From ce37c42919608e96ade3748fe23c3062a0a966c5 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Wed, 19 Feb 2014 18:52:39 -0500 Subject: ext4: fix error return from ext4_ext_handle_uninitialized_extents() Commit 3779473246 breaks the return of error codes from ext4_ext_handle_uninitialized_extents() in ext4_ext_map_blocks(). A portion of the patch assigns that function's signed integer return value to an unsigned int. Consequently, negatively valued error codes are lost and can be treated as a bogus allocated block count. Signed-off-by: Eric Whitney Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext4/extents.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 74bc2d549c58..9875fd0918e7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4128,7 +4128,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_extent newex, *ex, *ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0; - int free_on_err = 0, err = 0, depth; + int free_on_err = 0, err = 0, depth, ret; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; @@ -4189,9 +4189,13 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, if (!ext4_ext_is_uninitialized(ex)) goto out; - allocated = ext4_ext_handle_uninitialized_extents( + ret = ext4_ext_handle_uninitialized_extents( handle, inode, map, path, flags, allocated, newblock); + if (ret < 0) + err = ret; + else + allocated = ret; goto out3; } } -- cgit v1.2.3 From a9b8241594adda0a7a4fb3b87bf29d2dff0d997d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 20 Feb 2014 21:17:35 -0500 Subject: ext4: merge uninitialized extents Allow for merging uninitialized extents. Signed-off-by: Darrick J. Wong Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9875fd0918e7..ef4b535e0a02 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1691,7 +1691,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, * the extent that was written properly split out and conversion to * initialized is trivial. */ - if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2)) + if (ext4_ext_is_uninitialized(ex1) != ext4_ext_is_uninitialized(ex2)) return 0; ext1_ee_len = ext4_ext_get_actual_len(ex1); @@ -1708,6 +1708,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, */ if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN) return 0; + if (ext4_ext_is_uninitialized(ex1) && + (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) || + atomic_read(&EXT4_I(inode)->i_unwritten) || + (ext1_ee_len + ext2_ee_len > EXT_UNINIT_MAX_LEN))) + return 0; #ifdef AGGRESSIVE_TEST if (ext1_ee_len >= 4) return 0; @@ -1731,7 +1736,7 @@ static int ext4_ext_try_to_merge_right(struct inode *inode, { struct ext4_extent_header *eh; unsigned int depth, len; - int merge_done = 0; + int merge_done = 0, uninit; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); @@ -1741,8 +1746,11 @@ static int ext4_ext_try_to_merge_right(struct inode *inode, if (!ext4_can_extents_be_merged(inode, ex, ex + 1)) break; /* merge with next extent! */ + uninit = ext4_ext_is_uninitialized(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(ex + 1)); + if (uninit) + ext4_ext_mark_uninitialized(ex); if (ex + 1 < EXT_LAST_EXTENT(eh)) { len = (EXT_LAST_EXTENT(eh) - ex - 1) @@ -1896,7 +1904,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *npath = NULL; int depth, len, err; ext4_lblk_t next; - int mb_flags = 0; + int mb_flags = 0, uninit; if (unlikely(ext4_ext_get_actual_len(newext) == 0)) { EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0"); @@ -1946,9 +1954,11 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, path + depth); if (err) return err; - + uninit = ext4_ext_is_uninitialized(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); + if (uninit) + ext4_ext_mark_uninitialized(ex); eh = path[depth].p_hdr; nearex = ex; goto merge; @@ -1971,10 +1981,13 @@ prepend: if (err) return err; + uninit = ext4_ext_is_uninitialized(ex); ex->ee_block = newext->ee_block; ext4_ext_store_pblock(ex, ext4_ext_pblock(newext)); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); + if (uninit) + ext4_ext_mark_uninitialized(ex); eh = path[depth].p_hdr; nearex = ex; goto merge; -- cgit v1.2.3 From a633f5a319cf4116d977e25fea2830dce23a8e74 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Sat, 22 Feb 2014 06:18:17 -0500 Subject: ext4: translate fallocate mode bits to strings Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + fs/ext4/extents.c | 1 - include/trace/events/ext4.h | 9 +++++++-- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d3a534fdc5ff..b7207db3107c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -31,6 +31,7 @@ #include #include #include +#include #ifdef __KERNEL__ #include #endif diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ef4b535e0a02..2e0608e3be6e 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include "ext4_jbd2.h" diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 197d3125df2a..451e0202aa69 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -68,6 +68,11 @@ struct extent_status; { EXTENT_STATUS_DELAYED, "D" }, \ { EXTENT_STATUS_HOLE, "H" }) +#define show_falloc_mode(mode) __print_flags(mode, "|", \ + { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \ + { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \ + { FALLOC_FL_NO_HIDE_STALE, "NO_HIDE_STALE"}) + TRACE_EVENT(ext4_free_inode, TP_PROTO(struct inode *inode), @@ -1349,10 +1354,10 @@ TRACE_EVENT(ext4_fallocate_enter, __entry->mode = mode; ), - TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %d", + TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, - __entry->len, __entry->mode) + __entry->len, show_falloc_mode(__entry->mode)) ); TRACE_EVENT(ext4_fallocate_exit, -- cgit v1.2.3 From 9eb79482a97152930b113b51dff530aba9e28c8e Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 23 Feb 2014 15:18:59 -0500 Subject: ext4: Add support FALLOC_FL_COLLAPSE_RANGE for fallocate This patch implements fallocate's FALLOC_FL_COLLAPSE_RANGE for Ext4. The semantics of this flag are following: 1) It collapses the range lying between offset and length by removing any data blocks which are present in this range and than updates all the logical offsets of extents beyond "offset + len" to nullify the hole created by removing blocks. In short, it does not leave a hole. 2) It should be used exclusively. No other fallocate flag in combination. 3) Offset and length supplied to fallocate should be fs block size aligned in case of xfs and ext4. 