summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2009-04-05Audit: remove spaces from audit_log_d_pathEric Paris2-3/+3
audit_log_d_path had spaces in the strings which would be emitted on the error paths. This patch simply replaces those spaces with an _ or removes the needless spaces entirely. Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-05audit: audit_set_auditable defined but not usedEric Paris1-8/+8
after 0590b9335a1c72a3f0defcc6231287f7817e07c8 audit_set_auditable() is now only used by the audit tree code. If CONFIG_AUDIT_TREE is unset it will be defined but unused. This patch simply moves the function inside a CONFIG_AUDIT_TREE block. cc1: warnings being treated as errors /home/acme_unencrypted/git/linux-2.6-tip/kernel/auditsc.c:745: error: ‘audit_set_auditable’ defined but not used make[2]: *** [kernel/auditsc.o] Error 1 make[1]: *** [kernel] Error 2 make[1]: *** Waiting for unfinished jobs.... Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-05audit: incorrect ref counting in audit tree tag_chunkEric Paris1-0/+2
tag_chunk has bad exit paths in which the inotify ref counting is wrong. At the top of the function we found &old_watch using inotify_find_watch(). inotify_find_watch takes a reference to the watch. This is never dropped on an error path. Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-05audit: Fix possible return value truncation in audit_get_context()Paul Moore1-1/+1
The audit subsystem treats syscall return codes as type long, unfortunately the audit_get_context() function mistakenly converts the return code to an int type in the parameters which could cause problems on systems where the sizeof(int) != sizeof(long). Signed-off-by: Paul Moore <paul.moore@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-05audit: ignore terminating NUL in AUDIT_USER_TTY messagesMiloslav Trmac1-0/+3
AUDIT_USER_TTY, like all other messages sent from user-space, is sent NUL-terminated. Unlike other user-space audit messages, which come only from trusted sources, AUDIT_USER_TTY messages are processed using audit_log_n_untrustedstring(). This patch modifies AUDIT_USER_TTY handling to ignore the trailing NUL and use the "quoted_string" representation of the message if possible. Signed-off-by: Miloslav Trmac <mitr@redhat.com> Cc: Eric Paris <eparis@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Steve Grubb <sgrubb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-05Audit: fix handling of 'strings' with NULL charactersMiloslav Trmac1-1/+1
currently audit_log_n_untrustedstring() uses audit_string_contains_control() to check if the 'string' has any control characters. If the 'string' has an embedded NULL audit_string_contains_control() will return that the data has no control characters and will then pass the string to audit_log_n_string with the total length, not the length up to the first NULL. audit_log_n_string() does a memcpy of the entire length and so the actual audit record emitted may then contain a NULL and then whatever random memory is after the NULL. Since we want to log the entire octet stream (if we can't trust the data to be a string we can't trust that a NULL isn't actually a part of it) we should just consider NULL as a control character. If the caller is certain they want to stop at the first NULL they should be using audit_log_untrustedstring. Signed-off-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-05make the e->rule.xxx shorter in kernel auditfilter.cZhenwen Xu1-8/+8
make the e->rule.xxx shorter in kernel/auditfilter.c -- --------------------------------- Zhenwen Xu - Open and Free Home Page: http://zhwen.org My Studio: http://dim4.cn >From 99692dc640b278f1cb1a15646ce42f22e89c0f77 Mon Sep 17 00:00:00 2001 From: Zhenwen Xu <Helight.Xu@gmail.com> Date: Thu, 12 Mar 2009 22:04:59 +0800 Subject: [PATCH] make the e->rule.xxx shorter in kernel/auditfilter.c Signed-off-by: Zhenwen Xu <Helight.Xu@gmail.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-05auditsc: fix kernel-doc notationRandy Dunlap1-2/+2
