linux/fs/fs-writeback.c

794 lines
22 KiB
C
Raw Normal View History

/*
* fs/fs-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
*
* Contains all the functions related to writing back and waiting
* upon dirty inodes against superblocks, and writing back dirty
* pages against inodes. ie: data writeback. Writeout of the
* inode itself is not handled here.
*
* 10Apr2002 Andrew Morton
* Split out of fs/inode.c
* Additions for address_space-based writeback
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include "internal.h"
/**
* writeback_acquire - attempt to get exclusive writeback access to a device
* @bdi: the device's backing_dev_info structure
*
* It is a waste of resources to have more than one pdflush thread blocked on
* a single request queue. Exclusion at the request_queue level is obtained
* via a flag in the request_queue's backing_dev_info.state.
*
* Non-request_queue-backed address_spaces will share default_backing_dev_info,
* unless they implement their own. Which is somewhat inefficient, as this
* may prevent concurrent writeback against multiple devices.
*/
static int writeback_acquire(struct backing_dev_info *bdi)
{
return !test_and_set_bit(BDI_pdflush, &bdi->state);
}
/**
* writeback_in_progress - determine whether there is writeback in progress
* @bdi: the device's backing_dev_info structure.
*
* Determine whether there is writeback in progress against a backing device.
*/
int writeback_in_progress(struct backing_dev_info *bdi)
{
return test_bit(BDI_pdflush, &bdi->state);
}
/**
* writeback_release - relinquish exclusive writeback access against a device.
* @bdi: the device's backing_dev_info structure
*/
static void writeback_release(struct backing_dev_info *bdi)
{
BUG_ON(!writeback_in_progress(bdi));
clear_bit(BDI_pdflush, &bdi->state);
}
static noinline void block_dump___mark_inode_dirty(struct inode *inode)
{
if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
struct dentry *dentry;
const char *name = "?";
dentry = d_find_alias(inode);
if (dentry) {
spin_lock(&dentry->d_lock);
name = (const char *) dentry->d_name.name;
}
printk(KERN_DEBUG
"%s(%d): dirtied inode %lu (%s) on %s\n",
current->comm, task_pid_nr(current), inode->i_ino,
name, inode->i_sb->s_id);
if (dentry) {
spin_unlock(&dentry->d_lock);
dput(dentry);
}
}
}
/**
* __mark_inode_dirty - internal function
* @inode: inode to mark
* @flags: what kind of dirty (i.e. I_DIRTY_SYNC)
* Mark an inode as dirty. Callers should use mark_inode_dirty or
* mark_inode_dirty_sync.
*
* Put the inode on the super block's dirty list.
*
* CAREFUL! We mark it dirty unconditionally, but move it onto the
* dirty list only if it is hashed or if it refers to a blockdev.
* If it was not hashed, it will never be added to the dirty list
* even if it is later hashed, as it will have been marked dirty already.
*
* In short, make sure you hash any inodes _before_ you start marking
* them dirty.
*
* This function *must* be atomic for the I_DIRTY_PAGES case -
* set_page_dirty() is called under spinlock in several places.
*
* Note that for blockdevs, inode->dirtied_when represents the dirtying time of
* the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of
* the kernel-internal blockdev inode represents the dirtying time of the
* blockdev's pages. This is why for I_DIRTY_PAGES we always use
* page->mapping->host, so the page-dirtying time is recorded in the internal
* blockdev inode.
*/
void __mark_inode_dirty(struct inode *inode, int flags)
{
struct super_block *sb = inode->i_sb;
/*
* Don't do this for I_DIRTY_PAGES - that doesn't actually
* dirty the inode itself
*/
if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
if (sb->s_op->dirty_inode)
sb->s_op->dirty_inode(inode);
}
/*
* make sure that changes are seen by all cpus before we test i_state
* -- mikulas
*/
smp_mb();
/* avoid the locking if we can */
if ((inode->i_state & flags) == flags)
return;
if (unlikely(block_dump))
block_dump___mark_inode_dirty(inode);
spin_lock(&inode_lock);
if ((inode->i_state & flags) != flags) {
const int was_dirty = inode->i_state & I_DIRTY;
inode->i_state |= flags;
/*
* If the inode is being synced, just update its dirty state.
* The unlocker will place the inode on the appropriate
* superblock list, based upon its state.
*/
if (inode->i_state & I_SYNC)
goto out;
/*
* Only add valid (hashed) inodes to the superblock's
* dirty list. Add blockdev inodes as well.
*/
if (!S_ISBLK(inode->i_mode)) {
if (hlist_unhashed(&inode->i_hash))
goto out;
}
if (inode->i_state & (I_FREEING|I_CLEAR))
goto out;
/*
* If the inode was already on s_dirty/s_io/s_more_io, don't
* reposition it (that would break s_dirty time-ordering).
*/
if (!was_dirty) {
inode->dirtied_when = jiffies;
list_move(&inode->i_list, &sb->s_dirty);
}
}
out:
spin_unlock(&inode_lock);
}
EXPORT_SYMBOL(__mark_inode_dirty);
static int write_inode(struct inode *inode, int sync)
{
if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
return inode->i_sb->s_op->write_inode(inode, sync);
return 0;
}
/*
* Redirty an inode: set its when-it-was dirtied timestamp and move it to the
* furthest end of its superblock's dirty-inode list.
*
* Before stamping the inode's ->dirtied_when, we check to see whether it is
* already the most-recently-dirtied inode on the s_dirty list. If that is
* the case then the inode must have been redirtied while it was being written
* out and we don't reset its dirtied_when.