4) Collaspe range does not work beyond i_size. Signed-off-by: Namjae Jeon Signed-off-by: Ashish Sangwan Tested-by: Dongsu Park Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 3 + fs/ext4/extents.c | 307 +++++++++++++++++++++++++++++++++++++++++++- fs/ext4/move_extent.c | 2 +- include/trace/events/ext4.h | 33 ++++- 4 files changed, 342 insertions(+), 3 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b7207db3107c..beec42750a8c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2758,6 +2758,7 @@ extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk); extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); extern int ext4_ext_precache(struct inode *inode); +extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); /* move_extent.c */ extern void ext4_double_down_write_data_sem(struct inode *first, @@ -2767,6 +2768,8 @@ extern void ext4_double_up_write_data_sem(struct inode *orig_inode, extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 start_orig, __u64 start_donor, __u64 len, __u64 *moved_len); +extern int mext_next_extent(struct inode *inode, struct ext4_ext_path *path, + struct ext4_extent **extent); /* page-io.c */ extern int __init ext4_init_pageio(void); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 2e0608e3be6e..bbba1ef5417d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4581,12 +4581,16 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) unsigned int credits, blkbits = inode->i_blkbits; /* Return error if mode is not supported */ - if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | + FALLOC_FL_COLLAPSE_RANGE)) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) return ext4_punch_hole(inode, offset, len); + if (mode & FALLOC_FL_COLLAPSE_RANGE) + return ext4_collapse_range(inode, offset, len); + ret = ext4_convert_inline_data(inode); if (ret) return ret; @@ -4885,3 +4889,304 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, ext4_es_lru_add(inode); return error; } + +/* + * ext4_access_path: + * Function to access the path buffer for marking it dirty. + * It also checks if there are sufficient credits left in the journal handle + * to update path. + */ +static int +ext4_access_path(handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) +{ + int credits, err; + + if (!ext4_handle_valid(handle)) + return 0; + + /* + * Check if need to extend journal credits + * 3 for leaf, sb, and inode plus 2 (bmap and group + * descriptor) for each block group; assume two block + * groups + */ + if (handle->h_buffer_credits < 7) { + credits = ext4_writepage_trans_blocks(inode); + err = ext4_ext_truncate_extend_restart(handle, inode, credits); + /* EAGAIN is success */ + if (err && err != -EAGAIN) + return err; + } + + err = ext4_ext_get_access(handle, inode, path); + return err; +} + +/* + * ext4_ext_shift_path_extents: + * Shift the extents of a path structure lying between path[depth].p_ext + * and EXT_LAST_EXTENT(path[depth].p_hdr) downwards, by subtracting shift + * from starting block for each extent. + */ +static int +ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, + struct inode *inode, handle_t *handle, + ext4_lblk_t *start) +{ + int depth, err = 0; + struct ext4_extent *ex_start, *ex_last; + bool update = 0; + depth = path->p_depth; + + while (depth >= 0) { + if (depth == path->p_depth) { + ex_start = path[depth].p_ext; + if (!ex_start) + return -EIO; + + ex_last = EXT_LAST_EXTENT(path[depth].p_hdr); + if (!ex_last) + return -EIO; + + err = ext4_access_path(handle, inode, path + depth); + if (err) + goto out; + + if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) + update = 1; + + *start = ex_last->ee_block + + ext4_ext_get_actual_len(ex_last); + + while (ex_start <= ex_last) { + ex_start->ee_block -= shift; + if (ex_start > + EXT_FIRST_EXTENT(path[depth].p_hdr)) { + if (ext4_ext_try_to_merge_right(inode, + path, ex_start - 1)) + ex_last--; + } + ex_start++; + } + err = ext4_ext_dirty(handle, inode, path + depth); + if (err) + goto out; + + if (--depth < 0 || !update) + break; + } + + /* Update index too */ + err = ext4_access_path(handle, inode, path + depth); + if (err) + goto out; + + path[depth].p_idx->ei_block -= shift; + err = ext4_ext_dirty(handle, inode, path + depth); + if (err) + goto out; + + /* we are done if current index is not a starting index */ + if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr)) + break; + + depth--; + } + +out: + return err; +} + +/* + * ext4_ext_shift_extents: + * All the extents which lies in the range from start to the last allocated + * block for the file are shifted downwards by shift blocks. + * On success, 0 is returned, error otherwise. + */ +static int +ext4_ext_shift_extents(struct inode *inode, handle_t *handle, + ext4_lblk_t start, ext4_lblk_t shift) +{ + struct ext4_ext_path *path; + int ret = 0, depth; + struct ext4_extent *extent; + ext4_lblk_t stop_block, current_block; + ext4_lblk_t ex_start, ex_end; + + /* Let path point to the last extent */ + path = ext4_ext_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0); + if (IS_ERR(path)) + return PTR_ERR(path); + + depth = path->p_depth; + extent = path[depth].p_ext; + if (!extent) { + ext4_ext_drop_refs(path); + kfree(path); + return ret; + } + + stop_block = extent->ee_block + ext4_ext_get_actual_len(extent); + ext4_ext_drop_refs(path); + kfree(path); + + /* Nothing to shift, if hole is at the end of file */ + if (start >= stop_block) + return ret; + + /* + * Don't start shifting extents until we make sure the hole is big + * enough to accomodate the shift. + */ + path = ext4_ext_find_extent(inode, start - 1, NULL, 0); + depth = path->p_depth; + extent = path[depth].p_ext; + ex_start = extent->ee_block; + ex_end = extent->ee_block + ext4_ext_get_actual_len(extent); + ext4_ext_drop_refs(path); + kfree(path); + + if ((start == ex_start && shift > ex_start) || + (shift > start - ex_end)) + return -EINVAL; + + /* Its safe to start updating extents */ + while (start < stop_block) { + path = ext4_ext_find_extent(inode, start, NULL, 0); + if (IS_ERR(path)) + return PTR_ERR(path); + depth = path->p_depth; + extent = path[depth].p_ext; + current_block = extent->ee_block; + if (start > current_block) { + /* Hole, move to the next extent */ + ret = mext_next_extent(inode, path, &extent); + if (ret != 0) { + ext4_ext_drop_refs(path); + kfree(path); + if (ret == 1) + ret = 0; + break; + } + } + ret = ext4_ext_shift_path_extents(path, shift, inode, + handle, &start); + ext4_ext_drop_refs(path); + kfree(path); + if (ret) + break; + } + + return ret; +} + +/* + * ext4_collapse_range: + * This implements the fallocate's collapse range functionality for ext4 + * Returns: 0 and non-zero on