;
static int tx_descriptors = SPIDER_NET_TX_DESCRIPTORS_DEFAULT;
-module_param(rx_descriptors, int, 0644);
-module_param(tx_descriptors, int, 0644);
+module_param(rx_descriptors, int, 0444);
+module_param(tx_descriptors, int, 0444);
MODULE_PARM_DESC(rx_descriptors, "number of descriptors used " \
"in rx chains");
spider_net_init_chain(struct spider_net_card *card,
struct spider_net_descr_chain *chain,
struct spider_net_descr *start_descr,
- int direction, int no)
+ int no)
{
int i;
struct spider_net_descr *descr;
buf = pci_map_single(card->pdev, descr,
SPIDER_NET_DESCR_SIZE,
- direction);
+ PCI_DMA_BIDIRECTIONAL);
if (pci_dma_mapping_error(buf))
goto iommu_error;
(descr-1)->next = start_descr;
start_descr->prev = descr-1;
- descr = start_descr;
- if (direction == PCI_DMA_FROMDEVICE)
- for (i=0; i < no; i++, descr++)
- descr->next_descr_addr = descr->next->bus_addr;
-
spin_lock_init(&chain->lock);
chain->head = start_descr;
chain->tail = start_descr;
if (descr->bus_addr)
pci_unmap_single(card->pdev, descr->bus_addr,
SPIDER_NET_DESCR_SIZE,
- direction);
+ PCI_DMA_BIDIRECTIONAL);
return -ENOMEM;
}
struct spider_net_descr *descr;
descr = card->rx_chain.head;
- while (descr->next != card->rx_chain.head) {
+ do {
if (descr->skb) {
dev_kfree_skb(descr->skb);
pci_unmap_single(card->pdev, descr->buf_addr,
SPIDER_NET_MAX_FRAME,
- PCI_DMA_FROMDEVICE);
+ PCI_DMA_BIDIRECTIONAL);
}
descr = descr->next;
- }
+ } while (descr != card->rx_chain.head);
}
/**
spider_net_prepare_tx_descr(struct spider_net_card *card,
struct sk_buff *skb)
{
- struct spider_net_descr *descr = card->tx_chain.head;
+ struct spider_net_descr *descr;
dma_addr_t buf;
+ unsigned long flags;
+ int length;
- buf = pci_map_single(card->pdev, skb->data, skb->len, PCI_DMA_TODEVICE);
+ length = skb->len;
+ if (length < ETH_ZLEN) {
+ if (skb_pad(skb, ETH_ZLEN-length))
+ return 0;
+ length = ETH_ZLEN;
+ }
+
+ buf = pci_map_single(card->pdev, skb->data, length, PCI_DMA_TODEVICE);
if (pci_dma_mapping_error(buf)) {
if (netif_msg_tx_err(card) && net_ratelimit())
pr_err("could not iommu-map packet (%p, %i). "
- "Dropping packet\n", skb->data, skb->len);
+ "Dropping packet\n", skb->data, length);
card->spider_stats.tx_iommu_map_error++;
return -ENOMEM;
}
+ spin_lock_irqsave(&card->tx_chain.lock, flags);
+ descr = card->tx_chain.head;
+ card->tx_chain.head = descr->next;
+
descr->buf_addr = buf;
- descr->buf_size = skb->len;
+ descr->buf_size = length;
descr->next_descr_addr = 0;
descr->skb = skb;
descr->data_status = 0;
descr->dmac_cmd_status =
SPIDER_NET_DESCR_CARDOWNED | SPIDER_NET_DMAC_NOCS;
+ spin_unlock_irqrestore(&card->tx_chain.lock, flags);
+
if (skb->protocol == htons(ETH_P_IP))
switch (skb->nh.iph->protocol) {
case IPPROTO_TCP:
break;
}
+ /* Chain the bus address, so that the DMA engine finds this descr. */
descr->prev->next_descr_addr = descr->bus_addr;
+ card->netdev->trans_start = jiffies; /* set netdev watchdog timer */
return 0;
}
-/**
- * spider_net_release_tx_descr - processes a used tx descriptor
- * @card: card structure
- * @descr: descriptor to release
- *
- * releases a used tx descriptor (unmapping, freeing of skb)
- */
-static inline void
-spider_net_release_tx_descr(struct spider_net_card *card)
+static int
+spider_net_set_low_watermark(struct spider_net_card *card)
{
+ unsigned long flags;
+ int status;
+ int cnt=0;
+ int i;
struct spider_net_descr *descr = card->tx_chain.tail;
- struct sk_buff *skb;
- card->tx_chain.tail = card->tx_chain.tail->next;
- descr->dmac_cmd_status |= SPIDER_NET_DESCR_NOT_IN_USE;
+ /* Measure the length of the queue. Measurement does not
+ * need to be precise -- does not need a lock. */
+ while (descr != card->tx_chain.head) {
+ status = descr->dmac_cmd_status & SPIDER_NET_DESCR_NOT_IN_USE;
+ if (status == SPIDER_NET_DESCR_NOT_IN_USE)
+ break;
+ descr = descr->next;
+ cnt++;
+ }
- /* unmap the skb */
- skb = descr->skb;
- pci_unmap_single(card->pdev, descr->buf_addr, skb->len,
- PCI_DMA_TODEVICE);
- dev_kfree_skb_any(skb);
+ /* If TX queue is short, don't even bother with interrupts */
+ if (cnt < card->num_tx_desc/4)
+ return cnt;
+
+ /* Set low-watermark 3/4th's of the way into the queue. */
+ descr = card->tx_chain.tail;
+ cnt = (cnt*3)/4;
+ for (i=0;i<cnt; i++)
+ descr = descr->next;
+
+ /* Set the new watermark, clear the old watermark */
+ spin_lock_irqsave(&card->tx_chain.lock, flags);
+ descr->dmac_cmd_status |= SPIDER_NET_DESCR_TXDESFLG;
+ if (card->low_watermark && card->low_watermark != descr)
+ card->low_watermark->dmac_cmd_status =
+ card->low_watermark->dmac_cmd_status & ~SPIDER_NET_DESCR_TXDESFLG;
+ card->low_watermark = descr;
+ spin_unlock_irqrestore(&card->tx_chain.lock, flags);
+ return cnt;
}
/**
spider_net_release_tx_chain(struct spider_net_card *card, int brutal)
{
struct spider_net_descr_chain *chain = &card->tx_chain;
+ struct spider_net_descr *descr;
+ struct sk_buff *skb;
+ u32 buf_addr;
+ unsigned long flags;
int status;
- spider_net_read_reg(card, SPIDER_NET_GDTDMACCNTR);
-
while (chain->tail != chain->head) {
- status = spider_net_get_descr_status(chain->tail);
+ spin_lock_irqsave(&chain->lock, flags);
+ descr = chain->tail;
+
+ status = spider_net_get_descr_status(descr);
switch (status) {
case SPIDER_NET_DESCR_COMPLETE:
card->netdev_stats.tx_packets++;
- card->netdev_stats.tx_bytes += chain->tail->skb->len;
+ card->netdev_stats.tx_bytes += descr->skb->len;
break;
case SPIDER_NET_DESCR_CARDOWNED:
- if (!brutal)
+ if (!brutal) {
+ spin_unlock_irqrestore(&chain->lock, flags);
return 1;
+ }
+
/* fallthrough, if we release the descriptors
* brutally (then we don't care about
* SPIDER_NET_DESCR_CARDOWNED) */
default:
card->netdev_stats.tx_dropped++;
- return 1;
+ if (!brutal) {
+ spin_unlock_irqrestore(&chain->lock, flags);
+ return 1;
+ }
}
- spider_net_release_tx_descr(card);
- }
+ chain->tail = descr->next;
+ descr->dmac_cmd_status |= SPIDER_NET_DESCR_NOT_IN_USE;
+ skb = descr->skb;
+ buf_addr = descr->buf_addr;
+ spin_unlock_irqrestore(&chain->lock, flags);
+
+ /* unmap the skb */
+ if (skb) {
+ int len = skb->len < ETH_ZLEN ? ETH_ZLEN : skb->len;
+ pci_unmap_single(card->pdev, buf_addr, len, PCI_DMA_TODEVICE);
+ dev_kfree_skb(skb);
+ }
+ }
return 0;
}
* @card: card structure
* @descr: descriptor address to enable TX processing at
*
- * spider_net_kick_tx_dma writes the current tx chain head as start address
- * of the tx descriptor chain and enables the transmission DMA engine
+ * This routine will start the transmit DMA running if
+ * it is not already running. This routine ned only be
+ * called when queueing a new packet to an empty tx queue.
+ * Writes the current tx chain head as start address
+ * of the tx descriptor chain and enables the transmission
+ * DMA engine.
*/
static inline void
spider_net_kick_tx_dma(struct spider_net_card *card)
static int
spider_net_xmit(struct sk_buff *skb, struct net_device *netdev)
{
+ int cnt;
struct spider_net_card *card = netdev_priv(netdev);
struct spider_net_descr_chain *chain = &card->tx_chain;
- struct spider_net_descr *descr = chain->head;
- unsigned long flags;
- int result;
-
- spin_lock_irqsave(&chain->lock, flags);
spider_net_release_tx_chain(card, 0);
- if (chain->head->next == chain->tail->prev) {
- card->netdev_stats.tx_dropped++;
- result = NETDEV_TX_LOCKED;
- goto out;
- }
+ if ((chain->head->next == chain->tail->prev) ||
+ (spider_net_prepare_tx_descr(card, skb) != 0)) {
- if (spider_net_get_descr_status(descr) != SPIDER_NET_DESCR_NOT_IN_USE) {
card->netdev_stats.tx_dropped++;
- result = NETDEV_TX_LOCKED;
- goto out;
+ netif_stop_queue(netdev);
+ return NETDEV_TX_BUSY;
}
- if (spider_net_prepare_tx_descr(card, skb) != 0) {
- card->netdev_stats.tx_dropped++;
- result = NETDEV_TX_BUSY;
- goto out;
- }
-
- result = NETDEV_TX_OK;
-
- spider_net_kick_tx_dma(card);
- card->tx_chain.head = card->tx_chain.head->next;
-
-out:
- spin_unlock_irqrestore(&chain->lock, flags);
- netif_wake_queue(netdev);
- return result;
+ cnt = spider_net_set_low_watermark(card);
+ if (cnt < 5)
+ spider_net_kick_tx_dma(card);
+ return NETDEV_TX_OK;
}
/**
* spider_net_cleanup_tx_ring - cleans up the TX ring
* @card: card structure
*
- * spider_net_cleanup_tx_ring is called by the tx_timer (as we don't use
- * interrupts to cleanup our TX ring) and returns sent packets to the stack
- * by freeing them
+ * spider_net_cleanup_tx_ring is called by either the tx_timer
+ * or from the NAPI polling routine.
+ * This routine releases resources associted with transmitted
+ * packets, including updating the queue tail pointer.
*/
static void
spider_net_cleanup_tx_ring(struct spider_net_card *card)
{
- unsigned long flags;
-
- spin_lock_irqsave(&card->tx_chain.lock, flags);
-
if ((spider_net_release_tx_chain(card, 0) != 0) &&
- (card->netdev->flags & IFF_UP))
+ (card->netdev->flags & IFF_UP)) {
spider_net_kick_tx_dma(card);
-
- spin_unlock_irqrestore(&card->tx_chain.lock, flags);
+ netif_wake_queue(card->netdev);
+ }
}
/**
int packets_to_do, packets_done = 0;
int no_more_packets = 0;
+ spider_net_cleanup_tx_ring(card);
packets_to_do = min(*budget, netdev->quota);
while (packets_to_do) {
case SPIDER_NET_PHYINT:
case SPIDER_NET_GMAC2INT:
case SPIDER_NET_GMAC1INT:
- case SPIDER_NET_GIPSINT:
case SPIDER_NET_GFIFOINT:
case SPIDER_NET_DMACINT:
case SPIDER_NET_GSYSINT:
break; */
+ case SPIDER_NET_GIPSINT:
+ show_error = 0;
+ break;
+
case SPIDER_NET_GPWOPCMPINT:
/* PHY write operation completed */
show_error = 0;
case SPIDER_NET_GDTDCEINT:
/* chain end. If a descriptor should be sent, kick off
* tx dma
- if (card->tx_chain.tail == card->tx_chain.head)
+ if (card->tx_chain.tail != card->tx_chain.head)
spider_net_kick_tx_dma(card);
- show_error = 0; */
+ */
+ show_error = 0;
break;
/* case SPIDER_NET_G1TMCNTINT: not used. print a message */
if (netif_msg_intr(card))
pr_err("got descriptor chain end interrupt, "
"restarting DMAC %c.\n",
- 'D'+i-SPIDER_NET_GDDDCEINT);
+ 'D'-(i-SPIDER_NET_GDDDCEINT)/3);
spider_net_refill_rx_chain(card);
spider_net_enable_rxdmac(card);
show_error = 0;
}
if ((show_error) && (netif_msg_intr(card)))
- pr_err("Got error interrupt, GHIINT0STS = 0x%08x, "
+ pr_err("Got error interrupt on %s, GHIINT0STS = 0x%08x, "
"GHIINT1STS = 0x%08x, GHIINT2STS = 0x%08x\n",
+ card->netdev->name,
status_reg, error_reg1, error_reg2);
/* clear interrupt sources */
spider_net_rx_irq_off(card);
netif_rx_schedule(netdev);
}
+ if (status_reg & SPIDER_NET_TXINT)
+ netif_rx_schedule(netdev);
if (status_reg & SPIDER_NET_ERRINT )
spider_net_handle_error_irq(card, status_reg);
SPIDER_NET_INT2_MASK_VALUE);
spider_net_write_reg(card, SPIDER_NET_GDTDMACCNTR,
- SPIDER_NET_GDTDCEIDIS);
+ SPIDER_NET_GDTBSTA | SPIDER_NET_GDTDCEIDIS);
}
/**
spider_net_open(struct net_device *netdev)
{
struct spider_net_card *card = netdev_priv(netdev);
- int result;
+ struct spider_net_descr *descr;
+ int i, result;
result = -ENOMEM;
if (spider_net_init_chain(card, &card->tx_chain, card->descr,
- PCI_DMA_TODEVICE, card->tx_desc))
+ card->num_tx_desc))
goto alloc_tx_failed;
+
+ card->low_watermark = NULL;
+
+ /* rx_chain is after tx_chain, so offset is descr + tx_count */
if (spider_net_init_chain(card, &card->rx_chain,
- card->descr + card->rx_desc,
- PCI_DMA_FROMDEVICE, card->rx_desc))
+ card->descr + card->num_tx_desc,
+ card->num_rx_desc))
goto alloc_rx_failed;
+ descr = card->rx_chain.head;
+ for (i=0; i < card->num_rx_desc; i++, descr++)
+ descr->next_descr_addr = descr->next->bus_addr;
+
/* allocate rx skbs */
if (spider_net_alloc_rx_skbs(card))
goto alloc_skbs_failed;
spider_net_disable_rxdmac(card);
/* release chains */
- if (spin_trylock(&card->tx_chain.lock)) {
- spider_net_release_tx_chain(card, 1);
- spin_unlock(&card->tx_chain.lock);
- }
+ spider_net_release_tx_chain(card, 1);
spider_net_free_chain(card, &card->tx_chain);
spider_net_free_chain(card, &card->rx_chain);
card->options.rx_csum = SPIDER_NET_RX_CSUM_DEFAULT;
- card->tx_desc = tx_descriptors;
- card->rx_desc = rx_descriptors;
+ card->num_tx_desc = tx_descriptors;
+ card->num_rx_desc = rx_descriptors;
spider_net_setup_netdev_ops(netdev);
*/
static int __init spider_net_init(void)
{
+ printk(KERN_INFO "Spidernet version %s.\n", VERSION);
+
if (rx_descriptors < SPIDER_NET_RX_DESCRIPTORS_MIN) {
rx_descriptors = SPIDER_NET_RX_DESCRIPTORS_MIN;
pr_info("adjusting rx descriptors to %i.\n", rx_descriptors);
#ifndef _SPIDER_NET_H
#define _SPIDER_NET_H
+#define VERSION "1.1 A"
+
#include "sungem_phy.h"
extern int spider_net_stop(struct net_device *netdev);
#define SPIDER_NET_TX_DESCRIPTORS_MIN 16
#define SPIDER_NET_TX_DESCRIPTORS_MAX 512
-#define SPIDER_NET_TX_TIMER 20
+#define SPIDER_NET_TX_TIMER (HZ/5)
#define SPIDER_NET_RX_CSUM_DEFAULT 1
#define SPIDER_NET_MACMODE_VALUE 0x00000001
#define SPIDER_NET_BURSTLMT_VALUE 0x00000200 /* about 16 us */
-/* 1(0) enable r/tx dma
+/* DMAC control register GDMACCNTR
+ *
+ * 1(0) enable r/tx dma
* 0000000 fixed to 0
*
* 000000 fixed to 0
*
* 000000 fixed to 0
* 00 burst alignment: 128 bytes
+ * 11 burst alignment: 1024 bytes
*
* 00000 fixed to 0
* 0 descr writeback size 32 bytes
#define SPIDER_NET_DMA_RX_VALUE 0x80000000
#define SPIDER_NET_DMA_RX_FEND_VALUE 0x00030003
/* to set TX_DMA_EN */
-#define SPIDER_NET_TX_DMA_EN 0x80000000
-#define SPIDER_NET_GDTDCEIDIS 0x00000002
-#define SPIDER_NET_DMA_TX_VALUE SPIDER_NET_TX_DMA_EN | \
- SPIDER_NET_GDTDCEIDIS
+#define SPIDER_NET_TX_DMA_EN 0x80000000
+#define SPIDER_NET_GDTBSTA 0x00000300
+#define SPIDER_NET_GDTDCEIDIS 0x00000002
+#define SPIDER_NET_DMA_TX_VALUE SPIDER_NET_TX_DMA_EN | \
+ SPIDER_NET_GDTBSTA | \
+ SPIDER_NET_GDTDCEIDIS
+
#define SPIDER_NET_DMA_TX_FEND_VALUE 0x00030003
/* SPIDER_NET_UA_DESCR_VALUE is OR'ed with the unicast address */
SPIDER_NET_GRISPDNGINT
};
-#define SPIDER_NET_TXINT ( (1 << SPIDER_NET_GTTEDINT) | \
- (1 << SPIDER_NET_GDTDCEINT) | \
- (1 << SPIDER_NET_GDTFDCINT) )
+#define SPIDER_NET_TXINT ( (1 << SPIDER_NET_GDTFDCINT) )
-/* we rely on flagged descriptor interrupts*/
-#define SPIDER_NET_RXINT ( (1 << SPIDER_NET_GDAFDCINT) | \
- (1 << SPIDER_NET_GRMFLLINT) )
+/* We rely on flagged descriptor interrupts */
+#define SPIDER_NET_RXINT ( (1 << SPIDER_NET_GDAFDCINT) )
#define SPIDER_NET_ERRINT ( 0xffffffff & \
(~SPIDER_NET_TXINT) & \
#define SPIDER_NET_DESCR_FORCE_END 0x50000000 /* used in rx and tx */
#define SPIDER_NET_DESCR_CARDOWNED 0xA0000000 /* used in rx and tx */
#define SPIDER_NET_DESCR_NOT_IN_USE 0xF0000000
+#define SPIDER_NET_DESCR_TXDESFLG 0x00800000
struct spider_net_descr {
/* as defined by the hardware */
struct spider_net_descr_chain tx_chain;
struct spider_net_descr_chain rx_chain;
+ struct spider_net_descr *low_watermark;
struct net_device_stats netdev_stats;
/* for ethtool */
int msg_enable;
- int rx_desc;
- int tx_desc;
+ int num_rx_desc;
+ int num_tx_desc;
struct spider_net_extra_stats spider_stats;
struct spider_net_descr descr[0];
/* clear and fill out info */
memset(drvinfo, 0, sizeof(struct ethtool_drvinfo));
strncpy(drvinfo->driver, spider_net_driver_name, 32);
- strncpy(drvinfo->version, "0.1", 32);
+ strncpy(drvinfo->version, VERSION, 32);
strcpy(drvinfo->fw_version, "no information");
strncpy(drvinfo->bus_info, pci_name(card->pdev), 32);
}
struct spider_net_card *card = netdev->priv;
ering->tx_max_pending = SPIDER_NET_TX_DESCRIPTORS_MAX;
- ering->tx_pending = card->tx_desc;
+ ering->tx_pending = card->num_tx_desc;
ering->rx_max_pending = SPIDER_NET_RX_DESCRIPTORS_MAX;
- ering->rx_pending = card->rx_desc;
+ ering->rx_pending = card->num_rx_desc;
}
static int spider_net_get_stats_count(struct net_device *netdev)
out1:
free_netdev(dev);
out:
- iounmap((void *)ioaddr);
+ iounmap((void __iomem *)ioaddr);
return ERR_PTR(err);
}
out1:
#ifdef CONFIG_SUN3
- iounmap((void *)dev->base_addr);
+ iounmap((void __iomem *)dev->base_addr);
#endif
out:
free_netdev(dev);
ioaddr_probe[1] = tmp2;
#ifdef CONFIG_SUN3
- iounmap((void *)ioaddr);
+ iounmap((void __iomem *)ioaddr);
#endif
return 0;
}
{
unregister_netdev(sun3lance_dev);
#ifdef CONFIG_SUN3
- iounmap((void *)sun3lance_dev->base_addr);
+ iounmap((void __iomem *)sun3lance_dev->base_addr);
#endif
free_netdev(sun3lance_dev);
}
}
/* Note: this routine returns extra data bits for size detection. */
-static unsigned __init tulip_read_eeprom(void __iomem *regs, int location, int addr_len)
+static unsigned __devinit tulip_read_eeprom(void __iomem *regs, int location, int addr_len)
{
int i;
unsigned retval = 0;
goto fill_defaults;
}
-static int __init de_init_one (struct pci_dev *pdev,
+static int __devinit de_init_one (struct pci_dev *pdev,
const struct pci_device_id *ent)
{
struct net_device *dev;
return rc;
}
-static void __exit de_remove_one (struct pci_dev *pdev)
+static void __devexit de_remove_one (struct pci_dev *pdev)
{
struct net_device *dev = pci_get_drvdata(pdev);
struct de_private *de = dev->priv;
.name = DRV_NAME,
.id_table = de_pci_tbl,
.probe = de_init_one,
- .remove = __exit_p(de_remove_one),
+ .remove = __devexit_p(de_remove_one),
#ifdef CONFIG_PM
.suspend = de_suspend,
.resume = de_resume,
config HT_IRQ
bool "Interrupts on hypertransport devices"
default y
- depends on X86_LOCAL_APIC && X86_IO_APIC
+ depends on PCI && X86_LOCAL_APIC && X86_IO_APIC
help
This allows native hypertransport devices to use interrupts.
dt->tm_min = BCD2BIN(chip->buf[2]);
dt->tm_hour = BCD2BIN(chip->buf[3]);
dt->tm_mday = BCD2BIN(chip->buf[4]);
- dt->tm_mon = BCD2BIN(chip->buf[5] - 1);
+ dt->tm_mon = BCD2BIN(chip->buf[5]) - 1;
dt->tm_wday = BCD2BIN(chip->buf[6]);
dt->tm_year = BCD2BIN(chip->buf[7]);
tmp |= RCR1_CIE;
writeb(tmp, rtc->regbase + RCR1);
- ret = request_irq(rtc->periodic_irq, sh_rtc_periodic, SA_INTERRUPT,
+ ret = request_irq(rtc->periodic_irq, sh_rtc_periodic, IRQF_DISABLED,
"sh-rtc period", dev);
if (unlikely(ret)) {
dev_err(dev, "request period IRQ failed with %d, IRQ %d\n",
return ret;
}
- ret = request_irq(rtc->carry_irq, sh_rtc_interrupt, SA_INTERRUPT,
+ ret = request_irq(rtc->carry_irq, sh_rtc_interrupt, IRQF_DISABLED,
"sh-rtc carry", dev);
if (unlikely(ret)) {
dev_err(dev, "request carry IRQ failed with %d, IRQ %d\n",
goto err_bad_carry;
}
- ret = request_irq(rtc->alarm_irq, sh_rtc_interrupt, SA_INTERRUPT,
+ ret = request_irq(rtc->alarm_irq, sh_rtc_interrupt, IRQF_DISABLED,
"sh-rtc alarm", dev);
if (unlikely(ret)) {
dev_err(dev, "request alarm IRQ failed with %d, IRQ %d\n",
* are all disabled */
v3020_set_reg(chip, V3020_STATUS_0, 0x0);
- dev_info(&pdev->dev, "Chip available at physical address 0x%p,"
+ dev_info(&pdev->dev, "Chip available at physical address 0x%llx,"
"data connected to D%d\n",
- (void*)pdev->resource[0].start,
+ (unsigned long long)pdev->resource[0].start,
chip->leftshift);
platform_set_drvdata(pdev, chip);
monbuf = kzalloc(sizeof(struct mon_buf), GFP_KERNEL);
if (!monbuf)
return -ENOMEM;
- monbuf->data = kzalloc(monbuf->hdr.datalen,
+ monbuf->data = kzalloc(monhdr->datalen,
GFP_KERNEL | GFP_DMA);
if (!monbuf->data) {
kfree(monbuf);
struct res_acc_data *res_data;
struct subchannel *sch;
- res_data = (struct res_acc_data *)data;
+ res_data = data;
sch = get_subchannel_by_schid(schid);
if (!sch)
/* Check if a subchannel is newly available. */
u32 isinfo[28];
} *lir;
- lir = (struct lir*) data;
+ lir = data;
if (!(lir->iq&0x80))
/* NULL link incident record */
return -EINVAL;
struct channel_path *chp;
struct subchannel *sch;
- chp = (struct channel_path *)data;
+ chp = data;
sch = get_subchannel_by_schid(schid);
if (!sch)
/* Check if the subchannel is now available. */
return chp_add(chpid);
}
-static inline int
-__check_for_io_and_kill(struct subchannel *sch, int index)
+static inline int check_for_io_on_path(struct subchannel *sch, int index)
{
int cc;
cc = stsch(sch->schid, &sch->schib);
if (cc)
return 0;
- if (sch->schib.scsw.actl && sch->schib.pmcw.lpum == (0x80 >> index)) {
- device_set_waiting(sch);
+ if (sch->schib.scsw.actl && sch->schib.pmcw.lpum == (0x80 >> index))
return 1;
- }
return 0;
}
} else {
sch->opm &= ~(0x80 >> chp);
sch->lpm &= ~(0x80 >> chp);
- /*
- * Give running I/O a grace period in which it
- * can successfully terminate, even using the
- * just varied off path. Then kill it.
- */
- if (!__check_for_io_and_kill(sch, chp) && !sch->lpm) {
+ if (check_for_io_on_path(sch, chp))
+ /* Path verification is done after killing. */
+ device_kill_io(sch);
+ else if (!sch->lpm) {
if (css_enqueue_subchannel_slow(sch->schid)) {
css_clear_subchannel_slow_list();
need_rescan = 1;
struct irb *irb;
struct pt_regs *old_regs;
- irq_enter ();
old_regs = set_irq_regs(regs);
+ irq_enter();
asm volatile ("mc 0,0");
if (S390_lowcore.int_clock >= S390_lowcore.jiffy_timer)
/**
* out of the sie which costs more cycles than it saves.
*/
} while (!MACHINE_IS_VM && tpi (NULL) != 0);
+ irq_exit();
set_irq_regs(old_regs);
- irq_exit ();
}
#ifdef CONFIG_CCW_CONSOLE
struct device *dev;
dev = bus_find_device(&css_bus_type, NULL,
- (void *)&schid, check_subchannel);
+ &schid, check_subchannel);
return dev ? to_subchannel(dev) : NULL;
}
int state; /* device state */
atomic_t onoff;
unsigned long registered;
- __u16 devno; /* device number */
- __u16 sch_no; /* subchannel number */
- __u8 ssid; /* subchannel set id */
+ struct ccw_dev_id dev_id; /* device id */
+ struct subchannel_id schid; /* subchannel number */
__u8 imask; /* lpm mask for SNID/SID/SPGID */
int iretry; /* retry counter SNID/SID/SPGID */
struct {
/* Helper functions for vary on/off. */
int device_is_online(struct subchannel *);
-void device_set_waiting(struct subchannel *);
+void device_kill_io(struct subchannel *);
/* Machine check helper function. */
void device_kill_pending_timer(struct subchannel *);
}
struct match_data {
- unsigned int devno;
- unsigned int ssid;
+ struct ccw_dev_id dev_id;
struct ccw_device * sibling;
};
static int
match_devno(struct device * dev, void * data)
{
- struct match_data * d = (struct match_data *)data;
+ struct match_data * d = data;
struct ccw_device * cdev;
cdev = to_ccwdev(dev);
if ((cdev->private->state == DEV_STATE_DISCONNECTED) &&
- (cdev->private->devno == d->devno) &&
- (cdev->private->ssid == d->ssid) &&
+ ccw_dev_id_is_equal(&cdev->private->dev_id, &d->dev_id) &&
(cdev != d->sibling)) {
cdev->private->state = DEV_STATE_NOT_OPER;
return 1;
return 0;
}
-static struct ccw_device *
-get_disc_ccwdev_by_devno(unsigned int devno, unsigned int ssid,
- struct ccw_device *sibling)
+static struct ccw_device * get_disc_ccwdev_by_dev_id(struct ccw_dev_id *dev_id,
+ struct ccw_device *sibling)
{
struct device *dev;
struct match_data data;
- data.devno = devno;
- data.ssid = ssid;
+ data.dev_id = *dev_id;
data.sibling = sibling;
dev = bus_find_device(&ccw_bus_type, NULL, &data, match_devno);
struct ccw_device *cdev;
- cdev = (struct ccw_device *)data;
+ cdev = data;
if (device_add(&cdev->dev)) {
put_device(&cdev->dev);
return;
struct subchannel *sch;
int need_rename;
- cdev = (struct ccw_device *)data;
+ cdev = data;
sch = to_subchannel(cdev->dev.parent);
- if (cdev->private->devno != sch->schib.pmcw.dev) {
+ if (cdev->private->dev_id.devno != sch->schib.pmcw.dev) {
/*
* The device number has changed. This is usually only when
* a device has been detached under VM and then re-appeared
* get possibly sick...
*/
struct ccw_device *other_cdev;
+ struct ccw_dev_id dev_id;
need_rename = 1;
- other_cdev = get_disc_ccwdev_by_devno(sch->schib.pmcw.dev,
- sch->schid.ssid, cdev);
+ dev_id.devno = sch->schib.pmcw.dev;
+ dev_id.ssid = sch->schid.ssid;
+ other_cdev = get_disc_ccwdev_by_dev_id(&dev_id, cdev);
if (other_cdev) {
struct subchannel *other_sch;
}
/* Update ssd info here. */
css_get_ssd_info(sch);
- cdev->private->devno = sch->schib.pmcw.dev;
+ cdev->private->dev_id.devno = sch->schib.pmcw.dev;
} else
need_rename = 0;
device_remove_files(&cdev->dev);
snprintf (cdev->dev.bus_id, BUS_ID_SIZE, "0.%x.%04x",
sch->schid.ssid, sch->schib.pmcw.dev);
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_add_changed, (void *)cdev);
+ ccw_device_add_changed, cdev);
queue_work(ccw_device_work, &cdev->private->kick_work);
}
int ret;
unsigned long flags;
- cdev = (struct ccw_device *) data;
+ cdev = data;
sch = to_subchannel(cdev->dev.parent);
if (klist_node_attached(&cdev->dev.knode_parent)) {
break;
sch = to_subchannel(cdev->dev.parent);
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_call_sch_unregister, (void *) cdev);
+ ccw_device_call_sch_unregister, cdev);
queue_work(slow_path_wq, &cdev->private->kick_work);
if (atomic_dec_and_test(&ccw_device_init_count))
wake_up(&ccw_device_init_wq);
if (!get_device(&cdev->dev))
break;
PREPARE_WORK(&cdev->private->kick_work,
- io_subchannel_register, (void *) cdev);
+ io_subchannel_register, cdev);
queue_work(slow_path_wq, &cdev->private->kick_work);
break;
}
/* Init private data. */
priv = cdev->private;
- priv->devno = sch->schib.pmcw.dev;
- priv->ssid = sch->schid.ssid;
- priv->sch_no = sch->schid.sch_no;
+ priv->dev_id.devno = sch->schib.pmcw.dev;
+ priv->dev_id.ssid = sch->schid.ssid;
+ priv->schid = sch->schid;
priv->state = DEV_STATE_NOT_OPER;
INIT_LIST_HEAD(&priv->cmb_list);
init_waitqueue_head(&priv->wait_q);
*/
if (get_device(&cdev->dev)) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_unregister, (void *) cdev);
+ ccw_device_unregister, cdev);
queue_work(ccw_device_work, &cdev->private->kick_work);
}
return 0;
{
char *bus_id;
- bus_id = (char *)id;
+ bus_id = id;
return (strncmp(bus_id, dev->bus_id, BUS_ID_SIZE) == 0);
}
/* states to wait for i/o completion before doing something */
DEV_STATE_CLEAR_VERIFY,
DEV_STATE_TIMEOUT_KILL,
- DEV_STATE_WAIT4IO,
DEV_STATE_QUIESCE,
/* special states for devices gone not operational */
DEV_STATE_DISCONNECTED,
cdev->private->state = DEV_STATE_DISCONNECTED;
}
-void
-device_set_waiting(struct subchannel *sch)
-{
- struct ccw_device *cdev;
-
- if (!sch->dev.driver_data)
- return;
- cdev = sch->dev.driver_data;
- ccw_device_set_timeout(cdev, 10*HZ);
- cdev->private->state = DEV_STATE_WAIT4IO;
-}
-
/*
* Timeout function. It just triggers a DEV_EVENT_TIMEOUT.
*/
cdev->id.cu_model != cdev->private->senseid.cu_model ||
cdev->id.dev_type != cdev->private->senseid.dev_type ||
cdev->id.dev_model != cdev->private->senseid.dev_model ||
- cdev->private->devno != sch->schib.pmcw.dev) {
+ cdev->private->dev_id.devno != sch->schib.pmcw.dev) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_do_unreg_rereg, (void *)cdev);
+ ccw_device_do_unreg_rereg, cdev);
queue_work(ccw_device_work, &cdev->private->kick_work);
return 0;
}
case DEV_STATE_NOT_OPER:
CIO_DEBUG(KERN_WARNING, 2,
"SenseID : unknown device %04x on subchannel "
- "0.%x.%04x\n", cdev->private->devno,
+ "0.%x.%04x\n", cdev->private->dev_id.devno,
sch->schid.ssid, sch->schid.sch_no);
break;
case DEV_STATE_OFFLINE:
CIO_DEBUG(KERN_INFO, 2, "SenseID : device 0.%x.%04x reports: "
"CU Type/Mod = %04X/%02X, Dev Type/Mod = "
"%04X/%02X\n",
- cdev->private->ssid, cdev->private->devno,
+ cdev->private->dev_id.ssid,
+ cdev->private->dev_id.devno,
cdev->id.cu_type, cdev->id.cu_model,
cdev->id.dev_type, cdev->id.dev_model);
break;
case DEV_STATE_BOXED:
CIO_DEBUG(KERN_WARNING, 2,
"SenseID : boxed device %04x on subchannel "
- "0.%x.%04x\n", cdev->private->devno,
+ "0.%x.%04x\n", cdev->private->dev_id.devno,
sch->schid.ssid, sch->schid.sch_no);
break;
}
struct subchannel *sch;
int ret;
- cdev = (struct ccw_device *)data;
+ cdev = data;
sch = to_subchannel(cdev->dev.parent);
ret = (sch->driver && sch->driver->notify) ?
sch->driver->notify(&sch->dev, CIO_OPER) : 0;
if (!ret)
/* Driver doesn't want device back. */
- ccw_device_do_unreg_rereg((void *)cdev);
+ ccw_device_do_unreg_rereg(cdev);
else {
/* Reenable channel measurements, if needed. */
cmf_reenable(cdev);
if (state == DEV_STATE_BOXED)
CIO_DEBUG(KERN_WARNING, 2,
"Boxed device %04x on subchannel %04x\n",
- cdev->private->devno, sch->schid.sch_no);
+ cdev->private->dev_id.devno, sch->schid.sch_no);
if (cdev->private->flags.donotify) {
cdev->private->flags.donotify = 0;
PREPARE_WORK(&cdev->private->kick_work, ccw_device_oper_notify,
- (void *)cdev);
+ cdev);
queue_work(ccw_device_notify_work, &cdev->private->kick_work);
}
wake_up(&cdev->private->wait_q);
/* PGID mismatch, can't pathgroup. */
CIO_MSG_EVENT(0, "SNID - pgid mismatch for device "
"0.%x.%04x, can't pathgroup\n",
- cdev->private->ssid, cdev->private->devno);
+ cdev->private->dev_id.ssid,
+ cdev->private->dev_id.devno);
cdev->private->options.pgroup = 0;
return;
}
struct subchannel *sch;
int ret;
- cdev = (struct ccw_device *)data;
+ cdev = data;
sch = to_subchannel(cdev->dev.parent);
/* Extra sanity. */
if (sch->lpm)
if (get_device(&cdev->dev)) {
PREPARE_WORK(&cdev->private->kick_work,
ccw_device_call_sch_unregister,
- (void *)cdev);
+ cdev);
queue_work(ccw_device_work,
&cdev->private->kick_work);
} else
break;
default:
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_nopath_notify, (void *)cdev);
+ ccw_device_nopath_notify, cdev);
queue_work(ccw_device_notify_work, &cdev->private->kick_work);
ccw_device_done(cdev, DEV_STATE_NOT_OPER);
break;
sch = to_subchannel(cdev->dev.parent);
if (get_device(&cdev->dev)) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_call_sch_unregister, (void *)cdev);
+ ccw_device_call_sch_unregister, cdev);
queue_work(ccw_device_work, &cdev->private->kick_work);
}
wake_up(&cdev->private->wait_q);
}
if (get_device(&cdev->dev)) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_call_sch_unregister, (void *)cdev);
+ ccw_device_call_sch_unregister, cdev);
queue_work(ccw_device_work, &cdev->private->kick_work);
}
wake_up(&cdev->private->wait_q);
sch = to_subchannel(cdev->dev.parent);
if (!sch->lpm) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_nopath_notify, (void *)cdev);
+ ccw_device_nopath_notify, cdev);
queue_work(ccw_device_notify_work,
&cdev->private->kick_work);
} else
/* Basic sense hasn't started. Try again. */
ccw_device_do_sense(cdev, irb);
else {
- printk("Huh? %s(%s): unsolicited interrupt...\n",
+ printk(KERN_INFO "Huh? %s(%s): unsolicited "
+ "interrupt...\n",
__FUNCTION__, cdev->dev.bus_id);
if (cdev->handler)
cdev->handler (cdev, 0, irb);
cdev->private->state = DEV_STATE_ONLINE;
if (cdev->handler)
cdev->handler(cdev, cdev->private->intparm,
- ERR_PTR(-ETIMEDOUT));
+ ERR_PTR(-EIO));
if (!sch->lpm) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_nopath_notify, (void *)cdev);
+ ccw_device_nopath_notify, cdev);
queue_work(ccw_device_notify_work, &cdev->private->kick_work);
} else if (cdev->private->flags.doverify)
/* Start delayed path verification. */
sch = to_subchannel(cdev->dev.parent);
if (!sch->lpm) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_nopath_notify, (void *)cdev);
+ ccw_device_nopath_notify, cdev);
queue_work(ccw_device_notify_work,
&cdev->private->kick_work);
} else
cdev->private->state = DEV_STATE_ONLINE;
if (cdev->handler)
cdev->handler(cdev, cdev->private->intparm,
- ERR_PTR(-ETIMEDOUT));
-}
-
-static void
-ccw_device_wait4io_irq(struct ccw_device *cdev, enum dev_event dev_event)
-{
- struct irb *irb;
- struct subchannel *sch;
-
- irb = (struct irb *) __LC_IRB;
- /*
- * Accumulate status and find out if a basic sense is needed.
- * This is fine since we have already adapted the lpm.
- */
- ccw_device_accumulate_irb(cdev, irb);
- if (cdev->private->flags.dosense) {
- if (ccw_device_do_sense(cdev, irb) == 0) {
- cdev->private->state = DEV_STATE_W4SENSE;
- }
- return;
- }
-
- /* Iff device is idle, reset timeout. */
- sch = to_subchannel(cdev->dev.parent);
- if (!stsch(sch->schid, &sch->schib))
- if (sch->schib.scsw.actl == 0)
- ccw_device_set_timeout(cdev, 0);
- /* Call the handler. */
- ccw_device_call_handler(cdev);
- if (!sch->lpm) {
- PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_nopath_notify, (void *)cdev);
- queue_work(ccw_device_notify_work, &cdev->private->kick_work);
- } else if (cdev->private->flags.doverify)
- ccw_device_online_verify(cdev, 0);
+ ERR_PTR(-EIO));
}
-static void
-ccw_device_wait4io_timeout(struct ccw_device *cdev, enum dev_event dev_event)
+void device_kill_io(struct subchannel *sch)
{
int ret;
- struct subchannel *sch;
+ struct ccw_device *cdev;
- sch = to_subchannel(cdev->dev.parent);
- ccw_device_set_timeout(cdev, 0);
+ cdev = sch->dev.driver_data;
ret = ccw_device_cancel_halt_clear(cdev);
if (ret == -EBUSY) {
ccw_device_set_timeout(cdev, 3*HZ);
if (ret == -ENODEV) {
if (!sch->lpm) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_nopath_notify, (void *)cdev);
+ ccw_device_nopath_notify, cdev);
queue_work(ccw_device_notify_work,
&cdev->private->kick_work);
} else
}
if (cdev->handler)
cdev->handler(cdev, cdev->private->intparm,
- ERR_PTR(-ETIMEDOUT));
+ ERR_PTR(-EIO));
if (!sch->lpm) {
PREPARE_WORK(&cdev->private->kick_work,
- ccw_device_nopath_notify, (void *)cdev);
+ ccw_device_nopath_notify, cdev);
queue_work(ccw_device_notify_work, &cdev->private->kick_work);
- } else if (cdev->private->flags.doverify)
+ } else
/* Start delayed path verification. */
ccw_device_online_verify(cdev, 0);
}
[DEV_EVENT_TIMEOUT] = ccw_device_killing_timeout,
[DEV_EVENT_VERIFY] = ccw_device_nop, //FIXME
},
- [DEV_STATE_WAIT4IO] = {
- [DEV_EVENT_NOTOPER] = ccw_device_online_notoper,
- [DEV_EVENT_INTERRUPT] = ccw_device_wait4io_irq,
- [DEV_EVENT_TIMEOUT] = ccw_device_wait4io_timeout,
- [DEV_EVENT_VERIFY] = ccw_device_delay_verify,
- },
[DEV_STATE_QUIESCE] = {
[DEV_EVENT_NOTOPER] = ccw_device_quiesce_done,
[DEV_EVENT_INTERRUPT] = ccw_device_quiesce_done,
*/
CIO_MSG_EVENT(2, "SenseID : device %04x on Subchannel "
"0.%x.%04x reports cmd reject\n",
- cdev->private->devno, sch->schid.ssid,
+ cdev->private->dev_id.devno, sch->schid.ssid,
sch->schid.sch_no);
return -EOPNOTSUPP;
}
CIO_MSG_EVENT(2, "SenseID : UC on dev 0.%x.%04x, "
"lpum %02X, cnt %02d, sns :"
" %02X%02X%02X%02X %02X%02X%02X%02X ...\n",
- cdev->private->ssid, cdev->private->devno,
+ cdev->private->dev_id.ssid,
+ cdev->private->dev_id.devno,
irb->esw.esw0.sublog.lpum,
irb->esw.esw0.erw.scnt,
irb->ecw[0], irb->ecw[1],
CIO_MSG_EVENT(2, "SenseID : path %02X for device %04x "
"on subchannel 0.%x.%04x is "
"'not operational'\n", sch->orb.lpm,
- cdev->private->devno, sch->schid.ssid,
- sch->schid.sch_no);
+ cdev->private->dev_id.devno,
+ sch->schid.ssid, sch->schid.sch_no);
return -EACCES;
}
/* Hmm, whatever happened, try again. */
CIO_MSG_EVENT(2, "SenseID : start_IO() for device %04x on "
"subchannel 0.%x.%04x returns status %02X%02X\n",
- cdev->private->devno, sch->schid.ssid, sch->schid.sch_no,
+ cdev->private->dev_id.devno, sch->schid.ssid,
+ sch->schid.sch_no,
irb->scsw.dstat, irb->scsw.cstat);
return -EAGAIN;
}
/* fall through. */
default: /* Sense ID failed. Try asking VM. */
if (MACHINE_IS_VM) {
- VM_virtual_device_info (cdev->private->devno,
+ VM_virtual_device_info (cdev->private->dev_id.devno,
&cdev->private->senseid);
if (cdev->private->senseid.cu_type != 0xFFFF) {
/* Got the device information from VM. */
if (cdev->private->state == DEV_STATE_NOT_OPER)
return -ENODEV;
if (cdev->private->state != DEV_STATE_ONLINE &&
- cdev->private->state != DEV_STATE_WAIT4IO &&
cdev->private->state != DEV_STATE_W4SENSE)
return -EINVAL;
sch = to_subchannel(cdev->dev.parent);
if (cdev->private->state == DEV_STATE_NOT_OPER)
return -ENODEV;
if (cdev->private->state != DEV_STATE_ONLINE &&
- cdev->private->state != DEV_STATE_WAIT4IO &&
cdev->private->state != DEV_STATE_W4SENSE)
return -EINVAL;
sch = to_subchannel(cdev->dev.parent);
int
_ccw_device_get_subchannel_number(struct ccw_device *cdev)
{
- return cdev->private->sch_no;
+ return cdev->private->schid.sch_no;
}
int
_ccw_device_get_device_number(struct ccw_device *cdev)
{
- return cdev->private->devno;
+ return cdev->private->dev_id.devno;
}
CIO_MSG_EVENT(2, "SNID - Device %04x on Subchannel "
"0.%x.%04x, lpm %02X, became 'not "
"operational'\n",
- cdev->private->devno, sch->schid.ssid,
+ cdev->private->dev_id.devno,
+ sch->schid.ssid,
sch->schid.sch_no, cdev->private->imask);
}
CIO_MSG_EVENT(2, "SNID - device 0.%x.%04x, unit check, "
"lpum %02X, cnt %02d, sns : "
"%02X%02X%02X%02X %02X%02X%02X%02X ...\n",
- cdev->private->ssid, cdev->private->devno,
+ cdev->private->dev_id.ssid,
+ cdev->private->dev_id.devno,
irb->esw.esw0.sublog.lpum,
irb->esw.esw0.erw.scnt,
irb->ecw[0], irb->ecw[1],
if (irb->scsw.cc == 3) {
CIO_MSG_EVENT(2, "SNID - Device %04x on Subchannel 0.%x.%04x,"
" lpm %02X, became 'not operational'\n",
- cdev->private->devno, sch->schid.ssid,
+ cdev->private->dev_id.devno, sch->schid.ssid,
sch->schid.sch_no, sch->orb.lpm);
return -EACCES;
}
if (cdev->private->pgid[i].inf.ps.state2 == SNID_STATE2_RESVD_ELSE) {
CIO_MSG_EVENT(2, "SNID - Device %04x on Subchannel 0.%x.%04x "
"is reserved by someone else\n",
- cdev->private->devno, sch->schid.ssid,
+ cdev->private->dev_id.devno, sch->schid.ssid,
sch->schid.sch_no);
return -EUSERS;
}
/* PGID command failed on this path. */
CIO_MSG_EVENT(2, "SPID - Device %04x on Subchannel "
"0.%x.%04x, lpm %02X, became 'not operational'\n",
- cdev->private->devno, sch->schid.ssid,
+ cdev->private->dev_id.devno, sch->schid.ssid,
sch->schid.sch_no, cdev->private->imask);
return ret;
}
/* nop command failed on this path. */
CIO_MSG_EVENT(2, "NOP - Device %04x on Subchannel "
"0.%x.%04x, lpm %02X, became 'not operational'\n",
- cdev->private->devno, sch->schid.ssid,
+ cdev->private->dev_id.devno, sch->schid.ssid,
sch->schid.sch_no, cdev->private->imask);
return ret;
}
CIO_MSG_EVENT(2, "SPID - device 0.%x.%04x, unit check, "
"cnt %02d, "
"sns : %02X%02X%02X%02X %02X%02X%02X%02X ...\n",
- cdev->private->ssid,
- cdev->private->devno, irb->esw.esw0.erw.scnt,
+ cdev->private->dev_id.ssid,
+ cdev->private->dev_id.devno,
+ irb->esw.esw0.erw.scnt,
irb->ecw[0], irb->ecw[1],
irb->ecw[2], irb->ecw[3],
irb->ecw[4], irb->ecw[5],
if (irb->scsw.cc == 3) {
CIO_MSG_EVENT(2, "SPID - Device %04x on Subchannel 0.%x.%04x,"
" lpm %02X, became 'not operational'\n",
- cdev->private->devno, sch->schid.ssid,
+ cdev->private->dev_id.devno, sch->schid.ssid,
sch->schid.sch_no, cdev->private->imask);
return -EACCES;
}
if (irb->scsw.cc == 3) {
CIO_MSG_EVENT(2, "NOP - Device %04x on Subchannel 0.%x.%04x,"
" lpm %02X, became 'not operational'\n",
- cdev->private->devno, sch->schid.ssid,
+ cdev->private->dev_id.devno, sch->schid.ssid,
sch->schid.sch_no, cdev->private->imask);
return -EACCES;
}
SCHN_STAT_CHN_CTRL_CHK |
SCHN_STAT_INTF_CTRL_CHK)))
return;
-
CIO_MSG_EVENT(0, "Channel-Check or Interface-Control-Check "
"received"
" ... device %04x on subchannel 0.%x.%04x, dev_stat "
": %02X sch_stat : %02X\n",
- cdev->private->devno, cdev->private->ssid,
- cdev->private->sch_no,
+ cdev->private->dev_id.devno, cdev->private->schid.ssid,
+ cdev->private->schid.sch_no,
irb->scsw.dstat, irb->scsw.cstat);
if (irb->scsw.cc != 3) {
char dbf_text[15];
- sprintf(dbf_text, "chk%x", cdev->private->sch_no);
+ sprintf(dbf_text, "chk%x", cdev->private->schid.sch_no);
CIO_TRACE_EVENT(0, dbf_text);
CIO_HEX_EVENT(0, irb, sizeof (struct irb));
}
void *ptr;
int available;
- sprintf(dbf_text,"qfqs%4x",cdev->private->sch_no);
+ sprintf(dbf_text,"qfqs%4x",cdev->private->schid.sch_no);
QDIO_DBF_TEXT0(0,setup,dbf_text);
for (i=0;i<no_input_qs;i++) {
q=irq_ptr->input_qs[i];
irq_ptr = cdev->private->qdio_data;
- sprintf(dbf_text,"qehi%4x",cdev->private->sch_no);
+ sprintf(dbf_text,"qehi%4x",cdev->private->schid.sch_no);
QDIO_DBF_TEXT0(0,setup,dbf_text);
QDIO_DBF_TEXT0(0,trace,dbf_text);
int rc;
char dbf_text[15];
- sprintf(dbf_text,"qini%4x",init_data->cdev->private->sch_no);
+ sprintf(dbf_text,"qini%4x",init_data->cdev->private->schid.sch_no);
QDIO_DBF_TEXT0(0,setup,dbf_text);
QDIO_DBF_TEXT0(0,trace,dbf_text);
struct qdio_irq *irq_ptr;
char dbf_text[15];
- sprintf(dbf_text,"qalc%4x",init_data->cdev->private->sch_no);
+ sprintf(dbf_text,"qalc%4x",init_data->cdev->private->schid.sch_no);
QDIO_DBF_TEXT0(0,setup,dbf_text);
QDIO_DBF_TEXT0(0,trace,dbf_text);
if ( (init_data->no_input_qs>QDIO_MAX_QUEUES_PER_IRQ) ||
tiqdio_set_delay_target(irq_ptr,TIQDIO_DELAY_TARGET);
}
- sprintf(dbf_text,"qest%4x",cdev->private->sch_no);
+ sprintf(dbf_text,"qest%4x",cdev->private->schid.sch_no);
QDIO_DBF_TEXT0(0,setup,dbf_text);
QDIO_DBF_TEXT0(0,trace,dbf_text);
* Copyright (C) 2001 David S. Miller (davem@redhat.com)
*/
-#include <linux/kernel.h>
#include <linux/kthread.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
+#include <linux/syscalls.h>
#include <linux/delay.h>
#include <asm/oplib.h>
#include <asm/ebus.h>
*/
#include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/init.h>
#include <linux/kthread.h>
-#include <linux/errno.h>
#include <linux/delay.h>
#include <linux/ioport.h>
-#include <linux/init.h>
#include <linux/miscdevice.h>
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/kernel.h>
+#include <linux/syscalls.h>
#include <asm/ebus.h>
#include <asm/uaccess.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <asm/irq.h>
-#include <asm/io.h>
+#include <linux/io.h>
#include <linux/blkdev.h>
#include <asm/system.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/interrupt.h>
-#include <asm/io.h>
+#include <linux/io.h>
#include "scsi.h"
#include <scsi/scsi_host.h>
#include "dtc.h"
#include <linux/pci.h>
#include <linux/stat.h>
#include <linux/delay.h>
+#include <linux/io.h>
#include <scsi/scsicam.h>
-#include <asm/io.h>
#include <asm/system.h>
#include <scsi/scsi.h>
if (((magic64 == HBA_SIGNATURE_64_BIT) &&
((adapter->pdev->subsystem_device !=
- PCI_SUBSYS_ID_MEGARAID_SATA_150_6) ||
+ PCI_SUBSYS_ID_MEGARAID_SATA_150_6) &&
(adapter->pdev->subsystem_device !=
PCI_SUBSYS_ID_MEGARAID_SATA_150_4))) ||
(adapter->pdev->vendor == PCI_VENDOR_ID_LSI_LOGIC &&
#include <linux/blkdev.h>
#include <linux/stat.h>
#include <linux/delay.h>
+#include <linux/io.h>
-#include <asm/io.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/signal.h>
#include <linux/sched.h>
-#include <asm/io.h>
+#include <linux/io.h>
#include <linux/blkdev.h>
#include <linux/interrupt.h>
#include <linux/stat.h>
#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/stat.h>
+#include <linux/io.h>
#include <asm/system.h>
#include <asm/dma.h>
-#include <asm/io.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
uart_unregister_driver(&ioc4_uart_rs422);
}
-module_init(ioc4_serial_init);
+late_initcall(ioc4_serial_init); /* Call only after tty init is done */
module_exit(ioc4_serial_exit);
MODULE_AUTHOR("Pat Gefre - Silicon Graphics Inc. (SGI) <pfg@sgi.com>");
}
if (request_irq(port->irqs[0], sci_mpxed_interrupt,
- SA_INTERRUPT, "sci", port)) {
+ IRQF_DISABLED, "sci", port)) {
printk(KERN_ERR "sci: Cannot allocate irq.\n");
return -ENODEV;
}
if (!port->irqs[i])
continue;
if (request_irq(port->irqs[i], handlers[i],
- SA_INTERRUPT, desc[i], port)) {
+ IRQF_DISABLED, desc[i], port)) {
printk(KERN_ERR "sci: Cannot allocate irq.\n");
return -ENODEV;
}
return 0;
}
-static struct console sunzilog_console = {
+static struct console sunzilog_console_ops = {
.name = "ttyS",
.write = sunzilog_console_write,
.device = uart_console_device,
if (i == NUM_CHANNELS)
return NULL;
- sunzilog_console.index = i;
+ sunzilog_console_ops.index = i;
sunzilog_port_table[i].flags |= SUNZILOG_FLAG_IS_CONS;
- return &sunzilog_console;
+ return &sunzilog_console_ops;
}
#else
menu "SN Devices"
depends on SGI_SN
-config SGI_IOC4
- tristate "SGI IOC4 Base IO support"
- depends on MMTIMER
- default m
- ---help---
- This option enables basic support for the SGI IOC4-based Base IO
- controller card. This option does not enable any specific
- functions on such a card, but provides necessary infrastructure
- for other drivers to utilize.
-
- If you have an SGI Altix with an IOC4-based
- I/O controller say Y. Otherwise say N.
-
config SGI_IOC3
tristate "SGI IOC3 Base IO support"
default m
#
#
-obj-$(CONFIG_SGI_IOC4) += ioc4.o
obj-$(CONFIG_SGI_IOC3) += ioc3.o
+++ /dev/null
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2005 Silicon Graphics, Inc. All Rights Reserved.
- */
-
-/* This file contains the master driver module for use by SGI IOC4 subdrivers.
- *
- * It allocates any resources shared between multiple subdevices, and
- * provides accessor functions (where needed) and the like for those
- * resources. It also provides a mechanism for the subdevice modules
- * to support loading and unloading.
- *
- * Non-shared resources (e.g. external interrupt A_INT_OUT register page
- * alias, serial port and UART registers) are handled by the subdevice
- * modules themselves.
- *
- * This is all necessary because IOC4 is not implemented as a multi-function
- * PCI device, but an amalgamation of disparate registers for several
- * types of device (ATA, serial, external interrupts). The normal
- * resource management in the kernel doesn't have quite the right interfaces
- * to handle this situation (e.g. multiple modules can't claim the same
- * PCI ID), thus this IOC4 master module.
- */
-
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-#include <linux/ioc4.h>
-#include <linux/mmtimer.h>
-#include <linux/rtc.h>
-#include <linux/mutex.h>
-#include <asm/sn/addrs.h>
-#include <asm/sn/clksupport.h>
-#include <asm/sn/shub_mmr.h>
-
-/***************
- * Definitions *
- ***************/
-
-/* Tweakable values */
-
-/* PCI bus speed detection/calibration */
-#define IOC4_CALIBRATE_COUNT 63 /* Calibration cycle period */
-#define IOC4_CALIBRATE_CYCLES 256 /* Average over this many cycles */
-#define IOC4_CALIBRATE_DISCARD 2 /* Discard first few cycles */
-#define IOC4_CALIBRATE_LOW_MHZ 25 /* Lower bound on bus speed sanity */
-#define IOC4_CALIBRATE_HIGH_MHZ 75 /* Upper bound on bus speed sanity */
-#define IOC4_CALIBRATE_DEFAULT_MHZ 66 /* Assumed if sanity check fails */
-
-/************************
- * Submodule management *
- ************************/
-
-static DEFINE_MUTEX(ioc4_mutex);
-
-static LIST_HEAD(ioc4_devices);
-static LIST_HEAD(ioc4_submodules);
-
-/* Register an IOC4 submodule */
-int
-ioc4_register_submodule(struct ioc4_submodule *is)
-{
- struct ioc4_driver_data *idd;
-
- mutex_lock(&ioc4_mutex);
- list_add(&is->is_list, &ioc4_submodules);
-
- /* Initialize submodule for each IOC4 */
- if (!is->is_probe)
- goto out;
-
- list_for_each_entry(idd, &ioc4_devices, idd_list) {
- if (is->is_probe(idd)) {
- printk(KERN_WARNING
- "%s: IOC4 submodule %s probe failed "
- "for pci_dev %s",
- __FUNCTION__, module_name(is->is_owner),
- pci_name(idd->idd_pdev));
- }
- }
- out:
- mutex_unlock(&ioc4_mutex);
- return 0;
-}
-
-/* Unregister an IOC4 submodule */
-void
-ioc4_unregister_submodule(struct ioc4_submodule *is)
-{
- struct ioc4_driver_data *idd;
-
- mutex_lock(&ioc4_mutex);
- list_del(&is->is_list);
-
- /* Remove submodule for each IOC4 */
- if (!is->is_remove)
- goto out;
-
- list_for_each_entry(idd, &ioc4_devices, idd_list) {
- if (is->is_remove(idd)) {
- printk(KERN_WARNING
- "%s: IOC4 submodule %s remove failed "
- "for pci_dev %s.\n",
- __FUNCTION__, module_name(is->is_owner),
- pci_name(idd->idd_pdev));
- }
- }
- out:
- mutex_unlock(&ioc4_mutex);
-}
-
-/*********************
- * Device management *
- *********************/
-
-#define IOC4_CALIBRATE_LOW_LIMIT \
- (1000*IOC4_EXTINT_COUNT_DIVISOR/IOC4_CALIBRATE_LOW_MHZ)
-#define IOC4_CALIBRATE_HIGH_LIMIT \
- (1000*IOC4_EXTINT_COUNT_DIVISOR/IOC4_CALIBRATE_HIGH_MHZ)
-#define IOC4_CALIBRATE_DEFAULT \
- (1000*IOC4_EXTINT_COUNT_DIVISOR/IOC4_CALIBRATE_DEFAULT_MHZ)
-
-#define IOC4_CALIBRATE_END \
- (IOC4_CALIBRATE_CYCLES + IOC4_CALIBRATE_DISCARD)
-
-#define IOC4_INT_OUT_MODE_TOGGLE 0x7 /* Toggle INT_OUT every COUNT+1 ticks */
-
-/* Determines external interrupt output clock period of the PCI bus an
- * IOC4 is attached to. This value can be used to determine the PCI
- * bus speed.
- *
- * IOC4 has a design feature that various internal timers are derived from
- * the PCI bus clock. This causes IOC4 device drivers to need to take the
- * bus speed into account when setting various register values (e.g. INT_OUT
- * register COUNT field, UART divisors, etc). Since this information is
- * needed by several subdrivers, it is determined by the main IOC4 driver,
- * even though the following code utilizes external interrupt registers
- * to perform the speed calculation.
- */
-static void
-ioc4_clock_calibrate(struct ioc4_driver_data *idd)
-{
- extern unsigned long sn_rtc_cycles_per_second;
- union ioc4_int_out int_out;
- union ioc4_gpcr gpcr;
- unsigned int state, last_state = 1;
- uint64_t start = 0, end, period;
- unsigned int count = 0;
-
- /* Enable output */
- gpcr.raw = 0;
- gpcr.fields.dir = IOC4_GPCR_DIR_0;
- gpcr.fields.int_out_en = 1;
- writel(gpcr.raw, &idd->idd_misc_regs->gpcr_s.raw);
-
- /* Reset to power-on state */
- writel(0, &idd->idd_misc_regs->int_out.raw);
- mmiowb();
-
- /* Set up square wave */
- int_out.raw = 0;
- int_out.fields.count = IOC4_CALIBRATE_COUNT;
- int_out.fields.mode = IOC4_INT_OUT_MODE_TOGGLE;
- int_out.fields.diag = 0;
- writel(int_out.raw, &idd->idd_misc_regs->int_out.raw);
- mmiowb();
-
- /* Check square wave period averaged over some number of cycles */
- do {
- int_out.raw = readl(&idd->idd_misc_regs->int_out.raw);
- state = int_out.fields.int_out;
- if (!last_state && state) {
- count++;
- if (count == IOC4_CALIBRATE_END) {
- end = rtc_time();
- break;
- } else if (count == IOC4_CALIBRATE_DISCARD)
- start = rtc_time();
- }
- last_state = state;
- } while (1);
-
- /* Calculation rearranged to preserve intermediate precision.
- * Logically:
- * 1. "end - start" gives us number of RTC cycles over all the
- * square wave cycles measured.
- * 2. Divide by number of square wave cycles to get number of
- * RTC cycles per square wave cycle.
- * 3. Divide by 2*(int_out.fields.count+1), which is the formula
- * by which the IOC4 generates the square wave, to get the
- * number of RTC cycles per IOC4 INT_OUT count.
- * 4. Divide by sn_rtc_cycles_per_second to get seconds per
- * count.
- * 5. Multiply by 1E9 to get nanoseconds per count.
- */
- period = ((end - start) * 1000000000) /
- (IOC4_CALIBRATE_CYCLES * 2 * (IOC4_CALIBRATE_COUNT + 1)
- * sn_rtc_cycles_per_second);
-
- /* Bounds check the result. */
- if (period > IOC4_CALIBRATE_LOW_LIMIT ||
- period < IOC4_CALIBRATE_HIGH_LIMIT) {
- printk(KERN_INFO
- "IOC4 %s: Clock calibration failed. Assuming"
- "PCI clock is %d ns.\n",
- pci_name(idd->idd_pdev),
- IOC4_CALIBRATE_DEFAULT / IOC4_EXTINT_COUNT_DIVISOR);
- period = IOC4_CALIBRATE_DEFAULT;
- } else {
- printk(KERN_DEBUG
- "IOC4 %s: PCI clock is %ld ns.\n",
- pci_name(idd->idd_pdev),
- period / IOC4_EXTINT_COUNT_DIVISOR);
- }
-
- /* Remember results. We store the extint clock period rather
- * than the PCI clock period so that greater precision is
- * retained. Divide by IOC4_EXTINT_COUNT_DIVISOR to get
- * PCI clock period.
- */
- idd->count_period = period;
-}
-
-/* There are three variants of IOC4 cards: IO9, IO10, and PCI-RT.
- * Each brings out different combinations of IOC4 signals, thus.
- * the IOC4 subdrivers need to know to which we're attached.
- *
- * We look for the presence of a SCSI (IO9) or SATA (IO10) controller
- * on the same PCI bus at slot number 3 to differentiate IO9 from IO10.
- * If neither is present, it's a PCI-RT.
- */
-static unsigned int
-ioc4_variant(struct ioc4_driver_data *idd)
-{
- struct pci_dev *pdev = NULL;
- int found = 0;
-
- /* IO9: Look for a QLogic ISP 12160 at the same bus and slot 3. */
- do {
- pdev = pci_get_device(PCI_VENDOR_ID_QLOGIC,
- PCI_DEVICE_ID_QLOGIC_ISP12160, pdev);
- if (pdev &&
- idd->idd_pdev->bus->number == pdev->bus->number &&
- 3 == PCI_SLOT(pdev->devfn))
- found = 1;
- pci_dev_put(pdev);
- } while (pdev && !found);
- if (NULL != pdev)
- return IOC4_VARIANT_IO9;
-
- /* IO10: Look for a Vitesse VSC 7174 at the same bus and slot 3. */
- pdev = NULL;
- do {
- pdev = pci_get_device(PCI_VENDOR_ID_VITESSE,
- PCI_DEVICE_ID_VITESSE_VSC7174, pdev);
- if (pdev &&
- idd->idd_pdev->bus->number == pdev->bus->number &&
- 3 == PCI_SLOT(pdev->devfn))
- found = 1;
- pci_dev_put(pdev);
- } while (pdev && !found);
- if (NULL != pdev)
- return IOC4_VARIANT_IO10;
-
- /* PCI-RT: No SCSI/SATA controller will be present */
- return IOC4_VARIANT_PCI_RT;
-}
-
-/* Adds a new instance of an IOC4 card */
-static int
-ioc4_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
-{
- struct ioc4_driver_data *idd;
- struct ioc4_submodule *is;
- uint32_t pcmd;
- int ret;
-
- /* Enable IOC4 and take ownership of it */
- if ((ret = pci_enable_device(pdev))) {
- printk(KERN_WARNING
- "%s: Failed to enable IOC4 device for pci_dev %s.\n",
- __FUNCTION__, pci_name(pdev));
- goto out;
- }
- pci_set_master(pdev);
-
- /* Set up per-IOC4 data */
- idd = kmalloc(sizeof(struct ioc4_driver_data), GFP_KERNEL);
- if (!idd) {
- printk(KERN_WARNING
- "%s: Failed to allocate IOC4 data for pci_dev %s.\n",
- __FUNCTION__, pci_name(pdev));
- ret = -ENODEV;
- goto out_idd;
- }
- idd->idd_pdev = pdev;
- idd->idd_pci_id = pci_id;
-
- /* Map IOC4 misc registers. These are shared between subdevices
- * so the main IOC4 module manages them.
- */
- idd->idd_bar0 = pci_resource_start(idd->idd_pdev, 0);
- if (!idd->idd_bar0) {
- printk(KERN_WARNING
- "%s: Unable to find IOC4 misc resource "
- "for pci_dev %s.\n",
- __FUNCTION__, pci_name(idd->idd_pdev));
- ret = -ENODEV;
- goto out_pci;
- }
- if (!request_region(idd->idd_bar0, sizeof(struct ioc4_misc_regs),
- "ioc4_misc")) {
- printk(KERN_WARNING
- "%s: Unable to request IOC4 misc region "
- "for pci_dev %s.\n",
- __FUNCTION__, pci_name(idd->idd_pdev));
- ret = -ENODEV;
- goto out_pci;
- }
- idd->idd_misc_regs = ioremap(idd->idd_bar0,
- sizeof(struct ioc4_misc_regs));
- if (!idd->idd_misc_regs) {
- printk(KERN_WARNING
- "%s: Unable to remap IOC4 misc region "
- "for pci_dev %s.\n",
- __FUNCTION__, pci_name(idd->idd_pdev));
- ret = -ENODEV;
- goto out_misc_region;
- }
-
- /* Failsafe portion of per-IOC4 initialization */
-
- /* Detect card variant */
- idd->idd_variant = ioc4_variant(idd);
- printk(KERN_INFO "IOC4 %s: %s card detected.\n", pci_name(pdev),
- idd->idd_variant == IOC4_VARIANT_IO9 ? "IO9" :
- idd->idd_variant == IOC4_VARIANT_PCI_RT ? "PCI-RT" :
- idd->idd_variant == IOC4_VARIANT_IO10 ? "IO10" : "unknown");
-
- /* Initialize IOC4 */
- pci_read_config_dword(idd->idd_pdev, PCI_COMMAND, &pcmd);
- pci_write_config_dword(idd->idd_pdev, PCI_COMMAND,
- pcmd | PCI_COMMAND_PARITY | PCI_COMMAND_SERR);
-
- /* Determine PCI clock */
- ioc4_clock_calibrate(idd);
-
- /* Disable/clear all interrupts. Need to do this here lest
- * one submodule request the shared IOC4 IRQ, but interrupt
- * is generated by a different subdevice.
- */
- /* Disable */
- writel(~0, &idd->idd_misc_regs->other_iec.raw);
- writel(~0, &idd->idd_misc_regs->sio_iec);
- /* Clear (i.e. acknowledge) */
- writel(~0, &idd->idd_misc_regs->other_ir.raw);
- writel(~0, &idd->idd_misc_regs->sio_ir);
-
- /* Track PCI-device specific data */
- idd->idd_serial_data = NULL;
- pci_set_drvdata(idd->idd_pdev, idd);
-
- mutex_lock(&ioc4_mutex);
- list_add_tail(&idd->idd_list, &ioc4_devices);
-
- /* Add this IOC4 to all submodules */
- list_for_each_entry(is, &ioc4_submodules, is_list) {
- if (is->is_probe && is->is_probe(idd)) {
- printk(KERN_WARNING
- "%s: IOC4 submodule 0x%s probe failed "
- "for pci_dev %s.\n",
- __FUNCTION__, module_name(is->is_owner),
- pci_name(idd->idd_pdev));
- }
- }
- mutex_unlock(&ioc4_mutex);
-
- return 0;
-
-out_misc_region:
- release_region(idd->idd_bar0, sizeof(struct ioc4_misc_regs));
-out_pci:
- kfree(idd);
-out_idd:
- pci_disable_device(pdev);
-out:
- return ret;
-}
-
-/* Removes a particular instance of an IOC4 card. */
-static void
-ioc4_remove(struct pci_dev *pdev)
-{
- struct ioc4_submodule *is;
- struct ioc4_driver_data *idd;
-
- idd = pci_get_drvdata(pdev);
-
- /* Remove this IOC4 from all submodules */
- mutex_lock(&ioc4_mutex);
- list_for_each_entry(is, &ioc4_submodules, is_list) {
- if (is->is_remove && is->is_remove(idd)) {
- printk(KERN_WARNING
- "%s: IOC4 submodule 0x%s remove failed "
- "for pci_dev %s.\n",
- __FUNCTION__, module_name(is->is_owner),
- pci_name(idd->idd_pdev));
- }
- }
- mutex_unlock(&ioc4_mutex);
-
- /* Release resources */
- iounmap(idd->idd_misc_regs);
- if (!idd->idd_bar0) {
- printk(KERN_WARNING
- "%s: Unable to get IOC4 misc mapping for pci_dev %s. "
- "Device removal may be incomplete.\n",
- __FUNCTION__, pci_name(idd->idd_pdev));
- }
- release_region(idd->idd_bar0, sizeof(struct ioc4_misc_regs));
-
- /* Disable IOC4 and relinquish */
- pci_disable_device(pdev);
-
- /* Remove and free driver data */
- mutex_lock(&ioc4_mutex);
- list_del(&idd->idd_list);
- mutex_unlock(&ioc4_mutex);
- kfree(idd);
-}
-
-static struct pci_device_id ioc4_id_table[] = {
- {PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC4, PCI_ANY_ID,
- PCI_ANY_ID, 0x0b4000, 0xFFFFFF},
- {0}
-};
-
-static struct pci_driver ioc4_driver = {
- .name = "IOC4",
- .id_table = ioc4_id_table,
- .probe = ioc4_probe,
- .remove = ioc4_remove,
-};
-
-MODULE_DEVICE_TABLE(pci, ioc4_id_table);
-
-/*********************
- * Module management *
- *********************/
-
-/* Module load */
-static int __devinit
-ioc4_init(void)
-{
- return pci_register_driver(&ioc4_driver);
-}
-
-/* Module unload */
-static void __devexit
-ioc4_exit(void)
-{
- pci_unregister_driver(&ioc4_driver);
-}
-
-module_init(ioc4_init);
-module_exit(ioc4_exit);
-
-MODULE_AUTHOR("Brent Casavant - Silicon Graphics, Inc. <bcasavan@sgi.com>");
-MODULE_DESCRIPTION("PCI driver master module for SGI IOC4 Base-IO Card");
-MODULE_LICENSE("GPL");
-
-EXPORT_SYMBOL(ioc4_register_submodule);
-EXPORT_SYMBOL(ioc4_unregister_submodule);
depends on FB && PCI
select I2C_ALGOBIT if FB_NVIDIA_I2C
select I2C if FB_NVIDIA_I2C
- select FB_DDC if FB_NVIDIA_I2C
select FB_MODE_HELPERS
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
}
+static u8 *nvidia_do_probe_i2c_edid(struct nvidia_i2c_chan *chan)
+{
+ u8 start = 0x0;
+ struct i2c_msg msgs[] = {
+ {
+ .addr = 0x50,
+ .len = 1,
+ .buf = &start,
+ }, {
+ .addr = 0x50,
+ .flags = I2C_M_RD,
+ .len = EDID_LENGTH,
+ },
+ };
+ u8 *buf;
+
+ if (!chan->par)
+ return NULL;
+
+ buf = kmalloc(EDID_LENGTH, GFP_KERNEL);
+ if (!buf) {
+ dev_warn(&chan->par->pci_dev->dev, "Out of memory!\n");
+ return NULL;
+ }
+ msgs[1].buf = buf;
+
+ if (i2c_transfer(&chan->adapter, msgs, 2) == 2)
+ return buf;
+ dev_dbg(&chan->par->pci_dev->dev, "Unable to read EDID block.\n");
+ kfree(buf);
+ return NULL;
+}
+
int nvidia_probe_i2c_connector(struct fb_info *info, int conn, u8 **out_edid)
{
struct nvidia_par *par = info->par;
- u8 *edid;
-
- edid = fb_ddc_read(&par->chan[conn - 1].adapter);
+ u8 *edid = NULL;
+ int i;
+
+ for (i = 0; i < 3; i++) {
+ /* Do the real work */
+ edid = nvidia_do_probe_i2c_edid(&par->chan[conn - 1]);
+ if (edid)
+ break;
+ }
if (!edid && conn == 1) {
/* try to get from firmware */
config W1
tristate "Dallas's 1-wire support"
- depends on CONNECTOR
---help---
Dallas' 1-wire bus is useful to connect slow 1-pin devices
such as iButtons and thermal sensors.
If you are not using a security module that requires using
extended attributes for file security labels, say N.
+config EXT4DEV_FS
+ tristate "Ext4dev/ext4 extended fs support development (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ select JBD2
+ help
+ Ext4dev is a predecessor filesystem of the next generation
+ extended fs ext4, based on ext3 filesystem code. It will be
+ renamed ext4 fs later, once ext4dev is mature and stabilized.
+
+ Unlike the change from ext2 filesystem to ext3 filesystem,
+ the on-disk format of ext4dev is not the same as ext3 any more:
+ it is based on extent maps and it supports 48-bit physical block
+ numbers. These combined on-disk format changes will allow
+ ext4dev/ext4 to handle more than 16 TB filesystem volumes --
+ a hard limit that ext3 cannot overcome without changing the
+ on-disk format.
+
+ Other than extent maps and 48-bit block numbers, ext4dev also is
+ likely to have other new features such as persistent preallocation,
+ high resolution time stamps, and larger file support etc. These
+ features will be added to ext4dev gradually.
+
+ To compile this file system support as a module, choose M here. The
+ module will be called ext4dev. Be aware, however, that the filesystem
+ of your root partition (the one containing the directory /) cannot
+ be compiled as a module, and so this could be dangerous.
+
+ If unsure, say N.
+
+config EXT4DEV_FS_XATTR
+ bool "Ext4dev extended attributes"
+ depends on EXT4DEV_FS
+ default y
+ help
+ Extended attributes are name:value pairs associated with inodes by
+ the kernel or by users (see the attr(5) manual page, or visit
+ <http://acl.bestbits.at/> for details).
+
+ If unsure, say N.
+
+ You need this for POSIX ACL support on ext4dev/ext4.
+
+config EXT4DEV_FS_POSIX_ACL
+ bool "Ext4dev POSIX Access Control Lists"
+ depends on EXT4DEV_FS_XATTR
+ select FS_POSIX_ACL
+ help
+ POSIX Access Control Lists (ACLs) support permissions for users and
+ groups beyond the owner/group/world scheme.
+
+ To learn more about Access Control Lists, visit the POSIX ACLs for
+ Linux website <http://acl.bestbits.at/>.
+
+ If you don't know what Access Control Lists are, say N
+
+config EXT4DEV_FS_SECURITY
+ bool "Ext4dev Security Labels"
+ depends on EXT4DEV_FS_XATTR
+ help
+ Security labels support alternative access control models
+ implemented by security modules like SELinux. This option
+ enables an extended attribute handler for file security
+ labels in the ext4dev/ext4 filesystem.
+
+ If you are not using a security module that requires using
+ extended attributes for file security labels, say N.
+
config JBD
tristate
help
generated. To turn debugging off again, do
"echo 0 > /proc/sys/fs/jbd-debug".
+config JBD2
+ tristate
+ help
+ This is a generic journaling layer for block devices that support
+ both 32-bit and 64-bit block numbers. It is currently used by
+ the ext4dev/ext4 filesystem, but it could also be used to add
+ journal support to other file systems or block devices such
+ as RAID or LVM.
+
+ If you are using ext4dev/ext4, you need to say Y here. If you are not
+ using ext4dev/ext4 then you will probably want to say N.
+
+ To compile this device as a module, choose M here. The module will be
+ called jbd2. If you are compiling ext4dev/ext4 into the kernel,
+ you cannot compile this code as a module.
+
+config JBD2_DEBUG
+ bool "JBD2 (ext4dev/ext4) debugging support"
+ depends on JBD2
+ help
+ If you are using the ext4dev/ext4 journaled file system (or
+ potentially any other filesystem/device using JBD2), this option
+ allows you to enable debugging output while the system is running,
+ in order to help track down any problems you are having.
+ By default, the debugging output will be turned off.
+
+ If you select Y here, then you will be able to turn on debugging
+ with "echo N > /proc/sys/fs/jbd2-debug", where N is a number between
+ 1 and 5. The higher the number, the more debugging output is
+ generated. To turn debugging off again, do
+ "echo 0 > /proc/sys/fs/jbd2-debug".
+
config FS_MBCACHE
-# Meta block cache for Extended Attributes (ext2/ext3)
+# Meta block cache for Extended Attributes (ext2/ext3/ext4)
tristate
- depends on EXT2_FS_XATTR || EXT3_FS_XATTR
- default y if EXT2_FS=y || EXT3_FS=y
- default m if EXT2_FS=m || EXT3_FS=m
+ depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4DEV_FS_XATTR
+ default y if EXT2_FS=y || EXT3_FS=y || EXT4DEV_FS=y
+ default m if EXT2_FS=m || EXT3_FS=m || EXT4DEV_FS=m
config REISERFS_FS
tristate "Reiserfs support"
config CIFS_UPCALL
bool "Kerberos/SPNEGO advanced session setup (EXPERIMENTAL)"
depends on CIFS_EXPERIMENTAL
- select CONNECTOR
+ depends on CONNECTOR
help
Enables an upcall mechanism for CIFS which will be used to contact
userspace helper utilities to provide SPNEGO packaged Kerberos
# Do not add any filesystems before this line
obj-$(CONFIG_REISERFS_FS) += reiserfs/
obj-$(CONFIG_EXT3_FS) += ext3/ # Before ext2 so root fs can be ext3
+obj-$(CONFIG_EXT4DEV_FS) += ext4/ # Before ext2 so root fs can be ext4dev
obj-$(CONFIG_JBD) += jbd/
+obj-$(CONFIG_JBD2) += jbd2/
obj-$(CONFIG_EXT2_FS) += ext2/
obj-$(CONFIG_CRAMFS) += cramfs/
obj-$(CONFIG_RAMFS) += ramfs/
{
_enter("{%lu}", inode->i_ino);
- BUG_ON(sizeof(union afs_dir_block) != 2048);
- BUG_ON(sizeof(union afs_dirent) != 32);
+ BUILD_BUG_ON(sizeof(union afs_dir_block) != 2048);
+ BUILD_BUG_ON(sizeof(union afs_dirent) != 32);
if (AFS_FS_I(inode)->flags & AFS_VNODE_DELETED)
return -ENOENT;
_enter("{%lu},%p{%s}", dir->i_ino, dentry, dentry->d_name.name);
/* insanity checks first */
- BUG_ON(sizeof(union afs_dir_block) != 2048);
- BUG_ON(sizeof(union afs_dirent) != 32);
+ BUILD_BUG_ON(sizeof(union afs_dir_block) != 2048);
+ BUILD_BUG_ON(sizeof(union afs_dirent) != 32);
if (dentry->d_name.len > 255) {
_leave(" = -ENAMETOOLONG");
struct autofs_sb_info {
u32 magic;
- struct dentry *root;
int pipefd;
struct file *pipe;
pid_t oz_pgrp;
}
void autofs4_dentry_release(struct dentry *);
-
+extern void autofs4_kill_sb(struct super_block *);
.owner = THIS_MODULE,
.name = "autofs",
.get_sb = autofs_get_sb,
- .kill_sb = kill_anon_super,
+ .kill_sb = autofs4_kill_sb,
};
static int __init init_autofs4_fs(void)
*/
static void autofs4_force_release(struct autofs_sb_info *sbi)
{
- struct dentry *this_parent = sbi->root;
+ struct dentry *this_parent = sbi->sb->s_root;
struct list_head *next;
spin_lock(&dcache_lock);
spin_lock(&dcache_lock);
}
- if (this_parent != sbi->root) {
+ if (this_parent != sbi->sb->s_root) {
struct dentry *dentry = this_parent;
next = this_parent->d_u.d_child.next;
goto resume;
}
spin_unlock(&dcache_lock);
-
- dput(sbi->root);
- sbi->root = NULL;
- shrink_dcache_sb(sbi->sb);
-
- return;
}
-static void autofs4_put_super(struct super_block *sb)
+void autofs4_kill_sb(struct super_block *sb)
{
struct autofs_sb_info *sbi = autofs4_sbi(sb);
kfree(sbi);
DPRINTK("shutting down");
+ kill_anon_super(sb);
}
static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt)
}
static struct super_operations autofs4_sops = {
- .put_super = autofs4_put_super,
.statfs = simple_statfs,
.show_options = autofs4_show_options,
};
s->s_fs_info = sbi;
sbi->magic = AUTOFS_SBI_MAGIC;
- sbi->root = NULL;
sbi->pipefd = -1;
sbi->catatonic = 0;
sbi->exp_timeout = 0;
sbi->pipe = pipe;
sbi->pipefd = pipefd;
- /*
- * Take a reference to the root dentry so we get a chance to
- * clean up the dentry tree on umount.
- * See autofs4_force_release.
- */
- sbi->root = dget(root);
-
/*
* Success! Install the root dentry now to indicate completion.
*/
fput(sbi->pipe); /* Close the pipe */
sbi->pipe = NULL;
}
- shrink_dcache_sb(sbi->sb);
}
static int autofs4_write(struct file *file, const void *addr, int bytes)
static int dump_seek(struct file *file, loff_t off)
{
if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
- if (file->f_op->llseek(file, off, 1) != off)
+ if (file->f_op->llseek(file, off, SEEK_CUR) < 0)
return 0;
} else {
char *buf = (char *)get_zeroed_page(GFP_KERNEL);
static int alignfile(struct file *file, loff_t *foffset)
{
- char buf[4] = { 0, };
+ static const char buf[4] = { 0, };
DUMP_WRITE(buf, roundup(*foffset, 4) - *foffset, foffset);
return 1;
}
DUMP_WRITE(elf, sizeof(*elf));
offset += sizeof(*elf); /* Elf header */
- offset += (segs+1) * sizeof(struct elf_phdr); /* Program headers */
+ offset += (segs + 1) * sizeof(struct elf_phdr); /* Program headers */
+ foffset = offset;
/* Write notes phdr entry */
{
DUMP_WRITE(&phdr, sizeof(phdr));
}
- foffset = offset;
-
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
/* Write program headers for segments dump */
phdr.p_align = ELF_EXEC_PAGESIZE;
DUMP_WRITE(&phdr, sizeof(phdr));
- foffset += sizeof(phdr);
}
#ifdef ELF_CORE_WRITE_EXTRA_PHDRS
static inline struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
{
struct bio_vec *bvl;
- struct biovec_slab *bp;
/*
* see comment near bvec_array define!
* idx now points to the pool we want to allocate from
*/
- bp = bvec_slabs + *idx;
bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask);
- if (bvl)
+ if (bvl) {
+ struct biovec_slab *bp = bvec_slabs + *idx;
+
memset(bvl, 0, bp->nr_vecs * sizeof(struct bio_vec));
+ }
return bvl;
}
bio_init(bio);
if (likely(nr_iovecs)) {
- unsigned long idx;
+ unsigned long idx = 0; /* shut up gcc */
bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
if (unlikely(!bvl)) {
bdevname(bh->b_bdev, b));
}
set_bit(AS_EIO, &page->mapping->flags);
+ set_buffer_write_io_error(bh);
clear_buffer_uptodate(bh);
SetPageError(page);
}
static inline void __remove_assoc_queue(struct buffer_head *bh)
{
list_del_init(&bh->b_assoc_buffers);
+ WARN_ON(!bh->b_assoc_map);
+ if (buffer_write_io_error(bh))
+ set_bit(AS_EIO, &bh->b_assoc_map->flags);
+ bh->b_assoc_map = NULL;
}
int inode_has_buffers(struct inode *inode)
spin_lock(&buffer_mapping->private_lock);
list_move_tail(&bh->b_assoc_buffers,
&mapping->private_list);
+ bh->b_assoc_map = mapping;
spin_unlock(&buffer_mapping->private_lock);
}
}
spin_lock(lock);
while (!list_empty(list)) {
bh = BH_ENTRY(list->next);
- list_del_init(&bh->b_assoc_buffers);
+ __remove_assoc_queue(bh);
if (buffer_dirty(bh) || buffer_locked(bh)) {
list_add(&bh->b_assoc_buffers, &tmp);
if (buffer_dirty(bh)) {
while (!list_empty(&tmp)) {
bh = BH_ENTRY(tmp.prev);
- __remove_assoc_queue(bh);
+ list_del_init(&bh->b_assoc_buffers);
get_bh(bh);
spin_unlock(lock);
wait_on_buffer(bh);
} while ((size << sizebits) < PAGE_SIZE);
index = block >> sizebits;
- block = index << sizebits;
+ /*
+ * Check for a block which wants to lie outside our maximum possible
+ * pagecache index. (this comparison is done using sector_t types).
+ */
+ if (unlikely(index != block >> sizebits)) {
+ char b[BDEVNAME_SIZE];
+
+ printk(KERN_ERR "%s: requested out-of-range block %llu for "
+ "device %s\n",
+ __FUNCTION__, (unsigned long long)block,
+ bdevname(bdev, b));
+ return -EIO;
+ }
+ block = index << sizebits;
/* Create a page with the proper size buffers.. */
page = grow_dev_page(bdev, block, index, size);
if (!page)
for (;;) {
struct buffer_head * bh;
+ int ret;
bh = __find_get_block(bdev, block, size);
if (bh)
return bh;
- if (!grow_buffers(bdev, block, size))
+ ret = grow_buffers(bdev, block, size);
+ if (ret < 0)
+ return NULL;
+ if (ret == 0)
free_more_memory();
}
}
spin_lock(&buffer_mapping->private_lock);
list_del_init(&bh->b_assoc_buffers);
+ bh->b_assoc_map = NULL;
spin_unlock(&buffer_mapping->private_lock);
}
__brelse(bh);
clear_buffer_new(bh);
kaddr = kmap_atomic(page, KM_USER0);
memset(kaddr+block_start, 0, bh->b_size);
+ flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
*/
kaddr = kmap_atomic(page, KM_USER0);
memset(kaddr, 0, PAGE_CACHE_SIZE);
+ flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
SetPageUptodate(page);
set_page_dirty(page);
} __attribute__((packed));
/* everyone */
-extern const struct cifs_sid sid_everyone;
+/* extern const struct cifs_sid sid_everyone;*/
/* group users */
-extern const struct cifs_sid sid_user;
+/* extern const struct cifs_sid sid_user;*/
#endif /* _CIFSACL_H */
/* smbdes.c */
extern void E_P16(unsigned char *p14, unsigned char *p16);
extern void E_P24(unsigned char *p21, unsigned char *c8, unsigned char *p24);
-extern void D_P16(unsigned char *p14, unsigned char *in, unsigned char *out);
-extern void E_old_pw_hash(unsigned char *, unsigned char *, unsigned char *);
struct task_struct * oplockThread = NULL;
extern struct task_struct * dnotifyThread; /* remove sparse warning */
struct task_struct * dnotifyThread = NULL;
+static struct super_operations cifs_super_ops;
unsigned int CIFSMaxBufSize = CIFS_MAX_MSGSIZE;
module_param(CIFSMaxBufSize, int, 0);
MODULE_PARM_DESC(CIFSMaxBufSize,"Network buffer size (not including header). Default: 16384 Range: 8192 to 130048");
/* Only need to call the old QFSInfo if failed
on newer one */
if(rc)
- rc = CIFSSMBQFSInfo(xid, pTcon, buf);
+ if(pTcon->ses->capabilities & CAP_NT_SMBS)
+ rc = CIFSSMBQFSInfo(xid, pTcon, buf); /* not supported by OS2 */
- /* Old Windows servers do not support level 103, retry with level
- one if old server failed the previous call */
+ /* Some old Windows servers also do not support level 103, retry with
+ older level one if old server failed the previous call or we
+ bypassed it because we detected that this was an older LANMAN sess */
if(rc)
rc = SMBOldQFSInfo(xid, pTcon, buf);
/*
return;
}
+#ifdef CONFIG_CIFS_STATS2
+static int cifs_show_stats(struct seq_file *s, struct vfsmount *mnt)
+{
+ /* BB FIXME */
+ return 0;
+}
+#endif
+
static int cifs_remount(struct super_block *sb, int *flags, char *data)
{
*flags |= MS_NODIRATIME;
return 0;
}
-struct super_operations cifs_super_ops = {
+static struct super_operations cifs_super_ops = {
.read_inode = cifs_read_inode,
.put_super = cifs_put_super,
.statfs = cifs_statfs,
.show_options = cifs_show_options,
.umount_begin = cifs_umount_begin,
.remount_fs = cifs_remount,
+#ifdef CONFIG_CIFS_STATS2
+ .show_stats = cifs_show_stats,
+#endif
};
static int
static loff_t cifs_llseek(struct file *file, loff_t offset, int origin)
{
/* origin == SEEK_END => we must revalidate the cached file length */
- if (origin == 2) {
+ if (origin == SEEK_END) {
int retval = cifs_revalidate(file->f_dentry);
if (retval < 0)
return (loff_t)retval;
#ifdef CONFIG_PROC_FS
cifs_proc_init();
#endif
- INIT_LIST_HEAD(&GlobalServerList); /* BB not implemented yet */
+/* INIT_LIST_HEAD(&GlobalServerList);*/ /* BB not implemented yet */
INIT_LIST_HEAD(&GlobalSMBSessionList);
INIT_LIST_HEAD(&GlobalTreeConnectionList);
INIT_LIST_HEAD(&GlobalOplock_Q);
GlobalCurrentXid = 0;
GlobalTotalActiveXid = 0;
GlobalMaxActiveXid = 0;
+ memset(Local_System_Name, 0, 15);
rwlock_init(&GlobalSMBSeslock);
spin_lock_init(&GlobalMid_Lock);
extern const struct address_space_operations cifs_addr_ops_smallbuf;
/* Functions related to super block operations */
-extern struct super_operations cifs_super_ops;
+/* extern struct super_operations cifs_super_ops;*/
extern void cifs_read_inode(struct inode *);
extern void cifs_delete_inode(struct inode *);
/* extern void cifs_write_inode(struct inode *); *//* BB not needed yet */
char sessid[4]; /* unique token id for this session */
/* (returned on Negotiate */
int capabilities; /* allow selective disabling of caps by smb sess */
- __u16 timeZone;
+ int timeAdj; /* Adjust for difference in server time zone in sec */
__u16 CurrentMid; /* multiplex id - rotating counter */
char cryptKey[CIFS_CRYPTO_KEY_SIZE];
/* 16th byte of RFC1001 workstation name is always null */
char * domainName;
char * password;
};
-/* session flags */
+/* no more than one of the following three session flags may be set */
#define CIFS_SES_NT4 1
-
+#define CIFS_SES_OS2 2
+#define CIFS_SES_W9X 4
+/* following flag is set for old servers such as OS2 (and Win95?)
+ which do not negotiate NTLM or POSIX dialects, but instead
+ negotiate one of the older LANMAN dialects */
+#define CIFS_SES_LANMAN 8
/*
* there is one of these for each connection to a resource on a particular
* session
* This list helps improve performance and eliminate the messages indicating
* that we had a communications error talking to the server in this list.
*/
-GLOBAL_EXTERN struct servers_not_supported *NotSuppList; /*@z4a */
+/* Feature not supported */
+/* GLOBAL_EXTERN struct servers_not_supported *NotSuppList; */
/*
* The following is a hash table of all the users we know about.
GLOBAL_EXTERN unsigned int extended_security; /* if on, session setup sent
with more secure ntlmssp2 challenge/resp */
GLOBAL_EXTERN unsigned int sign_CIFS_PDUs; /* enable smb packet signing */
-GLOBAL_EXTERN unsigned int secFlags;
GLOBAL_EXTERN unsigned int linuxExtEnabled;/*enable Linux/Unix CIFS extensions*/
GLOBAL_EXTERN unsigned int CIFSMaxBufSize; /* max size not including hdr */
GLOBAL_EXTERN unsigned int cifs_min_rcv; /* min size of big ntwrk buf pool */
#ifdef CONFIG_CIFS_WEAK_PW_HASH
#define LANMAN_PROT 0
-#define CIFS_PROT 1
+#define LANMAN2_PROT 1
+#define CIFS_PROT 2
#else
#define CIFS_PROT 0
#endif
/* Dialect index is 13 for LANMAN */
+#define MIN_TZ_ADJ (15 * 60) /* minimum grid for timezones in seconds */
+
typedef struct lanman_neg_rsp {
struct smb_hdr hdr; /* wct = 13 */
__le16 DialectIndex;
__le16 MaxNumberVcs;
__le16 RawMode;
__le32 SessionKey;
- __le32 ServerTime;
+ struct {
+ __le16 Time;
+ __le16 Date;
+ } __attribute__((packed)) SrvTime;
__le16 ServerTimeZone;
__le16 EncryptionKeyLength;
__le16 Reserved;
typedef struct smb_com_close_req {
struct smb_hdr hdr; /* wct = 3 */
__u16 FileID;
- __u32 LastWriteTime; /* should be zero */
+ __u32 LastWriteTime; /* should be zero or -1 */
__u16 ByteCount; /* 0 */
} __attribute__((packed)) CLOSE_REQ;
extern int SendReceive2(const unsigned int /* xid */ , struct cifsSesInfo *,
struct kvec *, int /* nvec to send */,
int * /* type of buf returned */ , const int long_op);
-extern int SendReceiveBlockingLock(const unsigned int /* xid */ , struct cifsTconInfo *,
+extern int SendReceiveBlockingLock(const unsigned int /* xid */ ,
+ struct cifsTconInfo *,
struct smb_hdr * /* input */ ,
struct smb_hdr * /* out */ ,
int * /* bytes returned */);
-extern int checkSMBhdr(struct smb_hdr *smb, __u16 mid);
-extern int checkSMB(struct smb_hdr *smb, __u16 mid, int length);
+extern int checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length);
extern int is_valid_oplock_break(struct smb_hdr *smb, struct TCP_Server_Info *);
extern int is_size_safe_to_change(struct cifsInodeInfo *);
extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *);
extern void DeleteOplockQEntry(struct oplock_q_entry *);
extern struct timespec cifs_NTtimeToUnix(u64 /* utc nanoseconds since 1601 */ );
extern u64 cifs_UnixTimeToNT(struct timespec);
+extern __le64 cnvrtDosCifsTm(__u16 date, __u16 time);
+extern struct timespec cnvrtDosUnixTm(__u16 date, __u16 time);
+
extern int cifs_get_inode_info(struct inode **pinode,
const unsigned char *search_path,
FILE_ALL_INFO * pfile_info,
extern int CIFSSMBQPathInfo(const int xid, struct cifsTconInfo *tcon,
const unsigned char *searchName,
FILE_ALL_INFO * findData,
+ int legacy /* whether to use old info level */,
const struct nls_table *nls_codepage, int remap);
extern int SMBQueryInformation(const int xid, struct cifsTconInfo *tcon,
const unsigned char *searchName,
extern struct cifsTconInfo *tconInfoAlloc(void);
extern void tconInfoFree(struct cifsTconInfo *);
-extern int cifs_reconnect(struct TCP_Server_Info *server);
-
extern int cifs_sign_smb(struct smb_hdr *, struct TCP_Server_Info *,__u32 *);
extern int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *,
__u32 *);
} protocols[] = {
#ifdef CONFIG_CIFS_WEAK_PW_HASH
{LANMAN_PROT, "\2LM1.2X002"},
+ {LANMAN2_PROT, "\2LANMAN2.1"},
#endif /* weak password hashing for legacy clients */
{CIFS_PROT, "\2NT LM 0.12"},
{POSIX_PROT, "\2POSIX 2"},
} protocols[] = {
#ifdef CONFIG_CIFS_WEAK_PW_HASH
{LANMAN_PROT, "\2LM1.2X002"},
+ {LANMAN2_PROT, "\2LANMAN2.1"},
#endif /* weak password hashing for legacy clients */
{CIFS_PROT, "\2NT LM 0.12"},
{BAD_PROT, "\2"}
/* define the number of elements in the cifs dialect array */
#ifdef CONFIG_CIFS_POSIX
#ifdef CONFIG_CIFS_WEAK_PW_HASH
-#define CIFS_NUM_PROT 3
+#define CIFS_NUM_PROT 4
#else
#define CIFS_NUM_PROT 2
#endif /* CIFS_WEAK_PW_HASH */
#else /* not posix */
#ifdef CONFIG_CIFS_WEAK_PW_HASH
-#define CIFS_NUM_PROT 2
+#define CIFS_NUM_PROT 3
#else
#define CIFS_NUM_PROT 1
#endif /* CONFIG_CIFS_WEAK_PW_HASH */
struct TCP_Server_Info * server;
u16 count;
unsigned int secFlags;
+ u16 dialect;
if(ses->server)
server = ses->server;
if (rc != 0)
goto neg_err_exit;
- cFYI(1,("Dialect: %d", pSMBr->DialectIndex));
+ dialect = le16_to_cpu(pSMBr->DialectIndex);
+ cFYI(1,("Dialect: %d", dialect));
/* Check wct = 1 error case */
- if((pSMBr->hdr.WordCount < 13) || (pSMBr->DialectIndex == BAD_PROT)) {
+ if((pSMBr->hdr.WordCount < 13) || (dialect == BAD_PROT)) {
/* core returns wct = 1, but we do not ask for core - otherwise
small wct just comes when dialect index is -1 indicating we
could not negotiate a common dialect */
goto neg_err_exit;
#ifdef CONFIG_CIFS_WEAK_PW_HASH
} else if((pSMBr->hdr.WordCount == 13)
- && (pSMBr->DialectIndex == LANMAN_PROT)) {
+ && ((dialect == LANMAN_PROT)
+ || (dialect == LANMAN2_PROT))) {
+ __s16 tmp;
struct lanman_neg_rsp * rsp = (struct lanman_neg_rsp *)pSMBr;
if((secFlags & CIFSSEC_MAY_LANMAN) ||
server->maxRw = 0;/* we do not need to use raw anyway */
server->capabilities = CAP_MPX_MODE;
}
- server->timeZone = le16_to_cpu(rsp->ServerTimeZone);
+ tmp = (__s16)le16_to_cpu(rsp->ServerTimeZone);
+ if (tmp == -1) {
+ /* OS/2 often does not set timezone therefore
+ * we must use server time to calc time zone.
+ * Could deviate slightly from the right zone.
+ * Smallest defined timezone difference is 15 minutes
+ * (i.e. Nepal). Rounding up/down is done to match
+ * this requirement.
+ */
+ int val, seconds, remain, result;
+ struct timespec ts, utc;
+ utc = CURRENT_TIME;
+ ts = cnvrtDosUnixTm(le16_to_cpu(rsp->SrvTime.Date),
+ le16_to_cpu(rsp->SrvTime.Time));
+ cFYI(1,("SrvTime: %d sec since 1970 (utc: %d) diff: %d",
+ (int)ts.tv_sec, (int)utc.tv_sec,
+ (int)(utc.tv_sec - ts.tv_sec)));
+ val = (int)(utc.tv_sec - ts.tv_sec);
+ seconds = val < 0 ? -val : val;
+ result = (seconds / MIN_TZ_ADJ) * MIN_TZ_ADJ;
+ remain = seconds % MIN_TZ_ADJ;
+ if(remain >= (MIN_TZ_ADJ / 2))
+ result += MIN_TZ_ADJ;
+ if(val < 0)
+ result = - result;
+ server->timeAdj = result;
+ } else {
+ server->timeAdj = (int)tmp;
+ server->timeAdj *= 60; /* also in seconds */
+ }
+ cFYI(1,("server->timeAdj: %d seconds", server->timeAdj));
+
/* BB get server time for time conversions and add
code to use it and timezone since this is not UTC */
- if (rsp->EncryptionKeyLength == cpu_to_le16(CIFS_CRYPTO_KEY_SIZE)) {
+ if (rsp->EncryptionKeyLength ==
+ cpu_to_le16(CIFS_CRYPTO_KEY_SIZE)) {
memcpy(server->cryptKey, rsp->EncryptionKey,
CIFS_CRYPTO_KEY_SIZE);
} else if (server->secMode & SECMODE_PW_ENCRYPT) {
cFYI(0, ("Max buf = %d", ses->server->maxBuf));
GETU32(ses->server->sessid) = le32_to_cpu(pSMBr->SessionKey);
server->capabilities = le32_to_cpu(pSMBr->Capabilities);
- server->timeZone = le16_to_cpu(pSMBr->ServerTimeZone);
+ server->timeAdj = (int)(__s16)le16_to_cpu(pSMBr->ServerTimeZone);
+ server->timeAdj *= 60;
if (pSMBr->EncryptionKeyLength == CIFS_CRYPTO_KEY_SIZE) {
memcpy(server->cryptKey, pSMBr->u.EncryptionKey,
CIFS_CRYPTO_KEY_SIZE);
pSMBr = (CLOSE_RSP *)pSMB; /* BB removeme BB */
pSMB->FileID = (__u16) smb_file_id;
- pSMB->LastWriteTime = 0;
+ pSMB->LastWriteTime = 0xFFFFFFFF;
pSMB->ByteCount = 0;
rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
(struct smb_hdr *) pSMBr, &bytes_returned, 0);
/* security id for everyone */
-const struct cifs_sid sid_everyone = {1, 1, {0, 0, 0, 0, 0, 0}, {0, 0, 0, 0}};
+const static struct cifs_sid sid_everyone =
+ {1, 1, {0, 0, 0, 0, 0, 0}, {0, 0, 0, 0}};
/* group users */
-const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {32, 545, 0, 0}};
+const static struct cifs_sid sid_user =
+ {1, 2 , {0, 0, 0, 0, 0, 5}, {32, 545, 0, 0}};
/* Convert CIFS ACL to POSIX form */
static int parse_sec_desc(struct cifs_sid * psec_desc, int acl_len)
return rc;
}
-
/* Legacy Query Path Information call for lookup to old servers such
as Win9x/WinME */
int SMBQueryInformation(const int xid, struct cifsTconInfo *tcon,
if (rc) {
cFYI(1, ("Send error in QueryInfo = %d", rc));
} else if (pFinfo) { /* decode response */
+ struct timespec ts;
+ __u32 time = le32_to_cpu(pSMBr->last_write_time);
+ /* BB FIXME - add time zone adjustment BB */
memset(pFinfo, 0, sizeof(FILE_ALL_INFO));
+ ts.tv_nsec = 0;
+ ts.tv_sec = time;
+ /* decode time fields */
+ pFinfo->ChangeTime = cpu_to_le64(cifs_UnixTimeToNT(ts));
+ pFinfo->LastWriteTime = pFinfo->ChangeTime;
+ pFinfo->LastAccessTime = 0;
pFinfo->AllocationSize =
cpu_to_le64(le32_to_cpu(pSMBr->size));
pFinfo->EndOfFile = pFinfo->AllocationSize;
CIFSSMBQPathInfo(const int xid, struct cifsTconInfo *tcon,
const unsigned char *searchName,
FILE_ALL_INFO * pFindData,
+ int legacy /* old style infolevel */,
const struct nls_table *nls_codepage, int remap)
{
/* level 263 SMB_QUERY_FILE_ALL_INFO */
byte_count = params + 1 /* pad */ ;
pSMB->TotalParameterCount = cpu_to_le16(params);
pSMB->ParameterCount = pSMB->TotalParameterCount;
- pSMB->InformationLevel = cpu_to_le16(SMB_QUERY_FILE_ALL_INFO);
+ if(legacy)
+ pSMB->InformationLevel = cpu_to_le16(SMB_INFO_STANDARD);
+ else
+ pSMB->InformationLevel = cpu_to_le16(SMB_QUERY_FILE_ALL_INFO);
pSMB->Reserved4 = 0;
pSMB->hdr.smb_buf_length += byte_count;
pSMB->ByteCount = cpu_to_le16(byte_count);
} else { /* decode response */
rc = validate_t2((struct smb_t2_rsp *)pSMBr);
- if (rc || (pSMBr->ByteCount < 40))
+ if (rc) /* BB add auto retry on EOPNOTSUPP? */
+ rc = -EIO;
+ else if (!legacy && (pSMBr->ByteCount < 40))
rc = -EIO; /* bad smb */
+ else if(legacy && (pSMBr->ByteCount < 24))
+ rc = -EIO; /* 24 or 26 expected but we do not read last field */
else if (pFindData){
+ int size;
__u16 data_offset = le16_to_cpu(pSMBr->t2.DataOffset);
+ if(legacy) /* we do not read the last field, EAsize, fortunately
+ since it varies by subdialect and on Set vs. Get, is
+ two bytes or 4 bytes depending but we don't care here */
+ size = sizeof(FILE_INFO_STANDARD);
+ else
+ size = sizeof(FILE_ALL_INFO);
memcpy((char *) pFindData,
(char *) &pSMBr->hdr.Protocol +
- data_offset, sizeof (FILE_ALL_INFO));
+ data_offset, size);
} else
rc = -ENOMEM;
}
strncpy(pSMB->RequestFileName, searchName, name_len);
}
+ if(ses->server) {
+ if(ses->server->secMode &
+ (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
+ pSMB->hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
+ }
+
+ pSMB->hdr.Uid = ses->Suid;
+
params = 2 /* level */ + name_len /*includes null */ ;
pSMB->TotalDataCount = 0;
pSMB->DataCount = 0;
* wake up waiters on reconnection? - (not needed currently)
*/
-int
+static int
cifs_reconnect(struct TCP_Server_Info *server)
{
int rc = 0;
separator[0] = ',';
separator[1] = 0;
- memset(vol->source_rfc1001_name,0x20,15);
- for(i=0;i < strnlen(utsname()->nodename,15);i++) {
- /* does not have to be a perfect mapping since the field is
- informational, only used for servers that do not support
- port 445 and it can be overridden at mount time */
- vol->source_rfc1001_name[i] =
- toupper(utsname()->nodename[i]);
+ if (Local_System_Name[0] != 0)
+ memcpy(vol->source_rfc1001_name, Local_System_Name,15);
+ else {
+ char *nodename = utsname()->nodename;
+ int n = strnlen(nodename,15);
+ memset(vol->source_rfc1001_name,0x20,15);
+ for(i=0 ; i < n ; i++) {
+ /* does not have to be perfect mapping since field is
+ informational, only used for servers that do not support
+ port 445 and it can be overridden at mount time */
+ vol->source_rfc1001_name[i] = toupper(nodename[i]);
+ }
}
vol->source_rfc1001_name[15] = 0;
/* null target name indicates to use *SMBSERVR default called name
}
/* else do not bother copying these informational fields */
}
- if(smb_buffer_response->WordCount == 3)
+ if((smb_buffer_response->WordCount == 3) ||
+ (smb_buffer_response->WordCount == 7))
+ /* field is in same location */
tcon->Flags = le16_to_cpu(pSMBr->OptionalSupport);
else
tcon->Flags = 0;
first_time = 1;
}
if (!rc) {
+ pSesInfo->flags = 0;
pSesInfo->capabilities = pSesInfo->server->capabilities;
if(linuxExtEnabled == 0)
pSesInfo->capabilities &= (~CAP_UNIX);
/* pSesInfo->sequence_number = 0;*/
- cFYI(1,("Security Mode: 0x%x Capabilities: 0x%x Time Zone: %d",
+ cFYI(1,("Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d",
pSesInfo->server->secMode,
pSesInfo->server->capabilities,
- pSesInfo->server->timeZone));
+ pSesInfo->server->timeAdj));
if(experimEnabled < 2)
rc = CIFS_SessSetup(xid, pSesInfo,
first_time, nls_info);
else if (extended_security
- && (pSesInfo->capabilities & CAP_EXTENDED_SECURITY)
+ && (pSesInfo->capabilities
+ & CAP_EXTENDED_SECURITY)
&& (pSesInfo->server->secType == NTLMSSP)) {
rc = -EOPNOTSUPP;
} else if (extended_security
if (!rc) {
if(ntlmv2_flag) {
char * v2_response;
- cFYI(1,("Can use more secure NTLM version 2 password hash"));
+ cFYI(1,("more secure NTLM ver2 hash"));
if(CalcNTLMv2_partial_mac_key(pSesInfo,
nls_info)) {
rc = -ENOMEM;
pfindData = (FILE_ALL_INFO *)buf;
/* could do find first instead but this returns more info */
rc = CIFSSMBQPathInfo(xid, pTcon, search_path, pfindData,
+ 0 /* not legacy */,
cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
/* BB optimize code so we do not make the above call
/* get new inode */
if (*pinode == NULL) {
*pinode = new_inode(sb);
- if (*pinode == NULL)
+ if (*pinode == NULL) {
+ kfree(buf);
return -ENOMEM;
+ }
/* Is an i_ino of zero legal? Can we use that to check
if the server supports returning inode numbers? Are
there other sanity checks we can use to ensure that
(pTcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE) & 0xFFFFFE00;*/
/* Linux can not store file creation time so ignore it */
- inode->i_atime =
- cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastAccessTime));
+ if(pfindData->LastAccessTime)
+ inode->i_atime = cifs_NTtimeToUnix
+ (le64_to_cpu(pfindData->LastAccessTime));
+ else /* do not need to use current_fs_time - time not stored */
+ inode->i_atime = CURRENT_TIME;
inode->i_mtime =
cifs_NTtimeToUnix(le64_to_cpu(pfindData->LastWriteTime));
inode->i_ctime =
tmpbuffer,
len - 1,
cifs_sb->local_nls);
- else {
+ else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+ cERROR(1,("SFU style symlinks not implemented yet"));
+ /* add open and read as in fs/cifs/inode.c */
+
+ } else {
rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN, GENERIC_READ,
OPEN_REPARSE_POINT,&fid, &oplock, NULL,
cifs_sb->local_nls,
buf[3] += d;
}
+#if 0 /* currently unused */
/***********************************************************************
the rfc 2104 version of hmac_md5 initialisation.
***********************************************************************/
-void
+static void
hmac_md5_init_rfc2104(unsigned char *key, int key_len,
struct HMACMD5Context *ctx)
{
MD5Init(&ctx->ctx);
MD5Update(&ctx->ctx, ctx->k_ipad, 64);
}
+#endif
/***********************************************************************
the microsoft version of hmac_md5 initialisation.
single function to calculate an HMAC MD5 digest from data.
use the microsoft hmacmd5 init method because the key is 16 bytes.
************************************************************/
-void
+#if 0 /* currently unused */
+static void
hmac_md5(unsigned char key[16], unsigned char *data, int data_len,
unsigned char *digest)
{
}
hmac_md5_final(digest, &ctx);
}
+#endif
/* The following definitions come from lib/hmacmd5.c */
-void hmac_md5_init_rfc2104(unsigned char *key, int key_len,
- struct HMACMD5Context *ctx);
+/* void hmac_md5_init_rfc2104(unsigned char *key, int key_len,
+ struct HMACMD5Context *ctx);*/
void hmac_md5_init_limK_to_64(const unsigned char *key, int key_len,
struct HMACMD5Context *ctx);
void hmac_md5_update(const unsigned char *text, int text_len,
struct HMACMD5Context *ctx);
void hmac_md5_final(unsigned char *digest, struct HMACMD5Context *ctx);
-void hmac_md5(unsigned char key[16], unsigned char *data, int data_len,
- unsigned char *digest);
+/* void hmac_md5(unsigned char key[16], unsigned char *data, int data_len,
+ unsigned char *digest);*/
return;
}
-int
+static int
checkSMBhdr(struct smb_hdr *smb, __u16 mid)
{
/* Make sure that this really is an SMB, that it is a response,
}
int
-checkSMB(struct smb_hdr *smb, __u16 mid, int length)
+checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length)
{
__u32 len = smb->smb_buf_length;
__u32 clc_len; /* calculated length */
cFYI(0, ("checkSMB Length: 0x%x, smb_buf_length: 0x%x", length, len));
- if (((unsigned int)length < 2 + sizeof (struct smb_hdr)) ||
- (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4)) {
- if ((unsigned int)length < 2 + sizeof (struct smb_hdr)) {
- if (((unsigned int)length >=
- sizeof (struct smb_hdr) - 1)
+
+ if (length < 2 + sizeof (struct smb_hdr)) {
+ if ((length >= sizeof (struct smb_hdr) - 1)
&& (smb->Status.CifsError != 0)) {
- smb->WordCount = 0;
- /* some error cases do not return wct and bcc */
+ smb->WordCount = 0;
+ /* some error cases do not return wct and bcc */
+ return 0;
+ } else if ((length == sizeof(struct smb_hdr) + 1) &&
+ (smb->WordCount == 0)) {
+ char * tmp = (char *)smb;
+ /* Need to work around a bug in two servers here */
+ /* First, check if the part of bcc they sent was zero */
+ if (tmp[sizeof(struct smb_hdr)] == 0) {
+ /* some servers return only half of bcc
+ * on simple responses (wct, bcc both zero)
+ * in particular have seen this on
+ * ulogoffX and FindClose. This leaves
+ * one byte of bcc potentially unitialized
+ */
+ /* zero rest of bcc */
+ tmp[sizeof(struct smb_hdr)+1] = 0;
return 0;
- } else {
- cERROR(1, ("Length less than smb header size"));
}
+ cERROR(1,("rcvd invalid byte count (bcc)"));
+ } else {
+ cERROR(1, ("Length less than smb header size"));
}
- if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4)
- cERROR(1, ("smb length greater than MaxBufSize, mid=%d",
+ return 1;
+ }
+ if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
+ cERROR(1, ("smb length greater than MaxBufSize, mid=%d",
smb->Mid));
return 1;
}
return 1;
clc_len = smbCalcSize_LE(smb);
- if(4 + len != (unsigned int)length) {
+ if(4 + len != length) {
cERROR(1, ("Length read does not match RFC1001 length %d",len));
return 1;
}
/* Convert to 100ns intervals and then add the NTFS time offset. */
return (u64) t.tv_sec * 10000000 + t.tv_nsec/100 + NTFS_TIME_OFFSET;
}
+
+static int total_days_of_prev_months[] =
+{0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334};
+
+
+__le64 cnvrtDosCifsTm(__u16 date, __u16 time)
+{
+ return cpu_to_le64(cifs_UnixTimeToNT(cnvrtDosUnixTm(date, time)));
+}
+
+struct timespec cnvrtDosUnixTm(__u16 date, __u16 time)
+{
+ struct timespec ts;
+ int sec, min, days, month, year;
+ SMB_TIME * st = (SMB_TIME *)&time;
+ SMB_DATE * sd = (SMB_DATE *)&date;
+
+ cFYI(1,("date %d time %d",date, time));
+
+ sec = 2 * st->TwoSeconds;
+ min = st->Minutes;
+ if((sec > 59) || (min > 59))
+ cERROR(1,("illegal time min %d sec %d", min, sec));
+ sec += (min * 60);
+ sec += 60 * 60 * st->Hours;
+ if(st->Hours > 24)
+ cERROR(1,("illegal hours %d",st->Hours));
+ days = sd->Day;
+ month = sd->Month;
+ if((days > 31) || (month > 12))
+ cERROR(1,("illegal date, month %d day: %d", month, days));
+ month -= 1;
+ days += total_days_of_prev_months[month];
+ days += 3652; /* account for difference in days between 1980 and 1970 */
+ year = sd->Year;
+ days += year * 365;
+ days += (year/4); /* leap year */
+ /* generalized leap year calculation is more complex, ie no leap year
+ for years/100 except for years/400, but since the maximum number for DOS
+ year is 2**7, the last year is 1980+127, which means we need only
+ consider 2 special case years, ie the years 2000 and 2100, and only
+ adjust for the lack of leap year for the year 2100, as 2000 was a
+ leap year (divisable by 400) */
+ if(year >= 120) /* the year 2100 */
+ days = days - 1; /* do not count leap year for the year 2100 */
+
+ /* adjust for leap year where we are still before leap day */
+ if(year != 120)
+ days -= ((year & 0x03) == 0) && (month < 2 ? 1 : 0);
+ sec += 24 * 60 * 60 * days;
+
+ ts.tv_sec = sec;
+
+ /* cFYI(1,("sec after cnvrt dos to unix time %d",sec)); */
+
+ ts.tv_nsec = 0;
+ return ts;
+}
return rc;
}
+static void AdjustForTZ(struct cifsTconInfo * tcon, struct inode * inode)
+{
+ if((tcon) && (tcon->ses) && (tcon->ses->server)) {
+ inode->i_ctime.tv_sec += tcon->ses->server->timeAdj;
+ inode->i_mtime.tv_sec += tcon->ses->server->timeAdj;
+ inode->i_atime.tv_sec += tcon->ses->server->timeAdj;
+ }
+ return;
+}
+
+
static void fill_in_inode(struct inode *tmp_inode, int new_buf_type,
char * buf, int *pobject_type, int isNewInode)
{
tmp_inode->i_ctime =
cifs_NTtimeToUnix(le64_to_cpu(pfindData->ChangeTime));
} else { /* legacy, OS2 and DOS style */
+/* struct timespec ts;*/
FIND_FILE_STANDARD_INFO * pfindData =
(FIND_FILE_STANDARD_INFO *)buf;
+ tmp_inode->i_mtime = cnvrtDosUnixTm(
+ le16_to_cpu(pfindData->LastWriteDate),
+ le16_to_cpu(pfindData->LastWriteTime));
+ tmp_inode->i_atime = cnvrtDosUnixTm(
+ le16_to_cpu(pfindData->LastAccessDate),
+ le16_to_cpu(pfindData->LastAccessTime));
+ tmp_inode->i_ctime = cnvrtDosUnixTm(
+ le16_to_cpu(pfindData->LastWriteDate),
+ le16_to_cpu(pfindData->LastWriteTime));
+ AdjustForTZ(cifs_sb->tcon, tmp_inode);
attr = le16_to_cpu(pfindData->Attributes);
allocation_size = le32_to_cpu(pfindData->AllocationSize);
end_of_file = le32_to_cpu(pfindData->DataSize);
- tmp_inode->i_atime = CURRENT_TIME;
- /* tmp_inode->i_mtime = BB FIXME - add dos time handling
- tmp_inode->i_ctime = 0; BB FIXME */
-
}
/* Linux can not store file creation time unfortunately so ignore it */
filename = &pFindData->FileName[0];
/* one byte length, no name conversion */
len = (unsigned int)pFindData->FileNameLength;
+ cifsFile->srch_inf.resume_key = pFindData->ResumeKey;
} else {
cFYI(1,("Unknown findfirst level %d",level));
return -EINVAL;
ses->serverOS = kzalloc(len + 1, GFP_KERNEL);
if(ses->serverOS)
strncpy(ses->serverOS, bcc_ptr, len);
+ if(strncmp(ses->serverOS, "OS/2",4) == 0) {
+ cFYI(1,("OS/2 server"));
+ ses->flags |= CIFS_SES_OS2;
+ }
bcc_ptr += len + 1;
bleft -= len + 1;
if(len > bleft)
return rc;
- if(ses->serverDomain)
- kfree(ses->serverDomain);
-
- ses->serverDomain = kzalloc(len + 1, GFP_KERNEL);
- if(ses->serverOS)
- strncpy(ses->serverOS, bcc_ptr, len);
-
- bcc_ptr += len + 1;
- bleft -= len + 1;
-
+ /* No domain field in LANMAN case. Domain is
+ returned by old servers in the SMB negprot response */
+ /* BB For newer servers which do not support Unicode,
+ but thus do return domain here we could add parsing
+ for it later, but it is not very important */
cFYI(1,("ascii: bytes left %d",bleft));
return rc;
str_area = kmalloc(2000, GFP_KERNEL);
bcc_ptr = str_area;
+ ses->flags &= ~CIFS_SES_LANMAN;
+
if(type == LANMAN) {
#ifdef CONFIG_CIFS_WEAK_PW_HASH
char lnm_session_key[CIFS_SESS_KEY_SIZE];
/* and copy into bcc */
calc_lanman_hash(ses, lnm_session_key);
-
+ ses->flags |= CIFS_SES_LANMAN;
/* #ifdef CONFIG_CIFS_DEBUG2
cifs_dump_mem("cryptkey: ",ses->server->cryptKey,
CIFS_SESS_KEY_SIZE);
smbhash(p24 + 16, c8, p21 + 14, 1);
}
-void
+#if 0 /* currently unsued */
+static void
D_P16(unsigned char *p14, unsigned char *in, unsigned char *out)
{
smbhash(out, in, p14, 0);
smbhash(out + 8, in + 8, p14 + 7, 0);
}
-void
+static void
E_old_pw_hash(unsigned char *p14, unsigned char *in, unsigned char *out)
{
smbhash(out, in, p14, 1);
smbhash(out + 8, in + 8, p14 + 7, 1);
}
-#if 0
/* these routines are currently unneeded, but may be
needed later */
void
void SMBencrypt(unsigned char *passwd, unsigned char *c8, unsigned char *p24);
void E_md4hash(const unsigned char *passwd, unsigned char *p16);
-void nt_lm_owf_gen(char *pwd, unsigned char nt_p16[16], unsigned char p16[16]);
static void SMBOWFencrypt(unsigned char passwd[16], unsigned char *c8,
unsigned char p24[24]);
-void NTLMSSPOWFencrypt(unsigned char passwd[8],
- unsigned char *ntlmchalresp, unsigned char p24[24]);
void SMBNTencrypt(unsigned char *passwd, unsigned char *c8, unsigned char *p24);
/*
memset(wpwd,0,129 * 2);
}
+#if 0 /* currently unused */
/* Does both the NT and LM owfs of a user's password */
-void
+static void
nt_lm_owf_gen(char *pwd, unsigned char nt_p16[16], unsigned char p16[16])
{
char passwd[514];
/* clear out local copy of user's password (just being paranoid). */
memset(passwd, '\0', sizeof (passwd));
}
+#endif
/* Does the NTLMv2 owfs of a user's password */
#if 0 /* function not needed yet - but will be soon */
}
/* Does the des encryption from the FIRST 8 BYTES of the NT or LM MD4 hash. */
-void
+#if 0 /* currently unused */
+static void
NTLMSSPOWFencrypt(unsigned char passwd[8],
unsigned char *ntlmchalresp, unsigned char p24[24])
{
E_P24(p21, ntlmchalresp, p24);
}
+#endif
/* Does the NT MD4 hash then des encryption. */
HANDLE_IOCTL(BLKFRAGET, w_long)
HANDLE_IOCTL(BLKSECTGET, w_long)
HANDLE_IOCTL(BLKPG, blkpg_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_KEEPSETTINGS, hdio_ioctl_trans)
HANDLE_IOCTL(HDIO_GET_UNMASKINTR, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_DMA, hdio_ioctl_trans)
-HANDLE_IOCTL(HDIO_GET_32BIT, hdio_ioctl_trans)
HANDLE_IOCTL(HDIO_GET_MULTCOUNT, hdio_ioctl_trans)
+HANDLE_IOCTL(HDIO_GET_KEEPSETTINGS, hdio_ioctl_trans)
+HANDLE_IOCTL(HDIO_GET_32BIT, hdio_ioctl_trans)
HANDLE_IOCTL(HDIO_GET_NOWERR, hdio_ioctl_trans)
+HANDLE_IOCTL(HDIO_GET_DMA, hdio_ioctl_trans)
HANDLE_IOCTL(HDIO_GET_NICE, hdio_ioctl_trans)
+HANDLE_IOCTL(HDIO_GET_WCACHE, hdio_ioctl_trans)
+HANDLE_IOCTL(HDIO_GET_ACOUSTIC, hdio_ioctl_trans)
+HANDLE_IOCTL(HDIO_GET_ADDRESS, hdio_ioctl_trans)
+HANDLE_IOCTL(HDIO_GET_BUSSTATE, hdio_ioctl_trans)
HANDLE_IOCTL(FDSETPRM32, fd_ioctl_trans)
HANDLE_IOCTL(FDDEFPRM32, fd_ioctl_trans)
HANDLE_IOCTL(FDGETPRM32, fd_ioctl_trans)
spin_unlock(&dcache_lock);
}
+/*
+ * destroy a single subtree of dentries for unmount
+ * - see the comments on shrink_dcache_for_umount() for a description of the
+ * locking
+ */
+static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
+{
+ struct dentry *parent;
+
+ BUG_ON(!IS_ROOT(dentry));
+
+ /* detach this root from the system */
+ spin_lock(&dcache_lock);
+ if (!list_empty(&dentry->d_lru)) {
+ dentry_stat.nr_unused--;
+ list_del_init(&dentry->d_lru);
+ }
+ __d_drop(dentry);
+ spin_unlock(&dcache_lock);
+
+ for (;;) {
+ /* descend to the first leaf in the current subtree */
+ while (!list_empty(&dentry->d_subdirs)) {
+ struct dentry *loop;
+
+ /* this is a branch with children - detach all of them
+ * from the system in one go */
+ spin_lock(&dcache_lock);
+ list_for_each_entry(loop, &dentry->d_subdirs,
+ d_u.d_child) {
+ if (!list_empty(&loop->d_lru)) {
+ dentry_stat.nr_unused--;
+ list_del_init(&loop->d_lru);
+ }
+
+ __d_drop(loop);
+ cond_resched_lock(&dcache_lock);
+ }
+ spin_unlock(&dcache_lock);
+
+ /* move to the first child */
+ dentry = list_entry(dentry->d_subdirs.next,
+ struct dentry, d_u.d_child);
+ }
+
+ /* consume the dentries from this leaf up through its parents
+ * until we find one with children or run out altogether */
+ do {
+ struct inode *inode;
+
+ if (atomic_read(&dentry->d_count) != 0) {
+ printk(KERN_ERR
+ "BUG: Dentry %p{i=%lx,n=%s}"
+ " still in use (%d)"
+ " [unmount of %s %s]\n",
+ dentry,
+ dentry->d_inode ?
+ dentry->d_inode->i_ino : 0UL,
+ dentry->d_name.name,
+ atomic_read(&dentry->d_count),
+ dentry->d_sb->s_type->name,
+ dentry->d_sb->s_id);
+ BUG();
+ }
+
+ parent = dentry->d_parent;
+ if (parent == dentry)
+ parent = NULL;
+ else
+ atomic_dec(&parent->d_count);
+
+ list_del(&dentry->d_u.d_child);
+ dentry_stat.nr_dentry--; /* For d_free, below */
+
+ inode = dentry->d_inode;
+ if (inode) {
+ dentry->d_inode = NULL;
+ list_del_init(&dentry->d_alias);
+ if (dentry->d_op && dentry->d_op->d_iput)
+ dentry->d_op->d_iput(dentry, inode);
+ else
+ iput(inode);
+ }
+
+ d_free(dentry);
+
+ /* finished when we fall off the top of the tree,
+ * otherwise we ascend to the parent and move to the
+ * next sibling if there is one */
+ if (!parent)
+ return;
+
+ dentry = parent;
+
+ } while (list_empty(&dentry->d_subdirs));
+
+ dentry = list_entry(dentry->d_subdirs.next,
+ struct dentry, d_u.d_child);
+ }
+}
+
+/*
+ * destroy the dentries attached to a superblock on unmounting
+ * - we don't need to use dentry->d_lock, and only need dcache_lock when
+ * removing the dentry from the system lists and hashes because:
+ * - the superblock is detached from all mountings and open files, so the
+ * dentry trees will not be rearranged by the VFS
+ * - s_umount is write-locked, so the memory pressure shrinker will ignore
+ * any dentries belonging to this superblock that it comes across
+ * - the filesystem itself is no longer permitted to rearrange the dentries
+ * in this superblock
+ */
+void shrink_dcache_for_umount(struct super_block *sb)
+{
+ struct dentry *dentry;
+
+ if (down_read_trylock(&sb->s_umount))
+ BUG();
+
+ dentry = sb->s_root;
+ sb->s_root = NULL;
+ atomic_dec(&dentry->d_count);
+ shrink_dcache_for_umount_subtree(dentry);
+
+ while (!hlist_empty(&sb->s_anon)) {
+ dentry = hlist_entry(sb->s_anon.first, struct dentry, d_hash);
+ shrink_dcache_for_umount_subtree(dentry);
+ }
+}
+
/*
* Search for at least 1 mount point in the dentry's subdirs.
* We descend to the next level whenever the d_subdirs
menu "Distributed Lock Manager"
- depends on INET && EXPERIMENTAL
+ depends on INET && IP_SCTP && EXPERIMENTAL
config DLM
tristate "Distributed Lock Manager (DLM)"
depends on IPV6 || IPV6=n
- depends on IP_SCTP
select CONFIGFS_FS
help
A general purpose distributed lock manager for kernel or userspace
}
len = iov[0].iov_len + iov[1].iov_len;
- r = ret = kernel_recvmsg(sctp_con.sock, &msg, iov, 1, len,
+ r = ret = kernel_recvmsg(sctp_con.sock, &msg, iov, msg.msg_iovlen, len,
MSG_NOSIGNAL | MSG_DONTWAIT);
if (ret <= 0)
goto out_close;
/* Maximum msec timeout value storeable in a long int */
#define EP_MAX_MSTIMEO min(1000ULL * MAX_SCHEDULE_TIMEOUT / HZ, (LONG_MAX - 999ULL) / HZ)
+#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
+
struct epoll_filefd {
struct file *file;
*/
asmlinkage long sys_epoll_create(int size)
{
- int error, fd;
+ int error, fd = -1;
struct eventpoll *ep;
struct inode *inode;
struct file *file;
return error;
}
-#define MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
/*
* Implement the event wait interface for the eventpoll file. It is the kernel
current, epfd, events, maxevents, timeout));
/* The maximum number of event must be greater than zero */
- if (maxevents <= 0 || maxevents > MAX_EVENTS)
+ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
return -EINVAL;
/* Verify that the area passed by the user is writeable */
}
+#ifdef TIF_RESTORE_SIGMASK
+
+/*
+ * Implement the event wait interface for the eventpoll file. It is the kernel
+ * part of the user space epoll_pwait(2).
+ */
+asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
+ int maxevents, int timeout, const sigset_t __user *sigmask,
+ size_t sigsetsize)
+{
+ int error;
+ sigset_t ksigmask, sigsaved;
+
+ /*
+ * If the caller wants a certain signal mask to be set during the wait,
+ * we apply it here.
+ */
+ if (sigmask) {
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+ if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
+ return -EFAULT;
+ sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+ }
+
+ error = sys_epoll_wait(epfd, events, maxevents, timeout);
+
+ /*
+ * If we changed the signal mask, we need to restore the original one.
+ * In case we've got a signal while waiting, we do not restore the
+ * signal mask yet, and we allow do_signal() to deliver the signal on
+ * the way back to userspace, before the signal mask is restored.
+ */
+ if (sigmask) {
+ if (error == -EINTR) {
+ memcpy(¤t->saved_sigmask, &sigsaved,
+ sizeof(sigsaved));
+ set_thread_flag(TIF_RESTORE_SIGMASK);
+ } else
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ }
+
+ return error;
+}
+
+#endif /* #ifdef TIF_RESTORE_SIGMASK */
+
+
/*
* Creates the file descriptor to be used by the epoll interface.
*/
{
char * p;
substring_t args[MAX_OPT_ARGS];
- unsigned long kind = EXT2_MOUNT_ERRORS_CONT;
int option;
if (!options)
/* *sb_block = match_int(&args[0]); */
break;
case Opt_err_panic:
- kind = EXT2_MOUNT_ERRORS_PANIC;
+ clear_opt (sbi->s_mount_opt, ERRORS_CONT);
+ clear_opt (sbi->s_mount_opt, ERRORS_RO);
+ set_opt (sbi->s_mount_opt, ERRORS_PANIC);
break;
case Opt_err_ro:
- kind = EXT2_MOUNT_ERRORS_RO;
+ clear_opt (sbi->s_mount_opt, ERRORS_CONT);
+ clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
+ set_opt (sbi->s_mount_opt, ERRORS_RO);
break;
case Opt_err_cont:
- kind = EXT2_MOUNT_ERRORS_CONT;
+ clear_opt (sbi->s_mount_opt, ERRORS_RO);
+ clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
+ set_opt (sbi->s_mount_opt, ERRORS_CONT);
break;
case Opt_nouid32:
set_opt (sbi->s_mount_opt, NO_UID32);
return 0;
}
}
- sbi->s_mount_opt |= kind;
return 1;
}
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_RO)
set_opt(sbi->s_mount_opt, ERRORS_RO);
+ else
+ set_opt(sbi->s_mount_opt, ERRORS_CONT);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
set_opt(sbi->s_mount_opt, ERRORS_PANIC);
else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_RO)
set_opt(sbi->s_mount_opt, ERRORS_RO);
+ else
+ set_opt(sbi->s_mount_opt, ERRORS_CONT);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
--- /dev/null
+#
+# Makefile for the linux ext4-filesystem routines.
+#
+
+obj-$(CONFIG_EXT4DEV_FS) += ext4dev.o
+
+ext4dev-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \
+ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o
+
+ext4dev-$(CONFIG_EXT4DEV_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
+ext4dev-$(CONFIG_EXT4DEV_FS_POSIX_ACL) += acl.o
+ext4dev-$(CONFIG_EXT4DEV_FS_SECURITY) += xattr_security.o
--- /dev/null
+/*
+ * linux/fs/ext4/acl.c
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ */
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/ext4_fs.h>
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Convert from filesystem to in-memory representation.
+ */
+static struct posix_acl *
+ext4_acl_from_disk(const void *value, size_t size)
+{
+ const char *end = (char *)value + size;
+ int n, count;
+ struct posix_acl *acl;
+
+ if (!value)
+ return NULL;
+ if (size < sizeof(ext4_acl_header))
+ return ERR_PTR(-EINVAL);
+ if (((ext4_acl_header *)value)->a_version !=
+ cpu_to_le32(EXT4_ACL_VERSION))
+ return ERR_PTR(-EINVAL);
+ value = (char *)value + sizeof(ext4_acl_header);
+ count = ext4_acl_count(size);
+ if (count < 0)
+ return ERR_PTR(-EINVAL);
+ if (count == 0)
+ return NULL;
+ acl = posix_acl_alloc(count, GFP_KERNEL);
+ if (!acl)
+ return ERR_PTR(-ENOMEM);
+ for (n=0; n < count; n++) {
+ ext4_acl_entry *entry =
+ (ext4_acl_entry *)value;
+ if ((char *)value + sizeof(ext4_acl_entry_short) > end)
+ goto fail;
+ acl->a_entries[n].e_tag = le16_to_cpu(entry->e_tag);
+ acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
+ switch(acl->a_entries[n].e_tag) {
+ case ACL_USER_OBJ:
+ case ACL_GROUP_OBJ:
+ case ACL_MASK:
+ case ACL_OTHER:
+ value = (char *)value +
+ sizeof(ext4_acl_entry_short);
+ acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
+ break;
+
+ case ACL_USER:
+ case ACL_GROUP:
+ value = (char *)value + sizeof(ext4_acl_entry);
+ if ((char *)value > end)
+ goto fail;
+ acl->a_entries[n].e_id =
+ le32_to_cpu(entry->e_id);
+ break;
+
+ default:
+ goto fail;
+ }
+ }
+ if (value != end)
+ goto fail;
+ return acl;
+
+fail:
+ posix_acl_release(acl);
+ return ERR_PTR(-EINVAL);
+}
+
+/*
+ * Convert from in-memory to filesystem representation.
+ */
+static void *
+ext4_acl_to_disk(const struct posix_acl *acl, size_t *size)
+{
+ ext4_acl_header *ext_acl;
+ char *e;
+ size_t n;
+
+ *size = ext4_acl_size(acl->a_count);
+ ext_acl = kmalloc(sizeof(ext4_acl_header) + acl->a_count *
+ sizeof(ext4_acl_entry), GFP_KERNEL);
+ if (!ext_acl)
+ return ERR_PTR(-ENOMEM);
+ ext_acl->a_version = cpu_to_le32(EXT4_ACL_VERSION);
+ e = (char *)ext_acl + sizeof(ext4_acl_header);
+ for (n=0; n < acl->a_count; n++) {
+ ext4_acl_entry *entry = (ext4_acl_entry *)e;
+ entry->e_tag = cpu_to_le16(acl->a_entries[n].e_tag);
+ entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
+ switch(acl->a_entries[n].e_tag) {
+ case ACL_USER:
+ case ACL_GROUP:
+ entry->e_id =
+ cpu_to_le32(acl->a_entries[n].e_id);
+ e += sizeof(ext4_acl_entry);
+ break;
+
+ case ACL_USER_OBJ:
+ case ACL_GROUP_OBJ:
+ case ACL_MASK:
+ case ACL_OTHER:
+ e += sizeof(ext4_acl_entry_short);
+ break;
+
+ default:
+ goto fail;
+ }
+ }
+ return (char *)ext_acl;
+
+fail:
+ kfree(ext_acl);
+ return ERR_PTR(-EINVAL);
+}
+
+static inline struct posix_acl *
+ext4_iget_acl(struct inode *inode, struct posix_acl **i_acl)
+{
+ struct posix_acl *acl = EXT4_ACL_NOT_CACHED;
+
+ spin_lock(&inode->i_lock);
+ if (*i_acl != EXT4_ACL_NOT_CACHED)
+ acl = posix_acl_dup(*i_acl);
+ spin_unlock(&inode->i_lock);
+
+ return acl;
+}
+
+static inline void
+ext4_iset_acl(struct inode *inode, struct posix_acl **i_acl,
+ struct posix_acl *acl)
+{
+ spin_lock(&inode->i_lock);
+ if (*i_acl != EXT4_ACL_NOT_CACHED)
+ posix_acl_release(*i_acl);
+ *i_acl = posix_acl_dup(acl);
+ spin_unlock(&inode->i_lock);
+}
+
+/*
+ * Inode operation get_posix_acl().
+ *
+ * inode->i_mutex: don't care
+ */
+static struct posix_acl *
+ext4_get_acl(struct inode *inode, int type)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int name_index;
+ char *value = NULL;
+ struct posix_acl *acl;
+ int retval;
+
+ if (!test_opt(inode->i_sb, POSIX_ACL))
+ return NULL;
+
+ switch(type) {
+ case ACL_TYPE_ACCESS:
+ acl = ext4_iget_acl(inode, &ei->i_acl);
+ if (acl != EXT4_ACL_NOT_CACHED)
+ return acl;
+ name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
+ break;
+
+ case ACL_TYPE_DEFAULT:
+ acl = ext4_iget_acl(inode, &ei->i_default_acl);
+ if (acl != EXT4_ACL_NOT_CACHED)
+ return acl;
+ name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
+ break;
+
+ default:
+ return ERR_PTR(-EINVAL);
+ }
+ retval = ext4_xattr_get(inode, name_index, "", NULL, 0);
+ if (retval > 0) {
+ value = kmalloc(retval, GFP_KERNEL);
+ if (!value)
+ return ERR_PTR(-ENOMEM);
+ retval = ext4_xattr_get(inode, name_index, "", value, retval);
+ }
+ if (retval > 0)
+ acl = ext4_acl_from_disk(value, retval);
+ else if (retval == -ENODATA || retval == -ENOSYS)
+ acl = NULL;
+ else
+ acl = ERR_PTR(retval);
+ kfree(value);
+
+ if (!IS_ERR(acl)) {
+ switch(type) {
+ case ACL_TYPE_ACCESS:
+ ext4_iset_acl(inode, &ei->i_acl, acl);
+ break;
+
+ case ACL_TYPE_DEFAULT:
+ ext4_iset_acl(inode, &ei->i_default_acl, acl);
+ break;
+ }
+ }
+ return acl;
+}
+
+/*
+ * Set the access or default ACL of an inode.
+ *
+ * inode->i_mutex: down unless called from ext4_new_inode
+ */
+static int
+ext4_set_acl(handle_t *handle, struct inode *inode, int type,
+ struct posix_acl *acl)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int name_index;
+ void *value = NULL;
+ size_t size = 0;
+ int error;
+
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+
+ switch(type) {
+ case ACL_TYPE_ACCESS:
+ name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
+ if (acl) {
+ mode_t mode = inode->i_mode;
+ error = posix_acl_equiv_mode(acl, &mode);
+ if (error < 0)
+ return error;
+ else {
+ inode->i_mode = mode;
+ ext4_mark_inode_dirty(handle, inode);
+ if (error == 0)
+ acl = NULL;
+ }
+ }
+ break;
+
+ case ACL_TYPE_DEFAULT:
+ name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
+ if (!S_ISDIR(inode->i_mode))
+ return acl ? -EACCES : 0;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+ if (acl) {
+ value = ext4_acl_to_disk(acl, &size);
+ if (IS_ERR(value))
+ return (int)PTR_ERR(value);
+ }
+
+ error = ext4_xattr_set_handle(handle, inode, name_index, "",
+ value, size, 0);
+
+ kfree(value);
+ if (!error) {
+ switch(type) {
+ case ACL_TYPE_ACCESS:
+ ext4_iset_acl(inode, &ei->i_acl, acl);
+ break;
+
+ case ACL_TYPE_DEFAULT:
+ ext4_iset_acl(inode, &ei->i_default_acl, acl);
+ break;
+ }
+ }
+ return error;
+}
+
+static int
+ext4_check_acl(struct inode *inode, int mask)
+{
+ struct posix_acl *acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
+
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ if (acl) {
+ int error = posix_acl_permission(inode, acl, mask);
+ posix_acl_release(acl);
+ return error;
+ }
+
+ return -EAGAIN;
+}
+
+int
+ext4_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+ return generic_permission(inode, mask, ext4_check_acl);
+}
+
+/*
+ * Initialize the ACLs of a new inode. Called from ext4_new_inode.
+ *
+ * dir->i_mutex: down
+ * inode->i_mutex: up (access to inode is still exclusive)
+ */
+int
+ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+ struct posix_acl *acl = NULL;
+ int error = 0;
+
+ if (!S_ISLNK(inode->i_mode)) {
+ if (test_opt(dir->i_sb, POSIX_ACL)) {
+ acl = ext4_get_acl(dir, ACL_TYPE_DEFAULT);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ }
+ if (!acl)
+ inode->i_mode &= ~current->fs->umask;
+ }
+ if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
+ struct posix_acl *clone;
+ mode_t mode;
+
+ if (S_ISDIR(inode->i_mode)) {
+ error = ext4_set_acl(handle, inode,
+ ACL_TYPE_DEFAULT, acl);
+ if (error)
+ goto cleanup;
+ }
+ clone = posix_acl_clone(acl, GFP_KERNEL);
+ error = -ENOMEM;
+ if (!clone)
+ goto cleanup;
+
+ mode = inode->i_mode;
+ error = posix_acl_create_masq(clone, &mode);
+ if (error >= 0) {
+ inode->i_mode = mode;
+ if (error > 0) {
+ /* This is an extended ACL */
+ error = ext4_set_acl(handle, inode,
+ ACL_TYPE_ACCESS, clone);
+ }
+ }
+ posix_acl_release(clone);
+ }
+cleanup:
+ posix_acl_release(acl);
+ return error;
+}
+
+/*
+ * Does chmod for an inode that may have an Access Control List. The
+ * inode->i_mode field must be updated to the desired value by the caller
+ * before calling this function.
+ * Returns 0 on success, or a negative error number.
+ *
+ * We change the ACL rather than storing some ACL entries in the file
+ * mode permission bits (which would be more efficient), because that
+ * would break once additional permissions (like ACL_APPEND, ACL_DELETE
+ * for directories) are added. There are no more bits available in the
+ * file mode.
+ *
+ * inode->i_mutex: down
+ */
+int
+ext4_acl_chmod(struct inode *inode)
+{
+ struct posix_acl *acl, *clone;
+ int error;
+
+ if (S_ISLNK(inode->i_mode))
+ return -EOPNOTSUPP;
+ if (!test_opt(inode->i_sb, POSIX_ACL))
+ return 0;
+ acl = ext4_get_acl(inode, ACL_TYPE_ACCESS);
+ if (IS_ERR(acl) || !acl)
+ return PTR_ERR(acl);
+ clone = posix_acl_clone(acl, GFP_KERNEL);
+ posix_acl_release(acl);
+ if (!clone)
+ return -ENOMEM;
+ error = posix_acl_chmod_masq(clone, inode->i_mode);
+ if (!error) {
+ handle_t *handle;
+ int retries = 0;
+
+ retry:
+ handle = ext4_journal_start(inode,
+ EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+ if (IS_ERR(handle)) {
+ error = PTR_ERR(handle);
+ ext4_std_error(inode->i_sb, error);
+ goto out;
+ }
+ error = ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, clone);
+ ext4_journal_stop(handle);
+ if (error == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+ }
+out:
+ posix_acl_release(clone);
+ return error;
+}
+
+/*
+ * Extended attribute handlers
+ */
+static size_t
+ext4_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
+ const char *name, size_t name_len)
+{
+ const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
+
+ if (!test_opt(inode->i_sb, POSIX_ACL))
+ return 0;
+ if (list && size <= list_len)
+ memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
+ return size;
+}
+
+static size_t
+ext4_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
+ const char *name, size_t name_len)
+{
+ const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
+
+ if (!test_opt(inode->i_sb, POSIX_ACL))
+ return 0;
+ if (list && size <= list_len)
+ memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
+ return size;
+}
+
+static int
+ext4_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+{
+ struct posix_acl *acl;
+ int error;
+
+ if (!test_opt(inode->i_sb, POSIX_ACL))
+ return -EOPNOTSUPP;
+
+ acl = ext4_get_acl(inode, type);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ if (acl == NULL)
+ return -ENODATA;
+ error = posix_acl_to_xattr(acl, buffer, size);
+ posix_acl_release(acl);
+
+ return error;
+}
+
+static int
+ext4_xattr_get_acl_access(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ return ext4_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
+}
+
+static int
+ext4_xattr_get_acl_default(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ return ext4_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
+}
+
+static int
+ext4_xattr_set_acl(struct inode *inode, int type, const void *value,
+ size_t size)
+{
+ handle_t *handle;
+ struct posix_acl *acl;
+ int error, retries = 0;
+
+ if (!test_opt(inode->i_sb, POSIX_ACL))
+ return -EOPNOTSUPP;
+ if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ return -EPERM;
+
+ if (value) {
+ acl = posix_acl_from_xattr(value, size);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ else if (acl) {
+ error = posix_acl_valid(acl);
+ if (error)
+ goto release_and_out;
+ }
+ } else
+ acl = NULL;
+
+retry:
+ handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ error = ext4_set_acl(handle, inode, type, acl);
+ ext4_journal_stop(handle);
+ if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+
+release_and_out:
+ posix_acl_release(acl);
+ return error;
+}
+
+static int
+ext4_xattr_set_acl_access(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ return ext4_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
+}
+
+static int
+ext4_xattr_set_acl_default(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ return ext4_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
+}
+
+struct xattr_handler ext4_xattr_acl_access_handler = {
+ .prefix = POSIX_ACL_XATTR_ACCESS,
+ .list = ext4_xattr_list_acl_access,
+ .get = ext4_xattr_get_acl_access,
+ .set = ext4_xattr_set_acl_access,
+};
+
+struct xattr_handler ext4_xattr_acl_default_handler = {
+ .prefix = POSIX_ACL_XATTR_DEFAULT,
+ .list = ext4_xattr_list_acl_default,
+ .get = ext4_xattr_get_acl_default,
+ .set = ext4_xattr_set_acl_default,
+};
--- /dev/null
+/*
+ File: fs/ext4/acl.h
+
+ (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/posix_acl_xattr.h>
+
+#define EXT4_ACL_VERSION 0x0001
+
+typedef struct {
+ __le16 e_tag;
+ __le16 e_perm;
+ __le32 e_id;
+} ext4_acl_entry;
+
+typedef struct {
+ __le16 e_tag;
+ __le16 e_perm;
+} ext4_acl_entry_short;
+
+typedef struct {
+ __le32 a_version;
+} ext4_acl_header;
+
+static inline size_t ext4_acl_size(int count)
+{
+ if (count <= 4) {
+ return sizeof(ext4_acl_header) +
+ count * sizeof(ext4_acl_entry_short);
+ } else {
+ return sizeof(ext4_acl_header) +
+ 4 * sizeof(ext4_acl_entry_short) +
+ (count - 4) * sizeof(ext4_acl_entry);
+ }
+}
+
+static inline int ext4_acl_count(size_t size)
+{
+ ssize_t s;
+ size -= sizeof(ext4_acl_header);
+ s = size - 4 * sizeof(ext4_acl_entry_short);
+ if (s < 0) {
+ if (size % sizeof(ext4_acl_entry_short))
+ return -1;
+ return size / sizeof(ext4_acl_entry_short);
+ } else {
+ if (s % sizeof(ext4_acl_entry))
+ return -1;
+ return s / sizeof(ext4_acl_entry) + 4;
+ }
+}
+
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+
+/* Value for inode->u.ext4_i.i_acl and inode->u.ext4_i.i_default_acl
+ if the ACL has not been cached */
+#define EXT4_ACL_NOT_CACHED ((void *)-1)
+
+/* acl.c */
+extern int ext4_permission (struct inode *, int, struct nameidata *);
+extern int ext4_acl_chmod (struct inode *);
+extern int ext4_init_acl (handle_t *, struct inode *, struct inode *);
+
+#else /* CONFIG_EXT4DEV_FS_POSIX_ACL */
+#include <linux/sched.h>
+#define ext4_permission NULL
+
+static inline int
+ext4_acl_chmod(struct inode *inode)
+{
+ return 0;
+}
+
+static inline int
+ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+ return 0;
+}
+#endif /* CONFIG_EXT4DEV_FS_POSIX_ACL */
+
--- /dev/null
+/*
+ * linux/fs/ext4/balloc.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * Enhanced block allocation by Stephen Tweedie (sct@redhat.com), 1993
+ * Big-endian to little-endian byte-swapping/bitmaps by
+ * David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/time.h>
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+
+/*
+ * balloc.c contains the blocks allocation and deallocation routines
+ */
+
+/*
+ * Calculate the block group number and offset, given a block number
+ */
+void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
+ unsigned long *blockgrpp, ext4_grpblk_t *offsetp)
+{
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ ext4_grpblk_t offset;
+
+ blocknr = blocknr - le32_to_cpu(es->s_first_data_block);
+ offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb));
+ if (offsetp)
+ *offsetp = offset;
+ if (blockgrpp)
+ *blockgrpp = blocknr;
+
+}
+
+/*
+ * The free blocks are managed by bitmaps. A file system contains several
+ * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
+ * block for inodes, N blocks for the inode table and data blocks.