Fix auditsc kernel-doc notation: Warning(linux-2.6.28-git7//kernel/auditsc.c:2156): No description found for parameter 'attr' Warning(linux-2.6.28-git7//kernel/auditsc.c:2156): Excess function parameter 'u_attr' description in '__audit_mq_open' Warning(linux-2.6.28-git7//kernel/auditsc.c:2204): No description found for parameter 'notification' Warning(linux-2.6.28-git7//kernel/auditsc.c:2204): Excess function parameter 'u_notification' description in '__audit_mq_notify' Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> cc: Al Viro <viro@zeniv.linux.org.uk> cc: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-05audit: EXECVE record - removed bogus newlineJiri Pirko1-5/+4
(updated) Added hunk that changes the comment, the rest is the same. EXECVE records contain a newline after every argument. auditd converts "\n" to " " so you cannot see newlines even in raw logs, but they're there nevertheless. If you're not using auditd, you need to work round them. These '\n' chars are can be easily replaced by spaces when creating record in kernel. Note there is no need for trailing '\n' in an audit record. record before this patch: "type=EXECVE msg=audit(1231421801.566:31): argc=4 a0=\"./test\"\na1=\"a\"\na2=\"b\"\na3=\"c\"\n" record after this patch: "type=EXECVE msg=audit(1231421801.566:31): argc=4 a0=\"./test\" a1=\"a\" a2=\"b\" a3=\"c\"" Signed-off-by: Jiri Pirko <jpirko@redhat.com> Acked-by: Eric Paris <eparis@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-04-03Merge branch 'x86-fixes-for-linus' of ↵Linus Torvalds10-81/+43
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86, mtrr: remove debug message x86: disable stack-protector for __restore_processor_state() x86: fix is_io_mapping_possible() build warning on i386 allnoconfig x86, setup: compile with -DDISABLE_BRANCH_PROFILING x86/dma: unify definition of pci_unmap_addr* and pci_unmap_len macros x86, mm: fix misuse of debug_kmap_atomic x86: remove duplicated code with pcpu_need_numa() x86,percpu: fix inverted NUMA test in setup_pcpu_remap() x86: signal: check sas_ss_size instead of sas_ss_flags()
2009-04-03Merge branch 'core-cleanups-for-linus' of ↵Linus Torvalds1-2/+0
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'core-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: ptrace: remove a useless goto
2009-04-03Merge branch 'stacktrace-for-linus' of ↵Linus Torvalds1-3/+22
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'stacktrace-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: symbols, stacktrace: look up init symbols after module symbols
2009-04-03Merge branch 'rcu-for-linus' of ↵Linus Torvalds1-0/+44
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: rcu: rcu_barrier VS cpu_hotplug: Ensure callbacks in dead cpu are migrated to online cpu
2009-04-03Merge branch 'ipi-for-linus' of ↵Linus Torvalds7-262/+304
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'ipi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: s390: remove arch specific smp_send_stop() panic: clean up kernel/panic.c panic, smp: provide smp_send_stop() wrapper on UP too panic: decrease oops_in_progress only after having done the panic generic-ipi: eliminate WARN_ON()s during oops/panic generic-ipi: cleanups generic-ipi: remove CSD_FLAG_WAIT generic-ipi: remove kmalloc() generic IPI: simplify barriers and locking
2009-04-03Merge branch 'locking-for-linus' of ↵Linus Torvalds4-19/+13
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: locking: rename trace_softirq_[enter|exit] => lockdep_softirq_[enter|exit] lockdep: remove duplicate CONFIG_DEBUG_LOCKDEP definitions lockdep: require framepointers for x86 lockdep: remove extra "irq" string lockdep: fix incorrect state name
2009-04-04x86, mtrr: remove debug messageIngo Molnar1-3/+0