error. + */ +int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +{ + struct super_block *sb = inode->i_sb; + ext4_lblk_t punch_start, punch_stop; + handle_t *handle; + unsigned int credits; + loff_t new_size; + int ret; + + BUG_ON(offset + len > i_size_read(inode)); + + /* Collapse range works only on fs block size aligned offsets. */ + if (offset & (EXT4_BLOCK_SIZE(sb) - 1) || + len & (EXT4_BLOCK_SIZE(sb) - 1)) + return -EINVAL; + + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + trace_ext4_collapse_range(inode, offset, len); + + punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb); + punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb); + + /* Write out all dirty pages */ + ret = filemap_write_and_wait_range(inode->i_mapping, offset, -1); + if (ret) + return ret; + + /* Take mutex lock */ + mutex_lock(&inode->i_mutex); + + /* It's not possible punch hole on append only file */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { + ret = -EPERM; + goto out_mutex; + } + + if (IS_SWAPFILE(inode)) { + ret = -ETXTBSY; + goto out_mutex; + } + + /* Currently just for extent based files */ + if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { + ret = -EOPNOTSUPP; + goto out_mutex; + } + + truncate_pagecache_range(inode, offset, -1); + + /* Wait for existing dio to complete */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + + credits = ext4_writepage_trans_blocks(inode); + handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_dio; + } + + down_write(&EXT4_I(inode)->i_data_sem); + ext4_discard_preallocations(inode); + + ret = ext4_es_remove_extent(inode, punch_start, + EXT_MAX_BLOCKS - punch_start - 1); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_stop; + } + + ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_stop; + } + + ret = ext4_ext_shift_extents(inode, handle, punch_stop, + punch_stop - punch_start); + if (ret) { + up_write(&EXT4_I(inode)->i_data_sem); + goto out_stop; + } + + new_size = i_size_read(inode) - len; + truncate_setsize(inode, new_size); + EXT4_I(inode)->i_disksize = new_size; + + ext4_discard_preallocations(inode); + up_write(&EXT4_I(inode)->i_data_sem); + if (IS_SYNC(inode)) + ext4_handle_sync(handle); + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); + +out_stop: + ext4_journal_stop(handle); +out_dio: + ext4_inode_resume_unlocked_dio(inode); +out_mutex: + mutex_unlock(&inode->i_mutex); + return ret; +} diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index f39a88abe32c..58ee7dc87669 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -76,7 +76,7 @@ copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest) * ext4_ext_path structure refers to the last extent, or a negative error * value on failure. */ -static int +int mext_next_extent(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent **extent) { diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 451e0202aa69..e9d7ee77d3a1 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -16,6 +16,11 @@ struct mpage_da_data; struct ext4_map_blocks; struct extent_status; +/* shim until we merge in the xfs_collapse_range branch */ +#ifndef FALLOC_FL_COLLAPSE_RANGE +#define FALLOC_FL_COLLAPSE_RANGE 0x08 +#endif + #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) #define show_mballoc_flags(flags) __print_flags(flags, "|", \ @@ -71,7 +76,8 @@ struct extent_status; #define show_falloc_mode(mode) __print_flags(mode, "|", \ { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \ { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \ - { FALLOC_FL_NO_HIDE_STALE, "NO_HIDE_STALE"}) + { FALLOC_FL_NO_HIDE_STALE, "NO_HIDE_STALE"}, \ + { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}) TRACE_EVENT(ext4_free_inode, @@ -2415,6 +2421,31 @@ TRACE_EVENT(ext4_es_shrink_exit, __entry->shrunk_nr, __entry->cache_cnt) ); +TRACE_EVENT(ext4_collapse_range, + TP_PROTO(struct inode *inode, loff_t offset, loff_t len), + + TP_ARGS(inode, offset, len), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, offset) + __field(loff_t, len) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->offset = offset; + __entry->len = len; + ), + + TP_printk("dev %d,%d ino %lu offset %lld len %lld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->offset, __entry->len) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 31cf0f2c3195258f83adabf1a71a782a92b8268a Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Thu, 13 Mar 2014 23:14:46 -0400 Subject: ext4: delete path dealloc code in ext4_ext_handle_uninitialized_extents Code deallocating the extent path referenced by an argument to ext4_ext_handle_uninitialized_extents was made redundant with identical code in its one caller, ext4_ext_map_blocks, by commit 3779473246. Allocating and deallocating the path in the same function also makes the code clearer. Signed-off-by: Eric Whitney Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index bbba1ef5417d..17b2fb2e8d19 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4005,10 +4005,6 @@ out1: map->m_pblk = newblock; map->m_len = allocated; out2: - if (path) { - ext4_ext_drop_refs(path); - kfree(path); - } return err ? err : allocated; } @@ -4208,7 +4204,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, err = ret; else allocated = ret; - goto out3; + goto out2; } } @@ -4489,7 +4485,6 @@ out2: kfree(path); } -out3: trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); ext4_es_lru_add(inode); -- cgit v1.2.3 From c06344939422bbd032ac967223a7863de57496b5 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Thu, 13 Mar 2014 23:34:16 -0400 Subject: ext4: fix partial cluster handling for bigalloc file systems Commit 9cb00419fa, which enables hole punching for bigalloc file systems, exposed a bug introduced by commit 6ae06ff51e in an earlier release. When run on a bigalloc file system, xfstests generic/013, 068, 075, 083, 091, 100, 112, 127, 263, 269, and 270 fail with e2fsck errors or cause kernel error messages indicating that previously freed blocks are being freed again. The latter commit optimizes the selection of the starting extent in ext4_ext_rm_leaf() when hole punching by beginning with the extent supplied in the path argument rather than with the last extent in the leaf node (as is still done when truncating). However, the code in rm_leaf that initially sets partial_cluster to track cluster sharing on extent boundaries is only guaranteed to run if rm_leaf starts with the last node in the leaf. Consequently, partial_cluster is not correctly initialized when hole punching, and a cluster on the boundary of a punched region that should be retained may instead be deallocated. Signed-off-by: Eric Whitney Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext4/extents.