+ *
+ * The file system contains group descriptors which are located after the
+ * super block. Each descriptor contains the number of the bitmap block and
+ * the free blocks count in the block. The descriptors are loaded in memory
+ * when a file system is mounted (see ext4_read_super).
+ */
+
+
+#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
+
+/**
+ * ext4_get_group_desc() -- load group descriptor from disk
+ * @sb: super block
+ * @block_group: given block group
+ * @bh: pointer to the buffer head to store the block
+ * group descriptor
+ */
+struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
+ unsigned int block_group,
+ struct buffer_head ** bh)
+{
+ unsigned long group_desc;
+ unsigned long offset;
+ struct ext4_group_desc * desc;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (block_group >= sbi->s_groups_count) {
+ ext4_error (sb, "ext4_get_group_desc",
+ "block_group >= groups_count - "
+ "block_group = %d, groups_count = %lu",
+ block_group, sbi->s_groups_count);
+
+ return NULL;
+ }
+ smp_rmb();
+
+ group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
+ offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
+ if (!sbi->s_group_desc[group_desc]) {
+ ext4_error (sb, "ext4_get_group_desc",
+ "Group descriptor not loaded - "
+ "block_group = %d, group_desc = %lu, desc = %lu",
+ block_group, group_desc, offset);
+ return NULL;
+ }
+
+ desc = (struct ext4_group_desc *)(
+ (__u8 *)sbi->s_group_desc[group_desc]->b_data +
+ offset * EXT4_DESC_SIZE(sb));
+ if (bh)
+ *bh = sbi->s_group_desc[group_desc];
+ return desc;
+}
+
+/**
+ * read_block_bitmap()
+ * @sb: super block
+ * @block_group: given block group
+ *
+ * Read the bitmap for a given block_group, reading into the specified
+ * slot in the superblock's bitmap cache.
+ *
+ * Return buffer_head on success or NULL in case of failure.
+ */
+static struct buffer_head *
+read_block_bitmap(struct super_block *sb, unsigned int block_group)
+{
+ struct ext4_group_desc * desc;
+ struct buffer_head * bh = NULL;
+
+ desc = ext4_get_group_desc (sb, block_group, NULL);
+ if (!desc)
+ goto error_out;
+ bh = sb_bread(sb, ext4_block_bitmap(sb, desc));
+ if (!bh)
+ ext4_error (sb, "read_block_bitmap",
+ "Cannot read block bitmap - "
+ "block_group = %d, block_bitmap = %llu",
+ block_group,
+ ext4_block_bitmap(sb, desc));
+error_out:
+ return bh;
+}
+/*
+ * The reservation window structure operations
+ * --------------------------------------------
+ * Operations include:
+ * dump, find, add, remove, is_empty, find_next_reservable_window, etc.
+ *
+ * We use a red-black tree to represent per-filesystem reservation
+ * windows.
+ *
+ */
+
+/**
+ * __rsv_window_dump() -- Dump the filesystem block allocation reservation map
+ * @rb_root: root of per-filesystem reservation rb tree
+ * @verbose: verbose mode
+ * @fn: function which wishes to dump the reservation map
+ *
+ * If verbose is turned on, it will print the whole block reservation
+ * windows(start, end). Otherwise, it will only print out the "bad" windows,
+ * those windows that overlap with their immediate neighbors.
+ */
+#if 1
+static void __rsv_window_dump(struct rb_root *root, int verbose,
+ const char *fn)
+{
+ struct rb_node *n;
+ struct ext4_reserve_window_node *rsv, *prev;
+ int bad;
+
+restart:
+ n = rb_first(root);
+ bad = 0;
+ prev = NULL;
+
+ printk("Block Allocation Reservation Windows Map (%s):\n", fn);
+ while (n) {
+ rsv = list_entry(n, struct ext4_reserve_window_node, rsv_node);
+ if (verbose)
+ printk("reservation window 0x%p "
+ "start: %llu, end: %llu\n",
+ rsv, rsv->rsv_start, rsv->rsv_end);
+ if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) {
+ printk("Bad reservation %p (start >= end)\n",
+ rsv);
+ bad = 1;
+ }
+ if (prev && prev->rsv_end >= rsv->rsv_start) {
+ printk("Bad reservation %p (prev->end >= start)\n",
+ rsv);
+ bad = 1;
+ }
+ if (bad) {
+ if (!verbose) {
+ printk("Restarting reservation walk in verbose mode\n");
+ verbose = 1;
+ goto restart;
+ }
+ }
+ n = rb_next(n);
+ prev = rsv;
+ }
+ printk("Window map complete.\n");
+ if (bad)
+ BUG();
+}
+#define rsv_window_dump(root, verbose) \
+ __rsv_window_dump((root), (verbose), __FUNCTION__)
+#else
+#define rsv_window_dump(root, verbose) do {} while (0)
+#endif
+
+/**
+ * goal_in_my_reservation()
+ * @rsv: inode's reservation window
+ * @grp_goal: given goal block relative to the allocation block group
+ * @group: the current allocation block group
+ * @sb: filesystem super block
+ *
+ * Test if the given goal block (group relative) is within the file's
+ * own block reservation window range.
+ *
+ * If the reservation window is outside the goal allocation group, return 0;
+ * grp_goal (given goal block) could be -1, which means no specific
+ * goal block. In this case, always return 1.
+ * If the goal block is within the reservation window, return 1;
+ * otherwise, return 0;
+ */
+static int
+goal_in_my_reservation(struct ext4_reserve_window *rsv, ext4_grpblk_t grp_goal,
+ unsigned int group, struct super_block * sb)
+{
+ ext4_fsblk_t group_first_block, group_last_block;
+
+ group_first_block = ext4_group_first_block_no(sb, group);
+ group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
+
+ if ((rsv->_rsv_start > group_last_block) ||
+ (rsv->_rsv_end < group_first_block))
+ return 0;
+ if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start)
+ || (grp_goal + group_first_block > rsv->_rsv_end)))
+ return 0;
+ return 1;
+}
+
+/**
+ * search_reserve_window()
+ * @rb_root: root of reservation tree
+ * @goal: target allocation block
+ *
+ * Find the reserved window which includes the goal, or the previous one
+ * if the goal is not in any window.
+ * Returns NULL if there are no windows or if all windows start after the goal.
+ */
+static struct ext4_reserve_window_node *
+search_reserve_window(struct rb_root *root, ext4_fsblk_t goal)
+{
+ struct rb_node *n = root->rb_node;
+ struct ext4_reserve_window_node *rsv;
+
+ if (!n)
+ return NULL;
+
+ do {
+ rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
+
+ if (goal < rsv->rsv_start)
+ n = n->rb_left;
+ else if (goal > rsv->rsv_end)
+ n = n->rb_right;
+ else
+ return rsv;
+ } while (n);
+ /*
+ * We've fallen off the end of the tree: the goal wasn't inside
+ * any particular node. OK, the previous node must be to one
+ * side of the interval containing the goal. If it's the RHS,
+ * we need to back up one.
+ */
+ if (rsv->rsv_start > goal) {
+ n = rb_prev(&rsv->rsv_node);
+ rsv = rb_entry(n, struct ext4_reserve_window_node, rsv_node);
+ }
+ return rsv;
+}
+
+/**
+ * ext4_rsv_window_add() -- Insert a window to the block reservation rb tree.
+ * @sb: super block
+ * @rsv: reservation window to add
+ *
+ * Must be called with rsv_lock hold.
+ */
+void ext4_rsv_window_add(struct super_block *sb,
+ struct ext4_reserve_window_node *rsv)
+{
+ struct rb_root *root = &EXT4_SB(sb)->s_rsv_window_root;
+ struct rb_node *node = &rsv->rsv_node;
+ ext4_fsblk_t start = rsv->rsv_start;
+
+ struct rb_node ** p = &root->rb_node;
+ struct rb_node * parent = NULL;
+ struct ext4_reserve_window_node *this;
+
+ while (*p)
+ {
+ parent = *p;
+ this = rb_entry(parent, struct ext4_reserve_window_node, rsv_node);
+
+ if (start < this->rsv_start)
+ p = &(*p)->rb_left;
+ else if (start > this->rsv_end)
+ p = &(*p)->rb_right;
+ else {
+ rsv_window_dump(root, 1);
+ BUG();
+ }
+ }
+
+ rb_link_node(node, parent, p);
+ rb_insert_color(node, root);
+}
+
+/**
+ * ext4_rsv_window_remove() -- unlink a window from the reservation rb tree
+ * @sb: super block
+ * @rsv: reservation window to remove
+ *
+ * Mark the block reservation window as not allocated, and unlink it
+ * from the filesystem reservation window rb tree. Must be called with
+ * rsv_lock hold.
+ */
+static void rsv_window_remove(struct super_block *sb,
+ struct ext4_reserve_window_node *rsv)
+{
+ rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
+ rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
+ rsv->rsv_alloc_hit = 0;
+ rb_erase(&rsv->rsv_node, &EXT4_SB(sb)->s_rsv_window_root);
+}
+
+/*
+ * rsv_is_empty() -- Check if the reservation window is allocated.
+ * @rsv: given reservation window to check
+ *
+ * returns 1 if the end block is EXT4_RESERVE_WINDOW_NOT_ALLOCATED.
+ */
+static inline int rsv_is_empty(struct ext4_reserve_window *rsv)
+{
+ /* a valid reservation end block could not be 0 */
+ return rsv->_rsv_end == EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
+}
+
+/**
+ * ext4_init_block_alloc_info()
+ * @inode: file inode structure
+ *
+ * Allocate and initialize the reservation window structure, and
+ * link the window to the ext4 inode structure at last
+ *
+ * The reservation window structure is only dynamically allocated
+ * and linked to ext4 inode the first time the open file
+ * needs a new block. So, before every ext4_new_block(s) call, for
+ * regular files, we should check whether the reservation window
+ * structure exists or not. In the latter case, this function is called.
+ * Fail to do so will result in block reservation being turned off for that
+ * open file.
+ *
+ * This function is called from ext4_get_blocks_handle(), also called
+ * when setting the reservation window size through ioctl before the file
+ * is open for write (needs block allocation).
+ *
+ * Needs truncate_mutex protection prior to call this function.
+ */
+void ext4_init_block_alloc_info(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info;
+ struct super_block *sb = inode->i_sb;
+
+ block_i = kmalloc(sizeof(*block_i), GFP_NOFS);
+ if (block_i) {
+ struct ext4_reserve_window_node *rsv = &block_i->rsv_window_node;
+
+ rsv->rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
+ rsv->rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
+
+ /*
+ * if filesystem is mounted with NORESERVATION, the goal
+ * reservation window size is set to zero to indicate
+ * block reservation is off
+ */
+ if (!test_opt(sb, RESERVATION))
+ rsv->rsv_goal_size = 0;
+ else
+ rsv->rsv_goal_size = EXT4_DEFAULT_RESERVE_BLOCKS;
+ rsv->rsv_alloc_hit = 0;
+ block_i->last_alloc_logical_block = 0;
+ block_i->last_alloc_physical_block = 0;
+ }
+ ei->i_block_alloc_info = block_i;
+}
+
+/**
+ * ext4_discard_reservation()
+ * @inode: inode
+ *
+ * Discard(free) block reservation window on last file close, or truncate
+ * or at last iput().
+ *
+ * It is being called in three cases:
+ * ext4_release_file(): last writer close the file
+ * ext4_clear_inode(): last iput(), when nobody link to this file.
+ * ext4_truncate(): when the block indirect map is about to change.
+ *
+ */
+void ext4_discard_reservation(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_block_alloc_info *block_i = ei->i_block_alloc_info;
+ struct ext4_reserve_window_node *rsv;
+ spinlock_t *rsv_lock = &EXT4_SB(inode->i_sb)->s_rsv_window_lock;
+
+ if (!block_i)
+ return;
+
+ rsv = &block_i->rsv_window_node;
+ if (!rsv_is_empty(&rsv->rsv_window)) {
+ spin_lock(rsv_lock);
+ if (!rsv_is_empty(&rsv->rsv_window))
+ rsv_window_remove(inode->i_sb, rsv);
+ spin_unlock(rsv_lock);
+ }
+}
+
+/**
+ * ext4_free_blocks_sb() -- Free given blocks and update quota
+ * @handle: handle to this transaction
+ * @sb: super block
+ * @block: start physcial block to free
+ * @count: number of blocks to free
+ * @pdquot_freed_blocks: pointer to quota
+ */
+void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
+ ext4_fsblk_t block, unsigned long count,
+ unsigned long *pdquot_freed_blocks)
+{
+ struct buffer_head *bitmap_bh = NULL;
+ struct buffer_head *gd_bh;
+ unsigned long block_group;
+ ext4_grpblk_t bit;
+ unsigned long i;
+ unsigned long overflow;
+ struct ext4_group_desc * desc;
+ struct ext4_super_block * es;
+ struct ext4_sb_info *sbi;
+ int err = 0, ret;
+ ext4_grpblk_t group_freed;
+
+ *pdquot_freed_blocks = 0;
+ sbi = EXT4_SB(sb);
+ es = sbi->s_es;
+ if (block < le32_to_cpu(es->s_first_data_block) ||
+ block + count < block ||
+ block + count > ext4_blocks_count(es)) {
+ ext4_error (sb, "ext4_free_blocks",
+ "Freeing blocks not in datazone - "
+ "block = %llu, count = %lu", block, count);
+ goto error_return;
+ }
+
+ ext4_debug ("freeing block(s) %llu-%llu\n", block, block + count - 1);
+
+do_more:
+ overflow = 0;
+ ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+ /*
+ * Check to see if we are freeing blocks across a group
+ * boundary.
+ */
+ if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
+ overflow = bit + count - EXT4_BLOCKS_PER_GROUP(sb);
+ count -= overflow;
+ }
+ brelse(bitmap_bh);
+ bitmap_bh = read_block_bitmap(sb, block_group);
+ if (!bitmap_bh)
+ goto error_return;
+ desc = ext4_get_group_desc (sb, block_group, &gd_bh);
+ if (!desc)
+ goto error_return;
+
+ if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
+ in_range(ext4_inode_bitmap(sb, desc), block, count) ||
+ in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
+ in_range(block + count - 1, ext4_inode_table(sb, desc),
+ sbi->s_itb_per_group))
+ ext4_error (sb, "ext4_free_blocks",
+ "Freeing blocks in system zones - "
+ "Block = %llu, count = %lu",
+ block, count);
+
+ /*
+ * We are about to start releasing blocks in the bitmap,
+ * so we need undo access.
+ */
+ /* @@@ check errors */
+ BUFFER_TRACE(bitmap_bh, "getting undo access");
+ err = ext4_journal_get_undo_access(handle, bitmap_bh);
+ if (err)
+ goto error_return;
+
+ /*
+ * We are about to modify some metadata. Call the journal APIs
+ * to unshare ->b_data if a currently-committing transaction is
+ * using it
+ */
+ BUFFER_TRACE(gd_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, gd_bh);
+ if (err)
+ goto error_return;
+
+ jbd_lock_bh_state(bitmap_bh);
+
+ for (i = 0, group_freed = 0; i < count; i++) {
+ /*
+ * An HJ special. This is expensive...
+ */
+#ifdef CONFIG_JBD_DEBUG
+ jbd_unlock_bh_state(bitmap_bh);
+ {
+ struct buffer_head *debug_bh;
+ debug_bh = sb_find_get_block(sb, block + i);
+ if (debug_bh) {
+ BUFFER_TRACE(debug_bh, "Deleted!");
+ if (!bh2jh(bitmap_bh)->b_committed_data)
+ BUFFER_TRACE(debug_bh,
+ "No commited data in bitmap");
+ BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap");
+ __brelse(debug_bh);
+ }
+ }
+ jbd_lock_bh_state(bitmap_bh);
+#endif
+ if (need_resched()) {
+ jbd_unlock_bh_state(bitmap_bh);
+ cond_resched();
+ jbd_lock_bh_state(bitmap_bh);
+ }
+ /* @@@ This prevents newly-allocated data from being
+ * freed and then reallocated within the same
+ * transaction.
+ *
+ * Ideally we would want to allow that to happen, but to
+ * do so requires making jbd2_journal_forget() capable of
+ * revoking the queued write of a data block, which
+ * implies blocking on the journal lock. *forget()
+ * cannot block due to truncate races.
+ *
+ * Eventually we can fix this by making jbd2_journal_forget()
+ * return a status indicating whether or not it was able
+ * to revoke the buffer. On successful revoke, it is
+ * safe not to set the allocation bit in the committed
+ * bitmap, because we know that there is no outstanding
+ * activity on the buffer any more and so it is safe to
+ * reallocate it.
+ */
+ BUFFER_TRACE(bitmap_bh, "set in b_committed_data");
+ J_ASSERT_BH(bitmap_bh,
+ bh2jh(bitmap_bh)->b_committed_data != NULL);
+ ext4_set_bit_atomic(sb_bgl_lock(sbi, block_group), bit + i,
+ bh2jh(bitmap_bh)->b_committed_data);
+
+ /*
+ * We clear the bit in the bitmap after setting the committed
+ * data bit, because this is the reverse order to that which
+ * the allocator uses.
+ */
+ BUFFER_TRACE(bitmap_bh, "clear bit");
+ if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
+ bit + i, bitmap_bh->b_data)) {
+ jbd_unlock_bh_state(bitmap_bh);
+ ext4_error(sb, __FUNCTION__,
+ "bit already cleared for block %llu",
+ (ext4_fsblk_t)(block + i));
+ jbd_lock_bh_state(bitmap_bh);
+ BUFFER_TRACE(bitmap_bh, "bit already cleared");
+ } else {
+ group_freed++;
+ }
+ }
+ jbd_unlock_bh_state(bitmap_bh);
+
+ spin_lock(sb_bgl_lock(sbi, block_group));
+ desc->bg_free_blocks_count =
+ cpu_to_le16(le16_to_cpu(desc->bg_free_blocks_count) +
+ group_freed);
+ spin_unlock(sb_bgl_lock(sbi, block_group));
+ percpu_counter_mod(&sbi->s_freeblocks_counter, count);
+
+ /* We dirtied the bitmap block */
+ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+ err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+
+ /* And the group descriptor block */
+ BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
+ ret = ext4_journal_dirty_metadata(handle, gd_bh);
+ if (!err) err = ret;
+ *pdquot_freed_blocks += group_freed;
+
+ if (overflow && !err) {
+ block += count;
+ count = overflow;
+ goto do_more;
+ }
+ sb->s_dirt = 1;
+error_return:
+ brelse(bitmap_bh);
+ ext4_std_error(sb, err);
+ return;
+}
+
+/**
+ * ext4_free_blocks() -- Free given blocks and update quota
+ * @handle: handle for this transaction
+ * @inode: inode
+ * @block: start physical block to free
+ * @count: number of blocks to count
+ */
+void ext4_free_blocks(handle_t *handle, struct inode *inode,
+ ext4_fsblk_t block, unsigned long count)
+{
+ struct super_block * sb;
+ unsigned long dquot_freed_blocks;
+
+ sb = inode->i_sb;
+ if (!sb) {
+ printk ("ext4_free_blocks: nonexistent device");
+ return;
+ }
+ ext4_free_blocks_sb(handle, sb, block, count, &dquot_freed_blocks);
+ if (dquot_freed_blocks)
+ DQUOT_FREE_BLOCK(inode, dquot_freed_blocks);
+ return;
+}
+
+/**
+ * ext4_test_allocatable()
+ * @nr: given allocation block group
+ * @bh: bufferhead contains the bitmap of the given block group
+ *
+ * For ext4 allocations, we must not reuse any blocks which are
+ * allocated in the bitmap buffer's "last committed data" copy. This
+ * prevents deletes from freeing up the page for reuse until we have
+ * committed the delete transaction.
+ *
+ * If we didn't do this, then deleting something and reallocating it as
+ * data would allow the old block to be overwritten before the
+ * transaction committed (because we force data to disk before commit).
+ * This would lead to corruption if we crashed between overwriting the
+ * data and committing the delete.
+ *
+ * @@@ We may want to make this allocation behaviour conditional on
+ * data-writes at some point, and disable it for metadata allocations or
+ * sync-data inodes.
+ */
+static int ext4_test_allocatable(ext4_grpblk_t nr, struct buffer_head *bh)
+{
+ int ret;
+ struct journal_head *jh = bh2jh(bh);
+
+ if (ext4_test_bit(nr, bh->b_data))
+ return 0;
+
+ jbd_lock_bh_state(bh);
+ if (!jh->b_committed_data)
+ ret = 1;
+ else
+ ret = !ext4_test_bit(nr, jh->b_committed_data);
+ jbd_unlock_bh_state(bh);
+ return ret;
+}
+
+/**
+ * bitmap_search_next_usable_block()
+ * @start: the starting block (group relative) of the search
+ * @bh: bufferhead contains the block group bitmap
+ * @maxblocks: the ending block (group relative) of the reservation
+ *
+ * The bitmap search --- search forward alternately through the actual
+ * bitmap on disk and the last-committed copy in journal, until we find a
+ * bit free in both bitmaps.
+ */
+static ext4_grpblk_t
+bitmap_search_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh,
+ ext4_grpblk_t maxblocks)
+{
+ ext4_grpblk_t next;
+ struct journal_head *jh = bh2jh(bh);
+
+ while (start < maxblocks) {
+ next = ext4_find_next_zero_bit(bh->b_data, maxblocks, start);
+ if (next >= maxblocks)
+ return -1;
+ if (ext4_test_allocatable(next, bh))
+ return next;
+ jbd_lock_bh_state(bh);
+ if (jh->b_committed_data)
+ start = ext4_find_next_zero_bit(jh->b_committed_data,
+ maxblocks, next);
+ jbd_unlock_bh_state(bh);
+ }
+ return -1;
+}
+
+/**
+ * find_next_usable_block()
+ * @start: the starting block (group relative) to find next
+ * allocatable block in bitmap.
+ * @bh: bufferhead contains the block group bitmap
+ * @maxblocks: the ending block (group relative) for the search
+ *
+ * Find an allocatable block in a bitmap. We honor both the bitmap and
+ * its last-committed copy (if that exists), and perform the "most
+ * appropriate allocation" algorithm of looking for a free block near
+ * the initial goal; then for a free byte somewhere in the bitmap; then
+ * for any free bit in the bitmap.
+ */
+static ext4_grpblk_t
+find_next_usable_block(ext4_grpblk_t start, struct buffer_head *bh,
+ ext4_grpblk_t maxblocks)
+{
+ ext4_grpblk_t here, next;
+ char *p, *r;
+
+ if (start > 0) {
+ /*
+ * The goal was occupied; search forward for a free
+ * block within the next XX blocks.
+ *
+ * end_goal is more or less random, but it has to be
+ * less than EXT4_BLOCKS_PER_GROUP. Aligning up to the
+ * next 64-bit boundary is simple..
+ */
+ ext4_grpblk_t end_goal = (start + 63) & ~63;
+ if (end_goal > maxblocks)
+ end_goal = maxblocks;
+ here = ext4_find_next_zero_bit(bh->b_data, end_goal, start);
+ if (here < end_goal && ext4_test_allocatable(here, bh))
+ return here;
+ ext4_debug("Bit not found near goal\n");
+ }
+
+ here = start;
+ if (here < 0)
+ here = 0;
+
+ p = ((char *)bh->b_data) + (here >> 3);
+ r = memscan(p, 0, (maxblocks - here + 7) >> 3);
+ next = (r - ((char *)bh->b_data)) << 3;
+
+ if (next < maxblocks && next >= start && ext4_test_allocatable(next, bh))
+ return next;
+
+ /*
+ * The bitmap search --- search forward alternately through the actual
+ * bitmap and the last-committed copy until we find a bit free in
+ * both
+ */
+ here = bitmap_search_next_usable_block(here, bh, maxblocks);
+ return here;
+}
+
+/**
+ * claim_block()
+ * @block: the free block (group relative) to allocate
+ * @bh: the bufferhead containts the block group bitmap
+ *
+ * We think we can allocate this block in this bitmap. Try to set the bit.
+ * If that succeeds then check that nobody has allocated and then freed the
+ * block since we saw that is was not marked in b_committed_data. If it _was_
+ * allocated and freed then clear the bit in the bitmap again and return
+ * zero (failure).
+ */
+static inline int
+claim_block(spinlock_t *lock, ext4_grpblk_t block, struct buffer_head *bh)
+{
+ struct journal_head *jh = bh2jh(bh);
+ int ret;
+
+ if (ext4_set_bit_atomic(lock, block, bh->b_data))
+ return 0;
+ jbd_lock_bh_state(bh);
+ if (jh->b_committed_data && ext4_test_bit(block,jh->b_committed_data)) {
+ ext4_clear_bit_atomic(lock, block, bh->b_data);
+ ret = 0;
+ } else {
+ ret = 1;
+ }
+ jbd_unlock_bh_state(bh);
+ return ret;
+}
+
+/**
+ * ext4_try_to_allocate()
+ * @sb: superblock
+ * @handle: handle to this transaction
+ * @group: given allocation block group
+ * @bitmap_bh: bufferhead holds the block bitmap
+ * @grp_goal: given target block within the group
+ * @count: target number of blocks to allocate
+ * @my_rsv: reservation window
+ *
+ * Attempt to allocate blocks within a give range. Set the range of allocation
+ * first, then find the first free bit(s) from the bitmap (within the range),
+ * and at last, allocate the blocks by claiming the found free bit as allocated.
+ *
+ * To set the range of this allocation:
+ * if there is a reservation window, only try to allocate block(s) from the
+ * file's own reservation window;
+ * Otherwise, the allocation range starts from the give goal block, ends at
+ * the block group's last block.
+ *
+ * If we failed to allocate the desired block then we may end up crossing to a
+ * new bitmap. In that case we must release write access to the old one via
+ * ext4_journal_release_buffer(), else we'll run out of credits.
+ */
+static ext4_grpblk_t
+ext4_try_to_allocate(struct super_block *sb, handle_t *handle, int group,
+ struct buffer_head *bitmap_bh, ext4_grpblk_t grp_goal,
+ unsigned long *count, struct ext4_reserve_window *my_rsv)
+{
+ ext4_fsblk_t group_first_block;
+ ext4_grpblk_t start, end;
+ unsigned long num = 0;
+
+ /* we do allocation within the reservation window if we have a window */
+ if (my_rsv) {
+ group_first_block = ext4_group_first_block_no(sb, group);
+ if (my_rsv->_rsv_start >= group_first_block)
+ start = my_rsv->_rsv_start - group_first_block;
+ else
+ /* reservation window cross group boundary */
+ start = 0;
+ end = my_rsv->_rsv_end - group_first_block + 1;
+ if (end > EXT4_BLOCKS_PER_GROUP(sb))
+ /* reservation window crosses group boundary */
+ end = EXT4_BLOCKS_PER_GROUP(sb);
+ if ((start <= grp_goal) && (grp_goal < end))
+ start = grp_goal;
+ else
+ grp_goal = -1;
+ } else {
+ if (grp_goal > 0)
+ start = grp_goal;
+ else
+ start = 0;
+ end = EXT4_BLOCKS_PER_GROUP(sb);
+ }
+
+ BUG_ON(start > EXT4_BLOCKS_PER_GROUP(sb));
+
+repeat:
+ if (grp_goal < 0 || !ext4_test_allocatable(grp_goal, bitmap_bh)) {
+ grp_goal = find_next_usable_block(start, bitmap_bh, end);
+ if (grp_goal < 0)
+ goto fail_access;
+ if (!my_rsv) {
+ int i;
+
+ for (i = 0; i < 7 && grp_goal > start &&
+ ext4_test_allocatable(grp_goal - 1,
+ bitmap_bh);
+ i++, grp_goal--)
+ ;
+ }
+ }
+ start = grp_goal;
+
+ if (!claim_block(sb_bgl_lock(EXT4_SB(sb), group),
+ grp_goal, bitmap_bh)) {
+ /*
+ * The block was allocated by another thread, or it was
+ * allocated and then freed by another thread
+ */
+ start++;
+ grp_goal++;
+ if (start >= end)
+ goto fail_access;
+ goto repeat;
+ }
+ num++;
+ grp_goal++;
+ while (num < *count && grp_goal < end
+ && ext4_test_allocatable(grp_goal, bitmap_bh)
+ && claim_block(sb_bgl_lock(EXT4_SB(sb), group),
+ grp_goal, bitmap_bh)) {
+ num++;
+ grp_goal++;
+ }
+ *count = num;
+ return grp_goal - num;
+fail_access:
+ *count = num;
+ return -1;
+}
+
+/**
+ * find_next_reservable_window():
+ * find a reservable space within the given range.
+ * It does not allocate the reservation window for now:
+ * alloc_new_reservation() will do the work later.
+ *
+ * @search_head: the head of the searching list;
+ * This is not necessarily the list head of the whole filesystem
+ *
+ * We have both head and start_block to assist the search
+ * for the reservable space. The list starts from head,
+ * but we will shift to the place where start_block is,
+ * then start from there, when looking for a reservable space.
+ *
+ * @size: the target new reservation window size
+ *
+ * @group_first_block: the first block we consider to start
+ * the real search from
+ *
+ * @last_block:
+ * the maximum block number that our goal reservable space
+ * could start from. This is normally the last block in this
+ * group. The search will end when we found the start of next
+ * possible reservable space is out of this boundary.
+ * This could handle the cross boundary reservation window
+ * request.
+ *
+ * basically we search from the given range, rather than the whole
+ * reservation double linked list, (start_block, last_block)
+ * to find a free region that is of my size and has not
+ * been reserved.
+ *
+ */
+static int find_next_reservable_window(
+ struct ext4_reserve_window_node *search_head,
+ struct ext4_reserve_window_node *my_rsv,
+ struct super_block * sb,
+ ext4_fsblk_t start_block,
+ ext4_fsblk_t last_block)
+{
+ struct rb_node *next;
+ struct ext4_reserve_window_node *rsv, *prev;
+ ext4_fsblk_t cur;
+ int size = my_rsv->rsv_goal_size;
+
+ /* TODO: make the start of the reservation window byte-aligned */
+ /* cur = *start_block & ~7;*/
+ cur = start_block;
+ rsv = search_head;
+ if (!rsv)
+ return -1;
+
+ while (1) {
+ if (cur <= rsv->rsv_end)
+ cur = rsv->rsv_end + 1;
+
+ /* TODO?
+ * in the case we could not find a reservable space
+ * that is what is expected, during the re-search, we could
+ * remember what's the largest reservable space we could have
+ * and return that one.
+ *
+ * For now it will fail if we could not find the reservable
+ * space with expected-size (or more)...
+ */
+ if (cur > last_block)
+ return -1; /* fail */
+
+ prev = rsv;
+ next = rb_next(&rsv->rsv_node);
+ rsv = list_entry(next,struct ext4_reserve_window_node,rsv_node);
+
+ /*
+ * Reached the last reservation, we can just append to the
+ * previous one.
+ */
+ if (!next)
+ break;
+
+ if (cur + size <= rsv->rsv_start) {
+ /*
+ * Found a reserveable space big enough. We could
+ * have a reservation across the group boundary here
+ */
+ break;
+ }
+ }
+ /*
+ * we come here either :
+ * when we reach the end of the whole list,
+ * and there is empty reservable space after last entry in the list.
+ * append it to the end of the list.
+ *
+ * or we found one reservable space in the middle of the list,
+ * return the reservation window that we could append to.
+ * succeed.
+ */
+
+ if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window)))
+ rsv_window_remove(sb, my_rsv);
+
+ /*
+ * Let's book the whole avaliable window for now. We will check the
+ * disk bitmap later and then, if there are free blocks then we adjust
+ * the window size if it's larger than requested.
+ * Otherwise, we will remove this node from the tree next time
+ * call find_next_reservable_window.
+ */
+ my_rsv->rsv_start = cur;
+ my_rsv->rsv_end = cur + size - 1;
+ my_rsv->rsv_alloc_hit = 0;
+
+ if (prev != my_rsv)
+ ext4_rsv_window_add(sb, my_rsv);
+
+ return 0;
+}
+
+/**
+ * alloc_new_reservation()--allocate a new reservation window
+ *
+ * To make a new reservation, we search part of the filesystem
+ * reservation list (the list that inside the group). We try to
+ * allocate a new reservation window near the allocation goal,
+ * or the beginning of the group, if there is no goal.
+ *
+ * We first find a reservable space after the goal, then from
+ * there, we check the bitmap for the first free block after
+ * it. If there is no free block until the end of group, then the
+ * whole group is full, we failed. Otherwise, check if the free
+ * block is inside the expected reservable space, if so, we
+ * succeed.
+ * If the first free block is outside the reservable space, then
+ * start from the first free block, we search for next available
+ * space, and go on.
+ *
+ * on succeed, a new reservation will be found and inserted into the list
+ * It contains at least one free block, and it does not overlap with other
+ * reservation windows.
+ *
+ * failed: we failed to find a reservation window in this group
+ *
+ * @rsv: the reservation
+ *
+ * @grp_goal: The goal (group-relative). It is where the search for a
+ * free reservable space should start from.
+ * if we have a grp_goal(grp_goal >0 ), then start from there,
+ * no grp_goal(grp_goal = -1), we start from the first block
+ * of the group.
+ *
+ * @sb: the super block
+ * @group: the group we are trying to allocate in
+ * @bitmap_bh: the block group block bitmap
+ *
+ */
+static int alloc_new_reservation(struct ext4_reserve_window_node *my_rsv,
+ ext4_grpblk_t grp_goal, struct super_block *sb,
+ unsigned int group, struct buffer_head *bitmap_bh)
+{
+ struct ext4_reserve_window_node *search_head;
+ ext4_fsblk_t group_first_block, group_end_block, start_block;
+ ext4_grpblk_t first_free_block;
+ struct rb_root *fs_rsv_root = &EXT4_SB(sb)->s_rsv_window_root;
+ unsigned long size;
+ int ret;
+ spinlock_t *rsv_lock = &EXT4_SB(sb)->s_rsv_window_lock;
+
+ group_first_block = ext4_group_first_block_no(sb, group);
+ group_end_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
+
+ if (grp_goal < 0)
+ start_block = group_first_block;
+ else
+ start_block = grp_goal + group_first_block;
+
+ size = my_rsv->rsv_goal_size;
+
+ if (!rsv_is_empty(&my_rsv->rsv_window)) {
+ /*
+ * if the old reservation is cross group boundary
+ * and if the goal is inside the old reservation window,
+ * we will come here when we just failed to allocate from
+ * the first part of the window. We still have another part
+ * that belongs to the next group. In this case, there is no
+ * point to discard our window and try to allocate a new one
+ * in this group(which will fail). we should
+ * keep the reservation window, just simply move on.
+ *
+ * Maybe we could shift the start block of the reservation
+ * window to the first block of next group.
+ */
+
+ if ((my_rsv->rsv_start <= group_end_block) &&
+ (my_rsv->rsv_end > group_end_block) &&
+ (start_block >= my_rsv->rsv_start))
+ return -1;
+
+ if ((my_rsv->rsv_alloc_hit >
+ (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) {
+ /*
+ * if the previously allocation hit ratio is
+ * greater than 1/2, then we double the size of
+ * the reservation window the next time,
+ * otherwise we keep the same size window
+ */
+ size = size * 2;
+ if (size > EXT4_MAX_RESERVE_BLOCKS)
+ size = EXT4_MAX_RESERVE_BLOCKS;
+ my_rsv->rsv_goal_size= size;
+ }
+ }
+
+ spin_lock(rsv_lock);
+ /*
+ * shift the search start to the window near the goal block
+ */
+ search_head = search_reserve_window(fs_rsv_root, start_block);
+
+ /*
+ * find_next_reservable_window() simply finds a reservable window
+ * inside the given range(start_block, group_end_block).
+ *
+ * To make sure the reservation window has a free bit inside it, we
+ * need to check the bitmap after we found a reservable window.
+ */
+retry:
+ ret = find_next_reservable_window(search_head, my_rsv, sb,
+ start_block, group_end_block);
+
+ if (ret == -1) {
+ if (!rsv_is_empty(&my_rsv->rsv_window))
+ rsv_window_remove(sb, my_rsv);
+ spin_unlock(rsv_lock);
+ return -1;
+ }
+
+ /*
+ * On success, find_next_reservable_window() returns the
+ * reservation window where there is a reservable space after it.
+ * Before we reserve this reservable space, we need
+ * to make sure there is at least a free block inside this region.
+ *
+ * searching the first free bit on the block bitmap and copy of
+ * last committed bitmap alternatively, until we found a allocatable
+ * block. Search start from the start block of the reservable space
+ * we just found.
+ */
+ spin_unlock(rsv_lock);
+ first_free_block = bitmap_search_next_usable_block(
+ my_rsv->rsv_start - group_first_block,
+ bitmap_bh, group_end_block - group_first_block + 1);
+
+ if (first_free_block < 0) {
+ /*
+ * no free block left on the bitmap, no point
+ * to reserve the space. return failed.
+ */
+ spin_lock(rsv_lock);
+ if (!rsv_is_empty(&my_rsv->rsv_window))
+ rsv_window_remove(sb, my_rsv);
+ spin_unlock(rsv_lock);
+ return -1; /* failed */
+ }
+
+ start_block = first_free_block + group_first_block;
+ /*
+ * check if the first free block is within the
+ * free space we just reserved
+ */
+ if (start_block >= my_rsv->rsv_start && start_block < my_rsv->rsv_end)
+ return 0; /* success */
+ /*
+ * if the first free bit we found is out of the reservable space
+ * continue search for next reservable space,
+ * start from where the free block is,
+ * we also shift the list head to where we stopped last time
+ */
+ search_head = my_rsv;
+ spin_lock(rsv_lock);
+ goto retry;
+}
+
+/**
+ * try_to_extend_reservation()
+ * @my_rsv: given reservation window
+ * @sb: super block
+ * @size: the delta to extend
+ *
+ * Attempt to expand the reservation window large enough to have
+ * required number of free blocks
+ *
+ * Since ext4_try_to_allocate() will always allocate blocks within
+ * the reservation window range, if the window size is too small,
+ * multiple blocks allocation has to stop at the end of the reservation
+ * window. To make this more efficient, given the total number of
+ * blocks needed and the current size of the window, we try to
+ * expand the reservation window size if necessary on a best-effort
+ * basis before ext4_new_blocks() tries to allocate blocks,
+ */
+static void try_to_extend_reservation(struct ext4_reserve_window_node *my_rsv,
+ struct super_block *sb, int size)
+{
+ struct ext4_reserve_window_node *next_rsv;
+ struct rb_node *next;
+ spinlock_t *rsv_lock = &EXT4_SB(sb)->s_rsv_window_lock;
+
+ if (!spin_trylock(rsv_lock))
+ return;
+
+ next = rb_next(&my_rsv->rsv_node);
+
+ if (!next)
+ my_rsv->rsv_end += size;
+ else {
+ next_rsv = list_entry(next, struct ext4_reserve_window_node, rsv_node);
+
+ if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size)
+ my_rsv->rsv_end += size;
+ else
+ my_rsv->rsv_end = next_rsv->rsv_start - 1;
+ }
+ spin_unlock(rsv_lock);
+}
+
+/**
+ * ext4_try_to_allocate_with_rsv()
+ * @sb: superblock
+ * @handle: handle to this transaction
+ * @group: given allocation block group
+ * @bitmap_bh: bufferhead holds the block bitmap
+ * @grp_goal: given target block within the group
+ * @count: target number of blocks to allocate
+ * @my_rsv: reservation window
+ * @errp: pointer to store the error code
+ *
+ * This is the main function used to allocate a new block and its reservation
+ * window.
+ *
+ * Each time when a new block allocation is need, first try to allocate from
+ * its own reservation. If it does not have a reservation window, instead of
+ * looking for a free bit on bitmap first, then look up the reservation list to
+ * see if it is inside somebody else's reservation window, we try to allocate a
+ * reservation window for it starting from the goal first. Then do the block
+ * allocation within the reservation window.
+ *
+ * This will avoid keeping on searching the reservation list again and
+ * again when somebody is looking for a free block (without
+ * reservation), and there are lots of free blocks, but they are all
+ * being reserved.
+ *
+ * We use a red-black tree for the per-filesystem reservation list.
+ *
+ */
+static ext4_grpblk_t
+ext4_try_to_allocate_with_rsv(struct super_block *sb, handle_t *handle,
+ unsigned int group, struct buffer_head *bitmap_bh,
+ ext4_grpblk_t grp_goal,
+ struct ext4_reserve_window_node * my_rsv,
+ unsigned long *count, int *errp)
+{
+ ext4_fsblk_t group_first_block, group_last_block;
+ ext4_grpblk_t ret = 0;
+ int fatal;
+ unsigned long num = *count;
+
+ *errp = 0;
+
+ /*
+ * Make sure we use undo access for the bitmap, because it is critical
+ * that we do the frozen_data COW on bitmap buffers in all cases even
+ * if the buffer is in BJ_Forget state in the committing transaction.
+ */
+ BUFFER_TRACE(bitmap_bh, "get undo access for new block");
+ fatal = ext4_journal_get_undo_access(handle, bitmap_bh);
+ if (fatal) {
+ *errp = fatal;
+ return -1;
+ }
+
+ /*
+ * we don't deal with reservation when
+ * filesystem is mounted without reservation
+ * or the file is not a regular file
+ * or last attempt to allocate a block with reservation turned on failed
+ */
+ if (my_rsv == NULL ) {
+ ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh,
+ grp_goal, count, NULL);
+ goto out;
+ }
+ /*
+ * grp_goal is a group relative block number (if there is a goal)
+ * 0 < grp_goal < EXT4_BLOCKS_PER_GROUP(sb)
+ * first block is a filesystem wide block number
+ * first block is the block number of the first block in this group
+ */
+ group_first_block = ext4_group_first_block_no(sb, group);
+ group_last_block = group_first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1);
+
+ /*
+ * Basically we will allocate a new block from inode's reservation
+ * window.
+ *
+ * We need to allocate a new reservation window, if:
+ * a) inode does not have a reservation window; or
+ * b) last attempt to allocate a block from existing reservation
+ * failed; or
+ * c) we come here with a goal and with a reservation window
+ *
+ * We do not need to allocate a new reservation window if we come here
+ * at the beginning with a goal and the goal is inside the window, or
+ * we don't have a goal but already have a reservation window.
+ * then we could go to allocate from the reservation window directly.
+ */
+ while (1) {
+ if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) ||
+ !goal_in_my_reservation(&my_rsv->rsv_window,
+ grp_goal, group, sb)) {
+ if (my_rsv->rsv_goal_size < *count)
+ my_rsv->rsv_goal_size = *count;
+ ret = alloc_new_reservation(my_rsv, grp_goal, sb,
+ group, bitmap_bh);
+ if (ret < 0)
+ break; /* failed */
+
+ if (!goal_in_my_reservation(&my_rsv->rsv_window,
+ grp_goal, group, sb))
+ grp_goal = -1;
+ } else if (grp_goal > 0 &&
+ (my_rsv->rsv_end-grp_goal+1) < *count)
+ try_to_extend_reservation(my_rsv, sb,
+ *count-my_rsv->rsv_end + grp_goal - 1);
+
+ if ((my_rsv->rsv_start > group_last_block) ||
+ (my_rsv->rsv_end < group_first_block)) {
+ rsv_window_dump(&EXT4_SB(sb)->s_rsv_window_root, 1);
+ BUG();
+ }
+ ret = ext4_try_to_allocate(sb, handle, group, bitmap_bh,
+ grp_goal, &num, &my_rsv->rsv_window);
+ if (ret >= 0) {
+ my_rsv->rsv_alloc_hit += num;
+ *count = num;
+ break; /* succeed */
+ }
+ num = *count;
+ }
+out:
+ if (ret >= 0) {
+ BUFFER_TRACE(bitmap_bh, "journal_dirty_metadata for "
+ "bitmap block");
+ fatal = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ if (fatal) {
+ *errp = fatal;
+ return -1;
+ }
+ return ret;
+ }
+
+ BUFFER_TRACE(bitmap_bh, "journal_release_buffer");
+ ext4_journal_release_buffer(handle, bitmap_bh);
+ return ret;
+}
+
+/**
+ * ext4_has_free_blocks()
+ * @sbi: in-core super block structure.
+ *
+ * Check if filesystem has at least 1 free block available for allocation.
+ */
+static int ext4_has_free_blocks(struct ext4_sb_info *sbi)
+{
+ ext4_fsblk_t free_blocks, root_blocks;
+
+ free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+ root_blocks = ext4_r_blocks_count(sbi->s_es);
+ if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) &&
+ sbi->s_resuid != current->fsuid &&
+ (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) {
+ return 0;
+ }
+ return 1;
+}
+
+/**
+ * ext4_should_retry_alloc()
+ * @sb: super block
+ * @retries number of attemps has been made
+ *
+ * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
+ * it is profitable to retry the operation, this function will wait
+ * for the current or commiting transaction to complete, and then
+ * return TRUE.
+ *
+ * if the total number of retries exceed three times, return FALSE.
+ */
+int ext4_should_retry_alloc(struct super_block *sb, int *retries)
+{
+ if (!ext4_has_free_blocks(EXT4_SB(sb)) || (*retries)++ > 3)
+ return 0;
+
+ jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
+
+ return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+}
+
+/**
+ * ext4_new_blocks() -- core block(s) allocation function
+ * @handle: handle to this transaction
+ * @inode: file inode
+ * @goal: given target block(filesystem wide)
+ * @count: target number of blocks to allocate
+ * @errp: error code
+ *
+ * ext4_new_blocks uses a goal block to assist allocation. It tries to
+ * allocate block(s) from the block group contains the goal block first. If that
+ * fails, it will try to allocate block(s) from other block groups without
+ * any specific goal block.
+ *
+ */
+ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
+ ext4_fsblk_t goal, unsigned long *count, int *errp)
+{
+ struct buffer_head *bitmap_bh = NULL;
+ struct buffer_head *gdp_bh;
+ unsigned long group_no;
+ int goal_group;
+ ext4_grpblk_t grp_target_blk; /* blockgroup relative goal block */
+ ext4_grpblk_t grp_alloc_blk; /* blockgroup-relative allocated block*/
+ ext4_fsblk_t ret_block; /* filesyetem-wide allocated block */
+ int bgi; /* blockgroup iteration index */
+ int fatal = 0, err;
+ int performed_allocation = 0;
+ ext4_grpblk_t free_blocks; /* number of free blocks in a group */
+ struct super_block *sb;
+ struct ext4_group_desc *gdp;
+ struct ext4_super_block *es;
+ struct ext4_sb_info *sbi;
+ struct ext4_reserve_window_node *my_rsv = NULL;
+ struct ext4_block_alloc_info *block_i;
+ unsigned short windowsz = 0;
+#ifdef EXT4FS_DEBUG
+ static int goal_hits, goal_attempts;
+#endif
+ unsigned long ngroups;
+ unsigned long num = *count;
+
+ *errp = -ENOSPC;
+ sb = inode->i_sb;
+ if (!sb) {
+ printk("ext4_new_block: nonexistent device");
+ return 0;
+ }
+
+ /*
+ * Check quota for allocation of this block.
+ */
+ if (DQUOT_ALLOC_BLOCK(inode, num)) {
+ *errp = -EDQUOT;
+ return 0;
+ }
+
+ sbi = EXT4_SB(sb);
+ es = EXT4_SB(sb)->s_es;
+ ext4_debug("goal=%lu.\n", goal);
+ /*
+ * Allocate a block from reservation only when
+ * filesystem is mounted with reservation(default,-o reservation), and
+ * it's a regular file, and
+ * the desired window size is greater than 0 (One could use ioctl
+ * command EXT4_IOC_SETRSVSZ to set the window size to 0 to turn off
+ * reservation on that particular file)
+ */
+ block_i = EXT4_I(inode)->i_block_alloc_info;
+ if (block_i && ((windowsz = block_i->rsv_window_node.rsv_goal_size) > 0))
+ my_rsv = &block_i->rsv_window_node;
+
+ if (!ext4_has_free_blocks(sbi)) {
+ *errp = -ENOSPC;
+ goto out;
+ }
+
+ /*
+ * First, test whether the goal block is free.
+ */
+ if (goal < le32_to_cpu(es->s_first_data_block) ||
+ goal >= ext4_blocks_count(es))
+ goal = le32_to_cpu(es->s_first_data_block);
+ ext4_get_group_no_and_offset(sb, goal, &group_no, &grp_target_blk);
+ goal_group = group_no;
+retry_alloc:
+ gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
+ if (!gdp)
+ goto io_error;
+
+ free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+ /*
+ * if there is not enough free blocks to make a new resevation
+ * turn off reservation for this allocation
+ */
+ if (my_rsv && (free_blocks < windowsz)
+ && (rsv_is_empty(&my_rsv->rsv_window)))
+ my_rsv = NULL;
+
+ if (free_blocks > 0) {
+ bitmap_bh = read_block_bitmap(sb, group_no);
+ if (!bitmap_bh)
+ goto io_error;
+ grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle,
+ group_no, bitmap_bh, grp_target_blk,
+ my_rsv, &num, &fatal);
+ if (fatal)
+ goto out;
+ if (grp_alloc_blk >= 0)
+ goto allocated;
+ }
+
+ ngroups = EXT4_SB(sb)->s_groups_count;
+ smp_rmb();
+
+ /*
+ * Now search the rest of the groups. We assume that
+ * i and gdp correctly point to the last group visited.
+ */
+ for (bgi = 0; bgi < ngroups; bgi++) {
+ group_no++;
+ if (group_no >= ngroups)
+ group_no = 0;
+ gdp = ext4_get_group_desc(sb, group_no, &gdp_bh);
+ if (!gdp) {
+ *errp = -EIO;
+ goto out;
+ }
+ free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+ /*
+ * skip this group if the number of
+ * free blocks is less than half of the reservation
+ * window size.
+ */
+ if (free_blocks <= (windowsz/2))
+ continue;
+
+ brelse(bitmap_bh);
+ bitmap_bh = read_block_bitmap(sb, group_no);
+ if (!bitmap_bh)
+ goto io_error;
+ /*
+ * try to allocate block(s) from this group, without a goal(-1).
+ */
+ grp_alloc_blk = ext4_try_to_allocate_with_rsv(sb, handle,
+ group_no, bitmap_bh, -1, my_rsv,
+ &num, &fatal);
+ if (fatal)
+ goto out;
+ if (grp_alloc_blk >= 0)
+ goto allocated;
+ }
+ /*
+ * We may end up a bogus ealier ENOSPC error due to
+ * filesystem is "full" of reservations, but
+ * there maybe indeed free blocks avaliable on disk
+ * In this case, we just forget about the reservations
+ * just do block allocation as without reservations.
+ */
+ if (my_rsv) {
+ my_rsv = NULL;
+ group_no = goal_group;
+ goto retry_alloc;
+ }
+ /* No space left on the device */
+ *errp = -ENOSPC;
+ goto out;
+
+allocated:
+
+ ext4_debug("using block group %d(%d)\n",
+ group_no, gdp->bg_free_blocks_count);
+
+ BUFFER_TRACE(gdp_bh, "get_write_access");
+ fatal = ext4_journal_get_write_access(handle, gdp_bh);
+ if (fatal)
+ goto out;
+
+ ret_block = grp_alloc_blk + ext4_group_first_block_no(sb, group_no);
+
+ if (in_range(ext4_block_bitmap(sb, gdp), ret_block, num) ||
+ in_range(ext4_block_bitmap(sb, gdp), ret_block, num) ||
+ in_range(ret_block, ext4_inode_table(sb, gdp),
+ EXT4_SB(sb)->s_itb_per_group) ||
+ in_range(ret_block + num - 1, ext4_inode_table(sb, gdp),
+ EXT4_SB(sb)->s_itb_per_group))
+ ext4_error(sb, "ext4_new_block",
+ "Allocating block in system zone - "
+ "blocks from %llu, length %lu",
+ ret_block, num);
+
+ performed_allocation = 1;
+
+#ifdef CONFIG_JBD_DEBUG
+ {
+ struct buffer_head *debug_bh;
+
+ /* Record bitmap buffer state in the newly allocated block */
+ debug_bh = sb_find_get_block(sb, ret_block);
+ if (debug_bh) {
+ BUFFER_TRACE(debug_bh, "state when allocated");
+ BUFFER_TRACE2(debug_bh, bitmap_bh, "bitmap state");
+ brelse(debug_bh);
+ }
+ }
+ jbd_lock_bh_state(bitmap_bh);
+ spin_lock(sb_bgl_lock(sbi, group_no));
+ if (buffer_jbd(bitmap_bh) && bh2jh(bitmap_bh)->b_committed_data) {
+ int i;
+
+ for (i = 0; i < num; i++) {
+ if (ext4_test_bit(grp_alloc_blk+i,
+ bh2jh(bitmap_bh)->b_committed_data)) {
+ printk("%s: block was unexpectedly set in "
+ "b_committed_data\n", __FUNCTION__);
+ }
+ }
+ }
+ ext4_debug("found bit %d\n", grp_alloc_blk);
+ spin_unlock(sb_bgl_lock(sbi, group_no));
+ jbd_unlock_bh_state(bitmap_bh);
+#endif
+
+ if (ret_block + num - 1 >= ext4_blocks_count(es)) {
+ ext4_error(sb, "ext4_new_block",
+ "block(%llu) >= blocks count(%llu) - "
+ "block_group = %lu, es == %p ", ret_block,
+ ext4_blocks_count(es), group_no, es);
+ goto out;
+ }
+
+ /*
+ * It is up to the caller to add the new buffer to a journal
+ * list of some description. We don't know in advance whether
+ * the caller wants to use it as metadata or data.
+ */
+ ext4_debug("allocating block %lu. Goal hits %d of %d.\n",
+ ret_block, goal_hits, goal_attempts);
+
+ spin_lock(sb_bgl_lock(sbi, group_no));
+ gdp->bg_free_blocks_count =
+ cpu_to_le16(le16_to_cpu(gdp->bg_free_blocks_count)-num);
+ spin_unlock(sb_bgl_lock(sbi, group_no));
+ percpu_counter_mod(&sbi->s_freeblocks_counter, -num);
+
+ BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor");
+ err = ext4_journal_dirty_metadata(handle, gdp_bh);
+ if (!fatal)
+ fatal = err;
+
+ sb->s_dirt = 1;
+ if (fatal)
+ goto out;
+
+ *errp = 0;
+ brelse(bitmap_bh);
+ DQUOT_FREE_BLOCK(inode, *count-num);
+ *count = num;
+ return ret_block;
+
+io_error:
+ *errp = -EIO;
+out:
+ if (fatal) {
+ *errp = fatal;
+ ext4_std_error(sb, fatal);
+ }
+ /*
+ * Undo the block allocation
+ */
+ if (!performed_allocation)
+ DQUOT_FREE_BLOCK(inode, *count);
+ brelse(bitmap_bh);
+ return 0;
+}
+
+ext4_fsblk_t ext4_new_block(handle_t *handle, struct inode *inode,
+ ext4_fsblk_t goal, int *errp)
+{
+ unsigned long count = 1;
+
+ return ext4_new_blocks(handle, inode, goal, &count, errp);
+}
+
+/**
+ * ext4_count_free_blocks() -- count filesystem free blocks
+ * @sb: superblock
+ *
+ * Adds up the number of free blocks from each block group.
+ */
+ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
+{
+ ext4_fsblk_t desc_count;
+ struct ext4_group_desc *gdp;
+ int i;
+ unsigned long ngroups = EXT4_SB(sb)->s_groups_count;
+#ifdef EXT4FS_DEBUG
+ struct ext4_super_block *es;
+ ext4_fsblk_t bitmap_count;
+ unsigned long x;
+ struct buffer_head *bitmap_bh = NULL;
+
+ es = EXT4_SB(sb)->s_es;
+ desc_count = 0;
+ bitmap_count = 0;
+ gdp = NULL;
+
+ smp_rmb();
+ for (i = 0; i < ngroups; i++) {
+ gdp = ext4_get_group_desc(sb, i, NULL);
+ if (!gdp)
+ continue;
+ desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
+ brelse(bitmap_bh);
+ bitmap_bh = read_block_bitmap(sb, i);
+ if (bitmap_bh == NULL)
+ continue;
+
+ x = ext4_count_free(bitmap_bh, sb->s_blocksize);
+ printk("group %d: stored = %d, counted = %lu\n",
+ i, le16_to_cpu(gdp->bg_free_blocks_count), x);
+ bitmap_count += x;
+ }
+ brelse(bitmap_bh);
+ printk("ext4_count_free_blocks: stored = %llu"
+ ", computed = %llu, %llu\n",
+ EXT4_FREE_BLOCKS_COUNT(es),
+ desc_count, bitmap_count);
+ return bitmap_count;
+#else
+ desc_count = 0;
+ smp_rmb();
+ for (i = 0; i < ngroups; i++) {
+ gdp = ext4_get_group_desc(sb, i, NULL);
+ if (!gdp)
+ continue;
+ desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
+ }
+
+ return desc_count;
+#endif
+}
+
+static inline int
+block_in_use(ext4_fsblk_t block, struct super_block *sb, unsigned char *map)
+{
+ ext4_grpblk_t offset;
+
+ ext4_get_group_no_and_offset(sb, block, NULL, &offset);
+ return ext4_test_bit (offset, map);
+}
+
+static inline int test_root(int a, int b)
+{
+ int num = b;
+
+ while (a > num)
+ num *= b;
+ return num == a;
+}
+
+static int ext4_group_sparse(int group)
+{
+ if (group <= 1)
+ return 1;
+ if (!(group & 1))
+ return 0;
+ return (test_root(group, 7) || test_root(group, 5) ||
+ test_root(group, 3));
+}
+
+/**
+ * ext4_bg_has_super - number of blocks used by the superblock in group
+ * @sb: superblock for filesystem
+ * @group: group number to check
+ *
+ * Return the number of blocks used by the superblock (primary or backup)
+ * in this group. Currently this will be only 0 or 1.
+ */
+int ext4_bg_has_super(struct super_block *sb, int group)
+{
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
+ !ext4_group_sparse(group))
+ return 0;
+ return 1;
+}
+
+static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb, int group)
+{
+ unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
+ unsigned long first = metagroup * EXT4_DESC_PER_BLOCK(sb);
+ unsigned long last = first + EXT4_DESC_PER_BLOCK(sb) - 1;
+
+ if (group == first || group == first + 1 || group == last)
+ return 1;
+ return 0;
+}
+
+static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb, int group)
+{
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
+ !ext4_group_sparse(group))
+ return 0;
+ return EXT4_SB(sb)->s_gdb_count;
+}
+
+/**
+ * ext4_bg_num_gdb - number of blocks used by the group table in group
+ * @sb: superblock for filesystem
+ * @group: group number to check
+ *
+ * Return the number of blocks used by the group descriptor table
+ * (primary or backup) in this group. In the future there may be a
+ * different number of descriptor blocks in each group.
+ */
+unsigned long ext4_bg_num_gdb(struct super_block *sb, int group)
+{
+ unsigned long first_meta_bg =
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
+ unsigned long metagroup = group / EXT4_DESC_PER_BLOCK(sb);
+
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG) ||
+ metagroup < first_meta_bg)
+ return ext4_bg_num_gdb_nometa(sb,group);
+
+ return ext4_bg_num_gdb_meta(sb,group);
+
+}
--- /dev/null
+/*
+ * linux/fs/ext4/bitmap.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ */
+
+#include <linux/buffer_head.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+
+#ifdef EXT4FS_DEBUG
+
+static int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
+
+unsigned long ext4_count_free (struct buffer_head * map, unsigned int numchars)
+{
+ unsigned int i;
+ unsigned long sum = 0;
+
+ if (!map)
+ return (0);
+ for (i = 0; i < numchars; i++)
+ sum += nibblemap[map->b_data[i] & 0xf] +
+ nibblemap[(map->b_data[i] >> 4) & 0xf];
+ return (sum);
+}
+
+#endif /* EXT4FS_DEBUG */
+
--- /dev/null
+/*
+ * linux/fs/ext4/dir.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/fs/minix/dir.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * ext4 directory handling functions
+ *
+ * Big-endian to little-endian byte-swapping/bitmaps by
+ * David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ * Hash Tree Directory indexing (c) 2001 Daniel Phillips
+ *
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/buffer_head.h>
+#include <linux/smp_lock.h>
+#include <linux/slab.h>
+#include <linux/rbtree.h>
+
+static unsigned char ext4_filetype_table[] = {
+ DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
+};
+
+static int ext4_readdir(struct file *, void *, filldir_t);
+static int ext4_dx_readdir(struct file * filp,
+ void * dirent, filldir_t filldir);
+static int ext4_release_dir (struct inode * inode,
+ struct file * filp);
+
+const struct file_operations ext4_dir_operations = {
+ .llseek = generic_file_llseek,
+ .read = generic_read_dir,
+ .readdir = ext4_readdir, /* we take BKL. needed?*/
+ .ioctl = ext4_ioctl, /* BKL held */
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ext4_compat_ioctl,
+#endif
+ .fsync = ext4_sync_file, /* BKL held */
+#ifdef CONFIG_EXT4_INDEX
+ .release = ext4_release_dir,
+#endif
+};
+
+
+static unsigned char get_dtype(struct super_block *sb, int filetype)
+{
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) ||
+ (filetype >= EXT4_FT_MAX))
+ return DT_UNKNOWN;
+
+ return (ext4_filetype_table[filetype]);
+}
+
+
+int ext4_check_dir_entry (const char * function, struct inode * dir,
+ struct ext4_dir_entry_2 * de,
+ struct buffer_head * bh,
+ unsigned long offset)
+{
+ const char * error_msg = NULL;
+ const int rlen = le16_to_cpu(de->rec_len);
+
+ if (rlen < EXT4_DIR_REC_LEN(1))
+ error_msg = "rec_len is smaller than minimal";
+ else if (rlen % 4 != 0)
+ error_msg = "rec_len % 4 != 0";
+ else if (rlen < EXT4_DIR_REC_LEN(de->name_len))
+ error_msg = "rec_len is too small for name_len";
+ else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
+ error_msg = "directory entry across blocks";
+ else if (le32_to_cpu(de->inode) >
+ le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))
+ error_msg = "inode out of bounds";
+
+ if (error_msg != NULL)
+ ext4_error (dir->i_sb, function,
+ "bad entry in directory #%lu: %s - "
+ "offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
+ dir->i_ino, error_msg, offset,
+ (unsigned long) le32_to_cpu(de->inode),
+ rlen, de->name_len);
+ return error_msg == NULL ? 1 : 0;
+}
+
+static int ext4_readdir(struct file * filp,
+ void * dirent, filldir_t filldir)
+{
+ int error = 0;
+ unsigned long offset;
+ int i, stored;
+ struct ext4_dir_entry_2 *de;
+ struct super_block *sb;
+ int err;
+ struct inode *inode = filp->f_dentry->d_inode;
+ int ret = 0;
+
+ sb = inode->i_sb;
+
+#ifdef CONFIG_EXT4_INDEX
+ if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_COMPAT_DIR_INDEX) &&
+ ((EXT4_I(inode)->i_flags & EXT4_INDEX_FL) ||
+ ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+ err = ext4_dx_readdir(filp, dirent, filldir);
+ if (err != ERR_BAD_DX_DIR) {
+ ret = err;
+ goto out;
+ }
+ /*
+ * We don't set the inode dirty flag since it's not
+ * critical that it get flushed back to the disk.
+ */
+ EXT4_I(filp->f_dentry->d_inode)->i_flags &= ~EXT4_INDEX_FL;
+ }
+#endif
+ stored = 0;
+ offset = filp->f_pos & (sb->s_blocksize - 1);
+
+ while (!error && !stored && filp->f_pos < inode->i_size) {
+ unsigned long blk = filp->f_pos >> EXT4_BLOCK_SIZE_BITS(sb);
+ struct buffer_head map_bh;
+ struct buffer_head *bh = NULL;
+
+ map_bh.b_state = 0;
+ err = ext4_get_blocks_wrap(NULL, inode, blk, 1, &map_bh, 0, 0);
+ if (err > 0) {
+ page_cache_readahead(sb->s_bdev->bd_inode->i_mapping,
+ &filp->f_ra,
+ filp,
+ map_bh.b_blocknr >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits),
+ 1);
+ bh = ext4_bread(NULL, inode, blk, 0, &err);
+ }
+
+ /*
+ * We ignore I/O errors on directories so users have a chance
+ * of recovering data when there's a bad sector
+ */
+ if (!bh) {
+ ext4_error (sb, "ext4_readdir",
+ "directory #%lu contains a hole at offset %lu",
+ inode->i_ino, (unsigned long)filp->f_pos);
+ filp->f_pos += sb->s_blocksize - offset;
+ continue;
+ }
+
+revalidate:
+ /* If the dir block has changed since the last call to
+ * readdir(2), then we might be pointing to an invalid
+ * dirent right now. Scan from the start of the block
+ * to make sure. */
+ if (filp->f_version != inode->i_version) {
+ for (i = 0; i < sb->s_blocksize && i < offset; ) {
+ de = (struct ext4_dir_entry_2 *)
+ (bh->b_data + i);
+ /* It's too expensive to do a full
+ * dirent test each time round this
+ * loop, but we do have to test at
+ * least that it is non-zero. A
+ * failure will be detected in the
+ * dirent test below. */
+ if (le16_to_cpu(de->rec_len) <
+ EXT4_DIR_REC_LEN(1))
+ break;
+ i += le16_to_cpu(de->rec_len);
+ }
+ offset = i;
+ filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
+ | offset;
+ filp->f_version = inode->i_version;
+ }
+
+ while (!error && filp->f_pos < inode->i_size
+ && offset < sb->s_blocksize) {
+ de = (struct ext4_dir_entry_2 *) (bh->b_data + offset);
+ if (!ext4_check_dir_entry ("ext4_readdir", inode, de,
+ bh, offset)) {
+ /*
+ * On error, skip the f_pos to the next block
+ */
+ filp->f_pos = (filp->f_pos |
+ (sb->s_blocksize - 1)) + 1;
+ brelse (bh);
+ ret = stored;
+ goto out;
+ }
+ offset += le16_to_cpu(de->rec_len);
+ if (le32_to_cpu(de->inode)) {
+ /* We might block in the next section
+ * if the data destination is
+ * currently swapped out. So, use a
+ * version stamp to detect whether or
+ * not the directory has been modified
+ * during the copy operation.
+ */
+ unsigned long version = filp->f_version;
+
+ error = filldir(dirent, de->name,
+ de->name_len,
+ filp->f_pos,
+ le32_to_cpu(de->inode),
+ get_dtype(sb, de->file_type));
+ if (error)
+ break;
+ if (version != filp->f_version)
+ goto revalidate;
+ stored ++;
+ }
+ filp->f_pos += le16_to_cpu(de->rec_len);
+ }
+ offset = 0;
+ brelse (bh);
+ }
+out:
+ return ret;
+}
+
+#ifdef CONFIG_EXT4_INDEX
+/*
+ * These functions convert from the major/minor hash to an f_pos
+ * value.
+ *
+ * Currently we only use major hash numer. This is unfortunate, but
+ * on 32-bit machines, the same VFS interface is used for lseek and
+ * llseek, so if we use the 64 bit offset, then the 32-bit versions of
+ * lseek/telldir/seekdir will blow out spectacularly, and from within
+ * the ext2 low-level routine, we don't know if we're being called by
+ * a 64-bit version of the system call or the 32-bit version of the
+ * system call. Worse yet, NFSv2 only allows for a 32-bit readdir
+ * cookie. Sigh.
+ */
+#define hash2pos(major, minor) (major >> 1)
+#define pos2maj_hash(pos) ((pos << 1) & 0xffffffff)
+#define pos2min_hash(pos) (0)
+
+/*
+ * This structure holds the nodes of the red-black tree used to store
+ * the directory entry in hash order.
+ */
+struct fname {
+ __u32 hash;
+ __u32 minor_hash;
+ struct rb_node rb_hash;
+ struct fname *next;
+ __u32 inode;
+ __u8 name_len;
+ __u8 file_type;
+ char name[0];
+};
+
+/*
+ * This functoin implements a non-recursive way of freeing all of the
+ * nodes in the red-black tree.
+ */
+static void free_rb_tree_fname(struct rb_root *root)
+{
+ struct rb_node *n = root->rb_node;
+ struct rb_node *parent;
+ struct fname *fname;
+
+ while (n) {
+ /* Do the node's children first */
+ if ((n)->rb_left) {
+ n = n->rb_left;
+ continue;
+ }
+ if (n->rb_right) {
+ n = n->rb_right;
+ continue;
+ }
+ /*
+ * The node has no children; free it, and then zero
+ * out parent's link to it. Finally go to the
+ * beginning of the loop and try to free the parent
+ * node.
+ */
+ parent = rb_parent(n);
+ fname = rb_entry(n, struct fname, rb_hash);
+ while (fname) {
+ struct fname * old = fname;
+ fname = fname->next;
+ kfree (old);
+ }
+ if (!parent)
+ root->rb_node = NULL;
+ else if (parent->rb_left == n)
+ parent->rb_left = NULL;
+ else if (parent->rb_right == n)
+ parent->rb_right = NULL;
+ n = parent;
+ }
+ root->rb_node = NULL;
+}
+
+
+static struct dir_private_info *create_dir_info(loff_t pos)
+{
+ struct dir_private_info *p;
+
+ p = kmalloc(sizeof(struct dir_private_info), GFP_KERNEL);
+ if (!p)
+ return NULL;
+ p->root.rb_node = NULL;
+ p->curr_node = NULL;
+ p->extra_fname = NULL;
+ p->last_pos = 0;
+ p->curr_hash = pos2maj_hash(pos);
+ p->curr_minor_hash = pos2min_hash(pos);
+ p->next_hash = 0;
+ return p;
+}
+
+void ext4_htree_free_dir_info(struct dir_private_info *p)
+{
+ free_rb_tree_fname(&p->root);
+ kfree(p);
+}
+
+/*
+ * Given a directory entry, enter it into the fname rb tree.
+ */
+int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
+ __u32 minor_hash,
+ struct ext4_dir_entry_2 *dirent)
+{
+ struct rb_node **p, *parent = NULL;
+ struct fname * fname, *new_fn;
+ struct dir_private_info *info;
+ int len;
+
+ info = (struct dir_private_info *) dir_file->private_data;
+ p = &info->root.rb_node;
+
+ /* Create and allocate the fname structure */
+ len = sizeof(struct fname) + dirent->name_len + 1;
+ new_fn = kzalloc(len, GFP_KERNEL);
+ if (!new_fn)
+ return -ENOMEM;
+ new_fn->hash = hash;
+ new_fn->minor_hash = minor_hash;
+ new_fn->inode = le32_to_cpu(dirent->inode);
+ new_fn->name_len = dirent->name_len;
+ new_fn->file_type = dirent->file_type;
+ memcpy(new_fn->name, dirent->name, dirent->name_len);
+ new_fn->name[dirent->name_len] = 0;
+
+ while (*p) {
+ parent = *p;
+ fname = rb_entry(parent, struct fname, rb_hash);
+
+ /*
+ * If the hash and minor hash match up, then we put
+ * them on a linked list. This rarely happens...
+ */
+ if ((new_fn->hash == fname->hash) &&
+ (new_fn->minor_hash == fname->minor_hash)) {
+ new_fn->next = fname->next;
+ fname->next = new_fn;
+ return 0;
+ }
+
+ if (new_fn->hash < fname->hash)
+ p = &(*p)->rb_left;
+ else if (new_fn->hash > fname->hash)
+ p = &(*p)->rb_right;
+ else if (new_fn->minor_hash < fname->minor_hash)
+ p = &(*p)->rb_left;
+ else /* if (new_fn->minor_hash > fname->minor_hash) */
+ p = &(*p)->rb_right;
+ }
+
+ rb_link_node(&new_fn->rb_hash, parent, p);
+ rb_insert_color(&new_fn->rb_hash, &info->root);
+ return 0;
+}
+
+
+
+/*
+ * This is a helper function for ext4_dx_readdir. It calls filldir
+ * for all entres on the fname linked list. (Normally there is only
+ * one entry on the linked list, unless there are 62 bit hash collisions.)
+ */
+static int call_filldir(struct file * filp, void * dirent,
+ filldir_t filldir, struct fname *fname)
+{
+ struct dir_private_info *info = filp->private_data;
+ loff_t curr_pos;
+ struct inode *inode = filp->f_dentry->d_inode;
+ struct super_block * sb;
+ int error;
+
+ sb = inode->i_sb;
+
+ if (!fname) {
+ printk("call_filldir: called with null fname?!?\n");
+ return 0;
+ }
+ curr_pos = hash2pos(fname->hash, fname->minor_hash);
+ while (fname) {
+ error = filldir(dirent, fname->name,
+ fname->name_len, curr_pos,
+ fname->inode,
+ get_dtype(sb, fname->file_type));
+ if (error) {
+ filp->f_pos = curr_pos;
+ info->extra_fname = fname->next;
+ return error;
+ }
+ fname = fname->next;
+ }
+ return 0;
+}
+
+static int ext4_dx_readdir(struct file * filp,
+ void * dirent, filldir_t filldir)
+{
+ struct dir_private_info *info = filp->private_data;
+ struct inode *inode = filp->f_dentry->d_inode;
+ struct fname *fname;
+ int ret;
+
+ if (!info) {
+ info = create_dir_info(filp->f_pos);
+ if (!info)
+ return -ENOMEM;
+ filp->private_data = info;
+ }
+
+ if (filp->f_pos == EXT4_HTREE_EOF)
+ return 0; /* EOF */
+
+ /* Some one has messed with f_pos; reset the world */
+ if (info->last_pos != filp->f_pos) {
+ free_rb_tree_fname(&info->root);
+ info->curr_node = NULL;
+ info->extra_fname = NULL;
+ info->curr_hash = pos2maj_hash(filp->f_pos);
+ info->curr_minor_hash = pos2min_hash(filp->f_pos);
+ }
+
+ /*
+ * If there are any leftover names on the hash collision
+ * chain, return them first.
+ */
+ if (info->extra_fname &&
+ call_filldir(filp, dirent, filldir, info->extra_fname))
+ goto finished;
+
+ if (!info->curr_node)
+ info->curr_node = rb_first(&info->root);
+
+ while (1) {
+ /*
+ * Fill the rbtree if we have no more entries,
+ * or the inode has changed since we last read in the
+ * cached entries.
+ */
+ if ((!info->curr_node) ||
+ (filp->f_version != inode->i_version)) {
+ info->curr_node = NULL;
+ free_rb_tree_fname(&info->root);
+ filp->f_version = inode->i_version;
+ ret = ext4_htree_fill_tree(filp, info->curr_hash,
+ info->curr_minor_hash,
+ &info->next_hash);
+ if (ret < 0)
+ return ret;
+ if (ret == 0) {
+ filp->f_pos = EXT4_HTREE_EOF;
+ break;
+ }
+ info->curr_node = rb_first(&info->root);
+ }
+
+ fname = rb_entry(info->curr_node, struct fname, rb_hash);
+ info->curr_hash = fname->hash;
+ info->curr_minor_hash = fname->minor_hash;
+ if (call_filldir(filp, dirent, filldir, fname))
+ break;
+
+ info->curr_node = rb_next(info->curr_node);
+ if (!info->curr_node) {
+ if (info->next_hash == ~0) {
+ filp->f_pos = EXT4_HTREE_EOF;
+ break;
+ }
+ info->curr_hash = info->next_hash;
+ info->curr_minor_hash = 0;
+ }
+ }
+finished:
+ info->last_pos = filp->f_pos;
+ return 0;
+}
+
+static int ext4_release_dir (struct inode * inode, struct file * filp)
+{
+ if (filp->private_data)
+ ext4_htree_free_dir_info(filp->private_data);
+
+ return 0;
+}
+
+#endif
--- /dev/null
+/*
+ * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
+ * Written by Alex Tomas <alex@clusterfs.com>
+ *
+ * Architecture independence:
+ * Copyright (c) 2005, Bull S.A.
+ * Written by Pierre Peiffer <pierre.peiffer@bull.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-
+ */
+
+/*
+ * Extents support for EXT4
+ *
+ * TODO:
+ * - ext4*_error() should be used in some situations
+ * - analyze all BUG()/BUG_ON(), use -EIO where appropriate
+ * - smart tree reduction
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/jbd.h>
+#include <linux/smp_lock.h>
+#include <linux/highuid.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/ext4_fs_extents.h>
+#include <asm/uaccess.h>
+
+
+/*
+ * ext_pblock:
+ * combine low and high parts of physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext_pblock(struct ext4_extent *ex)
+{
+ ext4_fsblk_t block;
+
+ block = le32_to_cpu(ex->ee_start);
+ block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1;
+ return block;
+}
+
+/*
+ * idx_pblock:
+ * combine low and high parts of a leaf physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix)
+{
+ ext4_fsblk_t block;
+
+ block = le32_to_cpu(ix->ei_leaf);
+ block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1;
+ return block;
+}
+
+/*
+ * ext4_ext_store_pblock:
+ * stores a large physical block number into an extent struct,
+ * breaking it into parts
+ */
+static inline void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb)
+{
+ ex->ee_start = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+ ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
+}
+
+/*
+ * ext4_idx_store_pblock:
+ * stores a large physical block number into an index struct,
+ * breaking it into parts
+ */
+static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb)
+{
+ ix->ei_leaf = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+ ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff);
+}
+
+static int ext4_ext_check_header(const char *function, struct inode *inode,
+ struct ext4_extent_header *eh)
+{
+ const char *error_msg = NULL;
+
+ if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) {
+ error_msg = "invalid magic";
+ goto corrupted;
+ }
+ if (unlikely(eh->eh_max == 0)) {
+ error_msg = "invalid eh_max";
+ goto corrupted;
+ }
+ if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) {
+ error_msg = "invalid eh_entries";
+ goto corrupted;
+ }
+ return 0;
+
+corrupted:
+ ext4_error(inode->i_sb, function,
+ "bad header in inode #%lu: %s - magic %x, "
+ "entries %u, max %u, depth %u",
+ inode->i_ino, error_msg, le16_to_cpu(eh->eh_magic),
+ le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
+ le16_to_cpu(eh->eh_depth));
+
+ return -EIO;
+}
+
+static handle_t *ext4_ext_journal_restart(handle_t *handle, int needed)
+{
+ int err;
+
+ if (handle->h_buffer_credits > needed)
+ return handle;
+ if (!ext4_journal_extend(handle, needed))
+ return handle;
+ err = ext4_journal_restart(handle, needed);
+
+ return handle;
+}
+
+/*
+ * could return:
+ * - EROFS
+ * - ENOMEM
+ */
+static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ if (path->p_bh) {
+ /* path points to block */
+ return ext4_journal_get_write_access(handle, path->p_bh);
+ }
+ /* path points to leaf/index in inode body */
+ /* we use in-core data, no need to protect them */
+ return 0;
+}
+
+/*
+ * could return:
+ * - EROFS
+ * - ENOMEM
+ * - EIO
+ */
+static int ext4_ext_dirty(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ int err;
+ if (path->p_bh) {
+ /* path points to block */
+ err = ext4_journal_dirty_metadata(handle, path->p_bh);
+ } else {
+ /* path points to leaf/index in inode body */
+ err = ext4_mark_inode_dirty(handle, inode);
+ }
+ return err;
+}
+
+static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_fsblk_t block)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ ext4_fsblk_t bg_start;
+ ext4_grpblk_t colour;
+ int depth;
+
+ if (path) {
+ struct ext4_extent *ex;
+ depth = path->p_depth;
+
+ /* try to predict block placement */
+ if ((ex = path[depth].p_ext))
+ return ext_pblock(ex)+(block-le32_to_cpu(ex->ee_block));
+
+ /* it looks like index is empty;
+ * try to find starting block from index itself */
+ if (path[depth].p_bh)
+ return path[depth].p_bh->b_blocknr;
+ }
+
+ /* OK. use inode's group */
+ bg_start = (ei->i_block_group * EXT4_BLOCKS_PER_GROUP(inode->i_sb)) +
+ le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_first_data_block);
+ colour = (current->pid % 16) *
+ (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+ return bg_start + colour + block;
+}
+
+static ext4_fsblk_t
+ext4_ext_new_block(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path,
+ struct ext4_extent *ex, int *err)
+{
+ ext4_fsblk_t goal, newblock;
+
+ goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block));
+ newblock = ext4_new_block(handle, inode, goal, err);
+ return newblock;
+}
+
+static inline int ext4_ext_space_block(struct inode *inode)
+{
+ int size;
+
+ size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+ / sizeof(struct ext4_extent);
+#ifdef AGRESSIVE_TEST
+ if (size > 6)
+ size = 6;
+#endif
+ return size;
+}
+
+static inline int ext4_ext_space_block_idx(struct inode *inode)
+{
+ int size;
+
+ size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
+ / sizeof(struct ext4_extent_idx);
+#ifdef AGRESSIVE_TEST
+ if (size > 5)
+ size = 5;
+#endif
+ return size;
+}
+
+static inline int ext4_ext_space_root(struct inode *inode)
+{
+ int size;
+
+ size = sizeof(EXT4_I(inode)->i_data);
+ size -= sizeof(struct ext4_extent_header);
+ size /= sizeof(struct ext4_extent);
+#ifdef AGRESSIVE_TEST
+ if (size > 3)
+ size = 3;
+#endif
+ return size;
+}
+
+static inline int ext4_ext_space_root_idx(struct inode *inode)
+{
+ int size;
+
+ size = sizeof(EXT4_I(inode)->i_data);
+ size -= sizeof(struct ext4_extent_header);
+ size /= sizeof(struct ext4_extent_idx);
+#ifdef AGRESSIVE_TEST
+ if (size > 4)
+ size = 4;
+#endif
+ return size;
+}
+
+#ifdef EXT_DEBUG
+static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
+{
+ int k, l = path->p_depth;
+
+ ext_debug("path:");
+ for (k = 0; k <= l; k++, path++) {
+ if (path->p_idx) {
+ ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block),
+ idx_pblock(path->p_idx));
+ } else if (path->p_ext) {
+ ext_debug(" %d:%d:%llu ",
+ le32_to_cpu(path->p_ext->ee_block),
+ le16_to_cpu(path->p_ext->ee_len),
+ ext_pblock(path->p_ext));
+ } else
+ ext_debug(" []");
+ }
+ ext_debug("\n");
+}
+
+static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
+{
+ int depth = ext_depth(inode);
+ struct ext4_extent_header *eh;
+ struct ext4_extent *ex;
+ int i;
+
+ if (!path)
+ return;
+
+ eh = path[depth].p_hdr;
+ ex = EXT_FIRST_EXTENT(eh);
+
+ for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
+ ext_debug("%d:%d:%llu ", le32_to_cpu(ex->ee_block),
+ le16_to_cpu(ex->ee_len), ext_pblock(ex));
+ }
+ ext_debug("\n");
+}
+#else
+#define ext4_ext_show_path(inode,path)
+#define ext4_ext_show_leaf(inode,path)
+#endif
+
+static void ext4_ext_drop_refs(struct ext4_ext_path *path)
+{
+ int depth = path->p_depth;
+ int i;
+
+ for (i = 0; i <= depth; i++, path++)
+ if (path->p_bh) {
+ brelse(path->p_bh);
+ path->p_bh = NULL;
+ }
+}
+
+/*
+ * ext4_ext_binsearch_idx:
+ * binary search for the closest index of the given block
+ */
+static void
+ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int block)
+{
+ struct ext4_extent_header *eh = path->p_hdr;
+ struct ext4_extent_idx *r, *l, *m;
+
+ BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC);
+ BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max));
+ BUG_ON(le16_to_cpu(eh->eh_entries) <= 0);
+
+ ext_debug("binsearch for %d(idx): ", block);
+
+ l = EXT_FIRST_INDEX(eh) + 1;
+ r = EXT_FIRST_INDEX(eh) + le16_to_cpu(eh->eh_entries) - 1;
+ while (l <= r) {
+ m = l + (r - l) / 2;
+ if (block < le32_to_cpu(m->ei_block))
+ r = m - 1;
+ else
+ l = m + 1;
+ ext_debug("%p(%u):%p(%u):%p(%u) ", l, l->ei_block,
+ m, m->ei_block, r, r->ei_block);
+ }
+
+ path->p_idx = l - 1;
+ ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block),
+ idx_block(path->p_idx));
+
+#ifdef CHECK_BINSEARCH
+ {
+ struct ext4_extent_idx *chix, *ix;
+ int k;
+
+ chix = ix = EXT_FIRST_INDEX(eh);
+ for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
+ if (k != 0 &&
+ le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) {
+ printk("k=%d, ix=0x%p, first=0x%p\n", k,
+ ix, EXT_FIRST_INDEX(eh));
+ printk("%u <= %u\n",
+ le32_to_cpu(ix->ei_block),
+ le32_to_cpu(ix[-1].ei_block));
+ }
+ BUG_ON(k && le32_to_cpu(ix->ei_block)
+ <= le32_to_cpu(ix[-1].ei_block));
+ if (block < le32_to_cpu(ix->ei_block))
+ break;
+ chix = ix;
+ }
+ BUG_ON(chix != path->p_idx);
+ }
+#endif
+
+}
+
+/*
+ * ext4_ext_binsearch:
+ * binary search for closest extent of the given block
+ */
+static void
+ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block)
+{
+ struct ext4_extent_header *eh = path->p_hdr;
+ struct ext4_extent *r, *l, *m;
+
+ BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC);
+ BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max));
+
+ if (eh->eh_entries == 0) {
+ /*
+ * this leaf is empty:
+ * we get such a leaf in split/add case
+ */
+ return;
+ }
+
+ ext_debug("binsearch for %d: ", block);
+
+ l = EXT_FIRST_EXTENT(eh) + 1;
+ r = EXT_FIRST_EXTENT(eh) + le16_to_cpu(eh->eh_entries) - 1;
+
+ while (l <= r) {
+ m = l + (r - l) / 2;
+ if (block < le32_to_cpu(m->ee_block))
+ r = m - 1;
+ else
+ l = m + 1;
+ ext_debug("%p(%u):%p(%u):%p(%u) ", l, l->ee_block,
+ m, m->ee_block, r, r->ee_block);
+ }
+
+ path->p_ext = l - 1;
+ ext_debug(" -> %d:%llu:%d ",
+ le32_to_cpu(path->p_ext->ee_block),
+ ext_pblock(path->p_ext),
+ le16_to_cpu(path->p_ext->ee_len));
+
+#ifdef CHECK_BINSEARCH
+ {
+ struct ext4_extent *chex, *ex;
+ int k;
+
+ chex = ex = EXT_FIRST_EXTENT(eh);
+ for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) {
+ BUG_ON(k && le32_to_cpu(ex->ee_block)
+ <= le32_to_cpu(ex[-1].ee_block));
+ if (block < le32_to_cpu(ex->ee_block))
+ break;
+ chex = ex;
+ }
+ BUG_ON(chex != path->p_ext);
+ }
+#endif
+
+}
+
+int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
+{
+ struct ext4_extent_header *eh;
+
+ eh = ext_inode_hdr(inode);
+ eh->eh_depth = 0;
+ eh->eh_entries = 0;
+ eh->eh_magic = EXT4_EXT_MAGIC;
+ eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode));
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_ext_invalidate_cache(inode);
+ return 0;
+}
+
+struct ext4_ext_path *
+ext4_ext_find_extent(struct inode *inode, int block, struct ext4_ext_path *path)
+{
+ struct ext4_extent_header *eh;
+ struct buffer_head *bh;
+ short int depth, i, ppos = 0, alloc = 0;
+
+ eh = ext_inode_hdr(inode);
+ BUG_ON(eh == NULL);
+ if (ext4_ext_check_header(__FUNCTION__, inode, eh))
+ return ERR_PTR(-EIO);
+
+ i = depth = ext_depth(inode);
+
+ /* account possible depth increase */
+ if (!path) {
+ path = kmalloc(sizeof(struct ext4_ext_path) * (depth + 2),
+ GFP_NOFS);
+ if (!path)
+ return ERR_PTR(-ENOMEM);
+ alloc = 1;
+ }
+ memset(path, 0, sizeof(struct ext4_ext_path) * (depth + 1));
+ path[0].p_hdr = eh;
+
+ /* walk through the tree */
+ while (i) {
+ ext_debug("depth %d: num %d, max %d\n",
+ ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
+ ext4_ext_binsearch_idx(inode, path + ppos, block);
+ path[ppos].p_block = idx_pblock(path[ppos].p_idx);
+ path[ppos].p_depth = i;
+ path[ppos].p_ext = NULL;
+
+ bh = sb_bread(inode->i_sb, path[ppos].p_block);
+ if (!bh)
+ goto err;
+
+ eh = ext_block_hdr(bh);
+ ppos++;
+ BUG_ON(ppos > depth);
+ path[ppos].p_bh = bh;
+ path[ppos].p_hdr = eh;
+ i--;
+
+ if (ext4_ext_check_header(__FUNCTION__, inode, eh))
+ goto err;
+ }
+
+ path[ppos].p_depth = i;
+ path[ppos].p_hdr = eh;
+ path[ppos].p_ext = NULL;
+ path[ppos].p_idx = NULL;
+
+ if (ext4_ext_check_header(__FUNCTION__, inode, eh))
+ goto err;
+
+ /* find extent */
+ ext4_ext_binsearch(inode, path + ppos, block);
+
+ ext4_ext_show_path(inode, path);
+
+ return path;
+
+err:
+ ext4_ext_drop_refs(path);
+ if (alloc)
+ kfree(path);
+ return ERR_PTR(-EIO);
+}
+
+/*
+ * ext4_ext_insert_index:
+ * insert new index [@logical;@ptr] into the block at @curp;
+ * check where to insert: before @curp or after @curp
+ */
+static int ext4_ext_insert_index(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *curp,
+ int logical, ext4_fsblk_t ptr)
+{
+ struct ext4_extent_idx *ix;
+ int len, err;
+
+ if ((err = ext4_ext_get_access(handle, inode, curp)))
+ return err;
+
+ BUG_ON(logical == le32_to_cpu(curp->p_idx->ei_block));
+ len = EXT_MAX_INDEX(curp->p_hdr) - curp->p_idx;
+ if (logical > le32_to_cpu(curp->p_idx->ei_block)) {
+ /* insert after */
+ if (curp->p_idx != EXT_LAST_INDEX(curp->p_hdr)) {
+ len = (len - 1) * sizeof(struct ext4_extent_idx);
+ len = len < 0 ? 0 : len;
+ ext_debug("insert new index %d after: %d. "
+ "move %d from 0x%p to 0x%p\n",
+ logical, ptr, len,
+ (curp->p_idx + 1), (curp->p_idx + 2));
+ memmove(curp->p_idx + 2, curp->p_idx + 1, len);
+ }
+ ix = curp->p_idx + 1;
+ } else {
+ /* insert before */
+ len = len * sizeof(struct ext4_extent_idx);
+ len = len < 0 ? 0 : len;
+ ext_debug("insert new index %d before: %d. "
+ "move %d from 0x%p to 0x%p\n",
+ logical, ptr, len,
+ curp->p_idx, (curp->p_idx + 1));
+ memmove(curp->p_idx + 1, curp->p_idx, len);
+ ix = curp->p_idx;
+ }
+
+ ix->ei_block = cpu_to_le32(logical);
+ ext4_idx_store_pblock(ix, ptr);
+ curp->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(curp->p_hdr->eh_entries)+1);
+
+ BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries)
+ > le16_to_cpu(curp->p_hdr->eh_max));
+ BUG_ON(ix > EXT_LAST_INDEX(curp->p_hdr));
+
+ err = ext4_ext_dirty(handle, inode, curp);
+ ext4_std_error(inode->i_sb, err);
+
+ return err;
+}
+
+/*
+ * ext4_ext_split:
+ * inserts new subtree into the path, using free index entry
+ * at depth @at:
+ * - allocates all needed blocks (new leaf and all intermediate index blocks)
+ * - makes decision where to split
+ * - moves remaining extents and index entries (right to the split point)
+ * into the newly allocated blocks
+ * - initializes subtree
+ */
+static int ext4_ext_split(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path,
+ struct ext4_extent *newext, int at)
+{
+ struct buffer_head *bh = NULL;
+ int depth = ext_depth(inode);
+ struct ext4_extent_header *neh;
+ struct ext4_extent_idx *fidx;
+ struct ext4_extent *ex;
+ int i = at, k, m, a;
+ ext4_fsblk_t newblock, oldblock;
+ __le32 border;
+ ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */
+ int err = 0;
+
+ /* make decision: where to split? */
+ /* FIXME: now decision is simplest: at current extent */
+
+ /* if current leaf will be split, then we should use
+ * border from split point */
+ BUG_ON(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr));
+ if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) {
+ border = path[depth].p_ext[1].ee_block;
+ ext_debug("leaf will be split."
+ " next leaf starts at %d\n",
+ le32_to_cpu(border));
+ } else {
+ border = newext->ee_block;
+ ext_debug("leaf will be added."
+ " next leaf starts at %d\n",
+ le32_to_cpu(border));
+ }
+
+ /*
+ * If error occurs, then we break processing
+ * and mark filesystem read-only. index won't
+ * be inserted and tree will be in consistent
+ * state. Next mount will repair buffers too.
+ */
+
+ /*
+ * Get array to track all allocated blocks.
+ * We need this to handle errors and free blocks
+ * upon them.
+ */
+ ablocks = kmalloc(sizeof(ext4_fsblk_t) * depth, GFP_NOFS);
+ if (!ablocks)
+ return -ENOMEM;
+ memset(ablocks, 0, sizeof(ext4_fsblk_t) * depth);
+
+ /* allocate all needed blocks */
+ ext_debug("allocate %d blocks for indexes/leaf\n", depth - at);
+ for (a = 0; a < depth - at; a++) {
+ newblock = ext4_ext_new_block(handle, inode, path, newext, &err);
+ if (newblock == 0)
+ goto cleanup;
+ ablocks[a] = newblock;
+ }
+
+ /* initialize new leaf */
+ newblock = ablocks[--a];
+ BUG_ON(newblock == 0);
+ bh = sb_getblk(inode->i_sb, newblock);
+ if (!bh) {
+ err = -EIO;
+ goto cleanup;
+ }
+ lock_buffer(bh);
+
+ if ((err = ext4_journal_get_create_access(handle, bh)))
+ goto cleanup;
+
+ neh = ext_block_hdr(bh);
+ neh->eh_entries = 0;
+ neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode));
+ neh->eh_magic = EXT4_EXT_MAGIC;
+ neh->eh_depth = 0;
+ ex = EXT_FIRST_EXTENT(neh);
+
+ /* move remainder of path[depth] to the new leaf */
+ BUG_ON(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max);
+ /* start copy from next extent */
+ /* TODO: we could do it by single memmove */
+ m = 0;
+ path[depth].p_ext++;
+ while (path[depth].p_ext <=
+ EXT_MAX_EXTENT(path[depth].p_hdr)) {
+ ext_debug("move %d:%llu:%d in new leaf %llu\n",
+ le32_to_cpu(path[depth].p_ext->ee_block),
+ ext_pblock(path[depth].p_ext),
+ le16_to_cpu(path[depth].p_ext->ee_len),
+ newblock);
+ /*memmove(ex++, path[depth].p_ext++,
+ sizeof(struct ext4_extent));
+ neh->eh_entries++;*/
+ path[depth].p_ext++;
+ m++;
+ }
+ if (m) {
+ memmove(ex, path[depth].p_ext-m, sizeof(struct ext4_extent)*m);
+ neh->eh_entries = cpu_to_le16(le16_to_cpu(neh->eh_entries)+m);
+ }
+
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+
+ if ((err = ext4_journal_dirty_metadata(handle, bh)))
+ goto cleanup;
+ brelse(bh);
+ bh = NULL;
+
+ /* correct old leaf */
+ if (m) {
+ if ((err = ext4_ext_get_access(handle, inode, path + depth)))
+ goto cleanup;
+ path[depth].p_hdr->eh_entries =
+ cpu_to_le16(le16_to_cpu(path[depth].p_hdr->eh_entries)-m);
+ if ((err = ext4_ext_dirty(handle, inode, path + depth)))
+ goto cleanup;
+
+ }
+
+ /* create intermediate indexes */
+ k = depth - at - 1;
+ BUG_ON(k < 0);
+ if (k)
+ ext_debug("create %d intermediate indices\n", k);
+ /* insert new index into current index block */
+ /* current depth stored in i var */
+ i = depth - 1;
+ while (k--) {
+ oldblock = newblock;
+ newblock = ablocks[--a];
+ bh = sb_getblk(inode->i_sb, (ext4_fsblk_t)newblock);
+ if (!bh) {
+ err = -EIO;
+ goto cleanup;
+ }
+ lock_buffer(bh);
+
+ if ((err = ext4_journal_get_create_access(handle, bh)))
+ goto cleanup;
+
+ neh = ext_block_hdr(bh);
+ neh->eh_entries = cpu_to_le16(1);
+ neh->eh_magic = EXT4_EXT_MAGIC;
+ neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode));
+ neh->eh_depth = cpu_to_le16(depth - i);
+ fidx = EXT_FIRST_INDEX(neh);
+ fidx->ei_block = border;
+ ext4_idx_store_pblock(fidx, oldblock);
+
+ ext_debug("int.index at %d (block %llu): %lu -> %llu\n", i,
+ newblock, (unsigned long) le32_to_cpu(border),
+ oldblock);
+ /* copy indexes */
+ m = 0;
+ path[i].p_idx++;
+
+ ext_debug("cur 0x%p, last 0x%p\n", path[i].p_idx,
+ EXT_MAX_INDEX(path[i].p_hdr));
+ BUG_ON(EXT_MAX_INDEX(path[i].p_hdr) !=
+ EXT_LAST_INDEX(path[i].p_hdr));
+ while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) {
+ ext_debug("%d: move %d:%d in new index %llu\n", i,
+ le32_to_cpu(path[i].p_idx->ei_block),
+ idx_pblock(path[i].p_idx),
+ newblock);
+ /*memmove(++fidx, path[i].p_idx++,
+ sizeof(struct ext4_extent_idx));
+ neh->eh_entries++;
+ BUG_ON(neh->eh_entries > neh->eh_max);*/
+ path[i].p_idx++;
+ m++;
+ }
+ if (m) {
+ memmove(++fidx, path[i].p_idx - m,
+ sizeof(struct ext4_extent_idx) * m);
+ neh->eh_entries =
+ cpu_to_le16(le16_to_cpu(neh->eh_entries) + m);
+ }
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+
+ if ((err = ext4_journal_dirty_metadata(handle, bh)))
+ goto cleanup;
+ brelse(bh);
+ bh = NULL;
+
+ /* correct old index */
+ if (m) {
+ err = ext4_ext_get_access(handle, inode, path + i);
+ if (err)
+ goto cleanup;
+ path[i].p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(path[i].p_hdr->eh_entries)-m);
+ err = ext4_ext_dirty(handle, inode, path + i);
+ if (err)
+ goto cleanup;
+ }
+
+ i--;
+ }
+
+ /* insert new index */
+ if (err)
+ goto cleanup;
+
+ err = ext4_ext_insert_index(handle, inode, path + at,
+ le32_to_cpu(border), newblock);
+
+cleanup:
+ if (bh) {
+ if (buffer_locked(bh))
+ unlock_buffer(bh);
+ brelse(bh);
+ }
+
+ if (err) {
+ /* free all allocated blocks in error case */
+ for (i = 0; i < depth; i++) {
+ if (!ablocks[i])
+ continue;
+ ext4_free_blocks(handle, inode, ablocks[i], 1);
+ }
+ }
+ kfree(ablocks);
+
+ return err;
+}
+
+/*
+ * ext4_ext_grow_indepth:
+ * implements tree growing procedure:
+ * - allocates new block
+ * - moves top-level data (index block or leaf) into the new block
+ * - initializes new top-level, creating index that points to the
+ * just created block
+ */
+static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path,
+ struct ext4_extent *newext)
+{
+ struct ext4_ext_path *curp = path;
+ struct ext4_extent_header *neh;
+ struct ext4_extent_idx *fidx;
+ struct buffer_head *bh;
+ ext4_fsblk_t newblock;
+ int err = 0;
+
+ newblock = ext4_ext_new_block(handle, inode, path, newext, &err);
+ if (newblock == 0)
+ return err;
+
+ bh = sb_getblk(inode->i_sb, newblock);
+ if (!bh) {
+ err = -EIO;
+ ext4_std_error(inode->i_sb, err);
+ return err;
+ }
+ lock_buffer(bh);
+
+ if ((err = ext4_journal_get_create_access(handle, bh))) {
+ unlock_buffer(bh);
+ goto out;
+ }
+
+ /* move top-level index/leaf into new block */
+ memmove(bh->b_data, curp->p_hdr, sizeof(EXT4_I(inode)->i_data));
+
+ /* set size of new block */
+ neh = ext_block_hdr(bh);
+ /* old root could have indexes or leaves
+ * so calculate e_max right way */
+ if (ext_depth(inode))
+ neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode));
+ else
+ neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode));
+ neh->eh_magic = EXT4_EXT_MAGIC;
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+
+ if ((err = ext4_journal_dirty_metadata(handle, bh)))
+ goto out;
+
+ /* create index in new top-level index: num,max,pointer */
+ if ((err = ext4_ext_get_access(handle, inode, curp)))
+ goto out;
+
+ curp->p_hdr->eh_magic = EXT4_EXT_MAGIC;
+ curp->p_hdr->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode));
+ curp->p_hdr->eh_entries = cpu_to_le16(1);
+ curp->p_idx = EXT_FIRST_INDEX(curp->p_hdr);
+ /* FIXME: it works, but actually path[0] can be index */
+ curp->p_idx->ei_block = EXT_FIRST_EXTENT(path[0].p_hdr)->ee_block;
+ ext4_idx_store_pblock(curp->p_idx, newblock);
+
+ neh = ext_inode_hdr(inode);
+ fidx = EXT_FIRST_INDEX(neh);
+ ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n",
+ le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max),
+ le32_to_cpu(fidx->ei_block), idx_pblock(fidx));
+
+ neh->eh_depth = cpu_to_le16(path->p_depth + 1);
+ err = ext4_ext_dirty(handle, inode, curp);
+out:
+ brelse(bh);
+
+ return err;
+}
+
+/*
+ * ext4_ext_create_new_leaf:
+ * finds empty index and adds new leaf.
+ * if no free index is found, then it requests in-depth growing.
+ */
+static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path,
+ struct ext4_extent *newext)
+{
+ struct ext4_ext_path *curp;
+ int depth, i, err = 0;
+
+repeat:
+ i = depth = ext_depth(inode);
+
+ /* walk up to the tree and look for free index entry */
+ curp = path + depth;
+ while (i > 0 && !EXT_HAS_FREE_INDEX(curp)) {
+ i--;
+ curp--;
+ }
+
+ /* we use already allocated block for index block,
+ * so subsequent data blocks should be contiguous */
+ if (EXT_HAS_FREE_INDEX(curp)) {
+ /* if we found index with free entry, then use that
+ * entry: create all needed subtree and add new leaf */
+ err = ext4_ext_split(handle, inode, path, newext, i);
+
+ /* refill path */
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode,
+ le32_to_cpu(newext->ee_block),
+ path);
+ if (IS_ERR(path))
+ err = PTR_ERR(path);
+ } else {
+ /* tree is full, time to grow in depth */
+ err = ext4_ext_grow_indepth(handle, inode, path, newext);
+ if (err)
+ goto out;
+
+ /* refill path */
+ ext4_ext_drop_refs(path);
+ path = ext4_ext_find_extent(inode,
+ le32_to_cpu(newext->ee_block),
+ path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ goto out;
+ }
+
+ /*
+ * only first (depth 0 -> 1) produces free space;
+ * in all other cases we have to split the grown tree
+ */
+ depth = ext_depth(inode);
+ if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) {
+ /* now we need to split */
+ goto repeat;
+ }
+ }
+
+out:
+ return err;
+}
+
+/*
+ * ext4_ext_next_allocated_block:
+ * returns allocated block in subsequent extent or EXT_MAX_BLOCK.
+ * NOTE: it considers block number from index entry as
+ * allocated block. Thus, index entries have to be consistent
+ * with leaves.
+ */
+static unsigned long
+ext4_ext_next_allocated_block(struct ext4_ext_path *path)
+{
+ int depth;
+
+ BUG_ON(path == NULL);
+ depth = path->p_depth;
+
+ if (depth == 0 && path->p_ext == NULL)
+ return EXT_MAX_BLOCK;
+
+ while (depth >= 0) {
+ if (depth == path->p_depth) {
+ /* leaf */
+ if (path[depth].p_ext !=
+ EXT_LAST_EXTENT(path[depth].p_hdr))
+ return le32_to_cpu(path[depth].p_ext[1].ee_block);
+ } else {
+ /* index */
+ if (path[depth].p_idx !=
+ EXT_LAST_INDEX(path[depth].p_hdr))
+ return le32_to_cpu(path[depth].p_idx[1].ei_block);
+ }
+ depth--;
+ }
+
+ return EXT_MAX_BLOCK;
+}
+
+/*
+ * ext4_ext_next_leaf_block:
+ * returns first allocated block from next leaf or EXT_MAX_BLOCK
+ */
+static unsigned ext4_ext_next_leaf_block(struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ int depth;
+
+ BUG_ON(path == NULL);
+ depth = path->p_depth;
+
+ /* zero-tree has no leaf blocks at all */
+ if (depth == 0)
+ return EXT_MAX_BLOCK;
+
+ /* go to index block */
+ depth--;
+
+ while (depth >= 0) {
+ if (path[depth].p_idx !=
+ EXT_LAST_INDEX(path[depth].p_hdr))
+ return le32_to_cpu(path[depth].p_idx[1].ei_block);
+ depth--;
+ }
+
+ return EXT_MAX_BLOCK;
+}
+
+/*
+ * ext4_ext_correct_indexes:
+ * if leaf gets modified and modified extent is first in the leaf,
+ * then we have to correct all indexes above.
+ * TODO: do we need to correct tree in all cases?
+ */
+int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ struct ext4_extent_header *eh;
+ int depth = ext_depth(inode);
+ struct ext4_extent *ex;
+ __le32 border;
+ int k, err = 0;
+
+ eh = path[depth].p_hdr;
+ ex = path[depth].p_ext;
+ BUG_ON(ex == NULL);
+ BUG_ON(eh == NULL);
+
+ if (depth == 0) {
+ /* there is no tree at all */
+ return 0;
+ }
+
+ if (ex != EXT_FIRST_EXTENT(eh)) {
+ /* we correct tree if first leaf got modified only */
+ return 0;
+ }
+
+ /*
+ * TODO: we need correction if border is smaller than current one
+ */
+ k = depth - 1;
+ border = path[depth].p_ext->ee_block;
+ if ((err = ext4_ext_get_access(handle, inode, path + k)))
+ return err;
+ path[k].p_idx->ei_block = border;
+ if ((err = ext4_ext_dirty(handle, inode, path + k)))
+ return err;
+
+ while (k--) {
+ /* change all left-side indexes */
+ if (path[k+1].p_idx != EXT_FIRST_INDEX(path[k+1].p_hdr))
+ break;
+ if ((err = ext4_ext_get_access(handle, inode, path + k)))
+ break;
+ path[k].p_idx->ei_block = border;
+ if ((err = ext4_ext_dirty(handle, inode, path + k)))
+ break;
+ }
+
+ return err;
+}
+
+static int inline
+ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
+ struct ext4_extent *ex2)
+{
+ if (le32_to_cpu(ex1->ee_block) + le16_to_cpu(ex1->ee_len) !=
+ le32_to_cpu(ex2->ee_block))
+ return 0;
+
+ /*
+ * To allow future support for preallocated extents to be added
+ * as an RO_COMPAT feature, refuse to merge to extents if
+ * this can result in the top bit of ee_len being set.
+ */
+ if (le16_to_cpu(ex1->ee_len) + le16_to_cpu(ex2->ee_len) > EXT_MAX_LEN)
+ return 0;
+#ifdef AGRESSIVE_TEST
+ if (le16_to_cpu(ex1->ee_len) >= 4)
+ return 0;
+#endif
+
+ if (ext_pblock(ex1) + le16_to_cpu(ex1->ee_len) == ext_pblock(ex2))
+ return 1;
+ return 0;
+}
+
+/*
+ * ext4_ext_insert_extent:
+ * tries to merge requsted extent into the existing extent or
+ * inserts requested extent as new one into the tree,
+ * creating new leaf in the no-space case.
+ */
+int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path,
+ struct ext4_extent *newext)
+{
+ struct ext4_extent_header * eh;
+ struct ext4_extent *ex, *fex;
+ struct ext4_extent *nearex; /* nearest extent */
+ struct ext4_ext_path *npath = NULL;
+ int depth, len, err, next;
+
+ BUG_ON(newext->ee_len == 0);
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ BUG_ON(path[depth].p_hdr == NULL);
+
+ /* try to insert block into found extent and return */
+ if (ex && ext4_can_extents_be_merged(inode, ex, newext)) {
+ ext_debug("append %d block to %d:%d (from %llu)\n",
+ le16_to_cpu(newext->ee_len),
+ le32_to_cpu(ex->ee_block),
+ le16_to_cpu(ex->ee_len), ext_pblock(ex));
+ if ((err = ext4_ext_get_access(handle, inode, path + depth)))
+ return err;
+ ex->ee_len = cpu_to_le16(le16_to_cpu(ex->ee_len)
+ + le16_to_cpu(newext->ee_len));
+ eh = path[depth].p_hdr;
+ nearex = ex;
+ goto merge;
+ }
+
+repeat:
+ depth = ext_depth(inode);
+ eh = path[depth].p_hdr;
+ if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max))
+ goto has_space;
+
+ /* probably next leaf has space for us? */
+ fex = EXT_LAST_EXTENT(eh);
+ next = ext4_ext_next_leaf_block(inode, path);
+ if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)
+ && next != EXT_MAX_BLOCK) {
+ ext_debug("next leaf block - %d\n", next);
+ BUG_ON(npath != NULL);
+ npath = ext4_ext_find_extent(inode, next, NULL);
+ if (IS_ERR(npath))
+ return PTR_ERR(npath);
+ BUG_ON(npath->p_depth != path->p_depth);
+ eh = npath[depth].p_hdr;
+ if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) {
+ ext_debug("next leaf isnt full(%d)\n",
+ le16_to_cpu(eh->eh_entries));
+ path = npath;
+ goto repeat;
+ }
+ ext_debug("next leaf has no free space(%d,%d)\n",
+ le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max));
+ }
+
+ /*
+ * There is no free space in the found leaf.
+ * We're gonna add a new leaf in the tree.
+ */
+ err = ext4_ext_create_new_leaf(handle, inode, path, newext);
+ if (err)
+ goto cleanup;
+ depth = ext_depth(inode);
+ eh = path[depth].p_hdr;
+
+has_space:
+ nearex = path[depth].p_ext;
+
+ if ((err = ext4_ext_get_access(handle, inode, path + depth)))
+ goto cleanup;
+
+ if (!nearex) {
+ /* there is no extent in this leaf, create first one */
+ ext_debug("first extent in the leaf: %d:%llu:%d\n",
+ le32_to_cpu(newext->ee_block),
+ ext_pblock(newext),
+ le16_to_cpu(newext->ee_len));
+ path[depth].p_ext = EXT_FIRST_EXTENT(eh);
+ } else if (le32_to_cpu(newext->ee_block)
+ > le32_to_cpu(nearex->ee_block)) {
+/* BUG_ON(newext->ee_block == nearex->ee_block); */
+ if (nearex != EXT_LAST_EXTENT(eh)) {
+ len = EXT_MAX_EXTENT(eh) - nearex;
+ len = (len - 1) * sizeof(struct ext4_extent);
+ len = len < 0 ? 0 : len;
+ ext_debug("insert %d:%llu:%d after: nearest 0x%p, "
+ "move %d from 0x%p to 0x%p\n",
+ le32_to_cpu(newext->ee_block),
+ ext_pblock(newext),
+ le16_to_cpu(newext->ee_len),
+ nearex, len, nearex + 1, nearex + 2);
+ memmove(nearex + 2, nearex + 1, len);
+ }
+ path[depth].p_ext = nearex + 1;
+ } else {
+ BUG_ON(newext->ee_block == nearex->ee_block);
+ len = (EXT_MAX_EXTENT(eh) - nearex) * sizeof(struct ext4_extent);
+ len = len < 0 ? 0 : len;
+ ext_debug("insert %d:%llu:%d before: nearest 0x%p, "
+ "move %d from 0x%p to 0x%p\n",
+ le32_to_cpu(newext->ee_block),
+ ext_pblock(newext),
+ le16_to_cpu(newext->ee_len),
+ nearex, len, nearex + 1, nearex + 2);
+ memmove(nearex + 1, nearex, len);
+ path[depth].p_ext = nearex;
+ }
+
+ eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)+1);
+ nearex = path[depth].p_ext;
+ nearex->ee_block = newext->ee_block;
+ nearex->ee_start = newext->ee_start;
+ nearex->ee_start_hi = newext->ee_start_hi;
+ nearex->ee_len = newext->ee_len;
+
+merge:
+ /* try to merge extents to the right */
+ while (nearex < EXT_LAST_EXTENT(eh)) {
+ if (!ext4_can_extents_be_merged(inode, nearex, nearex + 1))
+ break;
+ /* merge with next extent! */
+ nearex->ee_len = cpu_to_le16(le16_to_cpu(nearex->ee_len)
+ + le16_to_cpu(nearex[1].ee_len));
+ if (nearex + 1 < EXT_LAST_EXTENT(eh)) {
+ len = (EXT_LAST_EXTENT(eh) - nearex - 1)
+ * sizeof(struct ext4_extent);
+ memmove(nearex + 1, nearex + 2, len);
+ }
+ eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)-1);
+ BUG_ON(eh->eh_entries == 0);
+ }
+
+ /* try to merge extents to the left */
+
+ /* time to correct all indexes above */
+ err = ext4_ext_correct_indexes(handle, inode, path);
+ if (err)
+ goto cleanup;
+
+ err = ext4_ext_dirty(handle, inode, path + depth);
+
+cleanup:
+ if (npath) {
+ ext4_ext_drop_refs(npath);
+ kfree(npath);
+ }
+ ext4_ext_tree_changed(inode);
+ ext4_ext_invalidate_cache(inode);
+ return err;
+}
+
+int ext4_ext_walk_space(struct inode *inode, unsigned long block,
+ unsigned long num, ext_prepare_callback func,
+ void *cbdata)
+{
+ struct ext4_ext_path *path = NULL;
+ struct ext4_ext_cache cbex;
+ struct ext4_extent *ex;
+ unsigned long next, start = 0, end = 0;
+ unsigned long last = block + num;
+ int depth, exists, err = 0;
+
+ BUG_ON(func == NULL);
+ BUG_ON(inode == NULL);
+
+ while (block < last && block != EXT_MAX_BLOCK) {
+ num = last - block;
+ /* find extent for this block */
+ path = ext4_ext_find_extent(inode, block, path);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ path = NULL;
+ break;
+ }
+
+ depth = ext_depth(inode);
+ BUG_ON(path[depth].p_hdr == NULL);
+ ex = path[depth].p_ext;
+ next = ext4_ext_next_allocated_block(path);
+
+ exists = 0;
+ if (!ex) {
+ /* there is no extent yet, so try to allocate
+ * all requested space */
+ start = block;
+ end = block + num;
+ } else if (le32_to_cpu(ex->ee_block) > block) {
+ /* need to allocate space before found extent */
+ start = block;
+ end = le32_to_cpu(ex->ee_block);
+ if (block + num < end)
+ end = block + num;
+ } else if (block >=
+ le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len)) {
+ /* need to allocate space after found extent */
+ start = block;
+ end = block + num;
+ if (end >= next)
+ end = next;
+ } else if (block >= le32_to_cpu(ex->ee_block)) {
+ /*
+ * some part of requested space is covered
+ * by found extent
+ */
+ start = block;
+ end = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len);
+ if (block + num < end)
+ end = block + num;
+ exists = 1;
+ } else {
+ BUG();
+ }
+ BUG_ON(end <= start);
+
+ if (!exists) {
+ cbex.ec_block = start;
+ cbex.ec_len = end - start;
+ cbex.ec_start = 0;
+ cbex.ec_type = EXT4_EXT_CACHE_GAP;
+ } else {
+ cbex.ec_block = le32_to_cpu(ex->ee_block);
+ cbex.ec_len = le16_to_cpu(ex->ee_len);
+ cbex.ec_start = ext_pblock(ex);
+ cbex.ec_type = EXT4_EXT_CACHE_EXTENT;
+ }
+
+ BUG_ON(cbex.ec_len == 0);
+ err = func(inode, path, &cbex, cbdata);
+ ext4_ext_drop_refs(path);
+
+ if (err < 0)
+ break;
+ if (err == EXT_REPEAT)
+ continue;
+ else if (err == EXT_BREAK) {
+ err = 0;
+ break;
+ }
+
+ if (ext_depth(inode) != depth) {
+ /* depth was changed. we have to realloc path */
+ kfree(path);
+ path = NULL;
+ }
+
+ block = cbex.ec_block + cbex.ec_len;
+ }
+
+ if (path) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+
+ return err;
+}
+
+static inline void
+ext4_ext_put_in_cache(struct inode *inode, __u32 block,
+ __u32 len, __u32 start, int type)
+{
+ struct ext4_ext_cache *cex;
+ BUG_ON(len == 0);
+ cex = &EXT4_I(inode)->i_cached_extent;
+ cex->ec_type = type;
+ cex->ec_block = block;
+ cex->ec_len = len;
+ cex->ec_start = start;
+}
+
+/*
+ * ext4_ext_put_gap_in_cache:
+ * calculate boundaries of the gap that the requested block fits into
+ * and cache this gap
+ */
+static inline void
+ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
+ unsigned long block)
+{
+ int depth = ext_depth(inode);
+ unsigned long lblock, len;
+ struct ext4_extent *ex;
+
+ ex = path[depth].p_ext;
+ if (ex == NULL) {
+ /* there is no extent yet, so gap is [0;-] */
+ lblock = 0;
+ len = EXT_MAX_BLOCK;
+ ext_debug("cache gap(whole file):");
+ } else if (block < le32_to_cpu(ex->ee_block)) {
+ lblock = block;
+ len = le32_to_cpu(ex->ee_block) - block;
+ ext_debug("cache gap(before): %lu [%lu:%lu]",
+ (unsigned long) block,
+ (unsigned long) le32_to_cpu(ex->ee_block),
+ (unsigned long) le16_to_cpu(ex->ee_len));
+ } else if (block >= le32_to_cpu(ex->ee_block)
+ + le16_to_cpu(ex->ee_len)) {
+ lblock = le32_to_cpu(ex->ee_block)
+ + le16_to_cpu(ex->ee_len);
+ len = ext4_ext_next_allocated_block(path);
+ ext_debug("cache gap(after): [%lu:%lu] %lu",
+ (unsigned long) le32_to_cpu(ex->ee_block),
+ (unsigned long) le16_to_cpu(ex->ee_len),
+ (unsigned long) block);
+ BUG_ON(len == lblock);
+ len = len - lblock;
+ } else {
+ lblock = len = 0;
+ BUG();
+ }
+
+ ext_debug(" -> %lu:%lu\n", (unsigned long) lblock, len);
+ ext4_ext_put_in_cache(inode, lblock, len, 0, EXT4_EXT_CACHE_GAP);
+}
+
+static inline int
+ext4_ext_in_cache(struct inode *inode, unsigned long block,
+ struct ext4_extent *ex)
+{
+ struct ext4_ext_cache *cex;
+
+ cex = &EXT4_I(inode)->i_cached_extent;
+
+ /* has cache valid data? */
+ if (cex->ec_type == EXT4_EXT_CACHE_NO)
+ return EXT4_EXT_CACHE_NO;
+
+ BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP &&
+ cex->ec_type != EXT4_EXT_CACHE_EXTENT);
+ if (block >= cex->ec_block && block < cex->ec_block + cex->ec_len) {
+ ex->ee_block = cpu_to_le32(cex->ec_block);
+ ext4_ext_store_pblock(ex, cex->ec_start);
+ ex->ee_len = cpu_to_le16(cex->ec_len);
+ ext_debug("%lu cached by %lu:%lu:%llu\n",
+ (unsigned long) block,
+ (unsigned long) cex->ec_block,
+ (unsigned long) cex->ec_len,
+ cex->ec_start);
+ return cex->ec_type;
+ }
+
+ /* not in cache */
+ return EXT4_EXT_CACHE_NO;
+}
+
+/*
+ * ext4_ext_rm_idx:
+ * removes index from the index block.
+ * It's used in truncate case only, thus all requests are for
+ * last index in the block only.
+ */
+int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ struct buffer_head *bh;
+ int err;
+ ext4_fsblk_t leaf;
+
+ /* free index block */
+ path--;
+ leaf = idx_pblock(path->p_idx);
+ BUG_ON(path->p_hdr->eh_entries == 0);
+ if ((err = ext4_ext_get_access(handle, inode, path)))
+ return err;
+ path->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(path->p_hdr->eh_entries)-1);
+ if ((err = ext4_ext_dirty(handle, inode, path)))
+ return err;
+ ext_debug("index is empty, remove it, free block %llu\n", leaf);
+ bh = sb_find_get_block(inode->i_sb, leaf);
+ ext4_forget(handle, 1, inode, bh, leaf);
+ ext4_free_blocks(handle, inode, leaf, 1);
+ return err;
+}
+
+/*
+ * ext4_ext_calc_credits_for_insert:
+ * This routine returns max. credits that the extent tree can consume.
+ * It should be OK for low-performance paths like ->writepage()
+ * To allow many writing processes to fit into a single transaction,
+ * the caller should calculate credits under truncate_mutex and
+ * pass the actual path.
+ */
+int inline ext4_ext_calc_credits_for_insert(struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ int depth, needed;
+
+ if (path) {
+ /* probably there is space in leaf? */
+ depth = ext_depth(inode);
+ if (le16_to_cpu(path[depth].p_hdr->eh_entries)
+ < le16_to_cpu(path[depth].p_hdr->eh_max))
+ return 1;
+ }
+
+ /*
+ * given 32-bit logical block (4294967296 blocks), max. tree
+ * can be 4 levels in depth -- 4 * 340^4 == 53453440000.
+ * Let's also add one more level for imbalance.
+ */
+ depth = 5;
+
+ /* allocation of new data block(s) */
+ needed = 2;
+
+ /*
+ * tree can be full, so it would need to grow in depth:
+ * allocation + old root + new root
+ */
+ needed += 2 + 1 + 1;
+
+ /*
+ * Index split can happen, we would need:
+ * allocate intermediate indexes (bitmap + group)
+ * + change two blocks at each level, but root (already included)
+ */
+ needed = (depth * 2) + (depth * 2);
+
+ /* any allocation modifies superblock */
+ needed += 1;
+
+ return needed;
+}
+
+static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
+ struct ext4_extent *ex,
+ unsigned long from, unsigned long to)
+{
+ struct buffer_head *bh;
+ int i;
+
+#ifdef EXTENTS_STATS
+ {
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ unsigned short ee_len = le16_to_cpu(ex->ee_len);
+ spin_lock(&sbi->s_ext_stats_lock);
+ sbi->s_ext_blocks += ee_len;
+ sbi->s_ext_extents++;
+ if (ee_len < sbi->s_ext_min)
+ sbi->s_ext_min = ee_len;
+ if (ee_len > sbi->s_ext_max)
+ sbi->s_ext_max = ee_len;
+ if (ext_depth(inode) > sbi->s_depth_max)
+ sbi->s_depth_max = ext_depth(inode);
+ spin_unlock(&sbi->s_ext_stats_lock);
+ }
+#endif
+ if (from >= le32_to_cpu(ex->ee_block)
+ && to == le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) {
+ /* tail removal */
+ unsigned long num;
+ ext4_fsblk_t start;
+ num = le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - from;
+ start = ext_pblock(ex) + le16_to_cpu(ex->ee_len) - num;
+ ext_debug("free last %lu blocks starting %llu\n", num, start);
+ for (i = 0; i < num; i++) {
+ bh = sb_find_get_block(inode->i_sb, start + i);
+ ext4_forget(handle, 0, inode, bh, start + i);
+ }
+ ext4_free_blocks(handle, inode, start, num);
+ } else if (from == le32_to_cpu(ex->ee_block)
+ && to <= le32_to_cpu(ex->ee_block) + le16_to_cpu(ex->ee_len) - 1) {
+ printk("strange request: removal %lu-%lu from %u:%u\n",
+ from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len));
+ } else {
+ printk("strange request: removal(2) %lu-%lu from %u:%u\n",
+ from, to, le32_to_cpu(ex->ee_block), le16_to_cpu(ex->ee_len));
+ }
+ return 0;
+}
+
+static int
+ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path, unsigned long start)
+{
+ int err = 0, correct_index = 0;
+ int depth = ext_depth(inode), credits;
+ struct ext4_extent_header *eh;
+ unsigned a, b, block, num;
+ unsigned long ex_ee_block;
+ unsigned short ex_ee_len;
+ struct ext4_extent *ex;
+
+ ext_debug("truncate since %lu in leaf\n", start);
+ if (!path[depth].p_hdr)
+ path[depth].p_hdr = ext_block_hdr(path[depth].p_bh);
+ eh = path[depth].p_hdr;
+ BUG_ON(eh == NULL);
+ BUG_ON(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max));
+ BUG_ON(eh->eh_magic != EXT4_EXT_MAGIC);
+
+ /* find where to start removing */
+ ex = EXT_LAST_EXTENT(eh);
+
+ ex_ee_block = le32_to_cpu(ex->ee_block);
+ ex_ee_len = le16_to_cpu(ex->ee_len);
+
+ while (ex >= EXT_FIRST_EXTENT(eh) &&
+ ex_ee_block + ex_ee_len > start) {
+ ext_debug("remove ext %lu:%u\n", ex_ee_block, ex_ee_len);
+ path[depth].p_ext = ex;
+
+ a = ex_ee_block > start ? ex_ee_block : start;
+ b = ex_ee_block + ex_ee_len - 1 < EXT_MAX_BLOCK ?
+ ex_ee_block + ex_ee_len - 1 : EXT_MAX_BLOCK;
+
+ ext_debug(" border %u:%u\n", a, b);
+
+ if (a != ex_ee_block && b != ex_ee_block + ex_ee_len - 1) {
+ block = 0;
+ num = 0;
+ BUG();
+ } else if (a != ex_ee_block) {
+ /* remove tail of the extent */
+ block = ex_ee_block;
+ num = a - block;
+ } else if (b != ex_ee_block + ex_ee_len - 1) {
+ /* remove head of the extent */
+ block = a;
+ num = b - a;
+ /* there is no "make a hole" API yet */
+ BUG();
+ } else {
+ /* remove whole extent: excellent! */
+ block = ex_ee_block;
+ num = 0;
+ BUG_ON(a != ex_ee_block);
+ BUG_ON(b != ex_ee_block + ex_ee_len - 1);
+ }
+
+ /* at present, extent can't cross block group: */
+ /* leaf + bitmap + group desc + sb + inode */
+ credits = 5;
+ if (ex == EXT_FIRST_EXTENT(eh)) {
+ correct_index = 1;
+ credits += (ext_depth(inode)) + 1;
+ }
+#ifdef CONFIG_QUOTA
+ credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+#endif
+
+ handle = ext4_ext_journal_restart(handle, credits);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ goto out;
+ }
+
+ err = ext4_ext_get_access(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ err = ext4_remove_blocks(handle, inode, ex, a, b);
+ if (err)
+ goto out;
+
+ if (num == 0) {
+ /* this extent is removed; mark slot entirely unused */
+ ext4_ext_store_pblock(ex, 0);
+ eh->eh_entries = cpu_to_le16(le16_to_cpu(eh->eh_entries)-1);
+ }
+
+ ex->ee_block = cpu_to_le32(block);
+ ex->ee_len = cpu_to_le16(num);
+
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ ext_debug("new extent: %u:%u:%llu\n", block, num,
+ ext_pblock(ex));
+ ex--;
+ ex_ee_block = le32_to_cpu(ex->ee_block);
+ ex_ee_len = le16_to_cpu(ex->ee_len);
+ }
+
+ if (correct_index && eh->eh_entries)
+ err = ext4_ext_correct_indexes(handle, inode, path);
+
+ /* if this leaf is free, then we should
+ * remove it from index block above */
+ if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL)
+ err = ext4_ext_rm_idx(handle, inode, path + depth);
+
+out:
+ return err;
+}
+
+/*
+ * ext4_ext_more_to_rm:
+ * returns 1 if current index has to be freed (even partial)
+ */
+static int inline
+ext4_ext_more_to_rm(struct ext4_ext_path *path)
+{
+ BUG_ON(path->p_idx == NULL);
+
+ if (path->p_idx < EXT_FIRST_INDEX(path->p_hdr))
+ return 0;
+
+ /*
+ * if truncate on deeper level happened, it wasn't partial,
+ * so we have to consider current index for truncation
+ */
+ if (le16_to_cpu(path->p_hdr->eh_entries) == path->p_block)
+ return 0;
+ return 1;
+}
+
+int ext4_ext_remove_space(struct inode *inode, unsigned long start)
+{
+ struct super_block *sb = inode->i_sb;
+ int depth = ext_depth(inode);
+ struct ext4_ext_path *path;
+ handle_t *handle;
+ int i = 0, err = 0;
+
+ ext_debug("truncate since %lu\n", start);
+
+ /* probably first extent we're gonna free will be last in block */
+ handle = ext4_journal_start(inode, depth + 1);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ ext4_ext_invalidate_cache(inode);
+
+ /*
+ * We start scanning from right side, freeing all the blocks
+ * after i_size and walking into the tree depth-wise.
+ */
+ path = kmalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_KERNEL);
+ if (path == NULL) {
+ ext4_journal_stop(handle);
+ return -ENOMEM;
+ }
+ memset(path, 0, sizeof(struct ext4_ext_path) * (depth + 1));
+ path[0].p_hdr = ext_inode_hdr(inode);
+ if (ext4_ext_check_header(__FUNCTION__, inode, path[0].p_hdr)) {
+ err = -EIO;
+ goto out;
+ }
+ path[0].p_depth = depth;
+
+ while (i >= 0 && err == 0) {
+ if (i == depth) {
+ /* this is leaf block */
+ err = ext4_ext_rm_leaf(handle, inode, path, start);
+ /* root level has p_bh == NULL, brelse() eats this */
+ brelse(path[i].p_bh);
+ path[i].p_bh = NULL;
+ i--;
+ continue;
+ }
+
+ /* this is index block */
+ if (!path[i].p_hdr) {
+ ext_debug("initialize header\n");
+ path[i].p_hdr = ext_block_hdr(path[i].p_bh);
+ if (ext4_ext_check_header(__FUNCTION__, inode,
+ path[i].p_hdr)) {
+ err = -EIO;
+ goto out;
+ }
+ }
+
+ BUG_ON(le16_to_cpu(path[i].p_hdr->eh_entries)
+ > le16_to_cpu(path[i].p_hdr->eh_max));
+ BUG_ON(path[i].p_hdr->eh_magic != EXT4_EXT_MAGIC);
+
+ if (!path[i].p_idx) {
+ /* this level hasn't been touched yet */
+ path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr);
+ path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1;
+ ext_debug("init index ptr: hdr 0x%p, num %d\n",
+ path[i].p_hdr,
+ le16_to_cpu(path[i].p_hdr->eh_entries));
+ } else {
+ /* we were already here, see at next index */
+ path[i].p_idx--;
+ }
+
+ ext_debug("level %d - index, first 0x%p, cur 0x%p\n",
+ i, EXT_FIRST_INDEX(path[i].p_hdr),
+ path[i].p_idx);
+ if (ext4_ext_more_to_rm(path + i)) {
+ /* go to the next level */
+ ext_debug("move to level %d (block %llu)\n",
+ i + 1, idx_pblock(path[i].p_idx));
+ memset(path + i + 1, 0, sizeof(*path));
+ path[i+1].p_bh =
+ sb_bread(sb, idx_pblock(path[i].p_idx));
+ if (!path[i+1].p_bh) {
+ /* should we reset i_size? */
+ err = -EIO;
+ break;
+ }
+
+ /* save actual number of indexes since this
+ * number is changed at the next iteration */
+ path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries);
+ i++;
+ } else {
+ /* we finished processing this index, go up */
+ if (path[i].p_hdr->eh_entries == 0 && i > 0) {
+ /* index is empty, remove it;
+ * handle must be already prepared by the
+ * truncatei_leaf() */
+ err = ext4_ext_rm_idx(handle, inode, path + i);
+ }
+ /* root level has p_bh == NULL, brelse() eats this */
+ brelse(path[i].p_bh);
+ path[i].p_bh = NULL;
+ i--;
+ ext_debug("return to level %d\n", i);
+ }
+ }
+
+ /* TODO: flexible tree reduction should be here */
+ if (path->p_hdr->eh_entries == 0) {
+ /*
+ * truncate to zero freed all the tree,
+ * so we need to correct eh_depth
+ */
+ err = ext4_ext_get_access(handle, inode, path);
+ if (err == 0) {
+ ext_inode_hdr(inode)->eh_depth = 0;
+ ext_inode_hdr(inode)->eh_max =
+ cpu_to_le16(ext4_ext_space_root(inode));
+ err = ext4_ext_dirty(handle, inode, path);
+ }
+ }
+out:
+ ext4_ext_tree_changed(inode);
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ ext4_journal_stop(handle);
+
+ return err;
+}
+
+/*
+ * called at mount time
+ */
+void ext4_ext_init(struct super_block *sb)
+{
+ /*
+ * possible initialization would be here
+ */
+
+ if (test_opt(sb, EXTENTS)) {
+ printk("EXT4-fs: file extents enabled");
+#ifdef AGRESSIVE_TEST
+ printk(", agressive tests");
+#endif
+#ifdef CHECK_BINSEARCH
+ printk(", check binsearch");
+#endif
+#ifdef EXTENTS_STATS
+ printk(", stats");
+#endif
+ printk("\n");
+#ifdef EXTENTS_STATS
+ spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock);
+ EXT4_SB(sb)->s_ext_min = 1 << 30;
+ EXT4_SB(sb)->s_ext_max = 0;
+#endif
+ }
+}
+
+/*
+ * called at umount time
+ */
+void ext4_ext_release(struct super_block *sb)
+{
+ if (!test_opt(sb, EXTENTS))
+ return;
+
+#ifdef EXTENTS_STATS
+ if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) {
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n",
+ sbi->s_ext_blocks, sbi->s_ext_extents,
+ sbi->s_ext_blocks / sbi->s_ext_extents);
+ printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n",
+ sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max);
+ }
+#endif
+}
+
+int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
+ ext4_fsblk_t iblock,
+ unsigned long max_blocks, struct buffer_head *bh_result,
+ int create, int extend_disksize)
+{
+ struct ext4_ext_path *path = NULL;
+ struct ext4_extent newex, *ex;
+ ext4_fsblk_t goal, newblock;
+ int err = 0, depth;
+ unsigned long allocated = 0;
+
+ __clear_bit(BH_New, &bh_result->b_state);
+ ext_debug("blocks %d/%lu requested for inode %u\n", (int) iblock,
+ max_blocks, (unsigned) inode->i_ino);
+ mutex_lock(&EXT4_I(inode)->truncate_mutex);
+
+ /* check in cache */
+ if ((goal = ext4_ext_in_cache(inode, iblock, &newex))) {
+ if (goal == EXT4_EXT_CACHE_GAP) {
+ if (!create) {
+ /* block isn't allocated yet and
+ * user doesn't want to allocate it */
+ goto out2;
+ }
+ /* we should allocate requested block */
+ } else if (goal == EXT4_EXT_CACHE_EXTENT) {
+ /* block is already allocated */
+ newblock = iblock
+ - le32_to_cpu(newex.ee_block)
+ + ext_pblock(&newex);
+ /* number of remaining blocks in the extent */
+ allocated = le16_to_cpu(newex.ee_len) -
+ (iblock - le32_to_cpu(newex.ee_block));
+ goto out;
+ } else {
+ BUG();
+ }
+ }
+
+ /* find extent for this block */
+ path = ext4_ext_find_extent(inode, iblock, NULL);
+ if (IS_ERR(path)) {
+ err = PTR_ERR(path);
+ path = NULL;
+ goto out2;
+ }
+
+ depth = ext_depth(inode);
+
+ /*
+ * consistent leaf must not be empty;
+ * this situation is possible, though, _during_ tree modification;
+ * this is why assert can't be put in ext4_ext_find_extent()
+ */
+ BUG_ON(path[depth].p_ext == NULL && depth != 0);
+
+ if ((ex = path[depth].p_ext)) {
+ unsigned long ee_block = le32_to_cpu(ex->ee_block);
+ ext4_fsblk_t ee_start = ext_pblock(ex);
+ unsigned short ee_len = le16_to_cpu(ex->ee_len);
+
+ /*
+ * Allow future support for preallocated extents to be added
+ * as an RO_COMPAT feature:
+ * Uninitialized extents are treated as holes, except that
+ * we avoid (fail) allocating new blocks during a write.
+ */
+ if (ee_len > EXT_MAX_LEN)
+ goto out2;
+ /* if found extent covers block, simply return it */
+ if (iblock >= ee_block && iblock < ee_block + ee_len) {
+ newblock = iblock - ee_block + ee_start;
+ /* number of remaining blocks in the extent */
+ allocated = ee_len - (iblock - ee_block);
+ ext_debug("%d fit into %lu:%d -> %llu\n", (int) iblock,
+ ee_block, ee_len, newblock);
+ ext4_ext_put_in_cache(inode, ee_block, ee_len,
+ ee_start, EXT4_EXT_CACHE_EXTENT);
+ goto out;
+ }
+ }
+
+ /*
+ * requested block isn't allocated yet;
+ * we couldn't try to create block if create flag is zero
+ */
+ if (!create) {
+ /* put just found gap into cache to speed up
+ * subsequent requests */
+ ext4_ext_put_gap_in_cache(inode, path, iblock);
+ goto out2;
+ }
+ /*
+ * Okay, we need to do block allocation. Lazily initialize the block
+ * allocation info here if necessary.
+ */
+ if (S_ISREG(inode->i_mode) && (!EXT4_I(inode)->i_block_alloc_info))
+ ext4_init_block_alloc_info(inode);
+
+ /* allocate new block */
+ goal = ext4_ext_find_goal(inode, path, iblock);
+ allocated = max_blocks;
+ newblock = ext4_new_blocks(handle, inode, goal, &allocated, &err);
+ if (!newblock)
+ goto out2;
+ ext_debug("allocate new block: goal %llu, found %llu/%lu\n",
+ goal, newblock, allocated);
+
+ /* try to insert new extent into found leaf and return */
+ newex.ee_block = cpu_to_le32(iblock);
+ ext4_ext_store_pblock(&newex, newblock);
+ newex.ee_len = cpu_to_le16(allocated);
+ err = ext4_ext_insert_extent(handle, inode, path, &newex);
+ if (err)
+ goto out2;
+
+ if (extend_disksize && inode->i_size > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = inode->i_size;
+
+ /* previous routine could use block we allocated */
+ newblock = ext_pblock(&newex);
+ __set_bit(BH_New, &bh_result->b_state);
+
+ ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
+ EXT4_EXT_CACHE_EXTENT);
+out:
+ if (allocated > max_blocks)
+ allocated = max_blocks;
+ ext4_ext_show_leaf(inode, path);
+ __set_bit(BH_Mapped, &bh_result->b_state);
+ bh_result->b_bdev = inode->i_sb->s_bdev;
+ bh_result->b_blocknr = newblock;
+out2:
+ if (path) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+ mutex_unlock(&EXT4_I(inode)->truncate_mutex);
+
+ return err ? err : allocated;
+}
+
+void ext4_ext_truncate(struct inode * inode, struct page *page)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct super_block *sb = inode->i_sb;
+ unsigned long last_block;
+ handle_t *handle;
+ int err = 0;
+
+ /*
+ * probably first extent we're gonna free will be last in block
+ */
+ err = ext4_writepage_trans_blocks(inode) + 3;
+ handle = ext4_journal_start(inode, err);
+ if (IS_ERR(handle)) {
+ if (page) {
+ clear_highpage(page);
+ flush_dcache_page(page);
+ unlock_page(page);
+ page_cache_release(page);
+ }
+ return;
+ }
+
+ if (page)
+ ext4_block_truncate_page(handle, page, mapping, inode->i_size);
+
+ mutex_lock(&EXT4_I(inode)->truncate_mutex);
+ ext4_ext_invalidate_cache(inode);
+
+ /*
+ * TODO: optimization is possible here.
+ * Probably we need not scan at all,
+ * because page truncation is enough.
+ */
+ if (ext4_orphan_add(handle, inode))
+ goto out_stop;
+
+ /* we have to know where to truncate from in crash case */
+ EXT4_I(inode)->i_disksize = inode->i_size;
+ ext4_mark_inode_dirty(handle, inode);
+
+ last_block = (inode->i_size + sb->s_blocksize - 1)
+ >> EXT4_BLOCK_SIZE_BITS(sb);
+ err = ext4_ext_remove_space(inode, last_block);
+
+ /* In a multi-transaction truncate, we only make the final
+ * transaction synchronous. */
+ if (IS_SYNC(inode))
+ handle->h_sync = 1;
+
+out_stop:
+ /*
+ * If this was a simple ftruncate() and the file will remain alive,
+ * then we need to clear up the orphan record which we created above.
+ * However, if this was a real unlink then we were called by
+ * ext4_delete_inode(), and we allow that function to clean up the
+ * orphan info for us.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+
+ mutex_unlock(&EXT4_I(inode)->truncate_mutex);
+ ext4_journal_stop(handle);
+}
+
+/*
+ * ext4_ext_writepage_trans_blocks:
+ * calculate max number of blocks we could modify
+ * in order to allocate new block for an inode
+ */
+int ext4_ext_writepage_trans_blocks(struct inode *inode, int num)
+{
+ int needed;
+
+ needed = ext4_ext_calc_credits_for_insert(inode, NULL);
+
+ /* caller wants to allocate num blocks, but note it includes sb */
+ needed = needed * num - (num - 1);
+
+#ifdef CONFIG_QUOTA
+ needed += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+#endif
+
+ return needed;
+}
+
+EXPORT_SYMBOL(ext4_mark_inode_dirty);
+EXPORT_SYMBOL(ext4_ext_invalidate_cache);
+EXPORT_SYMBOL(ext4_ext_insert_extent);
+EXPORT_SYMBOL(ext4_ext_walk_space);
+EXPORT_SYMBOL(ext4_ext_find_goal);
+EXPORT_SYMBOL(ext4_ext_calc_credits_for_insert);
+
--- /dev/null
+/*
+ * linux/fs/ext4/file.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/fs/minix/file.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * ext4 fs regular file handling primitives
+ *
+ * 64-bit file support on 64-bit platforms by Jakub Jelinek
+ * (jj@sunsite.ms.mff.cuni.cz)
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/ext4_jbd2.h>
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Called when an inode is released. Note that this is different
+ * from ext4_file_open: open gets called at every open, but release
+ * gets called only when /all/ the files are closed.
+ */
+static int ext4_release_file (struct inode * inode, struct file * filp)
+{
+ /* if we are the last writer on the inode, drop the block reservation */
+ if ((filp->f_mode & FMODE_WRITE) &&
+ (atomic_read(&inode->i_writecount) == 1))
+ {
+ mutex_lock(&EXT4_I(inode)->truncate_mutex);
+ ext4_discard_reservation(inode);
+ mutex_unlock(&EXT4_I(inode)->truncate_mutex);
+ }
+ if (is_dx(inode) && filp->private_data)
+ ext4_htree_free_dir_info(filp->private_data);
+
+ return 0;
+}
+
+static ssize_t
+ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_dentry->d_inode;
+ ssize_t ret;
+ int err;
+
+ ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+ /*
+ * Skip flushing if there was an error, or if nothing was written.
+ */
+ if (ret <= 0)
+ return ret;
+
+ /*
+ * If the inode is IS_SYNC, or is O_SYNC and we are doing data
+ * journalling then we need to make sure that we force the transaction
+ * to disk to keep all metadata uptodate synchronously.
+ */
+ if (file->f_flags & O_SYNC) {
+ /*
+ * If we are non-data-journaled, then the dirty data has
+ * already been flushed to backing store by generic_osync_inode,
+ * and the inode has been flushed too if there have been any
+ * modifications other than mere timestamp updates.
+ *
+ * Open question --- do we care about flushing timestamps too
+ * if the inode is IS_SYNC?
+ */
+ if (!ext4_should_journal_data(inode))
+ return ret;
+
+ goto force_commit;
+ }
+
+ /*
+ * So we know that there has been no forced data flush. If the inode
+ * is marked IS_SYNC, we need to force one ourselves.
+ */
+ if (!IS_SYNC(inode))
+ return ret;
+
+ /*
+ * Open question #2 --- should we force data to disk here too? If we
+ * don't, the only impact is that data=writeback filesystems won't
+ * flush data to disk automatically on IS_SYNC, only metadata (but
+ * historically, that is what ext2 has done.)
+ */
+
+force_commit:
+ err = ext4_force_commit(inode->i_sb);
+ if (err)
+ return err;
+ return ret;
+}
+
+const struct file_operations ext4_file_operations = {
+ .llseek = generic_file_llseek,
+ .read = do_sync_read,
+ .write = do_sync_write,
+ .aio_read = generic_file_aio_read,
+ .aio_write = ext4_file_write,
+ .ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ext4_compat_ioctl,
+#endif
+ .mmap = generic_file_mmap,
+ .open = generic_file_open,
+ .release = ext4_release_file,
+ .fsync = ext4_sync_file,
+ .sendfile = generic_file_sendfile,
+ .splice_read = generic_file_splice_read,
+ .splice_write = generic_file_splice_write,
+};
+
+struct inode_operations ext4_file_inode_operations = {
+ .truncate = ext4_truncate,
+ .setattr = ext4_setattr,
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = ext4_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+ .permission = ext4_permission,
+};
+
--- /dev/null
+/*
+ * linux/fs/ext4/fsync.c
+ *
+ * Copyright (C) 1993 Stephen Tweedie (sct@redhat.com)
+ * from
+ * Copyright (C) 1992 Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ * from
+ * linux/fs/minix/truncate.c Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * ext4fs fsync primitive
+ *
+ * Big-endian to little-endian byte-swapping/bitmaps by
+ * David S. Miller (davem@caip.rutgers.edu), 1995
+ *
+ * Removed unnecessary code duplication for little endian machines
+ * and excessive __inline__s.
+ * Andi Kleen, 1997
+ *
+ * Major simplications and cleanup - we only need to do the metadata, because
+ * we can depend on generic_block_fdatasync() to sync the data blocks.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/ext4_jbd2.h>
+
+/*
+ * akpm: A new design for ext4_sync_file().
+ *
+ * This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
+ * There cannot be a transaction open by this task.
+ * Another task could have dirtied this inode. Its data can be in any
+ * state in the journalling system.
+ *
+ * What we do is just kick off a commit and wait on it. This will snapshot the
+ * inode to disk.
+ */
+
+int ext4_sync_file(struct file * file, struct dentry *dentry, int datasync)
+{
+ struct inode *inode = dentry->d_inode;
+ int ret = 0;
+
+ J_ASSERT(ext4_journal_current_handle() == 0);
+
+ /*
+ * data=writeback:
+ * The caller's filemap_fdatawrite()/wait will sync the data.
+ * sync_inode() will sync the metadata
+ *
+ * data=ordered:
+ * The caller's filemap_fdatawrite() will write the data and
+ * sync_inode() will write the inode if it is dirty. Then the caller's
+ * filemap_fdatawait() will wait on the pages.
+ *
+ * data=journal:
+ * filemap_fdatawrite won't do anything (the buffers are clean).
+ * ext4_force_commit will write the file data into the journal and
+ * will wait on that.
+ * filemap_fdatawait() will encounter a ton of newly-dirtied pages
+ * (they were dirtied by commit). But that's OK - the blocks are
+ * safe in-journal, which is all fsync() needs to ensure.
+ */
+ if (ext4_should_journal_data(inode)) {
+ ret = ext4_force_commit(inode->i_sb);
+ goto out;
+ }
+
+ /*
+ * The VFS has written the file data. If the inode is unaltered
+ * then we need not start a commit.
+ */
+ if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) {
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = 0, /* sys_fsync did this */
+ };
+ ret = sync_inode(inode, &wbc);
+ }
+out:
+ return ret;
+}
--- /dev/null
+/*
+ * linux/fs/ext4/hash.c
+ *
+ * Copyright (C) 2002 by Theodore Ts'o
+ *
+ * This file is released under the GPL v2.
+ *
+ * This file may be redistributed under the terms of the GNU Public
+ * License.
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/sched.h>
+#include <linux/ext4_fs.h>
+#include <linux/cryptohash.h>
+
+#define DELTA 0x9E3779B9
+
+static void TEA_transform(__u32 buf[4], __u32 const in[])
+{
+ __u32 sum = 0;
+ __u32 b0 = buf[0], b1 = buf[1];
+ __u32 a = in[0], b = in[1], c = in[2], d = in[3];
+ int n = 16;
+
+ do {
+ sum += DELTA;
+ b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
+ b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
+ } while(--n);
+
+ buf[0] += b0;
+ buf[1] += b1;
+}
+
+
+/* The old legacy hash */
+static __u32 dx_hack_hash (const char *name, int len)
+{
+ __u32 hash0 = 0x12a3fe2d, hash1 = 0x37abe8f9;
+ while (len--) {
+ __u32 hash = hash1 + (hash0 ^ (*name++ * 7152373));
+
+ if (hash & 0x80000000) hash -= 0x7fffffff;
+ hash1 = hash0;
+ hash0 = hash;
+ }
+ return (hash0 << 1);
+}
+
+static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+{
+ __u32 pad, val;
+ int i;
+
+ pad = (__u32)len | ((__u32)len << 8);
+ pad |= pad << 16;
+
+ val = pad;
+ if (len > num*4)
+ len = num * 4;
+ for (i=0; i < len; i++) {
+ if ((i % 4) == 0)
+ val = pad;
+ val = msg[i] + (val << 8);
+ if ((i % 4) == 3) {
+ *buf++ = val;
+ val = pad;
+ num--;
+ }
+ }
+ if (--num >= 0)
+ *buf++ = val;
+ while (--num >= 0)
+ *buf++ = pad;
+}
+
+/*
+ * Returns the hash of a filename. If len is 0 and name is NULL, then
+ * this function can be used to test whether or not a hash version is
+ * supported.
+ *
+ * The seed is an 4 longword (32 bits) "secret" which can be used to
+ * uniquify a hash. If the seed is all zero's, then some default seed
+ * may be used.
+ *
+ * A particular hash version specifies whether or not the seed is
+ * represented, and whether or not the returned hash is 32 bits or 64
+ * bits. 32 bit hashes will return 0 for the minor hash.
