linux-sg2042/fs/inode.c

1711 lines
44 KiB
C
Raw Normal View History

/*
* linux/fs/inode.c
*
* (C) 1997 Linus Torvalds
*/
#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>
2009-09-23 07:43:50 +08:00
#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/ima.h>
/*
* This is needed for the following functions:
* - inode_has_buffers
* - invalidate_bdev
*
* FIXME: remove all knowledge of the buffer layer from this file
*/
#include <linux/buffer_head.h>
/*
* New inode.c implementation.
*
* This implementation has the basic premise of trying
* to be extremely low-overhead and SMP-safe, yet be
* simple enough to be "obviously correct".
*
* Famous last words.
*/
/* inode dynamic allocation 1999, Andrea Arcangeli <andrea@suse.de> */
/* #define INODE_PARANOIA 1 */
/* #define INODE_DEBUG 1 */
/*
* Inode lookup is no longer as critical as it used to be:
* most of the lookups are going to be through the dcache.
*/
#define I_HASHBITS i_hash_shift
#define I_HASHMASK i_hash_mask
static unsigned int i_hash_mask __read_mostly;
static unsigned int i_hash_shift __read_mostly;
/*
* Each inode can be on two separate lists. One is
* the hash list of the inode, used for lookups. The
* other linked list is the "type" list:
* "in_use" - valid inode, i_count > 0, i_nlink > 0
* "dirty" - as "in_use" but also dirty
* "unused" - valid inode, i_count = 0
*
* A "dirty" list is maintained for each super block,
* allowing for low-overhead inode sync() operations.
*/
static LIST_HEAD(inode_lru);
static struct hlist_head *inode_hashtable __read_mostly;
/*
* A simple spinlock to protect the list manipulations.
*
* NOTE! You also have to own the lock if you change
* the i_state of an inode while it is in use..
*/
DEFINE_SPINLOCK(inode_lock);
/*
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>
2009-09-23 07:43:50 +08:00
* iprune_sem provides exclusion between the kswapd or try_to_free_pages
* icache shrinking path, and the umount path. Without this exclusion,
* by the time prune_icache calls iput for the inode whose pages it has
* been invalidating, or by the time it calls clear_inode & destroy_inode
* from its final dispose_list, the struct super_block they refer to
* (for inode->i_sb->s_op) may already have been freed and reused.
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>
2009-09-23 07:43:50 +08:00
*
* We make this an rwsem because the fastpath is icache shrinking. In
* some cases a filesystem may be doing a significant amount of work in
* its inode reclaim code, so this should improve parallelism.
*/
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>
2009-09-23 07:43:50 +08:00
static DECLARE_RWSEM(iprune_sem);
/*
* Statistics gathering..
*/
struct inodes_stat_t inodes_stat;
static struct percpu_counter nr_inodes __cacheline_aligned_in_smp;
static struct percpu_counter nr_inodes_unused __cacheline_aligned_in_smp;
static struct kmem_cache *inode_cachep __read_mostly;
static inline int get_nr_inodes(void)
{
return percpu_counter_sum_positive(&nr_inodes);
}
static inline int get_nr_inodes_unused(void)
{
return percpu_counter_sum_positive(&nr_inodes_unused);
}
int get_nr_dirty_inodes(void)
{
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
static void wake_up_inode(struct inode *inode)
{
/*
* Prevent speculative execution through spin_unlock(&inode_lock);
*/
smp_mb();
wake_up_bit(&inode->i_state, __I_NEW);
}
/**
* 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 address_space_operations empty_aops;
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_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);
init_rwsem(&inode->i_alloc_sem);
lockdep_set_class(&inode->i_alloc_sem, &sb->s_type->i_alloc_sem_key);
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
percpu_counter_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 __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
percpu_counter_dec(&nr_inodes);
}
EXPORT_SYMBOL(__destroy_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
kmem_cache_free(inode_cachep, (inode));
}
/*
* 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);
INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
spin_lock_init(&inode->i_data.tree_lock);
spin_lock_init(&inode->i_data.i_mmap_lock);
INIT_LIST_HEAD(&inode->i_data.private_list);
spin_lock_init(&inode->i_data.private_lock);
INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap);
INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear);
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_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)
{
if (list_empty(&inode->i_lru)) {
list_add(&inode->i_lru, &inode_lru);
percpu_counter_inc(&nr_inodes_unused);
}
}
static void inode_lru_list_del(struct inode *inode)
{
if (!list_empty(&inode->i_lru)) {
list_del_init(&inode->i_lru);
percpu_counter_dec(&nr_inodes_unused);
}
}
static inline void __inode_sb_list_add(struct inode *inode)
{
list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
}
/**
* 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_lock);
__inode_sb_list_add(inode);
spin_unlock(&inode_lock);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);
static inline void __inode_sb_list_del(struct inode *inode)
{
list_del_init(&inode->i_sb_list);
}
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_HASHBITS);
return tmp & I_HASHMASK;
}
/**
* __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_lock);
hlist_add_head(&inode->i_hash, b);
spin_unlock(&inode_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.
