android_kernel_samsung_msm8976/fs/inode.c

1675 lines
43 KiB
C
Raw Normal View History

/*
* (C) 1997 Linus Torvalds
* (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
*/
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/dcache.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/writeback.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
fs: turn iprune_mutex into rwsem We have had a report of bad memory allocation latency during DVD-RAM (UDF) writing. This is causing the user's desktop session to become unusable. Jan tracked the cause of this down to UDF inode reclaim blocking: gnome-screens D ffff810006d1d598 0 20686 1 ffff810006d1d508 0000000000000082 ffff810037db6718 0000000000000800 ffff810006d1d488 ffffffff807e4280 ffffffff807e4280 ffff810006d1a580 ffff8100bccbc140 ffff810006d1a8c0 0000000006d1d4e8 ffff810006d1a8c0 Call Trace: [<ffffffff804477f3>] io_schedule+0x63/0xa5 [<ffffffff802c2587>] sync_buffer+0x3b/0x3f [<ffffffff80447d2a>] __wait_on_bit+0x47/0x79 [<ffffffff80447dc6>] out_of_line_wait_on_bit+0x6a/0x77 [<ffffffff802c24f6>] __wait_on_buffer+0x1f/0x21 [<ffffffff802c442a>] __bread+0x70/0x86 [<ffffffff88de9ec7>] :udf:udf_tread+0x38/0x3a [<ffffffff88de0fcf>] :udf:udf_update_inode+0x4d/0x68c [<ffffffff88de26e1>] :udf:udf_write_inode+0x1d/0x2b [<ffffffff802bcf85>] __writeback_single_inode+0x1c0/0x394 [<ffffffff802bd205>] write_inode_now+0x7d/0xc4 [<ffffffff88de2e76>] :udf:udf_clear_inode+0x3d/0x53 [<ffffffff802b39ae>] clear_inode+0xc2/0x11b [<ffffffff802b3ab1>] dispose_list+0x5b/0x102 [<ffffffff802b3d35>] shrink_icache_memory+0x1dd/0x213 [<ffffffff8027ede3>] shrink_slab+0xe3/0x158 [<ffffffff8027fbab>] try_to_free_pages+0x177/0x232 [<ffffffff8027a578>] __alloc_pages+0x1fa/0x392 [<ffffffff802951fa>] alloc_page_vma+0x176/0x189 [<ffffffff802822d8>] __do_fault+0x10c/0x417 [<ffffffff80284232>] handle_mm_fault+0x466/0x940 [<ffffffff8044b922>] do_page_fault+0x676/0xabf This blocks with iprune_mutex held, which then blocks other reclaimers: X D ffff81009d47c400 0 17285 14831 ffff8100844f3728 0000000000000086 0000000000000000 ffff81000000e288 ffff81000000da00 ffffffff807e4280 ffffffff807e4280 ffff81009d47c400 ffffffff805ff890 ffff81009d47c740 00000000844f3808 ffff81009d47c740 Call Trace: [<ffffffff80447f8c>] __mutex_lock_slowpath+0x72/0xa9 [<ffffffff80447e1a>] mutex_lock+0x1e/0x22 [<ffffffff802b3ba1>] shrink_icache_memory+0x49/0x213 [<ffffffff8027ede3>] shrink_slab+0xe3/0x158 [<ffffffff8027fbab>] try_to_free_pages+0x177/0x232 [<ffffffff8027a578>] __alloc_pages+0x1fa/0x392 [<ffffffff8029507f>] alloc_pages_current+0xd1/0xd6 [<ffffffff80279ac0>] __get_free_pages+0xe/0x4d [<ffffffff802ae1b7>] __pollwait+0x5e/0xdf [<ffffffff8860f2b4>] :nvidia:nv_kern_poll+0x2e/0x73 [<ffffffff802ad949>] do_select+0x308/0x506 [<ffffffff802adced>] core_sys_select+0x1a6/0x254 [<ffffffff802ae0b7>] sys_select+0xb5/0x157 Now I think the main problem is having the filesystem block (and do IO) in inode reclaim. The problem is that this doesn't get accounted well and penalizes a random allocator with a big latency spike caused by work generated from elsewhere. I think the best idea would be to avoid this. By design if possible, or by deferring the hard work to an asynchronous context. If the latter, then the fs would probably want to throttle creation of new work with queue size of the deferred work, but let's not get into those details. Anyway, the other obvious thing we looked at is the iprune_mutex which is causing the cascading blocking. We could turn this into an rwsem to improve concurrency. It is unreasonable to totally ban all potentially slow or blocking operations in inode reclaim, so I think this is a cheap way to get a small improvement. This doesn't solve the whole problem of course. The process doing inode reclaim will still take the latency hit, and concurrent processes may end up contending on filesystem locks. So fs developers should keep these problems in mind. Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jan Kara <jack@ucw.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 23:43:50 +00:00
#include <linux/rwsem.h>
#include <linux/hash.h>
#include <linux/swap.h>
#include <linux/security.h>
#include <linux/pagemap.h>
#include <linux/cdev.h>
#include <linux/bootmem.h>
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/async.h>
#include <linux/posix_acl.h>
#include <linux/prefetch.h>
#include <linux/ima.h>
#include <linux/cred.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include "internal.h"
/*
* Inode locking rules:
*
* inode->i_lock protects:
* inode->i_state, inode->i_hash, __iget()
* inode->i_sb->s_inode_lru_lock protects:
* inode->i_sb->s_inode_lru, inode->i_lru
* inode_sb_list_lock protects:
* sb->s_inodes, inode->i_sb_list
writeback: split inode_wb_list_lock into bdi_writeback.list_lock Split the global inode_wb_list_lock into a per-bdi_writeback list_lock, as it's currently the most contended lock in the system for metadata heavy workloads. It won't help for single-filesystem workloads for which we'll need the I/O-less balance_dirty_pages, but at least we can dedicate a cpu to spinning on each bdi now for larger systems. Based on earlier patches from Nick Piggin and Dave Chinner. It reduces lock contentions to 1/4 in this test case: 10 HDD JBOD, 100 dd on each disk, XFS, 6GB ram lock_stat version 0.3 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- vanilla 2.6.39-rc3: inode_wb_list_lock: 42590 44433 0.12 147.74 144127.35 252274 886792 0.08 121.34 917211.23 ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 34 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 12893 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 10702 [<ffffffff8115afef>] writeback_single_inode+0x16d/0x20a ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 19 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 5550 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 8511 [<ffffffff8115b4ad>] writeback_sb_inodes+0x10f/0x157 2.6.39-rc3 + patch: &(&wb->list_lock)->rlock: 11383 11657 0.14 151.69 40429.51 90825 527918 0.11 145.90 556843.37 ------------------------ &(&wb->list_lock)->rlock 10 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 1493 [<ffffffff8115b1ed>] writeback_inodes_wb+0x3d/0x150 &(&wb->list_lock)->rlock 3652 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f &(&wb->list_lock)->rlock 1412 [<ffffffff8115a38e>] writeback_single_inode+0x17f/0x223 ------------------------ &(&wb->list_lock)->rlock 3 [<ffffffff8110b5af>] bdi_lock_two+0x46/0x4b &(&wb->list_lock)->rlock 6 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 2061 [<ffffffff8115af97>] __mark_inode_dirty+0x173/0x1cf &(&wb->list_lock)->rlock 2629 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f hughd@google.com: fix recursive lock when bdi_lock_two() is called with new the same as old akpm@linux-foundation.org: cleanup bdev_inode_switch_bdi() comment Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2011-04-22 00:19:44 +00:00
* bdi->wb.list_lock protects:
* bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
* inode_hash_lock protects:
* inode_hashtable, inode->i_hash
*
* Lock ordering:
*
* inode_sb_list_lock
* inode->i_lock
* inode->i_sb->s_inode_lru_lock
*
writeback: split inode_wb_list_lock into bdi_writeback.list_lock Split the global inode_wb_list_lock into a per-bdi_writeback list_lock, as it's currently the most contended lock in the system for metadata heavy workloads. It won't help for single-filesystem workloads for which we'll need the I/O-less balance_dirty_pages, but at least we can dedicate a cpu to spinning on each bdi now for larger systems. Based on earlier patches from Nick Piggin and Dave Chinner. It reduces lock contentions to 1/4 in this test case: 10 HDD JBOD, 100 dd on each disk, XFS, 6GB ram lock_stat version 0.3 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- class name con-bounces contentions waittime-min waittime-max waittime-total acq-bounces acquisitions holdtime-min holdtime-max holdtime-total ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- vanilla 2.6.39-rc3: inode_wb_list_lock: 42590 44433 0.12 147.74 144127.35 252274 886792 0.08 121.34 917211.23 ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 34 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 12893 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 10702 [<ffffffff8115afef>] writeback_single_inode+0x16d/0x20a ------------------ inode_wb_list_lock 2 [<ffffffff81165da5>] bdev_inode_switch_bdi+0x29/0x85 inode_wb_list_lock 19 [<ffffffff8115bd0b>] inode_wb_list_del+0x22/0x49 inode_wb_list_lock 5550 [<ffffffff8115bb53>] __mark_inode_dirty+0x170/0x1d0 inode_wb_list_lock 8511 [<ffffffff8115b4ad>] writeback_sb_inodes+0x10f/0x157 2.6.39-rc3 + patch: &(&wb->list_lock)->rlock: 11383 11657 0.14 151.69 40429.51 90825 527918 0.11 145.90 556843.37 ------------------------ &(&wb->list_lock)->rlock 10 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 1493 [<ffffffff8115b1ed>] writeback_inodes_wb+0x3d/0x150 &(&wb->list_lock)->rlock 3652 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f &(&wb->list_lock)->rlock 1412 [<ffffffff8115a38e>] writeback_single_inode+0x17f/0x223 ------------------------ &(&wb->list_lock)->rlock 3 [<ffffffff8110b5af>] bdi_lock_two+0x46/0x4b &(&wb->list_lock)->rlock 6 [<ffffffff8115b189>] inode_wb_list_del+0x5f/0x86 &(&wb->list_lock)->rlock 2061 [<ffffffff8115af97>] __mark_inode_dirty+0x173/0x1cf &(&wb->list_lock)->rlock 2629 [<ffffffff8115a8e9>] writeback_sb_inodes+0x123/0x16f hughd@google.com: fix recursive lock when bdi_lock_two() is called with new the same as old akpm@linux-foundation.org: cleanup bdev_inode_switch_bdi() comment Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2011-04-22 00:19:44 +00:00
* bdi->wb.list_lock
* inode->i_lock
*
* inode_hash_lock
* inode_sb_list_lock
* inode->i_lock
*
* iunique_lock
* inode_hash_lock
*/
static unsigned int i_hash_mask __read_mostly;
static unsigned int i_hash_shift __read_mostly;
static struct hlist_head *inode_hashtable __read_mostly;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
/*
* Empty aops. Can be used for the cases where the user does not
* define any of the address_space operations.
