From 55583e899a5357308274601364741a83e78d6ac4 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 4 Jan 2024 22:20:33 +0800 Subject: ext4: fix double-free of blocks due to wrong extents moved_len In ext4_move_extents(), moved_len is only updated when all moves are successfully executed, and only discards orig_inode and donor_inode preallocations when moved_len is not zero. When the loop fails to exit after successfully moving some extents, moved_len is not updated and remains at 0, so it does not discard the preallocations. If the moved extents overlap with the preallocated extents, the overlapped extents are freed twice in ext4_mb_release_inode_pa() and ext4_process_freed_data() (as described in commit 94d7c16cbbbd ("ext4: Fix double-free of blocks with EXT4_IOC_MOVE_EXT")), and bb_free is incremented twice. Hence when trim is executed, a zero-division bug is triggered in mb_update_avg_fragment_size() because bb_free is not zero and bb_fragments is zero. Therefore, update move_len after each extent move to avoid the issue. Reported-by: Wei Chen Reported-by: xingwei lee Closes: https://lore.kernel.org/r/CAO4mrferzqBUnCag8R3m2zf897ts9UEuhjFQGPtODT92rYyR2Q@mail.gmail.com Fixes: fcf6b1b729bc ("ext4: refactor ext4_move_extents code base") CC: # 3.18 Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240104142040.2835097-2-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/move_extent.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 3aa57376d9c2..391efa6d4c56 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -618,6 +618,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, goto out; o_end = o_start + len; + *moved_len = 0; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; @@ -672,7 +673,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ - move_extent_per_page(o_filp, donor_inode, + *moved_len += move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); @@ -682,9 +683,6 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, o_start += cur_len; d_start += cur_len; } - *moved_len = o_start - orig_blk; - if (*moved_len > len) - *moved_len = len; out: if (*moved_len) { -- cgit v1.2.3 From 172202152a125955367393956acf5f4ffd092e0d Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 4 Jan 2024 22:20:34 +0800 Subject: ext4: do not trim the group with corrupted block bitmap Otherwise operating on an incorrupted block bitmap can lead to all sorts of unknown problems. Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240104142040.2835097-3-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f44f668e407f..c86c90b494de 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -6761,6 +6761,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) bool set_trimmed = false; void *bitmap; + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + return 0; + last = ext4_last_grp_cluster(sb, e4b->bd_group); bitmap = e4b->bd_bitmap; if (start == 0 && max >= last) -- cgit v1.2.3 From c9b528c35795b711331ed36dc3dbee90d5812d4e Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 4 Jan 2024 22:20:35 +0800 Subject: ext4: regenerate buddy after block freeing failed if under fc replay This mostly reverts commit 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") and reintroduces mb_regenerate_buddy(). Based on code in mb_free_blocks(), fast commit replay can end up marking as free blocks that are already marked as such. This causes corruption of the buddy bitmap so we need to regenerate it in that case. Reported-by: Jan Kara Fixes: 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240104142040.2835097-4-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c86c90b494de..c97ad0e77831 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1233,6 +1233,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, atomic64_add(period, &sbi->s_mb_generation_time); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) + mb_set_bits(buddy, 0, count); + + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1920,6 +1938,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, ext4_mark_group_bitmap_corrupted( sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); + } else { + mb_regenerate_buddy(e4b); } goto done; } -- cgit v1.2.3 From 2331fd4a49864e1571b4f50aa3aa1536ed6220d0 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 4 Jan 2024 22:20:36 +0800 Subject: ext4: avoid bb_free and bb_fragments inconsistency in mb_free_blocks() After updating bb_free in mb_free_blocks, it is possible to return without updating bb_fragments because the block being freed is found to have already been freed, which leads to inconsistency between bb_free and bb_fragments. Since the group may be unlocked in ext4_grp_locked_error(), this can lead to problems such as dividing by zero when calculating the average fragment length. Hence move the update of bb_free to after the block double-free check guarantees that the corresponding statistics are updated only after the core block bitmap is modified. Fixes: eabe0444df90 ("ext4: speed-up releasing blocks on commit") CC: # 3.10 Suggested-by: Jan Kara Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240104142040.2835097-5-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 39 +++++++++++++++++++++------------------ 1 file changed, 21 insertions(+), 18 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c97ad0e77831..fa351aa323dc 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1909,11 +1909,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); - this_cpu_inc(discard_pa_seq); - e4b->bd_info->bb_free += count; - if (first < e4b->bd_info->bb_first_free) - e4b->bd_info->bb_first_free = first; - /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ @@ -1927,23 +1922,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; + /* + * Fastcommit replay can free already freed blocks which + * corrupts allocation info. Regenerate it. + */ + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + mb_regenerate_buddy(e4b); + goto check; + } + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); - if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block (bit %u); block bitmap corrupt.", - block); - ext4_mark_group_bitmap_corrupted( - sb, e4b->bd_group, + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, blocknr, + "freeing already freed block (bit %u); block bitmap corrupt.", + block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); - } else { - mb_regenerate_buddy(e4b); - } - goto done; + return; } + this_cpu_inc(discard_pa_seq); + e4b->bd_info->bb_free += count; + if (first < e4b->bd_info->bb_first_free) + e4b->bd_info->bb_first_free = first; + /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; @@ -1968,9 +1971,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); -done: mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); +check: mb_check_buddy(e4b); } -- cgit v1.2.3 From 993bf0f4c393b3667830918f9247438a8f6fdb5b Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 4 Jan 2024 22:20:37 +0800 Subject: ext4: avoid dividing by 0 in mb_update_avg_fragment_size() when block bitmap corrupt Determine if bb_fragments is 0 instead of determining bb_free to eliminate the risk of dividing by zero when the block bitmap is corrupted. Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240104142040.2835097-6-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index fa351aa323dc..751e31df0f10 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -842,7 +842,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int new_order; - if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0) return; new_order = mb_avg_fragment_size_order(sb, -- cgit v1.2.3 From 4530b3660d396a646aad91a787b6ab37cf604b53 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 4 Jan 2024 22:20:38 +0800 Subject: ext4: avoid allocating blocks from corrupted group in ext4_mb_try_best_found() Determine if the group block bitmap is corrupted before using ac_b_ex in ext4_mb_try_best_found() to avoid allocating blocks from a group with a corrupted block bitmap in the following concurrency and making the situation worse. ext4_mb_regular_allocator ext4_lock_group(sb, group) ext4_mb_good_group // check if the group bbitmap is corrupted ext4_mb_complex_scan_group // Scan group gets ac_b_ex but doesn't use it ext4_unlock_group(sb, group) ext4_mark_group_bitmap_corrupted(group) // The block bitmap was corrupted during // the group unlock gap. ext4_mb_try_best_found ext4_lock_group(ac->ac_sb, group) ext4_mb_use_best_found mb_mark_used // Allocating blocks in block bitmap corrupted group Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240104142040.2835097-7-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 751e31df0f10..82afe275e6c8 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2299,6 +2299,9 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac, return; ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { @@ -2306,6 +2309,7 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac, ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); } -- cgit v1.2.3 From 832698373a25950942c04a512daa652c18a9b513 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 4 Jan 2024 22:20:39 +0800 Subject: ext4: avoid allocating blocks from corrupted group in ext4_mb_find_by_goal() Places the logic for checking if the group's block bitmap is corrupt under the protection of the group lock to avoid allocating blocks from the group with a corrupted block bitmap. Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240104142040.2835097-8-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 82afe275e6c8..2069d768c619 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2336,12 +2336,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, if (err) return err; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { - ext4_mb_unload_buddy(e4b); - return 0; - } - ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ @@ -2374,6 +2372,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); -- cgit v1.2.3 From c5f3a3821de42ede9bcaeb892d1539717cf590cb Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Thu, 4 Jan 2024 22:20:40 +0800 Subject: ext4: mark the group block bitmap as corrupted before reporting an error Otherwise unlocking the group in ext4_grp_locked_error may allow other processes to modify the core block bitmap that is known to be corrupt. Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240104142040.2835097-9-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 2069d768c619..c7f63dd7afcc 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -564,14 +564,14 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(EXT4_SB(sb), first + i); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing block already freed " "(bit %u)", first + i); - ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, - EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_clear_bit(first + i, e4b->bd_info->bb_bitmap); } @@ -1933,12 +1933,12 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing already freed block (bit %u); block bitmap corrupt.", block); - ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, - EXT4_GROUP_INFO_BBITMAP_CORRUPT); return; } @@ -2406,12 +2406,12 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, k = mb_find_next_zero_bit(buddy, max, 0); if (k >= max) { + ext4_mark_group_bitmap_corrupted(ac->ac_sb, + e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, "%d free clusters of order %d. But found 0", grp->bb_counters[i], i); - ext4_mark_group_bitmap_corrupted(ac->ac_sb, - e4b->bd_group, - EXT4_GROUP_INFO_BBITMAP_CORRUPT); break; } ac->ac_found++; @@ -2462,12 +2462,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, * free blocks even though group info says we * have free blocks */ + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But bitmap says 0", free); - ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, - EXT4_GROUP_INFO_BBITMAP_CORRUPT); break; } @@ -2493,12 +2493,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, if (WARN_ON(ex.fe_len <= 0)) break; if (free < ex.fe_len) { + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But got %d blocks", free, ex.fe_len); - ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, - EXT4_GROUP_INFO_BBITMAP_CORRUPT); /* * The number of free blocks differs. This mostly * indicate that the bitmap is corrupt. So exit -- cgit v1.2.3 From 133de5a0d8f8e32b34feaa8beae7a189482f1856 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:20:54 +0800 Subject: ext4: remove unused return value of __mb_check_buddy Remove unused return value of __mb_check_buddy. Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240105092102.496631-2-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c7f63dd7afcc..0d0917cf2e8f 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -677,7 +677,7 @@ do { \ } \ } while (0) -static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, +static void __mb_check_buddy(struct ext4_buddy *e4b, char *file, const char *function, int line) { struct super_block *sb = e4b->bd_sb; @@ -696,7 +696,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, void *buddy2; if (e4b->bd_info->bb_check_counter++ % 10) - return 0; + return; while (order > 1) { buddy = mb_find_buddy(e4b, order, &max); @@ -758,7 +758,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, grp = ext4_get_group_info(sb, e4b->bd_group); if (!grp) - return NULL; + return; list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; @@ -768,7 +768,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, for (i = 0; i < pa->pa_len; i++) MB_CHECK_ASSERT(mb_test_bit(k + i, buddy)); } - return 0; } #undef MB_CHECK_ASSERT #define mb_check_buddy(e4b) __mb_check_buddy(e4b, \ -- cgit v1.2.3 From 438a35e72d09c01da7ffb49570ecd11ca632270b Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:20:55 +0800 Subject: ext4: remove unused parameter ngroup in ext4_mb_choose_next_group_*() Remove unused parameter ngroup in ext4_mb_choose_next_group_*(). Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Reviewed-by: Ojaswin Mujoo Link: https://lore.kernel.org/r/20240105092102.496631-3-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 0d0917cf2e8f..9c867a13bf8d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -870,7 +870,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) * cr level needs an update. */ static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context *ac, - enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups) + enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *iter; @@ -944,7 +944,7 @@ ext4_mb_find_good_group_avg_frag_lists(struct ext4_allocation_context *ac, int o * order. Updates *new_cr if cr level needs an update. */ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *ac, - enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups) + enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = NULL; @@ -989,7 +989,7 @@ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context * * much and fall to CR_GOAL_LEN_SLOW in that case. */ static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context *ac, - enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups) + enum criteria *new_cr, ext4_group_t *group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = NULL; @@ -1124,11 +1124,11 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, } if (*new_cr == CR_POWER2_ALIGNED) { - ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group, ngroups); + ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group); } else if (*new_cr == CR_GOAL_LEN_FAST) { - ext4_mb_choose_next_group_goal_fast(ac, new_cr, group, ngroups); + ext4_mb_choose_next_group_goal_fast(ac, new_cr, group); } else if (*new_cr == CR_BEST_AVAIL_LEN) { - ext4_mb_choose_next_group_best_avail(ac, new_cr, group, ngroups); + ext4_mb_choose_next_group_best_avail(ac, new_cr, group); } else { /* * TODO: For CR=2, we can arrange groups in an rb tree sorted by -- cgit v1.2.3 From 11fd1a5d642355a45f4008d308399c26a8b3d3f0 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:20:56 +0800 Subject: ext4: remove unneeded return value of ext4_mb_release_context Function ext4_mb_release_context always return 0 and the return value is never used. Just remove unneeded return value of ext4_mb_release_context. Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240105092102.496631-4-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 9c867a13bf8d..dfd2de7aa0cf 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5968,7 +5968,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) /* * release all resource we used in allocation */ -static int ext4_mb_release_context(struct ext4_allocation_context *ac) +static void ext4_mb_release_context(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; @@ -6005,7 +6005,6 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); - return 0; } static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) -- cgit v1.2.3 From 97c32dbffce12136c06d9ceb6919850233d3a1c2 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:20:57 +0800 Subject: ext4: remove unused ext4_allocation_context::ac_groups_considered Remove unused ext4_allocation_context::ac_groups_considered Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240105092102.496631-5-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index d7aeb5da7d86..56938532b4ce 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -192,7 +192,6 @@ struct ext4_allocation_context { */ ext4_grpblk_t ac_orig_goal_len; - __u32 ac_groups_considered; __u32 ac_flags; /* allocation hints */ __u16 ac_groups_scanned; __u16 ac_groups_linear_remaining; -- cgit v1.2.3 From 908177175a2ac7280cac738f33ccbbbcff035c5c Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:20:58 +0800 Subject: ext4: remove unused return value of ext4_mb_release Remove unused return value of ext4_mb_release. Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240105092102.496631-6-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 2 +- fs/ext4/mballoc.c | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index a5d784872303..cabce11778fc 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2912,7 +2912,7 @@ extern const struct seq_operations ext4_mb_seq_groups_ops; extern const struct seq_operations ext4_mb_seq_structs_summary_ops; extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset); extern int ext4_mb_init(struct super_block *); -extern int ext4_mb_release(struct super_block *); +extern void ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); extern void ext4_discard_preallocations(struct inode *, unsigned int); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index dfd2de7aa0cf..26b199d2c330 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3750,7 +3750,7 @@ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp) return count; } -int ext4_mb_release(struct super_block *sb) +void ext4_mb_release(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; @@ -3826,8 +3826,6 @@ int ext4_mb_release(struct super_block *sb) } free_percpu(sbi->s_locality_groups); - - return 0; } static inline int ext4_issue_discard(struct super_block *sb, -- cgit v1.2.3 From 820c280896eaf715b39ac1ad38976bcc749082b7 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:20:59 +0800 Subject: ext4: remove unused return value of ext4_mb_release_inode_pa Remove unused return value of ext4_mb_release_inode_pa Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240105092102.496631-7-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 26b199d2c330..3349723ff93f 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5307,7 +5307,7 @@ static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac) * the caller MUST hold group/inode locks. * TODO: optimize the case when there are no in-core structures yet */ -static noinline_for_stack int +static noinline_for_stack void ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, struct ext4_prealloc_space *pa) { @@ -5357,8 +5357,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, */ } atomic_add(free, &sbi->s_mb_discarded); - - return 0; } static noinline_for_stack int -- cgit v1.2.3 From 20427949b9b584422c05bb31e48b1b68615dd794 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:21:00 +0800 Subject: ext4: remove unused return value of ext4_mb_release_group_pa Remove unused return value of ext4_mb_release_group_pa. Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240105092102.496631-8-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 3349723ff93f..a8e61bb181fa 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5359,7 +5359,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, atomic_add(free, &sbi->s_mb_discarded); } -static noinline_for_stack int +static noinline_for_stack void ext4_mb_release_group_pa(struct ext4_buddy *e4b, struct ext4_prealloc_space *pa) { @@ -5373,13 +5373,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", e4b->bd_group, group, pa->pa_pstart); - return 0; + return; } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); - - return 0; } /* -- cgit v1.2.3 From 2ffd2a6ad1d3a8213bb5805f45f49098fe615db1 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:21:01 +0800 Subject: ext4: remove unnecessary parameter "needed" in ext4_discard_preallocations The "needed" controls the number of ext4_prealloc_space to discard in ext4_discard_preallocations. Function ext4_discard_preallocations is supposed to discard all non-used preallocated blocks when "needed" is 0 and now ext4_discard_preallocations is always called with "needed" = 0. Remove unnecessary parameter "needed" and remove all non-used preallocated spaces in ext4_discard_preallocations to simplify the code. Note: If count of non-used preallocated spaces could be more than UINT_MAX, there was a memory leak as some non-used preallocated spaces are left ununsed and this commit will fix it. Otherwise, there is no behavior change. Signed-off-by: Kemeng Shi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240105092102.496631-9-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 2 +- fs/ext4/extents.c | 10 +++++----- fs/ext4/file.c | 2 +- fs/ext4/indirect.c | 2 +- fs/ext4/inode.c | 6 +++--- fs/ext4/ioctl.c | 2 +- fs/ext4/mballoc.c | 10 +++------- fs/ext4/move_extent.c | 4 ++-- fs/ext4/super.c | 2 +- 9 files changed, 18 insertions(+), 22 deletions(-) (limited to 'fs') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index cabce11778fc..786b6857ab47 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2915,7 +2915,7 @@ extern int ext4_mb_init(struct super_block *); extern void ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); -extern void ext4_discard_preallocations(struct inode *, unsigned int); +extern void ext4_discard_preallocations(struct inode *); extern int __init ext4_init_mballoc(void); extern void ext4_exit_mballoc(void); extern ext4_group_t ext4_mb_prefetch(struct super_block *sb, diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 01299b55a567..9106715254ac 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; @@ -4313,7 +4313,7 @@ got_allocated_blocks: * not a good idea to call discard here directly, * but otherwise we'd need to call it every free(). */ - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; ext4_free_blocks(handle, inode, NULL, newblock, @@ -5357,7 +5357,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start); ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1); @@ -5365,7 +5365,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); ret = ext4_ext_shift_extents(inode, handle, punch_stop, punch_stop - punch_start, SHIFT_LEFT); @@ -5497,7 +5497,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) goto out_stop; down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); path = ext4_find_extent(inode, offset_lblk, NULL, 0); if (IS_ERR(path)) { diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6aa15dafc677..54d6ff22585c 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -174,7 +174,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp) (atomic_read(&inode->i_writecount) == 1) && !EXT4_I(inode)->i_reserved_data_blocks) { down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); up_write(&EXT4_I(inode)->i_data_sem); } if (is_dx(inode) && filp->private_data) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index a9f3716119d3..d8ca7f64f952 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -714,7 +714,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5af1b0b8680e..4cae8698f70c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -371,7 +371,7 @@ void ext4_da_update_reserve_space(struct inode *inode, */ if ((ei->i_reserved_data_blocks == 0) && !inode_is_open_for_write(inode)) - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); } static int __check_block_validity(struct inode *inode, const char *func, @@ -4017,7 +4017,7 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) if (stop_block > first_block) { down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, first_block, stop_block - first_block); @@ -4170,7 +4170,7 @@ int ext4_truncate(struct inode *inode) down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) err = ext4_ext_truncate(handle, inode); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index aa6be510eb8f..7160a71044c8 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -467,7 +467,7 @@ static long swap_inode_boot_loader(struct super_block *sb, ext4_reset_inode_seed(inode); ext4_reset_inode_seed(inode_bl); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a8e61bb181fa..f3da7db2beee 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5498,7 +5498,7 @@ out_dbg: * * FIXME!! Make sure it is valid at all the call sites */ -void ext4_discard_preallocations(struct inode *inode, unsigned int needed) +void ext4_discard_preallocations(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; @@ -5520,15 +5520,12 