From 72d0d248ca8232dbd30d35b42d0d86e39b3e322b Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 16 Jul 2012 15:23:48 -0400 Subject: fuse: add FUSE_AUTO_INVAL_DATA init flag FUSE_AUTO_INVAL_DATA is provided to enable updated/auto cache invalidation logic. Signed-off-by: Brian Foster Signed-off-by: Miklos Szeredi --- fs/fuse/fuse_i.h | 3 +++ fs/fuse/inode.c | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 771fb6322c0..e24dd74e306 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -484,6 +484,9 @@ struct fuse_conn { /** Is fallocate not implemented by fs? */ unsigned no_fallocate:1; + /** Use enhanced/automatic page cache invalidation. */ + unsigned auto_inval_data:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 1cd61652018..dd37ee291b8 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -834,6 +834,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->big_writes = 1; if (arg->flags & FUSE_DONT_MASK) fc->dont_mask = 1; + if (arg->flags & FUSE_AUTO_INVAL_DATA) + fc->auto_inval_data = 1; } else { ra_pages = fc->max_read / PAGE_CACHE_SIZE; fc->no_lock = 1; @@ -859,7 +861,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE; arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | - FUSE_FLOCK_LOCKS; + FUSE_FLOCK_LOCKS | FUSE_AUTO_INVAL_DATA; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); -- cgit v1.2.3-70-g09d2 From eed2179efe1aac145bf6d54b925b750976380fa6 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 16 Jul 2012 15:23:49 -0400 Subject: fuse: invalidate inode mapping if mtime changes We currently invalidate the inode address space mapping if the file size changes unexpectedly. In the case of a fuse network filesystem, a portion of a file could be overwritten remotely without changing the file size. Compare the old mtime as well to detect this condition and invalidate the mapping if the file has been updated. The original logic (to ignore changes in mtime) is preserved unless the client specifies FUSE_AUTO_INVAL_DATA on init. Signed-off-by: Brian Foster Signed-off-by: Miklos Szeredi --- fs/fuse/inode.c | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index dd37ee291b8..dd4401650b4 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -197,6 +197,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); loff_t oldsize; + struct timespec old_mtime; spin_lock(&fc->lock); if (attr_version != 0 && fi->attr_version > attr_version) { @@ -204,15 +205,35 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, return; } + old_mtime = inode->i_mtime; fuse_change_attributes_common(inode, attr, attr_valid); oldsize = inode->i_size; i_size_write(inode, attr->size); spin_unlock(&fc->lock); - if (S_ISREG(inode->i_mode) && oldsize != attr->size) { - truncate_pagecache(inode, oldsize, attr->size); - invalidate_inode_pages2(inode->i_mapping); + if (S_ISREG(inode->i_mode)) { + bool inval = false; + + if (oldsize != attr->size) { + truncate_pagecache(inode, oldsize, attr->size); + inval = true; + } else if (fc->auto_inval_data) { + struct timespec new_mtime = { + .tv_sec = attr->mtime, + .tv_nsec = attr->mtimensec, + }; + + /* + * Auto inval mode also checks and invalidates if mtime + * has changed. + */ + if (!timespec_equal(&old_mtime, &new_mtime)) + inval = true; + } + + if (inval) + invalidate_inode_pages2(inode->i_mapping); } } -- cgit v1.2.3-70-g09d2 From a8894274a3581125fb311eabfc97cd0123740c5e Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 16 Jul 2012 15:23:50 -0400 Subject: fuse: update attributes on aio_read A fuse-based network filesystem might allow for the inode and/or file data to change unexpectedly. A local client that opens and repeatedly reads a file might never pick up on such changes and indefinitely return stale data. Always invoke fuse_update_attributes() in the read path to cause an attr revalidation when the attributes expire. This leads to a page cache invalidation if necessary and ensures fuse issues new read requests to the fuse client. The original logic (reval only on reads beyond EOF) is preserved unless the client specifies FUSE_AUTO_INVAL_DATA on init. Signed-off-by: Brian Foster Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index b321a688cde..5800101e5ce 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -703,13 +703,16 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); - if (pos + iov_length(iov, nr_segs) > i_size_read(inode)) { + /* + * In auto invalidate mode, always update attributes on read. + * Otherwise, only update if we attempt to read past EOF (to ensure + * i_size is up to date). + */ + if (fc->auto_inval_data || + (pos + iov_length(iov, nr_segs) > i_size_read(inode))) { int err; - /* - * If trying to read past EOF, make sure the i_size - * attribute is up-to-date. - */ err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL); if (err) return err; -- cgit v1.2.3-70-g09d2 From 69fe05c90ed58aac956dccb9e6d3a325fb3b8767 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 18 Jul 2012 16:09:40 +0200 Subject: fuse: add missing INIT flags Add missing flags that userspace derived from the protocol version number. This makes the protocol more flexible. Signed-off-by: Miklos Szeredi --- fs/fuse/inode.c | 3 ++- include/linux/fuse.h | 8 ++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index dd4401650b4..ce0a2838ccd 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -882,7 +882,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE; arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | - FUSE_FLOCK_LOCKS | FUSE_AUTO_INVAL_DATA; + FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | + FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); diff --git a/include/linux/fuse.h b/include/linux/fuse.h index e4a9d2af9aa..6455c5b64c2 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -169,7 +169,11 @@ struct fuse_file_lock { * FUSE_POSIX_LOCKS: remote locking for POSIX file locks * FUSE_EXPORT_SUPPORT: filesystem handles lookups of "." and ".." * FUSE_DONT_MASK: don't apply umask to file mode on create operations + * FUSE_SPLICE_WRITE: kernel supports splice write on the device + * FUSE_SPLICE_MOVE: kernel supports splice move on the device + * FUSE_SPLICE_READ: kernel supports splice read on the device * FUSE_FLOCK_LOCKS: remote locking for BSD style file locks + * FUSE_HAS_IOCTL_DIR: kernel supports ioctl on directories * FUSE_AUTO_INVAL_DATA: automatically invalidate cached pages */ #define FUSE_ASYNC_READ (1 << 0) @@ -179,7 +183,11 @@ struct fuse_file_lock { #define FUSE_EXPORT_SUPPORT (1 << 4) #define FUSE_BIG_WRITES (1 << 5) #define FUSE_DONT_MASK (1 << 6) +#define FUSE_SPLICE_WRITE (1 << 7) +#define FUSE_SPLICE_MOVE (1 << 8) +#define FUSE_SPLICE_READ (1 << 9) #define FUSE_FLOCK_LOCKS (1 << 10) +#define FUSE_HAS_IOCTL_DIR (1 << 11) #define FUSE_AUTO_INVAL_DATA (1 << 12) /** -- cgit v1.2.3-70-g09d2 From 0e8d96dd2c99405c707f540b5922ec869b848979 Mon Sep 17 00:00:00 2001 From: Kautuk Consul Date: Mon, 20 Feb 2012 03:46:12 -0500 Subject: exofs: readpage_strip: Add a BUG_ON to check for PageLocked(page) readpage_strip can be called from several code paths all of which require that the page be locked before any operations are carried out. Since we export the exofs_readpage callback to the VFS, add a BUG_ON to check for PageLocked(page) to make sure that this understanding is never compromised. Signed-off-by: Kautuk Consul Signed-off-by: Boaz Harrosh --- fs/exofs/inode.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 5badb0c039d..9a5ed30b8a3 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -389,6 +389,8 @@ static int readpage_strip(void *data, struct page *page) size_t len; int ret; + BUG_ON(!PageLocked(page)); + /* FIXME: Just for debugging, will be removed */ if (PageUptodate(page)) EXOFS_ERR("PageUptodate(0x%lx, 0x%lx)\n", pcol->inode->i_ino, -- cgit v1.2.3-70-g09d2 From 66153f6e0f89c75d18e490739b0149dfd2e53b69 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 4 Jun 2012 14:48:27 +0300 Subject: exofs: stop using s_dirt Exofs has the '->write_super()' handler and makes some use of the '->s_dirt' superblock flag, but it really needs neither of them because it never sets 's_dirt' to one which means the VFS never calls its '->write_super()' handler. Thus, remove both. Note, I am trying to remove both 's_dirt' and 'write_super()' from VFS altogether once all users are gone. Signed-off-by: Artem Bityutskiy Signed-off-by: Boaz Harrosh --- fs/exofs/super.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'fs') diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 433783624d1..dde41a75c7c 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -400,8 +400,6 @@ static int exofs_sync_fs(struct super_block *sb, int wait) ret = ore_write(ios); if (unlikely(ret)) EXOFS_ERR("%s: ore_write failed.\n", __func__); - else - sb->s_dirt = 0; unlock_super(sb); @@ -412,14 +410,6 @@ out: return ret; } -static void exofs_write_super(struct super_block *sb) -{ - if (!(sb->s_flags & MS_RDONLY)) - exofs_sync_fs(sb, 1); - else - sb->s_dirt = 0; -} - static void _exofs_print_device(const char *msg, const char *dev_path, struct osd_dev *od, u64 pid) { @@ -952,7 +942,6 @@ static const struct super_operations exofs_sops = { .write_inode = exofs_write_inode, .evict_inode = exofs_evict_inode, .put_super = exofs_put_super, - .write_super = exofs_write_super, .sync_fs = exofs_sync_fs, .statfs = exofs_statfs, }; -- cgit v1.2.3-70-g09d2 From 4b74f6ea8417e48bb1fc65880a0574134a8b4745 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Fri, 20 Jul 2012 15:50:27 +0300 Subject: exofs: Fix __r4w_get_page when offset is beyond i_size It is very common for the end of the file to be unaligned on stripe size. But since we know it's beyond file's end then the XOR should be preformed with all zeros. Old code used to just read zeros out of the OSD devices, which is a great waist. But what scares me more about this situation is that, we now have pages attached to the file's mapping that are beyond i_size. I don't like the kind of bugs this calls for. Fix both birds, by returning a global ZERO_PAGE, if offset is beyond i_size. Signed-off-by: Boaz Harrosh --- fs/exofs/inode.