*/
const struct address_space_operations empty_aops = {
};
EXPORT_SYMBOL(empty_aops);
/*
* Statistics gathering..
*/
struct inodes_stat_t inodes_stat;
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 06:49:19 +00:00
static DEFINE_PER_CPU(unsigned int, nr_inodes);
static DEFINE_PER_CPU(unsigned int, nr_unused);
static struct kmem_cache *inode_cachep __read_mostly;
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 06:49:19 +00:00
static int get_nr_inodes(void)
{
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 06:49:19 +00:00
int i;
int sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_inodes, i);
return sum < 0 ? 0 : sum;
}
static inline int get_nr_inodes_unused(void)
{
int i;
int sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_unused, i);
return sum < 0 ? 0 : sum;
}
int get_nr_dirty_inodes(void)
{
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 06:49:19 +00:00
/* not actually dirty inodes, but a wild approximation */
int nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
return nr_dirty > 0 ? nr_dirty : 0;
}
/*
* Handle nr_inode sysctl
*/
#ifdef CONFIG_SYSCTL
int proc_nr_inodes(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
inodes_stat.nr_inodes = get_nr_inodes();
inodes_stat.nr_unused = get_nr_inodes_unused();
return proc_dointvec(table, write, buffer, lenp, ppos);
}
#endif
/**
* inode_init_always - perform inode structure intialisation
* @sb: superblock inode belongs to
* @inode: inode to initialise
*
* These are initializations that need to be done on every inode
* allocation as the fields are not initialised by slab allocation.
*/
int inode_init_always(struct super_block *sb, struct inode *inode)
{
static const struct inode_operations empty_iops;
static const struct file_operations empty_fops;
struct address_space *const mapping = &inode->i_data;
inode->i_sb = sb;
inode->i_blkbits = sb->s_blocksize_bits;
inode->i_flags = 0;
atomic_set(&inode->i_count, 1);
inode->i_op = &empty_iops;
inode->i_fop = &empty_fops;
inode->i_nlink = 1;
inode->i_opflags = 0;
inode->i_uid = 0;
inode->i_gid = 0;
atomic_set(&inode->i_writecount, 0);
inode->i_size = 0;
inode->i_blocks = 0;
inode->i_bytes = 0;
inode->i_generation = 0;
#ifdef CONFIG_QUOTA
memset(&inode->i_dquot, 0, sizeof(inode->i_dquot));
#endif
inode->i_pipe = NULL;
inode->i_bdev = NULL;
inode->i_cdev = NULL;
inode->i_rdev = 0;
inode->dirtied_when = 0;
if (security_inode_alloc(inode))
goto out;
spin_lock_init(&inode->i_lock);
lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
mutex_init(&inode->i_mutex);
lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);
atomic_set(&inode->i_dio_count, 0);
mapping->a_ops = &empty_aops;
mapping->host = inode;
mapping->flags = 0;
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
mapping->assoc_mapping = NULL;
mapping->backing_dev_info = &default_backing_dev_info;
mapping->writeback_index = 0;
/*
* If the block_device provides a backing_dev_info for client
* inodes then use that. Otherwise the inode share the bdev's
* backing_dev_info.
*/
if (sb->s_bdev) {
struct backing_dev_info *bdi;
bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
mapping->backing_dev_info = bdi;
}
inode->i_private = NULL;
inode->i_mapping = mapping;
#ifdef CONFIG_FS_POSIX_ACL
inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
#endif
#ifdef CONFIG_FSNOTIFY
inode->i_fsnotify_mask = 0;
#endif
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 06:49:19 +00:00
this_cpu_inc(nr_inodes);
return 0;
out:
return -ENOMEM;
}
EXPORT_SYMBOL(inode_init_always);
static struct inode *alloc_inode(struct super_block *sb)
{
struct inode *inode;
if (sb->s_op->alloc_inode)
inode = sb->s_op->alloc_inode(sb);
else
inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);
if (!inode)
return NULL;
if (unlikely(inode_init_always(sb, inode))) {
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
else
kmem_cache_free(inode_cachep, inode);
return NULL;
}
return inode;
}
void free_inode_nonrcu(struct inode *inode)
{
kmem_cache_free(inode_cachep, inode);
}
EXPORT_SYMBOL(free_inode_nonrcu);
void __destroy_inode(struct inode *inode)
{
BUG_ON(inode_has_buffers(inode));
security_inode_free(inode);
fsnotify_inode_delete(inode);
#ifdef CONFIG_FS_POSIX_ACL
if (inode->i_acl && inode->i_acl != ACL_NOT_CACHED)
posix_acl_release(inode->i_acl);
if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
posix_acl_release(inode->i_default_acl);
#endif
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 06:49:19 +00:00
this_cpu_dec(nr_inodes);
}
EXPORT_SYMBOL(__destroy_inode);
2011-01-07 06:49:49 +00:00
static void i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
INIT_LIST_HEAD(&inode->i_dentry);
kmem_cache_free(inode_cachep, inode);
}
static void destroy_inode(struct inode *inode)
{
BUG_ON(!list_empty(&inode->i_lru));
__destroy_inode(inode);
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
else
2011-01-07 06:49:49 +00:00
call_rcu(&inode->i_rcu, i_callback);
}
mm: prevent concurrent unmap_mapping_range() on the same inode Michael Leun reported that running parallel opens on a fuse filesystem can trigger a "kernel BUG at mm/truncate.c:475" Gurudas Pai reported the same bug on NFS. The reason is, unmap_mapping_range() is not prepared for more than one concurrent invocation per inode. For example: thread1: going through a big range, stops in the middle of a vma and stores the restart address in vm_truncate_count. thread2: comes in with a small (e.g. single page) unmap request on the same vma, somewhere before restart_address, finds that the vma was already unmapped up to the restart address and happily returns without doing anything. Another scenario would be two big unmap requests, both having to restart the unmapping and each one setting vm_truncate_count to its own value. This could go on forever without any of them being able to finish. Truncate and hole punching already serialize with i_mutex. Other callers of unmap_mapping_range() do not, and it's difficult to get i_mutex protection for all callers. In particular ->d_revalidate(), which calls invalidate_inode_pages2_range() in fuse, may be called with or without i_mutex. This patch adds a new mutex to 'struct address_space' to prevent running multiple concurrent unmap_mapping_range() on the same mapping. [ We'll hopefully get rid of all this with the upcoming mm preemptibility series by Peter Zijlstra, the "mm: Remove i_mmap_mutex lockbreak" patch in particular. But that is for 2.6.39 ] Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Reported-by: Michael Leun <lkml20101129@newton.leun.net> Reported-by: Gurudas Pai <gurudas.pai@oracle.com> Tested-by: Gurudas Pai <gurudas.pai@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-23 12:49:47 +00:00
void address_space_init_once(struct address_space *mapping)
{
memset(mapping, 0, sizeof(*mapping));
INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
spin_lock_init(&mapping->tree_lock);
mutex_init(&mapping->i_mmap_mutex);
mm: prevent concurrent unmap_mapping_range() on the same inode Michael Leun reported that running parallel opens on a fuse filesystem can trigger a "kernel BUG at mm/truncate.c:475" Gurudas Pai reported the same bug on NFS. The reason is, unmap_mapping_range() is not prepared for more than one concurrent invocation per inode. For example: thread1: going through a big range, stops in the middle of a vma and stores the restart address in vm_truncate_count. thread2: comes in with a small (e.g. single page) unmap request on the same vma, somewhere before restart_address, finds that the vma was already unmapped up to the restart address and happily returns without doing anything. Another scenario would be two big unmap requests, both having to restart the unmapping and each one setting vm_truncate_count to its own value. This could go on forever without any of them being able to finish. Truncate and hole punching already serialize with i_mutex. Other callers of unmap_mapping_range() do not, and it's difficult to get i_mutex protection for all callers. In particular ->d_revalidate(), which calls invalidate_inode_pages2_range() in fuse, may be called with or without i_mutex. This patch adds a new mutex to 'struct address_space' to prevent running multiple concurrent unmap_mapping_range() on the same mapping. [ We'll hopefully get rid of all this with the upcoming mm preemptibility series by Peter Zijlstra, the "mm: Remove i_mmap_mutex lockbreak" patch in particular. But that is for 2.6.39 ] Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Reported-by: Michael Leun <lkml20101129@newton.leun.net> Reported-by: Gurudas Pai <gurudas.pai@oracle.com> Tested-by: Gurudas Pai <gurudas.pai@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-23 12:49:47 +00:00
INIT_LIST_HEAD(&mapping->private_list);
spin_lock_init(&mapping->private_lock);
INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
}
EXPORT_SYMBOL(address_space_init_once);
/*
* These are initializations that only need to be done
* once, because the fields are idempotent across use
* of the inode, so let the slab aware of that.
