X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Ffs-writeback.c;h=e5eaa62fd17f14e1d1b47c31966f4c1646eafde7;hb=50cca715a64b66ccf173767d94d4020ea0a6129c;hp=0b3064079fa530e9c6d68739d931cff50af069a3;hpb=8bc3be2751b4f74ab90a446da1912fd8204d53f7;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 0b30640..e5eaa62 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -8,7 +8,7 @@ * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * - * 10Apr2002 akpm@zip.com.au + * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ @@ -25,6 +25,45 @@ #include #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); +} + /** * __mark_inode_dirty - internal function * @inode: inode to mark @@ -382,11 +421,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * If we're a pdlfush thread, then implement pdflush collision avoidance * against the entire list. * - * WB_SYNC_HOLD is a hack for sys_sync(): reattach the inode to sb->s_dirty so - * that it can be located for waiting on in __writeback_single_inode(). - * - * Called under inode_lock. - * * 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, @@ -402,11 +436,13 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * 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. */ -static void -sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc) +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); @@ -461,10 +497,6 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc) __iget(inode); pages_skipped = wbc->pages_skipped; __writeback_single_inode(inode, wbc); - if (wbc->sync_mode == WB_SYNC_HOLD) { - inode->dirtied_when = jiffies; - list_move(&inode->i_list, &sb->s_dirty); - } if (current_is_pdflush()) writeback_release(bdi); if (wbc->pages_skipped != pages_skipped) { @@ -485,8 +517,58 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc) 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_WILL_FREE)) + 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. @@ -515,8 +597,7 @@ writeback_inodes(struct writeback_control *wbc) might_sleep(); spin_lock(&sb_lock); restart: - sb = sb_entry(super_blocks.prev); - for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) { + 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++; @@ -527,11 +608,8 @@ restart: * be unmounted by the time it is released. */ if (down_read_trylock(&sb->s_umount)) { - if (sb->s_root) { - spin_lock(&inode_lock); + if (sb->s_root) sync_sb_inodes(sb, wbc); - spin_unlock(&inode_lock); - } up_read(&sb->s_umount); } spin_lock(&sb_lock); @@ -546,8 +624,7 @@ restart: /* * writeback and wait upon the filesystem's dirty inodes. The caller will - * do this in two passes - one to write, and one to wait. WB_SYNC_HOLD is - * used to park the written inodes on sb->s_dirty for the wait pass. + * 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(). @@ -558,34 +635,21 @@ restart: void sync_inodes_sb(struct super_block *sb, int wait) { struct writeback_control wbc = { - .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_HOLD, + .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; - 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) + - nr_dirty + nr_unstable; - wbc.nr_to_write += wbc.nr_to_write / 2; /* Bit more for luck */ - spin_lock(&inode_lock); - sync_sb_inodes(sb, &wbc); - spin_unlock(&inode_lock); -} + if (!wait) { + unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); + unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); -/* - * Rather lame livelock avoidance. - */ -static void set_sb_syncing(int val) -{ - struct super_block *sb; - spin_lock(&sb_lock); - sb = sb_entry(super_blocks.prev); - for (; sb != sb_entry(&super_blocks); sb = sb_entry(sb->s_list.prev)) { - sb->s_syncing = val; - } - spin_unlock(&sb_lock); + 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); } /** @@ -614,9 +678,6 @@ static void __sync_inodes(int wait) spin_lock(&sb_lock); restart: list_for_each_entry(sb, &super_blocks, s_list) { - if (sb->s_syncing) - continue; - sb->s_syncing = 1; sb->s_count++; spin_unlock(&sb_lock); down_read(&sb->s_umount); @@ -634,13 +695,10 @@ restart: void sync_inodes(int wait) { - set_sb_syncing(0); __sync_inodes(0); - if (wait) { - set_sb_syncing(0); + if (wait) __sync_inodes(1); - } } /** @@ -658,7 +716,7 @@ int write_inode_now(struct inode *inode, int sync) int ret; struct writeback_control wbc = { .nr_to_write = LONG_MAX, - .sync_mode = WB_SYNC_ALL, + .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; @@ -750,43 +808,4 @@ int generic_osync_inode(struct inode *inode, struct address_space *mapping, int return err; } - EXPORT_SYMBOL(generic_osync_inode); - -/** - * 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. - */ -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 - */ -void writeback_release(struct backing_dev_info *bdi) -{ - BUG_ON(!writeback_in_progress(bdi)); - clear_bit(BDI_pdflush, &bdi->state); -}