*/
static void __remove_inode_hash(struct inode *inode)
{
hlist_del_init(&inode->i_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_lock);
hlist_del_init(&inode->i_hash);
spin_unlock(&inode_lock);
}
EXPORT_SYMBOL(remove_inode_hash);
void end_writeback(struct inode *inode)
{
might_sleep();
BUG_ON(inode->i_data.nrpages);
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);
inode->i_state = I_FREEING | I_CLEAR;
}
EXPORT_SYMBOL(end_writeback);
static void evict(struct inode *inode)
{
const struct super_operations *op = inode->i_sb->s_op;
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);
}
/*
* 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);
[PATCH] bugfix: two read_inode() calls without clear_inode() call between Bug symptoms ~~~~~~~~~~~~ For the same inode VFS calls read_inode() twice and doesn't call clear_inode() between the two read_inode() invocations. Bug description ~~~~~~~~~~~~~~~ Suppose we have an inode which has zero reference count but is still in the inode cache. Suppose kswapd invokes shrink_icache_memory() to free some RAM. In prune_icache() inodes are removed from i_hash. prune_icache () is then going to call clear_inode(), but drops the inode_lock spinlock before this. If in this moment another task calls iget() for an inode which was just removed from i_hash by prune_icache(), then iget() invokes read_inode() for this inode, because it is *already removed* from i_hash. The end result is: we call iget(#N) then iput(#N); inode #N has zero i_count now and is in the inode cache; kswapd starts. kswapd removes the inode #N from i_hash ans is preempted; we call iget(#N) again; read_inode() is invoked as the result; but we expect clear_inode() before. Fix ~~~~~~~ To fix the bug I remove inodes from i_hash later, when clear_inode() is actually called. I remove them from i_hash under spinlock protection. Since the i_state is set to I_FREEING, it is safe to do this. The others will sleep waiting for the inode state change. I also postpone removing inodes from i_sb_list. It is not compulsory to do so but I do it for readability reasons. Inodes are added/removed to the lists together everywhere in the code and there is no point to change this rule. This is harmless because the only user of i_sb_list which somehow may interfere with me (invalidate_list()) is excluded by the iprune_sem mutex. The same race is possible in invalidate_list() so I do the same for it. Acked-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 04:58:12 +08:00
spin_lock(&inode_lock);
__remove_inode_hash(inode);
__inode_sb_list_del(inode);
[PATCH] bugfix: two read_inode() calls without clear_inode() call between Bug symptoms ~~~~~~~~~~~~ For the same inode VFS calls read_inode() twice and doesn't call clear_inode() between the two read_inode() invocations. Bug description ~~~~~~~~~~~~~~~ Suppose we have an inode which has zero reference count but is still in the inode cache. Suppose kswapd invokes shrink_icache_memory() to free some RAM. In prune_icache() inodes are removed from i_hash. prune_icache () is then going to call clear_inode(), but drops the inode_lock spinlock before this. If in this moment another task calls iget() for an inode which was just removed from i_hash by prune_icache(), then iget() invokes read_inode() for this inode, because it is *already removed* from i_hash. The end result is: we call iget(#N) then iput(#N); inode #N has zero i_count now and is in the inode cache; kswapd starts. kswapd removes the inode #N from i_hash ans is preempted; we call iget(#N) again; read_inode() is invoked as the result; but we expect clear_inode() before. Fix ~~~~~~~ To fix the bug I remove inodes from i_hash later, when clear_inode() is actually called. I remove them from i_hash under spinlock protection. Since the i_state is set to I_FREEING, it is safe to do this. The others will sleep waiting for the inode state change. I also postpone removing inodes from i_sb_list. It is not compulsory to do so but I do it for readability reasons. Inodes are added/removed to the lists together everywhere in the code and there is no point to change this rule. This is harmless because the only user of i_sb_list which somehow may interfere with me (invalidate_list()) is excluded by the iprune_sem mutex. The same race is possible in invalidate_list() so I do the same for it. Acked-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 04:58:12 +08:00
spin_unlock(&inode_lock);
wake_up_inode(inode);
destroy_inode(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);
down_write(&iprune_sem);
spin_lock(&inode_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
if (atomic_read(&inode->i_count))
continue;
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
WARN_ON(1);
continue;
}
inode->i_state |= I_FREEING;
/*
* Move the inode off the IO lists and LRU once I_FREEING is
* set so that it won't get moved back on there if it is dirty.