+ */
+int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
+{
+ __u32 hash;
+ __u32 minor_hash = 0;
+ const char *p;
+ int i;
+ __u32 in[8], buf[4];
+
+ /* Initialize the default seed for the hash checksum functions */
+ buf[0] = 0x67452301;
+ buf[1] = 0xefcdab89;
+ buf[2] = 0x98badcfe;
+ buf[3] = 0x10325476;
+
+ /* Check to see if the seed is all zero's */
+ if (hinfo->seed) {
+ for (i=0; i < 4; i++) {
+ if (hinfo->seed[i])
+ break;
+ }
+ if (i < 4)
+ memcpy(buf, hinfo->seed, sizeof(buf));
+ }
+
+ switch (hinfo->hash_version) {
+ case DX_HASH_LEGACY:
+ hash = dx_hack_hash(name, len);
+ break;
+ case DX_HASH_HALF_MD4:
+ p = name;
+ while (len > 0) {
+ str2hashbuf(p, len, in, 8);
+ half_md4_transform(buf, in);
+ len -= 32;
+ p += 32;
+ }
+ minor_hash = buf[2];
+ hash = buf[1];
+ break;
+ case DX_HASH_TEA:
+ p = name;
+ while (len > 0) {
+ str2hashbuf(p, len, in, 4);
+ TEA_transform(buf, in);
+ len -= 16;
+ p += 16;
+ }
+ hash = buf[0];
+ minor_hash = buf[1];
+ break;
+ default:
+ hinfo->hash = 0;
+ return -1;
+ }
+ hash = hash & ~1;
+ if (hash == (EXT4_HTREE_EOF << 1))
+ hash = (EXT4_HTREE_EOF-1) << 1;
+ hinfo->hash = hash;
+ hinfo->minor_hash = minor_hash;
+ return 0;
+}
--- /dev/null
+/*
+ * linux/fs/ext4/ialloc.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * BSD ufs-inspired inode and directory allocation by
+ * Stephen Tweedie (sct@redhat.com), 1993
+ * Big-endian to little-endian byte-swapping/bitmaps by
+ * David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/random.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <asm/byteorder.h>
+
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * ialloc.c contains the inodes allocation and deallocation routines
+ */
+
+/*
+ * The free inodes are managed by bitmaps. A file system contains several
+ * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
+ * block for inodes, N blocks for the inode table and data blocks.
+ *
+ * The file system contains group descriptors which are located after the
+ * super block. Each descriptor contains the number of the bitmap block and
+ * the free blocks count in the block.
+ */
+
+
+/*
+ * Read the inode allocation bitmap for a given block_group, reading
+ * into the specified slot in the superblock's bitmap cache.
+ *
+ * Return buffer_head of bitmap on success or NULL.
+ */
+static struct buffer_head *
+read_inode_bitmap(struct super_block * sb, unsigned long block_group)
+{
+ struct ext4_group_desc *desc;
+ struct buffer_head *bh = NULL;
+
+ desc = ext4_get_group_desc(sb, block_group, NULL);
+ if (!desc)
+ goto error_out;
+
+ bh = sb_bread(sb, ext4_inode_bitmap(sb, desc));
+ if (!bh)
+ ext4_error(sb, "read_inode_bitmap",
+ "Cannot read inode bitmap - "
+ "block_group = %lu, inode_bitmap = %llu",
+ block_group, ext4_inode_bitmap(sb, desc));
+error_out:
+ return bh;
+}
+
+/*
+ * NOTE! When we get the inode, we're the only people
+ * that have access to it, and as such there are no
+ * race conditions we have to worry about. The inode
+ * is not on the hash-lists, and it cannot be reached
+ * through the filesystem because the directory entry
+ * has been deleted earlier.
+ *
+ * HOWEVER: we must make sure that we get no aliases,
+ * which means that we have to call "clear_inode()"
+ * _before_ we mark the inode not in use in the inode
+ * bitmaps. Otherwise a newly created file might use
+ * the same inode number (not actually the same pointer
+ * though), and then we'd have two inodes sharing the
+ * same inode number and space on the harddisk.
+ */
+void ext4_free_inode (handle_t *handle, struct inode * inode)
+{
+ struct super_block * sb = inode->i_sb;
+ int is_directory;
+ unsigned long ino;
+ struct buffer_head *bitmap_bh = NULL;
+ struct buffer_head *bh2;
+ unsigned long block_group;
+ unsigned long bit;
+ struct ext4_group_desc * gdp;
+ struct ext4_super_block * es;
+ struct ext4_sb_info *sbi;
+ int fatal = 0, err;
+
+ if (atomic_read(&inode->i_count) > 1) {
+ printk ("ext4_free_inode: inode has count=%d\n",
+ atomic_read(&inode->i_count));
+ return;
+ }
+ if (inode->i_nlink) {
+ printk ("ext4_free_inode: inode has nlink=%d\n",
+ inode->i_nlink);
+ return;
+ }
+ if (!sb) {
+ printk("ext4_free_inode: inode on nonexistent device\n");
+ return;
+ }
+ sbi = EXT4_SB(sb);
+
+ ino = inode->i_ino;
+ ext4_debug ("freeing inode %lu\n", ino);
+
+ /*
+ * Note: we must free any quota before locking the superblock,
+ * as writing the quota to disk may need the lock as well.
+ */
+ DQUOT_INIT(inode);
+ ext4_xattr_delete_inode(handle, inode);
+ DQUOT_FREE_INODE(inode);
+ DQUOT_DROP(inode);
+
+ is_directory = S_ISDIR(inode->i_mode);
+
+ /* Do this BEFORE marking the inode not in use or returning an error */
+ clear_inode (inode);
+
+ es = EXT4_SB(sb)->s_es;
+ if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
+ ext4_error (sb, "ext4_free_inode",
+ "reserved or nonexistent inode %lu", ino);
+ goto error_return;
+ }
+ block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+ bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+ bitmap_bh = read_inode_bitmap(sb, block_group);
+ if (!bitmap_bh)
+ goto error_return;
+
+ BUFFER_TRACE(bitmap_bh, "get_write_access");
+ fatal = ext4_journal_get_write_access(handle, bitmap_bh);
+ if (fatal)
+ goto error_return;
+
+ /* Ok, now we can actually update the inode bitmaps.. */
+ if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
+ bit, bitmap_bh->b_data))
+ ext4_error (sb, "ext4_free_inode",
+ "bit already cleared for inode %lu", ino);
+ else {
+ gdp = ext4_get_group_desc (sb, block_group, &bh2);
+
+ BUFFER_TRACE(bh2, "get_write_access");
+ fatal = ext4_journal_get_write_access(handle, bh2);
+ if (fatal) goto error_return;
+
+ if (gdp) {
+ spin_lock(sb_bgl_lock(sbi, block_group));
+ gdp->bg_free_inodes_count = cpu_to_le16(
+ le16_to_cpu(gdp->bg_free_inodes_count) + 1);
+ if (is_directory)
+ gdp->bg_used_dirs_count = cpu_to_le16(
+ le16_to_cpu(gdp->bg_used_dirs_count) - 1);
+ spin_unlock(sb_bgl_lock(sbi, block_group));
+ percpu_counter_inc(&sbi->s_freeinodes_counter);
+ if (is_directory)
+ percpu_counter_dec(&sbi->s_dirs_counter);
+
+ }
+ BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle, bh2);
+ if (!fatal) fatal = err;
+ }
+ BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+ if (!fatal)
+ fatal = err;
+ sb->s_dirt = 1;
+error_return:
+ brelse(bitmap_bh);
+ ext4_std_error(sb, fatal);
+}
+
+/*
+ * There are two policies for allocating an inode. If the new inode is
+ * a directory, then a forward search is made for a block group with both
+ * free space and a low directory-to-inode ratio; if that fails, then of
+ * the groups with above-average free space, that group with the fewest
+ * directories already is chosen.
+ *
+ * For other inodes, search forward from the parent directory\'s block
+ * group to find a free inode.
+ */
+static int find_group_dir(struct super_block *sb, struct inode *parent)
+{
+ int ngroups = EXT4_SB(sb)->s_groups_count;
+ unsigned int freei, avefreei;
+ struct ext4_group_desc *desc, *best_desc = NULL;
+ struct buffer_head *bh;
+ int group, best_group = -1;
+
+ freei = percpu_counter_read_positive(&EXT4_SB(sb)->s_freeinodes_counter);
+ avefreei = freei / ngroups;
+
+ for (group = 0; group < ngroups; group++) {
+ desc = ext4_get_group_desc (sb, group, &bh);
+ if (!desc || !desc->bg_free_inodes_count)
+ continue;
+ if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+ continue;
+ if (!best_desc ||
+ (le16_to_cpu(desc->bg_free_blocks_count) >
+ le16_to_cpu(best_desc->bg_free_blocks_count))) {
+ best_group = group;
+ best_desc = desc;
+ }
+ }
+ return best_group;
+}
+
+/*
+ * Orlov's allocator for directories.
+ *
+ * We always try to spread first-level directories.
+ *
+ * If there are blockgroups with both free inodes and free blocks counts
+ * not worse than average we return one with smallest directory count.
+ * Otherwise we simply return a random group.
+ *
+ * For the rest rules look so:
+ *
+ * It's OK to put directory into a group unless
+ * it has too many directories already (max_dirs) or
+ * it has too few free inodes left (min_inodes) or
+ * it has too few free blocks left (min_blocks) or
+ * it's already running too large debt (max_debt).
+ * Parent's group is prefered, if it doesn't satisfy these
+ * conditions we search cyclically through the rest. If none
+ * of the groups look good we just look for a group with more
+ * free inodes than average (starting at parent's group).
+ *
+ * Debt is incremented each time we allocate a directory and decremented
+ * when we allocate an inode, within 0--255.
+ */
+
+#define INODE_COST 64
+#define BLOCK_COST 256
+
+static int find_group_orlov(struct super_block *sb, struct inode *parent)
+{
+ int parent_group = EXT4_I(parent)->i_block_group;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ int ngroups = sbi->s_groups_count;
+ int inodes_per_group = EXT4_INODES_PER_GROUP(sb);
+ unsigned int freei, avefreei;
+ ext4_fsblk_t freeb, avefreeb;
+ ext4_fsblk_t blocks_per_dir;
+ unsigned int ndirs;
+ int max_debt, max_dirs, min_inodes;
+ ext4_grpblk_t min_blocks;
+ int group = -1, i;
+ struct ext4_group_desc *desc;
+ struct buffer_head *bh;
+
+ freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter);
+ avefreei = freei / ngroups;
+ freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
+ avefreeb = freeb;
+ do_div(avefreeb, ngroups);
+ ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter);
+
+ if ((parent == sb->s_root->d_inode) ||
+ (EXT4_I(parent)->i_flags & EXT4_TOPDIR_FL)) {
+ int best_ndir = inodes_per_group;
+ int best_group = -1;
+
+ get_random_bytes(&group, sizeof(group));
+ parent_group = (unsigned)group % ngroups;
+ for (i = 0; i < ngroups; i++) {
+ group = (parent_group + i) % ngroups;
+ desc = ext4_get_group_desc (sb, group, &bh);
+ if (!desc || !desc->bg_free_inodes_count)
+ continue;
+ if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir)
+ continue;
+ if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
+ continue;
+ if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb)
+ continue;
+ best_group = group;
+ best_ndir = le16_to_cpu(desc->bg_used_dirs_count);
+ }
+ if (best_group >= 0)
+ return best_group;
+ goto fallback;
+ }
+
+ blocks_per_dir = ext4_blocks_count(es) - freeb;
+ do_div(blocks_per_dir, ndirs);
+
+ max_dirs = ndirs / ngroups + inodes_per_group / 16;
+ min_inodes = avefreei - inodes_per_group / 4;
+ min_blocks = avefreeb - EXT4_BLOCKS_PER_GROUP(sb) / 4;
+
+ max_debt = EXT4_BLOCKS_PER_GROUP(sb);
+ max_debt /= max_t(int, blocks_per_dir, BLOCK_COST);
+ if (max_debt * INODE_COST > inodes_per_group)
+ max_debt = inodes_per_group / INODE_COST;
+ if (max_debt > 255)
+ max_debt = 255;
+ if (max_debt == 0)
+ max_debt = 1;
+
+ for (i = 0; i < ngroups; i++) {
+ group = (parent_group + i) % ngroups;
+ desc = ext4_get_group_desc (sb, group, &bh);
+ if (!desc || !desc->bg_free_inodes_count)
+ continue;
+ if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs)
+ continue;
+ if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes)
+ continue;
+ if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks)
+ continue;
+ return group;
+ }
+
+fallback:
+ for (i = 0; i < ngroups; i++) {
+ group = (parent_group + i) % ngroups;
+ desc = ext4_get_group_desc (sb, group, &bh);
+ if (!desc || !desc->bg_free_inodes_count)
+ continue;
+ if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei)
+ return group;
+ }
+
+ if (avefreei) {
+ /*
+ * The free-inodes counter is approximate, and for really small
+ * filesystems the above test can fail to find any blockgroups
+ */
+ avefreei = 0;
+ goto fallback;
+ }
+
+ return -1;
+}
+
+static int find_group_other(struct super_block *sb, struct inode *parent)
+{
+ int parent_group = EXT4_I(parent)->i_block_group;
+ int ngroups = EXT4_SB(sb)->s_groups_count;
+ struct ext4_group_desc *desc;
+ struct buffer_head *bh;
+ int group, i;
+
+ /*
+ * Try to place the inode in its parent directory
+ */
+ group = parent_group;
+ desc = ext4_get_group_desc (sb, group, &bh);
+ if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
+ le16_to_cpu(desc->bg_free_blocks_count))
+ return group;
+
+ /*
+ * We're going to place this inode in a different blockgroup from its
+ * parent. We want to cause files in a common directory to all land in
+ * the same blockgroup. But we want files which are in a different
+ * directory which shares a blockgroup with our parent to land in a
+ * different blockgroup.
+ *
+ * So add our directory's i_ino into the starting point for the hash.
+ */
+ group = (group + parent->i_ino) % ngroups;
+
+ /*
+ * Use a quadratic hash to find a group with a free inode and some free
+ * blocks.
+ */
+ for (i = 1; i < ngroups; i <<= 1) {
+ group += i;
+ if (group >= ngroups)
+ group -= ngroups;
+ desc = ext4_get_group_desc (sb, group, &bh);
+ if (desc && le16_to_cpu(desc->bg_free_inodes_count) &&
+ le16_to_cpu(desc->bg_free_blocks_count))
+ return group;
+ }
+
+ /*
+ * That failed: try linear search for a free inode, even if that group
+ * has no free blocks.
+ */
+ group = parent_group;
+ for (i = 0; i < ngroups; i++) {
+ if (++group >= ngroups)
+ group = 0;
+ desc = ext4_get_group_desc (sb, group, &bh);
+ if (desc && le16_to_cpu(desc->bg_free_inodes_count))
+ return group;
+ }
+
+ return -1;
+}
+
+/*
+ * There are two policies for allocating an inode. If the new inode is
+ * a directory, then a forward search is made for a block group with both
+ * free space and a low directory-to-inode ratio; if that fails, then of
+ * the groups with above-average free space, that group with the fewest
+ * directories already is chosen.
+ *
+ * For other inodes, search forward from the parent directory's block
+ * group to find a free inode.
+ */
+struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
+{
+ struct super_block *sb;
+ struct buffer_head *bitmap_bh = NULL;
+ struct buffer_head *bh2;
+ int group;
+ unsigned long ino = 0;
+ struct inode * inode;
+ struct ext4_group_desc * gdp = NULL;
+ struct ext4_super_block * es;
+ struct ext4_inode_info *ei;
+ struct ext4_sb_info *sbi;
+ int err = 0;
+ struct inode *ret;
+ int i;
+
+ /* Cannot create files in a deleted directory */
+ if (!dir || !dir->i_nlink)
+ return ERR_PTR(-EPERM);
+
+ sb = dir->i_sb;
+ inode = new_inode(sb);
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+ ei = EXT4_I(inode);
+
+ sbi = EXT4_SB(sb);
+ es = sbi->s_es;
+ if (S_ISDIR(mode)) {
+ if (test_opt (sb, OLDALLOC))
+ group = find_group_dir(sb, dir);
+ else
+ group = find_group_orlov(sb, dir);
+ } else
+ group = find_group_other(sb, dir);
+
+ err = -ENOSPC;
+ if (group == -1)
+ goto out;
+
+ for (i = 0; i < sbi->s_groups_count; i++) {
+ err = -EIO;
+
+ gdp = ext4_get_group_desc(sb, group, &bh2);
+ if (!gdp)
+ goto fail;
+
+ brelse(bitmap_bh);
+ bitmap_bh = read_inode_bitmap(sb, group);
+ if (!bitmap_bh)
+ goto fail;
+
+ ino = 0;
+
+repeat_in_this_group:
+ ino = ext4_find_next_zero_bit((unsigned long *)
+ bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
+ if (ino < EXT4_INODES_PER_GROUP(sb)) {
+
+ BUFFER_TRACE(bitmap_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, bitmap_bh);
+ if (err)
+ goto fail;
+
+ if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
+ ino, bitmap_bh->b_data)) {
+ /* we won it */
+ BUFFER_TRACE(bitmap_bh,
+ "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle,
+ bitmap_bh);
+ if (err)
+ goto fail;
+ goto got;
+ }
+ /* we lost it */
+ jbd2_journal_release_buffer(handle, bitmap_bh);
+
+ if (++ino < EXT4_INODES_PER_GROUP(sb))
+ goto repeat_in_this_group;
+ }
+
+ /*
+ * This case is possible in concurrent environment. It is very
+ * rare. We cannot repeat the find_group_xxx() call because
+ * that will simply return the same blockgroup, because the
+ * group descriptor metadata has not yet been updated.
+ * So we just go onto the next blockgroup.
+ */
+ if (++group == sbi->s_groups_count)
+ group = 0;
+ }
+ err = -ENOSPC;
+ goto out;
+
+got:
+ ino += group * EXT4_INODES_PER_GROUP(sb) + 1;
+ if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
+ ext4_error (sb, "ext4_new_inode",
+ "reserved inode or inode > inodes count - "
+ "block_group = %d, inode=%lu", group, ino);
+ err = -EIO;
+ goto fail;
+ }
+
+ BUFFER_TRACE(bh2, "get_write_access");
+ err = ext4_journal_get_write_access(handle, bh2);
+ if (err) goto fail;
+ spin_lock(sb_bgl_lock(sbi, group));
+ gdp->bg_free_inodes_count =
+ cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
+ if (S_ISDIR(mode)) {
+ gdp->bg_used_dirs_count =
+ cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
+ }
+ spin_unlock(sb_bgl_lock(sbi, group));
+ BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle, bh2);
+ if (err) goto fail;
+
+ percpu_counter_dec(&sbi->s_freeinodes_counter);
+ if (S_ISDIR(mode))
+ percpu_counter_inc(&sbi->s_dirs_counter);
+ sb->s_dirt = 1;
+
+ inode->i_uid = current->fsuid;
+ if (test_opt (sb, GRPID))
+ inode->i_gid = dir->i_gid;
+ else if (dir->i_mode & S_ISGID) {
+ inode->i_gid = dir->i_gid;
+ if (S_ISDIR(mode))
+ mode |= S_ISGID;
+ } else
+ inode->i_gid = current->fsgid;
+ inode->i_mode = mode;
+
+ inode->i_ino = ino;
+ /* This is the optimal IO size (for stat), not the fs block size */
+ inode->i_blocks = 0;
+ inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
+
+ memset(ei->i_data, 0, sizeof(ei->i_data));
+ ei->i_dir_start_lookup = 0;
+ ei->i_disksize = 0;
+
+ ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
+ if (S_ISLNK(mode))
+ ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
+ /* dirsync only applies to directories */
+ if (!S_ISDIR(mode))
+ ei->i_flags &= ~EXT4_DIRSYNC_FL;
+#ifdef EXT4_FRAGMENTS
+ ei->i_faddr = 0;
+ ei->i_frag_no = 0;
+ ei->i_frag_size = 0;
+#endif
+ ei->i_file_acl = 0;
+ ei->i_dir_acl = 0;
+ ei->i_dtime = 0;
+ ei->i_block_alloc_info = NULL;
+ ei->i_block_group = group;
+
+ ext4_set_inode_flags(inode);
+ if (IS_DIRSYNC(inode))
+ handle->h_sync = 1;
+ insert_inode_hash(inode);
+ spin_lock(&sbi->s_next_gen_lock);
+ inode->i_generation = sbi->s_next_generation++;
+ spin_unlock(&sbi->s_next_gen_lock);
+
+ ei->i_state = EXT4_STATE_NEW;
+ ei->i_extra_isize =
+ (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) ?
+ sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE : 0;
+
+ ret = inode;
+ if(DQUOT_ALLOC_INODE(inode)) {
+ err = -EDQUOT;
+ goto fail_drop;
+ }
+
+ err = ext4_init_acl(handle, inode, dir);
+ if (err)
+ goto fail_free_drop;
+
+ err = ext4_init_security(handle,inode, dir);
+ if (err)
+ goto fail_free_drop;
+
+ err = ext4_mark_inode_dirty(handle, inode);
+ if (err) {
+ ext4_std_error(sb, err);
+ goto fail_free_drop;
+ }
+ if (test_opt(sb, EXTENTS)) {
+ EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
+ ext4_ext_tree_init(handle, inode);
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
+ err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ if (err) goto fail;
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ }
+ }
+
+ ext4_debug("allocating inode %lu\n", inode->i_ino);
+ goto really_out;
+fail:
+ ext4_std_error(sb, err);
+out:
+ iput(inode);
+ ret = ERR_PTR(err);
+really_out:
+ brelse(bitmap_bh);
+ return ret;
+
+fail_free_drop:
+ DQUOT_FREE_INODE(inode);
+
+fail_drop:
+ DQUOT_DROP(inode);
+ inode->i_flags |= S_NOQUOTA;
+ inode->i_nlink = 0;
+ iput(inode);
+ brelse(bitmap_bh);
+ return ERR_PTR(err);
+}
+
+/* Verify that we are loading a valid orphan from disk */
+struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
+{
+ unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
+ unsigned long block_group;
+ int bit;
+ struct buffer_head *bitmap_bh = NULL;
+ struct inode *inode = NULL;
+
+ /* Error cases - e2fsck has already cleaned up for us */
+ if (ino > max_ino) {
+ ext4_warning(sb, __FUNCTION__,
+ "bad orphan ino %lu! e2fsck was run?", ino);
+ goto out;
+ }
+
+ block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+ bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+ bitmap_bh = read_inode_bitmap(sb, block_group);
+ if (!bitmap_bh) {
+ ext4_warning(sb, __FUNCTION__,
+ "inode bitmap error for orphan %lu", ino);
+ goto out;
+ }
+
+ /* Having the inode bit set should be a 100% indicator that this
+ * is a valid orphan (no e2fsck run on fs). Orphans also include
+ * inodes that were being truncated, so we can't check i_nlink==0.
+ */
+ if (!ext4_test_bit(bit, bitmap_bh->b_data) ||
+ !(inode = iget(sb, ino)) || is_bad_inode(inode) ||
+ NEXT_ORPHAN(inode) > max_ino) {
+ ext4_warning(sb, __FUNCTION__,
+ "bad orphan inode %lu! e2fsck was run?", ino);
+ printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+ bit, (unsigned long long)bitmap_bh->b_blocknr,
+ ext4_test_bit(bit, bitmap_bh->b_data));
+ printk(KERN_NOTICE "inode=%p\n", inode);
+ if (inode) {
+ printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
+ is_bad_inode(inode));
+ printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
+ NEXT_ORPHAN(inode));
+ printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
+ }
+ /* Avoid freeing blocks if we got a bad deleted inode */
+ if (inode && inode->i_nlink == 0)
+ inode->i_blocks = 0;
+ iput(inode);
+ inode = NULL;
+ }
+out:
+ brelse(bitmap_bh);
+ return inode;
+}
+
+unsigned long ext4_count_free_inodes (struct super_block * sb)
+{
+ unsigned long desc_count;
+ struct ext4_group_desc *gdp;
+ int i;
+#ifdef EXT4FS_DEBUG
+ struct ext4_super_block *es;
+ unsigned long bitmap_count, x;
+ struct buffer_head *bitmap_bh = NULL;
+
+ es = EXT4_SB(sb)->s_es;
+ desc_count = 0;
+ bitmap_count = 0;
+ gdp = NULL;
+ for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ gdp = ext4_get_group_desc (sb, i, NULL);
+ if (!gdp)
+ continue;
+ desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+ brelse(bitmap_bh);
+ bitmap_bh = read_inode_bitmap(sb, i);
+ if (!bitmap_bh)
+ continue;
+
+ x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
+ printk("group %d: stored = %d, counted = %lu\n",
+ i, le16_to_cpu(gdp->bg_free_inodes_count), x);
+ bitmap_count += x;
+ }
+ brelse(bitmap_bh);
+ printk("ext4_count_free_inodes: stored = %u, computed = %lu, %lu\n",
+ le32_to_cpu(es->s_free_inodes_count), desc_count, bitmap_count);
+ return desc_count;
+#else
+ desc_count = 0;
+ for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ gdp = ext4_get_group_desc (sb, i, NULL);
+ if (!gdp)
+ continue;
+ desc_count += le16_to_cpu(gdp->bg_free_inodes_count);
+ cond_resched();
+ }
+ return desc_count;
+#endif
+}
+
+/* Called at mount-time, super-block is locked */
+unsigned long ext4_count_dirs (struct super_block * sb)
+{
+ unsigned long count = 0;
+ int i;
+
+ for (i = 0; i < EXT4_SB(sb)->s_groups_count; i++) {
+ struct ext4_group_desc *gdp = ext4_get_group_desc (sb, i, NULL);
+ if (!gdp)
+ continue;
+ count += le16_to_cpu(gdp->bg_used_dirs_count);
+ }
+ return count;
+}
+
--- /dev/null
+/*
+ * linux/fs/ext4/inode.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/fs/minix/inode.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Goal-directed block allocation by Stephen Tweedie
+ * (sct@redhat.com), 1993, 1998
+ * Big-endian to little-endian byte-swapping/bitmaps by
+ * David S. Miller (davem@caip.rutgers.edu), 1995
+ * 64-bit file support on 64-bit platforms by Jakub Jelinek
+ * (jj@sunsite.ms.mff.cuni.cz)
+ *
+ * Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/jbd2.h>
+#include <linux/smp_lock.h>
+#include <linux/highuid.h>
+#include <linux/pagemap.h>
+#include <linux/quotaops.h>
+#include <linux/string.h>
+#include <linux/buffer_head.h>
+#include <linux/writeback.h>
+#include <linux/mpage.h>
+#include <linux/uio.h>
+#include <linux/bio.h>
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Test whether an inode is a fast symlink.
+ */
+static int ext4_inode_is_fast_symlink(struct inode *inode)
+{
+ int ea_blocks = EXT4_I(inode)->i_file_acl ?
+ (inode->i_sb->s_blocksize >> 9) : 0;
+
+ return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
+}
+
+/*
+ * The ext4 forget function must perform a revoke if we are freeing data
+ * which has been journaled. Metadata (eg. indirect blocks) must be
+ * revoked in all cases.
+ *
+ * "bh" may be NULL: a metadata block may have been freed from memory
+ * but there may still be a record of it in the journal, and that record
+ * still needs to be revoked.
+ */
+int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t blocknr)
+{
+ int err;
+
+ might_sleep();
+
+ BUFFER_TRACE(bh, "enter");
+
+ jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
+ "data mode %lx\n",
+ bh, is_metadata, inode->i_mode,
+ test_opt(inode->i_sb, DATA_FLAGS));
+
+ /* Never use the revoke function if we are doing full data
+ * journaling: there is no need to, and a V1 superblock won't
+ * support it. Otherwise, only skip the revoke on un-journaled
+ * data blocks. */
+
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+ (!is_metadata && !ext4_should_journal_data(inode))) {
+ if (bh) {
+ BUFFER_TRACE(bh, "call jbd2_journal_forget");
+ return ext4_journal_forget(handle, bh);
+ }
+ return 0;
+ }
+
+ /*
+ * data!=journal && (is_metadata || should_journal_data(inode))
+ */
+ BUFFER_TRACE(bh, "call ext4_journal_revoke");
+ err = ext4_journal_revoke(handle, blocknr, bh);
+ if (err)
+ ext4_abort(inode->i_sb, __FUNCTION__,
+ "error %d when attempting revoke", err);
+ BUFFER_TRACE(bh, "exit");
+ return err;
+}
+
+/*
+ * Work out how many blocks we need to proceed with the next chunk of a
+ * truncate transaction.
+ */
+static unsigned long blocks_for_truncate(struct inode *inode)
+{
+ unsigned long needed;
+
+ needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);
+
+ /* Give ourselves just enough room to cope with inodes in which
+ * i_blocks is corrupt: we've seen disk corruptions in the past
+ * which resulted in random data in an inode which looked enough
+ * like a regular file for ext4 to try to delete it. Things
+ * will go a bit crazy if that happens, but at least we should
+ * try not to panic the whole kernel. */
+ if (needed < 2)
+ needed = 2;
+
+ /* But we need to bound the transaction so we don't overflow the
+ * journal. */
+ if (needed > EXT4_MAX_TRANS_DATA)
+ needed = EXT4_MAX_TRANS_DATA;
+
+ return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
+}
+
+/*
+ * Truncate transactions can be complex and absolutely huge. So we need to
+ * be able to restart the transaction at a conventient checkpoint to make
+ * sure we don't overflow the journal.
+ *
+ * start_transaction gets us a new handle for a truncate transaction,
+ * and extend_transaction tries to extend the existing one a bit. If
+ * extend fails, we need to propagate the failure up and restart the
+ * transaction in the top-level truncate loop. --sct
+ */
+static handle_t *start_transaction(struct inode *inode)
+{
+ handle_t *result;
+
+ result = ext4_journal_start(inode, blocks_for_truncate(inode));
+ if (!IS_ERR(result))
+ return result;
+
+ ext4_std_error(inode->i_sb, PTR_ERR(result));
+ return result;
+}
+
+/*
+ * Try to extend this transaction for the purposes of truncation.
+ *
+ * Returns 0 if we managed to create more room. If we can't create more
+ * room, and the transaction must be restarted we return 1.
+ */
+static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
+{
+ if (handle->h_buffer_credits > EXT4_RESERVE_TRANS_BLOCKS)
+ return 0;
+ if (!ext4_journal_extend(handle, blocks_for_truncate(inode)))
+ return 0;
+ return 1;
+}
+
+/*
+ * Restart the transaction associated with *handle. This does a commit,
+ * so before we call here everything must be consistently dirtied against
+ * this transaction.
+ */
+static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
+{
+ jbd_debug(2, "restarting handle %p\n", handle);
+ return ext4_journal_restart(handle, blocks_for_truncate(inode));
+}
+
+/*
+ * Called at the last iput() if i_nlink is zero.
+ */
+void ext4_delete_inode (struct inode * inode)
+{
+ handle_t *handle;
+
+ truncate_inode_pages(&inode->i_data, 0);
+
+ if (is_bad_inode(inode))
+ goto no_delete;
+
+ handle = start_transaction(inode);
+ if (IS_ERR(handle)) {
+ /*
+ * If we're going to skip the normal cleanup, we still need to
+ * make sure that the in-core orphan linked list is properly
+ * cleaned up.
+ */
+ ext4_orphan_del(NULL, inode);
+ goto no_delete;
+ }
+
+ if (IS_SYNC(inode))
+ handle->h_sync = 1;
+ inode->i_size = 0;
+ if (inode->i_blocks)
+ ext4_truncate(inode);
+ /*
+ * Kill off the orphan record which ext4_truncate created.
+ * AKPM: I think this can be inside the above `if'.
+ * Note that ext4_orphan_del() has to be able to cope with the
+ * deletion of a non-existent orphan - this is because we don't
+ * know if ext4_truncate() actually created an orphan record.
+ * (Well, we could do this if we need to, but heck - it works)
+ */
+ ext4_orphan_del(handle, inode);
+ EXT4_I(inode)->i_dtime = get_seconds();
+
+ /*
+ * One subtle ordering requirement: if anything has gone wrong
+ * (transaction abort, IO errors, whatever), then we can still
+ * do these next steps (the fs will already have been marked as
+ * having errors), but we can't free the inode if the mark_dirty
+ * fails.
+ */
+ if (ext4_mark_inode_dirty(handle, inode))
+ /* If that failed, just do the required in-core inode clear. */
+ clear_inode(inode);
+ else
+ ext4_free_inode(handle, inode);
+ ext4_journal_stop(handle);
+ return;
+no_delete:
+ clear_inode(inode); /* We must guarantee clearing of inode... */
+}
+
+typedef struct {
+ __le32 *p;
+ __le32 key;
+ struct buffer_head *bh;
+} Indirect;
+
+static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
+{
+ p->key = *(p->p = v);
+ p->bh = bh;
+}
+
+static int verify_chain(Indirect *from, Indirect *to)
+{
+ while (from <= to && from->key == *from->p)
+ from++;
+ return (from > to);
+}
+
+/**
+ * ext4_block_to_path - parse the block number into array of offsets
+ * @inode: inode in question (we are only interested in its superblock)
+ * @i_block: block number to be parsed
+ * @offsets: array to store the offsets in
+ * @boundary: set this non-zero if the referred-to block is likely to be
+ * followed (on disk) by an indirect block.
+ *
+ * To store the locations of file's data ext4 uses a data structure common
+ * for UNIX filesystems - tree of pointers anchored in the inode, with
+ * data blocks at leaves and indirect blocks in intermediate nodes.
+ * This function translates the block number into path in that tree -
+ * return value is the path length and @offsets[n] is the offset of
+ * pointer to (n+1)th node in the nth one. If @block is out of range
+ * (negative or too large) warning is printed and zero returned.
+ *
+ * Note: function doesn't find node addresses, so no IO is needed. All
+ * we need to know is the capacity of indirect blocks (taken from the
+ * inode->i_sb).
+ */
+
+/*
+ * Portability note: the last comparison (check that we fit into triple
+ * indirect block) is spelled differently, because otherwise on an
+ * architecture with 32-bit longs and 8Kb pages we might get into trouble
+ * if our filesystem had 8Kb blocks. We might use long long, but that would
+ * kill us on x86. Oh, well, at least the sign propagation does not matter -
+ * i_block would have to be negative in the very beginning, so we would not
+ * get there at all.
+ */
+
+static int ext4_block_to_path(struct inode *inode,
+ long i_block, int offsets[4], int *boundary)
+{
+ int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
+ const long direct_blocks = EXT4_NDIR_BLOCKS,
+ indirect_blocks = ptrs,
+ double_blocks = (1 << (ptrs_bits * 2));
+ int n = 0;
+ int final = 0;
+
+ if (i_block < 0) {
+ ext4_warning (inode->i_sb, "ext4_block_to_path", "block < 0");
+ } else if (i_block < direct_blocks) {
+ offsets[n++] = i_block;
+ final = direct_blocks;
+ } else if ( (i_block -= direct_blocks) < indirect_blocks) {
+ offsets[n++] = EXT4_IND_BLOCK;
+ offsets[n++] = i_block;
+ final = ptrs;
+ } else if ((i_block -= indirect_blocks) < double_blocks) {
+ offsets[n++] = EXT4_DIND_BLOCK;
+ offsets[n++] = i_block >> ptrs_bits;
+ offsets[n++] = i_block & (ptrs - 1);
+ final = ptrs;
+ } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) {
+ offsets[n++] = EXT4_TIND_BLOCK;
+ offsets[n++] = i_block >> (ptrs_bits * 2);
+ offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1);
+ offsets[n++] = i_block & (ptrs - 1);
+ final = ptrs;
+ } else {
+ ext4_warning(inode->i_sb, "ext4_block_to_path", "block > big");
+ }
+ if (boundary)
+ *boundary = final - 1 - (i_block & (ptrs - 1));
+ return n;
+}
+
+/**
+ * ext4_get_branch - read the chain of indirect blocks leading to data
+ * @inode: inode in question
+ * @depth: depth of the chain (1 - direct pointer, etc.)
+ * @offsets: offsets of pointers in inode/indirect blocks
+ * @chain: place to store the result
+ * @err: here we store the error value
+ *
+ * Function fills the array of triples <key, p, bh> and returns %NULL
+ * if everything went OK or the pointer to the last filled triple
+ * (incomplete one) otherwise. Upon the return chain[i].key contains
+ * the number of (i+1)-th block in the chain (as it is stored in memory,
+ * i.e. little-endian 32-bit), chain[i].p contains the address of that
+ * number (it points into struct inode for i==0 and into the bh->b_data
+ * for i>0) and chain[i].bh points to the buffer_head of i-th indirect
+ * block for i>0 and NULL for i==0. In other words, it holds the block
+ * numbers of the chain, addresses they were taken from (and where we can
+ * verify that chain did not change) and buffer_heads hosting these
+ * numbers.
+ *
+ * Function stops when it stumbles upon zero pointer (absent block)
+ * (pointer to last triple returned, *@err == 0)
+ * or when it gets an IO error reading an indirect block
+ * (ditto, *@err == -EIO)
+ * or when it notices that chain had been changed while it was reading
+ * (ditto, *@err == -EAGAIN)
+ * or when it reads all @depth-1 indirect blocks successfully and finds
+ * the whole chain, all way to the data (returns %NULL, *err == 0).
+ */
+static Indirect *ext4_get_branch(struct inode *inode, int depth, int *offsets,
+ Indirect chain[4], int *err)
+{
+ struct super_block *sb = inode->i_sb;
+ Indirect *p = chain;
+ struct buffer_head *bh;
+
+ *err = 0;
+ /* i_data is not going away, no lock needed */
+ add_chain (chain, NULL, EXT4_I(inode)->i_data + *offsets);
+ if (!p->key)
+ goto no_block;
+ while (--depth) {
+ bh = sb_bread(sb, le32_to_cpu(p->key));
+ if (!bh)
+ goto failure;
+ /* Reader: pointers */
+ if (!verify_chain(chain, p))
+ goto changed;
+ add_chain(++p, bh, (__le32*)bh->b_data + *++offsets);
+ /* Reader: end */
+ if (!p->key)
+ goto no_block;
+ }
+ return NULL;
+
+changed:
+ brelse(bh);
+ *err = -EAGAIN;
+ goto no_block;
+failure:
+ *err = -EIO;
+no_block:
+ return p;
+}
+
+/**
+ * ext4_find_near - find a place for allocation with sufficient locality
+ * @inode: owner
+ * @ind: descriptor of indirect block.
+ *
+ * This function returns the prefered place for block allocation.
+ * It is used when heuristic for sequential allocation fails.
+ * Rules are:
+ * + if there is a block to the left of our position - allocate near it.
+ * + if pointer will live in indirect block - allocate near that block.
+ * + if pointer will live in inode - allocate in the same
+ * cylinder group.
+ *
+ * In the latter case we colour the starting block by the callers PID to
+ * prevent it from clashing with concurrent allocations for a different inode
+ * in the same block group. The PID is used here so that functionally related
+ * files will be close-by on-disk.
+ *
+ * Caller must make sure that @ind is valid and will stay that way.
+ */
+static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ __le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data;
+ __le32 *p;
+ ext4_fsblk_t bg_start;
+ ext4_grpblk_t colour;
+
+ /* Try to find previous block */
+ for (p = ind->p - 1; p >= start; p--) {
+ if (*p)
+ return le32_to_cpu(*p);
+ }
+
+ /* No such thing, so let's try location of indirect block */
+ if (ind->bh)
+ return ind->bh->b_blocknr;
+
+ /*
+ * It is going to be referred to from the inode itself? OK, just put it
+ * into the same cylinder group then.
+ */
+ bg_start = ext4_group_first_block_no(inode->i_sb, ei->i_block_group);
+ colour = (current->pid % 16) *
+ (EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
+ return bg_start + colour;
+}
+
+/**
+ * ext4_find_goal - find a prefered place for allocation.
+ * @inode: owner
+ * @block: block we want
+ * @chain: chain of indirect blocks
+ * @partial: pointer to the last triple within a chain
+ * @goal: place to store the result.
+ *
+ * Normally this function find the prefered place for block allocation,
+ * stores it in *@goal and returns zero.
+ */
+
+static ext4_fsblk_t ext4_find_goal(struct inode *inode, long block,
+ Indirect chain[4], Indirect *partial)
+{
+ struct ext4_block_alloc_info *block_i;
+
+ block_i = EXT4_I(inode)->i_block_alloc_info;
+
+ /*
+ * try the heuristic for sequential allocation,
+ * failing that at least try to get decent locality.
+ */
+ if (block_i && (block == block_i->last_alloc_logical_block + 1)
+ && (block_i->last_alloc_physical_block != 0)) {
+ return block_i->last_alloc_physical_block + 1;
+ }
+
+ return ext4_find_near(inode, partial);
+}
+
+/**
+ * ext4_blks_to_allocate: Look up the block map and count the number
+ * of direct blocks need to be allocated for the given branch.
+ *
+ * @branch: chain of indirect blocks
+ * @k: number of blocks need for indirect blocks
+ * @blks: number of data blocks to be mapped.
+ * @blocks_to_boundary: the offset in the indirect block
+ *
+ * return the total number of blocks to be allocate, including the
+ * direct and indirect blocks.
+ */
+static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned long blks,
+ int blocks_to_boundary)
+{
+ unsigned long count = 0;
+
+ /*
+ * Simple case, [t,d]Indirect block(s) has not allocated yet
+ * then it's clear blocks on that path have not allocated
+ */
+ if (k > 0) {
+ /* right now we don't handle cross boundary allocation */
+ if (blks < blocks_to_boundary + 1)
+ count += blks;
+ else
+ count += blocks_to_boundary + 1;
+ return count;
+ }
+
+ count++;
+ while (count < blks && count <= blocks_to_boundary &&
+ le32_to_cpu(*(branch[0].p + count)) == 0) {
+ count++;
+ }
+ return count;
+}
+
+/**
+ * ext4_alloc_blocks: multiple allocate blocks needed for a branch
+ * @indirect_blks: the number of blocks need to allocate for indirect
+ * blocks
+ *
+ * @new_blocks: on return it will store the new block numbers for
+ * the indirect blocks(if needed) and the first direct block,
+ * @blks: on return it will store the total number of allocated
+ * direct blocks
+ */
+static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
+ ext4_fsblk_t goal, int indirect_blks, int blks,
+ ext4_fsblk_t new_blocks[4], int *err)
+{
+ int target, i;
+ unsigned long count = 0;
+ int index = 0;
+ ext4_fsblk_t current_block = 0;
+ int ret = 0;
+
+ /*
+ * Here we try to allocate the requested multiple blocks at once,
+ * on a best-effort basis.
+ * To build a branch, we should allocate blocks for
+ * the indirect blocks(if not allocated yet), and at least
+ * the first direct block of this branch. That's the
+ * minimum number of blocks need to allocate(required)
+ */
+ target = blks + indirect_blks;
+
+ while (1) {
+ count = target;
+ /* allocating blocks for indirect blocks and direct blocks */
+ current_block = ext4_new_blocks(handle,inode,goal,&count,err);
+ if (*err)
+ goto failed_out;
+
+ target -= count;
+ /* allocate blocks for indirect blocks */
+ while (index < indirect_blks && count) {
+ new_blocks[index++] = current_block++;
+ count--;
+ }
+
+ if (count > 0)
+ break;
+ }
+
+ /* save the new block number for the first direct block */
+ new_blocks[index] = current_block;
+
+ /* total number of blocks allocated for direct blocks */
+ ret = count;
+ *err = 0;
+ return ret;
+failed_out:
+ for (i = 0; i <index; i++)
+ ext4_free_blocks(handle, inode, new_blocks[i], 1);
+ return ret;
+}
+
+/**
+ * ext4_alloc_branch - allocate and set up a chain of blocks.
+ * @inode: owner
+ * @indirect_blks: number of allocated indirect blocks
+ * @blks: number of allocated direct blocks
+ * @offsets: offsets (in the blocks) to store the pointers to next.
+ * @branch: place to store the chain in.
+ *
+ * This function allocates blocks, zeroes out all but the last one,
+ * links them into chain and (if we are synchronous) writes them to disk.
+ * In other words, it prepares a branch that can be spliced onto the
+ * inode. It stores the information about that chain in the branch[], in
+ * the same format as ext4_get_branch() would do. We are calling it after
+ * we had read the existing part of chain and partial points to the last
+ * triple of that (one with zero ->key). Upon the exit we have the same
+ * picture as after the successful ext4_get_block(), except that in one
+ * place chain is disconnected - *branch->p is still zero (we did not
+ * set the last link), but branch->key contains the number that should
+ * be placed into *branch->p to fill that gap.
+ *
+ * If allocation fails we free all blocks we've allocated (and forget
+ * their buffer_heads) and return the error value the from failed
+ * ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
+ * as described above and return 0.
+ */
+static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
+ int indirect_blks, int *blks, ext4_fsblk_t goal,
+ int *offsets, Indirect *branch)
+{
+ int blocksize = inode->i_sb->s_blocksize;
+ int i, n = 0;
+ int err = 0;
+ struct buffer_head *bh;
+ int num;
+ ext4_fsblk_t new_blocks[4];
+ ext4_fsblk_t current_block;
+
+ num = ext4_alloc_blocks(handle, inode, goal, indirect_blks,
+ *blks, new_blocks, &err);
+ if (err)
+ return err;
+
+ branch[0].key = cpu_to_le32(new_blocks[0]);
+ /*
+ * metadata blocks and data blocks are allocated.
+ */
+ for (n = 1; n <= indirect_blks; n++) {
+ /*
+ * Get buffer_head for parent block, zero it out
+ * and set the pointer to new one, then send
+ * parent to disk.
+ */
+ bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+ branch[n].bh = bh;
+ lock_buffer(bh);
+ BUFFER_TRACE(bh, "call get_create_access");
+ err = ext4_journal_get_create_access(handle, bh);
+ if (err) {
+ unlock_buffer(bh);
+ brelse(bh);
+ goto failed;
+ }
+
+ memset(bh->b_data, 0, blocksize);
+ branch[n].p = (__le32 *) bh->b_data + offsets[n];
+ branch[n].key = cpu_to_le32(new_blocks[n]);
+ *branch[n].p = branch[n].key;
+ if ( n == indirect_blks) {
+ current_block = new_blocks[n];
+ /*
+ * End of chain, update the last new metablock of
+ * the chain to point to the new allocated
+ * data blocks numbers
+ */
+ for (i=1; i < num; i++)
+ *(branch[n].p + i) = cpu_to_le32(++current_block);
+ }
+ BUFFER_TRACE(bh, "marking uptodate");
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+
+ BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle, bh);
+ if (err)
+ goto failed;
+ }
+ *blks = num;
+ return err;
+failed:
+ /* Allocation failed, free what we already allocated */
+ for (i = 1; i <= n ; i++) {
+ BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget");
+ ext4_journal_forget(handle, branch[i].bh);
+ }
+ for (i = 0; i <indirect_blks; i++)
+ ext4_free_blocks(handle, inode, new_blocks[i], 1);
+
+ ext4_free_blocks(handle, inode, new_blocks[i], num);
+
+ return err;
+}
+
+/**
+ * ext4_splice_branch - splice the allocated branch onto inode.
+ * @inode: owner
+ * @block: (logical) number of block we are adding
+ * @chain: chain of indirect blocks (with a missing link - see
+ * ext4_alloc_branch)
+ * @where: location of missing link
+ * @num: number of indirect blocks we are adding
+ * @blks: number of direct blocks we are adding
+ *
+ * This function fills the missing link and does all housekeeping needed in
+ * inode (->i_blocks, etc.). In case of success we end up with the full
+ * chain to new block and return 0.
+ */
+static int ext4_splice_branch(handle_t *handle, struct inode *inode,
+ long block, Indirect *where, int num, int blks)
+{
+ int i;
+ int err = 0;
+ struct ext4_block_alloc_info *block_i;
+ ext4_fsblk_t current_block;
+
+ block_i = EXT4_I(inode)->i_block_alloc_info;
+ /*
+ * If we're splicing into a [td]indirect block (as opposed to the
+ * inode) then we need to get write access to the [td]indirect block
+ * before the splice.
+ */
+ if (where->bh) {
+ BUFFER_TRACE(where->bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, where->bh);
+ if (err)
+ goto err_out;
+ }
+ /* That's it */
+
+ *where->p = where->key;
+
+ /*
+ * Update the host buffer_head or inode to point to more just allocated
+ * direct blocks blocks
+ */
+ if (num == 0 && blks > 1) {
+ current_block = le32_to_cpu(where->key) + 1;
+ for (i = 1; i < blks; i++)
+ *(where->p + i ) = cpu_to_le32(current_block++);
+ }
+
+ /*
+ * update the most recently allocated logical & physical block
+ * in i_block_alloc_info, to assist find the proper goal block for next
+ * allocation
+ */
+ if (block_i) {
+ block_i->last_alloc_logical_block = block + blks - 1;
+ block_i->last_alloc_physical_block =
+ le32_to_cpu(where[num].key) + blks - 1;
+ }
+
+ /* We are done with atomic stuff, now do the rest of housekeeping */
+
+ inode->i_ctime = CURRENT_TIME_SEC;
+ ext4_mark_inode_dirty(handle, inode);
+
+ /* had we spliced it onto indirect block? */
+ if (where->bh) {
+ /*
+ * If we spliced it onto an indirect block, we haven't
+ * altered the inode. Note however that if it is being spliced
+ * onto an indirect block at the very end of the file (the
+ * file is growing) then we *will* alter the inode to reflect
+ * the new i_size. But that is not done here - it is done in
+ * generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
+ */
+ jbd_debug(5, "splicing indirect only\n");
+ BUFFER_TRACE(where->bh, "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle, where->bh);
+ if (err)
+ goto err_out;
+ } else {
+ /*
+ * OK, we spliced it into the inode itself on a direct block.
+ * Inode was dirtied above.
+ */
+ jbd_debug(5, "splicing direct\n");
+ }
+ return err;
+
+err_out:
+ for (i = 1; i <= num; i++) {
+ BUFFER_TRACE(where[i].bh, "call jbd2_journal_forget");
+ ext4_journal_forget(handle, where[i].bh);
+ ext4_free_blocks(handle,inode,le32_to_cpu(where[i-1].key),1);
+ }
+ ext4_free_blocks(handle, inode, le32_to_cpu(where[num].key), blks);
+
+ return err;
+}
+
+/*
+ * Allocation strategy is simple: if we have to allocate something, we will
+ * have to go the whole way to leaf. So let's do it before attaching anything
+ * to tree, set linkage between the newborn blocks, write them if sync is
+ * required, recheck the path, free and repeat if check fails, otherwise
+ * set the last missing link (that will protect us from any truncate-generated
+ * removals - all blocks on the path are immune now) and possibly force the
+ * write on the parent block.
+ * That has a nice additional property: no special recovery from the failed
+ * allocations is needed - we simply release blocks and do not touch anything
+ * reachable from inode.
+ *
+ * `handle' can be NULL if create == 0.
+ *
+ * The BKL may not be held on entry here. Be sure to take it early.
+ * return > 0, # of blocks mapped or allocated.
+ * return = 0, if plain lookup failed.
+ * return < 0, error case.
+ */
+int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
+ sector_t iblock, unsigned long maxblocks,
+ struct buffer_head *bh_result,
+ int create, int extend_disksize)
+{
+ int err = -EIO;
+ int offsets[4];
+ Indirect chain[4];
+ Indirect *partial;
+ ext4_fsblk_t goal;
+ int indirect_blks;
+ int blocks_to_boundary = 0;
+ int depth;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ int count = 0;
+ ext4_fsblk_t first_block = 0;
+
+
+ J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
+ J_ASSERT(handle != NULL || create == 0);
+ depth = ext4_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
+
+ if (depth == 0)
+ goto out;
+
+ partial = ext4_get_branch(inode, depth, offsets, chain, &err);
+
+ /* Simplest case - block found, no allocation needed */
+ if (!partial) {
+ first_block = le32_to_cpu(chain[depth - 1].key);
+ clear_buffer_new(bh_result);
+ count++;
+ /*map more blocks*/
+ while (count < maxblocks && count <= blocks_to_boundary) {
+ ext4_fsblk_t blk;
+
+ if (!verify_chain(chain, partial)) {
+ /*
+ * Indirect block might be removed by
+ * truncate while we were reading it.
+ * Handling of that case: forget what we've
+ * got now. Flag the err as EAGAIN, so it
+ * will reread.
+ */
+ err = -EAGAIN;
+ count = 0;
+ break;
+ }
+ blk = le32_to_cpu(*(chain[depth-1].p + count));
+
+ if (blk == first_block + count)
+ count++;
+ else
+ break;
+ }
+ if (err != -EAGAIN)
+ goto got_it;
+ }
+
+ /* Next simple case - plain lookup or failed read of indirect block */
+ if (!create || err == -EIO)
+ goto cleanup;
+
+ mutex_lock(&ei->truncate_mutex);
+
+ /*
+ * If the indirect block is missing while we are reading
+ * the chain(ext4_get_branch() returns -EAGAIN err), or
+ * if the chain has been changed after we grab the semaphore,
+ * (either because another process truncated this branch, or
+ * another get_block allocated this branch) re-grab the chain to see if
+ * the request block has been allocated or not.
+ *
+ * Since we already block the truncate/other get_block
+ * at this point, we will have the current copy of the chain when we
+ * splice the branch into the tree.
+ */
+ if (err == -EAGAIN || !verify_chain(chain, partial)) {
+ while (partial > chain) {
+ brelse(partial->bh);
+ partial--;
+ }
+ partial = ext4_get_branch(inode, depth, offsets, chain, &err);
+ if (!partial) {
+ count++;
+ mutex_unlock(&ei->truncate_mutex);
+ if (err)
+ goto cleanup;
+ clear_buffer_new(bh_result);
+ goto got_it;
+ }
+ }
+
+ /*
+ * Okay, we need to do block allocation. Lazily initialize the block
+ * allocation info here if necessary
+ */
+ if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
+ ext4_init_block_alloc_info(inode);
+
+ goal = ext4_find_goal(inode, iblock, chain, partial);
+
+ /* the number of blocks need to allocate for [d,t]indirect blocks */
+ indirect_blks = (chain + depth) - partial - 1;
+
+ /*
+ * Next look up the indirect map to count the totoal number of
+ * direct blocks to allocate for this branch.
+ */
+ count = ext4_blks_to_allocate(partial, indirect_blks,
+ maxblocks, blocks_to_boundary);
+ /*
+ * Block out ext4_truncate while we alter the tree
+ */
+ err = ext4_alloc_branch(handle, inode, indirect_blks, &count, goal,
+ offsets + (partial - chain), partial);
+
+ /*
+ * The ext4_splice_branch call will free and forget any buffers
+ * on the new chain if there is a failure, but that risks using
+ * up transaction credits, especially for bitmaps where the
+ * credits cannot be returned. Can we handle this somehow? We
+ * may need to return -EAGAIN upwards in the worst case. --sct
+ */
+ if (!err)
+ err = ext4_splice_branch(handle, inode, iblock,
+ partial, indirect_blks, count);
+ /*
+ * i_disksize growing is protected by truncate_mutex. Don't forget to
+ * protect it if you're about to implement concurrent
+ * ext4_get_block() -bzzz
+ */
+ if (!err && extend_disksize && inode->i_size > ei->i_disksize)
+ ei->i_disksize = inode->i_size;
+ mutex_unlock(&ei->truncate_mutex);
+ if (err)
+ goto cleanup;
+
+ set_buffer_new(bh_result);
+got_it:
+ map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
+ if (count > blocks_to_boundary)
+ set_buffer_boundary(bh_result);
+ err = count;
+ /* Clean up and exit */
+ partial = chain + depth - 1; /* the whole chain */
+cleanup:
+ while (partial > chain) {
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse(partial->bh);
+ partial--;
+ }
+ BUFFER_TRACE(bh_result, "returned");
+out:
+ return err;
+}
+
+#define DIO_CREDITS (EXT4_RESERVE_TRANS_BLOCKS + 32)
+
+static int ext4_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ handle_t *handle = journal_current_handle();
+ int ret = 0;
+ unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
+
+ if (!create)
+ goto get_block; /* A read */
+
+ if (max_blocks == 1)
+ goto get_block; /* A single block get */
+
+ if (handle->h_transaction->t_state == T_LOCKED) {
+ /*
+ * Huge direct-io writes can hold off commits for long
+ * periods of time. Let this commit run.
+ */
+ ext4_journal_stop(handle);
+ handle = ext4_journal_start(inode, DIO_CREDITS);
+ if (IS_ERR(handle))
+ ret = PTR_ERR(handle);
+ goto get_block;
+ }
+
+ if (handle->h_buffer_credits <= EXT4_RESERVE_TRANS_BLOCKS) {
+ /*
+ * Getting low on buffer credits...
+ */
+ ret = ext4_journal_extend(handle, DIO_CREDITS);
+ if (ret > 0) {
+ /*
+ * Couldn't extend the transaction. Start a new one.
+ */
+ ret = ext4_journal_restart(handle, DIO_CREDITS);
+ }
+ }
+
+get_block:
+ if (ret == 0) {
+ ret = ext4_get_blocks_wrap(handle, inode, iblock,
+ max_blocks, bh_result, create, 0);
+ if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+ ret = 0;
+ }
+ }
+ return ret;
+}
+
+/*
+ * `handle' can be NULL if create is zero
+ */
+struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
+ long block, int create, int *errp)
+{
+ struct buffer_head dummy;
+ int fatal = 0, err;
+
+ J_ASSERT(handle != NULL || create == 0);
+
+ dummy.b_state = 0;
+ dummy.b_blocknr = -1000;
+ buffer_trace_init(&dummy.b_history);
+ err = ext4_get_blocks_wrap(handle, inode, block, 1,
+ &dummy, create, 1);
+ /*
+ * ext4_get_blocks_handle() returns number of blocks
+ * mapped. 0 in case of a HOLE.
+ */
+ if (err > 0) {
+ if (err > 1)
+ WARN_ON(1);
+ err = 0;
+ }
+ *errp = err;
+ if (!err && buffer_mapped(&dummy)) {
+ struct buffer_head *bh;
+ bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
+ if (!bh) {
+ *errp = -EIO;
+ goto err;
+ }
+ if (buffer_new(&dummy)) {
+ J_ASSERT(create != 0);
+ J_ASSERT(handle != 0);
+
+ /*
+ * Now that we do not always journal data, we should
+ * keep in mind whether this should always journal the
+ * new buffer as metadata. For now, regular file
+ * writes use ext4_get_block instead, so it's not a
+ * problem.
+ */
+ lock_buffer(bh);
+ BUFFER_TRACE(bh, "call get_create_access");
+ fatal = ext4_journal_get_create_access(handle, bh);
+ if (!fatal && !buffer_uptodate(bh)) {
+ memset(bh->b_data,0,inode->i_sb->s_blocksize);
+ set_buffer_uptodate(bh);
+ }
+ unlock_buffer(bh);
+ BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle, bh);
+ if (!fatal)
+ fatal = err;
+ } else {
+ BUFFER_TRACE(bh, "not a new buffer");
+ }
+ if (fatal) {
+ *errp = fatal;
+ brelse(bh);
+ bh = NULL;
+ }
+ return bh;
+ }
+err:
+ return NULL;
+}
+
+struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
+ int block, int create, int *err)
+{
+ struct buffer_head * bh;
+
+ bh = ext4_getblk(handle, inode, block, create, err);
+ if (!bh)
+ return bh;
+ if (buffer_uptodate(bh))
+ return bh;
+ ll_rw_block(READ_META, 1, &bh);
+ wait_on_buffer(bh);
+ if (buffer_uptodate(bh))
+ return bh;
+ put_bh(bh);
+ *err = -EIO;
+ return NULL;
+}
+
+static int walk_page_buffers( handle_t *handle,
+ struct buffer_head *head,
+ unsigned from,
+ unsigned to,
+ int *partial,
+ int (*fn)( handle_t *handle,
+ struct buffer_head *bh))
+{
+ struct buffer_head *bh;
+ unsigned block_start, block_end;
+ unsigned blocksize = head->b_size;
+ int err, ret = 0;
+ struct buffer_head *next;
+
+ for ( bh = head, block_start = 0;
+ ret == 0 && (bh != head || !block_start);
+ block_start = block_end, bh = next)
+ {
+ next = bh->b_this_page;
+ block_end = block_start + blocksize;
+ if (block_end <= from || block_start >= to) {
+ if (partial && !buffer_uptodate(bh))
+ *partial = 1;
+ continue;
+ }
+ err = (*fn)(handle, bh);
+ if (!ret)
+ ret = err;
+ }
+ return ret;
+}
+
+/*
+ * To preserve ordering, it is essential that the hole instantiation and
+ * the data write be encapsulated in a single transaction. We cannot
+ * close off a transaction and start a new one between the ext4_get_block()
+ * and the commit_write(). So doing the jbd2_journal_start at the start of
+ * prepare_write() is the right place.
+ *
+ * Also, this function can nest inside ext4_writepage() ->
+ * block_write_full_page(). In that case, we *know* that ext4_writepage()
+ * has generated enough buffer credits to do the whole page. So we won't
+ * block on the journal in that case, which is good, because the caller may
+ * be PF_MEMALLOC.
+ *
+ * By accident, ext4 can be reentered when a transaction is open via
+ * quota file writes. If we were to commit the transaction while thus
+ * reentered, there can be a deadlock - we would be holding a quota
+ * lock, and the commit would never complete if another thread had a
+ * transaction open and was blocking on the quota lock - a ranking
+ * violation.
+ *
+ * So what we do is to rely on the fact that jbd2_journal_stop/journal_start
+ * will _not_ run commit under these circumstances because handle->h_ref
+ * is elevated. We'll still have enough credits for the tiny quotafile
+ * write.
+ */
+static int do_journal_get_write_access(handle_t *handle,
+ struct buffer_head *bh)
+{
+ if (!buffer_mapped(bh) || buffer_freed(bh))
+ return 0;
+ return ext4_journal_get_write_access(handle, bh);
+}
+
+static int ext4_prepare_write(struct file *file, struct page *page,
+ unsigned from, unsigned to)
+{
+ struct inode *inode = page->mapping->host;
+ int ret, needed_blocks = ext4_writepage_trans_blocks(inode);
+ handle_t *handle;
+ int retries = 0;
+
+retry:
+ handle = ext4_journal_start(inode, needed_blocks);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
+ ret = nobh_prepare_write(page, from, to, ext4_get_block);
+ else
+ ret = block_prepare_write(page, from, to, ext4_get_block);
+ if (ret)
+ goto prepare_write_failed;
+
+ if (ext4_should_journal_data(inode)) {
+ ret = walk_page_buffers(handle, page_buffers(page),
+ from, to, NULL, do_journal_get_write_access);
+ }
+prepare_write_failed:
+ if (ret)
+ ext4_journal_stop(handle);
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+out:
+ return ret;
+}
+
+int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
+{
+ int err = jbd2_journal_dirty_data(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(__FUNCTION__, __FUNCTION__,
+ bh, handle,err);
+ return err;
+}
+
+/* For commit_write() in data=journal mode */
+static int commit_write_fn(handle_t *handle, struct buffer_head *bh)
+{
+ if (!buffer_mapped(bh) || buffer_freed(bh))
+ return 0;
+ set_buffer_uptodate(bh);
+ return ext4_journal_dirty_metadata(handle, bh);
+}
+
+/*
+ * We need to pick up the new inode size which generic_commit_write gave us
+ * `file' can be NULL - eg, when called from page_symlink().
+ *
+ * ext4 never places buffers on inode->i_mapping->private_list. metadata
+ * buffers are managed internally.
+ */
+static int ext4_ordered_commit_write(struct file *file, struct page *page,
+ unsigned from, unsigned to)
+{
+ handle_t *handle = ext4_journal_current_handle();
+ struct inode *inode = page->mapping->host;
+ int ret = 0, ret2;
+
+ ret = walk_page_buffers(handle, page_buffers(page),
+ from, to, NULL, ext4_journal_dirty_data);
+
+ if (ret == 0) {
+ /*
+ * generic_commit_write() will run mark_inode_dirty() if i_size
+ * changes. So let's piggyback the i_disksize mark_inode_dirty
+ * into that.
+ */
+ loff_t new_i_size;
+
+ new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ if (new_i_size > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = new_i_size;
+ ret = generic_commit_write(file, page, from, to);
+ }
+ ret2 = ext4_journal_stop(handle);
+ if (!ret)
+ ret = ret2;
+ return ret;
+}
+
+static int ext4_writeback_commit_write(struct file *file, struct page *page,
+ unsigned from, unsigned to)
+{
+ handle_t *handle = ext4_journal_current_handle();
+ struct inode *inode = page->mapping->host;
+ int ret = 0, ret2;
+ loff_t new_i_size;
+
+ new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ if (new_i_size > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = new_i_size;
+
+ if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
+ ret = nobh_commit_write(file, page, from, to);
+ else
+ ret = generic_commit_write(file, page, from, to);
+
+ ret2 = ext4_journal_stop(handle);
+ if (!ret)
+ ret = ret2;
+ return ret;
+}
+
+static int ext4_journalled_commit_write(struct file *file,
+ struct page *page, unsigned from, unsigned to)
+{
+ handle_t *handle = ext4_journal_current_handle();
+ struct inode *inode = page->mapping->host;
+ int ret = 0, ret2;
+ int partial = 0;
+ loff_t pos;
+
+ /*
+ * Here we duplicate the generic_commit_write() functionality
+ */
+ pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+
+ ret = walk_page_buffers(handle, page_buffers(page), from,
+ to, &partial, commit_write_fn);
+ if (!partial)
+ SetPageUptodate(page);
+ if (pos > inode->i_size)
+ i_size_write(inode, pos);
+ EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
+ if (inode->i_size > EXT4_I(inode)->i_disksize) {
+ EXT4_I(inode)->i_disksize = inode->i_size;
+ ret2 = ext4_mark_inode_dirty(handle, inode);
+ if (!ret)
+ ret = ret2;
+ }
+ ret2 = ext4_journal_stop(handle);
+ if (!ret)
+ ret = ret2;
+ return ret;
+}
+
+/*
+ * bmap() is special. It gets used by applications such as lilo and by
+ * the swapper to find the on-disk block of a specific piece of data.
+ *
+ * Naturally, this is dangerous if the block concerned is still in the
+ * journal. If somebody makes a swapfile on an ext4 data-journaling
+ * filesystem and enables swap, then they may get a nasty shock when the
+ * data getting swapped to that swapfile suddenly gets overwritten by
+ * the original zero's written out previously to the journal and
+ * awaiting writeback in the kernel's buffer cache.
+ *
+ * So, if we see any bmap calls here on a modified, data-journaled file,
+ * take extra steps to flush any blocks which might be in the cache.
+ */
+static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
+{
+ struct inode *inode = mapping->host;
+ journal_t *journal;
+ int err;
+
+ if (EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
+ /*
+ * This is a REALLY heavyweight approach, but the use of
+ * bmap on dirty files is expected to be extremely rare:
+ * only if we run lilo or swapon on a freshly made file
+ * do we expect this to happen.
+ *
+ * (bmap requires CAP_SYS_RAWIO so this does not
+ * represent an unprivileged user DOS attack --- we'd be
+ * in trouble if mortal users could trigger this path at
+ * will.)
+ *
+ * NB. EXT4_STATE_JDATA is not set on files other than
+ * regular files. If somebody wants to bmap a directory
+ * or symlink and gets confused because the buffer
+ * hasn't yet been flushed to disk, they deserve
+ * everything they get.
+ */
+
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_JDATA;
+ journal = EXT4_JOURNAL(inode);
+ jbd2_journal_lock_updates(journal);
+ err = jbd2_journal_flush(journal);
+ jbd2_journal_unlock_updates(journal);
+
+ if (err)
+ return 0;
+ }
+
+ return generic_block_bmap(mapping,block,ext4_get_block);
+}
+
+static int bget_one(handle_t *handle, struct buffer_head *bh)
+{
+ get_bh(bh);
+ return 0;
+}
+
+static int bput_one(handle_t *handle, struct buffer_head *bh)
+{
+ put_bh(bh);
+ return 0;
+}
+
+static int jbd2_journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
+{
+ if (buffer_mapped(bh))
+ return ext4_journal_dirty_data(handle, bh);
+ return 0;
+}
+
+/*
+ * Note that we always start a transaction even if we're not journalling
+ * data. This is to preserve ordering: any hole instantiation within
+ * __block_write_full_page -> ext4_get_block() should be journalled
+ * along with the data so we don't crash and then get metadata which
+ * refers to old data.
+ *
+ * In all journalling modes block_write_full_page() will start the I/O.
+ *
+ * Problem:
+ *
+ * ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
+ * ext4_writepage()
+ *
+ * Similar for:
+ *
+ * ext4_file_write() -> generic_file_write() -> __alloc_pages() -> ...
+ *
+ * Same applies to ext4_get_block(). We will deadlock on various things like
+ * lock_journal and i_truncate_mutex.
+ *
+ * Setting PF_MEMALLOC here doesn't work - too many internal memory
+ * allocations fail.
+ *
+ * 16May01: If we're reentered then journal_current_handle() will be
+ * non-zero. We simply *return*.
+ *
+ * 1 July 2001: @@@ FIXME:
+ * In journalled data mode, a data buffer may be metadata against the
+ * current transaction. But the same file is part of a shared mapping
+ * and someone does a writepage() on it.
+ *
+ * We will move the buffer onto the async_data list, but *after* it has
+ * been dirtied. So there's a small window where we have dirty data on
+ * BJ_Metadata.
+ *
+ * Note that this only applies to the last partial page in the file. The
+ * bit which block_write_full_page() uses prepare/commit for. (That's
+ * broken code anyway: it's wrong for msync()).
+ *
+ * It's a rare case: affects the final partial page, for journalled data
+ * where the file is subject to bith write() and writepage() in the same
+ * transction. To fix it we'll need a custom block_write_full_page().
+ * We'll probably need that anyway for journalling writepage() output.
+ *
+ * We don't honour synchronous mounts for writepage(). That would be
+ * disastrous. Any write() or metadata operation will sync the fs for
+ * us.
+ *
+ * AKPM2: if all the page's buffers are mapped to disk and !data=journal,
+ * we don't need to open a transaction here.
+ */
+static int ext4_ordered_writepage(struct page *page,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = page->mapping->host;
+ struct buffer_head *page_bufs;
+ handle_t *handle = NULL;
+ int ret = 0;
+ int err;
+
+ J_ASSERT(PageLocked(page));
+
+ /*
+ * We give up here if we're reentered, because it might be for a
+ * different filesystem.
+ */
+ if (ext4_journal_current_handle())
+ goto out_fail;
+
+ handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_fail;
+ }
+
+ if (!page_has_buffers(page)) {
+ create_empty_buffers(page, inode->i_sb->s_blocksize,
+ (1 << BH_Dirty)|(1 << BH_Uptodate));
+ }
+ page_bufs = page_buffers(page);
+ walk_page_buffers(handle, page_bufs, 0,
+ PAGE_CACHE_SIZE, NULL, bget_one);
+
+ ret = block_write_full_page(page, ext4_get_block, wbc);
+
+ /*
+ * The page can become unlocked at any point now, and
+ * truncate can then come in and change things. So we
+ * can't touch *page from now on. But *page_bufs is
+ * safe due to elevated refcount.
+ */
+
+ /*
+ * And attach them to the current transaction. But only if
+ * block_write_full_page() succeeded. Otherwise they are unmapped,
+ * and generally junk.
+ */
+ if (ret == 0) {
+ err = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE,
+ NULL, jbd2_journal_dirty_data_fn);
+ if (!ret)
+ ret = err;
+ }
+ walk_page_buffers(handle, page_bufs, 0,
+ PAGE_CACHE_SIZE, NULL, bput_one);
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ return ret;
+
+out_fail:
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return ret;
+}
+
+static int ext4_writeback_writepage(struct page *page,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = page->mapping->host;
+ handle_t *handle = NULL;
+ int ret = 0;
+ int err;
+
+ if (ext4_journal_current_handle())
+ goto out_fail;
+
+ handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_fail;
+ }
+
+ if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
+ ret = nobh_writepage(page, ext4_get_block, wbc);
+ else
+ ret = block_write_full_page(page, ext4_get_block, wbc);
+
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ return ret;
+
+out_fail:
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+ return ret;
+}
+
+static int ext4_journalled_writepage(struct page *page,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = page->mapping->host;
+ handle_t *handle = NULL;
+ int ret = 0;
+ int err;
+
+ if (ext4_journal_current_handle())
+ goto no_write;
+
+ handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto no_write;
+ }
+
+ if (!page_has_buffers(page) || PageChecked(page)) {
+ /*
+ * It's mmapped pagecache. Add buffers and journal it. There
+ * doesn't seem much point in redirtying the page here.
+ */
+ ClearPageChecked(page);
+ ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
+ ext4_get_block);
+ if (ret != 0) {
+ ext4_journal_stop(handle);
+ goto out_unlock;
+ }
+ ret = walk_page_buffers(handle, page_buffers(page), 0,
+ PAGE_CACHE_SIZE, NULL, do_journal_get_write_access);
+
+ err = walk_page_buffers(handle, page_buffers(page), 0,
+ PAGE_CACHE_SIZE, NULL, commit_write_fn);
+ if (ret == 0)
+ ret = err;
+ EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
+ unlock_page(page);
+ } else {
+ /*
+ * It may be a page full of checkpoint-mode buffers. We don't
+ * really know unless we go poke around in the buffer_heads.
+ * But block_write_full_page will do the right thing.
+ */
+ ret = block_write_full_page(page, ext4_get_block, wbc);
+ }
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+out:
+ return ret;
+
+no_write:
+ redirty_page_for_writepage(wbc, page);
+out_unlock:
+ unlock_page(page);
+ goto out;
+}
+
+static int ext4_readpage(struct file *file, struct page *page)
+{
+ return mpage_readpage(page, ext4_get_block);
+}
+
+static int
+ext4_readpages(struct file *file, struct address_space *mapping,
+ struct list_head *pages, unsigned nr_pages)
+{
+ return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
+}
+
+static void ext4_invalidatepage(struct page *page, unsigned long offset)
+{
+ journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+
+ /*
+ * If it's a full truncate we just forget about the pending dirtying
+ */
+ if (offset == 0)
+ ClearPageChecked(page);
+
+ jbd2_journal_invalidatepage(journal, page, offset);
+}
+
+static int ext4_releasepage(struct page *page, gfp_t wait)
+{
+ journal_t *journal = EXT4_JOURNAL(page->mapping->host);
+
+ WARN_ON(PageChecked(page));
+ if (!page_has_buffers(page))
+ return 0;
+ return jbd2_journal_try_to_free_buffers(journal, page, wait);
+}
+
+/*
+ * If the O_DIRECT write will extend the file then add this inode to the
+ * orphan list. So recovery will truncate it back to the original size
+ * if the machine crashes during the write.
+ *
+ * If the O_DIRECT write is intantiating holes inside i_size and the machine
+ * crashes then stale disk data _may_ be exposed inside the file.
+ */
+static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ handle_t *handle = NULL;
+ ssize_t ret;
+ int orphan = 0;
+ size_t count = iov_length(iov, nr_segs);
+
+ if (rw == WRITE) {
+ loff_t final_size = offset + count;
+
+ handle = ext4_journal_start(inode, DIO_CREDITS);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ if (final_size > inode->i_size) {
+ ret = ext4_orphan_add(handle, inode);
+ if (ret)
+ goto out_stop;
+ orphan = 1;
+ ei->i_disksize = inode->i_size;
+ }
+ }
+
+ ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+ offset, nr_segs,
+ ext4_get_block, NULL);
+
+ /*
+ * Reacquire the handle: ext4_get_block() can restart the transaction
+ */
+ handle = journal_current_handle();
+
+out_stop:
+ if (handle) {
+ int err;
+
+ if (orphan && inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+ if (orphan && ret > 0) {
+ loff_t end = offset + ret;
+ if (end > inode->i_size) {
+ ei->i_disksize = end;
+ i_size_write(inode, end);
+ /*
+ * We're going to return a positive `ret'
+ * here due to non-zero-length I/O, so there's
+ * no way of reporting error returns from
+ * ext4_mark_inode_dirty() to userspace. So
+ * ignore it.
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
+ }
+ err = ext4_journal_stop(handle);
+ if (ret == 0)
+ ret = err;
+ }
+out:
+ return ret;
+}
+
+/*
+ * Pages can be marked dirty completely asynchronously from ext4's journalling
+ * activity. By filemap_sync_pte(), try_to_unmap_one(), etc. We cannot do
+ * much here because ->set_page_dirty is called under VFS locks. The page is
+ * not necessarily locked.
+ *
+ * We cannot just dirty the page and leave attached buffers clean, because the
+ * buffers' dirty state is "definitive". We cannot just set the buffers dirty
+ * or jbddirty because all the journalling code will explode.
+ *
+ * So what we do is to mark the page "pending dirty" and next time writepage
+ * is called, propagate that into the buffers appropriately.
+ */
+static int ext4_journalled_set_page_dirty(struct page *page)
+{
+ SetPageChecked(page);
+ return __set_page_dirty_nobuffers(page);
+}
+
+static const struct address_space_operations ext4_ordered_aops = {
+ .readpage = ext4_readpage,
+ .readpages = ext4_readpages,
+ .writepage = ext4_ordered_writepage,
+ .sync_page = block_sync_page,
+ .prepare_write = ext4_prepare_write,
+ .commit_write = ext4_ordered_commit_write,
+ .bmap = ext4_bmap,
+ .invalidatepage = ext4_invalidatepage,
+ .releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
+ .migratepage = buffer_migrate_page,
+};
+
+static const struct address_space_operations ext4_writeback_aops = {
+ .readpage = ext4_readpage,
+ .readpages = ext4_readpages,
+ .writepage = ext4_writeback_writepage,
+ .sync_page = block_sync_page,
+ .prepare_write = ext4_prepare_write,
+ .commit_write = ext4_writeback_commit_write,
+ .bmap = ext4_bmap,
+ .invalidatepage = ext4_invalidatepage,
+ .releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
+ .migratepage = buffer_migrate_page,
+};
+
+static const struct address_space_operations ext4_journalled_aops = {
+ .readpage = ext4_readpage,
+ .readpages = ext4_readpages,
+ .writepage = ext4_journalled_writepage,
+ .sync_page = block_sync_page,
+ .prepare_write = ext4_prepare_write,
+ .commit_write = ext4_journalled_commit_write,
+ .set_page_dirty = ext4_journalled_set_page_dirty,
+ .bmap = ext4_bmap,
+ .invalidatepage = ext4_invalidatepage,
+ .releasepage = ext4_releasepage,
+};
+
+void ext4_set_aops(struct inode *inode)
+{
+ if (ext4_should_order_data(inode))
+ inode->i_mapping->a_ops = &ext4_ordered_aops;
+ else if (ext4_should_writeback_data(inode))
+ inode->i_mapping->a_ops = &ext4_writeback_aops;
+ else
+ inode->i_mapping->a_ops = &ext4_journalled_aops;
+}
+
+/*
+ * ext4_block_truncate_page() zeroes out a mapping from file offset `from'
+ * up to the end of the block which corresponds to `from'.
+ * This required during truncate. We need to physically zero the tail end
+ * of that block so it doesn't yield old data if the file is later grown.
+ */
+int ext4_block_truncate_page(handle_t *handle, struct page *page,
+ struct address_space *mapping, loff_t from)
+{
+ ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
+ unsigned offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned blocksize, iblock, length, pos;
+ struct inode *inode = mapping->host;
+ struct buffer_head *bh;
+ int err = 0;
+ void *kaddr;
+
+ blocksize = inode->i_sb->s_blocksize;
+ length = blocksize - (offset & (blocksize - 1));
+ iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+ /*
+ * For "nobh" option, we can only work if we don't need to
+ * read-in the page - otherwise we create buffers to do the IO.
+ */
+ if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) &&
+ ext4_should_writeback_data(inode) && PageUptodate(page)) {
+ kaddr = kmap_atomic(page, KM_USER0);
+ memset(kaddr + offset, 0, length);
+ flush_dcache_page(page);
+ kunmap_atomic(kaddr, KM_USER0);
+ set_page_dirty(page);
+ goto unlock;
+ }
+
+ if (!page_has_buffers(page))
+ create_empty_buffers(page, blocksize, 0);
+
+ /* Find the buffer that contains "offset" */
+ bh = page_buffers(page);
+ pos = blocksize;
+ while (offset >= pos) {
+ bh = bh->b_this_page;
+ iblock++;
+ pos += blocksize;
+ }
+
+ err = 0;
+ if (buffer_freed(bh)) {
+ BUFFER_TRACE(bh, "freed: skip");
+ goto unlock;
+ }
+
+ if (!buffer_mapped(bh)) {
+ BUFFER_TRACE(bh, "unmapped");
+ ext4_get_block(inode, iblock, bh, 0);
+ /* unmapped? It's a hole - nothing to do */
+ if (!buffer_mapped(bh)) {
+ BUFFER_TRACE(bh, "still unmapped");
+ goto unlock;
+ }
+ }
+
+ /* Ok, it's mapped. Make sure it's up-to-date */
+ if (PageUptodate(page))
+ set_buffer_uptodate(bh);
+
+ if (!buffer_uptodate(bh)) {
+ err = -EIO;
+ ll_rw_block(READ, 1, &bh);
+ wait_on_buffer(bh);
+ /* Uhhuh. Read error. Complain and punt. */
+ if (!buffer_uptodate(bh))
+ goto unlock;
+ }
+
+ if (ext4_should_journal_data(inode)) {
+ BUFFER_TRACE(bh, "get write access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err)
+ goto unlock;
+ }
+
+ kaddr = kmap_atomic(page, KM_USER0);
+ memset(kaddr + offset, 0, length);
+ flush_dcache_page(page);
+ kunmap_atomic(kaddr, KM_USER0);
+
+ BUFFER_TRACE(bh, "zeroed end of block");
+
+ err = 0;
+ if (ext4_should_journal_data(inode)) {
+ err = ext4_journal_dirty_metadata(handle, bh);
+ } else {
+ if (ext4_should_order_data(inode))
+ err = ext4_journal_dirty_data(handle, bh);
+ mark_buffer_dirty(bh);
+ }
+
+unlock:
+ unlock_page(page);
+ page_cache_release(page);
+ return err;
+}
+
+/*
+ * Probably it should be a library function... search for first non-zero word
+ * or memcmp with zero_page, whatever is better for particular architecture.
+ * Linus?
+ */
+static inline int all_zeroes(__le32 *p, __le32 *q)
+{
+ while (p < q)
+ if (*p++)
+ return 0;
+ return 1;
+}
+
+/**
+ * ext4_find_shared - find the indirect blocks for partial truncation.
+ * @inode: inode in question
+ * @depth: depth of the affected branch
+ * @offsets: offsets of pointers in that branch (see ext4_block_to_path)
+ * @chain: place to store the pointers to partial indirect blocks
+ * @top: place to the (detached) top of branch
+ *
+ * This is a helper function used by ext4_truncate().
+ *
+ * When we do truncate() we may have to clean the ends of several
+ * indirect blocks but leave the blocks themselves alive. Block is
+ * partially truncated if some data below the new i_size is refered
+ * from it (and it is on the path to the first completely truncated
+ * data block, indeed). We have to free the top of that path along
+ * with everything to the right of the path. Since no allocation
+ * past the truncation point is possible until ext4_truncate()
+ * finishes, we may safely do the latter, but top of branch may
+ * require special attention - pageout below the truncation point
+ * might try to populate it.
+ *
+ * We atomically detach the top of branch from the tree, store the
+ * block number of its root in *@top, pointers to buffer_heads of
+ * partially truncated blocks - in @chain[].bh and pointers to
+ * their last elements that should not be removed - in
+ * @chain[].p. Return value is the pointer to last filled element
+ * of @chain.
+ *
+ * The work left to caller to do the actual freeing of subtrees:
+ * a) free the subtree starting from *@top
+ * b) free the subtrees whose roots are stored in
+ * (@chain[i].p+1 .. end of @chain[i].bh->b_data)
+ * c) free the subtrees growing from the inode past the @chain[0].
+ * (no partially truncated stuff there). */
+
+static Indirect *ext4_find_shared(struct inode *inode, int depth,
+ int offsets[4], Indirect chain[4], __le32 *top)
+{
+ Indirect *partial, *p;
+ int k, err;
+
+ *top = 0;
+ /* Make k index the deepest non-null offest + 1 */
+ for (k = depth; k > 1 && !offsets[k-1]; k--)
+ ;
+ partial = ext4_get_branch(inode, k, offsets, chain, &err);
+ /* Writer: pointers */
+ if (!partial)
+ partial = chain + k-1;
+ /*
+ * If the branch acquired continuation since we've looked at it -
+ * fine, it should all survive and (new) top doesn't belong to us.
+ */
+ if (!partial->key && *partial->p)
+ /* Writer: end */
+ goto no_top;
+ for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--)
+ ;
+ /*
+ * OK, we've found the last block that must survive. The rest of our
+ * branch should be detached before unlocking. However, if that rest
+ * of branch is all ours and does not grow immediately from the inode
+ * it's easier to cheat and just decrement partial->p.
+ */
+ if (p == chain + k - 1 && p > chain) {
+ p->p--;
+ } else {
+ *top = *p->p;
+ /* Nope, don't do this in ext4. Must leave the tree intact */
+#if 0
+ *p->p = 0;
+#endif
+ }
+ /* Writer: end */
+
+ while(partial > p) {
+ brelse(partial->bh);
+ partial--;
+ }
+no_top:
+ return partial;
+}
+
+/*
+ * Zero a number of block pointers in either an inode or an indirect block.
+ * If we restart the transaction we must again get write access to the
+ * indirect block for further modification.
+ *
+ * We release `count' blocks on disk, but (last - first) may be greater
+ * than `count' because there can be holes in there.
+ */
+static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t block_to_free,
+ unsigned long count, __le32 *first, __le32 *last)
+{
+ __le32 *p;
+ if (try_to_extend_transaction(handle, inode)) {
+ if (bh) {
+ BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+ ext4_journal_dirty_metadata(handle, bh);
+ }
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_test_restart(handle, inode);
+ if (bh) {
+ BUFFER_TRACE(bh, "retaking write access");
+ ext4_journal_get_write_access(handle, bh);
+ }
+ }
+
+ /*
+ * Any buffers which are on the journal will be in memory. We find
+ * them on the hash table so jbd2_journal_revoke() will run jbd2_journal_forget()
+ * on them. We've already detached each block from the file, so
+ * bforget() in jbd2_journal_forget() should be safe.
+ *
+ * AKPM: turn on bforget in jbd2_journal_forget()!!!
+ */
+ for (p = first; p < last; p++) {
+ u32 nr = le32_to_cpu(*p);
+ if (nr) {
+ struct buffer_head *bh;
+
+ *p = 0;
+ bh = sb_find_get_block(inode->i_sb, nr);
+ ext4_forget(handle, 0, inode, bh, nr);
+ }
+ }
+
+ ext4_free_blocks(handle, inode, block_to_free, count);
+}
+
+/**
+ * ext4_free_data - free a list of data blocks
+ * @handle: handle for this transaction
+ * @inode: inode we are dealing with
+ * @this_bh: indirect buffer_head which contains *@first and *@last
+ * @first: array of block numbers
+ * @last: points immediately past the end of array
+ *
+ * We are freeing all blocks refered from that array (numbers are stored as
+ * little-endian 32-bit) and updating @inode->i_blocks appropriately.
+ *
+ * We accumulate contiguous runs of blocks to free. Conveniently, if these
+ * blocks are contiguous then releasing them at one time will only affect one
+ * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't
+ * actually use a lot of journal space.
+ *
+ * @this_bh will be %NULL if @first and @last point into the inode's direct
+ * block pointers.
+ */
+static void ext4_free_data(handle_t *handle, struct inode *inode,
+ struct buffer_head *this_bh,
+ __le32 *first, __le32 *last)
+{
+ ext4_fsblk_t block_to_free = 0; /* Starting block # of a run */
+ unsigned long count = 0; /* Number of blocks in the run */
+ __le32 *block_to_free_p = NULL; /* Pointer into inode/ind
+ corresponding to
+ block_to_free */
+ ext4_fsblk_t nr; /* Current block # */
+ __le32 *p; /* Pointer into inode/ind
+ for current block */
+ int err;
+
+ if (this_bh) { /* For indirect block */
+ BUFFER_TRACE(this_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, this_bh);
+ /* Important: if we can't update the indirect pointers
+ * to the blocks, we can't free them. */
+ if (err)
+ return;
+ }
+
+ for (p = first; p < last; p++) {
+ nr = le32_to_cpu(*p);
+ if (nr) {
+ /* accumulate blocks to free if they're contiguous */
+ if (count == 0) {
+ block_to_free = nr;
+ block_to_free_p = p;
+ count = 1;
+ } else if (nr == block_to_free + count) {
+ count++;
+ } else {
+ ext4_clear_blocks(handle, inode, this_bh,
+ block_to_free,
+ count, block_to_free_p, p);
+ block_to_free = nr;
+ block_to_free_p = p;
+ count = 1;
+ }
+ }
+ }
+
+ if (count > 0)
+ ext4_clear_blocks(handle, inode, this_bh, block_to_free,
+ count, block_to_free_p, p);
+
+ if (this_bh) {
+ BUFFER_TRACE(this_bh, "call ext4_journal_dirty_metadata");
+ ext4_journal_dirty_metadata(handle, this_bh);
+ }
+}
+
+/**
+ * ext4_free_branches - free an array of branches
+ * @handle: JBD handle for this transaction
+ * @inode: inode we are dealing with
+ * @parent_bh: the buffer_head which contains *@first and *@last
+ * @first: array of block numbers
+ * @last: pointer immediately past the end of array
+ * @depth: depth of the branches to free
+ *
+ * We are freeing all blocks refered from these branches (numbers are
+ * stored as little-endian 32-bit) and updating @inode->i_blocks
+ * appropriately.
+ */
+static void ext4_free_branches(handle_t *handle, struct inode *inode,
+ struct buffer_head *parent_bh,
+ __le32 *first, __le32 *last, int depth)
+{
+ ext4_fsblk_t nr;
+ __le32 *p;
+
+ if (is_handle_aborted(handle))
+ return;
+
+ if (depth--) {
+ struct buffer_head *bh;
+ int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ p = last;
+ while (--p >= first) {
+ nr = le32_to_cpu(*p);
+ if (!nr)
+ continue; /* A hole */
+
+ /* Go read the buffer for the next level down */
+ bh = sb_bread(inode->i_sb, nr);
+
+ /*
+ * A read failure? Report error and clear slot
+ * (should be rare).
+ */
+ if (!bh) {
+ ext4_error(inode->i_sb, "ext4_free_branches",
+ "Read failure, inode=%lu, block=%llu",
+ inode->i_ino, nr);
+ continue;
+ }
+
+ /* This zaps the entire block. Bottom up. */
+ BUFFER_TRACE(bh, "free child branches");
+ ext4_free_branches(handle, inode, bh,
+ (__le32*)bh->b_data,
+ (__le32*)bh->b_data + addr_per_block,
+ depth);
+
+ /*
+ * We've probably journalled the indirect block several
+ * times during the truncate. But it's no longer
+ * needed and we now drop it from the transaction via
+ * jbd2_journal_revoke().
+ *
+ * That's easy if it's exclusively part of this
+ * transaction. But if it's part of the committing
+ * transaction then jbd2_journal_forget() will simply
+ * brelse() it. That means that if the underlying
+ * block is reallocated in ext4_get_block(),
+ * unmap_underlying_metadata() will find this block
+ * and will try to get rid of it. damn, damn.
+ *
+ * If this block has already been committed to the
+ * journal, a revoke record will be written. And
+ * revoke records must be emitted *before* clearing
+ * this block's bit in the bitmaps.
+ */
+ ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
+
+ /*
+ * Everything below this this pointer has been
+ * released. Now let this top-of-subtree go.
+ *
+ * We want the freeing of this indirect block to be
+ * atomic in the journal with the updating of the
+ * bitmap block which owns it. So make some room in
+ * the journal.
+ *
+ * We zero the parent pointer *after* freeing its
+ * pointee in the bitmaps, so if extend_transaction()
+ * for some reason fails to put the bitmap changes and
+ * the release into the same transaction, recovery
+ * will merely complain about releasing a free block,
+ * rather than leaking blocks.
+ */
+ if (is_handle_aborted(handle))
+ return;
+ if (try_to_extend_transaction(handle, inode)) {
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_test_restart(handle, inode);
+ }
+
+ ext4_free_blocks(handle, inode, nr, 1);
+
+ if (parent_bh) {
+ /*
+ * The block which we have just freed is
+ * pointed to by an indirect block: journal it
+ */
+ BUFFER_TRACE(parent_bh, "get_write_access");
+ if (!ext4_journal_get_write_access(handle,
+ parent_bh)){
+ *p = 0;
+ BUFFER_TRACE(parent_bh,
+ "call ext4_journal_dirty_metadata");
+ ext4_journal_dirty_metadata(handle,
+ parent_bh);
+ }
+ }
+ }
+ } else {
+ /* We have reached the bottom of the tree. */
+ BUFFER_TRACE(parent_bh, "free data blocks");
+ ext4_free_data(handle, inode, parent_bh, first, last);
+ }
+}
+
+/*
+ * ext4_truncate()
+ *
+ * We block out ext4_get_block() block instantiations across the entire
+ * transaction, and VFS/VM ensures that ext4_truncate() cannot run
+ * simultaneously on behalf of the same inode.
+ *
+ * As we work through the truncate and commmit bits of it to the journal there
+ * is one core, guiding principle: the file's tree must always be consistent on
+ * disk. We must be able to restart the truncate after a crash.
+ *
+ * The file's tree may be transiently inconsistent in memory (although it
+ * probably isn't), but whenever we close off and commit a journal transaction,
+ * the contents of (the filesystem + the journal) must be consistent and
+ * restartable. It's pretty simple, really: bottom up, right to left (although
+ * left-to-right works OK too).
+ *
+ * Note that at recovery time, journal replay occurs *before* the restart of
+ * truncate against the orphan inode list.
+ *
+ * The committed inode has the new, desired i_size (which is the same as
+ * i_disksize in this case). After a crash, ext4_orphan_cleanup() will see
+ * that this inode's truncate did not complete and it will again call
+ * ext4_truncate() to have another go. So there will be instantiated blocks
+ * to the right of the truncation point in a crashed ext4 filesystem. But
+ * that's fine - as long as they are linked from the inode, the post-crash
+ * ext4_truncate() run will find them and release them.
+ */
+void ext4_truncate(struct inode *inode)
+{
+ handle_t *handle;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ __le32 *i_data = ei->i_data;
+ int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ struct address_space *mapping = inode->i_mapping;
+ int offsets[4];
+ Indirect chain[4];
+ Indirect *partial;
+ __le32 nr = 0;
+ int n;
+ long last_block;
+ unsigned blocksize = inode->i_sb->s_blocksize;
+ struct page *page;
+
+ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ S_ISLNK(inode->i_mode)))
+ return;
+ if (ext4_inode_is_fast_symlink(inode))
+ return;
+ if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+ return;
+
+ /*
+ * We have to lock the EOF page here, because lock_page() nests
+ * outside jbd2_journal_start().
+ */
+ if ((inode->i_size & (blocksize - 1)) == 0) {
+ /* Block boundary? Nothing to do */
+ page = NULL;
+ } else {
+ page = grab_cache_page(mapping,
+ inode->i_size >> PAGE_CACHE_SHIFT);
+ if (!page)
+ return;
+ }
+
+ if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ return ext4_ext_truncate(inode, page);
+
+ handle = start_transaction(inode);
+ if (IS_ERR(handle)) {
+ if (page) {
+ clear_highpage(page);
+ flush_dcache_page(page);
+ unlock_page(page);
+ page_cache_release(page);
+ }
+ return; /* AKPM: return what? */
+ }
+
+ last_block = (inode->i_size + blocksize-1)
+ >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+
+ if (page)
+ ext4_block_truncate_page(handle, page, mapping, inode->i_size);
+
+ n = ext4_block_to_path(inode, last_block, offsets, NULL);
+ if (n == 0)
+ goto out_stop; /* error */
+
+ /*
+ * OK. This truncate is going to happen. We add the inode to the
+ * orphan list, so that if this truncate spans multiple transactions,
+ * and we crash, we will resume the truncate when the filesystem
+ * recovers. It also marks the inode dirty, to catch the new size.
+ *
+ * Implication: the file must always be in a sane, consistent
+ * truncatable state while each transaction commits.
+ */
+ if (ext4_orphan_add(handle, inode))
+ goto out_stop;
+
+ /*
+ * The orphan list entry will now protect us from any crash which
+ * occurs before the truncate completes, so it is now safe to propagate
+ * the new, shorter inode size (held for now in i_size) into the
+ * on-disk inode. We do this via i_disksize, which is the value which
+ * ext4 *really* writes onto the disk inode.
+ */
+ ei->i_disksize = inode->i_size;
+
+ /*
+ * From here we block out all ext4_get_block() callers who want to
+ * modify the block allocation tree.
+ */
+ mutex_lock(&ei->truncate_mutex);
+
+ if (n == 1) { /* direct blocks */
+ ext4_free_data(handle, inode, NULL, i_data+offsets[0],
+ i_data + EXT4_NDIR_BLOCKS);
+ goto do_indirects;
+ }
+
+ partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+ /* Kill the top of shared branch (not detached) */
+ if (nr) {
+ if (partial == chain) {
+ /* Shared branch grows from the inode */
+ ext4_free_branches(handle, inode, NULL,
+ &nr, &nr+1, (chain+n-1) - partial);
+ *partial->p = 0;
+ /*
+ * We mark the inode dirty prior to restart,
+ * and prior to stop. No need for it here.
+ */
+ } else {
+ /* Shared branch grows from an indirect block */
+ BUFFER_TRACE(partial->bh, "get_write_access");
+ ext4_free_branches(handle, inode, partial->bh,
+ partial->p,
+ partial->p+1, (chain+n-1) - partial);
+ }
+ }
+ /* Clear the ends of indirect blocks on the shared branch */
+ while (partial > chain) {
+ ext4_free_branches(handle, inode, partial->bh, partial->p + 1,
+ (__le32*)partial->bh->b_data+addr_per_block,
+ (chain+n-1) - partial);
+ BUFFER_TRACE(partial->bh, "call brelse");
+ brelse (partial->bh);
+ partial--;
+ }
+do_indirects:
+ /* Kill the remaining (whole) subtrees */
+ switch (offsets[0]) {
+ default:
+ nr = i_data[EXT4_IND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
+ i_data[EXT4_IND_BLOCK] = 0;
+ }
+ case EXT4_IND_BLOCK:
+ nr = i_data[EXT4_DIND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
+ i_data[EXT4_DIND_BLOCK] = 0;
+ }
+ case EXT4_DIND_BLOCK:
+ nr = i_data[EXT4_TIND_BLOCK];
+ if (nr) {
+ ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
+ i_data[EXT4_TIND_BLOCK] = 0;
+ }
+ case EXT4_TIND_BLOCK:
+ ;
+ }
+
+ ext4_discard_reservation(inode);
+
+ mutex_unlock(&ei->truncate_mutex);
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
+ ext4_mark_inode_dirty(handle, inode);
+
+ /*
+ * In a multi-transaction truncate, we only make the final transaction
+ * synchronous
+ */
+ if (IS_SYNC(inode))
+ handle->h_sync = 1;
+out_stop:
+ /*
+ * If this was a simple ftruncate(), and the file will remain alive
+ * then we need to clear up the orphan record which we created above.
+ * However, if this was a real unlink then we were called by
+ * ext4_delete_inode(), and we allow that function to clean up the
+ * orphan info for us.
+ */
+ if (inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+
+ ext4_journal_stop(handle);
+}
+
+static ext4_fsblk_t ext4_get_inode_block(struct super_block *sb,
+ unsigned long ino, struct ext4_iloc *iloc)
+{
+ unsigned long desc, group_desc, block_group;
+ unsigned long offset;
+ ext4_fsblk_t block;
+ struct buffer_head *bh;
+ struct ext4_group_desc * gdp;
+
+ if (!ext4_valid_inum(sb, ino)) {
+ /*
+ * This error is already checked for in namei.c unless we are
+ * looking at an NFS filehandle, in which case no error
+ * report is needed
+ */
+ return 0;
+ }
+
+ block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+ if (block_group >= EXT4_SB(sb)->s_groups_count) {
+ ext4_error(sb,"ext4_get_inode_block","group >= groups count");
+ return 0;
+ }
+ smp_rmb();
+ group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
+ desc = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
+ bh = EXT4_SB(sb)->s_group_desc[group_desc];
+ if (!bh) {
+ ext4_error (sb, "ext4_get_inode_block",
+ "Descriptor not loaded");
+ return 0;
+ }
+
+ gdp = (struct ext4_group_desc *)((__u8 *)bh->b_data +
+ desc * EXT4_DESC_SIZE(sb));
+ /*
+ * Figure out the offset within the block group inode table
+ */
+ offset = ((ino - 1) % EXT4_INODES_PER_GROUP(sb)) *
+ EXT4_INODE_SIZE(sb);
+ block = ext4_inode_table(sb, gdp) +
+ (offset >> EXT4_BLOCK_SIZE_BITS(sb));
+
+ iloc->block_group = block_group;
+ iloc->offset = offset & (EXT4_BLOCK_SIZE(sb) - 1);
+ return block;
+}
+
+/*
+ * ext4_get_inode_loc returns with an extra refcount against the inode's
+ * underlying buffer_head on success. If 'in_mem' is true, we have all
+ * data in memory that is needed to recreate the on-disk version of this
+ * inode.
+ */
+static int __ext4_get_inode_loc(struct inode *inode,
+ struct ext4_iloc *iloc, int in_mem)
+{
+ ext4_fsblk_t block;
+ struct buffer_head *bh;
+
+ block = ext4_get_inode_block(inode->i_sb, inode->i_ino, iloc);
+ if (!block)
+ return -EIO;
+
+ bh = sb_getblk(inode->i_sb, block);
+ if (!bh) {
+ ext4_error (inode->i_sb, "ext4_get_inode_loc",
+ "unable to read inode block - "
+ "inode=%lu, block=%llu",
+ inode->i_ino, block);
+ return -EIO;
+ }
+ if (!buffer_uptodate(bh)) {
+ lock_buffer(bh);
+ if (buffer_uptodate(bh)) {
+ /* someone brought it uptodate while we waited */
+ unlock_buffer(bh);
+ goto has_buffer;
+ }
+
+ /*
+ * If we have all information of the inode in memory and this
+ * is the only valid inode in the block, we need not read the
+ * block.
+ */
+ if (in_mem) {
+ struct buffer_head *bitmap_bh;
+ struct ext4_group_desc *desc;
+ int inodes_per_buffer;
+ int inode_offset, i;
+ int block_group;
+ int start;
+
+ block_group = (inode->i_ino - 1) /
+ EXT4_INODES_PER_GROUP(inode->i_sb);
+ inodes_per_buffer = bh->b_size /
+ EXT4_INODE_SIZE(inode->i_sb);
+ inode_offset = ((inode->i_ino - 1) %
+ EXT4_INODES_PER_GROUP(inode->i_sb));
+ start = inode_offset & ~(inodes_per_buffer - 1);
+
+ /* Is the inode bitmap in cache? */
+ desc = ext4_get_group_desc(inode->i_sb,
+ block_group, NULL);
+ if (!desc)
+ goto make_io;
+
+ bitmap_bh = sb_getblk(inode->i_sb,
+ ext4_inode_bitmap(inode->i_sb, desc));
+ if (!bitmap_bh)
+ goto make_io;
+
+ /*
+ * If the inode bitmap isn't in cache then the
+ * optimisation may end up performing two reads instead
+ * of one, so skip it.
+ */
+ if (!buffer_uptodate(bitmap_bh)) {
+ brelse(bitmap_bh);
+ goto make_io;
+ }
+ for (i = start; i < start + inodes_per_buffer; i++) {
+ if (i == inode_offset)
+ continue;
+ if (ext4_test_bit(i, bitmap_bh->b_data))
+ break;
+ }
+ brelse(bitmap_bh);
+ if (i == start + inodes_per_buffer) {
+ /* all other inodes are free, so skip I/O */
+ memset(bh->b_data, 0, bh->b_size);
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+ goto has_buffer;
+ }
+ }
+
+make_io:
+ /*
+ * There are other valid inodes in the buffer, this inode
+ * has in-inode xattrs, or we don't have this inode in memory.
+ * Read the block from disk.
+ */
+ get_bh(bh);
+ bh->b_end_io = end_buffer_read_sync;
+ submit_bh(READ_META, bh);
+ wait_on_buffer(bh);
+ if (!buffer_uptodate(bh)) {
+ ext4_error(inode->i_sb, "ext4_get_inode_loc",
+ "unable to read inode block - "
+ "inode=%lu, block=%llu",
+ inode->i_ino, block);
+ brelse(bh);
+ return -EIO;
+ }
+ }
+has_buffer:
+ iloc->bh = bh;
+ return 0;
+}
+
+int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
+{
+ /* We have all inode data except xattrs in memory here. */
+ return __ext4_get_inode_loc(inode, iloc,
+ !(EXT4_I(inode)->i_state & EXT4_STATE_XATTR));
+}
+
+void ext4_set_inode_flags(struct inode *inode)
+{
+ unsigned int flags = EXT4_I(inode)->i_flags;
+
+ inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+ if (flags & EXT4_SYNC_FL)
+ inode->i_flags |= S_SYNC;
+ if (flags & EXT4_APPEND_FL)
+ inode->i_flags |= S_APPEND;
+ if (flags & EXT4_IMMUTABLE_FL)
+ inode->i_flags |= S_IMMUTABLE;
+ if (flags & EXT4_NOATIME_FL)
+ inode->i_flags |= S_NOATIME;
+ if (flags & EXT4_DIRSYNC_FL)
+ inode->i_flags |= S_DIRSYNC;
+}
+
+void ext4_read_inode(struct inode * inode)
+{
+ struct ext4_iloc iloc;
+ struct ext4_inode *raw_inode;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct buffer_head *bh;
+ int block;
+
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+ ei->i_acl = EXT4_ACL_NOT_CACHED;
+ ei->i_default_acl = EXT4_ACL_NOT_CACHED;
+#endif
+ ei->i_block_alloc_info = NULL;
+
+ if (__ext4_get_inode_loc(inode, &iloc, 0))
+ goto bad_inode;
+ bh = iloc.bh;
+ raw_inode = ext4_raw_inode(&iloc);
+ inode->i_mode = le16_to_cpu(raw_inode->i_mode);
+ inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
+ inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
+ if(!(test_opt (inode->i_sb, NO_UID32))) {
+ inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16;
+ inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16;
+ }
+ inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
+ inode->i_size = le32_to_cpu(raw_inode->i_size);
+ inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime);
+ inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime);
+ inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime);
+ inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0;
+
+ ei->i_state = 0;
+ ei->i_dir_start_lookup = 0;
+ ei->i_dtime = le32_to_cpu(raw_inode->i_dtime);
+ /* We now have enough fields to check if the inode was active or not.
+ * This is needed because nfsd might try to access dead inodes
+ * the test is that same one that e2fsck uses
+ * NeilBrown 1999oct15
+ */
+ if (inode->i_nlink == 0) {
+ if (inode->i_mode == 0 ||
+ !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) {
+ /* this inode is deleted */
+ brelse (bh);
+ goto bad_inode;
+ }
+ /* The only unlinked inodes we let through here have
+ * valid i_mode and are being read by the orphan
+ * recovery code: that's fine, we're about to complete
+ * the process of deleting those. */
+ }
+ inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
+ ei->i_flags = le32_to_cpu(raw_inode->i_flags);
+#ifdef EXT4_FRAGMENTS
+ ei->i_faddr = le32_to_cpu(raw_inode->i_faddr);
+ ei->i_frag_no = raw_inode->i_frag;
+ ei->i_frag_size = raw_inode->i_fsize;
+#endif
+ ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
+ if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
+ cpu_to_le32(EXT4_OS_HURD))
+ ei->i_file_acl |=
+ ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
+ if (!S_ISREG(inode->i_mode)) {
+ ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl);
+ } else {
+ inode->i_size |=
+ ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32;
+ }
+ ei->i_disksize = inode->i_size;
+ inode->i_generation = le32_to_cpu(raw_inode->i_generation);
+ ei->i_block_group = iloc.block_group;
+ /*
+ * NOTE! The in-memory inode i_data array is in little-endian order
+ * even on big-endian machines: we do NOT byteswap the block numbers!
+ */
+ for (block = 0; block < EXT4_N_BLOCKS; block++)
+ ei->i_data[block] = raw_inode->i_block[block];
+ INIT_LIST_HEAD(&ei->i_orphan);
+
+ if (inode->i_ino >= EXT4_FIRST_INO(inode->i_sb) + 1 &&
+ EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
+ /*
+ * When mke2fs creates big inodes it does not zero out
+ * the unused bytes above EXT4_GOOD_OLD_INODE_SIZE,
+ * so ignore those first few inodes.
+ */
+ ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
+ if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
+ EXT4_INODE_SIZE(inode->i_sb))
+ goto bad_inode;
+ if (ei->i_extra_isize == 0) {
+ /* The extra space is currently unused. Use it. */
+ ei->i_extra_isize = sizeof(struct ext4_inode) -
+ EXT4_GOOD_OLD_INODE_SIZE;
+ } else {
+ __le32 *magic = (void *)raw_inode +
+ EXT4_GOOD_OLD_INODE_SIZE +
+ ei->i_extra_isize;
+ if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC))
+ ei->i_state |= EXT4_STATE_XATTR;
+ }
+ } else
+ ei->i_extra_isize = 0;
+
+ if (S_ISREG(inode->i_mode)) {
+ inode->i_op = &ext4_file_inode_operations;
+ inode->i_fop = &ext4_file_operations;
+ ext4_set_aops(inode);
+ } else if (S_ISDIR(inode->i_mode)) {
+ inode->i_op = &ext4_dir_inode_operations;
+ inode->i_fop = &ext4_dir_operations;
+ } else if (S_ISLNK(inode->i_mode)) {
+ if (ext4_inode_is_fast_symlink(inode))
+ inode->i_op = &ext4_fast_symlink_inode_operations;
+ else {
+ inode->i_op = &ext4_symlink_inode_operations;
+ ext4_set_aops(inode);
+ }
+ } else {
+ inode->i_op = &ext4_special_inode_operations;
+ if (raw_inode->i_block[0])
+ init_special_inode(inode, inode->i_mode,
+ old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
+ else
+ init_special_inode(inode, inode->i_mode,
+ new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
+ }
+ brelse (iloc.bh);
+ ext4_set_inode_flags(inode);
+ return;
+
+bad_inode:
+ make_bad_inode(inode);
+ return;
+}
+
+/*
+ * Post the struct inode info into an on-disk inode location in the
+ * buffer-cache. This gobbles the caller's reference to the
+ * buffer_head in the inode location struct.
+ *
+ * The caller must have write access to iloc->bh.
+ */
+static int ext4_do_update_inode(handle_t *handle,
+ struct inode *inode,
+ struct ext4_iloc *iloc)
+{
+ struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct buffer_head *bh = iloc->bh;
+ int err = 0, rc, block;
+
+ /* For fields not not tracking in the in-memory inode,
+ * initialise them to zero for new inodes. */
+ if (ei->i_state & EXT4_STATE_NEW)
+ memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
+
+ raw_inode->i_mode = cpu_to_le16(inode->i_mode);
+ if(!(test_opt(inode->i_sb, NO_UID32))) {
+ raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
+ raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid));
+/*
+ * Fix up interoperability with old kernels. Otherwise, old inodes get
+ * re-used with the upper 16 bits of the uid/gid intact
+ */
+ if(!ei->i_dtime) {
+ raw_inode->i_uid_high =
+ cpu_to_le16(high_16_bits(inode->i_uid));
+ raw_inode->i_gid_high =
+ cpu_to_le16(high_16_bits(inode->i_gid));
+ } else {
+ raw_inode->i_uid_high = 0;
+ raw_inode->i_gid_high = 0;
+ }
+ } else {
+ raw_inode->i_uid_low =
+ cpu_to_le16(fs_high2lowuid(inode->i_uid));
+ raw_inode->i_gid_low =
+ cpu_to_le16(fs_high2lowgid(inode->i_gid));
+ raw_inode->i_uid_high = 0;
+ raw_inode->i_gid_high = 0;
+ }
+ raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
+ raw_inode->i_size = cpu_to_le32(ei->i_disksize);
+ raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
+ raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
+ raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);
+ raw_inode->i_blocks = cpu_to_le32(inode->i_blocks);
+ raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
+ raw_inode->i_flags = cpu_to_le32(ei->i_flags);
+#ifdef EXT4_FRAGMENTS
+ raw_inode->i_faddr = cpu_to_le32(ei->i_faddr);
+ raw_inode->i_frag = ei->i_frag_no;
+ raw_inode->i_fsize = ei->i_frag_size;
+#endif
+ if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
+ cpu_to_le32(EXT4_OS_HURD))
+ raw_inode->i_file_acl_high =
+ cpu_to_le16(ei->i_file_acl >> 32);
+ raw_inode->i_file_acl = cpu_to_le32(ei->i_file_acl);
+ if (!S_ISREG(inode->i_mode)) {
+ raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl);
+ } else {
+ raw_inode->i_size_high =
+ cpu_to_le32(ei->i_disksize >> 32);
+ if (ei->i_disksize > 0x7fffffffULL) {
+ struct super_block *sb = inode->i_sb;
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
+ EXT4_SB(sb)->s_es->s_rev_level ==
+ cpu_to_le32(EXT4_GOOD_OLD_REV)) {
+ /* If this is the first large file
+ * created, add a flag to the superblock.
+ */
+ err = ext4_journal_get_write_access(handle,
+ EXT4_SB(sb)->s_sbh);
+ if (err)
+ goto out_brelse;
+ ext4_update_dynamic_rev(sb);
+ EXT4_SET_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
+ sb->s_dirt = 1;
+ handle->h_sync = 1;
+ err = ext4_journal_dirty_metadata(handle,
+ EXT4_SB(sb)->s_sbh);
+ }
+ }
+ }
+ raw_inode->i_generation = cpu_to_le32(inode->i_generation);
+ if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
+ if (old_valid_dev(inode->i_rdev)) {
+ raw_inode->i_block[0] =
+ cpu_to_le32(old_encode_dev(inode->i_rdev));
+ raw_inode->i_block[1] = 0;
+ } else {
+ raw_inode->i_block[0] = 0;
+ raw_inode->i_block[1] =
+ cpu_to_le32(new_encode_dev(inode->i_rdev));
+ raw_inode->i_block[2] = 0;
+ }
+ } else for (block = 0; block < EXT4_N_BLOCKS; block++)
+ raw_inode->i_block[block] = ei->i_data[block];
+
+ if (ei->i_extra_isize)
+ raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
+
+ BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+ rc = ext4_journal_dirty_metadata(handle, bh);
+ if (!err)
+ err = rc;
+ ei->i_state &= ~EXT4_STATE_NEW;
+
+out_brelse:
+ brelse (bh);
+ ext4_std_error(inode->i_sb, err);
+ return err;
+}
+
+/*
+ * ext4_write_inode()
+ *
+ * We are called from a few places:
+ *
+ * - Within generic_file_write() for O_SYNC files.
+ * Here, there will be no transaction running. We wait for any running
+ * trasnaction to commit.
+ *
+ * - Within sys_sync(), kupdate and such.
+ * We wait on commit, if tol to.
+ *
+ * - Within prune_icache() (PF_MEMALLOC == true)
+ * Here we simply return. We can't afford to block kswapd on the
+ * journal commit.
+ *
+ * In all cases it is actually safe for us to return without doing anything,
+ * because the inode has been copied into a raw inode buffer in
+ * ext4_mark_inode_dirty(). This is a correctness thing for O_SYNC and for
+ * knfsd.
+ *
+ * Note that we are absolutely dependent upon all inode dirtiers doing the
+ * right thing: they *must* call mark_inode_dirty() after dirtying info in
+ * which we are interested.
+ *
+ * It would be a bug for them to not do this. The code:
+ *
+ * mark_inode_dirty(inode)
+ * stuff();
+ * inode->i_size = expr;
+ *
+ * is in error because a kswapd-driven write_inode() could occur while
+ * `stuff()' is running, and the new i_size will be lost. Plus the inode
+ * will no longer be on the superblock's dirty inode list.
+ */
+int ext4_write_inode(struct inode *inode, int wait)
+{
+ if (current->flags & PF_MEMALLOC)
+ return 0;
+
+ if (ext4_journal_current_handle()) {
+ jbd_debug(0, "called recursively, non-PF_MEMALLOC!\n");
+ dump_stack();
+ return -EIO;
+ }
+
+ if (!wait)
+ return 0;
+
+ return ext4_force_commit(inode->i_sb);
+}
+
+/*
+ * ext4_setattr()
+ *
+ * Called from notify_change.
+ *
+ * We want to trap VFS attempts to truncate the file as soon as
+ * possible. In particular, we want to make sure that when the VFS
+ * shrinks i_size, we put the inode on the orphan list and modify
+ * i_disksize immediately, so that during the subsequent flushing of
+ * dirty pages and freeing of disk blocks, we can guarantee that any
+ * commit will leave the blocks being flushed in an unused state on
+ * disk. (On recovery, the inode will get truncated and the blocks will
+ * be freed, so we have a strong guarantee that no future commit will
+ * leave these blocks visible to the user.)
+ *
+ * Called with inode->sem down.
+ */
+int ext4_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ struct inode *inode = dentry->d_inode;
+ int error, rc = 0;
+ const unsigned int ia_valid = attr->ia_valid;
+
+ error = inode_change_ok(inode, attr);
+ if (error)
+ return error;
+
+ if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
+ (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
+ handle_t *handle;
+
+ /* (user+group)*(old+new) structure, inode write (sb,
+ * inode block, ? - but truncate inode update has it) */
+ handle = ext4_journal_start(inode, 2*(EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)+
+ EXT4_QUOTA_DEL_BLOCKS(inode->i_sb))+3);
+ if (IS_ERR(handle)) {
+ error = PTR_ERR(handle);
+ goto err_out;
+ }
+ error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0;
+ if (error) {
+ ext4_journal_stop(handle);
+ return error;
+ }
+ /* Update corresponding info in inode so that everything is in
+ * one transaction */
+ if (attr->ia_valid & ATTR_UID)
+ inode->i_uid = attr->ia_uid;
+ if (attr->ia_valid & ATTR_GID)
+ inode->i_gid = attr->ia_gid;
+ error = ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+ }
+
+ if (S_ISREG(inode->i_mode) &&
+ attr->ia_valid & ATTR_SIZE && attr->ia_size < inode->i_size) {
+ handle_t *handle;
+
+ handle = ext4_journal_start(inode, 3);
+ if (IS_ERR(handle)) {
+ error = PTR_ERR(handle);
+ goto err_out;
+ }
+
+ error = ext4_orphan_add(handle, inode);
+ EXT4_I(inode)->i_disksize = attr->ia_size;
+ rc = ext4_mark_inode_dirty(handle, inode);
+ if (!error)
+ error = rc;
+ ext4_journal_stop(handle);
+ }
+
+ rc = inode_setattr(inode, attr);
+
+ /* If inode_setattr's call to ext4_truncate failed to get a
+ * transaction handle at all, we need to clean up the in-core
+ * orphan list manually. */
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+
+ if (!rc && (ia_valid & ATTR_MODE))
+ rc = ext4_acl_chmod(inode);
+
+err_out:
+ ext4_std_error(inode->i_sb, error);
+ if (!error)
+ error = rc;
+ return error;
+}
+
+
+/*
+ * How many blocks doth make a writepage()?
+ *
+ * With N blocks per page, it may be:
+ * N data blocks
+ * 2 indirect block
+ * 2 dindirect
+ * 1 tindirect
+ * N+5 bitmap blocks (from the above)
+ * N+5 group descriptor summary blocks
+ * 1 inode block
+ * 1 superblock.
+ * 2 * EXT4_SINGLEDATA_TRANS_BLOCKS for the quote files
+ *
+ * 3 * (N + 5) + 2 + 2 * EXT4_SINGLEDATA_TRANS_BLOCKS
+ *
+ * With ordered or writeback data it's the same, less the N data blocks.
+ *
+ * If the inode's direct blocks can hold an integral number of pages then a
+ * page cannot straddle two indirect blocks, and we can only touch one indirect
+ * and dindirect block, and the "5" above becomes "3".
+ *
+ * This still overestimates under most circumstances. If we were to pass the
+ * start and end offsets in here as well we could do block_to_path() on each
+ * block and work out the exact number of indirects which are touched. Pah.
+ */
+
+int ext4_writepage_trans_blocks(struct inode *inode)
+{
+ int bpp = ext4_journal_blocks_per_page(inode);
+ int indirects = (EXT4_NDIR_BLOCKS % bpp) ? 5 : 3;
+ int ret;
+
+ if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ return ext4_ext_writepage_trans_blocks(inode, bpp);
+
+ if (ext4_should_journal_data(inode))
+ ret = 3 * (bpp + indirects) + 2;
+ else
+ ret = 2 * (bpp + indirects) + 2;
+
+#ifdef CONFIG_QUOTA
+ /* We know that structure was already allocated during DQUOT_INIT so
+ * we will be updating only the data blocks + inodes */
+ ret += 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+#endif
+
+ return ret;
+}
+
+/*
+ * The caller must have previously called ext4_reserve_inode_write().
+ * Give this, we know that the caller already has write access to iloc->bh.
+ */
+int ext4_mark_iloc_dirty(handle_t *handle,
+ struct inode *inode, struct ext4_iloc *iloc)
+{
+ int err = 0;
+
+ /* the do_update_inode consumes one bh->b_count */
+ get_bh(iloc->bh);
+
+ /* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
+ err = ext4_do_update_inode(handle, inode, iloc);
+ put_bh(iloc->bh);
+ return err;
+}
+
+/*
+ * On success, We end up with an outstanding reference count against
+ * iloc->bh. This _must_ be cleaned up later.
+ */
+
+int
+ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
+ struct ext4_iloc *iloc)
+{
+ int err = 0;
+ if (handle) {
+ err = ext4_get_inode_loc(inode, iloc);
+ if (!err) {
+ BUFFER_TRACE(iloc->bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, iloc->bh);
+ if (err) {
+ brelse(iloc->bh);
+ iloc->bh = NULL;
+ }
+ }
+ }
+ ext4_std_error(inode->i_sb, err);
+ return err;
+}
+
+/*
+ * What we do here is to mark the in-core inode as clean with respect to inode
+ * dirtiness (it may still be data-dirty).
+ * This means that the in-core inode may be reaped by prune_icache
+ * without having to perform any I/O. This is a very good thing,
+ * because *any* task may call prune_icache - even ones which
+ * have a transaction open against a different journal.
+ *
+ * Is this cheating? Not really. Sure, we haven't written the
+ * inode out, but prune_icache isn't a user-visible syncing function.
+ * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
+ * we start and wait on commits.
+ *
+ * Is this efficient/effective? Well, we're being nice to the system
+ * by cleaning up our inodes proactively so they can be reaped
+ * without I/O. But we are potentially leaving up to five seconds'
+ * worth of inodes floating about which prune_icache wants us to
+ * write out. One way to fix that would be to get prune_icache()
+ * to do a write_super() to free up some memory. It has the desired
+ * effect.
+ */
+int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
+{
+ struct ext4_iloc iloc;
+ int err;
+
+ might_sleep();
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (!err)
+ err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+ return err;
+}
+
+/*
+ * ext4_dirty_inode() is called from __mark_inode_dirty()
+ *
+ * We're really interested in the case where a file is being extended.
+ * i_size has been changed by generic_commit_write() and we thus need
+ * to include the updated inode in the current transaction.
+ *
+ * Also, DQUOT_ALLOC_SPACE() will always dirty the inode when blocks
+ * are allocated to the file.
+ *
+ * If the inode is marked synchronous, we don't honour that here - doing
+ * so would cause a commit on atime updates, which we don't bother doing.
+ * We handle synchronous inodes at the highest possible level.
+ */
+void ext4_dirty_inode(struct inode *inode)
+{
+ handle_t *current_handle = ext4_journal_current_handle();
+ handle_t *handle;
+
+ handle = ext4_journal_start(inode, 2);
+ if (IS_ERR(handle))
+ goto out;
+ if (current_handle &&
+ current_handle->h_transaction != handle->h_transaction) {
+ /* This task has a transaction open against a different fs */
+ printk(KERN_EMERG "%s: transactions do not match!\n",
+ __FUNCTION__);
+ } else {
+ jbd_debug(5, "marking dirty. outer handle=%p\n",
+ current_handle);
+ ext4_mark_inode_dirty(handle, inode);
+ }
+ ext4_journal_stop(handle);
+out:
+ return;
+}
+
+#if 0
+/*
+ * Bind an inode's backing buffer_head into this transaction, to prevent
+ * it from being flushed to disk early. Unlike
+ * ext4_reserve_inode_write, this leaves behind no bh reference and
+ * returns no iloc structure, so the caller needs to repeat the iloc
+ * lookup to mark the inode dirty later.
+ */
+static int ext4_pin_inode(handle_t *handle, struct inode *inode)
+{
+ struct ext4_iloc iloc;
+
+ int err = 0;
+ if (handle) {
+ err = ext4_get_inode_loc(inode, &iloc);
+ if (!err) {
+ BUFFER_TRACE(iloc.bh, "get_write_access");
+ err = jbd2_journal_get_write_access(handle, iloc.bh);
+ if (!err)
+ err = ext4_journal_dirty_metadata(handle,
+ iloc.bh);
+ brelse(iloc.bh);
+ }
+ }
+ ext4_std_error(inode->i_sb, err);
+ return err;
+}
+#endif
+
+int ext4_change_inode_journal_flag(struct inode *inode, int val)
+{
+ journal_t *journal;
+ handle_t *handle;
+ int err;
+
+ /*
+ * We have to be very careful here: changing a data block's
+ * journaling status dynamically is dangerous. If we write a
+ * data block to the journal, change the status and then delete
+ * that block, we risk forgetting to revoke the old log record
+ * from the journal and so a subsequent replay can corrupt data.
+ * So, first we make sure that the journal is empty and that
+ * nobody is changing anything.
+ */
+
+ journal = EXT4_JOURNAL(inode);
+ if (is_journal_aborted(journal) || IS_RDONLY(inode))
+ return -EROFS;
+
+ jbd2_journal_lock_updates(journal);
+ jbd2_journal_flush(journal);
+
+ /*
+ * OK, there are no updates running now, and all cached data is
+ * synced to disk. We are now in a completely consistent state
+ * which doesn't have anything in the journal, and we know that
+ * no filesystem updates are running, so it is safe to modify
+ * the inode's in-core data-journaling state flag now.
+ */
+
+ if (val)
+ EXT4_I(inode)->i_flags |= EXT4_JOURNAL_DATA_FL;
+ else
+ EXT4_I(inode)->i_flags &= ~EXT4_JOURNAL_DATA_FL;
+ ext4_set_aops(inode);
+
+ jbd2_journal_unlock_updates(journal);
+
+ /* Finally we can mark the inode as dirty. */
+
+ handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ err = ext4_mark_inode_dirty(handle, inode);
+ handle->h_sync = 1;
+ ext4_journal_stop(handle);
+ ext4_std_error(inode->i_sb, err);
+
+ return err;
+}
--- /dev/null
+/*
+ * linux/fs/ext4/ioctl.c
+ *
+ * Copyright (C) 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/capability.h>
+#include <linux/ext4_fs.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/time.h>
+#include <linux/compat.h>
+#include <linux/smp_lock.h>
+#include <asm/uaccess.h>
+
+int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
+ unsigned long arg)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned int flags;
+ unsigned short rsv_window_size;
+
+ ext4_debug ("cmd = %u, arg = %lu\n", cmd, arg);
+
+ switch (cmd) {
+ case EXT4_IOC_GETFLAGS:
+ flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+ return put_user(flags, (int __user *) arg);
+ case EXT4_IOC_SETFLAGS: {
+ handle_t *handle = NULL;
+ int err;
+ struct ext4_iloc iloc;
+ unsigned int oldflags;
+ unsigned int jflag;
+
+ if (IS_RDONLY(inode))
+ return -EROFS;
+
+ if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ return -EACCES;
+
+ if (get_user(flags, (int __user *) arg))
+ return -EFAULT;
+
+ if (!S_ISDIR(inode->i_mode))
+ flags &= ~EXT4_DIRSYNC_FL;
+
+ mutex_lock(&inode->i_mutex);
+ oldflags = ei->i_flags;
+
+ /* The JOURNAL_DATA flag is modifiable only by root */
+ jflag = flags & EXT4_JOURNAL_DATA_FL;
+
+ /*
+ * The IMMUTABLE and APPEND_ONLY flags can only be changed by
+ * the relevant capability.
+ *
+ * This test looks nicer. Thanks to Pauline Middelink
+ */
+ if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
+ if (!capable(CAP_LINUX_IMMUTABLE)) {
+ mutex_unlock(&inode->i_mutex);
+ return -EPERM;
+ }
+ }
+
+ /*
+ * The JOURNAL_DATA flag can only be changed by
+ * the relevant capability.
+ */
+ if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+ if (!capable(CAP_SYS_RESOURCE)) {
+ mutex_unlock(&inode->i_mutex);
+ return -EPERM;
+ }
+ }
+
+
+ handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle)) {
+ mutex_unlock(&inode->i_mutex);
+ return PTR_ERR(handle);
+ }
+ if (IS_SYNC(inode))
+ handle->h_sync = 1;
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (err)
+ goto flags_err;
+
+ flags = flags & EXT4_FL_USER_MODIFIABLE;
+ flags |= oldflags & ~EXT4_FL_USER_MODIFIABLE;
+ ei->i_flags = flags;
+
+ ext4_set_inode_flags(inode);
+ inode->i_ctime = CURRENT_TIME_SEC;
+
+ err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+flags_err:
+ ext4_journal_stop(handle);
+ if (err) {
+ mutex_unlock(&inode->i_mutex);
+ return err;
+ }
+
+ if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
+ err = ext4_change_inode_journal_flag(inode, jflag);
+ mutex_unlock(&inode->i_mutex);
+ return err;
+ }
+ case EXT4_IOC_GETVERSION:
+ case EXT4_IOC_GETVERSION_OLD:
+ return put_user(inode->i_generation, (int __user *) arg);
+ case EXT4_IOC_SETVERSION:
+ case EXT4_IOC_SETVERSION_OLD: {
+ handle_t *handle;
+ struct ext4_iloc iloc;
+ __u32 generation;
+ int err;
+
+ if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ return -EPERM;
+ if (IS_RDONLY(inode))
+ return -EROFS;
+ if (get_user(generation, (int __user *) arg))
+ return -EFAULT;
+
+ handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (err == 0) {
+ inode->i_ctime = CURRENT_TIME_SEC;
+ inode->i_generation = generation;
+ err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+ }
+ ext4_journal_stop(handle);
+ return err;
+ }
+#ifdef CONFIG_JBD_DEBUG
+ case EXT4_IOC_WAIT_FOR_READONLY:
+ /*
+ * This is racy - by the time we're woken up and running,
+ * the superblock could be released. And the module could
+ * have been unloaded. So sue me.
+ *
+ * Returns 1 if it slept, else zero.
+ */
+ {
+ struct super_block *sb = inode->i_sb;
+ DECLARE_WAITQUEUE(wait, current);
+ int ret = 0;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ add_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
+ if (timer_pending(&EXT4_SB(sb)->turn_ro_timer)) {
+ schedule();
+ ret = 1;
+ }
+ remove_wait_queue(&EXT4_SB(sb)->ro_wait_queue, &wait);
+ return ret;
+ }
+#endif
+ case EXT4_IOC_GETRSVSZ:
+ if (test_opt(inode->i_sb, RESERVATION)
+ && S_ISREG(inode->i_mode)
+ && ei->i_block_alloc_info) {
+ rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
+ return put_user(rsv_window_size, (int __user *)arg);
+ }
+ return -ENOTTY;
+ case EXT4_IOC_SETRSVSZ: {
+
+ if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
+ return -ENOTTY;
+
+ if (IS_RDONLY(inode))
+ return -EROFS;
+
+ if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ return -EACCES;
+
+ if (get_user(rsv_window_size, (int __user *)arg))
+ return -EFAULT;
+
+ if (rsv_window_size > EXT4_MAX_RESERVE_BLOCKS)
+ rsv_window_size = EXT4_MAX_RESERVE_BLOCKS;
+
+ /*
+ * need to allocate reservation structure for this inode
+ * before set the window size
+ */
+ mutex_lock(&ei->truncate_mutex);
+ if (!ei->i_block_alloc_info)
+ ext4_init_block_alloc_info(inode);
+
+ if (ei->i_block_alloc_info){
+ struct ext4_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
+ rsv->rsv_goal_size = rsv_window_size;
+ }
+ mutex_unlock(&ei->truncate_mutex);
+ return 0;
+ }
+ case EXT4_IOC_GROUP_EXTEND: {
+ ext4_fsblk_t n_blocks_count;
+ struct super_block *sb = inode->i_sb;
+ int err;
+
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ if (IS_RDONLY(inode))
+ return -EROFS;
+
+ if (get_user(n_blocks_count, (__u32 __user *)arg))
+ return -EFAULT;
+
+ err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
+ jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+ jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+
+ return err;
+ }
+ case EXT4_IOC_GROUP_ADD: {
+ struct ext4_new_group_data input;
+ struct super_block *sb = inode->i_sb;
+ int err;
+
+ if (!capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ if (IS_RDONLY(inode))
+ return -EROFS;
+
+ if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
+ sizeof(input)))
+ return -EFAULT;
+
+ err = ext4_group_add(sb, &input);
+ jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
+ jbd2_journal_flush(EXT4_SB(sb)->s_journal);
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+
+ return err;
+ }
+
+ default:
+ return -ENOTTY;
+ }
+}
+
+#ifdef CONFIG_COMPAT
+long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct inode *inode = file->f_dentry->d_inode;
+ int ret;
+
+ /* These are just misnamed, they actually get/put from/to user an int */
+ switch (cmd) {
+ case EXT4_IOC32_GETFLAGS:
+ cmd = EXT4_IOC_GETFLAGS;
+ break;
+ case EXT4_IOC32_SETFLAGS:
+ cmd = EXT4_IOC_SETFLAGS;
+ break;
+ case EXT4_IOC32_GETVERSION:
+ cmd = EXT4_IOC_GETVERSION;
+ break;
+ case EXT4_IOC32_SETVERSION:
+ cmd = EXT4_IOC_SETVERSION;
+ break;
+ case EXT4_IOC32_GROUP_EXTEND:
+ cmd = EXT4_IOC_GROUP_EXTEND;
+ break;
+ case EXT4_IOC32_GETVERSION_OLD:
+ cmd = EXT4_IOC_GETVERSION_OLD;
+ break;
+ case EXT4_IOC32_SETVERSION_OLD:
+ cmd = EXT4_IOC_SETVERSION_OLD;
+ break;
+#ifdef CONFIG_JBD_DEBUG
+ case EXT4_IOC32_WAIT_FOR_READONLY:
+ cmd = EXT4_IOC_WAIT_FOR_READONLY;
+ break;
+#endif
+ case EXT4_IOC32_GETRSVSZ:
+ cmd = EXT4_IOC_GETRSVSZ;
+ break;
+ case EXT4_IOC32_SETRSVSZ:
+ cmd = EXT4_IOC_SETRSVSZ;
+ break;
+ case EXT4_IOC_GROUP_ADD:
+ break;
+ default:
+ return -ENOIOCTLCMD;
+ }
+ lock_kernel();
+ ret = ext4_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
+ unlock_kernel();
+ return ret;
+}
+#endif
--- /dev/null
+/*
+ * linux/fs/ext4/namei.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/fs/minix/namei.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Big-endian to little-endian byte-swapping/bitmaps by
+ * David S. Miller (davem@caip.rutgers.edu), 1995
+ * Directory entry file type support and forward compatibility hooks
+ * for B-tree directories by Theodore Ts'o (tytso@mit.edu), 1998
+ * Hash Tree Directory indexing (c)
+ * Daniel Phillips, 2001
+ * Hash Tree Directory indexing porting
+ * Christopher Li, 2002
+ * Hash Tree Directory indexing cleanup
+ * Theodore Ts'o, 2002
+ */
+
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/jbd2.h>
+#include <linux/time.h>
+#include <linux/ext4_fs.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/fcntl.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/quotaops.h>
+#include <linux/buffer_head.h>
+#include <linux/bio.h>
+#include <linux/smp_lock.h>
+
+#include "namei.h"
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * define how far ahead to read directories while searching them.
+ */
+#define NAMEI_RA_CHUNKS 2
+#define NAMEI_RA_BLOCKS 4
+#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
+#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b))
+
+static struct buffer_head *ext4_append(handle_t *handle,
+ struct inode *inode,
+ u32 *block, int *err)
+{
+ struct buffer_head *bh;
+
+ *block = inode->i_size >> inode->i_sb->s_blocksize_bits;
+
+ if ((bh = ext4_bread(handle, inode, *block, 1, err))) {
+ inode->i_size += inode->i_sb->s_blocksize;
+ EXT4_I(inode)->i_disksize = inode->i_size;
+ ext4_journal_get_write_access(handle,bh);
+ }
+ return bh;
+}
+
+#ifndef assert
+#define assert(test) J_ASSERT(test)
+#endif
+
+#ifndef swap
+#define swap(x, y) do { typeof(x) z = x; x = y; y = z; } while (0)
+#endif
+
+#ifdef DX_DEBUG
+#define dxtrace(command) command
+#else
+#define dxtrace(command)
+#endif
+
+struct fake_dirent
+{
+ __le32 inode;
+ __le16 rec_len;
+ u8 name_len;
+ u8 file_type;
+};
+
+struct dx_countlimit
+{
+ __le16 limit;
+ __le16 count;
+};
+
+struct dx_entry
+{
+ __le32 hash;
+ __le32 block;
+};
+
+/*
+ * dx_root_info is laid out so that if it should somehow get overlaid by a
+ * dirent the two low bits of the hash version will be zero. Therefore, the
+ * hash version mod 4 should never be 0. Sincerely, the paranoia department.
+ */
+
+struct dx_root
+{
+ struct fake_dirent dot;
+ char dot_name[4];
+ struct fake_dirent dotdot;
+ char dotdot_name[4];
+ struct dx_root_info
+ {
+ __le32 reserved_zero;
+ u8 hash_version;
+ u8 info_length; /* 8 */
+ u8 indirect_levels;
+ u8 unused_flags;
+ }
+ info;
+ struct dx_entry entries[0];
+};
+
+struct dx_node
+{
+ struct fake_dirent fake;
+ struct dx_entry entries[0];
+};
+
+
+struct dx_frame
+{
+ struct buffer_head *bh;
+ struct dx_entry *entries;
+ struct dx_entry *at;
+};
+
+struct dx_map_entry
+{
+ u32 hash;
+ u32 offs;
+};
+
+#ifdef CONFIG_EXT4_INDEX
+static inline unsigned dx_get_block (struct dx_entry *entry);
+static void dx_set_block (struct dx_entry *entry, unsigned value);
+static inline unsigned dx_get_hash (struct dx_entry *entry);
+static void dx_set_hash (struct dx_entry *entry, unsigned value);
+static unsigned dx_get_count (struct dx_entry *entries);
+static unsigned dx_get_limit (struct dx_entry *entries);
+static void dx_set_count (struct dx_entry *entries, unsigned value);
+static void dx_set_limit (struct dx_entry *entries, unsigned value);
+static unsigned dx_root_limit (struct inode *dir, unsigned infosize);
+static unsigned dx_node_limit (struct inode *dir);
+static struct dx_frame *dx_probe(struct dentry *dentry,
+ struct inode *dir,
+ struct dx_hash_info *hinfo,
+ struct dx_frame *frame,
+ int *err);
+static void dx_release (struct dx_frame *frames);
+static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
+ struct dx_hash_info *hinfo, struct dx_map_entry map[]);
+static void dx_sort_map(struct dx_map_entry *map, unsigned count);
+static struct ext4_dir_entry_2 *dx_move_dirents (char *from, char *to,
+ struct dx_map_entry *offsets, int count);
+static struct ext4_dir_entry_2* dx_pack_dirents (char *base, int size);
+static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block);
+static int ext4_htree_next_block(struct inode *dir, __u32 hash,
+ struct dx_frame *frame,
+ struct dx_frame *frames,
+ __u32 *start_hash);
+static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
+ struct ext4_dir_entry_2 **res_dir, int *err);
+static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
+ struct inode *inode);
+
+/*
+ * Future: use high four bits of block for coalesce-on-delete flags
+ * Mask them off for now.
+ */
+
+static inline unsigned dx_get_block (struct dx_entry *entry)
+{
+ return le32_to_cpu(entry->block) & 0x00ffffff;
+}
+
+static inline void dx_set_block (struct dx_entry *entry, unsigned value)
+{
+ entry->block = cpu_to_le32(value);
+}
+
+static inline unsigned dx_get_hash (struct dx_entry *entry)
+{
+ return le32_to_cpu(entry->hash);
+}
+
+static inline void dx_set_hash (struct dx_entry *entry, unsigned value)
+{
+ entry->hash = cpu_to_le32(value);
+}
+
+static inline unsigned dx_get_count (struct dx_entry *entries)
+{
+ return le16_to_cpu(((struct dx_countlimit *) entries)->count);
+}
+
+static inline unsigned dx_get_limit (struct dx_entry *entries)
+{
+ return le16_to_cpu(((struct dx_countlimit *) entries)->limit);
+}
+
+static inline void dx_set_count (struct dx_entry *entries, unsigned value)
+{
+ ((struct dx_countlimit *) entries)->count = cpu_to_le16(value);
+}
+
+static inline void dx_set_limit (struct dx_entry *entries, unsigned value)
+{
+ ((struct dx_countlimit *) entries)->limit = cpu_to_le16(value);
+}
+
+static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize)
+{
+ unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) -
+ EXT4_DIR_REC_LEN(2) - infosize;
+ return 0? 20: entry_space / sizeof(struct dx_entry);
+}
+
+static inline unsigned dx_node_limit (struct inode *dir)
+{
+ unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
+ return 0? 22: entry_space / sizeof(struct dx_entry);
+}
+
+/*
+ * Debug
+ */
+#ifdef DX_DEBUG
+static void dx_show_index (char * label, struct dx_entry *entries)
+{
+ int i, n = dx_get_count (entries);
+ printk("%s index ", label);
+ for (i = 0; i < n; i++) {
+ printk("%x->%u ", i? dx_get_hash(entries + i) :
+ 0, dx_get_block(entries + i));
+ }
+ printk("\n");
+}
+
+struct stats
+{
+ unsigned names;
+ unsigned space;
+ unsigned bcount;
+};
+
+static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext4_dir_entry_2 *de,
+ int size, int show_names)
+{
+ unsigned names = 0, space = 0;
+ char *base = (char *) de;
+ struct dx_hash_info h = *hinfo;
+
+ printk("names: ");
+ while ((char *) de < base + size)
+ {
+ if (de->inode)
+ {
+ if (show_names)
+ {
+ int len = de->name_len;
+ char *name = de->name;
+ while (len--) printk("%c", *name++);
+ ext4fs_dirhash(de->name, de->name_len, &h);
+ printk(":%x.%u ", h.hash,
+ ((char *) de - base));
+ }
+ space += EXT4_DIR_REC_LEN(de->name_len);
+ names++;
+ }
+ de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len));
+ }
+ printk("(%i)\n", names);
+ return (struct stats) { names, space, 1 };
+}
+
+struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
+ struct dx_entry *entries, int levels)
+{
+ unsigned blocksize = dir->i_sb->s_blocksize;
+ unsigned count = dx_get_count (entries), names = 0, space = 0, i;
+ unsigned bcount = 0;
+ struct buffer_head *bh;
+ int err;
+ printk("%i indexed blocks...\n", count);
+ for (i = 0; i < count; i++, entries++)
+ {
+ u32 block = dx_get_block(entries), hash = i? dx_get_hash(entries): 0;
+ u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash;
+ struct stats stats;
+ printk("%s%3u:%03u hash %8x/%8x ",levels?"":" ", i, block, hash, range);
+ if (!(bh = ext4_bread (NULL,dir, block, 0,&err))) continue;
+ stats = levels?
+ dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1):
+ dx_show_leaf(hinfo, (struct ext4_dir_entry_2 *) bh->b_data, blocksize, 0);
+ names += stats.names;
+ space += stats.space;
+ bcount += stats.bcount;
+ brelse (bh);
+ }
+ if (bcount)
+ printk("%snames %u, fullness %u (%u%%)\n", levels?"":" ",
+ names, space/bcount,(space/bcount)*100/blocksize);
+ return (struct stats) { names, space, bcount};
+}
+#endif /* DX_DEBUG */
+
+/*
+ * Probe for a directory leaf block to search.
+ *
+ * dx_probe can return ERR_BAD_DX_DIR, which means there was a format
+ * error in the directory index, and the caller should fall back to
+ * searching the directory normally. The callers of dx_probe **MUST**
+ * check for this error code, and make sure it never gets reflected
+ * back to userspace.
+ */
+static struct dx_frame *
+dx_probe(struct dentry *dentry, struct inode *dir,
+ struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err)
+{
+ unsigned count, indirect;
+ struct dx_entry *at, *entries, *p, *q, *m;
+ struct dx_root *root;
+ struct buffer_head *bh;
+ struct dx_frame *frame = frame_in;
+ u32 hash;
+
+ frame->bh = NULL;
+ if (dentry)
+ dir = dentry->d_parent->d_inode;
+ if (!(bh = ext4_bread (NULL,dir, 0, 0, err)))
+ goto fail;
+ root = (struct dx_root *) bh->b_data;
+ if (root->info.hash_version != DX_HASH_TEA &&
+ root->info.hash_version != DX_HASH_HALF_MD4 &&
+ root->info.hash_version != DX_HASH_LEGACY) {
+ ext4_warning(dir->i_sb, __FUNCTION__,
+ "Unrecognised inode hash code %d",
+ root->info.hash_version);
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail;
+ }
+ hinfo->hash_version = root->info.hash_version;
+ hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
+ if (dentry)
+ ext4fs_dirhash(dentry->d_name.name, dentry->d_name.len, hinfo);
+ hash = hinfo->hash;
+
+ if (root->info.unused_flags & 1) {
+ ext4_warning(dir->i_sb, __FUNCTION__,
+ "Unimplemented inode hash flags: %#06x",
+ root->info.unused_flags);
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail;
+ }
+
+ if ((indirect = root->info.indirect_levels) > 1) {
+ ext4_warning(dir->i_sb, __FUNCTION__,
+ "Unimplemented inode hash depth: %#06x",
+ root->info.indirect_levels);
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail;
+ }
+
+ entries = (struct dx_entry *) (((char *)&root->info) +
+ root->info.info_length);
+ assert(dx_get_limit(entries) == dx_root_limit(dir,
+ root->info.info_length));
+ dxtrace (printk("Look up %x", hash));
+ while (1)
+ {
+ count = dx_get_count(entries);
+ assert (count && count <= dx_get_limit(entries));
+ p = entries + 1;
+ q = entries + count - 1;
+ while (p <= q)
+ {
+ m = p + (q - p)/2;
+ dxtrace(printk("."));
+ if (dx_get_hash(m) > hash)
+ q = m - 1;
+ else
+ p = m + 1;
+ }
+
+ if (0) // linear search cross check
+ {
+ unsigned n = count - 1;
+ at = entries;
+ while (n--)
+ {
+ dxtrace(printk(","));
+ if (dx_get_hash(++at) > hash)
+ {
+ at--;
+ break;
+ }
+ }
+ assert (at == p - 1);
+ }
+
+ at = p - 1;
+ dxtrace(printk(" %x->%u\n", at == entries? 0: dx_get_hash(at), dx_get_block(at)));
+ frame->bh = bh;
+ frame->entries = entries;
+ frame->at = at;
+ if (!indirect--) return frame;
+ if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err)))
+ goto fail2;
+ at = entries = ((struct dx_node *) bh->b_data)->entries;
+ assert (dx_get_limit(entries) == dx_node_limit (dir));
+ frame++;
+ }
+fail2:
+ while (frame >= frame_in) {
+ brelse(frame->bh);
+ frame--;
+ }
+fail:
+ return NULL;
+}
+
+static void dx_release (struct dx_frame *frames)
+{
+ if (frames[0].bh == NULL)
+ return;
+
+ if (((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels)
+ brelse(frames[1].bh);
+ brelse(frames[0].bh);
+}
+
+/*
+ * This function increments the frame pointer to search the next leaf
+ * block, and reads in the necessary intervening nodes if the search
+ * should be necessary. Whether or not the search is necessary is
+ * controlled by the hash parameter. If the hash value is even, then
+ * the search is only continued if the next block starts with that
+ * hash value. This is used if we are searching for a specific file.
+ *
+ * If the hash value is HASH_NB_ALWAYS, then always go to the next block.
+ *
+ * This function returns 1 if the caller should continue to search,
+ * or 0 if it should not. If there is an error reading one of the
+ * index blocks, it will a negative error code.
+ *
+ * If start_hash is non-null, it will be filled in with the starting
+ * hash of the next page.
+ */
+static int ext4_htree_next_block(struct inode *dir, __u32 hash,
+ struct dx_frame *frame,
+ struct dx_frame *frames,
+ __u32 *start_hash)
+{
+ struct dx_frame *p;
+ struct buffer_head *bh;
+ int err, num_frames = 0;
+ __u32 bhash;
+
+ p = frame;
+ /*
+ * Find the next leaf page by incrementing the frame pointer.
+ * If we run out of entries in the interior node, loop around and
+ * increment pointer in the parent node. When we break out of
+ * this loop, num_frames indicates the number of interior
+ * nodes need to be read.
+ */
+ while (1) {
+ if (++(p->at) < p->entries + dx_get_count(p->entries))
+ break;
+ if (p == frames)
+ return 0;
+ num_frames++;
+ p--;
+ }
+
+ /*
+ * If the hash is 1, then continue only if the next page has a
+ * continuation hash of any value. This is used for readdir
+ * handling. Otherwise, check to see if the hash matches the
+ * desired contiuation hash. If it doesn't, return since
+ * there's no point to read in the successive index pages.
+ */
+ bhash = dx_get_hash(p->at);
+ if (start_hash)
+ *start_hash = bhash;
+ if ((hash & 1) == 0) {
+ if ((bhash & ~1) != hash)
+ return 0;
+ }
+ /*
+ * If the hash is HASH_NB_ALWAYS, we always go to the next
+ * block so no check is necessary
+ */
+ while (num_frames--) {
+ if (!(bh = ext4_bread(NULL, dir, dx_get_block(p->at),
+ 0, &err)))
+ return err; /* Failure */
+ p++;
+ brelse (p->bh);
+ p->bh = bh;
+ p->at = p->entries = ((struct dx_node *) bh->b_data)->entries;
+ }
+ return 1;
+}
+
+
+/*
+ * p is at least 6 bytes before the end of page
+ */
+static inline struct ext4_dir_entry_2 *ext4_next_entry(struct ext4_dir_entry_2 *p)
+{
+ return (struct ext4_dir_entry_2 *)((char*)p + le16_to_cpu(p->rec_len));
+}
+
+/*
+ * This function fills a red-black tree with information from a
+ * directory block. It returns the number directory entries loaded
+ * into the tree. If there is an error it is returned in err.
+ */
+static int htree_dirblock_to_tree(struct file *dir_file,
+ struct inode *dir, int block,
+ struct dx_hash_info *hinfo,
+ __u32 start_hash, __u32 start_minor_hash)
+{
+ struct buffer_head *bh;
+ struct ext4_dir_entry_2 *de, *top;
+ int err, count = 0;
+
+ dxtrace(printk("In htree dirblock_to_tree: block %d\n", block));
+ if (!(bh = ext4_bread (NULL, dir, block, 0, &err)))
+ return err;
+
+ de = (struct ext4_dir_entry_2 *) bh->b_data;
+ top = (struct ext4_dir_entry_2 *) ((char *) de +
+ dir->i_sb->s_blocksize -
+ EXT4_DIR_REC_LEN(0));
+ for (; de < top; de = ext4_next_entry(de)) {
+ ext4fs_dirhash(de->name, de->name_len, hinfo);
+ if ((hinfo->hash < start_hash) ||
+ ((hinfo->hash == start_hash) &&
+ (hinfo->minor_hash < start_minor_hash)))
+ continue;
+ if (de->inode == 0)
+ continue;
+ if ((err = ext4_htree_store_dirent(dir_file,
+ hinfo->hash, hinfo->minor_hash, de)) != 0) {
+ brelse(bh);
+ return err;
+ }
+ count++;
+ }
+ brelse(bh);
+ return count;
+}
+
+
+/*
+ * This function fills a red-black tree with information from a
+ * directory. We start scanning the directory in hash order, starting
+ * at start_hash and start_minor_hash.
+ *
+ * This function returns the number of entries inserted into the tree,
+ * or a negative error code.