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed) mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); trace_ext4_discard_preallocations(inode, - atomic_read(&ei->i_prealloc_active), needed); - - if (needed == 0) - needed = UINT_MAX; + atomic_read(&ei->i_prealloc_active), 0); repeat: /* first, collect all pa's in the inode */ write_lock(&ei->i_prealloc_lock); - for (iter = rb_first(&ei->i_prealloc_node); iter && needed; + for (iter = rb_first(&ei->i_prealloc_node); iter; iter = rb_next(iter)) { pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); @@ -5552,7 +5549,6 @@ repeat: spin_unlock(&pa->pa_lock); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); list_add(&pa->u.pa_tmp_list, &list); - needed--; continue; } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 391efa6d4c56..7cd4afa4de1d 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -686,8 +686,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, out: if (*moved_len) { - ext4_discard_preallocations(orig_inode, 0); - ext4_discard_preallocations(donor_inode, 0); + ext4_discard_preallocations(orig_inode); + ext4_discard_preallocations(donor_inode); } ext4_free_ext_path(path); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dcba0f85dfe2..0f931d0c227d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1525,7 +1525,7 @@ void ext4_clear_inode(struct inode *inode) ext4_fc_del(inode); invalidate_inode_buffers(inode); clear_inode(inode); - ext4_discard_preallocations(inode, 0); + ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { -- cgit v1.2.3 From f0e54b6087de9571ec61c189d6c378b81edbe3b2 Mon Sep 17 00:00:00 2001 From: Kemeng Shi Date: Fri, 5 Jan 2024 17:21:02 +0800 Subject: ext4: remove 'needed' in trace_ext4_discard_preallocations As 'needed' to trace_ext4_discard_preallocations is always 0 which is meaningless. Just remove it. Signed-off-by: Kemeng Shi Suggested-by: Jan Kara Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240105092102.496631-10-shikemeng@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index f3da7db2beee..e4f7cf9d89c4 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5510,9 +5510,8 @@ void ext4_discard_preallocations(struct inode *inode) struct rb_node *iter; int err; - if (!S_ISREG(inode->i_mode)) { + if (!S_ISREG(inode->i_mode)) return; - } if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -5520,7 +5519,7 @@ void ext4_discard_preallocations(struct inode *inode) mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); trace_ext4_discard_preallocations(inode, - atomic_read(&ei->i_prealloc_active), 0); + atomic_read(&ei->i_prealloc_active)); repeat: /* first, collect all pa's in the inode */ -- cgit v1.2.3 From eba38cc7578bef94865341c73608bdf49193a51d Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 28 Jan 2024 09:53:55 +0100 Subject: bcachefs: Fix build on parisc by avoiding __multi3() The gcc compiler on paric does support the __int128 type, although the architecture does not have native 128-bit support. The effect is, that the bcachefs u128_square() function will pull in the libgcc __multi3() helper, which breaks the kernel build when bcachefs is built as module since this function isn't currently exported in arch/parisc/kernel/parisc_ksyms.c. The build failure can be seen in the latest debian kernel build at: https://buildd.debian.org/status/fetch.php?pkg=linux&arch=hppa&ver=6.7.1-1%7Eexp1&stamp=1706132569&raw=0 We prefer to not export that symbol, so fall back to the optional 64-bit implementation provided by bcachefs and thus avoid usage of __multi3(). Signed-off-by: Helge Deller Cc: Kent Overstreet Signed-off-by: Kent Overstreet --- fs/bcachefs/mean_and_variance.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/bcachefs/mean_and_variance.h b/fs/bcachefs/mean_and_variance.h index b2be565bb8f2..64df11ab422b 100644 --- a/fs/bcachefs/mean_and_variance.h +++ b/fs/bcachefs/mean_and_variance.h @@ -17,7 +17,7 @@ * Rust and rustc has issues with u128. */ -#if defined(__SIZEOF_INT128__) && defined(__KERNEL__) +#if defined(__SIZEOF_INT128__) && defined(__KERNEL__) && !defined(CONFIG_PARISC) typedef struct { unsigned __int128 v; -- cgit v1.2.3 From 6bb3f7f4c3f4da8e09de188f2f63e8f741bba3bd Mon Sep 17 00:00:00 2001 From: Guoyu Ou Date: Sun, 28 Jan 2024 16:46:17 +0800 Subject: bcachefs: unlock parent dir if entry is not found in subvolume deletion Parent dir is locked by user_path_locked_at() before validating the required dentry. It should be unlocked if we can not perform the deletion. This fixes the problem: $ bcachefs subvolume delete not-exist-entry BCH_IOCTL_SUBVOLUME_DESTROY ioctl error: No such file or directory $ bcachefs subvolume delete not-exist-entry the second will stuck because the parent dir is locked in the previous deletion. Signed-off-by: Guoyu Ou Signed-off-by: Kent Overstreet --- fs/bcachefs/fs-ioctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/bcachefs/fs-ioctl.c b/fs/bcachefs/fs-ioctl.c index 3a4c24c28e7f..3dc8630ff9fe 100644 --- a/fs/bcachefs/fs-ioctl.c +++ b/fs/bcachefs/fs-ioctl.c @@ -455,6 +455,7 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp, if (IS_ERR(victim)) return PTR_ERR(victim); + dir = d_inode(path.dentry); if (victim->d_sb->s_fs_info != c) { ret = -EXDEV; goto err; @@ -463,14 +464,13 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp, ret = -ENOENT; goto err; } - dir = d_inode(path.dentry); ret = __bch2_unlink(dir, victim, true); if (!ret) { fsnotify_rmdir(dir, victim); d_delete(victim); } - inode_unlock(dir); err: + inode_unlock(dir); dput(victim); path_put(&path); return ret; -- cgit v1.2.3 From 82ef1a5356572219f41f9123ca047259a77bd67b Mon Sep 17 00:00:00 2001 From: Andrey Albershteyn Date: Wed, 24 Jan 2024 11:26:44 +0100 Subject: xfs: reset XFS_ATTR_INCOMPLETE filter on node removal In XFS_DAS_NODE_REMOVE_ATTR case, xfs_attr_mode_remove_attr() sets filter to XFS_ATTR_INCOMPLETE. The filter is then reset in xfs_attr_complete_op() if XFS_DA_OP_REPLACE operation is performed. The filter is not reset though if XFS just removes the attribute (args->value == NULL) with xfs_attr_defer_remove(). attr code goes to XFS_DAS_DONE state. Fix this by always resetting XFS_ATTR_INCOMPLETE filter. The replace operation already resets this filter in anyway and others are completed at this step hence don't need it. Fixes: fdaf1bb3cafc ("xfs: ATTR_REPLACE algorithm with LARP enabled needs rework") Signed-off-by: Andrey Albershteyn Reviewed-by: Christoph Hellwig Signed-off-by: Chandan Babu R --- fs/xfs/libxfs/xfs_attr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 9976a00a73f9..e965a48e7db9 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -421,10 +421,10 @@ xfs_attr_complete_op( bool do_replace = args->op_flags & XFS_DA_OP_REPLACE; args->op_flags &= ~XFS_DA_OP_REPLACE; - if (do_replace) { - args->attr_filter &= ~XFS_ATTR_INCOMPLETE; + args->attr_filter &= ~XFS_ATTR_INCOMPLETE; + if (do_replace) return replace_state; - } + return XFS_DAS_DONE; } -- cgit v1.2.3 From 881f78f472556ed05588172d5b5676b48dc48240 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Mon, 29 Jan 2024 20:27:23 -0800 Subject: xfs: remove conditional building of rt geometry validator functions I mistakenly turned off CONFIG_XFS_RT in the Kconfig file for arm64 variant of the djwong-wtf git branch. Unfortunately, it took me a good hour to figure out that RT wasn't built because this is what got printed to dmesg: XFS (sda2): realtime geometry sanity check failed XFS (sda2): Metadata corruption detected at xfs_sb_read_verify+0x170/0x190 [xfs], xfs_sb block 0x0 Whereas I would have expected: XFS (sda2): Not built with CONFIG_XFS_RT XFS (sda2): RT mount failed The root cause of these problems is the conditional compilation of the new functions xfs_validate_rtextents and xfs_compute_rextslog that I introduced in the two commits listed below. The !RT versions of these functions return false and 0, respectively, which causes primary superblock validation to fail, which explains the first message. Move the two functions to other parts of libxfs that are not conditionally defined by CONFIG_XFS_RT and remove the broken stubs so that validation works again. Fixes: e14293803f4e ("xfs: don't allow overly small or large realtime volumes") Fixes: a6a38f309afc ("xfs: make rextslog computation consistent with mkfs") Signed-off-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig Signed-off-by: Chandan Babu R --- fs/xfs/libxfs/xfs_rtbitmap.c | 14 -------------- fs/xfs/libxfs/xfs_rtbitmap.h | 16 ---------------- fs/xfs/libxfs/xfs_sb.c | 14 ++++++++++++++ fs/xfs/libxfs/xfs_sb.h | 2 ++ fs/xfs/libxfs/xfs_types.h | 12 ++++++++++++ fs/xfs/scrub/rtbitmap.c | 1 + fs/xfs/scrub/rtsummary.c | 1 + 7 files changed, 30 insertions(+), 30 deletions(-) (limited to 'fs') diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index 31100120b2c5..e31663cb7b43 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -1118,20 +1118,6 @@ xfs_rtbitmap_blockcount( return howmany_64(rtextents, NBBY * mp->m_sb.sb_blocksize); } -/* - * Compute the maximum level number of the realtime summary file, as defined by - * mkfs. The historic use of highbit32 on a 64-bit quantity prohibited correct - * use of rt volumes with more than 2^32 extents. - */ -uint8_t -xfs_compute_rextslog( - xfs_rtbxlen_t rtextents) -{ - if (!rtextents) - return 0; - return xfs_highbit64(rtextents); -} - /* * Compute the number of rtbitmap words needed to populate every block of a * bitmap that is large enough to track the given number of rt extents. diff --git a/fs/xfs/libxfs/xfs_rtbitmap.h b/fs/xfs/libxfs/xfs_rtbitmap.h index 274dc7dae1fa..152a66750af5 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.h +++ b/fs/xfs/libxfs/xfs_rtbitmap.h @@ -351,20 +351,6 @@ xfs_rtfree_extent( int xfs_rtfree_blocks(struct xfs_trans *tp, xfs_fsblock_t rtbno, xfs_filblks_t rtlen); -uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents); - -/* Do we support an rt volume having this number of rtextents? */ -static inline bool -xfs_validate_rtextents( - xfs_rtbxlen_t rtextents) -{ - /* No runt rt volumes */ - if (rtextents == 0) - return false; - - return true; -} - xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents); unsigned long long xfs_rtbitmap_wordcount(struct xfs_mount *mp, @@ -383,8 +369,6 @@ unsigned long long xfs_rtsummary_wordcount(struct xfs_mount *mp, # define xfs_rtsummary_read_buf(a,b) (-ENOSYS) # define xfs_rtbuf_cache_relse(a) (0) # define xfs_rtalloc_extent_is_free(m,t,s,l,i) (-ENOSYS) -# define xfs_compute_rextslog(rtx) (0) -# define xfs_validate_rtextents(rtx) (false) static inline xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp, xfs_rtbxlen_t rtextents) { diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 4a9e8588f4c9..5bb6e2bd6dee 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1377,3 +1377,17 @@ xfs_validate_stripe_geometry( } return true; } + +/* + * Compute the maximum level number of the realtime summary file, as defined by + * mkfs. The historic use of highbit32 on a 64-bit quantity prohibited correct + * use of rt volumes with more than 2^32 extents. + */ +uint8_t +xfs_compute_rextslog( + xfs_rtbxlen_t rtextents) +{ + if (!rtextents) + return 0; + return xfs_highbit64(rtextents); +} diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h index 19134b23c10b..2e8e8d63d4eb 100644 --- a/fs/xfs/libxfs/xfs_sb.h +++ b/fs/xfs/libxfs/xfs_sb.h @@ -38,4 +38,6 @@ extern int xfs_sb_get_secondary(struct xfs_mount *mp, extern bool xfs_validate_stripe_geometry(struct xfs_mount *mp, __s64 sunit, __s64 swidth, int sectorsize, bool silent); +uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents); + #endif /* __XFS_SB_H__ */ diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index 20b5375f2d9c..62e02d5380ad 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -251,4 +251,16 @@ bool xfs_verify_fileoff(struct xfs_mount *mp, xfs_fileoff_t off); bool xfs_verify_fileext(struct xfs_mount *mp, xfs_fileoff_t off, xfs_fileoff_t len); +/* Do we support an rt volume having this number of rtextents? */ +static inline bool +xfs_validate_rtextents( + xfs_rtbxlen_t rtextents) +{ + /* No runt rt volumes */ + if (rtextents == 0) + return false; + + return true; +} + #endif /* __XFS_TYPES_H__ */ diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index 441ca9977652..46583517377f 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -15,6 +15,7 @@ #include "xfs_inode.h" #include "xfs_bmap.h" #include "xfs_bit.h" +#include "xfs_sb.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/repair.h" diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c index fabd0ed9dfa6..b1ff4f33324a 100644 --- a/fs/xfs/scrub/rtsummary.c +++ b/fs/xfs/scrub/rtsummary.c @@ -16,6 +16,7 @@ #include "xfs_rtbitmap.h" #include "xfs_bit.h" #include "xfs_bmap.h" +#include "xfs_sb.