*/
void inode_init_once(struct inode *inode)
{
memset(inode, 0, sizeof(*inode));
INIT_HLIST_NODE(&inode->i_hash);
INIT_LIST_HEAD(&inode->i_dentry);
INIT_LIST_HEAD(&inode->i_devices);
INIT_LIST_HEAD(&inode->i_wb_list);
INIT_LIST_HEAD(&inode->i_lru);
mm: prevent concurrent unmap_mapping_range() on the same inode Michael Leun reported that running parallel opens on a fuse filesystem can trigger a "kernel BUG at mm/truncate.c:475" Gurudas Pai reported the same bug on NFS. The reason is, unmap_mapping_range() is not prepared for more than one concurrent invocation per inode. For example: thread1: going through a big range, stops in the middle of a vma and stores the restart address in vm_truncate_count. thread2: comes in with a small (e.g. single page) unmap request on the same vma, somewhere before restart_address, finds that the vma was already unmapped up to the restart address and happily returns without doing anything. Another scenario would be two big unmap requests, both having to restart the unmapping and each one setting vm_truncate_count to its own value. This could go on forever without any of them being able to finish. Truncate and hole punching already serialize with i_mutex. Other callers of unmap_mapping_range() do not, and it's difficult to get i_mutex protection for all callers. In particular ->d_revalidate(), which calls invalidate_inode_pages2_range() in fuse, may be called with or without i_mutex. This patch adds a new mutex to 'struct address_space' to prevent running multiple concurrent unmap_mapping_range() on the same mapping. [ We'll hopefully get rid of all this with the upcoming mm preemptibility series by Peter Zijlstra, the "mm: Remove i_mmap_mutex lockbreak" patch in particular. But that is for 2.6.39 ] Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Reported-by: Michael Leun <lkml20101129@newton.leun.net> Reported-by: Gurudas Pai <gurudas.pai@oracle.com> Tested-by: Gurudas Pai <gurudas.pai@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-23 12:49:47 +00:00
address_space_init_once(&inode->i_data);
i_size_ordered_init(inode);
#ifdef CONFIG_FSNOTIFY
INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
#endif
}
EXPORT_SYMBOL(inode_init_once);
static void init_once(void *foo)
{
struct inode *inode = (struct inode *) foo;
inode_init_once(inode);
}
/*
* inode->i_lock must be held
*/
void __iget(struct inode *inode)
{
atomic_inc(&inode->i_count);
}
/*
* get additional reference to inode; caller must already hold one.
*/
void ihold(struct inode *inode)
{
WARN_ON(atomic_inc_return(&inode->i_count) < 2);
}
EXPORT_SYMBOL(ihold);
static void inode_lru_list_add(struct inode *inode)
{
spin_lock(&inode->i_sb->s_inode_lru_lock);
if (list_empty(&inode->i_lru)) {
list_add(&inode->i_lru, &inode->i_sb->s_inode_lru);
inode->i_sb->s_nr_inodes_unused++;
this_cpu_inc(nr_unused);
}
spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
static void inode_lru_list_del(struct inode *inode)
{
spin_lock(&inode->i_sb->s_inode_lru_lock);
if (!list_empty(&inode->i_lru)) {
list_del_init(&inode->i_lru);
inode->i_sb->s_nr_inodes_unused--;
this_cpu_dec(nr_unused);
}
spin_unlock(&inode->i_sb->s_inode_lru_lock);
}
/**
* inode_sb_list_add - add inode to the superblock list of inodes
* @inode: inode to add
*/
void inode_sb_list_add(struct inode *inode)
{
spin_lock(&inode_sb_list_lock);
list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
spin_unlock(&inode_sb_list_lock);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);
static inline void inode_sb_list_del(struct inode *inode)
{
if (!list_empty(&inode->i_sb_list)) {
spin_lock(&inode_sb_list_lock);
list_del_init(&inode->i_sb_list);
spin_unlock(&inode_sb_list_lock);
}
}
static unsigned long hash(struct super_block *sb, unsigned long hashval)
{
unsigned long tmp;
tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
L1_CACHE_BYTES;
tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift);
return tmp & i_hash_mask;
}
/**
* __insert_inode_hash - hash an inode
* @inode: unhashed inode
* @hashval: unsigned long value used to locate this object in the
* inode_hashtable.
*
* Add an inode to the inode hash for this superblock.
*/
void __insert_inode_hash(struct inode *inode, unsigned long hashval)
{
struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval);
spin_lock(&inode_hash_lock);
spin_lock(&inode->i_lock);
hlist_add_head(&inode->i_hash, b);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(__insert_inode_hash);
/**
* __remove_inode_hash - remove an inode from the hash
* @inode: inode to unhash
*
* Remove an inode from the superblock.
*/
void __remove_inode_hash(struct inode *inode)
{
spin_lock(&inode_hash_lock);
spin_lock(&inode->i_lock);
hlist_del_init(&inode->i_hash);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(__remove_inode_hash);
void end_writeback(struct inode *inode)
{
might_sleep();
/*
* We have to cycle tree_lock here because reclaim can be still in the
* process of removing the last page (in __delete_from_page_cache())
* and we must not free mapping under it.
*/
spin_lock_irq(&inode->i_data.tree_lock);
BUG_ON(inode->i_data.nrpages);
spin_unlock_irq(&inode->i_data.tree_lock);
BUG_ON(!list_empty(&inode->i_data.private_list));
BUG_ON(!(inode->i_state & I_FREEING));
BUG_ON(inode->i_state & I_CLEAR);
inode_sync_wait(inode);
2011-01-07 06:49:49 +00:00
/* don't need i_lock here, no concurrent mods to i_state */
inode->i_state = I_FREEING | I_CLEAR;
}
EXPORT_SYMBOL(end_writeback);
/*
* Free the inode passed in, removing it from the lists it is still connected
* to. We remove any pages still attached to the inode and wait for any IO that
* is still in progress before finally destroying the inode.
*
* An inode must already be marked I_FREEING so that we avoid the inode being
* moved back onto lists if we race with other code that manipulates the lists
* (e.g. writeback_single_inode). The caller is responsible for setting this.
*
* An inode must already be removed from the LRU list before being evicted from
* the cache. This should occur atomically with setting the I_FREEING state
* flag, so no inodes here should ever be on the LRU when being evicted.
*/
static void evict(struct inode *inode)
{
const struct super_operations *op = inode->i_sb->s_op;
BUG_ON(!(inode->i_state & I_FREEING));
BUG_ON(!list_empty(&inode->i_lru));
if (!list_empty(&inode->i_wb_list))
inode_wb_list_del(inode);
inode_sb_list_del(inode);
if (op->evict_inode) {
op->evict_inode(inode);
} else {
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
end_writeback(inode);
}
if (S_ISBLK(inode->i_mode) && inode->i_bdev)
bd_forget(inode);
if (S_ISCHR(inode->i_mode) && inode->i_cdev)
cd_forget(inode);
remove_inode_hash(inode);
spin_lock(&inode->i_lock);
wake_up_bit(&inode->i_state, __I_NEW);
BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
spin_unlock(&inode->i_lock);
destroy_inode(inode);
}
/*
* dispose_list - dispose of the contents of a local list
* @head: the head of the list to free
*
* Dispose-list gets a local list with local inodes in it, so it doesn't
* need to worry about list corruption and SMP locks.
*/
static void dispose_list(struct list_head *head)
{
while (!list_empty(head)) {
struct inode *inode;
inode = list_first_entry(head, struct inode, i_lru);
list_del_init(&inode->i_lru);
evict(inode);
}
}
/**
* evict_inodes - evict all evictable inodes for a superblock
* @sb: superblock to operate on
*
* Make sure that no inodes with zero refcount are retained. This is
* called by superblock shutdown after having MS_ACTIVE flag removed,
* so any inode reaching zero refcount during or after that call will
* be immediately evicted.
*/
void evict_inodes(struct super_block *sb)
{
struct inode *inode, *next;
LIST_HEAD(dispose);
spin_lock(&inode_sb_list_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
if (atomic_read(&inode->i_count))
continue;
spin_lock(&inode->i_lock);
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
spin_unlock(&inode->i_lock);
continue;
}
inode->i_state |= I_FREEING;
inode_lru_list_del(inode);
spin_unlock(&inode->i_lock);
list_add(&inode->i_lru, &dispose);
}
spin_unlock(&inode_sb_list_lock);
dispose_list(&dispose);
}
/**
* invalidate_inodes - attempt to free all inodes on a superblock
* @sb: superblock to operate on
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 06:25:47 +00:00
* @kill_dirty: flag to guide handling of dirty inodes
*
* Attempts to free all inodes for a given superblock. If there were any
* busy inodes return a non-zero value, else zero.
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 06:25:47 +00:00
* If @kill_dirty is set, discard dirty inodes too, otherwise treat
* them as busy.
*/
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 06:25:47 +00:00
int invalidate_inodes(struct super_block *sb, bool kill_dirty)
{
int busy = 0;
struct inode *inode, *next;
LIST_HEAD(dispose);
spin_lock(&inode_sb_list_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
spin_unlock(&inode->i_lock);
continue;
}
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 06:25:47 +00:00
if (inode->i_state & I_DIRTY && !kill_dirty) {
spin_unlock(&inode->i_lock);
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 06:25:47 +00:00
busy = 1;
continue;
}
if (atomic_read(&inode->i_count)) {
spin_unlock(&inode->i_lock);
busy = 1;
continue;
}
inode->i_state |= I_FREEING;
inode_lru_list_del(inode);
spin_unlock(&inode->i_lock);
list_add(&inode->i_lru, &dispose);
}
spin_unlock(&inode_sb_list_lock);
dispose_list(&dispose);
return busy;
}
static int can_unuse(struct inode *inode)
{
if (inode->i_state & ~I_REFERENCED)
return 0;
if (inode_has_buffers(inode))
return 0;
if (atomic_read(&inode->i_count))
return 0;
if (inode->i_data.nrpages)
return 0;
return 1;
}
/*
* Walk the superblock inode LRU for freeable inodes and attempt to free them.