+ */
+int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
+ __u32 start_minor_hash, __u32 *next_hash)
+{
+ struct dx_hash_info hinfo;
+ struct ext4_dir_entry_2 *de;
+ struct dx_frame frames[2], *frame;
+ struct inode *dir;
+ int block, err;
+ int count = 0;
+ int ret;
+ __u32 hashval;
+
+ dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
+ start_minor_hash));
+ dir = dir_file->f_dentry->d_inode;
+ if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
+ hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+ hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
+ count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
+ start_hash, start_minor_hash);
+ *next_hash = ~0;
+ return count;
+ }
+ hinfo.hash = start_hash;
+ hinfo.minor_hash = 0;
+ frame = dx_probe(NULL, dir_file->f_dentry->d_inode, &hinfo, frames, &err);
+ if (!frame)
+ return err;
+
+ /* Add '.' and '..' from the htree header */
+ if (!start_hash && !start_minor_hash) {
+ de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
+ if ((err = ext4_htree_store_dirent(dir_file, 0, 0, de)) != 0)
+ goto errout;
+ count++;
+ }
+ if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) {
+ de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
+ de = ext4_next_entry(de);
+ if ((err = ext4_htree_store_dirent(dir_file, 2, 0, de)) != 0)
+ goto errout;
+ count++;
+ }
+
+ while (1) {
+ block = dx_get_block(frame->at);
+ ret = htree_dirblock_to_tree(dir_file, dir, block, &hinfo,
+ start_hash, start_minor_hash);
+ if (ret < 0) {
+ err = ret;
+ goto errout;
+ }
+ count += ret;
+ hashval = ~0;
+ ret = ext4_htree_next_block(dir, HASH_NB_ALWAYS,
+ frame, frames, &hashval);
+ *next_hash = hashval;
+ if (ret < 0) {
+ err = ret;
+ goto errout;
+ }
+ /*
+ * Stop if: (a) there are no more entries, or
+ * (b) we have inserted at least one entry and the
+ * next hash value is not a continuation
+ */
+ if ((ret == 0) ||
+ (count && ((hashval & 1) == 0)))
+ break;
+ }
+ dx_release(frames);
+ dxtrace(printk("Fill tree: returned %d entries, next hash: %x\n",
+ count, *next_hash));
+ return count;
+errout:
+ dx_release(frames);
+ return (err);
+}
+
+
+/*
+ * Directory block splitting, compacting
+ */
+
+static int dx_make_map (struct ext4_dir_entry_2 *de, int size,
+ struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
+{
+ int count = 0;
+ char *base = (char *) de;
+ struct dx_hash_info h = *hinfo;
+
+ while ((char *) de < base + size)
+ {
+ if (de->name_len && de->inode) {
+ ext4fs_dirhash(de->name, de->name_len, &h);
+ map_tail--;
+ map_tail->hash = h.hash;
+ map_tail->offs = (u32) ((char *) de - base);
+ count++;
+ cond_resched();
+ }
+ /* XXX: do we need to check rec_len == 0 case? -Chris */
+ de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len));
+ }
+ return count;
+}
+
+static void dx_sort_map (struct dx_map_entry *map, unsigned count)
+{
+ struct dx_map_entry *p, *q, *top = map + count - 1;
+ int more;
+ /* Combsort until bubble sort doesn't suck */
+ while (count > 2) {
+ count = count*10/13;
+ if (count - 9 < 2) /* 9, 10 -> 11 */
+ count = 11;
+ for (p = top, q = p - count; q >= map; p--, q--)
+ if (p->hash < q->hash)
+ swap(*p, *q);
+ }
+ /* Garden variety bubble sort */
+ do {
+ more = 0;
+ q = top;
+ while (q-- > map) {
+ if (q[1].hash >= q[0].hash)
+ continue;
+ swap(*(q+1), *q);
+ more = 1;
+ }
+ } while(more);
+}
+
+static void dx_insert_block(struct dx_frame *frame, u32 hash, u32 block)
+{
+ struct dx_entry *entries = frame->entries;
+ struct dx_entry *old = frame->at, *new = old + 1;
+ int count = dx_get_count(entries);
+
+ assert(count < dx_get_limit(entries));
+ assert(old < entries + count);
+ memmove(new + 1, new, (char *)(entries + count) - (char *)(new));
+ dx_set_hash(new, hash);
+ dx_set_block(new, block);
+ dx_set_count(entries, count + 1);
+}
+#endif
+
+
+static void ext4_update_dx_flag(struct inode *inode)
+{
+ if (!EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_COMPAT_DIR_INDEX))
+ EXT4_I(inode)->i_flags &= ~EXT4_INDEX_FL;
+}
+
+/*
+ * NOTE! unlike strncmp, ext4_match returns 1 for success, 0 for failure.
+ *
+ * `len <= EXT4_NAME_LEN' is guaranteed by caller.
+ * `de != NULL' is guaranteed by caller.
+ */
+static inline int ext4_match (int len, const char * const name,
+ struct ext4_dir_entry_2 * de)
+{
+ if (len != de->name_len)
+ return 0;
+ if (!de->inode)
+ return 0;
+ return !memcmp(name, de->name, len);
+}
+
+/*
+ * Returns 0 if not found, -1 on failure, and 1 on success
+ */
+static inline int search_dirblock(struct buffer_head * bh,
+ struct inode *dir,
+ struct dentry *dentry,
+ unsigned long offset,
+ struct ext4_dir_entry_2 ** res_dir)
+{
+ struct ext4_dir_entry_2 * de;
+ char * dlimit;
+ int de_len;
+ const char *name = dentry->d_name.name;
+ int namelen = dentry->d_name.len;
+
+ de = (struct ext4_dir_entry_2 *) bh->b_data;
+ dlimit = bh->b_data + dir->i_sb->s_blocksize;
+ while ((char *) de < dlimit) {
+ /* this code is executed quadratically often */
+ /* do minimal checking `by hand' */
+
+ if ((char *) de + namelen <= dlimit &&
+ ext4_match (namelen, name, de)) {
+ /* found a match - just to be sure, do a full check */
+ if (!ext4_check_dir_entry("ext4_find_entry",
+ dir, de, bh, offset))
+ return -1;
+ *res_dir = de;
+ return 1;
+ }
+ /* prevent looping on a bad block */
+ de_len = le16_to_cpu(de->rec_len);
+ if (de_len <= 0)
+ return -1;
+ offset += de_len;
+ de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
+ }
+ return 0;
+}
+
+
+/*
+ * ext4_find_entry()
+ *
+ * finds an entry in the specified directory with the wanted name. It
+ * returns the cache buffer in which the entry was found, and the entry
+ * itself (as a parameter - res_dir). It does NOT read the inode of the
+ * entry - you'll have to do that yourself if you want to.
+ *
+ * The returned buffer_head has ->b_count elevated. The caller is expected
+ * to brelse() it when appropriate.
+ */
+static struct buffer_head * ext4_find_entry (struct dentry *dentry,
+ struct ext4_dir_entry_2 ** res_dir)
+{
+ struct super_block * sb;
+ struct buffer_head * bh_use[NAMEI_RA_SIZE];
+ struct buffer_head * bh, *ret = NULL;
+ unsigned long start, block, b;
+ int ra_max = 0; /* Number of bh's in the readahead
+ buffer, bh_use[] */
+ int ra_ptr = 0; /* Current index into readahead
+ buffer */
+ int num = 0;
+ int nblocks, i, err;
+ struct inode *dir = dentry->d_parent->d_inode;
+ int namelen;
+ const u8 *name;
+ unsigned blocksize;
+
+ *res_dir = NULL;
+ sb = dir->i_sb;
+ blocksize = sb->s_blocksize;
+ namelen = dentry->d_name.len;
+ name = dentry->d_name.name;
+ if (namelen > EXT4_NAME_LEN)
+ return NULL;
+#ifdef CONFIG_EXT4_INDEX
+ if (is_dx(dir)) {
+ bh = ext4_dx_find_entry(dentry, res_dir, &err);
+ /*
+ * On success, or if the error was file not found,
+ * return. Otherwise, fall back to doing a search the
+ * old fashioned way.
+ */
+ if (bh || (err != ERR_BAD_DX_DIR))
+ return bh;
+ dxtrace(printk("ext4_find_entry: dx failed, falling back\n"));
+ }
+#endif
+ nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
+ start = EXT4_I(dir)->i_dir_start_lookup;
+ if (start >= nblocks)
+ start = 0;
+ block = start;
+restart:
+ do {
+ /*
+ * We deal with the read-ahead logic here.
+ */
+ if (ra_ptr >= ra_max) {
+ /* Refill the readahead buffer */
+ ra_ptr = 0;
+ b = block;
+ for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) {
+ /*
+ * Terminate if we reach the end of the
+ * directory and must wrap, or if our
+ * search has finished at this block.
+ */
+ if (b >= nblocks || (num && block == start)) {
+ bh_use[ra_max] = NULL;
+ break;
+ }
+ num++;
+ bh = ext4_getblk(NULL, dir, b++, 0, &err);
+ bh_use[ra_max] = bh;
+ if (bh)
+ ll_rw_block(READ_META, 1, &bh);
+ }
+ }
+ if ((bh = bh_use[ra_ptr++]) == NULL)
+ goto next;
+ wait_on_buffer(bh);
+ if (!buffer_uptodate(bh)) {
+ /* read error, skip block & hope for the best */
+ ext4_error(sb, __FUNCTION__, "reading directory #%lu "
+ "offset %lu", dir->i_ino, block);
+ brelse(bh);
+ goto next;
+ }
+ i = search_dirblock(bh, dir, dentry,
+ block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
+ if (i == 1) {
+ EXT4_I(dir)->i_dir_start_lookup = block;
+ ret = bh;
+ goto cleanup_and_exit;
+ } else {
+ brelse(bh);
+ if (i < 0)
+ goto cleanup_and_exit;
+ }
+ next:
+ if (++block >= nblocks)
+ block = 0;
+ } while (block != start);
+
+ /*
+ * If the directory has grown while we were searching, then
+ * search the last part of the directory before giving up.
+ */
+ block = nblocks;
+ nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
+ if (block < nblocks) {
+ start = 0;
+ goto restart;
+ }
+
+cleanup_and_exit:
+ /* Clean up the read-ahead blocks */
+ for (; ra_ptr < ra_max; ra_ptr++)
+ brelse (bh_use[ra_ptr]);
+ return ret;
+}
+
+#ifdef CONFIG_EXT4_INDEX
+static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry,
+ struct ext4_dir_entry_2 **res_dir, int *err)
+{
+ struct super_block * sb;
+ struct dx_hash_info hinfo;
+ u32 hash;
+ struct dx_frame frames[2], *frame;
+ struct ext4_dir_entry_2 *de, *top;
+ struct buffer_head *bh;
+ unsigned long block;
+ int retval;
+ int namelen = dentry->d_name.len;
+ const u8 *name = dentry->d_name.name;
+ struct inode *dir = dentry->d_parent->d_inode;
+
+ sb = dir->i_sb;
+ /* NFS may look up ".." - look at dx_root directory block */
+ if (namelen > 2 || name[0] != '.'||(name[1] != '.' && name[1] != '\0')){
+ if (!(frame = dx_probe(dentry, NULL, &hinfo, frames, err)))
+ return NULL;
+ } else {
+ frame = frames;
+ frame->bh = NULL; /* for dx_release() */
+ frame->at = (struct dx_entry *)frames; /* hack for zero entry*/
+ dx_set_block(frame->at, 0); /* dx_root block is 0 */
+ }
+ hash = hinfo.hash;
+ do {
+ block = dx_get_block(frame->at);
+ if (!(bh = ext4_bread (NULL,dir, block, 0, err)))
+ goto errout;
+ de = (struct ext4_dir_entry_2 *) bh->b_data;
+ top = (struct ext4_dir_entry_2 *) ((char *) de + sb->s_blocksize -
+ EXT4_DIR_REC_LEN(0));
+ for (; de < top; de = ext4_next_entry(de))
+ if (ext4_match (namelen, name, de)) {
+ if (!ext4_check_dir_entry("ext4_find_entry",
+ dir, de, bh,
+ (block<<EXT4_BLOCK_SIZE_BITS(sb))
+ +((char *)de - bh->b_data))) {
+ brelse (bh);
+ goto errout;
+ }
+ *res_dir = de;
+ dx_release (frames);
+ return bh;
+ }
+ brelse (bh);
+ /* Check to see if we should continue to search */
+ retval = ext4_htree_next_block(dir, hash, frame,
+ frames, NULL);
+ if (retval < 0) {
+ ext4_warning(sb, __FUNCTION__,
+ "error reading index page in directory #%lu",
+ dir->i_ino);
+ *err = retval;
+ goto errout;
+ }
+ } while (retval == 1);
+
+ *err = -ENOENT;
+errout:
+ dxtrace(printk("%s not found\n", name));
+ dx_release (frames);
+ return NULL;
+}
+#endif
+
+static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+{
+ struct inode * inode;
+ struct ext4_dir_entry_2 * de;
+ struct buffer_head * bh;
+
+ if (dentry->d_name.len > EXT4_NAME_LEN)
+ return ERR_PTR(-ENAMETOOLONG);
+
+ bh = ext4_find_entry(dentry, &de);
+ inode = NULL;
+ if (bh) {
+ unsigned long ino = le32_to_cpu(de->inode);
+ brelse (bh);
+ if (!ext4_valid_inum(dir->i_sb, ino)) {
+ ext4_error(dir->i_sb, "ext4_lookup",
+ "bad inode number: %lu", ino);
+ inode = NULL;
+ } else
+ inode = iget(dir->i_sb, ino);
+
+ if (!inode)
+ return ERR_PTR(-EACCES);
+ }
+ return d_splice_alias(inode, dentry);
+}
+
+
+struct dentry *ext4_get_parent(struct dentry *child)
+{
+ unsigned long ino;
+ struct dentry *parent;
+ struct inode *inode;
+ struct dentry dotdot;
+ struct ext4_dir_entry_2 * de;
+ struct buffer_head *bh;
+
+ dotdot.d_name.name = "..";
+ dotdot.d_name.len = 2;
+ dotdot.d_parent = child; /* confusing, isn't it! */
+
+ bh = ext4_find_entry(&dotdot, &de);
+ inode = NULL;
+ if (!bh)
+ return ERR_PTR(-ENOENT);
+ ino = le32_to_cpu(de->inode);
+ brelse(bh);
+
+ if (!ext4_valid_inum(child->d_inode->i_sb, ino)) {
+ ext4_error(child->d_inode->i_sb, "ext4_get_parent",
+ "bad inode number: %lu", ino);
+ inode = NULL;
+ } else
+ inode = iget(child->d_inode->i_sb, ino);
+
+ if (!inode)
+ return ERR_PTR(-EACCES);
+
+ parent = d_alloc_anon(inode);
+ if (!parent) {
+ iput(inode);
+ parent = ERR_PTR(-ENOMEM);
+ }
+ return parent;
+}
+
+#define S_SHIFT 12
+static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
+ [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE,
+ [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR,
+ [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV,
+ [S_IFBLK >> S_SHIFT] = EXT4_FT_BLKDEV,
+ [S_IFIFO >> S_SHIFT] = EXT4_FT_FIFO,
+ [S_IFSOCK >> S_SHIFT] = EXT4_FT_SOCK,
+ [S_IFLNK >> S_SHIFT] = EXT4_FT_SYMLINK,
+};
+
+static inline void ext4_set_de_type(struct super_block *sb,
+ struct ext4_dir_entry_2 *de,
+ umode_t mode) {
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE))
+ de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
+}
+
+#ifdef CONFIG_EXT4_INDEX
+static struct ext4_dir_entry_2 *
+dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
+{
+ unsigned rec_len = 0;
+
+ while (count--) {
+ struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + map->offs);
+ rec_len = EXT4_DIR_REC_LEN(de->name_len);
+ memcpy (to, de, rec_len);
+ ((struct ext4_dir_entry_2 *) to)->rec_len =
+ cpu_to_le16(rec_len);
+ de->inode = 0;
+ map++;
+ to += rec_len;
+ }
+ return (struct ext4_dir_entry_2 *) (to - rec_len);
+}
+
+static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size)
+{
+ struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base;
+ unsigned rec_len = 0;
+
+ prev = to = de;
+ while ((char*)de < base + size) {
+ next = (struct ext4_dir_entry_2 *) ((char *) de +
+ le16_to_cpu(de->rec_len));
+ if (de->inode && de->name_len) {
+ rec_len = EXT4_DIR_REC_LEN(de->name_len);
+ if (de > to)
+ memmove(to, de, rec_len);
+ to->rec_len = cpu_to_le16(rec_len);
+ prev = to;
+ to = (struct ext4_dir_entry_2 *) (((char *) to) + rec_len);
+ }
+ de = next;
+ }
+ return prev;
+}
+
+static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
+ struct buffer_head **bh,struct dx_frame *frame,
+ struct dx_hash_info *hinfo, int *error)
+{
+ unsigned blocksize = dir->i_sb->s_blocksize;
+ unsigned count, continued;
+ struct buffer_head *bh2;
+ u32 newblock;
+ u32 hash2;
+ struct dx_map_entry *map;
+ char *data1 = (*bh)->b_data, *data2;
+ unsigned split;
+ struct ext4_dir_entry_2 *de = NULL, *de2;
+ int err;
+
+ bh2 = ext4_append (handle, dir, &newblock, error);
+ if (!(bh2)) {
+ brelse(*bh);
+ *bh = NULL;
+ goto errout;
+ }
+
+ BUFFER_TRACE(*bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, *bh);
+ if (err) {
+ journal_error:
+ brelse(*bh);
+ brelse(bh2);
+ *bh = NULL;
+ ext4_std_error(dir->i_sb, err);
+ goto errout;
+ }
+ BUFFER_TRACE(frame->bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, frame->bh);
+ if (err)
+ goto journal_error;
+
+ data2 = bh2->b_data;
+
+ /* create map in the end of data2 block */
+ map = (struct dx_map_entry *) (data2 + blocksize);
+ count = dx_make_map ((struct ext4_dir_entry_2 *) data1,
+ blocksize, hinfo, map);
+ map -= count;
+ split = count/2; // need to adjust to actual middle
+ dx_sort_map (map, count);
+ hash2 = map[split].hash;
+ continued = hash2 == map[split - 1].hash;
+ dxtrace(printk("Split block %i at %x, %i/%i\n",
+ dx_get_block(frame->at), hash2, split, count-split));
+
+ /* Fancy dance to stay within two buffers */
+ de2 = dx_move_dirents(data1, data2, map + split, count - split);
+ de = dx_pack_dirents(data1,blocksize);
+ de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de);
+ de2->rec_len = cpu_to_le16(data2 + blocksize - (char *) de2);
+ dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1));
+ dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1));
+
+ /* Which block gets the new entry? */
+ if (hinfo->hash >= hash2)
+ {
+ swap(*bh, bh2);
+ de = de2;
+ }
+ dx_insert_block (frame, hash2 + continued, newblock);
+ err = ext4_journal_dirty_metadata (handle, bh2);
+ if (err)
+ goto journal_error;
+ err = ext4_journal_dirty_metadata (handle, frame->bh);
+ if (err)
+ goto journal_error;
+ brelse (bh2);
+ dxtrace(dx_show_index ("frame", frame->entries));
+errout:
+ return de;
+}
+#endif
+
+
+/*
+ * Add a new entry into a directory (leaf) block. If de is non-NULL,
+ * it points to a directory entry which is guaranteed to be large
+ * enough for new directory entry. If de is NULL, then
+ * add_dirent_to_buf will attempt search the directory block for
+ * space. It will return -ENOSPC if no space is available, and -EIO
+ * and -EEXIST if directory entry already exists.
+ *
+ * NOTE! bh is NOT released in the case where ENOSPC is returned. In
+ * all other cases bh is released.
+ */
+static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
+ struct inode *inode, struct ext4_dir_entry_2 *de,
+ struct buffer_head * bh)
+{
+ struct inode *dir = dentry->d_parent->d_inode;
+ const char *name = dentry->d_name.name;
+ int namelen = dentry->d_name.len;
+ unsigned long offset = 0;
+ unsigned short reclen;
+ int nlen, rlen, err;
+ char *top;
+
+ reclen = EXT4_DIR_REC_LEN(namelen);
+ if (!de) {
+ de = (struct ext4_dir_entry_2 *)bh->b_data;
+ top = bh->b_data + dir->i_sb->s_blocksize - reclen;
+ while ((char *) de <= top) {
+ if (!ext4_check_dir_entry("ext4_add_entry", dir, de,
+ bh, offset)) {
+ brelse (bh);
+ return -EIO;
+ }
+ if (ext4_match (namelen, name, de)) {
+ brelse (bh);
+ return -EEXIST;
+ }
+ nlen = EXT4_DIR_REC_LEN(de->name_len);
+ rlen = le16_to_cpu(de->rec_len);
+ if ((de->inode? rlen - nlen: rlen) >= reclen)
+ break;
+ de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
+ offset += rlen;
+ }
+ if ((char *) de > top)
+ return -ENOSPC;
+ }
+ BUFFER_TRACE(bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err) {
+ ext4_std_error(dir->i_sb, err);
+ brelse(bh);
+ return err;
+ }
+
+ /* By now the buffer is marked for journaling */
+ nlen = EXT4_DIR_REC_LEN(de->name_len);
+ rlen = le16_to_cpu(de->rec_len);
+ if (de->inode) {
+ struct ext4_dir_entry_2 *de1 = (struct ext4_dir_entry_2 *)((char *)de + nlen);
+ de1->rec_len = cpu_to_le16(rlen - nlen);
+ de->rec_len = cpu_to_le16(nlen);
+ de = de1;
+ }
+ de->file_type = EXT4_FT_UNKNOWN;
+ if (inode) {
+ de->inode = cpu_to_le32(inode->i_ino);
+ ext4_set_de_type(dir->i_sb, de, inode->i_mode);
+ } else
+ de->inode = 0;
+ de->name_len = namelen;
+ memcpy (de->name, name, namelen);
+ /*
+ * XXX shouldn't update any times until successful
+ * completion of syscall, but too many callers depend
+ * on this.
+ *
+ * XXX similarly, too many callers depend on
+ * ext4_new_inode() setting the times, but error
+ * recovery deletes the inode, so the worst that can
+ * happen is that the times are slightly out of date
+ * and/or different from the directory change time.
+ */
+ dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
+ ext4_update_dx_flag(dir);
+ dir->i_version++;
+ ext4_mark_inode_dirty(handle, dir);
+ BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+ err = ext4_journal_dirty_metadata(handle, bh);
+ if (err)
+ ext4_std_error(dir->i_sb, err);
+ brelse(bh);
+ return 0;
+}
+
+#ifdef CONFIG_EXT4_INDEX
+/*
+ * This converts a one block unindexed directory to a 3 block indexed
+ * directory, and adds the dentry to the indexed directory.
+ */
+static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
+ struct inode *inode, struct buffer_head *bh)
+{
+ struct inode *dir = dentry->d_parent->d_inode;
+ const char *name = dentry->d_name.name;
+ int namelen = dentry->d_name.len;
+ struct buffer_head *bh2;
+ struct dx_root *root;
+ struct dx_frame frames[2], *frame;
+ struct dx_entry *entries;
+ struct ext4_dir_entry_2 *de, *de2;
+ char *data1, *top;
+ unsigned len;
+ int retval;
+ unsigned blocksize;
+ struct dx_hash_info hinfo;
+ u32 block;
+ struct fake_dirent *fde;
+
+ blocksize = dir->i_sb->s_blocksize;
+ dxtrace(printk("Creating index\n"));
+ retval = ext4_journal_get_write_access(handle, bh);
+ if (retval) {
+ ext4_std_error(dir->i_sb, retval);
+ brelse(bh);
+ return retval;
+ }
+ root = (struct dx_root *) bh->b_data;
+
+ bh2 = ext4_append (handle, dir, &block, &retval);
+ if (!(bh2)) {
+ brelse(bh);
+ return retval;
+ }
+ EXT4_I(dir)->i_flags |= EXT4_INDEX_FL;
+ data1 = bh2->b_data;
+
+ /* The 0th block becomes the root, move the dirents out */
+ fde = &root->dotdot;
+ de = (struct ext4_dir_entry_2 *)((char *)fde + le16_to_cpu(fde->rec_len));
+ len = ((char *) root) + blocksize - (char *) de;
+ memcpy (data1, de, len);
+ de = (struct ext4_dir_entry_2 *) data1;
+ top = data1 + len;
+ while ((char *)(de2=(void*)de+le16_to_cpu(de->rec_len)) < top)
+ de = de2;
+ de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de);
+ /* Initialize the root; the dot dirents already exist */
+ de = (struct ext4_dir_entry_2 *) (&root->dotdot);
+ de->rec_len = cpu_to_le16(blocksize - EXT4_DIR_REC_LEN(2));
+ memset (&root->info, 0, sizeof(root->info));
+ root->info.info_length = sizeof(root->info);
+ root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+ entries = root->entries;
+ dx_set_block (entries, 1);
+ dx_set_count (entries, 1);
+ dx_set_limit (entries, dx_root_limit(dir, sizeof(root->info)));
+
+ /* Initialize as for dx_probe */
+ hinfo.hash_version = root->info.hash_version;
+ hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
+ ext4fs_dirhash(name, namelen, &hinfo);
+ frame = frames;
+ frame->entries = entries;
+ frame->at = entries;
+ frame->bh = bh;
+ bh = bh2;
+ de = do_split(handle,dir, &bh, frame, &hinfo, &retval);
+ dx_release (frames);
+ if (!(de))
+ return retval;
+
+ return add_dirent_to_buf(handle, dentry, inode, de, bh);
+}
+#endif
+
+/*
+ * ext4_add_entry()
+ *
+ * adds a file entry to the specified directory, using the same
+ * semantics as ext4_find_entry(). It returns NULL if it failed.
+ *
+ * NOTE!! The inode part of 'de' is left at 0 - which means you
+ * may not sleep between calling this and putting something into
+ * the entry, as someone else might have used it while you slept.
+ */
+static int ext4_add_entry (handle_t *handle, struct dentry *dentry,
+ struct inode *inode)
+{
+ struct inode *dir = dentry->d_parent->d_inode;
+ unsigned long offset;
+ struct buffer_head * bh;
+ struct ext4_dir_entry_2 *de;
+ struct super_block * sb;
+ int retval;
+#ifdef CONFIG_EXT4_INDEX
+ int dx_fallback=0;
+#endif
+ unsigned blocksize;
+ u32 block, blocks;
+
+ sb = dir->i_sb;
+ blocksize = sb->s_blocksize;
+ if (!dentry->d_name.len)
+ return -EINVAL;
+#ifdef CONFIG_EXT4_INDEX
+ if (is_dx(dir)) {
+ retval = ext4_dx_add_entry(handle, dentry, inode);
+ if (!retval || (retval != ERR_BAD_DX_DIR))
+ return retval;
+ EXT4_I(dir)->i_flags &= ~EXT4_INDEX_FL;
+ dx_fallback++;
+ ext4_mark_inode_dirty(handle, dir);
+ }
+#endif
+ blocks = dir->i_size >> sb->s_blocksize_bits;
+ for (block = 0, offset = 0; block < blocks; block++) {
+ bh = ext4_bread(handle, dir, block, 0, &retval);
+ if(!bh)
+ return retval;
+ retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
+ if (retval != -ENOSPC)
+ return retval;
+
+#ifdef CONFIG_EXT4_INDEX
+ if (blocks == 1 && !dx_fallback &&
+ EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
+ return make_indexed_dir(handle, dentry, inode, bh);
+#endif
+ brelse(bh);
+ }
+ bh = ext4_append(handle, dir, &block, &retval);
+ if (!bh)
+ return retval;
+ de = (struct ext4_dir_entry_2 *) bh->b_data;
+ de->inode = 0;
+ de->rec_len = cpu_to_le16(blocksize);
+ return add_dirent_to_buf(handle, dentry, inode, de, bh);
+}
+
+#ifdef CONFIG_EXT4_INDEX
+/*
+ * Returns 0 for success, or a negative error value
+ */
+static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
+ struct inode *inode)
+{
+ struct dx_frame frames[2], *frame;
+ struct dx_entry *entries, *at;
+ struct dx_hash_info hinfo;
+ struct buffer_head * bh;
+ struct inode *dir = dentry->d_parent->d_inode;
+ struct super_block * sb = dir->i_sb;
+ struct ext4_dir_entry_2 *de;
+ int err;
+
+ frame = dx_probe(dentry, NULL, &hinfo, frames, &err);
+ if (!frame)
+ return err;
+ entries = frame->entries;
+ at = frame->at;
+
+ if (!(bh = ext4_bread(handle,dir, dx_get_block(frame->at), 0, &err)))
+ goto cleanup;
+
+ BUFFER_TRACE(bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err)
+ goto journal_error;
+
+ err = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
+ if (err != -ENOSPC) {
+ bh = NULL;
+ goto cleanup;
+ }
+
+ /* Block full, should compress but for now just split */
+ dxtrace(printk("using %u of %u node entries\n",
+ dx_get_count(entries), dx_get_limit(entries)));
+ /* Need to split index? */
+ if (dx_get_count(entries) == dx_get_limit(entries)) {
+ u32 newblock;
+ unsigned icount = dx_get_count(entries);
+ int levels = frame - frames;
+ struct dx_entry *entries2;
+ struct dx_node *node2;
+ struct buffer_head *bh2;
+
+ if (levels && (dx_get_count(frames->entries) ==
+ dx_get_limit(frames->entries))) {
+ ext4_warning(sb, __FUNCTION__,
+ "Directory index full!");
+ err = -ENOSPC;
+ goto cleanup;
+ }
+ bh2 = ext4_append (handle, dir, &newblock, &err);
+ if (!(bh2))
+ goto cleanup;
+ node2 = (struct dx_node *)(bh2->b_data);
+ entries2 = node2->entries;
+ node2->fake.rec_len = cpu_to_le16(sb->s_blocksize);
+ node2->fake.inode = 0;
+ BUFFER_TRACE(frame->bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, frame->bh);
+ if (err)
+ goto journal_error;
+ if (levels) {
+ unsigned icount1 = icount/2, icount2 = icount - icount1;
+ unsigned hash2 = dx_get_hash(entries + icount1);
+ dxtrace(printk("Split index %i/%i\n", icount1, icount2));
+
+ BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
+ err = ext4_journal_get_write_access(handle,
+ frames[0].bh);
+ if (err)
+ goto journal_error;
+
+ memcpy ((char *) entries2, (char *) (entries + icount1),
+ icount2 * sizeof(struct dx_entry));
+ dx_set_count (entries, icount1);
+ dx_set_count (entries2, icount2);
+ dx_set_limit (entries2, dx_node_limit(dir));
+
+ /* Which index block gets the new entry? */
+ if (at - entries >= icount1) {
+ frame->at = at = at - entries - icount1 + entries2;
+ frame->entries = entries = entries2;
+ swap(frame->bh, bh2);
+ }
+ dx_insert_block (frames + 0, hash2, newblock);
+ dxtrace(dx_show_index ("node", frames[1].entries));
+ dxtrace(dx_show_index ("node",
+ ((struct dx_node *) bh2->b_data)->entries));
+ err = ext4_journal_dirty_metadata(handle, bh2);
+ if (err)
+ goto journal_error;
+ brelse (bh2);
+ } else {
+ dxtrace(printk("Creating second level index...\n"));
+ memcpy((char *) entries2, (char *) entries,
+ icount * sizeof(struct dx_entry));
+ dx_set_limit(entries2, dx_node_limit(dir));
+
+ /* Set up root */
+ dx_set_count(entries, 1);
+ dx_set_block(entries + 0, newblock);
+ ((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1;
+
+ /* Add new access path frame */
+ frame = frames + 1;
+ frame->at = at = at - entries + entries2;
+ frame->entries = entries = entries2;
+ frame->bh = bh2;
+ err = ext4_journal_get_write_access(handle,
+ frame->bh);
+ if (err)
+ goto journal_error;
+ }
+ ext4_journal_dirty_metadata(handle, frames[0].bh);
+ }
+ de = do_split(handle, dir, &bh, frame, &hinfo, &err);
+ if (!de)
+ goto cleanup;
+ err = add_dirent_to_buf(handle, dentry, inode, de, bh);
+ bh = NULL;
+ goto cleanup;
+
+journal_error:
+ ext4_std_error(dir->i_sb, err);
+cleanup:
+ if (bh)
+ brelse(bh);
+ dx_release(frames);
+ return err;
+}
+#endif
+
+/*
+ * ext4_delete_entry deletes a directory entry by merging it with the
+ * previous entry
+ */
+static int ext4_delete_entry (handle_t *handle,
+ struct inode * dir,
+ struct ext4_dir_entry_2 * de_del,
+ struct buffer_head * bh)
+{
+ struct ext4_dir_entry_2 * de, * pde;
+ int i;
+
+ i = 0;
+ pde = NULL;
+ de = (struct ext4_dir_entry_2 *) bh->b_data;
+ while (i < bh->b_size) {
+ if (!ext4_check_dir_entry("ext4_delete_entry", dir, de, bh, i))
+ return -EIO;
+ if (de == de_del) {
+ BUFFER_TRACE(bh, "get_write_access");
+ ext4_journal_get_write_access(handle, bh);
+ if (pde)
+ pde->rec_len =
+ cpu_to_le16(le16_to_cpu(pde->rec_len) +
+ le16_to_cpu(de->rec_len));
+ else
+ de->inode = 0;
+ dir->i_version++;
+ BUFFER_TRACE(bh, "call ext4_journal_dirty_metadata");
+ ext4_journal_dirty_metadata(handle, bh);
+ return 0;
+ }
+ i += le16_to_cpu(de->rec_len);
+ pde = de;
+ de = (struct ext4_dir_entry_2 *)
+ ((char *) de + le16_to_cpu(de->rec_len));
+ }
+ return -ENOENT;
+}
+
+/*
+ * ext4_mark_inode_dirty is somewhat expensive, so unlike ext2 we
+ * do not perform it in these functions. We perform it at the call site,
+ * if it is needed.
+ */
+static inline void ext4_inc_count(handle_t *handle, struct inode *inode)
+{
+ inc_nlink(inode);
+}
+
+static inline void ext4_dec_count(handle_t *handle, struct inode *inode)
+{
+ drop_nlink(inode);
+}
+
+static int ext4_add_nondir(handle_t *handle,
+ struct dentry *dentry, struct inode *inode)
+{
+ int err = ext4_add_entry(handle, dentry, inode);
+ if (!err) {
+ ext4_mark_inode_dirty(handle, inode);
+ d_instantiate(dentry, inode);
+ return 0;
+ }
+ ext4_dec_count(handle, inode);
+ iput(inode);
+ return err;
+}
+
+/*
+ * By the time this is called, we already have created
+ * the directory cache entry for the new file, but it
+ * is so far negative - it has no inode.
+ *
+ * If the create succeeds, we fill in the inode information
+ * with d_instantiate().
+ */
+static int ext4_create (struct inode * dir, struct dentry * dentry, int mode,
+ struct nameidata *nd)
+{
+ handle_t *handle;
+ struct inode * inode;
+ int err, retries = 0;
+
+retry:
+ handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+ 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(dir))
+ handle->h_sync = 1;
+
+ inode = ext4_new_inode (handle, dir, mode);
+ err = PTR_ERR(inode);
+ if (!IS_ERR(inode)) {
+ inode->i_op = &ext4_file_inode_operations;
+ inode->i_fop = &ext4_file_operations;
+ ext4_set_aops(inode);
+ err = ext4_add_nondir(handle, dentry, inode);
+ }
+ ext4_journal_stop(handle);
+ if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+}
+
+static int ext4_mknod (struct inode * dir, struct dentry *dentry,
+ int mode, dev_t rdev)
+{
+ handle_t *handle;
+ struct inode *inode;
+ int err, retries = 0;
+
+ if (!new_valid_dev(rdev))
+ return -EINVAL;
+
+retry:
+ handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+ 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(dir))
+ handle->h_sync = 1;
+
+ inode = ext4_new_inode (handle, dir, mode);
+ err = PTR_ERR(inode);
+ if (!IS_ERR(inode)) {
+ init_special_inode(inode, inode->i_mode, rdev);
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ inode->i_op = &ext4_special_inode_operations;
+#endif
+ err = ext4_add_nondir(handle, dentry, inode);
+ }
+ ext4_journal_stop(handle);
+ if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+}
+
+static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode)
+{
+ handle_t *handle;
+ struct inode * inode;
+ struct buffer_head * dir_block;
+ struct ext4_dir_entry_2 * de;
+ int err, retries = 0;
+
+ if (dir->i_nlink >= EXT4_LINK_MAX)
+ return -EMLINK;
+
+retry:
+ handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+ 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(dir))
+ handle->h_sync = 1;
+
+ inode = ext4_new_inode (handle, dir, S_IFDIR | mode);
+ err = PTR_ERR(inode);
+ if (IS_ERR(inode))
+ goto out_stop;
+
+ inode->i_op = &ext4_dir_inode_operations;
+ inode->i_fop = &ext4_dir_operations;
+ inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
+ dir_block = ext4_bread (handle, inode, 0, 1, &err);
+ if (!dir_block) {
+ drop_nlink(inode); /* is this nlink == 0? */
+ ext4_mark_inode_dirty(handle, inode);
+ iput (inode);
+ goto out_stop;
+ }
+ BUFFER_TRACE(dir_block, "get_write_access");
+ ext4_journal_get_write_access(handle, dir_block);
+ de = (struct ext4_dir_entry_2 *) dir_block->b_data;
+ de->inode = cpu_to_le32(inode->i_ino);
+ de->name_len = 1;
+ de->rec_len = cpu_to_le16(EXT4_DIR_REC_LEN(de->name_len));
+ strcpy (de->name, ".");
+ ext4_set_de_type(dir->i_sb, de, S_IFDIR);
+ de = (struct ext4_dir_entry_2 *)
+ ((char *) de + le16_to_cpu(de->rec_len));
+ de->inode = cpu_to_le32(dir->i_ino);
+ de->rec_len = cpu_to_le16(inode->i_sb->s_blocksize-EXT4_DIR_REC_LEN(1));
+ de->name_len = 2;
+ strcpy (de->name, "..");
+ ext4_set_de_type(dir->i_sb, de, S_IFDIR);
+ inode->i_nlink = 2;
+ BUFFER_TRACE(dir_block, "call ext4_journal_dirty_metadata");
+ ext4_journal_dirty_metadata(handle, dir_block);
+ brelse (dir_block);
+ ext4_mark_inode_dirty(handle, inode);
+ err = ext4_add_entry (handle, dentry, inode);
+ if (err) {
+ inode->i_nlink = 0;
+ ext4_mark_inode_dirty(handle, inode);
+ iput (inode);
+ goto out_stop;
+ }
+ inc_nlink(dir);
+ ext4_update_dx_flag(dir);
+ ext4_mark_inode_dirty(handle, dir);
+ d_instantiate(dentry, inode);
+out_stop:
+ ext4_journal_stop(handle);
+ if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+}
+
+/*
+ * routine to check that the specified directory is empty (for rmdir)
+ */
+static int empty_dir (struct inode * inode)
+{
+ unsigned long offset;
+ struct buffer_head * bh;
+ struct ext4_dir_entry_2 * de, * de1;
+ struct super_block * sb;
+ int err = 0;
+
+ sb = inode->i_sb;
+ if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
+ !(bh = ext4_bread (NULL, inode, 0, 0, &err))) {
+ if (err)
+ ext4_error(inode->i_sb, __FUNCTION__,
+ "error %d reading directory #%lu offset 0",
+ err, inode->i_ino);
+ else
+ ext4_warning(inode->i_sb, __FUNCTION__,
+ "bad directory (dir #%lu) - no data block",
+ inode->i_ino);
+ return 1;
+ }
+ de = (struct ext4_dir_entry_2 *) bh->b_data;
+ de1 = (struct ext4_dir_entry_2 *)
+ ((char *) de + le16_to_cpu(de->rec_len));
+ if (le32_to_cpu(de->inode) != inode->i_ino ||
+ !le32_to_cpu(de1->inode) ||
+ strcmp (".", de->name) ||
+ strcmp ("..", de1->name)) {
+ ext4_warning (inode->i_sb, "empty_dir",
+ "bad directory (dir #%lu) - no `.' or `..'",
+ inode->i_ino);
+ brelse (bh);
+ return 1;
+ }
+ offset = le16_to_cpu(de->rec_len) + le16_to_cpu(de1->rec_len);
+ de = (struct ext4_dir_entry_2 *)
+ ((char *) de1 + le16_to_cpu(de1->rec_len));
+ while (offset < inode->i_size ) {
+ if (!bh ||
+ (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+ err = 0;
+ brelse (bh);
+ bh = ext4_bread (NULL, inode,
+ offset >> EXT4_BLOCK_SIZE_BITS(sb), 0, &err);
+ if (!bh) {
+ if (err)
+ ext4_error(sb, __FUNCTION__,
+ "error %d reading directory"
+ " #%lu offset %lu",
+ err, inode->i_ino, offset);
+ offset += sb->s_blocksize;
+ continue;
+ }
+ de = (struct ext4_dir_entry_2 *) bh->b_data;
+ }
+ if (!ext4_check_dir_entry("empty_dir", inode, de, bh, offset)) {
+ de = (struct ext4_dir_entry_2 *)(bh->b_data +
+ sb->s_blocksize);
+ offset = (offset | (sb->s_blocksize - 1)) + 1;
+ continue;
+ }
+ if (le32_to_cpu(de->inode)) {
+ brelse (bh);
+ return 0;
+ }
+ offset += le16_to_cpu(de->rec_len);
+ de = (struct ext4_dir_entry_2 *)
+ ((char *) de + le16_to_cpu(de->rec_len));
+ }
+ brelse (bh);
+ return 1;
+}
+
+/* ext4_orphan_add() links an unlinked or truncated inode into a list of
+ * such inodes, starting at the superblock, in case we crash before the
+ * file is closed/deleted, or in case the inode truncate spans multiple
+ * transactions and the last transaction is not recovered after a crash.
+ *
+ * At filesystem recovery time, we walk this list deleting unlinked
+ * inodes and truncating linked inodes in ext4_orphan_cleanup().
+ */
+int ext4_orphan_add(handle_t *handle, struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+ struct ext4_iloc iloc;
+ int err = 0, rc;
+
+ lock_super(sb);
+ if (!list_empty(&EXT4_I(inode)->i_orphan))
+ goto out_unlock;
+
+ /* Orphan handling is only valid for files with data blocks
+ * being truncated, or files being unlinked. */
+
+ /* @@@ FIXME: Observation from aviro:
+ * I think I can trigger J_ASSERT in ext4_orphan_add(). We block
+ * here (on lock_super()), so race with ext4_link() which might bump
+ * ->i_nlink. For, say it, character device. Not a regular file,
+ * not a directory, not a symlink and ->i_nlink > 0.
+ */
+ J_ASSERT ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
+
+ BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+ if (err)
+ goto out_unlock;
+
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (err)
+ goto out_unlock;
+
+ /* Insert this inode at the head of the on-disk orphan list... */
+ NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
+ EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+ err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
+ if (!err)
+ err = rc;
+
+ /* Only add to the head of the in-memory list if all the
+ * previous operations succeeded. If the orphan_add is going to
+ * fail (possibly taking the journal offline), we can't risk
+ * leaving the inode on the orphan list: stray orphan-list
+ * entries can cause panics at unmount time.
+ *
+ * This is safe: on error we're going to ignore the orphan list
+ * anyway on the next recovery. */
+ if (!err)
+ list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
+
+ jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
+ jbd_debug(4, "orphan inode %lu will point to %d\n",
+ inode->i_ino, NEXT_ORPHAN(inode));
+out_unlock:
+ unlock_super(sb);
+ ext4_std_error(inode->i_sb, err);
+ return err;
+}
+
+/*
+ * ext4_orphan_del() removes an unlinked or truncated inode from the list
+ * of such inodes stored on disk, because it is finally being cleaned up.
+ */
+int ext4_orphan_del(handle_t *handle, struct inode *inode)
+{
+ struct list_head *prev;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi;
+ unsigned long ino_next;
+ struct ext4_iloc iloc;
+ int err = 0;
+
+ lock_super(inode->i_sb);
+ if (list_empty(&ei->i_orphan)) {
+ unlock_super(inode->i_sb);
+ return 0;
+ }
+
+ ino_next = NEXT_ORPHAN(inode);
+ prev = ei->i_orphan.prev;
+ sbi = EXT4_SB(inode->i_sb);
+
+ jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);
+
+ list_del_init(&ei->i_orphan);
+
+ /* If we're on an error path, we may not have a valid
+ * transaction handle with which to update the orphan list on
+ * disk, but we still need to remove the inode from the linked
+ * list in memory. */
+ if (!handle)
+ goto out;
+
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (err)
+ goto out_err;
+
+ if (prev == &sbi->s_orphan) {
+ jbd_debug(4, "superblock will point to %lu\n", ino_next);
+ BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, sbi->s_sbh);
+ if (err)
+ goto out_brelse;
+ sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+ err = ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+ } else {
+ struct ext4_iloc iloc2;
+ struct inode *i_prev =
+ &list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode;
+
+ jbd_debug(4, "orphan inode %lu will point to %lu\n",
+ i_prev->i_ino, ino_next);
+ err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
+ if (err)
+ goto out_brelse;
+ NEXT_ORPHAN(i_prev) = ino_next;
+ err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
+ }
+ if (err)
+ goto out_brelse;
+ NEXT_ORPHAN(inode) = 0;
+ err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+
+out_err:
+ ext4_std_error(inode->i_sb, err);
+out:
+ unlock_super(inode->i_sb);
+ return err;
+
+out_brelse:
+ brelse(iloc.bh);
+ goto out_err;
+}
+
+static int ext4_rmdir (struct inode * dir, struct dentry *dentry)
+{
+ int retval;
+ struct inode * inode;
+ struct buffer_head * bh;
+ struct ext4_dir_entry_2 * de;
+ handle_t *handle;
+
+ /* Initialize quotas before so that eventual writes go in
+ * separate transaction */
+ DQUOT_INIT(dentry->d_inode);
+ handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ retval = -ENOENT;
+ bh = ext4_find_entry (dentry, &de);
+ if (!bh)
+ goto end_rmdir;
+
+ if (IS_DIRSYNC(dir))
+ handle->h_sync = 1;
+
+ inode = dentry->d_inode;
+
+ retval = -EIO;
+ if (le32_to_cpu(de->inode) != inode->i_ino)
+ goto end_rmdir;
+
+ retval = -ENOTEMPTY;
+ if (!empty_dir (inode))
+ goto end_rmdir;
+
+ retval = ext4_delete_entry(handle, dir, de, bh);
+ if (retval)
+ goto end_rmdir;
+ if (inode->i_nlink != 2)
+ ext4_warning (inode->i_sb, "ext4_rmdir",
+ "empty directory has nlink!=2 (%d)",
+ inode->i_nlink);
+ inode->i_version++;
+ clear_nlink(inode);
+ /* There's no need to set i_disksize: the fact that i_nlink is
+ * zero will ensure that the right thing happens during any
+ * recovery. */
+ inode->i_size = 0;
+ ext4_orphan_add(handle, inode);
+ inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
+ ext4_mark_inode_dirty(handle, inode);
+ drop_nlink(dir);
+ ext4_update_dx_flag(dir);
+ ext4_mark_inode_dirty(handle, dir);
+
+end_rmdir:
+ ext4_journal_stop(handle);
+ brelse (bh);
+ return retval;
+}
+
+static int ext4_unlink(struct inode * dir, struct dentry *dentry)
+{
+ int retval;
+ struct inode * inode;
+ struct buffer_head * bh;
+ struct ext4_dir_entry_2 * de;
+ handle_t *handle;
+
+ /* Initialize quotas before so that eventual writes go
+ * in separate transaction */
+ DQUOT_INIT(dentry->d_inode);
+ handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(dir))
+ handle->h_sync = 1;
+
+ retval = -ENOENT;
+ bh = ext4_find_entry (dentry, &de);
+ if (!bh)
+ goto end_unlink;
+
+ inode = dentry->d_inode;
+
+ retval = -EIO;
+ if (le32_to_cpu(de->inode) != inode->i_ino)
+ goto end_unlink;
+
+ if (!inode->i_nlink) {
+ ext4_warning (inode->i_sb, "ext4_unlink",
+ "Deleting nonexistent file (%lu), %d",
+ inode->i_ino, inode->i_nlink);
+ inode->i_nlink = 1;
+ }
+ retval = ext4_delete_entry(handle, dir, de, bh);
+ if (retval)
+ goto end_unlink;
+ dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
+ ext4_update_dx_flag(dir);
+ ext4_mark_inode_dirty(handle, dir);
+ drop_nlink(inode);
+ if (!inode->i_nlink)
+ ext4_orphan_add(handle, inode);
+ inode->i_ctime = dir->i_ctime;
+ ext4_mark_inode_dirty(handle, inode);
+ retval = 0;
+
+end_unlink:
+ ext4_journal_stop(handle);
+ brelse (bh);
+ return retval;
+}
+
+static int ext4_symlink (struct inode * dir,
+ struct dentry *dentry, const char * symname)
+{
+ handle_t *handle;
+ struct inode * inode;
+ int l, err, retries = 0;
+
+ l = strlen(symname)+1;
+ if (l > dir->i_sb->s_blocksize)
+ return -ENAMETOOLONG;
+
+retry:
+ handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 5 +
+ 2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(dir))
+ handle->h_sync = 1;
+
+ inode = ext4_new_inode (handle, dir, S_IFLNK|S_IRWXUGO);
+ err = PTR_ERR(inode);
+ if (IS_ERR(inode))
+ goto out_stop;
+
+ if (l > sizeof (EXT4_I(inode)->i_data)) {
+ inode->i_op = &ext4_symlink_inode_operations;
+ ext4_set_aops(inode);
+ /*
+ * page_symlink() calls into ext4_prepare/commit_write.
+ * We have a transaction open. All is sweetness. It also sets
+ * i_size in generic_commit_write().
+ */
+ err = __page_symlink(inode, symname, l,
+ mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
+ if (err) {
+ ext4_dec_count(handle, inode);
+ ext4_mark_inode_dirty(handle, inode);
+ iput (inode);
+ goto out_stop;
+ }
+ } else {
+ inode->i_op = &ext4_fast_symlink_inode_operations;
+ memcpy((char*)&EXT4_I(inode)->i_data,symname,l);
+ inode->i_size = l-1;
+ }
+ EXT4_I(inode)->i_disksize = inode->i_size;
+ err = ext4_add_nondir(handle, dentry, inode);
+out_stop:
+ ext4_journal_stop(handle);
+ if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+}
+
+static int ext4_link (struct dentry * old_dentry,
+ struct inode * dir, struct dentry *dentry)
+{
+ handle_t *handle;
+ struct inode *inode = old_dentry->d_inode;
+ int err, retries = 0;
+
+ if (inode->i_nlink >= EXT4_LINK_MAX)
+ return -EMLINK;
+
+retry:
+ handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(dir))
+ handle->h_sync = 1;
+
+ inode->i_ctime = CURRENT_TIME_SEC;
+ ext4_inc_count(handle, inode);
+ atomic_inc(&inode->i_count);
+
+ err = ext4_add_nondir(handle, dentry, inode);
+ ext4_journal_stop(handle);
+ if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+}
+
+#define PARENT_INO(buffer) \
+ ((struct ext4_dir_entry_2 *) ((char *) buffer + \
+ le16_to_cpu(((struct ext4_dir_entry_2 *) buffer)->rec_len)))->inode
+
+/*
+ * Anybody can rename anything with this: the permission checks are left to the
+ * higher-level routines.
+ */
+static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry,
+ struct inode * new_dir,struct dentry *new_dentry)
+{
+ handle_t *handle;
+ struct inode * old_inode, * new_inode;
+ struct buffer_head * old_bh, * new_bh, * dir_bh;
+ struct ext4_dir_entry_2 * old_de, * new_de;
+ int retval;
+
+ old_bh = new_bh = dir_bh = NULL;
+
+ /* Initialize quotas before so that eventual writes go
+ * in separate transaction */
+ if (new_dentry->d_inode)
+ DQUOT_INIT(new_dentry->d_inode);
+ handle = ext4_journal_start(old_dir, 2 *
+ EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
+ handle->h_sync = 1;
+
+ old_bh = ext4_find_entry (old_dentry, &old_de);
+ /*
+ * Check for inode number is _not_ due to possible IO errors.
+ * We might rmdir the source, keep it as pwd of some process
+ * and merrily kill the link to whatever was created under the
+ * same name. Goodbye sticky bit ;-<
+ */
+ old_inode = old_dentry->d_inode;
+ retval = -ENOENT;
+ if (!old_bh || le32_to_cpu(old_de->inode) != old_inode->i_ino)
+ goto end_rename;
+
+ new_inode = new_dentry->d_inode;
+ new_bh = ext4_find_entry (new_dentry, &new_de);
+ if (new_bh) {
+ if (!new_inode) {
+ brelse (new_bh);
+ new_bh = NULL;
+ }
+ }
+ if (S_ISDIR(old_inode->i_mode)) {
+ if (new_inode) {
+ retval = -ENOTEMPTY;
+ if (!empty_dir (new_inode))
+ goto end_rename;
+ }
+ retval = -EIO;
+ dir_bh = ext4_bread (handle, old_inode, 0, 0, &retval);
+ if (!dir_bh)
+ goto end_rename;
+ if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino)
+ goto end_rename;
+ retval = -EMLINK;
+ if (!new_inode && new_dir!=old_dir &&
+ new_dir->i_nlink >= EXT4_LINK_MAX)
+ goto end_rename;
+ }
+ if (!new_bh) {
+ retval = ext4_add_entry (handle, new_dentry, old_inode);
+ if (retval)
+ goto end_rename;
+ } else {
+ BUFFER_TRACE(new_bh, "get write access");
+ ext4_journal_get_write_access(handle, new_bh);
+ new_de->inode = cpu_to_le32(old_inode->i_ino);
+ if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
+ EXT4_FEATURE_INCOMPAT_FILETYPE))
+ new_de->file_type = old_de->file_type;
+ new_dir->i_version++;
+ BUFFER_TRACE(new_bh, "call ext4_journal_dirty_metadata");
+ ext4_journal_dirty_metadata(handle, new_bh);
+ brelse(new_bh);
+ new_bh = NULL;
+ }
+
+ /*
+ * Like most other Unix systems, set the ctime for inodes on a
+ * rename.
+ */
+ old_inode->i_ctime = CURRENT_TIME_SEC;
+ ext4_mark_inode_dirty(handle, old_inode);
+
+ /*
+ * ok, that's it
+ */
+ if (le32_to_cpu(old_de->inode) != old_inode->i_ino ||
+ old_de->name_len != old_dentry->d_name.len ||
+ strncmp(old_de->name, old_dentry->d_name.name, old_de->name_len) ||
+ (retval = ext4_delete_entry(handle, old_dir,
+ old_de, old_bh)) == -ENOENT) {
+ /* old_de could have moved from under us during htree split, so
+ * make sure that we are deleting the right entry. We might
+ * also be pointing to a stale entry in the unused part of
+ * old_bh so just checking inum and the name isn't enough. */
+ struct buffer_head *old_bh2;
+ struct ext4_dir_entry_2 *old_de2;
+
+ old_bh2 = ext4_find_entry(old_dentry, &old_de2);
+ if (old_bh2) {
+ retval = ext4_delete_entry(handle, old_dir,
+ old_de2, old_bh2);
+ brelse(old_bh2);
+ }
+ }
+ if (retval) {
+ ext4_warning(old_dir->i_sb, "ext4_rename",
+ "Deleting old file (%lu), %d, error=%d",
+ old_dir->i_ino, old_dir->i_nlink, retval);
+ }
+
+ if (new_inode) {
+ drop_nlink(new_inode);
+ new_inode->i_ctime = CURRENT_TIME_SEC;
+ }
+ old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC;
+ ext4_update_dx_flag(old_dir);
+ if (dir_bh) {
+ BUFFER_TRACE(dir_bh, "get_write_access");
+ ext4_journal_get_write_access(handle, dir_bh);
+ PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino);
+ BUFFER_TRACE(dir_bh, "call ext4_journal_dirty_metadata");
+ ext4_journal_dirty_metadata(handle, dir_bh);
+ drop_nlink(old_dir);
+ if (new_inode) {
+ drop_nlink(new_inode);
+ } else {
+ inc_nlink(new_dir);
+ ext4_update_dx_flag(new_dir);
+ ext4_mark_inode_dirty(handle, new_dir);
+ }
+ }
+ ext4_mark_inode_dirty(handle, old_dir);
+ if (new_inode) {
+ ext4_mark_inode_dirty(handle, new_inode);
+ if (!new_inode->i_nlink)
+ ext4_orphan_add(handle, new_inode);
+ }
+ retval = 0;
+
+end_rename:
+ brelse (dir_bh);
+ brelse (old_bh);
+ brelse (new_bh);
+ ext4_journal_stop(handle);
+ return retval;
+}
+
+/*
+ * directories can handle most operations...
+ */
+struct inode_operations ext4_dir_inode_operations = {
+ .create = ext4_create,
+ .lookup = ext4_lookup,
+ .link = ext4_link,
+ .unlink = ext4_unlink,
+ .symlink = ext4_symlink,
+ .mkdir = ext4_mkdir,
+ .rmdir = ext4_rmdir,
+ .mknod = ext4_mknod,
+ .rename = ext4_rename,
+ .setattr = ext4_setattr,
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = ext4_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+ .permission = ext4_permission,
+};
+
+struct inode_operations ext4_special_inode_operations = {
+ .setattr = ext4_setattr,
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = ext4_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+ .permission = ext4_permission,
+};
--- /dev/null
+/* linux/fs/ext4/namei.h
+ *
+ * Copyright (C) 2005 Simtec Electronics
+ * Ben Dooks <ben@simtec.co.uk>
+ *
+*/
+
+extern struct dentry *ext4_get_parent(struct dentry *child);
--- /dev/null
+/*
+ * linux/fs/ext4/resize.c
+ *
+ * Support for resizing an ext4 filesystem while it is mounted.
+ *
+ * Copyright (C) 2001, 2002 Andreas Dilger <adilger@clusterfs.com>
+ *
+ * This could probably be made into a module, because it is not often in use.
+ */
+
+
+#define EXT4FS_DEBUG
+
+#include <linux/sched.h>
+#include <linux/smp_lock.h>
+#include <linux/ext4_jbd2.h>
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+
+#define outside(b, first, last) ((b) < (first) || (b) >= (last))
+#define inside(b, first, last) ((b) >= (first) && (b) < (last))
+
+static int verify_group_input(struct super_block *sb,
+ struct ext4_new_group_data *input)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ ext4_fsblk_t start = ext4_blocks_count(es);
+ ext4_fsblk_t end = start + input->blocks_count;
+ unsigned group = input->group;
+ ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group;
+ unsigned overhead = ext4_bg_has_super(sb, group) ?
+ (1 + ext4_bg_num_gdb(sb, group) +
+ le16_to_cpu(es->s_reserved_gdt_blocks)) : 0;
+ ext4_fsblk_t metaend = start + overhead;
+ struct buffer_head *bh = NULL;
+ ext4_grpblk_t free_blocks_count, offset;
+ int err = -EINVAL;
+
+ input->free_blocks_count = free_blocks_count =
+ input->blocks_count - 2 - overhead - sbi->s_itb_per_group;
+
+ if (test_opt(sb, DEBUG))
+ printk(KERN_DEBUG "EXT4-fs: adding %s group %u: %u blocks "
+ "(%d free, %u reserved)\n",
+ ext4_bg_has_super(sb, input->group) ? "normal" :
+ "no-super", input->group, input->blocks_count,
+ free_blocks_count, input->reserved_blocks);
+
+ ext4_get_group_no_and_offset(sb, start, NULL, &offset);
+ if (group != sbi->s_groups_count)
+ ext4_warning(sb, __FUNCTION__,
+ "Cannot add at group %u (only %lu groups)",
+ input->group, sbi->s_groups_count);
+ else if (offset != 0)
+ ext4_warning(sb, __FUNCTION__, "Last group not full");
+ else if (input->reserved_blocks > input->blocks_count / 5)
+ ext4_warning(sb, __FUNCTION__, "Reserved blocks too high (%u)",
+ input->reserved_blocks);
+ else if (free_blocks_count < 0)
+ ext4_warning(sb, __FUNCTION__, "Bad blocks count %u",
+ input->blocks_count);
+ else if (!(bh = sb_bread(sb, end - 1)))
+ ext4_warning(sb, __FUNCTION__,
+ "Cannot read last block (%llu)",
+ end - 1);
+ else if (outside(input->block_bitmap, start, end))
+ ext4_warning(sb, __FUNCTION__,
+ "Block bitmap not in group (block %llu)",
+ input->block_bitmap);
+ else if (outside(input->inode_bitmap, start, end))
+ ext4_warning(sb, __FUNCTION__,
+ "Inode bitmap not in group (block %llu)",
+ input->inode_bitmap);
+ else if (outside(input->inode_table, start, end) ||
+ outside(itend - 1, start, end))
+ ext4_warning(sb, __FUNCTION__,
+ "Inode table not in group (blocks %llu-%llu)",
+ input->inode_table, itend - 1);
+ else if (input->inode_bitmap == input->block_bitmap)
+ ext4_warning(sb, __FUNCTION__,
+ "Block bitmap same as inode bitmap (%llu)",
+ input->block_bitmap);
+ else if (inside(input->block_bitmap, input->inode_table, itend))
+ ext4_warning(sb, __FUNCTION__,
+ "Block bitmap (%llu) in inode table (%llu-%llu)",
+ input->block_bitmap, input->inode_table, itend-1);
+ else if (inside(input->inode_bitmap, input->inode_table, itend))
+ ext4_warning(sb, __FUNCTION__,
+ "Inode bitmap (%llu) in inode table (%llu-%llu)",
+ input->inode_bitmap, input->inode_table, itend-1);
+ else if (inside(input->block_bitmap, start, metaend))
+ ext4_warning(sb, __FUNCTION__,
+ "Block bitmap (%llu) in GDT table"
+ " (%llu-%llu)",
+ input->block_bitmap, start, metaend - 1);
+ else if (inside(input->inode_bitmap, start, metaend))
+ ext4_warning(sb, __FUNCTION__,
+ "Inode bitmap (%llu) in GDT table"
+ " (%llu-%llu)",
+ input->inode_bitmap, start, metaend - 1);
+ else if (inside(input->inode_table, start, metaend) ||
+ inside(itend - 1, start, metaend))
+ ext4_warning(sb, __FUNCTION__,
+ "Inode table (%llu-%llu) overlaps"
+ "GDT table (%llu-%llu)",
+ input->inode_table, itend - 1, start, metaend - 1);
+ else
+ err = 0;
+ brelse(bh);
+
+ return err;
+}
+
+static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
+ ext4_fsblk_t blk)
+{
+ struct buffer_head *bh;
+ int err;
+
+ bh = sb_getblk(sb, blk);
+ if (!bh)
+ return ERR_PTR(-EIO);
+ if ((err = ext4_journal_get_write_access(handle, bh))) {
+ brelse(bh);
+ bh = ERR_PTR(err);
+ } else {
+ lock_buffer(bh);
+ memset(bh->b_data, 0, sb->s_blocksize);
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+ }
+
+ return bh;
+}
+
+/*
+ * To avoid calling the atomic setbit hundreds or thousands of times, we only
+ * need to use it within a single byte (to ensure we get endianness right).
+ * We can use memset for the rest of the bitmap as there are no other users.
+ */
+static void mark_bitmap_end(int start_bit, int end_bit, char *bitmap)
+{
+ int i;
+
+ if (start_bit >= end_bit)
+ return;
+
+ ext4_debug("mark end bits +%d through +%d used\n", start_bit, end_bit);
+ for (i = start_bit; i < ((start_bit + 7) & ~7UL); i++)
+ ext4_set_bit(i, bitmap);
+ if (i < end_bit)
+ memset(bitmap + (i >> 3), 0xff, (end_bit - i) >> 3);
+}
+
+/*
+ * Set up the block and inode bitmaps, and the inode table for the new group.
+ * This doesn't need to be part of the main transaction, since we are only
+ * changing blocks outside the actual filesystem. We still do journaling to
+ * ensure the recovery is correct in case of a failure just after resize.
+ * If any part of this fails, we simply abort the resize.
+ */
+static int setup_new_group_blocks(struct super_block *sb,
+ struct ext4_new_group_data *input)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_fsblk_t start = ext4_group_first_block_no(sb, input->group);
+ int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
+ le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0;
+ unsigned long gdblocks = ext4_bg_num_gdb(sb, input->group);
+ struct buffer_head *bh;
+ handle_t *handle;
+ ext4_fsblk_t block;
+ ext4_grpblk_t bit;
+ int i;
+ int err = 0, err2;
+
+ handle = ext4_journal_start_sb(sb, reserved_gdb + gdblocks +
+ 2 + sbi->s_itb_per_group);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ lock_super(sb);
+ if (input->group != sbi->s_groups_count) {
+ err = -EBUSY;
+ goto exit_journal;
+ }
+
+ if (IS_ERR(bh = bclean(handle, sb, input->block_bitmap))) {
+ err = PTR_ERR(bh);
+ goto exit_journal;
+ }
+
+ if (ext4_bg_has_super(sb, input->group)) {
+ ext4_debug("mark backup superblock %#04lx (+0)\n", start);
+ ext4_set_bit(0, bh->b_data);
+ }
+
+ /* Copy all of the GDT blocks into the backup in this group */
+ for (i = 0, bit = 1, block = start + 1;
+ i < gdblocks; i++, block++, bit++) {
+ struct buffer_head *gdb;
+
+ ext4_debug("update backup group %#04lx (+%d)\n", block, bit);
+
+ gdb = sb_getblk(sb, block);
+ if (!gdb) {
+ err = -EIO;
+ goto exit_bh;
+ }
+ if ((err = ext4_journal_get_write_access(handle, gdb))) {
+ brelse(gdb);
+ goto exit_bh;
+ }
+ lock_buffer(bh);
+ memcpy(gdb->b_data, sbi->s_group_desc[i]->b_data, bh->b_size);
+ set_buffer_uptodate(gdb);
+ unlock_buffer(bh);
+ ext4_journal_dirty_metadata(handle, gdb);
+ ext4_set_bit(bit, bh->b_data);
+ brelse(gdb);
+ }
+
+ /* Zero out all of the reserved backup group descriptor table blocks */
+ for (i = 0, bit = gdblocks + 1, block = start + bit;
+ i < reserved_gdb; i++, block++, bit++) {
+ struct buffer_head *gdb;
+
+ ext4_debug("clear reserved block %#04lx (+%d)\n", block, bit);
+
+ if (IS_ERR(gdb = bclean(handle, sb, block))) {
+ err = PTR_ERR(bh);
+ goto exit_bh;
+ }
+ ext4_journal_dirty_metadata(handle, gdb);
+ ext4_set_bit(bit, bh->b_data);
+ brelse(gdb);
+ }
+ ext4_debug("mark block bitmap %#04x (+%ld)\n", input->block_bitmap,
+ input->block_bitmap - start);
+ ext4_set_bit(input->block_bitmap - start, bh->b_data);
+ ext4_debug("mark inode bitmap %#04x (+%ld)\n", input->inode_bitmap,
+ input->inode_bitmap - start);
+ ext4_set_bit(input->inode_bitmap - start, bh->b_data);
+
+ /* Zero out all of the inode table blocks */
+ for (i = 0, block = input->inode_table, bit = block - start;
+ i < sbi->s_itb_per_group; i++, bit++, block++) {
+ struct buffer_head *it;
+
+ ext4_debug("clear inode block %#04lx (+%d)\n", block, bit);
+ if (IS_ERR(it = bclean(handle, sb, block))) {
+ err = PTR_ERR(it);
+ goto exit_bh;
+ }
+ ext4_journal_dirty_metadata(handle, it);
+ brelse(it);
+ ext4_set_bit(bit, bh->b_data);
+ }
+ mark_bitmap_end(input->blocks_count, EXT4_BLOCKS_PER_GROUP(sb),
+ bh->b_data);
+ ext4_journal_dirty_metadata(handle, bh);
+ brelse(bh);
+
+ /* Mark unused entries in inode bitmap used */
+ ext4_debug("clear inode bitmap %#04x (+%ld)\n",
+ input->inode_bitmap, input->inode_bitmap - start);
+ if (IS_ERR(bh = bclean(handle, sb, input->inode_bitmap))) {
+ err = PTR_ERR(bh);
+ goto exit_journal;
+ }
+
+ mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb),
+ bh->b_data);
+ ext4_journal_dirty_metadata(handle, bh);
+exit_bh:
+ brelse(bh);
+
+exit_journal:
+ unlock_super(sb);
+ if ((err2 = ext4_journal_stop(handle)) && !err)
+ err = err2;
+
+ return err;
+}
+
+
+/*
+ * Iterate through the groups which hold BACKUP superblock/GDT copies in an
+ * ext4 filesystem. The counters should be initialized to 1, 5, and 7 before
+ * calling this for the first time. In a sparse filesystem it will be the
+ * sequence of powers of 3, 5, and 7: 1, 3, 5, 7, 9, 25, 27, 49, 81, ...
+ * For a non-sparse filesystem it will be every group: 1, 2, 3, 4, ...
+ */
+static unsigned ext4_list_backups(struct super_block *sb, unsigned *three,
+ unsigned *five, unsigned *seven)
+{
+ unsigned *min = three;
+ int mult = 3;
+ unsigned ret;
+
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
+ ret = *min;
+ *min += 1;
+ return ret;
+ }
+
+ if (*five < *min) {
+ min = five;
+ mult = 5;
+ }
+ if (*seven < *min) {
+ min = seven;
+ mult = 7;
+ }
+
+ ret = *min;
+ *min *= mult;
+
+ return ret;
+}
+
+/*
+ * Check that all of the backup GDT blocks are held in the primary GDT block.
+ * It is assumed that they are stored in group order. Returns the number of
+ * groups in current filesystem that have BACKUPS, or -ve error code.
+ */
+static int verify_reserved_gdb(struct super_block *sb,
+ struct buffer_head *primary)
+{
+ const ext4_fsblk_t blk = primary->b_blocknr;
+ const unsigned long end = EXT4_SB(sb)->s_groups_count;
+ unsigned three = 1;
+ unsigned five = 5;
+ unsigned seven = 7;
+ unsigned grp;
+ __le32 *p = (__le32 *)primary->b_data;
+ int gdbackups = 0;
+
+ while ((grp = ext4_list_backups(sb, &three, &five, &seven)) < end) {
+ if (le32_to_cpu(*p++) !=
+ grp * EXT4_BLOCKS_PER_GROUP(sb) + blk){
+ ext4_warning(sb, __FUNCTION__,
+ "reserved GDT %llu"
+ " missing grp %d (%llu)",
+ blk, grp,
+ grp *
+ (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
+ blk);
+ return -EINVAL;
+ }
+ if (++gdbackups > EXT4_ADDR_PER_BLOCK(sb))
+ return -EFBIG;
+ }
+
+ return gdbackups;
+}
+
+/*
+ * Called when we need to bring a reserved group descriptor table block into
+ * use from the resize inode. The primary copy of the new GDT block currently
+ * is an indirect block (under the double indirect block in the resize inode).
+ * The new backup GDT blocks will be stored as leaf blocks in this indirect
+ * block, in group order. Even though we know all the block numbers we need,
+ * we check to ensure that the resize inode has actually reserved these blocks.
+ *
+ * Don't need to update the block bitmaps because the blocks are still in use.
+ *
+ * We get all of the error cases out of the way, so that we are sure to not
+ * fail once we start modifying the data on disk, because JBD has no rollback.
+ */
+static int add_new_gdb(handle_t *handle, struct inode *inode,
+ struct ext4_new_group_data *input,
+ struct buffer_head **primary)
+{
+ struct super_block *sb = inode->i_sb;
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ unsigned long gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
+ ext4_fsblk_t gdblock = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + gdb_num;
+ struct buffer_head **o_group_desc, **n_group_desc;
+ struct buffer_head *dind;
+ int gdbackups;
+ struct ext4_iloc iloc;
+ __le32 *data;
+ int err;
+
+ if (test_opt(sb, DEBUG))
+ printk(KERN_DEBUG
+ "EXT4-fs: ext4_add_new_gdb: adding group block %lu\n",
+ gdb_num);
+
+ /*
+ * If we are not using the primary superblock/GDT copy don't resize,
+ * because the user tools have no way of handling this. Probably a
+ * bad time to do it anyways.
+ */
+ if (EXT4_SB(sb)->s_sbh->b_blocknr !=
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) {
+ ext4_warning(sb, __FUNCTION__,
+ "won't resize using backup superblock at %llu",
+ (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr);
+ return -EPERM;
+ }
+
+ *primary = sb_bread(sb, gdblock);
+ if (!*primary)
+ return -EIO;
+
+ if ((gdbackups = verify_reserved_gdb(sb, *primary)) < 0) {
+ err = gdbackups;
+ goto exit_bh;
+ }
+
+ data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
+ dind = sb_bread(sb, le32_to_cpu(*data));
+ if (!dind) {
+ err = -EIO;
+ goto exit_bh;
+ }
+
+ data = (__le32 *)dind->b_data;
+ if (le32_to_cpu(data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)]) != gdblock) {
+ ext4_warning(sb, __FUNCTION__,
+ "new group %u GDT block %llu not reserved",
+ input->group, gdblock);
+ err = -EINVAL;
+ goto exit_dind;
+ }
+
+ if ((err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh)))
+ goto exit_dind;
+
+ if ((err = ext4_journal_get_write_access(handle, *primary)))
+ goto exit_sbh;
+
+ if ((err = ext4_journal_get_write_access(handle, dind)))
+ goto exit_primary;
+
+ /* ext4_reserve_inode_write() gets a reference on the iloc */
+ if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
+ goto exit_dindj;
+
+ n_group_desc = kmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
+ GFP_KERNEL);
+ if (!n_group_desc) {
+ err = -ENOMEM;
+ ext4_warning (sb, __FUNCTION__,
+ "not enough memory for %lu groups", gdb_num + 1);
+ goto exit_inode;
+ }
+
+ /*
+ * Finally, we have all of the possible failures behind us...
+ *
+ * Remove new GDT block from inode double-indirect block and clear out
+ * the new GDT block for use (which also "frees" the backup GDT blocks
+ * from the reserved inode). We don't need to change the bitmaps for
+ * these blocks, because they are marked as in-use from being in the
+ * reserved inode, and will become GDT blocks (primary and backup).
+ */
+ data[gdb_num % EXT4_ADDR_PER_BLOCK(sb)] = 0;
+ ext4_journal_dirty_metadata(handle, dind);
+ brelse(dind);
+ inode->i_blocks -= (gdbackups + 1) * sb->s_blocksize >> 9;
+ ext4_mark_iloc_dirty(handle, inode, &iloc);
+ memset((*primary)->b_data, 0, sb->s_blocksize);
+ ext4_journal_dirty_metadata(handle, *primary);
+
+ o_group_desc = EXT4_SB(sb)->s_group_desc;
+ memcpy(n_group_desc, o_group_desc,
+ EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *));
+ n_group_desc[gdb_num] = *primary;
+ EXT4_SB(sb)->s_group_desc = n_group_desc;
+ EXT4_SB(sb)->s_gdb_count++;
+ kfree(o_group_desc);
+
+ es->s_reserved_gdt_blocks =
+ cpu_to_le16(le16_to_cpu(es->s_reserved_gdt_blocks) - 1);
+ ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+
+ return 0;
+
+exit_inode:
+ //ext4_journal_release_buffer(handle, iloc.bh);
+ brelse(iloc.bh);
+exit_dindj:
+ //ext4_journal_release_buffer(handle, dind);
+exit_primary:
+ //ext4_journal_release_buffer(handle, *primary);
+exit_sbh:
+ //ext4_journal_release_buffer(handle, *primary);
+exit_dind:
+ brelse(dind);
+exit_bh:
+ brelse(*primary);
+
+ ext4_debug("leaving with error %d\n", err);
+ return err;
+}
+
+/*
+ * Called when we are adding a new group which has a backup copy of each of
+ * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks.
+ * We need to add these reserved backup GDT blocks to the resize inode, so
+ * that they are kept for future resizing and not allocated to files.
+ *
+ * Each reserved backup GDT block will go into a different indirect block.
+ * The indirect blocks are actually the primary reserved GDT blocks,
+ * so we know in advance what their block numbers are. We only get the
+ * double-indirect block to verify it is pointing to the primary reserved
+ * GDT blocks so we don't overwrite a data block by accident. The reserved
+ * backup GDT blocks are stored in their reserved primary GDT block.
+ */
+static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
+ struct ext4_new_group_data *input)
+{
+ struct super_block *sb = inode->i_sb;
+ int reserved_gdb =le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks);
+ struct buffer_head **primary;
+ struct buffer_head *dind;
+ struct ext4_iloc iloc;
+ ext4_fsblk_t blk;
+ __le32 *data, *end;
+ int gdbackups = 0;
+ int res, i;
+ int err;
+
+ primary = kmalloc(reserved_gdb * sizeof(*primary), GFP_KERNEL);
+ if (!primary)
+ return -ENOMEM;
+
+ data = EXT4_I(inode)->i_data + EXT4_DIND_BLOCK;
+ dind = sb_bread(sb, le32_to_cpu(*data));
+ if (!dind) {
+ err = -EIO;
+ goto exit_free;
+ }
+
+ blk = EXT4_SB(sb)->s_sbh->b_blocknr + 1 + EXT4_SB(sb)->s_gdb_count;
+ data = (__le32 *)dind->b_data + EXT4_SB(sb)->s_gdb_count;
+ end = (__le32 *)dind->b_data + EXT4_ADDR_PER_BLOCK(sb);
+
+ /* Get each reserved primary GDT block and verify it holds backups */
+ for (res = 0; res < reserved_gdb; res++, blk++) {
+ if (le32_to_cpu(*data) != blk) {
+ ext4_warning(sb, __FUNCTION__,
+ "reserved block %llu"
+ " not at offset %ld",
+ blk,
+ (long)(data - (__le32 *)dind->b_data));
+ err = -EINVAL;
+ goto exit_bh;
+ }
+ primary[res] = sb_bread(sb, blk);
+ if (!primary[res]) {
+ err = -EIO;
+ goto exit_bh;
+ }
+ if ((gdbackups = verify_reserved_gdb(sb, primary[res])) < 0) {
+ brelse(primary[res]);
+ err = gdbackups;
+ goto exit_bh;
+ }
+ if (++data >= end)
+ data = (__le32 *)dind->b_data;
+ }
+
+ for (i = 0; i < reserved_gdb; i++) {
+ if ((err = ext4_journal_get_write_access(handle, primary[i]))) {
+ /*
+ int j;
+ for (j = 0; j < i; j++)
+ ext4_journal_release_buffer(handle, primary[j]);
+ */
+ goto exit_bh;
+ }
+ }
+
+ if ((err = ext4_reserve_inode_write(handle, inode, &iloc)))
+ goto exit_bh;
+
+ /*
+ * Finally we can add each of the reserved backup GDT blocks from
+ * the new group to its reserved primary GDT block.
+ */
+ blk = input->group * EXT4_BLOCKS_PER_GROUP(sb);
+ for (i = 0; i < reserved_gdb; i++) {
+ int err2;
+ data = (__le32 *)primary[i]->b_data;
+ /* printk("reserving backup %lu[%u] = %lu\n",
+ primary[i]->b_blocknr, gdbackups,
+ blk + primary[i]->b_blocknr); */
+ data[gdbackups] = cpu_to_le32(blk + primary[i]->b_blocknr);
+ err2 = ext4_journal_dirty_metadata(handle, primary[i]);
+ if (!err)
+ err = err2;
+ }
+ inode->i_blocks += reserved_gdb * sb->s_blocksize >> 9;
+ ext4_mark_iloc_dirty(handle, inode, &iloc);
+
+exit_bh:
+ while (--res >= 0)
+ brelse(primary[res]);
+ brelse(dind);
+
+exit_free:
+ kfree(primary);
+
+ return err;
+}
+
+/*
+ * Update the backup copies of the ext4 metadata. These don't need to be part
+ * of the main resize transaction, because e2fsck will re-write them if there
+ * is a problem (basically only OOM will cause a problem). However, we
+ * _should_ update the backups if possible, in case the primary gets trashed
+ * for some reason and we need to run e2fsck from a backup superblock. The
+ * important part is that the new block and inode counts are in the backup
+ * superblocks, and the location of the new group metadata in the GDT backups.
+ *
+ * We do not need lock_super() for this, because these blocks are not
+ * otherwise touched by the filesystem code when it is mounted. We don't
+ * need to worry about last changing from sbi->s_groups_count, because the
+ * worst that can happen is that we do not copy the full number of backups
+ * at this time. The resize which changed s_groups_count will backup again.
+ */
+static void update_backups(struct super_block *sb,
+ int blk_off, char *data, int size)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ const unsigned long last = sbi->s_groups_count;
+ const int bpg = EXT4_BLOCKS_PER_GROUP(sb);
+ unsigned three = 1;
+ unsigned five = 5;
+ unsigned seven = 7;
+ unsigned group;
+ int rest = sb->s_blocksize - size;
+ handle_t *handle;
+ int err = 0, err2;
+
+ handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
+ if (IS_ERR(handle)) {
+ group = 1;
+ err = PTR_ERR(handle);
+ goto exit_err;
+ }
+
+ while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) {
+ struct buffer_head *bh;
+
+ /* Out of journal space, and can't get more - abort - so sad */
+ if (handle->h_buffer_credits == 0 &&
+ ext4_journal_extend(handle, EXT4_MAX_TRANS_DATA) &&
+ (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA)))
+ break;
+
+ bh = sb_getblk(sb, group * bpg + blk_off);
+ if (!bh) {
+ err = -EIO;
+ break;
+ }
+ ext4_debug("update metadata backup %#04lx\n",
+ (unsigned long)bh->b_blocknr);
+ if ((err = ext4_journal_get_write_access(handle, bh)))
+ break;
+ lock_buffer(bh);
+ memcpy(bh->b_data, data, size);
+ if (rest)
+ memset(bh->b_data + size, 0, rest);
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+ ext4_journal_dirty_metadata(handle, bh);
+ brelse(bh);
+ }
+ if ((err2 = ext4_journal_stop(handle)) && !err)
+ err = err2;
+
+ /*
+ * Ugh! Need to have e2fsck write the backup copies. It is too
+ * late to revert the resize, we shouldn't fail just because of
+ * the backup copies (they are only needed in case of corruption).
+ *
+ * However, if we got here we have a journal problem too, so we
+ * can't really start a transaction to mark the superblock.
+ * Chicken out and just set the flag on the hope it will be written
+ * to disk, and if not - we will simply wait until next fsck.
+ */
+exit_err:
+ if (err) {
+ ext4_warning(sb, __FUNCTION__,
+ "can't update backup for group %d (err %d), "
+ "forcing fsck on next reboot", group, err);
+ sbi->s_mount_state &= ~EXT4_VALID_FS;
+ sbi->s_es->s_state &= cpu_to_le16(~EXT4_VALID_FS);
+ mark_buffer_dirty(sbi->s_sbh);
+ }
+}
+
+/* Add group descriptor data to an existing or new group descriptor block.
+ * Ensure we handle all possible error conditions _before_ we start modifying
+ * the filesystem, because we cannot abort the transaction and not have it
+ * write the data to disk.
+ *
+ * If we are on a GDT block boundary, we need to get the reserved GDT block.
+ * Otherwise, we may need to add backup GDT blocks for a sparse group.
+ *
+ * We only need to hold the superblock lock while we are actually adding
+ * in the new group's counts to the superblock. Prior to that we have
+ * not really "added" the group at all. We re-check that we are still
+ * adding in the last group in case things have changed since verifying.
+ */
+int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ int reserved_gdb = ext4_bg_has_super(sb, input->group) ?
+ le16_to_cpu(es->s_reserved_gdt_blocks) : 0;
+ struct buffer_head *primary = NULL;
+ struct ext4_group_desc *gdp;
+ struct inode *inode = NULL;
+ handle_t *handle;
+ int gdb_off, gdb_num;
+ int err, err2;
+
+ gdb_num = input->group / EXT4_DESC_PER_BLOCK(sb);
+ gdb_off = input->group % EXT4_DESC_PER_BLOCK(sb);
+
+ if (gdb_off == 0 && !EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER)) {
+ ext4_warning(sb, __FUNCTION__,
+ "Can't resize non-sparse filesystem further");
+ return -EPERM;
+ }
+
+ if (ext4_blocks_count(es) + input->blocks_count <
+ ext4_blocks_count(es)) {
+ ext4_warning(sb, __FUNCTION__, "blocks_count overflow\n");
+ return -EINVAL;
+ }
+
+ if (le32_to_cpu(es->s_inodes_count) + EXT4_INODES_PER_GROUP(sb) <
+ le32_to_cpu(es->s_inodes_count)) {
+ ext4_warning(sb, __FUNCTION__, "inodes_count overflow\n");
+ return -EINVAL;
+ }
+
+ if (reserved_gdb || gdb_off == 0) {
+ if (!EXT4_HAS_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_COMPAT_RESIZE_INODE)){
+ ext4_warning(sb, __FUNCTION__,
+ "No reserved GDT blocks, can't resize");
+ return -EPERM;
+ }
+ inode = iget(sb, EXT4_RESIZE_INO);
+ if (!inode || is_bad_inode(inode)) {
+ ext4_warning(sb, __FUNCTION__,
+ "Error opening resize inode");
+ iput(inode);
+ return -ENOENT;
+ }
+ }
+
+ if ((err = verify_group_input(sb, input)))
+ goto exit_put;
+
+ if ((err = setup_new_group_blocks(sb, input)))
+ goto exit_put;
+
+ /*
+ * We will always be modifying at least the superblock and a GDT
+ * block. If we are adding a group past the last current GDT block,
+ * we will also modify the inode and the dindirect block. If we
+ * are adding a group with superblock/GDT backups we will also
+ * modify each of the reserved GDT dindirect blocks.
+ */
+ handle = ext4_journal_start_sb(sb,
+ ext4_bg_has_super(sb, input->group) ?
+ 3 + reserved_gdb : 4);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ goto exit_put;
+ }
+
+ lock_super(sb);
+ if (input->group != sbi->s_groups_count) {
+ ext4_warning(sb, __FUNCTION__,
+ "multiple resizers run on filesystem!");
+ err = -EBUSY;
+ goto exit_journal;
+ }
+
+ if ((err = ext4_journal_get_write_access(handle, sbi->s_sbh)))
+ goto exit_journal;
+
+ /*
+ * We will only either add reserved group blocks to a backup group
+ * or remove reserved blocks for the first group in a new group block.
+ * Doing both would be mean more complex code, and sane people don't
+ * use non-sparse filesystems anymore. This is already checked above.
+ */
+ if (gdb_off) {
+ primary = sbi->s_group_desc[gdb_num];
+ if ((err = ext4_journal_get_write_access(handle, primary)))
+ goto exit_journal;
+
+ if (reserved_gdb && ext4_bg_num_gdb(sb, input->group) &&
+ (err = reserve_backup_gdb(handle, inode, input)))
+ goto exit_journal;
+ } else if ((err = add_new_gdb(handle, inode, input, &primary)))
+ goto exit_journal;
+
+ /*
+ * OK, now we've set up the new group. Time to make it active.
+ *
+ * Current kernels don't lock all allocations via lock_super(),
+ * so we have to be safe wrt. concurrent accesses the group
+ * data. So we need to be careful to set all of the relevant
+ * group descriptor data etc. *before* we enable the group.
+ *
+ * The key field here is sbi->s_groups_count: as long as
+ * that retains its old value, nobody is going to access the new
+ * group.
+ *
+ * So first we update all the descriptor metadata for the new
+ * group; then we update the total disk blocks count; then we
+ * update the groups count to enable the group; then finally we
+ * update the free space counts so that the system can start
+ * using the new disk blocks.
+ */
+
+ /* Update group descriptor block for new group */
+ gdp = (struct ext4_group_desc *)primary->b_data + gdb_off;
+
+ ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
+ ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
+ ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
+ gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count);
+ gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb));
+
+ /*
+ * Make the new blocks and inodes valid next. We do this before
+ * increasing the group count so that once the group is enabled,
+ * all of its blocks and inodes are already valid.
+ *
+ * We always allocate group-by-group, then block-by-block or
+ * inode-by-inode within a group, so enabling these
+ * blocks/inodes before the group is live won't actually let us
+ * allocate the new space yet.
+ */
+ ext4_blocks_count_set(es, ext4_blocks_count(es) +
+ input->blocks_count);
+ es->s_inodes_count = cpu_to_le32(le32_to_cpu(es->s_inodes_count) +
+ EXT4_INODES_PER_GROUP(sb));
+
+ /*
+ * We need to protect s_groups_count against other CPUs seeing
+ * inconsistent state in the superblock.
+ *
+ * The precise rules we use are:
+ *
+ * * Writers of s_groups_count *must* hold lock_super
+ * AND
+ * * Writers must perform a smp_wmb() after updating all dependent
+ * data and before modifying the groups count
+ *
+ * * Readers must hold lock_super() over the access
+ * OR
+ * * Readers must perform an smp_rmb() after reading the groups count
+ * and before reading any dependent data.
+ *
+ * NB. These rules can be relaxed when checking the group count
+ * while freeing data, as we can only allocate from a block
+ * group after serialising against the group count, and we can
+ * only then free after serialising in turn against that
+ * allocation.
+ */
+ smp_wmb();
+
+ /* Update the global fs size fields */
+ sbi->s_groups_count++;
+
+ ext4_journal_dirty_metadata(handle, primary);
+
+ /* Update the reserved block counts only once the new group is
+ * active. */
+ ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
+ input->reserved_blocks);
+
+ /* Update the free space counts */
+ percpu_counter_mod(&sbi->s_freeblocks_counter,
+ input->free_blocks_count);
+ percpu_counter_mod(&sbi->s_freeinodes_counter,
+ EXT4_INODES_PER_GROUP(sb));
+
+ ext4_journal_dirty_metadata(handle, sbi->s_sbh);
+ sb->s_dirt = 1;
+
+exit_journal:
+ unlock_super(sb);
+ if ((err2 = ext4_journal_stop(handle)) && !err)
+ err = err2;
+ if (!err) {
+ update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es,
+ sizeof(struct ext4_super_block));
+ update_backups(sb, primary->b_blocknr, primary->b_data,
+ primary->b_size);
+ }
+exit_put:
+ iput(inode);
+ return err;
+} /* ext4_group_add */
+
+/* Extend the filesystem to the new number of blocks specified. This entry
+ * point is only used to extend the current filesystem to the end of the last
+ * existing group. It can be accessed via ioctl, or by "remount,resize=<size>"
+ * for emergencies (because it has no dependencies on reserved blocks).
+ *
+ * If we _really_ wanted, we could use default values to call ext4_group_add()
+ * allow the "remount" trick to work for arbitrary resizing, assuming enough
+ * GDT blocks are reserved to grow to the desired size.
+ */
+int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es,
+ ext4_fsblk_t n_blocks_count)
+{
+ ext4_fsblk_t o_blocks_count;
+ unsigned long o_groups_count;
+ ext4_grpblk_t last;
+ ext4_grpblk_t add;
+ struct buffer_head * bh;
+ handle_t *handle;
+ int err;
+ unsigned long freed_blocks;
+
+ /* We don't need to worry about locking wrt other resizers just
+ * yet: we're going to revalidate es->s_blocks_count after
+ * taking lock_super() below. */
+ o_blocks_count = ext4_blocks_count(es);
+ o_groups_count = EXT4_SB(sb)->s_groups_count;
+
+ if (test_opt(sb, DEBUG))
+ printk(KERN_DEBUG "EXT4-fs: extending last group from %llu uto %llu blocks\n",
+ o_blocks_count, n_blocks_count);
+
+ if (n_blocks_count == 0 || n_blocks_count == o_blocks_count)
+ return 0;
+
+ if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
+ printk(KERN_ERR "EXT4-fs: filesystem on %s:"
+ " too large to resize to %llu blocks safely\n",
+ sb->s_id, n_blocks_count);
+ if (sizeof(sector_t) < 8)
+ ext4_warning(sb, __FUNCTION__,
+ "CONFIG_LBD not enabled\n");
+ return -EINVAL;
+ }
+
+ if (n_blocks_count < o_blocks_count) {
+ ext4_warning(sb, __FUNCTION__,
+ "can't shrink FS - resize aborted");
+ return -EBUSY;
+ }
+
+ /* Handle the remaining blocks in the last group only. */
+ ext4_get_group_no_and_offset(sb, o_blocks_count, NULL, &last);
+
+ if (last == 0) {
+ ext4_warning(sb, __FUNCTION__,
+ "need to use ext2online to resize further");
+ return -EPERM;
+ }
+
+ add = EXT4_BLOCKS_PER_GROUP(sb) - last;
+
+ if (o_blocks_count + add < o_blocks_count) {
+ ext4_warning(sb, __FUNCTION__, "blocks_count overflow");
+ return -EINVAL;
+ }
+
+ if (o_blocks_count + add > n_blocks_count)
+ add = n_blocks_count - o_blocks_count;
+
+ if (o_blocks_count + add < n_blocks_count)
+ ext4_warning(sb, __FUNCTION__,
+ "will only finish group (%llu"
+ " blocks, %u new)",
+ o_blocks_count + add, add);
+
+ /* See if the device is actually as big as what was requested */
+ bh = sb_bread(sb, o_blocks_count + add -1);
+ if (!bh) {
+ ext4_warning(sb, __FUNCTION__,
+ "can't read last block, resize aborted");
+ return -ENOSPC;
+ }
+ brelse(bh);
+
+ /* We will update the superblock, one block bitmap, and
+ * one group descriptor via ext4_free_blocks().
+ */
+ handle = ext4_journal_start_sb(sb, 3);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ ext4_warning(sb, __FUNCTION__, "error %d on journal start",err);
+ goto exit_put;
+ }
+
+ lock_super(sb);
+ if (o_blocks_count != ext4_blocks_count(es)) {
+ ext4_warning(sb, __FUNCTION__,
+ "multiple resizers run on filesystem!");
+ unlock_super(sb);
+ err = -EBUSY;
+ goto exit_put;
+ }
+
+ if ((err = ext4_journal_get_write_access(handle,
+ EXT4_SB(sb)->s_sbh))) {
+ ext4_warning(sb, __FUNCTION__,
+ "error %d on journal write access", err);
+ unlock_super(sb);
+ ext4_journal_stop(handle);
+ goto exit_put;
+ }
+ ext4_blocks_count_set(es, o_blocks_count + add);
+ ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ sb->s_dirt = 1;
+ unlock_super(sb);
+ ext4_debug("freeing blocks %lu through %llu\n", o_blocks_count,
+ o_blocks_count + add);
+ ext4_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
+ ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
+ o_blocks_count + add);
+ if ((err = ext4_journal_stop(handle)))
+ goto exit_put;
+ if (test_opt(sb, DEBUG))
+ printk(KERN_DEBUG "EXT4-fs: extended group to %llu blocks\n",
+ ext4_blocks_count(es));
+ update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es,
+ sizeof(struct ext4_super_block));
+exit_put:
+ return err;
+} /* ext4_group_extend */
--- /dev/null
+/*
+ * linux/fs/ext4/super.c
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/fs/minix/inode.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * Big-endian to little-endian byte-swapping/bitmaps by
+ * David S. Miller (davem@caip.rutgers.edu), 1995
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/parser.h>
+#include <linux/smp_lock.h>
+#include <linux/buffer_head.h>
+#include <linux/vfs.h>
+#include <linux/random.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/quotaops.h>
+#include <linux/seq_file.h>
+
+#include <asm/uaccess.h>
+
+#include "xattr.h"
+#include "acl.h"
+#include "namei.h"
+
+static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
+ unsigned long journal_devnum);
+static int ext4_create_journal(struct super_block *, struct ext4_super_block *,
+ unsigned int);
+static void ext4_commit_super (struct super_block * sb,
+ struct ext4_super_block * es,
+ int sync);
+static void ext4_mark_recovery_complete(struct super_block * sb,
+ struct ext4_super_block * es);
+static void ext4_clear_journal_err(struct super_block * sb,
+ struct ext4_super_block * es);
+static int ext4_sync_fs(struct super_block *sb, int wait);
+static const char *ext4_decode_error(struct super_block * sb, int errno,
+ char nbuf[16]);
+static int ext4_remount (struct super_block * sb, int * flags, char * data);
+static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf);
+static void ext4_unlockfs(struct super_block *sb);
+static void ext4_write_super (struct super_block * sb);
+static void ext4_write_super_lockfs(struct super_block *sb);
+
+
+ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
+ struct ext4_group_desc *bg)
+{
+ return le32_to_cpu(bg->bg_block_bitmap) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (ext4_fsblk_t)le32_to_cpu(bg->bg_block_bitmap_hi) << 32 : 0);
+}
+
+ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
+ struct ext4_group_desc *bg)
+{
+ return le32_to_cpu(bg->bg_inode_bitmap) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_bitmap_hi) << 32 : 0);
+}
+
+ext4_fsblk_t ext4_inode_table(struct super_block *sb,
+ struct ext4_group_desc *bg)
+{
+ return le32_to_cpu(bg->bg_inode_table) |
+ (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
+ (ext4_fsblk_t)le32_to_cpu(bg->bg_inode_table_hi) << 32 : 0);
+}
+
+void ext4_block_bitmap_set(struct super_block *sb,
+ struct ext4_group_desc *bg, ext4_fsblk_t blk)
+{
+ bg->bg_block_bitmap = cpu_to_le32((u32)blk);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_block_bitmap_hi = cpu_to_le32(blk >> 32);
+}
+
+void ext4_inode_bitmap_set(struct super_block *sb,
+ struct ext4_group_desc *bg, ext4_fsblk_t blk)
+{
+ bg->bg_inode_bitmap = cpu_to_le32((u32)blk);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_inode_bitmap_hi = cpu_to_le32(blk >> 32);
+}
+
+void ext4_inode_table_set(struct super_block *sb,
+ struct ext4_group_desc *bg, ext4_fsblk_t blk)
+{
+ bg->bg_inode_table = cpu_to_le32((u32)blk);
+ if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
+ bg->bg_inode_table_hi = cpu_to_le32(blk >> 32);
+}
+
+/*
+ * Wrappers for jbd2_journal_start/end.
+ *
+ * The only special thing we need to do here is to make sure that all
+ * journal_end calls result in the superblock being marked dirty, so
+ * that sync() will call the filesystem's write_super callback if
+ * appropriate.
+ */
+handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
+{
+ journal_t *journal;
+
+ if (sb->s_flags & MS_RDONLY)
+ return ERR_PTR(-EROFS);
+
+ /* Special case here: if the journal has aborted behind our
+ * backs (eg. EIO in the commit thread), then we still need to
+ * take the FS itself readonly cleanly. */
+ journal = EXT4_SB(sb)->s_journal;
+ if (is_journal_aborted(journal)) {
+ ext4_abort(sb, __FUNCTION__,
+ "Detected aborted journal");
+ return ERR_PTR(-EROFS);
+ }
+
+ return jbd2_journal_start(journal, nblocks);
+}
+
+/*
+ * The only special thing we need to do here is to make sure that all
+ * jbd2_journal_stop calls result in the superblock being marked dirty, so
+ * that sync() will call the filesystem's write_super callback if
+ * appropriate.
+ */
+int __ext4_journal_stop(const char *where, handle_t *handle)
+{
+ struct super_block *sb;
+ int err;
+ int rc;
+
+ sb = handle->h_transaction->t_journal->j_private;
+ err = handle->h_err;
+ rc = jbd2_journal_stop(handle);
+
+ if (!err)
+ err = rc;
+ if (err)
+ __ext4_std_error(sb, where, err);
+ return err;
+}
+
+void ext4_journal_abort_handle(const char *caller, const char *err_fn,
+ struct buffer_head *bh, handle_t *handle, int err)
+{
+ char nbuf[16];
+ const char *errstr = ext4_decode_error(NULL, err, nbuf);
+
+ if (bh)
+ BUFFER_TRACE(bh, "abort");
+
+ if (!handle->h_err)
+ handle->h_err = err;
+
+ if (is_handle_aborted(handle))
+ return;
+
+ printk(KERN_ERR "%s: aborting transaction: %s in %s\n",
+ caller, errstr, err_fn);
+
+ jbd2_journal_abort_handle(handle);
+}
+
+/* Deal with the reporting of failure conditions on a filesystem such as
+ * inconsistencies detected or read IO failures.
+ *
+ * On ext2, we can store the error state of the filesystem in the
+ * superblock. That is not possible on ext4, because we may have other
+ * write ordering constraints on the superblock which prevent us from
+ * writing it out straight away; and given that the journal is about to
+ * be aborted, we can't rely on the current, or future, transactions to
+ * write out the superblock safely.
+ *
+ * We'll just use the jbd2_journal_abort() error code to record an error in
+ * the journal instead. On recovery, the journal will compain about
+ * that error until we've noted it down and cleared it.
+ */
+
+static void ext4_handle_error(struct super_block *sb)
+{
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+
+ if (sb->s_flags & MS_RDONLY)
+ return;
+
+ if (!test_opt (sb, ERRORS_CONT)) {
+ journal_t *journal = EXT4_SB(sb)->s_journal;
+
+ EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
+ if (journal)
+ jbd2_journal_abort(journal, -EIO);
+ }
+ if (test_opt (sb, ERRORS_RO)) {
+ printk (KERN_CRIT "Remounting filesystem read-only\n");
+ sb->s_flags |= MS_RDONLY;
+ }
+ ext4_commit_super(sb, es, 1);
+ if (test_opt(sb, ERRORS_PANIC))
+ panic("EXT4-fs (device %s): panic forced after error\n",
+ sb->s_id);
+}
+
+void ext4_error (struct super_block * sb, const char * function,
+ const char * fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s: ",sb->s_id, function);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ ext4_handle_error(sb);
+}
+
+static const char *ext4_decode_error(struct super_block * sb, int errno,
+ char nbuf[16])
+{
+ char *errstr = NULL;
+
+ switch (errno) {
+ case -EIO:
+ errstr = "IO failure";
+ break;
+ case -ENOMEM:
+ errstr = "Out of memory";
+ break;
+ case -EROFS:
+ if (!sb || EXT4_SB(sb)->s_journal->j_flags & JBD2_ABORT)
+ errstr = "Journal has aborted";
+ else
+ errstr = "Readonly filesystem";
+ break;
+ default:
+ /* If the caller passed in an extra buffer for unknown
+ * errors, textualise them now. Else we just return
+ * NULL. */
+ if (nbuf) {
+ /* Check for truncated error codes... */
+ if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
+ errstr = nbuf;
+ }
+ break;
+ }
+
+ return errstr;
+}
+
+/* __ext4_std_error decodes expected errors from journaling functions
+ * automatically and invokes the appropriate error response. */
+
+void __ext4_std_error (struct super_block * sb, const char * function,
+ int errno)
+{
+ char nbuf[16];
+ const char *errstr;
+
+ /* Special case: if the error is EROFS, and we're not already
+ * inside a transaction, then there's really no point in logging
+ * an error. */
+ if (errno == -EROFS && journal_current_handle() == NULL &&
+ (sb->s_flags & MS_RDONLY))
+ return;
+
+ errstr = ext4_decode_error(sb, errno, nbuf);
+ printk (KERN_CRIT "EXT4-fs error (device %s) in %s: %s\n",
+ sb->s_id, function, errstr);
+
+ ext4_handle_error(sb);
+}
+
+/*
+ * ext4_abort is a much stronger failure handler than ext4_error. The
+ * abort function may be used to deal with unrecoverable failures such
+ * as journal IO errors or ENOMEM at a critical moment in log management.
+ *
+ * We unconditionally force the filesystem into an ABORT|READONLY state,
+ * unless the error response on the fs has been set to panic in which
+ * case we take the easy way out and panic immediately.
+ */
+
+void ext4_abort (struct super_block * sb, const char * function,
+ const char * fmt, ...)
+{
+ va_list args;
+
+ printk (KERN_CRIT "ext4_abort called.\n");
+
+ va_start(args, fmt);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s: ",sb->s_id, function);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+
+ if (test_opt(sb, ERRORS_PANIC))
+ panic("EXT4-fs panic from previous error\n");
+
+ if (sb->s_flags & MS_RDONLY)
+ return;
+
+ printk(KERN_CRIT "Remounting filesystem read-only\n");
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ sb->s_flags |= MS_RDONLY;
+ EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
+ jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+}
+
+void ext4_warning (struct super_block * sb, const char * function,
+ const char * fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ printk(KERN_WARNING "EXT4-fs warning (device %s): %s: ",
+ sb->s_id, function);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+}
+
+void ext4_update_dynamic_rev(struct super_block *sb)
+{
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ if (le32_to_cpu(es->s_rev_level) > EXT4_GOOD_OLD_REV)
+ return;
+
+ ext4_warning(sb, __FUNCTION__,
+ "updating to rev %d because of new feature flag, "
+ "running e2fsck is recommended",
+ EXT4_DYNAMIC_REV);
+
+ es->s_first_ino = cpu_to_le32(EXT4_GOOD_OLD_FIRST_INO);
+ es->s_inode_size = cpu_to_le16(EXT4_GOOD_OLD_INODE_SIZE);
+ es->s_rev_level = cpu_to_le32(EXT4_DYNAMIC_REV);
+ /* leave es->s_feature_*compat flags alone */
+ /* es->s_uuid will be set by e2fsck if empty */
+
+ /*
+ * The rest of the superblock fields should be zero, and if not it
+ * means they are likely already in use, so leave them alone. We
+ * can leave it up to e2fsck to clean up any inconsistencies there.
+ */
+}
+
+/*
+ * Open the external journal device
+ */
+static struct block_device *ext4_blkdev_get(dev_t dev)
+{
+ struct block_device *bdev;
+ char b[BDEVNAME_SIZE];
+
+ bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+ if (IS_ERR(bdev))
+ goto fail;
+ return bdev;
+
+fail:
+ printk(KERN_ERR "EXT4: failed to open journal device %s: %ld\n",
+ __bdevname(dev, b), PTR_ERR(bdev));
+ return NULL;
+}
+
+/*
+ * Release the journal device
+ */
+static int ext4_blkdev_put(struct block_device *bdev)
+{
+ bd_release(bdev);
+ return blkdev_put(bdev);
+}
+
+static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
+{
+ struct block_device *bdev;
+ int ret = -ENODEV;
+
+ bdev = sbi->journal_bdev;
+ if (bdev) {
+ ret = ext4_blkdev_put(bdev);
+ sbi->journal_bdev = NULL;
+ }
+ return ret;
+}
+
+static inline struct inode *orphan_list_entry(struct list_head *l)
+{
+ return &list_entry(l, struct ext4_inode_info, i_orphan)->vfs_inode;
+}
+
+static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi)
+{
+ struct list_head *l;
+
+ printk(KERN_ERR "sb orphan head is %d\n",
+ le32_to_cpu(sbi->s_es->s_last_orphan));
+
+ printk(KERN_ERR "sb_info orphan list:\n");
+ list_for_each(l, &sbi->s_orphan) {
+ struct inode *inode = orphan_list_entry(l);
+ printk(KERN_ERR " "
+ "inode %s:%lu at %p: mode %o, nlink %d, next %d\n",
+ inode->i_sb->s_id, inode->i_ino, inode,
+ inode->i_mode, inode->i_nlink,
+ NEXT_ORPHAN(inode));
+ }
+}
+
+static void ext4_put_super (struct super_block * sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ int i;
+
+ ext4_ext_release(sb);
+ ext4_xattr_put_super(sb);
+ jbd2_journal_destroy(sbi->s_journal);
+ if (!(sb->s_flags & MS_RDONLY)) {
+ EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ es->s_state = cpu_to_le16(sbi->s_mount_state);
+ BUFFER_TRACE(sbi->s_sbh, "marking dirty");
+ mark_buffer_dirty(sbi->s_sbh);
+ ext4_commit_super(sb, es, 1);
+ }
+
+ for (i = 0; i < sbi->s_gdb_count; i++)
+ brelse(sbi->s_group_desc[i]);
+ kfree(sbi->s_group_desc);
+ percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
+ brelse(sbi->s_sbh);
+#ifdef CONFIG_QUOTA
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(sbi->s_qf_names[i]);
+#endif
+
+ /* Debugging code just in case the in-memory inode orphan list
+ * isn't empty. The on-disk one can be non-empty if we've
+ * detected an error and taken the fs readonly, but the
+ * in-memory list had better be clean by this point. */
+ if (!list_empty(&sbi->s_orphan))
+ dump_orphan_list(sb, sbi);
+ J_ASSERT(list_empty(&sbi->s_orphan));
+
+ invalidate_bdev(sb->s_bdev, 0);
+ if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) {
+ /*
+ * Invalidate the journal device's buffers. We don't want them
+ * floating about in memory - the physical journal device may
+ * hotswapped, and it breaks the `ro-after' testing code.
+ */
+ sync_blockdev(sbi->journal_bdev);
+ invalidate_bdev(sbi->journal_bdev, 0);
+ ext4_blkdev_remove(sbi);
+ }
+ sb->s_fs_info = NULL;
+ kfree(sbi);
+ return;
+}
+
+static kmem_cache_t *ext4_inode_cachep;
+
+/*
+ * Called inside transaction, so use GFP_NOFS
+ */
+static struct inode *ext4_alloc_inode(struct super_block *sb)
+{
+ struct ext4_inode_info *ei;
+
+ ei = kmem_cache_alloc(ext4_inode_cachep, SLAB_NOFS);
+ if (!ei)
+ return NULL;
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+ ei->i_acl = EXT4_ACL_NOT_CACHED;
+ ei->i_default_acl = EXT4_ACL_NOT_CACHED;
+#endif
+ ei->i_block_alloc_info = NULL;
+ ei->vfs_inode.i_version = 1;
+ memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
+ return &ei->vfs_inode;
+}
+
+static void ext4_destroy_inode(struct inode *inode)
+{
+ kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
+}
+
+static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+{
+ struct ext4_inode_info *ei = (struct ext4_inode_info *) foo;
+
+ if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
+ SLAB_CTOR_CONSTRUCTOR) {
+ INIT_LIST_HEAD(&ei->i_orphan);
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ init_rwsem(&ei->xattr_sem);
+#endif
+ mutex_init(&ei->truncate_mutex);
+ inode_init_once(&ei->vfs_inode);
+ }
+}
+
+static int init_inodecache(void)
+{
+ ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
+ sizeof(struct ext4_inode_info),
+ 0, (SLAB_RECLAIM_ACCOUNT|
+ SLAB_MEM_SPREAD),
+ init_once, NULL);
+ if (ext4_inode_cachep == NULL)
+ return -ENOMEM;
+ return 0;
+}
+
+static void destroy_inodecache(void)
+{
+ kmem_cache_destroy(ext4_inode_cachep);
+}
+
+static void ext4_clear_inode(struct inode *inode)
+{
+ struct ext4_block_alloc_info *rsv = EXT4_I(inode)->i_block_alloc_info;
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+ if (EXT4_I(inode)->i_acl &&
+ EXT4_I(inode)->i_acl != EXT4_ACL_NOT_CACHED) {
+ posix_acl_release(EXT4_I(inode)->i_acl);
+ EXT4_I(inode)->i_acl = EXT4_ACL_NOT_CACHED;
+ }
+ if (EXT4_I(inode)->i_default_acl &&
+ EXT4_I(inode)->i_default_acl != EXT4_ACL_NOT_CACHED) {
+ posix_acl_release(EXT4_I(inode)->i_default_acl);
+ EXT4_I(inode)->i_default_acl = EXT4_ACL_NOT_CACHED;
+ }
+#endif
+ ext4_discard_reservation(inode);
+ EXT4_I(inode)->i_block_alloc_info = NULL;
+ if (unlikely(rsv))
+ kfree(rsv);
+}
+
+static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb)
+{
+#if defined(CONFIG_QUOTA)
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (sbi->s_jquota_fmt)
+ seq_printf(seq, ",jqfmt=%s",
+ (sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0");
+
+ if (sbi->s_qf_names[USRQUOTA])
+ seq_printf(seq, ",usrjquota=%s", sbi->s_qf_names[USRQUOTA]);
+
+ if (sbi->s_qf_names[GRPQUOTA])
+ seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
+
+ if (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA)
+ seq_puts(seq, ",usrquota");
+
+ if (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)
+ seq_puts(seq, ",grpquota");
+#endif
+}
+
+static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
+{
+ struct super_block *sb = vfs->mnt_sb;
+
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ seq_puts(seq, ",data=journal");
+ else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ seq_puts(seq, ",data=ordered");
+ else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+ seq_puts(seq, ",data=writeback");
+
+ ext4_show_quota_options(seq, sb);
+
+ return 0;
+}
+
+
+static struct dentry *ext4_get_dentry(struct super_block *sb, void *vobjp)
+{
+ __u32 *objp = vobjp;
+ unsigned long ino = objp[0];
+ __u32 generation = objp[1];
+ struct inode *inode;
+ struct dentry *result;
+
+ if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
+ return ERR_PTR(-ESTALE);
+ if (ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
+ return ERR_PTR(-ESTALE);
+
+ /* iget isn't really right if the inode is currently unallocated!!
+ *
+ * ext4_read_inode will return a bad_inode if the inode had been
+ * deleted, so we should be safe.
+ *
+ * Currently we don't know the generation for parent directory, so
+ * a generation of 0 means "accept any"
+ */
+ inode = iget(sb, ino);
+ if (inode == NULL)
+ return ERR_PTR(-ENOMEM);
+ if (is_bad_inode(inode) ||
+ (generation && inode->i_generation != generation)) {
+ iput(inode);
+ return ERR_PTR(-ESTALE);
+ }
+ /* now to find a dentry.
+ * If possible, get a well-connected one
+ */
+ result = d_alloc_anon(inode);
+ if (!result) {
+ iput(inode);
+ return ERR_PTR(-ENOMEM);
+ }
+ return result;
+}
+
+#ifdef CONFIG_QUOTA
+#define QTYPE2NAME(t) ((t)==USRQUOTA?"user":"group")
+#define QTYPE2MOPT(on, t) ((t)==USRQUOTA?((on)##USRJQUOTA):((on)##GRPJQUOTA))
+
+static int ext4_dquot_initialize(struct inode *inode, int type);
+static int ext4_dquot_drop(struct inode *inode);
+static int ext4_write_dquot(struct dquot *dquot);
+static int ext4_acquire_dquot(struct dquot *dquot);
+static int ext4_release_dquot(struct dquot *dquot);
+static int ext4_mark_dquot_dirty(struct dquot *dquot);
+static int ext4_write_info(struct super_block *sb, int type);
+static int ext4_quota_on(struct super_block *sb, int type, int format_id, char *path);
+static int ext4_quota_on_mount(struct super_block *sb, int type);
+static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
+ size_t len, loff_t off);
+static ssize_t ext4_quota_write(struct super_block *sb, int type,
+ const char *data, size_t len, loff_t off);
+
+static struct dquot_operations ext4_quota_operations = {
+ .initialize = ext4_dquot_initialize,
+ .drop = ext4_dquot_drop,
+ .alloc_space = dquot_alloc_space,
+ .alloc_inode = dquot_alloc_inode,
+ .free_space = dquot_free_space,
+ .free_inode = dquot_free_inode,
+ .transfer = dquot_transfer,
+ .write_dquot = ext4_write_dquot,
+ .acquire_dquot = ext4_acquire_dquot,
+ .release_dquot = ext4_release_dquot,
+ .mark_dirty = ext4_mark_dquot_dirty,
+ .write_info = ext4_write_info
+};
+
+static struct quotactl_ops ext4_qctl_operations = {
+ .quota_on = ext4_quota_on,
+ .quota_off = vfs_quota_off,
+ .quota_sync = vfs_quota_sync,
+ .get_info = vfs_get_dqinfo,
+ .set_info = vfs_set_dqinfo,
+ .get_dqblk = vfs_get_dqblk,
+ .set_dqblk = vfs_set_dqblk
+};
+#endif
+
+static struct super_operations ext4_sops = {
+ .alloc_inode = ext4_alloc_inode,
+ .destroy_inode = ext4_destroy_inode,
+ .read_inode = ext4_read_inode,
+ .write_inode = ext4_write_inode,
+ .dirty_inode = ext4_dirty_inode,
+ .delete_inode = ext4_delete_inode,
+ .put_super = ext4_put_super,
+ .write_super = ext4_write_super,
+ .sync_fs = ext4_sync_fs,
+ .write_super_lockfs = ext4_write_super_lockfs,
+ .unlockfs = ext4_unlockfs,
+ .statfs = ext4_statfs,
+ .remount_fs = ext4_remount,
+ .clear_inode = ext4_clear_inode,
+ .show_options = ext4_show_options,
+#ifdef CONFIG_QUOTA
+ .quota_read = ext4_quota_read,
+ .quota_write = ext4_quota_write,
+#endif
+};
+
+static struct export_operations ext4_export_ops = {
+ .get_parent = ext4_get_parent,
+ .get_dentry = ext4_get_dentry,
+};
+
+enum {
+ Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
+ Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, Opt_err_ro,
+ Opt_nouid32, Opt_nocheck, Opt_debug, Opt_oldalloc, Opt_orlov,
+ Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
+ Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
+ Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
+ Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+ Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
+ Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
+ Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
+ Opt_grpquota, Opt_extents,
+};
+
+static match_table_t tokens = {
+ {Opt_bsd_df, "bsddf"},
+ {Opt_minix_df, "minixdf"},
+ {Opt_grpid, "grpid"},
+ {Opt_grpid, "bsdgroups"},
+ {Opt_nogrpid, "nogrpid"},
+ {Opt_nogrpid, "sysvgroups"},
+ {Opt_resgid, "resgid=%u"},
+ {Opt_resuid, "resuid=%u"},
+ {Opt_sb, "sb=%u"},
+ {Opt_err_cont, "errors=continue"},
+ {Opt_err_panic, "errors=panic"},
+ {Opt_err_ro, "errors=remount-ro"},
+ {Opt_nouid32, "nouid32"},
+ {Opt_nocheck, "nocheck"},
+ {Opt_nocheck, "check=none"},
+ {Opt_debug, "debug"},
+ {Opt_oldalloc, "oldalloc"},
+ {Opt_orlov, "orlov"},
+ {Opt_user_xattr, "user_xattr"},
+ {Opt_nouser_xattr, "nouser_xattr"},
+ {Opt_acl, "acl"},
+ {Opt_noacl, "noacl"},
+ {Opt_reservation, "reservation"},
+ {Opt_noreservation, "noreservation"},
+ {Opt_noload, "noload"},
+ {Opt_nobh, "nobh"},
+ {Opt_bh, "bh"},
+ {Opt_commit, "commit=%u"},
+ {Opt_journal_update, "journal=update"},
+ {Opt_journal_inum, "journal=%u"},
+ {Opt_journal_dev, "journal_dev=%u"},
+ {Opt_abort, "abort"},
+ {Opt_data_journal, "data=journal"},
+ {Opt_data_ordered, "data=ordered"},
+ {Opt_data_writeback, "data=writeback"},
+ {Opt_offusrjquota, "usrjquota="},
+ {Opt_usrjquota, "usrjquota=%s"},
+ {Opt_offgrpjquota, "grpjquota="},
+ {Opt_grpjquota, "grpjquota=%s"},
+ {Opt_jqfmt_vfsold, "jqfmt=vfsold"},
+ {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
+ {Opt_grpquota, "grpquota"},
+ {Opt_noquota, "noquota"},
+ {Opt_quota, "quota"},
+ {Opt_usrquota, "usrquota"},
+ {Opt_barrier, "barrier=%u"},
+ {Opt_extents, "extents"},
+ {Opt_err, NULL},
+ {Opt_resize, "resize"},
+};
+
+static ext4_fsblk_t get_sb_block(void **data)
+{
+ ext4_fsblk_t sb_block;
+ char *options = (char *) *data;
+
+ if (!options || strncmp(options, "sb=", 3) != 0)
+ return 1; /* Default location */
+ options += 3;
+ /*todo: use simple_strtoll with >32bit ext4 */
+ sb_block = simple_strtoul(options, &options, 0);
+ if (*options && *options != ',') {
+ printk("EXT4-fs: Invalid sb specification: %s\n",
+ (char *) *data);
+ return 1;
+ }
+ if (*options == ',')
+ options++;
+ *data = (void *) options;
+ return sb_block;
+}
+
+static int parse_options (char *options, struct super_block *sb,
+ unsigned int *inum, unsigned long *journal_devnum,
+ ext4_fsblk_t *n_blocks_count, int is_remount)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ char * p;
+ substring_t args[MAX_OPT_ARGS];
+ int data_opt = 0;
+ int option;
+#ifdef CONFIG_QUOTA
+ int qtype;
+ char *qname;
+#endif
+
+ if (!options)
+ return 1;
+
+ while ((p = strsep (&options, ",")) != NULL) {
+ int token;
+ if (!*p)
+ continue;
+
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_bsd_df:
+ clear_opt (sbi->s_mount_opt, MINIX_DF);
+ break;
+ case Opt_minix_df:
+ set_opt (sbi->s_mount_opt, MINIX_DF);
+ break;
+ case Opt_grpid:
+ set_opt (sbi->s_mount_opt, GRPID);
+ break;
+ case Opt_nogrpid:
+ clear_opt (sbi->s_mount_opt, GRPID);
+ break;
+ case Opt_resuid:
+ if (match_int(&args[0], &option))
+ return 0;
+ sbi->s_resuid = option;
+ break;
+ case Opt_resgid:
+ if (match_int(&args[0], &option))
+ return 0;
+ sbi->s_resgid = option;
+ break;
+ case Opt_sb:
+ /* handled by get_sb_block() instead of here */
+ /* *sb_block = match_int(&args[0]); */
+ break;
+ case Opt_err_panic:
+ clear_opt (sbi->s_mount_opt, ERRORS_CONT);
+ clear_opt (sbi->s_mount_opt, ERRORS_RO);
+ set_opt (sbi->s_mount_opt, ERRORS_PANIC);
+ break;
+ case Opt_err_ro:
+ clear_opt (sbi->s_mount_opt, ERRORS_CONT);
+ clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
+ set_opt (sbi->s_mount_opt, ERRORS_RO);
+ break;
+ case Opt_err_cont:
+ clear_opt (sbi->s_mount_opt, ERRORS_RO);
+ clear_opt (sbi->s_mount_opt, ERRORS_PANIC);
+ set_opt (sbi->s_mount_opt, ERRORS_CONT);
+ break;
+ case Opt_nouid32:
+ set_opt (sbi->s_mount_opt, NO_UID32);
+ break;
+ case Opt_nocheck:
+ clear_opt (sbi->s_mount_opt, CHECK);
+ break;
+ case Opt_debug:
+ set_opt (sbi->s_mount_opt, DEBUG);
+ break;
+ case Opt_oldalloc:
+ set_opt (sbi->s_mount_opt, OLDALLOC);
+ break;
+ case Opt_orlov:
+ clear_opt (sbi->s_mount_opt, OLDALLOC);
+ break;
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ case Opt_user_xattr:
+ set_opt (sbi->s_mount_opt, XATTR_USER);
+ break;
+ case Opt_nouser_xattr:
+ clear_opt (sbi->s_mount_opt, XATTR_USER);
+ break;
+#else
+ case Opt_user_xattr:
+ case Opt_nouser_xattr:
+ printk("EXT4 (no)user_xattr options not supported\n");
+ break;
+#endif
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+ case Opt_acl:
+ set_opt(sbi->s_mount_opt, POSIX_ACL);
+ break;
+ case Opt_noacl:
+ clear_opt(sbi->s_mount_opt, POSIX_ACL);
+ break;
+#else
+ case Opt_acl:
+ case Opt_noacl:
+ printk("EXT4 (no)acl options not supported\n");
+ break;
+#endif
+ case Opt_reservation:
+ set_opt(sbi->s_mount_opt, RESERVATION);
+ break;
+ case Opt_noreservation:
+ clear_opt(sbi->s_mount_opt, RESERVATION);
+ break;
+ case Opt_journal_update:
+ /* @@@ FIXME */
+ /* Eventually we will want to be able to create
+ a journal file here. For now, only allow the
+ user to specify an existing inode to be the
+ journal file. */
+ if (is_remount) {
+ printk(KERN_ERR "EXT4-fs: cannot specify "
+ "journal on remount\n");
+ return 0;
+ }
+ set_opt (sbi->s_mount_opt, UPDATE_JOURNAL);
+ break;
+ case Opt_journal_inum:
+ if (is_remount) {
+ printk(KERN_ERR "EXT4-fs: cannot specify "
+ "journal on remount\n");
+ return 0;
+ }
+ if (match_int(&args[0], &option))
+ return 0;
+ *inum = option;
+ break;
+ case Opt_journal_dev:
+ if (is_remount) {
+ printk(KERN_ERR "EXT4-fs: cannot specify "
+ "journal on remount\n");
+ return 0;
+ }
+ if (match_int(&args[0], &option))
+ return 0;
+ *journal_devnum = option;
+ break;
+ case Opt_noload:
+ set_opt (sbi->s_mount_opt, NOLOAD);
+ break;
+ case Opt_commit:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0)
+ return 0;
+ if (option == 0)
+ option = JBD_DEFAULT_MAX_COMMIT_AGE;
+ sbi->s_commit_interval = HZ * option;
+ break;
+ case Opt_data_journal:
+ data_opt = EXT4_MOUNT_JOURNAL_DATA;
+ goto datacheck;
+ case Opt_data_ordered:
+ data_opt = EXT4_MOUNT_ORDERED_DATA;
+ goto datacheck;
+ case Opt_data_writeback:
+ data_opt = EXT4_MOUNT_WRITEBACK_DATA;
+ datacheck:
+ if (is_remount) {
+ if ((sbi->s_mount_opt & EXT4_MOUNT_DATA_FLAGS)
+ != data_opt) {
+ printk(KERN_ERR
+ "EXT4-fs: cannot change data "
+ "mode on remount\n");
+ return 0;
+ }
+ } else {
+ sbi->s_mount_opt &= ~EXT4_MOUNT_DATA_FLAGS;
+ sbi->s_mount_opt |= data_opt;
+ }
+ break;
+#ifdef CONFIG_QUOTA
+ case Opt_usrjquota:
+ qtype = USRQUOTA;
+ goto set_qf_name;
+ case Opt_grpjquota:
+ qtype = GRPQUOTA;
+set_qf_name:
+ if (sb_any_quota_enabled(sb)) {
+ printk(KERN_ERR
+ "EXT4-fs: Cannot change journalled "
+ "quota options when quota turned on.\n");
+ return 0;
+ }
+ qname = match_strdup(&args[0]);
+ if (!qname) {
+ printk(KERN_ERR
+ "EXT4-fs: not enough memory for "
+ "storing quotafile name.\n");
+ return 0;
+ }
+ if (sbi->s_qf_names[qtype] &&
+ strcmp(sbi->s_qf_names[qtype], qname)) {
+ printk(KERN_ERR
+ "EXT4-fs: %s quota file already "
+ "specified.\n", QTYPE2NAME(qtype));
+ kfree(qname);
+ return 0;
+ }
+ sbi->s_qf_names[qtype] = qname;
+ if (strchr(sbi->s_qf_names[qtype], '/')) {
+ printk(KERN_ERR
+ "EXT4-fs: quotafile must be on "
+ "filesystem root.\n");
+ kfree(sbi->s_qf_names[qtype]);
+ sbi->s_qf_names[qtype] = NULL;
+ return 0;
+ }
+ set_opt(sbi->s_mount_opt, QUOTA);
+ break;
+ case Opt_offusrjquota:
+ qtype = USRQUOTA;
+ goto clear_qf_name;
+ case Opt_offgrpjquota:
+ qtype = GRPQUOTA;
+clear_qf_name:
+ if (sb_any_quota_enabled(sb)) {
+ printk(KERN_ERR "EXT4-fs: Cannot change "
+ "journalled quota options when "
+ "quota turned on.\n");
+ return 0;
+ }
+ /*
+ * The space will be released later when all options
+ * are confirmed to be correct
+ */
+ sbi->s_qf_names[qtype] = NULL;
+ break;
+ case Opt_jqfmt_vfsold:
+ sbi->s_jquota_fmt = QFMT_VFS_OLD;
+ break;
+ case Opt_jqfmt_vfsv0:
+ sbi->s_jquota_fmt = QFMT_VFS_V0;
+ break;
+ case Opt_quota:
+ case Opt_usrquota:
+ set_opt(sbi->s_mount_opt, QUOTA);
+ set_opt(sbi->s_mount_opt, USRQUOTA);
+ break;
+ case Opt_grpquota:
+ set_opt(sbi->s_mount_opt, QUOTA);
+ set_opt(sbi->s_mount_opt, GRPQUOTA);
+ break;
+ case Opt_noquota:
+ if (sb_any_quota_enabled(sb)) {
+ printk(KERN_ERR "EXT4-fs: Cannot change quota "
+ "options when quota turned on.\n");
+ return 0;
+ }
+ clear_opt(sbi->s_mount_opt, QUOTA);
+ clear_opt(sbi->s_mount_opt, USRQUOTA);
+ clear_opt(sbi->s_mount_opt, GRPQUOTA);
+ break;
+#else
+ case Opt_quota:
+ case Opt_usrquota:
+ case Opt_grpquota:
+ case Opt_usrjquota:
+ case Opt_grpjquota:
+ case Opt_offusrjquota:
+ case Opt_offgrpjquota:
+ case Opt_jqfmt_vfsold:
+ case Opt_jqfmt_vfsv0:
+ printk(KERN_ERR
+ "EXT4-fs: journalled quota options not "
+ "supported.\n");
+ break;
+ case Opt_noquota:
+ break;
+#endif
+ case Opt_abort:
+ set_opt(sbi->s_mount_opt, ABORT);
+ break;
+ case Opt_barrier:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option)
+ set_opt(sbi->s_mount_opt, BARRIER);
+ else
+ clear_opt(sbi->s_mount_opt, BARRIER);
+ break;
+ case Opt_ignore:
+ break;
+ case Opt_resize:
+ if (!is_remount) {
+ printk("EXT4-fs: resize option only available "
+ "for remount\n");
+ return 0;
+ }
+ if (match_int(&args[0], &option) != 0)
+ return 0;
+ *n_blocks_count = option;
+ break;
+ case Opt_nobh:
+ set_opt(sbi->s_mount_opt, NOBH);
+ break;
+ case Opt_bh:
+ clear_opt(sbi->s_mount_opt, NOBH);
+ break;
+ case Opt_extents:
+ set_opt (sbi->s_mount_opt, EXTENTS);
+ break;
+ default:
+ printk (KERN_ERR
+ "EXT4-fs: Unrecognized mount option \"%s\" "
+ "or missing value\n", p);
+ return 0;
+ }
+ }
+#ifdef CONFIG_QUOTA
+ if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+ if ((sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA) &&
+ sbi->s_qf_names[USRQUOTA])
+ clear_opt(sbi->s_mount_opt, USRQUOTA);
+
+ if ((sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA) &&
+ sbi->s_qf_names[GRPQUOTA])
+ clear_opt(sbi->s_mount_opt, GRPQUOTA);
+
+ if ((sbi->s_qf_names[USRQUOTA] &&
+ (sbi->s_mount_opt & EXT4_MOUNT_GRPQUOTA)) ||
+ (sbi->s_qf_names[GRPQUOTA] &&
+ (sbi->s_mount_opt & EXT4_MOUNT_USRQUOTA))) {
+ printk(KERN_ERR "EXT4-fs: old and new quota "
+ "format mixing.\n");
+ return 0;
+ }
+
+ if (!sbi->s_jquota_fmt) {
+ printk(KERN_ERR "EXT4-fs: journalled quota format "
+ "not specified.\n");
+ return 0;
+ }
+ } else {
+ if (sbi->s_jquota_fmt) {
+ printk(KERN_ERR "EXT4-fs: journalled quota format "
+ "specified with no journalling "
+ "enabled.\n");
+ return 0;
+ }
+ }
+#endif
+ return 1;
+}
+
+static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
+ int read_only)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ int res = 0;
+
+ if (le32_to_cpu(es->s_rev_level) > EXT4_MAX_SUPP_REV) {
+ printk (KERN_ERR "EXT4-fs warning: revision level too high, "
+ "forcing read-only mode\n");
+ res = MS_RDONLY;
+ }
+ if (read_only)
+ return res;
+ if (!(sbi->s_mount_state & EXT4_VALID_FS))
+ printk (KERN_WARNING "EXT4-fs warning: mounting unchecked fs, "
+ "running e2fsck is recommended\n");
+ else if ((sbi->s_mount_state & EXT4_ERROR_FS))
+ printk (KERN_WARNING
+ "EXT4-fs warning: mounting fs with errors, "
+ "running e2fsck is recommended\n");
+ else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
+ le16_to_cpu(es->s_mnt_count) >=
+ (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
+ printk (KERN_WARNING
+ "EXT4-fs warning: maximal mount count reached, "
+ "running e2fsck is recommended\n");
+ else if (le32_to_cpu(es->s_checkinterval) &&
+ (le32_to_cpu(es->s_lastcheck) +
+ le32_to_cpu(es->s_checkinterval) <= get_seconds()))
+ printk (KERN_WARNING
+ "EXT4-fs warning: checktime reached, "
+ "running e2fsck is recommended\n");
+#if 0
+ /* @@@ We _will_ want to clear the valid bit if we find
+ * inconsistencies, to force a fsck at reboot. But for
+ * a plain journaled filesystem we can keep it set as
+ * valid forever! :)
+ */
+ es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) & ~EXT4_VALID_FS);
+#endif
+ if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
+ es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
+ es->s_mnt_count=cpu_to_le16(le16_to_cpu(es->s_mnt_count) + 1);
+ es->s_mtime = cpu_to_le32(get_seconds());
+ ext4_update_dynamic_rev(sb);
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+
+ ext4_commit_super(sb, es, 1);
+ if (test_opt(sb, DEBUG))
+ printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%lu, "
+ "bpg=%lu, ipg=%lu, mo=%04lx]\n",
+ sb->s_blocksize,
+ sbi->s_groups_count,
+ EXT4_BLOCKS_PER_GROUP(sb),
+ EXT4_INODES_PER_GROUP(sb),
+ sbi->s_mount_opt);
+
+ printk(KERN_INFO "EXT4 FS on %s, ", sb->s_id);
+ if (EXT4_SB(sb)->s_journal->j_inode == NULL) {
+ char b[BDEVNAME_SIZE];
+
+ printk("external journal on %s\n",
+ bdevname(EXT4_SB(sb)->s_journal->j_dev, b));
+ } else {
+ printk("internal journal\n");
+ }
+ return res;
+}
+
+/* Called at mount-time, super-block is locked */
+static int ext4_check_descriptors (struct super_block * sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
+ ext4_fsblk_t last_block;
+ ext4_fsblk_t block_bitmap;
+ ext4_fsblk_t inode_bitmap;
+ ext4_fsblk_t inode_table;
+ struct ext4_group_desc * gdp = NULL;
+ int desc_block = 0;
+ int i;
+
+ ext4_debug ("Checking group descriptors");
+
+ for (i = 0; i < sbi->s_groups_count; i++)
+ {
+ if (i == sbi->s_groups_count - 1)
+ last_block = ext4_blocks_count(sbi->s_es) - 1;
+ else
+ last_block = first_block +
+ (EXT4_BLOCKS_PER_GROUP(sb) - 1);
+
+ if ((i % EXT4_DESC_PER_BLOCK(sb)) == 0)
+ gdp = (struct ext4_group_desc *)
+ sbi->s_group_desc[desc_block++]->b_data;
+ block_bitmap = ext4_block_bitmap(sb, gdp);
+ if (block_bitmap < first_block || block_bitmap > last_block)
+ {
+ ext4_error (sb, "ext4_check_descriptors",
+ "Block bitmap for group %d"
+ " not in group (block %llu)!",
+ i, block_bitmap);
+ return 0;
+ }
+ inode_bitmap = ext4_inode_bitmap(sb, gdp);
+ if (inode_bitmap < first_block || inode_bitmap > last_block)
+ {
+ ext4_error (sb, "ext4_check_descriptors",
+ "Inode bitmap for group %d"
+ " not in group (block %llu)!",
+ i, inode_bitmap);
+ return 0;
+ }
+ inode_table = ext4_inode_table(sb, gdp);
+ if (inode_table < first_block ||
+ inode_table + sbi->s_itb_per_group > last_block)
+ {
+ ext4_error (sb, "ext4_check_descriptors",
+ "Inode table for group %d"
+ " not in group (block %llu)!",
+ i, inode_table);
+ return 0;
+ }
+ first_block += EXT4_BLOCKS_PER_GROUP(sb);
+ gdp = (struct ext4_group_desc *)
+ ((__u8 *)gdp + EXT4_DESC_SIZE(sb));
+ }
+
+ ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
+ sbi->s_es->s_free_inodes_count=cpu_to_le32(ext4_count_free_inodes(sb));
+ return 1;
+}
+
+
+/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at
+ * the superblock) which were deleted from all directories, but held open by
+ * a process at the time of a crash. We walk the list and try to delete these
+ * inodes at recovery time (only with a read-write filesystem).
+ *
+ * In order to keep the orphan inode chain consistent during traversal (in
+ * case of crash during recovery), we link each inode into the superblock
+ * orphan list_head and handle it the same way as an inode deletion during
+ * normal operation (which journals the operations for us).
+ *
+ * We only do an iget() and an iput() on each inode, which is very safe if we
+ * accidentally point at an in-use or already deleted inode. The worst that
+ * can happen in this case is that we get a "bit already cleared" message from
+ * ext4_free_inode(). The only reason we would point at a wrong inode is if
+ * e2fsck was run on this filesystem, and it must have already done the orphan
+ * inode cleanup for us, so we can safely abort without any further action.
+ */
+static void ext4_orphan_cleanup (struct super_block * sb,
+ struct ext4_super_block * es)
+{
+ unsigned int s_flags = sb->s_flags;
+ int nr_orphans = 0, nr_truncates = 0;
+#ifdef CONFIG_QUOTA
+ int i;
+#endif
+ if (!es->s_last_orphan) {
+ jbd_debug(4, "no orphan inodes to clean up\n");
+ return;
+ }
+
+ if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+ if (es->s_last_orphan)
+ jbd_debug(1, "Errors on filesystem, "
+ "clearing orphan list.\n");
+ es->s_last_orphan = 0;
+ jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
+ return;
+ }
+
+ if (s_flags & MS_RDONLY) {
+ printk(KERN_INFO "EXT4-fs: %s: orphan cleanup on readonly fs\n",
+ sb->s_id);
+ sb->s_flags &= ~MS_RDONLY;
+ }
+#ifdef CONFIG_QUOTA
+ /* Needed for iput() to work correctly and not trash data */
+ sb->s_flags |= MS_ACTIVE;
+ /* Turn on quotas so that they are updated correctly */
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (EXT4_SB(sb)->s_qf_names[i]) {
+ int ret = ext4_quota_on_mount(sb, i);
+ if (ret < 0)
+ printk(KERN_ERR
+ "EXT4-fs: Cannot turn on journalled "
+ "quota: error %d\n", ret);
+ }
+ }
+#endif
+
+ while (es->s_last_orphan) {
+ struct inode *inode;
+
+ if (!(inode =
+ ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) {
+ es->s_last_orphan = 0;
+ break;
+ }
+
+ list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
+ DQUOT_INIT(inode);
+ if (inode->i_nlink) {
+ printk(KERN_DEBUG
+ "%s: truncating inode %lu to %Ld bytes\n",
+ __FUNCTION__, inode->i_ino, inode->i_size);
+ jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
+ inode->i_ino, inode->i_size);
+ ext4_truncate(inode);
+ nr_truncates++;
+ } else {
+ printk(KERN_DEBUG
+ "%s: deleting unreferenced inode %lu\n",
+ __FUNCTION__, inode->i_ino);
+ jbd_debug(2, "deleting unreferenced inode %lu\n",
+ inode->i_ino);
+ nr_orphans++;
+ }
+ iput(inode); /* The delete magic happens here! */
+ }
+
+#define PLURAL(x) (x), ((x)==1) ? "" : "s"
+
+ if (nr_orphans)
+ printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n",
+ sb->s_id, PLURAL(nr_orphans));
+ if (nr_truncates)
+ printk(KERN_INFO "EXT4-fs: %s: %d truncate%s cleaned up\n",
+ sb->s_id, PLURAL(nr_truncates));
+#ifdef CONFIG_QUOTA
+ /* Turn quotas off */
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (sb_dqopt(sb)->files[i])
+ vfs_quota_off(sb, i);
+ }
+#endif
+ sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+}
+
+#define log2(n) ffz(~(n))
+
+/*
+ * Maximal file size. There is a direct, and {,double-,triple-}indirect
+ * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
+ * We need to be 1 filesystem block less than the 2^32 sector limit.
+ */
+static loff_t ext4_max_size(int bits)
+{
+ loff_t res = EXT4_NDIR_BLOCKS;
+ /* This constant is calculated to be the largest file size for a
+ * dense, 4k-blocksize file such that the total number of
+ * sectors in the file, including data and all indirect blocks,
+ * does not exceed 2^32. */
+ const loff_t upper_limit = 0x1ff7fffd000LL;
+
+ res += 1LL << (bits-2);
+ res += 1LL << (2*(bits-2));
+ res += 1LL << (3*(bits-2));
+ res <<= bits;
+ if (res > upper_limit)
+ res = upper_limit;
+ return res;
+}
+
+static ext4_fsblk_t descriptor_loc(struct super_block *sb,
+ ext4_fsblk_t logical_sb_block, int nr)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ unsigned long bg, first_meta_bg;
+ int has_super = 0;
+
+ first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
+
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
+ nr < first_meta_bg)
+ return logical_sb_block + nr + 1;
+ bg = sbi->s_desc_per_block * nr;
+ if (ext4_bg_has_super(sb, bg))
+ has_super = 1;
+ return (has_super + ext4_group_first_block_no(sb, bg));
+}
+
+
+static int ext4_fill_super (struct super_block *sb, void *data, int silent)
+{
+ struct buffer_head * bh;
+ struct ext4_super_block *es = NULL;
+ struct ext4_sb_info *sbi;
+ ext4_fsblk_t block;
+ ext4_fsblk_t sb_block = get_sb_block(&data);
+ ext4_fsblk_t logical_sb_block;
+ unsigned long offset = 0;
+ unsigned int journal_inum = 0;
+ unsigned long journal_devnum = 0;
+ unsigned long def_mount_opts;
+ struct inode *root;
+ int blocksize;
+ int hblock;
+ int db_count;
+ int i;
+ int needs_recovery;
+ __le32 features;
+ __u64 blocks_count;
+
+ sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+ if (!sbi)
+ return -ENOMEM;
+ sb->s_fs_info = sbi;
+ sbi->s_mount_opt = 0;
+ sbi->s_resuid = EXT4_DEF_RESUID;
+ sbi->s_resgid = EXT4_DEF_RESGID;
+
+ unlock_kernel();
+
+ blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
+ if (!blocksize) {
+ printk(KERN_ERR "EXT4-fs: unable to set blocksize\n");
+ goto out_fail;
+ }
+
+ /*
+ * The ext4 superblock will not be buffer aligned for other than 1kB
+ * block sizes. We need to calculate the offset from buffer start.
+ */
+ if (blocksize != EXT4_MIN_BLOCK_SIZE) {
+ logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
+ offset = do_div(logical_sb_block, blocksize);
+ } else {
+ logical_sb_block = sb_block;
+ }
+
+ if (!(bh = sb_bread(sb, logical_sb_block))) {
+ printk (KERN_ERR "EXT4-fs: unable to read superblock\n");
+ goto out_fail;
+ }
+ /*
+ * Note: s_es must be initialized as soon as possible because
+ * some ext4 macro-instructions depend on its value
+ */
+ es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
+ sbi->s_es = es;
+ sb->s_magic = le16_to_cpu(es->s_magic);
+ if (sb->s_magic != EXT4_SUPER_MAGIC)
+ goto cantfind_ext4;
+
+ /* Set defaults before we parse the mount options */
+ def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
+ if (def_mount_opts & EXT4_DEFM_DEBUG)
+ set_opt(sbi->s_mount_opt, DEBUG);
+ if (def_mount_opts & EXT4_DEFM_BSDGROUPS)
+ set_opt(sbi->s_mount_opt, GRPID);
+ if (def_mount_opts & EXT4_DEFM_UID16)
+ set_opt(sbi->s_mount_opt, NO_UID32);
+ if (def_mount_opts & EXT4_DEFM_XATTR_USER)
+ set_opt(sbi->s_mount_opt, XATTR_USER);
+ if (def_mount_opts & EXT4_DEFM_ACL)
+ set_opt(sbi->s_mount_opt, POSIX_ACL);
+ if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
+ sbi->s_mount_opt |= EXT4_MOUNT_JOURNAL_DATA;
+ else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
+ sbi->s_mount_opt |= EXT4_MOUNT_ORDERED_DATA;
+ else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
+ sbi->s_mount_opt |= EXT4_MOUNT_WRITEBACK_DATA;
+
+ if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
+ set_opt(sbi->s_mount_opt, ERRORS_PANIC);
+ else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_RO)
+ set_opt(sbi->s_mount_opt, ERRORS_RO);
+ else
+ set_opt(sbi->s_mount_opt, ERRORS_CONT);
+
+ sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
+ sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+
+ set_opt(sbi->s_mount_opt, RESERVATION);
+
+ if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
+ NULL, 0))
+ goto failed_mount;
+
+ sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+
+ if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
+ (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
+ EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
+ EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U)))
+ printk(KERN_WARNING
+ "EXT4-fs warning: feature flags set on rev 0 fs, "
+ "running e2fsck is recommended\n");
+ /*
+ * Check feature flags regardless of the revision level, since we
+ * previously didn't change the revision level when setting the flags,
+ * so there is a chance incompat flags are set on a rev 0 filesystem.
+ */
+ features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP);
+ if (features) {
+ printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of "
+ "unsupported optional features (%x).\n",
+ sb->s_id, le32_to_cpu(features));
+ goto failed_mount;
+ }
+ features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP);
+ if (!(sb->s_flags & MS_RDONLY) && features) {
+ printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of "
+ "unsupported optional features (%x).\n",
+ sb->s_id, le32_to_cpu(features));
+ goto failed_mount;
+ }
+ blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+
+ if (blocksize < EXT4_MIN_BLOCK_SIZE ||
+ blocksize > EXT4_MAX_BLOCK_SIZE) {
+ printk(KERN_ERR
+ "EXT4-fs: Unsupported filesystem blocksize %d on %s.\n",
+ blocksize, sb->s_id);
+ goto failed_mount;
+ }
+
+ hblock = bdev_hardsect_size(sb->s_bdev);
+ if (sb->s_blocksize != blocksize) {
+ /*
+ * Make sure the blocksize for the filesystem is larger
+ * than the hardware sectorsize for the machine.
+ */
+ if (blocksize < hblock) {
+ printk(KERN_ERR "EXT4-fs: blocksize %d too small for "
+ "device blocksize %d.\n", blocksize, hblock);
+ goto failed_mount;
+ }
+
+ brelse (bh);
+ sb_set_blocksize(sb, blocksize);
+ logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
+ offset = do_div(logical_sb_block, blocksize);
+ bh = sb_bread(sb, logical_sb_block);
+ if (!bh) {
+ printk(KERN_ERR
+ "EXT4-fs: Can't read superblock on 2nd try.\n");
+ goto failed_mount;
+ }
+ es = (struct ext4_super_block *)(((char *)bh->b_data) + offset);
+ sbi->s_es = es;
+ if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
+ printk (KERN_ERR
+ "EXT4-fs: Magic mismatch, very weird !\n");
+ goto failed_mount;
+ }
+ }
+
+ sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits);
+
+ if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
+ sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
+ sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
+ } else {
+ sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
+ sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
+ if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
+ (sbi->s_inode_size & (sbi->s_inode_size - 1)) ||
+ (sbi->s_inode_size > blocksize)) {
+ printk (KERN_ERR
+ "EXT4-fs: unsupported inode size: %d\n",
+ sbi->s_inode_size);
+ goto failed_mount;
+ }
+ }
+ sbi->s_frag_size = EXT4_MIN_FRAG_SIZE <<
+ le32_to_cpu(es->s_log_frag_size);
+ if (blocksize != sbi->s_frag_size) {
+ printk(KERN_ERR
+ "EXT4-fs: fragsize %lu != blocksize %u (unsupported)\n",
+ sbi->s_frag_size, blocksize);
+ goto failed_mount;
+ }
+ sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) {
+ if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
+ sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
+ sbi->s_desc_size & (sbi->s_desc_size - 1)) {
+ printk(KERN_ERR
+ "EXT4-fs: unsupported descriptor size %lu\n",
+ sbi->s_desc_size);
+ goto failed_mount;
+ }
+ } else
+ sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
+ sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
+ sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
+ sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
+ if (EXT4_INODE_SIZE(sb) == 0)
+ goto cantfind_ext4;
+ sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
+ if (sbi->s_inodes_per_block == 0)
+ goto cantfind_ext4;
+ sbi->s_itb_per_group = sbi->s_inodes_per_group /
+ sbi->s_inodes_per_block;
+ sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
+ sbi->s_sbh = bh;
+ sbi->s_mount_state = le16_to_cpu(es->s_state);
+ sbi->s_addr_per_block_bits = log2(EXT4_ADDR_PER_BLOCK(sb));
+ sbi->s_desc_per_block_bits = log2(EXT4_DESC_PER_BLOCK(sb));
+ for (i=0; i < 4; i++)
+ sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
+ sbi->s_def_hash_version = es->s_def_hash_version;
+
+ if (sbi->s_blocks_per_group > blocksize * 8) {
+ printk (KERN_ERR
+ "EXT4-fs: #blocks per group too big: %lu\n",
+ sbi->s_blocks_per_group);
+ goto failed_mount;
+ }
+ if (sbi->s_frags_per_group > blocksize * 8) {
+ printk (KERN_ERR
+ "EXT4-fs: #fragments per group too big: %lu\n",
+ sbi->s_frags_per_group);
+ goto failed_mount;
+ }
+ if (sbi->s_inodes_per_group > blocksize * 8) {
+ printk (KERN_ERR
+ "EXT4-fs: #inodes per group too big: %lu\n",
+ sbi->s_inodes_per_group);
+ goto failed_mount;
+ }
+
+ if (ext4_blocks_count(es) >
+ (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
+ printk(KERN_ERR "EXT4-fs: filesystem on %s:"
+ " too large to mount safely\n", sb->s_id);
+ if (sizeof(sector_t) < 8)
+ printk(KERN_WARNING "EXT4-fs: CONFIG_LBD not "
+ "enabled\n");
+ goto failed_mount;
+ }
+
+ if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
+ goto cantfind_ext4;
+ blocks_count = (ext4_blocks_count(es) -
+ le32_to_cpu(es->s_first_data_block) +
+ EXT4_BLOCKS_PER_GROUP(sb) - 1);
+ do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
+ sbi->s_groups_count = blocks_count;
+ db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
+ EXT4_DESC_PER_BLOCK(sb);
+ sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *),
+ GFP_KERNEL);
+ if (sbi->s_group_desc == NULL) {
+ printk (KERN_ERR "EXT4-fs: not enough memory\n");
+ goto failed_mount;
+ }
+
+ bgl_lock_init(&sbi->s_blockgroup_lock);
+
+ for (i = 0; i < db_count; i++) {
+ block = descriptor_loc(sb, logical_sb_block, i);
+ sbi->s_group_desc[i] = sb_bread(sb, block);
+ if (!sbi->s_group_desc[i]) {
+ printk (KERN_ERR "EXT4-fs: "
+ "can't read group descriptor %d\n", i);
+ db_count = i;
+ goto failed_mount2;
+ }
+ }
+ if (!ext4_check_descriptors (sb)) {
+ printk(KERN_ERR "EXT4-fs: group descriptors corrupted!\n");
+ goto failed_mount2;
+ }
+ sbi->s_gdb_count = db_count;
+ get_random_bytes(&sbi->s_next_generation, sizeof(u32));
+ spin_lock_init(&sbi->s_next_gen_lock);
+
+ percpu_counter_init(&sbi->s_freeblocks_counter,
+ ext4_count_free_blocks(sb));
+ percpu_counter_init(&sbi->s_freeinodes_counter,
+ ext4_count_free_inodes(sb));
+ percpu_counter_init(&sbi->s_dirs_counter,
+ ext4_count_dirs(sb));
+
+ /* per fileystem reservation list head & lock */
+ spin_lock_init(&sbi->s_rsv_window_lock);
+ sbi->s_rsv_window_root = RB_ROOT;
+ /* Add a single, static dummy reservation to the start of the
+ * reservation window list --- it gives us a placeholder for
+ * append-at-start-of-list which makes the allocation logic
+ * _much_ simpler. */
+ sbi->s_rsv_window_head.rsv_start = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
+ sbi->s_rsv_window_head.rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
+ sbi->s_rsv_window_head.rsv_alloc_hit = 0;
+ sbi->s_rsv_window_head.rsv_goal_size = 0;
+ ext4_rsv_window_add(sb, &sbi->s_rsv_window_head);
+
+ /*
+ * set up enough so that it can read an inode
+ */
+ sb->s_op = &ext4_sops;
+ sb->s_export_op = &ext4_export_ops;
+ sb->s_xattr = ext4_xattr_handlers;
+#ifdef CONFIG_QUOTA
+ sb->s_qcop = &ext4_qctl_operations;
+ sb->dq_op = &ext4_quota_operations;
+#endif
+ INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
+
+ sb->s_root = NULL;
+
+ needs_recovery = (es->s_last_orphan != 0 ||
+ EXT4_HAS_INCOMPAT_FEATURE(sb,
+ EXT4_FEATURE_INCOMPAT_RECOVER));
+
+ /*
+ * The first inode we look at is the journal inode. Don't try
+ * root first: it may be modified in the journal!