*/
list_move(&inode->i_lru, &dispose);
list_del_init(&inode->i_wb_list);
if (!(inode->i_state & (I_DIRTY | I_SYNC)))
percpu_counter_dec(&nr_inodes_unused);
}
spin_unlock(&inode_lock);
dispose_list(&dispose);
up_write(&iprune_sem);
}
/**
* invalidate_inodes - attempt to free all inodes on a superblock
* @sb: superblock to operate on
*
* Attempts to free all inodes for a given superblock. If there were any
* busy inodes return a non-zero value, else zero.
*/
int invalidate_inodes(struct super_block *sb)
{
int busy = 0;
struct inode *inode, *next;
LIST_HEAD(dispose);
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>
2009-09-23 07:43:50 +08:00
down_write(&iprune_sem);
spin_lock(&inode_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
continue;
if (atomic_read(&inode->i_count)) {
busy = 1;
continue;
}
inode->i_state |= I_FREEING;
/*
* Move the inode off the IO lists and LRU once I_FREEING is
* set so that it won't get moved back on there if it is dirty.
*/
list_move(&inode->i_lru, &dispose);
list_del_init(&inode->i_wb_list);
if (!(inode->i_state & (I_DIRTY | I_SYNC)))
percpu_counter_dec(&nr_inodes_unused);
}
spin_unlock(&inode_lock);
dispose_list(&dispose);
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>
2009-09-23 07:43:50 +08:00
up_write(&iprune_sem);
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;
}
/*
* Scan `goal' inodes on the unused list for freeable ones. They 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.
*/
static void prune_icache(int nr_to_scan)
{
LIST_HEAD(freeable);
int nr_scanned;
unsigned long reap = 0;
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>
2009-09-23 07:43:50 +08:00
down_read(&iprune_sem);
spin_lock(&inode_lock);
for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
struct inode *inode;
if (list_empty(&inode_lru))
break;
inode = list_entry(inode_lru.prev, struct inode, i_lru);
/*
* 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);
percpu_counter_dec(&nr_inodes_unused);
continue;
}
/* recently referenced inodes get one more pass */
if (inode->i_state & I_REFERENCED) {
list_move(&inode->i_lru, &inode_lru);
inode->i_state &= ~I_REFERENCED;
continue;
}
if (inode_has_buffers(inode) || inode->i_data.nrpages) {
__iget(inode);
spin_unlock(&inode_lock);
if (remove_inode_buffers(inode))
reap += invalidate_mapping_pages(&inode->i_data,
0, -1);
iput(inode);
spin_lock(&inode_lock);
if (inode != list_entry(inode_lru.next,
struct inode, i_lru))
continue; /* wrong inode or list_empty */
if (!can_unuse(inode))
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>
2009-03-13 05:31:38 +08:00
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
/*
* Move the inode off the IO lists and LRU once I_FREEING is
* set so that it won't get moved back on there if it is dirty.
*/
list_move(&inode->i_lru, &freeable);
list_del_init(&inode->i_wb_list);
percpu_counter_dec(&nr_inodes_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 16:55:45 +08:00
if (current_is_kswapd())
__count_vm_events(KSWAPD_INODESTEAL, reap);
else
__count_vm_events(PGINODESTEAL, reap);
spin_unlock(&inode_lock);
dispose_list(&freeable);
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>
2009-09-23 07:43:50 +08:00
up_read(&iprune_sem);
}
/*
* shrink_icache_memory() will attempt to reclaim some unused inodes. Here,
* "unused" means that no dentries are referring to the inodes: the files are
* not open and the dcache references to those inodes have already been
* reclaimed.
*
* This function is passed the number of inodes to scan, and it returns the
* total number of remaining possibly-reclaimable inodes.