* This is called from the superblock shrinker function with a number of inodes
* to trim from the LRU. Inodes to be freed are moved to a temporary list and
* then are freed outside inode_lock by dispose_list().
*
* Any inodes which are pinned purely because of attached pagecache have their
* pagecache removed. If the inode has metadata buffers attached to
* mapping->private_list then try to remove them.
*
* If the inode has the I_REFERENCED flag set, then it means that it has been
* used recently - the flag is set in iput_final(). When we encounter such an
* inode, clear the flag and move it to the back of the LRU so it gets another
* pass through the LRU before it gets reclaimed. This is necessary because of
* the fact we are doing lazy LRU updates to minimise lock contention so the
* LRU does not have strict ordering. Hence we don't want to reclaim inodes
* with this flag set because they are the inodes that are out of order.
*/
void prune_icache_sb(struct super_block *sb, int nr_to_scan)
{
LIST_HEAD(freeable);
int nr_scanned;
unsigned long reap = 0;
spin_lock(&sb->s_inode_lru_lock);
for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) {
struct inode *inode;
if (list_empty(&sb->s_inode_lru))
break;
inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru);
/*
* we are inverting the sb->s_inode_lru_lock/inode->i_lock here,
* so use a trylock. If we fail to get the lock, just move the
* inode to the back of the list so we don't spin on it.
*/
if (!spin_trylock(&inode->i_lock)) {
list_move(&inode->i_lru, &sb->s_inode_lru);
continue;
}
/*
* Referenced or dirty inodes are still in use. Give them
* another pass through the LRU as we canot reclaim them now.
*/
if (atomic_read(&inode->i_count) ||
(inode->i_state & ~I_REFERENCED)) {
list_del_init(&inode->i_lru);
spin_unlock(&inode->i_lock);
sb->s_nr_inodes_unused--;
this_cpu_dec(nr_unused);
continue;
}
/* recently referenced inodes get one more pass */
if (inode->i_state & I_REFERENCED) {
inode->i_state &= ~I_REFERENCED;
list_move(&inode->i_lru, &sb->s_inode_lru);
spin_unlock(&inode->i_lock);
continue;
}
if (inode_has_buffers(inode) || inode->i_data.nrpages) {
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&sb->s_inode_lru_lock);
if (remove_inode_buffers(inode))
reap += invalidate_mapping_pages(&inode->i_data,
0, -1);
iput(inode);
spin_lock(&sb->s_inode_lru_lock);
if (inode != list_entry(sb->s_inode_lru.next,
struct inode, i_lru))
continue; /* wrong inode or list_empty */
/* avoid lock inversions with trylock */
if (!spin_trylock(&inode->i_lock))
continue;
if (!can_unuse(inode)) {
spin_unlock(&inode->i_lock);
continue;
}
}
fs: new inode i_state corruption fix There was a report of a data corruption http://lkml.org/lkml/2008/11/14/121. There is a script included to reproduce the problem. During testing, I encountered a number of strange things with ext3, so I tried ext2 to attempt to reduce complexity of the problem. I found that fsstress would quickly hang in wait_on_inode, waiting for I_LOCK to be cleared, even though instrumentation showed that unlock_new_inode had already been called for that inode. This points to memory scribble, or synchronisation problme. i_state of I_NEW inodes is not protected by inode_lock because other processes are not supposed to touch them until I_LOCK (and I_NEW) is cleared. Adding WARN_ON(inode->i_state & I_NEW) to sites where we modify i_state revealed that generic_sync_sb_inodes is picking up new inodes from the inode lists and passing them to __writeback_single_inode without waiting for I_NEW. Subsequently modifying i_state causes corruption. In my case it would look like this: CPU0 CPU1 unlock_new_inode() __sync_single_inode() reg <- inode->i_state reg -> reg & ~(I_LOCK|I_NEW) reg <- inode->i_state reg -> inode->i_state reg -> reg | I_SYNC reg -> inode->i_state Non-atomic RMW on CPU1 overwrites CPU0 store and sets I_LOCK|I_NEW again. Fix for this is rather than wait for I_NEW inodes, just skip over them: inodes concurrently being created are not subject to data integrity operations, and should not significantly contribute to dirty memory either. After this change, I'm unable to reproduce any of the added warnings or hangs after ~1hour of running. Previously, the new warnings would start immediately and hang would happen in under 5 minutes. I'm also testing on ext3 now, and so far no problems there either. I don't know whether this fixes the problem reported above, but it fixes a real problem for me. Cc: "Jorge Boncompte [DTI2]" <jorge@dti2.net> Reported-by: Adrian Hunter <ext-adrian.hunter@nokia.com> Cc: Jan Kara <jack@suse.cz> Cc: <stable@kernel.org> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-12 21:31:38 +00:00
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
spin_unlock(&inode->i_lock);
list_move(&inode->i_lru, &freeable);
sb->s_nr_inodes_unused--;
this_cpu_dec(nr_unused);
}
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 08:55:45 +00:00
if (current_is_kswapd())
__count_vm_events(KSWAPD_INODESTEAL, reap);
else
__count_vm_events(PGINODESTEAL, reap);
spin_unlock(&sb->s_inode_lru_lock);
dispose_list(&freeable);
}
static void __wait_on_freeing_inode(struct inode *inode);
/*
* Called with the inode lock held.
*/
static struct inode *find_inode(struct super_block *sb,
struct hlist_head *head,
int (*test)(struct inode *, void *),
void *data)
{
struct hlist_node *node;
struct inode *inode = NULL;
repeat:
hlist_for_each_entry(inode, node, head, i_hash) {
spin_lock(&inode->i_lock);
if (inode->i_sb != sb) {
spin_unlock(&inode->i_lock);
continue;
}
if (!test(inode, data)) {
spin_unlock(&inode->i_lock);
continue;
}
if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
__wait_on_freeing_inode(inode);
goto repeat;
}
__iget(inode);
spin_unlock(&inode->i_lock);
return inode;
}
return NULL;
}
/*
* find_inode_fast is the fast path version of find_inode, see the comment at
* iget_locked for details.
*/
static struct inode *find_inode_fast(struct super_block *sb,
struct hlist_head *head, unsigned long ino)
{
struct hlist_node *node;
struct inode *inode = NULL;
repeat:
hlist_for_each_entry(inode, node, head, i_hash) {
spin_lock(&inode->i_lock);
if (inode->i_ino != ino) {
spin_unlock(&inode->i_lock);
continue;
}
if (inode->i_sb != sb) {
spin_unlock(&inode->i_lock);
continue;
}
if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
__wait_on_freeing_inode(inode);
goto repeat;
}
__iget(inode);
spin_unlock(&inode->i_lock);
return inode;
}
return NULL;
}
/*
* Each cpu owns a range of LAST_INO_BATCH numbers.
* 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations,
* to renew the exhausted range.
*
* This does not significantly increase overflow rate because every CPU can
* consume at most LAST_INO_BATCH-1 unused inode numbers. So there is
* NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the
* 2^32 range, and is a worst-case. Even a 50% wastage would only increase
* overflow rate by 2x, which does not seem too significant.
*
* On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
* error if st_ino won't fit in target struct field. Use 32bit counter
* here to attempt to avoid that.
*/
#define LAST_INO_BATCH 1024
static DEFINE_PER_CPU(unsigned int, last_ino);
unsigned int get_next_ino(void)
{
unsigned int *p = &get_cpu_var(last_ino);
unsigned int res = *p;
#ifdef CONFIG_SMP
if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) {
static atomic_t shared_last_ino;
int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino);
res = next - LAST_INO_BATCH;
}
#endif
*p = ++res;
put_cpu_var(last_ino);
return res;
}
EXPORT_SYMBOL(get_next_ino);
/**
* new_inode_pseudo - obtain an inode
* @sb: superblock
*
* Allocates a new inode for given superblock.
* Inode wont be chained in superblock s_inodes list
* This means :
* - fs can't be unmount
* - quotas, fsnotify, writeback can't work
*/
struct inode *new_inode_pseudo(struct super_block *sb)
{
struct inode *inode = alloc_inode(sb);
if (inode) {
spin_lock(&inode->i_lock);
inode->i_state = 0;
spin_unlock(&inode->i_lock);
INIT_LIST_HEAD(&inode->i_sb_list);
}
return inode;
}
/**
* new_inode - obtain an inode
* @sb: superblock
*
Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated It is often known at allocation time whether a page may be migrated or not. This patch adds a flag called __GFP_MOVABLE and a new mask called GFP_HIGH_MOVABLE. Allocations using the __GFP_MOVABLE can be either migrated using the page migration mechanism or reclaimed by syncing with backing storage and discarding. An API function very similar to alloc_zeroed_user_highpage() is added for __GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable(). The flags used by alloc_zeroed_user_highpage() are not changed because it would change the semantics of an existing API. After this patch is applied there are no in-kernel users of alloc_zeroed_user_highpage() so it probably should be marked deprecated if this patch is merged. Note that this patch includes a minor cleanup to the use of __GFP_ZERO in shmem.c to keep all flag modifications to inode->mapping in the shmem_dir_alloc() helper function. This clean-up suggestion is courtesy of Hugh Dickens. Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the concept. Credit to Hugh Dickens for catching issues with shmem swap vector and ramfs allocations. [akpm@linux-foundation.org: build fix] [hugh@veritas.com: __GFP_ZERO cleanup] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 11:03:05 +00:00
* Allocates a new inode for given superblock. The default gfp_mask
* for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE.
Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated It is often known at allocation time whether a page may be migrated or not. This patch adds a flag called __GFP_MOVABLE and a new mask called GFP_HIGH_MOVABLE. Allocations using the __GFP_MOVABLE can be either migrated using the page migration mechanism or reclaimed by syncing with backing storage and discarding. An API function very similar to alloc_zeroed_user_highpage() is added for __GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable(). The flags used by alloc_zeroed_user_highpage() are not changed because it would change the semantics of an existing API. After this patch is applied there are no in-kernel users of alloc_zeroed_user_highpage() so it probably should be marked deprecated if this patch is merged. Note that this patch includes a minor cleanup to the use of __GFP_ZERO in shmem.c to keep all flag modifications to inode->mapping in the shmem_dir_alloc() helper function. This clean-up suggestion is courtesy of Hugh Dickens. Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the concept. Credit to Hugh Dickens for catching issues with shmem swap vector and ramfs allocations. [akpm@linux-foundation.org: build fix] [hugh@veritas.com: __GFP_ZERO cleanup] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 11:03:05 +00:00
* If HIGHMEM pages are unsuitable or it is known that pages allocated
* for the page cache are not reclaimable or migratable,
* mapping_set_gfp_mask() must be called with suitable flags on the
* newly created inode's mapping
*
*/
struct inode *new_inode(struct super_block *sb)
{
struct inode *inode;
spin_lock_prefetch(&inode_sb_list_lock);
inode = new_inode_pseudo(sb);
if (inode)
inode_sb_list_add(inode);
return inode;
}
EXPORT_SYMBOL(new_inode);
/**
* unlock_new_inode - clear the I_NEW state and wake up any waiters
* @inode: new inode to unlock
*
* Called when the inode is fully initialised to clear the new state of the
* inode and wake up anyone waiting for the inode to finish initialisation.
*/
void unlock_new_inode(struct inode *inode)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (S_ISDIR(inode->i_mode)) {
struct file_system_type *type = inode->i_sb->s_type;
/* Set new key only if filesystem hasn't already changed it */
if (!lockdep_match_class(&inode->i_mutex,
&type->i_mutex_key)) {
/*
* ensure nobody is actually holding i_mutex
*/
mutex_destroy(&inode->i_mutex);
mutex_init(&inode->i_mutex);
lockdep_set_class(&inode->i_mutex,
&type->i_mutex_dir_key);
}
}
#endif
spin_lock(&inode->i_lock);
WARN_ON(!(inode->i_state & I_NEW));
inode->i_state &= ~I_NEW;
wake_up_bit(&inode->i_state, __I_NEW);
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(unlock_new_inode);
/**
* iget5_locked - obtain an inode from a mounted file system
* @sb: super block of file system
* @hashval: hash value (usually inode number) to get
* @test: callback used for comparisons between inodes
* @set: callback used to initialize a new struct inode
* @data: opaque data pointer to pass to @test and @set
*
* Search for the inode specified by @hashval and @data in the inode cache,
* and if present it is return it with an increased reference count. This is
* a generalized version of iget_locked() for file systems where the inode
* number is not sufficient for unique identification of an inode.
*
* If the inode is not in cache, allocate a new inode and return it locked,
* hashed, and with the I_NEW flag set. The file system gets to fill it in
* before unlocking it via unlock_new_inode().
*
* Note both @test and @set are called with the inode_hash_lock held, so can't
* sleep.
*/
struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *), void *data)
{
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
struct inode *inode;
spin_lock(&inode_hash_lock);
inode = find_inode(sb, head, test, data);
spin_unlock(&inode_hash_lock);
if (inode) {
wait_on_inode(inode);
return inode;
}
inode = alloc_inode(sb);
if (inode) {
struct inode *old;
spin_lock(&inode_hash_lock);
/* We released the lock, so.. */
old = find_inode(sb, head, test, data);
if (!old) {
if (set(inode, data))
goto set_failed;
spin_lock(&inode->i_lock);
inode->i_state = I_NEW;
hlist_add_head(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
inode_sb_list_add(inode);
spin_unlock(&inode_hash_lock);
/* Return the locked inode with I_NEW set, the
* caller is responsible for filling in the contents
*/
return inode;
}
/*
* Uhhuh, somebody else created the same inode under
* us. Use the old inode instead of the one we just
* allocated.
*/
spin_unlock(&inode_hash_lock);
destroy_inode(inode);
inode = old;
wait_on_inode(inode);
}
return inode;
set_failed:
spin_unlock(&inode_hash_lock);
destroy_inode(inode);
return NULL;
}
EXPORT_SYMBOL(iget5_locked);
/**
* iget_locked - obtain an inode from a mounted file system
* @sb: super block of file system
* @ino: inode number to get
*
* Search for the inode specified by @ino in the inode cache and if present
* return it with an increased reference count. This is for file systems
* where the inode number is sufficient for unique identification of an inode.
*
* If the inode is not in cache, allocate a new inode and return it locked,
* hashed, and with the I_NEW flag set. The file system gets to fill it in
* before unlocking it via unlock_new_inode().
*/
struct inode *iget_locked(struct super_block *sb, unsigned long ino)
{
struct hlist_head *head = inode_hashtable + hash(sb, ino);
struct inode *inode;
spin_lock(&inode_hash_lock);
inode = find_inode_fast(sb, head, ino);
spin_unlock(&inode_hash_lock);
if (inode) {
wait_on_inode(inode);
return inode;
}
inode = alloc_inode(sb);
if (inode) {
struct inode *old;
spin_lock(&inode_hash_lock);
/* We released the lock, so.. */
old = find_inode_fast(sb, head, ino);
if (!old) {
inode->i_ino = ino;
spin_lock(&inode->i_lock);
inode->i_state = I_NEW;
hlist_add_head(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
inode_sb_list_add(inode);
spin_unlock(&inode_hash_lock);
/* Return the locked inode with I_NEW set, the
* caller is responsible for filling in the contents
*/
return inode;
}
/*
* Uhhuh, somebody else created the same inode under
* us. Use the old inode instead of the one we just
* allocated.
*/
spin_unlock(&inode_hash_lock);
destroy_inode(inode);
inode = old;
wait_on_inode(inode);
}
return inode;
}
EXPORT_SYMBOL(iget_locked);
/*
* search the inode cache for a matching inode number.
* If we find one, then the inode number we are trying to
* allocate is not unique and so we should not use it.
*
* Returns 1 if the inode number is unique, 0 if it is not.
*/
static int test_inode_iunique(struct super_block *sb, unsigned long ino)
{
struct hlist_head *b = inode_hashtable + hash(sb, ino);
struct hlist_node *node;
struct inode *inode;
spin_lock(&inode_hash_lock);
hlist_for_each_entry(inode, node, b, i_hash) {
if (inode->i_ino == ino && inode->i_sb == sb) {
spin_unlock(&inode_hash_lock);
return 0;
}
}
spin_unlock(&inode_hash_lock);
return 1;
}
/**
* iunique - get a unique inode number
* @sb: superblock
* @max_reserved: highest reserved inode number
*
* Obtain an inode number that is unique on the system for a given
* superblock. This is used by file systems that have no natural
* permanent inode numbering system. An inode number is returned that
* is higher than the reserved limit but unique.
*
* BUGS:
* With a large number of inodes live on the file system this function
* currently becomes quite slow.
*/
ino_t iunique(struct super_block *sb, ino_t max_reserved)
{
inode numbering: make static counters in new_inode and iunique be 32 bits The problems are: - on filesystems w/o permanent inode numbers, i_ino values can be larger than 32 bits, which can cause problems for some 32 bit userspace programs on a 64 bit kernel. We can't do anything for filesystems that have actual >32-bit inode numbers, but on filesystems that generate i_ino values on the fly, we should try to have them fit in 32 bits. We could trivially fix this by making the static counters in new_inode and iunique 32 bits, but... - many filesystems call new_inode and assume that the i_ino values they are given are unique. They are not guaranteed to be so, since the static counter can wrap. This problem is exacerbated by the fix for #1. - after allocating a new inode, some filesystems call iunique to try to get a unique i_ino value, but they don't actually add their inodes to the hashtable, and so they're still not guaranteed to be unique if that counter wraps. This patch set takes the simpler approach of simply using iunique and hashing the inodes afterward. Christoph H. previously mentioned that he thought that this approach may slow down lookups for filesystems that currently hash their inodes. The questions are: 1) how much would this slow down lookups for these filesystems? 2) is it enough to justify adding more infrastructure to avoid it? What might be best is to start with this approach and then only move to using IDR or some other scheme if these extra inodes in the hashtable prove to be problematic. I've done some cursory testing with this patch and the overhead of hashing and unhashing the inodes with pipefs is pretty low -- just a few seconds of system time added on to the creation and destruction of 10 million pipes (very similar to the overhead that the IDR approach would add). The hard thing to measure is what effect this has on other filesystems. I'm open to ways to try and gauge this. Again, I've only converted pipefs as an example. If this approach is acceptable then I'll start work on patches to convert other filesystems. With a pretty-much-worst-case microbenchmark provided by Eric Dumazet <dada1@cosmosbay.com>: hashing patch (pipebench): sys 1m15.329s sys 1m16.249s sys 1m17.169s unpatched (pipebench): sys 1m9.836s sys 1m12.541s sys 1m14.153s Which works out to 1.05642174294555027017. So ~5-6% slowdown. This patch: When a 32-bit program that was not compiled with large file offsets does a stat and gets a st_ino value back that won't fit in the 32 bit field, glibc (correctly) generates an EOVERFLOW error. We can't do anything about fs's with larger permanent inode numbers, but when we generate them on the fly, we ought to try and have them fit within a 32 bit field. This patch takes the first step toward this by making the static counters in these two functions be 32 bits. [jlayton@redhat.com: mention that it's only the case for 32bit, non-LFS stat] Signed-off-by: Jeff Layton <jlayton@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 07:32:29 +00:00
/*
* On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
* error if st_ino won't fit in target struct field. Use 32bit counter
* here to attempt to avoid that.