*/
static void redirty_tail(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
if (!list_empty(&sb->s_dirty)) {
struct inode *tail_inode;
tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
writeback: guard against jiffies wraparound on inode->dirtied_when checks (try #3) The dirtied_when value on an inode is supposed to represent the first time that an inode has one of its pages dirtied. This value is in units of jiffies. It's used in several places in the writeback code to determine when to write out an inode. The problem is that these checks assume that dirtied_when is updated periodically. If an inode is continuously being used for I/O it can be persistently marked as dirty and will continue to age. Once the time compared to is greater than or equal to half the maximum of the jiffies type, the logic of the time_*() macros inverts and the opposite of what is needed is returned. On 32-bit architectures that's just under 25 days (assuming HZ == 1000). As the least-recently dirtied inode, it'll end up being the first one that pdflush will try to write out. sync_sb_inodes does this check: /* Was this inode dirtied after sync_sb_inodes was called? */ if (time_after(inode->dirtied_when, start)) break; ...but now dirtied_when appears to be in the future. sync_sb_inodes bails out without attempting to write any dirty inodes. When this occurs, pdflush will stop writing out inodes for this superblock. Nothing can unwedge it until jiffies moves out of the problematic window. This patch fixes this problem by changing the checks against dirtied_when to also check whether it appears to be in the future. If it does, then we consider the value to be far in the past. This should shrink the problematic window of time to such a small period (30s) as not to matter. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Acked-by: Ian Kent <raven@themaw.net> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:56:37 +00:00
if (time_before(inode->dirtied_when,
tail_inode->dirtied_when))
inode->dirtied_when = jiffies;
}
list_move(&inode->i_list, &sb->s_dirty);
}
/*
* requeue inode for re-scanning after sb->s_io list is exhausted.
*/
static void requeue_io(struct inode *inode)
{
list_move(&inode->i_list, &inode->i_sb->s_more_io);
}
static void inode_sync_complete(struct inode *inode)
{
/*
* Prevent speculative execution through spin_unlock(&inode_lock);
*/
smp_mb();
wake_up_bit(&inode->i_state, __I_SYNC);
}
writeback: guard against jiffies wraparound on inode->dirtied_when checks (try #3) The dirtied_when value on an inode is supposed to represent the first time that an inode has one of its pages dirtied. This value is in units of jiffies. It's used in several places in the writeback code to determine when to write out an inode. The problem is that these checks assume that dirtied_when is updated periodically. If an inode is continuously being used for I/O it can be persistently marked as dirty and will continue to age. Once the time compared to is greater than or equal to half the maximum of the jiffies type, the logic of the time_*() macros inverts and the opposite of what is needed is returned. On 32-bit architectures that's just under 25 days (assuming HZ == 1000). As the least-recently dirtied inode, it'll end up being the first one that pdflush will try to write out. sync_sb_inodes does this check: /* Was this inode dirtied after sync_sb_inodes was called? */ if (time_after(inode->dirtied_when, start)) break; ...but now dirtied_when appears to be in the future. sync_sb_inodes bails out without attempting to write any dirty inodes. When this occurs, pdflush will stop writing out inodes for this superblock. Nothing can unwedge it until jiffies moves out of the problematic window. This patch fixes this problem by changing the checks against dirtied_when to also check whether it appears to be in the future. If it does, then we consider the value to be far in the past. This should shrink the problematic window of time to such a small period (30s) as not to matter. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Acked-by: Ian Kent <raven@themaw.net> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:56:37 +00:00
static bool inode_dirtied_after(struct inode *inode, unsigned long t)
{
bool ret = time_after(inode->dirtied_when, t);
#ifndef CONFIG_64BIT
/*
* For inodes being constantly redirtied, dirtied_when can get stuck.
* It _appears_ to be in the future, but is actually in distant past.
* This test is necessary to prevent such wrapped-around relative times
* from permanently stopping the whole pdflush writeback.
*/
ret = ret && time_before_eq(inode->dirtied_when, jiffies);
#endif
return ret;
}
/*
* Move expired dirty inodes from @delaying_queue to @dispatch_queue.
*/
static void move_expired_inodes(struct list_head *delaying_queue,
struct list_head *dispatch_queue,
unsigned long *older_than_this)
{
while (!list_empty(delaying_queue)) {
struct inode *inode = list_entry(delaying_queue->prev,
struct inode, i_list);
if (older_than_this &&
writeback: guard against jiffies wraparound on inode->dirtied_when checks (try #3) The dirtied_when value on an inode is supposed to represent the first time that an inode has one of its pages dirtied. This value is in units of jiffies. It's used in several places in the writeback code to determine when to write out an inode. The problem is that these checks assume that dirtied_when is updated periodically. If an inode is continuously being used for I/O it can be persistently marked as dirty and will continue to age. Once the time compared to is greater than or equal to half the maximum of the jiffies type, the logic of the time_*() macros inverts and the opposite of what is needed is returned. On 32-bit architectures that's just under 25 days (assuming HZ == 1000). As the least-recently dirtied inode, it'll end up being the first one that pdflush will try to write out. sync_sb_inodes does this check: /* Was this inode dirtied after sync_sb_inodes was called? */ if (time_after(inode->dirtied_when, start)) break; ...but now dirtied_when appears to be in the future. sync_sb_inodes bails out without attempting to write any dirty inodes. When this occurs, pdflush will stop writing out inodes for this superblock. Nothing can unwedge it until jiffies moves out of the problematic window. This patch fixes this problem by changing the checks against dirtied_when to also check whether it appears to be in the future. If it does, then we consider the value to be far in the past. This should shrink the problematic window of time to such a small period (30s) as not to matter. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Acked-by: Ian Kent <raven@themaw.net> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:56:37 +00:00
inode_dirtied_after(inode, *older_than_this))
break;
list_move(&inode->i_list, dispatch_queue);
}
}
/*
* Queue all expired dirty inodes for io, eldest first.