*/
static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
{
if (nr) {
/*
* Nasty deadlock avoidance. We may hold various FS locks,
* and we don't want to recurse into the FS that called us
* in clear_inode() and friends..
*/
if (!(gfp_mask & __GFP_FS))
return -1;
prune_icache(nr);
}
return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure;
}
static struct shrinker icache_shrinker = {
.shrink = shrink_icache_memory,
.seeks = DEFAULT_SEEKS,
};
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) {
if (inode->i_sb != sb)
continue;
if (!test(inode, data))
continue;
if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
__wait_on_freeing_inode(inode);
goto repeat;
}
__iget(inode);
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) {
if (inode->i_ino != ino)
continue;
if (inode->i_sb != sb)
continue;
if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
__wait_on_freeing_inode(inode);
goto repeat;
}
__iget(inode);
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 - 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 19:03:05 +08:00
* 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 19:03:05 +08:00
* 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_lock);
inode = alloc_inode(sb);
if (inode) {
spin_lock(&inode_lock);
__inode_sb_list_add(inode);
inode->i_state = 0;
spin_unlock(&inode_lock);
}
return inode;
}
EXPORT_SYMBOL(new_inode);
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
/*
* This is special! We do not need the spinlock when clearing I_NEW,
* because we're guaranteed that nobody else tries to do anything about
* the state of the inode when it is locked, as we just created it (so
* there can be no old holders that haven't tested I_NEW).
* However we must emit the memory barrier so that other CPUs reliably
* see the clearing of I_NEW after the other inode initialisation has
* completed.
*/
smp_mb();
WARN_ON(!(inode->i_state & I_NEW));
inode->i_state &= ~I_NEW;
wake_up_inode(inode);
}
EXPORT_SYMBOL(unlock_new_inode);
/*
* This is called without the inode lock held.. Be careful.
*
* We no longer cache the sb_flags in i_flags - see fs.h
* -- rmk@arm.uk.linux.org
*/
static struct inode *get_new_inode(struct super_block *sb,
struct hlist_head *head,
int (*test)(struct inode *, void *),
int (*set)(struct inode *, void *),
void *data)
{
struct inode *inode;
inode = alloc_inode(sb);
if (inode) {
struct inode *old;
spin_lock(&inode_lock);
/* We released the lock, so.. */
old = find_inode(sb, head, test, data);
if (!old) {
if (set(inode, data))
goto set_failed;
hlist_add_head(&inode->i_hash, head);
__inode_sb_list_add(inode);
inode->i_state = I_NEW;
spin_unlock(&inode_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_lock);
destroy_inode(inode);
inode = old;
wait_on_inode(inode);
}
return inode;
set_failed:
spin_unlock(&inode_lock);
destroy_inode(inode);
return NULL;
}
/*
* get_new_inode_fast is the fast path version of get_new_inode, see the
* comment at iget_locked for details.
*/
static struct inode *get_new_inode_fast(struct super_block *sb,
struct hlist_head *head, unsigned long ino)
{
struct inode *inode;
inode = alloc_inode(sb);
if (inode) {
struct inode *old;
spin_lock(&inode_lock);
/* We released the lock, so.. */
old = find_inode_fast(sb, head, ino);
if (!old) {
inode->i_ino = ino;
hlist_add_head(&inode->i_hash, head);
__inode_sb_list_add(inode);
inode->i_state = I_NEW;
spin_unlock(&inode_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_lock);
destroy_inode(inode);
inode = old;
wait_on_inode(inode);
}
return inode;
}
/*
* 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;
hlist_for_each_entry(inode, node, b, i_hash) {
if (inode->i_ino == ino && inode->i_sb == sb)
return 0;
}
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 15:32:29 +08:00
/*
* 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 15:32:29 +08:00
static unsigned int counter;
ino_t res;
spin_lock(&inode_lock);
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);
spin_unlock(&inode_lock);
return res;
}
EXPORT_SYMBOL(iunique);
struct inode *igrab(struct inode *inode)
{
spin_lock(&inode_lock);
if (!(inode->i_state & (I_FREEING|I_WILL_FREE)))
__iget(inode);
else
/*
* 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;
spin_unlock(&inode_lock);
return inode;
}
EXPORT_SYMBOL(igrab);
/**
* ifind - internal function, you want ilookup5() or iget5().