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 17b2fb2e8d19..e35f93b4cb13 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2597,6 +2597,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); + /* + * If we're starting with an extent other than the last one in the + * node, we need to see if it shares a cluster with the extent to + * the right (towards the end of the file). If its leftmost cluster + * is this extent's rightmost cluster and it is not cluster aligned, + * we'll mark it as a partial that is not to be deallocated. + */ + + if (ex != EXT_LAST_EXTENT(eh)) { + ext4_fsblk_t current_pblk, right_pblk; + long long current_cluster, right_cluster; + + current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1; + current_cluster = (long long)EXT4_B2C(sbi, current_pblk); + right_pblk = ext4_ext_pblock(ex + 1); + right_cluster = (long long)EXT4_B2C(sbi, right_pblk); + if (current_cluster == right_cluster && + EXT4_PBLK_COFF(sbi, right_pblk)) + *partial_cluster = -right_cluster; + } + trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster); while (ex >= EXT_FIRST_EXTENT(eh) && -- cgit v1.2.3 From f282ac19d86f0507e91759dcf3d15fcb3a964d2a Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 18 Mar 2014 17:44:35 -0400 Subject: ext4: Update inode i_size after the preallocation Currently in ext4_fallocate we would update inode size, c_time and sync the file with every partial allocation which is entirely unnecessary. It is true that if the crash happens in the middle of truncate we might end up with unchanged i size, or c_time which I do not think is really a problem - it does not mean file system corruption in any way. Note that xfs is doing things the same way e.g. update all of the mentioned after the allocation is done. This commit moves all the updates after the allocation is done. In addition we also need to change m_time as not only inode has been change bot also data regions might have changed (unwritten extents). However m_time will be only updated when i_size changed. Also we do not need to be paranoid about changing the c_time only if the actual allocation have happened, we can change it even if we try to allocate only to find out that there are already block allocated. It's not really a big deal and it will save us some additional complexity. Also use ext4_debug, instead of ext4_warning in #ifdef EXT4FS_DEBUG section. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" - -- v3: Do not remove the code to set EXT4_INODE_EOFBLOCKS flag fs/ext4/extents.c | 96 ++++++++++++++++++++++++------------------------------- 1 file changed, 42 insertions(+), 54 deletions(-) --- fs/ext4/extents.c | 96 ++++++++++++++++++++++++------------------------------- 1 file changed, 42 insertions(+), 54 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e35f93b4cb13..e4be6b79121d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4546,36 +4546,6 @@ retry: ext4_std_error(inode->i_sb, err); } -static void ext4_falloc_update_inode(struct inode *inode, - int mode, loff_t new_size, int update_ctime) -{ - struct timespec now; - - if (update_ctime) { - now = current_fs_time(inode->i_sb); - if (!timespec_equal(&inode->i_ctime, &now)) - inode->i_ctime = now; - } - /* - * Update only when preallocation was requested beyond - * the file size. - */ - if (!(mode & FALLOC_FL_KEEP_SIZE)) { - if (new_size > i_size_read(inode)) - i_size_write(inode, new_size); - if (new_size > EXT4_I(inode)->i_disksize) - ext4_update_i_disksize(inode, new_size); - } else { - /* - * Mark that we allocate beyond EOF so the subsequent truncate - * can proceed even if the new size is the same as i_size. - */ - if (new_size > i_size_read(inode)) - ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS); - } - -} - /* * preallocate space for a file. This implements ext4's fallocate file * operation, which gets called from sys_fallocate system call. @@ -4587,13 +4557,14 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); handle_t *handle; - loff_t new_size; + loff_t new_size = 0; unsigned int max_blocks; int ret = 0; int ret2 = 0; int retries = 0; int flags; struct ext4_map_blocks map; + struct timespec tv; unsigned int credits, blkbits = inode->i_blkbits; /* Return error if mode is not supported */ @@ -4631,12 +4602,15 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) */ credits = ext4_chunk_trans_blocks(inode, max_blocks); mutex_lock(&inode->i_mutex); - ret = inode_newsize_ok(inode, (len + offset)); - if (ret) { - mutex_unlock(&inode->i_mutex); - trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); - return ret; + + if (!(mode & FALLOC_FL_KEEP_SIZE) && + offset + len > i_size_read(inode)) { + new_size = offset + len; + ret = inode_newsize_ok(inode, new_size); + if (ret) + goto out; } + flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT; if (mode & FALLOC_FL_KEEP_SIZE) flags |= EXT4_GET_BLOCKS_KEEP_SIZE; @@ -4660,28 +4634,14 @@ retry: } ret = ext4_map_blocks(handle, inode, &map, flags); if (ret <= 0) { -#ifdef EXT4FS_DEBUG - ext4_warning(inode->i_sb, - "inode #%lu: block %u: len %u: " - "ext4_ext_map_blocks returned %d", - inode->i_ino, map.m_lblk, - map.m_len, ret); -#endif + ext4_debug("inode #%lu: block %u: len %u: " + "ext4_ext_map_blocks returned %d", + inode->i_ino, map.m_lblk, + map.m_len, ret); ext4_mark_inode_dirty(handle, inode); ret2 = ext4_journal_stop(handle); break; } - if ((map.m_lblk + ret) >= (EXT4_BLOCK_ALIGN(offset + len, - blkbits) >> blkbits)) - new_size = offset + len; - else - new_size = ((loff_t) map.m_lblk + ret) << blkbits; - - ext4_falloc_update_inode(inode, mode, new_size, - (map.m_flags & EXT4_MAP_NEW)); - ext4_mark_inode_dirty(handle, inode); - if ((file->f_flags & O_SYNC) && ret >= max_blocks) - ext4_handle_sync(handle); ret2 = ext4_journal_stop(handle); if (ret2) break; @@ -4691,6 +4651,34 @@ retry: ret = 0; goto retry; } + + handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); + if (IS_ERR(handle)) + goto out; + + tv = inode->i_ctime = ext4_current_time(inode); + + if (ret > 0 && new_size) { + if (new_size > i_size_read(inode)) { + i_size_write(inode, new_size); + inode->i_mtime = tv; + } + if (new_size > EXT4_I(inode)->i_disksize) + ext4_update_i_disksize(inode, new_size); + } else if (ret > 0 && !new_size) { + /* + * Mark that we allocate beyond EOF so the subsequent truncate + * can proceed even if the new size is the same as i_size. + */ + if ((offset + len) > i_size_read(inode)) + ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS); + } + ext4_mark_inode_dirty(handle, inode); + if (file->f_flags & O_SYNC) + ext4_handle_sync(handle); + + ext4_journal_stop(handle); +out: mutex_unlock(&inode->i_mutex); trace_ext4_fallocate_exit(inode, offset, max_blocks, ret > 0 ? ret2 : ret); -- cgit v1.2.3 From 0e8b6879f3c234036181526683be2b0231892ae4 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 18 Mar 2014 18:03:51 -0400 Subject: ext4: refactor ext4_fallocate code Move block allocation out of the ext4_fallocate into separate function called ext4_alloc_file_blocks(). This will allow us to use the same allocation code for other allocation operations such as zero range which is commit in the next patch. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 129 +++++++++++++++++++++++++++++++----------------------- 1 file changed, 74 insertions(+), 55 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e4be6b79121d..2db2d77769a2 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4546,6 +4546,64 @@ retry: ext4_std_error(inode->i_sb, err); } +static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, + ext4_lblk_t len, int flags, int mode) +{ + struct inode *inode = file_inode(file); + handle_t *handle; + int ret = 0; + int ret2 = 0; + int retries = 0; + struct ext4_map_blocks map; + unsigned int credits; + + map.m_lblk = offset; + /* + * Don't normalize the request if it can fit in one extent so + * that it doesn't get unnecessarily split into multiple + * extents. + */ + if (len <= EXT_UNINIT_MAX_LEN) + flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; + + /* + * credits to insert 1 extent into extent tree + */ + credits = ext4_chunk_trans_blocks(inode, len); + +retry: + while (ret >= 0 && ret < len) { + map.m_lblk = map.m_lblk + ret; + map.m_len = len = len - ret; + handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, + credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + break; + } + ret = ext4_map_blocks(handle, inode, &map, flags); + if (ret <= 0) { + ext4_debug("inode #%lu: block %u: len %u: " + "ext4_ext_map_blocks returned %d", + inode->i_ino, map.m_lblk, + map.m_len, ret); + ext4_mark_inode_dirty(handle, inode); + ret2 = ext4_journal_stop(handle); + break; + } + ret2 = ext4_journal_stop(handle); + if (ret2) + break; + } + if (ret == -ENOSPC && + ext4_should_retry_alloc(inode->i_sb, &retries)) { + ret = 0; + goto retry; + } + + return ret > 0 ? ret2 : ret; +} + /* * preallocate space for a file. This implements ext4's fallocate file * operation, which gets called from sys_fallocate system call. @@ -4560,12 +4618,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) loff_t new_size = 0; unsigned int max_blocks; int ret = 0; - int ret2 = 0; - int retries = 0; int flags; - struct ext4_map_blocks map; + ext4_lblk_t lblk; struct timespec tv; - unsigned int credits, blkbits = inode->i_blkbits; + unsigned int blkbits = inode->i_blkbits; /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | @@ -4590,17 +4646,18 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) return -EOPNOTSUPP; trace_ext4_fallocate_enter(inode, offset, len, mode); - map.m_lblk = offset >> blkbits; + lblk = offset >> blkbits; /* * We can't just convert len to max_blocks because * If blocksize = 4096 offset = 3072 and len = 2048 */ max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) - - map.m_lblk; - /* - * credits to insert 1 extent into extent tree - */ - credits = ext4_chunk_trans_blocks(inode, max_blocks); + - lblk; + + flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT; + if (mode & FALLOC_FL_KEEP_SIZE) + flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + mutex_lock(&inode->i_mutex); if (!(mode & FALLOC_FL_KEEP_SIZE) && @@ -4611,46 +4668,9 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto out; } - flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT; - if (mode & FALLOC_FL_KEEP_SIZE) - flags |= EXT4_GET_BLOCKS_KEEP_SIZE; - /* - * Don't normalize the request if it can fit in one extent so - * that it doesn't get unnecessarily split into multiple - * extents. - */ - if (len <= EXT_UNINIT_MAX_LEN << blkbits) - flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; - -retry: - while (ret >= 0 && ret < max_blocks) { - map.m_lblk = map.m_lblk + ret; - map.m_len = max_blocks = max_blocks - ret; - handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, - credits); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - break; - } - ret = ext4_map_blocks(handle, inode, &map, flags); - if (ret <= 0) { - ext4_debug("inode #%lu: block %u: len %u: " - "ext4_ext_map_blocks returned %d", - inode->i_ino, map.m_lblk, - map.m_len, ret); - ext4_mark_inode_dirty(handle, inode); - ret2 = ext4_journal_stop(handle); - break; - } - ret2 = ext4_journal_stop(handle); - if (ret2) - break; - } - if (ret == -ENOSPC && - ext4_should_retry_alloc(inode->i_sb, &retries)) { - ret = 0; - goto retry; - } + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags, mode); + if (ret) + goto out; handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) @@ -4658,14 +4678,14 @@ retry: tv = inode->i_ctime = ext4_current_time(inode); - if (ret > 0 && new_size) { + if (!ret && new_size) { if (new_size > i_size_read(inode)) { i_size_write(inode, new_size); inode->i_mtime = tv; } if (new_size > EXT4_I(inode)->i_disksize) ext4_update_i_disksize(inode, new_size); - } else if (ret > 0 && !new_size) { + } else if (!ret && !new_size) { /* * Mark that we allocate beyond EOF so the subsequent truncate * can proceed even if the new size is the same as i_size. @@ -4680,9 +4700,8 @@ retry: ext4_journal_stop(handle); out: mutex_unlock(&inode->i_mutex); - trace_ext4_fallocate_exit(inode, offset, max_blocks, - ret > 0 ? ret2 : ret); - return ret > 0 ? ret2 : ret; + trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); + return ret; } /* -- cgit v1.2.3 From b8a8684502a0fc852afa0056c6bb2a9273f6fcc0 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 18 Mar 2014 18:05:35 -0400 Subject: ext4: Introduce FALLOC_FL_ZERO_RANGE flag for fallocate Introduce new FALLOC_FL_ZERO_RANGE flag for fallocate. This has the same functionality as xfs ioctl XFS_IOC_ZERO_RANGE. It can be used to convert a range of file to zeros preferably without issuing data IO. Blocks should be preallocated for the regions that span holes in the file, and the entire range is preferable converted to unwritten extents This can be also used to preallocate blocks past EOF in the same way as with fallocate. Flag FALLOC_FL_KEEP_SIZE which should cause the inode size to remain the same. Also add appropriate tracepoints. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 + fs/ext4/extents.c | 273 +++++++++++++++++++++++++++++++++++++++++--- fs/ext4/inode.c | 17 ++- include/trace/events/ext4.h | 68 +++++------ 4 files changed, 307 insertions(+), 53 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index beec42750a8c..1b3cbf8cacf9 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -568,6 +568,8 @@ enum { #define EXT4_GET_BLOCKS_NO_LOCK 0x0100 /* Do not put hole in extent cache */ #define EXT4_GET_BLOCKS_NO_PUT_HOLE 0x0200 + /* Convert written extents to unwritten */ +#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN 0x0400 /* * The bit position of these flags must not overlap with any of the diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 2db2d77769a2..464e95da716e 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3602,6 +3602,8 @@ out: * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * + * This works the same way in the case of initialized -> unwritten conversion. + * * One of more index blocks maybe needed if the extent tree grow after * the uninitialized extent split. To prevent ENOSPC occur at the IO * complete, we need to split the uninitialized extent before DIO submit @@ -3612,7 +3614,7 @@ out: * * Returns the size of uninitialized extent to be written on success. */ -static int ext4_split_unwritten_extents(handle_t *handle, +static int ext4_split_convert_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, @@ -3624,9 +3626,9 @@ static int ext4_split_unwritten_extents(handle_t *handle, unsigned int ee_len; int split_flag = 0, depth; - ext_debug("ext4_split_unwritten_extents: inode %lu, logical" - "block %llu, max_blocks %u\n", inode->i_ino, - (unsigned long long)map->m_lblk, map->m_len); + ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n", + __func__, inode->i_ino, + (unsigned long long)map->m_lblk, map->m_len); eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; @@ -3641,14 +3643,73 @@ static int ext4_split_unwritten_extents(handle_t *handle, ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); - split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; - split_flag |= EXT4_EXT_MARK_UNINIT2; - if (flags & EXT4_GET_BLOCKS_CONVERT) - split_flag |= EXT4_EXT_DATA_VALID2; + /* Convert to unwritten */ + if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) { + split_flag |= EXT4_EXT_DATA_VALID1; + /* Convert to initialized */ + } else if (flags & EXT4_GET_BLOCKS_CONVERT) { + split_flag |= ee_block + ee_len <= eof_block ? + EXT4_EXT_MAY_ZEROOUT : 0; + split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2); + } flags |= EXT4_GET_BLOCKS_PRE_IO; return ext4_split_extent(handle, inode, path, map, split_flag, flags); } +static int ext4_convert_initialized_extents(handle_t *handle, + struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path) +{ + struct ext4_extent *ex; + ext4_lblk_t ee_block; + unsigned int ee_len; + int depth; + int err = 0; + + depth = ext_depth(inode); + ex = path[depth].p_ext; + ee_block = le32_to_cpu(ex->ee_block); + ee_len = ext4_ext_get_actual_len(ex); + + ext_debug("%s: inode %lu, logical" + "block %llu, max_blocks %u\n", __func__, inode->i_ino, + (unsigned long long)ee_block, ee_len); + + if (ee_block != map->m_lblk || ee_len > map->m_len) { + err = ext4_split_convert_extents(handle, inode, map, path, + EXT4_GET_BLOCKS_CONVERT_UNWRITTEN); + if (err < 0) + goto out; + ext4_ext_drop_refs(path); + path = ext4_ext_find_extent(inode, map->m_lblk, path, 0); + if (IS_ERR(path)) { + err = PTR_ERR(path); + goto out; + } + depth = ext_depth(inode); + ex = path[depth].p_ext; + } + + err = ext4_ext_get_access(handle, inode, path + depth); + if (err) + goto out; + /* first mark the extent as uninitialized */ + ext4_ext_mark_uninitialized(ex); + + /* note: ext4_ext_correct_indexes() isn't needed here because + * borders are not changed + */ + ext4_ext_try_to_merge(handle, inode, path, ex); + + /* Mark modified extent as dirty */ + err = ext4_ext_dirty(handle, inode, path + path->p_depth); +out: + ext4_ext_show_leaf(inode, path); + return err; +} + + static int ext4_convert_unwritten_extents_endio(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, @@ -3682,8 +3743,8 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, inode->i_ino, (unsigned long long)ee_block, ee_len, (unsigned long long)map->m_lblk, map->m_len); #endif - err = ext4_split_unwritten_extents(handle, inode, map, path, - EXT4_GET_BLOCKS_CONVERT); + err = ext4_split_convert_extents(handle, inode, map, path, + EXT4_GET_BLOCKS_CONVERT); if (err < 0) goto out; ext4_ext_drop_refs(path); @@ -3883,6 +3944,38 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, return allocated_clusters; } +static int +ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path, int flags, + unsigned int allocated, ext4_fsblk_t newblock) +{ + int ret = 0; + int err = 0; + + /* + * Make sure that the extent is no bigger than we support with + * uninitialized extent + */ + if (map->m_len > EXT_UNINIT_MAX_LEN) + map->m_len = EXT_UNINIT_MAX_LEN / 2; + + ret = ext4_convert_initialized_extents(handle, inode, map, + path); + if (ret >= 0) { + ext4_update_inode_fsync_trans(handle, inode, 1); + err = check_eofblocks_fl(handle, inode, map->m_lblk, + path, map->m_len); + } else + err = ret; + map->m_flags |= EXT4_MAP_UNWRITTEN; + if (allocated > map->m_len) + allocated = map->m_len; + map->m_len = allocated; + + return err ? err : allocated; +} + static int ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, @@ -3910,8 +4003,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, /* get_block() before submit the IO, split the extent */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { - ret = ext4_split_unwritten_extents(handle, inode, map, - path, flags); + ret = ext4_split_convert_extents(handle, inode, map, + path, flags | EXT4_GET_BLOCKS_CONVERT); if (ret <= 0) goto out; /* @@ -4199,6 +4292,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len; + /* * Uninitialized extents are treated as holes, except that * we split out initialized portions during a write. @@ -4215,7 +4309,17 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk, ee_block, ee_len, newblock); - if (!ext4_ext_is_uninitialized(ex)) + /* + * If the extent is initialized check whether the + * caller wants to convert it to unwritten. + */ + if ((!ext4_ext_is_uninitialized(ex)) && + (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { + allocated = ext4_ext_convert_initialized_extent( + handle, inode, map, path, flags, + allocated, newblock); + goto out2; + } else if (!ext4_ext_is_uninitialized(ex)) goto out; ret = ext4_ext_handle_uninitialized_extents( @@ -4604,6 +4708,144 @@ retry: return ret > 0 ? ret2 : ret; } +static long ext4_zero_range(struct file *file, loff_t offset, + loff_t len, int mode) +{ + struct inode *inode = file_inode(file); + handle_t *handle = NULL; + unsigned int max_blocks; + loff_t new_size = 0; + int ret = 0; + int flags; + int partial; + loff_t start, end; + ext4_lblk_t lblk; + struct address_space *mapping = inode->i_mapping; + unsigned int blkbits = inode->i_blkbits; + + trace_ext4_zero_range(inode, offset, len, mode); + + /* + * Write out all dirty pages to avoid race conditions + * Then release them. + */ + if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { + ret = filemap_write_and_wait_range(mapping, offset, + offset + len - 1); + if (ret) + return ret; + } + + /* + * Round up offset. This is not fallocate, we neet to zero out + * blocks, so convert interior block aligned part of the range to + * unwritten and possibly manually zero out unaligned parts of the + * range. + */ + start = round_up(offset, 1 << blkbits); + end = round_down((offset + len), 1 << blkbits); + + if (start < offset || end > offset + len) + return -EINVAL; + partial = (offset + len) & ((1 << blkbits) - 1); + + lblk = start >> blkbits; + max_blocks = (end >> blkbits); + if (max_blocks < lblk) + max_blocks = 0; + else + max_blocks -= lblk; + + flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT | + EXT4_GET_BLOCKS_CONVERT_UNWRITTEN; + if (mode & FALLOC_FL_KEEP_SIZE) + flags |= EXT4_GET_BLOCKS_KEEP_SIZE; + + mutex_lock(&inode->i_mutex); + + /* + * Indirect files do not support unwritten extnets + */ + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { + ret = -EOPNOTSUPP; + goto out_mutex; + } + + if (!(mode & FALLOC_FL_KEEP_SIZE) && + offset + len > i_size_read(inode)) { + new_size = offset + len; + ret = inode_newsize_ok(inode, new_size); + if (ret) + goto out_mutex; + /* + * If we have a partial block after EOF we have to allocate + * the entire block. + */ + if (partial) + max_blocks += 1; + } + + if (max_blocks > 0) { + + /* Now release the pages and zero block aligned part of pages*/ + truncate_pagecache_range(inode, start, end - 1); + + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + + /* + * Remove entire range from the extent status tree. + */ + ret = ext4_es_remove_extent(inode, lblk, max_blocks); + if (ret) + goto out_dio; + + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags, + mode); + if (ret) + goto out_dio; + } + + handle = ext4_journal_start(inode, EXT4_HT_MISC, 4); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + ext4_std_error(inode->i_sb, ret); + goto out_dio; + } + + inode->i_mtime = inode->i_ctime = ext4_current_time(inode); + + if (!ret && new_size) { + if (new_size > i_size_read(inode)) + i_size_write(inode, new_size); + if (new_size > EXT4_I(inode)->i_disksize) + ext4_update_i_disksize(inode, new_size); + } else if (!ret && !new_size) { + /* + * Mark that we allocate beyond EOF so the subsequent truncate + * can proceed even if the new size is the same as i_size. + */ + if ((offset + len) > i_size_read(inode)) + ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS); + } + + ext4_mark_inode_dirty(handle, inode); + + /* Zero out partial block at the edges of the range */ + ret = ext4_zero_partial_blocks(handle, inode, offset, len); + + if (file->f_flags & O_SYNC) + ext4_handle_sync(handle); + + ext4_journal_stop(handle); +out_dio: + ext4_inode_resume_unlocked_dio(inode); +out_mutex: + mutex_unlock(&inode->i_mutex); + return ret; +} + /* * preallocate space for a file. This implements ext4's fallocate file * operation, which gets called from sys_fallocate system call. @@ -4625,7 +4867,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | - FALLOC_FL_COLLAPSE_RANGE)) + FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) @@ -4645,6 +4887,9 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EOPNOTSUPP; + if (mode & FALLOC_FL_ZERO_RANGE) + return ext4_zero_range(file, offset, len, mode); + trace_ext4_fallocate_enter(inode, offset, len, mode); lblk = offset >> blkbits; /* diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ab3e8357929d..7cc24555eca8 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -503,6 +503,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, { struct extent_status es; int retval; + int ret = 0; #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; @@ -558,7 +559,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, EXT4_GET_BLOCKS_KEEP_SIZE); } if (retval > 0) { - int ret; unsigned int status; if (unlikely(retval != map->m_len)) { @@ -585,7 +585,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, found: if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { - int ret = check_block_validity(inode, map); + ret = check_block_validity(inode, map); if (ret != 0) return ret; } @@ -602,7 +602,13 @@ found: * with buffer head unmapped. */ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) - return retval; + /* + * If we need to convert extent to unwritten + * we continue and do the actual work in + * ext4_ext_map_blocks() + */ + if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) + return retval; /* * Here we clear m_flags because after allocating an new extent, @@ -658,7 +664,6 @@ found: ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED); if (retval > 0) { - int ret; unsigned int status; if (unlikely(retval != map->m_len)) { @@ -693,7 +698,7 @@ found: has_zeroout: up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { - int ret = check_block_validity(inode, map); + ret = check_block_validity(inode, map); if (ret != 0) return ret; } @@ -3507,7 +3512,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) if (!S_ISREG(inode->i_mode)) return -EOPNOTSUPP; - trace_ext4_punch_hole(inode, offset, length); + trace_ext4_punch_hole(inode, offset, length, 0); /* * Write out all dirty pages to avoid race conditions diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index e9d7ee77d3a1..010ea89eeb0e 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -21,6 +21,10 @@ struct extent_status; #define FALLOC_FL_COLLAPSE_RANGE 0x08 #endif +#ifndef FALLOC_FL_ZERO_RANGE +#define FALLOC_FL_ZERO_RANGE 0x10 +#endif + #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) #define show_mballoc_flags(flags) __print_flags(flags, "|", \ @@ -77,7 +81,8 @@ struct