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" -- cgit v1.2.3 From f884a9f9e59206a2d41f265e7e403f080d10b493 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 10 Jan 2024 17:48:44 +0100 Subject: btrfs: send: return EOPNOTSUPP on unknown flags When some ioctl flags are checked we return EOPNOTSUPP, like for BTRFS_SCRUB_SUPPORTED_FLAGS, BTRFS_SUBVOL_CREATE_ARGS_MASK or fallocate modes. The EINVAL is supposed to be for a supported but invalid values or combination of options. Fix that when checking send flags so it's consistent with the rest. CC: stable@vger.kernel.org # 4.14+ Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5rryOLzp3EKq8RTbjMHMHeaJubfpsVLF6H4qJnKCUR1w@mail.gmail.com/ Reviewed-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/send.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 2d7519a6ce72..7902298c1f25 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -8111,7 +8111,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) } if (arg->flags & ~BTRFS_SEND_FLAG_MASK) { - ret = -EINVAL; + ret = -EOPNOTSUPP; goto out; } -- cgit v1.2.3 From 0c309d66dacddf8ce939b891d9ead4a8e21ad6f0 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Wed, 10 Jan 2024 17:51:26 -0800 Subject: btrfs: forbid creating subvol qgroups Creating a qgroup 0/subvolid leads to various races and it isn't helpful, because you can't specify a subvol id when creating a subvol, so you can't be sure it will be the right one. Any requirements on the automatic subvol can be gratified by using a higher level qgroup and the inheritance parameters of subvol creation. Fixes: cecbb533b5fc ("btrfs: record simple quota deltas in delayed refs") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Qu Wenruo Signed-off-by: Boris Burkov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5d42319b43f2..fb2323b323bf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3806,6 +3806,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } + if (sa->create && is_fstree(sa->qgroupid)) { + ret = -EINVAL; + goto out; + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); -- cgit v1.2.3 From a8df35619948bd8363d330c20a90c9a7fbff28c0 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Wed, 10 Jan 2024 17:30:00 -0800 Subject: btrfs: forbid deleting live subvol qgroup If a subvolume still exists, forbid deleting its qgroup 0/subvolid. This behavior generally leads to incorrect behavior in squotas and doesn't have a legitimate purpose. Fixes: cecbb533b5fc ("btrfs: record simple quota deltas in delayed refs") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo Signed-off-by: Boris Burkov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 63b426cc7798..5470e1cdf10c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1736,6 +1736,15 @@ out: return ret; } +static bool qgroup_has_usage(struct btrfs_qgroup *qgroup) +{ + return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 || + qgroup->excl > 0 || qgroup->excl_cmpr > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0); +} + int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1755,6 +1764,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) goto out; } + if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) { + ret = -EBUSY; + goto out; + } + /* Check if there are no children of this qgroup */ if (!list_empty(&qgroup->members)) { ret = -EBUSY; -- cgit v1.2.3 From e03ee2fe873eb68c1f9ba5112fee70303ebf9dfb Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Sat, 20 Jan 2024 19:41:28 +1030 Subject: btrfs: do not ASSERT() if the newly created subvolume already got read [BUG] There is a syzbot crash, triggered by the ASSERT() during subvolume creation: assertion failed: !anon_dev, in fs/btrfs/disk-io.c:1319 ------------[ cut here ]------------ kernel BUG at fs/btrfs/disk-io.c:1319! invalid opcode: 0000 [#1] PREEMPT SMP KASAN RIP: 0010:btrfs_get_root_ref.part.0+0x9aa/0xa60 btrfs_get_new_fs_root+0xd3/0xf0 create_subvol+0xd02/0x1650 btrfs_mksubvol+0xe95/0x12b0 __btrfs_ioctl_snap_create+0x2f9/0x4f0 btrfs_ioctl_snap_create+0x16b/0x200 btrfs_ioctl+0x35f0/0x5cf0 __x64_sys_ioctl+0x19d/0x210 do_syscall_64+0x3f/0xe0 entry_SYSCALL_64_after_hwframe+0x63/0x6b ---[ end trace 0000000000000000 ]--- [CAUSE] During create_subvol(), after inserting root item for the newly created subvolume, we would trigger btrfs_get_new_fs_root() to get the btrfs_root of that subvolume. The idea here is, we have preallocated an anonymous device number for the subvolume, thus we can assign it to the new subvolume. But there is really nothing preventing things like backref walk to read the new subvolume. If that happens before we call btrfs_get_new_fs_root(), the subvolume would be read out, with a new anonymous device number assigned already. In that case, we would trigger ASSERT(), as we really expect no one to read out that subvolume (which is not yet accessible from the fs). But things like backref walk is still possible to trigger the read on the subvolume. Thus our assumption on the ASSERT() is not correct in the first place. [FIX] Fix it by removing the ASSERT(), and just free the @anon_dev, reset it to 0, and continue. If the subvolume tree is read out by something else, it should have already get a new anon_dev assigned thus we only need to free the preallocated one. Reported-by: Chenyuan Yang Fixes: 2dfb1e43f57d ("btrfs: preallocate anon block device at first phase of snapshot creation") CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c6907d533fe8..e71ef97d0a7c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1336,8 +1336,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { - /* Shouldn't get preallocated anon_dev for cached roots */ - ASSERT(!anon_dev); + /* + * Some other caller may have read out the newly inserted + * subvolume already (for things like backref walk etc). Not + * that common but still possible. In that case, we just need + * to free the anon_dev. + */ + if (unlikely(anon_dev)) { + free_anon_bdev(anon_dev); + anon_dev = 0; + } + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); -- cgit v1.2.3 From d81786f53aec14fd4d56263145a0635afbc64617 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 31 Jan 2024 13:49:19 -0500 Subject: tracefs: Zero out the tracefs_inode when allocating it eventfs uses the tracefs_inode and assumes that it's already initialized to zero. That is, it doesn't set fields to zero (like ti->private) after getting its tracefs_inode. This causes bugs due to stale values. Just initialize the entire structure to zero on allocation so there isn't any more surprises. This is a partial fix to access to ti->private. The assignment still needs to be made before the dentry is instantiated. Link: https://lore.kernel.org/linux-trace-kernel/20240131185512.315825944@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Cc: Greg Kroah-Hartman Fixes: 5790b1fb3d672 ("eventfs: Remove eventfs_file and just use eventfs_inode") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202401291043.e62e89dc-oliver.sang@intel.com Suggested-by: Linus Torvalds Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/inode.c | 6 ++++-- fs/tracefs/internal.h | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index e1b172c0e091..888e42087847 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -38,8 +38,6 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb) if (!ti) return NULL; - ti->flags = 0; - return &ti->vfs_inode; } @@ -779,7 +777,11 @@ static void init_once(void *foo) { struct tracefs_inode *ti = (struct tracefs_inode *) foo; + /* inode_init_once() calls memset() on the vfs_inode portion */ inode_init_once(&ti->vfs_inode); + + /* Zero out the rest */ + memset_after(ti, 0, vfs_inode); } static int __init tracefs_init(void) diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 91c2bf0b91d9..7d84349ade87 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -11,9 +11,10 @@ enum { }; struct tracefs_inode { + struct inode vfs_inode; + /* The below gets initialized with memset_after(ti, 0, vfs_inode) */ unsigned long flags; void *private; - struct inode vfs_inode; }; /* -- cgit v1.2.3 From 4fa4b010b83fb2f837b5ef79e38072a79e96e4f1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 31 Jan 2024 13:49:20 -0500 Subject: eventfs: Initialize the tracefs inode properly The tracefs-specific fields in the inode were not initialized before the inode was exposed to others through the dentry with 'd_instantiate()'. Move the field initializations up to before the d_instantiate. Link: https://lore.kernel.org/linux-trace-kernel/20240131185512.478449628@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Cc: Greg Kroah-Hartman Fixes: 5790b1fb3d672 ("eventfs: Remove eventfs_file and just use eventfs_inode") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202401291043.e62e89dc-oliver.sang@intel.com Signed-off-by: Linus Torvalds Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 1c3dd0ad4660..824b1811e342 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -370,6 +370,8 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; + /* Only directories have ti->private set to an ei, not files */ + ti->private = ei; inc_nlink(inode); d_instantiate(dentry, inode); @@ -515,7 +517,6 @@ create_file_dentry(struct eventfs_inode *ei, int idx, static void eventfs_post_create_dir(struct eventfs_inode *ei) { struct eventfs_inode *ei_child; - struct tracefs_inode *ti; lockdep_assert_held(&eventfs_mutex); @@ -525,9 +526,6 @@ static void eventfs_post_create_dir(struct eventfs_inode *ei) srcu_read_lock_held(&eventfs_srcu)) { ei_child->d_parent = ei->dentry; } - - ti = get_tracefs(ei->dentry->d_inode); - ti->private = ei; } /** -- cgit v1.2.3 From 99c001cb617df409dac275a059d6c3f187a2da7a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 31 Jan 2024 13:49:21 -0500 Subject: tracefs: Avoid using the ei->dentry pointer unnecessarily The eventfs_find_events() code tries to walk up the tree to find the event directory that a dentry belongs to, in order to then find the eventfs inode that is associated with that event directory. However, it uses an odd combination of walking the dentry parent, looking up the eventfs inode associated with that, and then looking up the dentry from there. Repeat. But the code shouldn't have back-pointers to dentries in the first place, and it should just walk the dentry parenthood chain directly. Similarly, 'set_top_events_ownership()' looks up the dentry from the eventfs inode, but the only reason it wants a dentry is to look up the superblock in order to look up the root dentry. But it already has the real filesystem inode, which has that same superblock pointer. So just pass in the superblock pointer using the information that's already there, instead of looking up extraneous data that is irrelevant. Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240131185512.638645365@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Cc: Greg Kroah-Hartman Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions") Signed-off-by: Linus Torvalds Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 824b1811e342..e9819d719d2a 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -156,33 +156,30 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, return ret; } -static void update_top_events_attr(struct eventfs_inode *ei, struct dentry *dentry) +static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb) { - struct inode *inode; + struct inode *root; /* Only update if the "events" was on the top level */ if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL)) return; /* Get the tracefs root inode. */ - inode = d_inode(dentry->d_sb->s_root); - ei->attr.uid = inode->i_uid; - ei->attr.gid = inode->i_gid; + root = d_inode(sb->s_root); + ei->attr.uid = root->i_uid; + ei->attr.gid = root->i_gid; } static void set_top_events_ownership(struct inode *inode) { struct tracefs_inode *ti = get_tracefs(inode); struct eventfs_inode *ei = ti->private; - struct dentry *dentry; /* The top events directory doesn't get automatically updated */ if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL)) return; - dentry = ei->dentry; - - update_top_events_attr(ei, dentry); + update_top_events_attr(ei, inode->i_sb); if (!(ei->attr.mode & EVENTFS_SAVE_UID)) inode->i_uid = ei->attr.uid; @@ -235,8 +232,10 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) mutex_lock(&eventfs_mutex); do { - /* The parent always has an ei, except for events itself */ - ei = dentry->d_parent->d_fsdata; + // The parent is stable because we do not do renames + dentry = dentry->d_parent; + // ... and directories always have d_fsdata + ei = dentry->d_fsdata; /* * If the ei is being freed, the ownership of the children @@ -246,12 +245,11 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) ei = NULL; break; } - - dentry = ei->dentry; + // Walk upwards until you find the events inode } while (!ei->is_events); mutex_unlock(&eventfs_mutex); - update_top_events_attr(ei, dentry); + update_top_events_attr(ei, dentry->d_sb); return ei; } -- cgit v1.2.3 From ee36a3b345c433a846effcdcfba437c2298eeda5 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Mon, 29 Jan 2024 13:58:13 +0000 Subject: cifs: make sure that channel scaling is done only once Following a successful cifs_tree_connect, we have the code to scale up/down the number of channels in the session. However, it is not protected by a lock today. As a result, this code can be executed by several processes that select the same channel. The core functions handle this well, as they pick chan_lock. However, we've seen cases where smb2_reconnect throws some warnings. To fix that, this change introduces a flags bitmap inside the cifs_ses structure. A new flag type is used to ensure that only one process enters this section at any time. Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/cifsglob.h | 3 +++ fs/smb/client/smb2pdu.c | 20 +++++++++++++++++--- 2 files changed, 20 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 16befff4cbb4..9093c507042f 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1032,6 +1032,8 @@ struct cifs_chan { __u8 signkey[SMB3_SIGN_KEY_SIZE]; }; +#define CIFS_SES_FLAG_SCALE_CHANNELS (0x1) + /* * Session structure. One of these for each uid session with a particular host */ @@ -1064,6 +1066,7 @@ struct cifs_ses { enum securityEnum sectype; /* what security flavor was specified? */ bool sign; /* is signing required? */ bool domainAuto:1; + unsigned int flags; __u16 session_flags; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; __u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE]; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 86f6f35b7f32..6db54c6ef571 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -399,6 +399,15 @@ skip_sess_setup: goto out; } + spin_lock(&ses->ses_lock); + if (ses->flags & CIFS_SES_FLAG_SCALE_CHANNELS) { + spin_unlock(&ses->ses_lock); + mutex_unlock(&ses->session_mutex); + goto skip_add_channels; + } + ses->flags |= CIFS_SES_FLAG_SCALE_CHANNELS; + spin_unlock(&ses->ses_lock); + if (!rc && (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { mutex_unlock(&ses->session_mutex); @@ -428,17 +437,22 @@ skip_sess_setup: if (ses->chan_max > ses->chan_count && ses->iface_count && !SERVER_IS_CHAN(server)) { - if (ses->chan_count == 1) + if (ses->chan_count == 1) { cifs_server_dbg(VFS, "supports multichannel now\n"); + queue_delayed_work(cifsiod_wq, &tcon->query_interfaces, + (SMB_INTERFACE_POLL_INTERVAL * HZ)); + } cifs_try_adding_channels(ses); - queue_delayed_work(cifsiod_wq, &tcon->query_interfaces, - (SMB_INTERFACE_POLL_INTERVAL * HZ)); } } else { mutex_unlock(&ses->session_mutex); } + skip_add_channels: + spin_lock(&ses->ses_lock); + ses->flags &= ~CIFS_SES_FLAG_SCALE_CHANNELS; + spin_unlock(&ses->ses_lock); if (smb2_command != SMB2_INTERNAL_CMD) mod_delayed_work(cifsiod_wq, &server->reconnect, 0); -- cgit v1.2.3 From 49304c2b93e4f7468b51ef717cbe637981397115 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 31 Jan 2024 23:32:27 -0500 Subject: tracefs: dentry lookup crapectomy The dentry lookup for eventfs files was very broken, and had lots of signs of the old situation where the filesystem names were all created statically in the dentry tree, rather than being looked up dynamically based on the eventfs data structures. You could see it in the naming - how it claimed to "create" dentries rather than just look up the dentries that were given it. You could see it in various nonsensical and very incorrect operations, like using "simple_lookup()" on the dentries that were passed in, which only results in those dentries becoming negative dentries. Which meant that any other lookup would possibly return ENOENT if it saw that negative dentry before the data was then later filled in. You could see it in the immense amount of nonsensical code that didn't actually just do lookups. Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240131233227.73db55e1@gandalf.local.home Cc: stable@vger.kernel.org Cc: Al Viro Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Greg Kroah-Hartman Cc: Ajay Kaher Cc: Mark Rutland Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions") Signed-off-by: Linus Torvalds Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 275 +++++++++-------------------------------------- fs/tracefs/inode.c | 69 ------------ fs/tracefs/internal.h | 3 - 3 files changed, 50 insertions(+), 297 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index e9819d719d2a..04c2ab90f93e 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -230,7 +230,6 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) { struct eventfs_inode *ei; - mutex_lock(&eventfs_mutex); do { // The parent is stable because we do not do renames dentry = dentry->d_parent; @@ -247,7 +246,6 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) } // Walk upwards until you find the events inode } while (!ei->is_events); - mutex_unlock(&eventfs_mutex); update_top_events_attr(ei, dentry->d_sb); @@ -280,11 +278,10 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode, } /** - * create_file - create a file in the tracefs filesystem - * @name: the name of the file to create. + * lookup_file - look up a file in the tracefs filesystem + * @dentry: the dentry to look up * @mode: the permission that the file should have. * @attr: saved attributes changed by user - * @parent: parent dentry for this file. * @data: something that the caller will want to get to later on. * @fop: struct file_operations that should be used for this file. * @@ -292,13 +289,13 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode, * directory. The inode.i_private pointer will point to @data in the open() * call. */ -static struct dentry *create_file(const char *name, umode_t mode, +static struct dentry *lookup_file(struct dentry *dentry, + umode_t mode, struct eventfs_attr *attr, - struct dentry *parent, void *data, + void *data, const struct file_operations *fop) { struct tracefs_inode *ti; - struct dentry *dentry; struct inode *inode; if (!(mode & S_IFMT)) @@ -307,15 +304,9 @@ static struct dentry *create_file(const char *name, umode_t mode, if (WARN_ON_ONCE(!S_ISREG(mode))) return NULL; - WARN_ON_ONCE(!parent); - dentry = eventfs_start_creating(name, parent); - - if (IS_ERR(dentry)) - return dentry; - inode = tracefs_get_inode(dentry->d_sb); if (unlikely(!inode)) - return eventfs_failed_creating(dentry); + return ERR_PTR(-ENOMEM); /* If the user updated the directory's attributes, use them */ update_inode_attr(dentry, inode, attr, mode); @@ -329,32 +320,29 @@ static struct dentry *create_file(const char *name, umode_t mode, ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; - d_instantiate(dentry, inode); + + d_add(dentry, inode); fsnotify_create(dentry->d_parent->d_inode, dentry); - return eventfs_end_creating(dentry); + return dentry; }; /** - * create_dir - create a dir in the tracefs filesystem + * lookup_dir_entry - look up a dir in the tracefs filesystem + * @dentry: the directory to look up * @ei: the eventfs_inode that represents the directory to create - * @parent: parent dentry for this file. * - * This function will create a dentry for a directory represented by + * This function will look up a dentry for a directory represented by * a eventfs_inode. */ -static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent) +static struct dentry *lookup_dir_entry(struct dentry *dentry, + struct eventfs_inode *pei, struct eventfs_inode *ei) { struct tracefs_inode *ti; - struct dentry *dentry; struct inode *inode; - dentry = eventfs_start_creating(ei->name, parent); - if (IS_ERR(dentry)) - return dentry; - inode = tracefs_get_inode(dentry->d_sb); if (unlikely(!inode)) - return eventfs_failed_creating(dentry); + return ERR_PTR(-ENOMEM); /* If the user updated the directory's attributes, use them */ update_inode_attr(dentry, inode, &ei->attr, @@ -371,11 +359,14 @@ static struct dentry *create_dir(struct eventfs_inode *ei, struct dentry *parent /* Only directories have ti->private set to an ei, not files */ ti->private = ei; + dentry->d_fsdata = ei; + ei->dentry = dentry; // Remove me! + inc_nlink(inode); - d_instantiate(dentry, inode); + d_add(dentry, inode); inc_nlink(dentry->d_parent->d_inode); fsnotify_mkdir(dentry->d_parent->d_inode, dentry); - return eventfs_end_creating(dentry); + return dentry; } static void free_ei(struct eventfs_inode *ei) @@ -425,7 +416,7 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry) } /** - * create_file_dentry - create a dentry for a file of an eventfs_inode + * lookup_file_dentry - create a dentry for a file of an eventfs_inode * @ei: the eventfs_inode that the file will be created under * @idx: the index into the d_children[] of the @ei * @parent: The parent dentry of the created file. @@ -438,157 +429,21 @@ void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry) * address located at @e_dentry. */ static struct dentry * -create_file_dentry(struct eventfs_inode *ei, int idx, - struct dentry *parent, const char *name, umode_t mode, void *data, +lookup_file_dentry(struct dentry *dentry, + struct eventfs_inode *ei, int idx, + umode_t mode, void *data, const struct file_operations *fops) { struct eventfs_attr *attr = NULL; struct dentry **e_dentry = &ei->d_children[idx]; - struct dentry *dentry; - - WARN_ON_ONCE(!inode_is_locked(parent->d_inode)); - mutex_lock(&eventfs_mutex); - if (ei->is_freed) { - mutex_unlock(&eventfs_mutex); - return NULL; - } - /* If the e_dentry already has a dentry, use it */ - if (*e_dentry) { - dget(*e_dentry); - mutex_unlock(&eventfs_mutex); - return *e_dentry; - } - - /* ei->entry_attrs are protected by SRCU */ if (ei->entry_attrs) attr = &ei->entry_attrs[idx]; - mutex_unlock(&eventfs_mutex); - - dentry = create_file(name, mode, attr, parent, data, fops); + dentry->d_fsdata = ei; // NOTE: ei of _parent_ + lookup_file(dentry, mode, attr, data, fops); - mutex_lock(&eventfs_mutex); - - if (IS_ERR_OR_NULL(dentry)) { - /* - * When the mutex was released, something else could have - * created the dentry for this e_dentry. In which case - * use that one. - * - * If ei->is_freed is set, the e_dentry is currently on its - * way to being freed, don't return it. If e_dentry is NULL - * it means it was already freed. - */ - if (ei->is_freed) { - dentry = NULL; - } else { - dentry = *e_dentry; - dget(dentry); - } - mutex_unlock(&eventfs_mutex); - return dentry; - } - - if (!*e_dentry && !ei->is_freed) { - *e_dentry = dentry; - dentry->d_fsdata = ei; - } else { - /* - * Should never happen unless we get here due to being freed. - * Otherwise it means two dentries exist with the same name. - */ - WARN_ON_ONCE(!ei->is_freed); - dentry = NULL; - } - mutex_unlock(&eventfs_mutex); - - return dentry; -} - -/** - * eventfs_post_create_dir - post create dir routine - * @ei: eventfs_inode of recently created dir - * - * Map the meta-data of files within an eventfs dir to their parent dentry - */ -static void eventfs_post_create_dir(struct eventfs_inode *ei) -{ - struct eventfs_inode *ei_child; - - lockdep_assert_held(&eventfs_mutex); - - /* srcu lock already held */ - /* fill parent-child relation */ - list_for_each_entry_srcu(ei_child, &ei->children, list, - srcu_read_lock_held(&eventfs_srcu)) { - ei_child->d_parent = ei->dentry; - } -} - -/** - * create_dir_dentry - Create a directory dentry for the eventfs_inode - * @pei: The eventfs_inode parent of ei. - * @ei: The eventfs_inode to create the directory for - * @parent: The dentry of the parent of this directory - * - * This creates and attaches a directory dentry to the eventfs_inode @ei. - */ -static struct dentry * -create_dir_dentry(struct eventfs_inode *pei, struct eventfs_inode *ei, - struct dentry *parent) -{ - struct dentry *dentry = NULL; - - WARN_ON_ONCE(!inode_is_locked(parent->d_inode)); - - mutex_lock(&eventfs_mutex); - if (pei->is_freed || ei->is_freed) { - mutex_unlock(&eventfs_mutex); - return NULL; - } - if (ei->dentry) { - /* If the eventfs_inode already has a dentry, use it */ - dentry = ei->dentry; - dget(dentry); - mutex_unlock(&eventfs_mutex); - return dentry; - } - mutex_unlock(&eventfs_mutex); - - dentry = create_dir(ei, parent); - - mutex_lock(&eventfs_mutex); - - if (IS_ERR_OR_NULL(dentry) && !ei->is_freed) { - /* - * When the mutex was released, something else could have - * created the dentry for this e_dentry. In which case - * use that one. - * - * If ei->is_freed is set, the e_dentry is currently on its - * way to being freed. - */ - dentry = ei->dentry; - if (dentry) - dget(dentry); - mutex_unlock(&eventfs_mutex); - return dentry; - } - - if (!ei->dentry && !ei->is_freed) { - ei->dentry = dentry; - eventfs_post_create_dir(ei); - dentry->d_fsdata = ei; - } else { - /* - * Should never happen unless we get here due to being freed. - * Otherwise it means two dentries exist with the same name. - */ - WARN_ON_ONCE(!ei->is_freed); - dentry = NULL; - } - mutex_unlock(&eventfs_mutex); + *e_dentry = dentry; // Remove me return dentry; } @@ -607,79 +462,49 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - const struct file_operations *fops; - const struct eventfs_entry *entry; struct eventfs_inode *ei_child; struct tracefs_inode *ti; struct eventfs_inode *ei; - struct dentry *ei_dentry = NULL; - struct dentry *ret = NULL; - struct dentry *d; const char *name = dentry->d_name.name; - umode_t mode; - void *data; - int idx; - int i; - int r; ti = get_tracefs(dir); if (!