+ */
+ if (!test_opt(sb, NOLOAD) &&
+ EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
+ if (ext4_load_journal(sb, es, journal_devnum))
+ goto failed_mount3;
+ } else if (journal_inum) {
+ if (ext4_create_journal(sb, es, journal_inum))
+ goto failed_mount3;
+ } else {
+ if (!silent)
+ printk (KERN_ERR
+ "ext4: No journal on filesystem on %s\n",
+ sb->s_id);
+ goto failed_mount3;
+ }
+
+ /* We have now updated the journal if required, so we can
+ * validate the data journaling mode. */
+ switch (test_opt(sb, DATA_FLAGS)) {
+ case 0:
+ /* No mode set, assume a default based on the journal
+ * capabilities: ORDERED_DATA if the journal can
+ * cope, else JOURNAL_DATA
+ */
+ if (jbd2_journal_check_available_features
+ (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE))
+ set_opt(sbi->s_mount_opt, ORDERED_DATA);
+ else
+ set_opt(sbi->s_mount_opt, JOURNAL_DATA);
+ break;
+
+ case EXT4_MOUNT_ORDERED_DATA:
+ case EXT4_MOUNT_WRITEBACK_DATA:
+ if (!jbd2_journal_check_available_features
+ (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
+ printk(KERN_ERR "EXT4-fs: Journal does not support "
+ "requested data journaling mode\n");
+ goto failed_mount4;
+ }
+ default:
+ break;
+ }
+
+ if (test_opt(sb, NOBH)) {
+ if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
+ printk(KERN_WARNING "EXT4-fs: Ignoring nobh option - "
+ "its supported only with writeback mode\n");
+ clear_opt(sbi->s_mount_opt, NOBH);
+ }
+ }
+ /*
+ * The jbd2_journal_load will have done any necessary log recovery,
+ * so we can safely mount the rest of the filesystem now.
+ */
+
+ root = iget(sb, EXT4_ROOT_INO);
+ sb->s_root = d_alloc_root(root);
+ if (!sb->s_root) {
+ printk(KERN_ERR "EXT4-fs: get root inode failed\n");
+ iput(root);
+ goto failed_mount4;
+ }
+ if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
+ dput(sb->s_root);
+ sb->s_root = NULL;
+ printk(KERN_ERR "EXT4-fs: corrupt root inode, run e2fsck\n");
+ goto failed_mount4;
+ }
+
+ ext4_setup_super (sb, es, sb->s_flags & MS_RDONLY);
+ /*
+ * akpm: core read_super() calls in here with the superblock locked.
+ * That deadlocks, because orphan cleanup needs to lock the superblock
+ * in numerous places. Here we just pop the lock - it's relatively
+ * harmless, because we are now ready to accept write_super() requests,
+ * and aviro says that's the only reason for hanging onto the
+ * superblock lock.
+ */
+ EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
+ ext4_orphan_cleanup(sb, es);
+ EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
+ if (needs_recovery)
+ printk (KERN_INFO "EXT4-fs: recovery complete.\n");
+ ext4_mark_recovery_complete(sb, es);
+ printk (KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n",
+ test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal":
+ test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
+ "writeback");
+
+ ext4_ext_init(sb);
+
+ lock_kernel();
+ return 0;
+
+cantfind_ext4:
+ if (!silent)
+ printk(KERN_ERR "VFS: Can't find ext4 filesystem on dev %s.\n",
+ sb->s_id);
+ goto failed_mount;
+
+failed_mount4:
+ jbd2_journal_destroy(sbi->s_journal);
+failed_mount3:
+ percpu_counter_destroy(&sbi->s_freeblocks_counter);
+ percpu_counter_destroy(&sbi->s_freeinodes_counter);
+ percpu_counter_destroy(&sbi->s_dirs_counter);
+failed_mount2:
+ for (i = 0; i < db_count; i++)
+ brelse(sbi->s_group_desc[i]);
+ kfree(sbi->s_group_desc);
+failed_mount:
+#ifdef CONFIG_QUOTA
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(sbi->s_qf_names[i]);
+#endif
+ ext4_blkdev_remove(sbi);
+ brelse(bh);
+out_fail:
+ sb->s_fs_info = NULL;
+ kfree(sbi);
+ lock_kernel();
+ return -EINVAL;
+}
+
+/*
+ * Setup any per-fs journal parameters now. We'll do this both on
+ * initial mount, once the journal has been initialised but before we've
+ * done any recovery; and again on any subsequent remount.
+ */
+static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (sbi->s_commit_interval)
+ journal->j_commit_interval = sbi->s_commit_interval;
+ /* We could also set up an ext4-specific default for the commit
+ * interval here, but for now we'll just fall back to the jbd
+ * default. */
+
+ spin_lock(&journal->j_state_lock);
+ if (test_opt(sb, BARRIER))
+ journal->j_flags |= JBD2_BARRIER;
+ else
+ journal->j_flags &= ~JBD2_BARRIER;
+ spin_unlock(&journal->j_state_lock);
+}
+
+static journal_t *ext4_get_journal(struct super_block *sb,
+ unsigned int journal_inum)
+{
+ struct inode *journal_inode;
+ journal_t *journal;
+
+ /* First, test for the existence of a valid inode on disk. Bad
+ * things happen if we iget() an unused inode, as the subsequent
+ * iput() will try to delete it. */
+
+ journal_inode = iget(sb, journal_inum);
+ if (!journal_inode) {
+ printk(KERN_ERR "EXT4-fs: no journal found.\n");
+ return NULL;
+ }
+ if (!journal_inode->i_nlink) {
+ make_bad_inode(journal_inode);
+ iput(journal_inode);
+ printk(KERN_ERR "EXT4-fs: journal inode is deleted.\n");
+ return NULL;
+ }
+
+ jbd_debug(2, "Journal inode found at %p: %Ld bytes\n",
+ journal_inode, journal_inode->i_size);
+ if (is_bad_inode(journal_inode) || !S_ISREG(journal_inode->i_mode)) {
+ printk(KERN_ERR "EXT4-fs: invalid journal inode.\n");
+ iput(journal_inode);
+ return NULL;
+ }
+
+ journal = jbd2_journal_init_inode(journal_inode);
+ if (!journal) {
+ printk(KERN_ERR "EXT4-fs: Could not load journal inode\n");
+ iput(journal_inode);
+ return NULL;
+ }
+ journal->j_private = sb;
+ ext4_init_journal_params(sb, journal);
+ return journal;
+}
+
+static journal_t *ext4_get_dev_journal(struct super_block *sb,
+ dev_t j_dev)
+{
+ struct buffer_head * bh;
+ journal_t *journal;
+ ext4_fsblk_t start;
+ ext4_fsblk_t len;
+ int hblock, blocksize;
+ ext4_fsblk_t sb_block;
+ unsigned long offset;
+ struct ext4_super_block * es;
+ struct block_device *bdev;
+
+ bdev = ext4_blkdev_get(j_dev);
+ if (bdev == NULL)
+ return NULL;
+
+ if (bd_claim(bdev, sb)) {
+ printk(KERN_ERR
+ "EXT4: failed to claim external journal device.\n");
+ blkdev_put(bdev);
+ return NULL;
+ }
+
+ blocksize = sb->s_blocksize;
+ hblock = bdev_hardsect_size(bdev);
+ if (blocksize < hblock) {
+ printk(KERN_ERR
+ "EXT4-fs: blocksize too small for journal device.\n");
+ goto out_bdev;
+ }
+
+ sb_block = EXT4_MIN_BLOCK_SIZE / blocksize;
+ offset = EXT4_MIN_BLOCK_SIZE % blocksize;
+ set_blocksize(bdev, blocksize);
+ if (!(bh = __bread(bdev, sb_block, blocksize))) {
+ printk(KERN_ERR "EXT4-fs: couldn't read superblock of "
+ "external journal\n");
+ goto out_bdev;
+ }
+
+ es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
+ if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) ||
+ !(le32_to_cpu(es->s_feature_incompat) &
+ EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) {
+ printk(KERN_ERR "EXT4-fs: external journal has "
+ "bad superblock\n");
+ brelse(bh);
+ goto out_bdev;
+ }
+
+ if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
+ printk(KERN_ERR "EXT4-fs: journal UUID does not match\n");
+ brelse(bh);
+ goto out_bdev;
+ }
+
+ len = ext4_blocks_count(es);
+ start = sb_block + 1;
+ brelse(bh); /* we're done with the superblock */
+
+ journal = jbd2_journal_init_dev(bdev, sb->s_bdev,
+ start, len, blocksize);
+ if (!journal) {
+ printk(KERN_ERR "EXT4-fs: failed to create device journal\n");
+ goto out_bdev;
+ }
+ journal->j_private = sb;
+ ll_rw_block(READ, 1, &journal->j_sb_buffer);
+ wait_on_buffer(journal->j_sb_buffer);
+ if (!buffer_uptodate(journal->j_sb_buffer)) {
+ printk(KERN_ERR "EXT4-fs: I/O error on journal device\n");
+ goto out_journal;
+ }
+ if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
+ printk(KERN_ERR "EXT4-fs: External journal has more than one "
+ "user (unsupported) - %d\n",
+ be32_to_cpu(journal->j_superblock->s_nr_users));
+ goto out_journal;
+ }
+ EXT4_SB(sb)->journal_bdev = bdev;
+ ext4_init_journal_params(sb, journal);
+ return journal;
+out_journal:
+ jbd2_journal_destroy(journal);
+out_bdev:
+ ext4_blkdev_put(bdev);
+ return NULL;
+}
+
+static int ext4_load_journal(struct super_block *sb,
+ struct ext4_super_block *es,
+ unsigned long journal_devnum)
+{
+ journal_t *journal;
+ unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
+ dev_t journal_dev;
+ int err = 0;
+ int really_read_only;
+
+ if (journal_devnum &&
+ journal_devnum != le32_to_cpu(es->s_journal_dev)) {
+ printk(KERN_INFO "EXT4-fs: external journal device major/minor "
+ "numbers have changed\n");
+ journal_dev = new_decode_dev(journal_devnum);
+ } else
+ journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));
+
+ really_read_only = bdev_read_only(sb->s_bdev);
+
+ /*
+ * Are we loading a blank journal or performing recovery after a
+ * crash? For recovery, we need to check in advance whether we
+ * can get read-write access to the device.
+ */
+
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER)) {
+ if (sb->s_flags & MS_RDONLY) {
+ printk(KERN_INFO "EXT4-fs: INFO: recovery "
+ "required on readonly filesystem.\n");
+ if (really_read_only) {
+ printk(KERN_ERR "EXT4-fs: write access "
+ "unavailable, cannot proceed.\n");
+ return -EROFS;
+ }
+ printk (KERN_INFO "EXT4-fs: write access will "
+ "be enabled during recovery.\n");
+ }
+ }
+
+ if (journal_inum && journal_dev) {
+ printk(KERN_ERR "EXT4-fs: filesystem has both journal "
+ "and inode journals!\n");
+ return -EINVAL;
+ }
+
+ if (journal_inum) {
+ if (!(journal = ext4_get_journal(sb, journal_inum)))
+ return -EINVAL;
+ } else {
+ if (!(journal = ext4_get_dev_journal(sb, journal_dev)))
+ return -EINVAL;
+ }
+
+ if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
+ err = jbd2_journal_update_format(journal);
+ if (err) {
+ printk(KERN_ERR "EXT4-fs: error updating journal.\n");
+ jbd2_journal_destroy(journal);
+ return err;
+ }
+ }
+
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER))
+ err = jbd2_journal_wipe(journal, !really_read_only);
+ if (!err)
+ err = jbd2_journal_load(journal);
+
+ if (err) {
+ printk(KERN_ERR "EXT4-fs: error loading journal.\n");
+ jbd2_journal_destroy(journal);
+ return err;
+ }
+
+ EXT4_SB(sb)->s_journal = journal;
+ ext4_clear_journal_err(sb, es);
+
+ if (journal_devnum &&
+ journal_devnum != le32_to_cpu(es->s_journal_dev)) {
+ es->s_journal_dev = cpu_to_le32(journal_devnum);
+ sb->s_dirt = 1;
+
+ /* Make sure we flush the recovery flag to disk. */
+ ext4_commit_super(sb, es, 1);
+ }
+
+ return 0;
+}
+
+static int ext4_create_journal(struct super_block * sb,
+ struct ext4_super_block * es,
+ unsigned int journal_inum)
+{
+ journal_t *journal;
+
+ if (sb->s_flags & MS_RDONLY) {
+ printk(KERN_ERR "EXT4-fs: readonly filesystem when trying to "
+ "create journal.\n");
+ return -EROFS;
+ }
+
+ if (!(journal = ext4_get_journal(sb, journal_inum)))
+ return -EINVAL;
+
+ printk(KERN_INFO "EXT4-fs: creating new journal on inode %u\n",
+ journal_inum);
+
+ if (jbd2_journal_create(journal)) {
+ printk(KERN_ERR "EXT4-fs: error creating journal.\n");
+ jbd2_journal_destroy(journal);
+ return -EIO;
+ }
+
+ EXT4_SB(sb)->s_journal = journal;
+
+ ext4_update_dynamic_rev(sb);
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL);
+
+ es->s_journal_inum = cpu_to_le32(journal_inum);
+ sb->s_dirt = 1;
+
+ /* Make sure we flush the recovery flag to disk. */
+ ext4_commit_super(sb, es, 1);
+
+ return 0;
+}
+
+static void ext4_commit_super (struct super_block * sb,
+ struct ext4_super_block * es,
+ int sync)
+{
+ struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
+
+ if (!sbh)
+ return;
+ es->s_wtime = cpu_to_le32(get_seconds());
+ ext4_free_blocks_count_set(es, ext4_count_free_blocks(sb));
+ es->s_free_inodes_count = cpu_to_le32(ext4_count_free_inodes(sb));
+ BUFFER_TRACE(sbh, "marking dirty");
+ mark_buffer_dirty(sbh);
+ if (sync)
+ sync_dirty_buffer(sbh);
+}
+
+
+/*
+ * Have we just finished recovery? If so, and if we are mounting (or
+ * remounting) the filesystem readonly, then we will end up with a
+ * consistent fs on disk. Record that fact.
+ */
+static void ext4_mark_recovery_complete(struct super_block * sb,
+ struct ext4_super_block * es)
+{
+ journal_t *journal = EXT4_SB(sb)->s_journal;
+
+ jbd2_journal_lock_updates(journal);
+ jbd2_journal_flush(journal);
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER) &&
+ sb->s_flags & MS_RDONLY) {
+ EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ sb->s_dirt = 0;
+ ext4_commit_super(sb, es, 1);
+ }
+ jbd2_journal_unlock_updates(journal);
+}
+
+/*
+ * If we are mounting (or read-write remounting) a filesystem whose journal
+ * has recorded an error from a previous lifetime, move that error to the
+ * main filesystem now.
+ */
+static void ext4_clear_journal_err(struct super_block * sb,
+ struct ext4_super_block * es)
+{
+ journal_t *journal;
+ int j_errno;
+ const char *errstr;
+
+ journal = EXT4_SB(sb)->s_journal;
+
+ /*
+ * Now check for any error status which may have been recorded in the
+ * journal by a prior ext4_error() or ext4_abort()
+ */
+
+ j_errno = jbd2_journal_errno(journal);
+ if (j_errno) {
+ char nbuf[16];
+
+ errstr = ext4_decode_error(sb, j_errno, nbuf);
+ ext4_warning(sb, __FUNCTION__, "Filesystem error recorded "
+ "from previous mount: %s", errstr);
+ ext4_warning(sb, __FUNCTION__, "Marking fs in need of "
+ "filesystem check.");
+
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+ ext4_commit_super (sb, es, 1);
+
+ jbd2_journal_clear_err(journal);
+ }
+}
+
+/*
+ * Force the running and committing transactions to commit,
+ * and wait on the commit.
+ */
+int ext4_force_commit(struct super_block *sb)
+{
+ journal_t *journal;
+ int ret;
+
+ if (sb->s_flags & MS_RDONLY)
+ return 0;
+
+ journal = EXT4_SB(sb)->s_journal;
+ sb->s_dirt = 0;
+ ret = ext4_journal_force_commit(journal);
+ return ret;
+}
+
+/*
+ * Ext4 always journals updates to the superblock itself, so we don't
+ * have to propagate any other updates to the superblock on disk at this
+ * point. Just start an async writeback to get the buffers on their way
+ * to the disk.
+ *
+ * This implicitly triggers the writebehind on sync().
+ */
+
+static void ext4_write_super (struct super_block * sb)
+{
+ if (mutex_trylock(&sb->s_lock) != 0)
+ BUG();
+ sb->s_dirt = 0;
+}
+
+static int ext4_sync_fs(struct super_block *sb, int wait)
+{
+ tid_t target;
+
+ sb->s_dirt = 0;
+ if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
+ if (wait)
+ jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
+ }
+ return 0;
+}
+
+/*
+ * LVM calls this function before a (read-only) snapshot is created. This
+ * gives us a chance to flush the journal completely and mark the fs clean.
+ */
+static void ext4_write_super_lockfs(struct super_block *sb)
+{
+ sb->s_dirt = 0;
+
+ if (!(sb->s_flags & MS_RDONLY)) {
+ journal_t *journal = EXT4_SB(sb)->s_journal;
+
+ /* Now we set up the journal barrier. */
+ jbd2_journal_lock_updates(journal);
+ jbd2_journal_flush(journal);
+
+ /* Journal blocked and flushed, clear needs_recovery flag. */
+ EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
+ }
+}
+
+/*
+ * Called by LVM after the snapshot is done. We need to reset the RECOVER
+ * flag here, even though the filesystem is not technically dirty yet.
+ */
+static void ext4_unlockfs(struct super_block *sb)
+{
+ if (!(sb->s_flags & MS_RDONLY)) {
+ lock_super(sb);
+ /* Reser the needs_recovery flag before the fs is unlocked. */
+ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
+ ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
+ unlock_super(sb);
+ jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
+ }
+}
+
+static int ext4_remount (struct super_block * sb, int * flags, char * data)
+{
+ struct ext4_super_block * es;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_fsblk_t n_blocks_count = 0;
+ unsigned long old_sb_flags;
+ struct ext4_mount_options old_opts;
+ int err;
+#ifdef CONFIG_QUOTA
+ int i;
+#endif
+
+ /* Store the original options */
+ old_sb_flags = sb->s_flags;
+ old_opts.s_mount_opt = sbi->s_mount_opt;
+ old_opts.s_resuid = sbi->s_resuid;
+ old_opts.s_resgid = sbi->s_resgid;
+ old_opts.s_commit_interval = sbi->s_commit_interval;
+#ifdef CONFIG_QUOTA
+ old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
+ for (i = 0; i < MAXQUOTAS; i++)
+ old_opts.s_qf_names[i] = sbi->s_qf_names[i];
+#endif
+
+ /*
+ * Allow the "check" option to be passed as a remount option.
+ */
+ if (!parse_options(data, sb, NULL, NULL, &n_blocks_count, 1)) {
+ err = -EINVAL;
+ goto restore_opts;
+ }
+
+ if (sbi->s_mount_opt & EXT4_MOUNT_ABORT)
+ ext4_abort(sb, __FUNCTION__, "Abort forced by user");
+
+ sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ ((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
+
+ es = sbi->s_es;
+
+ ext4_init_journal_params(sb, sbi->s_journal);
+
+ if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY) ||
+ n_blocks_count > ext4_blocks_count(es)) {
+ if (sbi->s_mount_opt & EXT4_MOUNT_ABORT) {
+ err = -EROFS;
+ goto restore_opts;
+ }
+
+ if (*flags & MS_RDONLY) {
+ /*
+ * First of all, the unconditional stuff we have to do
+ * to disable replay of the journal when we next remount
+ */
+ sb->s_flags |= MS_RDONLY;
+
+ /*
+ * OK, test if we are remounting a valid rw partition
+ * readonly, and if so set the rdonly flag and then
+ * mark the partition as valid again.
+ */
+ if (!(es->s_state & cpu_to_le16(EXT4_VALID_FS)) &&
+ (sbi->s_mount_state & EXT4_VALID_FS))
+ es->s_state = cpu_to_le16(sbi->s_mount_state);
+
+ ext4_mark_recovery_complete(sb, es);
+ } else {
+ __le32 ret;
+ if ((ret = EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ ~EXT4_FEATURE_RO_COMPAT_SUPP))) {
+ printk(KERN_WARNING "EXT4-fs: %s: couldn't "
+ "remount RDWR because of unsupported "
+ "optional features (%x).\n",
+ sb->s_id, le32_to_cpu(ret));
+ err = -EROFS;
+ goto restore_opts;
+ }
+ /*
+ * Mounting a RDONLY partition read-write, so reread
+ * and store the current valid flag. (It may have
+ * been changed by e2fsck since we originally mounted
+ * the partition.)
+ */
+ ext4_clear_journal_err(sb, es);
+ sbi->s_mount_state = le16_to_cpu(es->s_state);
+ if ((err = ext4_group_extend(sb, es, n_blocks_count)))
+ goto restore_opts;
+ if (!ext4_setup_super (sb, es, 0))
+ sb->s_flags &= ~MS_RDONLY;
+ }
+ }
+#ifdef CONFIG_QUOTA
+ /* Release old quota file names */
+ for (i = 0; i < MAXQUOTAS; i++)
+ if (old_opts.s_qf_names[i] &&
+ old_opts.s_qf_names[i] != sbi->s_qf_names[i])
+ kfree(old_opts.s_qf_names[i]);
+#endif
+ return 0;
+restore_opts:
+ sb->s_flags = old_sb_flags;
+ sbi->s_mount_opt = old_opts.s_mount_opt;
+ sbi->s_resuid = old_opts.s_resuid;
+ sbi->s_resgid = old_opts.s_resgid;
+ sbi->s_commit_interval = old_opts.s_commit_interval;
+#ifdef CONFIG_QUOTA
+ sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (sbi->s_qf_names[i] &&
+ old_opts.s_qf_names[i] != sbi->s_qf_names[i])
+ kfree(sbi->s_qf_names[i]);
+ sbi->s_qf_names[i] = old_opts.s_qf_names[i];
+ }
+#endif
+ return err;
+}
+
+static int ext4_statfs (struct dentry * dentry, struct kstatfs * buf)
+{
+ struct super_block *sb = dentry->d_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ ext4_fsblk_t overhead;
+ int i;
+
+ if (test_opt (sb, MINIX_DF))
+ overhead = 0;
+ else {
+ unsigned long ngroups;
+ ngroups = EXT4_SB(sb)->s_groups_count;
+ smp_rmb();
+
+ /*
+ * Compute the overhead (FS structures)
+ */
+
+ /*
+ * All of the blocks before first_data_block are
+ * overhead
+ */
+ overhead = le32_to_cpu(es->s_first_data_block);
+
+ /*
+ * Add the overhead attributed to the superblock and
+ * block group descriptors. If the sparse superblocks
+ * feature is turned on, then not all groups have this.
+ */
+ for (i = 0; i < ngroups; i++) {
+ overhead += ext4_bg_has_super(sb, i) +
+ ext4_bg_num_gdb(sb, i);
+ cond_resched();
+ }
+
+ /*
+ * Every block group has an inode bitmap, a block
+ * bitmap, and an inode table.
+ */
+ overhead += (ngroups * (2 + EXT4_SB(sb)->s_itb_per_group));
+ }
+
+ buf->f_type = EXT4_SUPER_MAGIC;
+ buf->f_bsize = sb->s_blocksize;
+ buf->f_blocks = ext4_blocks_count(es) - overhead;
+ buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
+ buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
+ if (buf->f_bfree < ext4_r_blocks_count(es))
+ buf->f_bavail = 0;
+ buf->f_files = le32_to_cpu(es->s_inodes_count);
+ buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
+ buf->f_namelen = EXT4_NAME_LEN;
+ return 0;
+}
+
+/* Helper function for writing quotas on sync - we need to start transaction before quota file
+ * is locked for write. Otherwise the are possible deadlocks:
+ * Process 1 Process 2
+ * ext4_create() quota_sync()
+ * jbd2_journal_start() write_dquot()
+ * DQUOT_INIT() down(dqio_mutex)
+ * down(dqio_mutex) jbd2_journal_start()
+ *
+ */
+
+#ifdef CONFIG_QUOTA
+
+static inline struct inode *dquot_to_inode(struct dquot *dquot)
+{
+ return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type];
+}
+
+static int ext4_dquot_initialize(struct inode *inode, int type)
+{
+ handle_t *handle;
+ int ret, err;
+
+ /* We may create quota structure so we need to reserve enough blocks */
+ handle = ext4_journal_start(inode, 2*EXT4_QUOTA_INIT_BLOCKS(inode->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ret = dquot_initialize(inode, type);
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ return ret;
+}
+
+static int ext4_dquot_drop(struct inode *inode)
+{
+ handle_t *handle;
+ int ret, err;
+
+ /* We may delete quota structure so we need to reserve enough blocks */
+ handle = ext4_journal_start(inode, 2*EXT4_QUOTA_DEL_BLOCKS(inode->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ret = dquot_drop(inode);
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ return ret;
+}
+
+static int ext4_write_dquot(struct dquot *dquot)
+{
+ int ret, err;
+ handle_t *handle;
+ struct inode *inode;
+
+ inode = dquot_to_inode(dquot);
+ handle = ext4_journal_start(inode,
+ EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ret = dquot_commit(dquot);
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ return ret;
+}
+
+static int ext4_acquire_dquot(struct dquot *dquot)
+{
+ int ret, err;
+ handle_t *handle;
+
+ handle = ext4_journal_start(dquot_to_inode(dquot),
+ EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ret = dquot_acquire(dquot);
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ return ret;
+}
+
+static int ext4_release_dquot(struct dquot *dquot)
+{
+ int ret, err;
+ handle_t *handle;
+
+ handle = ext4_journal_start(dquot_to_inode(dquot),
+ EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ret = dquot_release(dquot);
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ return ret;
+}
+
+static int ext4_mark_dquot_dirty(struct dquot *dquot)
+{
+ /* Are we journalling quotas? */
+ if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
+ EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
+ dquot_mark_dquot_dirty(dquot);
+ return ext4_write_dquot(dquot);
+ } else {
+ return dquot_mark_dquot_dirty(dquot);
+ }
+}
+
+static int ext4_write_info(struct super_block *sb, int type)
+{
+ int ret, err;
+ handle_t *handle;
+
+ /* Data block + inode block */
+ handle = ext4_journal_start(sb->s_root->d_inode, 2);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ ret = dquot_commit_info(sb, type);
+ err = ext4_journal_stop(handle);
+ if (!ret)
+ ret = err;
+ return ret;
+}
+
+/*
+ * Turn on quotas during mount time - we need to find
+ * the quota file and such...
+ */
+static int ext4_quota_on_mount(struct super_block *sb, int type)
+{
+ return vfs_quota_on_mount(sb, EXT4_SB(sb)->s_qf_names[type],
+ EXT4_SB(sb)->s_jquota_fmt, type);
+}
+
+/*
+ * Standard function to be called on quota_on
+ */
+static int ext4_quota_on(struct super_block *sb, int type, int format_id,
+ char *path)
+{
+ int err;
+ struct nameidata nd;
+
+ if (!test_opt(sb, QUOTA))
+ return -EINVAL;
+ /* Not journalling quota? */
+ if (!EXT4_SB(sb)->s_qf_names[USRQUOTA] &&
+ !EXT4_SB(sb)->s_qf_names[GRPQUOTA])
+ return vfs_quota_on(sb, type, format_id, path);
+ err = path_lookup(path, LOOKUP_FOLLOW, &nd);
+ if (err)
+ return err;
+ /* Quotafile not on the same filesystem? */
+ if (nd.mnt->mnt_sb != sb) {
+ path_release(&nd);
+ return -EXDEV;
+ }
+ /* Quotafile not of fs root? */
+ if (nd.dentry->d_parent->d_inode != sb->s_root->d_inode)
+ printk(KERN_WARNING
+ "EXT4-fs: Quota file not on filesystem root. "
+ "Journalled quota will not work.\n");
+ path_release(&nd);
+ return vfs_quota_on(sb, type, format_id, path);
+}
+
+/* Read data from quotafile - avoid pagecache and such because we cannot afford
+ * acquiring the locks... As quota files are never truncated and quota code
+ * itself serializes the operations (and noone else should touch the files)
+ * we don't have to be afraid of races */
+static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
+ size_t len, loff_t off)
+{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ sector_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
+ int err = 0;
+ int offset = off & (sb->s_blocksize - 1);
+ int tocopy;
+ size_t toread;
+ struct buffer_head *bh;
+ loff_t i_size = i_size_read(inode);
+
+ if (off > i_size)
+ return 0;
+ if (off+len > i_size)
+ len = i_size-off;
+ toread = len;
+ while (toread > 0) {
+ tocopy = sb->s_blocksize - offset < toread ?
+ sb->s_blocksize - offset : toread;
+ bh = ext4_bread(NULL, inode, blk, 0, &err);
+ if (err)
+ return err;
+ if (!bh) /* A hole? */
+ memset(data, 0, tocopy);
+ else
+ memcpy(data, bh->b_data+offset, tocopy);
+ brelse(bh);
+ offset = 0;
+ toread -= tocopy;
+ data += tocopy;
+ blk++;
+ }
+ return len;
+}
+
+/* Write to quotafile (we know the transaction is already started and has
+ * enough credits) */
+static ssize_t ext4_quota_write(struct super_block *sb, int type,
+ const char *data, size_t len, loff_t off)
+{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ sector_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
+ int err = 0;
+ int offset = off & (sb->s_blocksize - 1);
+ int tocopy;
+ int journal_quota = EXT4_SB(sb)->s_qf_names[type] != NULL;
+ size_t towrite = len;
+ struct buffer_head *bh;
+ handle_t *handle = journal_current_handle();
+
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
+ while (towrite > 0) {
+ tocopy = sb->s_blocksize - offset < towrite ?
+ sb->s_blocksize - offset : towrite;
+ bh = ext4_bread(handle, inode, blk, 1, &err);
+ if (!bh)
+ goto out;
+ if (journal_quota) {
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err) {
+ brelse(bh);
+ goto out;
+ }
+ }
+ lock_buffer(bh);
+ memcpy(bh->b_data+offset, data, tocopy);
+ flush_dcache_page(bh->b_page);
+ unlock_buffer(bh);
+ if (journal_quota)
+ err = ext4_journal_dirty_metadata(handle, bh);
+ else {
+ /* Always do at least ordered writes for quotas */
+ err = ext4_journal_dirty_data(handle, bh);
+ mark_buffer_dirty(bh);
+ }
+ brelse(bh);
+ if (err)
+ goto out;
+ offset = 0;
+ towrite -= tocopy;
+ data += tocopy;
+ blk++;
+ }
+out:
+ if (len == towrite)
+ return err;
+ if (inode->i_size < off+len-towrite) {
+ i_size_write(inode, off+len-towrite);
+ EXT4_I(inode)->i_disksize = inode->i_size;
+ }
+ inode->i_version++;
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ ext4_mark_inode_dirty(handle, inode);
+ mutex_unlock(&inode->i_mutex);
+ return len - towrite;
+}
+
+#endif
+
+static int ext4_get_sb(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+{
+ return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super, mnt);
+}
+
+static struct file_system_type ext4dev_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "ext4dev",
+ .get_sb = ext4_get_sb,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+
+static int __init init_ext4_fs(void)
+{
+ int err = init_ext4_xattr();
+ if (err)
+ return err;
+ err = init_inodecache();
+ if (err)
+ goto out1;
+ err = register_filesystem(&ext4dev_fs_type);
+ if (err)
+ goto out;
+ return 0;
+out:
+ destroy_inodecache();
+out1:
+ exit_ext4_xattr();
+ return err;
+}
+
+static void __exit exit_ext4_fs(void)
+{
+ unregister_filesystem(&ext4dev_fs_type);
+ destroy_inodecache();
+ exit_ext4_xattr();
+}
+
+MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
+MODULE_DESCRIPTION("Fourth Extended Filesystem with extents");
+MODULE_LICENSE("GPL");
+module_init(init_ext4_fs)
+module_exit(exit_ext4_fs)
--- /dev/null
+/*
+ * linux/fs/ext4/symlink.c
+ *
+ * Only fast symlinks left here - the rest is done by generic code. AV, 1999
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/fs/minix/symlink.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ * ext4 symlink handling code
+ */
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/namei.h>
+#include "xattr.h"
+
+static void * ext4_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ struct ext4_inode_info *ei = EXT4_I(dentry->d_inode);
+ nd_set_link(nd, (char*)ei->i_data);
+ return NULL;
+}
+
+struct inode_operations ext4_symlink_inode_operations = {
+ .readlink = generic_readlink,
+ .follow_link = page_follow_link_light,
+ .put_link = page_put_link,
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = ext4_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+};
+
+struct inode_operations ext4_fast_symlink_inode_operations = {
+ .readlink = generic_readlink,
+ .follow_link = ext4_follow_link,
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = ext4_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+};
--- /dev/null
+/*
+ * linux/fs/ext4/xattr.c
+ *
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ *
+ * Fix by Harrison Xing <harrison@mountainviewdata.com>.
+ * Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>.
+ * Extended attributes for symlinks and special files added per
+ * suggestion of Luka Renko <luka.renko@hermes.si>.
+ * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>,
+ * Red Hat Inc.
+ * ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz
+ * and Andreas Gruenbacher <agruen@suse.de>.
+ */
+
+/*
+ * Extended attributes are stored directly in inodes (on file systems with
+ * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl
+ * field contains the block number if an inode uses an additional block. All
+ * attributes must fit in the inode and one additional block. Blocks that
+ * contain the identical set of attributes may be shared among several inodes.
+ * Identical blocks are detected by keeping a cache of blocks that have
+ * recently been accessed.
+ *
+ * The attributes in inodes and on blocks have a different header; the entries
+ * are stored in the same format:
+ *
+ * +------------------+
+ * | header |
+ * | entry 1 | |
+ * | entry 2 | | growing downwards
+ * | entry 3 | v
+ * | four null bytes |
+ * | . . . |
+ * | value 1 | ^
+ * | value 3 | | growing upwards
+ * | value 2 | |
+ * +------------------+
+ *
+ * The header is followed by multiple entry descriptors. In disk blocks, the
+ * entry descriptors are kept sorted. In inodes, they are unsorted. The
+ * attribute values are aligned to the end of the block in no specific order.
+ *
+ * Locking strategy
+ * ----------------
+ * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem.
+ * EA blocks are only changed if they are exclusive to an inode, so
+ * holding xattr_sem also means that nothing but the EA block's reference
+ * count can change. Multiple writers to the same block are synchronized
+ * by the buffer lock.
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/mbcache.h>
+#include <linux/quotaops.h>
+#include <linux/rwsem.h>
+#include "xattr.h"
+#include "acl.h"
+
+#define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data))
+#define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr))
+#define BFIRST(bh) ENTRY(BHDR(bh)+1)
+#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)
+
+#define IHDR(inode, raw_inode) \
+ ((struct ext4_xattr_ibody_header *) \
+ ((void *)raw_inode + \
+ EXT4_GOOD_OLD_INODE_SIZE + \
+ EXT4_I(inode)->i_extra_isize))
+#define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
+
+#ifdef EXT4_XATTR_DEBUG
+# define ea_idebug(inode, f...) do { \
+ printk(KERN_DEBUG "inode %s:%lu: ", \
+ inode->i_sb->s_id, inode->i_ino); \
+ printk(f); \
+ printk("\n"); \
+ } while (0)
+# define ea_bdebug(bh, f...) do { \
+ char b[BDEVNAME_SIZE]; \
+ printk(KERN_DEBUG "block %s:%lu: ", \
+ bdevname(bh->b_bdev, b), \
+ (unsigned long) bh->b_blocknr); \
+ printk(f); \
+ printk("\n"); \
+ } while (0)
+#else
+# define ea_idebug(f...)
+# define ea_bdebug(f...)
+#endif
+
+static void ext4_xattr_cache_insert(struct buffer_head *);
+static struct buffer_head *ext4_xattr_cache_find(struct inode *,
+ struct ext4_xattr_header *,
+ struct mb_cache_entry **);
+static void ext4_xattr_rehash(struct ext4_xattr_header *,
+ struct ext4_xattr_entry *);
+
+static struct mb_cache *ext4_xattr_cache;
+
+static struct xattr_handler *ext4_xattr_handler_map[] = {
+ [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler,
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+ [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &ext4_xattr_acl_access_handler,
+ [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext4_xattr_acl_default_handler,
+#endif
+ [EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler,
+#ifdef CONFIG_EXT4DEV_FS_SECURITY
+ [EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler,
+#endif
+};
+
+struct xattr_handler *ext4_xattr_handlers[] = {
+ &ext4_xattr_user_handler,
+ &ext4_xattr_trusted_handler,
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+ &ext4_xattr_acl_access_handler,
+ &ext4_xattr_acl_default_handler,
+#endif
+#ifdef CONFIG_EXT4DEV_FS_SECURITY
+ &ext4_xattr_security_handler,
+#endif
+ NULL
+};
+
+static inline struct xattr_handler *
+ext4_xattr_handler(int name_index)
+{
+ struct xattr_handler *handler = NULL;
+
+ if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map))
+ handler = ext4_xattr_handler_map[name_index];
+ return handler;
+}
+
+/*
+ * Inode operation listxattr()
+ *
+ * dentry->d_inode->i_mutex: don't care
+ */
+ssize_t
+ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+ return ext4_xattr_list(dentry->d_inode, buffer, size);
+}
+
+static int
+ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
+{
+ while (!IS_LAST_ENTRY(entry)) {
+ struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry);
+ if ((void *)next >= end)
+ return -EIO;
+ entry = next;
+ }
+ return 0;
+}
+
+static inline int
+ext4_xattr_check_block(struct buffer_head *bh)
+{
+ int error;
+
+ if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
+ BHDR(bh)->h_blocks != cpu_to_le32(1))
+ return -EIO;
+ error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
+ return error;
+}
+
+static inline int
+ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size)
+{
+ size_t value_size = le32_to_cpu(entry->e_value_size);
+
+ if (entry->e_value_block != 0 || value_size > size ||
+ le16_to_cpu(entry->e_value_offs) + value_size > size)
+ return -EIO;
+ return 0;
+}
+
+static int
+ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
+ const char *name, size_t size, int sorted)
+{
+ struct ext4_xattr_entry *entry;
+ size_t name_len;
+ int cmp = 1;
+
+ if (name == NULL)
+ return -EINVAL;
+ name_len = strlen(name);
+ entry = *pentry;
+ for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
+ cmp = name_index - entry->e_name_index;
+ if (!cmp)
+ cmp = name_len - entry->e_name_len;
+ if (!cmp)
+ cmp = memcmp(name, entry->e_name, name_len);
+ if (cmp <= 0 && (sorted || cmp == 0))
+ break;
+ }
+ *pentry = entry;
+ if (!cmp && ext4_xattr_check_entry(entry, size))
+ return -EIO;
+ return cmp ? -ENODATA : 0;
+}
+
+static int
+ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
+ void *buffer, size_t buffer_size)
+{
+ struct buffer_head *bh = NULL;
+ struct ext4_xattr_entry *entry;
+ size_t size;
+ int error;
+
+ ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
+ name_index, name, buffer, (long)buffer_size);
+
+ error = -ENODATA;
+ if (!EXT4_I(inode)->i_file_acl)
+ goto cleanup;
+ ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
+ bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+ if (!bh)
+ goto cleanup;
+ ea_bdebug(bh, "b_count=%d, refcount=%d",
+ atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
+ if (ext4_xattr_check_block(bh)) {
+bad_block: ext4_error(inode->i_sb, __FUNCTION__,
+ "inode %lu: bad block %llu", inode->i_ino,
+ EXT4_I(inode)->i_file_acl);
+ error = -EIO;
+ goto cleanup;
+ }
+ ext4_xattr_cache_insert(bh);
+ entry = BFIRST(bh);
+ error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1);
+ if (error == -EIO)
+ goto bad_block;
+ if (error)
+ goto cleanup;
+ size = le32_to_cpu(entry->e_value_size);
+ if (buffer) {
+ error = -ERANGE;
+ if (size > buffer_size)
+ goto cleanup;
+ memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs),
+ size);
+ }
+ error = size;
+
+cleanup:
+ brelse(bh);
+ return error;
+}
+
+static int
+ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
+ void *buffer, size_t buffer_size)
+{
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_xattr_entry *entry;
+ struct ext4_inode *raw_inode;
+ struct ext4_iloc iloc;
+ size_t size;
+ void *end;
+ int error;
+
+ if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
+ return -ENODATA;
+ error = ext4_get_inode_loc(inode, &iloc);
+ if (error)
+ return error;
+ raw_inode = ext4_raw_inode(&iloc);
+ header = IHDR(inode, raw_inode);
+ entry = IFIRST(header);
+ end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+ error = ext4_xattr_check_names(entry, end);
+ if (error)
+ goto cleanup;
+ error = ext4_xattr_find_entry(&entry, name_index, name,
+ end - (void *)entry, 0);
+ if (error)
+ goto cleanup;
+ size = le32_to_cpu(entry->e_value_size);
+ if (buffer) {
+ error = -ERANGE;
+ if (size > buffer_size)
+ goto cleanup;
+ memcpy(buffer, (void *)IFIRST(header) +
+ le16_to_cpu(entry->e_value_offs), size);
+ }
+ error = size;
+
+cleanup:
+ brelse(iloc.bh);
+ return error;
+}
+
+/*
+ * ext4_xattr_get()
+ *
+ * Copy an extended attribute into the buffer
+ * provided, or compute the buffer size required.
+ * Buffer is NULL to compute the size of the buffer required.
+ *
+ * Returns a negative error number on failure, or the number of bytes
+ * used / required on success.
+ */
+int
+ext4_xattr_get(struct inode *inode, int name_index, const char *name,
+ void *buffer, size_t buffer_size)
+{
+ int error;
+
+ down_read(&EXT4_I(inode)->xattr_sem);
+ error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
+ buffer_size);
+ if (error == -ENODATA)
+ error = ext4_xattr_block_get(inode, name_index, name, buffer,
+ buffer_size);
+ up_read(&EXT4_I(inode)->xattr_sem);
+ return error;
+}
+
+static int
+ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
+ char *buffer, size_t buffer_size)
+{
+ size_t rest = buffer_size;
+
+ for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
+ struct xattr_handler *handler =
+ ext4_xattr_handler(entry->e_name_index);
+
+ if (handler) {
+ size_t size = handler->list(inode, buffer, rest,
+ entry->e_name,
+ entry->e_name_len);
+ if (buffer) {
+ if (size > rest)
+ return -ERANGE;
+ buffer += size;
+ }
+ rest -= size;
+ }
+ }
+ return buffer_size - rest;
+}
+
+static int
+ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
+{
+ struct buffer_head *bh = NULL;
+ int error;
+
+ ea_idebug(inode, "buffer=%p, buffer_size=%ld",
+ buffer, (long)buffer_size);
+
+ error = 0;
+ if (!EXT4_I(inode)->i_file_acl)
+ goto cleanup;
+ ea_idebug(inode, "reading block %u", EXT4_I(inode)->i_file_acl);
+ bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+ error = -EIO;
+ if (!bh)
+ goto cleanup;
+ ea_bdebug(bh, "b_count=%d, refcount=%d",
+ atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
+ if (ext4_xattr_check_block(bh)) {
+ ext4_error(inode->i_sb, __FUNCTION__,
+ "inode %lu: bad block %llu", inode->i_ino,
+ EXT4_I(inode)->i_file_acl);
+ error = -EIO;
+ goto cleanup;
+ }
+ ext4_xattr_cache_insert(bh);
+ error = ext4_xattr_list_entries(inode, BFIRST(bh), buffer, buffer_size);
+
+cleanup:
+ brelse(bh);
+
+ return error;
+}
+
+static int
+ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
+{
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_inode *raw_inode;
+ struct ext4_iloc iloc;
+ void *end;
+ int error;
+
+ if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR))
+ return 0;
+ error = ext4_get_inode_loc(inode, &iloc);
+ if (error)
+ return error;
+ raw_inode = ext4_raw_inode(&iloc);
+ header = IHDR(inode, raw_inode);
+ end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+ error = ext4_xattr_check_names(IFIRST(header), end);
+ if (error)
+ goto cleanup;
+ error = ext4_xattr_list_entries(inode, IFIRST(header),
+ buffer, buffer_size);
+
+cleanup:
+ brelse(iloc.bh);
+ return error;
+}
+
+/*
+ * ext4_xattr_list()
+ *
+ * Copy a list of attribute names into the buffer
+ * provided, or compute the buffer size required.
+ * Buffer is NULL to compute the size of the buffer required.
+ *
+ * Returns a negative error number on failure, or the number of bytes
+ * used / required on success.
+ */
+int
+ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
+{
+ int i_error, b_error;
+
+ down_read(&EXT4_I(inode)->xattr_sem);
+ i_error = ext4_xattr_ibody_list(inode, buffer, buffer_size);
+ if (i_error < 0) {
+ b_error = 0;
+ } else {
+ if (buffer) {
+ buffer += i_error;
+ buffer_size -= i_error;
+ }
+ b_error = ext4_xattr_block_list(inode, buffer, buffer_size);
+ if (b_error < 0)
+ i_error = 0;
+ }
+ up_read(&EXT4_I(inode)->xattr_sem);
+ return i_error + b_error;
+}
+
+/*
+ * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is
+ * not set, set it.
+ */
+static void ext4_xattr_update_super_block(handle_t *handle,
+ struct super_block *sb)
+{
+ if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR))
+ return;
+
+ lock_super(sb);
+ if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
+ EXT4_SB(sb)->s_es->s_feature_compat |=
+ cpu_to_le32(EXT4_FEATURE_COMPAT_EXT_ATTR);
+ sb->s_dirt = 1;
+ ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
+ }
+ unlock_super(sb);
+}
+
+/*
+ * Release the xattr block BH: If the reference count is > 1, decrement
+ * it; otherwise free the block.
+ */
+static void
+ext4_xattr_release_block(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh)
+{
+ struct mb_cache_entry *ce = NULL;
+
+ ce = mb_cache_entry_get(ext4_xattr_cache, bh->b_bdev, bh->b_blocknr);
+ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) {
+ ea_bdebug(bh, "refcount now=0; freeing");
+ if (ce)
+ mb_cache_entry_free(ce);
+ ext4_free_blocks(handle, inode, bh->b_blocknr, 1);
+ get_bh(bh);
+ ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
+ } else {
+ if (ext4_journal_get_write_access(handle, bh) == 0) {
+ lock_buffer(bh);
+ BHDR(bh)->h_refcount = cpu_to_le32(
+ le32_to_cpu(BHDR(bh)->h_refcount) - 1);
+ ext4_journal_dirty_metadata(handle, bh);
+ if (IS_SYNC(inode))
+ handle->h_sync = 1;
+ DQUOT_FREE_BLOCK(inode, 1);
+ unlock_buffer(bh);
+ ea_bdebug(bh, "refcount now=%d; releasing",
+ le32_to_cpu(BHDR(bh)->h_refcount));
+ }
+ if (ce)
+ mb_cache_entry_release(ce);
+ }
+}
+
+struct ext4_xattr_info {
+ int name_index;
+ const char *name;
+ const void *value;
+ size_t value_len;
+};
+
+struct ext4_xattr_search {
+ struct ext4_xattr_entry *first;
+ void *base;
+ void *end;
+ struct ext4_xattr_entry *here;
+ int not_found;
+};
+
+static int
+ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
+{
+ struct ext4_xattr_entry *last;
+ size_t free, min_offs = s->end - s->base, name_len = strlen(i->name);
+
+ /* Compute min_offs and last. */
+ last = s->first;
+ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+ if (!last->e_value_block && last->e_value_size) {
+ size_t offs = le16_to_cpu(last->e_value_offs);
+ if (offs < min_offs)
+ min_offs = offs;
+ }
+ }
+ free = min_offs - ((void *)last - s->base) - sizeof(__u32);
+ if (!s->not_found) {
+ if (!s->here->e_value_block && s->here->e_value_size) {
+ size_t size = le32_to_cpu(s->here->e_value_size);
+ free += EXT4_XATTR_SIZE(size);
+ }
+ free += EXT4_XATTR_LEN(name_len);
+ }
+ if (i->value) {
+ if (free < EXT4_XATTR_SIZE(i->value_len) ||
+ free < EXT4_XATTR_LEN(name_len) +
+ EXT4_XATTR_SIZE(i->value_len))
+ return -ENOSPC;
+ }
+
+ if (i->value && s->not_found) {
+ /* Insert the new name. */
+ size_t size = EXT4_XATTR_LEN(name_len);
+ size_t rest = (void *)last - (void *)s->here + sizeof(__u32);
+ memmove((void *)s->here + size, s->here, rest);
+ memset(s->here, 0, size);
+ s->here->e_name_index = i->name_index;
+ s->here->e_name_len = name_len;
+ memcpy(s->here->e_name, i->name, name_len);
+ } else {
+ if (!s->here->e_value_block && s->here->e_value_size) {
+ void *first_val = s->base + min_offs;
+ size_t offs = le16_to_cpu(s->here->e_value_offs);
+ void *val = s->base + offs;
+ size_t size = EXT4_XATTR_SIZE(
+ le32_to_cpu(s->here->e_value_size));
+
+ if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) {
+ /* The old and the new value have the same
+ size. Just replace. */
+ s->here->e_value_size =
+ cpu_to_le32(i->value_len);
+ memset(val + size - EXT4_XATTR_PAD, 0,
+ EXT4_XATTR_PAD); /* Clear pad bytes. */
+ memcpy(val, i->value, i->value_len);
+ return 0;
+ }
+
+ /* Remove the old value. */
+ memmove(first_val + size, first_val, val - first_val);
+ memset(first_val, 0, size);
+ s->here->e_value_size = 0;
+ s->here->e_value_offs = 0;
+ min_offs += size;
+
+ /* Adjust all value offsets. */
+ last = s->first;
+ while (!IS_LAST_ENTRY(last)) {
+ size_t o = le16_to_cpu(last->e_value_offs);
+ if (!last->e_value_block &&
+ last->e_value_size && o < offs)
+ last->e_value_offs =
+ cpu_to_le16(o + size);
+ last = EXT4_XATTR_NEXT(last);
+ }
+ }
+ if (!i->value) {
+ /* Remove the old name. */
+ size_t size = EXT4_XATTR_LEN(name_len);
+ last = ENTRY((void *)last - size);
+ memmove(s->here, (void *)s->here + size,
+ (void *)last - (void *)s->here + sizeof(__u32));
+ memset(last, 0, size);
+ }
+ }
+
+ if (i->value) {
+ /* Insert the new value. */
+ s->here->e_value_size = cpu_to_le32(i->value_len);
+ if (i->value_len) {
+ size_t size = EXT4_XATTR_SIZE(i->value_len);
+ void *val = s->base + min_offs - size;
+ s->here->e_value_offs = cpu_to_le16(min_offs - size);
+ memset(val + size - EXT4_XATTR_PAD, 0,
+ EXT4_XATTR_PAD); /* Clear the pad bytes. */
+ memcpy(val, i->value, i->value_len);
+ }
+ }
+ return 0;
+}
+
+struct ext4_xattr_block_find {
+ struct ext4_xattr_search s;
+ struct buffer_head *bh;
+};
+
+static int
+ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
+ struct ext4_xattr_block_find *bs)
+{
+ struct super_block *sb = inode->i_sb;
+ int error;
+
+ ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld",
+ i->name_index, i->name, i->value, (long)i->value_len);
+
+ if (EXT4_I(inode)->i_file_acl) {
+ /* The inode already has an extended attribute block. */
+ bs->bh = sb_bread(sb, EXT4_I(inode)->i_file_acl);
+ error = -EIO;
+ if (!bs->bh)
+ goto cleanup;
+ ea_bdebug(bs->bh, "b_count=%d, refcount=%d",
+ atomic_read(&(bs->bh->b_count)),
+ le32_to_cpu(BHDR(bs->bh)->h_refcount));
+ if (ext4_xattr_check_block(bs->bh)) {
+ ext4_error(sb, __FUNCTION__,
+ "inode %lu: bad block %llu", inode->i_ino,
+ EXT4_I(inode)->i_file_acl);
+ error = -EIO;
+ goto cleanup;
+ }
+ /* Find the named attribute. */
+ bs->s.base = BHDR(bs->bh);
+ bs->s.first = BFIRST(bs->bh);
+ bs->s.end = bs->bh->b_data + bs->bh->b_size;
+ bs->s.here = bs->s.first;
+ error = ext4_xattr_find_entry(&bs->s.here, i->name_index,
+ i->name, bs->bh->b_size, 1);
+ if (error && error != -ENODATA)
+ goto cleanup;
+ bs->s.not_found = error;
+ }
+ error = 0;
+
+cleanup:
+ return error;
+}
+
+static int
+ext4_xattr_block_set(handle_t *handle, struct inode *inode,
+ struct ext4_xattr_info *i,
+ struct ext4_xattr_block_find *bs)
+{
+ struct super_block *sb = inode->i_sb;
+ struct buffer_head *new_bh = NULL;
+ struct ext4_xattr_search *s = &bs->s;
+ struct mb_cache_entry *ce = NULL;
+ int error;
+
+#define header(x) ((struct ext4_xattr_header *)(x))
+
+ if (i->value && i->value_len > sb->s_blocksize)
+ return -ENOSPC;
+ if (s->base) {
+ ce = mb_cache_entry_get(ext4_xattr_cache, bs->bh->b_bdev,
+ bs->bh->b_blocknr);
+ if (header(s->base)->h_refcount == cpu_to_le32(1)) {
+ if (ce) {
+ mb_cache_entry_free(ce);
+ ce = NULL;
+ }
+ ea_bdebug(bs->bh, "modifying in-place");
+ error = ext4_journal_get_write_access(handle, bs->bh);
+ if (error)
+ goto cleanup;
+ lock_buffer(bs->bh);
+ error = ext4_xattr_set_entry(i, s);
+ if (!error) {
+ if (!IS_LAST_ENTRY(s->first))
+ ext4_xattr_rehash(header(s->base),
+ s->here);
+ ext4_xattr_cache_insert(bs->bh);
+ }
+ unlock_buffer(bs->bh);
+ if (error == -EIO)
+ goto bad_block;
+ if (!error)
+ error = ext4_journal_dirty_metadata(handle,
+ bs->bh);
+ if (error)
+ goto cleanup;
+ goto inserted;
+ } else {
+ int offset = (char *)s->here - bs->bh->b_data;
+
+ if (ce) {
+ mb_cache_entry_release(ce);
+ ce = NULL;
+ }
+ ea_bdebug(bs->bh, "cloning");
+ s->base = kmalloc(bs->bh->b_size, GFP_KERNEL);
+ error = -ENOMEM;
+ if (s->base == NULL)
+ goto cleanup;
+ memcpy(s->base, BHDR(bs->bh), bs->bh->b_size);
+ s->first = ENTRY(header(s->base)+1);
+ header(s->base)->h_refcount = cpu_to_le32(1);
+ s->here = ENTRY(s->base + offset);
+ s->end = s->base + bs->bh->b_size;
+ }
+ } else {
+ /* Allocate a buffer where we construct the new block. */
+ s->base = kmalloc(sb->s_blocksize, GFP_KERNEL);
+ /* assert(header == s->base) */
+ error = -ENOMEM;
+ if (s->base == NULL)
+ goto cleanup;
+ memset(s->base, 0, sb->s_blocksize);
+ header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
+ header(s->base)->h_blocks = cpu_to_le32(1);
+ header(s->base)->h_refcount = cpu_to_le32(1);
+ s->first = ENTRY(header(s->base)+1);
+ s->here = ENTRY(header(s->base)+1);
+ s->end = s->base + sb->s_blocksize;
+ }
+
+ error = ext4_xattr_set_entry(i, s);
+ if (error == -EIO)
+ goto bad_block;
+ if (error)
+ goto cleanup;
+ if (!IS_LAST_ENTRY(s->first))
+ ext4_xattr_rehash(header(s->base), s->here);
+
+inserted:
+ if (!IS_LAST_ENTRY(s->first)) {
+ new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce);
+ if (new_bh) {
+ /* We found an identical block in the cache. */
+ if (new_bh == bs->bh)
+ ea_bdebug(new_bh, "keeping");
+ else {
+ /* The old block is released after updating
+ the inode. */
+ error = -EDQUOT;
+ if (DQUOT_ALLOC_BLOCK(inode, 1))
+ goto cleanup;
+ error = ext4_journal_get_write_access(handle,
+ new_bh);
+ if (error)
+ goto cleanup_dquot;
+ lock_buffer(new_bh);
+ BHDR(new_bh)->h_refcount = cpu_to_le32(1 +
+ le32_to_cpu(BHDR(new_bh)->h_refcount));
+ ea_bdebug(new_bh, "reusing; refcount now=%d",
+ le32_to_cpu(BHDR(new_bh)->h_refcount));
+ unlock_buffer(new_bh);
+ error = ext4_journal_dirty_metadata(handle,
+ new_bh);
+ if (error)
+ goto cleanup_dquot;
+ }
+ mb_cache_entry_release(ce);
+ ce = NULL;
+ } else if (bs->bh && s->base == bs->bh->b_data) {
+ /* We were modifying this block in-place. */
+ ea_bdebug(bs->bh, "keeping this block");
+ new_bh = bs->bh;
+ get_bh(new_bh);
+ } else {
+ /* We need to allocate a new block */
+ ext4_fsblk_t goal = le32_to_cpu(
+ EXT4_SB(sb)->s_es->s_first_data_block) +
+ (ext4_fsblk_t)EXT4_I(inode)->i_block_group *
+ EXT4_BLOCKS_PER_GROUP(sb);
+ ext4_fsblk_t block = ext4_new_block(handle, inode,
+ goal, &error);
+ if (error)
+ goto cleanup;
+ ea_idebug(inode, "creating block %d", block);
+
+ new_bh = sb_getblk(sb, block);
+ if (!new_bh) {
+getblk_failed:
+ ext4_free_blocks(handle, inode, block, 1);
+ error = -EIO;
+ goto cleanup;
+ }
+ lock_buffer(new_bh);
+ error = ext4_journal_get_create_access(handle, new_bh);
+ if (error) {
+ unlock_buffer(new_bh);
+ goto getblk_failed;
+ }
+ memcpy(new_bh->b_data, s->base, new_bh->b_size);
+ set_buffer_uptodate(new_bh);
+ unlock_buffer(new_bh);
+ ext4_xattr_cache_insert(new_bh);
+ error = ext4_journal_dirty_metadata(handle, new_bh);
+ if (error)
+ goto cleanup;
+ }
+ }
+
+ /* Update the inode. */
+ EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;
+
+ /* Drop the previous xattr block. */
+ if (bs->bh && bs->bh != new_bh)
+ ext4_xattr_release_block(handle, inode, bs->bh);
+ error = 0;
+
+cleanup:
+ if (ce)
+ mb_cache_entry_release(ce);
+ brelse(new_bh);
+ if (!(bs->bh && s->base == bs->bh->b_data))
+ kfree(s->base);
+
+ return error;
+
+cleanup_dquot:
+ DQUOT_FREE_BLOCK(inode, 1);
+ goto cleanup;
+
+bad_block:
+ ext4_error(inode->i_sb, __FUNCTION__,
+ "inode %lu: bad block %llu", inode->i_ino,
+ EXT4_I(inode)->i_file_acl);
+ goto cleanup;
+
+#undef header
+}
+
+struct ext4_xattr_ibody_find {
+ struct ext4_xattr_search s;
+ struct ext4_iloc iloc;
+};
+
+static int
+ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
+ struct ext4_xattr_ibody_find *is)
+{
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_inode *raw_inode;
+ int error;
+
+ if (EXT4_I(inode)->i_extra_isize == 0)
+ return 0;
+ raw_inode = ext4_raw_inode(&is->iloc);
+ header = IHDR(inode, raw_inode);
+ is->s.base = is->s.first = IFIRST(header);
+ is->s.here = is->s.first;
+ is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+ if (EXT4_I(inode)->i_state & EXT4_STATE_XATTR) {
+ error = ext4_xattr_check_names(IFIRST(header), is->s.end);
+ if (error)
+ return error;
+ /* Find the named attribute. */
+ error = ext4_xattr_find_entry(&is->s.here, i->name_index,
+ i->name, is->s.end -
+ (void *)is->s.base, 0);
+ if (error && error != -ENODATA)
+ return error;
+ is->s.not_found = error;
+ }
+ return 0;
+}
+
+static int
+ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+ struct ext4_xattr_info *i,
+ struct ext4_xattr_ibody_find *is)
+{
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_xattr_search *s = &is->s;
+ int error;
+
+ if (EXT4_I(inode)->i_extra_isize == 0)
+ return -ENOSPC;
+ error = ext4_xattr_set_entry(i, s);
+ if (error)
+ return error;
+ header = IHDR(inode, ext4_raw_inode(&is->iloc));
+ if (!IS_LAST_ENTRY(s->first)) {
+ header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
+ EXT4_I(inode)->i_state |= EXT4_STATE_XATTR;
+ } else {
+ header->h_magic = cpu_to_le32(0);
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_XATTR;
+ }
+ return 0;
+}
+
+/*
+ * ext4_xattr_set_handle()
+ *
+ * Create, replace or remove an extended attribute for this inode. Buffer
+ * is NULL to remove an existing extended attribute, and non-NULL to
+ * either replace an existing extended attribute, or create a new extended
+ * attribute. The flags XATTR_REPLACE and XATTR_CREATE
+ * specify that an extended attribute must exist and must not exist
+ * previous to the call, respectively.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+int
+ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
+ const char *name, const void *value, size_t value_len,
+ int flags)
+{
+ struct ext4_xattr_info i = {
+ .name_index = name_index,
+ .name = name,
+ .value = value,
+ .value_len = value_len,
+
+ };
+ struct ext4_xattr_ibody_find is = {
+ .s = { .not_found = -ENODATA, },
+ };
+ struct ext4_xattr_block_find bs = {
+ .s = { .not_found = -ENODATA, },
+ };
+ int error;
+
+ if (!name)
+ return -EINVAL;
+ if (strlen(name) > 255)
+ return -ERANGE;
+ down_write(&EXT4_I(inode)->xattr_sem);
+ error = ext4_get_inode_loc(inode, &is.iloc);
+ if (error)
+ goto cleanup;
+
+ if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) {
+ struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
+ memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_NEW;
+ }
+
+ error = ext4_xattr_ibody_find(inode, &i, &is);
+ if (error)
+ goto cleanup;
+ if (is.s.not_found)
+ error = ext4_xattr_block_find(inode, &i, &bs);
+ if (error)
+ goto cleanup;
+ if (is.s.not_found && bs.s.not_found) {
+ error = -ENODATA;
+ if (flags & XATTR_REPLACE)
+ goto cleanup;
+ error = 0;
+ if (!value)
+ goto cleanup;
+ } else {
+ error = -EEXIST;
+ if (flags & XATTR_CREATE)
+ goto cleanup;
+ }
+ error = ext4_journal_get_write_access(handle, is.iloc.bh);
+ if (error)
+ goto cleanup;
+ if (!value) {
+ if (!is.s.not_found)
+ error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+ else if (!bs.s.not_found)
+ error = ext4_xattr_block_set(handle, inode, &i, &bs);
+ } else {
+ error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+ if (!error && !bs.s.not_found) {
+ i.value = NULL;
+ error = ext4_xattr_block_set(handle, inode, &i, &bs);
+ } else if (error == -ENOSPC) {
+ error = ext4_xattr_block_set(handle, inode, &i, &bs);
+ if (error)
+ goto cleanup;
+ if (!is.s.not_found) {
+ i.value = NULL;
+ error = ext4_xattr_ibody_set(handle, inode, &i,
+ &is);
+ }
+ }
+ }
+ if (!error) {
+ ext4_xattr_update_super_block(handle, inode->i_sb);
+ inode->i_ctime = CURRENT_TIME_SEC;
+ error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
+ /*
+ * The bh is consumed by ext4_mark_iloc_dirty, even with
+ * error != 0.
+ */
+ is.iloc.bh = NULL;
+ if (IS_SYNC(inode))
+ handle->h_sync = 1;
+ }
+
+cleanup:
+ brelse(is.iloc.bh);
+ brelse(bs.bh);
+ up_write(&EXT4_I(inode)->xattr_sem);
+ return error;
+}
+
+/*
+ * ext4_xattr_set()
+ *
+ * Like ext4_xattr_set_handle, but start from an inode. This extended
+ * attribute modification is a filesystem transaction by itself.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+int
+ext4_xattr_set(struct inode *inode, int name_index, const char *name,
+ const void *value, size_t value_len, int flags)
+{
+ handle_t *handle;
+ int error, retries = 0;
+
+retry:
+ handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+ if (IS_ERR(handle)) {
+ error = PTR_ERR(handle);
+ } else {
+ int error2;
+
+ error = ext4_xattr_set_handle(handle, inode, name_index, name,
+ value, value_len, flags);
+ error2 = ext4_journal_stop(handle);
+ if (error == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+ if (error == 0)
+ error = error2;
+ }
+
+ return error;
+}
+
+/*
+ * ext4_xattr_delete_inode()
+ *
+ * Free extended attribute resources associated with this inode. This
+ * is called immediately before an inode is freed. We have exclusive
+ * access to the inode.
+ */
+void
+ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
+{
+ struct buffer_head *bh = NULL;
+
+ if (!EXT4_I(inode)->i_file_acl)
+ goto cleanup;
+ bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+ if (!bh) {
+ ext4_error(inode->i_sb, __FUNCTION__,
+ "inode %lu: block %llu read error", inode->i_ino,
+ EXT4_I(inode)->i_file_acl);
+ goto cleanup;
+ }
+ if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
+ BHDR(bh)->h_blocks != cpu_to_le32(1)) {
+ ext4_error(inode->i_sb, __FUNCTION__,
+ "inode %lu: bad block %llu", inode->i_ino,
+ EXT4_I(inode)->i_file_acl);
+ goto cleanup;
+ }
+ ext4_xattr_release_block(handle, inode, bh);
+ EXT4_I(inode)->i_file_acl = 0;
+
+cleanup:
+ brelse(bh);
+}
+
+/*
+ * ext4_xattr_put_super()
+ *
+ * This is called when a file system is unmounted.
+ */
+void
+ext4_xattr_put_super(struct super_block *sb)
+{
+ mb_cache_shrink(sb->s_bdev);
+}
+
+/*
+ * ext4_xattr_cache_insert()
+ *
+ * Create a new entry in the extended attribute cache, and insert
+ * it unless such an entry is already in the cache.
+ *
+ * Returns 0, or a negative error number on failure.
+ */
+static void
+ext4_xattr_cache_insert(struct buffer_head *bh)
+{
+ __u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
+ struct mb_cache_entry *ce;
+ int error;
+
+ ce = mb_cache_entry_alloc(ext4_xattr_cache);
+ if (!ce) {
+ ea_bdebug(bh, "out of memory");
+ return;
+ }
+ error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, &hash);
+ if (error) {
+ mb_cache_entry_free(ce);
+ if (error == -EBUSY) {
+ ea_bdebug(bh, "already in cache");
+ error = 0;
+ }
+ } else {
+ ea_bdebug(bh, "inserting [%x]", (int)hash);
+ mb_cache_entry_release(ce);
+ }
+}
+
+/*
+ * ext4_xattr_cmp()
+ *
+ * Compare two extended attribute blocks for equality.
+ *
+ * Returns 0 if the blocks are equal, 1 if they differ, and
+ * a negative error number on errors.
+ */
+static int
+ext4_xattr_cmp(struct ext4_xattr_header *header1,
+ struct ext4_xattr_header *header2)
+{
+ struct ext4_xattr_entry *entry1, *entry2;
+
+ entry1 = ENTRY(header1+1);
+ entry2 = ENTRY(header2+1);
+ while (!IS_LAST_ENTRY(entry1)) {
+ if (IS_LAST_ENTRY(entry2))
+ return 1;
+ if (entry1->e_hash != entry2->e_hash ||
+ entry1->e_name_index != entry2->e_name_index ||
+ entry1->e_name_len != entry2->e_name_len ||
+ entry1->e_value_size != entry2->e_value_size ||
+ memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len))
+ return 1;
+ if (entry1->e_value_block != 0 || entry2->e_value_block != 0)
+ return -EIO;
+ if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs),
+ (char *)header2 + le16_to_cpu(entry2->e_value_offs),
+ le32_to_cpu(entry1->e_value_size)))
+ return 1;
+
+ entry1 = EXT4_XATTR_NEXT(entry1);
+ entry2 = EXT4_XATTR_NEXT(entry2);
+ }
+ if (!IS_LAST_ENTRY(entry2))
+ return 1;
+ return 0;
+}
+
+/*
+ * ext4_xattr_cache_find()
+ *
+ * Find an identical extended attribute block.
+ *
+ * Returns a pointer to the block found, or NULL if such a block was
+ * not found or an error occurred.
+ */
+static struct buffer_head *
+ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
+ struct mb_cache_entry **pce)
+{
+ __u32 hash = le32_to_cpu(header->h_hash);
+ struct mb_cache_entry *ce;
+
+ if (!header->h_hash)
+ return NULL; /* never share */
+ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
+again:
+ ce = mb_cache_entry_find_first(ext4_xattr_cache, 0,
+ inode->i_sb->s_bdev, hash);
+ while (ce) {
+ struct buffer_head *bh;
+
+ if (IS_ERR(ce)) {
+ if (PTR_ERR(ce) == -EAGAIN)
+ goto again;
+ break;
+ }
+ bh = sb_bread(inode->i_sb, ce->e_block);
+ if (!bh) {
+ ext4_error(inode->i_sb, __FUNCTION__,
+ "inode %lu: block %lu read error",
+ inode->i_ino, (unsigned long) ce->e_block);
+ } else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
+ EXT4_XATTR_REFCOUNT_MAX) {
+ ea_idebug(inode, "block %lu refcount %d>=%d",
+ (unsigned long) ce->e_block,
+ le32_to_cpu(BHDR(bh)->h_refcount),
+ EXT4_XATTR_REFCOUNT_MAX);
+ } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
+ *pce = ce;
+ return bh;
+ }
+ brelse(bh);
+ ce = mb_cache_entry_find_next(ce, 0, inode->i_sb->s_bdev, hash);
+ }
+ return NULL;
+}
+
+#define NAME_HASH_SHIFT 5
+#define VALUE_HASH_SHIFT 16
+
+/*
+ * ext4_xattr_hash_entry()
+ *
+ * Compute the hash of an extended attribute.
+ */
+static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
+ struct ext4_xattr_entry *entry)
+{
+ __u32 hash = 0;
+ char *name = entry->e_name;
+ int n;
+
+ for (n=0; n < entry->e_name_len; n++) {
+ hash = (hash << NAME_HASH_SHIFT) ^
+ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
+ *name++;
+ }
+
+ if (entry->e_value_block == 0 && entry->e_value_size != 0) {
+ __le32 *value = (__le32 *)((char *)header +
+ le16_to_cpu(entry->e_value_offs));
+ for (n = (le32_to_cpu(entry->e_value_size) +
+ EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) {
+ hash = (hash << VALUE_HASH_SHIFT) ^
+ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
+ le32_to_cpu(*value++);
+ }
+ }
+ entry->e_hash = cpu_to_le32(hash);
+}
+
+#undef NAME_HASH_SHIFT
+#undef VALUE_HASH_SHIFT
+
+#define BLOCK_HASH_SHIFT 16
+
+/*
+ * ext4_xattr_rehash()
+ *
+ * Re-compute the extended attribute hash value after an entry has changed.
+ */
+static void ext4_xattr_rehash(struct ext4_xattr_header *header,
+ struct ext4_xattr_entry *entry)
+{
+ struct ext4_xattr_entry *here;
+ __u32 hash = 0;
+
+ ext4_xattr_hash_entry(header, entry);
+ here = ENTRY(header+1);
+ while (!IS_LAST_ENTRY(here)) {
+ if (!here->e_hash) {
+ /* Block is not shared if an entry's hash value == 0 */
+ hash = 0;
+ break;
+ }
+ hash = (hash << BLOCK_HASH_SHIFT) ^
+ (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^
+ le32_to_cpu(here->e_hash);
+ here = EXT4_XATTR_NEXT(here);
+ }
+ header->h_hash = cpu_to_le32(hash);
+}
+
+#undef BLOCK_HASH_SHIFT
+
+int __init
+init_ext4_xattr(void)
+{
+ ext4_xattr_cache = mb_cache_create("ext4_xattr", NULL,
+ sizeof(struct mb_cache_entry) +
+ sizeof(((struct mb_cache_entry *) 0)->e_indexes[0]), 1, 6);
+ if (!ext4_xattr_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void
+exit_ext4_xattr(void)
+{
+ if (ext4_xattr_cache)
+ mb_cache_destroy(ext4_xattr_cache);
+ ext4_xattr_cache = NULL;
+}
--- /dev/null
+/*
+ File: fs/ext4/xattr.h
+
+ On-disk format of extended attributes for the ext4 filesystem.
+
+ (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org>
+*/
+
+#include <linux/xattr.h>
+
+/* Magic value in attribute blocks */
+#define EXT4_XATTR_MAGIC 0xEA020000
+
+/* Maximum number of references to one attribute block */
+#define EXT4_XATTR_REFCOUNT_MAX 1024
+
+/* Name indexes */
+#define EXT4_XATTR_INDEX_USER 1
+#define EXT4_XATTR_INDEX_POSIX_ACL_ACCESS 2
+#define EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT 3
+#define EXT4_XATTR_INDEX_TRUSTED 4
+#define EXT4_XATTR_INDEX_LUSTRE 5
+#define EXT4_XATTR_INDEX_SECURITY 6
+
+struct ext4_xattr_header {
+ __le32 h_magic; /* magic number for identification */
+ __le32 h_refcount; /* reference count */
+ __le32 h_blocks; /* number of disk blocks used */
+ __le32 h_hash; /* hash value of all attributes */
+ __u32 h_reserved[4]; /* zero right now */
+};
+
+struct ext4_xattr_ibody_header {
+ __le32 h_magic; /* magic number for identification */
+};
+
+struct ext4_xattr_entry {
+ __u8 e_name_len; /* length of name */
+ __u8 e_name_index; /* attribute name index */
+ __le16 e_value_offs; /* offset in disk block of value */
+ __le32 e_value_block; /* disk block attribute is stored on (n/i) */
+ __le32 e_value_size; /* size of attribute value */
+ __le32 e_hash; /* hash value of name and value */
+ char e_name[0]; /* attribute name */
+};
+
+#define EXT4_XATTR_PAD_BITS 2
+#define EXT4_XATTR_PAD (1<<EXT4_XATTR_PAD_BITS)
+#define EXT4_XATTR_ROUND (EXT4_XATTR_PAD-1)
+#define EXT4_XATTR_LEN(name_len) \
+ (((name_len) + EXT4_XATTR_ROUND + \
+ sizeof(struct ext4_xattr_entry)) & ~EXT4_XATTR_ROUND)
+#define EXT4_XATTR_NEXT(entry) \
+ ( (struct ext4_xattr_entry *)( \
+ (char *)(entry) + EXT4_XATTR_LEN((entry)->e_name_len)) )
+#define EXT4_XATTR_SIZE(size) \
+ (((size) + EXT4_XATTR_ROUND) & ~EXT4_XATTR_ROUND)
+
+# ifdef CONFIG_EXT4DEV_FS_XATTR
+
+extern struct xattr_handler ext4_xattr_user_handler;
+extern struct xattr_handler ext4_xattr_trusted_handler;
+extern struct xattr_handler ext4_xattr_acl_access_handler;
+extern struct xattr_handler ext4_xattr_acl_default_handler;
+extern struct xattr_handler ext4_xattr_security_handler;
+
+extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
+
+extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);
+extern int ext4_xattr_list(struct inode *, char *, size_t);
+extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
+extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
+
+extern void ext4_xattr_delete_inode(handle_t *, struct inode *);
+extern void ext4_xattr_put_super(struct super_block *);
+
+extern int init_ext4_xattr(void);
+extern void exit_ext4_xattr(void);
+
+extern struct xattr_handler *ext4_xattr_handlers[];
+
+# else /* CONFIG_EXT4DEV_FS_XATTR */
+
+static inline int
+ext4_xattr_get(struct inode *inode, int name_index, const char *name,
+ void *buffer, size_t size, int flags)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ext4_xattr_list(struct inode *inode, void *buffer, size_t size)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ext4_xattr_set(struct inode *inode, int name_index, const char *name,
+ const void *value, size_t size, int flags)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int
+ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
+ const char *name, const void *value, size_t size, int flags)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void
+ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
+{
+}
+
+static inline void
+ext4_xattr_put_super(struct super_block *sb)
+{
+}
+
+static inline int
+init_ext4_xattr(void)
+{
+ return 0;
+}
+
+static inline void
+exit_ext4_xattr(void)
+{
+}
+
+#define ext4_xattr_handlers NULL
+
+# endif /* CONFIG_EXT4DEV_FS_XATTR */
+
+#ifdef CONFIG_EXT4DEV_FS_SECURITY
+extern int ext4_init_security(handle_t *handle, struct inode *inode,
+ struct inode *dir);
+#else
+static inline int ext4_init_security(handle_t *handle, struct inode *inode,
+ struct inode *dir)
+{
+ return 0;
+}
+#endif
--- /dev/null
+/*
+ * linux/fs/ext4/xattr_security.c
+ * Handler for storing security labels as extended attributes.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/smp_lock.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/ext4_fs.h>
+#include <linux/security.h>
+#include "xattr.h"
+
+static size_t
+ext4_xattr_security_list(struct inode *inode, char *list, size_t list_size,
+ const char *name, size_t name_len)
+{
+ const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
+ const size_t total_len = prefix_len + name_len + 1;
+
+
+ if (list && total_len <= list_size) {
+ memcpy(list, XATTR_SECURITY_PREFIX, prefix_len);
+ memcpy(list+prefix_len, name, name_len);
+ list[prefix_len + name_len] = '\0';
+ }
+ return total_len;
+}
+
+static int
+ext4_xattr_security_get(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+ return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY, name,
+ buffer, size);
+}
+
+static int
+ext4_xattr_security_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+ return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY, name,
+ value, size, flags);
+}
+
+int
+ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir)
+{
+ int err;
+ size_t len;
+ void *value;
+ char *name;
+
+ err = security_inode_init_security(inode, dir, &name, &value, &len);
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ return 0;
+ return err;
+ }
+ err = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_SECURITY,
+ name, value, len, 0);
+ kfree(name);
+ kfree(value);
+ return err;
+}
+
+struct xattr_handler ext4_xattr_security_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .list = ext4_xattr_security_list,
+ .get = ext4_xattr_security_get,
+ .set = ext4_xattr_security_set,
+};
--- /dev/null
+/*
+ * linux/fs/ext4/xattr_trusted.c
+ * Handler for trusted extended attributes.
+ *
+ * Copyright (C) 2003 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/capability.h>
+#include <linux/fs.h>
+#include <linux/smp_lock.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/ext4_fs.h>
+#include "xattr.h"
+
+#define XATTR_TRUSTED_PREFIX "trusted."
+
+static size_t
+ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
+ const char *name, size_t name_len)
+{
+ const size_t prefix_len = sizeof(XATTR_TRUSTED_PREFIX)-1;
+ const size_t total_len = prefix_len + name_len + 1;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return 0;
+
+ if (list && total_len <= list_size) {
+ memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
+ memcpy(list+prefix_len, name, name_len);
+ list[prefix_len + name_len] = '\0';
+ }
+ return total_len;
+}
+
+static int
+ext4_xattr_trusted_get(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+ return ext4_xattr_get(inode, EXT4_XATTR_INDEX_TRUSTED, name,
+ buffer, size);
+}
+
+static int
+ext4_xattr_trusted_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+ return ext4_xattr_set(inode, EXT4_XATTR_INDEX_TRUSTED, name,
+ value, size, flags);
+}
+
+struct xattr_handler ext4_xattr_trusted_handler = {
+ .prefix = XATTR_TRUSTED_PREFIX,
+ .list = ext4_xattr_trusted_list,
+ .get = ext4_xattr_trusted_get,
+ .set = ext4_xattr_trusted_set,
+};
--- /dev/null
+/*
+ * linux/fs/ext4/xattr_user.c
+ * Handler for extended user attributes.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/smp_lock.h>
+#include <linux/ext4_jbd2.h>
+#include <linux/ext4_fs.h>
+#include "xattr.h"
+
+#define XATTR_USER_PREFIX "user."
+
+static size_t
+ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size,
+ const char *name, size_t name_len)
+{
+ const size_t prefix_len = sizeof(XATTR_USER_PREFIX)-1;
+ const size_t total_len = prefix_len + name_len + 1;
+
+ if (!test_opt(inode->i_sb, XATTR_USER))
+ return 0;
+
+ if (list && total_len <= list_size) {
+ memcpy(list, XATTR_USER_PREFIX, prefix_len);
+ memcpy(list+prefix_len, name, name_len);
+ list[prefix_len + name_len] = '\0';
+ }
+ return total_len;
+}
+
+static int
+ext4_xattr_user_get(struct inode *inode, const char *name,
+ void *buffer, size_t size)
+{
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+ if (!test_opt(inode->i_sb, XATTR_USER))
+ return -EOPNOTSUPP;
+ return ext4_xattr_get(inode, EXT4_XATTR_INDEX_USER, name, buffer, size);
+}
+
+static int
+ext4_xattr_user_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ if (strcmp(name, "") == 0)
+ return -EINVAL;
+ if (!test_opt(inode->i_sb, XATTR_USER))
+ return -EOPNOTSUPP;
+ return ext4_xattr_set(inode, EXT4_XATTR_INDEX_USER, name,
+ value, size, flags);
+}
+
+struct xattr_handler ext4_xattr_user_handler = {
+ .prefix = XATTR_USER_PREFIX,
+ .list = ext4_xattr_user_list,
+ .get = ext4_xattr_user_get,
+ .set = ext4_xattr_user_set,
+};
ret = writeback_inode(i1);
if (!ret && i2)
ret = writeback_inode(i2);
- if (!ret && sb) {
+ if (!ret) {
struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
ret = filemap_flush(mapping);
}
struct fuse_entry_out outarg;
struct fuse_conn *fc;
struct fuse_req *req;
+ struct dentry *parent;
/* Doesn't hurt to "reset" the validity timeout */
fuse_invalidate_entry_cache(entry);
if (IS_ERR(req))
return 0;
- fuse_lookup_init(req, entry->d_parent->d_inode, entry, &outarg);
+ parent = dget_parent(entry);
+ fuse_lookup_init(req, parent->d_inode, entry, &outarg);
request_send(fc, req);
+ dput(parent);
err = req->out.h.error;
/* Zero nodeid is same as -ENOENT */
if (!err && !outarg.nodeid)
fuse_send_forget(fc, req, outarg.nodeid, 1);
return 0;
}
+ spin_lock(&fc->lock);
fi->nlookup ++;
+ spin_unlock(&fc->lock);
}
fuse_put_request(fc, req);
if (err || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
return 1;
}
-/*
- * Check if there's already a hashed alias of this directory inode.
- * If yes, then lookup and mkdir must not create a new alias.
- */
-static int dir_alias(struct inode *inode)
-{
- if (S_ISDIR(inode->i_mode)) {
- struct dentry *alias = d_find_alias(inode);
- if (alias) {
- dput(alias);
- return 1;
- }
- }
- return 0;
-}
-
static int invalid_nodeid(u64 nodeid)
{
return !nodeid || nodeid == FUSE_ROOT_ID;
S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m);
}
+/*
+ * Add a directory inode to a dentry, ensuring that no other dentry
+ * refers to this inode. Called with fc->inst_mutex.
+ */
+static int fuse_d_add_directory(struct dentry *entry, struct inode *inode)
+{
+ struct dentry *alias = d_find_alias(inode);
+ if (alias) {
+ /* This tries to shrink the subtree below alias */
+ fuse_invalidate_entry(alias);
+ dput(alias);
+ if (!list_empty(&inode->i_dentry))
+ return -EBUSY;
+ }
+ d_add(entry, inode);
+ return 0;
+}
+
static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
struct nameidata *nd)
{
if (err && err != -ENOENT)
return ERR_PTR(err);
- if (inode && dir_alias(inode)) {
- iput(inode);
- return ERR_PTR(-EIO);
- }
- d_add(entry, inode);
+ if (inode && S_ISDIR(inode->i_mode)) {
+ mutex_lock(&fc->inst_mutex);
+ err = fuse_d_add_directory(entry, inode);
+ mutex_unlock(&fc->inst_mutex);
+ if (err) {
+ iput(inode);
+ return ERR_PTR(err);
+ }
+ } else
+ d_add(entry, inode);
+
entry->d_op = &fuse_dentry_operations;
if (!err)
fuse_change_timeout(entry, &outarg);
}
fuse_put_request(fc, req);
- if (dir_alias(inode)) {
- iput(inode);
- return -EIO;
- }
+ if (S_ISDIR(inode->i_mode)) {
+ struct dentry *alias;
+ mutex_lock(&fc->inst_mutex);
+ alias = d_find_alias(inode);
+ if (alias) {
+ /* New directory must have moved since mkdir */
+ mutex_unlock(&fc->inst_mutex);
+ dput(alias);
+ iput(inode);
+ return -EBUSY;
+ }
+ d_instantiate(entry, inode);
+ mutex_unlock(&fc->inst_mutex);
+ } else
+ d_instantiate(entry, inode);
- d_instantiate(entry, inode);
fuse_change_timeout(entry, &outarg);
fuse_invalidate_attr(dir);
return 0;
}
}
+static void fuse_vmtruncate(struct inode *inode, loff_t offset)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ int need_trunc;
+
+ spin_lock(&fc->lock);
+ need_trunc = inode->i_size > offset;
+ i_size_write(inode, offset);
+ spin_unlock(&fc->lock);
+
+ if (need_trunc) {
+ struct address_space *mapping = inode->i_mapping;
+ unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+ truncate_inode_pages(mapping, offset);
+ }
+}
+
/*
* Set attributes, and at the same time refresh them.
*
* Truncation is slightly complicated, because the 'truncate' request
* may fail, in which case we don't want to touch the mapping.
- * vmtruncate() doesn't allow for this case. So do the rlimit
- * checking by hand and call vmtruncate() only after the file has
- * actually been truncated.
+ * vmtruncate() doesn't allow for this case, so do the rlimit checking
+ * and the actual truncation by hand.
*/
static int fuse_setattr(struct dentry *entry, struct iattr *attr)
{
make_bad_inode(inode);
err = -EIO;
} else {
- if (is_truncate) {
- loff_t origsize = i_size_read(inode);
- i_size_write(inode, outarg.attr.size);
- if (origsize > outarg.attr.size)
- vmtruncate(inode, outarg.attr.size);
- }
+ if (is_truncate)
+ fuse_vmtruncate(inode, outarg.attr.size);
fuse_change_attributes(inode, &outarg.attr);
fi->i_time = time_to_jiffies(outarg.attr_valid,
outarg.attr_valid_nsec);
err = -EIO;
if (!err) {
pos += count;
- if (pos > i_size_read(inode))
+ spin_lock(&fc->lock);
+ if (pos > inode->i_size)
i_size_write(inode, pos);
+ spin_unlock(&fc->lock);
if (offset == 0 && to == PAGE_CACHE_SIZE) {
clear_page_dirty(page);
}
fuse_put_request(fc, req);
if (res > 0) {
- if (write && pos > i_size_read(inode))
- i_size_write(inode, pos);
+ if (write) {
+ spin_lock(&fc->lock);
+ if (pos > inode->i_size)
+ i_size_write(inode, pos);
+ spin_unlock(&fc->lock);
+ }
*ppos = pos;
}
fuse_invalidate_attr(inode);
/** Lock protecting accessess to members of this structure */
spinlock_t lock;
+ /** Mutex protecting against directory alias creation */
+ struct mutex inst_mutex;
+
/** Refcount */
atomic_t count;
void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr)
{
+ struct fuse_conn *fc = get_fuse_conn(inode);
if (S_ISREG(inode->i_mode) && i_size_read(inode) != attr->size)
invalidate_inode_pages(inode->i_mapping);
inode->i_nlink = attr->nlink;
inode->i_uid = attr->uid;
inode->i_gid = attr->gid;
+ spin_lock(&fc->lock);
i_size_write(inode, attr->size);
+ spin_unlock(&fc->lock);
inode->i_blocks = attr->blocks;
inode->i_atime.tv_sec = attr->atime;
inode->i_atime.tv_nsec = attr->atimensec;
static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
{
inode->i_mode = attr->mode & S_IFMT;
- i_size_write(inode, attr->size);
+ inode->i_size = attr->size;
if (S_ISREG(inode->i_mode)) {
fuse_init_common(inode);
fuse_init_file_inode(inode);
struct inode *inode;
struct fuse_inode *fi;
struct fuse_conn *fc = get_fuse_conn_super(sb);
- int retried = 0;
retry:
inode = iget5_locked(sb, nodeid, fuse_inode_eq, fuse_inode_set, &nodeid);
fuse_init_inode(inode, attr);
unlock_new_inode(inode);
} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
- BUG_ON(retried);
/* Inode has changed type, any I/O on the old should fail */
make_bad_inode(inode);
iput(inode);
- retried = 1;
goto retry;
}
fi = get_fuse_inode(inode);
+ spin_lock(&fc->lock);
fi->nlookup ++;
+ spin_unlock(&fc->lock);
fuse_change_attributes(inode, attr);
return inode;
}
fc = kzalloc(sizeof(*fc), GFP_KERNEL);
if (fc) {
spin_lock_init(&fc->lock);
+ mutex_init(&fc->inst_mutex);
atomic_set(&fc->count, 1);
init_waitqueue_head(&fc->waitq);
init_waitqueue_head(&fc->blocked_waitq);
void fuse_conn_put(struct fuse_conn *fc)
{
- if (atomic_dec_and_test(&fc->count))
+ if (atomic_dec_and_test(&fc->count)) {
+ mutex_destroy(&fc->inst_mutex);
kfree(fc);
+ }
}
struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
strncpy(buf, table_name, 256);
buf[255] = '\0';
- p = strstr(buf, ":");
+ p = strchr(buf, ':');
if (!p) {
log_info("invalid table_name \"%s\"", table_name);
kfree(ls);
else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle)
log_write_header(sdp, 0, PULL);
lops_after_commit(sdp, ai);
- sdp->sd_log_head = sdp->sd_log_flush_head;
+ gfs2_log_lock(sdp);
+ sdp->sd_log_head = sdp->sd_log_flush_head;
sdp->sd_log_blks_free -= sdp->sd_log_num_hdrs;
-
sdp->sd_log_blks_reserved = 0;
sdp->sd_log_commited_buf = 0;
sdp->sd_log_num_hdrs = 0;
sdp->sd_log_commited_revoke = 0;
- gfs2_log_lock(sdp);
if (!list_empty(&ai->ai_ail1_list)) {
list_add(&ai->ai_list, &sdp->sd_ail1_list);
ai = NULL;
ptr = kaddr + bh_offset(bh);
if (*ptr == cpu_to_be32(GFS2_MAGIC))
rv = 1;
- kunmap_atomic(page, KM_USER0);
+ kunmap_atomic(kaddr, KM_USER0);
return rv;
}
memcpy(bh->b_data,
kaddr + bh_offset(bd2->bd_bh),
sdp->sd_sb.sb_bsize);
- kunmap_atomic(page, KM_USER0);
+ kunmap_atomic(kaddr, KM_USER0);
*(__be32 *)bh->b_data = 0;
} else {
bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
kaddr = kmap_atomic(page, KM_USER0);
memset(kaddr, 0, PAGE_CACHE_SIZE);
- kunmap_atomic(page, KM_USER0);
+ kunmap_atomic(kaddr, KM_USER0);
SetPageUptodate(page);
memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
ip->i_di.di_size);
memset(kaddr + ip->i_di.di_size, 0, PAGE_CACHE_SIZE - ip->i_di.di_size);
- kunmap_atomic(page, KM_USER0);
+ kunmap_atomic(kaddr, KM_USER0);
brelse(dibh);
loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + from;
loff_t end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
struct gfs2_alloc *al;
+ unsigned int write_len = to - from;
+
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME|GL_AOP, &ip->i_gh);
error = gfs2_glock_nq_m_atime(1, &ip->i_gh);
if (error)
goto out_uninit;
- gfs2_write_calc_reserv(ip, to - from, &data_blocks, &ind_blocks);
+ gfs2_write_calc_reserv(ip, write_len, &data_blocks, &ind_blocks);
- error = gfs2_write_alloc_required(ip, pos, from - to, &alloc_required);
+ error = gfs2_write_alloc_required(ip, pos, write_len, &alloc_required);
if (error)
goto out_unlock;
+ ip->i_alloc.al_requested = 0;
if (alloc_required) {
al = gfs2_alloc_get(ip);
kaddr = kmap_atomic(page, KM_USER0);
memcpy(dibh->b_data + sizeof(struct gfs2_dinode) + from,
kaddr + from, to - from);
- kunmap_atomic(page, KM_USER0);
+ kunmap_atomic(kaddr, KM_USER0);
SetPageUptodate(page);
struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
static inline void gfs2_alloc_put(struct gfs2_inode *ip)
{
- return; /* Se we can see where ip->i_alloc is used */
+ return; /* So we can see where ip->i_alloc is used */
}
int gfs2_inplace_reserve_i(struct gfs2_inode *ip,
if (h_vm_pgoff >= h_pgoff)
v_offset = 0;
- unmap_hugepage_range(vma,
+ __unmap_hugepage_range(vma,
vma->vm_start + v_offset, vma->vm_end);
}
}
unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
- if (!ioprio_valid(aprio))
- return bprio;
- if (!ioprio_valid(bprio))
- return aprio;
-
if (aclass == IOPRIO_CLASS_NONE)
aclass = IOPRIO_CLASS_BE;
if (bclass == IOPRIO_CLASS_NONE)
__FUNCTION__);
kfree(journal);
journal = NULL;
+ goto out;
}
journal->j_dev = bdev;
journal->j_fs_dev = fs_dev;
J_ASSERT(bh != NULL);
journal->j_sb_buffer = bh;
journal->j_superblock = (journal_superblock_t *)bh->b_data;
-
+out:
return journal;
}
--- /dev/null
+#
+# Makefile for the linux journaling routines.
+#
+
+obj-$(CONFIG_JBD2) += jbd2.o
+
+jbd2-objs := transaction.o commit.o recovery.o checkpoint.o revoke.o journal.o
--- /dev/null
+/*
+ * linux/fs/checkpoint.c
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
+ *
+ * Copyright 1999 Red Hat Software --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Checkpoint routines for the generic filesystem journaling code.
+ * Part of the ext2fs journaling system.
+ *
+ * Checkpointing is the process of ensuring that a section of the log is
+ * committed fully to disk, so that that portion of the log can be
+ * reused.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+/*
+ * Unlink a buffer from a transaction checkpoint list.
+ *
+ * Called with j_list_lock held.
+ */
+static inline void __buffer_unlink_first(struct journal_head *jh)
+{
+ transaction_t *transaction = jh->b_cp_transaction;
+
+ jh->b_cpnext->b_cpprev = jh->b_cpprev;
+ jh->b_cpprev->b_cpnext = jh->b_cpnext;
+ if (transaction->t_checkpoint_list == jh) {
+ transaction->t_checkpoint_list = jh->b_cpnext;
+ if (transaction->t_checkpoint_list == jh)
+ transaction->t_checkpoint_list = NULL;
+ }
+}
+
+/*
+ * Unlink a buffer from a transaction checkpoint(io) list.
+ *
+ * Called with j_list_lock held.
+ */
+static inline void __buffer_unlink(struct journal_head *jh)
+{
+ transaction_t *transaction = jh->b_cp_transaction;
+
+ __buffer_unlink_first(jh);
+ if (transaction->t_checkpoint_io_list == jh) {
+ transaction->t_checkpoint_io_list = jh->b_cpnext;
+ if (transaction->t_checkpoint_io_list == jh)
+ transaction->t_checkpoint_io_list = NULL;
+ }
+}
+
+/*
+ * Move a buffer from the checkpoint list to the checkpoint io list
+ *
+ * Called with j_list_lock held
+ */
+static inline void __buffer_relink_io(struct journal_head *jh)
+{
+ transaction_t *transaction = jh->b_cp_transaction;
+
+ __buffer_unlink_first(jh);
+
+ if (!transaction->t_checkpoint_io_list) {
+ jh->b_cpnext = jh->b_cpprev = jh;
+ } else {
+ jh->b_cpnext = transaction->t_checkpoint_io_list;
+ jh->b_cpprev = transaction->t_checkpoint_io_list->b_cpprev;
+ jh->b_cpprev->b_cpnext = jh;
+ jh->b_cpnext->b_cpprev = jh;
+ }
+ transaction->t_checkpoint_io_list = jh;
+}
+
+/*
+ * Try to release a checkpointed buffer from its transaction.
+ * Returns 1 if we released it and 2 if we also released the
+ * whole transaction.
+ *
+ * Requires j_list_lock
+ * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
+ */
+static int __try_to_free_cp_buf(struct journal_head *jh)
+{
+ int ret = 0;
+ struct buffer_head *bh = jh2bh(jh);
+
+ if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) {
+ JBUFFER_TRACE(jh, "remove from checkpoint list");
+ ret = __jbd2_journal_remove_checkpoint(jh) + 1;
+ jbd_unlock_bh_state(bh);
+ jbd2_journal_remove_journal_head(bh);
+ BUFFER_TRACE(bh, "release");
+ __brelse(bh);
+ } else {
+ jbd_unlock_bh_state(bh);
+ }
+ return ret;
+}
+
+/*
+ * __jbd2_log_wait_for_space: wait until there is space in the journal.
+ *
+ * Called under j-state_lock *only*. It will be unlocked if we have to wait
+ * for a checkpoint to free up some space in the log.
+ */
+void __jbd2_log_wait_for_space(journal_t *journal)
+{
+ int nblocks;
+ assert_spin_locked(&journal->j_state_lock);
+
+ nblocks = jbd_space_needed(journal);
+ while (__jbd2_log_space_left(journal) < nblocks) {
+ if (journal->j_flags & JBD2_ABORT)
+ return;
+ spin_unlock(&journal->j_state_lock);
+ mutex_lock(&journal->j_checkpoint_mutex);
+
+ /*
+ * Test again, another process may have checkpointed while we
+ * were waiting for the checkpoint lock
+ */
+ spin_lock(&journal->j_state_lock);
+ nblocks = jbd_space_needed(journal);
+ if (__jbd2_log_space_left(journal) < nblocks) {
+ spin_unlock(&journal->j_state_lock);
+ jbd2_log_do_checkpoint(journal);
+ spin_lock(&journal->j_state_lock);
+ }
+ mutex_unlock(&journal->j_checkpoint_mutex);
+ }
+}
+
+/*
+ * We were unable to perform jbd_trylock_bh_state() inside j_list_lock.
+ * The caller must restart a list walk. Wait for someone else to run
+ * jbd_unlock_bh_state().
+ */
+static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
+ __releases(journal->j_list_lock)
+{
+ get_bh(bh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_lock_bh_state(bh);
+ jbd_unlock_bh_state(bh);
+ put_bh(bh);
+}
+
+/*
+ * Clean up transaction's list of buffers submitted for io.
+ * We wait for any pending IO to complete and remove any clean
+ * buffers. Note that we take the buffers in the opposite ordering
+ * from the one in which they were submitted for IO.
+ *
+ * Called with j_list_lock held.
+ */
+static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
+{
+ struct journal_head *jh;
+ struct buffer_head *bh;
+ tid_t this_tid;
+ int released = 0;
+
+ this_tid = transaction->t_tid;
+restart:
+ /* Did somebody clean up the transaction in the meanwhile? */
+ if (journal->j_checkpoint_transactions != transaction ||
+ transaction->t_tid != this_tid)
+ return;
+ while (!released && transaction->t_checkpoint_io_list) {
+ jh = transaction->t_checkpoint_io_list;
+ bh = jh2bh(jh);
+ if (!jbd_trylock_bh_state(bh)) {
+ jbd_sync_bh(journal, bh);
+ spin_lock(&journal->j_list_lock);
+ goto restart;
+ }
+ if (buffer_locked(bh)) {
+ atomic_inc(&bh->b_count);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ wait_on_buffer(bh);
+ /* the journal_head may have gone by now */
+ BUFFER_TRACE(bh, "brelse");
+ __brelse(bh);
+ spin_lock(&journal->j_list_lock);
+ goto restart;
+ }
+ /*
+ * Now in whatever state the buffer currently is, we know that
+ * it has been written out and so we can drop it from the list
+ */
+ released = __jbd2_journal_remove_checkpoint(jh);
+ jbd_unlock_bh_state(bh);
+ jbd2_journal_remove_journal_head(bh);
+ __brelse(bh);
+ }
+}
+
+#define NR_BATCH 64
+
+static void
+__flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
+{
+ int i;
+
+ ll_rw_block(SWRITE, *batch_count, bhs);
+ for (i = 0; i < *batch_count; i++) {
+ struct buffer_head *bh = bhs[i];
+ clear_buffer_jwrite(bh);
+ BUFFER_TRACE(bh, "brelse");
+ __brelse(bh);
+ }
+ *batch_count = 0;
+}
+
+/*
+ * Try to flush one buffer from the checkpoint list to disk.
+ *
+ * Return 1 if something happened which requires us to abort the current
+ * scan of the checkpoint list.
+ *
+ * Called with j_list_lock held and drops it if 1 is returned
+ * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
+ */
+static int __process_buffer(journal_t *journal, struct journal_head *jh,
+ struct buffer_head **bhs, int *batch_count)
+{
+ struct buffer_head *bh = jh2bh(jh);
+ int ret = 0;
+
+ if (buffer_locked(bh)) {
+ atomic_inc(&bh->b_count);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ wait_on_buffer(bh);
+ /* the journal_head may have gone by now */
+ BUFFER_TRACE(bh, "brelse");
+ __brelse(bh);
+ ret = 1;
+ } else if (jh->b_transaction != NULL) {
+ transaction_t *t = jh->b_transaction;
+ tid_t tid = t->t_tid;
+
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ jbd2_log_start_commit(journal, tid);
+ jbd2_log_wait_commit(journal, tid);
+ ret = 1;
+ } else if (!buffer_dirty(bh)) {
+ J_ASSERT_JH(jh, !buffer_jbddirty(bh));
+ BUFFER_TRACE(bh, "remove from checkpoint");
+ __jbd2_journal_remove_checkpoint(jh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ jbd2_journal_remove_journal_head(bh);
+ __brelse(bh);
+ ret = 1;
+ } else {
+ /*
+ * Important: we are about to write the buffer, and
+ * possibly block, while still holding the journal lock.
+ * We cannot afford to let the transaction logic start
+ * messing around with this buffer before we write it to
+ * disk, as that would break recoverability.
+ */
+ BUFFER_TRACE(bh, "queue");
+ get_bh(bh);
+ J_ASSERT_BH(bh, !buffer_jwrite(bh));
+ set_buffer_jwrite(bh);
+ bhs[*batch_count] = bh;
+ __buffer_relink_io(jh);
+ jbd_unlock_bh_state(bh);
+ (*batch_count)++;
+ if (*batch_count == NR_BATCH) {
+ spin_unlock(&journal->j_list_lock);
+ __flush_batch(journal, bhs, batch_count);
+ ret = 1;
+ }
+ }
+ return ret;
+}
+
+/*
+ * Perform an actual checkpoint. We take the first transaction on the
+ * list of transactions to be checkpointed and send all its buffers
+ * to disk. We submit larger chunks of data at once.
+ *
+ * The journal should be locked before calling this function.
+ */
+int jbd2_log_do_checkpoint(journal_t *journal)
+{
+ transaction_t *transaction;
+ tid_t this_tid;
+ int result;
+
+ jbd_debug(1, "Start checkpoint\n");
+
+ /*
+ * First thing: if there are any transactions in the log which
+ * don't need checkpointing, just eliminate them from the
+ * journal straight away.
+ */
+ result = jbd2_cleanup_journal_tail(journal);
+ jbd_debug(1, "cleanup_journal_tail returned %d\n", result);
+ if (result <= 0)
+ return result;
+
+ /*
+ * OK, we need to start writing disk blocks. Take one transaction
+ * and write it.
+ */
+ spin_lock(&journal->j_list_lock);
+ if (!journal->j_checkpoint_transactions)
+ goto out;
+ transaction = journal->j_checkpoint_transactions;
+ this_tid = transaction->t_tid;
+restart:
+ /*
+ * If someone cleaned up this transaction while we slept, we're
+ * done (maybe it's a new transaction, but it fell at the same
+ * address).
+ */
+ if (journal->j_checkpoint_transactions == transaction &&
+ transaction->t_tid == this_tid) {
+ int batch_count = 0;
+ struct buffer_head *bhs[NR_BATCH];
+ struct journal_head *jh;
+ int retry = 0;
+
+ while (!retry && transaction->t_checkpoint_list) {
+ struct buffer_head *bh;
+
+ jh = transaction->t_checkpoint_list;
+ bh = jh2bh(jh);
+ if (!jbd_trylock_bh_state(bh)) {
+ jbd_sync_bh(journal, bh);
+ retry = 1;
+ break;
+ }
+ retry = __process_buffer(journal, jh, bhs,&batch_count);
+ if (!retry && lock_need_resched(&journal->j_list_lock)){
+ spin_unlock(&journal->j_list_lock);
+ retry = 1;
+ break;
+ }
+ }
+
+ if (batch_count) {
+ if (!retry) {
+ spin_unlock(&journal->j_list_lock);
+ retry = 1;
+ }
+ __flush_batch(journal, bhs, &batch_count);
+ }
+
+ if (retry) {
+ spin_lock(&journal->j_list_lock);
+ goto restart;
+ }
+ /*
+ * Now we have cleaned up the first transaction's checkpoint
+ * list. Let's clean up the second one
+ */
+ __wait_cp_io(journal, transaction);
+ }
+out:
+ spin_unlock(&journal->j_list_lock);
+ result = jbd2_cleanup_journal_tail(journal);
+ if (result < 0)
+ return result;
+ return 0;
+}
+
+/*
+ * Check the list of checkpoint transactions for the journal to see if
+ * we have already got rid of any since the last update of the log tail
+ * in the journal superblock. If so, we can instantly roll the
+ * superblock forward to remove those transactions from the log.
+ *
+ * Return <0 on error, 0 on success, 1 if there was nothing to clean up.
+ *
+ * Called with the journal lock held.
+ *
+ * This is the only part of the journaling code which really needs to be
+ * aware of transaction aborts. Checkpointing involves writing to the
+ * main filesystem area rather than to the journal, so it can proceed
+ * even in abort state, but we must not update the journal superblock if
+ * we have an abort error outstanding.
+ */
+
+int jbd2_cleanup_journal_tail(journal_t *journal)
+{
+ transaction_t * transaction;
+ tid_t first_tid;
+ unsigned long blocknr, freed;
+
+ /* OK, work out the oldest transaction remaining in the log, and
+ * the log block it starts at.
+ *
+ * If the log is now empty, we need to work out which is the
+ * next transaction ID we will write, and where it will
+ * start. */
+
+ spin_lock(&journal->j_state_lock);
+ spin_lock(&journal->j_list_lock);
+ transaction = journal->j_checkpoint_transactions;
+ if (transaction) {
+ first_tid = transaction->t_tid;
+ blocknr = transaction->t_log_start;
+ } else if ((transaction = journal->j_committing_transaction) != NULL) {
+ first_tid = transaction->t_tid;
+ blocknr = transaction->t_log_start;
+ } else if ((transaction = journal->j_running_transaction) != NULL) {
+ first_tid = transaction->t_tid;
+ blocknr = journal->j_head;
+ } else {
+ first_tid = journal->j_transaction_sequence;
+ blocknr = journal->j_head;
+ }
+ spin_unlock(&journal->j_list_lock);
+ J_ASSERT(blocknr != 0);
+
+ /* If the oldest pinned transaction is at the tail of the log
+ already then there's not much we can do right now. */
+ if (journal->j_tail_sequence == first_tid) {
+ spin_unlock(&journal->j_state_lock);
+ return 1;
+ }
+
+ /* OK, update the superblock to recover the freed space.
+ * Physical blocks come first: have we wrapped beyond the end of
+ * the log? */
+ freed = blocknr - journal->j_tail;
+ if (blocknr < journal->j_tail)
+ freed = freed + journal->j_last - journal->j_first;
+
+ jbd_debug(1,
+ "Cleaning journal tail from %d to %d (offset %lu), "
+ "freeing %lu\n",
+ journal->j_tail_sequence, first_tid, blocknr, freed);
+
+ journal->j_free += freed;
+ journal->j_tail_sequence = first_tid;
+ journal->j_tail = blocknr;
+ spin_unlock(&journal->j_state_lock);
+ if (!(journal->j_flags & JBD2_ABORT))
+ jbd2_journal_update_superblock(journal, 1);
+ return 0;
+}
+
+
+/* Checkpoint list management */
+
+/*
+ * journal_clean_one_cp_list
+ *
+ * Find all the written-back checkpoint buffers in the given list and release them.
+ *
+ * Called with the journal locked.
+ * Called with j_list_lock held.
+ * Returns number of bufers reaped (for debug)
+ */
+
+static int journal_clean_one_cp_list(struct journal_head *jh, int *released)
+{
+ struct journal_head *last_jh;
+ struct journal_head *next_jh = jh;
+ int ret, freed = 0;
+
+ *released = 0;
+ if (!jh)
+ return 0;
+
+ last_jh = jh->b_cpprev;
+ do {
+ jh = next_jh;
+ next_jh = jh->b_cpnext;
+ /* Use trylock because of the ranking */
+ if (jbd_trylock_bh_state(jh2bh(jh))) {
+ ret = __try_to_free_cp_buf(jh);
+ if (ret) {
+ freed++;
+ if (ret == 2) {
+ *released = 1;
+ return freed;
+ }
+ }
+ }
+ /*
+ * This function only frees up some memory
+ * if possible so we dont have an obligation
+ * to finish processing. Bail out if preemption
+ * requested:
+ */
+ if (need_resched())
+ return freed;
+ } while (jh != last_jh);
+
+ return freed;
+}
+
+/*
+ * journal_clean_checkpoint_list
+ *
+ * Find all the written-back checkpoint buffers in the journal and release them.
+ *
+ * Called with the journal locked.
+ * Called with j_list_lock held.
+ * Returns number of buffers reaped (for debug)
+ */
+
+int __jbd2_journal_clean_checkpoint_list(journal_t *journal)
+{
+ transaction_t *transaction, *last_transaction, *next_transaction;
+ int ret = 0;
+ int released;
+
+ transaction = journal->j_checkpoint_transactions;
+ if (!transaction)
+ goto out;
+
+ last_transaction = transaction->t_cpprev;
+ next_transaction = transaction;
+ do {
+ transaction = next_transaction;
+ next_transaction = transaction->t_cpnext;
+ ret += journal_clean_one_cp_list(transaction->
+ t_checkpoint_list, &released);
+ /*
+ * This function only frees up some memory if possible so we
+ * dont have an obligation to finish processing. Bail out if
+ * preemption requested:
+ */
+ if (need_resched())
+ goto out;
+ if (released)
+ continue;
+ /*
+ * It is essential that we are as careful as in the case of
+ * t_checkpoint_list with removing the buffer from the list as
+ * we can possibly see not yet submitted buffers on io_list
+ */
+ ret += journal_clean_one_cp_list(transaction->
+ t_checkpoint_io_list, &released);
+ if (need_resched())
+ goto out;
+ } while (transaction != last_transaction);
+out:
+ return ret;
+}
+
+/*
+ * journal_remove_checkpoint: called after a buffer has been committed
+ * to disk (either by being write-back flushed to disk, or being
+ * committed to the log).
+ *
+ * We cannot safely clean a transaction out of the log until all of the
+ * buffer updates committed in that transaction have safely been stored
+ * elsewhere on disk. To achieve this, all of the buffers in a
+ * transaction need to be maintained on the transaction's checkpoint
+ * lists until they have been rewritten, at which point this function is
+ * called to remove the buffer from the existing transaction's
+ * checkpoint lists.
+ *
+ * The function returns 1 if it frees the transaction, 0 otherwise.
+ *
+ * This function is called with the journal locked.
+ * This function is called with j_list_lock held.
+ * This function is called with jbd_lock_bh_state(jh2bh(jh))
+ */
+
+int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
+{
+ transaction_t *transaction;
+ journal_t *journal;
+ int ret = 0;
+
+ JBUFFER_TRACE(jh, "entry");
+
+ if ((transaction = jh->b_cp_transaction) == NULL) {
+ JBUFFER_TRACE(jh, "not on transaction");
+ goto out;
+ }
+ journal = transaction->t_journal;
+
+ __buffer_unlink(jh);
+ jh->b_cp_transaction = NULL;
+
+ if (transaction->t_checkpoint_list != NULL ||
+ transaction->t_checkpoint_io_list != NULL)
+ goto out;
+ JBUFFER_TRACE(jh, "transaction has no more buffers");
+
+ /*
+ * There is one special case to worry about: if we have just pulled the
+ * buffer off a committing transaction's forget list, then even if the
+ * checkpoint list is empty, the transaction obviously cannot be
+ * dropped!
+ *
+ * The locking here around j_committing_transaction is a bit sleazy.
+ * See the comment at the end of jbd2_journal_commit_transaction().
+ */
+ if (transaction == journal->j_committing_transaction) {
+ JBUFFER_TRACE(jh, "belongs to committing transaction");
+ goto out;
+ }
+
+ /* OK, that was the last buffer for the transaction: we can now
+ safely remove this transaction from the log */
+
+ __jbd2_journal_drop_transaction(journal, transaction);
+
+ /* Just in case anybody was waiting for more transactions to be
+ checkpointed... */
+ wake_up(&journal->j_wait_logspace);
+ ret = 1;
+out:
+ JBUFFER_TRACE(jh, "exit");
+ return ret;
+}
+
+/*
+ * journal_insert_checkpoint: put a committed buffer onto a checkpoint
+ * list so that we know when it is safe to clean the transaction out of
+ * the log.
+ *
+ * Called with the journal locked.
+ * Called with j_list_lock held.
+ */
+void __jbd2_journal_insert_checkpoint(struct journal_head *jh,
+ transaction_t *transaction)
+{
+ JBUFFER_TRACE(jh, "entry");
+ J_ASSERT_JH(jh, buffer_dirty(jh2bh(jh)) || buffer_jbddirty(jh2bh(jh)));
+ J_ASSERT_JH(jh, jh->b_cp_transaction == NULL);
+
+ jh->b_cp_transaction = transaction;
+
+ if (!transaction->t_checkpoint_list) {
+ jh->b_cpnext = jh->b_cpprev = jh;
+ } else {
+ jh->b_cpnext = transaction->t_checkpoint_list;
+ jh->b_cpprev = transaction->t_checkpoint_list->b_cpprev;
+ jh->b_cpprev->b_cpnext = jh;
+ jh->b_cpnext->b_cpprev = jh;
+ }
+ transaction->t_checkpoint_list = jh;
+}
+
+/*
+ * We've finished with this transaction structure: adios...
+ *
+ * The transaction must have no links except for the checkpoint by this
+ * point.
+ *
+ * Called with the journal locked.
+ * Called with j_list_lock held.
+ */
+
+void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transaction)
+{
+ assert_spin_locked(&journal->j_list_lock);
+ if (transaction->t_cpnext) {
+ transaction->t_cpnext->t_cpprev = transaction->t_cpprev;
+ transaction->t_cpprev->t_cpnext = transaction->t_cpnext;
+ if (journal->j_checkpoint_transactions == transaction)
+ journal->j_checkpoint_transactions =
+ transaction->t_cpnext;
+ if (journal->j_checkpoint_transactions == transaction)
+ journal->j_checkpoint_transactions = NULL;
+ }
+
+ J_ASSERT(transaction->t_state == T_FINISHED);
+ J_ASSERT(transaction->t_buffers == NULL);
+ J_ASSERT(transaction->t_sync_datalist == NULL);
+ J_ASSERT(transaction->t_forget == NULL);
+ J_ASSERT(transaction->t_iobuf_list == NULL);
+ J_ASSERT(transaction->t_shadow_list == NULL);
+ J_ASSERT(transaction->t_log_list == NULL);
+ J_ASSERT(transaction->t_checkpoint_list == NULL);
+ J_ASSERT(transaction->t_checkpoint_io_list == NULL);
+ J_ASSERT(transaction->t_updates == 0);
+ J_ASSERT(journal->j_committing_transaction != transaction);
+ J_ASSERT(journal->j_running_transaction != transaction);
+
+ jbd_debug(1, "Dropping transaction %d, all done\n", transaction->t_tid);
+ kfree(transaction);
+}
--- /dev/null
+/*
+ * linux/fs/jbd2/commit.c
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
+ *
+ * Copyright 1998 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Journal commit routines for the generic filesystem journaling code;
+ * part of the ext2fs journaling system.
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/smp_lock.h>
+
+/*
+ * Default IO end handler for temporary BJ_IO buffer_heads.
+ */
+static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
+{
+ BUFFER_TRACE(bh, "");
+ if (uptodate)
+ set_buffer_uptodate(bh);
+ else
+ clear_buffer_uptodate(bh);
+ unlock_buffer(bh);
+}
+
+/*
+ * When an ext3-ordered file is truncated, it is possible that many pages are
+ * not sucessfully freed, because they are attached to a committing transaction.
+ * After the transaction commits, these pages are left on the LRU, with no
+ * ->mapping, and with attached buffers. These pages are trivially reclaimable
+ * by the VM, but their apparent absence upsets the VM accounting, and it makes
+ * the numbers in /proc/meminfo look odd.
+ *
+ * So here, we have a buffer which has just come off the forget list. Look to
+ * see if we can strip all buffers from the backing page.
+ *
+ * Called under lock_journal(), and possibly under journal_datalist_lock. The
+ * caller provided us with a ref against the buffer, and we drop that here.
+ */
+static void release_buffer_page(struct buffer_head *bh)
+{
+ struct page *page;
+
+ if (buffer_dirty(bh))
+ goto nope;
+ if (atomic_read(&bh->b_count) != 1)
+ goto nope;
+ page = bh->b_page;
+ if (!page)
+ goto nope;
+ if (page->mapping)
+ goto nope;
+
+ /* OK, it's a truncated page */
+ if (TestSetPageLocked(page))
+ goto nope;
+
+ page_cache_get(page);
+ __brelse(bh);
+ try_to_free_buffers(page);
+ unlock_page(page);
+ page_cache_release(page);
+ return;
+
+nope:
+ __brelse(bh);
+}
+
+/*
+ * Try to acquire jbd_lock_bh_state() against the buffer, when j_list_lock is
+ * held. For ranking reasons we must trylock. If we lose, schedule away and
+ * return 0. j_list_lock is dropped in this case.
+ */
+static int inverted_lock(journal_t *journal, struct buffer_head *bh)
+{
+ if (!jbd_trylock_bh_state(bh)) {
+ spin_unlock(&journal->j_list_lock);
+ schedule();
+ return 0;
+ }
+ return 1;
+}
+
+/* Done it all: now write the commit record. We should have
+ * cleaned up our previous buffers by now, so if we are in abort
+ * mode we can now just skip the rest of the journal write
+ * entirely.
+ *
+ * Returns 1 if the journal needs to be aborted or 0 on success
+ */
+static int journal_write_commit_record(journal_t *journal,
+ transaction_t *commit_transaction)
+{
+ struct journal_head *descriptor;
+ struct buffer_head *bh;
+ int i, ret;
+ int barrier_done = 0;
+
+ if (is_journal_aborted(journal))
+ return 0;
+
+ descriptor = jbd2_journal_get_descriptor_buffer(journal);
+ if (!descriptor)
+ return 1;
+
+ bh = jh2bh(descriptor);
+
+ /* AKPM: buglet - add `i' to tmp! */
+ for (i = 0; i < bh->b_size; i += 512) {
+ journal_header_t *tmp = (journal_header_t*)bh->b_data;
+ tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+ tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK);
+ tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid);
+ }
+
+ JBUFFER_TRACE(descriptor, "write commit block");
+ set_buffer_dirty(bh);
+ if (journal->j_flags & JBD2_BARRIER) {
+ set_buffer_ordered(bh);
+ barrier_done = 1;
+ }
+ ret = sync_dirty_buffer(bh);
+ /* is it possible for another commit to fail at roughly
+ * the same time as this one? If so, we don't want to
+ * trust the barrier flag in the super, but instead want
+ * to remember if we sent a barrier request
+ */
+ if (ret == -EOPNOTSUPP && barrier_done) {
+ char b[BDEVNAME_SIZE];
+
+ printk(KERN_WARNING
+ "JBD: barrier-based sync failed on %s - "
+ "disabling barriers\n",
+ bdevname(journal->j_dev, b));
+ spin_lock(&journal->j_state_lock);
+ journal->j_flags &= ~JBD2_BARRIER;
+ spin_unlock(&journal->j_state_lock);
+
+ /* And try again, without the barrier */
+ clear_buffer_ordered(bh);
+ set_buffer_uptodate(bh);
+ set_buffer_dirty(bh);
+ ret = sync_dirty_buffer(bh);
+ }
+ put_bh(bh); /* One for getblk() */
+ jbd2_journal_put_journal_head(descriptor);
+
+ return (ret == -EIO);
+}
+
+static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
+{
+ int i;
+
+ for (i = 0; i < bufs; i++) {
+ wbuf[i]->b_end_io = end_buffer_write_sync;
+ /* We use-up our safety reference in submit_bh() */
+ submit_bh(WRITE, wbuf[i]);
+ }
+}
+
+/*
+ * Submit all the data buffers to disk
+ */
+static void journal_submit_data_buffers(journal_t *journal,
+ transaction_t *commit_transaction)
+{
+ struct journal_head *jh;
+ struct buffer_head *bh;
+ int locked;
+ int bufs = 0;
+ struct buffer_head **wbuf = journal->j_wbuf;
+
+ /*
+ * Whenever we unlock the journal and sleep, things can get added
+ * onto ->t_sync_datalist, so we have to keep looping back to
+ * write_out_data until we *know* that the list is empty.
+ *
+ * Cleanup any flushed data buffers from the data list. Even in
+ * abort mode, we want to flush this out as soon as possible.
+ */
+write_out_data:
+ cond_resched();
+ spin_lock(&journal->j_list_lock);
+
+ while (commit_transaction->t_sync_datalist) {
+ jh = commit_transaction->t_sync_datalist;
+ bh = jh2bh(jh);
+ locked = 0;
+
+ /* Get reference just to make sure buffer does not disappear
+ * when we are forced to drop various locks */
+ get_bh(bh);
+ /* If the buffer is dirty, we need to submit IO and hence
+ * we need the buffer lock. We try to lock the buffer without
+ * blocking. If we fail, we need to drop j_list_lock and do
+ * blocking lock_buffer().
+ */
+ if (buffer_dirty(bh)) {
+ if (test_set_buffer_locked(bh)) {
+ BUFFER_TRACE(bh, "needs blocking lock");
+ spin_unlock(&journal->j_list_lock);
+ /* Write out all data to prevent deadlocks */
+ journal_do_submit_data(wbuf, bufs);
+ bufs = 0;
+ lock_buffer(bh);
+ spin_lock(&journal->j_list_lock);
+ }
+ locked = 1;
+ }
+ /* We have to get bh_state lock. Again out of order, sigh. */
+ if (!inverted_lock(journal, bh)) {
+ jbd_lock_bh_state(bh);
+ spin_lock(&journal->j_list_lock);
+ }
+ /* Someone already cleaned up the buffer? */
+ if (!buffer_jbd(bh)
+ || jh->b_transaction != commit_transaction
+ || jh->b_jlist != BJ_SyncData) {
+ jbd_unlock_bh_state(bh);
+ if (locked)
+ unlock_buffer(bh);
+ BUFFER_TRACE(bh, "already cleaned up");
+ put_bh(bh);
+ continue;
+ }
+ if (locked && test_clear_buffer_dirty(bh)) {
+ BUFFER_TRACE(bh, "needs writeout, adding to array");
+ wbuf[bufs++] = bh;
+ __jbd2_journal_file_buffer(jh, commit_transaction,
+ BJ_Locked);
+ jbd_unlock_bh_state(bh);
+ if (bufs == journal->j_wbufsize) {
+ spin_unlock(&journal->j_list_lock);
+ journal_do_submit_data(wbuf, bufs);
+ bufs = 0;
+ goto write_out_data;
+ }
+ }
+ else {
+ BUFFER_TRACE(bh, "writeout complete: unfile");
+ __jbd2_journal_unfile_buffer(jh);
+ jbd_unlock_bh_state(bh);
+ if (locked)
+ unlock_buffer(bh);
+ jbd2_journal_remove_journal_head(bh);
+ /* Once for our safety reference, once for
+ * jbd2_journal_remove_journal_head() */
+ put_bh(bh);
+ put_bh(bh);
+ }
+
+ if (lock_need_resched(&journal->j_list_lock)) {
+ spin_unlock(&journal->j_list_lock);
+ goto write_out_data;
+ }
+ }
+ spin_unlock(&journal->j_list_lock);
+ journal_do_submit_data(wbuf, bufs);
+}
+
+static inline void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+ unsigned long long block)
+{
+ tag->t_blocknr = cpu_to_be32(block & (u32)~0);
+ if (tag_bytes > JBD_TAG_SIZE32)
+ tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
+}
+
+/*
+ * jbd2_journal_commit_transaction
+ *
+ * The primary function for committing a transaction to the log. This
+ * function is called by the journal thread to begin a complete commit.
+ */
+void jbd2_journal_commit_transaction(journal_t *journal)
+{
+ transaction_t *commit_transaction;
+ struct journal_head *jh, *new_jh, *descriptor;
+ struct buffer_head **wbuf = journal->j_wbuf;
+ int bufs;
+ int flags;
+ int err;
+ unsigned long long blocknr;
+ char *tagp = NULL;
+ journal_header_t *header;
+ journal_block_tag_t *tag = NULL;
+ int space_left = 0;
+ int first_tag = 0;
+ int tag_flag;
+ int i;
+ int tag_bytes = journal_tag_bytes(journal);
+
+ /*
+ * First job: lock down the current transaction and wait for
+ * all outstanding updates to complete.
+ */
+
+#ifdef COMMIT_STATS
+ spin_lock(&journal->j_list_lock);
+ summarise_journal_usage(journal);
+ spin_unlock(&journal->j_list_lock);
+#endif
+
+ /* Do we need to erase the effects of a prior jbd2_journal_flush? */
+ if (journal->j_flags & JBD2_FLUSHED) {
+ jbd_debug(3, "super block updated\n");
+ jbd2_journal_update_superblock(journal, 1);
+ } else {
+ jbd_debug(3, "superblock not updated\n");
+ }
+
+ J_ASSERT(journal->j_running_transaction != NULL);
+ J_ASSERT(journal->j_committing_transaction == NULL);
+
+ commit_transaction = journal->j_running_transaction;
+ J_ASSERT(commit_transaction->t_state == T_RUNNING);
+
+ jbd_debug(1, "JBD: starting commit of transaction %d\n",
+ commit_transaction->t_tid);
+
+ spin_lock(&journal->j_state_lock);
+ commit_transaction->t_state = T_LOCKED;
+
+ spin_lock(&commit_transaction->t_handle_lock);
+ while (commit_transaction->t_updates) {
+ DEFINE_WAIT(wait);
+
+ prepare_to_wait(&journal->j_wait_updates, &wait,
+ TASK_UNINTERRUPTIBLE);
+ if (commit_transaction->t_updates) {
+ spin_unlock(&commit_transaction->t_handle_lock);
+ spin_unlock(&journal->j_state_lock);
+ schedule();
+ spin_lock(&journal->j_state_lock);
+ spin_lock(&commit_transaction->t_handle_lock);
+ }
+ finish_wait(&journal->j_wait_updates, &wait);
+ }
+ spin_unlock(&commit_transaction->t_handle_lock);
+
+ J_ASSERT (commit_transaction->t_outstanding_credits <=
+ journal->j_max_transaction_buffers);
+
+ /*
+ * First thing we are allowed to do is to discard any remaining
+ * BJ_Reserved buffers. Note, it is _not_ permissible to assume
+ * that there are no such buffers: if a large filesystem
+ * operation like a truncate needs to split itself over multiple
+ * transactions, then it may try to do a jbd2_journal_restart() while
+ * there are still BJ_Reserved buffers outstanding. These must
+ * be released cleanly from the current transaction.
+ *
+ * In this case, the filesystem must still reserve write access
+ * again before modifying the buffer in the new transaction, but
+ * we do not require it to remember exactly which old buffers it
+ * has reserved. This is consistent with the existing behaviour
+ * that multiple jbd2_journal_get_write_access() calls to the same
+ * buffer are perfectly permissable.
+ */
+ while (commit_transaction->t_reserved_list) {
+ jh = commit_transaction->t_reserved_list;
+ JBUFFER_TRACE(jh, "reserved, unused: refile");
+ /*
+ * A jbd2_journal_get_undo_access()+jbd2_journal_release_buffer() may
+ * leave undo-committed data.
+ */
+ if (jh->b_committed_data) {
+ struct buffer_head *bh = jh2bh(jh);
+
+ jbd_lock_bh_state(bh);
+ jbd2_slab_free(jh->b_committed_data, bh->b_size);
+ jh->b_committed_data = NULL;
+ jbd_unlock_bh_state(bh);
+ }
+ jbd2_journal_refile_buffer(journal, jh);
+ }
+
+ /*
+ * Now try to drop any written-back buffers from the journal's
+ * checkpoint lists. We do this *before* commit because it potentially
+ * frees some memory
+ */
+ spin_lock(&journal->j_list_lock);
+ __jbd2_journal_clean_checkpoint_list(journal);
+ spin_unlock(&journal->j_list_lock);
+
+ jbd_debug (3, "JBD: commit phase 1\n");
+
+ /*
+ * Switch to a new revoke table.
+ */
+ jbd2_journal_switch_revoke_table(journal);
+
+ commit_transaction->t_state = T_FLUSH;
+ journal->j_committing_transaction = commit_transaction;
+ journal->j_running_transaction = NULL;
+ commit_transaction->t_log_start = journal->j_head;
+ wake_up(&journal->j_wait_transaction_locked);
+ spin_unlock(&journal->j_state_lock);
+
+ jbd_debug (3, "JBD: commit phase 2\n");
+
+ /*
+ * First, drop modified flag: all accesses to the buffers
+ * will be tracked for a new trasaction only -bzzz
+ */
+ spin_lock(&journal->j_list_lock);
+ if (commit_transaction->t_buffers) {
+ new_jh = jh = commit_transaction->t_buffers->b_tnext;
+ do {
+ J_ASSERT_JH(new_jh, new_jh->b_modified == 1 ||
+ new_jh->b_modified == 0);
+ new_jh->b_modified = 0;
+ new_jh = new_jh->b_tnext;
+ } while (new_jh != jh);
+ }
+ spin_unlock(&journal->j_list_lock);
+
+ /*
+ * Now start flushing things to disk, in the order they appear
+ * on the transaction lists. Data blocks go first.
+ */
+ err = 0;
+ journal_submit_data_buffers(journal, commit_transaction);
+
+ /*
+ * Wait for all previously submitted IO to complete.
+ */
+ spin_lock(&journal->j_list_lock);
+ while (commit_transaction->t_locked_list) {
+ struct buffer_head *bh;
+
+ jh = commit_transaction->t_locked_list->b_tprev;
+ bh = jh2bh(jh);
+ get_bh(bh);
+ if (buffer_locked(bh)) {
+ spin_unlock(&journal->j_list_lock);
+ wait_on_buffer(bh);
+ if (unlikely(!buffer_uptodate(bh)))
+ err = -EIO;
+ spin_lock(&journal->j_list_lock);
+ }
+ if (!inverted_lock(journal, bh)) {
+ put_bh(bh);
+ spin_lock(&journal->j_list_lock);
+ continue;
+ }
+ if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
+ __jbd2_journal_unfile_buffer(jh);
+ jbd_unlock_bh_state(bh);
+ jbd2_journal_remove_journal_head(bh);
+ put_bh(bh);
+ } else {
+ jbd_unlock_bh_state(bh);
+ }
+ put_bh(bh);
+ cond_resched_lock(&journal->j_list_lock);
+ }
+ spin_unlock(&journal->j_list_lock);
+
+ if (err)
+ __jbd2_journal_abort_hard(journal);
+
+ jbd2_journal_write_revoke_records(journal, commit_transaction);
+
+ jbd_debug(3, "JBD: commit phase 2\n");
+
+ /*
+ * If we found any dirty or locked buffers, then we should have
+ * looped back up to the write_out_data label. If there weren't
+ * any then journal_clean_data_list should have wiped the list
+ * clean by now, so check that it is in fact empty.
+ */
+ J_ASSERT (commit_transaction->t_sync_datalist == NULL);
+
+ jbd_debug (3, "JBD: commit phase 3\n");
+
+ /*
+ * Way to go: we have now written out all of the data for a
+ * transaction! Now comes the tricky part: we need to write out
+ * metadata. Loop over the transaction's entire buffer list:
+ */
+ commit_transaction->t_state = T_COMMIT;
+
+ descriptor = NULL;
+ bufs = 0;
+ while (commit_transaction->t_buffers) {
+
+ /* Find the next buffer to be journaled... */
+
+ jh = commit_transaction->t_buffers;
+
+ /* If we're in abort mode, we just un-journal the buffer and
+ release it for background writing. */
+
+ if (is_journal_aborted(journal)) {
+ JBUFFER_TRACE(jh, "journal is aborting: refile");
+ jbd2_journal_refile_buffer(journal, jh);
+ /* If that was the last one, we need to clean up
+ * any descriptor buffers which may have been
+ * already allocated, even if we are now
+ * aborting. */
+ if (!commit_transaction->t_buffers)
+ goto start_journal_io;
+ continue;
+ }
+
+ /* Make sure we have a descriptor block in which to
+ record the metadata buffer. */
+
+ if (!descriptor) {
+ struct buffer_head *bh;
+
+ J_ASSERT (bufs == 0);
+
+ jbd_debug(4, "JBD: get descriptor\n");
+
+ descriptor = jbd2_journal_get_descriptor_buffer(journal);
+ if (!descriptor) {
+ __jbd2_journal_abort_hard(journal);
+ continue;
+ }
+
+ bh = jh2bh(descriptor);
+ jbd_debug(4, "JBD: got buffer %llu (%p)\n",
+ (unsigned long long)bh->b_blocknr, bh->b_data);
+ header = (journal_header_t *)&bh->b_data[0];
+ header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+ header->h_blocktype = cpu_to_be32(JBD2_DESCRIPTOR_BLOCK);
+ header->h_sequence = cpu_to_be32(commit_transaction->t_tid);
+
+ tagp = &bh->b_data[sizeof(journal_header_t)];
+ space_left = bh->b_size - sizeof(journal_header_t);
+ first_tag = 1;
+ set_buffer_jwrite(bh);
+ set_buffer_dirty(bh);
+ wbuf[bufs++] = bh;
+
+ /* Record it so that we can wait for IO
+ completion later */
+ BUFFER_TRACE(bh, "ph3: file as descriptor");
+ jbd2_journal_file_buffer(descriptor, commit_transaction,
+ BJ_LogCtl);
+ }
+
+ /* Where is the buffer to be written? */
+
+ err = jbd2_journal_next_log_block(journal, &blocknr);
+ /* If the block mapping failed, just abandon the buffer
+ and repeat this loop: we'll fall into the
+ refile-on-abort condition above. */
+ if (err) {
+ __jbd2_journal_abort_hard(journal);
+ continue;
+ }
+
+ /*
+ * start_this_handle() uses t_outstanding_credits to determine
+ * the free space in the log, but this counter is changed
+ * by jbd2_journal_next_log_block() also.
+ */
+ commit_transaction->t_outstanding_credits--;
+
+ /* Bump b_count to prevent truncate from stumbling over
+ the shadowed buffer! @@@ This can go if we ever get
+ rid of the BJ_IO/BJ_Shadow pairing of buffers. */
+ atomic_inc(&jh2bh(jh)->b_count);
+
+ /* Make a temporary IO buffer with which to write it out
+ (this will requeue both the metadata buffer and the
+ temporary IO buffer). new_bh goes on BJ_IO*/
+
+ set_bit(BH_JWrite, &jh2bh(jh)->b_state);
+ /*
+ * akpm: jbd2_journal_write_metadata_buffer() sets
+ * new_bh->b_transaction to commit_transaction.
+ * We need to clean this up before we release new_bh
+ * (which is of type BJ_IO)
+ */
+ JBUFFER_TRACE(jh, "ph3: write metadata");
+ flags = jbd2_journal_write_metadata_buffer(commit_transaction,
+ jh, &new_jh, blocknr);
+ set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
+ wbuf[bufs++] = jh2bh(new_jh);
+
+ /* Record the new block's tag in the current descriptor
+ buffer */
+
+ tag_flag = 0;
+ if (flags & 1)
+ tag_flag |= JBD2_FLAG_ESCAPE;
+ if (!first_tag)
+ tag_flag |= JBD2_FLAG_SAME_UUID;
+
+ tag = (journal_block_tag_t *) tagp;
+ write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
+ tag->t_flags = cpu_to_be32(tag_flag);
+ tagp += tag_bytes;
+ space_left -= tag_bytes;
+
+ if (first_tag) {
+ memcpy (tagp, journal->j_uuid, 16);
+ tagp += 16;
+ space_left -= 16;
+ first_tag = 0;
+ }
+
+ /* If there's no more to do, or if the descriptor is full,
+ let the IO rip! */
+
+ if (bufs == journal->j_wbufsize ||
+ commit_transaction->t_buffers == NULL ||
+ space_left < tag_bytes + 16) {
+
+ jbd_debug(4, "JBD: Submit %d IOs\n", bufs);
+
+ /* Write an end-of-descriptor marker before
+ submitting the IOs. "tag" still points to
+ the last tag we set up. */
+
+ tag->t_flags |= cpu_to_be32(JBD2_FLAG_LAST_TAG);
+
+start_journal_io:
+ for (i = 0; i < bufs; i++) {
+ struct buffer_head *bh = wbuf[i];
+ lock_buffer(bh);
+ clear_buffer_dirty(bh);
+ set_buffer_uptodate(bh);
+ bh->b_end_io = journal_end_buffer_io_sync;
+ submit_bh(WRITE, bh);
+ }
+ cond_resched();
+
+ /* Force a new descriptor to be generated next
+ time round the loop. */
+ descriptor = NULL;
+ bufs = 0;
+ }
+ }
+
+ /* Lo and behold: we have just managed to send a transaction to
+ the log. Before we can commit it, wait for the IO so far to
+ complete. Control buffers being written are on the
+ transaction's t_log_list queue, and metadata buffers are on
+ the t_iobuf_list queue.
+
+ Wait for the buffers in reverse order. That way we are
+ less likely to be woken up until all IOs have completed, and
+ so we incur less scheduling load.
+ */
+
+ jbd_debug(3, "JBD: commit phase 4\n");
+
+ /*
+ * akpm: these are BJ_IO, and j_list_lock is not needed.
+ * See __journal_try_to_free_buffer.
+ */
+wait_for_iobuf:
+ while (commit_transaction->t_iobuf_list != NULL) {
+ struct buffer_head *bh;
+
+ jh = commit_transaction->t_iobuf_list->b_tprev;
+ bh = jh2bh(jh);
+ if (buffer_locked(bh)) {
+ wait_on_buffer(bh);
+ goto wait_for_iobuf;
+ }
+ if (cond_resched())
+ goto wait_for_iobuf;
+
+ if (unlikely(!buffer_uptodate(bh)))
+ err = -EIO;
+
+ clear_buffer_jwrite(bh);
+
+ JBUFFER_TRACE(jh, "ph4: unfile after journal write");
+ jbd2_journal_unfile_buffer(journal, jh);
+
+ /*
+ * ->t_iobuf_list should contain only dummy buffer_heads
+ * which were created by jbd2_journal_write_metadata_buffer().
+ */
+ BUFFER_TRACE(bh, "dumping temporary bh");
+ jbd2_journal_put_journal_head(jh);
+ __brelse(bh);
+ J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0);
+ free_buffer_head(bh);
+
+ /* We also have to unlock and free the corresponding
+ shadowed buffer */
+ jh = commit_transaction->t_shadow_list->b_tprev;
+ bh = jh2bh(jh);
+ clear_bit(BH_JWrite, &bh->b_state);
+ J_ASSERT_BH(bh, buffer_jbddirty(bh));
+
+ /* The metadata is now released for reuse, but we need
+ to remember it against this transaction so that when
+ we finally commit, we can do any checkpointing
+ required. */
+ JBUFFER_TRACE(jh, "file as BJ_Forget");
+ jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget);
+ /* Wake up any transactions which were waiting for this
+ IO to complete */
+ wake_up_bit(&bh->b_state, BH_Unshadow);
+ JBUFFER_TRACE(jh, "brelse shadowed buffer");
+ __brelse(bh);
+ }
+
+ J_ASSERT (commit_transaction->t_shadow_list == NULL);
+
+ jbd_debug(3, "JBD: commit phase 5\n");
+
+ /* Here we wait for the revoke record and descriptor record buffers */
+ wait_for_ctlbuf:
+ while (commit_transaction->t_log_list != NULL) {
+ struct buffer_head *bh;
+
+ jh = commit_transaction->t_log_list->b_tprev;
+ bh = jh2bh(jh);
+ if (buffer_locked(bh)) {
+ wait_on_buffer(bh);
+ goto wait_for_ctlbuf;
+ }
+ if (cond_resched())
+ goto wait_for_ctlbuf;
+
+ if (unlikely(!buffer_uptodate(bh)))
+ err = -EIO;
+
+ BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile");
+ clear_buffer_jwrite(bh);
+ jbd2_journal_unfile_buffer(journal, jh);
+ jbd2_journal_put_journal_head(jh);
+ __brelse(bh); /* One for getblk */
+ /* AKPM: bforget here */
+ }
+
+ jbd_debug(3, "JBD: commit phase 6\n");
+
+ if (journal_write_commit_record(journal, commit_transaction))
+ err = -EIO;
+
+ if (err)
+ __jbd2_journal_abort_hard(journal);
+
+ /* End of a transaction! Finally, we can do checkpoint
+ processing: any buffers committed as a result of this
+ transaction can be removed from any checkpoint list it was on
+ before. */
+
+ jbd_debug(3, "JBD: commit phase 7\n");
+
+ J_ASSERT(commit_transaction->t_sync_datalist == NULL);
+ J_ASSERT(commit_transaction->t_buffers == NULL);
+ J_ASSERT(commit_transaction->t_checkpoint_list == NULL);
+ J_ASSERT(commit_transaction->t_iobuf_list == NULL);
+ J_ASSERT(commit_transaction->t_shadow_list == NULL);
+ J_ASSERT(commit_transaction->t_log_list == NULL);
+
+restart_loop:
+ /*
+ * As there are other places (journal_unmap_buffer()) adding buffers
+ * to this list we have to be careful and hold the j_list_lock.
+ */
+ spin_lock(&journal->j_list_lock);
+ while (commit_transaction->t_forget) {
+ transaction_t *cp_transaction;
+ struct buffer_head *bh;
+
+ jh = commit_transaction->t_forget;
+ spin_unlock(&journal->j_list_lock);
+ bh = jh2bh(jh);
+ jbd_lock_bh_state(bh);
+ J_ASSERT_JH(jh, jh->b_transaction == commit_transaction ||
+ jh->b_transaction == journal->j_running_transaction);
+
+ /*
+ * If there is undo-protected committed data against
+ * this buffer, then we can remove it now. If it is a
+ * buffer needing such protection, the old frozen_data
+ * field now points to a committed version of the
+ * buffer, so rotate that field to the new committed
+ * data.
+ *
+ * Otherwise, we can just throw away the frozen data now.
+ */
+ if (jh->b_committed_data) {
+ jbd2_slab_free(jh->b_committed_data, bh->b_size);
+ jh->b_committed_data = NULL;
+ if (jh->b_frozen_data) {
+ jh->b_committed_data = jh->b_frozen_data;
+ jh->b_frozen_data = NULL;
+ }
+ } else if (jh->b_frozen_data) {
+ jbd2_slab_free(jh->b_frozen_data, bh->b_size);
+ jh->b_frozen_data = NULL;
+ }
+
+ spin_lock(&journal->j_list_lock);
+ cp_transaction = jh->b_cp_transaction;
+ if (cp_transaction) {
+ JBUFFER_TRACE(jh, "remove from old cp transaction");
+ __jbd2_journal_remove_checkpoint(jh);
+ }
+
+ /* Only re-checkpoint the buffer_head if it is marked
+ * dirty. If the buffer was added to the BJ_Forget list
+ * by jbd2_journal_forget, it may no longer be dirty and
+ * there's no point in keeping a checkpoint record for
+ * it. */
+
+ /* A buffer which has been freed while still being
+ * journaled by a previous transaction may end up still
+ * being dirty here, but we want to avoid writing back
+ * that buffer in the future now that the last use has
+ * been committed. That's not only a performance gain,
+ * it also stops aliasing problems if the buffer is left
+ * behind for writeback and gets reallocated for another
+ * use in a different page. */
+ if (buffer_freed(bh)) {
+ clear_buffer_freed(bh);
+ clear_buffer_jbddirty(bh);
+ }
+
+ if (buffer_jbddirty(bh)) {
+ JBUFFER_TRACE(jh, "add to new checkpointing trans");
+ __jbd2_journal_insert_checkpoint(jh, commit_transaction);
+ JBUFFER_TRACE(jh, "refile for checkpoint writeback");
+ __jbd2_journal_refile_buffer(jh);
+ jbd_unlock_bh_state(bh);
+ } else {
+ J_ASSERT_BH(bh, !buffer_dirty(bh));
+ /* The buffer on BJ_Forget list and not jbddirty means
+ * it has been freed by this transaction and hence it
+ * could not have been reallocated until this
+ * transaction has committed. *BUT* it could be
+ * reallocated once we have written all the data to
+ * disk and before we process the buffer on BJ_Forget
+ * list. */
+ JBUFFER_TRACE(jh, "refile or unfile freed buffer");
+ __jbd2_journal_refile_buffer(jh);
+ if (!jh->b_transaction) {
+ jbd_unlock_bh_state(bh);
+ /* needs a brelse */
+ jbd2_journal_remove_journal_head(bh);
+ release_buffer_page(bh);
+ } else
+ jbd_unlock_bh_state(bh);
+ }
+ cond_resched_lock(&journal->j_list_lock);
+ }
+ spin_unlock(&journal->j_list_lock);
+ /*
+ * This is a bit sleazy. We borrow j_list_lock to protect
+ * journal->j_committing_transaction in __jbd2_journal_remove_checkpoint.
+ * Really, __jbd2_journal_remove_checkpoint should be using j_state_lock but
+ * it's a bit hassle to hold that across __jbd2_journal_remove_checkpoint
+ */
+ spin_lock(&journal->j_state_lock);
+ spin_lock(&journal->j_list_lock);
+ /*
+ * Now recheck if some buffers did not get attached to the transaction
+ * while the lock was dropped...
+ */
+ if (commit_transaction->t_forget) {
+ spin_unlock(&journal->j_list_lock);
+ spin_unlock(&journal->j_state_lock);
+ goto restart_loop;
+ }
+
+ /* Done with this transaction! */
+
+ jbd_debug(3, "JBD: commit phase 8\n");
+
+ J_ASSERT(commit_transaction->t_state == T_COMMIT);
+
+ commit_transaction->t_state = T_FINISHED;
+ J_ASSERT(commit_transaction == journal->j_committing_transaction);
+ journal->j_commit_sequence = commit_transaction->t_tid;
+ journal->j_committing_transaction = NULL;
+ spin_unlock(&journal->j_state_lock);
+
+ if (commit_transaction->t_checkpoint_list == NULL) {
+ __jbd2_journal_drop_transaction(journal, commit_transaction);
+ } else {
+ if (journal->j_checkpoint_transactions == NULL) {
+ journal->j_checkpoint_transactions = commit_transaction;
+ commit_transaction->t_cpnext = commit_transaction;
+ commit_transaction->t_cpprev = commit_transaction;
+ } else {
+ commit_transaction->t_cpnext =
+ journal->j_checkpoint_transactions;
+ commit_transaction->t_cpprev =
+ commit_transaction->t_cpnext->t_cpprev;
+ commit_transaction->t_cpnext->t_cpprev =
+ commit_transaction;
+ commit_transaction->t_cpprev->t_cpnext =
+ commit_transaction;
+ }
+ }
+ spin_unlock(&journal->j_list_lock);
+
+ jbd_debug(1, "JBD: commit %d complete, head %d\n",
+ journal->j_commit_sequence, journal->j_tail_sequence);
+
+ wake_up(&journal->j_wait_done_commit);
+}
--- /dev/null
+/*
+ * linux/fs/jbd2/journal.c
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
+ *
+ * Copyright 1998 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Generic filesystem journal-writing code; part of the ext2fs
+ * journaling system.
+ *
+ * This file manages journals: areas of disk reserved for logging
+ * transactional updates. This includes the kernel journaling thread
+ * which is responsible for scheduling updates to the log.
+ *
+ * We do not actually manage the physical storage of the journal in this
+ * file: that is left to a per-journal policy function, which allows us
+ * to store the journal within a filesystem-specified area for ext2
+ * journaling (ext2 can use a reserved inode for storing the log).
+ */
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <linux/pagemap.h>
+#include <linux/kthread.h>
+#include <linux/poison.h>
+#include <linux/proc_fs.h>
+
+#include <asm/uaccess.h>
+#include <asm/page.h>
+
+EXPORT_SYMBOL(jbd2_journal_start);
+EXPORT_SYMBOL(jbd2_journal_restart);
+EXPORT_SYMBOL(jbd2_journal_extend);
+EXPORT_SYMBOL(jbd2_journal_stop);
+EXPORT_SYMBOL(jbd2_journal_lock_updates);
+EXPORT_SYMBOL(jbd2_journal_unlock_updates);
+EXPORT_SYMBOL(jbd2_journal_get_write_access);
+EXPORT_SYMBOL(jbd2_journal_get_create_access);
+EXPORT_SYMBOL(jbd2_journal_get_undo_access);
+EXPORT_SYMBOL(jbd2_journal_dirty_data);
+EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
+EXPORT_SYMBOL(jbd2_journal_release_buffer);
+EXPORT_SYMBOL(jbd2_journal_forget);
+#if 0
+EXPORT_SYMBOL(journal_sync_buffer);
+#endif
+EXPORT_SYMBOL(jbd2_journal_flush);
+EXPORT_SYMBOL(jbd2_journal_revoke);
+
+EXPORT_SYMBOL(jbd2_journal_init_dev);
+EXPORT_SYMBOL(jbd2_journal_init_inode);
+EXPORT_SYMBOL(jbd2_journal_update_format);
+EXPORT_SYMBOL(jbd2_journal_check_used_features);
+EXPORT_SYMBOL(jbd2_journal_check_available_features);
+EXPORT_SYMBOL(jbd2_journal_set_features);
+EXPORT_SYMBOL(jbd2_journal_create);
+EXPORT_SYMBOL(jbd2_journal_load);
+EXPORT_SYMBOL(jbd2_journal_destroy);
+EXPORT_SYMBOL(jbd2_journal_update_superblock);
+EXPORT_SYMBOL(jbd2_journal_abort);
+EXPORT_SYMBOL(jbd2_journal_errno);
+EXPORT_SYMBOL(jbd2_journal_ack_err);
+EXPORT_SYMBOL(jbd2_journal_clear_err);
+EXPORT_SYMBOL(jbd2_log_wait_commit);
+EXPORT_SYMBOL(jbd2_journal_start_commit);
+EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
+EXPORT_SYMBOL(jbd2_journal_wipe);
+EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
+EXPORT_SYMBOL(jbd2_journal_invalidatepage);
+EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
+EXPORT_SYMBOL(jbd2_journal_force_commit);
+
+static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
+static void __journal_abort_soft (journal_t *journal, int errno);
+static int jbd2_journal_create_jbd_slab(size_t slab_size);
+
+/*
+ * Helper function used to manage commit timeouts
+ */
+
+static void commit_timeout(unsigned long __data)
+{
+ struct task_struct * p = (struct task_struct *) __data;
+
+ wake_up_process(p);
+}
+
+/*
+ * kjournald2: The main thread function used to manage a logging device
+ * journal.