* @sb: super block of file system to search
* @head: the head of the list to search
* @test: callback used for comparisons between inodes
* @data: opaque data pointer to pass to @test
[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 16:10:44 +08:00
* @wait: if true wait for the inode to be unlocked, if false do not
*
* ifind() searches for the inode specified by @data in the inode
* cache. This is a generalized version of ifind_fast() for file systems where
* the inode number is not sufficient for unique identification of an inode.
*
* If the inode is in the cache, the inode is returned with an incremented
* reference count.
*
* Otherwise NULL is returned.
*
* Note, @test is called with the inode_lock held, so can't sleep.
*/
static struct inode *ifind(struct super_block *sb,
struct hlist_head *head, int (*test)(struct inode *, void *),
[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 16:10:44 +08:00
void *data, const int wait)
{
struct inode *inode;
spin_lock(&inode_lock);
inode = find_inode(sb, head, test, data);
if (inode) {
spin_unlock(&inode_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 16:10:44 +08:00
if (likely(wait))
wait_on_inode(inode);
return inode;
}
spin_unlock(&inode_lock);
return NULL;
}
/**
* ifind_fast - internal function, you want ilookup() or iget().
* @sb: super block of file system to search
* @head: head of the list to search
* @ino: inode number to search for
*
* ifind_fast() searches for the inode @ino in the inode cache. This is for
* file systems where the inode number is sufficient for unique identification
* of an inode.
*
* If the inode is in the cache, the inode is returned with an incremented
* reference count.
*
* Otherwise NULL is returned.
*/
static struct inode *ifind_fast(struct super_block *sb,
struct hlist_head *head, unsigned long ino)
{
struct inode *inode;
spin_lock(&inode_lock);
inode = find_inode_fast(sb, head, ino);
if (inode) {
spin_unlock(&inode_lock);
wait_on_inode(inode);
return inode;
}
spin_unlock(&inode_lock);
return NULL;
}
/**
[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 16:10:44 +08:00
* 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
*
* ilookup5() uses ifind() to search for the inode specified by @hashval and
* @data in the inode cache. This is a generalized version of ilookup() for
* file systems where the inode number is not sufficient for unique
* identification of an inode.
*
* If the inode is in the cache, the inode is returned with an incremented
[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 16:10:44 +08:00
* reference count. Note, the inode lock 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.
*
* Otherwise NULL is returned.
*
* Note, @test is called with the inode_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);
return ifind(sb, head, test, data, 0);
}
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
*
* ilookup5() uses ifind() to search for the inode specified by @hashval and
* @data in the inode cache. This is a generalized version of ilookup() for
* file systems where the inode number is not sufficient for unique
* identification of an inode.
*
* If the inode is in the cache, the inode lock is waited upon and the inode is
* returned with an incremented reference count.
*
* Otherwise NULL is returned.
*
* Note, @test is called with the inode_lock held, so can't sleep.
*/
struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data)
{
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
[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 16:10:44 +08:00
return ifind(sb, head, test, data, 1);
}
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
*
* ilookup() uses ifind_fast() to search for the inode @ino in the inode cache.
* This is for file systems where the inode number is sufficient for unique
* identification of an inode.
*
* If the inode is in the cache, the inode is returned with an incremented
* reference count.
*
* Otherwise NULL is returned.
*/
struct inode *ilookup(struct super_block *sb, unsigned long ino)
{
struct hlist_head *head = inode_hashtable + hash(sb, ino);
return ifind_fast(sb, head, ino);
}
EXPORT_SYMBOL(ilookup);
/**
* 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
*
* iget5_locked() uses ifind() to search for the inode specified by @hashval
* and @data in the inode cache and if present it is returned 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, get_new_inode() is called to allocate a new
* inode and this is returned 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_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;
[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 16:10:44 +08:00
inode = ifind(sb, head, test, data, 1);
if (inode)
return inode;
/*
* get_new_inode() will do the right thing, re-trying the search
* in case it had to block at any point.
*/
return get_new_inode(sb, head, test, set, data);
}
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
*
* iget_locked() uses ifind_fast() to search for the inode specified by @ino in
* the inode cache and if present it is returned 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, get_new_inode_fast() is called to allocate a
* new inode and this is returned 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;
inode = ifind_fast(sb, head, ino);
if (inode)
return inode;
/*
* get_new_inode_fast() will do the right thing, re-trying the search
* in case it had to block at any point.