(ti->flags & TRACEFS_EVENT_INODE)) - return NULL; - - /* Grab srcu to prevent the ei from going away */ - idx = srcu_read_lock(&eventfs_srcu); + return ERR_PTR(-EIO); - /* - * Grab the eventfs_mutex to consistent value from ti->private. - * This s - */ mutex_lock(&eventfs_mutex); - ei = READ_ONCE(ti->private); - if (ei && !ei->is_freed) - ei_dentry = READ_ONCE(ei->dentry); - mutex_unlock(&eventfs_mutex); - if (!ei || !ei_dentry) + ei = ti->private; + if (!ei || ei->is_freed) goto out; - data = ei->data; - - list_for_each_entry_srcu(ei_child, &ei->children, list, - srcu_read_lock_held(&eventfs_srcu)) { + list_for_each_entry(ei_child, &ei->children, list) { if (strcmp(ei_child->name, name) != 0) continue; - ret = simple_lookup(dir, dentry, flags); - if (IS_ERR(ret)) + if (ei_child->is_freed) goto out; - d = create_dir_dentry(ei, ei_child, ei_dentry); - dput(d); + lookup_dir_entry(dentry, ei, ei_child); goto out; } - for (i = 0; i < ei->nr_entries; i++) { - entry = &ei->entries[i]; - if (strcmp(name, entry->name) == 0) { - void *cdata = data; - mutex_lock(&eventfs_mutex); - /* If ei->is_freed, then the event itself may be too */ - if (!ei->is_freed) - r = entry->callback(name, &mode, &cdata, &fops); - else - r = -1; - mutex_unlock(&eventfs_mutex); - if (r <= 0) - continue; - ret = simple_lookup(dir, dentry, flags); - if (IS_ERR(ret)) - goto out; - d = create_file_dentry(ei, i, ei_dentry, name, mode, cdata, fops); - dput(d); - break; - } + for (int i = 0; i < ei->nr_entries; i++) { + void *data; + umode_t mode; + const struct file_operations *fops; + const struct eventfs_entry *entry = &ei->entries[i]; + + if (strcmp(name, entry->name) != 0) + continue; + + data = ei->data; + if (entry->callback(name, &mode, &data, &fops) <= 0) + goto out; + + lookup_file_dentry(dentry, ei, i, mode, data, fops); + goto out; } out: - srcu_read_unlock(&eventfs_srcu, idx); - return ret; + mutex_unlock(&eventfs_mutex); + return NULL; } /* diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 888e42087847..5c84460feeeb 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -495,75 +495,6 @@ struct dentry *tracefs_end_creating(struct dentry *dentry) return dentry; } -/** - * eventfs_start_creating - start the process of creating a dentry - * @name: Name of the file created for the dentry - * @parent: The parent dentry where this dentry will be created - * - * This is a simple helper function for the dynamically created eventfs - * files. When the directory of the eventfs files are accessed, their - * dentries are created on the fly. This function is used to start that - * process. - */ -struct dentry *eventfs_start_creating(const char *name, struct dentry *parent) -{ - struct dentry *dentry; - int error; - - /* Must always have a parent. */ - if (WARN_ON_ONCE(!parent)) - return ERR_PTR(-EINVAL); - - error = simple_pin_fs(&trace_fs_type, &tracefs_mount, - &tracefs_mount_count); - if (error) - return ERR_PTR(error); - - if (unlikely(IS_DEADDIR(parent->d_inode))) - dentry = ERR_PTR(-ENOENT); - else - dentry = lookup_one_len(name, parent, strlen(name)); - - if (!IS_ERR(dentry) && dentry->d_inode) { - dput(dentry); - dentry = ERR_PTR(-EEXIST); - } - - if (IS_ERR(dentry)) - simple_release_fs(&tracefs_mount, &tracefs_mount_count); - - return dentry; -} - -/** - * eventfs_failed_creating - clean up a failed eventfs dentry creation - * @dentry: The dentry to clean up - * - * If after calling eventfs_start_creating(), a failure is detected, the - * resources created by eventfs_start_creating() needs to be cleaned up. In - * that case, this function should be called to perform that clean up. - */ -struct dentry *eventfs_failed_creating(struct dentry *dentry) -{ - dput(dentry); - simple_release_fs(&tracefs_mount, &tracefs_mount_count); - return NULL; -} - -/** - * eventfs_end_creating - Finish the process of creating a eventfs dentry - * @dentry: The dentry that has successfully been created. - * - * This function is currently just a place holder to match - * eventfs_start_creating(). In case any synchronization needs to be added, - * this function will be used to implement that without having to modify - * the callers of eventfs_start_creating(). - */ -struct dentry *eventfs_end_creating(struct dentry *dentry) -{ - return dentry; -} - /* Find the inode that this will use for default */ static struct inode *instance_inode(struct dentry *parent, struct inode *inode) { diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 7d84349ade87..09037e2c173d 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -80,9 +80,6 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent); struct dentry *tracefs_end_creating(struct dentry *dentry); struct dentry *tracefs_failed_creating(struct dentry *dentry); struct inode *tracefs_get_inode(struct super_block *sb); -struct dentry *eventfs_start_creating(const char *name, struct dentry *parent); -struct dentry *eventfs_failed_creating(struct dentry *dentry); -struct dentry *eventfs_end_creating(struct dentry *dentry); void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry); #endif /* _TRACEFS_INTERNAL_H */ -- cgit v1.2.3 From 408600be78cdb8c650a97ecc7ff411cb216811b5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 31 Jan 2024 13:49:23 -0500 Subject: eventfs: Remove unused d_parent pointer field It's never used Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240131185512.961772428@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Cc: Greg Kroah-Hartman Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions") Signed-off-by: Linus Torvalds Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 4 +--- fs/tracefs/internal.h | 2 -- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 04c2ab90f93e..16ca8d9759b1 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -680,10 +680,8 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode INIT_LIST_HEAD(&ei->list); mutex_lock(&eventfs_mutex); - if (!parent->is_freed) { + if (!parent->is_freed) list_add_tail(&ei->list, &parent->children); - ei->d_parent = parent->dentry; - } mutex_unlock(&eventfs_mutex); /* Was the parent freed? */ diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 09037e2c173d..932733a2696a 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -36,7 +36,6 @@ struct eventfs_attr { * @name: the name of the directory to create * @children: link list into the child eventfs_inode * @dentry: the dentry of the directory - * @d_parent: pointer to the parent's dentry * @d_children: The array of dentries to represent the files when created * @entry_attrs: Saved mode and ownership of the @d_children * @attr: Saved mode and ownership of eventfs_inode itself @@ -51,7 +50,6 @@ struct eventfs_inode { const char *name; struct list_head children; struct dentry *dentry; /* Check is_freed to access */ - struct dentry *d_parent; struct dentry **d_children; struct eventfs_attr *entry_attrs; struct eventfs_attr attr; -- cgit v1.2.3 From 8dce06e98c70a7fcbb4bca7d90faf40522e65c58 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 31 Jan 2024 13:49:24 -0500 Subject: eventfs: Clean up dentry ops and add revalidate function In order for the dentries to stay up-to-date with the eventfs changes, just add a 'd_revalidate' function that checks the 'is_freed' bit. Also, clean up the dentry release to actually use d_release() rather than the slightly odd d_iput() function. We don't care about the inode, all we want to do is to get rid of the refcount to the eventfs data added by dentry->d_fsdata. It would probably be cleaner to make eventfs its own filesystem, or at least set its own dentry ops when looking up eventfs files. But as it is, only eventfs dentries use d_fsdata, so we don't really need to split these things up by use. Another thing that might be worth doing is to make all eventfs lookups mark their dentries as not worth caching. We could do that with d_delete(), but the DCACHE_DONTCACHE flag would likely be even better. As it is, the dentries are all freeable, but they only tend to get freed at memory pressure rather than more proactively. But that's a separate issue. Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240131185513.124644253@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Cc: Greg Kroah-Hartman Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions") Signed-off-by: Linus Torvalds Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 5 ++--- fs/tracefs/inode.c | 27 ++++++++++++++++++--------- fs/tracefs/internal.h | 3 ++- 3 files changed, 22 insertions(+), 13 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 16ca8d9759b1..b2285d5f3fed 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -378,13 +378,12 @@ static void free_ei(struct eventfs_inode *ei) } /** - * eventfs_set_ei_status_free - remove the dentry reference from an eventfs_inode - * @ti: the tracefs_inode of the dentry + * eventfs_d_release - dentry is going away * @dentry: dentry which has the reference to remove. * * Remove the association between a dentry from an eventfs_inode. */ -void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry) +void eventfs_d_release(struct dentry *dentry) { struct eventfs_inode *ei; int i; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 5c84460feeeb..d65ffad4c327 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -377,21 +377,30 @@ static const struct super_operations tracefs_super_operations = { .show_options = tracefs_show_options, }; -static void tracefs_dentry_iput(struct dentry *dentry, struct inode *inode) +/* + * It would be cleaner if eventfs had its own dentry ops. + * + * Note that d_revalidate is called potentially under RCU, + * so it can't take the eventfs mutex etc. It's fine - if + * we open a file just as it's marked dead, things will + * still work just fine, and just see the old stale case. + */ +static void tracefs_d_release(struct dentry *dentry) { - struct tracefs_inode *ti; + if (dentry->d_fsdata) + eventfs_d_release(dentry); +} - if (!dentry || !inode) - return; +static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct eventfs_inode *ei = dentry->d_fsdata; - ti = get_tracefs(inode); - if (ti && ti->flags & TRACEFS_EVENT_INODE) - eventfs_set_ei_status_free(ti, dentry); - iput(inode); + return !(ei && ei->is_freed); } static const struct dentry_operations tracefs_dentry_operations = { - .d_iput = tracefs_dentry_iput, + .d_revalidate = tracefs_d_revalidate, + .d_release = tracefs_d_release, }; static int trace_fill_super(struct super_block *sb, void *data, int silent) diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 932733a2696a..4b50a0668055 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -78,6 +78,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent); struct dentry *tracefs_end_creating(struct dentry *dentry); struct dentry *tracefs_failed_creating(struct dentry *dentry); struct inode *tracefs_get_inode(struct super_block *sb); -void eventfs_set_ei_status_free(struct tracefs_inode *ti, struct dentry *dentry); + +void eventfs_d_release(struct dentry *dentry); #endif /* _TRACEFS_INTERNAL_H */ -- cgit v1.2.3 From 43aa6f97c2d03a52c1ddb86768575fc84344bdbb Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 31 Jan 2024 13:49:25 -0500 Subject: eventfs: Get rid of dentry pointers without refcounts The eventfs inode had pointers to dentries (and child dentries) without actually holding a refcount on said pointer. That is fundamentally broken, and while eventfs tried to then maintain coherence with dentries going away by hooking into the '.d_iput' callback, that doesn't actually work since it's not ordered wrt lookups. There were two reasonms why eventfs tried to keep a pointer to a dentry: - the creation of a 'events' directory would actually have a stable dentry pointer that it created with tracefs_start_creating(). And it needed that dentry when tearing it all down again in eventfs_remove_events_dir(). This use is actually ok, because the special top-level events directory dentries are actually stable, not just a temporary cache of the eventfs data structures. - the 'eventfs_inode' (aka ei) needs to stay around as long as there are dentries that refer to it. It then used these dentry pointers as a replacement for doing reference counting: it would try to make sure that there was only ever one dentry associated with an event_inode, and keep a child dentry array around to see which dentries might still refer to the parent ei. This gets rid of the invalid dentry pointer use, and renames the one valid case to a different name to make it clear that it's not just any random dentry. The magic child dentry array that is kind of a "reverse reference