The MTRR code grew a new debug message which triggers commonly: [ 40.142276] get_mtrr: cpu0 reg00 base=0000000000 size=0000080000 write-back [ 40.142280] get_mtrr: cpu0 reg01 base=0000080000 size=0000040000 write-back [ 40.142284] get_mtrr: cpu0 reg02 base=0000100000 size=0000040000 write-back [ 40.142311] get_mtrr: cpu0 reg00 base=0000000000 size=0000080000 write-back [ 40.142314] get_mtrr: cpu0 reg01 base=0000080000 size=0000040000 write-back [ 40.142317] get_mtrr: cpu0 reg02 base=0000100000 size=0000040000 write-back Remove this annoyance. Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-03Merge branch 'for-linus' of ↵Linus Torvalds2-13/+42
git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse: fuse: allow private mappings of "direct_io" files fuse: allow kernel to access "direct_io" files
2009-04-03LANANA: Change of management and resyncAlan Cox1-63/+58
Bring the devices.txt back into some relationship with reality. Update the documentation a bit. Signed-off-by: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03Merge branch 'for-linus' of ↵Linus Torvalds35-315/+851
git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid: HID: remove compat stuff HID: constify arrays of struct apple_key_translation HID: add support for Kye/Genius Ergo 525V HID: Support Apple mini aluminum keyboard HID: support for Kensington slimblade device HID: DragonRise game controller force feedback driver HID: add support for another version of 0e8f:0003 device in hid-pl HID: fix race between usb_register_dev() and hiddev_open() HID: bring back possibility to specify vid/pid ignore on module load HID: make HID_DEBUG defaults consistent HID: autosuspend -- fix lockup of hid on reset HID: hid_reset_resume() needs to be defined only when CONFIG_PM is set HID: fix USB HID devices after STD with autosuspend HID: do not try to compile PM code with CONFIG_PM unset HID: autosuspend support for USB HID
2009-04-03Merge branch 'for-linus' of ↵Linus Torvalds109-177/+226
git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (28 commits) trivial: Update my email address trivial: NULL noise: drivers/mtd/tests/mtd_*test.c trivial: NULL noise: drivers/media/dvb/frontends/drx397xD_fw.h trivial: Fix misspelling of "Celsius". trivial: remove unused variable 'path' in alloc_file() trivial: fix a pdlfush -> pdflush typo in comment trivial: jbd header comment typo fix for JBD_PARANOID_IOFAIL trivial: wusb: Storage class should be before const qualifier trivial: drivers/char/bsr.c: Storage class should be before const qualifier trivial: h8300: Storage class should be before const qualifier trivial: fix where cgroup documentation is not correctly referred to trivial: Give the right path in Documentation example trivial: MTD: remove EOL from MODULE_DESCRIPTION trivial: Fix typo in bio_split()'s documentation trivial: PWM: fix of #endif comment trivial: fix typos/grammar errors in Kconfig texts trivial: Fix misspelling of firmware trivial: cgroups: documentation typo and spelling corrections trivial: Update contact info for Jochen Hein trivial: fix typo "resgister" -> "register" ...
2009-04-03Merge git://git.kernel.org/pub/scm/linux/kernel/git/czankel/xtensa-2.6Linus Torvalds45-306/+2466
* git://git.kernel.org/pub/scm/linux/kernel/git/czankel/xtensa-2.6: (21 commits) xtensa: we don't need to include asm/io.h xtensa: only build platform or variant if they contain a Makefile xtensa: make startup code discardable xtensa: ccount clocksource xtensa: remove platform rtc hooks xtensa: use generic sched_clock() xtensa: platform: s6105 xtensa: let platform override KERNELOFFSET xtensa: s6000 variant xtensa: s6000 variant core definitions xtensa: variant irq set callbacks xtensa: variant-specific code xtensa: nommu support xtensa: add flat support xtensa: enforce slab alignment to maximum register width xtensa: cope with ram beginning at higher addresses xtensa: don't make bootmem bitmap larger than required xtensa: fix init_bootmem_node() argument order xtensa: use correct stack pointer for stack traces xtensa: beat Kconfig into shape ...