*/
static DEFINE_SPINLOCK(iunique_lock);
inode numbering: make static counters in new_inode and iunique be 32 bits The problems are: - on filesystems w/o permanent inode numbers, i_ino values can be larger than 32 bits, which can cause problems for some 32 bit userspace programs on a 64 bit kernel. We can't do anything for filesystems that have actual >32-bit inode numbers, but on filesystems that generate i_ino values on the fly, we should try to have them fit in 32 bits. We could trivially fix this by making the static counters in new_inode and iunique 32 bits, but... - many filesystems call new_inode and assume that the i_ino values they are given are unique. They are not guaranteed to be so, since the static counter can wrap. This problem is exacerbated by the fix for #1. - after allocating a new inode, some filesystems call iunique to try to get a unique i_ino value, but they don't actually add their inodes to the hashtable, and so they're still not guaranteed to be unique if that counter wraps. This patch set takes the simpler approach of simply using iunique and hashing the inodes afterward. Christoph H. previously mentioned that he thought that this approach may slow down lookups for filesystems that currently hash their inodes. The questions are: 1) how much would this slow down lookups for these filesystems? 2) is it enough to justify adding more infrastructure to avoid it? What might be best is to start with this approach and then only move to using IDR or some other scheme if these extra inodes in the hashtable prove to be problematic. I've done some cursory testing with this patch and the overhead of hashing and unhashing the inodes with pipefs is pretty low -- just a few seconds of system time added on to the creation and destruction of 10 million pipes (very similar to the overhead that the IDR approach would add). The hard thing to measure is what effect this has on other filesystems. I'm open to ways to try and gauge this. Again, I've only converted pipefs as an example. If this approach is acceptable then I'll start work on patches to convert other filesystems. With a pretty-much-worst-case microbenchmark provided by Eric Dumazet <dada1@cosmosbay.com>: hashing patch (pipebench): sys 1m15.329s sys 1m16.249s sys 1m17.169s unpatched (pipebench): sys 1m9.836s sys 1m12.541s sys 1m14.153s Which works out to 1.05642174294555027017. So ~5-6% slowdown. This patch: When a 32-bit program that was not compiled with large file offsets does a stat and gets a st_ino value back that won't fit in the 32 bit field, glibc (correctly) generates an EOVERFLOW error. We can't do anything about fs's with larger permanent inode numbers, but when we generate them on the fly, we ought to try and have them fit within a 32 bit field. This patch takes the first step toward this by making the static counters in these two functions be 32 bits. [jlayton@redhat.com: mention that it's only the case for 32bit, non-LFS stat] Signed-off-by: Jeff Layton <jlayton@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 07:32:29 +00:00
static unsigned int counter;
ino_t res;
spin_lock(&iunique_lock);
do {
if (counter <= max_reserved)
counter = max_reserved + 1;
res = counter++;
} while (!test_inode_iunique(sb, res));
spin_unlock(&iunique_lock);
return res;
}
EXPORT_SYMBOL(iunique);
struct inode *igrab(struct inode *inode)
{
spin_lock(&inode->i_lock);
if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) {
__iget(inode);
spin_unlock(&inode->i_lock);
} else {
spin_unlock(&inode->i_lock);
/*
* Handle the case where s_op->clear_inode is not been
* called yet, and somebody is calling igrab
* while the inode is getting freed.
*/
inode = NULL;
}
return inode;
}
EXPORT_SYMBOL(igrab);
/**
* ilookup5_nowait - search for an inode in the inode cache
* @sb: super block of file system to search
* @hashval: hash value (usually inode number) to search for
* @test: callback used for comparisons between inodes
* @data: opaque data pointer to pass to @test
*
* Search for the inode specified by @hashval and @data in the inode cache.
* If the inode is in the cache, the inode is returned with an incremented
* reference count.
*
* Note: I_NEW is not waited upon so you have to be very careful what you do
* with the returned inode. You probably should be using ilookup5() instead.
*
* Note2: @test is called with the inode_hash_lock held, so can't sleep.
*/
struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
struct inode *inode;
spin_lock(&inode_hash_lock);
inode = find_inode(sb, head, test, data);
spin_unlock(&inode_hash_lock);
[PATCH] Fix soft lockup due to NTFS: VFS part and explanation Something has changed in the core kernel such that we now get concurrent inode write outs, one e.g via pdflush and one via sys_sync or whatever. This causes a nasty deadlock in ntfs. The only clean solution unfortunately requires a minor vfs api extension. First the deadlock analysis: Prerequisive knowledge: NTFS has a file $MFT (inode 0) loaded at mount time. The NTFS driver uses the page cache for storing the file contents as usual. More interestingly this file contains the table of on-disk inodes as a sequence of MFT_RECORDs. Thus NTFS driver accesses the on-disk inodes by accessing the MFT_RECORDs in the page cache pages of the loaded inode $MFT. The situation: VFS inode X on a mounted ntfs volume is dirty. For same inode X, the ntfs_inode is dirty and thus corresponding on-disk inode, which is as explained above in a dirty PAGE_CACHE_PAGE belonging to the table of inodes ($MFT, inode 0). What happens: Process 1: sys_sync()/umount()/whatever... calls __sync_single_inode() for $MFT -> do_writepages() -> write_page for the dirty page containing the on-disk inode X, the page is now locked -> ntfs_write_mst_block() which clears PageUptodate() on the page to prevent anyone else getting hold of it whilst it does the write out (this is necessary as the on-disk inode needs "fixups" applied before the write to disk which are removed again after the write and PageUptodate is then set again). It then analyses the page looking for dirty on-disk inodes and when it finds one it calls ntfs_may_write_mft_record() to see if it is safe to write this on-disk inode. This then calls ilookup5() to check if the corresponding VFS inode is in icache(). This in turn calls ifind() which waits on the inode lock via wait_on_inode whilst holding the global inode_lock. Process 2: pdflush results in a call to __sync_single_inode for the same VFS inode X on the ntfs volume. This locks the inode (I_LOCK) then calls write-inode -> ntfs_write_inode -> map_mft_record() -> read_cache_page() of the page (in page cache of table of inodes $MFT, inode 0) containing the on-disk inode. This page has PageUptodate() clear because of Process 1 (see above) so read_cache_page() blocks when tries to take the page lock for the page so it can call ntfs_read_page(). Thus Process 1 is holding the page lock on the page containing the on-disk inode X and it is waiting on the inode X to be unlocked in ifind() so it can write the page out and then unlock the page. And Process 2 is holding the inode lock on inode X and is waiting for the page to be unlocked so it can call ntfs_readpage() or discover that Process 1 set PageUptodate() again and use the page. Thus we have a deadlock due to ifind() waiting on the inode lock. The only sensible solution: NTFS does not care whether the VFS inode is locked or not when it calls ilookup5() (it doesn't use the VFS inode at all, it just uses it to find the corresponding ntfs_inode which is of course attached to the VFS inode (both are one single struct); and it uses the ntfs_inode which is subject to its own locking so I_LOCK is irrelevant) hence we want a modified ilookup5_nowait() which is the same as ilookup5() but it does not wait on the inode lock. Without such functionality I would have to keep my own ntfs_inode cache in the NTFS driver just so I can find ntfs_inodes independent of their VFS inodes which would be slow, memory and cpu cycle wasting, and incredibly stupid given the icache already exists in the VFS. Below is a patch that does the ilookup5_nowait() implementation in fs/inode.c and exports it. ilookup5_nowait.diff: Introduce ilookup5_nowait() which is basically the same as ilookup5() but it does not wait on the inode's lock (i.e. it omits the wait_on_inode() done in ifind()). This is needed to avoid a nasty deadlock in NTFS. Signed-off-by: Anton Altaparmakov <aia21@cantab.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 08:10:44 +00:00
return inode;
[PATCH] Fix soft lockup due to NTFS: VFS part and explanation Something has changed in the core kernel such that we now get concurrent inode write outs, one e.g via pdflush and one via sys_sync or whatever. This causes a nasty deadlock in ntfs. The only clean solution unfortunately requires a minor vfs api extension. First the deadlock analysis: Prerequisive knowledge: NTFS has a file $MFT (inode 0) loaded at mount time. The NTFS driver uses the page cache for storing the file contents as usual. More interestingly this file contains the table of on-disk inodes as a sequence of MFT_RECORDs. Thus NTFS driver accesses the on-disk inodes by accessing the MFT_RECORDs in the page cache pages of the loaded inode $MFT. The situation: VFS inode X on a mounted ntfs volume is dirty. For same inode X, the ntfs_inode is dirty and thus corresponding on-disk inode, which is as explained above in a dirty PAGE_CACHE_PAGE belonging to the table of inodes ($MFT, inode 0). What happens: Process 1: sys_sync()/umount()/whatever... calls __sync_single_inode() for $MFT -> do_writepages() -> write_page for the dirty page containing the on-disk inode X, the page is now locked -> ntfs_write_mst_block() which clears PageUptodate() on the page to prevent anyone else getting hold of it whilst it does the write out (this is necessary as the on-disk inode needs "fixups" applied before the write to disk which are removed again after the write and PageUptodate is then set again). It then analyses the page looking for dirty on-disk inodes and when it finds one it calls ntfs_may_write_mft_record() to see if it is safe to write this on-disk inode. This then calls ilookup5() to check if the corresponding VFS inode is in icache(). This in turn calls ifind() which waits on the inode lock via wait_on_inode whilst holding the global inode_lock. Process 2: pdflush results in a call to __sync_single_inode for the same VFS inode X on the ntfs volume. This locks the inode (I_LOCK) then calls write-inode -> ntfs_write_inode -> map_mft_record() -> read_cache_page() of the page (in page cache of table of inodes $MFT, inode 0) containing the on-disk inode. This page has PageUptodate() clear because of Process 1 (see above) so read_cache_page() blocks when tries to take the page lock for the page so it can call ntfs_read_page(). Thus Process 1 is holding the page lock on the page containing the on-disk inode X and it is waiting on the inode X to be unlocked in ifind() so it can write the page out and then unlock the page. And Process 2 is holding the inode lock on inode X and is waiting for the page to be unlocked so it can call ntfs_readpage() or discover that Process 1 set PageUptodate() again and use the page. Thus we have a deadlock due to ifind() waiting on the inode lock. The only sensible solution: NTFS does not care whether the VFS inode is locked or not when it calls ilookup5() (it doesn't use the VFS inode at all, it just uses it to find the corresponding ntfs_inode which is of course attached to the VFS inode (both are one single struct); and it uses the ntfs_inode which is subject to its own locking so I_LOCK is irrelevant) hence we want a modified ilookup5_nowait() which is the same as ilookup5() but it does not wait on the inode lock. Without such functionality I would have to keep my own ntfs_inode cache in the NTFS driver just so I can find ntfs_inodes independent of their VFS inodes which would be slow, memory and cpu cycle wasting, and incredibly stupid given the icache already exists in the VFS. Below is a patch that does the ilookup5_nowait() implementation in fs/inode.c and exports it. ilookup5_nowait.diff: Introduce ilookup5_nowait() which is basically the same as ilookup5() but it does not wait on the inode's lock (i.e. it omits the wait_on_inode() done in ifind()). This is needed to avoid a nasty deadlock in NTFS. Signed-off-by: Anton Altaparmakov <aia21@cantab.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 08:10:44 +00:00
}
EXPORT_SYMBOL(ilookup5_nowait);
/**
* ilookup5 - search for an inode in the inode cache
* @sb: super block of file system to search
* @hashval: hash value (usually inode number) to search for
* @test: callback used for comparisons between inodes
* @data: opaque data pointer to pass to @test
*
* Search for the inode specified by @hashval and @data in the inode cache,
* and if the inode is in the cache, return the inode with an incremented
* reference count. Waits on I_NEW before returning the inode.