+ *
+ * This kernel thread is responsible for two things:
+ *
+ * 1) COMMIT: Every so often we need to commit the current state of the
+ * filesystem to disk. The journal thread is responsible for writing
+ * all of the metadata buffers to disk.
+ *
+ * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
+ * of the data in that part of the log has been rewritten elsewhere on
+ * the disk. Flushing these old buffers to reclaim space in the log is
+ * known as checkpointing, and this thread is responsible for that job.
+ */
+
+static int kjournald2(void *arg)
+{
+ journal_t *journal = arg;
+ transaction_t *transaction;
+
+ /*
+ * Set up an interval timer which can be used to trigger a commit wakeup
+ * after the commit interval expires
+ */
+ setup_timer(&journal->j_commit_timer, commit_timeout,
+ (unsigned long)current);
+
+ /* Record that the journal thread is running */
+ journal->j_task = current;
+ wake_up(&journal->j_wait_done_commit);
+
+ printk(KERN_INFO "kjournald2 starting. Commit interval %ld seconds\n",
+ journal->j_commit_interval / HZ);
+
+ /*
+ * And now, wait forever for commit wakeup events.
+ */
+ spin_lock(&journal->j_state_lock);
+
+loop:
+ if (journal->j_flags & JBD2_UNMOUNT)
+ goto end_loop;
+
+ jbd_debug(1, "commit_sequence=%d, commit_request=%d\n",
+ journal->j_commit_sequence, journal->j_commit_request);
+
+ if (journal->j_commit_sequence != journal->j_commit_request) {
+ jbd_debug(1, "OK, requests differ\n");
+ spin_unlock(&journal->j_state_lock);
+ del_timer_sync(&journal->j_commit_timer);
+ jbd2_journal_commit_transaction(journal);
+ spin_lock(&journal->j_state_lock);
+ goto loop;
+ }
+
+ wake_up(&journal->j_wait_done_commit);
+ if (freezing(current)) {
+ /*
+ * The simpler the better. Flushing journal isn't a
+ * good idea, because that depends on threads that may
+ * be already stopped.
+ */
+ jbd_debug(1, "Now suspending kjournald2\n");
+ spin_unlock(&journal->j_state_lock);
+ refrigerator();
+ spin_lock(&journal->j_state_lock);
+ } else {
+ /*
+ * We assume on resume that commits are already there,
+ * so we don't sleep
+ */
+ DEFINE_WAIT(wait);
+ int should_sleep = 1;
+
+ prepare_to_wait(&journal->j_wait_commit, &wait,
+ TASK_INTERRUPTIBLE);
+ if (journal->j_commit_sequence != journal->j_commit_request)
+ should_sleep = 0;
+ transaction = journal->j_running_transaction;
+ if (transaction && time_after_eq(jiffies,
+ transaction->t_expires))
+ should_sleep = 0;
+ if (journal->j_flags & JBD2_UNMOUNT)
+ should_sleep = 0;
+ if (should_sleep) {
+ spin_unlock(&journal->j_state_lock);
+ schedule();
+ spin_lock(&journal->j_state_lock);
+ }
+ finish_wait(&journal->j_wait_commit, &wait);
+ }
+
+ jbd_debug(1, "kjournald2 wakes\n");
+
+ /*
+ * Were we woken up by a commit wakeup event?
+ */
+ transaction = journal->j_running_transaction;
+ if (transaction && time_after_eq(jiffies, transaction->t_expires)) {
+ journal->j_commit_request = transaction->t_tid;
+ jbd_debug(1, "woke because of timeout\n");
+ }
+ goto loop;
+
+end_loop:
+ spin_unlock(&journal->j_state_lock);
+ del_timer_sync(&journal->j_commit_timer);
+ journal->j_task = NULL;
+ wake_up(&journal->j_wait_done_commit);
+ jbd_debug(1, "Journal thread exiting.\n");
+ return 0;
+}
+
+static void jbd2_journal_start_thread(journal_t *journal)
+{
+ kthread_run(kjournald2, journal, "kjournald2");
+ wait_event(journal->j_wait_done_commit, journal->j_task != 0);
+}
+
+static void journal_kill_thread(journal_t *journal)
+{
+ spin_lock(&journal->j_state_lock);
+ journal->j_flags |= JBD2_UNMOUNT;
+
+ while (journal->j_task) {
+ wake_up(&journal->j_wait_commit);
+ spin_unlock(&journal->j_state_lock);
+ wait_event(journal->j_wait_done_commit, journal->j_task == 0);
+ spin_lock(&journal->j_state_lock);
+ }
+ spin_unlock(&journal->j_state_lock);
+}
+
+/*
+ * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal.
+ *
+ * Writes a metadata buffer to a given disk block. The actual IO is not
+ * performed but a new buffer_head is constructed which labels the data
+ * to be written with the correct destination disk block.
+ *
+ * Any magic-number escaping which needs to be done will cause a
+ * copy-out here. If the buffer happens to start with the
+ * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the
+ * magic number is only written to the log for descripter blocks. In
+ * this case, we copy the data and replace the first word with 0, and we
+ * return a result code which indicates that this buffer needs to be
+ * marked as an escaped buffer in the corresponding log descriptor
+ * block. The missing word can then be restored when the block is read
+ * during recovery.
+ *
+ * If the source buffer has already been modified by a new transaction
+ * since we took the last commit snapshot, we use the frozen copy of
+ * that data for IO. If we end up using the existing buffer_head's data
+ * for the write, then we *have* to lock the buffer to prevent anyone
+ * else from using and possibly modifying it while the IO is in
+ * progress.
+ *
+ * The function returns a pointer to the buffer_heads to be used for IO.
+ *
+ * We assume that the journal has already been locked in this function.
+ *
+ * Return value:
+ * <0: Error
+ * >=0: Finished OK
+ *
+ * On success:
+ * Bit 0 set == escape performed on the data
+ * Bit 1 set == buffer copy-out performed (kfree the data after IO)
+ */
+
+int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
+ struct journal_head *jh_in,
+ struct journal_head **jh_out,
+ unsigned long long blocknr)
+{
+ int need_copy_out = 0;
+ int done_copy_out = 0;
+ int do_escape = 0;
+ char *mapped_data;
+ struct buffer_head *new_bh;
+ struct journal_head *new_jh;
+ struct page *new_page;
+ unsigned int new_offset;
+ struct buffer_head *bh_in = jh2bh(jh_in);
+
+ /*
+ * The buffer really shouldn't be locked: only the current committing
+ * transaction is allowed to write it, so nobody else is allowed
+ * to do any IO.
+ *
+ * akpm: except if we're journalling data, and write() output is
+ * also part of a shared mapping, and another thread has
+ * decided to launch a writepage() against this buffer.
+ */
+ J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
+
+ new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+
+ /*
+ * If a new transaction has already done a buffer copy-out, then
+ * we use that version of the data for the commit.
+ */
+ jbd_lock_bh_state(bh_in);
+repeat:
+ if (jh_in->b_frozen_data) {
+ done_copy_out = 1;
+ new_page = virt_to_page(jh_in->b_frozen_data);
+ new_offset = offset_in_page(jh_in->b_frozen_data);
+ } else {
+ new_page = jh2bh(jh_in)->b_page;
+ new_offset = offset_in_page(jh2bh(jh_in)->b_data);
+ }
+
+ mapped_data = kmap_atomic(new_page, KM_USER0);
+ /*
+ * Check for escaping
+ */
+ if (*((__be32 *)(mapped_data + new_offset)) ==
+ cpu_to_be32(JBD2_MAGIC_NUMBER)) {
+ need_copy_out = 1;
+ do_escape = 1;
+ }
+ kunmap_atomic(mapped_data, KM_USER0);
+
+ /*
+ * Do we need to do a data copy?
+ */
+ if (need_copy_out && !done_copy_out) {
+ char *tmp;
+
+ jbd_unlock_bh_state(bh_in);
+ tmp = jbd2_slab_alloc(bh_in->b_size, GFP_NOFS);
+ jbd_lock_bh_state(bh_in);
+ if (jh_in->b_frozen_data) {
+ jbd2_slab_free(tmp, bh_in->b_size);
+ goto repeat;
+ }
+
+ jh_in->b_frozen_data = tmp;
+ mapped_data = kmap_atomic(new_page, KM_USER0);
+ memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
+ kunmap_atomic(mapped_data, KM_USER0);
+
+ new_page = virt_to_page(tmp);
+ new_offset = offset_in_page(tmp);
+ done_copy_out = 1;
+ }
+
+ /*
+ * Did we need to do an escaping? Now we've done all the
+ * copying, we can finally do so.
+ */
+ if (do_escape) {
+ mapped_data = kmap_atomic(new_page, KM_USER0);
+ *((unsigned int *)(mapped_data + new_offset)) = 0;
+ kunmap_atomic(mapped_data, KM_USER0);
+ }
+
+ /* keep subsequent assertions sane */
+ new_bh->b_state = 0;
+ init_buffer(new_bh, NULL, NULL);
+ atomic_set(&new_bh->b_count, 1);
+ jbd_unlock_bh_state(bh_in);
+
+ new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
+
+ set_bh_page(new_bh, new_page, new_offset);
+ new_jh->b_transaction = NULL;
+ new_bh->b_size = jh2bh(jh_in)->b_size;
+ new_bh->b_bdev = transaction->t_journal->j_dev;
+ new_bh->b_blocknr = blocknr;
+ set_buffer_mapped(new_bh);
+ set_buffer_dirty(new_bh);
+
+ *jh_out = new_jh;
+
+ /*
+ * The to-be-written buffer needs to get moved to the io queue,
+ * and the original buffer whose contents we are shadowing or
+ * copying is moved to the transaction's shadow queue.
+ */
+ JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
+ jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+ JBUFFER_TRACE(new_jh, "file as BJ_IO");
+ jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
+
+ return do_escape | (done_copy_out << 1);
+}
+
+/*
+ * Allocation code for the journal file. Manage the space left in the
+ * journal, so that we can begin checkpointing when appropriate.
+ */
+
+/*
+ * __jbd2_log_space_left: Return the number of free blocks left in the journal.
+ *
+ * Called with the journal already locked.
+ *
+ * Called under j_state_lock
+ */
+
+int __jbd2_log_space_left(journal_t *journal)
+{
+ int left = journal->j_free;
+
+ assert_spin_locked(&journal->j_state_lock);
+
+ /*
+ * Be pessimistic here about the number of those free blocks which
+ * might be required for log descriptor control blocks.
+ */
+
+#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */
+
+ left -= MIN_LOG_RESERVED_BLOCKS;
+
+ if (left <= 0)
+ return 0;
+ left -= (left >> 3);
+ return left;
+}
+
+/*
+ * Called under j_state_lock. Returns true if a transaction was started.
+ */
+int __jbd2_log_start_commit(journal_t *journal, tid_t target)
+{
+ /*
+ * Are we already doing a recent enough commit?
+ */
+ if (!tid_geq(journal->j_commit_request, target)) {
+ /*
+ * We want a new commit: OK, mark the request and wakup the
+ * commit thread. We do _not_ do the commit ourselves.
+ */
+
+ journal->j_commit_request = target;
+ jbd_debug(1, "JBD: requesting commit %d/%d\n",
+ journal->j_commit_request,
+ journal->j_commit_sequence);
+ wake_up(&journal->j_wait_commit);
+ return 1;
+ }
+ return 0;
+}
+
+int jbd2_log_start_commit(journal_t *journal, tid_t tid)
+{
+ int ret;
+
+ spin_lock(&journal->j_state_lock);
+ ret = __jbd2_log_start_commit(journal, tid);
+ spin_unlock(&journal->j_state_lock);
+ return ret;
+}
+
+/*
+ * Force and wait upon a commit if the calling process is not within
+ * transaction. This is used for forcing out undo-protected data which contains
+ * bitmaps, when the fs is running out of space.
+ *
+ * We can only force the running transaction if we don't have an active handle;
+ * otherwise, we will deadlock.
+ *
+ * Returns true if a transaction was started.
+ */
+int jbd2_journal_force_commit_nested(journal_t *journal)
+{
+ transaction_t *transaction = NULL;
+ tid_t tid;
+
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_running_transaction && !current->journal_info) {
+ transaction = journal->j_running_transaction;
+ __jbd2_log_start_commit(journal, transaction->t_tid);
+ } else if (journal->j_committing_transaction)
+ transaction = journal->j_committing_transaction;
+
+ if (!transaction) {
+ spin_unlock(&journal->j_state_lock);
+ return 0; /* Nothing to retry */
+ }
+
+ tid = transaction->t_tid;
+ spin_unlock(&journal->j_state_lock);
+ jbd2_log_wait_commit(journal, tid);
+ return 1;
+}
+
+/*
+ * Start a commit of the current running transaction (if any). Returns true
+ * if a transaction was started, and fills its tid in at *ptid
+ */
+int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
+{
+ int ret = 0;
+
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_running_transaction) {
+ tid_t tid = journal->j_running_transaction->t_tid;
+
+ ret = __jbd2_log_start_commit(journal, tid);
+ if (ret && ptid)
+ *ptid = tid;
+ } else if (journal->j_committing_transaction && ptid) {
+ /*
+ * If ext3_write_super() recently started a commit, then we
+ * have to wait for completion of that transaction
+ */
+ *ptid = journal->j_committing_transaction->t_tid;
+ ret = 1;
+ }
+ spin_unlock(&journal->j_state_lock);
+ return ret;
+}
+
+/*
+ * Wait for a specified commit to complete.
+ * The caller may not hold the journal lock.
+ */
+int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
+{
+ int err = 0;
+
+#ifdef CONFIG_JBD_DEBUG
+ spin_lock(&journal->j_state_lock);
+ if (!tid_geq(journal->j_commit_request, tid)) {
+ printk(KERN_EMERG
+ "%s: error: j_commit_request=%d, tid=%d\n",
+ __FUNCTION__, journal->j_commit_request, tid);
+ }
+ spin_unlock(&journal->j_state_lock);
+#endif
+ spin_lock(&journal->j_state_lock);
+ while (tid_gt(tid, journal->j_commit_sequence)) {
+ jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n",
+ tid, journal->j_commit_sequence);
+ wake_up(&journal->j_wait_commit);
+ spin_unlock(&journal->j_state_lock);
+ wait_event(journal->j_wait_done_commit,
+ !tid_gt(tid, journal->j_commit_sequence));
+ spin_lock(&journal->j_state_lock);
+ }
+ spin_unlock(&journal->j_state_lock);
+
+ if (unlikely(is_journal_aborted(journal))) {
+ printk(KERN_EMERG "journal commit I/O error\n");
+ err = -EIO;
+ }
+ return err;
+}
+
+/*
+ * Log buffer allocation routines:
+ */
+
+int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
+{
+ unsigned long blocknr;
+
+ spin_lock(&journal->j_state_lock);
+ J_ASSERT(journal->j_free > 1);
+
+ blocknr = journal->j_head;
+ journal->j_head++;
+ journal->j_free--;
+ if (journal->j_head == journal->j_last)
+ journal->j_head = journal->j_first;
+ spin_unlock(&journal->j_state_lock);
+ return jbd2_journal_bmap(journal, blocknr, retp);
+}
+
+/*
+ * Conversion of logical to physical block numbers for the journal
+ *
+ * On external journals the journal blocks are identity-mapped, so
+ * this is a no-op. If needed, we can use j_blk_offset - everything is
+ * ready.
+ */
+int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
+ unsigned long long *retp)
+{
+ int err = 0;
+ unsigned long long ret;
+
+ if (journal->j_inode) {
+ ret = bmap(journal->j_inode, blocknr);
+ if (ret)
+ *retp = ret;
+ else {
+ char b[BDEVNAME_SIZE];
+
+ printk(KERN_ALERT "%s: journal block not found "
+ "at offset %lu on %s\n",
+ __FUNCTION__,
+ blocknr,
+ bdevname(journal->j_dev, b));
+ err = -EIO;
+ __journal_abort_soft(journal, err);
+ }
+ } else {
+ *retp = blocknr; /* +journal->j_blk_offset */
+ }
+ return err;
+}
+
+/*
+ * We play buffer_head aliasing tricks to write data/metadata blocks to
+ * the journal without copying their contents, but for journal
+ * descriptor blocks we do need to generate bona fide buffers.
+ *
+ * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying
+ * the buffer's contents they really should run flush_dcache_page(bh->b_page).
+ * But we don't bother doing that, so there will be coherency problems with
+ * mmaps of blockdevs which hold live JBD-controlled filesystems.
+ */
+struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
+{
+ struct buffer_head *bh;
+ unsigned long long blocknr;
+ int err;
+
+ err = jbd2_journal_next_log_block(journal, &blocknr);
+
+ if (err)
+ return NULL;
+
+ bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ lock_buffer(bh);
+ memset(bh->b_data, 0, journal->j_blocksize);
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+ BUFFER_TRACE(bh, "return this buffer");
+ return jbd2_journal_add_journal_head(bh);
+}
+
+/*
+ * Management for journal control blocks: functions to create and
+ * destroy journal_t structures, and to initialise and read existing
+ * journal blocks from disk. */
+
+/* First: create and setup a journal_t object in memory. We initialise
+ * very few fields yet: that has to wait until we have created the
+ * journal structures from from scratch, or loaded them from disk. */
+
+static journal_t * journal_init_common (void)
+{
+ journal_t *journal;
+ int err;
+
+ journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL);
+ if (!journal)
+ goto fail;
+ memset(journal, 0, sizeof(*journal));
+
+ init_waitqueue_head(&journal->j_wait_transaction_locked);
+ init_waitqueue_head(&journal->j_wait_logspace);
+ init_waitqueue_head(&journal->j_wait_done_commit);
+ init_waitqueue_head(&journal->j_wait_checkpoint);
+ init_waitqueue_head(&journal->j_wait_commit);
+ init_waitqueue_head(&journal->j_wait_updates);
+ mutex_init(&journal->j_barrier);
+ mutex_init(&journal->j_checkpoint_mutex);
+ spin_lock_init(&journal->j_revoke_lock);
+ spin_lock_init(&journal->j_list_lock);
+ spin_lock_init(&journal->j_state_lock);
+
+ journal->j_commit_interval = (HZ * JBD_DEFAULT_MAX_COMMIT_AGE);
+
+ /* The journal is marked for error until we succeed with recovery! */
+ journal->j_flags = JBD2_ABORT;
+
+ /* Set up a default-sized revoke table for the new mount. */
+ err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
+ if (err) {
+ kfree(journal);
+ goto fail;
+ }
+ return journal;
+fail:
+ return NULL;
+}
+
+/* jbd2_journal_init_dev and jbd2_journal_init_inode:
+ *
+ * Create a journal structure assigned some fixed set of disk blocks to
+ * the journal. We don't actually touch those disk blocks yet, but we
+ * need to set up all of the mapping information to tell the journaling
+ * system where the journal blocks are.
+ *
+ */
+
+/**
+ * journal_t * jbd2_journal_init_dev() - creates an initialises a journal structure
+ * @bdev: Block device on which to create the journal
+ * @fs_dev: Device which hold journalled filesystem for this journal.
+ * @start: Block nr Start of journal.
+ * @len: Length of the journal in blocks.
+ * @blocksize: blocksize of journalling device
+ * @returns: a newly created journal_t *
+ *
+ * jbd2_journal_init_dev creates a journal which maps a fixed contiguous
+ * range of blocks on an arbitrary block device.
+ *
+ */
+journal_t * jbd2_journal_init_dev(struct block_device *bdev,
+ struct block_device *fs_dev,
+ unsigned long long start, int len, int blocksize)
+{
+ journal_t *journal = journal_init_common();
+ struct buffer_head *bh;
+ int n;
+
+ if (!journal)
+ return NULL;
+
+ /* journal descriptor can store up to n blocks -bzzz */
+ journal->j_blocksize = blocksize;
+ n = journal->j_blocksize / sizeof(journal_block_tag_t);
+ journal->j_wbufsize = n;
+ journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
+ if (!journal->j_wbuf) {
+ printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
+ __FUNCTION__);
+ kfree(journal);
+ journal = NULL;
+ goto out;
+ }
+ journal->j_dev = bdev;
+ journal->j_fs_dev = fs_dev;
+ journal->j_blk_offset = start;
+ journal->j_maxlen = len;
+
+ bh = __getblk(journal->j_dev, start, journal->j_blocksize);
+ J_ASSERT(bh != NULL);
+ journal->j_sb_buffer = bh;
+ journal->j_superblock = (journal_superblock_t *)bh->b_data;
+out:
+ return journal;
+}
+
+/**
+ * journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode.
+ * @inode: An inode to create the journal in
+ *
+ * jbd2_journal_init_inode creates a journal which maps an on-disk inode as
+ * the journal. The inode must exist already, must support bmap() and
+ * must have all data blocks preallocated.
+ */
+journal_t * jbd2_journal_init_inode (struct inode *inode)
+{
+ struct buffer_head *bh;
+ journal_t *journal = journal_init_common();
+ int err;
+ int n;
+ unsigned long long blocknr;
+
+ if (!journal)
+ return NULL;
+
+ journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
+ journal->j_inode = inode;
+ jbd_debug(1,
+ "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
+ journal, inode->i_sb->s_id, inode->i_ino,
+ (long long) inode->i_size,
+ inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize);
+
+ journal->j_maxlen = inode->i_size >> inode->i_sb->s_blocksize_bits;
+ journal->j_blocksize = inode->i_sb->s_blocksize;
+
+ /* journal descriptor can store up to n blocks -bzzz */
+ n = journal->j_blocksize / sizeof(journal_block_tag_t);
+ journal->j_wbufsize = n;
+ journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
+ if (!journal->j_wbuf) {
+ printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
+ __FUNCTION__);
+ kfree(journal);
+ return NULL;
+ }
+
+ err = jbd2_journal_bmap(journal, 0, &blocknr);
+ /* If that failed, give up */
+ if (err) {
+ printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
+ __FUNCTION__);
+ kfree(journal);
+ return NULL;
+ }
+
+ bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ J_ASSERT(bh != NULL);
+ journal->j_sb_buffer = bh;
+ journal->j_superblock = (journal_superblock_t *)bh->b_data;
+
+ return journal;
+}
+
+/*
+ * If the journal init or create aborts, we need to mark the journal
+ * superblock as being NULL to prevent the journal destroy from writing
+ * back a bogus superblock.
+ */
+static void journal_fail_superblock (journal_t *journal)
+{
+ struct buffer_head *bh = journal->j_sb_buffer;
+ brelse(bh);
+ journal->j_sb_buffer = NULL;
+}
+
+/*
+ * Given a journal_t structure, initialise the various fields for
+ * startup of a new journaling session. We use this both when creating
+ * a journal, and after recovering an old journal to reset it for
+ * subsequent use.
+ */
+
+static int journal_reset(journal_t *journal)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+ unsigned long long first, last;
+
+ first = be32_to_cpu(sb->s_first);
+ last = be32_to_cpu(sb->s_maxlen);
+
+ journal->j_first = first;
+ journal->j_last = last;
+
+ journal->j_head = first;
+ journal->j_tail = first;
+ journal->j_free = last - first;
+
+ journal->j_tail_sequence = journal->j_transaction_sequence;
+ journal->j_commit_sequence = journal->j_transaction_sequence - 1;
+ journal->j_commit_request = journal->j_commit_sequence;
+
+ journal->j_max_transaction_buffers = journal->j_maxlen / 4;
+
+ /* Add the dynamic fields and write it to disk. */
+ jbd2_journal_update_superblock(journal, 1);
+ jbd2_journal_start_thread(journal);
+ return 0;
+}
+
+/**
+ * int jbd2_journal_create() - Initialise the new journal file
+ * @journal: Journal to create. This structure must have been initialised
+ *
+ * Given a journal_t structure which tells us which disk blocks we can
+ * use, create a new journal superblock and initialise all of the
+ * journal fields from scratch.
+ **/
+int jbd2_journal_create(journal_t *journal)
+{
+ unsigned long long blocknr;
+ struct buffer_head *bh;
+ journal_superblock_t *sb;
+ int i, err;
+
+ if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) {
+ printk (KERN_ERR "Journal length (%d blocks) too short.\n",
+ journal->j_maxlen);
+ journal_fail_superblock(journal);
+ return -EINVAL;
+ }
+
+ if (journal->j_inode == NULL) {
+ /*
+ * We don't know what block to start at!
+ */
+ printk(KERN_EMERG
+ "%s: creation of journal on external device!\n",
+ __FUNCTION__);
+ BUG();
+ }
+
+ /* Zero out the entire journal on disk. We cannot afford to
+ have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */
+ jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
+ for (i = 0; i < journal->j_maxlen; i++) {
+ err = jbd2_journal_bmap(journal, i, &blocknr);
+ if (err)
+ return err;
+ bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ lock_buffer(bh);
+ memset (bh->b_data, 0, journal->j_blocksize);
+ BUFFER_TRACE(bh, "marking dirty");
+ mark_buffer_dirty(bh);
+ BUFFER_TRACE(bh, "marking uptodate");
+ set_buffer_uptodate(bh);
+ unlock_buffer(bh);
+ __brelse(bh);
+ }
+
+ sync_blockdev(journal->j_dev);
+ jbd_debug(1, "JBD: journal cleared.\n");
+
+ /* OK, fill in the initial static fields in the new superblock */
+ sb = journal->j_superblock;
+
+ sb->s_header.h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+ sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
+
+ sb->s_blocksize = cpu_to_be32(journal->j_blocksize);
+ sb->s_maxlen = cpu_to_be32(journal->j_maxlen);
+ sb->s_first = cpu_to_be32(1);
+
+ journal->j_transaction_sequence = 1;
+
+ journal->j_flags &= ~JBD2_ABORT;
+ journal->j_format_version = 2;
+
+ return journal_reset(journal);
+}
+
+/**
+ * void jbd2_journal_update_superblock() - Update journal sb on disk.
+ * @journal: The journal to update.
+ * @wait: Set to '0' if you don't want to wait for IO completion.
+ *
+ * Update a journal's dynamic superblock fields and write it to disk,
+ * optionally waiting for the IO to complete.
+ */
+void jbd2_journal_update_superblock(journal_t *journal, int wait)
+{
+ journal_superblock_t *sb = journal->j_superblock;
+ struct buffer_head *bh = journal->j_sb_buffer;
+
+ /*
+ * As a special case, if the on-disk copy is already marked as needing
+ * no recovery (s_start == 0) and there are no outstanding transactions
+ * in the filesystem, then we can safely defer the superblock update
+ * until the next commit by setting JBD2_FLUSHED. This avoids
+ * attempting a write to a potential-readonly device.
+ */
+ if (sb->s_start == 0 && journal->j_tail_sequence ==
+ journal->j_transaction_sequence) {
+ jbd_debug(1,"JBD: Skipping superblock update on recovered sb "
+ "(start %ld, seq %d, errno %d)\n",
+ journal->j_tail, journal->j_tail_sequence,
+ journal->j_errno);
+ goto out;
+ }
+
+ spin_lock(&journal->j_state_lock);
+ jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
+ journal->j_tail, journal->j_tail_sequence, journal->j_errno);
+
+ sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
+ sb->s_start = cpu_to_be32(journal->j_tail);
+ sb->s_errno = cpu_to_be32(journal->j_errno);
+ spin_unlock(&journal->j_state_lock);
+
+ BUFFER_TRACE(bh, "marking dirty");
+ mark_buffer_dirty(bh);
+ if (wait)
+ sync_dirty_buffer(bh);
+ else
+ ll_rw_block(SWRITE, 1, &bh);
+
+out:
+ /* If we have just flushed the log (by marking s_start==0), then
+ * any future commit will have to be careful to update the
+ * superblock again to re-record the true start of the log. */
+
+ spin_lock(&journal->j_state_lock);
+ if (sb->s_start)
+ journal->j_flags &= ~JBD2_FLUSHED;
+ else
+ journal->j_flags |= JBD2_FLUSHED;
+ spin_unlock(&journal->j_state_lock);
+}
+
+/*
+ * Read the superblock for a given journal, performing initial
+ * validation of the format.
+ */
+
+static int journal_get_superblock(journal_t *journal)
+{
+ struct buffer_head *bh;
+ journal_superblock_t *sb;
+ int err = -EIO;
+
+ bh = journal->j_sb_buffer;
+
+ J_ASSERT(bh != NULL);
+ if (!buffer_uptodate(bh)) {
+ ll_rw_block(READ, 1, &bh);
+ wait_on_buffer(bh);
+ if (!buffer_uptodate(bh)) {
+ printk (KERN_ERR
+ "JBD: IO error reading journal superblock\n");
+ goto out;
+ }
+ }
+
+ sb = journal->j_superblock;
+
+ err = -EINVAL;
+
+ if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) ||
+ sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) {
+ printk(KERN_WARNING "JBD: no valid journal superblock found\n");
+ goto out;
+ }
+
+ switch(be32_to_cpu(sb->s_header.h_blocktype)) {
+ case JBD2_SUPERBLOCK_V1:
+ journal->j_format_version = 1;
+ break;
+ case JBD2_SUPERBLOCK_V2:
+ journal->j_format_version = 2;
+ break;
+ default:
+ printk(KERN_WARNING "JBD: unrecognised superblock format ID\n");
+ goto out;
+ }
+
+ if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
+ journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
+ else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
+ printk (KERN_WARNING "JBD: journal file too short\n");
+ goto out;
+ }
+
+ return 0;
+
+out:
+ journal_fail_superblock(journal);
+ return err;
+}
+
+/*
+ * Load the on-disk journal superblock and read the key fields into the
+ * journal_t.
+ */
+
+static int load_superblock(journal_t *journal)
+{
+ int err;
+ journal_superblock_t *sb;
+
+ err = journal_get_superblock(journal);
+ if (err)
+ return err;
+
+ sb = journal->j_superblock;
+
+ journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
+ journal->j_tail = be32_to_cpu(sb->s_start);
+ journal->j_first = be32_to_cpu(sb->s_first);
+ journal->j_last = be32_to_cpu(sb->s_maxlen);
+ journal->j_errno = be32_to_cpu(sb->s_errno);
+
+ return 0;
+}
+
+
+/**
+ * int jbd2_journal_load() - Read journal from disk.
+ * @journal: Journal to act on.
+ *
+ * Given a journal_t structure which tells us which disk blocks contain
+ * a journal, read the journal from disk to initialise the in-memory
+ * structures.
+ */
+int jbd2_journal_load(journal_t *journal)
+{
+ int err;
+ journal_superblock_t *sb;
+
+ err = load_superblock(journal);
+ if (err)
+ return err;
+
+ sb = journal->j_superblock;
+ /* If this is a V2 superblock, then we have to check the
+ * features flags on it. */
+
+ if (journal->j_format_version >= 2) {
+ if ((sb->s_feature_ro_compat &
+ ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) ||
+ (sb->s_feature_incompat &
+ ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) {
+ printk (KERN_WARNING
+ "JBD: Unrecognised features on journal\n");
+ return -EINVAL;
+ }
+ }
+
+ /*
+ * Create a slab for this blocksize
+ */
+ err = jbd2_journal_create_jbd_slab(be32_to_cpu(sb->s_blocksize));
+ if (err)
+ return err;
+
+ /* Let the recovery code check whether it needs to recover any
+ * data from the journal. */
+ if (jbd2_journal_recover(journal))
+ goto recovery_error;
+
+ /* OK, we've finished with the dynamic journal bits:
+ * reinitialise the dynamic contents of the superblock in memory
+ * and reset them on disk. */
+ if (journal_reset(journal))
+ goto recovery_error;
+
+ journal->j_flags &= ~JBD2_ABORT;
+ journal->j_flags |= JBD2_LOADED;
+ return 0;
+
+recovery_error:
+ printk (KERN_WARNING "JBD: recovery failed\n");
+ return -EIO;
+}
+
+/**
+ * void jbd2_journal_destroy() - Release a journal_t structure.
+ * @journal: Journal to act on.
+ *
+ * Release a journal_t structure once it is no longer in use by the
+ * journaled object.
+ */
+void jbd2_journal_destroy(journal_t *journal)
+{
+ /* Wait for the commit thread to wake up and die. */
+ journal_kill_thread(journal);
+
+ /* Force a final log commit */
+ if (journal->j_running_transaction)
+ jbd2_journal_commit_transaction(journal);
+
+ /* Force any old transactions to disk */
+
+ /* Totally anal locking here... */
+ spin_lock(&journal->j_list_lock);
+ while (journal->j_checkpoint_transactions != NULL) {
+ spin_unlock(&journal->j_list_lock);
+ jbd2_log_do_checkpoint(journal);
+ spin_lock(&journal->j_list_lock);
+ }
+
+ J_ASSERT(journal->j_running_transaction == NULL);
+ J_ASSERT(journal->j_committing_transaction == NULL);
+ J_ASSERT(journal->j_checkpoint_transactions == NULL);
+ spin_unlock(&journal->j_list_lock);
+
+ /* We can now mark the journal as empty. */
+ journal->j_tail = 0;
+ journal->j_tail_sequence = ++journal->j_transaction_sequence;
+ if (journal->j_sb_buffer) {
+ jbd2_journal_update_superblock(journal, 1);
+ brelse(journal->j_sb_buffer);
+ }
+
+ if (journal->j_inode)
+ iput(journal->j_inode);
+ if (journal->j_revoke)
+ jbd2_journal_destroy_revoke(journal);
+ kfree(journal->j_wbuf);
+ kfree(journal);
+}
+
+
+/**
+ *int jbd2_journal_check_used_features () - Check if features specified are used.
+ * @journal: Journal to check.
+ * @compat: bitmask of compatible features
+ * @ro: bitmask of features that force read-only mount
+ * @incompat: bitmask of incompatible features
+ *
+ * Check whether the journal uses all of a given set of
+ * features. Return true (non-zero) if it does.
+ **/
+
+int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
+ unsigned long ro, unsigned long incompat)
+{
+ journal_superblock_t *sb;
+
+ if (!compat && !ro && !incompat)
+ return 1;
+ if (journal->j_format_version == 1)
+ return 0;
+
+ sb = journal->j_superblock;
+
+ if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) &&
+ ((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) &&
+ ((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat))
+ return 1;
+
+ return 0;
+}
+
+/**
+ * int jbd2_journal_check_available_features() - Check feature set in journalling layer
+ * @journal: Journal to check.
+ * @compat: bitmask of compatible features
+ * @ro: bitmask of features that force read-only mount
+ * @incompat: bitmask of incompatible features
+ *
+ * Check whether the journaling code supports the use of
+ * all of a given set of features on this journal. Return true
+ * (non-zero) if it can. */
+
+int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat,
+ unsigned long ro, unsigned long incompat)
+{
+ journal_superblock_t *sb;
+
+ if (!compat && !ro && !incompat)
+ return 1;
+
+ sb = journal->j_superblock;
+
+ /* We can support any known requested features iff the
+ * superblock is in version 2. Otherwise we fail to support any
+ * extended sb features. */
+
+ if (journal->j_format_version != 2)
+ return 0;
+
+ if ((compat & JBD2_KNOWN_COMPAT_FEATURES) == compat &&
+ (ro & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro &&
+ (incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat)
+ return 1;
+
+ return 0;
+}
+
+/**
+ * int jbd2_journal_set_features () - Mark a given journal feature in the superblock
+ * @journal: Journal to act on.
+ * @compat: bitmask of compatible features
+ * @ro: bitmask of features that force read-only mount
+ * @incompat: bitmask of incompatible features
+ *
+ * Mark a given journal feature as present on the
+ * superblock. Returns true if the requested features could be set.
+ *
+ */
+
+int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
+ unsigned long ro, unsigned long incompat)
+{
+ journal_superblock_t *sb;
+
+ if (jbd2_journal_check_used_features(journal, compat, ro, incompat))
+ return 1;
+
+ if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
+ return 0;
+
+ jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n",
+ compat, ro, incompat);
+
+ sb = journal->j_superblock;
+
+ sb->s_feature_compat |= cpu_to_be32(compat);
+ sb->s_feature_ro_compat |= cpu_to_be32(ro);
+ sb->s_feature_incompat |= cpu_to_be32(incompat);
+
+ return 1;
+}
+
+
+/**
+ * int jbd2_journal_update_format () - Update on-disk journal structure.
+ * @journal: Journal to act on.
+ *
+ * Given an initialised but unloaded journal struct, poke about in the
+ * on-disk structure to update it to the most recent supported version.
+ */
+int jbd2_journal_update_format (journal_t *journal)
+{
+ journal_superblock_t *sb;
+ int err;
+
+ err = journal_get_superblock(journal);
+ if (err)
+ return err;
+
+ sb = journal->j_superblock;
+
+ switch (be32_to_cpu(sb->s_header.h_blocktype)) {
+ case JBD2_SUPERBLOCK_V2:
+ return 0;
+ case JBD2_SUPERBLOCK_V1:
+ return journal_convert_superblock_v1(journal, sb);
+ default:
+ break;
+ }
+ return -EINVAL;
+}
+
+static int journal_convert_superblock_v1(journal_t *journal,
+ journal_superblock_t *sb)
+{
+ int offset, blocksize;
+ struct buffer_head *bh;
+
+ printk(KERN_WARNING
+ "JBD: Converting superblock from version 1 to 2.\n");
+
+ /* Pre-initialise new fields to zero */
+ offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb);
+ blocksize = be32_to_cpu(sb->s_blocksize);
+ memset(&sb->s_feature_compat, 0, blocksize-offset);
+
+ sb->s_nr_users = cpu_to_be32(1);
+ sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
+ journal->j_format_version = 2;
+
+ bh = journal->j_sb_buffer;
+ BUFFER_TRACE(bh, "marking dirty");
+ mark_buffer_dirty(bh);
+ sync_dirty_buffer(bh);
+ return 0;
+}
+
+
+/**
+ * int jbd2_journal_flush () - Flush journal
+ * @journal: Journal to act on.
+ *
+ * Flush all data for a given journal to disk and empty the journal.
+ * Filesystems can use this when remounting readonly to ensure that
+ * recovery does not need to happen on remount.
+ */
+
+int jbd2_journal_flush(journal_t *journal)
+{
+ int err = 0;
+ transaction_t *transaction = NULL;
+ unsigned long old_tail;
+
+ spin_lock(&journal->j_state_lock);
+
+ /* Force everything buffered to the log... */
+ if (journal->j_running_transaction) {
+ transaction = journal->j_running_transaction;
+ __jbd2_log_start_commit(journal, transaction->t_tid);
+ } else if (journal->j_committing_transaction)
+ transaction = journal->j_committing_transaction;
+
+ /* Wait for the log commit to complete... */
+ if (transaction) {
+ tid_t tid = transaction->t_tid;
+
+ spin_unlock(&journal->j_state_lock);
+ jbd2_log_wait_commit(journal, tid);
+ } else {
+ spin_unlock(&journal->j_state_lock);
+ }
+
+ /* ...and flush everything in the log out to disk. */
+ spin_lock(&journal->j_list_lock);
+ while (!err && journal->j_checkpoint_transactions != NULL) {
+ spin_unlock(&journal->j_list_lock);
+ err = jbd2_log_do_checkpoint(journal);
+ spin_lock(&journal->j_list_lock);
+ }
+ spin_unlock(&journal->j_list_lock);
+ jbd2_cleanup_journal_tail(journal);
+
+ /* Finally, mark the journal as really needing no recovery.
+ * This sets s_start==0 in the underlying superblock, which is
+ * the magic code for a fully-recovered superblock. Any future
+ * commits of data to the journal will restore the current
+ * s_start value. */
+ spin_lock(&journal->j_state_lock);
+ old_tail = journal->j_tail;
+ journal->j_tail = 0;
+ spin_unlock(&journal->j_state_lock);
+ jbd2_journal_update_superblock(journal, 1);
+ spin_lock(&journal->j_state_lock);
+ journal->j_tail = old_tail;
+
+ J_ASSERT(!journal->j_running_transaction);
+ J_ASSERT(!journal->j_committing_transaction);
+ J_ASSERT(!journal->j_checkpoint_transactions);
+ J_ASSERT(journal->j_head == journal->j_tail);
+ J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
+ spin_unlock(&journal->j_state_lock);
+ return err;
+}
+
+/**
+ * int jbd2_journal_wipe() - Wipe journal contents
+ * @journal: Journal to act on.
+ * @write: flag (see below)
+ *
+ * Wipe out all of the contents of a journal, safely. This will produce
+ * a warning if the journal contains any valid recovery information.
+ * Must be called between journal_init_*() and jbd2_journal_load().
+ *
+ * If 'write' is non-zero, then we wipe out the journal on disk; otherwise
+ * we merely suppress recovery.
+ */
+
+int jbd2_journal_wipe(journal_t *journal, int write)
+{
+ journal_superblock_t *sb;
+ int err = 0;
+
+ J_ASSERT (!(journal->j_flags & JBD2_LOADED));
+
+ err = load_superblock(journal);
+ if (err)
+ return err;
+
+ sb = journal->j_superblock;
+
+ if (!journal->j_tail)
+ goto no_recovery;
+
+ printk (KERN_WARNING "JBD: %s recovery information on journal\n",
+ write ? "Clearing" : "Ignoring");
+
+ err = jbd2_journal_skip_recovery(journal);
+ if (write)
+ jbd2_journal_update_superblock(journal, 1);
+
+ no_recovery:
+ return err;
+}
+
+/*
+ * journal_dev_name: format a character string to describe on what
+ * device this journal is present.
+ */
+
+static const char *journal_dev_name(journal_t *journal, char *buffer)
+{
+ struct block_device *bdev;
+
+ if (journal->j_inode)
+ bdev = journal->j_inode->i_sb->s_bdev;
+ else
+ bdev = journal->j_dev;
+
+ return bdevname(bdev, buffer);
+}
+
+/*
+ * Journal abort has very specific semantics, which we describe
+ * for journal abort.
+ *
+ * Two internal function, which provide abort to te jbd layer
+ * itself are here.
+ */
+
+/*
+ * Quick version for internal journal use (doesn't lock the journal).
+ * Aborts hard --- we mark the abort as occurred, but do _nothing_ else,
+ * and don't attempt to make any other journal updates.
+ */
+void __jbd2_journal_abort_hard(journal_t *journal)
+{
+ transaction_t *transaction;
+ char b[BDEVNAME_SIZE];
+
+ if (journal->j_flags & JBD2_ABORT)
+ return;
+
+ printk(KERN_ERR "Aborting journal on device %s.\n",
+ journal_dev_name(journal, b));
+
+ spin_lock(&journal->j_state_lock);
+ journal->j_flags |= JBD2_ABORT;
+ transaction = journal->j_running_transaction;
+ if (transaction)
+ __jbd2_log_start_commit(journal, transaction->t_tid);
+ spin_unlock(&journal->j_state_lock);
+}
+
+/* Soft abort: record the abort error status in the journal superblock,
+ * but don't do any other IO. */
+static void __journal_abort_soft (journal_t *journal, int errno)
+{
+ if (journal->j_flags & JBD2_ABORT)
+ return;
+
+ if (!journal->j_errno)
+ journal->j_errno = errno;
+
+ __jbd2_journal_abort_hard(journal);
+
+ if (errno)
+ jbd2_journal_update_superblock(journal, 1);
+}
+
+/**
+ * void jbd2_journal_abort () - Shutdown the journal immediately.
+ * @journal: the journal to shutdown.
+ * @errno: an error number to record in the journal indicating
+ * the reason for the shutdown.
+ *
+ * Perform a complete, immediate shutdown of the ENTIRE
+ * journal (not of a single transaction). This operation cannot be
+ * undone without closing and reopening the journal.
+ *
+ * The jbd2_journal_abort function is intended to support higher level error
+ * recovery mechanisms such as the ext2/ext3 remount-readonly error
+ * mode.
+ *
+ * Journal abort has very specific semantics. Any existing dirty,
+ * unjournaled buffers in the main filesystem will still be written to
+ * disk by bdflush, but the journaling mechanism will be suspended
+ * immediately and no further transaction commits will be honoured.
+ *
+ * Any dirty, journaled buffers will be written back to disk without
+ * hitting the journal. Atomicity cannot be guaranteed on an aborted
+ * filesystem, but we _do_ attempt to leave as much data as possible
+ * behind for fsck to use for cleanup.
+ *
+ * Any attempt to get a new transaction handle on a journal which is in
+ * ABORT state will just result in an -EROFS error return. A
+ * jbd2_journal_stop on an existing handle will return -EIO if we have
+ * entered abort state during the update.
+ *
+ * Recursive transactions are not disturbed by journal abort until the
+ * final jbd2_journal_stop, which will receive the -EIO error.
+ *
+ * Finally, the jbd2_journal_abort call allows the caller to supply an errno
+ * which will be recorded (if possible) in the journal superblock. This
+ * allows a client to record failure conditions in the middle of a
+ * transaction without having to complete the transaction to record the
+ * failure to disk. ext3_error, for example, now uses this
+ * functionality.
+ *
+ * Errors which originate from within the journaling layer will NOT
+ * supply an errno; a null errno implies that absolutely no further
+ * writes are done to the journal (unless there are any already in
+ * progress).
+ *
+ */
+
+void jbd2_journal_abort(journal_t *journal, int errno)
+{
+ __journal_abort_soft(journal, errno);
+}
+
+/**
+ * int jbd2_journal_errno () - returns the journal's error state.
+ * @journal: journal to examine.
+ *
+ * This is the errno numbet set with jbd2_journal_abort(), the last
+ * time the journal was mounted - if the journal was stopped
+ * without calling abort this will be 0.
+ *
+ * If the journal has been aborted on this mount time -EROFS will
+ * be returned.
+ */
+int jbd2_journal_errno(journal_t *journal)
+{
+ int err;
+
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_flags & JBD2_ABORT)
+ err = -EROFS;
+ else
+ err = journal->j_errno;
+ spin_unlock(&journal->j_state_lock);
+ return err;
+}
+
+/**
+ * int jbd2_journal_clear_err () - clears the journal's error state
+ * @journal: journal to act on.
+ *
+ * An error must be cleared or Acked to take a FS out of readonly
+ * mode.
+ */
+int jbd2_journal_clear_err(journal_t *journal)
+{
+ int err = 0;
+
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_flags & JBD2_ABORT)
+ err = -EROFS;
+ else
+ journal->j_errno = 0;
+ spin_unlock(&journal->j_state_lock);
+ return err;
+}
+
+/**
+ * void jbd2_journal_ack_err() - Ack journal err.
+ * @journal: journal to act on.
+ *
+ * An error must be cleared or Acked to take a FS out of readonly
+ * mode.
+ */
+void jbd2_journal_ack_err(journal_t *journal)
+{
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_errno)
+ journal->j_flags |= JBD2_ACK_ERR;
+ spin_unlock(&journal->j_state_lock);
+}
+
+int jbd2_journal_blocks_per_page(struct inode *inode)
+{
+ return 1 << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+}
+
+/*
+ * helper functions to deal with 32 or 64bit block numbers.
+ */
+size_t journal_tag_bytes(journal_t *journal)
+{
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
+ return JBD_TAG_SIZE64;
+ else
+ return JBD_TAG_SIZE32;
+}
+
+/*
+ * Simple support for retrying memory allocations. Introduced to help to
+ * debug different VM deadlock avoidance strategies.
+ */
+void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry)
+{
+ return kmalloc(size, flags | (retry ? __GFP_NOFAIL : 0));
+}
+
+/*
+ * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed
+ * and allocate frozen and commit buffers from these slabs.
+ *
+ * Reason for doing this is to avoid, SLAB_DEBUG - since it could
+ * cause bh to cross page boundary.
+ */
+
+#define JBD_MAX_SLABS 5
+#define JBD_SLAB_INDEX(size) (size >> 11)
+
+static kmem_cache_t *jbd_slab[JBD_MAX_SLABS];
+static const char *jbd_slab_names[JBD_MAX_SLABS] = {
+ "jbd2_1k", "jbd2_2k", "jbd2_4k", NULL, "jbd2_8k"
+};
+
+static void jbd2_journal_destroy_jbd_slabs(void)
+{
+ int i;
+
+ for (i = 0; i < JBD_MAX_SLABS; i++) {
+ if (jbd_slab[i])
+ kmem_cache_destroy(jbd_slab[i]);
+ jbd_slab[i] = NULL;
+ }
+}
+
+static int jbd2_journal_create_jbd_slab(size_t slab_size)
+{
+ int i = JBD_SLAB_INDEX(slab_size);
+
+ BUG_ON(i >= JBD_MAX_SLABS);
+
+ /*
+ * Check if we already have a slab created for this size
+ */
+ if (jbd_slab[i])
+ return 0;
+
+ /*
+ * Create a slab and force alignment to be same as slabsize -
+ * this will make sure that allocations won't cross the page
+ * boundary.
+ */
+ jbd_slab[i] = kmem_cache_create(jbd_slab_names[i],
+ slab_size, slab_size, 0, NULL, NULL);
+ if (!jbd_slab[i]) {
+ printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n");
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+void * jbd2_slab_alloc(size_t size, gfp_t flags)
+{
+ int idx;
+
+ idx = JBD_SLAB_INDEX(size);
+ BUG_ON(jbd_slab[idx] == NULL);
+ return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL);
+}
+
+void jbd2_slab_free(void *ptr, size_t size)
+{
+ int idx;
+
+ idx = JBD_SLAB_INDEX(size);
+ BUG_ON(jbd_slab[idx] == NULL);
+ kmem_cache_free(jbd_slab[idx], ptr);
+}
+
+/*
+ * Journal_head storage management
+ */
+static kmem_cache_t *jbd2_journal_head_cache;
+#ifdef CONFIG_JBD_DEBUG
+static atomic_t nr_journal_heads = ATOMIC_INIT(0);
+#endif
+
+static int journal_init_jbd2_journal_head_cache(void)
+{
+ int retval;
+
+ J_ASSERT(jbd2_journal_head_cache == 0);
+ jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
+ sizeof(struct journal_head),
+ 0, /* offset */
+ 0, /* flags */
+ NULL, /* ctor */
+ NULL); /* dtor */
+ retval = 0;
+ if (jbd2_journal_head_cache == 0) {
+ retval = -ENOMEM;
+ printk(KERN_EMERG "JBD: no memory for journal_head cache\n");
+ }
+ return retval;
+}
+
+static void jbd2_journal_destroy_jbd2_journal_head_cache(void)
+{
+ J_ASSERT(jbd2_journal_head_cache != NULL);
+ kmem_cache_destroy(jbd2_journal_head_cache);
+ jbd2_journal_head_cache = NULL;
+}
+
+/*
+ * journal_head splicing and dicing
+ */
+static struct journal_head *journal_alloc_journal_head(void)
+{
+ struct journal_head *ret;
+ static unsigned long last_warning;
+
+#ifdef CONFIG_JBD_DEBUG
+ atomic_inc(&nr_journal_heads);
+#endif
+ ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
+ if (ret == 0) {
+ jbd_debug(1, "out of memory for journal_head\n");
+ if (time_after(jiffies, last_warning + 5*HZ)) {
+ printk(KERN_NOTICE "ENOMEM in %s, retrying.\n",
+ __FUNCTION__);
+ last_warning = jiffies;
+ }
+ while (ret == 0) {
+ yield();
+ ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
+ }
+ }
+ return ret;
+}
+
+static void journal_free_journal_head(struct journal_head *jh)
+{
+#ifdef CONFIG_JBD_DEBUG
+ atomic_dec(&nr_journal_heads);
+ memset(jh, JBD_POISON_FREE, sizeof(*jh));
+#endif
+ kmem_cache_free(jbd2_journal_head_cache, jh);
+}
+
+/*
+ * A journal_head is attached to a buffer_head whenever JBD has an
+ * interest in the buffer.
+ *
+ * Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit
+ * is set. This bit is tested in core kernel code where we need to take
+ * JBD-specific actions. Testing the zeroness of ->b_private is not reliable
+ * there.
+ *
+ * When a buffer has its BH_JBD bit set, its ->b_count is elevated by one.
+ *
+ * When a buffer has its BH_JBD bit set it is immune from being released by
+ * core kernel code, mainly via ->b_count.
+ *
+ * A journal_head may be detached from its buffer_head when the journal_head's
+ * b_transaction, b_cp_transaction and b_next_transaction pointers are NULL.
+ * Various places in JBD call jbd2_journal_remove_journal_head() to indicate that the
+ * journal_head can be dropped if needed.
+ *
+ * Various places in the kernel want to attach a journal_head to a buffer_head
+ * _before_ attaching the journal_head to a transaction. To protect the
+ * journal_head in this situation, jbd2_journal_add_journal_head elevates the
+ * journal_head's b_jcount refcount by one. The caller must call
+ * jbd2_journal_put_journal_head() to undo this.
+ *
+ * So the typical usage would be:
+ *
+ * (Attach a journal_head if needed. Increments b_jcount)
+ * struct journal_head *jh = jbd2_journal_add_journal_head(bh);
+ * ...
+ * jh->b_transaction = xxx;
+ * jbd2_journal_put_journal_head(jh);
+ *
+ * Now, the journal_head's b_jcount is zero, but it is safe from being released
+ * because it has a non-zero b_transaction.
+ */
+
+/*
+ * Give a buffer_head a journal_head.
+ *
+ * Doesn't need the journal lock.
+ * May sleep.
+ */
+struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh)
+{
+ struct journal_head *jh;
+ struct journal_head *new_jh = NULL;
+
+repeat:
+ if (!buffer_jbd(bh)) {
+ new_jh = journal_alloc_journal_head();
+ memset(new_jh, 0, sizeof(*new_jh));
+ }
+
+ jbd_lock_bh_journal_head(bh);
+ if (buffer_jbd(bh)) {
+ jh = bh2jh(bh);
+ } else {
+ J_ASSERT_BH(bh,
+ (atomic_read(&bh->b_count) > 0) ||
+ (bh->b_page && bh->b_page->mapping));
+
+ if (!new_jh) {
+ jbd_unlock_bh_journal_head(bh);
+ goto repeat;
+ }
+
+ jh = new_jh;
+ new_jh = NULL; /* We consumed it */
+ set_buffer_jbd(bh);
+ bh->b_private = jh;
+ jh->b_bh = bh;
+ get_bh(bh);
+ BUFFER_TRACE(bh, "added journal_head");
+ }
+ jh->b_jcount++;
+ jbd_unlock_bh_journal_head(bh);
+ if (new_jh)
+ journal_free_journal_head(new_jh);
+ return bh->b_private;
+}
+
+/*
+ * Grab a ref against this buffer_head's journal_head. If it ended up not
+ * having a journal_head, return NULL
+ */
+struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh)
+{
+ struct journal_head *jh = NULL;
+
+ jbd_lock_bh_journal_head(bh);
+ if (buffer_jbd(bh)) {
+ jh = bh2jh(bh);
+ jh->b_jcount++;
+ }
+ jbd_unlock_bh_journal_head(bh);
+ return jh;
+}
+
+static void __journal_remove_journal_head(struct buffer_head *bh)
+{
+ struct journal_head *jh = bh2jh(bh);
+
+ J_ASSERT_JH(jh, jh->b_jcount >= 0);
+
+ get_bh(bh);
+ if (jh->b_jcount == 0) {
+ if (jh->b_transaction == NULL &&
+ jh->b_next_transaction == NULL &&
+ jh->b_cp_transaction == NULL) {
+ J_ASSERT_JH(jh, jh->b_jlist == BJ_None);
+ J_ASSERT_BH(bh, buffer_jbd(bh));
+ J_ASSERT_BH(bh, jh2bh(jh) == bh);
+ BUFFER_TRACE(bh, "remove journal_head");
+ if (jh->b_frozen_data) {
+ printk(KERN_WARNING "%s: freeing "
+ "b_frozen_data\n",
+ __FUNCTION__);
+ jbd2_slab_free(jh->b_frozen_data, bh->b_size);
+ }
+ if (jh->b_committed_data) {
+ printk(KERN_WARNING "%s: freeing "
+ "b_committed_data\n",
+ __FUNCTION__);
+ jbd2_slab_free(jh->b_committed_data, bh->b_size);
+ }
+ bh->b_private = NULL;
+ jh->b_bh = NULL; /* debug, really */
+ clear_buffer_jbd(bh);
+ __brelse(bh);
+ journal_free_journal_head(jh);
+ } else {
+ BUFFER_TRACE(bh, "journal_head was locked");
+ }
+ }
+}
+
+/*
+ * jbd2_journal_remove_journal_head(): if the buffer isn't attached to a transaction
+ * and has a zero b_jcount then remove and release its journal_head. If we did
+ * see that the buffer is not used by any transaction we also "logically"
+ * decrement ->b_count.
+ *
+ * We in fact take an additional increment on ->b_count as a convenience,
+ * because the caller usually wants to do additional things with the bh
+ * after calling here.
+ * The caller of jbd2_journal_remove_journal_head() *must* run __brelse(bh) at some
+ * time. Once the caller has run __brelse(), the buffer is eligible for
+ * reaping by try_to_free_buffers().
+ */
+void jbd2_journal_remove_journal_head(struct buffer_head *bh)
+{
+ jbd_lock_bh_journal_head(bh);
+ __journal_remove_journal_head(bh);
+ jbd_unlock_bh_journal_head(bh);
+}
+
+/*
+ * Drop a reference on the passed journal_head. If it fell to zero then try to
+ * release the journal_head from the buffer_head.
+ */
+void jbd2_journal_put_journal_head(struct journal_head *jh)
+{
+ struct buffer_head *bh = jh2bh(jh);
+
+ jbd_lock_bh_journal_head(bh);
+ J_ASSERT_JH(jh, jh->b_jcount > 0);
+ --jh->b_jcount;
+ if (!jh->b_jcount && !jh->b_transaction) {
+ __journal_remove_journal_head(bh);
+ __brelse(bh);
+ }
+ jbd_unlock_bh_journal_head(bh);
+}
+
+/*
+ * /proc tunables
+ */
+#if defined(CONFIG_JBD_DEBUG)
+int jbd2_journal_enable_debug;
+EXPORT_SYMBOL(jbd2_journal_enable_debug);
+#endif
+
+#if defined(CONFIG_JBD_DEBUG) && defined(CONFIG_PROC_FS)
+
+static struct proc_dir_entry *proc_jbd_debug;
+
+static int read_jbd_debug(char *page, char **start, off_t off,
+ int count, int *eof, void *data)
+{
+ int ret;
+
+ ret = sprintf(page + off, "%d\n", jbd2_journal_enable_debug);
+ *eof = 1;
+ return ret;
+}
+
+static int write_jbd_debug(struct file *file, const char __user *buffer,
+ unsigned long count, void *data)
+{
+ char buf[32];
+
+ if (count > ARRAY_SIZE(buf) - 1)
+ count = ARRAY_SIZE(buf) - 1;
+ if (copy_from_user(buf, buffer, count))
+ return -EFAULT;
+ buf[ARRAY_SIZE(buf) - 1] = '\0';
+ jbd2_journal_enable_debug = simple_strtoul(buf, NULL, 10);
+ return count;
+}
+
+#define JBD_PROC_NAME "sys/fs/jbd2-debug"
+
+static void __init create_jbd_proc_entry(void)
+{
+ proc_jbd_debug = create_proc_entry(JBD_PROC_NAME, 0644, NULL);
+ if (proc_jbd_debug) {
+ /* Why is this so hard? */
+ proc_jbd_debug->read_proc = read_jbd_debug;
+ proc_jbd_debug->write_proc = write_jbd_debug;
+ }
+}
+
+static void __exit jbd2_remove_jbd_proc_entry(void)
+{
+ if (proc_jbd_debug)
+ remove_proc_entry(JBD_PROC_NAME, NULL);
+}
+
+#else
+
+#define create_jbd_proc_entry() do {} while (0)
+#define jbd2_remove_jbd_proc_entry() do {} while (0)
+
+#endif
+
+kmem_cache_t *jbd2_handle_cache;
+
+static int __init journal_init_handle_cache(void)
+{
+ jbd2_handle_cache = kmem_cache_create("jbd2_journal_handle",
+ sizeof(handle_t),
+ 0, /* offset */
+ 0, /* flags */
+ NULL, /* ctor */
+ NULL); /* dtor */
+ if (jbd2_handle_cache == NULL) {
+ printk(KERN_EMERG "JBD: failed to create handle cache\n");
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static void jbd2_journal_destroy_handle_cache(void)
+{
+ if (jbd2_handle_cache)
+ kmem_cache_destroy(jbd2_handle_cache);
+}
+
+/*
+ * Module startup and shutdown
+ */
+
+static int __init journal_init_caches(void)
+{
+ int ret;
+
+ ret = jbd2_journal_init_revoke_caches();
+ if (ret == 0)
+ ret = journal_init_jbd2_journal_head_cache();
+ if (ret == 0)
+ ret = journal_init_handle_cache();
+ return ret;
+}
+
+static void jbd2_journal_destroy_caches(void)
+{
+ jbd2_journal_destroy_revoke_caches();
+ jbd2_journal_destroy_jbd2_journal_head_cache();
+ jbd2_journal_destroy_handle_cache();
+ jbd2_journal_destroy_jbd_slabs();
+}
+
+static int __init journal_init(void)
+{
+ int ret;
+
+ BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024);
+
+ ret = journal_init_caches();
+ if (ret != 0)
+ jbd2_journal_destroy_caches();
+ create_jbd_proc_entry();
+ return ret;
+}
+
+static void __exit journal_exit(void)
+{
+#ifdef CONFIG_JBD_DEBUG
+ int n = atomic_read(&nr_journal_heads);
+ if (n)
+ printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n);
+#endif
+ jbd2_remove_jbd_proc_entry();
+ jbd2_journal_destroy_caches();
+}
+
+MODULE_LICENSE("GPL");
+module_init(journal_init);
+module_exit(journal_exit);
+
--- /dev/null
+/*
+ * linux/fs/recovery.c
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
+ *
+ * Copyright 1999-2000 Red Hat Software --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Journal recovery routines for the generic filesystem journaling code;
+ * part of the ext2fs journaling system.
+ */
+
+#ifndef __KERNEL__
+#include "jfs_user.h"
+#else
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#endif
+
+/*
+ * Maintain information about the progress of the recovery job, so that
+ * the different passes can carry information between them.
+ */
+struct recovery_info
+{
+ tid_t start_transaction;
+ tid_t end_transaction;
+
+ int nr_replays;
+ int nr_revokes;
+ int nr_revoke_hits;
+};
+
+enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
+static int do_one_pass(journal_t *journal,
+ struct recovery_info *info, enum passtype pass);
+static int scan_revoke_records(journal_t *, struct buffer_head *,
+ tid_t, struct recovery_info *);
+
+#ifdef __KERNEL__
+
+/* Release readahead buffers after use */
+static void journal_brelse_array(struct buffer_head *b[], int n)
+{
+ while (--n >= 0)
+ brelse (b[n]);
+}
+
+
+/*
+ * When reading from the journal, we are going through the block device
+ * layer directly and so there is no readahead being done for us. We
+ * need to implement any readahead ourselves if we want it to happen at
+ * all. Recovery is basically one long sequential read, so make sure we
+ * do the IO in reasonably large chunks.
+ *
+ * This is not so critical that we need to be enormously clever about
+ * the readahead size, though. 128K is a purely arbitrary, good-enough
+ * fixed value.
+ */
+
+#define MAXBUF 8
+static int do_readahead(journal_t *journal, unsigned int start)
+{
+ int err;
+ unsigned int max, nbufs, next;
+ unsigned long long blocknr;
+ struct buffer_head *bh;
+
+ struct buffer_head * bufs[MAXBUF];
+
+ /* Do up to 128K of readahead */
+ max = start + (128 * 1024 / journal->j_blocksize);
+ if (max > journal->j_maxlen)
+ max = journal->j_maxlen;
+
+ /* Do the readahead itself. We'll submit MAXBUF buffer_heads at
+ * a time to the block device IO layer. */
+
+ nbufs = 0;
+
+ for (next = start; next < max; next++) {
+ err = jbd2_journal_bmap(journal, next, &blocknr);
+
+ if (err) {
+ printk (KERN_ERR "JBD: bad block at offset %u\n",
+ next);
+ goto failed;
+ }
+
+ bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ if (!bh) {
+ err = -ENOMEM;
+ goto failed;
+ }
+
+ if (!buffer_uptodate(bh) && !buffer_locked(bh)) {
+ bufs[nbufs++] = bh;
+ if (nbufs == MAXBUF) {
+ ll_rw_block(READ, nbufs, bufs);
+ journal_brelse_array(bufs, nbufs);
+ nbufs = 0;
+ }
+ } else
+ brelse(bh);
+ }
+
+ if (nbufs)
+ ll_rw_block(READ, nbufs, bufs);
+ err = 0;
+
+failed:
+ if (nbufs)
+ journal_brelse_array(bufs, nbufs);
+ return err;
+}
+
+#endif /* __KERNEL__ */
+
+
+/*
+ * Read a block from the journal
+ */
+
+static int jread(struct buffer_head **bhp, journal_t *journal,
+ unsigned int offset)
+{
+ int err;
+ unsigned long long blocknr;
+ struct buffer_head *bh;
+
+ *bhp = NULL;
+
+ if (offset >= journal->j_maxlen) {
+ printk(KERN_ERR "JBD: corrupted journal superblock\n");
+ return -EIO;
+ }
+
+ err = jbd2_journal_bmap(journal, offset, &blocknr);
+
+ if (err) {
+ printk (KERN_ERR "JBD: bad block at offset %u\n",
+ offset);
+ return err;
+ }
+
+ bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+ if (!bh)
+ return -ENOMEM;
+
+ if (!buffer_uptodate(bh)) {
+ /* If this is a brand new buffer, start readahead.
+ Otherwise, we assume we are already reading it. */
+ if (!buffer_req(bh))
+ do_readahead(journal, offset);
+ wait_on_buffer(bh);
+ }
+
+ if (!buffer_uptodate(bh)) {
+ printk (KERN_ERR "JBD: Failed to read block at offset %u\n",
+ offset);
+ brelse(bh);
+ return -EIO;
+ }
+
+ *bhp = bh;
+ return 0;
+}
+
+
+/*
+ * Count the number of in-use tags in a journal descriptor block.
+ */
+
+static int count_tags(journal_t *journal, struct buffer_head *bh)
+{
+ char * tagp;
+ journal_block_tag_t * tag;
+ int nr = 0, size = journal->j_blocksize;
+ int tag_bytes = journal_tag_bytes(journal);
+
+ tagp = &bh->b_data[sizeof(journal_header_t)];
+
+ while ((tagp - bh->b_data + tag_bytes) <= size) {
+ tag = (journal_block_tag_t *) tagp;
+
+ nr++;
+ tagp += tag_bytes;
+ if (!(tag->t_flags & cpu_to_be32(JBD2_FLAG_SAME_UUID)))
+ tagp += 16;
+
+ if (tag->t_flags & cpu_to_be32(JBD2_FLAG_LAST_TAG))
+ break;
+ }
+
+ return nr;
+}
+
+
+/* Make sure we wrap around the log correctly! */
+#define wrap(journal, var) \
+do { \
+ if (var >= (journal)->j_last) \
+ var -= ((journal)->j_last - (journal)->j_first); \
+} while (0)
+
+/**
+ * jbd2_journal_recover - recovers a on-disk journal
+ * @journal: the journal to recover
+ *
+ * The primary function for recovering the log contents when mounting a
+ * journaled device.
+ *
+ * Recovery is done in three passes. In the first pass, we look for the
+ * end of the log. In the second, we assemble the list of revoke
+ * blocks. In the third and final pass, we replay any un-revoked blocks
+ * in the log.
+ */
+int jbd2_journal_recover(journal_t *journal)
+{
+ int err;
+ journal_superblock_t * sb;
+
+ struct recovery_info info;
+
+ memset(&info, 0, sizeof(info));
+ sb = journal->j_superblock;
+
+ /*
+ * The journal superblock's s_start field (the current log head)
+ * is always zero if, and only if, the journal was cleanly
+ * unmounted.
+ */
+
+ if (!sb->s_start) {
+ jbd_debug(1, "No recovery required, last transaction %d\n",
+ be32_to_cpu(sb->s_sequence));
+ journal->j_transaction_sequence = be32_to_cpu(sb->s_sequence) + 1;
+ return 0;
+ }
+
+ err = do_one_pass(journal, &info, PASS_SCAN);
+ if (!err)
+ err = do_one_pass(journal, &info, PASS_REVOKE);
+ if (!err)
+ err = do_one_pass(journal, &info, PASS_REPLAY);
+
+ jbd_debug(0, "JBD: recovery, exit status %d, "
+ "recovered transactions %u to %u\n",
+ err, info.start_transaction, info.end_transaction);
+ jbd_debug(0, "JBD: Replayed %d and revoked %d/%d blocks\n",
+ info.nr_replays, info.nr_revoke_hits, info.nr_revokes);
+
+ /* Restart the log at the next transaction ID, thus invalidating
+ * any existing commit records in the log. */
+ journal->j_transaction_sequence = ++info.end_transaction;
+
+ jbd2_journal_clear_revoke(journal);
+ sync_blockdev(journal->j_fs_dev);
+ return err;
+}
+
+/**
+ * jbd2_journal_skip_recovery - Start journal and wipe exiting records
+ * @journal: journal to startup
+ *
+ * Locate any valid recovery information from the journal and set up the
+ * journal structures in memory to ignore it (presumably because the
+ * caller has evidence that it is out of date).
+ * This function does'nt appear to be exorted..
+ *
+ * We perform one pass over the journal to allow us to tell the user how
+ * much recovery information is being erased, and to let us initialise
+ * the journal transaction sequence numbers to the next unused ID.
+ */
+int jbd2_journal_skip_recovery(journal_t *journal)
+{
+ int err;
+ journal_superblock_t * sb;
+
+ struct recovery_info info;
+
+ memset (&info, 0, sizeof(info));
+ sb = journal->j_superblock;
+
+ err = do_one_pass(journal, &info, PASS_SCAN);
+
+ if (err) {
+ printk(KERN_ERR "JBD: error %d scanning journal\n", err);
+ ++journal->j_transaction_sequence;
+ } else {
+#ifdef CONFIG_JBD_DEBUG
+ int dropped = info.end_transaction - be32_to_cpu(sb->s_sequence);
+#endif
+ jbd_debug(0,
+ "JBD: ignoring %d transaction%s from the journal.\n",
+ dropped, (dropped == 1) ? "" : "s");
+ journal->j_transaction_sequence = ++info.end_transaction;
+ }
+
+ journal->j_tail = 0;
+ return err;
+}
+
+static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag)
+{
+ unsigned long long block = be32_to_cpu(tag->t_blocknr);
+ if (tag_bytes > JBD_TAG_SIZE32)
+ block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32;
+ return block;
+}
+
+static int do_one_pass(journal_t *journal,
+ struct recovery_info *info, enum passtype pass)
+{
+ unsigned int first_commit_ID, next_commit_ID;
+ unsigned long next_log_block;
+ int err, success = 0;
+ journal_superblock_t * sb;
+ journal_header_t * tmp;
+ struct buffer_head * bh;
+ unsigned int sequence;
+ int blocktype;
+ int tag_bytes = journal_tag_bytes(journal);
+
+ /* Precompute the maximum metadata descriptors in a descriptor block */
+ int MAX_BLOCKS_PER_DESC;
+ MAX_BLOCKS_PER_DESC = ((journal->j_blocksize-sizeof(journal_header_t))
+ / tag_bytes);
+
+ /*
+ * First thing is to establish what we expect to find in the log
+ * (in terms of transaction IDs), and where (in terms of log
+ * block offsets): query the superblock.
+ */
+
+ sb = journal->j_superblock;
+ next_commit_ID = be32_to_cpu(sb->s_sequence);
+ next_log_block = be32_to_cpu(sb->s_start);
+
+ first_commit_ID = next_commit_ID;
+ if (pass == PASS_SCAN)
+ info->start_transaction = first_commit_ID;
+
+ jbd_debug(1, "Starting recovery pass %d\n", pass);
+
+ /*
+ * Now we walk through the log, transaction by transaction,
+ * making sure that each transaction has a commit block in the
+ * expected place. Each complete transaction gets replayed back
+ * into the main filesystem.
+ */
+
+ while (1) {
+ int flags;
+ char * tagp;
+ journal_block_tag_t * tag;
+ struct buffer_head * obh;
+ struct buffer_head * nbh;
+
+ cond_resched(); /* We're under lock_kernel() */
+
+ /* If we already know where to stop the log traversal,
+ * check right now that we haven't gone past the end of
+ * the log. */
+
+ if (pass != PASS_SCAN)
+ if (tid_geq(next_commit_ID, info->end_transaction))
+ break;
+
+ jbd_debug(2, "Scanning for sequence ID %u at %lu/%lu\n",
+ next_commit_ID, next_log_block, journal->j_last);
+
+ /* Skip over each chunk of the transaction looking
+ * either the next descriptor block or the final commit
+ * record. */
+
+ jbd_debug(3, "JBD: checking block %ld\n", next_log_block);
+ err = jread(&bh, journal, next_log_block);
+ if (err)
+ goto failed;
+
+ next_log_block++;
+ wrap(journal, next_log_block);
+
+ /* What kind of buffer is it?
+ *
+ * If it is a descriptor block, check that it has the
+ * expected sequence number. Otherwise, we're all done
+ * here. */
+
+ tmp = (journal_header_t *)bh->b_data;
+
+ if (tmp->h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER)) {
+ brelse(bh);
+ break;
+ }
+
+ blocktype = be32_to_cpu(tmp->h_blocktype);
+ sequence = be32_to_cpu(tmp->h_sequence);
+ jbd_debug(3, "Found magic %d, sequence %d\n",
+ blocktype, sequence);
+
+ if (sequence != next_commit_ID) {
+ brelse(bh);
+ break;
+ }
+
+ /* OK, we have a valid descriptor block which matches
+ * all of the sequence number checks. What are we going
+ * to do with it? That depends on the pass... */
+
+ switch(blocktype) {
+ case JBD2_DESCRIPTOR_BLOCK:
+ /* If it is a valid descriptor block, replay it
+ * in pass REPLAY; otherwise, just skip over the
+ * blocks it describes. */
+ if (pass != PASS_REPLAY) {
+ next_log_block += count_tags(journal, bh);
+ wrap(journal, next_log_block);
+ brelse(bh);
+ continue;
+ }
+
+ /* A descriptor block: we can now write all of
+ * the data blocks. Yay, useful work is finally
+ * getting done here! */
+
+ tagp = &bh->b_data[sizeof(journal_header_t)];
+ while ((tagp - bh->b_data + tag_bytes)
+ <= journal->j_blocksize) {
+ unsigned long io_block;
+
+ tag = (journal_block_tag_t *) tagp;
+ flags = be32_to_cpu(tag->t_flags);
+
+ io_block = next_log_block++;
+ wrap(journal, next_log_block);
+ err = jread(&obh, journal, io_block);
+ if (err) {
+ /* Recover what we can, but
+ * report failure at the end. */
+ success = err;
+ printk (KERN_ERR
+ "JBD: IO error %d recovering "
+ "block %ld in log\n",
+ err, io_block);
+ } else {
+ unsigned long long blocknr;
+
+ J_ASSERT(obh != NULL);
+ blocknr = read_tag_block(tag_bytes,
+ tag);
+
+ /* If the block has been
+ * revoked, then we're all done
+ * here. */
+ if (jbd2_journal_test_revoke
+ (journal, blocknr,
+ next_commit_ID)) {
+ brelse(obh);
+ ++info->nr_revoke_hits;
+ goto skip_write;
+ }
+
+ /* Find a buffer for the new
+ * data being restored */
+ nbh = __getblk(journal->j_fs_dev,
+ blocknr,
+ journal->j_blocksize);
+ if (nbh == NULL) {
+ printk(KERN_ERR
+ "JBD: Out of memory "
+ "during recovery.\n");
+ err = -ENOMEM;
+ brelse(bh);
+ brelse(obh);
+ goto failed;
+ }
+
+ lock_buffer(nbh);
+ memcpy(nbh->b_data, obh->b_data,
+ journal->j_blocksize);
+ if (flags & JBD2_FLAG_ESCAPE) {
+ *((__be32 *)bh->b_data) =
+ cpu_to_be32(JBD2_MAGIC_NUMBER);
+ }
+
+ BUFFER_TRACE(nbh, "marking dirty");
+ set_buffer_uptodate(nbh);
+ mark_buffer_dirty(nbh);
+ BUFFER_TRACE(nbh, "marking uptodate");
+ ++info->nr_replays;
+ /* ll_rw_block(WRITE, 1, &nbh); */
+ unlock_buffer(nbh);
+ brelse(obh);
+ brelse(nbh);
+ }
+
+ skip_write:
+ tagp += tag_bytes;
+ if (!(flags & JBD2_FLAG_SAME_UUID))
+ tagp += 16;
+
+ if (flags & JBD2_FLAG_LAST_TAG)
+ break;
+ }
+
+ brelse(bh);
+ continue;
+
+ case JBD2_COMMIT_BLOCK:
+ /* Found an expected commit block: not much to
+ * do other than move on to the next sequence
+ * number. */
+ brelse(bh);
+ next_commit_ID++;
+ continue;
+
+ case JBD2_REVOKE_BLOCK:
+ /* If we aren't in the REVOKE pass, then we can
+ * just skip over this block. */
+ if (pass != PASS_REVOKE) {
+ brelse(bh);
+ continue;
+ }
+
+ err = scan_revoke_records(journal, bh,
+ next_commit_ID, info);
+ brelse(bh);
+ if (err)
+ goto failed;
+ continue;
+
+ default:
+ jbd_debug(3, "Unrecognised magic %d, end of scan.\n",
+ blocktype);
+ brelse(bh);
+ goto done;
+ }
+ }
+
+ done:
+ /*
+ * We broke out of the log scan loop: either we came to the
+ * known end of the log or we found an unexpected block in the
+ * log. If the latter happened, then we know that the "current"
+ * transaction marks the end of the valid log.
+ */
+
+ if (pass == PASS_SCAN)
+ info->end_transaction = next_commit_ID;
+ else {
+ /* It's really bad news if different passes end up at
+ * different places (but possible due to IO errors). */
+ if (info->end_transaction != next_commit_ID) {
+ printk (KERN_ERR "JBD: recovery pass %d ended at "
+ "transaction %u, expected %u\n",
+ pass, next_commit_ID, info->end_transaction);
+ if (!success)
+ success = -EIO;
+ }
+ }
+
+ return success;
+
+ failed:
+ return err;
+}
+
+
+/* Scan a revoke record, marking all blocks mentioned as revoked. */
+
+static int scan_revoke_records(journal_t *journal, struct buffer_head *bh,
+ tid_t sequence, struct recovery_info *info)
+{
+ jbd2_journal_revoke_header_t *header;
+ int offset, max;
+ int record_len = 4;
+
+ header = (jbd2_journal_revoke_header_t *) bh->b_data;
+ offset = sizeof(jbd2_journal_revoke_header_t);
+ max = be32_to_cpu(header->r_count);
+
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
+ record_len = 8;
+
+ while (offset + record_len <= max) {
+ unsigned long long blocknr;
+ int err;
+
+ if (record_len == 4)
+ blocknr = be32_to_cpu(* ((__be32 *) (bh->b_data+offset)));
+ else
+ blocknr = be64_to_cpu(* ((__be64 *) (bh->b_data+offset)));
+ offset += record_len;
+ err = jbd2_journal_set_revoke(journal, blocknr, sequence);
+ if (err)
+ return err;
+ ++info->nr_revokes;
+ }
+ return 0;
+}
--- /dev/null
+/*
+ * linux/fs/revoke.c
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 2000
+ *
+ * Copyright 2000 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Journal revoke routines for the generic filesystem journaling code;
+ * part of the ext2fs journaling system.
+ *
+ * Revoke is the mechanism used to prevent old log records for deleted
+ * metadata from being replayed on top of newer data using the same
+ * blocks. The revoke mechanism is used in two separate places:
+ *
+ * + Commit: during commit we write the entire list of the current
+ * transaction's revoked blocks to the journal
+ *
+ * + Recovery: during recovery we record the transaction ID of all
+ * revoked blocks. If there are multiple revoke records in the log
+ * for a single block, only the last one counts, and if there is a log
+ * entry for a block beyond the last revoke, then that log entry still
+ * gets replayed.
+ *
+ * We can get interactions between revokes and new log data within a
+ * single transaction:
+ *
+ * Block is revoked and then journaled:
+ * The desired end result is the journaling of the new block, so we
+ * cancel the revoke before the transaction commits.
+ *
+ * Block is journaled and then revoked:
+ * The revoke must take precedence over the write of the block, so we
+ * need either to cancel the journal entry or to write the revoke
+ * later in the log than the log block. In this case, we choose the
+ * latter: journaling a block cancels any revoke record for that block
+ * in the current transaction, so any revoke for that block in the
+ * transaction must have happened after the block was journaled and so
+ * the revoke must take precedence.
+ *
+ * Block is revoked and then written as data:
+ * The data write is allowed to succeed, but the revoke is _not_
+ * cancelled. We still need to prevent old log records from
+ * overwriting the new data. We don't even need to clear the revoke
+ * bit here.
+ *
+ * Revoke information on buffers is a tri-state value:
+ *
+ * RevokeValid clear: no cached revoke status, need to look it up
+ * RevokeValid set, Revoked clear:
+ * buffer has not been revoked, and cancel_revoke
+ * need do nothing.
+ * RevokeValid set, Revoked set:
+ * buffer has been revoked.
+ */
+
+#ifndef __KERNEL__
+#include "jfs_user.h"
+#else
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/smp_lock.h>
+#include <linux/init.h>
+#endif
+
+static kmem_cache_t *jbd2_revoke_record_cache;
+static kmem_cache_t *jbd2_revoke_table_cache;
+
+/* Each revoke record represents one single revoked block. During
+ journal replay, this involves recording the transaction ID of the
+ last transaction to revoke this block. */
+
+struct jbd2_revoke_record_s
+{
+ struct list_head hash;
+ tid_t sequence; /* Used for recovery only */
+ unsigned long long blocknr;
+};
+
+
+/* The revoke table is just a simple hash table of revoke records. */
+struct jbd2_revoke_table_s
+{
+ /* It is conceivable that we might want a larger hash table
+ * for recovery. Must be a power of two. */
+ int hash_size;
+ int hash_shift;
+ struct list_head *hash_table;
+};
+
+
+#ifdef __KERNEL__
+static void write_one_revoke_record(journal_t *, transaction_t *,
+ struct journal_head **, int *,
+ struct jbd2_revoke_record_s *);
+static void flush_descriptor(journal_t *, struct journal_head *, int);
+#endif
+
+/* Utility functions to maintain the revoke table */
+
+/* Borrowed from buffer.c: this is a tried and tested block hash function */
+static inline int hash(journal_t *journal, unsigned long long block)
+{
+ struct jbd2_revoke_table_s *table = journal->j_revoke;
+ int hash_shift = table->hash_shift;
+ int hash = (int)block ^ (int)((block >> 31) >> 1);
+
+ return ((hash << (hash_shift - 6)) ^
+ (hash >> 13) ^
+ (hash << (hash_shift - 12))) & (table->hash_size - 1);
+}
+
+static int insert_revoke_hash(journal_t *journal, unsigned long long blocknr,
+ tid_t seq)
+{
+ struct list_head *hash_list;
+ struct jbd2_revoke_record_s *record;
+
+repeat:
+ record = kmem_cache_alloc(jbd2_revoke_record_cache, GFP_NOFS);
+ if (!record)
+ goto oom;
+
+ record->sequence = seq;
+ record->blocknr = blocknr;
+ hash_list = &journal->j_revoke->hash_table[hash(journal, blocknr)];
+ spin_lock(&journal->j_revoke_lock);
+ list_add(&record->hash, hash_list);
+ spin_unlock(&journal->j_revoke_lock);
+ return 0;
+
+oom:
+ if (!journal_oom_retry)
+ return -ENOMEM;
+ jbd_debug(1, "ENOMEM in %s, retrying\n", __FUNCTION__);
+ yield();
+ goto repeat;
+}
+
+/* Find a revoke record in the journal's hash table. */
+
+static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal,
+ unsigned long long blocknr)
+{
+ struct list_head *hash_list;
+ struct jbd2_revoke_record_s *record;
+
+ hash_list = &journal->j_revoke->hash_table[hash(journal, blocknr)];
+
+ spin_lock(&journal->j_revoke_lock);
+ record = (struct jbd2_revoke_record_s *) hash_list->next;
+ while (&(record->hash) != hash_list) {
+ if (record->blocknr == blocknr) {
+ spin_unlock(&journal->j_revoke_lock);
+ return record;
+ }
+ record = (struct jbd2_revoke_record_s *) record->hash.next;
+ }
+ spin_unlock(&journal->j_revoke_lock);
+ return NULL;
+}
+
+int __init jbd2_journal_init_revoke_caches(void)
+{
+ jbd2_revoke_record_cache = kmem_cache_create("jbd2_revoke_record",
+ sizeof(struct jbd2_revoke_record_s),
+ 0, SLAB_HWCACHE_ALIGN, NULL, NULL);
+ if (jbd2_revoke_record_cache == 0)
+ return -ENOMEM;
+
+ jbd2_revoke_table_cache = kmem_cache_create("jbd2_revoke_table",
+ sizeof(struct jbd2_revoke_table_s),
+ 0, 0, NULL, NULL);
+ if (jbd2_revoke_table_cache == 0) {
+ kmem_cache_destroy(jbd2_revoke_record_cache);
+ jbd2_revoke_record_cache = NULL;
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+void jbd2_journal_destroy_revoke_caches(void)
+{
+ kmem_cache_destroy(jbd2_revoke_record_cache);
+ jbd2_revoke_record_cache = NULL;
+ kmem_cache_destroy(jbd2_revoke_table_cache);
+ jbd2_revoke_table_cache = NULL;
+}
+
+/* Initialise the revoke table for a given journal to a given size. */
+
+int jbd2_journal_init_revoke(journal_t *journal, int hash_size)
+{
+ int shift, tmp;
+
+ J_ASSERT (journal->j_revoke_table[0] == NULL);
+
+ shift = 0;
+ tmp = hash_size;
+ while((tmp >>= 1UL) != 0UL)
+ shift++;
+
+ journal->j_revoke_table[0] = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL);
+ if (!journal->j_revoke_table[0])
+ return -ENOMEM;
+ journal->j_revoke = journal->j_revoke_table[0];
+
+ /* Check that the hash_size is a power of two */
+ J_ASSERT ((hash_size & (hash_size-1)) == 0);
+
+ journal->j_revoke->hash_size = hash_size;
+
+ journal->j_revoke->hash_shift = shift;
+
+ journal->j_revoke->hash_table =
+ kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL);
+ if (!journal->j_revoke->hash_table) {
+ kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]);
+ journal->j_revoke = NULL;
+ return -ENOMEM;
+ }
+
+ for (tmp = 0; tmp < hash_size; tmp++)
+ INIT_LIST_HEAD(&journal->j_revoke->hash_table[tmp]);
+
+ journal->j_revoke_table[1] = kmem_cache_alloc(jbd2_revoke_table_cache, GFP_KERNEL);
+ if (!journal->j_revoke_table[1]) {
+ kfree(journal->j_revoke_table[0]->hash_table);
+ kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]);
+ return -ENOMEM;
+ }
+
+ journal->j_revoke = journal->j_revoke_table[1];
+
+ /* Check that the hash_size is a power of two */
+ J_ASSERT ((hash_size & (hash_size-1)) == 0);
+
+ journal->j_revoke->hash_size = hash_size;
+
+ journal->j_revoke->hash_shift = shift;
+
+ journal->j_revoke->hash_table =
+ kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL);
+ if (!journal->j_revoke->hash_table) {
+ kfree(journal->j_revoke_table[0]->hash_table);
+ kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[0]);
+ kmem_cache_free(jbd2_revoke_table_cache, journal->j_revoke_table[1]);
+ journal->j_revoke = NULL;
+ return -ENOMEM;
+ }
+
+ for (tmp = 0; tmp < hash_size; tmp++)
+ INIT_LIST_HEAD(&journal->j_revoke->hash_table[tmp]);
+
+ spin_lock_init(&journal->j_revoke_lock);
+
+ return 0;
+}
+
+/* Destoy a journal's revoke table. The table must already be empty! */
+
+void jbd2_journal_destroy_revoke(journal_t *journal)
+{
+ struct jbd2_revoke_table_s *table;
+ struct list_head *hash_list;
+ int i;
+
+ table = journal->j_revoke_table[0];
+ if (!table)
+ return;
+
+ for (i=0; i<table->hash_size; i++) {
+ hash_list = &table->hash_table[i];
+ J_ASSERT (list_empty(hash_list));
+ }
+
+ kfree(table->hash_table);
+ kmem_cache_free(jbd2_revoke_table_cache, table);
+ journal->j_revoke = NULL;
+
+ table = journal->j_revoke_table[1];
+ if (!table)
+ return;
+
+ for (i=0; i<table->hash_size; i++) {
+ hash_list = &table->hash_table[i];
+ J_ASSERT (list_empty(hash_list));
+ }
+
+ kfree(table->hash_table);
+ kmem_cache_free(jbd2_revoke_table_cache, table);
+ journal->j_revoke = NULL;
+}
+
+
+#ifdef __KERNEL__
+
+/*
+ * jbd2_journal_revoke: revoke a given buffer_head from the journal. This
+ * prevents the block from being replayed during recovery if we take a
+ * crash after this current transaction commits. Any subsequent
+ * metadata writes of the buffer in this transaction cancel the
+ * revoke.
+ *
+ * Note that this call may block --- it is up to the caller to make
+ * sure that there are no further calls to journal_write_metadata
+ * before the revoke is complete. In ext3, this implies calling the
+ * revoke before clearing the block bitmap when we are deleting
+ * metadata.
+ *
+ * Revoke performs a jbd2_journal_forget on any buffer_head passed in as a
+ * parameter, but does _not_ forget the buffer_head if the bh was only
+ * found implicitly.
+ *
+ * bh_in may not be a journalled buffer - it may have come off
+ * the hash tables without an attached journal_head.
+ *
+ * If bh_in is non-zero, jbd2_journal_revoke() will decrement its b_count
+ * by one.
+ */
+
+int jbd2_journal_revoke(handle_t *handle, unsigned long long blocknr,
+ struct buffer_head *bh_in)
+{
+ struct buffer_head *bh = NULL;
+ journal_t *journal;
+ struct block_device *bdev;
+ int err;
+
+ might_sleep();
+ if (bh_in)
+ BUFFER_TRACE(bh_in, "enter");
+
+ journal = handle->h_transaction->t_journal;
+ if (!jbd2_journal_set_features(journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)){
+ J_ASSERT (!"Cannot set revoke feature!");
+ return -EINVAL;
+ }
+
+ bdev = journal->j_fs_dev;
+ bh = bh_in;
+
+ if (!bh) {
+ bh = __find_get_block(bdev, blocknr, journal->j_blocksize);
+ if (bh)
+ BUFFER_TRACE(bh, "found on hash");
+ }
+#ifdef JBD_EXPENSIVE_CHECKING
+ else {
+ struct buffer_head *bh2;
+
+ /* If there is a different buffer_head lying around in
+ * memory anywhere... */
+ bh2 = __find_get_block(bdev, blocknr, journal->j_blocksize);
+ if (bh2) {
+ /* ... and it has RevokeValid status... */
+ if (bh2 != bh && buffer_revokevalid(bh2))
+ /* ...then it better be revoked too,
+ * since it's illegal to create a revoke
+ * record against a buffer_head which is
+ * not marked revoked --- that would
+ * risk missing a subsequent revoke
+ * cancel. */
+ J_ASSERT_BH(bh2, buffer_revoked(bh2));
+ put_bh(bh2);
+ }
+ }
+#endif
+
+ /* We really ought not ever to revoke twice in a row without
+ first having the revoke cancelled: it's illegal to free a
+ block twice without allocating it in between! */
+ if (bh) {
+ if (!J_EXPECT_BH(bh, !buffer_revoked(bh),
+ "inconsistent data on disk")) {
+ if (!bh_in)
+ brelse(bh);
+ return -EIO;
+ }
+ set_buffer_revoked(bh);
+ set_buffer_revokevalid(bh);
+ if (bh_in) {
+ BUFFER_TRACE(bh_in, "call jbd2_journal_forget");
+ jbd2_journal_forget(handle, bh_in);
+ } else {
+ BUFFER_TRACE(bh, "call brelse");
+ __brelse(bh);
+ }
+ }
+
+ jbd_debug(2, "insert revoke for block %llu, bh_in=%p\n",blocknr, bh_in);
+ err = insert_revoke_hash(journal, blocknr,
+ handle->h_transaction->t_tid);
+ BUFFER_TRACE(bh_in, "exit");
+ return err;
+}
+
+/*
+ * Cancel an outstanding revoke. For use only internally by the
+ * journaling code (called from jbd2_journal_get_write_access).
+ *
+ * We trust buffer_revoked() on the buffer if the buffer is already
+ * being journaled: if there is no revoke pending on the buffer, then we
+ * don't do anything here.
+ *
+ * This would break if it were possible for a buffer to be revoked and
+ * discarded, and then reallocated within the same transaction. In such
+ * a case we would have lost the revoked bit, but when we arrived here
+ * the second time we would still have a pending revoke to cancel. So,
+ * do not trust the Revoked bit on buffers unless RevokeValid is also
+ * set.
+ *
+ * The caller must have the journal locked.
+ */
+int jbd2_journal_cancel_revoke(handle_t *handle, struct journal_head *jh)
+{
+ struct jbd2_revoke_record_s *record;
+ journal_t *journal = handle->h_transaction->t_journal;
+ int need_cancel;
+ int did_revoke = 0; /* akpm: debug */
+ struct buffer_head *bh = jh2bh(jh);
+
+ jbd_debug(4, "journal_head %p, cancelling revoke\n", jh);
+
+ /* Is the existing Revoke bit valid? If so, we trust it, and
+ * only perform the full cancel if the revoke bit is set. If
+ * not, we can't trust the revoke bit, and we need to do the
+ * full search for a revoke record. */
+ if (test_set_buffer_revokevalid(bh)) {
+ need_cancel = test_clear_buffer_revoked(bh);
+ } else {
+ need_cancel = 1;
+ clear_buffer_revoked(bh);
+ }
+
+ if (need_cancel) {
+ record = find_revoke_record(journal, bh->b_blocknr);
+ if (record) {
+ jbd_debug(4, "cancelled existing revoke on "
+ "blocknr %llu\n", (unsigned long long)bh->b_blocknr);
+ spin_lock(&journal->j_revoke_lock);
+ list_del(&record->hash);
+ spin_unlock(&journal->j_revoke_lock);
+ kmem_cache_free(jbd2_revoke_record_cache, record);
+ did_revoke = 1;
+ }
+ }
+
+#ifdef JBD_EXPENSIVE_CHECKING
+ /* There better not be one left behind by now! */
+ record = find_revoke_record(journal, bh->b_blocknr);
+ J_ASSERT_JH(jh, record == NULL);
+#endif
+
+ /* Finally, have we just cleared revoke on an unhashed
+ * buffer_head? If so, we'd better make sure we clear the
+ * revoked status on any hashed alias too, otherwise the revoke
+ * state machine will get very upset later on. */
+ if (need_cancel) {
+ struct buffer_head *bh2;
+ bh2 = __find_get_block(bh->b_bdev, bh->b_blocknr, bh->b_size);
+ if (bh2) {
+ if (bh2 != bh)
+ clear_buffer_revoked(bh2);
+ __brelse(bh2);
+ }
+ }
+ return did_revoke;
+}
+
+/* journal_switch_revoke table select j_revoke for next transaction
+ * we do not want to suspend any processing until all revokes are
+ * written -bzzz
+ */
+void jbd2_journal_switch_revoke_table(journal_t *journal)
+{
+ int i;
+
+ if (journal->j_revoke == journal->j_revoke_table[0])
+ journal->j_revoke = journal->j_revoke_table[1];
+ else
+ journal->j_revoke = journal->j_revoke_table[0];
+
+ for (i = 0; i < journal->j_revoke->hash_size; i++)
+ INIT_LIST_HEAD(&journal->j_revoke->hash_table[i]);
+}
+
+/*
+ * Write revoke records to the journal for all entries in the current
+ * revoke hash, deleting the entries as we go.
+ *
+ * Called with the journal lock held.
+ */
+
+void jbd2_journal_write_revoke_records(journal_t *journal,
+ transaction_t *transaction)
+{
+ struct journal_head *descriptor;
+ struct jbd2_revoke_record_s *record;
+ struct jbd2_revoke_table_s *revoke;
+ struct list_head *hash_list;
+ int i, offset, count;
+
+ descriptor = NULL;
+ offset = 0;
+ count = 0;
+
+ /* select revoke table for committing transaction */
+ revoke = journal->j_revoke == journal->j_revoke_table[0] ?
+ journal->j_revoke_table[1] : journal->j_revoke_table[0];
+
+ for (i = 0; i < revoke->hash_size; i++) {
+ hash_list = &revoke->hash_table[i];
+
+ while (!list_empty(hash_list)) {
+ record = (struct jbd2_revoke_record_s *)
+ hash_list->next;
+ write_one_revoke_record(journal, transaction,
+ &descriptor, &offset,
+ record);
+ count++;
+ list_del(&record->hash);
+ kmem_cache_free(jbd2_revoke_record_cache, record);
+ }
+ }
+ if (descriptor)
+ flush_descriptor(journal, descriptor, offset);
+ jbd_debug(1, "Wrote %d revoke records\n", count);
+}
+
+/*
+ * Write out one revoke record. We need to create a new descriptor
+ * block if the old one is full or if we have not already created one.
+ */
+
+static void write_one_revoke_record(journal_t *journal,
+ transaction_t *transaction,
+ struct journal_head **descriptorp,
+ int *offsetp,
+ struct jbd2_revoke_record_s *record)
+{
+ struct journal_head *descriptor;
+ int offset;
+ journal_header_t *header;
+
+ /* If we are already aborting, this all becomes a noop. We
+ still need to go round the loop in
+ jbd2_journal_write_revoke_records in order to free all of the
+ revoke records: only the IO to the journal is omitted. */
+ if (is_journal_aborted(journal))
+ return;
+
+ descriptor = *descriptorp;
+ offset = *offsetp;
+
+ /* Make sure we have a descriptor with space left for the record */
+ if (descriptor) {
+ if (offset == journal->j_blocksize) {
+ flush_descriptor(journal, descriptor, offset);
+ descriptor = NULL;
+ }
+ }
+
+ if (!descriptor) {
+ descriptor = jbd2_journal_get_descriptor_buffer(journal);
+ if (!descriptor)
+ return;
+ header = (journal_header_t *) &jh2bh(descriptor)->b_data[0];
+ header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER);
+ header->h_blocktype = cpu_to_be32(JBD2_REVOKE_BLOCK);
+ header->h_sequence = cpu_to_be32(transaction->t_tid);
+
+ /* Record it so that we can wait for IO completion later */
+ JBUFFER_TRACE(descriptor, "file as BJ_LogCtl");
+ jbd2_journal_file_buffer(descriptor, transaction, BJ_LogCtl);
+
+ offset = sizeof(jbd2_journal_revoke_header_t);
+ *descriptorp = descriptor;
+ }
+
+ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) {
+ * ((__be64 *)(&jh2bh(descriptor)->b_data[offset])) =
+ cpu_to_be64(record->blocknr);
+ offset += 8;
+
+ } else {
+ * ((__be32 *)(&jh2bh(descriptor)->b_data[offset])) =
+ cpu_to_be32(record->blocknr);
+ offset += 4;
+ }
+
+ *offsetp = offset;
+}
+
+/*
+ * Flush a revoke descriptor out to the journal. If we are aborting,
+ * this is a noop; otherwise we are generating a buffer which needs to
+ * be waited for during commit, so it has to go onto the appropriate
+ * journal buffer list.
+ */
+
+static void flush_descriptor(journal_t *journal,
+ struct journal_head *descriptor,
+ int offset)
+{
+ jbd2_journal_revoke_header_t *header;
+ struct buffer_head *bh = jh2bh(descriptor);
+
+ if (is_journal_aborted(journal)) {
+ put_bh(bh);
+ return;
+ }
+
+ header = (jbd2_journal_revoke_header_t *) jh2bh(descriptor)->b_data;
+ header->r_count = cpu_to_be32(offset);
+ set_buffer_jwrite(bh);
+ BUFFER_TRACE(bh, "write");
+ set_buffer_dirty(bh);
+ ll_rw_block(SWRITE, 1, &bh);
+}
+#endif
+
+/*
+ * Revoke support for recovery.
+ *
+ * Recovery needs to be able to:
+ *
+ * record all revoke records, including the tid of the latest instance
+ * of each revoke in the journal
+ *
+ * check whether a given block in a given transaction should be replayed
+ * (ie. has not been revoked by a revoke record in that or a subsequent
+ * transaction)
+ *
+ * empty the revoke table after recovery.
+ */
+
+/*
+ * First, setting revoke records. We create a new revoke record for
+ * every block ever revoked in the log as we scan it for recovery, and
+ * we update the existing records if we find multiple revokes for a
+ * single block.
+ */
+
+int jbd2_journal_set_revoke(journal_t *journal,
+ unsigned long long blocknr,
+ tid_t sequence)
+{
+ struct jbd2_revoke_record_s *record;
+
+ record = find_revoke_record(journal, blocknr);
+ if (record) {
+ /* If we have multiple occurrences, only record the
+ * latest sequence number in the hashed record */
+ if (tid_gt(sequence, record->sequence))
+ record->sequence = sequence;
+ return 0;
+ }
+ return insert_revoke_hash(journal, blocknr, sequence);
+}
+
+/*
+ * Test revoke records. For a given block referenced in the log, has
+ * that block been revoked? A revoke record with a given transaction
+ * sequence number revokes all blocks in that transaction and earlier
+ * ones, but later transactions still need replayed.
+ */
+
+int jbd2_journal_test_revoke(journal_t *journal,
+ unsigned long long blocknr,
+ tid_t sequence)
+{
+ struct jbd2_revoke_record_s *record;
+
+ record = find_revoke_record(journal, blocknr);
+ if (!record)
+ return 0;
+ if (tid_gt(sequence, record->sequence))
+ return 0;
+ return 1;
+}
+
+/*
+ * Finally, once recovery is over, we need to clear the revoke table so
+ * that it can be reused by the running filesystem.
+ */
+
+void jbd2_journal_clear_revoke(journal_t *journal)
+{
+ int i;
+ struct list_head *hash_list;
+ struct jbd2_revoke_record_s *record;
+ struct jbd2_revoke_table_s *revoke;
+
+ revoke = journal->j_revoke;
+
+ for (i = 0; i < revoke->hash_size; i++) {
+ hash_list = &revoke->hash_table[i];
+ while (!list_empty(hash_list)) {
+ record = (struct jbd2_revoke_record_s*) hash_list->next;
+ list_del(&record->hash);
+ kmem_cache_free(jbd2_revoke_record_cache, record);
+ }
+ }
+}
--- /dev/null
+/*
+ * linux/fs/transaction.c
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
+ *
+ * Copyright 1998 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Generic filesystem transaction handling code; part of the ext2fs
+ * journaling system.
+ *
+ * This file manages transactions (compound commits managed by the
+ * journaling code) and handles (individual atomic operations by the
+ * filesystem).
+ */
+
+#include <linux/time.h>
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+#include <linux/smp_lock.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+
+/*
+ * jbd2_get_transaction: obtain a new transaction_t object.
+ *
+ * Simply allocate and initialise a new transaction. Create it in
+ * RUNNING state and add it to the current journal (which should not
+ * have an existing running transaction: we only make a new transaction
+ * once we have started to commit the old one).
+ *
+ * Preconditions:
+ * The journal MUST be locked. We don't perform atomic mallocs on the
+ * new transaction and we can't block without protecting against other
+ * processes trying to touch the journal while it is in transition.
+ *
+ * Called under j_state_lock
+ */
+
+static transaction_t *
+jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
+{
+ transaction->t_journal = journal;
+ transaction->t_state = T_RUNNING;
+ transaction->t_tid = journal->j_transaction_sequence++;
+ transaction->t_expires = jiffies + journal->j_commit_interval;
+ spin_lock_init(&transaction->t_handle_lock);
+
+ /* Set up the commit timer for the new transaction. */
+ journal->j_commit_timer.expires = transaction->t_expires;
+ add_timer(&journal->j_commit_timer);
+
+ J_ASSERT(journal->j_running_transaction == NULL);
+ journal->j_running_transaction = transaction;
+
+ return transaction;
+}
+
+/*
+ * Handle management.
+ *
+ * A handle_t is an object which represents a single atomic update to a
+ * filesystem, and which tracks all of the modifications which form part
+ * of that one update.
+ */
+
+/*
+ * start_this_handle: Given a handle, deal with any locking or stalling
+ * needed to make sure that there is enough journal space for the handle
+ * to begin. Attach the handle to a transaction and set up the
+ * transaction's buffer credits.
+ */
+
+static int start_this_handle(journal_t *journal, handle_t *handle)
+{
+ transaction_t *transaction;
+ int needed;
+ int nblocks = handle->h_buffer_credits;
+ transaction_t *new_transaction = NULL;
+ int ret = 0;
+
+ if (nblocks > journal->j_max_transaction_buffers) {
+ printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
+ current->comm, nblocks,
+ journal->j_max_transaction_buffers);
+ ret = -ENOSPC;
+ goto out;
+ }
+
+alloc_transaction:
+ if (!journal->j_running_transaction) {
+ new_transaction = jbd_kmalloc(sizeof(*new_transaction),
+ GFP_NOFS);
+ if (!new_transaction) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ memset(new_transaction, 0, sizeof(*new_transaction));
+ }
+
+ jbd_debug(3, "New handle %p going live.\n", handle);
+
+repeat:
+
+ /*
+ * We need to hold j_state_lock until t_updates has been incremented,
+ * for proper journal barrier handling
+ */
+ spin_lock(&journal->j_state_lock);
+repeat_locked:
+ if (is_journal_aborted(journal) ||
+ (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) {
+ spin_unlock(&journal->j_state_lock);
+ ret = -EROFS;
+ goto out;
+ }
+
+ /* Wait on the journal's transaction barrier if necessary */
+ if (journal->j_barrier_count) {
+ spin_unlock(&journal->j_state_lock);
+ wait_event(journal->j_wait_transaction_locked,
+ journal->j_barrier_count == 0);
+ goto repeat;
+ }
+
+ if (!journal->j_running_transaction) {
+ if (!new_transaction) {
+ spin_unlock(&journal->j_state_lock);
+ goto alloc_transaction;
+ }
+ jbd2_get_transaction(journal, new_transaction);
+ new_transaction = NULL;
+ }
+
+ transaction = journal->j_running_transaction;
+
+ /*
+ * If the current transaction is locked down for commit, wait for the
+ * lock to be released.
+ */
+ if (transaction->t_state == T_LOCKED) {
+ DEFINE_WAIT(wait);
+
+ prepare_to_wait(&journal->j_wait_transaction_locked,
+ &wait, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&journal->j_state_lock);
+ schedule();
+ finish_wait(&journal->j_wait_transaction_locked, &wait);
+ goto repeat;
+ }
+
+ /*
+ * If there is not enough space left in the log to write all potential
+ * buffers requested by this operation, we need to stall pending a log
+ * checkpoint to free some more log space.
+ */
+ spin_lock(&transaction->t_handle_lock);
+ needed = transaction->t_outstanding_credits + nblocks;
+
+ if (needed > journal->j_max_transaction_buffers) {
+ /*
+ * If the current transaction is already too large, then start
+ * to commit it: we can then go back and attach this handle to
+ * a new transaction.
+ */
+ DEFINE_WAIT(wait);
+
+ jbd_debug(2, "Handle %p starting new commit...\n", handle);
+ spin_unlock(&transaction->t_handle_lock);
+ prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
+ TASK_UNINTERRUPTIBLE);
+ __jbd2_log_start_commit(journal, transaction->t_tid);
+ spin_unlock(&journal->j_state_lock);
+ schedule();
+ finish_wait(&journal->j_wait_transaction_locked, &wait);
+ goto repeat;
+ }
+
+ /*
+ * The commit code assumes that it can get enough log space
+ * without forcing a checkpoint. This is *critical* for
+ * correctness: a checkpoint of a buffer which is also
+ * associated with a committing transaction creates a deadlock,
+ * so commit simply cannot force through checkpoints.
+ *
+ * We must therefore ensure the necessary space in the journal
+ * *before* starting to dirty potentially checkpointed buffers
+ * in the new transaction.
+ *
+ * The worst part is, any transaction currently committing can
+ * reduce the free space arbitrarily. Be careful to account for
+ * those buffers when checkpointing.
+ */
+
+ /*
+ * @@@ AKPM: This seems rather over-defensive. We're giving commit
+ * a _lot_ of headroom: 1/4 of the journal plus the size of
+ * the committing transaction. Really, we only need to give it
+ * committing_transaction->t_outstanding_credits plus "enough" for
+ * the log control blocks.
+ * Also, this test is inconsitent with the matching one in
+ * jbd2_journal_extend().
+ */
+ if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) {
+ jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle);
+ spin_unlock(&transaction->t_handle_lock);
+ __jbd2_log_wait_for_space(journal);
+ goto repeat_locked;
+ }
+
+ /* OK, account for the buffers that this operation expects to
+ * use and add the handle to the running transaction. */
+
+ handle->h_transaction = transaction;
+ transaction->t_outstanding_credits += nblocks;
+ transaction->t_updates++;
+ transaction->t_handle_count++;
+ jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n",
+ handle, nblocks, transaction->t_outstanding_credits,
+ __jbd2_log_space_left(journal));
+ spin_unlock(&transaction->t_handle_lock);
+ spin_unlock(&journal->j_state_lock);
+out:
+ if (unlikely(new_transaction)) /* It's usually NULL */
+ kfree(new_transaction);
+ return ret;
+}
+
+/* Allocate a new handle. This should probably be in a slab... */
+static handle_t *new_handle(int nblocks)
+{
+ handle_t *handle = jbd_alloc_handle(GFP_NOFS);
+ if (!handle)
+ return NULL;
+ memset(handle, 0, sizeof(*handle));
+ handle->h_buffer_credits = nblocks;
+ handle->h_ref = 1;
+
+ return handle;
+}
+
+/**
+ * handle_t *jbd2_journal_start() - Obtain a new handle.
+ * @journal: Journal to start transaction on.
+ * @nblocks: number of block buffer we might modify
+ *
+ * We make sure that the transaction can guarantee at least nblocks of
+ * modified buffers in the log. We block until the log can guarantee
+ * that much space.
+ *
+ * This function is visible to journal users (like ext3fs), so is not
+ * called with the journal already locked.
+ *
+ * Return a pointer to a newly allocated handle, or NULL on failure
+ */
+handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
+{
+ handle_t *handle = journal_current_handle();
+ int err;
+
+ if (!journal)
+ return ERR_PTR(-EROFS);
+
+ if (handle) {
+ J_ASSERT(handle->h_transaction->t_journal == journal);
+ handle->h_ref++;
+ return handle;
+ }
+
+ handle = new_handle(nblocks);
+ if (!handle)
+ return ERR_PTR(-ENOMEM);
+
+ current->journal_info = handle;
+
+ err = start_this_handle(journal, handle);
+ if (err < 0) {
+ jbd_free_handle(handle);
+ current->journal_info = NULL;
+ handle = ERR_PTR(err);
+ }
+ return handle;
+}
+
+/**
+ * int jbd2_journal_extend() - extend buffer credits.
+ * @handle: handle to 'extend'
+ * @nblocks: nr blocks to try to extend by.
+ *
+ * Some transactions, such as large extends and truncates, can be done
+ * atomically all at once or in several stages. The operation requests
+ * a credit for a number of buffer modications in advance, but can
+ * extend its credit if it needs more.
+ *
+ * jbd2_journal_extend tries to give the running handle more buffer credits.
+ * It does not guarantee that allocation - this is a best-effort only.
+ * The calling process MUST be able to deal cleanly with a failure to
+ * extend here.
+ *
+ * Return 0 on success, non-zero on failure.
+ *
+ * return code < 0 implies an error
+ * return code > 0 implies normal transaction-full status.
+ */
+int jbd2_journal_extend(handle_t *handle, int nblocks)
+{
+ transaction_t *transaction = handle->h_transaction;
+ journal_t *journal = transaction->t_journal;
+ int result;
+ int wanted;
+
+ result = -EIO;
+ if (is_handle_aborted(handle))
+ goto out;
+
+ result = 1;
+
+ spin_lock(&journal->j_state_lock);
+
+ /* Don't extend a locked-down transaction! */
+ if (handle->h_transaction->t_state != T_RUNNING) {
+ jbd_debug(3, "denied handle %p %d blocks: "
+ "transaction not running\n", handle, nblocks);
+ goto error_out;
+ }
+
+ spin_lock(&transaction->t_handle_lock);
+ wanted = transaction->t_outstanding_credits + nblocks;
+
+ if (wanted > journal->j_max_transaction_buffers) {
+ jbd_debug(3, "denied handle %p %d blocks: "
+ "transaction too large\n", handle, nblocks);
+ goto unlock;
+ }
+
+ if (wanted > __jbd2_log_space_left(journal)) {
+ jbd_debug(3, "denied handle %p %d blocks: "
+ "insufficient log space\n", handle, nblocks);
+ goto unlock;
+ }
+
+ handle->h_buffer_credits += nblocks;
+ transaction->t_outstanding_credits += nblocks;
+ result = 0;
+
+ jbd_debug(3, "extended handle %p by %d\n", handle, nblocks);
+unlock:
+ spin_unlock(&transaction->t_handle_lock);
+error_out:
+ spin_unlock(&journal->j_state_lock);
+out:
+ return result;
+}
+
+
+/**
+ * int jbd2_journal_restart() - restart a handle .
+ * @handle: handle to restart
+ * @nblocks: nr credits requested
+ *
+ * Restart a handle for a multi-transaction filesystem
+ * operation.
+ *
+ * If the jbd2_journal_extend() call above fails to grant new buffer credits
+ * to a running handle, a call to jbd2_journal_restart will commit the
+ * handle's transaction so far and reattach the handle to a new
+ * transaction capabable of guaranteeing the requested number of
+ * credits.
+ */
+
+int jbd2_journal_restart(handle_t *handle, int nblocks)
+{
+ transaction_t *transaction = handle->h_transaction;
+ journal_t *journal = transaction->t_journal;
+ int ret;
+
+ /* If we've had an abort of any type, don't even think about
+ * actually doing the restart! */
+ if (is_handle_aborted(handle))
+ return 0;
+
+ /*
+ * First unlink the handle from its current transaction, and start the
+ * commit on that.
+ */
+ J_ASSERT(transaction->t_updates > 0);
+ J_ASSERT(journal_current_handle() == handle);
+
+ spin_lock(&journal->j_state_lock);
+ spin_lock(&transaction->t_handle_lock);
+ transaction->t_outstanding_credits -= handle->h_buffer_credits;
+ transaction->t_updates--;
+
+ if (!transaction->t_updates)
+ wake_up(&journal->j_wait_updates);
+ spin_unlock(&transaction->t_handle_lock);
+
+ jbd_debug(2, "restarting handle %p\n", handle);
+ __jbd2_log_start_commit(journal, transaction->t_tid);
+ spin_unlock(&journal->j_state_lock);
+
+ handle->h_buffer_credits = nblocks;
+ ret = start_this_handle(journal, handle);
+ return ret;
+}
+
+
+/**
+ * void jbd2_journal_lock_updates () - establish a transaction barrier.
+ * @journal: Journal to establish a barrier on.
+ *
+ * This locks out any further updates from being started, and blocks
+ * until all existing updates have completed, returning only once the
+ * journal is in a quiescent state with no updates running.
+ *
+ * The journal lock should not be held on entry.
+ */
+void jbd2_journal_lock_updates(journal_t *journal)
+{
+ DEFINE_WAIT(wait);
+
+ spin_lock(&journal->j_state_lock);
+ ++journal->j_barrier_count;
+
+ /* Wait until there are no running updates */
+ while (1) {
+ transaction_t *transaction = journal->j_running_transaction;
+
+ if (!transaction)
+ break;
+
+ spin_lock(&transaction->t_handle_lock);
+ if (!transaction->t_updates) {
+ spin_unlock(&transaction->t_handle_lock);
+ break;
+ }
+ prepare_to_wait(&journal->j_wait_updates, &wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock(&transaction->t_handle_lock);
+ spin_unlock(&journal->j_state_lock);
+ schedule();
+ finish_wait(&journal->j_wait_updates, &wait);
+ spin_lock(&journal->j_state_lock);
+ }
+ spin_unlock(&journal->j_state_lock);
+
+ /*
+ * We have now established a barrier against other normal updates, but
+ * we also need to barrier against other jbd2_journal_lock_updates() calls
+ * to make sure that we serialise special journal-locked operations
+ * too.
+ */
+ mutex_lock(&journal->j_barrier);
+}
+
+/**
+ * void jbd2_journal_unlock_updates (journal_t* journal) - release barrier
+ * @journal: Journal to release the barrier on.
+ *
+ * Release a transaction barrier obtained with jbd2_journal_lock_updates().
+ *
+ * Should be called without the journal lock held.
+ */
+void jbd2_journal_unlock_updates (journal_t *journal)
+{
+ J_ASSERT(journal->j_barrier_count != 0);
+
+ mutex_unlock(&journal->j_barrier);
+ spin_lock(&journal->j_state_lock);
+ --journal->j_barrier_count;
+ spin_unlock(&journal->j_state_lock);
+ wake_up(&journal->j_wait_transaction_locked);
+}
+
+/*
+ * Report any unexpected dirty buffers which turn up. Normally those
+ * indicate an error, but they can occur if the user is running (say)
+ * tune2fs to modify the live filesystem, so we need the option of
+ * continuing as gracefully as possible. #
+ *
+ * The caller should already hold the journal lock and
+ * j_list_lock spinlock: most callers will need those anyway
+ * in order to probe the buffer's journaling state safely.
+ */
+static void jbd_unexpected_dirty_buffer(struct journal_head *jh)
+{
+ int jlist;
+
+ /* If this buffer is one which might reasonably be dirty
+ * --- ie. data, or not part of this journal --- then
+ * we're OK to leave it alone, but otherwise we need to
+ * move the dirty bit to the journal's own internal
+ * JBDDirty bit. */
+ jlist = jh->b_jlist;
+
+ if (jlist == BJ_Metadata || jlist == BJ_Reserved ||
+ jlist == BJ_Shadow || jlist == BJ_Forget) {
+ struct buffer_head *bh = jh2bh(jh);
+
+ if (test_clear_buffer_dirty(bh))
+ set_buffer_jbddirty(bh);
+ }
+}
+
+/*
+ * If the buffer is already part of the current transaction, then there
+ * is nothing we need to do. If it is already part of a prior
+ * transaction which we are still committing to disk, then we need to
+ * make sure that we do not overwrite the old copy: we do copy-out to
+ * preserve the copy going to disk. We also account the buffer against
+ * the handle's metadata buffer credits (unless the buffer is already
+ * part of the transaction, that is).
+ *
+ */
+static int
+do_get_write_access(handle_t *handle, struct journal_head *jh,
+ int force_copy)
+{
+ struct buffer_head *bh;
+ transaction_t *transaction;
+ journal_t *journal;
+ int error;
+ char *frozen_buffer = NULL;
+ int need_copy = 0;
+
+ if (is_handle_aborted(handle))
+ return -EROFS;
+
+ transaction = handle->h_transaction;
+ journal = transaction->t_journal;
+
+ jbd_debug(5, "buffer_head %p, force_copy %d\n", jh, force_copy);
+
+ JBUFFER_TRACE(jh, "entry");
+repeat:
+ bh = jh2bh(jh);
+
+ /* @@@ Need to check for errors here at some point. */
+
+ lock_buffer(bh);
+ jbd_lock_bh_state(bh);
+
+ /* We now hold the buffer lock so it is safe to query the buffer
+ * state. Is the buffer dirty?
+ *
+ * If so, there are two possibilities. The buffer may be
+ * non-journaled, and undergoing a quite legitimate writeback.
+ * Otherwise, it is journaled, and we don't expect dirty buffers
+ * in that state (the buffers should be marked JBD_Dirty
+ * instead.) So either the IO is being done under our own
+ * control and this is a bug, or it's a third party IO such as
+ * dump(8) (which may leave the buffer scheduled for read ---
+ * ie. locked but not dirty) or tune2fs (which may actually have
+ * the buffer dirtied, ugh.) */
+
+ if (buffer_dirty(bh)) {
+ /*
+ * First question: is this buffer already part of the current
+ * transaction or the existing committing transaction?
+ */
+ if (jh->b_transaction) {
+ J_ASSERT_JH(jh,
+ jh->b_transaction == transaction ||
+ jh->b_transaction ==
+ journal->j_committing_transaction);
+ if (jh->b_next_transaction)
+ J_ASSERT_JH(jh, jh->b_next_transaction ==
+ transaction);
+ }
+ /*
+ * In any case we need to clean the dirty flag and we must
+ * do it under the buffer lock to be sure we don't race
+ * with running write-out.
+ */
+ JBUFFER_TRACE(jh, "Unexpected dirty buffer");
+ jbd_unexpected_dirty_buffer(jh);
+ }
+
+ unlock_buffer(bh);
+
+ error = -EROFS;
+ if (is_handle_aborted(handle)) {
+ jbd_unlock_bh_state(bh);
+ goto out;
+ }
+ error = 0;
+
+ /*
+ * The buffer is already part of this transaction if b_transaction or
+ * b_next_transaction points to it
+ */
+ if (jh->b_transaction == transaction ||
+ jh->b_next_transaction == transaction)
+ goto done;
+
+ /*
+ * If there is already a copy-out version of this buffer, then we don't
+ * need to make another one
+ */
+ if (jh->b_frozen_data) {
+ JBUFFER_TRACE(jh, "has frozen data");
+ J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+ jh->b_next_transaction = transaction;
+ goto done;
+ }
+
+ /* Is there data here we need to preserve? */
+
+ if (jh->b_transaction && jh->b_transaction != transaction) {
+ JBUFFER_TRACE(jh, "owned by older transaction");
+ J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+ J_ASSERT_JH(jh, jh->b_transaction ==
+ journal->j_committing_transaction);
+
+ /* There is one case we have to be very careful about.
+ * If the committing transaction is currently writing
+ * this buffer out to disk and has NOT made a copy-out,
+ * then we cannot modify the buffer contents at all
+ * right now. The essence of copy-out is that it is the
+ * extra copy, not the primary copy, which gets
+ * journaled. If the primary copy is already going to
+ * disk then we cannot do copy-out here. */
+
+ if (jh->b_jlist == BJ_Shadow) {
+ DEFINE_WAIT_BIT(wait, &bh->b_state, BH_Unshadow);
+ wait_queue_head_t *wqh;
+
+ wqh = bit_waitqueue(&bh->b_state, BH_Unshadow);
+
+ JBUFFER_TRACE(jh, "on shadow: sleep");
+ jbd_unlock_bh_state(bh);
+ /* commit wakes up all shadow buffers after IO */
+ for ( ; ; ) {
+ prepare_to_wait(wqh, &wait.wait,
+ TASK_UNINTERRUPTIBLE);
+ if (jh->b_jlist != BJ_Shadow)
+ break;
+ schedule();
+ }
+ finish_wait(wqh, &wait.wait);
+ goto repeat;
+ }
+
+ /* Only do the copy if the currently-owning transaction
+ * still needs it. If it is on the Forget list, the
+ * committing transaction is past that stage. The
+ * buffer had better remain locked during the kmalloc,
+ * but that should be true --- we hold the journal lock
+ * still and the buffer is already on the BUF_JOURNAL
+ * list so won't be flushed.
+ *
+ * Subtle point, though: if this is a get_undo_access,
+ * then we will be relying on the frozen_data to contain
+ * the new value of the committed_data record after the
+ * transaction, so we HAVE to force the frozen_data copy
+ * in that case. */
+
+ if (jh->b_jlist != BJ_Forget || force_copy) {
+ JBUFFER_TRACE(jh, "generate frozen data");
+ if (!frozen_buffer) {
+ JBUFFER_TRACE(jh, "allocate memory for buffer");
+ jbd_unlock_bh_state(bh);
+ frozen_buffer =
+ jbd2_slab_alloc(jh2bh(jh)->b_size,
+ GFP_NOFS);
+ if (!frozen_buffer) {
+ printk(KERN_EMERG
+ "%s: OOM for frozen_buffer\n",
+ __FUNCTION__);
+ JBUFFER_TRACE(jh, "oom!");
+ error = -ENOMEM;
+ jbd_lock_bh_state(bh);
+ goto done;
+ }
+ goto repeat;
+ }
+ jh->b_frozen_data = frozen_buffer;
+ frozen_buffer = NULL;
+ need_copy = 1;
+ }
+ jh->b_next_transaction = transaction;
+ }
+
+
+ /*
+ * Finally, if the buffer is not journaled right now, we need to make
+ * sure it doesn't get written to disk before the caller actually
+ * commits the new data
+ */
+ if (!jh->b_transaction) {
+ JBUFFER_TRACE(jh, "no transaction");
+ J_ASSERT_JH(jh, !jh->b_next_transaction);
+ jh->b_transaction = transaction;
+ JBUFFER_TRACE(jh, "file as BJ_Reserved");
+ spin_lock(&journal->j_list_lock);
+ __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
+ spin_unlock(&journal->j_list_lock);
+ }
+
+done:
+ if (need_copy) {
+ struct page *page;
+ int offset;
+ char *source;
+
+ J_EXPECT_JH(jh, buffer_uptodate(jh2bh(jh)),
+ "Possible IO failure.\n");
+ page = jh2bh(jh)->b_page;
+ offset = ((unsigned long) jh2bh(jh)->b_data) & ~PAGE_MASK;
+ source = kmap_atomic(page, KM_USER0);
+ memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
+ kunmap_atomic(source, KM_USER0);
+ }
+ jbd_unlock_bh_state(bh);
+
+ /*
+ * If we are about to journal a buffer, then any revoke pending on it is
+ * no longer valid
+ */
+ jbd2_journal_cancel_revoke(handle, jh);
+
+out:
+ if (unlikely(frozen_buffer)) /* It's usually NULL */
+ jbd2_slab_free(frozen_buffer, bh->b_size);
+
+ JBUFFER_TRACE(jh, "exit");
+ return error;
+}
+
+/**
+ * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update.
+ * @handle: transaction to add buffer modifications to
+ * @bh: bh to be used for metadata writes
+ * @credits: variable that will receive credits for the buffer
+ *
+ * Returns an error code or 0 on success.
+ *
+ * In full data journalling mode the buffer may be of type BJ_AsyncData,
+ * because we're write()ing a buffer which is also part of a shared mapping.
+ */
+
+int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
+{
+ struct journal_head *jh = jbd2_journal_add_journal_head(bh);
+ int rc;
+
+ /* We do not want to get caught playing with fields which the
+ * log thread also manipulates. Make sure that the buffer
+ * completes any outstanding IO before proceeding. */
+ rc = do_get_write_access(handle, jh, 0);
+ jbd2_journal_put_journal_head(jh);
+ return rc;
+}
+
+
+/*
+ * When the user wants to journal a newly created buffer_head
+ * (ie. getblk() returned a new buffer and we are going to populate it
+ * manually rather than reading off disk), then we need to keep the
+ * buffer_head locked until it has been completely filled with new
+ * data. In this case, we should be able to make the assertion that
+ * the bh is not already part of an existing transaction.
+ *
+ * The buffer should already be locked by the caller by this point.
+ * There is no lock ranking violation: it was a newly created,
+ * unlocked buffer beforehand. */
+
+/**
+ * int jbd2_journal_get_create_access () - notify intent to use newly created bh
+ * @handle: transaction to new buffer to
+ * @bh: new buffer.
+ *
+ * Call this if you create a new bh.
+ */
+int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
+{
+ transaction_t *transaction = handle->h_transaction;
+ journal_t *journal = transaction->t_journal;
+ struct journal_head *jh = jbd2_journal_add_journal_head(bh);
+ int err;
+
+ jbd_debug(5, "journal_head %p\n", jh);
+ err = -EROFS;
+ if (is_handle_aborted(handle))
+ goto out;
+ err = 0;
+
+ JBUFFER_TRACE(jh, "entry");
+ /*
+ * The buffer may already belong to this transaction due to pre-zeroing
+ * in the filesystem's new_block code. It may also be on the previous,
+ * committing transaction's lists, but it HAS to be in Forget state in
+ * that case: the transaction must have deleted the buffer for it to be
+ * reused here.
+ */
+ jbd_lock_bh_state(bh);
+ spin_lock(&journal->j_list_lock);
+ J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
+ jh->b_transaction == NULL ||
+ (jh->b_transaction == journal->j_committing_transaction &&
+ jh->b_jlist == BJ_Forget)));
+
+ J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+ J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));
+
+ if (jh->b_transaction == NULL) {
+ jh->b_transaction = transaction;
+ JBUFFER_TRACE(jh, "file as BJ_Reserved");
+ __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
+ } else if (jh->b_transaction == journal->j_committing_transaction) {
+ JBUFFER_TRACE(jh, "set next transaction");
+ jh->b_next_transaction = transaction;
+ }
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+
+ /*
+ * akpm: I added this. ext3_alloc_branch can pick up new indirect
+ * blocks which contain freed but then revoked metadata. We need
+ * to cancel the revoke in case we end up freeing it yet again
+ * and the reallocating as data - this would cause a second revoke,
+ * which hits an assertion error.
+ */
+ JBUFFER_TRACE(jh, "cancelling revoke");
+ jbd2_journal_cancel_revoke(handle, jh);
+ jbd2_journal_put_journal_head(jh);
+out:
+ return err;
+}
+
+/**
+ * int jbd2_journal_get_undo_access() - Notify intent to modify metadata with
+ * non-rewindable consequences
+ * @handle: transaction
+ * @bh: buffer to undo
+ * @credits: store the number of taken credits here (if not NULL)
+ *
+ * Sometimes there is a need to distinguish between metadata which has
+ * been committed to disk and that which has not. The ext3fs code uses
+ * this for freeing and allocating space, we have to make sure that we
+ * do not reuse freed space until the deallocation has been committed,
+ * since if we overwrote that space we would make the delete
+ * un-rewindable in case of a crash.
+ *
+ * To deal with that, jbd2_journal_get_undo_access requests write access to a
+ * buffer for parts of non-rewindable operations such as delete
+ * operations on the bitmaps. The journaling code must keep a copy of
+ * the buffer's contents prior to the undo_access call until such time
+ * as we know that the buffer has definitely been committed to disk.
+ *
+ * We never need to know which transaction the committed data is part
+ * of, buffers touched here are guaranteed to be dirtied later and so
+ * will be committed to a new transaction in due course, at which point
+ * we can discard the old committed data pointer.
+ *
+ * Returns error number or 0 on success.
+ */
+int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
+{
+ int err;
+ struct journal_head *jh = jbd2_journal_add_journal_head(bh);
+ char *committed_data = NULL;
+
+ JBUFFER_TRACE(jh, "entry");
+
+ /*
+ * Do this first --- it can drop the journal lock, so we want to
+ * make sure that obtaining the committed_data is done
+ * atomically wrt. completion of any outstanding commits.
+ */
+ err = do_get_write_access(handle, jh, 1);
+ if (err)
+ goto out;
+
+repeat:
+ if (!jh->b_committed_data) {
+ committed_data = jbd2_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS);
+ if (!committed_data) {
+ printk(KERN_EMERG "%s: No memory for committed data\n",
+ __FUNCTION__);
+ err = -ENOMEM;
+ goto out;
+ }
+ }
+
+ jbd_lock_bh_state(bh);
+ if (!jh->b_committed_data) {
+ /* Copy out the current buffer contents into the
+ * preserved, committed copy. */
+ JBUFFER_TRACE(jh, "generate b_committed data");
+ if (!committed_data) {
+ jbd_unlock_bh_state(bh);
+ goto repeat;
+ }
+
+ jh->b_committed_data = committed_data;
+ committed_data = NULL;
+ memcpy(jh->b_committed_data, bh->b_data, bh->b_size);
+ }
+ jbd_unlock_bh_state(bh);
+out:
+ jbd2_journal_put_journal_head(jh);
+ if (unlikely(committed_data))
+ jbd2_slab_free(committed_data, bh->b_size);
+ return err;
+}
+
+/**
+ * int jbd2_journal_dirty_data() - mark a buffer as containing dirty data which
+ * needs to be flushed before we can commit the
+ * current transaction.
+ * @handle: transaction
+ * @bh: bufferhead to mark
+ *
+ * The buffer is placed on the transaction's data list and is marked as
+ * belonging to the transaction.
+ *
+ * Returns error number or 0 on success.
+ *
+ * jbd2_journal_dirty_data() can be called via page_launder->ext3_writepage
+ * by kswapd.
+ */
+int jbd2_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
+{
+ journal_t *journal = handle->h_transaction->t_journal;
+ int need_brelse = 0;
+ struct journal_head *jh;
+
+ if (is_handle_aborted(handle))
+ return 0;
+
+ jh = jbd2_journal_add_journal_head(bh);
+ JBUFFER_TRACE(jh, "entry");
+
+ /*
+ * The buffer could *already* be dirty. Writeout can start
+ * at any time.
+ */
+ jbd_debug(4, "jh: %p, tid:%d\n", jh, handle->h_transaction->t_tid);
+
+ /*
+ * What if the buffer is already part of a running transaction?
+ *
+ * There are two cases:
+ * 1) It is part of the current running transaction. Refile it,
+ * just in case we have allocated it as metadata, deallocated
+ * it, then reallocated it as data.
+ * 2) It is part of the previous, still-committing transaction.
+ * If all we want to do is to guarantee that the buffer will be
+ * written to disk before this new transaction commits, then
+ * being sure that the *previous* transaction has this same
+ * property is sufficient for us! Just leave it on its old
+ * transaction.
+ *
+ * In case (2), the buffer must not already exist as metadata
+ * --- that would violate write ordering (a transaction is free
+ * to write its data at any point, even before the previous
+ * committing transaction has committed). The caller must
+ * never, ever allow this to happen: there's nothing we can do
+ * about it in this layer.
+ */
+ jbd_lock_bh_state(bh);
+ spin_lock(&journal->j_list_lock);
+ if (jh->b_transaction) {
+ JBUFFER_TRACE(jh, "has transaction");
+ if (jh->b_transaction != handle->h_transaction) {
+ JBUFFER_TRACE(jh, "belongs to older transaction");
+ J_ASSERT_JH(jh, jh->b_transaction ==
+ journal->j_committing_transaction);
+
+ /* @@@ IS THIS TRUE ? */
+ /*
+ * Not any more. Scenario: someone does a write()
+ * in data=journal mode. The buffer's transaction has
+ * moved into commit. Then someone does another
+ * write() to the file. We do the frozen data copyout
+ * and set b_next_transaction to point to j_running_t.
+ * And while we're in that state, someone does a
+ * writepage() in an attempt to pageout the same area
+ * of the file via a shared mapping. At present that
+ * calls jbd2_journal_dirty_data(), and we get right here.
+ * It may be too late to journal the data. Simply
+ * falling through to the next test will suffice: the
+ * data will be dirty and wil be checkpointed. The
+ * ordering comments in the next comment block still
+ * apply.
+ */
+ //J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
+
+ /*
+ * If we're journalling data, and this buffer was
+ * subject to a write(), it could be metadata, forget
+ * or shadow against the committing transaction. Now,
+ * someone has dirtied the same darn page via a mapping
+ * and it is being writepage()'d.
+ * We *could* just steal the page from commit, with some
+ * fancy locking there. Instead, we just skip it -
+ * don't tie the page's buffers to the new transaction
+ * at all.
+ * Implication: if we crash before the writepage() data
+ * is written into the filesystem, recovery will replay
+ * the write() data.
+ */
+ if (jh->b_jlist != BJ_None &&
+ jh->b_jlist != BJ_SyncData &&
+ jh->b_jlist != BJ_Locked) {
+ JBUFFER_TRACE(jh, "Not stealing");
+ goto no_journal;
+ }
+
+ /*
+ * This buffer may be undergoing writeout in commit. We
+ * can't return from here and let the caller dirty it
+ * again because that can cause the write-out loop in
+ * commit to never terminate.
+ */
+ if (buffer_dirty(bh)) {
+ get_bh(bh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ need_brelse = 1;
+ sync_dirty_buffer(bh);
+ jbd_lock_bh_state(bh);
+ spin_lock(&journal->j_list_lock);
+ /* The buffer may become locked again at any
+ time if it is redirtied */
+ }
+
+ /* journal_clean_data_list() may have got there first */
+ if (jh->b_transaction != NULL) {
+ JBUFFER_TRACE(jh, "unfile from commit");
+ __jbd2_journal_temp_unlink_buffer(jh);
+ /* It still points to the committing
+ * transaction; move it to this one so
+ * that the refile assert checks are
+ * happy. */
+ jh->b_transaction = handle->h_transaction;
+ }
+ /* The buffer will be refiled below */
+
+ }
+ /*
+ * Special case --- the buffer might actually have been
+ * allocated and then immediately deallocated in the previous,
+ * committing transaction, so might still be left on that
+ * transaction's metadata lists.
+ */
+ if (jh->b_jlist != BJ_SyncData && jh->b_jlist != BJ_Locked) {
+ JBUFFER_TRACE(jh, "not on correct data list: unfile");
+ J_ASSERT_JH(jh, jh->b_jlist != BJ_Shadow);
+ __jbd2_journal_temp_unlink_buffer(jh);
+ jh->b_transaction = handle->h_transaction;
+ JBUFFER_TRACE(jh, "file as data");
+ __jbd2_journal_file_buffer(jh, handle->h_transaction,
+ BJ_SyncData);
+ }
+ } else {
+ JBUFFER_TRACE(jh, "not on a transaction");
+ __jbd2_journal_file_buffer(jh, handle->h_transaction, BJ_SyncData);
+ }
+no_journal:
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ if (need_brelse) {
+ BUFFER_TRACE(bh, "brelse");
+ __brelse(bh);
+ }
+ JBUFFER_TRACE(jh, "exit");
+ jbd2_journal_put_journal_head(jh);
+ return 0;
+}
+
+/**
+ * int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata
+ * @handle: transaction to add buffer to.
+ * @bh: buffer to mark
+ *
+ * mark dirty metadata which needs to be journaled as part of the current
+ * transaction.
+ *
+ * The buffer is placed on the transaction's metadata list and is marked
+ * as belonging to the transaction.
+ *
+ * Returns error number or 0 on success.
+ *
+ * Special care needs to be taken if the buffer already belongs to the
+ * current committing transaction (in which case we should have frozen
+ * data present for that commit). In that case, we don't relink the
+ * buffer: that only gets done when the old transaction finally
+ * completes its commit.
+ */
+int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
+{
+ transaction_t *transaction = handle->h_transaction;
+ journal_t *journal = transaction->t_journal;
+ struct journal_head *jh = bh2jh(bh);
+
+ jbd_debug(5, "journal_head %p\n", jh);
+ JBUFFER_TRACE(jh, "entry");
+ if (is_handle_aborted(handle))
+ goto out;
+
+ jbd_lock_bh_state(bh);
+
+ if (jh->b_modified == 0) {
+ /*
+ * This buffer's got modified and becoming part
+ * of the transaction. This needs to be done
+ * once a transaction -bzzz
+ */
+ jh->b_modified = 1;
+ J_ASSERT_JH(jh, handle->h_buffer_credits > 0);
+ handle->h_buffer_credits--;
+ }
+
+ /*
+ * fastpath, to avoid expensive locking. If this buffer is already
+ * on the running transaction's metadata list there is nothing to do.
+ * Nobody can take it off again because there is a handle open.
+ * I _think_ we're OK here with SMP barriers - a mistaken decision will
+ * result in this test being false, so we go in and take the locks.
+ */
+ if (jh->b_transaction == transaction && jh->b_jlist == BJ_Metadata) {
+ JBUFFER_TRACE(jh, "fastpath");
+ J_ASSERT_JH(jh, jh->b_transaction ==
+ journal->j_running_transaction);
+ goto out_unlock_bh;
+ }
+
+ set_buffer_jbddirty(bh);
+
+ /*
+ * Metadata already on the current transaction list doesn't
+ * need to be filed. Metadata on another transaction's list must
+ * be committing, and will be refiled once the commit completes:
+ * leave it alone for now.
+ */
+ if (jh->b_transaction != transaction) {
+ JBUFFER_TRACE(jh, "already on other transaction");
+ J_ASSERT_JH(jh, jh->b_transaction ==
+ journal->j_committing_transaction);
+ J_ASSERT_JH(jh, jh->b_next_transaction == transaction);
+ /* And this case is illegal: we can't reuse another
+ * transaction's data buffer, ever. */
+ goto out_unlock_bh;
+ }
+
+ /* That test should have eliminated the following case: */
+ J_ASSERT_JH(jh, jh->b_frozen_data == 0);
+
+ JBUFFER_TRACE(jh, "file as BJ_Metadata");
+ spin_lock(&journal->j_list_lock);
+ __jbd2_journal_file_buffer(jh, handle->h_transaction, BJ_Metadata);
+ spin_unlock(&journal->j_list_lock);
+out_unlock_bh:
+ jbd_unlock_bh_state(bh);
+out:
+ JBUFFER_TRACE(jh, "exit");
+ return 0;
+}
+
+/*
+ * jbd2_journal_release_buffer: undo a get_write_access without any buffer
+ * updates, if the update decided in the end that it didn't need access.
+ *
+ */
+void
+jbd2_journal_release_buffer(handle_t *handle, struct buffer_head *bh)
+{
+ BUFFER_TRACE(bh, "entry");
+}
+
+/**
+ * void jbd2_journal_forget() - bforget() for potentially-journaled buffers.
+ * @handle: transaction handle
+ * @bh: bh to 'forget'
+ *
+ * We can only do the bforget if there are no commits pending against the
+ * buffer. If the buffer is dirty in the current running transaction we
+ * can safely unlink it.
+ *
+ * bh may not be a journalled buffer at all - it may be a non-JBD
+ * buffer which came off the hashtable. Check for this.
+ *
+ * Decrements bh->b_count by one.
+ *
+ * Allow this call even if the handle has aborted --- it may be part of
+ * the caller's cleanup after an abort.
+ */
+int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
+{
+ transaction_t *transaction = handle->h_transaction;
+ journal_t *journal = transaction->t_journal;
+ struct journal_head *jh;
+ int drop_reserve = 0;
+ int err = 0;
+
+ BUFFER_TRACE(bh, "entry");
+
+ jbd_lock_bh_state(bh);
+ spin_lock(&journal->j_list_lock);
+
+ if (!buffer_jbd(bh))
+ goto not_jbd;
+ jh = bh2jh(bh);
+
+ /* Critical error: attempting to delete a bitmap buffer, maybe?
+ * Don't do any jbd operations, and return an error. */
+ if (!J_EXPECT_JH(jh, !jh->b_committed_data,
+ "inconsistent data on disk")) {
+ err = -EIO;
+ goto not_jbd;
+ }
+
+ /*
+ * The buffer's going from the transaction, we must drop
+ * all references -bzzz
+ */
+ jh->b_modified = 0;
+
+ if (jh->b_transaction == handle->h_transaction) {
+ J_ASSERT_JH(jh, !jh->b_frozen_data);
+
+ /* If we are forgetting a buffer which is already part
+ * of this transaction, then we can just drop it from
+ * the transaction immediately. */
+ clear_buffer_dirty(bh);
+ clear_buffer_jbddirty(bh);
+
+ JBUFFER_TRACE(jh, "belongs to current transaction: unfile");
+
+ drop_reserve = 1;
+
+ /*
+ * We are no longer going to journal this buffer.
+ * However, the commit of this transaction is still
+ * important to the buffer: the delete that we are now
+ * processing might obsolete an old log entry, so by
+ * committing, we can satisfy the buffer's checkpoint.
+ *
+ * So, if we have a checkpoint on the buffer, we should
+ * now refile the buffer on our BJ_Forget list so that
+ * we know to remove the checkpoint after we commit.
+ */
+
+ if (jh->b_cp_transaction) {
+ __jbd2_journal_temp_unlink_buffer(jh);
+ __jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
+ } else {
+ __jbd2_journal_unfile_buffer(jh);
+ jbd2_journal_remove_journal_head(bh);
+ __brelse(bh);
+ if (!buffer_jbd(bh)) {
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ __bforget(bh);
+ goto drop;
+ }
+ }
+ } else if (jh->b_transaction) {
+ J_ASSERT_JH(jh, (jh->b_transaction ==
+ journal->j_committing_transaction));
+ /* However, if the buffer is still owned by a prior
+ * (committing) transaction, we can't drop it yet... */
+ JBUFFER_TRACE(jh, "belongs to older transaction");
+ /* ... but we CAN drop it from the new transaction if we
+ * have also modified it since the original commit. */
+
+ if (jh->b_next_transaction) {
+ J_ASSERT(jh->b_next_transaction == transaction);
+ jh->b_next_transaction = NULL;
+ drop_reserve = 1;
+ }
+ }
+
+not_jbd:
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ __brelse(bh);
+drop:
+ if (drop_reserve) {
+ /* no need to reserve log space for this block -bzzz */
+ handle->h_buffer_credits++;
+ }
+ return err;
+}
+
+/**
+ * int jbd2_journal_stop() - complete a transaction
+ * @handle: tranaction to complete.
+ *
+ * All done for a particular handle.
+ *
+ * There is not much action needed here. We just return any remaining
+ * buffer credits to the transaction and remove the handle. The only
+ * complication is that we need to start a commit operation if the
+ * filesystem is marked for synchronous update.
+ *
+ * jbd2_journal_stop itself will not usually return an error, but it may
+ * do so in unusual circumstances. In particular, expect it to
+ * return -EIO if a jbd2_journal_abort has been executed since the
+ * transaction began.
+ */
+int jbd2_journal_stop(handle_t *handle)
+{
+ transaction_t *transaction = handle->h_transaction;
+ journal_t *journal = transaction->t_journal;
+ int old_handle_count, err;
+ pid_t pid;
+
+ J_ASSERT(transaction->t_updates > 0);
+ J_ASSERT(journal_current_handle() == handle);
+
+ if (is_handle_aborted(handle))
+ err = -EIO;
+ else
+ err = 0;
+
+ if (--handle->h_ref > 0) {
+ jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1,
+ handle->h_ref);
+ return err;
+ }
+
+ jbd_debug(4, "Handle %p going down\n", handle);
+
+ /*
+ * Implement synchronous transaction batching. If the handle
+ * was synchronous, don't force a commit immediately. Let's
+ * yield and let another thread piggyback onto this transaction.
+ * Keep doing that while new threads continue to arrive.
+ * It doesn't cost much - we're about to run a commit and sleep
+ * on IO anyway. Speeds up many-threaded, many-dir operations
+ * by 30x or more...
+ *
+ * But don't do this if this process was the most recent one to
+ * perform a synchronous write. We do this to detect the case where a
+ * single process is doing a stream of sync writes. No point in waiting
+ * for joiners in that case.
+ */
+ pid = current->pid;
+ if (handle->h_sync && journal->j_last_sync_writer != pid) {
+ journal->j_last_sync_writer = pid;
+ do {
+ old_handle_count = transaction->t_handle_count;
+ schedule_timeout_uninterruptible(1);
+ } while (old_handle_count != transaction->t_handle_count);
+ }
+
+ current->journal_info = NULL;
+ spin_lock(&journal->j_state_lock);
+ spin_lock(&transaction->t_handle_lock);
+ transaction->t_outstanding_credits -= handle->h_buffer_credits;
+ transaction->t_updates--;
+ if (!transaction->t_updates) {
+ wake_up(&journal->j_wait_updates);
+ if (journal->j_barrier_count)
+ wake_up(&journal->j_wait_transaction_locked);
+ }
+
+ /*
+ * If the handle is marked SYNC, we need to set another commit
+ * going! We also want to force a commit if the current
+ * transaction is occupying too much of the log, or if the
+ * transaction is too old now.
+ */
+ if (handle->h_sync ||
+ transaction->t_outstanding_credits >
+ journal->j_max_transaction_buffers ||
+ time_after_eq(jiffies, transaction->t_expires)) {
+ /* Do this even for aborted journals: an abort still
+ * completes the commit thread, it just doesn't write
+ * anything to disk. */
+ tid_t tid = transaction->t_tid;
+
+ spin_unlock(&transaction->t_handle_lock);
+ jbd_debug(2, "transaction too old, requesting commit for "
+ "handle %p\n", handle);
+ /* This is non-blocking */
+ __jbd2_log_start_commit(journal, transaction->t_tid);
+ spin_unlock(&journal->j_state_lock);
+
+ /*
+ * Special case: JBD2_SYNC synchronous updates require us
+ * to wait for the commit to complete.
+ */
+ if (handle->h_sync && !(current->flags & PF_MEMALLOC))
+ err = jbd2_log_wait_commit(journal, tid);
+ } else {
+ spin_unlock(&transaction->t_handle_lock);
+ spin_unlock(&journal->j_state_lock);
+ }
+
+ jbd_free_handle(handle);
+ return err;
+}
+
+/**int jbd2_journal_force_commit() - force any uncommitted transactions
+ * @journal: journal to force
+ *
+ * For synchronous operations: force any uncommitted transactions
+ * to disk. May seem kludgy, but it reuses all the handle batching
+ * code in a very simple manner.
+ */
+int jbd2_journal_force_commit(journal_t *journal)
+{
+ handle_t *handle;
+ int ret;
+
+ handle = jbd2_journal_start(journal, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ } else {
+ handle->h_sync = 1;
+ ret = jbd2_journal_stop(handle);
+ }
+ return ret;
+}
+
+/*
+ *
+ * List management code snippets: various functions for manipulating the
+ * transaction buffer lists.
+ *
+ */
+
+/*
+ * Append a buffer to a transaction list, given the transaction's list head
+ * pointer.
+ *
+ * j_list_lock is held.
+ *
+ * jbd_lock_bh_state(jh2bh(jh)) is held.
+ */
+
+static inline void
+__blist_add_buffer(struct journal_head **list, struct journal_head *jh)
+{
+ if (!*list) {
+ jh->b_tnext = jh->b_tprev = jh;
+ *list = jh;
+ } else {
+ /* Insert at the tail of the list to preserve order */
+ struct journal_head *first = *list, *last = first->b_tprev;
+ jh->b_tprev = last;
+ jh->b_tnext = first;
+ last->b_tnext = first->b_tprev = jh;
+ }
+}
+
+/*
+ * Remove a buffer from a transaction list, given the transaction's list
+ * head pointer.
+ *
+ * Called with j_list_lock held, and the journal may not be locked.
+ *
+ * jbd_lock_bh_state(jh2bh(jh)) is held.
+ */
+
+static inline void
+__blist_del_buffer(struct journal_head **list, struct journal_head *jh)
+{
+ if (*list == jh) {
+ *list = jh->b_tnext;
+ if (*list == jh)
+ *list = NULL;
+ }
+ jh->b_tprev->b_tnext = jh->b_tnext;
+ jh->b_tnext->b_tprev = jh->b_tprev;
+}
+
+/*
+ * Remove a buffer from the appropriate transaction list.
+ *
+ * Note that this function can *change* the value of
+ * bh->b_transaction->t_sync_datalist, t_buffers, t_forget,
+ * t_iobuf_list, t_shadow_list, t_log_list or t_reserved_list. If the caller
+ * is holding onto a copy of one of thee pointers, it could go bad.
+ * Generally the caller needs to re-read the pointer from the transaction_t.
+ *
+ * Called under j_list_lock. The journal may not be locked.
+ */
+void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
+{
+ struct journal_head **list = NULL;
+ transaction_t *transaction;
+ struct buffer_head *bh = jh2bh(jh);
+
+ J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+ transaction = jh->b_transaction;
+ if (transaction)
+ assert_spin_locked(&transaction->t_journal->j_list_lock);
+
+ J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
+ if (jh->b_jlist != BJ_None)
+ J_ASSERT_JH(jh, transaction != 0);
+
+ switch (jh->b_jlist) {
+ case BJ_None:
+ return;
+ case BJ_SyncData:
+ list = &transaction->t_sync_datalist;
+ break;
+ case BJ_Metadata:
+ transaction->t_nr_buffers--;
+ J_ASSERT_JH(jh, transaction->t_nr_buffers >= 0);
+ list = &transaction->t_buffers;
+ break;
+ case BJ_Forget:
+ list = &transaction->t_forget;
+ break;
+ case BJ_IO:
+ list = &transaction->t_iobuf_list;
+ break;
+ case BJ_Shadow:
+ list = &transaction->t_shadow_list;
+ break;
+ case BJ_LogCtl:
+ list = &transaction->t_log_list;
+ break;
+ case BJ_Reserved:
+ list = &transaction->t_reserved_list;
+ break;
+ case BJ_Locked:
+ list = &transaction->t_locked_list;
+ break;
+ }
+
+ __blist_del_buffer(list, jh);
+ jh->b_jlist = BJ_None;
+ if (test_clear_buffer_jbddirty(bh))
+ mark_buffer_dirty(bh); /* Expose it to the VM */
+}
+
+void __jbd2_journal_unfile_buffer(struct journal_head *jh)
+{
+ __jbd2_journal_temp_unlink_buffer(jh);
+ jh->b_transaction = NULL;
+}
+
+void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
+{
+ jbd_lock_bh_state(jh2bh(jh));
+ spin_lock(&journal->j_list_lock);
+ __jbd2_journal_unfile_buffer(jh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(jh2bh(jh));
+}
+
+/*
+ * Called from jbd2_journal_try_to_free_buffers().