list" is simply replaced by having child dentries take a ref to the ei. As does the directory dentries. That makes the broken use case go away. Link: https://lore.kernel.org/linux-trace-kernel/202401291043.e62e89dc-oliver.sang@intel.com/ Link: https://lore.kernel.org/linux-trace-kernel/20240131185513.280463000@goodmis.org Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Cc: Greg Kroah-Hartman Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions") Signed-off-by: Linus Torvalds Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 248 ++++++++++++++--------------------------------- fs/tracefs/internal.h | 7 +- 2 files changed, 78 insertions(+), 177 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index b2285d5f3fed..515fdace1eea 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -62,6 +62,35 @@ enum { #define EVENTFS_MODE_MASK (EVENTFS_SAVE_MODE - 1) +/* + * eventfs_inode reference count management. + * + * NOTE! We count only references from dentries, in the + * form 'dentry->d_fsdata'. There are also references from + * directory inodes ('ti->private'), but the dentry reference + * count is always a superset of the inode reference count. + */ +static void release_ei(struct kref *ref) +{ + struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref); + kfree(ei->entry_attrs); + kfree_const(ei->name); + kfree_rcu(ei, rcu); +} + +static inline void put_ei(struct eventfs_inode *ei) +{ + if (ei) + kref_put(&ei->kref, release_ei); +} + +static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei) +{ + if (ei) + kref_get(&ei->kref); + return ei; +} + static struct dentry *eventfs_root_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); @@ -289,7 +318,8 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode, * directory. The inode.i_private pointer will point to @data in the open() * call. */ -static struct dentry *lookup_file(struct dentry *dentry, +static struct dentry *lookup_file(struct eventfs_inode *parent_ei, + struct dentry *dentry, umode_t mode, struct eventfs_attr *attr, void *data, @@ -302,7 +332,7 @@ static struct dentry *lookup_file(struct dentry *dentry, mode |= S_IFREG; if (WARN_ON_ONCE(!S_ISREG(mode))) - return NULL; + return ERR_PTR(-EIO); inode = tracefs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -321,9 +351,12 @@ static struct dentry *lookup_file(struct dentry *dentry, ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; + // Files have their parent's ei as their fsdata + dentry->d_fsdata = get_ei(parent_ei); + d_add(dentry, inode); fsnotify_create(dentry->d_parent->d_inode, dentry); - return dentry; + return NULL; }; /** @@ -359,22 +392,29 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry, /* Only directories have ti->private set to an ei, not files */ ti->private = ei; - dentry->d_fsdata = ei; - ei->dentry = dentry; // Remove me! + dentry->d_fsdata = get_ei(ei); inc_nlink(inode); d_add(dentry, inode); inc_nlink(dentry->d_parent->d_inode); fsnotify_mkdir(dentry->d_parent->d_inode, dentry); - return dentry; + return NULL; } -static void free_ei(struct eventfs_inode *ei) +static inline struct eventfs_inode *alloc_ei(const char *name) { - kfree_const(ei->name); - kfree(ei->d_children); - kfree(ei->entry_attrs); - kfree(ei); + struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL); + + if (!ei) + return NULL; + + ei->name = kstrdup_const(name, GFP_KERNEL); + if (!ei->name) { + kfree(ei); + return NULL; + } + kref_init(&ei->kref); + return ei; } /** @@ -385,39 +425,13 @@ static void free_ei(struct eventfs_inode *ei) */ void eventfs_d_release(struct dentry *dentry) { - struct eventfs_inode *ei; - int i; - - mutex_lock(&eventfs_mutex); - - ei = dentry->d_fsdata; - if (!ei) - goto out; - - /* This could belong to one of the files of the ei */ - if (ei->dentry != dentry) { - for (i = 0; i < ei->nr_entries; i++) { - if (ei->d_children[i] == dentry) - break; - } - if (WARN_ON_ONCE(i == ei->nr_entries)) - goto out; - ei->d_children[i] = NULL; - } else if (ei->is_freed) { - free_ei(ei); - } else { - ei->dentry = NULL; - } - - dentry->d_fsdata = NULL; - out: - mutex_unlock(&eventfs_mutex); + put_ei(dentry->d_fsdata); } /** * lookup_file_dentry - create a dentry for a file of an eventfs_inode * @ei: the eventfs_inode that the file will be created under - * @idx: the index into the d_children[] of the @ei + * @idx: the index into the entry_attrs[] of the @ei * @parent: The parent dentry of the created file. * @name: The name of the file to create * @mode: The mode of the file. @@ -434,17 +448,11 @@ lookup_file_dentry(struct dentry *dentry, const struct file_operations *fops) { struct eventfs_attr *attr = NULL; - struct dentry **e_dentry = &ei->d_children[idx]; if (ei->entry_attrs) attr = &ei->entry_attrs[idx]; - dentry->d_fsdata = ei; // NOTE: ei of _parent_ - lookup_file(dentry, mode, attr, data, fops); - - *e_dentry = dentry; // Remove me - - return dentry; + return lookup_file(ei, dentry, mode, attr, data, fops); } /** @@ -465,6 +473,7 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, struct tracefs_inode *ti; struct eventfs_inode *ei; const char *name = dentry->d_name.name; + struct dentry *result = NULL; ti = get_tracefs(dir); if (!(ti->flags & TRACEFS_EVENT_INODE)) @@ -481,7 +490,7 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, continue; if (ei_child->is_freed) goto out; - lookup_dir_entry(dentry, ei, ei_child); + result = lookup_dir_entry(dentry, ei, ei_child); goto out; } @@ -498,12 +507,12 @@ static struct dentry *eventfs_root_lookup(struct inode *dir, if (entry->callback(name, &mode, &data, &fops) <= 0) goto out; - lookup_file_dentry(dentry, ei, i, mode, data, fops); + result = lookup_file_dentry(dentry, ei, i, mode, data, fops); goto out; } out: mutex_unlock(&eventfs_mutex); - return NULL; + return result; } /* @@ -653,25 +662,10 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode if (!parent) return ERR_PTR(-EINVAL); - ei = kzalloc(sizeof(*ei), GFP_KERNEL); + ei = alloc_ei(name); if (!ei) return ERR_PTR(-ENOMEM); - ei->name = kstrdup_const(name, GFP_KERNEL); - if (!ei->name) { - kfree(ei); - return ERR_PTR(-ENOMEM); - } - - if (size) { - ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL); - if (!ei->d_children) { - kfree_const(ei->name); - kfree(ei); - return ERR_PTR(-ENOMEM); - } - } - ei->entries = entries; ei->nr_entries = size; ei->data = data; @@ -685,7 +679,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode /* Was the parent freed? */ if (list_empty(&ei->list)) { - free_ei(ei); + put_ei(ei); ei = NULL; } return ei; @@ -720,28 +714,20 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry if (IS_ERR(dentry)) return ERR_CAST(dentry); - ei = kzalloc(sizeof(*ei), GFP_KERNEL); + ei = alloc_ei(name); if (!ei) - goto fail_ei; + goto fail; inode = tracefs_get_inode(dentry->d_sb); if (unlikely(!inode)) goto fail; - if (size) { - ei->d_children = kcalloc(size, sizeof(*ei->d_children), GFP_KERNEL); - if (!ei->d_children) - goto fail; - } - - ei->dentry = dentry; + // Note: we have a ref to the dentry from tracefs_start_creating() + ei->events_dir = dentry; ei->entries = entries; ei->nr_entries = size; ei->is_events = 1; ei->data = data; - ei->name = kstrdup_const(name, GFP_KERNEL); - if (!ei->name) - goto fail; /* Save the ownership of this directory */ uid = d_inode(dentry->d_parent)->i_uid; @@ -772,7 +758,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry inode->i_op = &eventfs_root_dir_inode_operations; inode->i_fop = &eventfs_file_operations; - dentry->d_fsdata = ei; + dentry->d_fsdata = get_ei(ei); /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); @@ -784,72 +770,11 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry return ei; fail: - kfree(ei->d_children); - kfree(ei); - fail_ei: + put_ei(ei); tracefs_failed_creating(dentry); return ERR_PTR(-ENOMEM); } -static LLIST_HEAD(free_list); - -static void eventfs_workfn(struct work_struct *work) -{ - struct eventfs_inode *ei, *tmp; - struct llist_node *llnode; - - llnode = llist_del_all(&free_list); - llist_for_each_entry_safe(ei, tmp, llnode, llist) { - /* This dput() matches the dget() from unhook_dentry() */ - for (int i = 0; i < ei->nr_entries; i++) { - if (ei->d_children[i]) - dput(ei->d_children[i]); - } - /* This should only get here if it had a dentry */ - if (!WARN_ON_ONCE(!ei->dentry)) - dput(ei->dentry); - } -} - -static DECLARE_WORK(eventfs_work, eventfs_workfn); - -static void free_rcu_ei(struct rcu_head *head) -{ - struct eventfs_inode *ei = container_of(head, struct eventfs_inode, rcu); - - if (ei->dentry) { - /* Do not free the ei until all references of dentry are gone */ - if (llist_add(&ei->llist, &free_list)) - queue_work(system_unbound_wq, &eventfs_work); - return; - } - - /* If the ei doesn't have a dentry, neither should its children */ - for (int i = 0; i < ei->nr_entries; i++) { - WARN_ON_ONCE(ei->d_children[i]); - } - - free_ei(ei); -} - -static void unhook_dentry(struct dentry *dentry) -{ - if (!dentry) - return; - /* - * Need to add a reference to the dentry that is expected by - * simple_recursive_removal(), which will include a dput(). - */ - dget(dentry); - - /* - * Also add a reference for the dput() in eventfs_workfn(). - * That is required as that dput() will free the ei after - * the SRCU grace period is over. - */ - dget(dentry); -} - /** * eventfs_remove_rec - remove eventfs dir or file from list * @ei: eventfs_inode to be removed. @@ -862,8 +787,6 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level) { struct eventfs_inode *ei_child; - if (!ei) - return; /* * Check recursion depth. It should never be greater than 3: * 0 - events/ @@ -875,28 +798,12 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level) return; /* search for nested folders or files */ - list_for_each_entry_srcu(ei_child, &ei->children, list, - lockdep_is_held(&eventfs_mutex)) { - /* Children only have dentry if parent does */ - WARN_ON_ONCE(ei_child->dentry && !ei->dentry); + list_for_each_entry(ei_child, &ei->children, list) eventfs_remove_rec(ei_child, level + 1); - } - ei->is_freed = 1; - - for (int i = 0; i < ei->nr_entries; i++) { - if (ei->d_children[i]) { - /* Children only have dentry if parent does */ - WARN_ON_ONCE(!ei->dentry); - unhook_dentry(ei->d_children[i]); - } - } - - unhook_dentry(ei->dentry); - - list_del_rcu(&ei->list); - call_srcu(&eventfs_srcu, &ei->rcu, free_rcu_ei); + list_del(&ei->list); + put_ei(ei); } /** @@ -907,22 +814,12 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level) */ void eventfs_remove_dir(struct eventfs_inode *ei) { - struct dentry *dentry; - if (!ei) return; mutex_lock(&eventfs_mutex); - dentry = ei->dentry; eventfs_remove_rec(ei, 0); mutex_unlock(&eventfs_mutex); - - /* - * If any of the ei children has a dentry, then the ei itself - * must have a dentry. - */ - if (dentry) - simple_recursive_removal(dentry, NULL); } /** @@ -935,7 +832,11 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei) { struct dentry *dentry; - dentry = ei->dentry; + dentry = ei->events_dir; + if (!dentry) + return; + + ei->events_dir = NULL; eventfs_remove_dir(ei); /* @@ -945,5 +846,6 @@ void eventfs_remove_events_dir(struct eventfs_inode *ei) * sticks around while the other ei->dentry are created * and destroyed dynamically. */ + d_invalidate(dentry); dput(dentry); } diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 4b50a0668055..1886f1826cd8 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -35,8 +35,7 @@ struct eventfs_attr { * @entries: the array of entries representing the files in the directory * @name: the name of the directory to create * @children: link list into the child eventfs_inode - * @dentry: the dentry of the directory - * @d_children: The array of dentries to represent the files when created + * @events_dir: the dentry of the events directory * @entry_attrs: Saved mode and ownership of the @d_children * @attr: Saved mode and ownership of eventfs_inode itself * @data: The private data to pass to the callbacks @@ -45,12 +44,12 @@ struct eventfs_attr { * @nr_entries: The number of items in @entries */ struct eventfs_inode { + struct kref kref; struct list_head list; const struct eventfs_entry *entries; const char *name; struct list_head children; - struct dentry *dentry; /* Check is_freed to access */ - struct dentry **d_children; + struct dentry *events_dir; struct eventfs_attr *entry_attrs; struct eventfs_attr attr; void *data; -- cgit v1.2.3 From 5a49f996046ba947466bc7461e4b19c4d1daf978 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 1 Feb 2024 10:34:47 -0500 Subject: eventfs: Warn if an eventfs_inode is freed without is_freed being set There should never be a case where an evenfs_inode is being freed without is_freed being set. Add a WARN_ON_ONCE() if it ever happens. That would mean there was one too many put_ei()s. Link: https://lore.kernel.org/linux-trace-kernel/20240201161616.843551963@goodmis.org Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 