[PATCH] Fix soft lockup due to NTFS: VFS part and explanation Something has changed in the core kernel such that we now get concurrent inode write outs, one e.g via pdflush and one via sys_sync or whatever. This causes a nasty deadlock in ntfs. The only clean solution unfortunately requires a minor vfs api extension. First the deadlock analysis: Prerequisive knowledge: NTFS has a file $MFT (inode 0) loaded at mount time. The NTFS driver uses the page cache for storing the file contents as usual. More interestingly this file contains the table of on-disk inodes as a sequence of MFT_RECORDs. Thus NTFS driver accesses the on-disk inodes by accessing the MFT_RECORDs in the page cache pages of the loaded inode $MFT. The situation: VFS inode X on a mounted ntfs volume is dirty. For same inode X, the ntfs_inode is dirty and thus corresponding on-disk inode, which is as explained above in a dirty PAGE_CACHE_PAGE belonging to the table of inodes ($MFT, inode 0). What happens: Process 1: sys_sync()/umount()/whatever... calls __sync_single_inode() for $MFT -> do_writepages() -> write_page for the dirty page containing the on-disk inode X, the page is now locked -> ntfs_write_mst_block() which clears PageUptodate() on the page to prevent anyone else getting hold of it whilst it does the write out (this is necessary as the on-disk inode needs "fixups" applied before the write to disk which are removed again after the write and PageUptodate is then set again). It then analyses the page looking for dirty on-disk inodes and when it finds one it calls ntfs_may_write_mft_record() to see if it is safe to write this on-disk inode. This then calls ilookup5() to check if the corresponding VFS inode is in icache(). This in turn calls ifind() which waits on the inode lock via wait_on_inode whilst holding the global inode_lock. Process 2: pdflush results in a call to __sync_single_inode for the same VFS inode X on the ntfs volume. This locks the inode (I_LOCK) then calls write-inode -> ntfs_write_inode -> map_mft_record() -> read_cache_page() of the page (in page cache of table of inodes $MFT, inode 0) containing the on-disk inode. This page has PageUptodate() clear because of Process 1 (see above) so read_cache_page() blocks when tries to take the page lock for the page so it can call ntfs_read_page(). Thus Process 1 is holding the page lock on the page containing the on-disk inode X and it is waiting on the inode X to be unlocked in ifind() so it can write the page out and then unlock the page. And Process 2 is holding the inode lock on inode X and is waiting for the page to be unlocked so it can call ntfs_readpage() or discover that Process 1 set PageUptodate() again and use the page. Thus we have a deadlock due to ifind() waiting on the inode lock. The only sensible solution: NTFS does not care whether the VFS inode is locked or not when it calls ilookup5() (it doesn't use the VFS inode at all, it just uses it to find the corresponding ntfs_inode which is of course attached to the VFS inode (both are one single struct); and it uses the ntfs_inode which is subject to its own locking so I_LOCK is irrelevant) hence we want a modified ilookup5_nowait() which is the same as ilookup5() but it does not wait on the inode lock. Without such functionality I would have to keep my own ntfs_inode cache in the NTFS driver just so I can find ntfs_inodes independent of their VFS inodes which would be slow, memory and cpu cycle wasting, and incredibly stupid given the icache already exists in the VFS. Below is a patch that does the ilookup5_nowait() implementation in fs/inode.c and exports it. ilookup5_nowait.diff: Introduce ilookup5_nowait() which is basically the same as ilookup5() but it does not wait on the inode's lock (i.e. it omits the wait_on_inode() done in ifind()). This is needed to avoid a nasty deadlock in NTFS. Signed-off-by: Anton Altaparmakov <aia21@cantab.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 08:10:44 +00:00
* returned with an incremented reference count.
*
* This is a generalized version of ilookup() for file systems where the
* inode number is not sufficient for unique identification of an inode.
*
* Note: @test is called with the inode_hash_lock held, so can't sleep.
*/
struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
struct inode *inode = ilookup5_nowait(sb, hashval, test, data);
if (inode)
wait_on_inode(inode);
return inode;
}
EXPORT_SYMBOL(ilookup5);
/**
* ilookup - search for an inode in the inode cache
* @sb: super block of file system to search
* @ino: inode number to search for
*
* Search for the inode @ino in the inode cache, and if the inode is in the
* cache, the inode is returned with an incremented reference count.
*/
struct inode *ilookup(struct super_block *sb, unsigned long ino)
{
struct hlist_head *head = inode_hashtable + hash(sb, ino);
struct inode *inode;
spin_lock(&inode_hash_lock);
inode = find_inode_fast(sb, head, ino);
spin_unlock(&inode_hash_lock);
if (inode)
wait_on_inode(inode);
return inode;
}
EXPORT_SYMBOL(ilookup);
int insert_inode_locked(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
ino_t ino = inode->i_ino;
struct hlist_head *head = inode_hashtable + hash(sb, ino);
while (1) {
struct hlist_node *node;
struct inode *old = NULL;
spin_lock(&inode_hash_lock);
hlist_for_each_entry(old, node, head, i_hash) {
if (old->i_ino != ino)
continue;
if (old->i_sb != sb)
continue;
spin_lock(&old->i_lock);
if (old->i_state & (I_FREEING|I_WILL_FREE)) {
spin_unlock(&old->i_lock);
continue;
}
break;
}
if (likely(!node)) {
spin_lock(&inode->i_lock);
inode->i_state |= I_NEW;
hlist_add_head(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
return 0;
}
__iget(old);
spin_unlock(&old->i_lock);
spin_unlock(&inode_hash_lock);
wait_on_inode(old);
if (unlikely(!inode_unhashed(old))) {
iput(old);
return -EBUSY;
}
iput(old);
}
}
EXPORT_SYMBOL(insert_inode_locked);
int insert_inode_locked4(struct inode *inode, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
struct super_block *sb = inode->i_sb;
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
while (1) {
struct hlist_node *node;
struct inode *old = NULL;
spin_lock(&inode_hash_lock);
hlist_for_each_entry(old, node, head, i_hash) {
if (old->i_sb != sb)
continue;
if (!test(old, data))
continue;
spin_lock(&old->i_lock);
if (old->i_state & (I_FREEING|I_WILL_FREE)) {
spin_unlock(&old->i_lock);
continue;
}
break;
}
if (likely(!node)) {
spin_lock(&inode->i_lock);
inode->i_state |= I_NEW;
hlist_add_head(&inode->i_hash, head);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
return 0;
}
__iget(old);
spin_unlock(&old->i_lock);
spin_unlock(&inode_hash_lock);
wait_on_inode(old);
if (unlikely(!inode_unhashed(old))) {
iput(old);
return -EBUSY;
}
iput(old);
}
}
EXPORT_SYMBOL(insert_inode_locked4);
int generic_delete_inode(struct inode *inode)
{
return 1;
}
EXPORT_SYMBOL(generic_delete_inode);
/*
* Normal UNIX filesystem behaviour: delete the
* inode when the usage count drops to zero, and
* i_nlink is zero.
*/
int generic_drop_inode(struct inode *inode)
{
return !inode->i_nlink || inode_unhashed(inode);
}
EXPORT_SYMBOL_GPL(generic_drop_inode);
/*
* Called when we're dropping the last reference
* to an inode.
*
* Call the FS "drop_inode()" function, defaulting to
* the legacy UNIX filesystem behaviour. If it tells
* us to evict inode, do so. Otherwise, retain inode
* in cache if fs is alive, sync and evict if fs is
* shutting down.