+ *
+ * Called under jbd_lock_bh_state(bh)
+ */
+static void
+__journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
+{
+ struct journal_head *jh;
+
+ jh = bh2jh(bh);
+
+ if (buffer_locked(bh) || buffer_dirty(bh))
+ goto out;
+
+ if (jh->b_next_transaction != 0)
+ goto out;
+
+ spin_lock(&journal->j_list_lock);
+ if (jh->b_transaction != 0 && jh->b_cp_transaction == 0) {
+ if (jh->b_jlist == BJ_SyncData || jh->b_jlist == BJ_Locked) {
+ /* A written-back ordered data buffer */
+ JBUFFER_TRACE(jh, "release data");
+ __jbd2_journal_unfile_buffer(jh);
+ jbd2_journal_remove_journal_head(bh);
+ __brelse(bh);
+ }
+ } else if (jh->b_cp_transaction != 0 && jh->b_transaction == 0) {
+ /* written-back checkpointed metadata buffer */
+ if (jh->b_jlist == BJ_None) {
+ JBUFFER_TRACE(jh, "remove from checkpoint list");
+ __jbd2_journal_remove_checkpoint(jh);
+ jbd2_journal_remove_journal_head(bh);
+ __brelse(bh);
+ }
+ }
+ spin_unlock(&journal->j_list_lock);
+out:
+ return;
+}
+
+
+/**
+ * int jbd2_journal_try_to_free_buffers() - try to free page buffers.
+ * @journal: journal for operation
+ * @page: to try and free
+ * @unused_gfp_mask: unused
+ *
+ *
+ * For all the buffers on this page,
+ * if they are fully written out ordered data, move them onto BUF_CLEAN
+ * so try_to_free_buffers() can reap them.
+ *
+ * This function returns non-zero if we wish try_to_free_buffers()
+ * to be called. We do this if the page is releasable by try_to_free_buffers().
+ * We also do it if the page has locked or dirty buffers and the caller wants
+ * us to perform sync or async writeout.
+ *
+ * This complicates JBD locking somewhat. We aren't protected by the
+ * BKL here. We wish to remove the buffer from its committing or
+ * running transaction's ->t_datalist via __jbd2_journal_unfile_buffer.
+ *
+ * This may *change* the value of transaction_t->t_datalist, so anyone
+ * who looks at t_datalist needs to lock against this function.
+ *
+ * Even worse, someone may be doing a jbd2_journal_dirty_data on this
+ * buffer. So we need to lock against that. jbd2_journal_dirty_data()
+ * will come out of the lock with the buffer dirty, which makes it
+ * ineligible for release here.
+ *
+ * Who else is affected by this? hmm... Really the only contender
+ * is do_get_write_access() - it could be looking at the buffer while
+ * journal_try_to_free_buffer() is changing its state. But that
+ * cannot happen because we never reallocate freed data as metadata
+ * while the data is part of a transaction. Yes?
+ */
+int jbd2_journal_try_to_free_buffers(journal_t *journal,
+ struct page *page, gfp_t unused_gfp_mask)
+{
+ struct buffer_head *head;
+ struct buffer_head *bh;
+ int ret = 0;
+
+ J_ASSERT(PageLocked(page));
+
+ head = page_buffers(page);
+ bh = head;
+ do {
+ struct journal_head *jh;
+
+ /*
+ * We take our own ref against the journal_head here to avoid
+ * having to add tons of locking around each instance of
+ * jbd2_journal_remove_journal_head() and jbd2_journal_put_journal_head().
+ */
+ jh = jbd2_journal_grab_journal_head(bh);
+ if (!jh)
+ continue;
+
+ jbd_lock_bh_state(bh);
+ __journal_try_to_free_buffer(journal, bh);
+ jbd2_journal_put_journal_head(jh);
+ jbd_unlock_bh_state(bh);
+ if (buffer_jbd(bh))
+ goto busy;
+ } while ((bh = bh->b_this_page) != head);
+ ret = try_to_free_buffers(page);
+busy:
+ return ret;
+}
+
+/*
+ * This buffer is no longer needed. If it is on an older transaction's
+ * checkpoint list we need to record it on this transaction's forget list
+ * to pin this buffer (and hence its checkpointing transaction) down until
+ * this transaction commits. If the buffer isn't on a checkpoint list, we
+ * release it.
+ * Returns non-zero if JBD no longer has an interest in the buffer.
+ *
+ * Called under j_list_lock.
+ *
+ * Called under jbd_lock_bh_state(bh).
+ */
+static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
+{
+ int may_free = 1;
+ struct buffer_head *bh = jh2bh(jh);
+
+ __jbd2_journal_unfile_buffer(jh);
+
+ if (jh->b_cp_transaction) {
+ JBUFFER_TRACE(jh, "on running+cp transaction");
+ __jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
+ clear_buffer_jbddirty(bh);
+ may_free = 0;
+ } else {
+ JBUFFER_TRACE(jh, "on running transaction");
+ jbd2_journal_remove_journal_head(bh);
+ __brelse(bh);
+ }
+ return may_free;
+}
+
+/*
+ * jbd2_journal_invalidatepage
+ *
+ * This code is tricky. It has a number of cases to deal with.
+ *
+ * There are two invariants which this code relies on:
+ *
+ * i_size must be updated on disk before we start calling invalidatepage on the
+ * data.
+ *
+ * This is done in ext3 by defining an ext3_setattr method which
+ * updates i_size before truncate gets going. By maintaining this
+ * invariant, we can be sure that it is safe to throw away any buffers
+ * attached to the current transaction: once the transaction commits,
+ * we know that the data will not be needed.
+ *
+ * Note however that we can *not* throw away data belonging to the
+ * previous, committing transaction!
+ *
+ * Any disk blocks which *are* part of the previous, committing
+ * transaction (and which therefore cannot be discarded immediately) are
+ * not going to be reused in the new running transaction
+ *
+ * The bitmap committed_data images guarantee this: any block which is
+ * allocated in one transaction and removed in the next will be marked
+ * as in-use in the committed_data bitmap, so cannot be reused until
+ * the next transaction to delete the block commits. This means that
+ * leaving committing buffers dirty is quite safe: the disk blocks
+ * cannot be reallocated to a different file and so buffer aliasing is
+ * not possible.
+ *
+ *
+ * The above applies mainly to ordered data mode. In writeback mode we
+ * don't make guarantees about the order in which data hits disk --- in
+ * particular we don't guarantee that new dirty data is flushed before
+ * transaction commit --- so it is always safe just to discard data
+ * immediately in that mode. --sct
+ */
+
+/*
+ * The journal_unmap_buffer helper function returns zero if the buffer
+ * concerned remains pinned as an anonymous buffer belonging to an older
+ * transaction.
+ *
+ * We're outside-transaction here. Either or both of j_running_transaction
+ * and j_committing_transaction may be NULL.
+ */
+static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh)
+{
+ transaction_t *transaction;
+ struct journal_head *jh;
+ int may_free = 1;
+ int ret;
+
+ BUFFER_TRACE(bh, "entry");
+
+ /*
+ * It is safe to proceed here without the j_list_lock because the
+ * buffers cannot be stolen by try_to_free_buffers as long as we are
+ * holding the page lock. --sct
+ */
+
+ if (!buffer_jbd(bh))
+ goto zap_buffer_unlocked;
+
+ spin_lock(&journal->j_state_lock);
+ jbd_lock_bh_state(bh);
+ spin_lock(&journal->j_list_lock);
+
+ jh = jbd2_journal_grab_journal_head(bh);
+ if (!jh)
+ goto zap_buffer_no_jh;
+
+ transaction = jh->b_transaction;
+ if (transaction == NULL) {
+ /* First case: not on any transaction. If it
+ * has no checkpoint link, then we can zap it:
+ * it's a writeback-mode buffer so we don't care
+ * if it hits disk safely. */
+ if (!jh->b_cp_transaction) {
+ JBUFFER_TRACE(jh, "not on any transaction: zap");
+ goto zap_buffer;
+ }
+
+ if (!buffer_dirty(bh)) {
+ /* bdflush has written it. We can drop it now */
+ goto zap_buffer;
+ }
+
+ /* OK, it must be in the journal but still not
+ * written fully to disk: it's metadata or
+ * journaled data... */
+
+ if (journal->j_running_transaction) {
+ /* ... and once the current transaction has
+ * committed, the buffer won't be needed any
+ * longer. */
+ JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget");
+ ret = __dispose_buffer(jh,
+ journal->j_running_transaction);
+ jbd2_journal_put_journal_head(jh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ spin_unlock(&journal->j_state_lock);
+ return ret;
+ } else {
+ /* There is no currently-running transaction. So the
+ * orphan record which we wrote for this file must have
+ * passed into commit. We must attach this buffer to
+ * the committing transaction, if it exists. */
+ if (journal->j_committing_transaction) {
+ JBUFFER_TRACE(jh, "give to committing trans");
+ ret = __dispose_buffer(jh,
+ journal->j_committing_transaction);
+ jbd2_journal_put_journal_head(jh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ spin_unlock(&journal->j_state_lock);
+ return ret;
+ } else {
+ /* The orphan record's transaction has
+ * committed. We can cleanse this buffer */
+ clear_buffer_jbddirty(bh);
+ goto zap_buffer;
+ }
+ }
+ } else if (transaction == journal->j_committing_transaction) {
+ if (jh->b_jlist == BJ_Locked) {
+ /*
+ * The buffer is on the committing transaction's locked
+ * list. We have the buffer locked, so I/O has
+ * completed. So we can nail the buffer now.
+ */
+ may_free = __dispose_buffer(jh, transaction);
+ goto zap_buffer;
+ }
+ /*
+ * If it is committing, we simply cannot touch it. We
+ * can remove it's next_transaction pointer from the
+ * running transaction if that is set, but nothing
+ * else. */
+ JBUFFER_TRACE(jh, "on committing transaction");
+ set_buffer_freed(bh);
+ if (jh->b_next_transaction) {
+ J_ASSERT(jh->b_next_transaction ==
+ journal->j_running_transaction);
+ jh->b_next_transaction = NULL;
+ }
+ jbd2_journal_put_journal_head(jh);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ spin_unlock(&journal->j_state_lock);
+ return 0;
+ } else {
+ /* Good, the buffer belongs to the running transaction.
+ * We are writing our own transaction's data, not any
+ * previous one's, so it is safe to throw it away
+ * (remember that we expect the filesystem to have set
+ * i_size already for this truncate so recovery will not
+ * expose the disk blocks we are discarding here.) */
+ J_ASSERT_JH(jh, transaction == journal->j_running_transaction);
+ may_free = __dispose_buffer(jh, transaction);
+ }
+
+zap_buffer:
+ jbd2_journal_put_journal_head(jh);
+zap_buffer_no_jh:
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh);
+ spin_unlock(&journal->j_state_lock);
+zap_buffer_unlocked:
+ clear_buffer_dirty(bh);
+ J_ASSERT_BH(bh, !buffer_jbddirty(bh));
+ clear_buffer_mapped(bh);
+ clear_buffer_req(bh);
+ clear_buffer_new(bh);
+ bh->b_bdev = NULL;
+ return may_free;
+}
+
+/**
+ * void jbd2_journal_invalidatepage()
+ * @journal: journal to use for flush...
+ * @page: page to flush
+ * @offset: length of page to invalidate.
+ *
+ * Reap page buffers containing data after offset in page.
+ *
+ */
+void jbd2_journal_invalidatepage(journal_t *journal,
+ struct page *page,
+ unsigned long offset)
+{
+ struct buffer_head *head, *bh, *next;
+ unsigned int curr_off = 0;
+ int may_free = 1;
+
+ if (!PageLocked(page))
+ BUG();
+ if (!page_has_buffers(page))
+ return;
+
+ /* We will potentially be playing with lists other than just the
+ * data lists (especially for journaled data mode), so be
+ * cautious in our locking. */
+
+ head = bh = page_buffers(page);
+ do {
+ unsigned int next_off = curr_off + bh->b_size;
+ next = bh->b_this_page;
+
+ if (offset <= curr_off) {
+ /* This block is wholly outside the truncation point */
+ lock_buffer(bh);
+ may_free &= journal_unmap_buffer(journal, bh);
+ unlock_buffer(bh);
+ }
+ curr_off = next_off;
+ bh = next;
+
+ } while (bh != head);
+
+ if (!offset) {
+ if (may_free && try_to_free_buffers(page))
+ J_ASSERT(!page_has_buffers(page));
+ }
+}
+
+/*
+ * File a buffer on the given transaction list.
+ */
+void __jbd2_journal_file_buffer(struct journal_head *jh,
+ transaction_t *transaction, int jlist)
+{
+ struct journal_head **list = NULL;
+ int was_dirty = 0;
+ struct buffer_head *bh = jh2bh(jh);
+
+ J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+ assert_spin_locked(&transaction->t_journal->j_list_lock);
+
+ J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
+ J_ASSERT_JH(jh, jh->b_transaction == transaction ||
+ jh->b_transaction == 0);
+
+ if (jh->b_transaction && jh->b_jlist == jlist)
+ return;
+
+ /* The following list of buffer states needs to be consistent
+ * with __jbd_unexpected_dirty_buffer()'s handling of dirty
+ * state. */
+
+ if (jlist == BJ_Metadata || jlist == BJ_Reserved ||
+ jlist == BJ_Shadow || jlist == BJ_Forget) {
+ if (test_clear_buffer_dirty(bh) ||
+ test_clear_buffer_jbddirty(bh))
+ was_dirty = 1;
+ }
+
+ if (jh->b_transaction)
+ __jbd2_journal_temp_unlink_buffer(jh);
+ jh->b_transaction = transaction;
+
+ switch (jlist) {
+ case BJ_None:
+ J_ASSERT_JH(jh, !jh->b_committed_data);
+ J_ASSERT_JH(jh, !jh->b_frozen_data);
+ return;
+ case BJ_SyncData:
+ list = &transaction->t_sync_datalist;
+ break;
+ case BJ_Metadata:
+ transaction->t_nr_buffers++;
+ list = &transaction->t_buffers;
+ break;
+ case BJ_Forget:
+ list = &transaction->t_forget;
+ break;
+ case BJ_IO:
+ list = &transaction->t_iobuf_list;
+ break;
+ case BJ_Shadow:
+ list = &transaction->t_shadow_list;
+ break;
+ case BJ_LogCtl:
+ list = &transaction->t_log_list;
+ break;
+ case BJ_Reserved:
+ list = &transaction->t_reserved_list;
+ break;
+ case BJ_Locked:
+ list = &transaction->t_locked_list;
+ break;
+ }
+
+ __blist_add_buffer(list, jh);
+ jh->b_jlist = jlist;
+
+ if (was_dirty)
+ set_buffer_jbddirty(bh);
+}
+
+void jbd2_journal_file_buffer(struct journal_head *jh,
+ transaction_t *transaction, int jlist)
+{
+ jbd_lock_bh_state(jh2bh(jh));
+ spin_lock(&transaction->t_journal->j_list_lock);
+ __jbd2_journal_file_buffer(jh, transaction, jlist);
+ spin_unlock(&transaction->t_journal->j_list_lock);
+ jbd_unlock_bh_state(jh2bh(jh));
+}
+
+/*
+ * Remove a buffer from its current buffer list in preparation for
+ * dropping it from its current transaction entirely. If the buffer has
+ * already started to be used by a subsequent transaction, refile the
+ * buffer on that transaction's metadata list.
+ *
+ * Called under journal->j_list_lock
+ *
+ * Called under jbd_lock_bh_state(jh2bh(jh))
+ */
+void __jbd2_journal_refile_buffer(struct journal_head *jh)
+{
+ int was_dirty;
+ struct buffer_head *bh = jh2bh(jh);
+
+ J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+ if (jh->b_transaction)
+ assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock);
+
+ /* If the buffer is now unused, just drop it. */
+ if (jh->b_next_transaction == NULL) {
+ __jbd2_journal_unfile_buffer(jh);
+ return;
+ }
+
+ /*
+ * It has been modified by a later transaction: add it to the new
+ * transaction's metadata list.
+ */
+
+ was_dirty = test_clear_buffer_jbddirty(bh);
+ __jbd2_journal_temp_unlink_buffer(jh);
+ jh->b_transaction = jh->b_next_transaction;
+ jh->b_next_transaction = NULL;
+ __jbd2_journal_file_buffer(jh, jh->b_transaction,
+ was_dirty ? BJ_Metadata : BJ_Reserved);
+ J_ASSERT_JH(jh, jh->b_transaction->t_state == T_RUNNING);
+
+ if (was_dirty)
+ set_buffer_jbddirty(bh);
+}
+
+/*
+ * For the unlocked version of this call, also make sure that any
+ * hanging journal_head is cleaned up if necessary.
+ *
+ * __jbd2_journal_refile_buffer is usually called as part of a single locked
+ * operation on a buffer_head, in which the caller is probably going to
+ * be hooking the journal_head onto other lists. In that case it is up
+ * to the caller to remove the journal_head if necessary. For the
+ * unlocked jbd2_journal_refile_buffer call, the caller isn't going to be
+ * doing anything else to the buffer so we need to do the cleanup
+ * ourselves to avoid a jh leak.
+ *
+ * *** The journal_head may be freed by this call! ***
+ */
+void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh)
+{
+ struct buffer_head *bh = jh2bh(jh);
+
+ jbd_lock_bh_state(bh);
+ spin_lock(&journal->j_list_lock);
+
+ __jbd2_journal_refile_buffer(jh);
+ jbd_unlock_bh_state(bh);
+ jbd2_journal_remove_journal_head(bh);
+
+ spin_unlock(&journal->j_list_lock);
+ __brelse(bh);
+}
which means just 'no padding', without the alignment
thing. But GCC doesn't have that -- we have to just
hope the structs are the right sizes, instead. */
- BUG_ON(sizeof(struct jffs2_unknown_node) != 12);
- BUG_ON(sizeof(struct jffs2_raw_dirent) != 40);
- BUG_ON(sizeof(struct jffs2_raw_inode) != 68);
- BUG_ON(sizeof(struct jffs2_raw_summary) != 32);
+ BUILD_BUG_ON(sizeof(struct jffs2_unknown_node) != 12);
+ BUILD_BUG_ON(sizeof(struct jffs2_raw_dirent) != 40);
+ BUILD_BUG_ON(sizeof(struct jffs2_raw_inode) != 68);
+ BUILD_BUG_ON(sizeof(struct jffs2_raw_summary) != 32);
printk(KERN_INFO "JFFS2 version 2.2."
#ifdef CONFIG_JFFS2_FS_WRITEBUFFER
/* Obtain client and file */
if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now check for conflicting locks */
resp->status = nlmsvc_testlock(file, &argp->lock, &resp->lock);
/* Obtain client and file */
if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
#if 0
/* If supplied state doesn't match current state, we assume it's
/* Obtain client and file */
if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Try to cancel request. */
resp->status = nlmsvc_cancel_blocked(file, &argp->lock);
/* Obtain client and file */
if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now try to remove the lock */
resp->status = nlmsvc_unlock(file, &argp->lock);
/* Obtain client and file */
if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now try to create the share */
resp->status = nlmsvc_share_file(host, file, argp);
/* Obtain client and file */
if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now try to lock the file */
resp->status = nlmsvc_unshare_file(host, file, argp);
struct nlm_host *host = NULL;
struct nlm_file *file = NULL;
struct nlm_lock *lock = &argp->lock;
- u32 error;
+ u32 error = 0;
/* nfsd callbacks must have been installed for this procedure */
if (!nlmsvc_ops)
no_locks:
if (host)
nlm_release_host(host);
+ if (error)
+ return error;
return nlm_lck_denied_nolocks;
}
/* Obtain client and file */
if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now check for conflicting locks */
resp->status = cast_status(nlmsvc_testlock(file, &argp->lock, &resp->lock));
/* Obtain client and file */
if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
#if 0
/* If supplied state doesn't match current state, we assume it's
/* Obtain client and file */
if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Try to cancel request. */
resp->status = cast_status(nlmsvc_cancel_blocked(file, &argp->lock));
/* Obtain client and file */
if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now try to remove the lock */
resp->status = cast_status(nlmsvc_unlock(file, &argp->lock));
/* Obtain client and file */
if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now try to create the share */
resp->status = cast_status(nlmsvc_share_file(host, file, argp));
/* Obtain client and file */
if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file)))
- return rpc_success;
+ return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
/* Now try to unshare the file */
resp->status = cast_status(nlmsvc_unshare_file(host, file, argp));
out_free:
kfree(file);
-#ifdef CONFIG_LOCKD_V4
- if (nfserr == 1)
- nfserr = nlm4_stale_fh;
- else
-#endif
- nfserr = nlm_lck_denied;
goto out_unlock;
}
static int
nlmsvc_is_client(struct nlm_host *host, struct nlm_host *dummy)
{
- return host->h_server;
+ if (host->h_server) {
+ /* we are destroying locks even though the client
+ * hasn't asked us too, so don't unmonitor the
+ * client
+ */
+ if (host->h_nsmhandle)
+ host->h_nsmhandle->sm_sticky = 1;
+ return 1;
+ } else
+ return 0;
}
/*
return -ENOMEM;
s->s_fs_info = sbi;
- /* N.B. These should be compile-time tests.
- Unfortunately that is impossible. */
- if (32 != sizeof (struct minix_inode))
- panic("bad V1 i-node size");
- if (64 != sizeof(struct minix2_inode))
- panic("bad V2 i-node size");
+ BUILD_BUG_ON(32 != sizeof (struct minix_inode));
+ BUILD_BUG_ON(64 != sizeof(struct minix2_inode));
if (!sb_set_blocksize(s, BLOCK_SIZE))
goto out_bad_hblock;
fh_put(&fh);
rqstp->rq_client = NULL;
exp_readunlock();
- /* nlm and nfsd don't share error codes.
- * we invent: 0 = no error
- * 1 = stale file handle
- * 2 = other error
+ /* We return nlm error codes as nlm doesn't know
+ * about nfsd, but nfsd does know about nlm..
*/
switch (nfserr) {
case nfs_ok:
return 0;
+ case nfserr_dropit:
+ return nlm_drop_reply;
+#ifdef CONFIG_LOCKD_V4
case nfserr_stale:
- return 1;
+ return nlm4_stale_fh;
+#endif
default:
- return 2;
+ return nlm_lck_denied;
}
}
/* Create RPC client */
cb->cb_client = rpc_create(&args);
- if (!cb->cb_client) {
+ if (IS_ERR(cb->cb_client)) {
dprintk("NFSD: couldn't create callback client\n");
goto out_err;
}
out_rpciod:
atomic_dec(&clp->cl_count);
rpciod_down();
- cb->cb_client = NULL;
out_clnt:
rpc_shutdown_client(cb->cb_client);
out_err:
+ cb->cb_client = NULL;
dprintk("NFSD: warning: no callback path to client %.*s\n",
(int)clp->cl_name.len, clp->cl_name.data);
}
}
static int
-do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
+do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open, int accmode)
{
- int accmode, status;
+ int status;
if (open->op_truncate &&
!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
return nfserr_inval;
- accmode = MAY_NOP;
if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
- accmode = MAY_READ;
- if (open->op_share_deny & NFS4_SHARE_ACCESS_WRITE)
+ accmode |= MAY_READ;
+ if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
accmode |= (MAY_WRITE | MAY_TRUNC);
- accmode |= MAY_OWNER_OVERRIDE;
+ if (open->op_share_deny & NFS4_SHARE_DENY_WRITE)
+ accmode |= MAY_WRITE;
status = fh_verify(rqstp, current_fh, S_IFREG, accmode);
&resfh.fh_handle.fh_base,
resfh.fh_handle.fh_size);
- status = do_open_permission(rqstp, current_fh, open);
+ status = do_open_permission(rqstp, current_fh, open, MAY_NOP);
}
fh_put(&resfh);
open->op_truncate = (open->op_iattr.ia_valid & ATTR_SIZE) &&
(open->op_iattr.ia_size == 0);
- status = do_open_permission(rqstp, current_fh, open);
+ status = do_open_permission(rqstp, current_fh, open, MAY_OWNER_OVERRIDE);
return status;
}
#if BITS_PER_LONG == 32
# if defined(CONFIG_LBD)
- BUG_ON(sizeof(sector_t) != 8);
+ BUILD_BUG_ON(sizeof(sector_t) != 8);
pagefactor = PAGE_CACHE_SIZE;
bitshift = BITS_PER_LONG;
# else
return name;
}
-static void disk_sysfs_symlinks(struct gendisk *disk)
+static int disk_sysfs_symlinks(struct gendisk *disk)
{
struct device *target = get_device(disk->driverfs_dev);
+ int err;
+ char *disk_name = NULL;
+
if (target) {
- char *disk_name = make_block_name(disk);
- sysfs_create_link(&disk->kobj,&target->kobj,"device");
- if (disk_name) {
- sysfs_create_link(&target->kobj,&disk->kobj,disk_name);
- kfree(disk_name);
+ disk_name = make_block_name(disk);
+ if (!disk_name) {
+ err = -ENOMEM;
+ goto err_out;
}
+
+ err = sysfs_create_link(&disk->kobj, &target->kobj, "device");
+ if (err)
+ goto err_out_disk_name;
+
+ err = sysfs_create_link(&target->kobj, &disk->kobj, disk_name);
+ if (err)
+ goto err_out_dev_link;
}
- sysfs_create_link(&disk->kobj, &block_subsys.kset.kobj, "subsystem");
+
+ err = sysfs_create_link(&disk->kobj, &block_subsys.kset.kobj,
+ "subsystem");
+ if (err)
+ goto err_out_disk_name_lnk;
+
+ kfree(disk_name);
+
+ return 0;
+
+err_out_disk_name_lnk:
+ if (target) {
+ sysfs_remove_link(&target->kobj, disk_name);
+err_out_dev_link:
+ sysfs_remove_link(&disk->kobj, "device");
+err_out_disk_name:
+ kfree(disk_name);
+err_out:
+ put_device(target);
+ }
+ return err;
}
/* Not exported, helper to add_disk(). */
*s = '!';
if ((err = kobject_add(&disk->kobj)))
return;
- disk_sysfs_symlinks(disk);
+ err = disk_sysfs_symlinks(disk);
+ if (err) {
+ kobject_del(&disk->kobj);
+ return;
+ }
disk_sysfs_add_subdirs(disk);
/* No minors to use for partitions */
/* Worst case buffer size needed for holding an integer. */
-#define PROC_NUMBUF 10
+#define PROC_NUMBUF 13
struct pid_entry {
int len;
return journal_end(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT);
}
-static void reiserfs_put_super(struct super_block *s)
+static void reiserfs_kill_sb(struct super_block *s)
{
- struct reiserfs_transaction_handle th;
- th.t_trans_id = 0;
+ if (REISERFS_SB(s)) {
+ if (REISERFS_SB(s)->xattr_root) {
+ d_invalidate(REISERFS_SB(s)->xattr_root);
+ dput(REISERFS_SB(s)->xattr_root);
+ REISERFS_SB(s)->xattr_root = NULL;
+ }
- if (REISERFS_SB(s)->xattr_root) {
- d_invalidate(REISERFS_SB(s)->xattr_root);
- dput(REISERFS_SB(s)->xattr_root);
+ if (REISERFS_SB(s)->priv_root) {
+ d_invalidate(REISERFS_SB(s)->priv_root);
+ dput(REISERFS_SB(s)->priv_root);
+ REISERFS_SB(s)->priv_root = NULL;
+ }
}
- if (REISERFS_SB(s)->priv_root) {
- d_invalidate(REISERFS_SB(s)->priv_root);
- dput(REISERFS_SB(s)->priv_root);
- }
+ kill_block_super(s);
+}
+
+static void reiserfs_put_super(struct super_block *s)
+{
+ struct reiserfs_transaction_handle th;
+ th.t_trans_id = 0;
/* change file system state to current state if it was mounted with read-write permissions */
if (!(s->s_flags & MS_RDONLY)) {
.owner = THIS_MODULE,
.name = "reiserfs",
.get_sb = get_super_block,
- .kill_sb = kill_block_super,
+ .kill_sb = reiserfs_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
ret = -ENOMEM;
page = page_cache_alloc_cold(mapping);
if (unlikely(!page))
- goto out_nomem;
+ goto out_ret;
/*
* This will also lock the page
if (sd->pos + this_len > isize)
vmtruncate(mapping->host, isize);
- goto out;
+ goto out_ret;
}
if (buf->page != page) {
out:
page_cache_release(page);
unlock_page(page);
-out_nomem:
+out_ret:
return ret;
}
* that need destruction out of superblock, call generic_shutdown_super()
* and release aforementioned objects. Note: dentries and inodes _are_
* taken care of and do not need specific handling.
+ *
+ * Upon calling this function, the filesystem may no longer alter or
+ * rearrange the set of dentries belonging to this super_block, nor may it
+ * change the attachments of dentries to inodes.
*/
void generic_shutdown_super(struct super_block *sb)
{
- struct dentry *root = sb->s_root;
struct super_operations *sop = sb->s_op;
- if (root) {
- sb->s_root = NULL;
- shrink_dcache_parent(root);
- shrink_dcache_sb(sb);
- dput(root);
+ if (sb->s_root) {
+ shrink_dcache_for_umount(sb);
fsync_super(sb);
lock_super(sb);
sb->s_flags &= ~MS_ACTIVE;
unsigned long blocknr;
int size = 0, i;
- if (1024 != sizeof (struct xenix_super_block))
- panic("Xenix FS: bad superblock size");
- if (512 != sizeof (struct sysv4_super_block))
- panic("SystemV FS: bad superblock size");
- if (512 != sizeof (struct sysv2_super_block))
- panic("SystemV FS: bad superblock size");
- if (500 != sizeof (struct coh_super_block))
- panic("Coherent FS: bad superblock size");
- if (64 != sizeof (struct sysv_inode))
- panic("sysv fs: bad inode size");
+ BUILD_BUG_ON(1024 != sizeof (struct xenix_super_block));
+ BUILD_BUG_ON(512 != sizeof (struct sysv4_super_block));
+ BUILD_BUG_ON(512 != sizeof (struct sysv2_super_block));
+ BUILD_BUG_ON(500 != sizeof (struct coh_super_block));
+ BUILD_BUG_ON(64 != sizeof (struct sysv_inode));
sbi = kzalloc(sizeof(struct sysv_sb_info), GFP_KERNEL);
if (!sbi)
#define ACPI_PDC_SMP_C_SWCOORD (0x0040)
#define ACPI_PDC_SMP_T_SWCOORD (0x0080)
#define ACPI_PDC_C_C1_FFH (0x0100)
+#define ACPI_PDC_C_C2C3_FFH (0x0200)
#define ACPI_PDC_EST_CAPABILITY_SMP (ACPI_PDC_SMP_C1PT | \
ACPI_PDC_C_C1_HALT | \
ACPI_PDC_SMP_P_SWCOORD | \
ACPI_PDC_P_FFH)
-#define ACPI_PDC_C_CAPABILITY_SMP (ACPI_PDC_SMP_C2C3 | \
- ACPI_PDC_SMP_C1PT | \
- ACPI_PDC_C_C1_HALT)
+#define ACPI_PDC_C_CAPABILITY_SMP (ACPI_PDC_SMP_C2C3 | \
+ ACPI_PDC_SMP_C1PT | \
+ ACPI_PDC_C_C1_HALT | \
+ ACPI_PDC_C_C1_FFH | \
+ ACPI_PDC_C_C2C3_FFH)
#endif /* __PDC_INTEL_H__ */
#define DOMAIN_COORD_TYPE_SW_ANY 0xfd
#define DOMAIN_COORD_TYPE_HW_ALL 0xfe
+#define ACPI_CSTATE_SYSTEMIO (0)
+#define ACPI_CSTATE_FFH (1)
+
/* Power Management */
struct acpi_processor_cx;
u8 valid;
u8 type;
u32 address;
+ u8 space_id;
+ u8 index;
u32 latency;
u32 latency_ticks;
u32 power;
#ifdef ARCH_HAS_POWER_INIT
void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
unsigned int cpu);
+int acpi_processor_ffh_cstate_probe(unsigned int cpu,
+ struct acpi_processor_cx *cx, struct acpi_power_register *reg);
+void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cstate);
#else
static inline void acpi_processor_power_init_bm_check(struct
acpi_processor_flags
flags->bm_check = 1;
return;
}
+static inline int acpi_processor_ffh_cstate_probe(unsigned int cpu,
+ struct acpi_processor_cx *cx, struct acpi_power_register *reg)
+{
+ return -1;
+}
+static inline void acpi_processor_ffh_cstate_enter(
+ struct acpi_processor_cx *cstate)
+{
+ return;
+}
#endif
/* in processor_perflib.c */
#define eth_io_copy_and_sum(skb,src,len,unused) \
memcpy_fromio((skb)->data,src,len)
-static inline int
-check_signature(const volatile void __iomem *io_addr,
- const unsigned char *signature, int length)
-{
- do {
- if (readb(io_addr) != *signature)
- return 0;
- io_addr++;
- signature++;
- } while (--length);
- return 1;
-}
-
/*
* The Alpha Jensen hardware for some rather strange reason puts
* the RTC clock at 0x170 instead of 0x70. Probably due to some
/*
* PCI space virtual addresses
*/
-#define VERSATILE_PCI_VIRT_BASE 0xe8000000
-#define VERSATILE_PCI_CFG_VIRT_BASE 0xe9000000
+#define VERSATILE_PCI_VIRT_BASE (void __iomem *)0xe8000000ul
+#define VERSATILE_PCI_CFG_VIRT_BASE (void __iomem *)0xe9000000ul
#if 0
#define VERSATILE_PCI_VIRT_MEM_BASE0 0xf4000000
#define eth_io_copy_and_sum(s,c,l,b) \
eth_copy_and_sum((s),__mem_pci(c),(l),(b))
-static inline int
-check_signature(void __iomem *io_addr, const unsigned char *signature,
- int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
#elif !defined(readb)
#define readb(c) (__readwrite_bug("readb"),0)
#define get_user(x,p) \
({ \
const register typeof(*(p)) __user *__p asm("r0") = (p);\
- register unsigned int __r2 asm("r2"); \
+ register unsigned long __r2 asm("r2"); \
register int __e asm("r0"); \
switch (sizeof(*(__p))) { \
case 1: \
--- /dev/null
+#include <asm-generic/irq_regs.h>
dampr = paddr | xAMPRx_L | xAMPRx_M | xAMPRx_S | xAMPRx_SS_16Kb | xAMPRx_V; \
\
if (type != __KM_CACHE) \
- asm volatile("movgs %0,dampr"#ampr :: "r"(dampr)); \
+ asm volatile("movgs %0,dampr"#ampr :: "r"(dampr) : "memory"); \
else \
asm volatile("movgs %0,iampr"#ampr"\n" \
"movgs %0,dampr"#ampr"\n" \
- :: "r"(dampr) \
+ :: "r"(dampr) : "memory" \
); \
\
asm("movsg damlr"#ampr",%0" : "=r"(damlr)); \
asm volatile("movgs %0,tplr \n" \
"movgs %1,tppr \n" \
"tlbpr %0,gr0,#2,#1" \
- : : "r"(damlr), "r"(dampr)); \
+ : : "r"(damlr), "r"(dampr) : "memory"); \
\
/*printk("TLB: SECN sl=%d L=%08lx P=%08lx\n", slot, damlr, dampr);*/ \
\
{
unsigned long paddr;
- preempt_disable();
+ inc_preempt_count();
paddr = page_to_phys(page);
switch (type) {
}
}
-#define __kunmap_atomic_primary(type, ampr) \
-do { \
- asm volatile("movgs gr0,dampr"#ampr"\n"); \
- if (type == __KM_CACHE) \
- asm volatile("movgs gr0,iampr"#ampr"\n"); \
+#define __kunmap_atomic_primary(type, ampr) \
+do { \
+ asm volatile("movgs gr0,dampr"#ampr"\n" ::: "memory"); \
+ if (type == __KM_CACHE) \
+ asm volatile("movgs gr0,iampr"#ampr"\n" ::: "memory"); \
} while(0)
-#define __kunmap_atomic_secondary(slot, vaddr) \
-do { \
- asm volatile("tlbpr %0,gr0,#4,#1" : : "r"(vaddr)); \
+#define __kunmap_atomic_secondary(slot, vaddr) \
+do { \
+ asm volatile("tlbpr %0,gr0,#4,#1" : : "r"(vaddr) : "memory"); \
} while(0)
static inline void kunmap_atomic(void *kvaddr, enum km_type type)
default:
BUG();
}
- preempt_enable();
+ dec_preempt_count();
+ preempt_check_resched();
}
#endif /* !__ASSEMBLY__ */
*/
#define xlate_dev_kmem_ptr(p) p
-/*
- * Check BIOS signature
- */
-static inline int check_signature(volatile void __iomem *io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
-
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
-
- retval = 1;
-out:
- return retval;
-}
-
#endif /* __KERNEL__ */
#endif /* _ASM_IO_H */
#if BITS_PER_LONG == 64
if (unlikely(b[0]))
return __ffs(b[0]);
- if (unlikely(b[1]))
+ if (likely(b[1]))
return __ffs(b[1]) + 64;
return __ffs(b[2]) + 128;
#elif BITS_PER_LONG == 32
#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void __force *)(b),(c),(d))
-/**
- * check_signature - find BIOS signatures
- * @io_addr: mmio address to check
- * @signature: signature block
- * @length: length of signature
- *
- * Perform a signature comparison with the mmio address io_addr. This
- * address should have been obtained by ioremap.
- * Returns 1 on a match.
- */
-
-static inline int check_signature(volatile void __iomem * io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
/*
* Cache management
*
: :"a" (eax), "c" (ecx));
}
+extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
+
/* from system description table in BIOS. Mostly for MCA use, but
others may find it useful. */
extern unsigned int machine_id;
* anything, so this is accurate.
*/
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
static __always_inline unsigned long __must_check
__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
{
return __copy_to_user_ll(to, from, n);
}
-static __always_inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- might_sleep();
- return __copy_to_user_inatomic(to, from, n);
-}
-
/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
+ * __copy_to_user: - Copy a block of data into user space, with less checking.
+ * @to: Destination address, in user space.
+ * @from: Source address, in kernel space.
* @n: Number of bytes to copy.
*
* Context: User context only. This function may sleep.
*
- * Copy data from user space to kernel space. Caller must check
+ * Copy data from kernel space to user space. Caller must check
* the specified block with access_ok() before calling this function.
*
* Returns number of bytes that could not be copied.
* On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- *
- * An alternate version - __copy_from_user_inatomic() - may be called from
- * atomic context and will fail rather than sleep. In this case the
- * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h
- * for explanation of why this is needed.
*/
+static __always_inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ might_sleep();
+ return __copy_to_user_inatomic(to, from, n);
+}
+
static __always_inline unsigned long
__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
{
}
return __copy_from_user_ll_nozero(to, from, n);
}
+
+/**
+ * __copy_from_user: - Copy a block of data from user space, with less checking.
+ * @to: Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n: Number of bytes to copy.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * Copy data from user space to kernel space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ *
+ * An alternate version - __copy_from_user_inatomic() - may be called from
+ * atomic context and will fail rather than sleep. In this case the
+ * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h
+ * for explanation of why this is needed.
+ */
static __always_inline unsigned long
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
#define __NR_vmsplice 316
#define __NR_move_pages 317
#define __NR_getcpu 318
+#define __NR_epoll_pwait 319
#ifdef __KERNEL__
-#define NR_syscalls 319
+#define NR_syscalls 320
#include <linux/err.h>
/*
#define VIC_BOOT_INTERRUPT_MASK 0xfe
-extern void smp_vic_timer_interrupt(struct pt_regs *regs);
+extern void smp_vic_timer_interrupt(void);
} voyager_module_t;
typedef struct voyager_eeprom_hdr {
- __u8 module_id[4] __attribute__((packed));
- __u8 version_id __attribute__((packed));
- __u8 config_id __attribute__((packed));
- __u16 boundry_id __attribute__((packed)); /* boundary scan id */
- __u16 ee_size __attribute__((packed)); /* size of EEPROM */
- __u8 assembly[11] __attribute__((packed)); /* assembly # */
- __u8 assembly_rev __attribute__((packed)); /* assembly rev */
- __u8 tracer[4] __attribute__((packed)); /* tracer number */
- __u16 assembly_cksum __attribute__((packed)); /* asm checksum */
- __u16 power_consump __attribute__((packed)); /* pwr requirements */
- __u16 num_asics __attribute__((packed)); /* number of asics */
- __u16 bist_time __attribute__((packed)); /* min. bist time */
- __u16 err_log_offset __attribute__((packed)); /* error log offset */
- __u16 scan_path_offset __attribute__((packed));/* scan path offset */
- __u16 cct_offset __attribute__((packed));
- __u16 log_length __attribute__((packed)); /* length of err log */
- __u16 xsum_end __attribute__((packed)); /* offset to end of
+ __u8 module_id[4];
+ __u8 version_id;
+ __u8 config_id;
+ __u16 boundry_id; /* boundary scan id */
+ __u16 ee_size; /* size of EEPROM */
+ __u8 assembly[11]; /* assembly # */
+ __u8 assembly_rev; /* assembly rev */
+ __u8 tracer[4]; /* tracer number */
+ __u16 assembly_cksum; /* asm checksum */
+ __u16 power_consump; /* pwr requirements */
+ __u16 num_asics; /* number of asics */
+ __u16 bist_time; /* min. bist time */
+ __u16 err_log_offset; /* error log offset */
+ __u16 scan_path_offset;/* scan path offset */
+ __u16 cct_offset;
+ __u16 log_length; /* length of err log */
+ __u16 xsum_end; /* offset to end of
checksum */
- __u8 reserved[4] __attribute__((packed));
- __u8 sflag __attribute__((packed)); /* starting sentinal */
- __u8 part_number[13] __attribute__((packed)); /* prom part number */
- __u8 version[10] __attribute__((packed)); /* version number */
- __u8 signature[8] __attribute__((packed));
- __u16 eeprom_chksum __attribute__((packed));
- __u32 data_stamp_offset __attribute__((packed));
- __u8 eflag __attribute__((packed)); /* ending sentinal */
-} voyager_eprom_hdr_t;
+ __u8 reserved[4];
+ __u8 sflag; /* starting sentinal */
+ __u8 part_number[13]; /* prom part number */
+ __u8 version[10]; /* version number */
+ __u8 signature[8];
+ __u16 eeprom_chksum;
+ __u32 data_stamp_offset;
+ __u8 eflag ; /* ending sentinal */
+} __attribute__((packed)) voyager_eprom_hdr_t;
* in the module EPROMs. We really only care about the IDs and
* offsets */
typedef struct voyager_sp_table {
- __u8 asic_id __attribute__((packed));
- __u8 bypass_flag __attribute__((packed));
- __u16 asic_data_offset __attribute__((packed));
- __u16 config_data_offset __attribute__((packed));
-} voyager_sp_table_t;
+ __u8 asic_id;
+ __u8 bypass_flag;
+ __u16 asic_data_offset;
+ __u16 config_data_offset;
+} __attribute__((packed)) voyager_sp_table_t;
typedef struct voyager_jtag_table {
- __u8 icode[4] __attribute__((packed));
- __u8 runbist[4] __attribute__((packed));
- __u8 intest[4] __attribute__((packed));
- __u8 samp_preld[4] __attribute__((packed));
- __u8 ireg_len __attribute__((packed));
-} voyager_jtt_t;
+ __u8 icode[4];
+ __u8 runbist[4];
+ __u8 intest[4];
+ __u8 samp_preld[4];
+ __u8 ireg_len;
+} __attribute__((packed)) voyager_jtt_t;
typedef struct voyager_asic_data_table {
- __u8 jtag_id[4] __attribute__((packed));
- __u16 length_bsr __attribute__((packed));
- __u16 length_bist_reg __attribute__((packed));
- __u32 bist_clk __attribute__((packed));
- __u16 subaddr_bits __attribute__((packed));
- __u16 seed_bits __attribute__((packed));
- __u16 sig_bits __attribute__((packed));
- __u16 jtag_offset __attribute__((packed));
-} voyager_at_t;
+ __u8 jtag_id[4];
+ __u16 length_bsr;
+ __u16 length_bist_reg;
+ __u32 bist_clk;
+ __u16 subaddr_bits;
+ __u16 seed_bits;
+ __u16 sig_bits;
+ __u16 jtag_offset;
+} __attribute__((packed)) voyager_at_t;
/* Voyager Interrupt Controller (VIC) registers */
#define NUMBER_OF_POS_REGS 8
typedef struct {
- __u8 MC_Slot __attribute__((packed));
- __u8 POS_Values[NUMBER_OF_POS_REGS] __attribute__((packed));
-} MC_SlotInformation_t;
+ __u8 MC_Slot;
+ __u8 POS_Values[NUMBER_OF_POS_REGS];
+} __attribute__((packed)) MC_SlotInformation_t;
struct QuadDescription {
- __u8 Type __attribute__((packed)); /* for type 0 (DYADIC or MONADIC) all fields
+ __u8 Type; /* for type 0 (DYADIC or MONADIC) all fields
* will be zero except for slot */
- __u8 StructureVersion __attribute__((packed));
- __u32 CPI_BaseAddress __attribute__((packed));
- __u32 LARC_BankSize __attribute__((packed));
- __u32 LocalMemoryStateBits __attribute__((packed));
- __u8 Slot __attribute__((packed)); /* Processor slots 1 - 4 */
-};
+ __u8 StructureVersion;
+ __u32 CPI_BaseAddress;
+ __u32 LARC_BankSize;
+ __u32 LocalMemoryStateBits;
+ __u8 Slot; /* Processor slots 1 - 4 */
+} __attribute__((packed));
struct ProcBoardInfo {
- __u8 Type __attribute__((packed));
- __u8 StructureVersion __attribute__((packed));
- __u8 NumberOfBoards __attribute__((packed));
- struct QuadDescription QuadData[MAX_PROCESSOR_BOARDS] __attribute__((packed));
-};
+ __u8 Type;
+ __u8 StructureVersion;
+ __u8 NumberOfBoards;
+ struct QuadDescription QuadData[MAX_PROCESSOR_BOARDS];
+} __attribute__((packed));
struct CacheDescription {
- __u8 Level __attribute__((packed));
- __u32 TotalSize __attribute__((packed));
- __u16 LineSize __attribute__((packed));
- __u8 Associativity __attribute__((packed));
- __u8 CacheType __attribute__((packed));
- __u8 WriteType __attribute__((packed));
- __u8 Number_CPUs_SharedBy __attribute__((packed));
- __u8 Shared_CPUs_Hardware_IDs[MAX_SHARED_CPUS] __attribute__((packed));
+ __u8 Level;
+ __u32 TotalSize;
+ __u16 LineSize;
+ __u8 Associativity;
+ __u8 CacheType;
+ __u8 WriteType;
+ __u8 Number_CPUs_SharedBy;
+ __u8 Shared_CPUs_Hardware_IDs[MAX_SHARED_CPUS];
-};
+} __attribute__((packed));
struct CPU_Description {
- __u8 CPU_HardwareId __attribute__((packed));
- char *FRU_String __attribute__((packed));
- __u8 NumberOfCacheLevels __attribute__((packed));
- struct CacheDescription CacheLevelData[MAX_CACHE_LEVELS] __attribute__((packed));
-};
+ __u8 CPU_HardwareId;
+ char *FRU_String;
+ __u8 NumberOfCacheLevels;
+ struct CacheDescription CacheLevelData[MAX_CACHE_LEVELS];
+} __attribute__((packed));
struct CPU_Info {
- __u8 Type __attribute__((packed));
- __u8 StructureVersion __attribute__((packed));
- __u8 NumberOf_CPUs __attribute__((packed));
- struct CPU_Description CPU_Data[MAX_CPUS] __attribute__((packed));
-};
+ __u8 Type;
+ __u8 StructureVersion;
+ __u8 NumberOf_CPUs;
+ struct CPU_Description CPU_Data[MAX_CPUS];
+} __attribute__((packed));
/*
#define flush_write_buffers() do { } while (0) /* M32R_FIXME */
-/**
- * check_signature - find BIOS signatures
- * @io_addr: mmio address to check
- * @signature: signature block
- * @length: length of signature
- *
- * Perform a signature comparison with the ISA mmio address io_addr.
- * Returns 1 on a match.
- *
- * This function is deprecated. New drivers should use ioremap and
- * check_signature.
- */
-
-static inline int check_signature(void __iomem *io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
-#if 0
-printk("check_signature\n");
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
-#endif
- return retval;
-}
-
static inline void
memset_io(volatile void __iomem *addr, unsigned char val, int count)
{
#ifndef __SUN3_MMU_H__
#define __SUN3_MMU_H__
+#include <linux/types.h>
#include <asm/movs.h>
#include <asm/sun3-head.h>
return;
}
-extern void *sun3_ioremap(unsigned long phys, unsigned long size,
+extern void __iomem *sun3_ioremap(unsigned long phys, unsigned long size,
unsigned long type);
extern int sun3_map_test(unsigned long addr, char *val);
break; \
case 8: \
{ \
- const void *__pu_ptr = (ptr); \
+ const void __user *__pu_ptr = (ptr); \
asm volatile ("\n" \
"1: moves.l %2,(%1)+\n" \
"2: moves.l %R2,(%1)\n" \
" .previous" \
: "+d" (res), "=&" #reg (__gu_val) \
: "m" (*(ptr)), "i" (err)); \
- (x) = (typeof(*(ptr)))(long)__gu_val; \
+ (x) = (typeof(*(ptr)))(unsigned long)__gu_val; \
})
#define __get_user(x, ptr) \
switch (n) {
case 1:
- __get_user_asm(res, *(u8 *)to, (u8 *)from, u8, b, d, 1);
+ __get_user_asm(res, *(u8 *)to, (u8 __user *)from, u8, b, d, 1);
break;
case 2:
- __get_user_asm(res, *(u16 *)to, (u16 *)from, u16, w, d, 2);
+ __get_user_asm(res, *(u16 *)to, (u16 __user *)from, u16, w, d, 2);
break;
case 3:
__constant_copy_from_user_asm(res, to, from, tmp, 3, w, b,);
break;
case 4:
- __get_user_asm(res, *(u32 *)to, (u32 *)from, u32, l, r, 4);
+ __get_user_asm(res, *(u32 *)to, (u32 __user *)from, u32, l, r, 4);
break;
case 5:
__constant_copy_from_user_asm(res, to, from, tmp, 5, l, b,);
switch (n) {
case 1:
- __put_user_asm(res, *(u8 *)from, (u8 *)to, b, d, 1);
+ __put_user_asm(res, *(u8 *)from, (u8 __user *)to, b, d, 1);
break;
case 2:
- __put_user_asm(res, *(u16 *)from, (u16 *)to, w, d, 2);
+ __put_user_asm(res, *(u16 *)from, (u16 __user *)to, w, d, 2);
break;
case 3:
__constant_copy_to_user_asm(res, to, from, tmp, 3, w, b,);
break;
case 4:
- __put_user_asm(res, *(u32 *)from, (u32 *)to, l, r, 4);
+ __put_user_asm(res, *(u32 *)from, (u32 __user *)to, l, r, 4);
break;
case 5:
__constant_copy_to_user_asm(res, to, from, tmp, 5, l, b,);
#define __NR_mq_notify 275
#define __NR_mq_getsetattr 276
#define __NR_waitid 277
-#define __NR_sys_setaltroot 278
+#define __NR_vserver 278
#define __NR_add_key 279
#define __NR_request_key 280
#define __NR_keyctl 281
-
+#define __NR_ioprio_set 282
+#define __NR_ioprio_get 283
+#define __NR_inotify_init 284
+#define __NR_inotify_add_watch 285
+#define __NR_inotify_rm_watch 286
+#define __NR_migrate_pages 287
+#define __NR_openat 288
+#define __NR_mkdirat 289
+#define __NR_mknodat 290
+#define __NR_fchownat 291
+#define __NR_futimesat 292
+#define __NR_fstatat64 293
+#define __NR_unlinkat 294
+#define __NR_renameat 295
+#define __NR_linkat 296
+#define __NR_symlinkat 297
+#define __NR_readlinkat 298
+#define __NR_fchmodat 299
+#define __NR_faccessat 300
+#define __NR_pselect6 301
+#define __NR_ppoll 302
+#define __NR_unshare 303
+#define __NR_set_robust_list 304
+#define __NR_get_robust_list 305
+#define __NR_splice 306
+#define __NR_sync_file_range 307
+#define __NR_tee 308
+#define __NR_vmsplice 309
+#define __NR_move_pages 310
+
#ifdef __KERNEL__
-#define NR_syscalls 282
+#define NR_syscalls 311
#include <linux/err.h>
/* user-visible error numbers are in the range -1 - -MAX_ERRNO: see
*/
#define eth_io_copy_and_sum(skb,src,len,unused) memcpy_fromio((skb)->data,(src),(len))
-/*
- * check_signature - find BIOS signatures
- * @io_addr: mmio address to check
- * @signature: signature block
- * @length: length of signature
- *
- * Perform a signature comparison with the mmio address io_addr. This
- * address should have been obtained by ioremap.
- * Returns 1 on a match.
- */
-static inline int check_signature(char __iomem *io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
/*
* The caches on some architectures aren't dma-coherent and have need to
* handle this in software. There are three types of operations that
#define irq_canonicalize(irq) (irq) /* Sane hardware, sane code ... */
#endif
-struct pt_regs;
-
extern asmlinkage unsigned int do_IRQ(unsigned int irq);
#ifdef CONFIG_MIPS_MT_SMTC
.endm
#ifdef CONFIG_SMP
- .macro get_saved_sp /* SMP variation */
-#ifdef CONFIG_32BIT
#ifdef CONFIG_MIPS_MT_SMTC
- .set mips32
- mfc0 k0, CP0_TCBIND;
- .set mips0
- lui k1, %hi(kernelsp)
- srl k0, k0, 19
- /* No need to shift down and up to clear bits 0-1 */
+#define PTEBASE_SHIFT 19 /* TCBIND */
#else
- mfc0 k0, CP0_CONTEXT
- lui k1, %hi(kernelsp)
- srl k0, k0, 23
-#endif
- addu k1, k0
- LONG_L k1, %lo(kernelsp)(k1)
+#define PTEBASE_SHIFT 23 /* CONTEXT */
#endif
-#ifdef CONFIG_64BIT
+ .macro get_saved_sp /* SMP variation */
#ifdef CONFIG_MIPS_MT_SMTC
- .set mips64
- mfc0 k0, CP0_TCBIND;
- .set mips0
- lui k0, %highest(kernelsp)
- dsrl k1, 19
- /* No need to shift down and up to clear bits 0-2 */
+ mfc0 k0, CP0_TCBIND
#else
- MFC0 k1, CP0_CONTEXT
- lui k0, %highest(kernelsp)
- dsrl k1, 23
- daddiu k0, %higher(kernelsp)
- dsll k0, k0, 16
- daddiu k0, %hi(kernelsp)
- dsll k0, k0, 16
-#endif /* CONFIG_MIPS_MT_SMTC */
- daddu k1, k1, k0
+ MFC0 k0, CP0_CONTEXT
+#endif
+#if defined(CONFIG_BUILD_ELF64) || (defined(CONFIG_64BIT) && __GNUC__ < 4)
+ lui k1, %highest(kernelsp)
+ daddiu k1, %higher(kernelsp)
+ dsll k1, 16
+ daddiu k1, %hi(kernelsp)
+ dsll k1, 16
+#else
+ lui k1, %hi(kernelsp)
+#endif
+ LONG_SRL k0, PTEBASE_SHIFT
+ LONG_ADDU k1, k0
LONG_L k1, %lo(kernelsp)(k1)
-#endif /* CONFIG_64BIT */
.endm
.macro set_saved_sp stackp temp temp2
-#ifdef CONFIG_32BIT
-#ifdef CONFIG_MIPS_MT_SMTC
- mfc0 \temp, CP0_TCBIND
- srl \temp, 19
-#else
- mfc0 \temp, CP0_CONTEXT
- srl \temp, 23
-#endif
-#endif
-#ifdef CONFIG_64BIT
#ifdef CONFIG_MIPS_MT_SMTC
mfc0 \temp, CP0_TCBIND
- dsrl \temp, 19
#else
MFC0 \temp, CP0_CONTEXT
- dsrl \temp, 23
-#endif
#endif
+ LONG_SRL \temp, PTEBASE_SHIFT
LONG_S \stackp, kernelsp(\temp)
.endm
#else
.macro get_saved_sp /* Uniprocessor variation */
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_BUILD_ELF64) || (defined(CONFIG_64BIT) && __GNUC__ < 4)
lui k1, %highest(kernelsp)
daddiu k1, %higher(kernelsp)
dsll k1, k1, 16
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
- * Copyright (C) 1995, 1996, 1999, 2001 Ralf Baechle
+ * Copyright (C) 1995, 96, 99, 2001, 06 Ralf Baechle
* Copyright (C) 1999 Silicon Graphics, Inc.
* Copyright (C) 2001 MIPS Technologies, Inc.
*/
#include <linux/posix_types.h>
typedef unsigned char cc_t;
-#if (_MIPS_SZLONG == 32)
-typedef unsigned long speed_t;
-typedef unsigned long tcflag_t;
-#endif
-#if (_MIPS_SZLONG == 64)
-typedef __u32 speed_t;
-typedef __u32 tcflag_t;
-#endif
+typedef unsigned int speed_t;
+typedef unsigned int tcflag_t;
/*
* The ABI says nothing about NCC but seems to use NCCS as
#include <asm/eeh.h>
-/**
- * check_signature - find BIOS signatures
- * @io_addr: mmio address to check
- * @signature: signature block
- * @length: length of signature
- *
- * Perform a signature comparison with the mmio address io_addr. This
- * address should have been obtained by ioremap.
- * Returns 1 on a match.
- */
-static inline int check_signature(const volatile void __iomem * io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
/* Nothing to do */
#define dma_cache_inv(_start,_size) do { } while (0)
#define iobarrier_r() eieio()
#define iobarrier_w() eieio()
-static inline int check_signature(volatile void __iomem * io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
/*
* Here comes the ppc implementation of the IOMAP
* interfaces.
u16 devno;
};
+static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1,
+ struct ccw_dev_id *dev_id2)
+{
+ return !memcmp(dev_id1, dev_id2, sizeof(struct ccw_dev_id));
+}
+
extern int diag210(struct diag210 *addr);
extern void wait_cons_dev(void);
spinlock_t lock;
unsigned long magic;
- void (*function)(unsigned long, struct pt_regs*);
+ void (*function)(unsigned long);
unsigned long data;
};
*
* Copyright (C) 1999 Niibe Yutaka
* Copyright (C) 2003 Paul Mundt
+ * Copyright (C) 2006 Lineo Solutions Inc. support SH4A UBC
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
#ifndef __ASM_CPU_SH4_UBC_H
#define __ASM_CPU_SH4_UBC_H
+#if defined(CONFIG_CPU_SH4A)
+#define UBC_CBR0 0xff200000
+#define UBC_CRR0 0xff200004
+#define UBC_CAR0 0xff200008
+#define UBC_CAMR0 0xff20000c
+#define UBC_CBR1 0xff200020
+#define UBC_CRR1 0xff200024
+#define UBC_CAR1 0xff200028
+#define UBC_CAMR1 0xff20002c
+#define UBC_CDR1 0xff200030
+#define UBC_CDMR1 0xff200034
+#define UBC_CETR1 0xff200038
+#define UBC_CCMFR 0xff200600
+#define UBC_CBCR 0xff200620
+
+/* CBR */
+#define UBC_CBR_AIE (0x01<<30)
+#define UBC_CBR_ID_INST (0x01<<4)
+#define UBC_CBR_RW_READ (0x01<<1)
+#define UBC_CBR_CE (0x01)
+
+#define UBC_CBR_AIV_MASK (0x00FF0000)
+#define UBC_CBR_AIV_SHIFT (16)
+#define UBC_CBR_AIV_SET(asid) (((asid)<<UBC_CBR_AIV_SHIFT) & UBC_CBR_AIV_MASK)
+
+#define UBC_CBR_INIT 0x20000000
+
+/* CRR */
+#define UBC_CRR_RES (0x01<<13)
+#define UBC_CRR_PCB (0x01<<1)
+#define UBC_CRR_BIE (0x01)
+
+#define UBC_CRR_INIT 0x00002000
+
+#else /* CONFIG_CPU_SH4 */
#define UBC_BARA 0xff200000
#define UBC_BAMRA 0xff200004
#define UBC_BBRA 0xff200008
#define UBC_BDRB 0xff200018
#define UBC_BDMRB 0xff20001c
#define UBC_BRCR 0xff200020
+#endif /* CONFIG_CPU_SH4 */
#endif /* __ASM_CPU_SH4_UBC_H */
#ifndef __ASM_SH_HW_IRQ_H
#define __ASM_SH_HW_IRQ_H
+#include <asm/atomic.h>
+
+extern atomic_t irq_err_count;
+
#endif /* __ASM_SH_HW_IRQ_H */
#define iounmap(addr) \
__iounmap((addr))
-static inline int check_signature(char __iomem *io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
/*
* The caches on some architectures aren't dma-coherent and have need to
* handle this in software. There are three types of operations that
#define INTC2_INTPRI_OFFSET 0x00
-void make_intc2_irq(unsigned int irq,
- unsigned int ipr_offset, unsigned int ipr_shift,
- unsigned int msk_offset, unsigned int msk_shift,
- unsigned int priority);
+struct intc2_data {
+ unsigned short irq;
+ unsigned char ipr_offset, ipr_shift;
+ unsigned char msk_offset, msk_shift;
+ unsigned char priority;
+};
+
+void make_intc2_irq(struct intc2_data *);
void init_IRQ_intc2(void);
-void intc2_add_clear_irq(int irq, int (*fn)(int));
-
#endif
extern int shmse_irq_demux(int irq);
--- /dev/null
+#include <asm-generic/irq_regs.h>
int (*init)(void);
int (*start)(void);
int (*stop)(void);
+#ifndef CONFIG_GENERIC_TIME
unsigned long (*get_offset)(void);
- unsigned long (*get_frequency)(void);
+#endif
};
struct sys_timer {
extern struct sys_timer tmu_timer;
extern struct sys_timer *sys_timer;
+#ifndef CONFIG_GENERIC_TIME
static inline unsigned long get_timer_offset(void)
{
return sys_timer->ops->get_offset();
}
-
-static inline unsigned long get_timer_frequency(void)
-{
- return sys_timer->ops->get_frequency();
-}
+#endif
/* arch/sh/kernel/timers/timer.c */
struct sys_timer *get_sys_timer(void);
/* arch/sh/kernel/time.c */
-void handle_timer_tick(struct pt_regs *);
+void handle_timer_tick(void);
#endif /* __ASM_SH_TIMER_H */
-
unsigned long onchip_remap(unsigned long addr, unsigned long size, const char* name);
extern void onchip_unmap(unsigned long vaddr);
-static __inline__ int check_signature(volatile void __iomem *io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
/*
* The caches on some architectures aren't dma-coherent and have need to
* handle this in software. There are three types of operations that
#define memcpy_toio(d,s,sz) _memcpy_toio(d,s,sz)
-static inline int check_signature(void __iomem *io_addr,
- const unsigned char *signature,
- int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature++)
- goto out;
- io_addr++;
- } while (--length);
- retval = 1;
-out:
- return retval;
-}
-
#define mmiowb()
#ifdef __KERNEL__
#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void *)(b),(c),(d))
-/**
- * check_signature - find BIOS signatures
- * @io_addr: mmio address to check
- * @signature: signature block
- * @length: length of signature
- *
- * Perform a signature comparison with the mmio address io_addr. This
- * address should have been obtained by ioremap.
- * Returns 1 on a match.
- */
-
-static inline int check_signature(void __iomem *io_addr,
- const unsigned char *signature, int length)
-{
- int retval = 0;
- do {
- if (readb(io_addr) != *signature)
- goto out;
- io_addr++;
- signature++;
- length--;
- } while (length);
- retval = 1;
-out:
- return retval;
-}
-
/* Nothing to do */
#define dma_cache_inv(_start,_size) do { } while (0)
: :"a" (eax), "c" (ecx));
}
+extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
+
#define stack_current() \
({ \
struct thread_info *ti; \
extern int ec_read(u8 addr, u8 *val);
extern int ec_write(u8 addr, u8 val);
+extern int ec_transaction(u8 command,
+ const u8 *wdata, unsigned wdata_len,
+ u8 *rdata, unsigned rdata_len);
#endif /*CONFIG_ACPI_EC*/
* bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src)
* bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit)
* bitmap_scnprintf(buf, len, src, nbits) Print bitmap src to buf
- * bitmap_parse(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf
+ * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf
+ * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf
* bitmap_scnlistprintf(buf, len, src, nbits) Print bitmap src as list to buf
* bitmap_parselist(buf, dst, nbits) Parse bitmap dst from list
* bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region
extern int bitmap_scnprintf(char *buf, unsigned int len,
const unsigned long *src, int nbits);
-extern int bitmap_parse(const char __user *ubuf, unsigned int ulen,
+extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user,
+ unsigned long *dst, int nbits);
+extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen,
unsigned long *dst, int nbits);
extern int bitmap_scnlistprintf(char *buf, unsigned int len,
const unsigned long *src, int nbits);
__bitmap_shift_left(dst, src, n, nbits);
}
+static inline int bitmap_parse(const char *buf, unsigned int buflen,
+ unsigned long *maskp, int nmaskbits)
+{
+ return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits);
+}
+
#endif /* __ASSEMBLY__ */
#endif /* __LINUX_BITMAP_H */
REQ_TYPE_ATA_CMD,
REQ_TYPE_ATA_TASK,
REQ_TYPE_ATA_TASKFILE,
+ REQ_TYPE_ATA_PC,
};
/*
bh_end_io_t *b_end_io; /* I/O completion */
void *b_private; /* reserved for b_end_io */
struct list_head b_assoc_buffers; /* associated with another mapping */
+ struct address_space *b_assoc_map; /* mapping this buffer is
+ associated with */
atomic_t b_count; /* users using this buffer_head */
};
--- /dev/null
+/*
+ * Fast, simple, yet decent quality random number generator based on
+ * a paper by David G. Carta ("Two Fast Implementations of the
+ * `Minimal Standard' Random Number Generator," Communications of the
+ * ACM, January, 1990).
+ *
+ * Copyright (c) 2002-2006 Hewlett-Packard Development Company, L.P.
+ * Contributed by Stephane Eranian <eranian@hpl.hp.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307 USA
+ */
+#ifndef _LINUX_CARTA_RANDOM32_H_
+#define _LINUX_CARTA_RANDOM32_H_
+
+u64 carta_random32(u64 seed);
+
+#endif /* _LINUX_CARTA_RANDOM32_H_ */
* Some need translations, these do not.
*/
COMPATIBLE_IOCTL(HDIO_GET_IDENTITY)
-COMPATIBLE_IOCTL(HDIO_SET_DMA)
-COMPATIBLE_IOCTL(HDIO_SET_UNMASKINTR)
-COMPATIBLE_IOCTL(HDIO_SET_NOWERR)
-COMPATIBLE_IOCTL(HDIO_SET_32BIT)
-COMPATIBLE_IOCTL(HDIO_SET_MULTCOUNT)
-COMPATIBLE_IOCTL(HDIO_DRIVE_CMD)
COMPATIBLE_IOCTL(HDIO_DRIVE_TASK)
-COMPATIBLE_IOCTL(HDIO_SET_PIO_MODE)
-COMPATIBLE_IOCTL(HDIO_SET_NICE)
-COMPATIBLE_IOCTL(HDIO_SET_KEEPSETTINGS)
+COMPATIBLE_IOCTL(HDIO_DRIVE_CMD)
+ULONG_IOCTL(HDIO_SET_MULTCOUNT)
+ULONG_IOCTL(HDIO_SET_UNMASKINTR)
+ULONG_IOCTL(HDIO_SET_KEEPSETTINGS)
+ULONG_IOCTL(HDIO_SET_32BIT)
+ULONG_IOCTL(HDIO_SET_NOWERR)
+ULONG_IOCTL(HDIO_SET_DMA)
+ULONG_IOCTL(HDIO_SET_PIO_MODE)
+ULONG_IOCTL(HDIO_SET_NICE)
+ULONG_IOCTL(HDIO_SET_WCACHE)
+ULONG_IOCTL(HDIO_SET_ACOUSTIC)
+ULONG_IOCTL(HDIO_SET_BUSSTATE)
+ULONG_IOCTL(HDIO_SET_ADDRESS)
COMPATIBLE_IOCTL(HDIO_SCAN_HWIF)
+/* 0x330 is reserved -- it used to be HDIO_GETGEO_BIG */
+COMPATIBLE_IOCTL(0x330)
/* 0x02 -- Floppy ioctls */
COMPATIBLE_IOCTL(FDMSGON)
COMPATIBLE_IOCTL(FDMSGOFF)
* See detailed comments in the file linux/bitmap.h describing the
* data type on which these cpumasks are based.
*
- * For details of cpumask_scnprintf() and cpumask_parse(),
- * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c.
+ * For details of cpumask_scnprintf() and cpumask_parse_user(),
+ * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c.
* For details of cpulist_scnprintf() and cpulist_parse(), see
* bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c.
* For details of cpu_remap(), see bitmap_bitremap in lib/bitmap.c
* unsigned long *cpus_addr(mask) Array of unsigned long's in mask
*
* int cpumask_scnprintf(buf, len, mask) Format cpumask for printing
- * int cpumask_parse(ubuf, ulen, mask) Parse ascii string as cpumask
+ * int cpumask_parse_user(ubuf, ulen, mask) Parse ascii string as cpumask
* int cpulist_scnprintf(buf, len, mask) Format cpumask as list for printing
* int cpulist_parse(buf, map) Parse ascii string as cpulist
* int cpu_remap(oldbit, old, new) newbit = map(old, new)(oldbit)
return bitmap_scnprintf(buf, len, srcp->bits, nbits);
}
-#define cpumask_parse(ubuf, ulen, dst) \
- __cpumask_parse((ubuf), (ulen), &(dst), NR_CPUS)
-static inline int __cpumask_parse(const char __user *buf, int len,
+#define cpumask_parse_user(ubuf, ulen, dst) \
+ __cpumask_parse_user((ubuf), (ulen), &(dst), NR_CPUS)
+static inline int __cpumask_parse_user(const char __user *buf, int len,
cpumask_t *dstp, int nbits)
{
- return bitmap_parse(buf, len, dstp->bits, nbits);
+ return bitmap_parse_user(buf, len, dstp->bits, nbits);
}
#define cpulist_scnprintf(buf, len, src) \
extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
extern void shrink_dcache_sb(struct super_block *);
extern void shrink_dcache_parent(struct dentry *);
+extern void shrink_dcache_for_umount(struct super_block *);
extern int d_invalidate(struct dentry *);
/* only used at mount-time */
{
struct list_head list;
struct elevator_ops ops;
- struct elevator_type *elevator_type;
struct elv_fs_entry *elevator_attrs;
char elevator_name[ELV_NAME_MAX];
struct module *elevator_owner;
--- /dev/null
+/*
+ * linux/include/linux/ext4_fs.h
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/include/linux/minix_fs.h
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+#ifndef _LINUX_EXT4_FS_H
+#define _LINUX_EXT4_FS_H
+
+#include <linux/types.h>
+#include <linux/blkdev.h>
+#include <linux/magic.h>
+
+/*
+ * The second extended filesystem constants/structures
+ */
+
+/*
+ * Define EXT4FS_DEBUG to produce debug messages
+ */
+#undef EXT4FS_DEBUG
+
+/*
+ * Define EXT4_RESERVATION to reserve data blocks for expanding files
+ */
+#define EXT4_DEFAULT_RESERVE_BLOCKS 8
+/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */
+#define EXT4_MAX_RESERVE_BLOCKS 1027
+#define EXT4_RESERVE_WINDOW_NOT_ALLOCATED 0
+/*
+ * Always enable hashed directories
+ */
+#define CONFIG_EXT4_INDEX
+
+/*
+ * Debug code
+ */
+#ifdef EXT4FS_DEBUG
+#define ext4_debug(f, a...) \
+ do { \
+ printk (KERN_DEBUG "EXT4-fs DEBUG (%s, %d): %s:", \
+ __FILE__, __LINE__, __FUNCTION__); \
+ printk (KERN_DEBUG f, ## a); \
+ } while (0)
+#else
+#define ext4_debug(f, a...) do {} while (0)
+#endif
+
+/*
+ * Special inodes numbers
+ */
+#define EXT4_BAD_INO 1 /* Bad blocks inode */
+#define EXT4_ROOT_INO 2 /* Root inode */
+#define EXT4_BOOT_LOADER_INO 5 /* Boot loader inode */
+#define EXT4_UNDEL_DIR_INO 6 /* Undelete directory inode */
+#define EXT4_RESIZE_INO 7 /* Reserved group descriptors inode */
+#define EXT4_JOURNAL_INO 8 /* Journal inode */
+
+/* First non-reserved inode for old ext4 filesystems */
+#define EXT4_GOOD_OLD_FIRST_INO 11
+
+/*
+ * Maximal count of links to a file
+ */
+#define EXT4_LINK_MAX 32000
+
+/*
+ * Macro-instructions used to manage several block sizes
+ */
+#define EXT4_MIN_BLOCK_SIZE 1024
+#define EXT4_MAX_BLOCK_SIZE 4096
+#define EXT4_MIN_BLOCK_LOG_SIZE 10
+#ifdef __KERNEL__
+# define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize)
+#else
+# define EXT4_BLOCK_SIZE(s) (EXT4_MIN_BLOCK_SIZE << (s)->s_log_block_size)
+#endif
+#define EXT4_ADDR_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / sizeof (__u32))
+#ifdef __KERNEL__
+# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits)
+#else
+# define EXT4_BLOCK_SIZE_BITS(s) ((s)->s_log_block_size + 10)
+#endif
+#ifdef __KERNEL__
+#define EXT4_ADDR_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_addr_per_block_bits)
+#define EXT4_INODE_SIZE(s) (EXT4_SB(s)->s_inode_size)
+#define EXT4_FIRST_INO(s) (EXT4_SB(s)->s_first_ino)
+#else
+#define EXT4_INODE_SIZE(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
+ EXT4_GOOD_OLD_INODE_SIZE : \
+ (s)->s_inode_size)
+#define EXT4_FIRST_INO(s) (((s)->s_rev_level == EXT4_GOOD_OLD_REV) ? \
+ EXT4_GOOD_OLD_FIRST_INO : \
+ (s)->s_first_ino)
+#endif
+
+/*
+ * Macro-instructions used to manage fragments
+ */
+#define EXT4_MIN_FRAG_SIZE 1024
+#define EXT4_MAX_FRAG_SIZE 4096
+#define EXT4_MIN_FRAG_LOG_SIZE 10
+#ifdef __KERNEL__
+# define EXT4_FRAG_SIZE(s) (EXT4_SB(s)->s_frag_size)
+# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_SB(s)->s_frags_per_block)
+#else
+# define EXT4_FRAG_SIZE(s) (EXT4_MIN_FRAG_SIZE << (s)->s_log_frag_size)
+# define EXT4_FRAGS_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_FRAG_SIZE(s))
+#endif
+
+/*
+ * Structure of a blocks group descriptor
+ */
+struct ext4_group_desc
+{
+ __le32 bg_block_bitmap; /* Blocks bitmap block */
+ __le32 bg_inode_bitmap; /* Inodes bitmap block */
+ __le32 bg_inode_table; /* Inodes table block */
+ __le16 bg_free_blocks_count; /* Free blocks count */
+ __le16 bg_free_inodes_count; /* Free inodes count */
+ __le16 bg_used_dirs_count; /* Directories count */
+ __u16 bg_flags;
+ __u32 bg_reserved[3];
+ __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */
+ __le32 bg_inode_bitmap_hi; /* Inodes bitmap block MSB */
+ __le32 bg_inode_table_hi; /* Inodes table block MSB */
+};
+
+#ifdef __KERNEL__
+#include <linux/ext4_fs_i.h>
+#include <linux/ext4_fs_sb.h>
+#endif
+/*
+ * Macro-instructions used to manage group descriptors
+ */
+#define EXT4_MIN_DESC_SIZE 32
+#define EXT4_MIN_DESC_SIZE_64BIT 64
+#define EXT4_MAX_DESC_SIZE EXT4_MIN_BLOCK_SIZE
+#define EXT4_DESC_SIZE(s) (EXT4_SB(s)->s_desc_size)
+#ifdef __KERNEL__
+# define EXT4_BLOCKS_PER_GROUP(s) (EXT4_SB(s)->s_blocks_per_group)
+# define EXT4_DESC_PER_BLOCK(s) (EXT4_SB(s)->s_desc_per_block)
+# define EXT4_INODES_PER_GROUP(s) (EXT4_SB(s)->s_inodes_per_group)
+# define EXT4_DESC_PER_BLOCK_BITS(s) (EXT4_SB(s)->s_desc_per_block_bits)
+#else
+# define EXT4_BLOCKS_PER_GROUP(s) ((s)->s_blocks_per_group)
+# define EXT4_DESC_PER_BLOCK(s) (EXT4_BLOCK_SIZE(s) / EXT4_DESC_SIZE(s))
+# define EXT4_INODES_PER_GROUP(s) ((s)->s_inodes_per_group)
+#endif
+
+/*
+ * Constants relative to the data blocks
+ */
+#define EXT4_NDIR_BLOCKS 12
+#define EXT4_IND_BLOCK EXT4_NDIR_BLOCKS
+#define EXT4_DIND_BLOCK (EXT4_IND_BLOCK + 1)
+#define EXT4_TIND_BLOCK (EXT4_DIND_BLOCK + 1)
+#define EXT4_N_BLOCKS (EXT4_TIND_BLOCK + 1)
+
+/*
+ * Inode flags
+ */
+#define EXT4_SECRM_FL 0x00000001 /* Secure deletion */
+#define EXT4_UNRM_FL 0x00000002 /* Undelete */
+#define EXT4_COMPR_FL 0x00000004 /* Compress file */
+#define EXT4_SYNC_FL 0x00000008 /* Synchronous updates */
+#define EXT4_IMMUTABLE_FL 0x00000010 /* Immutable file */
+#define EXT4_APPEND_FL 0x00000020 /* writes to file may only append */
+#define EXT4_NODUMP_FL 0x00000040 /* do not dump file */
+#define EXT4_NOATIME_FL 0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define EXT4_DIRTY_FL 0x00000100
+#define EXT4_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
+#define EXT4_NOCOMPR_FL 0x00000400 /* Don't compress */
+#define EXT4_ECOMPR_FL 0x00000800 /* Compression error */
+/* End compression flags --- maybe not all used */
+#define EXT4_INDEX_FL 0x00001000 /* hash-indexed directory */
+#define EXT4_IMAGIC_FL 0x00002000 /* AFS directory */
+#define EXT4_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */
+#define EXT4_NOTAIL_FL 0x00008000 /* file tail should not be merged */
+#define EXT4_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
+#define EXT4_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
+#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
+#define EXT4_EXTENTS_FL 0x00080000 /* Inode uses extents */
+
+#define EXT4_FL_USER_VISIBLE 0x000BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */
+
+/*
+ * Inode dynamic state flags
+ */
+#define EXT4_STATE_JDATA 0x00000001 /* journaled data exists */
+#define EXT4_STATE_NEW 0x00000002 /* inode is newly created */
+#define EXT4_STATE_XATTR 0x00000004 /* has in-inode xattrs */
+
+/* Used to pass group descriptor data when online resize is done */
+struct ext4_new_group_input {
+ __u32 group; /* Group number for this data */
+ __u64 block_bitmap; /* Absolute block number of block bitmap */
+ __u64 inode_bitmap; /* Absolute block number of inode bitmap */
+ __u64 inode_table; /* Absolute block number of inode table start */
+ __u32 blocks_count; /* Total number of blocks in this group */
+ __u16 reserved_blocks; /* Number of reserved blocks in this group */
+ __u16 unused;
+};
+
+/* The struct ext4_new_group_input in kernel space, with free_blocks_count */
+struct ext4_new_group_data {
+ __u32 group;
+ __u64 block_bitmap;
+ __u64 inode_bitmap;
+ __u64 inode_table;
+ __u32 blocks_count;
+ __u16 reserved_blocks;
+ __u16 unused;
+ __u32 free_blocks_count;
+};
+
+
+/*
+ * ioctl commands
+ */
+#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS
+#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS
+#define EXT4_IOC_GETVERSION _IOR('f', 3, long)
+#define EXT4_IOC_SETVERSION _IOW('f', 4, long)
+#define EXT4_IOC_GROUP_EXTEND _IOW('f', 7, unsigned long)
+#define EXT4_IOC_GROUP_ADD _IOW('f', 8,struct ext4_new_group_input)
+#define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION
+#define EXT4_IOC_SETVERSION_OLD FS_IOC_SETVERSION
+#ifdef CONFIG_JBD_DEBUG
+#define EXT4_IOC_WAIT_FOR_READONLY _IOR('f', 99, long)
+#endif
+#define EXT4_IOC_GETRSVSZ _IOR('f', 5, long)
+#define EXT4_IOC_SETRSVSZ _IOW('f', 6, long)
+
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS
+#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS
+#define EXT4_IOC32_GETVERSION _IOR('f', 3, int)
+#define EXT4_IOC32_SETVERSION _IOW('f', 4, int)
+#define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int)
+#define EXT4_IOC32_SETRSVSZ _IOW('f', 6, int)
+#define EXT4_IOC32_GROUP_EXTEND _IOW('f', 7, unsigned int)
+#ifdef CONFIG_JBD_DEBUG
+#define EXT4_IOC32_WAIT_FOR_READONLY _IOR('f', 99, int)
+#endif
+#define EXT4_IOC32_GETVERSION_OLD FS_IOC32_GETVERSION
+#define EXT4_IOC32_SETVERSION_OLD FS_IOC32_SETVERSION
+
+
+/*
+ * Mount options
+ */
+struct ext4_mount_options {
+ unsigned long s_mount_opt;
+ uid_t s_resuid;
+ gid_t s_resgid;
+ unsigned long s_commit_interval;
+#ifdef CONFIG_QUOTA
+ int s_jquota_fmt;
+ char *s_qf_names[MAXQUOTAS];
+#endif
+};
+
+/*
+ * Structure of an inode on the disk
+ */
+struct ext4_inode {
+ __le16 i_mode; /* File mode */
+ __le16 i_uid; /* Low 16 bits of Owner Uid */
+ __le32 i_size; /* Size in bytes */
+ __le32 i_atime; /* Access time */
+ __le32 i_ctime; /* Creation time */
+ __le32 i_mtime; /* Modification time */
+ __le32 i_dtime; /* Deletion Time */
+ __le16 i_gid; /* Low 16 bits of Group Id */
+ __le16 i_links_count; /* Links count */
+ __le32 i_blocks; /* Blocks count */
+ __le32 i_flags; /* File flags */
+ union {
+ struct {
+ __u32 l_i_reserved1;
+ } linux1;
+ struct {
+ __u32 h_i_translator;
+ } hurd1;
+ struct {
+ __u32 m_i_reserved1;
+ } masix1;
+ } osd1; /* OS dependent 1 */
+ __le32 i_block[EXT4_N_BLOCKS];/* Pointers to blocks */
+ __le32 i_generation; /* File version (for NFS) */
+ __le32 i_file_acl; /* File ACL */
+ __le32 i_dir_acl; /* Directory ACL */
+ __le32 i_faddr; /* Fragment address */
+ union {
+ struct {
+ __u8 l_i_frag; /* Fragment number */
+ __u8 l_i_fsize; /* Fragment size */
+ __le16 l_i_file_acl_high;
+ __le16 l_i_uid_high; /* these 2 fields */
+ __le16 l_i_gid_high; /* were reserved2[0] */
+ __u32 l_i_reserved2;
+ } linux2;
+ struct {
+ __u8 h_i_frag; /* Fragment number */
+ __u8 h_i_fsize; /* Fragment size */
+ __u16 h_i_mode_high;
+ __u16 h_i_uid_high;
+ __u16 h_i_gid_high;
+ __u32 h_i_author;
+ } hurd2;
+ struct {
+ __u8 m_i_frag; /* Fragment number */
+ __u8 m_i_fsize; /* Fragment size */
+ __le16 m_i_file_acl_high;
+ __u32 m_i_reserved2[2];
+ } masix2;
+ } osd2; /* OS dependent 2 */
+ __le16 i_extra_isize;
+ __le16 i_pad1;
+};
+
+#define i_size_high i_dir_acl
+
+#if defined(__KERNEL__) || defined(__linux__)
+#define i_reserved1 osd1.linux1.l_i_reserved1
+#define i_frag osd2.linux2.l_i_frag
+#define i_fsize osd2.linux2.l_i_fsize
+#define i_file_acl_high osd2.linux2.l_i_file_acl_high
+#define i_uid_low i_uid
+#define i_gid_low i_gid
+#define i_uid_high osd2.linux2.l_i_uid_high
+#define i_gid_high osd2.linux2.l_i_gid_high
+#define i_reserved2 osd2.linux2.l_i_reserved2
+
+#elif defined(__GNU__)
+
+#define i_translator osd1.hurd1.h_i_translator
+#define i_frag osd2.hurd2.h_i_frag;
+#define i_fsize osd2.hurd2.h_i_fsize;
+#define i_uid_high osd2.hurd2.h_i_uid_high
+#define i_gid_high osd2.hurd2.h_i_gid_high
+#define i_author osd2.hurd2.h_i_author
+
+#elif defined(__masix__)
+
+#define i_reserved1 osd1.masix1.m_i_reserved1
+#define i_frag osd2.masix2.m_i_frag
+#define i_fsize osd2.masix2.m_i_fsize
+#define i_file_acl_high osd2.masix2.m_i_file_acl_high
+#define i_reserved2 osd2.masix2.m_i_reserved2
+
+#endif /* defined(__KERNEL__) || defined(__linux__) */
+
+/*
+ * File system states
+ */
+#define EXT4_VALID_FS 0x0001 /* Unmounted cleanly */
+#define EXT4_ERROR_FS 0x0002 /* Errors detected */
+#define EXT4_ORPHAN_FS 0x0004 /* Orphans being recovered */
+
+/*
+ * Mount flags
+ */
+#define EXT4_MOUNT_CHECK 0x00001 /* Do mount-time checks */
+#define EXT4_MOUNT_OLDALLOC 0x00002 /* Don't use the new Orlov allocator */
+#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */
+#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */
+#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
+#define EXT4_MOUNT_ERRORS_RO 0x00020 /* Remount fs ro on errors */
+#define EXT4_MOUNT_ERRORS_PANIC 0x00040 /* Panic on errors */
+#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */
+#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/
+#define EXT4_MOUNT_ABORT 0x00200 /* Fatal error detected */
+#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */
+#define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */
+#define EXT4_MOUNT_ORDERED_DATA 0x00800 /* Flush data before commit */
+#define EXT4_MOUNT_WRITEBACK_DATA 0x00C00 /* No data ordering */
+#define EXT4_MOUNT_UPDATE_JOURNAL 0x01000 /* Update the journal format */
+#define EXT4_MOUNT_NO_UID32 0x02000 /* Disable 32-bit UIDs */
+#define EXT4_MOUNT_XATTR_USER 0x04000 /* Extended user attributes */
+#define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */
+#define EXT4_MOUNT_RESERVATION 0x10000 /* Preallocation */
+#define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */
+#define EXT4_MOUNT_NOBH 0x40000 /* No bufferheads */
+#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
+#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
+#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
+#define EXT4_MOUNT_EXTENTS 0x400000 /* Extents support */
+
+/* Compatibility, for having both ext2_fs.h and ext4_fs.h included at once */
+#ifndef _LINUX_EXT2_FS_H
+#define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt
+#define set_opt(o, opt) o |= EXT4_MOUNT_##opt
+#define test_opt(sb, opt) (EXT4_SB(sb)->s_mount_opt & \
+ EXT4_MOUNT_##opt)
+#else
+#define EXT2_MOUNT_NOLOAD EXT4_MOUNT_NOLOAD
+#define EXT2_MOUNT_ABORT EXT4_MOUNT_ABORT
+#define EXT2_MOUNT_DATA_FLAGS EXT4_MOUNT_DATA_FLAGS
+#endif
+
+#define ext4_set_bit ext2_set_bit
+#define ext4_set_bit_atomic ext2_set_bit_atomic
+#define ext4_clear_bit ext2_clear_bit
+#define ext4_clear_bit_atomic ext2_clear_bit_atomic
+#define ext4_test_bit ext2_test_bit
+#define ext4_find_first_zero_bit ext2_find_first_zero_bit
+#define ext4_find_next_zero_bit ext2_find_next_zero_bit
+
+/*
+ * Maximal mount counts between two filesystem checks
+ */
+#define EXT4_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */
+#define EXT4_DFL_CHECKINTERVAL 0 /* Don't use interval check */
+
+/*
+ * Behaviour when detecting errors
+ */
+#define EXT4_ERRORS_CONTINUE 1 /* Continue execution */
+#define EXT4_ERRORS_RO 2 /* Remount fs read-only */
+#define EXT4_ERRORS_PANIC 3 /* Panic */
+#define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE
+
+/*
+ * Structure of the super block
+ */
+struct ext4_super_block {
+/*00*/ __le32 s_inodes_count; /* Inodes count */
+ __le32 s_blocks_count; /* Blocks count */
+ __le32 s_r_blocks_count; /* Reserved blocks count */
+ __le32 s_free_blocks_count; /* Free blocks count */
+/*10*/ __le32 s_free_inodes_count; /* Free inodes count */
+ __le32 s_first_data_block; /* First Data Block */
+ __le32 s_log_block_size; /* Block size */
+ __le32 s_log_frag_size; /* Fragment size */
+/*20*/ __le32 s_blocks_per_group; /* # Blocks per group */
+ __le32 s_frags_per_group; /* # Fragments per group */
+ __le32 s_inodes_per_group; /* # Inodes per group */
+ __le32 s_mtime; /* Mount time */
+/*30*/ __le32 s_wtime; /* Write time */
+ __le16 s_mnt_count; /* Mount count */
+ __le16 s_max_mnt_count; /* Maximal mount count */
+ __le16 s_magic; /* Magic signature */
+ __le16 s_state; /* File system state */
+ __le16 s_errors; /* Behaviour when detecting errors */
+ __le16 s_minor_rev_level; /* minor revision level */
+/*40*/ __le32 s_lastcheck; /* time of last check */
+ __le32 s_checkinterval; /* max. time between checks */
+ __le32 s_creator_os; /* OS */
+ __le32 s_rev_level; /* Revision level */
+/*50*/ __le16 s_def_resuid; /* Default uid for reserved blocks */
+ __le16 s_def_resgid; /* Default gid for reserved blocks */
+ /*
+ * These fields are for EXT4_DYNAMIC_REV superblocks only.
+ *
+ * Note: the difference between the compatible feature set and
+ * the incompatible feature set is that if there is a bit set
+ * in the incompatible feature set that the kernel doesn't
+ * know about, it should refuse to mount the filesystem.
+ *
+ * e2fsck's requirements are more strict; if it doesn't know
+ * about a feature in either the compatible or incompatible
+ * feature set, it must abort and not try to meddle with
+ * things it doesn't understand...
+ */
+ __le32 s_first_ino; /* First non-reserved inode */
+ __le16 s_inode_size; /* size of inode structure */
+ __le16 s_block_group_nr; /* block group # of this superblock */
+ __le32 s_feature_compat; /* compatible feature set */
+/*60*/ __le32 s_feature_incompat; /* incompatible feature set */
+ __le32 s_feature_ro_compat; /* readonly-compatible feature set */
+/*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */
+/*78*/ char s_volume_name[16]; /* volume name */
+/*88*/ char s_last_mounted[64]; /* directory where last mounted */
+/*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */
+ /*
+ * Performance hints. Directory preallocation should only
+ * happen if the EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
+ */
+ __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/
+ __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */
+ __le16 s_reserved_gdt_blocks; /* Per group desc for online growth */
+ /*
+ * Journaling support valid if EXT4_FEATURE_COMPAT_HAS_JOURNAL set.
+ */
+/*D0*/ __u8 s_journal_uuid[16]; /* uuid of journal superblock */
+/*E0*/ __le32 s_journal_inum; /* inode number of journal file */
+ __le32 s_journal_dev; /* device number of journal file */
+ __le32 s_last_orphan; /* start of list of inodes to delete */
+ __le32 s_hash_seed[4]; /* HTREE hash seed */
+ __u8 s_def_hash_version; /* Default hash version to use */
+ __u8 s_reserved_char_pad;
+ __le16 s_desc_size; /* size of group descriptor */
+/*100*/ __le32 s_default_mount_opts;
+ __le32 s_first_meta_bg; /* First metablock block group */
+ __le32 s_mkfs_time; /* When the filesystem was created */
+ __le32 s_jnl_blocks[17]; /* Backup of the journal inode */
+ /* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
+/*150*/ __le32 s_blocks_count_hi; /* Blocks count */
+ __le32 s_r_blocks_count_hi; /* Reserved blocks count */
+ __le32 s_free_blocks_count_hi; /* Free blocks count */
+ __u32 s_reserved[169]; /* Padding to the end of the block */
+};
+
+#ifdef __KERNEL__
+static inline struct ext4_sb_info * EXT4_SB(struct super_block *sb)
+{
+ return sb->s_fs_info;
+}
+static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
+{
+ return container_of(inode, struct ext4_inode_info, vfs_inode);
+}
+
+static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
+{
+ return ino == EXT4_ROOT_INO ||
+ ino == EXT4_JOURNAL_INO ||
+ ino == EXT4_RESIZE_INO ||
+ (ino >= EXT4_FIRST_INO(sb) &&
+ ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
+}
+#else
+/* Assume that user mode programs are passing in an ext4fs superblock, not
+ * a kernel struct super_block. This will allow us to call the feature-test
+ * macros from user land. */
+#define EXT4_SB(sb) (sb)
+#endif
+
+#define NEXT_ORPHAN(inode) EXT4_I(inode)->i_dtime
+
+/*
+ * Codes for operating systems
+ */
+#define EXT4_OS_LINUX 0
+#define EXT4_OS_HURD 1
+#define EXT4_OS_MASIX 2
+#define EXT4_OS_FREEBSD 3
+#define EXT4_OS_LITES 4
+
+/*
+ * Revision levels
+ */
+#define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */
+#define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */
+
+#define EXT4_CURRENT_REV EXT4_GOOD_OLD_REV
+#define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV
+
+#define EXT4_GOOD_OLD_INODE_SIZE 128
+
+/*
+ * Feature set definitions
+ */
+
+#define EXT4_HAS_COMPAT_FEATURE(sb,mask) \
+ ( EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) )
+#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \
+ ( EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) )
+#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \
+ ( EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) )
+#define EXT4_SET_COMPAT_FEATURE(sb,mask) \
+ EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
+#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \
+ EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
+#define EXT4_SET_INCOMPAT_FEATURE(sb,mask) \
+ EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
+#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask) \
+ EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
+#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask) \
+ EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
+#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask) \
+ EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
+
+#define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001
+#define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002
+#define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004
+#define EXT4_FEATURE_COMPAT_EXT_ATTR 0x0008
+#define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010
+#define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020
+
+#define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001
+#define EXT4_FEATURE_RO_COMPAT_LARGE_FILE 0x0002
+#define EXT4_FEATURE_RO_COMPAT_BTREE_DIR 0x0004
+
+#define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001
+#define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002
+#define EXT4_FEATURE_INCOMPAT_RECOVER 0x0004 /* Needs recovery */
+#define EXT4_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 /* Journal device */
+#define EXT4_FEATURE_INCOMPAT_META_BG 0x0010
+#define EXT4_FEATURE_INCOMPAT_EXTENTS 0x0040 /* extents support */
+#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080
+
+#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
+#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
+ EXT4_FEATURE_INCOMPAT_RECOVER| \
+ EXT4_FEATURE_INCOMPAT_META_BG| \
+ EXT4_FEATURE_INCOMPAT_EXTENTS| \
+ EXT4_FEATURE_INCOMPAT_64BIT)
+#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
+ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
+ EXT4_FEATURE_RO_COMPAT_BTREE_DIR)
+
+/*
+ * Default values for user and/or group using reserved blocks
+ */
+#define EXT4_DEF_RESUID 0
+#define EXT4_DEF_RESGID 0
+
+/*
+ * Default mount options
+ */
+#define EXT4_DEFM_DEBUG 0x0001
+#define EXT4_DEFM_BSDGROUPS 0x0002
+#define EXT4_DEFM_XATTR_USER 0x0004
+#define EXT4_DEFM_ACL 0x0008
+#define EXT4_DEFM_UID16 0x0010
+#define EXT4_DEFM_JMODE 0x0060
+#define EXT4_DEFM_JMODE_DATA 0x0020
+#define EXT4_DEFM_JMODE_ORDERED 0x0040
+#define EXT4_DEFM_JMODE_WBACK 0x0060
+
+/*
+ * Structure of a directory entry
+ */
+#define EXT4_NAME_LEN 255
+
+struct ext4_dir_entry {
+ __le32 inode; /* Inode number */
+ __le16 rec_len; /* Directory entry length */
+ __le16 name_len; /* Name length */
+ char name[EXT4_NAME_LEN]; /* File name */
+};
+
+/*
+ * The new version of the directory entry. Since EXT4 structures are
+ * stored in intel byte order, and the name_len field could never be
+ * bigger than 255 chars, it's safe to reclaim the extra byte for the
+ * file_type field.
+ */
+struct ext4_dir_entry_2 {
+ __le32 inode; /* Inode number */
+ __le16 rec_len; /* Directory entry length */
+ __u8 name_len; /* Name length */
+ __u8 file_type;
+ char name[EXT4_NAME_LEN]; /* File name */
+};
+
+/*
+ * Ext4 directory file types. Only the low 3 bits are used. The
+ * other bits are reserved for now.
+ */
+#define EXT4_FT_UNKNOWN 0
+#define EXT4_FT_REG_FILE 1
+#define EXT4_FT_DIR 2
+#define EXT4_FT_CHRDEV 3
+#define EXT4_FT_BLKDEV 4
+#define EXT4_FT_FIFO 5
+#define EXT4_FT_SOCK 6
+#define EXT4_FT_SYMLINK 7
+
+#define EXT4_FT_MAX 8
+
+/*
+ * EXT4_DIR_PAD defines the directory entries boundaries
+ *
+ * NOTE: It must be a multiple of 4
+ */
+#define EXT4_DIR_PAD 4
+#define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1)
+#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \
+ ~EXT4_DIR_ROUND)
+/*
+ * Hash Tree Directory indexing
+ * (c) Daniel Phillips, 2001
+ */
+
+#ifdef CONFIG_EXT4_INDEX
+ #define is_dx(dir) (EXT4_HAS_COMPAT_FEATURE(dir->i_sb, \
+ EXT4_FEATURE_COMPAT_DIR_INDEX) && \
+ (EXT4_I(dir)->i_flags & EXT4_INDEX_FL))
+#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX)
+#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1)
+#else
+ #define is_dx(dir) 0
+#define EXT4_DIR_LINK_MAX(dir) ((dir)->i_nlink >= EXT4_LINK_MAX)
+#define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2)
+#endif
+
+/* Legal values for the dx_root hash_version field: */
+
+#define DX_HASH_LEGACY 0
+#define DX_HASH_HALF_MD4 1
+#define DX_HASH_TEA 2
+
+#ifdef __KERNEL__
+
+/* hash info structure used by the directory hash */
+struct dx_hash_info
+{
+ u32 hash;
+ u32 minor_hash;
+ int hash_version;
+ u32 *seed;
+};
+
+#define EXT4_HTREE_EOF 0x7fffffff
+
+/*
+ * Control parameters used by ext4_htree_next_block
+ */
+#define HASH_NB_ALWAYS 1
+
+
+/*
+ * Describe an inode's exact location on disk and in memory
+ */
+struct ext4_iloc
+{
+ struct buffer_head *bh;
+ unsigned long offset;
+ unsigned long block_group;
+};
+
+static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
+{
+ return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
+}
+
+/*
+ * This structure is stuffed into the struct file's private_data field
+ * for directories. It is where we put information so that we can do
+ * readdir operations in hash tree order.
+ */
+struct dir_private_info {
+ struct rb_root root;
+ struct rb_node *curr_node;
+ struct fname *extra_fname;
+ loff_t last_pos;
+ __u32 curr_hash;
+ __u32 curr_minor_hash;
+ __u32 next_hash;
+};
+
+/* calculate the first block number of the group */
+static inline ext4_fsblk_t
+ext4_group_first_block_no(struct super_block *sb, unsigned long group_no)
+{
+ return group_no * (ext4_fsblk_t)EXT4_BLOCKS_PER_GROUP(sb) +
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
+}
+
+/*
+ * Special error return code only used by dx_probe() and its callers.
+ */
+#define ERR_BAD_DX_DIR -75000
+
+void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr,
+ unsigned long *blockgrpp, ext4_grpblk_t *offsetp);
+
+/*
+ * Function prototypes
+ */
+
+/*
+ * Ok, these declarations are also in <linux/kernel.h> but none of the
+ * ext4 source programs needs to include it so they are duplicated here.
+ */
+# define NORET_TYPE /**/
+# define ATTRIB_NORET __attribute__((noreturn))
+# define NORET_AND noreturn,
+
+/* balloc.c */
+extern unsigned int ext4_block_group(struct super_block *sb,
+ ext4_fsblk_t blocknr);
+extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
+ ext4_fsblk_t blocknr);
+extern int ext4_bg_has_super(struct super_block *sb, int group);
+extern unsigned long ext4_bg_num_gdb(struct super_block *sb, int group);
+extern ext4_fsblk_t ext4_new_block (handle_t *handle, struct inode *inode,
+ ext4_fsblk_t goal, int *errp);
+extern ext4_fsblk_t ext4_new_blocks (handle_t *handle, struct inode *inode,
+ ext4_fsblk_t goal, unsigned long *count, int *errp);
+extern void ext4_free_blocks (handle_t *handle, struct inode *inode,
+ ext4_fsblk_t block, unsigned long count);
+extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb,
+ ext4_fsblk_t block, unsigned long count,
+ unsigned long *pdquot_freed_blocks);
+extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *);
+extern void ext4_check_blocks_bitmap (struct super_block *);
+extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
+ unsigned int block_group,
+ struct buffer_head ** bh);
+extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
+extern void ext4_init_block_alloc_info(struct inode *);
+extern void ext4_rsv_window_add(struct super_block *sb, struct ext4_reserve_window_node *rsv);
+
+/* dir.c */
+extern int ext4_check_dir_entry(const char *, struct inode *,
+ struct ext4_dir_entry_2 *,
+ struct buffer_head *, unsigned long);
+extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
+ __u32 minor_hash,
+ struct ext4_dir_entry_2 *dirent);
+extern void ext4_htree_free_dir_info(struct dir_private_info *p);
+
+/* fsync.c */
+extern int ext4_sync_file (struct file *, struct dentry *, int);
+
+/* hash.c */
+extern int ext4fs_dirhash(const char *name, int len, struct
+ dx_hash_info *hinfo);
+
+/* ialloc.c */
+extern struct inode * ext4_new_inode (handle_t *, struct inode *, int);
+extern void ext4_free_inode (handle_t *, struct inode *);
+extern struct inode * ext4_orphan_get (struct super_block *, unsigned long);
+extern unsigned long ext4_count_free_inodes (struct super_block *);
+extern unsigned long ext4_count_dirs (struct super_block *);
+extern void ext4_check_inodes_bitmap (struct super_block *);
+extern unsigned long ext4_count_free (struct buffer_head *, unsigned);
+
+
+/* inode.c */
+int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t blocknr);
+struct buffer_head * ext4_getblk (handle_t *, struct inode *, long, int, int *);
+struct buffer_head * ext4_bread (handle_t *, struct inode *, int, int, int *);
+int ext4_get_blocks_handle(handle_t *handle, struct inode *inode,
+ sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result,
+ int create, int extend_disksize);
+
+extern void ext4_read_inode (struct inode *);
+extern int ext4_write_inode (struct inode *, int);
+extern int ext4_setattr (struct dentry *, struct iattr *);
+extern void ext4_delete_inode (struct inode *);
+extern int ext4_sync_inode (handle_t *, struct inode *);
+extern void ext4_discard_reservation (struct inode *);
+extern void ext4_dirty_inode(struct inode *);
+extern int ext4_change_inode_journal_flag(struct inode *, int);
+extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern void ext4_truncate (struct inode *);
+extern void ext4_set_inode_flags(struct inode *);
+extern void ext4_set_aops(struct inode *inode);
+extern int ext4_writepage_trans_blocks(struct inode *);
+extern int ext4_block_truncate_page(handle_t *handle, struct page *page,
+ struct address_space *mapping, loff_t from);
+
+/* ioctl.c */
+extern int ext4_ioctl (struct inode *, struct file *, unsigned int,
+ unsigned long);
+extern long ext4_compat_ioctl (struct file *, unsigned int, unsigned long);
+
+/* namei.c */
+extern int ext4_orphan_add(handle_t *, struct inode *);
+extern int ext4_orphan_del(handle_t *, struct inode *);
+extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
+ __u32 start_minor_hash, __u32 *next_hash);
+
+/* resize.c */
+extern int ext4_group_add(struct super_block *sb,
+ struct ext4_new_group_data *input);
+extern int ext4_group_extend(struct super_block *sb,
+ struct ext4_super_block *es,
+ ext4_fsblk_t n_blocks_count);
+
+/* super.c */
+extern void ext4_error (struct super_block *, const char *, const char *, ...)
+ __attribute__ ((format (printf, 3, 4)));
+extern void __ext4_std_error (struct super_block *, const char *, int);
+extern void ext4_abort (struct super_block *, const char *, const char *, ...)
+ __attribute__ ((format (printf, 3, 4)));
+extern void ext4_warning (struct super_block *, const char *, const char *, ...)
+ __attribute__ ((format (printf, 3, 4)));
+extern void ext4_update_dynamic_rev (struct super_block *sb);
+extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
+ struct ext4_group_desc *bg);
+extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb,
+ struct ext4_group_desc *bg);
+extern ext4_fsblk_t ext4_inode_table(struct super_block *sb,
+ struct ext4_group_desc *bg);
+extern void ext4_block_bitmap_set(struct super_block *sb,
+ struct ext4_group_desc *bg, ext4_fsblk_t blk);
+extern void ext4_inode_bitmap_set(struct super_block *sb,
+ struct ext4_group_desc *bg, ext4_fsblk_t blk);
+extern void ext4_inode_table_set(struct super_block *sb,
+ struct ext4_group_desc *bg, ext4_fsblk_t blk);
+
+static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
+{
+ return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
+ le32_to_cpu(es->s_blocks_count);
+}
+
+static inline ext4_fsblk_t ext4_r_blocks_count(struct ext4_super_block *es)
+{
+ return ((ext4_fsblk_t)le32_to_cpu(es->s_r_blocks_count_hi) << 32) |
+ le32_to_cpu(es->s_r_blocks_count);
+}
+
+static inline ext4_fsblk_t ext4_free_blocks_count(struct ext4_super_block *es)
+{
+ return ((ext4_fsblk_t)le32_to_cpu(es->s_free_blocks_count_hi) << 32) |
+ le32_to_cpu(es->s_free_blocks_count);
+}
+
+static inline void ext4_blocks_count_set(struct ext4_super_block *es,
+ ext4_fsblk_t blk)
+{
+ es->s_blocks_count = cpu_to_le32((u32)blk);
+ es->s_blocks_count_hi = cpu_to_le32(blk >> 32);
+}
+
+static inline void ext4_free_blocks_count_set(struct ext4_super_block *es,
+ ext4_fsblk_t blk)
+{
+ es->s_free_blocks_count = cpu_to_le32((u32)blk);
+ es->s_free_blocks_count_hi = cpu_to_le32(blk >> 32);
+}
+
+static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
+ ext4_fsblk_t blk)
+{
+ es->s_r_blocks_count = cpu_to_le32((u32)blk);
+ es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
+}
+
+
+
+#define ext4_std_error(sb, errno) \
+do { \
+ if ((errno)) \
+ __ext4_std_error((sb), __FUNCTION__, (errno)); \
+} while (0)
+
+/*
+ * Inodes and files operations
+ */
+
+/* dir.c */
+extern const struct file_operations ext4_dir_operations;
+
+/* file.c */
+extern struct inode_operations ext4_file_inode_operations;
+extern const struct file_operations ext4_file_operations;
+
+/* namei.c */
+extern struct inode_operations ext4_dir_inode_operations;
+extern struct inode_operations ext4_special_inode_operations;
+
+/* symlink.c */
+extern struct inode_operations ext4_symlink_inode_operations;
+extern struct inode_operations ext4_fast_symlink_inode_operations;
+
+/* extents.c */
+extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
+extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
+extern int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
+ ext4_fsblk_t iblock,
+ unsigned long max_blocks, struct buffer_head *bh_result,
+ int create, int extend_disksize);
+extern void ext4_ext_truncate(struct inode *, struct page *);
+extern void ext4_ext_init(struct super_block *);
+extern void ext4_ext_release(struct super_block *);
+static inline int
+ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block,
+ unsigned long max_blocks, struct buffer_head *bh,
+ int create, int extend_disksize)
+{
+ if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)
+ return ext4_ext_get_blocks(handle, inode, block, max_blocks,
+ bh, create, extend_disksize);
+ return ext4_get_blocks_handle(handle, inode, block, max_blocks, bh,
+ create, extend_disksize);
+}
+
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_EXT4_FS_H */
--- /dev/null
+/*
+ * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
+ * Written by Alex Tomas <alex@clusterfs.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-
+ */
+
+#ifndef _LINUX_EXT4_EXTENTS
+#define _LINUX_EXT4_EXTENTS
+
+#include <linux/ext4_fs.h>
+
+/*
+ * With AGRESSIVE_TEST defined, the capacity of index/leaf blocks
+ * becomes very small, so index split, in-depth growing and
+ * other hard changes happen much more often.
+ * This is for debug purposes only.
+ */
+#define AGRESSIVE_TEST_
+
+/*
+ * With EXTENTS_STATS defined, the number of blocks and extents
+ * are collected in the truncate path. They'll be shown at
+ * umount time.
+ */
+#define EXTENTS_STATS__
+
+/*
+ * If CHECK_BINSEARCH is defined, then the results of the binary search
+ * will also be checked by linear search.
+ */
+#define CHECK_BINSEARCH__
+
+/*
+ * If EXT_DEBUG is defined you can use the 'extdebug' mount option
+ * to get lots of info about what's going on.
+ */
+#define EXT_DEBUG__
+#ifdef EXT_DEBUG
+#define ext_debug(a...) printk(a)
+#else
+#define ext_debug(a...)
+#endif
+
+/*
+ * If EXT_STATS is defined then stats numbers are collected.
+ * These number will be displayed at umount time.
+ */
+#define EXT_STATS_
+
+
+/*
+ * ext4_inode has i_block array (60 bytes total).
+ * The first 12 bytes store ext4_extent_header;
+ * the remainder stores an array of ext4_extent.
+ */
+
+/*
+ * This is the extent on-disk structure.
+ * It's used at the bottom of the tree.
+ */
+struct ext4_extent {
+ __le32 ee_block; /* first logical block extent covers */
+ __le16 ee_len; /* number of blocks covered by extent */
+ __le16 ee_start_hi; /* high 16 bits of physical block */
+ __le32 ee_start; /* low 32 bits of physical block */
+};
+
+/*
+ * This is index on-disk structure.
+ * It's used at all the levels except the bottom.
+ */
+struct ext4_extent_idx {
+ __le32 ei_block; /* index covers logical blocks from 'block' */
+ __le32 ei_leaf; /* pointer to the physical block of the next *
+ * level. leaf or next index could be there */
+ __le16 ei_leaf_hi; /* high 16 bits of physical block */
+ __u16 ei_unused;
+};
+
+/*
+ * Each block (leaves and indexes), even inode-stored has header.
+ */
+struct ext4_extent_header {
+ __le16 eh_magic; /* probably will support different formats */
+ __le16 eh_entries; /* number of valid entries */
+ __le16 eh_max; /* capacity of store in entries */
+ __le16 eh_depth; /* has tree real underlying blocks? */
+ __le32 eh_generation; /* generation of the tree */
+};
+
+#define EXT4_EXT_MAGIC cpu_to_le16(0xf30a)
+
+/*
+ * Array of ext4_ext_path contains path to some extent.
+ * Creation/lookup routines use it for traversal/splitting/etc.
+ * Truncate uses it to simulate recursive walking.
+ */
+struct ext4_ext_path {
+ ext4_fsblk_t p_block;
+ __u16 p_depth;
+ struct ext4_extent *p_ext;
+ struct ext4_extent_idx *p_idx;
+ struct ext4_extent_header *p_hdr;
+ struct buffer_head *p_bh;
+};
+
+/*
+ * structure for external API
+ */
+
+#define EXT4_EXT_CACHE_NO 0
+#define EXT4_EXT_CACHE_GAP 1
+#define EXT4_EXT_CACHE_EXTENT 2
+
+/*
+ * to be called by ext4_ext_walk_space()
+ * negative retcode - error
+ * positive retcode - signal for ext4_ext_walk_space(), see below
+ * callback must return valid extent (passed or newly created)
+ */
+typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *,
+ struct ext4_ext_cache *,
+ void *);
+
+#define EXT_CONTINUE 0
+#define EXT_BREAK 1
+#define EXT_REPEAT 2
+
+
+#define EXT_MAX_BLOCK 0xffffffff
+
+#define EXT_MAX_LEN ((1UL << 15) - 1)
+
+
+#define EXT_FIRST_EXTENT(__hdr__) \
+ ((struct ext4_extent *) (((char *) (__hdr__)) + \
+ sizeof(struct ext4_extent_header)))
+#define EXT_FIRST_INDEX(__hdr__) \
+ ((struct ext4_extent_idx *) (((char *) (__hdr__)) + \
+ sizeof(struct ext4_extent_header)))
+#define EXT_HAS_FREE_INDEX(__path__) \
+ (le16_to_cpu((__path__)->p_hdr->eh_entries) \
+ < le16_to_cpu((__path__)->p_hdr->eh_max))
+#define EXT_LAST_EXTENT(__hdr__) \
+ (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_LAST_INDEX(__hdr__) \
+ (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_MAX_EXTENT(__hdr__) \
+ (EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+#define EXT_MAX_INDEX(__hdr__) \
+ (EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)
+
+static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
+{
+ return (struct ext4_extent_header *) EXT4_I(inode)->i_data;
+}
+
+static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh)
+{
+ return (struct ext4_extent_header *) bh->b_data;
+}
+
+static inline unsigned short ext_depth(struct inode *inode)
+{
+ return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
+}
+
+static inline void ext4_ext_tree_changed(struct inode *inode)
+{
+ EXT4_I(inode)->i_ext_generation++;
+}
+
+static inline void
+ext4_ext_invalidate_cache(struct inode *inode)
+{
+ EXT4_I(inode)->i_cached_extent.ec_type = EXT4_EXT_CACHE_NO;
+}
+
+extern int ext4_extent_tree_init(handle_t *, struct inode *);
+extern int ext4_ext_calc_credits_for_insert(struct inode *, struct ext4_ext_path *);
+extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *);
+extern int ext4_ext_walk_space(struct inode *, unsigned long, unsigned long, ext_prepare_callback, void *);
+extern struct ext4_ext_path * ext4_ext_find_extent(struct inode *, int, struct ext4_ext_path *);
+
+#endif /* _LINUX_EXT4_EXTENTS */
+
--- /dev/null
+/*
+ * linux/include/linux/ext4_fs_i.h
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/include/linux/minix_fs_i.h
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+#ifndef _LINUX_EXT4_FS_I
+#define _LINUX_EXT4_FS_I
+
+#include <linux/rwsem.h>
+#include <linux/rbtree.h>
+#include <linux/seqlock.h>
+#include <linux/mutex.h>
+
+/* data type for block offset of block group */
+typedef int ext4_grpblk_t;
+
+/* data type for filesystem-wide blocks number */
+typedef unsigned long long ext4_fsblk_t;
+
+struct ext4_reserve_window {
+ ext4_fsblk_t _rsv_start; /* First byte reserved */
+ ext4_fsblk_t _rsv_end; /* Last byte reserved or 0 */
+};
+
+struct ext4_reserve_window_node {
+ struct rb_node rsv_node;
+ __u32 rsv_goal_size;
+ __u32 rsv_alloc_hit;
+ struct ext4_reserve_window rsv_window;
+};
+
+struct ext4_block_alloc_info {
+ /* information about reservation window */
+ struct ext4_reserve_window_node rsv_window_node;
+ /*
+ * was i_next_alloc_block in ext4_inode_info
+ * is the logical (file-relative) number of the
+ * most-recently-allocated block in this file.
+ * We use this for detecting linearly ascending allocation requests.
+ */
+ __u32 last_alloc_logical_block;
+ /*
+ * Was i_next_alloc_goal in ext4_inode_info
+ * is the *physical* companion to i_next_alloc_block.
+ * it the the physical block number of the block which was most-recentl
+ * allocated to this file. This give us the goal (target) for the next
+ * allocation when we detect linearly ascending requests.
+ */
+ ext4_fsblk_t last_alloc_physical_block;
+};
+
+#define rsv_start rsv_window._rsv_start
+#define rsv_end rsv_window._rsv_end
+
+/*
+ * storage for cached extent
+ */
+struct ext4_ext_cache {
+ ext4_fsblk_t ec_start;
+ __u32 ec_block;
+ __u32 ec_len; /* must be 32bit to return holes */
+ __u32 ec_type;
+};
+
+/*
+ * third extended file system inode data in memory
+ */
+struct ext4_inode_info {
+ __le32 i_data[15]; /* unconverted */
+ __u32 i_flags;
+#ifdef EXT4_FRAGMENTS
+ __u32 i_faddr;
+ __u8 i_frag_no;
+ __u8 i_frag_size;
+#endif
+ ext4_fsblk_t i_file_acl;
+ __u32 i_dir_acl;
+ __u32 i_dtime;
+
+ /*
+ * i_block_group is the number of the block group which contains
+ * this file's inode. Constant across the lifetime of the inode,
+ * it is ued for making block allocation decisions - we try to
+ * place a file's data blocks near its inode block, and new inodes
+ * near to their parent directory's inode.
+ */
+ __u32 i_block_group;
+ __u32 i_state; /* Dynamic state flags for ext4 */
+
+ /* block reservation info */
+ struct ext4_block_alloc_info *i_block_alloc_info;
+
+ __u32 i_dir_start_lookup;
+#ifdef CONFIG_EXT4DEV_FS_XATTR
+ /*
+ * Extended attributes can be read independently of the main file
+ * data. Taking i_mutex even when reading would cause contention
+ * between readers of EAs and writers of regular file data, so
+ * instead we synchronize on xattr_sem when reading or changing
+ * EAs.
+ */
+ struct rw_semaphore xattr_sem;
+#endif
+#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
+ struct posix_acl *i_acl;
+ struct posix_acl *i_default_acl;
+#endif
+
+ struct list_head i_orphan; /* unlinked but open inodes */
+
+ /*
+ * i_disksize keeps track of what the inode size is ON DISK, not
+ * in memory. During truncate, i_size is set to the new size by
+ * the VFS prior to calling ext4_truncate(), but the filesystem won't
+ * set i_disksize to 0 until the truncate is actually under way.
+ *
+ * The intent is that i_disksize always represents the blocks which
+ * are used by this file. This allows recovery to restart truncate
+ * on orphans if we crash during truncate. We actually write i_disksize
+ * into the on-disk inode when writing inodes out, instead of i_size.
+ *
+ * The only time when i_disksize and i_size may be different is when
+ * a truncate is in progress. The only things which change i_disksize
+ * are ext4_get_block (growth) and ext4_truncate (shrinkth).
+ */
+ loff_t i_disksize;
+
+ /* on-disk additional length */
+ __u16 i_extra_isize;
+
+ /*
+ * truncate_mutex is for serialising ext4_truncate() against
+ * ext4_getblock(). In the 2.4 ext2 design, great chunks of inode's
+ * data tree are chopped off during truncate. We can't do that in
+ * ext4 because whenever we perform intermediate commits during
+ * truncate, the inode and all the metadata blocks *must* be in a
+ * consistent state which allows truncation of the orphans to restart
+ * during recovery. Hence we must fix the get_block-vs-truncate race
+ * by other means, so we have truncate_mutex.
+ */
+ struct mutex truncate_mutex;
+ struct inode vfs_inode;
+
+ unsigned long i_ext_generation;
+ struct ext4_ext_cache i_cached_extent;
+};
+
+#endif /* _LINUX_EXT4_FS_I */
--- /dev/null
+/*
+ * linux/include/linux/ext4_fs_sb.h
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ * from
+ *
+ * linux/include/linux/minix_fs_sb.h
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ */
+
+#ifndef _LINUX_EXT4_FS_SB
+#define _LINUX_EXT4_FS_SB
+
+#ifdef __KERNEL__
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/blockgroup_lock.h>
+#include <linux/percpu_counter.h>
+#endif
+#include <linux/rbtree.h>
+
+/*
+ * third extended-fs super-block data in memory
+ */
+struct ext4_sb_info {
+ unsigned long s_frag_size; /* Size of a fragment in bytes */
+ unsigned long s_desc_size; /* Size of a group descriptor in bytes */
+ unsigned long s_frags_per_block;/* Number of fragments per block */
+ unsigned long s_inodes_per_block;/* Number of inodes per block */
+ unsigned long s_frags_per_group;/* Number of fragments in a group */
+ unsigned long s_blocks_per_group;/* Number of blocks in a group */
+ unsigned long s_inodes_per_group;/* Number of inodes in a group */
+ unsigned long s_itb_per_group; /* Number of inode table blocks per group */
+ unsigned long s_gdb_count; /* Number of group descriptor blocks */
+ unsigned long s_desc_per_block; /* Number of group descriptors per block */
+ unsigned long s_groups_count; /* Number of groups in the fs */
+ struct buffer_head * s_sbh; /* Buffer containing the super block */
+ struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */
+ struct buffer_head ** s_group_desc;
+ unsigned long s_mount_opt;
+ uid_t s_resuid;
+ gid_t s_resgid;
+ unsigned short s_mount_state;
+ unsigned short s_pad;
+ int s_addr_per_block_bits;
+ int s_desc_per_block_bits;
+ int s_inode_size;
+ int s_first_ino;
+ spinlock_t s_next_gen_lock;
+ u32 s_next_generation;
+ u32 s_hash_seed[4];
+ int s_def_hash_version;
+ struct percpu_counter s_freeblocks_counter;
+ struct percpu_counter s_freeinodes_counter;
+ struct percpu_counter s_dirs_counter;
+ struct blockgroup_lock s_blockgroup_lock;
+
+ /* root of the per fs reservation window tree */
+ spinlock_t s_rsv_window_lock;
+ struct rb_root s_rsv_window_root;
+ struct ext4_reserve_window_node s_rsv_window_head;
+
+ /* Journaling */
+ struct inode * s_journal_inode;
+ struct journal_s * s_journal;
+ struct list_head s_orphan;
+ unsigned long s_commit_interval;
+ struct block_device *journal_bdev;
+#ifdef CONFIG_JBD_DEBUG
+ struct timer_list turn_ro_timer; /* For turning read-only (crash simulation) */
+ wait_queue_head_t ro_wait_queue; /* For people waiting for the fs to go read-only */
+#endif
+#ifdef CONFIG_QUOTA
+ char *s_qf_names[MAXQUOTAS]; /* Names of quota files with journalled quota */
+ int s_jquota_fmt; /* Format of quota to use */
+#endif
+
+#ifdef EXTENTS_STATS
+ /* ext4 extents stats */
+ unsigned long s_ext_min;
+ unsigned long s_ext_max;
+ unsigned long s_depth_max;
+ spinlock_t s_ext_stats_lock;
+ unsigned long s_ext_blocks;
+ unsigned long s_ext_extents;
+#endif
+};
+
+#endif /* _LINUX_EXT4_FS_SB */
--- /dev/null
+/*
+ * linux/include/linux/ext4_jbd2.h
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>, 1999
+ *
+ * Copyright 1998--1999 Red Hat corp --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Ext4-specific journaling extensions.
+ */
+
+#ifndef _LINUX_EXT4_JBD_H
+#define _LINUX_EXT4_JBD_H
+
+#include <linux/fs.h>
+#include <linux/jbd2.h>
+#include <linux/ext4_fs.h>
+
+#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal)
+
+/* Define the number of blocks we need to account to a transaction to
+ * modify one block of data.
+ *
+ * We may have to touch one inode, one bitmap buffer, up to three
+ * indirection blocks, the group and superblock summaries, and the data
+ * block to complete the transaction.
+ *
+ * For extents-enabled fs we may have to allocate and modify up to
+ * 5 levels of tree + root which are stored in the inode. */
+
+#define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \
+ (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS) \
+ || test_opt(sb, EXTENTS) ? 27U : 8U)
+
+/* Extended attribute operations touch at most two data buffers,
+ * two bitmap buffers, and two group summaries, in addition to the inode
+ * and the superblock, which are already accounted for. */
+
+#define EXT4_XATTR_TRANS_BLOCKS 6U
+
+/* Define the minimum size for a transaction which modifies data. This
+ * needs to take into account the fact that we may end up modifying two
+ * quota files too (one for the group, one for the user quota). The
+ * superblock only gets updated once, of course, so don't bother
+ * counting that again for the quota updates. */
+
+#define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
+ EXT4_XATTR_TRANS_BLOCKS - 2 + \
+ 2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+
+/* Delete operations potentially hit one directory's namespace plus an
+ * entire inode, plus arbitrary amounts of bitmap/indirection data. Be
+ * generous. We can grow the delete transaction later if necessary. */
+
+#define EXT4_DELETE_TRANS_BLOCKS(sb) (2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64)
+
+/* Define an arbitrary limit for the amount of data we will anticipate
+ * writing to any given transaction. For unbounded transactions such as
+ * write(2) and truncate(2) we can write more than this, but we always
+ * start off at the maximum transaction size and grow the transaction
+ * optimistically as we go. */
+
+#define EXT4_MAX_TRANS_DATA 64U
+
+/* We break up a large truncate or write transaction once the handle's
+ * buffer credits gets this low, we need either to extend the
+ * transaction or to start a new one. Reserve enough space here for
+ * inode, bitmap, superblock, group and indirection updates for at least
+ * one block, plus two quota updates. Quota allocations are not
+ * needed. */
+
+#define EXT4_RESERVE_TRANS_BLOCKS 12U
+
+#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8
+
+#ifdef CONFIG_QUOTA
+/* Amount of blocks needed for quota update - we know that the structure was
+ * allocated so we need to update only inode+data */
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) (test_opt(sb, QUOTA) ? 2 : 0)
+/* Amount of blocks needed for quota insert/delete - we do some block writes
+ * but inode, sb and group updates are done only once */
+#define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
+ (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
+#define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
+ (EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
+#else
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) 0
+#define EXT4_QUOTA_INIT_BLOCKS(sb) 0
+#define EXT4_QUOTA_DEL_BLOCKS(sb) 0
+#endif
+
+int
+ext4_mark_iloc_dirty(handle_t *handle,
+ struct inode *inode,
+ struct ext4_iloc *iloc);
+
+/*
+ * On success, We end up with an outstanding reference count against
+ * iloc->bh. This _must_ be cleaned up later.
+ */
+
+int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
+ struct ext4_iloc *iloc);
+
+int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
+
+/*
+ * Wrapper functions with which ext4 calls into JBD. The intent here is
+ * to allow these to be turned into appropriate stubs so ext4 can control
+ * ext2 filesystems, so ext2+ext4 systems only nee one fs. This work hasn't
+ * been done yet.
+ */
+
+void ext4_journal_abort_handle(const char *caller, const char *err_fn,
+ struct buffer_head *bh, handle_t *handle, int err);
+
+static inline int
+__ext4_journal_get_undo_access(const char *where, handle_t *handle,
+ struct buffer_head *bh)
+{
+ int err = jbd2_journal_get_undo_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+ return err;
+}
+
+static inline int
+__ext4_journal_get_write_access(const char *where, handle_t *handle,
+ struct buffer_head *bh)
+{
+ int err = jbd2_journal_get_write_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+ return err;
+}
+
+static inline void
+ext4_journal_release_buffer(handle_t *handle, struct buffer_head *bh)
+{
+ jbd2_journal_release_buffer(handle, bh);
+}
+
+static inline int
+__ext4_journal_forget(const char *where, handle_t *handle, struct buffer_head *bh)
+{
+ int err = jbd2_journal_forget(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+ return err;
+}
+
+static inline int
+__ext4_journal_revoke(const char *where, handle_t *handle,
+ ext4_fsblk_t blocknr, struct buffer_head *bh)
+{
+ int err = jbd2_journal_revoke(handle, blocknr, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+ return err;
+}
+
+static inline int
+__ext4_journal_get_create_access(const char *where,
+ handle_t *handle, struct buffer_head *bh)
+{
+ int err = jbd2_journal_get_create_access(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+ return err;
+}
+
+static inline int
+__ext4_journal_dirty_metadata(const char *where,
+ handle_t *handle, struct buffer_head *bh)
+{
+ int err = jbd2_journal_dirty_metadata(handle, bh);
+ if (err)
+ ext4_journal_abort_handle(where, __FUNCTION__, bh, handle,err);
+ return err;
+}
+
+
+#define ext4_journal_get_undo_access(handle, bh) \
+ __ext4_journal_get_undo_access(__FUNCTION__, (handle), (bh))
+#define ext4_journal_get_write_access(handle, bh) \
+ __ext4_journal_get_write_access(__FUNCTION__, (handle), (bh))
+#define ext4_journal_revoke(handle, blocknr, bh) \
+ __ext4_journal_revoke(__FUNCTION__, (handle), (blocknr), (bh))
+#define ext4_journal_get_create_access(handle, bh) \
+ __ext4_journal_get_create_access(__FUNCTION__, (handle), (bh))
+#define ext4_journal_dirty_metadata(handle, bh) \
+ __ext4_journal_dirty_metadata(__FUNCTION__, (handle), (bh))
+#define ext4_journal_forget(handle, bh) \
+ __ext4_journal_forget(__FUNCTION__, (handle), (bh))
+
+int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh);
+
+handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
+int __ext4_journal_stop(const char *where, handle_t *handle);
+
+static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
+{
+ return ext4_journal_start_sb(inode->i_sb, nblocks);
+}
+
+#define ext4_journal_stop(handle) \
+ __ext4_journal_stop(__FUNCTION__, (handle))
+
+static inline handle_t *ext4_journal_current_handle(void)
+{
+ return journal_current_handle();
+}
+
+static inline int ext4_journal_extend(handle_t *handle, int nblocks)
+{
+ return jbd2_journal_extend(handle, nblocks);
+}
+
+static inline int ext4_journal_restart(handle_t *handle, int nblocks)
+{
+ return jbd2_journal_restart(handle, nblocks);
+}
+
+static inline int ext4_journal_blocks_per_page(struct inode *inode)
+{
+ return jbd2_journal_blocks_per_page(inode);
+}
+
+static inline int ext4_journal_force_commit(journal_t *journal)
+{
+ return jbd2_journal_force_commit(journal);
+}
+
+/* super.c */
+int ext4_force_commit(struct super_block *sb);
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+ if (!S_ISREG(inode->i_mode))
+ return 1;
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ return 1;
+ if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ return 1;
+ return 0;
+}
+
+static inline int ext4_should_order_data(struct inode *inode)
+{
+ if (!S_ISREG(inode->i_mode))
+ return 0;
+ if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ return 0;
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ return 1;
+ return 0;
+}
+
+static inline int ext4_should_writeback_data(struct inode *inode)
+{
+ if (!S_ISREG(inode->i_mode))
+ return 0;
+ if (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL)
+ return 0;
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+ return 1;
+ return 0;
+}
+
+#endif /* _LINUX_EXT4_JBD_H */
#endif
}
-
+/*
+ * NOTE: unlike i_size_read(), i_size_write() does need locking around it
+ * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
+ * can be lost, resulting in subsequent i_size_read() calls spinning forever.
+ */
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int);
void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
+void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
int hugetlb_report_meminfo(char *);
int hugetlb_report_node_meminfo(int, char *);
int ioremap_page_range(unsigned long addr, unsigned long end,
unsigned long phys_addr, pgprot_t prot);
+/**
+ * check_signature - find BIOS signatures
+ * @io_addr: mmio address to check
+ * @signature: signature block
+ * @length: length of signature
+ *
+ * Perform a signature comparison with the mmio address io_addr. This
+ * address should have been obtained by ioremap.
+ * Returns 1 on a match.
+ */
+
+static inline int check_signature(const volatile void __iomem *io_addr,
+ const unsigned char *signature, int length)
+{
+ int retval = 0;
+ do {
+ if (readb(io_addr) != *signature)
+ goto out;
+ io_addr++;
+ signature++;
+ length--;
+ } while (length);
+ retval = 1;
+out:
+ return retval;
+}
+
#endif /* _LINUX_IO_H */
* @pending_mask: pending rebalanced interrupts
* @dir: /proc/irq/ procfs entry
* @affinity_entry: /proc/irq/smp_affinity procfs entry on SMP
+ * @name: flow handler name for /proc/interrupts output
*
* Pad this out to 32 bytes for cache and indexing reasons.
*/
cpumask_t pending_mask;
#endif
#ifdef CONFIG_PROC_FS
- struct proc_dir_entry *dir;
+ struct proc_dir_entry *dir;
#endif
+ const char *name;
} ____cacheline_aligned;
extern struct irq_desc irq_desc[NR_IRQS];
extern void fastcall handle_percpu_irq(unsigned int irq, struct irq_desc *desc);
extern void fastcall handle_bad_irq(unsigned int irq, struct irq_desc *desc);
-/*
- * Get a descriptive string for the highlevel handler, for
- * /proc/interrupts output:
- */
-extern const char *handle_irq_name(irq_flow_handler_t handle);
-
/*
* Monolithic do_IRQ implementation.
* (is an explicit fastcall, because i386 4KSTACKS calls it from assembly)
extern struct irq_chip dummy_irq_chip;
extern void
-set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip,
- irq_flow_handler_t handle);
+set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+ irq_flow_handler_t handle, const char *name);
+
extern void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained);
+__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+ const char *name);
/*
* Set a highlevel flow handler for a given IRQ:
static inline void
set_irq_handler(unsigned int irq, irq_flow_handler_t handle)
{
- __set_irq_handler(irq, handle, 0);
+ __set_irq_handler(irq, handle, 0, NULL);
}
/*
set_irq_chained_handler(unsigned int irq,
irq_flow_handler_t handle)
{
- __set_irq_handler(irq, handle, 1);
+ __set_irq_handler(irq, handle, 1, NULL);
}
/* Handle dynamic irq creation and destruction */
--- /dev/null
+/*
+ * linux/include/linux/jbd2.h
+ *
+ * Written by Stephen C. Tweedie <sct@redhat.com>
+ *
+ * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved
+ *
+ * This file is part of the Linux kernel and is made available under
+ * the terms of the GNU General Public License, version 2, or at your
+ * option, any later version, incorporated herein by reference.
+ *
+ * Definitions for transaction data structures for the buffer cache
+ * filesystem journaling support.
+ */
+
+#ifndef _LINUX_JBD_H
+#define _LINUX_JBD_H
+
+/* Allow this file to be included directly into e2fsprogs */
+#ifndef __KERNEL__
+#include "jfs_compat.h"
+#define JBD2_DEBUG
+#define jfs_debug jbd_debug
+#else
+
+#include <linux/types.h>
+#include <linux/buffer_head.h>
+#include <linux/journal-head.h>
+#include <linux/stddef.h>
+#include <linux/bit_spinlock.h>
+#include <linux/mutex.h>
+#include <linux/timer.h>
+
+#include <asm/semaphore.h>
+#endif
+
+#define journal_oom_retry 1
+
+/*
+ * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds
+ * certain classes of error which can occur due to failed IOs. Under
+ * normal use we want ext3 to continue after such errors, because
+ * hardware _can_ fail, but for debugging purposes when running tests on
+ * known-good hardware we may want to trap these errors.
+ */
+#undef JBD_PARANOID_IOFAIL
+
+/*
+ * The default maximum commit age, in seconds.
+ */
+#define JBD_DEFAULT_MAX_COMMIT_AGE 5
+
+#ifdef CONFIG_JBD_DEBUG
+/*
+ * Define JBD_EXPENSIVE_CHECKING to enable more expensive internal
+ * consistency checks. By default we don't do this unless
+ * CONFIG_JBD_DEBUG is on.
+ */
+#define JBD_EXPENSIVE_CHECKING
+extern int jbd2_journal_enable_debug;
+
+#define jbd_debug(n, f, a...) \
+ do { \
+ if ((n) <= jbd2_journal_enable_debug) { \
+ printk (KERN_DEBUG "(%s, %d): %s: ", \
+ __FILE__, __LINE__, __FUNCTION__); \
+ printk (f, ## a); \
+ } \
+ } while (0)
+#else
+#define jbd_debug(f, a...) /**/
+#endif
+
+extern void * __jbd2_kmalloc (const char *where, size_t size, gfp_t flags, int retry);
+extern void * jbd2_slab_alloc(size_t size, gfp_t flags);
+extern void jbd2_slab_free(void *ptr, size_t size);
+
+#define jbd_kmalloc(size, flags) \
+ __jbd2_kmalloc(__FUNCTION__, (size), (flags), journal_oom_retry)
+#define jbd_rep_kmalloc(size, flags) \
+ __jbd2_kmalloc(__FUNCTION__, (size), (flags), 1)
+
+#define JBD2_MIN_JOURNAL_BLOCKS 1024
+
+#ifdef __KERNEL__
+
+/**
+ * typedef handle_t - The handle_t type represents a single atomic update being performed by some process.
+ *
+ * All filesystem modifications made by the process go
+ * through this handle. Recursive operations (such as quota operations)
+ * are gathered into a single update.
+ *
+ * The buffer credits field is used to account for journaled buffers
+ * being modified by the running process. To ensure that there is
+ * enough log space for all outstanding operations, we need to limit the
+ * number of outstanding buffers possible at any time. When the
+ * operation completes, any buffer credits not used are credited back to
+ * the transaction, so that at all times we know how many buffers the
+ * outstanding updates on a transaction might possibly touch.
+ *
+ * This is an opaque datatype.
+ **/
+typedef struct handle_s handle_t; /* Atomic operation type */
+
+
+/**
+ * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem.
+ *
+ * journal_t is linked to from the fs superblock structure.
+ *
+ * We use the journal_t to keep track of all outstanding transaction
+ * activity on the filesystem, and to manage the state of the log
+ * writing process.
+ *
+ * This is an opaque datatype.
+ **/
+typedef struct journal_s journal_t; /* Journal control structure */
+#endif
+
+/*
+ * Internal structures used by the logging mechanism:
+ */
+
+#define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */
+
+/*
+ * On-disk structures
+ */
+
+/*
+ * Descriptor block types:
+ */
+
+#define JBD2_DESCRIPTOR_BLOCK 1
+#define JBD2_COMMIT_BLOCK 2
+#define JBD2_SUPERBLOCK_V1 3
+#define JBD2_SUPERBLOCK_V2 4
+#define JBD2_REVOKE_BLOCK 5
+
+/*
+ * Standard header for all descriptor blocks:
+ */
+typedef struct journal_header_s
+{
+ __be32 h_magic;
+ __be32 h_blocktype;
+ __be32 h_sequence;
+} journal_header_t;
+
+
+/*
+ * The block tag: used to describe a single buffer in the journal.
+ * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this
+ * raw struct shouldn't be used for pointer math or sizeof() - use
+ * journal_tag_bytes(journal) instead to compute this.
+ */
+typedef struct journal_block_tag_s
+{
+ __be32 t_blocknr; /* The on-disk block number */
+ __be32 t_flags; /* See below */
+ __be32 t_blocknr_high; /* most-significant high 32bits. */
+} journal_block_tag_t;
+
+#define JBD_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high))
+#define JBD_TAG_SIZE64 (sizeof(journal_block_tag_t))
+
+/*
+ * The revoke descriptor: used on disk to describe a series of blocks to
+ * be revoked from the log
+ */
+typedef struct jbd2_journal_revoke_header_s
+{
+ journal_header_t r_header;
+ __be32 r_count; /* Count of bytes used in the block */
+} jbd2_journal_revoke_header_t;
+
+
+/* Definitions for the journal tag flags word: */
+#define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */
+#define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */
+#define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */
+#define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */
+
+
+/*
+ * The journal superblock. All fields are in big-endian byte order.
+ */
+typedef struct journal_superblock_s
+{
+/* 0x0000 */
+ journal_header_t s_header;
+
+/* 0x000C */
+ /* Static information describing the journal */
+ __be32 s_blocksize; /* journal device blocksize */
+ __be32 s_maxlen; /* total blocks in journal file */
+ __be32 s_first; /* first block of log information */
+
+/* 0x0018 */
+ /* Dynamic information describing the current state of the log */
+ __be32 s_sequence; /* first commit ID expected in log */
+ __be32 s_start; /* blocknr of start of log */
+
+/* 0x0020 */
+ /* Error value, as set by jbd2_journal_abort(). */
+ __be32 s_errno;
+
+/* 0x0024 */
+ /* Remaining fields are only valid in a version-2 superblock */
+ __be32 s_feature_compat; /* compatible feature set */
+ __be32 s_feature_incompat; /* incompatible feature set */
+ __be32 s_feature_ro_compat; /* readonly-compatible feature set */
+/* 0x0030 */
+ __u8 s_uuid[16]; /* 128-bit uuid for journal */
+
+/* 0x0040 */
+ __be32 s_nr_users; /* Nr of filesystems sharing log */
+
+ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/
+
+/* 0x0048 */
+ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/
+ __be32 s_max_trans_data; /* Limit of data blocks per trans. */
+
+/* 0x0050 */
+ __u32 s_padding[44];
+
+/* 0x0100 */
+ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */
+/* 0x0400 */
+} journal_superblock_t;
+
+#define JBD2_HAS_COMPAT_FEATURE(j,mask) \
+ ((j)->j_format_version >= 2 && \
+ ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask))))
+#define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \
+ ((j)->j_format_version >= 2 && \
+ ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask))))
+#define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \
+ ((j)->j_format_version >= 2 && \
+ ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask))))
+
+#define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001
+#define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002
+
+/* Features known to this kernel version: */
+#define JBD2_KNOWN_COMPAT_FEATURES 0
+#define JBD2_KNOWN_ROCOMPAT_FEATURES 0
+#define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \
+ JBD2_FEATURE_INCOMPAT_64BIT)
+
+#ifdef __KERNEL__
+
+#include <linux/fs.h>
+#include <linux/sched.h>
+
+#define JBD_ASSERTIONS
+#ifdef JBD_ASSERTIONS
+#define J_ASSERT(assert) \
+do { \
+ if (!(assert)) { \
+ printk (KERN_EMERG \
+ "Assertion failure in %s() at %s:%d: \"%s\"\n", \
+ __FUNCTION__, __FILE__, __LINE__, # assert); \
+ BUG(); \
+ } \
+} while (0)
+
+#if defined(CONFIG_BUFFER_DEBUG)
+void buffer_assertion_failure(struct buffer_head *bh);
+#define J_ASSERT_BH(bh, expr) \
+ do { \
+ if (!(expr)) \
+ buffer_assertion_failure(bh); \
+ J_ASSERT(expr); \
+ } while (0)
+#define J_ASSERT_JH(jh, expr) J_ASSERT_BH(jh2bh(jh), expr)
+#else
+#define J_ASSERT_BH(bh, expr) J_ASSERT(expr)
+#define J_ASSERT_JH(jh, expr) J_ASSERT(expr)
+#endif
+
+#else
+#define J_ASSERT(assert) do { } while (0)
+#endif /* JBD_ASSERTIONS */
+
+#if defined(JBD_PARANOID_IOFAIL)
+#define J_EXPECT(expr, why...) J_ASSERT(expr)
+#define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr)
+#define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr)
+#else
+#define __journal_expect(expr, why...) \
+ ({ \
+ int val = (expr); \
+ if (!val) { \
+ printk(KERN_ERR \
+ "EXT3-fs unexpected failure: %s;\n",# expr); \
+ printk(KERN_ERR why "\n"); \
+ } \
+ val; \
+ })
+#define J_EXPECT(expr, why...) __journal_expect(expr, ## why)
+#define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why)
+#define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why)
+#endif
+
+enum jbd_state_bits {
+ BH_JBD /* Has an attached ext3 journal_head */
+ = BH_PrivateStart,
+ BH_JWrite, /* Being written to log (@@@ DEBUGGING) */
+ BH_Freed, /* Has been freed (truncated) */
+ BH_Revoked, /* Has been revoked from the log */
+ BH_RevokeValid, /* Revoked flag is valid */
+ BH_JBDDirty, /* Is dirty but journaled */
+ BH_State, /* Pins most journal_head state */
+ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */
+ BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */
+};
+
+BUFFER_FNS(JBD, jbd)
+BUFFER_FNS(JWrite, jwrite)
+BUFFER_FNS(JBDDirty, jbddirty)
+TAS_BUFFER_FNS(JBDDirty, jbddirty)
+BUFFER_FNS(Revoked, revoked)
+TAS_BUFFER_FNS(Revoked, revoked)
+BUFFER_FNS(RevokeValid, revokevalid)
+TAS_BUFFER_FNS(RevokeValid, revokevalid)
+BUFFER_FNS(Freed, freed)
+
+static inline struct buffer_head *jh2bh(struct journal_head *jh)
+{
+ return jh->b_bh;
+}
+
+static inline struct journal_head *bh2jh(struct buffer_head *bh)
+{
+ return bh->b_private;
+}
+
+static inline void jbd_lock_bh_state(struct buffer_head *bh)
+{
+ bit_spin_lock(BH_State, &bh->b_state);
+}
+
+static inline int jbd_trylock_bh_state(struct buffer_head *bh)
+{
+ return bit_spin_trylock(BH_State, &bh->b_state);
+}
+
+static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
+{
+ return bit_spin_is_locked(BH_State, &bh->b_state);
+}
+
+static inline void jbd_unlock_bh_state(struct buffer_head *bh)
+{
+ bit_spin_unlock(BH_State, &bh->b_state);
+}
+
+static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
+{
+ bit_spin_lock(BH_JournalHead, &bh->b_state);
+}
+
+static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
+{
+ bit_spin_unlock(BH_JournalHead, &bh->b_state);
+}
+
+struct jbd2_revoke_table_s;
+
+/**
+ * struct handle_s - The handle_s type is the concrete type associated with
+ * handle_t.
+ * @h_transaction: Which compound transaction is this update a part of?
+ * @h_buffer_credits: Number of remaining buffers we are allowed to dirty.
+ * @h_ref: Reference count on this handle
+ * @h_err: Field for caller's use to track errors through large fs operations
+ * @h_sync: flag for sync-on-close
+ * @h_jdata: flag to force data journaling
+ * @h_aborted: flag indicating fatal error on handle
+ **/
+
+/* Docbook can't yet cope with the bit fields, but will leave the documentation
+ * in so it can be fixed later.
+ */
+
+struct handle_s
+{
+ /* Which compound transaction is this update a part of? */
+ transaction_t *h_transaction;
+
+ /* Number of remaining buffers we are allowed to dirty: */
+ int h_buffer_credits;
+
+ /* Reference count on this handle */
+ int h_ref;
+
+ /* Field for caller's use to track errors through large fs */
+ /* operations */
+ int h_err;
+
+ /* Flags [no locking] */
+ unsigned int h_sync: 1; /* sync-on-close */
+ unsigned int h_jdata: 1; /* force data journaling */
+ unsigned int h_aborted: 1; /* fatal error on handle */
+};
+
+
+/* The transaction_t type is the guts of the journaling mechanism. It
+ * tracks a compound transaction through its various states:
+ *
+ * RUNNING: accepting new updates
+ * LOCKED: Updates still running but we don't accept new ones
+ * RUNDOWN: Updates are tidying up but have finished requesting
+ * new buffers to modify (state not used for now)
+ * FLUSH: All updates complete, but we are still writing to disk
+ * COMMIT: All data on disk, writing commit record
+ * FINISHED: We still have to keep the transaction for checkpointing.
+ *
+ * The transaction keeps track of all of the buffers modified by a
+ * running transaction, and all of the buffers committed but not yet
+ * flushed to home for finished transactions.
+ */
+
+/*
+ * Lock ranking:
+ *
+ * j_list_lock
+ * ->jbd_lock_bh_journal_head() (This is "innermost")
+ *
+ * j_state_lock
+ * ->jbd_lock_bh_state()
+ *
+ * jbd_lock_bh_state()
+ * ->j_list_lock
+ *
+ * j_state_lock
+ * ->t_handle_lock
+ *
+ * j_state_lock
+ * ->j_list_lock (journal_unmap_buffer)
+ *
+ */
+
+struct transaction_s
+{
+ /* Pointer to the journal for this transaction. [no locking] */
+ journal_t *t_journal;
+
+ /* Sequence number for this transaction [no locking] */
+ tid_t t_tid;
+
+ /*
+ * Transaction's current state
+ * [no locking - only kjournald2 alters this]
+ * FIXME: needs barriers
+ * KLUDGE: [use j_state_lock]
+ */
+ enum {
+ T_RUNNING,
+ T_LOCKED,
+ T_RUNDOWN,
+ T_FLUSH,
+ T_COMMIT,
+ T_FINISHED
+ } t_state;
+
+ /*
+ * Where in the log does this transaction's commit start? [no locking]
+ */
+ unsigned long t_log_start;
+
+ /* Number of buffers on the t_buffers list [j_list_lock] */
+ int t_nr_buffers;
+
+ /*
+ * Doubly-linked circular list of all buffers reserved but not yet
+ * modified by this transaction [j_list_lock]
+ */
+ struct journal_head *t_reserved_list;
+
+ /*
+ * Doubly-linked circular list of all buffers under writeout during
+ * commit [j_list_lock]
+ */
+ struct journal_head *t_locked_list;
+
+ /*
+ * Doubly-linked circular list of all metadata buffers owned by this
+ * transaction [j_list_lock]
+ */
+ struct journal_head *t_buffers;
+
+ /*
+ * Doubly-linked circular list of all data buffers still to be
+ * flushed before this transaction can be committed [j_list_lock]
+ */
+ struct journal_head *t_sync_datalist;
+
+ /*
+ * Doubly-linked circular list of all forget buffers (superseded
+ * buffers which we can un-checkpoint once this transaction commits)
+ * [j_list_lock]
+ */
+ struct journal_head *t_forget;
+
+ /*
+ * Doubly-linked circular list of all buffers still to be flushed before
+ * this transaction can be checkpointed. [j_list_lock]
+ */
+ struct journal_head *t_checkpoint_list;
+
+ /*
+ * Doubly-linked circular list of all buffers submitted for IO while
+ * checkpointing. [j_list_lock]
+ */
+ struct journal_head *t_checkpoint_io_list;
+
+ /*
+ * Doubly-linked circular list of temporary buffers currently undergoing
+ * IO in the log [j_list_lock]
+ */
+ struct journal_head *t_iobuf_list;
+
+ /*
+ * Doubly-linked circular list of metadata buffers being shadowed by log
+ * IO. The IO buffers on the iobuf list and the shadow buffers on this
+ * list match each other one for one at all times. [j_list_lock]
+ */
+ struct journal_head *t_shadow_list;
+
+ /*
+ * Doubly-linked circular list of control buffers being written to the
+ * log. [j_list_lock]
+ */
+ struct journal_head *t_log_list;
+
+ /*
+ * Protects info related to handles
+ */
+ spinlock_t t_handle_lock;
+
+ /*
+ * Number of outstanding updates running on this transaction
+ * [t_handle_lock]
+ */
+ int t_updates;
+
+ /*
+ * Number of buffers reserved for use by all handles in this transaction
+ * handle but not yet modified. [t_handle_lock]
+ */
+ int t_outstanding_credits;
+
+ /*
+ * Forward and backward links for the circular list of all transactions
+ * awaiting checkpoint. [j_list_lock]
+ */
+ transaction_t *t_cpnext, *t_cpprev;
+
+ /*
+ * When will the transaction expire (become due for commit), in jiffies?