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 9a5ed30b8a3..3b2ee72aecb 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -574,8 +574,16 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) if (!pcol->that_locked_page || (pcol->that_locked_page->index != index)) { - struct page *page = find_get_page(pcol->inode->i_mapping, index); + struct page *page; + loff_t i_size = i_size_read(pcol->inode); + if (offset >= i_size) { + *uptodate = true; + EXOFS_DBGMSG("offset >= i_size index=0x%lx\n", index); + return ZERO_PAGE(0); + } + + page = find_get_page(pcol->inode->i_mapping, index); if (!page) { page = find_or_create_page(pcol->inode->i_mapping, index, GFP_NOFS); @@ -604,12 +612,13 @@ static void __r4w_put_page(void *priv, struct page *page) { struct page_collect *pcol = priv; - if (pcol->that_locked_page != page) { + if ((pcol->that_locked_page != page) && (ZERO_PAGE(0) != page)) { EXOFS_DBGMSG("index=0x%lx\n", page->index); page_cache_release(page); return; } - EXOFS_DBGMSG("that_locked_page index=0x%lx\n", page->index); + EXOFS_DBGMSG("that_locked_page index=0x%lx\n", + ZERO_PAGE(0) == page ? -1 : page->index); } static const struct _ore_r4w_op _r4w_op = { -- cgit v1.2.3-70-g09d2 From be388f3d9af4155db0dc9e7e59dd49db90271c1c Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Thu, 2 Aug 2012 14:59:57 +0300 Subject: exofs: Use proper max_IO calculations from ore exofs_max_io_pages should just use the ORE's calculated layout->max_io_length, And avoid unnecessary BUGs, calculations made here were also a layering violation. Signed-off-by: Boaz Harrosh --- fs/exofs/inode.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 3b2ee72aecb..1562c27a2fa 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -37,15 +37,12 @@ #define EXOFS_DBGMSG2(M...) do {} while (0) -enum {MAX_PAGES_KMALLOC = PAGE_SIZE / sizeof(struct page *), }; - unsigned exofs_max_io_pages(struct ore_layout *layout, unsigned expected_pages) { - unsigned pages = min_t(unsigned, expected_pages, MAX_PAGES_KMALLOC); + unsigned pages = min_t(unsigned, expected_pages, + layout->max_io_length / PAGE_SIZE); - /* TODO: easily support bio chaining */ - pages = min_t(unsigned, pages, layout->max_io_length / PAGE_SIZE); return pages; } @@ -101,7 +98,8 @@ static void _pcol_reset(struct page_collect *pcol) * it might not end here. don't be left with nothing */ if (!pcol->expected_pages) - pcol->expected_pages = MAX_PAGES_KMALLOC; + pcol->expected_pages = + exofs_max_io_pages(&pcol->sbi->layout, ~0); } static int pcol_try_alloc(struct page_collect *pcol) -- cgit v1.2.3-70-g09d2 From 9e62bb4458ad2cf28bd701aa5fab380b846db326 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Wed, 1 Aug 2012 17:48:36 +0300 Subject: ore: Fix out-of-bounds access in _ios_obj() _ios_obj() is accessed by group_index not device_table index. The oc->comps array is only a group_full of devices at a time it is not like ore_comp_dev() which is indexed by a global device_table index. This did not BUG until now because exofs only uses a single COMP for all devices. But with other FSs like PanFS this is not true. This bug was only in the write_path, all other users were using it correctly [This is a bug since 3.2 Kernel] CC: Stable Tree Signed-off-by: Boaz Harrosh --- fs/exofs/ore.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'fs') diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 24a49d47e93..1585db1aa36 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -837,11 +837,11 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp) bio->bi_rw |= REQ_WRITE; } - osd_req_write(or, _ios_obj(ios, dev), per_dev->offset, - bio, per_dev->length); + osd_req_write(or, _ios_obj(ios, cur_comp), + per_dev->offset, bio, per_dev->length); ORE_DBGMSG("write(0x%llx) offset=0x%llx " "length=0x%llx dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), _LLU(per_dev->offset), _LLU(per_dev->length), dev); } else if (ios->kern_buff) { @@ -853,20 +853,20 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp) (ios->si.unit_off + ios->length > ios->layout->stripe_unit)); - ret = osd_req_write_kern(or, _ios_obj(ios, per_dev->dev), + ret = osd_req_write_kern(or, _ios_obj(ios, cur_comp), per_dev->offset, ios->kern_buff, ios->length); if (unlikely(ret)) goto out; ORE_DBGMSG2("write_kern(0x%llx) offset=0x%llx " "length=0x%llx dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), _LLU(per_dev->offset), _LLU(ios->length), per_dev->dev); } else { - osd_req_set_attributes(or, _ios_obj(ios, dev)); + osd_req_set_attributes(or, _ios_obj(ios, cur_comp)); ORE_DBGMSG2("obj(0x%llx) set_attributes=%d dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), ios->out_attr_len, dev); } -- cgit v1.2.3-70-g09d2 From f0cd2dbb6cf387c11f87265462e370bb5469299e Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:11:59 +0300 Subject: vfs: kill write_super and sync_supers Finally we can kill the 'sync_supers' kernel thread along with the '->write_super()' superblock operation because all the users are gone. Now every file-system is supposed to self-manage own superblock and its dirty state. The nice thing about killing this thread is that it improves power management. Indeed, 'sync_supers' is a source of monotonic system wake-ups - it woke up every 5 seconds no matter what - even if there were no dirty superblocks and even if there were no file-systems using this service (e.g., btrfs and journalled ext4 do not need it). So it was wasting power most of the time. And because the thread was in the core of the kernel, all systems had to have it. So I am quite happy to make it go away. Interestingly, this thread is a left-over from the pdflush kernel thread which was a self-forking kernel thread responsible for all the write-back in old Linux kernels. It was turned into per-block device BDI threads, and 'sync_supers' was a left-over. Thus, R.I.P, pdflush as well. Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/super.c | 40 ---------------------------------- include/linux/backing-dev.h | 1 - include/linux/fs.h | 3 --- mm/backing-dev.c | 52 --------------------------------------------- mm/page-writeback.c | 1 - 5 files changed, 97 deletions(-) (limited to 'fs') diff --git a/fs/super.c b/fs/super.c index b05cf47463d..0902cfa6a12 100644 --- a/fs/super.c +++ b/fs/super.c @@ -536,46 +536,6 @@ void drop_super(struct super_block *sb) EXPORT_SYMBOL(drop_super); -/** - * sync_supers - helper for periodic superblock writeback - * - * Call the write_super method if present on all dirty superblocks in - * the system. This is for the periodic writeback used by most older - * filesystems. For data integrity superblock writeback use - * sync_filesystems() instead. - * - * Note: check the dirty flag before waiting, so we don't - * hold up the sync while mounting a device. (The newly - * mounted device won't need syncing.) - */ -void sync_supers(void) -{ - struct super_block *sb, *p = NULL; - - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (hlist_unhashed(&sb->s_instances)) - continue; - if (sb->s_op->write_super && sb->s_dirt) { - sb->s_count++; - spin_unlock(&sb_lock); - - down_read(&sb->s_umount); - if (sb->s_root && sb->s_dirt && (sb->s_flags & MS_BORN)) - sb->s_op->write_super(sb); - up_read(&sb->s_umount); - - spin_lock(&sb_lock); - if (p) - __put_super(p); - p = sb; - } - } - if (p) - __put_super(p); - spin_unlock(&sb_lock); -} - /** * iterate_supers - call function for all active superblocks * @f: function to call diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c97c6b9cd38..2a9a9abc912 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -124,7 +124,6 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, void bdi_start_background_writeback(struct backing_dev_info *bdi); int bdi_writeback_thread(void *data); int bdi_has_dirty_io(struct backing_dev_info *bdi); -void bdi_arm_supers_timer(void); void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); diff --git a/include/linux/fs.h b/include/linux/fs.h index 38dba16c417..aa110476a95 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1491,7 +1491,6 @@ struct sb_writers { struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ - unsigned char s_dirt; unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ @@ -1861,7 +1860,6 @@ struct super_operations { int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); - void (*write_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_fs) (struct super_block *); int (*unfreeze_fs) (struct super_block *); @@ -2397,7 +2395,6 @@ extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); -extern void sync_supers(void); extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6b4718e2ee3..b41823cc05e 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -39,12 +39,6 @@ DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); LIST_HEAD(bdi_pending_list); -static struct task_struct *sync_supers_tsk; -static struct timer_list sync_supers_timer; - -static int bdi_sync_supers(void *); -static void sync_supers_timer_fn(unsigned long); - void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2) { if (wb1 < wb2) { @@ -250,12 +244,6 @@ static int __init default_bdi_init(void) { int err; - sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers"); - BUG_ON(IS_ERR(sync_supers_tsk)); - - setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0); - bdi_arm_supers_timer(); - err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); @@ -270,46 +258,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi) return wb_has_dirty_io(&bdi->wb); } -/* - * kupdated() used to do this. We cannot do it from the bdi_forker_thread() - * or we risk deadlocking on ->s_umount. The longer term solution would be - * to implement sync_supers_bdi() or similar and simply do it from the - * bdi writeback thread individually. - */ -static int bdi_sync_supers(void *unused) -{ - set_user_nice(current, 0); - - while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - - /* - * Do this periodically, like kupdated() did before. - */ - sync_supers(); - } - - return 0; -} - -void bdi_arm_supers_timer(void) -{ - unsigned long next; - - if (!dirty_writeback_interval) - return; - - next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies; - mod_timer(&sync_supers_timer, round_jiffies_up(next)); -} - -static void sync_supers_timer_fn(unsigned long unused) -{ - wake_up_process(sync_supers_tsk); - bdi_arm_supers_timer(); -} - static void wakeup_timer_fn(unsigned long data) { struct backing_dev_info *bdi = (struct backing_dev_info *)data; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index e5363f34e02..5ad5ce23c1e 