extent_status; { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \ { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \ { FALLOC_FL_NO_HIDE_STALE, "NO_HIDE_STALE"}, \ - { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}) + { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \ + { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}) TRACE_EVENT(ext4_free_inode, @@ -1339,7 +1344,7 @@ TRACE_EVENT(ext4_direct_IO_exit, __entry->rw, __entry->ret) ); -TRACE_EVENT(ext4_fallocate_enter, +DECLARE_EVENT_CLASS(ext4__fallocate_mode, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode), @@ -1347,23 +1352,45 @@ TRACE_EVENT(ext4_fallocate_enter, TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) - __field( loff_t, pos ) - __field( loff_t, len ) + __field( loff_t, offset ) + __field( loff_t, len ) __field( int, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->pos = offset; + __entry->offset = offset; __entry->len = len; __entry->mode = mode; ), - TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %s", + TP_printk("dev %d,%d ino %lu offset %lld len %lld mode %s", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, __entry->pos, - __entry->len, show_falloc_mode(__entry->mode)) + (unsigned long) __entry->ino, + __entry->offset, __entry->len, + show_falloc_mode(__entry->mode)) +); + +DEFINE_EVENT(ext4__fallocate_mode, ext4_fallocate_enter, + + TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), + + TP_ARGS(inode, offset, len, mode) +); + +DEFINE_EVENT(ext4__fallocate_mode, ext4_punch_hole, + + TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), + + TP_ARGS(inode, offset, len, mode) +); + +DEFINE_EVENT(ext4__fallocate_mode, ext4_zero_range, + + TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), + + TP_ARGS(inode, offset, len, mode) ); TRACE_EVENT(ext4_fallocate_exit, @@ -1395,31 +1422,6 @@ TRACE_EVENT(ext4_fallocate_exit, __entry->ret) ); -TRACE_EVENT(ext4_punch_hole, - TP_PROTO(struct inode *inode, loff_t offset, loff_t len), - - TP_ARGS(inode, offset, len), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( loff_t, offset ) - __field( loff_t, len ) - ), - - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->offset = offset; - __entry->len = len; - ), - - TP_printk("dev %d,%d ino %lu offset %lld len %lld", - MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - __entry->offset, __entry->len) -); - TRACE_EVENT(ext4_unlink_enter, TP_PROTO(struct inode *parent, struct dentry *dentry), -- cgit v1.2.3 From e5b30416f3631bf4eed37c3bec9f789f9ae78446 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 1 Apr 2014 00:59:21 -0400 Subject: ext4: remove unneeded test of ret variable Currently in ext4_fallocate() and ext4_zero_range() we're testing ret variable along with new_size. However in ext4_fallocate() we just tested ret before and in ext4_zero_range() if will always be zero when we get there so there is no need to test it in both cases. Signed-off-by: Lukas Czerner Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 464e95da716e..c92ef8735ba2 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4816,12 +4816,12 @@ static long ext4_zero_range(struct file *file, loff_t offset, inode->i_mtime = inode->i_ctime = ext4_current_time(inode); - if (!ret && new_size) { + if (new_size) { if (new_size > i_size_read(inode)) i_size_write(inode, new_size); if (new_size > EXT4_I(inode)->i_disksize) ext4_update_i_disksize(inode, new_size); - } else if (!ret && !new_size) { + } else { /* * Mark that we allocate beyond EOF so the subsequent truncate * can proceed even if the new size is the same as i_size. @@ -4923,14 +4923,14 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) tv = inode->i_ctime = ext4_current_time(inode); - if (!ret && new_size) { + if (new_size) { if (new_size > i_size_read(inode)) { i_size_write(inode, new_size); inode->i_mtime = tv; } if (new_size > EXT4_I(inode)->i_disksize) ext4_update_i_disksize(inode, new_size); - } else if (!ret && !new_size) { + } else { /* * Mark that we allocate beyond EOF so the subsequent truncate * can proceed even if the new size is the same as i_size. -- cgit v1.2.3 From ad6599ab3ac98a4474544086e048ce86ec15a4d1 Mon Sep 17 00:00:00 2001 From: Eric Whitney Date: Tue, 1 Apr 2014 19:49:30 -0400 Subject: ext4: fix premature freeing of partial clusters split across leaf blocks Xfstests generic/311 and shared/298 fail when run on a bigalloc file system. Kernel error messages produced during the tests report that blocks to be freed are already on the to-be-freed list. When e2fsck is run at the end of the tests, it typically reports bad i_blocks and bad free blocks counts. The bug that causes these failures is located in ext4_ext_rm_leaf(). Code at the end of the function frees a partial cluster if it's not shared with an extent remaining in the leaf. However, if all the extents in the leaf have been removed, the code dereferences an invalid extent pointer (off the front of the leaf) when the check for sharing is made. This generally has the effect of unconditionally freeing the partial cluster, which leads to the observed failures when the partial cluster is shared with the last extent in the next leaf. Fix this by attempting to free the cluster only if extents remain in the leaf. Any remaining partial cluster will be freed if possible when the next leaf is processed or when leaf removal is complete. Signed-off-by: Eric Whitney Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext4/extents.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'fs/ext4/extents.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c92ef8735ba2..82df3ce9874a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2743,10 +2743,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, err = ext4_ext_correct_indexes(handle, inode, path); /* - * Free the partial cluster only if the current extent does not - * reference it. Otherwise we might free used cluster. + * If there's a partial cluster and at least one extent remains in + * the leaf, free the partial cluster if it isn't shared with the + * current extent. If there's a partial cluster and no extents + * remain in the leaf, it can't be freed here. It can only be + * freed when it's possible to determine if it's not shared with + * any other extent - when the next leaf is processed or when space + * removal is complete. */ - if (*partial_cluster > 0 && + if (*partial_cluster > 0 && eh->eh_entries && (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) != *partial_cluster)) { int flags = get_default_free_blocks_flags(inode); -- cgit v1.2.3