+ * [no locking]
+ */
+ unsigned long t_expires;
+
+ /*
+ * How many handles used this transaction? [t_handle_lock]
+ */
+ int t_handle_count;
+
+};
+
+/**
+ * struct journal_s - The journal_s type is the concrete type associated with
+ * journal_t.
+ * @j_flags: General journaling state flags
+ * @j_errno: Is there an outstanding uncleared error on the journal (from a
+ * prior abort)?
+ * @j_sb_buffer: First part of superblock buffer
+ * @j_superblock: Second part of superblock buffer
+ * @j_format_version: Version of the superblock format
+ * @j_state_lock: Protect the various scalars in the journal
+ * @j_barrier_count: Number of processes waiting to create a barrier lock
+ * @j_barrier: The barrier lock itself
+ * @j_running_transaction: The current running transaction..
+ * @j_committing_transaction: the transaction we are pushing to disk
+ * @j_checkpoint_transactions: a linked circular list of all transactions
+ * waiting for checkpointing
+ * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction
+ * to start committing, or for a barrier lock to be released
+ * @j_wait_logspace: Wait queue for waiting for checkpointing to complete
+ * @j_wait_done_commit: Wait queue for waiting for commit to complete
+ * @j_wait_checkpoint: Wait queue to trigger checkpointing
+ * @j_wait_commit: Wait queue to trigger commit
+ * @j_wait_updates: Wait queue to wait for updates to complete
+ * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints
+ * @j_head: Journal head - identifies the first unused block in the journal
+ * @j_tail: Journal tail - identifies the oldest still-used block in the
+ * journal.
+ * @j_free: Journal free - how many free blocks are there in the journal?
+ * @j_first: The block number of the first usable block
+ * @j_last: The block number one beyond the last usable block
+ * @j_dev: Device where we store the journal
+ * @j_blocksize: blocksize for the location where we store the journal.
+ * @j_blk_offset: starting block offset for into the device where we store the
+ * journal
+ * @j_fs_dev: Device which holds the client fs. For internal journal this will
+ * be equal to j_dev
+ * @j_maxlen: Total maximum capacity of the journal region on disk.
+ * @j_list_lock: Protects the buffer lists and internal buffer state.
+ * @j_inode: Optional inode where we store the journal. If present, all journal
+ * block numbers are mapped into this inode via bmap().
+ * @j_tail_sequence: Sequence number of the oldest transaction in the log
+ * @j_transaction_sequence: Sequence number of the next transaction to grant
+ * @j_commit_sequence: Sequence number of the most recently committed
+ * transaction
+ * @j_commit_request: Sequence number of the most recent transaction wanting
+ * commit
+ * @j_uuid: Uuid of client object.
+ * @j_task: Pointer to the current commit thread for this journal
+ * @j_max_transaction_buffers: Maximum number of metadata buffers to allow in a
+ * single compound commit transaction
+ * @j_commit_interval: What is the maximum transaction lifetime before we begin
+ * a commit?
+ * @j_commit_timer: The timer used to wakeup the commit thread
+ * @j_revoke_lock: Protect the revoke table
+ * @j_revoke: The revoke table - maintains the list of revoked blocks in the
+ * current transaction.
+ * @j_revoke_table: alternate revoke tables for j_revoke
+ * @j_wbuf: array of buffer_heads for jbd2_journal_commit_transaction
+ * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the
+ * number that will fit in j_blocksize
+ * @j_last_sync_writer: most recent pid which did a synchronous write
+ * @j_private: An opaque pointer to fs-private information.
+ */
+
+struct journal_s
+{
+ /* General journaling state flags [j_state_lock] */
+ unsigned long j_flags;
+
+ /*
+ * Is there an outstanding uncleared error on the journal (from a prior
+ * abort)? [j_state_lock]
+ */
+ int j_errno;
+
+ /* The superblock buffer */
+ struct buffer_head *j_sb_buffer;
+ journal_superblock_t *j_superblock;
+
+ /* Version of the superblock format */
+ int j_format_version;
+
+ /*
+ * Protect the various scalars in the journal
+ */
+ spinlock_t j_state_lock;
+
+ /*
+ * Number of processes waiting to create a barrier lock [j_state_lock]
+ */
+ int j_barrier_count;
+
+ /* The barrier lock itself */
+ struct mutex j_barrier;
+
+ /*
+ * Transactions: The current running transaction...
+ * [j_state_lock] [caller holding open handle]
+ */
+ transaction_t *j_running_transaction;
+
+ /*
+ * the transaction we are pushing to disk
+ * [j_state_lock] [caller holding open handle]
+ */
+ transaction_t *j_committing_transaction;
+
+ /*
+ * ... and a linked circular list of all transactions waiting for
+ * checkpointing. [j_list_lock]
+ */
+ transaction_t *j_checkpoint_transactions;
+
+ /*
+ * Wait queue for waiting for a locked transaction to start committing,
+ * or for a barrier lock to be released
+ */
+ wait_queue_head_t j_wait_transaction_locked;
+
+ /* Wait queue for waiting for checkpointing to complete */
+ wait_queue_head_t j_wait_logspace;
+
+ /* Wait queue for waiting for commit to complete */
+ wait_queue_head_t j_wait_done_commit;
+
+ /* Wait queue to trigger checkpointing */
+ wait_queue_head_t j_wait_checkpoint;
+
+ /* Wait queue to trigger commit */
+ wait_queue_head_t j_wait_commit;
+
+ /* Wait queue to wait for updates to complete */
+ wait_queue_head_t j_wait_updates;
+
+ /* Semaphore for locking against concurrent checkpoints */
+ struct mutex j_checkpoint_mutex;
+
+ /*
+ * Journal head: identifies the first unused block in the journal.
+ * [j_state_lock]
+ */
+ unsigned long j_head;
+
+ /*
+ * Journal tail: identifies the oldest still-used block in the journal.
+ * [j_state_lock]
+ */
+ unsigned long j_tail;
+
+ /*
+ * Journal free: how many free blocks are there in the journal?
+ * [j_state_lock]
+ */
+ unsigned long j_free;
+
+ /*
+ * Journal start and end: the block numbers of the first usable block
+ * and one beyond the last usable block in the journal. [j_state_lock]
+ */
+ unsigned long j_first;
+ unsigned long j_last;
+
+ /*
+ * Device, blocksize and starting block offset for the location where we
+ * store the journal.
+ */
+ struct block_device *j_dev;
+ int j_blocksize;
+ unsigned long long j_blk_offset;
+
+ /*
+ * Device which holds the client fs. For internal journal this will be
+ * equal to j_dev.
+ */
+ struct block_device *j_fs_dev;
+
+ /* Total maximum capacity of the journal region on disk. */
+ unsigned int j_maxlen;
+
+ /*
+ * Protects the buffer lists and internal buffer state.
+ */
+ spinlock_t j_list_lock;
+
+ /* Optional inode where we store the journal. If present, all */
+ /* journal block numbers are mapped into this inode via */
+ /* bmap(). */
+ struct inode *j_inode;
+
+ /*
+ * Sequence number of the oldest transaction in the log [j_state_lock]
+ */
+ tid_t j_tail_sequence;
+
+ /*
+ * Sequence number of the next transaction to grant [j_state_lock]
+ */
+ tid_t j_transaction_sequence;
+
+ /*
+ * Sequence number of the most recently committed transaction
+ * [j_state_lock].
+ */
+ tid_t j_commit_sequence;
+
+ /*
+ * Sequence number of the most recent transaction wanting commit
+ * [j_state_lock]
+ */
+ tid_t j_commit_request;
+
+ /*
+ * Journal uuid: identifies the object (filesystem, LVM volume etc)
+ * backed by this journal. This will eventually be replaced by an array
+ * of uuids, allowing us to index multiple devices within a single
+ * journal and to perform atomic updates across them.
+ */
+ __u8 j_uuid[16];
+
+ /* Pointer to the current commit thread for this journal */
+ struct task_struct *j_task;
+
+ /*
+ * Maximum number of metadata buffers to allow in a single compound
+ * commit transaction
+ */
+ int j_max_transaction_buffers;
+
+ /*
+ * What is the maximum transaction lifetime before we begin a commit?
+ */
+ unsigned long j_commit_interval;
+
+ /* The timer used to wakeup the commit thread: */
+ struct timer_list j_commit_timer;
+
+ /*
+ * The revoke table: maintains the list of revoked blocks in the
+ * current transaction. [j_revoke_lock]
+ */
+ spinlock_t j_revoke_lock;
+ struct jbd2_revoke_table_s *j_revoke;
+ struct jbd2_revoke_table_s *j_revoke_table[2];
+
+ /*
+ * array of bhs for jbd2_journal_commit_transaction
+ */
+ struct buffer_head **j_wbuf;
+ int j_wbufsize;
+
+ pid_t j_last_sync_writer;
+
+ /*
+ * An opaque pointer to fs-private information. ext3 puts its
+ * superblock pointer here
+ */
+ void *j_private;
+};
+
+/*
+ * Journal flag definitions
+ */
+#define JBD2_UNMOUNT 0x001 /* Journal thread is being destroyed */
+#define JBD2_ABORT 0x002 /* Journaling has been aborted for errors. */
+#define JBD2_ACK_ERR 0x004 /* The errno in the sb has been acked */
+#define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */
+#define JBD2_LOADED 0x010 /* The journal superblock has been loaded */
+#define JBD2_BARRIER 0x020 /* Use IDE barriers */
+
+/*
+ * Function declarations for the journaling transaction and buffer
+ * management
+ */
+
+/* Filing buffers */
+extern void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
+extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *);
+extern void __jbd2_journal_unfile_buffer(struct journal_head *);
+extern void __jbd2_journal_refile_buffer(struct journal_head *);
+extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *);
+extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
+extern void __journal_free_buffer(struct journal_head *bh);
+extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
+extern void __journal_clean_data_list(transaction_t *transaction);
+
+/* Log buffer allocation */
+extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *);
+int jbd2_journal_next_log_block(journal_t *, unsigned long long *);
+
+/* Commit management */
+extern void jbd2_journal_commit_transaction(journal_t *);
+
+/* Checkpoint list management */
+int __jbd2_journal_clean_checkpoint_list(journal_t *journal);
+int __jbd2_journal_remove_checkpoint(struct journal_head *);
+void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
+
+/* Buffer IO */
+extern int
+jbd2_journal_write_metadata_buffer(transaction_t *transaction,
+ struct journal_head *jh_in,
+ struct journal_head **jh_out,
+ unsigned long long blocknr);
+
+/* Transaction locking */
+extern void __wait_on_journal (journal_t *);
+
+/*
+ * Journal locking.
+ *
+ * We need to lock the journal during transaction state changes so that nobody
+ * ever tries to take a handle on the running transaction while we are in the
+ * middle of moving it to the commit phase. j_state_lock does this.
+ *
+ * Note that the locking is completely interrupt unsafe. We never touch
+ * journal structures from interrupts.
+ */
+
+static inline handle_t *journal_current_handle(void)
+{
+ return current->journal_info;
+}
+
+/* The journaling code user interface:
+ *
+ * Create and destroy handles
+ * Register buffer modifications against the current transaction.
+ */
+
+extern handle_t *jbd2_journal_start(journal_t *, int nblocks);
+extern int jbd2_journal_restart (handle_t *, int nblocks);
+extern int jbd2_journal_extend (handle_t *, int nblocks);
+extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
+extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
+extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
+extern int jbd2_journal_dirty_data (handle_t *, struct buffer_head *);
+extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
+extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
+extern int jbd2_journal_forget (handle_t *, struct buffer_head *);
+extern void journal_sync_buffer (struct buffer_head *);
+extern void jbd2_journal_invalidatepage(journal_t *,
+ struct page *, unsigned long);
+extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t);
+extern int jbd2_journal_stop(handle_t *);
+extern int jbd2_journal_flush (journal_t *);
+extern void jbd2_journal_lock_updates (journal_t *);
+extern void jbd2_journal_unlock_updates (journal_t *);
+
+extern journal_t * jbd2_journal_init_dev(struct block_device *bdev,
+ struct block_device *fs_dev,
+ unsigned long long start, int len, int bsize);
+extern journal_t * jbd2_journal_init_inode (struct inode *);
+extern int jbd2_journal_update_format (journal_t *);
+extern int jbd2_journal_check_used_features
+ (journal_t *, unsigned long, unsigned long, unsigned long);
+extern int jbd2_journal_check_available_features
+ (journal_t *, unsigned long, unsigned long, unsigned long);
+extern int jbd2_journal_set_features
+ (journal_t *, unsigned long, unsigned long, unsigned long);
+extern int jbd2_journal_create (journal_t *);
+extern int jbd2_journal_load (journal_t *journal);
+extern void jbd2_journal_destroy (journal_t *);
+extern int jbd2_journal_recover (journal_t *journal);
+extern int jbd2_journal_wipe (journal_t *, int);
+extern int jbd2_journal_skip_recovery (journal_t *);
+extern void jbd2_journal_update_superblock (journal_t *, int);
+extern void __jbd2_journal_abort_hard (journal_t *);
+extern void jbd2_journal_abort (journal_t *, int);
+extern int jbd2_journal_errno (journal_t *);
+extern void jbd2_journal_ack_err (journal_t *);
+extern int jbd2_journal_clear_err (journal_t *);
+extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
+extern int jbd2_journal_force_commit(journal_t *);
+
+/*
+ * journal_head management
+ */
+struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh);
+struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh);
+void jbd2_journal_remove_journal_head(struct buffer_head *bh);
+void jbd2_journal_put_journal_head(struct journal_head *jh);
+
+/*
+ * handle management
+ */
+extern kmem_cache_t *jbd2_handle_cache;
+
+static inline handle_t *jbd_alloc_handle(gfp_t gfp_flags)
+{
+ return kmem_cache_alloc(jbd2_handle_cache, gfp_flags);
+}
+
+static inline void jbd_free_handle(handle_t *handle)
+{
+ kmem_cache_free(jbd2_handle_cache, handle);
+}
+
+/* Primary revoke support */
+#define JOURNAL_REVOKE_DEFAULT_HASH 256
+extern int jbd2_journal_init_revoke(journal_t *, int);
+extern void jbd2_journal_destroy_revoke_caches(void);
+extern int jbd2_journal_init_revoke_caches(void);
+
+extern void jbd2_journal_destroy_revoke(journal_t *);
+extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *);
+extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *);
+extern void jbd2_journal_write_revoke_records(journal_t *, transaction_t *);
+
+/* Recovery revoke support */
+extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t);
+extern int jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t);
+extern void jbd2_journal_clear_revoke(journal_t *);
+extern void jbd2_journal_switch_revoke_table(journal_t *journal);
+
+/*
+ * The log thread user interface:
+ *
+ * Request space in the current transaction, and force transaction commit
+ * transitions on demand.
+ */
+
+int __jbd2_log_space_left(journal_t *); /* Called with journal locked */
+int jbd2_log_start_commit(journal_t *journal, tid_t tid);
+int __jbd2_log_start_commit(journal_t *journal, tid_t tid);
+int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
+int jbd2_journal_force_commit_nested(journal_t *journal);
+int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
+int jbd2_log_do_checkpoint(journal_t *journal);
+
+void __jbd2_log_wait_for_space(journal_t *journal);
+extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
+extern int jbd2_cleanup_journal_tail(journal_t *);
+
+/* Debugging code only: */
+
+#define jbd_ENOSYS() \
+do { \
+ printk (KERN_ERR "JBD unimplemented function %s\n", __FUNCTION__); \
+ current->state = TASK_UNINTERRUPTIBLE; \
+ schedule(); \
+} while (1)
+
+/*
+ * is_journal_abort
+ *
+ * Simple test wrapper function to test the JBD2_ABORT state flag. This
+ * bit, when set, indicates that we have had a fatal error somewhere,
+ * either inside the journaling layer or indicated to us by the client
+ * (eg. ext3), and that we and should not commit any further
+ * transactions.
+ */
+
+static inline int is_journal_aborted(journal_t *journal)
+{
+ return journal->j_flags & JBD2_ABORT;
+}
+
+static inline int is_handle_aborted(handle_t *handle)
+{
+ if (handle->h_aborted)
+ return 1;
+ return is_journal_aborted(handle->h_transaction->t_journal);
+}
+
+static inline void jbd2_journal_abort_handle(handle_t *handle)
+{
+ handle->h_aborted = 1;
+}
+
+#endif /* __KERNEL__ */
+
+/* Comparison functions for transaction IDs: perform comparisons using
+ * modulo arithmetic so that they work over sequence number wraps. */
+
+static inline int tid_gt(tid_t x, tid_t y)
+{
+ int difference = (x - y);
+ return (difference > 0);
+}
+
+static inline int tid_geq(tid_t x, tid_t y)
+{
+ int difference = (x - y);
+ return (difference >= 0);
+}
+
+extern int jbd2_journal_blocks_per_page(struct inode *inode);
+extern size_t journal_tag_bytes(journal_t *journal);
+
+/*
+ * Return the minimum number of blocks which must be free in the journal
+ * before a new transaction may be started. Must be called under j_state_lock.
+ */
+static inline int jbd_space_needed(journal_t *journal)
+{
+ int nblocks = journal->j_max_transaction_buffers;
+ if (journal->j_committing_transaction)
+ nblocks += journal->j_committing_transaction->
+ t_outstanding_credits;
+ return nblocks;
+}
+
+/*
+ * Definitions which augment the buffer_head layer
+ */
+
+/* journaling buffer types */
+#define BJ_None 0 /* Not journaled */
+#define BJ_SyncData 1 /* Normal data: flush before commit */
+#define BJ_Metadata 2 /* Normal journaled metadata */
+#define BJ_Forget 3 /* Buffer superseded by this transaction */
+#define BJ_IO 4 /* Buffer is for temporary IO use */
+#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */
+#define BJ_LogCtl 6 /* Buffer contains log descriptors */
+#define BJ_Reserved 7 /* Buffer is reserved for access by journal */
+#define BJ_Locked 8 /* Locked for I/O during commit */
+#define BJ_Types 9
+
+extern int jbd_blocks_per_page(struct inode *inode);
+
+#ifdef __KERNEL__
+
+#define buffer_trace_init(bh) do {} while (0)
+#define print_buffer_fields(bh) do {} while (0)
+#define print_buffer_trace(bh) do {} while (0)
+#define BUFFER_TRACE(bh, info) do {} while (0)
+#define BUFFER_TRACE2(bh, bh2, info) do {} while (0)
+#define JBUFFER_TRACE(jh, info) do {} while (0)
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_JBD_H */
#define LINUX_LOCKD_BIND_H
#include <linux/lockd/nlm.h>
+/* need xdr-encoded error codes too, so... */
+#include <linux/lockd/xdr.h>
+#ifdef CONFIG_LOCKD_V4
+#include <linux/lockd/xdr4.h>
+#endif
/* Dummy declarations */
struct svc_rqst;
#include <linux/nfs.h>
#include <linux/sunrpc/xdr.h>
+struct svc_rqst;
+
#define NLM_MAXCOOKIELEN 32
#define NLM_MAXSTRLEN 1024
#define nlm_lck_blocked __constant_htonl(NLM_LCK_BLOCKED)
#define nlm_lck_denied_grace_period __constant_htonl(NLM_LCK_DENIED_GRACE_PERIOD)
+#define nlm_drop_reply __constant_htonl(30000)
+
/* Lock info passed via NLM */
struct nlm_lock {
char * caller;
#define EFS_SUPER_MAGIC 0x414A53
#define EXT2_SUPER_MAGIC 0xEF53
#define EXT3_SUPER_MAGIC 0xEF53
+#define EXT4_SUPER_MAGIC 0xEF53
#define HPFS_SUPER_MAGIC 0xf995e849
#define ISOFS_SUPER_MAGIC 0x9660
#define JFFS2_SUPER_MAGIC 0x72b6
#ifndef CONFIG_DEBUG_PAGEALLOC
static inline void
-kernel_map_pages(struct page *page, int numpages, int enable)
-{
- if (!PageHighMem(page) && !enable)
- debug_check_no_locks_freed(page_address(page),
- numpages * PAGE_SIZE);
-}
+kernel_map_pages(struct page *page, int numpages, int enable) {}
#endif
extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk);
/* Am I unsafe to unload? */
int unsafe;
- /* Am I GPL-compatible */
- int license_gplok;
-
unsigned int taints; /* same bits as kernel:tainted */
#ifdef CONFIG_MODULE_UNLOAD
#ifndef LINUX_NBD_H
#define LINUX_NBD_H
+#include <linux/types.h>
+
#define NBD_SET_SOCK _IO( 0xab, 0 )
#define NBD_SET_BLKSIZE _IO( 0xab, 1 )
#define NBD_SET_SIZE _IO( 0xab, 2 )
#define _LINUX_NET_H
#include <linux/wait.h>
+#include <linux/random.h>
#include <asm/socket.h>
struct poll_table_struct;
extern struct socket *sockfd_lookup(int fd, int *err);
#define sockfd_put(sock) fput(sock->file)
extern int net_ratelimit(void);
-extern unsigned long net_random(void);
-extern void net_srandom(unsigned long);
-extern void net_random_init(void);
+
+#define net_random() random32()
+#define net_srandom(seed) srandom32(seed)
extern int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
struct kvec *vec, size_t num, size_t len);
* See detailed comments in the file linux/bitmap.h describing the
* data type on which these nodemasks are based.
*
- * For details of nodemask_scnprintf() and nodemask_parse(),
- * see bitmap_scnprintf() and bitmap_parse() in lib/bitmap.c.
+ * For details of nodemask_scnprintf() and nodemask_parse_user(),
+ * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c.
* For details of nodelist_scnprintf() and nodelist_parse(), see
* bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c.
* For details of node_remap(), see bitmap_bitremap in lib/bitmap.c.
* unsigned long *nodes_addr(mask) Array of unsigned long's in mask
*
* int nodemask_scnprintf(buf, len, mask) Format nodemask for printing
- * int nodemask_parse(ubuf, ulen, mask) Parse ascii string as nodemask
+ * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask
* int nodelist_scnprintf(buf, len, mask) Format nodemask as list for printing
* int nodelist_parse(buf, map) Parse ascii string as nodelist
* int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit)
return bitmap_scnprintf(buf, len, srcp->bits, nbits);
}
-#define nodemask_parse(ubuf, ulen, dst) \
- __nodemask_parse((ubuf), (ulen), &(dst), MAX_NUMNODES)
-static inline int __nodemask_parse(const char __user *buf, int len,
+#define nodemask_parse_user(ubuf, ulen, dst) \
+ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES)
+static inline int __nodemask_parse_user(const char __user *buf, int len,
nodemask_t *dstp, int nbits)
{
- return bitmap_parse(buf, len, dstp->bits, nbits);
+ return bitmap_parse_user(buf, len, dstp->bits, nbits);
}
#define nodelist_scnprintf(buf, len, src) \
unsigned int get_random_int(void);
unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len);
+u32 random32(void);
+void srandom32(u32 seed);
+
#endif /* __KERNEL___ */
#endif /* _LINUX_RANDOM_H */
* Check permission when a flow selects a xfrm_policy for processing
* XFRMs on a packet. The hook is called when selecting either a
* per-socket policy or a generic xfrm policy.
- * Return 0 if permission is granted.
+ * Return 0 if permission is granted, -ESRCH otherwise, or -errno
+ * on other errors.
* @xfrm_state_pol_flow_match:
* @x contains the state to match.
* @xp contains the policy to check for a match.
* @xfrm_flow_state_match:
* @fl contains the flow key to match.
* @xfrm points to the xfrm_state to match.
+ * @xp points to the xfrm_policy to match.
* Return 1 if there is a match.
* @xfrm_decode_session:
* @skb points to skb to decode.
int (*xfrm_policy_lookup)(struct xfrm_policy *xp, u32 fl_secid, u8 dir);
int (*xfrm_state_pol_flow_match)(struct xfrm_state *x,
struct xfrm_policy *xp, struct flowi *fl);
- int (*xfrm_flow_state_match)(struct flowi *fl, struct xfrm_state *xfrm);
+ int (*xfrm_flow_state_match)(struct flowi *fl, struct xfrm_state *xfrm,
+ struct xfrm_policy *xp);
int (*xfrm_decode_session)(struct sk_buff *skb, u32 *secid, int ckall);
#endif /* CONFIG_SECURITY_NETWORK_XFRM */
return security_ops->xfrm_policy_alloc_security(xp, sec_ctx, NULL);
}
-static inline int security_xfrm_sock_policy_alloc(struct xfrm_policy *xp, struct sock *sk)
-{
- return security_ops->xfrm_policy_alloc_security(xp, NULL, sk);
-}
-
static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new)
{
return security_ops->xfrm_policy_clone_security(old, new);
return security_ops->xfrm_state_pol_flow_match(x, xp, fl);
}
-static inline int security_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm)
+static inline int security_xfrm_flow_state_match(struct flowi *fl,
+ struct xfrm_state *xfrm, struct xfrm_policy *xp)
{
- return security_ops->xfrm_flow_state_match(fl, xfrm);
+ return security_ops->xfrm_flow_state_match(fl, xfrm, xp);
}
static inline int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid)
return 0;
}
-static inline int security_xfrm_sock_policy_alloc(struct xfrm_policy *xp, struct sock *sk)
-{
- return 0;
-}
-
static inline int security_xfrm_policy_clone(struct xfrm_policy *old, struct xfrm_policy *new)
{
return 0;
}
static inline int security_xfrm_flow_state_match(struct flowi *fl,
- struct xfrm_state *xfrm)
+ struct xfrm_state *xfrm, struct xfrm_policy *xp)
{
return 1;
}
RPC_PROG_MISMATCH = 2,
RPC_PROC_UNAVAIL = 3,
RPC_GARBAGE_ARGS = 4,
- RPC_SYSTEM_ERR = 5
+ RPC_SYSTEM_ERR = 5,
+ /* internal use only */
+ RPC_DROP_REPLY = 60000,
};
enum rpc_reject_stat {
#define rpc_proc_unavail __constant_htonl(RPC_PROC_UNAVAIL)
#define rpc_garbage_args __constant_htonl(RPC_GARBAGE_ARGS)
#define rpc_system_err __constant_htonl(RPC_SYSTEM_ERR)
+#define rpc_drop_reply __constant_htonl(RPC_DROP_REPLY)
#define rpc_auth_ok __constant_htonl(RPC_AUTH_OK)
#define rpc_autherr_badcred __constant_htonl(RPC_AUTH_BADCRED)
struct epoll_event __user *event);
asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events,
int maxevents, int timeout);
+asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
+ int maxevents, int timeout,
+ const sigset_t __user *sigmask,
+ size_t sigsetsize);
asmlinkage long sys_gethostname(char __user *name, int len);
asmlinkage long sys_sethostname(char __user *name, int len);
asmlinkage long sys_setdomainname(char __user *name, int len);
#define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y','U','1','2') /* 12 YUV 4:2:0 */
#define V4L2_PIX_FMT_YYUV v4l2_fourcc('Y','Y','U','V') /* 16 YUV 4:2:2 */
#define V4L2_PIX_FMT_HI240 v4l2_fourcc('H','I','2','4') /* 8 8-bit color */
-#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H','M','1','2') /* 8 YUV 4:1:1 16x16 macroblocks */
+#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H','M','1','2') /* 8 YUV 4:2:0 16x16 macroblocks */
/* see http://www.siliconimaging.com/RGB%20Bayer.htm */
#define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B','A','8','1') /* 8 BGBG.. GRGR.. */
__u8 mode;
__u8 type;
__u8 out;
+ __u8 attempt;
__u8 dev_class[3];
__u8 features[8];
__u16 interval;
return NULL;
}
+static inline struct hci_conn *hci_conn_hash_lookup_state(struct hci_dev *hdev,
+ __u8 type, __u16 state)
+{
+ struct hci_conn_hash *h = &hdev->conn_hash;
+ struct list_head *p;
+ struct hci_conn *c;
+
+ list_for_each(p, &h->list) {
+ c = list_entry(p, struct hci_conn, list);
+ if (c->type == type && c->state == state)
+ return c;
+ }
+ return NULL;
+}
+
+void hci_acl_connect(struct hci_conn *conn);
void hci_acl_disconn(struct hci_conn *conn, __u8 reason);
void hci_add_sco(struct hci_conn *conn, __u16 handle);
#define FLOW_DIR_FWD 2
struct sock;
-typedef void (*flow_resolve_t)(struct flowi *key, u16 family, u8 dir,
+typedef int (*flow_resolve_t)(struct flowi *key, u16 family, u8 dir,
void **objp, atomic_t **obj_refp);
extern void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir,
{
if (atomic_dec_and_test(&tw->tw_refcnt)) {
struct module *owner = tw->tw_prot->owner;
+ twsk_destructor((struct sock *)tw);
#ifdef SOCK_REFCNT_DEBUG
printk(KERN_DEBUG "%s timewait_sock %p released\n",
tw->tw_prot->name, tw);
{
struct inet_peer *avl_left, *avl_right;
struct inet_peer *unused_next, **unused_prevp;
- unsigned long dtime; /* the time of last use of not
+ __u32 dtime; /* the time of last use of not
* referenced entries */
atomic_t refcnt;
__be32 v4daddr; /* peer's address */
/* can be called with or without local BH being disabled */
struct inet_peer *inet_getpeer(__be32 daddr, int create);
-extern spinlock_t inet_peer_unused_lock;
-extern struct inet_peer **inet_peer_unused_tailp;
/* can be called from BH context or outside */
-static inline void inet_putpeer(struct inet_peer *p)
-{
- spin_lock_bh(&inet_peer_unused_lock);
- if (atomic_dec_and_test(&p->refcnt)) {
- p->unused_prevp = inet_peer_unused_tailp;
- p->unused_next = NULL;
- *inet_peer_unused_tailp = p;
- inet_peer_unused_tailp = &p->unused_next;
- p->dtime = jiffies;
- }
- spin_unlock_bh(&inet_peer_unused_lock);
-}
+extern void inet_putpeer(struct inet_peer *p);
extern spinlock_t inet_peer_idlock;
/* can be called with or without local BH being disabled */
#include <linux/net.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
+#include <asm/atomic.h>
/*
* NetLabel - A management interface for maintaining network packet label
/* LSM security attributes */
struct netlbl_lsm_cache {
+ atomic_t refcount;
void (*free) (const void *data);
void *data;
};
unsigned char *mls_cat;
size_t mls_cat_len;
- struct netlbl_lsm_cache cache;
+ struct netlbl_lsm_cache *cache;
};
/*
*/
+/**
+ * netlbl_secattr_cache_alloc - Allocate and initialize a secattr cache
+ * @flags: the memory allocation flags
+ *
+ * Description:
+ * Allocate and initialize a netlbl_lsm_cache structure. Returns a pointer
+ * on success, NULL on failure.
+ *
+ */
+static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc(gfp_t flags)
+{
+ struct netlbl_lsm_cache *cache;
+
+ cache = kzalloc(sizeof(*cache), flags);
+ if (cache)
+ atomic_set(&cache->refcount, 1);
+ return cache;
+}
+
+/**
+ * netlbl_secattr_cache_free - Frees a netlbl_lsm_cache struct
+ * @cache: the struct to free
+ *
+ * Description:
+ * Frees @secattr including all of the internal buffers.
+ *
+ */
+static inline void netlbl_secattr_cache_free(struct netlbl_lsm_cache *cache)
+{
+ if (!atomic_dec_and_test(&cache->refcount))
+ return;
+
+ if (cache->free)
+ cache->free(cache->data);
+ kfree(cache);
+}
+
/**
* netlbl_secattr_init - Initialize a netlbl_lsm_secattr struct
* @secattr: the struct to initialize
/**
* netlbl_secattr_destroy - Clears a netlbl_lsm_secattr struct
* @secattr: the struct to clear
- * @clear_cache: cache clear flag
*
* Description:
* Destroys the @secattr struct, including freeing all of the internal buffers.
- * If @clear_cache is true then free the cache fields, otherwise leave them
- * intact. The struct must be reset with a call to netlbl_secattr_init()
- * before reuse.
+ * The struct must be reset with a call to netlbl_secattr_init() before reuse.
*
*/
-static inline void netlbl_secattr_destroy(struct netlbl_lsm_secattr *secattr,
- u32 clear_cache)
+static inline void netlbl_secattr_destroy(struct netlbl_lsm_secattr *secattr)
{
- if (clear_cache && secattr->cache.data != NULL && secattr->cache.free)
- secattr->cache.free(secattr->cache.data);
+ if (secattr->cache)
+ netlbl_secattr_cache_free(secattr->cache);
kfree(secattr->domain);
kfree(secattr->mls_cat);
}
/**
* netlbl_secattr_free - Frees a netlbl_lsm_secattr struct
* @secattr: the struct to free
- * @clear_cache: cache clear flag
*
* Description:
- * Frees @secattr including all of the internal buffers. If @clear_cache is
- * true then free the cache fields, otherwise leave them intact.
+ * Frees @secattr including all of the internal buffers.
*
*/
-static inline void netlbl_secattr_free(struct netlbl_lsm_secattr *secattr,
- u32 clear_cache)
+static inline void netlbl_secattr_free(struct netlbl_lsm_secattr *secattr)
{
- netlbl_secattr_destroy(secattr, clear_cache);
+ netlbl_secattr_destroy(secattr);
kfree(secattr);
}
void sctp_write_space(struct sock *sk);
unsigned int sctp_poll(struct file *file, struct socket *sock,
poll_table *wait);
+void sctp_sock_rfree(struct sk_buff *skb);
/*
* sctp/primitive.c
return result;
}
+/* SCTP version of skb_set_owner_r. We need this one because
+ * of the way we have to do receive buffer accounting on bundled
+ * chunks.
+ */
+static inline void sctp_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
+{
+ struct sctp_ulpevent *event = sctp_skb2event(skb);
+
+ skb->sk = sk;
+ skb->destructor = sctp_sock_rfree;
+ atomic_add(event->rmem_len, &sk->sk_rmem_alloc);
+}
+
/* Tests if the list has one and only one entry. */
static inline int sctp_list_single_entry(struct list_head *head)
{
__u32 cumtsn;
int msg_flags;
int iif;
+ unsigned int rmem_len;
};
/* Retrieve the skb this event sits inside of. */
unsigned int twsk_obj_size;
int (*twsk_unique)(struct sock *sk,
struct sock *sktw, void *twp);
+ void (*twsk_destructor)(struct sock *sk);
};
static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
return 0;
}
+static inline void twsk_destructor(struct sock *sk)
+{
+ if (sk->sk_prot->twsk_prot->twsk_destructor != NULL)
+ sk->sk_prot->twsk_prot->twsk_destructor(sk);
+}
+
#endif /* _TIMEWAIT_SOCK_H */
int create, unsigned short family);
extern void xfrm_policy_flush(u8 type);
extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol);
-extern int xfrm_bundle_ok(struct xfrm_dst *xdst, struct flowi *fl, int family, int strict);
+extern int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *xdst,
+ struct flowi *fl, int family, int strict);
extern void xfrm_init_pmtu(struct dst_entry *dst);
extern wait_queue_head_t km_waitq;
static DEFINE_MUTEX(cpu_add_remove_lock);
static DEFINE_MUTEX(cpu_bitmask_lock);
-static __cpuinitdata BLOCKING_NOTIFIER_HEAD(cpu_chain);
+static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);
/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
* Should always be manipulated under cpu_add_remove_lock
/* Need to know about CPUs going up/down? */
int __cpuinit register_cpu_notifier(struct notifier_block *nb)
{
- return blocking_notifier_chain_register(&cpu_chain, nb);
+ int ret;
+ mutex_lock(&cpu_add_remove_lock);
+ ret = raw_notifier_chain_register(&cpu_chain, nb);
+ mutex_unlock(&cpu_add_remove_lock);
+ return ret;
}
#ifdef CONFIG_HOTPLUG_CPU
void unregister_cpu_notifier(struct notifier_block *nb)
{
- blocking_notifier_chain_unregister(&cpu_chain, nb);
+ mutex_lock(&cpu_add_remove_lock);
+ raw_notifier_chain_unregister(&cpu_chain, nb);
+ mutex_unlock(&cpu_add_remove_lock);
}
EXPORT_SYMBOL(unregister_cpu_notifier);
if (!cpu_online(cpu))
return -EINVAL;
- err = blocking_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE,
+ err = raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE,
(void *)(long)cpu);
if (err == NOTIFY_BAD) {
printk("%s: attempt to take down CPU %u failed\n",
if (IS_ERR(p)) {
/* CPU didn't die: tell everyone. Can't complain. */
- if (blocking_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED,
+ if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED,
(void *)(long)cpu) == NOTIFY_BAD)
BUG();
put_cpu();
/* CPU is completely dead: tell everyone. Too late to complain. */
- if (blocking_notifier_call_chain(&cpu_chain, CPU_DEAD,
+ if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD,
(void *)(long)cpu) == NOTIFY_BAD)
BUG();
if (cpu_online(cpu) || !cpu_present(cpu))
return -EINVAL;
- ret = blocking_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu);
+ ret = raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu);
if (ret == NOTIFY_BAD) {
printk("%s: attempt to bring up CPU %u failed\n",
__FUNCTION__, cpu);
BUG_ON(!cpu_online(cpu));
/* Now call notifier in preparation. */
- blocking_notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu);
+ raw_notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu);
out_notify:
if (ret != 0)
- blocking_notifier_call_chain(&cpu_chain,
+ raw_notifier_call_chain(&cpu_chain,
CPU_UP_CANCELED, hcpu);
return ret;
if (!p)
goto fork_out;
+ rt_mutex_init_task(p);
+
#ifdef CONFIG_TRACE_IRQFLAGS
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
p->lockdep_recursion = 0;
#endif
- rt_mutex_init_task(p);
-
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
#endif /* CONFIG_SMP */
void
-__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained)
+__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
+ const char *name)
{
struct irq_desc *desc;
unsigned long flags;
desc->depth = 1;
}
desc->handle_irq = handle;
+ desc->name = name;
if (handle != handle_bad_irq && is_chained) {
desc->status &= ~IRQ_DISABLED;
irq_flow_handler_t handle)
{
set_irq_chip(irq, chip);
- __set_irq_handler(irq, handle, 0);
+ __set_irq_handler(irq, handle, 0, NULL);
}
-/*
- * Get a descriptive string for the highlevel handler, for
- * /proc/interrupts output:
- */
-const char *
-handle_irq_name(irq_flow_handler_t handle)
+void
+set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
+ irq_flow_handler_t handle, const char *name)
{
- if (handle == handle_level_irq)
- return "level ";
- if (handle == handle_fasteoi_irq)
- return "fasteoi";
- if (handle == handle_edge_irq)
- return "edge ";
- if (handle == handle_simple_irq)
- return "simple ";
-#ifdef CONFIG_SMP
- if (handle == handle_percpu_irq)
- return "percpu ";
-#endif
- if (handle == handle_bad_irq)
- return "bad ";
-
- return NULL;
+ set_irq_chip(irq, chip);
+ __set_irq_handler(irq, handle, 0, name);
}
if (!irq_desc[irq].chip->set_affinity || no_irq_affinity)
return -EIO;
- err = cpumask_parse(buffer, count, new_value);
+ err = cpumask_parse_user(buffer, count, new_value);
if (err)
return err;
return 0;
}
+#define RECURSION_LIMIT 40
+
static int noinline print_infinite_recursion_bug(void)
{
__raw_spin_unlock(&hash_lock);
debug_atomic_inc(&nr_cyclic_check_recursions);
if (depth > max_recursion_depth)
max_recursion_depth = depth;
- if (depth >= 20)
+ if (depth >= RECURSION_LIMIT)
return print_infinite_recursion_bug();
/*
* Check this lock's dependency list:
if (depth > max_recursion_depth)
max_recursion_depth = depth;
- if (depth >= 20)
+ if (depth >= RECURSION_LIMIT)
return print_infinite_recursion_bug();
debug_atomic_inc(&nr_find_usage_forwards_checks);
if (depth > max_recursion_depth)
max_recursion_depth = depth;
- if (depth >= 20)
+ if (depth >= RECURSION_LIMIT)
return print_infinite_recursion_bug();
debug_atomic_inc(&nr_find_usage_backwards_checks);
return count + 1;
}
-extern void __error_too_big_MAX_LOCKDEP_SUBCLASSES(void);
-
/*
* Register a lock's class in the hash-table, if the class is not present
* yet. Otherwise we look it up. We cache the result in the lock object
* (or spin_lock_init()) call - which acts as the key. For static
* locks we use the lock object itself as the key.
*/
- if (sizeof(struct lock_class_key) > sizeof(struct lock_class))
- __error_too_big_MAX_LOCKDEP_SUBCLASSES();
+ BUILD_BUG_ON(sizeof(struct lock_class_key) > sizeof(struct lock_class));
key = lock->key->subkeys + subclass;
return try_module_get(mod);
}
+static inline void add_taint_module(struct module *mod, unsigned flag)
+{
+ add_taint(flag);
+ mod->taints |= flag;
+}
+
/* A thread that wants to hold a reference to a module only while it
* is running can call ths to safely exit.
* nfsd and lockd use this.
return 0;
}
/* Not in module's version table. OK, but that taints the kernel. */
- if (!(tainted & TAINT_FORCED_MODULE)) {
+ if (!(tainted & TAINT_FORCED_MODULE))
printk("%s: no version for \"%s\" found: kernel tainted.\n",
mod->name, symname);
- add_taint(TAINT_FORCED_MODULE);
- mod->taints |= TAINT_FORCED_MODULE;
- }
+ add_taint_module(mod, TAINT_FORCED_MODULE);
return 1;
}
unsigned long ret;
const unsigned long *crc;
- ret = __find_symbol(name, &owner, &crc, mod->license_gplok);
+ ret = __find_symbol(name, &owner, &crc,
+ !(mod->taints & TAINT_PROPRIETARY_MODULE));
if (ret) {
/* use_module can fail due to OOM, or module unloading */
if (!check_version(sechdrs, versindex, name, mod, crc) ||
if (!license)
license = "unspecified";
- mod->license_gplok = license_is_gpl_compatible(license);
- if (!mod->license_gplok && !(tainted & TAINT_PROPRIETARY_MODULE)) {
- printk(KERN_WARNING "%s: module license '%s' taints kernel.\n",
- mod->name, license);
- add_taint(TAINT_PROPRIETARY_MODULE);
- mod->taints |= TAINT_PROPRIETARY_MODULE;
+ if (!license_is_gpl_compatible(license)) {
+ if (!(tainted & TAINT_PROPRIETARY_MODULE))
+ printk(KERN_WARNING "%s: module license '%s' taints"
+ "kernel.\n", mod->name, license);
+ add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
}
}
modmagic = get_modinfo(sechdrs, infoindex, "vermagic");
/* This is allowed: modprobe --force will invalidate it. */
if (!modmagic) {
- add_taint(TAINT_FORCED_MODULE);
- mod->taints |= TAINT_FORCED_MODULE;
+ add_taint_module(mod, TAINT_FORCED_MODULE);
printk(KERN_WARNING "%s: no version magic, tainting kernel.\n",
mod->name);
} else if (!same_magic(modmagic, vermagic)) {
/* Set up license info based on the info section */
set_license(mod, get_modinfo(sechdrs, infoindex, "license"));
- if (strcmp(mod->name, "ndiswrapper") == 0) {
- add_taint(TAINT_PROPRIETARY_MODULE);
- mod->taints |= TAINT_PROPRIETARY_MODULE;
- }
- if (strcmp(mod->name, "driverloader") == 0) {
- add_taint(TAINT_PROPRIETARY_MODULE);
- mod->taints |= TAINT_PROPRIETARY_MODULE;
- }
+ if (strcmp(mod->name, "ndiswrapper") == 0)
+ add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
+ if (strcmp(mod->name, "driverloader") == 0)
+ add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
/* Set up MODINFO_ATTR fields */
setup_modinfo(mod, sechdrs, infoindex);
(mod->num_unused_gpl_syms && !unusedgplcrcindex)) {
printk(KERN_WARNING "%s: No versions for exported symbols."
" Tainting kernel.\n", mod->name);
- add_taint(TAINT_FORCED_MODULE);
- mod->taints |= TAINT_FORCED_MODULE;
+ add_taint_module(mod, TAINT_FORCED_MODULE);
}
#endif
mutex_unlock(&module_mutex);
}
+static char *taint_flags(unsigned int taints, char *buf)
+{
+ int bx = 0;
+
+ if (taints) {
+ buf[bx++] = '(';
+ if (taints & TAINT_PROPRIETARY_MODULE)
+ buf[bx++] = 'P';
+ if (taints & TAINT_FORCED_MODULE)
+ buf[bx++] = 'F';
+ /*
+ * TAINT_FORCED_RMMOD: could be added.
+ * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
+ * apply to modules.
+ */
+ buf[bx++] = ')';
+ }
+ buf[bx] = '\0';
+
+ return buf;
+}
+
static int m_show(struct seq_file *m, void *p)
{
struct module *mod = list_entry(p, struct module, list);
+ char buf[8];
+
seq_printf(m, "%s %lu",
mod->name, mod->init_size + mod->core_size);
print_unload_info(m, mod);
/* Used by oprofile and other similar tools. */
seq_printf(m, " 0x%p", mod->module_core);
+ /* Taints info */
+ if (mod->taints)
+ seq_printf(m, " %s", taint_flags(mod->taints, buf));
+
seq_printf(m, "\n");
return 0;
}
return mod;
}
-static char *taint_flags(unsigned int taints, char *buf)
-{
- *buf = '\0';
- if (taints) {
- int bx;
-
- buf[0] = '(';
- bx = 1;
- if (taints & TAINT_PROPRIETARY_MODULE)
- buf[bx++] = 'P';
- if (taints & TAINT_FORCED_MODULE)
- buf[bx++] = 'F';
- /*
- * TAINT_FORCED_RMMOD: could be added.
- * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
- * apply to modules.
- */
- buf[bx] = ')';
- }
- return buf;
-}
-
/* Don't grab lock, we're oopsing. */
void print_modules(void)
{
return a;
}
+/*
+ * Divide and limit the result to res >= 1
+ *
+ * This is necessary to prevent signal delivery starvation, when the result of
+ * the division would be rounded down to 0.
+ */
+static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div)
+{
+ cputime_t res = cputime_div(time, div);
+
+ return max_t(cputime_t, res, 1);
+}
+
/*
* Update expiry time from increment, and increase overrun count,
* given the current clock sample.
BUG();
break;
case CPUCLOCK_PROF:
- left = cputime_div(cputime_sub(expires.cpu, val.cpu),
- nthreads);
+ left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
+ nthreads);
do {
if (likely(!(t->flags & PF_EXITING))) {
ticks = cputime_add(prof_ticks(t), left);
} while (t != p);
break;
case CPUCLOCK_VIRT:
- left = cputime_div(cputime_sub(expires.cpu, val.cpu),
- nthreads);
+ left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
+ nthreads);
do {
if (likely(!(t->flags & PF_EXITING))) {
ticks = cputime_add(virt_ticks(t), left);
case CPUCLOCK_SCHED:
nsleft = expires.sched - val.sched;
do_div(nsleft, nthreads);
+ nsleft = max_t(unsigned long long, nsleft, 1);
do {
if (likely(!(t->flags & PF_EXITING))) {
ns = t->sched_time + nsleft;
prof_left = cputime_sub(prof_expires, utime);
prof_left = cputime_sub(prof_left, stime);
- prof_left = cputime_div(prof_left, nthreads);
+ prof_left = cputime_div_non_zero(prof_left, nthreads);
virt_left = cputime_sub(virt_expires, utime);
- virt_left = cputime_div(virt_left, nthreads);
+ virt_left = cputime_div_non_zero(virt_left, nthreads);
if (sched_expires) {
sched_left = sched_expires - sched_time;
do_div(sched_left, nthreads);
+ sched_left = max_t(unsigned long long, sched_left, 1);
} else {
sched_left = 0;
}
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/pm.h>
+#include <linux/console.h>
#include <linux/cpu.h>
#include "power.h"
if (error)
return error;
+ suspend_console();
error = device_suspend(PMSG_FREEZE);
if (error) {
+ resume_console();
printk("Some devices failed to suspend\n");
unprepare_processes();
return error;
if (in_suspend) {
device_resume();
+ resume_console();
pr_debug("PM: writing image.\n");
error = swsusp_write();
if (!error)
swsusp_free();
Done:
device_resume();
+ resume_console();
unprepare_processes();
return error;
}
pr_debug("PM: Preparing devices for restore.\n");
+ suspend_console();
if ((error = device_suspend(PMSG_PRETHAW))) {
+ resume_console();
printk("Some devices failed to suspend\n");
swsusp_free();
goto Thaw;
swsusp_resume();
pr_debug("PM: Restore failed, recovering.n");
device_resume();
+ resume_console();
Thaw:
unprepare_processes();
Done:
bio_set_pages_dirty(bio);
bio_put(bio);
} else {
- get_page(page);
+ if (rw == READ)
+ get_page(page); /* These pages are freed later */
bio->bi_private = *bio_chain;
*bio_chain = bio;
submit_bio(rw | (1 << BIO_RW_SYNC), bio);
#include <linux/swapops.h>
#include <linux/pm.h>
#include <linux/fs.h>
+#include <linux/console.h>
#include <linux/cpu.h>
#include <asm/uaccess.h>
/* Free memory before shutting down devices. */
error = swsusp_shrink_memory();
if (!error) {
+ suspend_console();
error = device_suspend(PMSG_FREEZE);
if (!error) {
in_suspend = 1;
error = swsusp_suspend();
device_resume();
}
+ resume_console();
}
up(&pm_sem);
if (!error)
snapshot_free_unused_memory(&data->handle);
down(&pm_sem);
pm_prepare_console();
+ suspend_console();
error = device_suspend(PMSG_PRETHAW);
if (!error) {
error = swsusp_resume();
device_resume();
}
+ resume_console();
pm_restore_console();
up(&pm_sem);
break;
}
/* Put devices to sleep */
+ suspend_console();
error = device_suspend(PMSG_SUSPEND);
if (error) {
printk(KERN_ERR "Failed to suspend some devices.\n");
/* Wake up devices */
device_resume();
}
-
+ resume_console();
if (pm_ops->finish)
pm_ops->finish(PM_SUSPEND_MEM);
console_locked = 0;
up(&console_sem);
spin_unlock_irqrestore(&logbuf_lock, flags);
- if (wake_klogd && !oops_in_progress && waitqueue_active(&log_wait)) {
- /*
- * If we printk from within the lock dependency code,
- * from within the scheduler code, then do not lock
- * up due to self-recursion:
- */
- if (!lockdep_internal())
- wake_up_interruptible(&log_wait);
- }
+ if (wake_klogd && !oops_in_progress && waitqueue_active(&log_wait))
+ wake_up_interruptible(&log_wait);
}
EXPORT_SYMBOL(release_console_sem);
unsigned long full_count = count, err;
cpumask_t new_value;
- err = cpumask_parse(buffer, count, new_value);
+ err = cpumask_parse_user(buffer, count, new_value);
if (err)
return err;
struct mm_struct *mm = next->mm;
struct mm_struct *oldmm = prev->active_mm;
- if (unlikely(!mm)) {
+ if (!mm) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
switch_mm(oldmm, mm, next);
- if (unlikely(!prev->mm)) {
+ if (!prev->mm) {
prev->active_mm = NULL;
WARN_ON(rq->prev_mm);
rq->prev_mm = oldmm;
* If there is a non-zero preempt_count or interrupts are disabled,
* we do not want to preempt the current task. Just return..
*/
- if (unlikely(ti->preempt_count || irqs_disabled()))
+ if (likely(ti->preempt_count || irqs_disabled()))
return;
need_resched:
cond_syscall(sys_epoll_create);
cond_syscall(sys_epoll_ctl);
cond_syscall(sys_epoll_wait);
+cond_syscall(sys_epoll_pwait);
cond_syscall(sys_semget);
cond_syscall(sys_semop);
cond_syscall(sys_semtimedop);
struct clocksource clocksource_jiffies = {
.name = "jiffies",
- .rating = 0, /* lowest rating*/
+ .rating = 1, /* lowest valid rating*/
.read = jiffies_read,
.mask = 0xffffffff, /*32bits*/
.mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
#include <linux/notifier.h>
#include <linux/kthread.h>
#include <linux/hardirq.h>
+#include <linux/mempolicy.h>
/*
* The per-CPU workqueue (if single thread, we always use the first
sigprocmask(SIG_BLOCK, &blocked, NULL);
flush_signals(current);
+ /*
+ * We inherited MPOL_INTERLEAVE from the booting kernel.
+ * Set MPOL_DEFAULT to insure node local allocations.
+ */
+ numa_default_policy();
+
/* SIG_IGN makes children autoreap: see do_notify_parent(). */
sa.sa.sa_handler = SIG_IGN;
sa.sa.sa_flags = 0;
config DETECT_SOFTLOCKUP
bool "Detect Soft Lockups"
- depends on DEBUG_KERNEL
+ depends on DEBUG_KERNEL && !S390
default y
help
Say Y here to enable the kernel to detect "soft lockups",
become the default in the future, until then this option is there to
test gcc for this.
+config HEADERS_CHECK
+ bool "Run 'make headers_check' when building vmlinux"
+ depends on !UML
+ help
+ This option will extract the user-visible kernel headers whenever
+ building the kernel, and will run basic sanity checks on them to
+ ensure that exported files do not attempt to include files which
+ were not exported, etc.
+
+ If you're making modifications to header files which are
+ relevant for userspace, say 'Y', and check the headers
+ exported to $(INSTALL_HDR_PATH) (usually 'usr/include' in
+ your build tree), to make sure they're suitable.
+
config RCU_TORTURE_TEST
tristate "torture tests for RCU"
depends on DEBUG_KERNEL
lib-y += kobject.o kref.o kobject_uevent.o klist.o
-obj-y += sort.o parser.o halfmd4.o iomap_copy.o debug_locks.o
+obj-y += sort.o parser.o halfmd4.o iomap_copy.o debug_locks.o random32.o
ifeq ($(CONFIG_DEBUG_KOBJECT),y)
CFLAGS_kobject.o += -DDEBUG
EXPORT_SYMBOL(bitmap_scnprintf);
/**
- * bitmap_parse - convert an ASCII hex string into a bitmap.
- * @ubuf: pointer to buffer in user space containing string.
- * @ubuflen: buffer size in bytes. If string is smaller than this
+ * __bitmap_parse - convert an ASCII hex string into a bitmap.
+ * @buf: pointer to buffer containing string.
+ * @buflen: buffer size in bytes. If string is smaller than this
* then it must be terminated with a \0.
+ * @is_user: location of buffer, 0 indicates kernel space
* @maskp: pointer to bitmap array that will contain result.
* @nmaskbits: size of bitmap, in bits.
*
* characters and for grouping errors such as "1,,5", ",44", "," and "".
* Leading and trailing whitespace accepted, but not embedded whitespace.
*/
-int bitmap_parse(const char __user *ubuf, unsigned int ubuflen,
- unsigned long *maskp, int nmaskbits)
+int __bitmap_parse(const char *buf, unsigned int buflen,
+ int is_user, unsigned long *maskp,
+ int nmaskbits)
{
int c, old_c, totaldigits, ndigits, nchunks, nbits;
u32 chunk;
+ const char __user *ubuf = buf;
bitmap_zero(maskp, nmaskbits);
chunk = ndigits = 0;
/* Get the next chunk of the bitmap */
- while (ubuflen) {
+ while (buflen) {
old_c = c;
- if (get_user(c, ubuf++))
- return -EFAULT;
- ubuflen--;
+ if (is_user) {
+ if (__get_user(c, ubuf++))
+ return -EFAULT;
+ }
+ else
+ c = *buf++;
+ buflen--;
if (isspace(c))
continue;
nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ;
if (nbits > nmaskbits)
return -EOVERFLOW;
- } while (ubuflen && c == ',');
+ } while (buflen && c == ',');
return 0;
}
-EXPORT_SYMBOL(bitmap_parse);
+EXPORT_SYMBOL(__bitmap_parse);
+
+/**
+ * bitmap_parse_user()
+ *
+ * @ubuf: pointer to user buffer containing string.
+ * @ulen: buffer size in bytes. If string is smaller than this
+ * then it must be terminated with a \0.
+ * @maskp: pointer to bitmap array that will contain result.
+ * @nmaskbits: size of bitmap, in bits.
+ *
+ * Wrapper for __bitmap_parse(), providing it with user buffer.
+ *
+ * We cannot have this as an inline function in bitmap.h because it needs
+ * linux/uaccess.h to get the access_ok() declaration and this causes
+ * cyclic dependencies.
+ */
+int bitmap_parse_user(const char __user *ubuf,
+ unsigned int ulen, unsigned long *maskp,
+ int nmaskbits)
+{
+ if (!access_ok(VERIFY_READ, ubuf, ulen))
+ return -EFAULT;
+ return __bitmap_parse((const char *)ubuf, ulen, 1, maskp, nmaskbits);
+}
+EXPORT_SYMBOL(bitmap_parse_user);
/*
* bscnl_emit(buf, buflen, rbot, rtop, bp)
--- /dev/null
+/*
+ This is a maximally equidistributed combined Tausworthe generator
+ based on code from GNU Scientific Library 1.5 (30 Jun 2004)
+
+ x_n = (s1_n ^ s2_n ^ s3_n)
+
+ s1_{n+1} = (((s1_n & 4294967294) <<12) ^ (((s1_n <<13) ^ s1_n) >>19))
+ s2_{n+1} = (((s2_n & 4294967288) << 4) ^ (((s2_n << 2) ^ s2_n) >>25))
+ s3_{n+1} = (((s3_n & 4294967280) <<17) ^ (((s3_n << 3) ^ s3_n) >>11))
+
+ The period of this generator is about 2^88.
+
+ From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe
+ Generators", Mathematics of Computation, 65, 213 (1996), 203--213.
+
+ This is available on the net from L'Ecuyer's home page,
+
+ http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps
+ ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps
+
+ There is an erratum in the paper "Tables of Maximally
+ Equidistributed Combined LFSR Generators", Mathematics of
+ Computation, 68, 225 (1999), 261--269:
+ http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps
+
+ ... the k_j most significant bits of z_j must be non-
+ zero, for each j. (Note: this restriction also applies to the
+ computer code given in [4], but was mistakenly not mentioned in
+ that paper.)
+
+ This affects the seeding procedure by imposing the requirement
+ s1 > 1, s2 > 7, s3 > 15.
+
+*/
+
+#include <linux/types.h>
+#include <linux/percpu.h>
+#include <linux/module.h>
+#include <linux/random.h>
+
+struct rnd_state {
+ u32 s1, s2, s3;
+};
+
+static DEFINE_PER_CPU(struct rnd_state, net_rand_state);
+
+static u32 __random32(struct rnd_state *state)
+{
+#define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b)
+
+ state->s1 = TAUSWORTHE(state->s1, 13, 19, 4294967294UL, 12);
+ state->s2 = TAUSWORTHE(state->s2, 2, 25, 4294967288UL, 4);
+ state->s3 = TAUSWORTHE(state->s3, 3, 11, 4294967280UL, 17);
+
+ return (state->s1 ^ state->s2 ^ state->s3);
+}
+
+static void __set_random32(struct rnd_state *state, unsigned long s)
+{
+ if (s == 0)
+ s = 1; /* default seed is 1 */
+
+#define LCG(n) (69069 * n)
+ state->s1 = LCG(s);
+ state->s2 = LCG(state->s1);
+ state->s3 = LCG(state->s2);
+
+ /* "warm it up" */
+ __random32(state);
+ __random32(state);
+ __random32(state);
+ __random32(state);
+ __random32(state);
+ __random32(state);
+}
+
+/**
+ * random32 - pseudo random number generator
+ *
+ * A 32 bit pseudo-random number is generated using a fast
+ * algorithm suitable for simulation. This algorithm is NOT
+ * considered safe for cryptographic use.
+ */
+u32 random32(void)
+{
+ unsigned long r;
+ struct rnd_state *state = &get_cpu_var(net_rand_state);
+ r = __random32(state);
+ put_cpu_var(state);
+ return r;
+}
+EXPORT_SYMBOL(random32);
+
+/**
+ * srandom32 - add entropy to pseudo random number generator
+ * @seed: seed value
+ *
+ * Add some additional seeding to the random32() pool.
+ * Note: this pool is per cpu so it only affects current CPU.
+ */
+void srandom32(u32 entropy)
+{
+ struct rnd_state *state = &get_cpu_var(net_rand_state);
+ __set_random32(state, state->s1 ^ entropy);
+ put_cpu_var(state);
+}
+EXPORT_SYMBOL(srandom32);
+
+/*
+ * Generate some initially weak seeding values to allow
+ * to start the random32() engine.
+ */
+static int __init random32_init(void)
+{
+ int i;
+
+ for_each_possible_cpu(i) {
+ struct rnd_state *state = &per_cpu(net_rand_state,i);
+ __set_random32(state, i + jiffies);
+ }
+ return 0;
+}
+core_initcall(random32_init);
+
+/*
+ * Generate better values after random number generator
+ * is fully initalized.
+ */
+static int __init random32_reseed(void)
+{
+ int i;
+ unsigned long seed;
+
+ for_each_possible_cpu(i) {
+ struct rnd_state *state = &per_cpu(net_rand_state,i);
+
+ get_random_bytes(&seed, sizeof(seed));
+ __set_random32(state, seed);
+ }
+ return 0;
+}
+late_initcall(random32_reseed);
return -ENOMEM;
}
-void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end)
+void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
}
}
+void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
+{
+ /*
+ * It is undesirable to test vma->vm_file as it should be non-null
+ * for valid hugetlb area. However, vm_file will be NULL in the error
+ * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails,
+ * do_mmap_pgoff() nullifies vma->vm_file before calling this function
+ * to clean up. Since no pte has actually been setup, it is safe to
+ * do nothing in this case.
+ */
+ if (vma->vm_file) {
+ spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+ __unmap_hugepage_range(vma, start, end);
+ spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+ }
+}
+
static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *ptep, pte_t pte)
{
return -ENOSYS;
}
-static struct page *new_vma_page(struct page *page, unsigned long private)
+static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
return NULL;
}
int accountable = 1;
unsigned long charged = 0, reqprot = prot;
- if (file) {
- if (is_file_hugepages(file))
- accountable = 0;
-
- if (!file->f_op || !file->f_op->mmap)
- return -ENODEV;
-
- if ((prot & PROT_EXEC) &&
- (file->f_vfsmnt->mnt_flags & MNT_NOEXEC))
- return -EPERM;
- }
/*
* Does the application expect PROT_READ to imply PROT_EXEC?
*
case MAP_PRIVATE:
if (!(file->f_mode & FMODE_READ))
return -EACCES;
+ if (file->f_vfsmnt->mnt_flags & MNT_NOEXEC) {
+ if (vm_flags & VM_EXEC)
+ return -EPERM;
+ vm_flags &= ~VM_MAYEXEC;
+ }
+ if (is_file_hugepages(file))
+ accountable = 0;
+
+ if (!file->f_op || !file->f_op->mmap)
+ return -ENODEV;
break;
default:
int i;
int reserved = 0;
- arch_free_page(page, order);
- if (!PageHighMem(page))
- debug_check_no_locks_freed(page_address(page),
- PAGE_SIZE<<order);
-
for (i = 0 ; i < (1 << order) ; ++i)
reserved += free_pages_check(page + i);
if (reserved)
return;
+ if (!PageHighMem(page))
+ debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
+ arch_free_page(page, order);
kernel_map_pages(page, 1 << order, 0);
+
local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
free_one_page(page_zone(page), page, order);
struct per_cpu_pages *pcp;
unsigned long flags;
- arch_free_page(page, 0);
-
if (PageAnon(page))
page->mapping = NULL;
if (free_pages_check(page))
return;
+ if (!PageHighMem(page))
+ debug_check_no_locks_freed(page_address(page), PAGE_SIZE);
+ arch_free_page(page, 0);
kernel_map_pages(page, 1, 0);
pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
}
-/* Return the zone index a PFN is in */
-int memmap_zone_idx(struct page *lmem_map)
-{
- int i;
- unsigned long phys_addr = virt_to_phys(lmem_map);
- unsigned long pfn = phys_addr >> PAGE_SHIFT;
-
- for (i = 0; i < MAX_NR_ZONES; i++)
- if (pfn < arch_zone_highest_possible_pfn[i])
- break;
-
- return i;
-}
#else
static inline unsigned long zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
return zholes_size[zone_type];
}
-static inline int memmap_zone_idx(struct page *lmem_map)
-{
- return MAX_NR_ZONES;
-}
#endif
static void __init calculate_node_totalpages(struct pglist_data *pgdat,
void page_remove_rmap(struct page *page)
{
if (atomic_add_negative(-1, &page->_mapcount)) {
-#ifdef CONFIG_DEBUG_VM
if (unlikely(page_mapcount(page) < 0)) {
printk (KERN_EMERG "Eeek! page_mapcount(page) went negative! (%d)\n", page_mapcount(page));
printk (KERN_EMERG " page->flags = %lx\n", page->flags);
printk (KERN_EMERG " page->count = %x\n", page_count(page));
printk (KERN_EMERG " page->mapping = %p\n", page->mapping);
+ BUG();
}
-#endif
- BUG_ON(page_mapcount(page) < 0);
+
/*
* It would be tidy to reset the PageAnon mapping here,
* but that might overwrite a racing page_add_anon_rmap
inode->i_mapping->a_ops = &shmem_aops;
inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ inode->i_generation = get_seconds();
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
};
#endif
+static struct dentry *shmem_get_parent(struct dentry *child)
+{
+ return ERR_PTR(-ESTALE);
+}
+
+static int shmem_match(struct inode *ino, void *vfh)
+{
+ __u32 *fh = vfh;
+ __u64 inum = fh[2];
+ inum = (inum << 32) | fh[1];
+ return ino->i_ino == inum && fh[0] == ino->i_generation;
+}
+
+static struct dentry *shmem_get_dentry(struct super_block *sb, void *vfh)
+{
+ struct dentry *de = NULL;
+ struct inode *inode;
+ __u32 *fh = vfh;
+ __u64 inum = fh[2];
+ inum = (inum << 32) | fh[1];
+
+ inode = ilookup5(sb, (unsigned long)(inum+fh[0]), shmem_match, vfh);
+ if (inode) {
+ de = d_find_alias(inode);
+ iput(inode);
+ }
+
+ return de? de: ERR_PTR(-ESTALE);
+}
+
+static struct dentry *shmem_decode_fh(struct super_block *sb, __u32 *fh,
+ int len, int type,
+ int (*acceptable)(void *context, struct dentry *de),
+ void *context)
+{
+ if (len < 3)
+ return ERR_PTR(-ESTALE);
+
+ return sb->s_export_op->find_exported_dentry(sb, fh, NULL, acceptable,
+ context);
+}
+
+static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
+ int connectable)
+{
+ struct inode *inode = dentry->d_inode;
+
+ if (*len < 3)
+ return 255;
+
+ if (hlist_unhashed(&inode->i_hash)) {
+ /* Unfortunately insert_inode_hash is not idempotent,
+ * so as we hash inodes here rather than at creation
+ * time, we need a lock to ensure we only try
+ * to do it once
+ */
+ static DEFINE_SPINLOCK(lock);
+ spin_lock(&lock);
+ if (hlist_unhashed(&inode->i_hash))
+ __insert_inode_hash(inode,
+ inode->i_ino + inode->i_generation);
+ spin_unlock(&lock);
+ }
+
+ fh[0] = inode->i_generation;
+ fh[1] = inode->i_ino;
+ fh[2] = ((__u64)inode->i_ino) >> 32;
+
+ *len = 3;
+ return 1;
+}
+
+static struct export_operations shmem_export_ops = {
+ .get_parent = shmem_get_parent,
+ .get_dentry = shmem_get_dentry,
+ .encode_fh = shmem_encode_fh,
+ .decode_fh = shmem_decode_fh,
+};
+
static int shmem_parse_options(char *options, int *mode, uid_t *uid,
gid_t *gid, unsigned long *blocks, unsigned long *inodes,
int *policy, nodemask_t *policy_nodes)
&inodes, &policy, &policy_nodes))
return -EINVAL;
}
+ sb->s_export_op = &shmem_export_ops;
#else
sb->s_flags |= MS_NOUSER;
#endif
}
/**
- * shmem_get_acl - generic_acl_operations->setacl() operation
+ * shmem_set_acl - generic_acl_operations->setacl() operation
*/
static void
shmem_set_acl(struct inode *inode, int type, struct posix_acl *acl)
return 0;
ret = remove_mapping(mapping, page);
- ClearPageUptodate(page);
return ret;
}
if (page->mapping != mapping)
return 0;
- if (PagePrivate(page) && !try_to_release_page(page, 0))
+ if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
return 0;
write_lock_irq(&mapping->tree_lock);
pagevec_release(&pvec);
cond_resched();
}
+ WARN_ON_ONCE(ret);
return ret;
}
EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
if (array_size > PAGE_SIZE) {
pages = __vmalloc_node(array_size, gfp_mask, PAGE_KERNEL, node);
area->flags |= VM_VPAGES;
- } else
- pages = kmalloc_node(array_size, (gfp_mask & ~__GFP_HIGHMEM), node);
+ } else {
+ pages = kmalloc_node(array_size,
+ (gfp_mask & ~(__GFP_HIGHMEM | __GFP_ZERO)),
+ node);
+ }
area->pages = pages;
if (!area->pages) {
remove_vm_area(area->addr);
return PAGE_CLEAN;
}
+/*
+ * Attempt to detach a locked page from its ->mapping. If it is dirty or if
+ * someone else has a ref on the page, abort and return 0. If it was
+ * successfully detached, return 1. Assumes the caller has a single ref on
+ * this page.
+ */
int remove_mapping(struct address_space *mapping, struct page *page)
{
BUG_ON(!PageLocked(page));
#define BT_DBG(D...)
#endif
-#define VERSION "2.10"
+#define VERSION "2.11"
/* Bluetooth sockets */
#define BT_MAX_PROTO 8
static struct net_proto_family *bt_proto[BT_MAX_PROTO];
+static DEFINE_RWLOCK(bt_proto_lock);
int bt_sock_register(int proto, struct net_proto_family *ops)
{
+ int err = 0;
+
if (proto < 0 || proto >= BT_MAX_PROTO)
return -EINVAL;
+ write_lock(&bt_proto_lock);
+
if (bt_proto[proto])
- return -EEXIST;
+ err = -EEXIST;
+ else
+ bt_proto[proto] = ops;
- bt_proto[proto] = ops;
- return 0;
+ write_unlock(&bt_proto_lock);
+
+ return err;
}
EXPORT_SYMBOL(bt_sock_register);
int bt_sock_unregister(int proto)
{
+ int err = 0;
+
if (proto < 0 || proto >= BT_MAX_PROTO)
return -EINVAL;
+ write_lock(&bt_proto_lock);
+
if (!bt_proto[proto])
- return -ENOENT;
+ err = -ENOENT;
+ else
+ bt_proto[proto] = NULL;
- bt_proto[proto] = NULL;
- return 0;
+ write_unlock(&bt_proto_lock);
+
+ return err;
}
EXPORT_SYMBOL(bt_sock_unregister);
static int bt_sock_create(struct socket *sock, int proto)
{
- int err = 0;
+ int err;
if (proto < 0 || proto >= BT_MAX_PROTO)
return -EINVAL;
request_module("bt-proto-%d", proto);
}
#endif
+
err = -EPROTONOSUPPORT;
+
+ read_lock(&bt_proto_lock);
+
if (bt_proto[proto] && try_module_get(bt_proto[proto]->owner)) {
err = bt_proto[proto]->create(sock, proto);
module_put(bt_proto[proto]->owner);
}
+
+ read_unlock(&bt_proto_lock);
+
return err;
}
return NULL;
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
- if (!conn)
- return NULL;
hci_dev_put(hdev);
- return &conn->dev;
+ return conn ? &conn->dev : NULL;
}
int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock)
#include <linux/ioctl.h>
#include <linux/file.h>
#include <linux/init.h>
+#include <linux/compat.h>
#include <net/sock.h>
#include <asm/system.h>
return 0;
}
+#ifdef CONFIG_COMPAT
+static int bnep_sock_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+ if (cmd == BNEPGETCONNLIST) {
+ struct bnep_connlist_req cl;
+ uint32_t uci;
+ int err;
+
+ if (get_user(cl.cnum, (uint32_t __user *) arg) ||
+ get_user(uci, (u32 __user *) (arg + 4)))
+ return -EFAULT;
+
+ cl.ci = compat_ptr(uci);
+
+ if (cl.cnum <= 0)
+ return -EINVAL;
+
+ err = bnep_get_connlist(&cl);
+
+ if (!err && put_user(cl.cnum, (uint32_t __user *) arg))
+ err = -EFAULT;
+
+ return err;
+ }
+
+ return bnep_sock_ioctl(sock, cmd, arg);
+}
+#endif
+
static const struct proto_ops bnep_sock_ops = {
- .family = PF_BLUETOOTH,
- .owner = THIS_MODULE,
- .release = bnep_sock_release,
- .ioctl = bnep_sock_ioctl,
- .bind = sock_no_bind,
- .getname = sock_no_getname,
- .sendmsg = sock_no_sendmsg,
- .recvmsg = sock_no_recvmsg,
- .poll = sock_no_poll,
- .listen = sock_no_listen,
- .shutdown = sock_no_shutdown,
- .setsockopt = sock_no_setsockopt,
- .getsockopt = sock_no_getsockopt,
- .connect = sock_no_connect,
- .socketpair = sock_no_socketpair,
- .accept = sock_no_accept,
- .mmap = sock_no_mmap
+ .family = PF_BLUETOOTH,
+ .owner = THIS_MODULE,
+ .release = bnep_sock_release,
+ .ioctl = bnep_sock_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = bnep_sock_compat_ioctl,
+#endif
+ .bind = sock_no_bind,
+ .getname = sock_no_getname,
+ .sendmsg = sock_no_sendmsg,
+ .recvmsg = sock_no_recvmsg,
+ .poll = sock_no_poll,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = sock_no_setsockopt,
+ .getsockopt = sock_no_getsockopt,
+ .connect = sock_no_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .mmap = sock_no_mmap
};
static struct proto bnep_proto = {
if (sock->type != SOCK_RAW)
return -ESOCKTNOSUPPORT;
- sk = sk_alloc(PF_BLUETOOTH, GFP_KERNEL, &bnep_proto, 1);
+ sk = sk_alloc(PF_BLUETOOTH, GFP_ATOMIC, &bnep_proto, 1);
if (!sk)
return -ENOMEM;
#include <linux/socket.h>
#include <linux/ioctl.h>
#include <linux/file.h>
+#include <linux/compat.h>
#include <net/sock.h>
#include <linux/isdn/capilli.h>
return -EINVAL;
}
+#ifdef CONFIG_COMPAT
+static int cmtp_sock_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+ if (cmd == CMTPGETCONNLIST) {
+ struct cmtp_connlist_req cl;
+ uint32_t uci;
+ int err;
+
+ if (get_user(cl.cnum, (uint32_t __user *) arg) ||
+ get_user(uci, (u32 __user *) (arg + 4)))
+ return -EFAULT;
+
+ cl.ci = compat_ptr(uci);
+
+ if (cl.cnum <= 0)
+ return -EINVAL;
+
+ err = cmtp_get_connlist(&cl);
+
+ if (!err && put_user(cl.cnum, (uint32_t __user *) arg))
+ err = -EFAULT;
+
+ return err;
+ }
+
+ return cmtp_sock_ioctl(sock, cmd, arg);
+}
+#endif
+
static const struct proto_ops cmtp_sock_ops = {
.family = PF_BLUETOOTH,
.owner = THIS_MODULE,
.release = cmtp_sock_release,
.ioctl = cmtp_sock_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = cmtp_sock_compat_ioctl,
+#endif
.bind = sock_no_bind,
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
if (sock->type != SOCK_RAW)
return -ESOCKTNOSUPPORT;
- sk = sk_alloc(PF_BLUETOOTH, GFP_KERNEL, &cmtp_proto, 1);
+ sk = sk_alloc(PF_BLUETOOTH, GFP_ATOMIC, &cmtp_proto, 1);
if (!sk)
return -ENOMEM;
#define BT_DBG(D...)
#endif
-static void hci_acl_connect(struct hci_conn *conn)
+void hci_acl_connect(struct hci_conn *conn)
{
struct hci_dev *hdev = conn->hdev;
struct inquiry_entry *ie;
conn->out = 1;
conn->link_mode = HCI_LM_MASTER;
+ conn->attempt++;
+
memset(&cp, 0, sizeof(cp));
bacpy(&cp.bdaddr, &conn->dst);
cp.pscan_rep_mode = 0x02;
cp.role_switch = 0x01;
else
cp.role_switch = 0x00;
-
+
hci_send_cmd(hdev, OGF_LINK_CTL, OCF_CREATE_CONN, sizeof(cp), &cp);
}
if (status) {
if (conn && conn->state == BT_CONNECT) {
- conn->state = BT_CLOSED;
- hci_proto_connect_cfm(conn, status);
- hci_conn_del(conn);
+ if (status != 0x0c || conn->attempt > 2) {
+ conn->state = BT_CLOSED;
+ hci_proto_connect_cfm(conn, status);
+ hci_conn_del(conn);
+ } else
+ conn->state = BT_CONNECT2;
}
} else {
if (!conn) {
static inline void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
{
struct hci_ev_conn_complete *ev = (struct hci_ev_conn_complete *) skb->data;
- struct hci_conn *conn;
+ struct hci_conn *conn, *pend;
BT_DBG("%s", hdev->name);
if (ev->status)
hci_conn_del(conn);
+ pend = hci_conn_hash_lookup_state(hdev, ACL_LINK, BT_CONNECT2);
+ if (pend)
+ hci_acl_connect(pend);
+
hci_dev_unlock(hdev);
}
sock->ops = &hci_sock_ops;
- sk = sk_alloc(PF_BLUETOOTH, GFP_KERNEL, &hci_sk_proto, 1);
+ sk = sk_alloc(PF_BLUETOOTH, GFP_ATOMIC, &hci_sk_proto, 1);
if (!sk)
return -ENOMEM;
struct hci_conn *conn = data;
int i;
- device_register(&conn->dev);
+ if (device_register(&conn->dev) < 0) {
+ BT_ERR("Failed to register connection device");
+ return;
+ }
for (i = 0; conn_attrs[i]; i++)
- device_create_file(&conn->dev, conn_attrs[i]);
+ if (device_create_file(&conn->dev, conn_attrs[i]) < 0)
+ BT_ERR("Failed to create connection attribute");
}
void hci_conn_add_sysfs(struct hci_conn *conn)
BT_DBG("%p name %s type %d", hdev, hdev->name, hdev->type);
dev->class = bt_class;
-
- if (hdev->parent)
- dev->parent = hdev->parent;
- else
- dev->parent = &bt_platform->dev;
+ dev->parent = hdev->parent;
strlcpy(dev->bus_id, hdev->name, BUS_ID_SIZE);
return err;
for (i = 0; bt_attrs[i]; i++)
- device_create_file(dev, bt_attrs[i]);
+ if (device_create_file(dev, bt_attrs[i]) < 0)
+ BT_ERR("Failed to create device attribute");
return 0;
}
if (intr_sk->sk_state != BT_CONNECTED)
wait_event_timeout(*(ctrl_sk->sk_sleep), (ctrl_sk->sk_state == BT_CLOSED), HZ);
- fput(session->ctrl_sock->file);
+ fput(session->intr_sock->file);
wait_event_timeout(*(intr_sk->sk_sleep), (intr_sk->sk_state == BT_CLOSED), HZ);
- fput(session->intr_sock->file);
+ fput(session->ctrl_sock->file);
__hidp_unlink_session(session);
return NULL;
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
- if (!conn)
- return NULL;
hci_dev_put(hdev);
- return &conn->dev;
+ return conn ? &conn->dev : NULL;
}
static inline void hidp_setup_input(struct hidp_session *session, struct hidp_connadd_req *req)
#include <linux/ioctl.h>
#include <linux/file.h>
#include <linux/init.h>
+#include <linux/compat.h>
#include <net/sock.h>
#include "hidp.h"
return -EINVAL;
}
+#ifdef CONFIG_COMPAT
+struct compat_hidp_connadd_req {
+ int ctrl_sock; // Connected control socket
+ int intr_sock; // Connteted interrupt socket
+ __u16 parser;
+ __u16 rd_size;
+ compat_uptr_t rd_data;
+ __u8 country;
+ __u8 subclass;
+ __u16 vendor;
+ __u16 product;
+ __u16 version;
+ __u32 flags;
+ __u32 idle_to;
+ char name[128];
+};
+
+static int hidp_sock_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+ if (cmd == HIDPGETCONNLIST) {
+ struct hidp_connlist_req cl;
+ uint32_t uci;
+ int err;
+
+ if (get_user(cl.cnum, (uint32_t __user *) arg) ||
+ get_user(uci, (u32 __user *) (arg + 4)))
+ return -EFAULT;
+
+ cl.ci = compat_ptr(uci);
+
+ if (cl.cnum <= 0)
+ return -EINVAL;
+
+ err = hidp_get_connlist(&cl);
+
+ if (!err && put_user(cl.cnum, (uint32_t __user *) arg))
+ err = -EFAULT;
+
+ return err;
+ } else if (cmd == HIDPCONNADD) {
+ struct compat_hidp_connadd_req ca;
+ struct hidp_connadd_req __user *uca;
+
+ uca = compat_alloc_user_space(sizeof(*uca));
+
+ if (copy_from_user(&ca, (void *) arg, sizeof(ca)))
+ return -EFAULT;
+
+ if (put_user(ca.ctrl_sock, &uca->ctrl_sock) ||
+ put_user(ca.intr_sock, &uca->intr_sock) ||
+ put_user(ca.parser, &uca->parser) ||
+ put_user(ca.rd_size, &uca->parser) ||
+ put_user(compat_ptr(ca.rd_data), &uca->rd_data) ||
+ put_user(ca.country, &uca->country) ||
+ put_user(ca.subclass, &uca->subclass) ||
+ put_user(ca.vendor, &uca->vendor) ||
+ put_user(ca.product, &uca->product) ||
+ put_user(ca.version, &uca->version) ||
+ put_user(ca.flags, &uca->flags) ||
+ put_user(ca.idle_to, &uca->idle_to) ||
+ copy_to_user(&uca->name[0], &ca.name[0], 128))
+ return -EFAULT;
+
+ arg = (unsigned long) uca;
+
+ /* Fall through. We don't actually write back any _changes_
+ to the structure anyway, so there's no need to copy back
+ into the original compat version */
+ }
+
+ return hidp_sock_ioctl(sock, cmd, arg);
+}
+#endif
+
static const struct proto_ops hidp_sock_ops = {
.family = PF_BLUETOOTH,
.owner = THIS_MODULE,
.release = hidp_sock_release,
.ioctl = hidp_sock_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = hidp_sock_compat_ioctl,
+#endif
.bind = sock_no_bind,
.getname = sock_no_getname,
.sendmsg = sock_no_sendmsg,
if (sock->type != SOCK_RAW)
return -ESOCKTNOSUPPORT;
- sk = sk_alloc(PF_BLUETOOTH, GFP_KERNEL, &hidp_proto, 1);
+ sk = sk_alloc(PF_BLUETOOTH, GFP_ATOMIC, &hidp_proto, 1);
if (!sk)
return -ENOMEM;
sock->ops = &l2cap_sock_ops;
- sk = l2cap_sock_alloc(sock, protocol, GFP_KERNEL);
+ sk = l2cap_sock_alloc(sock, protocol, GFP_ATOMIC);
if (!sk)
return -ENOMEM;
goto error;
}
- class_create_file(bt_class, &class_attr_l2cap);
+ if (class_create_file(bt_class, &class_attr_l2cap) < 0)
+ BT_ERR("Failed to create L2CAP info file");
BT_INFO("L2CAP ver %s", VERSION);
BT_INFO("L2CAP socket layer initialized");
kernel_thread(rfcomm_run, NULL, CLONE_KERNEL);
- class_create_file(bt_class, &class_attr_rfcomm_dlc);
+ if (class_create_file(bt_class, &class_attr_rfcomm_dlc) < 0)
+ BT_ERR("Failed to create RFCOMM info file");
rfcomm_init_sockets();
sock->ops = &rfcomm_sock_ops;
- if (!(sk = rfcomm_sock_alloc(sock, protocol, GFP_KERNEL)))
+ sk = rfcomm_sock_alloc(sock, protocol, GFP_ATOMIC);
+ if (!sk)
return -ENOMEM;
rfcomm_sock_init(sk, NULL);
if (err < 0)
goto error;
- class_create_file(bt_class, &class_attr_rfcomm);
+ if (class_create_file(bt_class, &class_attr_rfcomm) < 0)
+ BT_ERR("Failed to create RFCOMM info file");
BT_INFO("RFCOMM socket layer initialized");
return NULL;
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst);
- if (!conn)
- return NULL;
hci_dev_put(hdev);
- return &conn->dev;
+ return conn ? &conn->dev : NULL;
}
static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc)
BT_DBG("tty %p termios %p", tty, old);
+ if (!dev)
+ return;
+
/* Handle turning off CRTSCTS */
if ((old->c_cflag & CRTSCTS) && !(new->c_cflag & CRTSCTS))
BT_DBG("Turning off CRTSCTS unsupported");
sock->ops = &sco_sock_ops;
- if (!(sk = sco_sock_alloc(sock, protocol, GFP_KERNEL)))
+ sk = sco_sock_alloc(sock, protocol, GFP_ATOMIC);
+ if (!sk)
return -ENOMEM;
sco_sock_init(sk, NULL);
goto error;
}
- class_create_file(bt_class, &class_attr_sco);
+ if (class_create_file(bt_class, &class_attr_sco) < 0)
+ BT_ERR("Failed to create SCO info file");
BT_INFO("SCO (Voice Link) ver %s", VERSION);
BT_INFO("SCO socket layer initialized");
mod_timer(&br->gc_timer, jiffies + HZ/10);
}
-void br_fdb_delete_by_port(struct net_bridge *br, struct net_bridge_port *p)
+
+void br_fdb_delete_by_port(struct net_bridge *br,
+ const struct net_bridge_port *p,
+ int do_all)
{
int i;
if (f->dst != p)
continue;
+ if (f->is_static && !do_all)
+ continue;
/*
* if multiple ports all have the same device address
* then when one port is deleted, assign
br_stp_disable_port(p);
spin_unlock_bh(&br->lock);
- br_fdb_delete_by_port(br, p);
+ br_fdb_delete_by_port(br, p, 1);
list_del_rcu(&p->list);
return 0;
err2:
- br_fdb_delete_by_port(br, p);
+ br_fdb_delete_by_port(br, p, 1);
err1:
kobject_del(&p->kobj);
err0:
const unsigned char *newaddr);
extern void br_fdb_cleanup(unsigned long arg);
extern void br_fdb_delete_by_port(struct net_bridge *br,
- struct net_bridge_port *p);
+ const struct net_bridge_port *p, int do_all);
extern struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br,
const unsigned char *addr);
extern struct net_bridge_fdb_entry *br_fdb_get(struct net_bridge *br,
del_timer(&p->forward_delay_timer);
del_timer(&p->hold_timer);
+ br_fdb_delete_by_port(br, p, 0);
+
br_configuration_update(br);
br_port_state_selection(br);
if (i > 0) {
int cmlen = CMSG_COMPAT_LEN(i * sizeof(int));
- if (!err)
- err = put_user(SOL_SOCKET, &cm->cmsg_level);
+ err = put_user(SOL_SOCKET, &cm->cmsg_level);
if (!err)
err = put_user(SCM_RIGHTS, &cm->cmsg_type);
if (!err)
BUG_ON(!dev_boot_phase);
- net_random_init();
-
if (dev_proc_init())
goto out;
add_timer(&flow_hash_rnd_timer);
}
+static void flow_entry_kill(int cpu, struct flow_cache_entry *fle)
+{
+ if (fle->object)
+ atomic_dec(fle->object_ref);
+ kmem_cache_free(flow_cachep, fle);
+ flow_count(cpu)--;
+}
+
static void __flow_cache_shrink(int cpu, int shrink_to)
{
struct flow_cache_entry *fle, **flp;
}
while ((fle = *flp) != NULL) {
*flp = fle->next;
- if (fle->object)
- atomic_dec(fle->object_ref);
- kmem_cache_free(flow_cachep, fle);
- flow_count(cpu)--;
+ flow_entry_kill(cpu, fle);
}
}
}
nocache:
{
+ int err;
void *obj;
atomic_t *obj_ref;
- resolver(key, family, dir, &obj, &obj_ref);
+ err = resolver(key, family, dir, &obj, &obj_ref);
if (fle) {
- fle->genid = atomic_read(&flow_cache_genid);
-
- if (fle->object)
- atomic_dec(fle->object_ref);
-
- fle->object = obj;
- fle->object_ref = obj_ref;
- if (obj)
- atomic_inc(fle->object_ref);
+ if (err) {
+ /* Force security policy check on next lookup */
+ *head = fle->next;
+ flow_entry_kill(cpu, fle);
+ } else {
+ fle->genid = atomic_read(&flow_cache_genid);
+
+ if (fle->object)
+ atomic_dec(fle->object_ref);
+
+ fle->object = obj;
+ fle->object_ref = obj_ref;
+ if (obj)
+ atomic_inc(fle->object_ref);
+ }
}
local_bh_enable();
+ if (err)
+ obj = ERR_PTR(err);
return obj;
}
}
goto errout;
}
- err = rtnl_unicast(skb, NETLINK_CB(skb).pid);
+ err = rtnl_unicast(nskb, NETLINK_CB(skb).pid);
errout:
kfree(iw_buf);
dev_put(dev);
if (i > 0)
{
int cmlen = CMSG_LEN(i*sizeof(int));
- if (!err)
- err = put_user(SOL_SOCKET, &cm->cmsg_level);
+ err = put_user(SOL_SOCKET, &cm->cmsg_level);
if (!err)
err = put_user(SCM_RIGHTS, &cm->cmsg_type);
if (!err)
#include <asm/system.h>
#include <asm/uaccess.h>
-/*
- This is a maximally equidistributed combined Tausworthe generator
- based on code from GNU Scientific Library 1.5 (30 Jun 2004)
-
- x_n = (s1_n ^ s2_n ^ s3_n)
-
- s1_{n+1} = (((s1_n & 4294967294) <<12) ^ (((s1_n <<13) ^ s1_n) >>19))
- s2_{n+1} = (((s2_n & 4294967288) << 4) ^ (((s2_n << 2) ^ s2_n) >>25))
- s3_{n+1} = (((s3_n & 4294967280) <<17) ^ (((s3_n << 3) ^ s3_n) >>11))
-
- The period of this generator is about 2^88.
-
- From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe
- Generators", Mathematics of Computation, 65, 213 (1996), 203--213.
-
- This is available on the net from L'Ecuyer's home page,
-
- http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps
- ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps
-
- There is an erratum in the paper "Tables of Maximally
- Equidistributed Combined LFSR Generators", Mathematics of
- Computation, 68, 225 (1999), 261--269:
- http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps
-
- ... the k_j most significant bits of z_j must be non-
- zero, for each j. (Note: this restriction also applies to the
- computer code given in [4], but was mistakenly not mentioned in
- that paper.)
-
- This affects the seeding procedure by imposing the requirement
- s1 > 1, s2 > 7, s3 > 15.
-
-*/
-struct nrnd_state {
- u32 s1, s2, s3;
-};
-
-static DEFINE_PER_CPU(struct nrnd_state, net_rand_state);
-
-static u32 __net_random(struct nrnd_state *state)
-{
-#define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b)
-
- state->s1 = TAUSWORTHE(state->s1, 13, 19, 4294967294UL, 12);
- state->s2 = TAUSWORTHE(state->s2, 2, 25, 4294967288UL, 4);
- state->s3 = TAUSWORTHE(state->s3, 3, 11, 4294967280UL, 17);
-
- return (state->s1 ^ state->s2 ^ state->s3);
-}
-
-static void __net_srandom(struct nrnd_state *state, unsigned long s)
-{
- if (s == 0)
- s = 1; /* default seed is 1 */
-
-#define LCG(n) (69069 * n)
- state->s1 = LCG(s);
- state->s2 = LCG(state->s1);
- state->s3 = LCG(state->s2);
-
- /* "warm it up" */
- __net_random(state);
- __net_random(state);
- __net_random(state);
- __net_random(state);
- __net_random(state);
- __net_random(state);
-}
-
-
-unsigned long net_random(void)
-{
- unsigned long r;
- struct nrnd_state *state = &get_cpu_var(net_rand_state);
- r = __net_random(state);
- put_cpu_var(state);
- return r;
-}
-
-
-void net_srandom(unsigned long entropy)
-{
- struct nrnd_state *state = &get_cpu_var(net_rand_state);
- __net_srandom(state, state->s1^entropy);
- put_cpu_var(state);
-}
-
-void __init net_random_init(void)
-{
- int i;
-
- for_each_possible_cpu(i) {
- struct nrnd_state *state = &per_cpu(net_rand_state,i);
- __net_srandom(state, i+jiffies);
- }
-}
-
-static int net_random_reseed(void)
-{
- int i;
- unsigned long seed;
-
- for_each_possible_cpu(i) {
- struct nrnd_state *state = &per_cpu(net_rand_state,i);
-
- get_random_bytes(&seed, sizeof(seed));
- __net_srandom(state, seed);
- }
- return 0;
-}
-late_initcall(net_random_reseed);
-
int net_msg_cost = 5*HZ;
int net_msg_burst = 10;
{
return __printk_ratelimit(net_msg_cost, net_msg_burst);
}
-
-EXPORT_SYMBOL(net_random);
EXPORT_SYMBOL(net_ratelimit);
-EXPORT_SYMBOL(net_srandom);
/*
* Convert an ASCII string to binary IP.
}
if (sk->sk_state == DCCP_TIME_WAIT) {
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(nsk);
return nsk;
}
- inet_twsk_put((struct inet_timewait_sock *)nsk);
+ inet_twsk_put(inet_twsk(nsk));
return NULL;
}
goto discard_it;
do_time_wait:
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
goto no_dccp_socket;
}
}
if (sk->sk_state == DCCP_TIME_WAIT) {
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(nsk);
return nsk;
}
- inet_twsk_put((struct inet_timewait_sock *)nsk);
+ inet_twsk_put(inet_twsk(nsk));
return NULL;
}
goto discard_it;
do_time_wait:
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
goto no_dccp_socket;
}
if (peer) {
if ((sock->state != SS_CONNECTED &&
sock->state != SS_CONNECTING) &&
- scp->accept_mode == ACC_IMMED)
+ scp->accept_mode == ACC_IMMED) {
+ release_sock(sk);
return -ENOTCONN;
+ }
memcpy(sa, &scp->peer, sizeof(struct sockaddr_dn));
} else {
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- return memcmp(&fl1->nl_u.dn_u, &fl2->nl_u.dn_u, sizeof(fl1->nl_u.dn_u)) == 0 &&
- fl1->oif == fl2->oif &&
- fl1->iif == fl2->iif;
+ return ((fl1->nl_u.dn_u.daddr ^ fl2->nl_u.dn_u.daddr) |
+ (fl1->nl_u.dn_u.saddr ^ fl2->nl_u.dn_u.saddr) |
+#ifdef CONFIG_DECNET_ROUTE_FWMARK
+ (fl1->nl_u.dn_u.fwmark ^ fl2->nl_u.dn_u.fwmark) |
+#endif
+ (fl1->nl_u.dn_u.scope ^ fl2->nl_u.dn_u.scope) |
+ (fl1->oif ^ fl2->oif) |
+ (fl1->iif ^ fl2->iif)) == 0;
}
static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp)
#include <net/tcp.h>
#include <net/netlabel.h>
#include <net/cipso_ipv4.h>
+#include <asm/atomic.h>
#include <asm/bug.h>
struct cipso_v4_domhsh_entry {
unsigned char *key;
size_t key_len;
- struct netlbl_lsm_cache lsm_data;
+ struct netlbl_lsm_cache *lsm_data;
u32 activity;
struct list_head list;
* @entry: the entry to free
*
* Description:
- * This function frees the memory associated with a cache entry.
+ * This function frees the memory associated with a cache entry including the
+ * LSM cache data if there are no longer any users, i.e. reference count == 0.
*
*/
static void cipso_v4_cache_entry_free(struct cipso_v4_map_cache_entry *entry)
{
- if (entry->lsm_data.free)
- entry->lsm_data.free(entry->lsm_data.data);
+ if (entry->lsm_data)
+ netlbl_secattr_cache_free(entry->lsm_data);
kfree(entry->key);
kfree(entry);
}
entry->key_len == key_len &&
memcmp(entry->key, key, key_len) == 0) {
entry->activity += 1;
- secattr->cache.free = entry->lsm_data.free;
- secattr->cache.data = entry->lsm_data.data;
+ atomic_inc(&entry->lsm_data->refcount);
+ secattr->cache = entry->lsm_data;
if (prev_entry == NULL) {
spin_unlock_bh(&cipso_v4_cache[bkt].lock);
return 0;
memcpy(entry->key, cipso_ptr, cipso_ptr_len);
entry->key_len = cipso_ptr_len;
entry->hash = cipso_v4_map_cache_hash(cipso_ptr, cipso_ptr_len);
- entry->lsm_data.free = secattr->cache.free;
- entry->lsm_data.data = secattr->cache.data;
+ atomic_inc(&secattr->cache->refcount);
+ entry->lsm_data = secattr->cache;
bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETBITS - 1);
spin_lock_bh(&cipso_v4_cache[bkt].lock);
{
int cat = -1;
u32 bitmap_len_bits = bitmap_len * 8;
- u32 cipso_cat_size = doi_def->map.std->cat.cipso_size;
- u32 *cipso_array = doi_def->map.std->cat.cipso;
+ u32 cipso_cat_size;
+ u32 *cipso_array;
switch (doi_def->type) {
case CIPSO_V4_MAP_PASS:
return 0;
case CIPSO_V4_MAP_STD:
+ cipso_cat_size = doi_def->map.std->cat.cipso_size;
+ cipso_array = doi_def->map.std->cat.cipso;
for (;;) {
cat = cipso_v4_bitmap_walk(bitmap,
bitmap_len_bits,
u32 net_spot_max = 0;
u32 host_clen_bits = host_cat_len * 8;
u32 net_clen_bits = net_cat_len * 8;
- u32 host_cat_size = doi_def->map.std->cat.local_size;
- u32 *host_cat_array = doi_def->map.std->cat.local;
+ u32 host_cat_size;
+ u32 *host_cat_array;
switch (doi_def->type) {
case CIPSO_V4_MAP_PASS:
- net_spot_max = host_cat_len - 1;
- while (net_spot_max > 0 && host_cat[net_spot_max] == 0)
+ net_spot_max = host_cat_len;
+ while (net_spot_max > 0 && host_cat[net_spot_max - 1] == 0)
net_spot_max--;
if (net_spot_max > net_cat_len)
return -EINVAL;
memcpy(net_cat, host_cat, net_spot_max);
return net_spot_max;
case CIPSO_V4_MAP_STD:
+ host_cat_size = doi_def->map.std->cat.local_size;
+ host_cat_array = doi_def->map.std->cat.local;
for (;;) {
host_spot = cipso_v4_bitmap_walk(host_cat,
host_clen_bits,
int net_spot = -1;
u32 net_clen_bits = net_cat_len * 8;
u32 host_clen_bits = host_cat_len * 8;
- u32 net_cat_size = doi_def->map.std->cat.cipso_size;
- u32 *net_cat_array = doi_def->map.std->cat.cipso;
+ u32 net_cat_size;
+ u32 *net_cat_array;
switch (doi_def->type) {
case CIPSO_V4_MAP_PASS:
memcpy(host_cat, net_cat, net_cat_len);
return net_cat_len;
case CIPSO_V4_MAP_STD:
+ net_cat_size = doi_def->map.std->cat.cipso_size;
+ net_cat_array = doi_def->map.std->cat.cipso;
for (;;) {
net_spot = cipso_v4_bitmap_walk(net_cat,
net_clen_bits,
int inet_peer_maxttl = 10 * 60 * HZ; /* usual time to live: 10 min */
static struct inet_peer *inet_peer_unused_head;
-/* Exported for inet_putpeer inline function. */
-struct inet_peer **inet_peer_unused_tailp = &inet_peer_unused_head;
-DEFINE_SPINLOCK(inet_peer_unused_lock);
-#define PEER_MAX_CLEANUP_WORK 30
+static struct inet_peer **inet_peer_unused_tailp = &inet_peer_unused_head;
+static DEFINE_SPINLOCK(inet_peer_unused_lock);
static void peer_check_expire(unsigned long dummy);
static DEFINE_TIMER(peer_periodic_timer, peer_check_expire, 0, 0);
spin_lock_bh(&inet_peer_unused_lock);
p = inet_peer_unused_head;
if (p != NULL) {
- if (time_after(p->dtime + ttl, jiffies)) {
+ __u32 delta = (__u32)jiffies - p->dtime;
+ if (delta < ttl) {
/* Do not prune fresh entries. */
spin_unlock_bh(&inet_peer_unused_lock);
return -1;
/* Called with local BH disabled. */
static void peer_check_expire(unsigned long dummy)
{
- int i;
+ unsigned long now = jiffies;
int ttl;
if (peer_total >= inet_peer_threshold)
ttl = inet_peer_maxttl
- (inet_peer_maxttl - inet_peer_minttl) / HZ *
peer_total / inet_peer_threshold * HZ;
- for (i = 0; i < PEER_MAX_CLEANUP_WORK && !cleanup_once(ttl); i++);
+ while (!cleanup_once(ttl)) {
+ if (jiffies != now)
+ break;
+ }
/* Trigger the timer after inet_peer_gc_mintime .. inet_peer_gc_maxtime
* interval depending on the total number of entries (more entries,
peer_total / inet_peer_threshold * HZ;
add_timer(&peer_periodic_timer);
}
+
+void inet_putpeer(struct inet_peer *p)
+{
+ spin_lock_bh(&inet_peer_unused_lock);
+ if (atomic_dec_and_test(&p->refcnt)) {
+ p->unused_prevp = inet_peer_unused_tailp;
+ p->unused_next = NULL;
+ *inet_peer_unused_tailp = p;
+ inet_peer_unused_tailp = &p->unused_next;
+ p->dtime = (__u32)jiffies;
+ }
+ spin_unlock_bh(&inet_peer_unused_lock);
+}
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (flags == 0 &&
- skb->protocol == __constant_htons(ETH_P_WCCP)) {
- skb->protocol = __constant_htons(ETH_P_IP);
+ skb->protocol == htons(ETH_P_WCCP)) {
+ skb->protocol = htons(ETH_P_IP);
if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
static void __exit arp_tables_fini(void)
{
nf_unregister_sockopt(&arpt_sockopts);
+ xt_unregister_target(&arpt_error_target);
+ xt_unregister_target(&arpt_standard_target);
xt_proto_fini(NF_ARP);
}
static char __initdata version[] = "0.90";
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(format, args...)
-#endif
-
-
static inline int
ctnetlink_dump_tuples_proto(struct sk_buff *skb,
const struct ip_conntrack_tuple *tuple,
static int ctnetlink_done(struct netlink_callback *cb)
{
- DEBUGP("entered %s\n", __FUNCTION__);
if (cb->args[1])
ip_conntrack_put((struct ip_conntrack *)cb->args[1]);
return 0;
struct ip_conntrack_tuple_hash *h;
struct list_head *i;
- DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__,
- cb->args[0], *id);
-
read_lock_bh(&ip_conntrack_lock);
last = (struct ip_conntrack *)cb->args[1];
for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++) {
if (last)
ip_conntrack_put(last);
- DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);
return skb->len;
}
{
struct nfattr *tb[CTA_IP_MAX];
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_IP_MAX, attr);
if (nfattr_bad_size(tb, CTA_IP_MAX, cta_min_ip))
return -EINVAL;
tuple->dst.ip = *(__be32 *)NFA_DATA(tb[CTA_IP_V4_DST-1]);
- DEBUGP("leaving\n");
-
return 0;
}
struct ip_conntrack_protocol *proto;
int ret = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_PROTO_MAX, attr);
if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto))
struct nfattr *tb[CTA_TUPLE_MAX];
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
memset(tuple, 0, sizeof(*tuple));
nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]);
else
tuple->dst.dir = IP_CT_DIR_ORIGINAL;
- DUMP_TUPLE(tuple);
-
- DEBUGP("leaving\n");
-
return 0;
}
struct nfattr *tb[CTA_PROTONAT_MAX];
struct ip_nat_protocol *npt;
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr);
if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat))
ip_nat_proto_put(npt);
- DEBUGP("leaving\n");
return 0;
}
struct nfattr *tb[CTA_NAT_MAX];
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
memset(range, 0, sizeof(*range));
nfattr_parse_nested(tb, CTA_NAT_MAX, nat);
if (err < 0)
return err;
- DEBUGP("leaving\n");
return 0;
}
#endif
{
struct nfattr *tb[CTA_HELP_MAX];
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_HELP_MAX, attr);
if (!tb[CTA_HELP_NAME-1])
struct ip_conntrack *ct;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_MAX, cta_min))
return -EINVAL;
return err;
h = ip_conntrack_find_get(&tuple, NULL);
- if (!h) {
- DEBUGP("tuple not found in conntrack hash\n");
+ if (!h)
return -ENOENT;
- }
ct = tuplehash_to_ctrack(h);
ct->timeout.function((unsigned long)ct);
ip_conntrack_put(ct);
- DEBUGP("leaving\n");
return 0;
}
struct sk_buff *skb2 = NULL;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct nfgenmsg *msg = NLMSG_DATA(nlh);
u32 rlen;
return err;
h = ip_conntrack_find_get(&tuple, NULL);
- if (!h) {
- DEBUGP("tuple not found in conntrack hash");
+ if (!h)
return -ENOENT;
- }
- DEBUGP("tuple found\n");
+
ct = tuplehash_to_ctrack(h);
err = -ENOMEM;
if (err < 0)
goto out;
- DEBUGP("leaving\n");
return 0;
free:
char *helpname;
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
/* don't change helper of sibling connections */
if (ct->master)
return -EINVAL;
{
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (cda[CTA_HELP-1]) {
err = ctnetlink_change_helper(ct, cda);
if (err < 0)
ct->mark = ntohl(*(__be32 *)NFA_DATA(cda[CTA_MARK-1]));
#endif
- DEBUGP("all done\n");
return 0;
}
struct ip_conntrack *ct;
int err = -EINVAL;
- DEBUGP("entered %s\n", __FUNCTION__);
-
ct = ip_conntrack_alloc(otuple, rtuple);
if (ct == NULL || IS_ERR(ct))
return -ENOMEM;
if (ct->helper)
ip_conntrack_helper_put(ct->helper);
- DEBUGP("conntrack with id %u inserted\n", ct->id);
return 0;
err:
struct ip_conntrack_tuple_hash *h = NULL;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_MAX, cta_min))
return -EINVAL;
if (h == NULL) {
write_unlock_bh(&ip_conntrack_lock);
- DEBUGP("no such conntrack, create new\n");
err = -ENOENT;
if (nlh->nlmsg_flags & NLM_F_CREATE)
err = ctnetlink_create_conntrack(cda, &otuple, &rtuple);
/* We manipulate the conntrack inside the global conntrack table lock,
* so there's no need to increase the refcount */
- DEBUGP("conntrack found\n");
err = -EEXIST;
if (!(nlh->nlmsg_flags & NLM_F_EXCL))
err = ctnetlink_change_conntrack(tuplehash_to_ctrack(h), cda);
struct list_head *i;
u_int32_t *id = (u_int32_t *) &cb->args[0];
- DEBUGP("entered %s, last id=%llu\n", __FUNCTION__, *id);
-
read_lock_bh(&ip_conntrack_lock);
list_for_each_prev(i, &ip_conntrack_expect_list) {
exp = (struct ip_conntrack_expect *) i;
out:
read_unlock_bh(&ip_conntrack_lock);
- DEBUGP("leaving, last id=%llu\n", *id);
-
return skb->len;
}
struct sk_buff *skb2;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp))
return -EINVAL;
struct ip_conntrack *ct;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
/* caller guarantees that those three CTA_EXPECT_* exist */
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE);
if (err < 0)
struct ip_conntrack_expect *exp;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp))
return -EINVAL;
err = ctnetlink_change_expect(exp, cda);
write_unlock_bh(&ip_conntrack_lock);
- DEBUGP("leaving\n");
-
return err;
}
set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo)
{
struct iphdr *iph = (*pskb)->nh.iph;
- __be16 oldtos;
+ u_int16_t oldtos;
if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) {
if (!skb_make_writable(pskb, sizeof(struct iphdr)))
oldtos = iph->tos;
iph->tos &= ~IPT_ECN_IP_MASK;
iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK);
- iph->check = nf_csum_update(oldtos ^ htons(0xFFFF), iph->tos,
- iph->check);
+ iph->check = nf_csum_update(htons(oldtos) ^ htons(0xFFFF),
+ htons(iph->tos), iph->check);
}
return 1;
}
{
const struct ipt_tos_target_info *tosinfo = targinfo;
struct iphdr *iph = (*pskb)->nh.iph;
- __be16 oldtos;
+ u_int16_t oldtos;
if ((iph->tos & IPTOS_TOS_MASK) != tosinfo->tos) {
if (!skb_make_writable(pskb, sizeof(struct iphdr)))
iph = (*pskb)->nh.iph;
oldtos = iph->tos;
iph->tos = (iph->tos & IPTOS_PREC_MASK) | tosinfo->tos;
- iph->check = nf_csum_update(oldtos ^ htons(0xFFFF), iph->tos,
- iph->check);
+ iph->check = nf_csum_update(htons(oldtos) ^ htons(0xFFFF),
+ htons(iph->tos), iph->check);
}
return IPT_CONTINUE;
}
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- return memcmp(&fl1->nl_u.ip4_u, &fl2->nl_u.ip4_u, sizeof(fl1->nl_u.ip4_u)) == 0 &&
- fl1->oif == fl2->oif &&
- fl1->iif == fl2->iif;
+ return ((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
+ (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) |
+#ifdef CONFIG_IP_ROUTE_FWMARK
+ (fl1->nl_u.ip4_u.fwmark ^ fl2->nl_u.ip4_u.fwmark) |
+#endif
+ (*(u16 *)&fl1->nl_u.ip4_u.tos ^
+ *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (fl1->oif ^ fl2->oif) |
+ (fl1->iif ^ fl2->iif)) == 0;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
return;
}
struct tcphdr *th = skb->h.th;
struct {
struct tcphdr th;
- u32 tsopt[3];
+ u32 tsopt[TCPOLEN_TSTAMP_ALIGNED >> 2];
} rep;
struct ip_reply_arg arg;
bh_lock_sock(nsk);
return nsk;
}
- inet_twsk_put((struct inet_timewait_sock *)nsk);
+ inet_twsk_put(inet_twsk(nsk));
return NULL;
}
do_time_wait:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- inet_twsk_put((struct inet_timewait_sock *) sk);
+ inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
TCP_INC_STATS_BH(TCP_MIB_INERRS);
- inet_twsk_put((struct inet_timewait_sock *) sk);
+ inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
- switch (tcp_timewait_state_process((struct inet_timewait_sock *)sk,
- skb, th)) {
+ switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN: {
struct sock *sk2 = inet_lookup_listener(&tcp_hashinfo,
skb->nh.iph->daddr,
th->dest,
inet_iif(skb));
if (sk2) {
- inet_twsk_deschedule((struct inet_timewait_sock *)sk,
- &tcp_death_row);
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
+ inet_twsk_put(inet_twsk(sk));
sk = sk2;
goto process;
}
__u32 tstamp)
{
if (tp->rx_opt.tstamp_ok) {
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) |
- TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp);
*ptr++ = htonl(tp->rx_opt.ts_recent);
}
*ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
if (ts) {
if(sack)
- *ptr++ = __constant_htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) |
- (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
+ (TCPOLEN_SACK_PERM << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
else
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp); /* TSVAL */
*ptr++ = htonl(ts_recent); /* TSECR */
} else if(sack)
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_SACK_PERM << 8) |
+ TCPOLEN_SACK_PERM);
if (offer_wscale)
- *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | (wscale));
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_WINDOW << 16) |
+ (TCPOLEN_WINDOW << 8) |
+ (wscale));
}
/* This routine actually transmits TCP packets queued in by
xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
xdst->u.rt.fl.fl4_src == fl->fl4_src &&
xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
- xfrm_bundle_ok(xdst, fl, AF_INET, 0)) {
+ xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) {
dst_clone(dst);
break;
}
---help---
Support for MIPv6 route optimization mode.
+config IPV6_SIT
+ tristate "IPv6: IPv6-in-IPv4 tunnel (SIT driver)"
+ depends on IPV6
+ default y
+ ---help---
+ Tunneling means encapsulating data of one protocol type within
+ another protocol and sending it over a channel that understands the
+ encapsulating protocol. This driver implements encapsulation of IPv6
+ into IPv4 packets. This is useful if you want to connect two IPv6
+ networks over an IPv4-only path.
+
+ Saying M here will produce a module called sit.ko. If unsure, say Y.
+
config IPV6_TUNNEL
tristate "IPv6: IPv6-in-IPv6 tunnel"
select INET6_TUNNEL
obj-$(CONFIG_IPV6) += ipv6.o
-ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \
+ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o raw.o \
protocol.o icmp.o mcast.o reassembly.o tcp_ipv6.o \
exthdrs.o sysctl_net_ipv6.o datagram.o proc.o \
obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o
obj-$(CONFIG_NETFILTER) += netfilter/
+obj-$(CONFIG_IPV6_SIT) += sit.o
obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o
obj-y += exthdrs_core.o
ndev->regen_timer.data = (unsigned long) ndev;
if ((dev->flags&IFF_LOOPBACK) ||
dev->type == ARPHRD_TUNNEL ||
- dev->type == ARPHRD_NONE ||
- dev->type == ARPHRD_SIT) {
+#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+ dev->type == ARPHRD_SIT ||
+#endif
+ dev->type == ARPHRD_NONE) {
printk(KERN_INFO
"%s: Disabled Privacy Extensions\n",
dev->name);
This thing is done here expecting that the whole
class of non-broadcast devices need not cloning.
*/
+#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT))
cfg.fc_flags |= RTF_NONEXTHOP;
+#endif
ip6_route_add(&cfg);
}
ip6_route_add(&cfg);
}
+#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
static void sit_route_add(struct net_device *dev)
{
struct fib6_config cfg = {
/* prefix length - 96 bits "::d.d.d.d" */
ip6_route_add(&cfg);
}
+#endif
static void addrconf_add_lroute(struct net_device *dev)
{
if (dev == NULL)
goto err_exit;
+#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
if (dev->type == ARPHRD_SIT) {
struct ifreq ifr;
mm_segment_t oldfs;
err = dev_open(dev);
}
}
+#endif
err_exit:
rtnl_unlock();
return err;
}
+#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
static void sit_add_v4_addrs(struct inet6_dev *idev)
{
struct inet6_ifaddr * ifp;
}
}
}
+#endif
static void init_loopback(struct net_device *dev)
{
addrconf_add_linklocal(idev, &addr);
}
+#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
static void addrconf_sit_config(struct net_device *dev)
{
struct inet6_dev *idev;
} else
sit_route_add(dev);
}
+#endif
static inline int
ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev)
}
switch(dev->type) {
+#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
case ARPHRD_SIT:
addrconf_sit_config(dev);
break;
+#endif
case ARPHRD_TUNNEL6:
addrconf_ip6_tnl_config(dev);
break;
err = addrconf_init();
if (err)
goto addrconf_fail;
- sit_init();
/* Init v6 extension headers. */
ipv6_rthdr_init();
mip6_fini();
#endif
/* Cleanup code parts. */
- sit_cleanup();
ip6_flowlabel_cleanup();
addrconf_cleanup();
ip6_route_cleanup();
{
struct fib6_rule *r = (struct fib6_rule *) rule;
- if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen))
+ if (r->dst.plen &&
+ !ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen))
return 0;
- if ((flags & RT6_LOOKUP_F_HAS_SADDR) &&
- !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen))
- return 0;
+ if (r->src.plen) {
+ if (!(flags & RT6_LOOKUP_F_HAS_SADDR) ||
+ !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen))
+ return 0;
+ }
if (r->tclass && r->tclass != ((ntohl(fl->fl6_flowlabel) >> 20) & 0xff))
return 0;
ipv6_devconf.forwarding && ipv6_devconf.proxy_ndp &&
pneigh_lookup(&nd_tbl, &msg->target, dev, 0)) {
/* XXX: idev->cnf.prixy_ndp */
- WARN_ON(skb->dst != NULL &&
- ((struct rt6_info *)skb->dst)->rt6i_idev);
goto out;
}
.nl_u = {
.ip6_u = {
.daddr = *daddr,
- /* TODO: saddr */
},
},
};
struct dst_entry *dst;
int flags = strict ? RT6_LOOKUP_F_IFACE : 0;
+ if (saddr) {
+ memcpy(&fl.fl6_src, saddr, sizeof(*saddr));
+ flags |= RT6_LOOKUP_F_HAS_SADDR;
+ }
+
dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup);
if (dst->error == 0)
return (struct rt6_info *) dst;
void ip6_route_input(struct sk_buff *skb)
{
struct ipv6hdr *iph = skb->nh.ipv6h;
+ int flags = RT6_LOOKUP_F_HAS_SADDR;
struct flowi fl = {
.iif = skb->dev->ifindex,
.nl_u = {
},
.proto = iph->nexthdr,
};
- int flags = rt6_need_strict(&iph->daddr) ? RT6_LOOKUP_F_IFACE : 0;
+
+ if (rt6_need_strict(&iph->daddr))
+ flags |= RT6_LOOKUP_F_IFACE;
skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input);
}
if (rt6_need_strict(&fl->fl6_dst))
flags |= RT6_LOOKUP_F_IFACE;
+ if (!ipv6_addr_any(&fl->fl6_src))
+ flags |= RT6_LOOKUP_F_HAS_SADDR;
+
return fib6_rule_lookup(fl, flags, ip6_pol_route_output);
}
struct in6_addr *gateway,
struct net_device *dev)
{
+ int flags = RT6_LOOKUP_F_HAS_SADDR;
struct ip6rd_flowi rdfl = {
.fl = {
.oif = dev->ifindex,
},
.gateway = *gateway,
};
- int flags = rt6_need_strict(dest) ? RT6_LOOKUP_F_IFACE : 0;
+
+ if (rt6_need_strict(dest))
+ flags |= RT6_LOOKUP_F_IFACE;
return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect);
}
inet_del_protocol(&sit_protocol, IPPROTO_IPV6);
goto out;
}
+
+module_init(sit_init);
+module_exit(sit_cleanup);
+MODULE_LICENSE("GPL");
}
if (sk->sk_state == TCP_TIME_WAIT) {
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
return;
}
int tot_len = sizeof(struct tcphdr);
if (ts)
- tot_len += 3*4;
+ tot_len += TCPOLEN_TSTAMP_ALIGNED;
buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
GFP_ATOMIC);
bh_lock_sock(nsk);
return nsk;
}
- inet_twsk_put((struct inet_timewait_sock *)nsk);
+ inet_twsk_put(inet_twsk(nsk));
return NULL;
}
do_time_wait:
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
TCP_INC_STATS_BH(TCP_MIB_INERRS);
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
- switch (tcp_timewait_state_process((struct inet_timewait_sock *)sk,
- skb, th)) {
+ switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN:
{
struct sock *sk2;
xdst->u.rt6.rt6i_src.plen);
if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) &&
ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) &&
- xfrm_bundle_ok(xdst, fl, AF_INET6,
+ xfrm_bundle_ok(policy, xdst, fl, AF_INET6,
(xdst->u.rt6.rt6i_dst.plen != 128 ||
xdst->u.rt6.rt6i_src.plen != 128))) {
dst_clone(dst);
if (*dir)
goto out;
}
- else {
- *dir = security_xfrm_sock_policy_alloc(xp, sk);
- if (*dir)
- goto out;
- }
*dir = pol->sadb_x_policy_dir-1;
return xp;
config NETFILTER_XT_TARGET_CONNSECMARK
tristate '"CONNSECMARK" target support'
- depends on NETFILTER_XTABLES && (NF_CONNTRACK_SECMARK || IP_NF_CONNTRACK_SECMARK)
+ depends on NETFILTER_XTABLES && \
+ ((NF_CONNTRACK && NF_CONNTRACK_SECMARK) || \
+ (IP_NF_CONNTRACK && IP_NF_CONNTRACK_SECMARK))
help
The CONNSECMARK target copies security markings from packets
to connections, and restores security markings from connections
static char __initdata version[] = "0.93";
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(format, args...)
-#endif
-
-
static inline int
ctnetlink_dump_tuples_proto(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple,
{
if (cb->args[1])
nf_ct_put((struct nf_conn *)cb->args[1]);
- DEBUGP("entered %s\n", __FUNCTION__);
return 0;
}
struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
u_int8_t l3proto = nfmsg->nfgen_family;
- DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__,
- cb->args[0], *id);
-
read_lock_bh(&nf_conntrack_lock);
last = (struct nf_conn *)cb->args[1];
for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) {
if (last)
nf_ct_put(last);
- DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);
return skb->len;
}
struct nf_conntrack_l3proto *l3proto;
int ret = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_IP_MAX, attr);
l3proto = nf_ct_l3proto_find_get(tuple->src.l3num);
nf_ct_l3proto_put(l3proto);
- DEBUGP("leaving\n");
-
return ret;
}
struct nf_conntrack_protocol *proto;
int ret = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_PROTO_MAX, attr);
if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto))
struct nfattr *tb[CTA_TUPLE_MAX];
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
memset(tuple, 0, sizeof(*tuple));
nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]);
else
tuple->dst.dir = IP_CT_DIR_ORIGINAL;
- NF_CT_DUMP_TUPLE(tuple);
-
- DEBUGP("leaving\n");
-
return 0;
}
struct nfattr *tb[CTA_PROTONAT_MAX];
struct ip_nat_protocol *npt;
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr);
if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat))
ip_nat_proto_put(npt);
- DEBUGP("leaving\n");
return 0;
}
struct nfattr *tb[CTA_NAT_MAX];
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
memset(range, 0, sizeof(*range));
nfattr_parse_nested(tb, CTA_NAT_MAX, nat);
if (err < 0)
return err;
- DEBUGP("leaving\n");
return 0;
}
#endif
{
struct nfattr *tb[CTA_HELP_MAX];
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_HELP_MAX, attr);
if (!tb[CTA_HELP_NAME-1])
u_int8_t u3 = nfmsg->nfgen_family;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_MAX, cta_min))
return -EINVAL;
return err;
h = nf_conntrack_find_get(&tuple, NULL);
- if (!h) {
- DEBUGP("tuple not found in conntrack hash\n");
+ if (!h)
return -ENOENT;
- }
ct = nf_ct_tuplehash_to_ctrack(h);
ct->timeout.function((unsigned long)ct);
nf_ct_put(ct);
- DEBUGP("leaving\n");
return 0;
}
u_int8_t u3 = nfmsg->nfgen_family;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nlh->nlmsg_flags & NLM_F_DUMP) {
u32 rlen;
return err;
h = nf_conntrack_find_get(&tuple, NULL);
- if (!h) {
- DEBUGP("tuple not found in conntrack hash");
+ if (!h)
return -ENOENT;
- }
- DEBUGP("tuple found\n");
+
ct = nf_ct_tuplehash_to_ctrack(h);
err = -ENOMEM;
if (err < 0)
goto out;
- DEBUGP("leaving\n");
return 0;
free:
char *helpname;
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (!help) {
/* FIXME: we need to reallocate and rehash */
return -EBUSY;
{
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (cda[CTA_HELP-1]) {
err = ctnetlink_change_helper(ct, cda);
if (err < 0)
ct->mark = ntohl(*(u_int32_t *)NFA_DATA(cda[CTA_MARK-1]));
#endif
- DEBUGP("all done\n");
return 0;
}
struct nf_conn *ct;
int err = -EINVAL;
- DEBUGP("entered %s\n", __FUNCTION__);
-
ct = nf_conntrack_alloc(otuple, rtuple);
if (ct == NULL || IS_ERR(ct))
return -ENOMEM;
add_timer(&ct->timeout);
nf_conntrack_hash_insert(ct);
- DEBUGP("conntrack with id %u inserted\n", ct->id);
return 0;
err:
u_int8_t u3 = nfmsg->nfgen_family;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_MAX, cta_min))
return -EINVAL;
if (h == NULL) {
write_unlock_bh(&nf_conntrack_lock);
- DEBUGP("no such conntrack, create new\n");
err = -ENOENT;
if (nlh->nlmsg_flags & NLM_F_CREATE)
err = ctnetlink_create_conntrack(cda, &otuple, &rtuple);
/* We manipulate the conntrack inside the global conntrack table lock,
* so there's no need to increase the refcount */
- DEBUGP("conntrack found\n");
err = -EEXIST;
if (!(nlh->nlmsg_flags & NLM_F_EXCL))
err = ctnetlink_change_conntrack(nf_ct_tuplehash_to_ctrack(h), cda);
struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
u_int8_t l3proto = nfmsg->nfgen_family;
- DEBUGP("entered %s, last id=%llu\n", __FUNCTION__, *id);
-
read_lock_bh(&nf_conntrack_lock);
list_for_each_prev(i, &nf_conntrack_expect_list) {
exp = (struct nf_conntrack_expect *) i;
out:
read_unlock_bh(&nf_conntrack_lock);
- DEBUGP("leaving, last id=%llu\n", *id);
-
return skb->len;
}
u_int8_t u3 = nfmsg->nfgen_family;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp))
return -EINVAL;
struct nf_conn_help *help;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
/* caller guarantees that those three CTA_EXPECT_* exist */
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3);
if (err < 0)
u_int8_t u3 = nfmsg->nfgen_family;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp))
return -EINVAL;
err = ctnetlink_change_expect(exp, cda);
write_unlock_bh(&nf_conntrack_lock);
- DEBUGP("leaving\n");
-
return err;
}
static void __exit xt_nfqueue_fini(void)
{
- xt_register_targets(xt_nfqueue_target, ARRAY_SIZE(xt_nfqueue_target));
+ xt_unregister_targets(xt_nfqueue_target, ARRAY_SIZE(xt_nfqueue_target));
}
module_init(xt_nfqueue_init);
static void __exit xt_connmark_fini(void)
{
- xt_register_matches(xt_connmark_match, ARRAY_SIZE(xt_connmark_match));
+ xt_unregister_matches(xt_connmark_match, ARRAY_SIZE(xt_connmark_match));
}
module_init(xt_connmark_init);
int netlbl_cache_add(const struct sk_buff *skb,
const struct netlbl_lsm_secattr *secattr)
{
- if (secattr->cache.data == NULL)
+ if (secattr->cache == NULL)
return -ENOMSG;
if (CIPSO_V4_OPTEXIST(skb))
for (i = 0; i < 500; i++) {
struct htb_class *cl;
long diff;
- struct rb_node *p = q->wait_pq[level].rb_node;
+ struct rb_node *p = rb_first(&q->wait_pq[level]);
+
if (!p)
return 0;
- while (p->rb_left)
- p = p->rb_left;
cl = rb_entry(p, struct htb_class, pq_node);
if (time_after(cl->pq_key, q->jiffies)) {
assoc, sk, sctp_sk(sk)->type, sk->sk_state,
assoc->state, hash, assoc->assoc_id,
assoc->sndbuf_used,
- (sk->sk_rcvbuf - assoc->rwnd),
+ atomic_read(&assoc->rmem_alloc),
sock_i_uid(sk), sock_i_ino(sk),
epb->bind_addr.port,
assoc->peer.port);
sctp_association_put(asoc);
}
+/* Do accounting for the receive space on the socket.
+ * Accounting for the association is done in ulpevent.c
+ * We set this as a destructor for the cloned data skbs so that
+ * accounting is done at the correct time.
+ */
+void sctp_sock_rfree(struct sk_buff *skb)
+{
+ struct sock *sk = skb->sk;
+ struct sctp_ulpevent *event = sctp_skb2event(skb);
+
+ atomic_sub(event->rmem_len, &sk->sk_rmem_alloc);
+}
+
+
/* Helper function to wait for space in the sndbuf. */
static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
size_t msg_len)
sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) {
event = sctp_skb2event(skb);
if (event->asoc == assoc) {
- sock_rfree(skb);
+ sctp_sock_rfree(skb);
__skb_unlink(skb, &oldsk->sk_receive_queue);
__skb_queue_tail(&newsk->sk_receive_queue, skb);
- skb_set_owner_r(skb, newsk);
+ sctp_skb_set_owner_r(skb, newsk);
}
}
sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) {
event = sctp_skb2event(skb);
if (event->asoc == assoc) {
- sock_rfree(skb);
+ sctp_sock_rfree(skb);
__skb_unlink(skb, &oldsp->pd_lobby);
__skb_queue_tail(queue, skb);
- skb_set_owner_r(skb, newsk);
+ sctp_skb_set_owner_r(skb, newsk);
}
}
/* Initialize an ULP event from an given skb. */
-SCTP_STATIC void sctp_ulpevent_init(struct sctp_ulpevent *event, int msg_flags)
+SCTP_STATIC void sctp_ulpevent_init(struct sctp_ulpevent *event,
+ int msg_flags,
+ unsigned int len)
{
memset(event, 0, sizeof(struct sctp_ulpevent));
event->msg_flags = msg_flags;
+ event->rmem_len = len;
}
/* Create a new sctp_ulpevent. */
goto fail;
event = sctp_skb2event(skb);
- sctp_ulpevent_init(event, msg_flags);
+ sctp_ulpevent_init(event, msg_flags, skb->truesize);
return event;
sctp_association_hold((struct sctp_association *)asoc);
skb = sctp_event2skb(event);
event->asoc = (struct sctp_association *)asoc;
- atomic_add(skb->truesize, &event->asoc->rmem_alloc);
- skb_set_owner_r(skb, asoc->base.sk);
+ atomic_add(event->rmem_len, &event->asoc->rmem_alloc);
+ sctp_skb_set_owner_r(skb, asoc->base.sk);
}
/* A simple destructor to give up the reference to the association. */
static inline void sctp_ulpevent_release_owner(struct sctp_ulpevent *event)
{
struct sctp_association *asoc = event->asoc;
- struct sk_buff *skb = sctp_event2skb(event);
- atomic_sub(skb->truesize, &asoc->rmem_alloc);
+ atomic_sub(event->rmem_len, &asoc->rmem_alloc);
sctp_association_put(asoc);
}
/* Embed the event fields inside the cloned skb. */
event = sctp_skb2event(skb);
- sctp_ulpevent_init(event, MSG_NOTIFICATION);
+ sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize);
sre = (struct sctp_remote_error *)
skb_push(skb, sizeof(struct sctp_remote_error));
/* Embed the event fields inside the cloned skb. */
event = sctp_skb2event(skb);
- sctp_ulpevent_init(event, MSG_NOTIFICATION);
+ sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize);
ssf = (struct sctp_send_failed *)
skb_push(skb, sizeof(struct sctp_send_failed));
/* Embed the event fields inside the cloned skb. */
event = sctp_skb2event(skb);
- /* Initialize event with flags 0. */
- sctp_ulpevent_init(event, 0);
+ /* Initialize event with flags 0 and correct length
+ * Since this is a clone of the original skb, only account for
+ * the data of this chunk as other chunks will be accounted separately.
+ */
+ sctp_ulpevent_init(event, 0, skb->len + sizeof(struct sk_buff));
sctp_ulpevent_receive_data(event, asoc);
if (!new)
return NULL; /* try again later */
- new->sk = f_frag->sk;
+ sctp_skb_set_owner_r(new, f_frag->sk);
skb_shinfo(new)->frag_list = pos;
} else
*statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
/* Encode reply */
+ if (*statp == rpc_drop_reply) {
+ if (procp->pc_release)
+ procp->pc_release(rqstp, NULL, rqstp->rq_resp);
+ goto dropit;
+ }
if (*statp == rpc_success && (xdr = procp->pc_encode)
&& !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) {
dprintk("svc: failed to encode reply\n");
}
EXPORT_SYMBOL(xfrm_policy_walk);
-/* Find policy to apply to this flow. */
-
+/*
+ * Find policy to apply to this flow.
+ *
+ * Returns 0 if policy found, else an -errno.
+ */
static int xfrm_policy_match(struct xfrm_policy *pol, struct flowi *fl,
u8 type, u16 family, int dir)
{
struct xfrm_selector *sel = &pol->selector;
- int match;
+ int match, ret = -ESRCH;
if (pol->family != family ||
pol->type != type)
- return 0;
+ return ret;
match = xfrm_selector_match(sel, fl, family);
- if (match) {
- if (!security_xfrm_policy_lookup(pol, fl->secid, dir))
- return 1;
- }
+ if (match)
+ ret = security_xfrm_policy_lookup(pol, fl->secid, dir);
- return 0;
+ return ret;
}
static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl,
u16 family, u8 dir)
{
+ int err;
struct xfrm_policy *pol, *ret;
xfrm_address_t *daddr, *saddr;
struct hlist_node *entry;
chain = policy_hash_direct(daddr, saddr, family, dir);
ret = NULL;
hlist_for_each_entry(pol, entry, chain, bydst) {
- if (xfrm_policy_match(pol, fl, type, family, dir)) {
+ err = xfrm_policy_match(pol, fl, type, family, dir);
+ if (err) {
+ if (err == -ESRCH)
+ continue;
+ else {
+ ret = ERR_PTR(err);
+ goto fail;
+ }
+ } else {
ret = pol;
priority = ret->priority;
break;
}
chain = &xfrm_policy_inexact[dir];
hlist_for_each_entry(pol, entry, chain, bydst) {
- if (xfrm_policy_match(pol, fl, type, family, dir) &&
- pol->priority < priority) {
+ err = xfrm_policy_match(pol, fl, type, family, dir);
+ if (err) {
+ if (err == -ESRCH)
+ continue;
+ else {
+ ret = ERR_PTR(err);
+ goto fail;
+ }
+ } else if (pol->priority < priority) {
ret = pol;
break;
}
}
if (ret)
xfrm_pol_hold(ret);
+fail:
read_unlock_bh(&xfrm_policy_lock);
return ret;
}
-static void xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir,
+static int xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir,
void **objp, atomic_t **obj_refp)
{
struct xfrm_policy *pol;
+ int err = 0;
#ifdef CONFIG_XFRM_SUB_POLICY
pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_SUB, fl, family, dir);
- if (pol)
+ if (IS_ERR(pol)) {
+ err = PTR_ERR(pol);
+ pol = NULL;
+ }
+ if (pol || err)
goto end;
#endif
pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, fl, family, dir);
-
+ if (IS_ERR(pol)) {
+ err = PTR_ERR(pol);
+ pol = NULL;
+ }
#ifdef CONFIG_XFRM_SUB_POLICY
end:
#endif
if ((*objp = (void *) pol) != NULL)
*obj_refp = &pol->refcnt;
+ return err;
}
static inline int policy_to_flow_dir(int dir)
sk->sk_family);
int err = 0;
- if (match)
- err = security_xfrm_policy_lookup(pol, fl->secid, policy_to_flow_dir(dir));
-
- if (match && !err)
- xfrm_pol_hold(pol);
- else
+ if (match) {
+ err = security_xfrm_policy_lookup(pol, fl->secid,
+ policy_to_flow_dir(dir));
+ if (!err)
+ xfrm_pol_hold(pol);
+ else if (err == -ESRCH)
+ pol = NULL;
+ else
+ pol = ERR_PTR(err);
+ } else
pol = NULL;
}
read_unlock_bh(&xfrm_policy_lock);
pol_dead = 0;
xfrm_nr = 0;
- if (sk && sk->sk_policy[1])
+ if (sk && sk->sk_policy[1]) {
policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl);
+ if (IS_ERR(policy))
+ return PTR_ERR(policy);
+ }
if (!policy) {
/* To accelerate a bit... */
policy = flow_cache_lookup(fl, dst_orig->ops->family,
dir, xfrm_policy_lookup);
+ if (IS_ERR(policy))
+ return PTR_ERR(policy);
}
if (!policy)
fl, family,
XFRM_POLICY_OUT);
if (pols[1]) {
+ if (IS_ERR(pols[1])) {
+ err = PTR_ERR(pols[1]);
+ goto error;
+ }
if (pols[1]->action == XFRM_POLICY_BLOCK) {
err = -EPERM;
goto error;
}
pol = NULL;
- if (sk && sk->sk_policy[dir])
+ if (sk && sk->sk_policy[dir]) {
pol = xfrm_sk_policy_lookup(sk, dir, &fl);
+ if (IS_ERR(pol))
+ return 0;
+ }
if (!pol)
pol = flow_cache_lookup(&fl, family, fl_dir,
xfrm_policy_lookup);
+ if (IS_ERR(pol))
+ return 0;
+
if (!pol) {
if (skb->sp && secpath_has_nontransport(skb->sp, 0, &xerr_idx)) {
xfrm_secpath_reject(xerr_idx, skb, &fl);
&fl, family,
XFRM_POLICY_IN);
if (pols[1]) {
+ if (IS_ERR(pols[1]))
+ return 0;
pols[1]->curlft.use_time = (unsigned long)xtime.tv_sec;
npols ++;
}
static int stale_bundle(struct dst_entry *dst)
{
- return !xfrm_bundle_ok((struct xfrm_dst *)dst, NULL, AF_UNSPEC, 0);
+ return !xfrm_bundle_ok(NULL, (struct xfrm_dst *)dst, NULL, AF_UNSPEC, 0);
}
void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
* still valid.
*/
-int xfrm_bundle_ok(struct xfrm_dst *first, struct flowi *fl, int family, int strict)
+int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first,
+ struct flowi *fl, int family, int strict)
{
struct dst_entry *dst = &first->u.dst;
struct xfrm_dst *last;
if (fl && !xfrm_selector_match(&dst->xfrm->sel, fl, family))
return 0;
- if (fl && !security_xfrm_flow_state_match(fl, dst->xfrm))
+ if (fl && !security_xfrm_flow_state_match(fl, dst->xfrm, pol))
return 0;
if (dst->xfrm->km.state != XFRM_STATE_VALID)
return 0;
return x;
}
+static void xfrm_hash_grow_check(int have_hash_collision)
+{
+ if (have_hash_collision &&
+ (xfrm_state_hmask + 1) < xfrm_state_hashmax &&
+ xfrm_state_num > xfrm_state_hmask)
+ schedule_work(&xfrm_hash_work);
+}
+
static void __xfrm_state_insert(struct xfrm_state *x)
{
unsigned int h;
xfrm_state_num++;
- if (x->bydst.next != NULL &&
- (xfrm_state_hmask + 1) < xfrm_state_hashmax &&
- xfrm_state_num > xfrm_state_hmask)
- schedule_work(&xfrm_hash_work);
+ xfrm_hash_grow_check(x->bydst.next != NULL);
}
/* xfrm_state_lock is held */
h = xfrm_src_hash(daddr, saddr, family);
hlist_add_head(&x->bysrc, xfrm_state_bysrc+h);
wake_up(&km_waitq);
+
+ xfrm_state_num++;
+
+ xfrm_hash_grow_check(x->bydst.next != NULL);
}
return x;
xp->type = XFRM_POLICY_TYPE_MAIN;
copy_templates(xp, ut, nr);
- if (!xp->security) {
- int err = security_xfrm_sock_policy_alloc(xp, sk);
- if (err) {
- kfree(xp);
- *dir = err;
- return NULL;
- }
- }
-
*dir = p->dir;
return xp;
$(call cmd,gen)
else
-$(objhdr-y) : $(INSTALL_HDR_PATH)/$(_dst)/%.h: $(srctree)/$(obj)/%.h $(KBUILDFILES)
+$(objhdr-y) : $(INSTALL_HDR_PATH)/$(_dst)/%.h: $(objtree)/$(obj)/%.h $(KBUILDFILES)
$(call cmd,o_hdr_install)
$(header-y) : $(INSTALL_HDR_PATH)/$(_dst)/%.h: $(srctree)/$(obj)/%.h $(KBUILDFILES)
include scripts/Makefile.lib
kernelsymfile := $(objtree)/Module.symvers
-modulesymfile := $(KBUILD_EXTMOD)/Module.symvers
+modulesymfile := $(firstword $(KBUILD_EXTMOD))/Module.symvers
# Step 1), find all modules listed in $(MODVERDIR)/
__modules := $(sort $(shell grep -h '\.ko' /dev/null $(wildcard $(MODVERDIR)/*.mod)))
#include <ctype.h>
#include <stdlib.h>
#include <string.h>
+#include <stdbool.h>
#ifdef __sun__
#define CURS_MACROS
}
##
-# generic output function for typedefs
+# generic output function for all types (function, struct/union, typedef, enum);
+# calls the generated, variable output_ function name based on
+# functype and output_mode
sub output_declaration {
no strict 'refs';
my $name = shift;
}
##
-# generic output function - calls the right one based
-# on current output mode.
+# generic output function - calls the right one based on current output mode.
sub output_intro {
no strict 'refs';
my $func = "output_intro_".$output_mode;
$prototype =~ s/^asmlinkage +//;
$prototype =~ s/^inline +//;
$prototype =~ s/^__inline__ +//;
+ $prototype =~ s/^__inline +//;
+ $prototype =~ s/^__always_inline +//;
+ $prototype =~ s/^noinline +//;
$prototype =~ s/__devinit +//;
$prototype =~ s/^#define +//; #ak added
$prototype =~ s/__attribute__ \(\([a-z,]*\)\)//;
$in_doc_sect = 1;
$contents = $newcontents;
if ($contents ne "") {
- if (substr($contents, 0, 1) eq " ") {
- $contents = substr($contents, 1);
+ while ((substr($contents, 0, 1) eq " ") ||
+ substr($contents, 0, 1) eq "\t") {
+ $contents = substr($contents, 1);
}
$contents .= "\n";
}
return 1;
}
-static int dummy_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm)
+static int dummy_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm,
+ struct xfrm_policy *xp)
{
return 1;
}
int selinux_xfrm_policy_lookup(struct xfrm_policy *xp, u32 fl_secid, u8 dir);
int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
struct xfrm_policy *xp, struct flowi *fl);
-int selinux_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm);
+int selinux_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm,
+ struct xfrm_policy *xp);
/*
size_t bitmap_byte;
unsigned char bitmask;
+ if (src->highbit == 0) {
+ *dst = NULL;
+ *dst_len = 0;
+ return 0;
+ }
+
bitmap_len = src->highbit / 8;
if (src->highbit % 7)
bitmap_len += 1;
- if (bitmap_len == 0)
- return -EINVAL;
bitmap = kzalloc((bitmap_len & ~(sizeof(MAPTYPE) - 1)) +
sizeof(MAPTYPE),
{
int rc = -EPERM;
- if (!selinux_mls_enabled)
+ if (!selinux_mls_enabled) {
+ *low = NULL;
+ *low_len = 0;
+ *high = NULL;
+ *high_len = 0;
return 0;
+ }
if (low != NULL) {
rc = ebitmap_export(&context->range.level[0].cat,
return 0;
export_cat_failure:
- if (low != NULL)
+ if (low != NULL) {
kfree(*low);
- if (high != NULL)
+ *low = NULL;
+ *low_len = 0;
+ }
+ if (high != NULL) {
kfree(*high);
+ *high = NULL;
+ *high_len = 0;
+ }
return rc;
}
c = c->next;
ocontext_destroy(ctmp,i);
}
+ p->ocontexts[i] = NULL;
}
g = p->genfs;
g = g->next;
kfree(gtmp);
}
+ p->genfs = NULL;
cond_policydb_destroy(p);
*/
static void selinux_netlbl_cache_free(const void *data)
{
- struct netlbl_cache *cache = NETLBL_CACHE(data);
+ struct netlbl_cache *cache;
+
+ if (data == NULL)
+ return;
+
+ cache = NETLBL_CACHE(data);
switch (cache->type) {
case NETLBL_CACHE_T_MLS:
ebitmap_destroy(&cache->data.mls_label.level[0].cat);
struct netlbl_lsm_secattr secattr;
netlbl_secattr_init(&secattr);
+ secattr.cache = netlbl_secattr_cache_alloc(GFP_ATOMIC);
+ if (secattr.cache == NULL)
+ goto netlbl_cache_add_return;
cache = kzalloc(sizeof(*cache), GFP_ATOMIC);
if (cache == NULL)
- goto netlbl_cache_add_failure;
- secattr.cache.free = selinux_netlbl_cache_free;
- secattr.cache.data = (void *)cache;
+ goto netlbl_cache_add_return;
+ secattr.cache->free = selinux_netlbl_cache_free;
+ secattr.cache->data = (void *)cache;
cache->type = NETLBL_CACHE_T_MLS;
if (ebitmap_cpy(&cache->data.mls_label.level[0].cat,
&ctx->range.level[0].cat) != 0)
- goto netlbl_cache_add_failure;
+ goto netlbl_cache_add_return;
cache->data.mls_label.level[1].cat.highbit =
cache->data.mls_label.level[0].cat.highbit;
cache->data.mls_label.level[1].cat.node =
cache->data.mls_label.level[0].sens = ctx->range.level[0].sens;
cache->data.mls_label.level[1].sens = ctx->range.level[0].sens;
- if (netlbl_cache_add(skb, &secattr) != 0)
- goto netlbl_cache_add_failure;
-
- return;
+ netlbl_cache_add(skb, &secattr);
-netlbl_cache_add_failure:
- netlbl_secattr_destroy(&secattr, 1);
+netlbl_cache_add_return:
+ netlbl_secattr_destroy(&secattr);
}
/**
POLICY_RDLOCK;
- if (secattr->cache.data) {
- cache = NETLBL_CACHE(secattr->cache.data);
+ if (secattr->cache) {
+ cache = NETLBL_CACHE(secattr->cache->data);
switch (cache->type) {
case NETLBL_CACHE_T_SID:
*sid = cache->data.sid;
selinux_netlbl_cache_add(skb, &ctx_new);
ebitmap_destroy(&ctx_new.range.level[0].cat);
} else {
- *sid = SECINITSID_UNLABELED;
+ *sid = SECSID_NULL;
rc = 0;
}
&secattr,
base_sid,
sid);
- netlbl_secattr_destroy(&secattr, 0);
+ netlbl_secattr_destroy(&secattr);
return rc;
}
if (!ss_initialized)
return 0;
+ netlbl_secattr_init(&secattr);
+
POLICY_RDLOCK;
ctx = sidtab_search(&sidtab, sid);
if (ctx == NULL)
goto netlbl_socket_setsid_return;
- netlbl_secattr_init(&secattr);
secattr.domain = kstrdup(policydb.p_type_val_to_name[ctx->type - 1],
GFP_ATOMIC);
mls_export_lvl(ctx, &secattr.mls_lvl, NULL);
secattr.mls_lvl_vld = 1;
- mls_export_cat(ctx,
- &secattr.mls_cat,
- &secattr.mls_cat_len,
- NULL,
- NULL);
+ rc = mls_export_cat(ctx,
+ &secattr.mls_cat,
+ &secattr.mls_cat_len,
+ NULL,
+ NULL);
+ if (rc != 0)
+ goto netlbl_socket_setsid_return;
rc = netlbl_socket_setattr(sock, &secattr);
if (rc == 0)
sksec->nlbl_state = NLBL_LABELED;
- netlbl_secattr_destroy(&secattr, 0);
-
netlbl_socket_setsid_return:
POLICY_RDUNLOCK;
+ netlbl_secattr_destroy(&secattr);
return rc;
}
if (netlbl_sock_getattr(sk, &secattr) == 0 &&
selinux_netlbl_secattr_to_sid(NULL,
&secattr,
- sksec->sid,
+ SECINITSID_UNLABELED,
&nlbl_peer_sid) == 0)
sksec->peer_sid = nlbl_peer_sid;
- netlbl_secattr_destroy(&secattr, 0);
+ netlbl_secattr_destroy(&secattr);
sksec->nlbl_state = NLBL_REQUIRE;
if (rc != 0)
return SECSID_NULL;
- if (peer_sid == SECINITSID_UNLABELED)
- return SECSID_NULL;
-
return peer_sid;
}
u32 netlbl_sid;
u32 recv_perm;
- rc = selinux_netlbl_skbuff_getsid(skb, SECINITSID_NETMSG, &netlbl_sid);
+ rc = selinux_netlbl_skbuff_getsid(skb,
+ SECINITSID_UNLABELED,
+ &netlbl_sid);
if (rc != 0)
return rc;
- if (netlbl_sid == SECINITSID_UNLABELED)
+ if (netlbl_sid == SECSID_NULL)
return 0;
switch (sksec->sclass) {
u32 selinux_netlbl_socket_getpeersec_stream(struct socket *sock)
{
struct sk_security_struct *sksec = sock->sk->sk_security;
-
- if (sksec->peer_sid == SECINITSID_UNLABELED)
- return SECSID_NULL;
-
return sksec->peer_sid;
}
u32 selinux_netlbl_socket_getpeersec_dgram(struct sk_buff *skb)
{
int peer_sid;
- struct sock *sk = skb->sk;
- struct inode_security_struct *isec;
- if (sk == NULL || sk->sk_socket == NULL)
- return SECSID_NULL;
-
- isec = SOCK_INODE(sk->sk_socket)->i_security;
- if (selinux_netlbl_skbuff_getsid(skb, isec->sid, &peer_sid) != 0)
- return SECSID_NULL;
- if (peer_sid == SECINITSID_UNLABELED)
+ if (selinux_netlbl_skbuff_getsid(skb,
+ SECINITSID_UNLABELED,
+ &peer_sid) != 0)
return SECSID_NULL;
return peer_sid;
*/
int selinux_xfrm_policy_lookup(struct xfrm_policy *xp, u32 fl_secid, u8 dir)
{
- int rc = 0;
- u32 sel_sid = SECINITSID_UNLABELED;
+ int rc;
+ u32 sel_sid;
struct xfrm_sec_ctx *ctx;
/* Context sid is either set to label or ANY_ASSOC */
sel_sid = ctx->ctx_sid;
}
+ else
+ /*
+ * All flows should be treated as polmatch'ing an
+ * otherwise applicable "non-labeled" policy. This
+ * would prevent inadvertent "leaks".
+ */
+ return 0;
rc = avc_has_perm(fl_secid, sel_sid, SECCLASS_ASSOCIATION,
ASSOCIATION__POLMATCH,
NULL);
+ if (rc == -EACCES)
+ rc = -ESRCH;
+
return rc;
}
u32 pol_sid;
int err;
- if (x->security)
- state_sid = x->security->ctx_sid;
- else
- state_sid = SECINITSID_UNLABELED;
-
- if (xp->security)
+ if (xp->security) {
+ if (!x->security)
+ /* unlabeled SA and labeled policy can't match */
+ return 0;
+ else
+ state_sid = x->security->ctx_sid;
pol_sid = xp->security->ctx_sid;
- else
- pol_sid = SECINITSID_UNLABELED;
+ } else
+ if (x->security)
+ /* unlabeled policy and labeled SA can't match */
+ return 0;
+ else
+ /* unlabeled policy and unlabeled SA match all flows */
+ return 1;
err = avc_has_perm(state_sid, pol_sid, SECCLASS_ASSOCIATION,
ASSOCIATION__POLMATCH,
if (err)
return 0;
- return selinux_xfrm_flow_state_match(fl, x);
+ err = avc_has_perm(fl->secid, state_sid, SECCLASS_ASSOCIATION,
+ ASSOCIATION__SENDTO,
+ NULL)? 0:1;
+
+ return err;
}
/*
* can use a given security association.
*/
-int selinux_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm)
+int selinux_xfrm_flow_state_match(struct flowi *fl, struct xfrm_state *xfrm,
+ struct xfrm_policy *xp)
{
int rc = 0;
u32 sel_sid = SECINITSID_UNLABELED;
struct xfrm_sec_ctx *ctx;
+ if (!xp->security)
+ if (!xfrm->security)
+ return 1;
+ else
+ return 0;
+ else
+ if (!xfrm->security)
+ return 0;
+
/* Context sid is either set to label or ANY_ASSOC */
if ((ctx = xfrm->security)) {
if (!selinux_authorizable_ctx(ctx))
projects / linux-2.6-block.git / commitdiff