From f4ac904c411b55e58bb240f332f93db2455f0010 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 5 Aug 2011 14:19:00 +0000 Subject: btrfs: memory leak in btrfs_add_inode_defrag() We don't use the defrag struct on this path. Signed-off-by: Dan Carpenter Signed-off-by: Chris Mason --- fs/btrfs/file.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 010aec8be824..0705d15542c6 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -150,6 +150,8 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, spin_lock(&root->fs_info->defrag_inodes_lock); if (!BTRFS_I(inode)->in_defrag) __btrfs_add_inode_defrag(inode, defrag); + else + kfree(defrag); spin_unlock(&root->fs_info->defrag_inodes_lock); return 0; } -- cgit v1.2.3 From 9a4327ca1f45f82edad7dc0a4e52ce9316e0950c Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 18 Aug 2011 10:16:05 -0400 Subject: btrfs: unlock on error in btrfs_file_llseek() There were some unlocks on error missing in a recent patch to btrfs_file_llseek(). Signed-off-by: Dan Carpenter Signed-off-by: Chris Mason --- fs/btrfs/file.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 658d66959abe..f7d9df7f3fdd 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1804,10 +1804,14 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin) } } - if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) - return -EINVAL; - if (offset > inode->i_sb->s_maxbytes) - return -EINVAL; + if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) { + ret = -EINVAL; + goto out; + } + if (offset > inode->i_sb->s_maxbytes) { + ret = -EINVAL; + goto out; + } /* Special lock needed here? */ if (offset != file->f_pos) { -- cgit v1.2.3 From f1e490a7ebe41e06324abbbcd86005b0af02a375 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 18 Aug 2011 10:36:39 -0400 Subject: Btrfs: set i_size properly when fallocating and we already xfstests exposed a problem with preallocate when it fallocates a range that already has an extent. We don't set the new i_size properly because we see that we already have an extent. This isn't right and we should update i_size if the space already exists. With this patch we now pass xfstests 075. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/file.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0705d15542c6..15e5a1cd8764 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1631,11 +1631,15 @@ static long btrfs_fallocate(struct file *file, int mode, cur_offset = alloc_start; while (1) { + u64 actual_end; + em = btrfs_get_extent(inode, NULL, 0, cur_offset, alloc_end - cur_offset, 0); BUG_ON(IS_ERR_OR_NULL(em)); last_byte = min(extent_map_end(em), alloc_end); + actual_end = min_t(u64, extent_map_end(em), offset + len); last_byte = (last_byte + mask) & ~mask; + if (em->block_start == EXTENT_MAP_HOLE || (cur_offset >= inode->i_size && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { @@ -1648,6 +1652,16 @@ static long btrfs_fallocate(struct file *file, int mode, free_extent_map(em); break; } + } else if (actual_end > inode->i_size && + !(mode & FALLOC_FL_KEEP_SIZE)) { + /* + * We didn't need to allocate any more space, but we + * still extended the size of the file so we need to + * update i_size. + */ + inode->i_ctime = CURRENT_TIME; + i_size_write(inode, actual_end); + btrfs_ordered_update_i_size(inode, actual_end, NULL); } free_extent_map(em); -- cgit v1.2.3 From 0c1a98c81413e00a6c379d898e06a09350d31926 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Sun, 11 Sep 2011 10:52:24 -0400 Subject: Btrfs: fix the file extent gap when doing direct IO When we write some data to the place that is beyond the end of the file in direct I/O mode, a data hole will be created. And Btrfs should insert a file extent item that point to this hole into the fs tree. But unfortunately Btrfs forgets doing it. The following is a simple way to reproduce it: # mkfs.btrfs /dev/sdc2 # mount /dev/sdc2 /test4 # touch /test4/a # dd if=/dev/zero of=/test4/a seek=8 count=1 bs=4K oflag=direct conv=nocreat,notrunc # umount /test4 # btrfsck /dev/sdc2 root 5 inode 257 errors 100 Reported-by: Tsutomu Itoh Signed-off-by: Miao Xie Tested-by: Tsutomu Itoh Signed-off-by: Chris Mason --- fs/btrfs/file.