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1532,7 +1532,6 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); - bdi_arm_supers_timer(); return 0; } -- cgit v1.2.3-70-g09d2 From d3009c6cffd37e9bc8435a002fe862548c440d97 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:02 +0300 Subject: ext3: nuke write_super from comments The '->write_super' superblock method is gone, and this patch removes all the references to 'write_super' from ext3. Cc: Jan Kara Cc: Andrew Morton Cc: Andreas Dilger Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/ext3/inode.c | 8 -------- fs/ext3/super.c | 11 ----------- 2 files changed, 19 deletions(-) (limited to 'fs') diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 9a4a5c48b1c..a07597307fd 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -3459,14 +3459,6 @@ ext3_reserve_inode_write(handle_t *handle, struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode) { diff --git a/fs/ext3/super.c b/fs/ext3/super.c index ff9bcdc5b0d..8c892e93d8e 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -64,11 +64,6 @@ static int ext3_freeze(struct super_block *sb); /* * Wrappers for journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. */ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) { @@ -90,12 +85,6 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) return journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext3_journal_stop(const char *where, handle_t *handle) { struct super_block *sb; -- cgit v1.2.3-70-g09d2 From 7652bdfcb5888a389a7850ed19a4630e3a09cb9c Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:03 +0300 Subject: ext4: nuke write_super from comments The '->write_super' superblock method is gone, and this patch removes all the references to 'write_super' from ext3. Cc: "Theodore Ts'o" Cc: Andreas Dilger Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/ext4/inode.c | 8 -------- fs/ext4/super.c | 11 ----------- 2 files changed, 19 deletions(-) (limited to 'fs') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6324f74e034..bcb60d08a96 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4589,14 +4589,6 @@ static int ext4_expand_extra_isize(struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d76ec8277d3..3e0851e4f46 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -326,11 +326,6 @@ static void ext4_put_nojournal(handle_t *handle) /* * Wrappers for jbd2_journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. */ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) { @@ -356,12 +351,6 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) return jbd2_journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * jbd2_journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) { struct super_block *sb; -- cgit v1.2.3-70-g09d2 From f6463b0da6937e288b115d641ccd46c70fb3a4a8 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:04 +0300 Subject: ext4: nuke pdflush from comments The pdflush thread is long gone, so this patch removes references to pdflush from ext4 comments. Cc: "Theodore Ts'o" Cc: Andreas Dilger Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bcb60d08a96..dff171c3a12 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1970,7 +1970,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); * This function can get called via... * - ext4_da_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) - * - shrink_page_list via pdflush (no journal handle) + * - shrink_page_list via the kswapd/direct reclaim (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) * * We don't do any block allocation in this function. If we have page with -- cgit v1.2.3-70-g09d2 From 34eaadaf22b0dd453288c6b115e0c823a0fb74d5 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:05 +0300 Subject: btrfs: nuke write_super from comments The '->write_super' superblock method is gone, and this patch removes all the references to 'write_super' from btrfs. Cc: Chris Mason Cc: linux-btrfs@vger.kernel.org Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/btrfs/super.c | 4 ---- fs/btrfs/volumes.c | 4 ---- 2 files changed, 8 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8c6e61d6eed..f2eb24c477a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -100,10 +100,6 @@ static void __save_error_info(struct btrfs_fs_info *fs_info) fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR; } -/* NOTE: - * We move write_super stuff at umount in order to avoid deadlock - * for umount hold all lock. - */ static void save_error_info(struct btrfs_fs_info *fs_info) { __save_error_info(fs_info); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b8708f994e6..e86ae04abe6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1744,10 +1744,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) device->fs_devices = root->fs_info->fs_devices; - /* - * we don't want write_supers to jump in here with our device - * half setup - */ mutex_lock(&root->fs_info->fs_devices->device_list_mutex); list_add_rcu(&device->dev_list, &root->fs_info->fs_devices->devices); list_add(&device->dev_alloc_list, -- cgit v1.2.3-70-g09d2 From b257031408945eb89980e14cb79d5fd854d8f25f Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:06 +0300 Subject: btrfs: nuke pdflush from comments The pdflush thread is long gone, so this patch removes references to pdflush from btrfs comments. Cc: Chris Mason Cc: linux-btrfs@vger.kernel.org Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/btrfs/inode.c | 3 ++- fs/btrfs/ordered-data.