*/
return get_new_inode_fast(sb, head, ino);
}
EXPORT_SYMBOL(iget_locked);
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);
inode->i_state |= I_NEW;
while (1) {
struct hlist_node *node;
struct inode *old = NULL;
spin_lock(&inode_lock);
hlist_for_each_entry(old, node, head, i_hash) {
if (old->i_ino != ino)
continue;
if (old->i_sb != sb)
continue;
if (old->i_state & (I_FREEING|I_WILL_FREE))
continue;
break;
}
if (likely(!node)) {
hlist_add_head(&inode->i_hash, head);
spin_unlock(&inode_lock);
return 0;
}
__iget(old);
spin_unlock(&inode_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);
inode->i_state |= I_NEW;
while (1) {
struct hlist_node *node;
struct inode *old = NULL;
spin_lock(&inode_lock);
hlist_for_each_entry(old, node, head, i_hash) {
if (old->i_sb != sb)
continue;
if (!test(old, data))
continue;
if (old->i_state & (I_FREEING|I_WILL_FREE))
continue;
break;
}
if (likely(!node)) {
hlist_add_head(&inode->i_hash, head);
spin_unlock(&inode_lock);
return 0;
}
__iget(old);
spin_unlock(&inode_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;
if (op && op->drop_inode)
drop = op->drop_inode(inode);
else
drop = generic_drop_inode(inode);
if (!drop) {
if (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_lock);
return;
}
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>
2009-03-13 05:31:38 +08:00
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_WILL_FREE;
spin_unlock(&inode_lock);
write_inode_now(inode, 1);
spin_lock(&inode_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>
2009-03-13 05:31:38 +08:00
WARN_ON(inode->i_state & I_NEW);
inode->i_state &= ~I_WILL_FREE;
__remove_inode_hash(inode);
}
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>
2009-03-13 05:31:38 +08:00
WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
/*
* Move the inode off the IO lists and LRU once I_FREEING is
* set so that it won't get moved back on there if it is dirty.
*/
inode_lru_list_del(inode);
list_del_init(&inode->i_wb_list);
__inode_sb_list_del(inode);
spin_unlock(&inode_lock);
evict(inode);
remove_inode_hash(inode);
[PATCH] fix nr_unused accounting, and avoid recursing in iput with I_WILL_FREE set list_move(&inode->i_list, &inode_in_use); } else { list_move(&inode->i_list, &inode_unused); + inodes_stat.nr_unused++; } } wake_up_inode(inode); Are you sure the above diff is correct? It was added somewhere between 2.6.5 and 2.6.8. I think it's wrong. The only way I can imagine the i_count to be zero in the above path, is that I_WILL_FREE is set. And if I_WILL_FREE is set, then we must not increase nr_unused. So I believe the above change is buggy and it will definitely overstate the number of unused inodes and it should be backed out. Note that __writeback_single_inode before calling __sync_single_inode, can drop the spinlock and we can have both the dirty and locked bitflags clear here: spin_unlock(&inode_lock); __wait_on_inode(inode); iput(inode); XXXXXXX spin_lock(&inode_lock); } use inode again here a construct like the above makes zero sense from a reference counting standpoint. Either we don't ever use the inode again after the iput, or the inode_lock should be taken _before_ executing the iput (i.e. a __iput would be required). Taking the inode_lock after iput means the iget was useless if we keep using the inode after the iput. So the only chance the 2.6 was safe to call __writeback_single_inode with the i_count == 0, is that I_WILL_FREE is set (I_WILL_FREE will prevent the VM to free the inode in XXXXX). Potentially calling the above iput with I_WILL_FREE was also wrong because it would recurse in iput_final (the second mainline bug). The below (untested) patch fixes the nr_unused accounting, avoids recursing in iput when I_WILL_FREE is set and makes sure (with the BUG_ON) that we don't corrupt memory and that all holders that don't set I_WILL_FREE, keeps a reference on the inode! Signed-off-by: Andrea Arcangeli <andrea@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:03:05 +08:00
wake_up_inode(inode);
BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
destroy_inode(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_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_inode() after removing from the hash list will DTRT.
*
* This is called with inode_lock held.
*/
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_lock);
schedule();
finish_wait(wq, &wait.wait);
spin_lock(&inode_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);
register_shrinker(&icache_shrinker);
percpu_counter_init(&nr_inodes, 0);
percpu_counter_init(&nr_inodes_unused, 0);
/* 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);
/**
* 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);