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 15e5a1cd8764..98d95bb5f253 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1075,12 +1075,6 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file, start_pos = pos & ~((u64)root->sectorsize - 1); last_pos = ((u64)index + num_pages) << PAGE_CACHE_SHIFT; - if (start_pos > inode->i_size) { - err = btrfs_cont_expand(inode, i_size_read(inode), start_pos); - if (err) - return err; - } - again: for (i = 0; i < num_pages; i++) { pages[i] = find_or_create_page(inode->i_mapping, index + i, @@ -1338,6 +1332,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, struct inode *inode = fdentry(file)->d_inode; struct btrfs_root *root = BTRFS_I(inode)->root; loff_t *ppos = &iocb->ki_pos; + u64 start_pos; ssize_t num_written = 0; ssize_t err = 0; size_t count, ocount; @@ -1386,6 +1381,15 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, file_update_time(file); BTRFS_I(inode)->sequence++; + start_pos = round_down(pos, root->sectorsize); + if (start_pos > i_size_read(inode)) { + err = btrfs_cont_expand(inode, i_size_read(inode), start_pos); + if (err) { + mutex_unlock(&inode->i_mutex); + goto out; + } + } + if (unlikely(file->f_flags & O_DIRECT)) { num_written = __btrfs_direct_write(iocb, iov, nr_segs, pos, ppos, count, ocount); -- cgit v1.2.3 From 48802c8ae2a9d618ec734a61283d645ad527e06c Mon Sep 17 00:00:00 2001 From: Jeff Liu Date: Sun, 18 Sep 2011 10:34:02 -0400 Subject: BTRFS: Fix lseek return value for error The recent reworking of btrfs' lseek lead to incorrect values being returned. This adds checks for seeking beyond EOF in SEEK_HOLE and makes sure the error values come back correct. Andi Kleen also sent in similar patches. Signed-off-by: Jie Liu Reported-by: Andi Kleen Signed-off-by: Chris Mason --- fs/btrfs/file.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 3c3abff731a7..a381cd22f518 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1817,6 +1817,11 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin) goto out; case SEEK_DATA: case SEEK_HOLE: + if (offset >= i_size_read(inode)) { + mutex_unlock(&inode->i_mutex); + return -ENXIO; + } + ret = find_desired_extent(inode, &offset, origin); if (ret) { mutex_unlock(&inode->i_mutex); @@ -1825,11 +1830,11 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin) } if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) { - ret = -EINVAL; + offset = -EINVAL; goto out; } if (offset > inode->i_sb->s_maxbytes) { - ret = -EINVAL; + offset = -EINVAL; goto out; } -- cgit v1.2.3 From b6316429af7f365f307dfd2b6a7a42f2563aef19 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 30 Sep 2011 15:23:54 -0400 Subject: Btrfs: force a page fault if we have a shorty copy on a page boundary A user reported a problem where ceph was getting into 100% cpu usage while doing some writing. It turns out it's because we were doing a short write on a not uptodate page, which means we'd fall back at one page at a time and fault the page in. The problem is our position is on the page boundary, so our fault in logic wasn't actually reading the page, so we'd just spin forever or until the page got read in by somebody else. This will force a readpage if we end up doing a short copy. Alexandre could reproduce this easily with ceph and reports it fixes his problem. I also wrote a reproducer that no longer hangs my box with this patch. Thanks, Reported-and-tested-by: Alexandre Oliva Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/file.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 98d95bb5f253..e73051099368 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1036,11 +1036,13 @@ out: * on error we return an unlocked page and the error value * on success we return a locked page and 0 */ -static int prepare_uptodate_page(struct page *page, u64 pos) +static int prepare_uptodate_page(struct page *page, u64 pos, + bool force_uptodate) { int ret = 0; - if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) { + if (((pos & (PAGE_CACHE_SIZE - 1)) || force_uptodate) && + !PageUptodate(page)) { ret = btrfs_readpage(NULL, page); if (ret) return ret; @@ -1061,7 +1063,7 @@ static int prepare_uptodate_page(struct page *page, u64 pos) static noinline int prepare_pages(struct btrfs_root *root, struct file *file, struct page **pages, size_t num_pages, loff_t pos, unsigned long first_index, - size_t write_bytes) + size_t write_bytes, bool force_uptodate) { struct extent_state *cached_state = NULL; int i; @@ -1086,10 +1088,11 @@ again: } if (i == 0) - err = prepare_uptodate_page(pages[i], pos); + err = prepare_uptodate_page(pages[i], pos, + force_uptodate); if (i == num_pages - 1) err = prepare_uptodate_page(pages[i], - pos + write_bytes); + pos + write_bytes, false); if (err) { page_cache_release(pages[i]); faili = i - 1; @@ -1158,6 +1161,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, size_t num_written = 0; int nrptrs; int ret = 0; + bool force_page_uptodate = false; nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) / PAGE_CACHE_SIZE, PAGE_CACHE_SIZE / @@ -1200,7 +1204,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, * contents of pages from loop to loop */ ret = prepare_pages(root, file, pages, num_pages, - pos, first_index, write_bytes); + pos, first_index, write_bytes, + force_page_uptodate); if (ret) { btrfs_delalloc_release_space(inode, num_pages << PAGE_CACHE_SHIFT); @@ -1217,12 +1222,15 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, if (copied < write_bytes) nrptrs = 1; - if (copied == 0) + if (copied == 0) { + force_page_uptodate = true; dirty_pages = 0; - else + } else { + force_page_uptodate = false; dirty_pages = (copied + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + } /* * If we had a short copy we need to release the excess delaloc -- cgit v1.2.3 From 1b9c332b6c92e992b1971a08412c6f460a54b514 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 17 Aug 2011 10:19:52 -0400 Subject: Btrfs: only reserve space in fallocate if we have to do a preallocate Lukas found a problem where if he tries to fallocate over the same region twice and the first fallocate took up all the space we would fail with ENOSPC. This is because we reserve the total space we want to use for fallocate, regardless of wether or not we will have to actually preallocate. So instead move the check into the loop where we actually have to do the preallocate. Thanks, Tested-by: Lukas Czerner Signed-off-by: Josef Bacik --- fs/btrfs/file.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e4e57d59edb7..de569af766fe 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1615,10 +1615,6 @@ static long btrfs_fallocate(struct file *file, int mode, goto out; } - ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start); - if (ret) - goto out; - locked_end = alloc_end - 1; while (1) { struct btrfs_ordered_extent *ordered; @@ -1664,11 +1660,27 @@ static long btrfs_fallocate(struct file *file, int mode, if (em->block_start == EXTENT_MAP_HOLE || (cur_offset >= inode->i_size && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { + + /* + * Make sure we have enough space before we do the + * allocation. + */ + ret = btrfs_check_data_free_space(inode, last_byte - + cur_offset); + if (ret) { + free_extent_map(em); + break; + } + ret = btrfs_prealloc_file_range(inode, mode, cur_offset, last_byte - cur_offset, 1 << inode->i_blkbits, offset + len, &alloc_hint); + + /* Let go of our reservation. */ + btrfs_free_reserved_data_space(inode, last_byte - + cur_offset); if (ret < 0) { free_extent_map(em); break; @@ -1694,8 +1706,6 @@ static long btrfs_fallocate(struct file *file, int mode, } unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state, GFP_NOFS); - - btrfs_free_reserved_data_space(inode, alloc_end - alloc_start); out: mutex_unlock(&inode->i_mutex); return ret; -- cgit v1.2.3 From 3b16a4e3c355ee3c790473decfcf83d4faeb8ce0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 21 Sep 2011 15:05:58 -0400 Subject: Btrfs: use the inode's mapping mask for allocating pages Johannes pointed out we were allocating only kernel pages for doing writes, which is kind of a big deal if you are on 32bit and have more than a gig of ram. So fix our allocations to use the mapping's gfp but still clear __GFP_FS so we don't re-enter. Thanks, Reported-by: Johannes Weiner Signed-off-by: Josef Bacik --- fs/btrfs/ctree.h | 6 ++++++ fs/btrfs/file.c | 3 ++- fs/btrfs/free-space-cache.c | 6 ++++-- fs/btrfs/inode.c | 3 ++- fs/btrfs/ioctl.c | 3 ++- fs/btrfs/relocation.c | 3 ++- 6 files changed, 18 insertions(+), 6 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index a5faf8e33baa..47dea7118e0e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -30,6 +30,7 @@ #include #include #include +#include #include "extent_io.h" #include "extent_map.h" #include "async-thread.h" @@ -2117,6 +2118,11 @@ static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) (space_info->flags & BTRFS_BLOCK_GROUP_DATA)); } +static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) +{ + return mapping_gfp_mask(mapping) & ~__GFP_FS; +} + /* extent-tree.c */ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root, unsigned num_items) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index de569af766fe..f2e928289600 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1069,6 +1069,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file, int i; unsigned long index = pos >> PAGE_CACHE_SHIFT; struct inode *inode = fdentry(file)->d_inode; + gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); int err = 0; int faili = 0; u64 start_pos; @@ -1080,7 +1081,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file, again: for (i = 0; i < num_pages; i++) { pages[i] = find_or_create_page(inode->i_mapping, index + i, - GFP_NOFS); + mask); if (!pages[i]) { faili = i - 1; err = -ENOMEM; diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index ffc42ef44711..0a8ccdbdd464 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -254,6 +254,7 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, u64 num_bitmaps; u64 generation; pgoff_t index = 0; + gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); int