2009-04-03Merge git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstableLinus Torvalds17-544/+982
* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: Btrfs: BUG to BUG_ON changes Btrfs: remove dead code Btrfs: remove dead code Btrfs: fix typos in comments Btrfs: remove unused ftrace include Btrfs: fix __ucmpdi2 compile bug on 32 bit builds Btrfs: free inode struct when btrfs_new_inode fails Btrfs: fix race in worker_loop Btrfs: add flushoncommit mount option Btrfs: notreelog mount option Btrfs: introduce btrfs_show_options Btrfs: rework allocation clustering Btrfs: Optimize locking in btrfs_next_leaf() Btrfs: break up btrfs_search_slot into smaller pieces Btrfs: kill the pinned_mutex Btrfs: kill the block group alloc mutex Btrfs: clean up find_free_extent Btrfs: free space cache cleanups Btrfs: unplug in the async bio submission threads Btrfs: keep processing bios for a given bdev if our proc is batching
2009-04-03x86, PAT: Remove duplicate memtype reserve in pci mmapSuresh Siddha1-46/+0
pci mmap code was doing memtype reserve for a while now. Recently we added memtype tracking in remap_pfn_range, and pci code indirectly calls remap_pfn_range. So, we don't need seperate tracking in pci code anymore. Which means a patch that removes ~50 lines of code :-). Also, recently we found out that the pci tracking is not working as we expect it to work in some cases. Specifically, userlevel X mmap of pci, with some recent version of X, is having a problem with vm_page_prot getting reset. The pci tracking uses vm_page_prot to pass on the protection type from parent to child during fork. a) Parent does a pci mmap b) We look at PAT and get either UC_MINUS or WC mapping for parent c) Store that mapping type in vma vm_page_prot for future use d) This thread does a fork e) Fork results in mmap_ops ->open for the child process f) We get the vm_page_prot from vma and reserve that type for the child process But, between c) and e) above, the vma vm_page_prot is getting reset to zero. This results in PAT reserve failing at the time of fork as in here. http://marc.info/?l=linux-kernel&m=123858163103240&w=2 This cleanup makes the above problem go away as we do not depend on vm_page_prot in our PAT code anymore. Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03Merge branch 'upstream-linus' of ↵Linus Torvalds30-689/+4389
git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2 * 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2: (32 commits) ocfs2: recover orphans in offline slots during recovery and mount ocfs2: Pagecache usage optimization on ocfs2 ocfs2: fix rare stale inode errors when exporting via nfs ocfs2/dlm: Tweak mle_state output ocfs2/dlm: Do not purge lockres that is being migrated dlm_purge_lockres() ocfs2/dlm: Remove struct dlm_lock_name in struct dlm_master_list_entry ocfs2/dlm: Show the number of lockres/mles in dlm_state ocfs2/dlm: dlm_set_lockres_owner() and dlm_change_lockres_owner() inlined ocfs2/dlm: Improve lockres counts ocfs2/dlm: Track number of mles ocfs2/dlm: Indent dlm_cleanup_master_list() ocfs2/dlm: Activate dlm->master_hash for master list entries ocfs2/dlm: Create and destroy the dlm->master_hash ocfs2/dlm: Refactor dlm_clean_master_list() ocfs2/dlm: Clean up struct dlm_lock_name ocfs2/dlm: Encapsulate adding and removing of mle from dlm->master_list ocfs2: Optimize inode group allocation by recording last used group. ocfs2: Allocate inode groups from global_bitmap. ocfs2: Optimize inode allocation by remembering last group ocfs2: fix leaf start calculation in ocfs2_dx_dir_rebalance() ...
2009-04-03Merge branch 'next' of ↵Linus Torvalds16-241/+925
git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx * 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx: dma: Add SoF and EoF debugging to ipu_idmac.c, minor cleanup dw_dmac: add cyclic API to DW DMA driver dmaengine: Add privatecnt to revert DMA_PRIVATE property dmatest: add dma interrupts and callbacks dmatest: add xor test dmaengine: allow dma support for async_tx to be toggled async_tx: provide __async_inline for HAS_DMA=n archs dmaengine: kill some unused headers dmaengine: initialize tx_list in dma_async_tx_descriptor_init dma: i.MX31 IPU DMA robustness improvements dma: improve section assignment in i.MX31 IPU DMA driver dma: ipu_idmac driver cosmetic clean-up dmaengine: fail device registration if channel registration fails
2009-04-03ocfs2: recover orphans in offline slots during recovery and mountSrinivas Eeda4-18/+132
During recovery, a node recovers orphans in it's slot and the dead node(s). But if the dead nodes were holding orphans in offline slots, they will be left unrecovered. If the dead node is the last one to die and is holding orphans in other slots and is the first one to mount, then it only recovers it's own slot, which leaves orphans in offline slots. This patch queues complete_recovery to clean orphans for all offline slots during mount and node recovery. Signed-off-by: Srinivas Eeda <srinivas.eeda@oracle.com> Acked-by: Joel Becker <joel.becker@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: Pagecache usage optimization on ocfs2Hisashi Hifumi1-11/+12