*/
static void queue_io(struct super_block *sb,
unsigned long *older_than_this)
{
list_splice_init(&sb->s_more_io, sb->s_io.prev);
move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
}
int sb_has_dirty_inodes(struct super_block *sb)
{
return !list_empty(&sb->s_dirty) ||
!list_empty(&sb->s_io) ||
!list_empty(&sb->s_more_io);
}
EXPORT_SYMBOL(sb_has_dirty_inodes);
/*
* Write a single inode's dirty pages and inode data out to disk.
* If `wait' is set, wait on the writeout.
*
* The whole writeout design is quite complex and fragile. We want to avoid
* starvation of particular inodes when others are being redirtied, prevent
* livelocks, etc.
*
* Called under inode_lock.
*/
static int
__sync_single_inode(struct inode *inode, struct writeback_control *wbc)
{
unsigned dirty;
struct address_space *mapping = inode->i_mapping;
int wait = wbc->sync_mode == WB_SYNC_ALL;
int ret;
BUG_ON(inode->i_state & I_SYNC);
/* Set I_SYNC, reset I_DIRTY */
dirty = inode->i_state & I_DIRTY;
inode->i_state |= I_SYNC;
inode->i_state &= ~I_DIRTY;
spin_unlock(&inode_lock);
ret = do_writepages(mapping, wbc);
/* Don't write the inode if only I_DIRTY_PAGES was set */
if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
int err = write_inode(inode, wait);
if (ret == 0)
ret = err;
}
if (wait) {
int err = filemap_fdatawait(mapping);
if (ret == 0)
ret = err;
}
spin_lock(&inode_lock);
inode->i_state &= ~I_SYNC;
writeback: skip new or to-be-freed inodes 1) I_FREEING tests should be coupled with I_CLEAR The two I_FREEING tests are racy because clear_inode() can set i_state to I_CLEAR between the clear of I_SYNC and the test of I_FREEING. 2) skip I_WILL_FREE inodes in generic_sync_sb_inodes() to avoid possible races with generic_forget_inode() generic_forget_inode() sets I_WILL_FREE call writeback on its own, so generic_sync_sb_inodes() shall not try to step in and create possible races: generic_forget_inode inode->i_state |= I_WILL_FREE; spin_unlock(&inode_lock); generic_sync_sb_inodes() spin_lock(&inode_lock); __iget(inode); __writeback_single_inode // see non zero i_count may WARN here ==> WARN_ON(inode->i_state & I_WILL_FREE); spin_unlock(&inode_lock); may call generic_forget_inode again ==> iput(inode); The above race and warning didn't turn up because writeback_inodes() holds the s_umount lock, so generic_forget_inode() finds MS_ACTIVE and returns early. But we are not sure the UBIFS calls and future callers will guarantee that. So skip I_WILL_FREE inodes for the sake of safety. Cc: Eric Sandeen <sandeen@sandeen.net> Acked-by: Jeff Layton <jlayton@redhat.com> Cc: Masayoshi MIZUMA <m.mizuma@jp.fujitsu.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Acked-by: Jan Kara <jack@suse.cz> 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>
2009-06-16 22:33:17 +00:00
if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
if (!(inode->i_state & I_DIRTY) &&
mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
/*
* We didn't write back all the pages. nfs_writepages()
* sometimes bales out without doing anything. Redirty
* the inode; Move it from s_io onto s_more_io/s_dirty.
*/
/*
* akpm: if the caller was the kupdate function we put
* this inode at the head of s_dirty so it gets first
* consideration. Otherwise, move it to the tail, for
* the reasons described there. I'm not really sure
* how much sense this makes. Presumably I had a good
* reasons for doing it this way, and I'd rather not
* muck with it at present.
*/
if (wbc->for_kupdate) {
/*
* For the kupdate function we move the inode
* to s_more_io so it will get more writeout as
* soon as the queue becomes uncongested.