ret = 0; INIT_LIST_HEAD(&bitmaps); @@ -310,7 +311,7 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, if (!num_entries && !num_bitmaps) break; - page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, index, mask); if (!page) goto free_cache; @@ -563,6 +564,7 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, u64 start, end, len; u64 bytes = 0; u32 crc = ~(u32)0; + gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); int index = 0, num_pages = 0; int entries = 0; int bitmaps = 0; @@ -612,7 +614,7 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, * know and don't freak out. */ while (index < num_pages) { - page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, index, mask); if (!page) { int i; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2947e94947b5..88e3956be57d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3282,6 +3282,7 @@ static int btrfs_truncate_page(struct address_space *mapping, loff_t from) pgoff_t index = from >> PAGE_CACHE_SHIFT; unsigned offset = from & (PAGE_CACHE_SIZE-1); struct page *page; + gfp_t mask = btrfs_alloc_write_mask(mapping); int ret = 0; u64 page_start; u64 page_end; @@ -3294,7 +3295,7 @@ static int btrfs_truncate_page(struct address_space *mapping, loff_t from) ret = -ENOMEM; again: - page = find_or_create_page(mapping, index, GFP_NOFS); + page = find_or_create_page(mapping, index, mask); if (!page) { btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE); goto out; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 538f65a79ec5..24fd75bb0f96 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -843,6 +843,7 @@ static int cluster_pages_for_defrag(struct inode *inode, int i_done; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); if (isize == 0) return 0; @@ -860,7 +861,7 @@ again: for (i = 0; i < num_pages; i++) { struct page *page; page = find_or_create_page(inode->i_mapping, - start_index + i, GFP_NOFS); + start_index + i, mask); if (!page) break; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3ab67409f90f..7fa090fa0d39 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2921,6 +2921,7 @@ static int relocate_file_extent_cluster(struct inode *inode, unsigned long last_index; struct page *page; struct file_ra_state *ra; + gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); int nr = 0; int ret = 0; @@ -2955,7 +2956,7 @@ static int relocate_file_extent_cluster(struct inode *inode, ra, NULL, index, last_index + 1 - index); page = find_or_create_page(inode->i_mapping, index, - GFP_NOFS); + mask); if (!page) { btrfs_delalloc_release_metadata(inode, PAGE_CACHE_SIZE); -- cgit v1.2.3 From ef3d0fd27e90f67e35da516dafc1482c82939a60 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 15 Sep 2011 16:06:48 -0700 Subject: vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen Signed-off-by: Christoph Hellwig --- fs/btrfs/file.c | 2 +- fs/cifs/cifsfs.c | 2 +- fs/gfs2/file.c | 4 +-- fs/nfs/file.c | 5 ++-- fs/read_write.c | 85 ++++++++++++++++++++++++++---------------------------- include/linux/fs.h | 9 ++++-- 6 files changed, 54 insertions(+), 53 deletions(-) (limited to 'fs/btrfs/file.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e4e57d59edb7..1266f6e9cdb2 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1821,7 +1821,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin) switch (origin) { case SEEK_END: case SEEK_CUR: - offset = generic_file_llseek_unlocked(file, offset, origin); + offset = generic_file_llseek(file, offset, origin); goto out; case SEEK_DATA: case SEEK_HOLE: diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 54b8f1e7da94..db7ce87d37a5 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -723,7 +723,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int origin) if (rc < 0) return (loff_t)rc; } - return generic_file_llseek_unlocked(file, offset, origin); + return generic_file_llseek(file, offset, origin); } static int cifs_setlease(struct file *file, long arg, struct file_lock **lease) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index edeb9e802903..fe6bc0207818 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -63,11 +63,11 @@ static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin) error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); if (!error) { - error = generic_file_llseek_unlocked(file, offset, origin); + error = generic_file_llseek(file, offset, origin); gfs2_glock_dq_uninit(&i_gh); } } else - error = generic_file_llseek_unlocked(file, offset, origin); + error = generic_file_llseek(file, offset, origin); return error; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 28b8c3f3cda3..12623abcf3d4 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -198,11 +198,12 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin) if (retval < 0) return (loff_t)retval; + /* AK: should drop this lock. Unlikely to be needed. */ spin_lock(&inode->i_lock); - loff = generic_file_llseek_unlocked(filp, offset, origin); + loff = generic_file_llseek(filp, offset, origin); spin_unlock(&inode->i_lock); } else - loff = generic_file_llseek_unlocked(filp, offset, origin); + loff = generic_file_llseek(filp, offset, origin); return loff; } diff --git a/fs/read_write.c b/fs/read_write.c index 179f1c33ea57..672b187def62 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -35,23 +35,45 @@ static inline int unsigned_offsets(struct file *file) return file->f_mode & FMODE_UNSIGNED_OFFSET; } +static loff_t lseek_execute(struct file *file, struct inode *inode, + loff_t offset, loff_t maxsize) +{ + if (offset < 0 && !unsigned_offsets(file)) + return -EINVAL; + if (offset > maxsize) + return -EINVAL; + + if (offset != file->f_pos) { + file->f_pos = offset; + file->f_version = 0; + } + return offset; +} + /** - * generic_file_llseek_unlocked - lockless generic llseek implementation + * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @origin: type of seek * - * Updates the file offset to the value specified by @offset and @origin. - * Locking must be provided by the caller. + * This is a generic implemenation of ->llseek usable for all normal local + * filesystems. It just updates the file offset to the value specified by + * @offset and @origin under i_mutex. + * + * Synchronization: + * SEEK_SET is unsynchronized (but atomic on 64bit platforms) + * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. + * read/writes behave like SEEK_SET against seeks. + * SEEK_END */ loff_t -generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin) +generic_file_llseek(struct file *file, loff_t offset, int origin) { struct inode *inode = file->f_mapping->host; switch (origin) { case SEEK_END: - offset += inode->i_size; + offset += i_size_read(inode); break; case SEEK_CUR: /* @@ -62,14 +84,22 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin) */ if (offset == 0) return file->f_pos; - offset += file->f_pos; - break; + /* + * f_lock protects against read/modify/write race with other + * SEEK_CURs. Note that parallel writes and reads behave + * like SEEK_SET. + */ + spin_lock(&file->f_lock); + offset = lseek_execute(file, inode, file->f_pos + offset, + inode->i_sb->s_maxbytes); + spin_unlock(&file->f_lock); + return offset; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= inode->i_size) + if (offset >= i_size_read(inode)) return -ENXIO; break; case SEEK_HOLE: @@ -77,46 +107,13 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin) * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= inode->i_size) + if (offset >= i_size_read(inode)) return -ENXIO; - offset = inode->i_size; + offset = i_size_read(inode); break; } - if (offset < 0 && !unsigned_offsets(file)) - return -EINVAL; - if (offset > inode->i_sb->s_maxbytes) - return -EINVAL; - - /* Special lock needed here? */ - if (offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } - - return offset; -} -EXPORT_SYMBOL(generic_file_llseek_unlocked); - -/** - * generic_file_llseek - generic llseek implementation for regular files - * @file: file structure to seek on - * @offset: file offset to seek to - * @origin: type of seek - * - * This is a generic implemenation of ->llseek useable for all normal local - * filesystems. It just updates the file offset to the value specified by - * @offset and @origin under i_mutex. - */ -loff_t generic_file_llseek(struct file *file, loff_t offset, int origin) -{ - loff_t rval; - - mutex_lock(&file->f_dentry->d_inode->i_mutex); - rval = generic_file_llseek_unlocked(file, offset, origin); - mutex_unlock(&file->f_dentry->d_inode->i_mutex); - - return rval; + return lseek_execute(file, inode, offset, inode->i_sb->s_maxbytes); } EXPORT_SYMBOL(generic_file_llseek); diff --git a/include/linux/fs.h b/include/linux/fs.h index c1884e974ff4..db85196f6308 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -964,7 +964,12 @@ struct file { #define f_dentry f_path.dentry #define f_vfsmnt f_path.mnt const struct file_operations *f_op; - spinlock_t f_lock; /* f_ep_links, f_flags, no IRQ */ + + /* + * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR. + * Must not be taken from IRQ context. + */ + spinlock_t f_lock; #ifdef CONFIG_SMP int f_sb_list_cpu; #endif @@ -2398,8 +2403,6 @@ file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int origin); extern loff_t no_llseek(struct file *file, loff_t offset, int origin); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin); -extern loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset, - int origin); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); -- cgit v1.2.3