A page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate on pagesize != blocksize environment. This aops checks that all buffers which correspond to a part of a file that we want to read are uptodate. If so, we do not have to issue actual read IO to HDD even if a page is not uptodate because the portion we want to read are uptodate. "block_is_partially_uptodate" function is already used by ext2/3/4. With the following patch random read/write mixed workloads or random read after random write workloads can be optimized and we can get performance improvement. Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: fix rare stale inode errors when exporting via nfswengang wang9-8/+319
For nfs exporting, ocfs2_get_dentry() returns the dentry for fh. ocfs2_get_dentry() may read from disk when the inode is not in memory, without any cross cluster lock. this leads to the file system loading a stale inode. This patch fixes above problem. Solution is that in case of inode is not in memory, we get the cluster lock(PR) of alloc inode where the inode in question is allocated from (this causes node on which deletion is done sync the alloc inode) before reading out the inode itsself. then we check the bitmap in the group (the inode in question allcated from) to see if the bit is clear. if it's clear then it's stale. if the bit is set, we then check generation as the existing code does. We have to read out the inode in question from disk first to know its alloc slot and allot bit. And if its not stale we read it out using ocfs2_iget(). The second read should then be from cache. And also we have to add a per superblock nfs_sync_lock to cover the lock for alloc inode and that for inode in question. this is because ocfs2_get_dentry() and ocfs2_delete_inode() lock on them in reverse order. nfs_sync_lock is locked in EX mode in ocfs2_get_dentry() and in PR mode in ocfs2_delete_inode(). so that mutliple ocfs2_delete_inode() can run concurrently in normal case. [mfasheh@suse.com: build warning fixes and comment cleanups] Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com> Acked-by: Joel Becker <joel.becker@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Tweak mle_state outputSunil Mushran1-2/+5
The debugfs file, mle_state, now prints the number of largest number of mles in one hash link. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Do not purge lockres that is being migrated dlm_purge_lockres()Sunil Mushran1-2/+18
This patch attempts to fix a fine race between purging and migration. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Remove struct dlm_lock_name in struct dlm_master_list_entrySunil Mushran3-71/+23
This patch removes struct dlm_lock_name and adds the entries directly to struct dlm_master_list_entry. Under the new scheme, both mles that are backed by a lockres or not, will have the name populated in mle->mname. This allows us to get rid of code that was figuring out the location of the mle name. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Show the number of lockres/mles in dlm_stateSunil Mushran1-0/+36
This patch shows the number of lockres' and mles in the debugfs file, dlm_state. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: dlm_set_lockres_owner() and dlm_change_lockres_owner() inlinedSunil Mushran2-22/+18
This patch inlines dlm_set_lockres_owner() and dlm_change_lockres_owner(). Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Improve lockres countsSunil Mushran4-38/+11
This patch replaces the lockres counts that tracked the number number of locally and remotely mastered lockres' with a current and total count. The total count is the number of lockres' that have been created since the dlm domain was created. The number of locally and remotely mastered counts can be computed using the locking_state output. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Track number of mlesSunil Mushran3-1/+14
The lifetime of a mle is limited to the duration of the lockres mastery process. While typically this lifetime is fairly short, we have noticed the number of mles explode under certain circumstances. This patch tracks the number of each different types of mles and should help us determine how best to speed up the mastery process. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Indent dlm_cleanup_master_list()Sunil Mushran1-54/+52
The previous patch explicitly did not indent dlm_cleanup_master_list() so as to make the patch readable. This patch properly indents the function. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Activate dlm->master_hash for master list entriesSunil Mushran4-30/+60
With this patch, the mles are stored in a hash and not a simple list. This should improve the mle lookup time when the number of outstanding masteries is large. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Create and destroy the dlm->master_hashSunil Mushran2-0/+26
This patch adds code to create and destroy the dlm->master_hash. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Refactor dlm_clean_master_list()Sunil Mushran1-63/+85