*/
inode->i_state |= I_DIRTY_PAGES;
writeback: speed up writeback of big dirty files After making dirty a 100M file, the normal behavior is to start the writeback for all data after 30s delays. But sometimes the following happens instead: - after 30s: ~4M - after 5s: ~4M - after 5s: all remaining 92M Some analyze shows that the internal io dispatch queues goes like this: s_io s_more_io ------------------------- 1) 100M,1K 0 2) 1K 96M 3) 0 96M 1) initial state with a 100M file and a 1K file 2) 4M written, nr_to_write <= 0, so write more 3) 1K written, nr_to_write > 0, no more writes(BUG) nr_to_write > 0 in (3) fools the upper layer to think that data have all been written out. The big dirty file is actually still sitting in s_more_io. We cannot simply splice s_more_io back to s_io as soon as s_io becomes empty, and let the loop in generic_sync_sb_inodes() continue: this may starve newly expired inodes in s_dirty. It is also not an option to draw inodes from both s_more_io and s_dirty, an let the loop go on: this might lead to live locks, and might also starve other superblocks in sync time(well kupdate may still starve some superblocks, that's another bug). We have to return when a full scan of s_io completes. So nr_to_write > 0 does not necessarily mean that "all data are written". This patch introduces a flag writeback_control.more_io to indicate that more io should be done. With it the big dirty file no longer has to wait for the next kupdate invokation 5s later. In sync_sb_inodes() we only set more_io on super_blocks we actually visited. This avoids the interaction between two pdflush deamons. Also in __sync_single_inode() we don't blindly keep requeuing the io if the filesystem cannot progress. Failing to do so may lead to 100% iowait. Tested-by: Mike Snitzer <snitzer@gmail.com> Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn> Cc: Michael Rubin <mrubin@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:29:36 +00:00
if (wbc->nr_to_write <= 0) {
/*
* slice used up: queue for next turn
*/
requeue_io(inode);
} else {
/*
* somehow blocked: retry later
*/
redirty_tail(inode);
}
} else {
/*
* Otherwise fully redirty the inode so that
* other inodes on this superblock will get some
* writeout. Otherwise heavy writing to one
* file would indefinitely suspend writeout of
* all the other files.
*/
inode->i_state |= I_DIRTY_PAGES;
redirty_tail(inode);
}
} else if (inode->i_state & I_DIRTY) {
/*
* Someone redirtied the inode while were writing back
* the pages.
*/
redirty_tail(inode);
} else if (atomic_read(&inode->i_count)) {
/*
* The inode is clean, inuse
*/
list_move(&inode->i_list, &inode_in_use);
} else {
/*
* The inode is clean, unused
*/
list_move(&inode->i_list, &inode_unused);
}
}
inode_sync_complete(inode);
return ret;
}
/*
[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>
2005-10-30 23:03:05 +00:00
* Write out an inode's dirty pages. Called under inode_lock. Either the
* caller has ref on the inode (either via __iget or via syscall against an fd)
* or the inode has I_WILL_FREE set (via generic_forget_inode)
*/
static int
[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>
2005-10-30 23:03:05 +00:00
__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
{
wait_queue_head_t *wqh;
[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>
2005-10-30 23:03:05 +00:00
if (!atomic_read(&inode->i_count))
WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
[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>
2005-10-30 23:03:05 +00:00
else
WARN_ON(inode->i_state & I_WILL_FREE);
if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_SYNC)) {
writeback: fix time ordering of the per superblock dirty inode lists 6 Recycling the previous changelog: When the writeback function is operating in writeback-for-flushing mode (as opposed to writeback-for-integrity) and it encounters an I_LOCKed inode, it will skip writing that inode. This is done for throughput and latency: move on to another inode rather than blocking for this one. Writeback skips this inode by moving it off s_io and onto s_dirty, so that writeback can proceed with the other inodes on s_io. However that inode movement can corrupt s_dirty's reverse-time-orderedness. Fix that by using the new redirty_tail(), which will update the refiled inode's dirtied_when field. Note: the behaviour in here is a bit rude: if kupdate happens to come across a locked inode then it will defer writeback of that inode for another 30 seconds. We'll address that in the next patch. Address that here. What we do is to move the skipped inode to the _head_ of s_dirty, immediately eligible for writeout again. Instead of deferring that writeout for another 30 seconds. One would think that this might cause a livelock: we keep on trying to write the same locked inode. But it won't because: a) if that was the case, it would _already_ be happening on the balance_dirty_pages codepath. Because balance_dirty_pages() doesn't care about inode timestamps. b) if we skipped this inode then we won't have done any writeback. The higher-level writeback paths will see that wbc.nr_to_write didn't change and they'll then back off and take a nap. Cc: Mike Waychison <mikew@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 06:30:37 +00:00
/*
* We're skipping this inode because it's locked, and we're not
* doing writeback-for-data-integrity. Move it to s_more_io so
* that writeback can proceed with the other inodes on s_io.
* We'll have another go at writing back this inode when we
* completed a full scan of s_io.
writeback: fix time ordering of the per superblock dirty inode lists 6 Recycling the previous changelog: When the writeback function is operating in writeback-for-flushing mode (as opposed to writeback-for-integrity) and it encounters an I_LOCKed inode, it will skip writing that inode. This is done for throughput and latency: move on to another inode rather than blocking for this one. Writeback skips this inode by moving it off s_io and onto s_dirty, so that writeback can proceed with the other inodes on s_io. However that inode movement can corrupt s_dirty's reverse-time-orderedness. Fix that by using the new redirty_tail(), which will update the refiled inode's dirtied_when field. Note: the behaviour in here is a bit rude: if kupdate happens to come across a locked inode then it will defer writeback of that inode for another 30 seconds. We'll address that in the next patch. Address that here. What we do is to move the skipped inode to the _head_ of s_dirty, immediately eligible for writeout again. Instead of deferring that writeout for another 30 seconds. One would think that this might cause a livelock: we keep on trying to write the same locked inode. But it won't because: a) if that was the case, it would _already_ be happening on the balance_dirty_pages codepath. Because balance_dirty_pages() doesn't care about inode timestamps. b) if we skipped this inode then we won't have done any writeback. The higher-level writeback paths will see that wbc.nr_to_write didn't change and they'll then back off and take a nap. Cc: Mike Waychison <mikew@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 06:30:37 +00:00
*/
requeue_io(inode);
return 0;
}
/*
* It's a data-integrity sync. We must wait.