*/
static void iput_final(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
const struct super_operations *op = inode->i_sb->s_op;
int drop;
WARN_ON(inode->i_state & I_NEW);
if (op->drop_inode)
drop = op->drop_inode(inode);
else
drop = generic_drop_inode(inode);
if (!drop && (sb->s_flags & MS_ACTIVE)) {
inode->i_state |= I_REFERENCED;
if (!(inode->i_state & (I_DIRTY|I_SYNC)))
inode_lru_list_add(inode);
spin_unlock(&inode->i_lock);
return;
}
if (!drop) {
inode->i_state |= I_WILL_FREE;
spin_unlock(&inode->i_lock);
write_inode_now(inode, 1);
spin_lock(&inode->i_lock);
fs: new inode i_state corruption fix There was a report of a data corruption http://lkml.org/lkml/2008/11/14/121. There is a script included to reproduce the problem. During testing, I encountered a number of strange things with ext3, so I tried ext2 to attempt to reduce complexity of the problem. I found that fsstress would quickly hang in wait_on_inode, waiting for I_LOCK to be cleared, even though instrumentation showed that unlock_new_inode had already been called for that inode. This points to memory scribble, or synchronisation problme. i_state of I_NEW inodes is not protected by inode_lock because other processes are not supposed to touch them until I_LOCK (and I_NEW) is cleared. Adding WARN_ON(inode->i_state & I_NEW) to sites where we modify i_state revealed that generic_sync_sb_inodes is picking up new inodes from the inode lists and passing them to __writeback_single_inode without waiting for I_NEW. Subsequently modifying i_state causes corruption. In my case it would look like this: CPU0 CPU1 unlock_new_inode() __sync_single_inode() reg <- inode->i_state reg -> reg & ~(I_LOCK|I_NEW) reg <- inode->i_state reg -> inode->i_state reg -> reg | I_SYNC reg -> inode->i_state Non-atomic RMW on CPU1 overwrites CPU0 store and sets I_LOCK|I_NEW again. Fix for this is rather than wait for I_NEW inodes, just skip over them: inodes concurrently being created are not subject to data integrity operations, and should not significantly contribute to dirty memory either. After this change, I'm unable to reproduce any of the added warnings or hangs after ~1hour of running. Previously, the new warnings would start immediately and hang would happen in under 5 minutes. I'm also testing on ext3 now, and so far no problems there either. I don't know whether this fixes the problem reported above, but it fixes a real problem for me. Cc: "Jorge Boncompte [DTI2]" <jorge@dti2.net> Reported-by: Adrian Hunter <ext-adrian.hunter@nokia.com> Cc: Jan Kara <jack@suse.cz> Cc: <stable@kernel.org> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-12 21:31:38 +00:00
WARN_ON(inode->i_state & I_NEW);
inode->i_state &= ~I_WILL_FREE;
}
inode->i_state |= I_FREEING;
if (!list_empty(&inode->i_lru))
inode_lru_list_del(inode);
spin_unlock(&inode->i_lock);
evict(inode);
}
/**
* iput - put an inode
* @inode: inode to put
*
* Puts an inode, dropping its usage count. If the inode use count hits
* zero, the inode is then freed and may also be destroyed.
*
* Consequently, iput() can sleep.
*/
void iput(struct inode *inode)
{
if (inode) {
BUG_ON(inode->i_state & I_CLEAR);
if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock))
iput_final(inode);
}
}
EXPORT_SYMBOL(iput);
/**
* bmap - find a block number in a file
* @inode: inode of file
* @block: block to find
*
* Returns the block number on the device holding the inode that
* is the disk block number for the block of the file requested.
* That is, asked for block 4 of inode 1 the function will return the
* disk block relative to the disk start that holds that block of the
* file.
*/
sector_t bmap(struct inode *inode, sector_t block)
{
sector_t res = 0;
if (inode->i_mapping->a_ops->bmap)
res = inode->i_mapping->a_ops->bmap(inode->i_mapping, block);
return res;
}
EXPORT_SYMBOL(bmap);
/*
* With relative atime, only update atime if the previous atime is
* earlier than either the ctime or mtime or if at least a day has
* passed since the last atime update.
*/
static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
struct timespec now)
{
if (!(mnt->mnt_flags & MNT_RELATIME))
return 1;
/*
* Is mtime younger than atime? If yes, update atime:
*/
if (timespec_compare(&inode->i_mtime, &inode->i_atime) >= 0)
return 1;
/*
* Is ctime younger than atime? If yes, update atime:
*/
if (timespec_compare(&inode->i_ctime, &inode->i_atime) >= 0)
return 1;
/*
* Is the previous atime value older than a day? If yes,
* update atime:
*/
if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60)
return 1;
/*
* Good, we can skip the atime update:
*/
return 0;
}
/**
* touch_atime - update the access time
* @mnt: mount the inode is accessed on
* @dentry: dentry accessed
*
* Update the accessed time on an inode and mark it for writeback.
* This function automatically handles read only file systems and media,
* as well as the "noatime" flag and inode specific "noatime" markers.
*/
void touch_atime(struct vfsmount *mnt, struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
struct timespec now;
if (inode->i_flags & S_NOATIME)
return;
if (IS_NOATIME(inode))
return;
if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
return;
if (mnt->mnt_flags & MNT_NOATIME)
return;
if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
return;
now = current_fs_time(inode->i_sb);
if (!relatime_need_update(mnt, inode, now))
return;
if (timespec_equal(&inode->i_atime, &now))
return;
if (mnt_want_write(mnt))
return;
inode->i_atime = now;
mark_inode_dirty_sync(inode);
mnt_drop_write(mnt);
}
EXPORT_SYMBOL(touch_atime);
/**
* file_update_time - update mtime and ctime time
* @file: file accessed
*
* Update the mtime and ctime members of an inode and mark the inode
* for writeback. Note that this function is meant exclusively for
* usage in the file write path of filesystems, and filesystems may
* choose to explicitly ignore update via this function with the
* S_NOCMTIME inode flag, e.g. for network filesystem where these
* timestamps are handled by the server.
*/
void file_update_time(struct file *file)
{
struct inode *inode = file->f_path.dentry->d_inode;
struct timespec now;
enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
/* First try to exhaust all avenues to not sync */
if (IS_NOCMTIME(inode))
return;
now = current_fs_time(inode->i_sb);
if (!timespec_equal(&inode->i_mtime, &now))
sync_it = S_MTIME;
if (!timespec_equal(&inode->i_ctime, &now))
sync_it |= S_CTIME;
if (IS_I_VERSION(inode))
sync_it |= S_VERSION;
if (!sync_it)
return;
/* Finally allowed to write? Takes lock. */
if (mnt_want_write_file(file))
return;
/* Only change inode inside the lock region */
if (sync_it & S_VERSION)
inode_inc_iversion(inode);
if (sync_it & S_CTIME)
inode->i_ctime = now;
if (sync_it & S_MTIME)
inode->i_mtime = now;
mark_inode_dirty_sync(inode);
mnt_drop_write(file->f_path.mnt);
}
EXPORT_SYMBOL(file_update_time);
int inode_needs_sync(struct inode *inode)
{
if (IS_SYNC(inode))
return 1;
if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
return 1;
return 0;
}
EXPORT_SYMBOL(inode_needs_sync);
int inode_wait(void *word)
{
schedule();
return 0;
}
EXPORT_SYMBOL(inode_wait);
/*
* If we try to find an inode in the inode hash while it is being
* deleted, we have to wait until the filesystem completes its
* deletion before reporting that it isn't found. This function waits
* until the deletion _might_ have completed. Callers are responsible
* to recheck inode state.
*
* It doesn't matter if I_NEW is not set initially, a call to
* wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list
* will DTRT.
*/
static void __wait_on_freeing_inode(struct inode *inode)
{
wait_queue_head_t *wq;
DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
wq = bit_waitqueue(&inode->i_state, __I_NEW);
prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_hash_lock);
schedule();
finish_wait(wq, &wait.wait);
spin_lock(&inode_hash_lock);
}
static __initdata unsigned long ihash_entries;
static int __init set_ihash_entries(char *str)
{
if (!str)
return 0;
ihash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("ihash_entries=", set_ihash_entries);
/*
* Initialize the waitqueues and inode hash table.
*/
void __init inode_init_early(void)
{
int loop;
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
*/
if (hashdist)
return;
inode_hashtable =
alloc_large_system_hash("Inode-cache",
sizeof(struct hlist_head),
ihash_entries,
14,
HASH_EARLY,
&i_hash_shift,
&i_hash_mask,
0);
for (loop = 0; loop < (1 << i_hash_shift); loop++)
INIT_HLIST_HEAD(&inode_hashtable[loop]);
}
void __init inode_init(void)
{
int loop;
/* inode slab cache */
inode_cachep = kmem_cache_create("inode_cache",
sizeof(struct inode),
0,
(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
SLAB_MEM_SPREAD),
init_once);
/* Hash may have been set up in inode_init_early */
if (!hashdist)
return;
inode_hashtable =
alloc_large_system_hash("Inode-cache",
sizeof(struct hlist_head),
ihash_entries,
14,
0,
&i_hash_shift,
&i_hash_mask,
0);
for (loop = 0; loop < (1 << i_hash_shift); loop++)
INIT_HLIST_HEAD(&inode_hashtable[loop]);
}
void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
{
inode->i_mode = mode;
if (S_ISCHR(mode)) {
inode->i_fop = &def_chr_fops;
inode->i_rdev = rdev;
} else if (S_ISBLK(mode)) {
inode->i_fop = &def_blk_fops;
inode->i_rdev = rdev;
} else if (S_ISFIFO(mode))
inode->i_fop = &def_fifo_fops;
else if (S_ISSOCK(mode))
inode->i_fop = &bad_sock_fops;
else
printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for"
" inode %s:%lu\n", mode, inode->i_sb->s_id,
inode->i_ino);
}
EXPORT_SYMBOL(init_special_inode);
/**
* inode_init_owner - Init uid,gid,mode for new inode according to posix standards
* @inode: New inode
* @dir: Directory inode
* @mode: mode of the new inode
*/
void inode_init_owner(struct inode *inode, const struct inode *dir,
mode_t mode)
{
inode->i_uid = current_fsuid();
if (dir && 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;
}
EXPORT_SYMBOL(inode_init_owner);
/**
* inode_owner_or_capable - check current task permissions to inode
* @inode: inode being checked
*
* Return true if current either has CAP_FOWNER to the inode, or
* owns the file.
*/
bool inode_owner_or_capable(const struct inode *inode)
{
struct user_namespace *ns = inode_userns(inode);
if (current_user_ns() == ns && current_fsuid() == inode->i_uid)
return true;
if (ns_capable(ns, CAP_FOWNER))
return true;
return false;
}
EXPORT_SYMBOL(inode_owner_or_capable);