This patch refactors dlm_clean_master_list() so as to make it easier to convert the mle list to a hash. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Clean up struct dlm_lock_nameSunil Mushran3-44/+53
For master mle, the name it stored in the attached lockres in struct qstr. For block and migration mle, the name is stored inline in struct dlm_lock_name. This patch attempts to make struct dlm_lock_name look like a struct qstr. While we could use struct qstr, we don't because we want to avoid having to malloc and free the lockname string as the mle's lifetime is fairly short. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2/dlm: Encapsulate adding and removing of mle from dlm->master_listSunil Mushran2-11/+26
This patch encapsulates adding and removing of the mle from the dlm->master_list. This patch is part of the series of patches that converts the mle list to a mle hash. Signed-off-by: Sunil Mushran <sunil.mushran@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: Optimize inode group allocation by recording last used group.Tao Ma2-4/+31
In ocfs2, the block group search looks for the "emptiest" group to allocate from. So if the allocator has many equally(or almost equally) empty groups, new block group will tend to get spread out amongst them. So we add osb_inode_alloc_group in ocfs2_super to record the last used inode allocation group. For more details, please see http://oss.oracle.com/osswiki/OCFS2/DesignDocs/InodeAllocationStrategy. I have done some basic test and the results are a ten times improvement on some cold-cache stat workloads. Signed-off-by: Tao Ma <tao.ma@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: Allocate inode groups from global_bitmap.Tao Ma1-10/+19
Inode groups used to be allocated from local alloc file, but since we want all inodes to be contiguous enough, we will try to allocate them directly from global_bitmap. Signed-off-by: Tao Ma <tao.ma@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: Optimize inode allocation by remembering last groupTao Ma5-2/+46
In ocfs2, the inode block search looks for the "emptiest" inode group to allocate from. So if an inode alloc file has many equally (or almost equally) empty groups, new inodes will tend to get spread out amongst them, which in turn can put them all over the disk. This is undesirable because directory operations on conceptually "nearby" inodes force a large number of seeks. So we add ip_last_used_group in core directory inodes which records the last used allocation group. Another field named ip_last_used_slot is also added in case inode stealing happens. When claiming new inode, we passed in directory's inode so that the allocation can use this information. For more details, please see http://oss.oracle.com/osswiki/OCFS2/DesignDocs/InodeAllocationStrategy. Signed-off-by: Tao Ma <tao.ma@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: fix leaf start calculation in ocfs2_dx_dir_rebalance()Mark Fasheh2-2/+11
ocfs2_dx_dir_rebalance() is passed the block offset of a dx leaf which needs rebalancing. Since we rebalance an entire cluster at a time however, this function needs to calculate the beginning of that cluster, in blocks. The calculation was wrong, which would result in a read of non-leaf blocks. Fix the calculation by adding ocfs2_block_to_cluster_start() which is a more straight-forward way of determining this. Reported-by: Tristan Ye <tristan.ye@oracle.com> Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: re-order ocfs2_empty_dir checksMark Fasheh1-6/+3
ocfs2_empty_dir() is far more expensive than checking link count. Since both need to be checked at the same time, we can improve performance by checking link count first. Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: Enable indexed directoriesMark Fasheh1-1/+2
Since the disk format is finalized, we can set this feature bit in the supported mask. Signed-off-by: Mark Fasheh <mfasheh@suse.com> Acked-by: Joel Becker <Joel.Becker@oracle.com>
2009-04-03ocfs2: Add total entry count to dx_root_blockMark Fasheh2-44/+124
This little bit of extra accounting speeds up ocfs2_empty_dir() dramatically by allowing us to short-circuit the full directory scan. Signed-off-by: Mark Fasheh <mfasheh@suse.com>
2009-04-03ocfs2: Increase max links countMark Fasheh4-26/+66
Since we've now got a directory format capable of handling a large number of entries, we can increase the maximum link count supported. This only gets increased if the directory indexing feature is turned on. Signed-off-by: Mark Fasheh <mfasheh@suse.com> Acked-by: Joel Becker <joel.becker@oracle.com>
2009-04-03ocfs2: Introduce dir free space listMark Fasheh4-93/+490
The only operation which doesn't get faster with directory indexing is insert, which still has to walk the entire unindexed directory portion to find a free block. This patch provides an improvement in directory insert performance by maintaining a singly linked list of directory leaf blocks which have space for additional dirents. Signed-off-by: Mark Fasheh <mfasheh@suse.com> Acked-by: Joel Becker <joel.becker@oracle.com>