*/
if (inode->i_state & I_SYNC) {
DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
do {
spin_unlock(&inode_lock);
__wait_on_bit(wqh, &wq, inode_wait,
TASK_UNINTERRUPTIBLE);
spin_lock(&inode_lock);
} while (inode->i_state & I_SYNC);
}
return __sync_single_inode(inode, wbc);
}
/*
* Write out a superblock's list of dirty inodes. A wait will be performed
* upon no inodes, all inodes or the final one, depending upon sync_mode.
*
* If older_than_this is non-NULL, then only write out inodes which
* had their first dirtying at a time earlier than *older_than_this.
*
* If we're a pdflush thread, then implement pdflush collision avoidance
* against the entire list.
*
* If `bdi' is non-zero then we're being asked to writeback a specific queue.
* This function assumes that the blockdev superblock's inodes are backed by
* a variety of queues, so all inodes are searched. For other superblocks,
* assume that all inodes are backed by the same queue.
*
* FIXME: this linear search could get expensive with many fileystems. But
* how to fix? We need to go from an address_space to all inodes which share
* a queue with that address_space. (Easy: have a global "dirty superblocks"
* list).
*
* The inodes to be written are parked on sb->s_io. They are moved back onto
* sb->s_dirty as they are selected for writing. This way, none can be missed
* on the writer throttling path, and we get decent balancing between many
* throttled threads: we don't want them all piling up on inode_sync_wait.
*/
void generic_sync_sb_inodes(struct super_block *sb,
struct writeback_control *wbc)
{
const unsigned long start = jiffies; /* livelock avoidance */
int sync = wbc->sync_mode == WB_SYNC_ALL;
spin_lock(&inode_lock);
if (!wbc->for_kupdate || list_empty(&sb->s_io))
queue_io(sb, wbc->older_than_this);
while (!list_empty(&sb->s_io)) {
struct inode *inode = list_entry(sb->s_io.prev,
struct inode, i_list);
struct address_space *mapping = inode->i_mapping;
struct backing_dev_info *bdi = mapping->backing_dev_info;
long pages_skipped;
if (!bdi_cap_writeback_dirty(bdi)) {
redirty_tail(inode);
if (sb_is_blkdev_sb(sb)) {
/*
* Dirty memory-backed blockdev: the ramdisk
* driver does this. Skip just this inode
*/
continue;
}
/*
* Dirty memory-backed inode against a filesystem other
* than the kernel-internal bdev filesystem. Skip the
* entire superblock.
*/
break;
}
writeback: skip new or to-be-freed inodes 1) I_FREEING tests should be coupled with I_CLEAR The two I_FREEING tests are racy because clear_inode() can set i_state to I_CLEAR between the clear of I_SYNC and the test of I_FREEING. 2) skip I_WILL_FREE inodes in generic_sync_sb_inodes() to avoid possible races with generic_forget_inode() generic_forget_inode() sets I_WILL_FREE call writeback on its own, so generic_sync_sb_inodes() shall not try to step in and create possible races: generic_forget_inode inode->i_state |= I_WILL_FREE; spin_unlock(&inode_lock); generic_sync_sb_inodes() spin_lock(&inode_lock); __iget(inode); __writeback_single_inode // see non zero i_count may WARN here ==> WARN_ON(inode->i_state & I_WILL_FREE); spin_unlock(&inode_lock); may call generic_forget_inode again ==> iput(inode); The above race and warning didn't turn up because writeback_inodes() holds the s_umount lock, so generic_forget_inode() finds MS_ACTIVE and returns early. But we are not sure the UBIFS calls and future callers will guarantee that. So skip I_WILL_FREE inodes for the sake of safety. Cc: Eric Sandeen <sandeen@sandeen.net> Acked-by: Jeff Layton <jlayton@redhat.com> Cc: Masayoshi MIZUMA <m.mizuma@jp.fujitsu.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Acked-by: Jan Kara <jack@suse.cz> 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>
2009-06-16 22:33:17 +00:00
if (inode->i_state & (I_NEW | I_WILL_FREE)) {
fs: new inode i_state corruption fix There was a report of a data corruption http://lkml.org/lkml/2008/11/14/121. There is a script included to reproduce the problem. During testing, I encountered a number of strange things with ext3, so I tried ext2 to attempt to reduce complexity of the problem. I found that fsstress would quickly hang in wait_on_inode, waiting for I_LOCK to be cleared, even though instrumentation showed that unlock_new_inode had already been called for that inode. This points to memory scribble, or synchronisation problme. i_state of I_NEW inodes is not protected by inode_lock because other processes are not supposed to touch them until I_LOCK (and I_NEW) is cleared. Adding WARN_ON(inode->i_state & I_NEW) to sites where we modify i_state revealed that generic_sync_sb_inodes is picking up new inodes from the inode lists and passing them to __writeback_single_inode without waiting for I_NEW. Subsequently modifying i_state causes corruption. In my case it would look like this: CPU0 CPU1 unlock_new_inode() __sync_single_inode() reg <- inode->i_state reg -> reg & ~(I_LOCK|I_NEW) reg <- inode->i_state reg -> inode->i_state reg -> reg | I_SYNC reg -> inode->i_state Non-atomic RMW on CPU1 