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 83baec24946..6e8f416773d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -324,7 +324,8 @@ static noinline int add_async_extent(struct async_cow *cow, * If this code finds it can't get good compression, it puts an * entry onto the work queue to write the uncompressed bytes. This * makes sure that both compressed inodes and uncompressed inodes - * are written in the same order that pdflush sent them down. + * are written in the same order that the flusher thread sent them + * down. */ static noinline int compress_file_range(struct inode *inode, struct page *locked_page, diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 643335a4fe3..051c7fe551d 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -596,7 +596,7 @@ void btrfs_start_ordered_extent(struct inode *inode, /* * pages in the range can be dirty, clean or writeback. We * start IO on any dirty ones so the wait doesn't stall waiting - * for pdflush to find them + * for the flusher thread to find them */ if (!test_bit(BTRFS_ORDERED_DIRECT, &entry->flags)) filemap_fdatawrite_range(inode->i_mapping, start, end); -- cgit v1.2.3-70-g09d2 From 12810ad70858af10f5e00b3c178085c03baa457b Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:07 +0300 Subject: jbd/jbd2: nuke write_super from comments The '->write_super' superblock method is gone, and this patch removes all the references to 'write_super' from various jbd and jbd2. Cc: Andrew Morton Cc: Jan Kara Cc: "Theodore Ts'o" Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/jbd/journal.c | 4 ++-- fs/jbd2/journal.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 425c2f2cf17..09357508ec9 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -534,8 +534,8 @@ int journal_start_commit(journal_t *journal, tid_t *ptid) ret = 1; } else if (journal->j_committing_transaction) { /* - * If ext3_write_super() recently started a commit, then we - * have to wait for completion of that transaction + * If commit has been started, then we have to wait for + * completion of that transaction. */ if (ptid) *ptid = journal->j_committing_transaction->t_tid; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e9a3c4c8559..8625da27ecc 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -612,8 +612,8 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) ret = 1; } else if (journal->j_committing_transaction) { /* - * If ext3_write_super() recently started a commit, then we - * have to wait for completion of that transaction + * If commit has been started, then we have to wait for + * completion of that transaction. */ if (ptid) *ptid = journal->j_committing_transaction->t_tid; -- cgit v1.2.3-70-g09d2 From 0d5c3eba2e1e5aa74e097f49bc90b58f607e101c Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:08 +0300 Subject: vfs: nuke pdflush from comments The pdflush thread is long gone, so this patch removes references to pdflush from vfs comments. Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/bio.c | 2 +- include/linux/writeback.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/bio.c b/fs/bio.c index 73922abba83..5eaa70c9d96 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1312,7 +1312,7 @@ EXPORT_SYMBOL(bio_copy_kern); * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. - * But other code (eg, pdflush) could clean the pages if they are mapped + * But other code (eg, flusher threads) could clean the pages if they are mapped * pagecache. * * Simply disabling the call to bio_set_pages_dirty() is a good way to test the diff --git a/include/linux/writeback.h b/include/linux/writeback.h index c66fe3332d8..50c3e8fa06a 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -104,7 +104,6 @@ static inline void wait_on_inode(struct inode *inode) wait_on_bit(&inode->i_state, __I_NEW, inode_wait, TASK_UNINTERRUPTIBLE); } - /* * mm/page-writeback.c */ -- cgit v1.2.3-70-g09d2 From 50640bcc0a0e5a66587fa051b327654c739c9c19 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:09 +0300 Subject: hfs: nuke write_super from comments The '->write_super' superblock method is gone, and this patch removes all the references to 'write_super' from hfs. Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/hfs/mdb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 5fd51a5833f..b7ec224910c 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -236,10 +236,10 @@ out: * hfs_mdb_commit() * * Description: - * This updates the MDB on disk (look also at hfs_write_super()). + * This updates the MDB on disk. * It does not check, if the superblock has been modified, or * if the filesystem has been mounted read-only. It is mainly - * called by hfs_write_super() and hfs_btree_extend(). + * called by hfs_sync_fs() and flush_mdb(). * Input Variable(s): * struct hfs_mdb *mdb: Pointer to the hfs MDB * int backup; -- cgit v1.2.3-70-g09d2 From 166ac34b74faa757ca936fde790d2121a3f40f65 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:11 +0300 Subject: nilfs2: nuke write_super from comments The '->write_super' superblock method is gone, and this patch removes all the references to 'write_super' from ntfs. Cc: KONISHI Ryusuke Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/nilfs2/super.c | 4 ---- fs/nilfs2/the_nilfs.h | 2 -- 2 files changed, 6 deletions(-) (limited to 'fs') diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 6522cac6057..6a10812711c 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -676,17 +676,13 @@ static const struct super_operations nilfs_sops = { .alloc_inode = nilfs_alloc_inode, .destroy_inode = nilfs_destroy_inode, .dirty_inode = nilfs_dirty_inode, - /* .write_inode = nilfs_write_inode, */ - /* .drop_inode = nilfs_drop_inode, */ .evict_inode = nilfs_evict_inode, .put_super = nilfs_put_super, - /* .write_super = nilfs_write_super, */ .sync_fs = nilfs_sync_fs, .freeze_fs = nilfs_freeze, .unfreeze_fs = nilfs_unfreeze, .statfs = nilfs_statfs, .remount_fs = nilfs_remount, - /* .umount_begin */ .show_options = nilfs_show_options }; diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 6eee4177807..be1267a34ce 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -107,8 +107,6 @@ struct the_nilfs { * used for * - loading the latest checkpoint exclusively. * - allocating a new full segment. - * - protecting s_dirt in the super_block struct - * (see nilfs_write_super) and the following fields. */ struct buffer_head *ns_sbh[2]; struct nilfs_super_block *ns_sbp[2]; -- cgit v1.2.3-70-g09d2 From e76e0ec9849bcd3290c19ba6f71c7c01e7988414 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:13 +0300 Subject: gfs2: nuke pdflush from comments The pdflush thread is long gone, so this patch removes references to pdflush from gfs comments. Cc: Steven Whitehouse Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/gfs2/meta_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 3a56c8d94de..22255d96b27 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -52,7 +52,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the page. Note that this can - * potentially cause a busy-wait loop from pdflush and kswapd + * potentially cause a busy-wait loop from flusher thread and kswapd * activity, but those code paths have their own higher-level * throttling. */ -- cgit v1.2.3-70-g09d2 From 5c57f20b824a163bd7dfa42abc76582ad24a745a Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 25 Jul 2012 18:12:14 +0300 Subject: UBIFS: nuke pdflush from comments The pdflush thread is long gone, so this patch removes references to pdflush from UBIFS comments. Signed-off-by: Artem Bityutskiy Signed-off-by: Al Viro --- fs/ubifs/file.c | 10 +++++----- fs/ubifs/super.c | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 35389ca2d26..7bd6e72afd1 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -37,11 +37,11 @@ * * A thing to keep in mind: inode @i_mutex is locked in most VFS operations we * implement. However, this is not true for 'ubifs_writepage()', which may be - * called with @i_mutex unlocked. For example, when pdflush is doing background - * write-back, it calls 'ubifs_writepage()' with unlocked @i_mutex. At "normal" - * work-paths the @i_mutex is locked in 'ubifs_writepage()', e.g. in the - * "sys_write -> alloc_pages -> direct reclaim path". So, in 'ubifs_writepage()' - * we are only guaranteed that the page is locked. + * called with @i_mutex unlocked. For example, when flusher thread is doing + * background write-back, it calls 'ubifs_writepage()' with unlocked @i_mutex. + * At "normal" work-paths the @i_mutex is locked in 'ubifs_writepage()', e.g. + * in the "sys_write -> alloc_pages -> direct reclaim path". So, in + * 'ubifs_writepage()' we are only guaranteed that the page is locked. * * Similarly, @i_mutex is not always locked in 'ubifs_readpage()', e.g., the * read-ahead path does not lock it ("sys_read -> generic_file_aio_read -> diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 1c766c39c03..c3fa6c5327a 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -303,7 +303,7 @@ static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc) mutex_lock(&ui->ui_mutex); /* * Due to races between write-back forced by budgeting - * (see 'sync_some_inodes()') and pdflush write-back, the inode may + * (see 'sync_some_inodes()') and background write-back, the inode may * have already been synchronized, do not do this again. This might * also happen if it was synchronized in an VFS operation, e.g. * 'ubifs_link()'. -- cgit v1.2.3-70-g09d2 From fe7c80518e34d1786f4a940ce673a0bfcbe53298 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 4 Aug 2012 08:39:23 +0400 Subject: missed mnt_drop_write() in do_dentry_open() This one ought to be __mnt_drop_write(), to match __mnt_want_write() in the beginning... Signed-off-by: Al Viro --- fs/open.