overwrites CPU0 store and sets I_LOCK|I_NEW again. Fix for this is rather than wait for I_NEW inodes, just skip over them: inodes concurrently being created are not subject to data integrity operations, and should not significantly contribute to dirty memory either. After this change, I'm unable to reproduce any of the added warnings or hangs after ~1hour of running. Previously, the new warnings would start immediately and hang would happen in under 5 minutes. I'm also testing on ext3 now, and so far no problems there either. I don't know whether this fixes the problem reported above, but it fixes a real problem for me. Cc: "Jorge Boncompte [DTI2]" <jorge@dti2.net> Reported-by: Adrian Hunter <ext-adrian.hunter@nokia.com> Cc: Jan Kara <jack@suse.cz> Cc: <stable@kernel.org> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-12 21:31:38 +00:00
requeue_io(inode);
continue;
}
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
if (!sb_is_blkdev_sb(sb))
break; /* Skip a congested fs */
requeue_io(inode);
continue; /* Skip a congested blockdev */
}
if (wbc->bdi && bdi != wbc->bdi) {
if (!sb_is_blkdev_sb(sb))
break; /* fs has the wrong queue */
requeue_io(inode);
continue; /* blockdev has wrong queue */
}
writeback: guard against jiffies wraparound on inode->dirtied_when checks (try #3) The dirtied_when value on an inode is supposed to represent the first time that an inode has one of its pages dirtied. This value is in units of jiffies. It's used in several places in the writeback code to determine when to write out an inode. The problem is that these checks assume that dirtied_when is updated periodically. If an inode is continuously being used for I/O it can be persistently marked as dirty and will continue to age. Once the time compared to is greater than or equal to half the maximum of the jiffies type, the logic of the time_*() macros inverts and the opposite of what is needed is returned. On 32-bit architectures that's just under 25 days (assuming HZ == 1000). As the least-recently dirtied inode, it'll end up being the first one that pdflush will try to write out. sync_sb_inodes does this check: /* Was this inode dirtied after sync_sb_inodes was called? */ if (time_after(inode->dirtied_when, start)) break; ...but now dirtied_when appears to be in the future. sync_sb_inodes bails out without attempting to write any dirty inodes. When this occurs, pdflush will stop writing out inodes for this superblock. Nothing can unwedge it until jiffies moves out of the problematic window. This patch fixes this problem by changing the checks against dirtied_when to also check whether it appears to be in the future. If it does, then we consider the value to be far in the past. This should shrink the problematic window of time to such a small period (30s) as not to matter. Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Acked-by: Ian Kent <raven@themaw.net> Cc: Jens Axboe <jens.axboe@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-02 23:56:37 +00:00
/*
* Was this inode dirtied after sync_sb_inodes was called?
* This keeps sync from extra jobs and livelock.
*/
if (inode_dirtied_after(inode, start))
break;
/* Is another pdflush already flushing this queue? */
if (current_is_pdflush() && !writeback_acquire(bdi))
break;
writeback: skip new or to-be-freed inodes 1) I_FREEING tests should be coupled with I_CLEAR The two I_FREEING tests are racy because clear_inode() can set i_state to I_CLEAR between the clear of I_SYNC and the test of I_FREEING. 2) skip I_WILL_FREE inodes in generic_sync_sb_inodes() to avoid possible races with generic_forget_inode() generic_forget_inode() sets I_WILL_FREE call writeback on its own, so generic_sync_sb_inodes() shall not try to step in and create possible races: generic_forget_inode inode->i_state |= I_WILL_FREE; spin_unlock(&inode_lock); generic_sync_sb_inodes() spin_lock(&inode_lock); __iget(inode); __writeback_single_inode // see non zero i_count may WARN here ==> WARN_ON(inode->i_state & I_WILL_FREE); spin_unlock(&inode_lock); may call generic_forget_inode again ==> iput(inode); The above race and warning didn't turn up because writeback_inodes() holds the s_umount lock, so generic_forget_inode() finds MS_ACTIVE and returns early. But we are not sure the UBIFS calls and future callers will guarantee that. So skip I_WILL_FREE inodes for the sake of safety. Cc: Eric Sandeen <sandeen@sandeen.net> Acked-by: Jeff Layton <jlayton@redhat.com> Cc: Masayoshi MIZUMA <m.mizuma@jp.fujitsu.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Christoph Hellwig <hch@infradead.org> Acked-by: Jan Kara <jack@suse.cz> 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>
2009-06-16 22:33:17 +00:00
BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
__iget(inode);
pages_skipped = wbc->pages_skipped;
__writeback_single_inode(inode, wbc);
if (current_is_pdflush())
writeback_release(bdi);
if (wbc->pages_skipped != pages_skipped) {
/*
* writeback is not making progress due to locked
* buffers. Skip this inode for now.
*/
redirty_tail(inode);
}
spin_unlock(&inode_lock);
iput(inode);
cond_resched();
spin_lock(&inode_lock);
writeback: speed up writeback of big dirty files After making dirty a 100M file, the normal behavior is to start the writeback for all data after 30s delays. But sometimes the following happens instead: - after 30s: ~4M - after 5s: ~4M - after 5s: all remaining 92M Some analyze shows that the internal io dispatch queues goes like this: s_io s_more_io ------------------------- 1) 100M,1K 0 2) 1K 96M 3) 0 96M 1) initial state with a 100M file and a 1K file 2) 4M written, nr_to_write <= 0, so write more 3) 1K written, nr_to_write > 0, no more writes(BUG) nr_to_write > 0 in (3) fools the upper layer to think that data have all been written out. The big dirty file is actually still sitting in s_more_io. We cannot simply splice s_more_io back to s_io as soon as s_io becomes empty, and let the loop in generic_sync_sb_inodes() continue: this may starve newly expired inodes in s_dirty. It is also not an option to draw inodes from both s_more_io and s_dirty, an let the loop go on: this might lead to live locks, and might also starve other superblocks in sync time(well kupdate may still starve some superblocks, that's another bug). We have to return when a full scan of s_io completes. So nr_to_write > 0 does not necessarily mean that "all data are written". This patch introduces a flag writeback_control.more_io to indicate that more io should be done. With it the big dirty file no longer has to wait for the next kupdate invokation 5s later. In sync_sb_inodes() we only set more_io on super_blocks we actually visited. This avoids the interaction between two pdflush deamons. Also in __sync_single_inode() we don't blindly keep requeuing the io if the filesystem cannot progress. Failing to do so may lead to 100% iowait. Tested-by: Mike Snitzer <snitzer@gmail.com> Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn> Cc: Michael Rubin <mrubin@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:29:36 +00:00
if (wbc->nr_to_write <= 0) {
wbc->more_io = 1;
break;
writeback: speed up writeback of big dirty files After making dirty a 100M file, the normal behavior is to start the writeback for all data after 30s delays. But sometimes the following happens instead: - after 30s: ~4M - after 5s: ~4M - after 5s: all remaining 92M Some analyze shows that the internal io dispatch queues goes like this: s_io s_more_io ------------------------- 1) 100M,1K 0 2) 1K 96M 3) 0 96M 1) initial state with a 100M file and a 1K file 2) 4M written, nr_to_write <= 0, so write more 3) 1K written, nr_to_write > 0, no more writes(BUG) nr_to_write > 0 in (3) fools the upper layer to think that data have all been written out. The big dirty file is actually still sitting in s_more_io. We cannot simply splice s_more_io back to s_io as soon as s_io becomes empty, and let the loop in generic_sync_sb_inodes() continue: this may starve newly expired inodes in s_dirty. It is also not an option to draw inodes from both s_more_io and s_dirty, an let the loop go on: this might lead to live locks, and might also starve other superblocks in sync time(well kupdate may still starve some superblocks, that's another bug). We have to return when a full scan of s_io completes. So nr_to_write > 0 does not necessarily mean that "all data are written". This patch introduces a flag writeback_control.more_io to indicate that more io should be done. With it the big dirty file no longer has to wait for the next kupdate invokation 5s later. In sync_sb_inodes() we only set more_io on super_blocks we actually visited. This avoids the interaction between two pdflush deamons. Also in __sync_single_inode() we don't blindly keep requeuing the io if the filesystem cannot progress. Failing to do so may lead to 100% iowait. Tested-by: Mike Snitzer <snitzer@gmail.com> Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn> Cc: Michael Rubin <mrubin@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:29:36 +00:00
}
if (!list_empty(&sb->s_more_io))
wbc->more_io = 1;
}
if (sync) {
struct inode *inode, *old_inode = NULL;
/*
* Data integrity sync. Must wait for all pages under writeback,
* because there may have been pages dirtied before our sync
* call, but which had writeout started before we write it out.
* In which case, the inode may not be on the dirty list, but
* we still have to wait for that writeout.
*/
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
struct address_space *mapping;
if (inode->i_state &
(I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue;
mapping = inode->i_mapping;
if (mapping->nrpages == 0)
continue;
__iget(inode);
spin_unlock(&inode_lock);
/*
* We hold a reference to 'inode' so it couldn't have
* been removed from s_inodes list while we dropped the
* inode_lock. We cannot iput the inode now as we can
* be holding the last reference and we cannot iput it
* under inode_lock. So we keep the reference and iput
* it later.
*/
iput(old_inode);
old_inode = inode;
filemap_fdatawait(mapping);
cond_resched();
spin_lock(&inode_lock);
}
spin_unlock(&inode_lock);
iput(old_inode);
} else
spin_unlock(&inode_lock);
return; /* Leave any unwritten inodes on s_io */
}
EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
static void sync_sb_inodes(struct super_block *sb,
struct writeback_control *wbc)
{
generic_sync_sb_inodes(sb, wbc);
}
/*
* Start writeback of dirty pagecache data against all unlocked inodes.
*
* Note:
* We don't need to grab a reference to superblock here. If it has non-empty
* ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
* past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all
* empty. Since __sync_single_inode() regains inode_lock before it finally moves
* inode from superblock lists we are OK.
*
* If `older_than_this' is non-zero then only flush inodes which have a
* flushtime older than *older_than_this.
*
* If `bdi' is non-zero then we will scan the first inode against each
* superblock until we find the matching ones. One group will be the dirty
* inodes against a filesystem. Then when we hit the dummy blockdev superblock,
* sync_sb_inodes will seekout the blockdev which matches `bdi'. Maybe not
* super-efficient but we're about to do a ton of I/O...
*/
void
writeback_inodes(struct writeback_control *wbc)
{
struct super_block *sb;
might_sleep();
spin_lock(&sb_lock);
restart:
list_for_each_entry_reverse(sb, &super_blocks, s_list) {
if (sb_has_dirty_inodes(sb)) {
/* we're making our own get_super here */
sb->s_count++;
spin_unlock(&sb_lock);
/*
* If we can't get the readlock, there's no sense in
* waiting around, most of the time the FS is going to
* be unmounted by the time it is released.