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/open.c b/fs/open.c index f3d96e7e7b1..bc132e167d2 100644 --- a/fs/open.c +++ b/fs/open.c @@ -717,7 +717,7 @@ cleanup_all: * here, so just reset the state. */ file_reset_write(f); - mnt_drop_write(f->f_path.mnt); + __mnt_drop_write(f->f_path.mnt); } } cleanup_file: -- cgit v1.2.3-70-g09d2 From fb6ccff667712c46b4501b920ea73a326e49626a Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Tue, 24 Jul 2012 12:10:11 -0700 Subject: fuse: verify all ioctl retry iov elements Commit 7572777eef78ebdee1ecb7c258c0ef94d35bad16 attempted to verify that the total iovec from the client doesn't overflow iov_length() but it only checked the first element. The iovec could still overflow by starting with a small element. The obvious fix is to check all the elements. The overflow case doesn't look dangerous to the kernel as the copy is limited by the length after the overflow. This fix restores the intention of returning an error instead of successfully copying less than the iovec represented. I found this by code inspection. I built it but don't have a test case. I'm cc:ing stable because the initial commit did as well. Signed-off-by: Zach Brown Signed-off-by: Miklos Szeredi CC: [2.6.37+] --- fs/fuse/file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5800101e5ce..2eed3acfb6a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1703,7 +1703,7 @@ static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count) size_t n; u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT; - for (n = 0; n < count; n++) { + for (n = 0; n < count; n++, iov++) { if (iov->iov_len > (size_t) max) return -ENOMEM; max -= iov->iov_len; -- cgit v1.2.3-70-g09d2 From e00da2067b78a9246f767012a3803224c40b1f9f Mon Sep 17 00:00:00 2001 From: Alexander Block Date: Thu, 2 Aug 2012 17:16:20 -0600 Subject: Btrfs: remove mnt_want_write call in btrfs_mksubvol We got a recursive lock in mksubvol because the caller already held a lock. I think we got into this due to a merge error. Commit a874a63 removed the mnt_want_write call from btrfs_mksubvol and added a replacement call to mnt_want_write_file in btrfs_ioctl_snap_create_transid. Commit e7848683 however tried to move all calls to mnt_want_write above i_mutex. So somewhere while merging this, it got mixed up. The solution is to remove the mnt_want_write call completely from mksubvol. Reported-by: David Sterba Signed-off-by: Alexander Block Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bc2f6ffff3c..7bb755677a2 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -664,10 +664,6 @@ static noinline int btrfs_mksubvol(struct path *parent, struct dentry *dentry; int error; - error = mnt_want_write(parent->mnt); - if (error) - return error; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); dentry = lookup_one_len(name, parent->dentry, namelen); @@ -703,7 +699,6 @@ out_dput: dput(dentry); out_unlock: mutex_unlock(&dir->i_mutex); - mnt_drop_write(parent->mnt); return error; } -- cgit v1.2.3-70-g09d2 From a45440f05e9ebc26f2a375df911823fdef5b5281 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Mon, 6 Aug 2012 09:37:47 +0800 Subject: autofs4 - fix get_next_positive_subdir() Following a report of a crash during an automount expire I found that the locking in fs/autofs4/expire.c:get_next_positive_subdir() was wrong. Not only is the locking wrong but the function is more complex than it needs to be. The function is meant to calculate (and dget) the next entry in the list of directories contained in the root of an autofs mount point (an autofs indirect mount to be precise). The main problem was that the d_lock of the owner of the list was not being taken when walking the list, which lead to list corruption under load. The only other lock that needs to be taken is against the next dentry candidate so it can be checked for usability. Signed-off-by: Ian Kent Signed-off-by: Linus Torvalds --- fs/autofs4/expire.c | 31 +++++++++++++------------------ 1 file changed, 13 insertions(+), 18 deletions(-) (limited to 'fs') diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 1feb68ecef9..8c0e56d9293 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -94,25 +94,21 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev, { struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); struct list_head *next; - struct dentry *p, *q; + struct dentry *q; spin_lock(&sbi->lookup_lock); + spin_lock(&root->d_lock); - if (prev == NULL) { - spin_lock(&root->d_lock); + if (prev) + next = prev->d_u.d_child.next; + else { prev = dget_dlock(root); next = prev->d_subdirs.next; - p = prev; - goto start; } - p = prev; - spin_lock(&p->d_lock); -again: - next = p->d_u.d_child.next; -start: +cont: if (next == &root->d_subdirs) { - spin_unlock(&p->d_lock); + spin_unlock(&root->d_lock); spin_unlock(&sbi->lookup_lock); dput(prev); return NULL; @@ -121,16 +117,15 @@ start: q = list_entry(next, struct dentry, d_u.d_child); spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED); - /* Negative dentry - try next */ - if (!simple_positive(q)) { - spin_unlock(&p->d_lock); - lock_set_subclass(&q->d_lock.dep_map, 0, _RET_IP_); - p = q; - goto again; + /* Already gone or negative dentry (under construction) - try next */ + if (q->d_count == 0 || !simple_positive(q)) { + spin_unlock(&q->d_lock); + next = q->d_u.d_child.next; + goto cont; } dget_dlock(q); spin_unlock(&q->d_lock); - spin_unlock(&p->d_lock); + spin_unlock(&root->d_lock); spin_unlock(&sbi->lookup_lock); dput(prev); -- cgit v1.2.3-70-g09d2