*/
if (down_read_trylock(&sb->s_umount)) {
if (sb->s_root)
sync_sb_inodes(sb, wbc);
up_read(&sb->s_umount);
}
spin_lock(&sb_lock);
if (__put_super_and_need_restart(sb))
goto restart;
}
if (wbc->nr_to_write <= 0)
break;
}
spin_unlock(&sb_lock);
}
/*
* writeback and wait upon the filesystem's dirty inodes. The caller will
* do this in two passes - one to write, and one to wait.
*
* A finite limit is set on the number of pages which will be written.
* To prevent infinite livelock of sys_sync().
*
* We add in the number of potentially dirty inodes, because each inode write
* can dirty pagecache in the underlying blockdev.
*/
void sync_inodes_sb(struct super_block *sb, int wait)
{
struct writeback_control wbc = {
.sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:26 +00:00
.range_start = 0,
.range_end = LLONG_MAX,
};
if (!wait) {
unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
wbc.nr_to_write = nr_dirty + nr_unstable +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
} else
wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */
sync_sb_inodes(sb, &wbc);
}
/**
[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>
2005-10-30 23:03:05 +00:00
* write_inode_now - write an inode to disk
* @inode: inode to write to disk
* @sync: whether the write should be synchronous or not
*
* This function commits an inode to disk immediately if it is dirty. This is
* primarily needed by knfsd.
*
[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>
2005-10-30 23:03:05 +00:00
* The caller must either have a ref on the inode or must have set I_WILL_FREE.
*/
int write_inode_now(struct inode *inode, int sync)
{
int ret;
struct writeback_control wbc = {
.nr_to_write = LONG_MAX,
.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
[PATCH] writeback: fix range handling When a writeback_control's `start' and `end' fields are used to indicate a one-byte-range starting at file offset zero, the required values of .start=0,.end=0 mean that the ->writepages() implementation has no way of telling that it is being asked to perform a range request. Because we're currently overloading (start == 0 && end == 0) to mean "this is not a write-a-range request". To make all this sane, the patch changes range of writeback_control. So caller does: If it is calling ->writepages() to write pages, it sets range (range_start/end or range_cyclic) always. And if range_cyclic is true, ->writepages() thinks the range is cyclic, otherwise it just uses range_start and range_end. This patch does, - Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h -1 is usually ok for range_end (type is long long). But, if someone did, range_end += val; range_end is "val - 1" u64val = range_end >> bits; u64val is "~(0ULL)" or something, they are wrong. So, this adds LLONG_MAX to avoid nasty things, and uses LLONG_MAX for range_end. - All callers of ->writepages() sets range_start/end or range_cyclic. - Fix updates of ->writeback_index. It seems already bit strange. If it starts at 0 and ended by check of nr_to_write, this last index may reduce chance to scan end of file. So, this updates ->writeback_index only if range_cyclic is true or whole-file is scanned. Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Nathan Scott <nathans@sgi.com> Cc: Anton Altaparmakov <aia21@cantab.net> Cc: Steven French <sfrench@us.ibm.com> Cc: "Vladimir V. Saveliev" <vs@namesys.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:26 +00:00
.range_start = 0,
.range_end = LLONG_MAX,
};
if (!mapping_cap_writeback_dirty(inode->i_mapping))
wbc.nr_to_write = 0;
might_sleep();
spin_lock(&inode_lock);
ret = __writeback_single_inode(inode, &wbc);
spin_unlock(&inode_lock);
if (sync)
inode_sync_wait(inode);
return ret;
}
EXPORT_SYMBOL(write_inode_now);
/**
* sync_inode - write an inode and its pages to disk.
* @inode: the inode to sync
* @wbc: controls the writeback mode
*
* sync_inode() will write an inode and its pages to disk. It will also
* correctly update the inode on its superblock's dirty inode lists and will
* update inode->i_state.
*
* The caller must have a ref on the inode.
*/
int sync_inode(struct inode *inode, struct writeback_control *wbc)
{
int ret;
spin_lock(&inode_lock);
ret = __writeback_single_inode(inode, wbc);
spin_unlock(&inode_lock);
return ret;
}
EXPORT_SYMBOL(sync_inode);
/**
* generic_osync_inode - flush all dirty data for a given inode to disk
* @inode: inode to write
* @mapping: the address_space that should be flushed
* @what: what to write and wait upon
*
* This can be called by file_write functions for files which have the
* O_SYNC flag set, to flush dirty writes to disk.
*
* @what is a bitmask, specifying which part of the inode's data should be
* written and waited upon.
*
* OSYNC_DATA: i_mapping's dirty data
* OSYNC_METADATA: the buffers at i_mapping->private_list
* OSYNC_INODE: the inode itself
*/
int generic_osync_inode(struct inode *inode, struct address_space *mapping, int what)
{
int err = 0;
int need_write_inode_now = 0;
int err2;
if (what & OSYNC_DATA)
err = filemap_fdatawrite(mapping);
if (what & (OSYNC_METADATA|OSYNC_DATA)) {
err2 = sync_mapping_buffers(mapping);
if (!err)
err = err2;
}
if (what & OSYNC_DATA) {
err2 = filemap_fdatawait(mapping);
if (!err)
err = err2;
}
spin_lock(&inode_lock);
if ((inode->i_state & I_DIRTY) &&
((what & OSYNC_INODE) || (inode->i_state & I_DIRTY_DATASYNC)))
need_write_inode_now = 1;
spin_unlock(&inode_lock);
if (need_write_inode_now) {
err2 = write_inode_now(inode, 1);
if (!err)
err = err2;
}
else
inode_sync_wait(inode);
return err;
}
EXPORT_SYMBOL(generic_osync_inode);