515fdace1eea..ca7daee7c811 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -73,6 +73,9 @@ enum { static void release_ei(struct kref *ref) { struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref); + + WARN_ON_ONCE(!ei->is_freed); + kfree(ei->entry_attrs); kfree_const(ei->name); kfree_rcu(ei, rcu); @@ -84,6 +87,14 @@ static inline void put_ei(struct eventfs_inode *ei) kref_put(&ei->kref, release_ei); } +static inline void free_ei(struct eventfs_inode *ei) +{ + if (ei) { + ei->is_freed = 1; + put_ei(ei); + } +} + static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei) { if (ei) @@ -679,7 +690,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode /* Was the parent freed? */ if (list_empty(&ei->list)) { - put_ei(ei); + free_ei(ei); ei = NULL; } return ei; @@ -770,7 +781,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry return ei; fail: - put_ei(ei); + free_ei(ei); tracefs_failed_creating(dentry); return ERR_PTR(-ENOMEM); } @@ -801,9 +812,8 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level) list_for_each_entry(ei_child, &ei->children, list) eventfs_remove_rec(ei_child, level + 1); - ei->is_freed = 1; list_del(&ei->list); - put_ei(ei); + free_ei(ei); } /** -- cgit v1.2.3 From 264424dfdd5cbd92bc5b5ddf93944929fc877fac Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 1 Feb 2024 10:34:48 -0500 Subject: eventfs: Restructure eventfs_inode structure to be more condensed Some of the eventfs_inode structure has holes in it. Rework the structure to be a bit more condensed, and also remove the no longer used llist field. Link: https://lore.kernel.org/linux-trace-kernel/20240201161617.002321438@goodmis.org Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/internal.h | 27 ++++++++++++--------------- 1 file changed, 12 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h index 1886f1826cd8..beb3dcd0e434 100644 --- a/fs/tracefs/internal.h +++ b/fs/tracefs/internal.h @@ -32,40 +32,37 @@ struct eventfs_attr { /* * struct eventfs_inode - hold the properties of the eventfs directories. * @list: link list into the parent directory + * @rcu: Union with @list for freeing + * @children: link list into the child eventfs_inode * @entries: the array of entries representing the files in the directory * @name: the name of the directory to create - * @children: link list into the child eventfs_inode * @events_dir: the dentry of the events directory * @entry_attrs: Saved mode and ownership of the @d_children - * @attr: Saved mode and ownership of eventfs_inode itself * @data: The private data to pass to the callbacks + * @attr: Saved mode and ownership of eventfs_inode itself * @is_freed: Flag set if the eventfs is on its way to be freed * Note if is_freed is set, then dentry is corrupted. + * @is_events: Flag set for only the top level "events" directory * @nr_entries: The number of items in @entries + * @ino: The saved inode number */ struct eventfs_inode { - struct kref kref; - struct list_head list; + union { + struct list_head list; + struct rcu_head rcu; + }; + struct list_head children; const struct eventfs_entry *entries; const char *name; - struct list_head children; struct dentry *events_dir; struct eventfs_attr *entry_attrs; - struct eventfs_attr attr; void *data; + struct eventfs_attr attr; + struct kref kref; unsigned int is_freed:1; unsigned int is_events:1; unsigned int nr_entries:30; unsigned int ino; - /* - * Union - used for deletion - * @llist: for calling dput() if needed after RCU - * @rcu: eventfs_inode to delete in RCU - */ - union { - struct llist_node llist; - struct rcu_head rcu; - }; }; static inline struct tracefs_inode *get_tracefs(const struct inode *inode) -- cgit v1.2.3 From 12d823b31fadf47c8f36ecada7abac5f903cac33 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 1 Feb 2024 10:34:49 -0500 Subject: eventfs: Remove fsnotify*() functions from lookup() The dentries and inodes are created when referenced in the lookup code. There's no reason to call fsnotify_*() functions when they are created by a reference. It doesn't make any sense. Link: https://lore.kernel.org/linux-trace-kernel/20240201002719.GS2087318@ZenIV/ Link: https://lore.kernel.org/linux-trace-kernel/20240201161617.166973329@goodmis.org Cc: stable@vger.kernel.org Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Fixes: a376007917776 ("eventfs: Implement functions to create files and dirs when accessed"); Suggested-by: Al Viro Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index ca7daee7c811..9e031e5a2713 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -366,7 +366,6 @@ static struct dentry *lookup_file(struct eventfs_inode *parent_ei, dentry->d_fsdata = get_ei(parent_ei); d_add(dentry, inode); - fsnotify_create(dentry->d_parent->d_inode, dentry); return NULL; }; @@ -408,7 +407,6 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry, inc_nlink(inode); d_add(dentry, inode); inc_nlink(dentry->d_parent->d_inode); - fsnotify_mkdir(dentry->d_parent->d_inode, dentry); return NULL; } -- cgit v1.2.3 From ca185770db914869ff9fe773bac5e0e5e4165b83 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 1 Feb 2024 10:34:50 -0500 Subject: eventfs: Keep all directory links at 1 The directory link count in eventfs was somewhat bogus. It was only being updated when a directory child was being looked up and not on creation. One solution would be to update in get_attr() the link count by iterating the ei->children list and then adding 2. But that could slow down simple stat() calls, especially if it's done on all directories in eventfs. Another solution would be to add a parent pointer to the eventfs_inode and keep track of the number of sub directories it has on creation. But this adds overhead for something not really worthwhile. The solution decided upon is to keep all directory links in eventfs as 1. This tells user space not to rely on the hard links of directories. Which in this case it shouldn't. Link: https://lore.kernel.org/linux-trace-kernel/20240201002719.GS2087318@ZenIV/ Link: https://lore.kernel.org/linux-trace-kernel/20240201161617.339968298@goodmis.org Cc: stable@vger.kernel.org Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Christian Brauner Cc: Al Viro Cc: Ajay Kaher Fixes: c1504e510238 ("eventfs: Implement eventfs dir creation functions") Suggested-by: Al Viro Signed-off-by: Steven Rostedt (Google) --- fs/tracefs/event_inode.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 9e031e5a2713..110e8a272189 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -404,9 +404,7 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry, dentry->d_fsdata = get_ei(ei); - inc_nlink(inode); d_add(dentry, inode); - inc_nlink(dentry->d_parent->d_inode); return NULL; } @@ -769,9 +767,17 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry dentry->d_fsdata = get_ei(ei); - /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inc_nlink(inode); + /* + * Keep all eventfs directories with i_nlink == 1. + * Due to the dynamic nature of the dentry creations and not + * wanting to add a pointer to the parent eventfs_inode in the + * eventfs_inode structure, keeping the i_nlink in sync with the + * number of directories would cause too much complexity for + * something not worth much. Keeping directory links at 1 + * tells userspace not to trust the link number. + */ d_instantiate(dentry, inode); + /* The dentry of the "events" parent does keep track though */ inc_nlink(dentry->d_parent->d_inode); fsnotify_mkdir(dentry->d_parent->d_inode, dentry); tracefs_end_creating(dentry); -- cgit v1.2.3 From e77e15fa5eb1c830597c5ca53ea7af973bae2f78 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Thu, 1 Feb 2024 11:15:26 +0000 Subject: cifs: avoid redundant calls to disable multichannel When the server reports query network interface info call as unsupported following a tree connect, it means that multichannel is unsupported, even if the server capabilities report otherwise. When this happens, cifs_chan_skip_or_disable is called to disable multichannel on the client. However, we only need to call this when multichannel is currently setup. Fixes: f591062bdbf4 ("cifs: handle servers that still advertise multichannel after disabling") Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 6db54c6ef571..e257b10bc820 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -419,7 +419,7 @@ skip_sess_setup: rc = SMB3_request_interfaces(xid, tcon, false); free_xid(xid); - if (rc == -EOPNOTSUPP) { + if (rc == -EOPNOTSUPP && ses->chan_count > 1) { /* * some servers like Azure SMB server do not advertise * that multichannel has been disabled with server -- cgit v1.2.3 From 88675b22d34e6e815ad4bde09c590ccb2d50c59d Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Thu, 1 Feb 2024 11:15:28 +0000 Subject: cifs: do not search for channel if server is terminating In order to scale down the channels, the following sequence of operations happen: 1. server struct is marked for terminate 2. the channel is deallocated in the ses->chans array 3. at a later point the cifsd thread actually terminates the server Between 2 and 3, there can be calls to find the channel for a server struct. When that happens, there can be an ugly warning that's logged. But this is expected. So this change does two things: 1. in cifs_ses_get_chan_index, if server->terminate is set, return 2. always make sure server->terminate is set with chan_lock held Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/sess.c | 4 ++++ fs/smb/client/smb2pdu.c | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index cde81042bebd..3d2548c35c9d 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -75,6 +75,10 @@ cifs_ses_get_chan_index(struct cifs_ses *ses, { unsigned int i; + /* if the channel is waiting for termination */ + if (server->terminate) + return CIFS_INVAL_CHAN_INDEX; + for (i = 0; i < ses->chan_count; i++) { if (ses->chans[i].server == server) return i; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index e257b10bc820..c58fa44dd6b0 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -178,6 +178,7 @@ cifs_chan_skip_or_disable(struct cifs_ses *ses, } ses->chans[chan_index].server = NULL; + server->terminate = true; spin_unlock(&ses->chan_lock); /* @@ -188,7 +189,6 @@ cifs_chan_skip_or_disable(struct cifs_ses *ses, */ cifs_put_tcp_session(server, from_reconnect); - server->terminate = true; cifs_signal_cifsd_for_reconnect(server, false); /* mark primary server as needing reconnect */ -- cgit v1.2.3 From 6aac002bcfd554aff6d3ebb55e1660d078d70ab0 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Thu, 1 Feb 2024 11:15:29 +0000 Subject: cifs: failure to add channel on iface should bump up weight After the interface selection policy change to do a weighted round robin, each iface maintains a weight_fulfilled. When the weight_fulfilled reaches the total weight for the iface, we know that the weights can be reset and ifaces can be allocated from scratch again. During channel allocation failures on a particular channel, weight_fulfilled is not incremented. If a few interfaces are inactive, we could end up in a situation where the active interfaces are all allocated for the total_weight, and inactive ones are all that remain. This can cause a situation where no more channels can be allocated further. This change fixes it by increasing weight_fulfilled, even when channel allocation failure happens. This could mean that if there are temporary failures in channel allocation, the iface weights may not strictly be adhered to. But that's still okay. Fixes: a6d8fb54a515 ("cifs: distribute channels across interfaces based on speed") Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/sess.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 3d2548c35c9d..ed4bd88dd528 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -273,6 +273,8 @@ int cifs_try_adding_channels(struct cifs_ses *ses) &iface->sockaddr, rc); kref_put(&iface->refcount, release_iface); + /* failure to add chan should increase weight */ + iface->weight_fulfilled++; continue; } -- cgit v1.2.3 From 11d4d1dba3315f73d2d1d386f5bf4811a8241d45 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Mon, 29 Jan 2024 21:04:44 -0300 Subject: smb: client: increase number of PDUs allowed in a compound request With the introduction of SMB2_OP_QUERY_WSL_EA, the client may now send 5 commands in a single compound request in order to query xattrs from potential WSL reparse points, which should be fine as we currently allow up to 5 PDUs in a single compound request. However, if encryption is enabled (e.g. 'seal' mount option) or enforced by the server, current MAX_COMPOUND(5) won't be enough as we require an extra PDU for the transform header. Fix this by increasing MAX_COMPOUND to 7 and, while we're at it, add an WARN_ON_ONCE() and return -EIO instead of -ENOMEM in case we attempt to send a compound request that couldn't include the extra transform header. Signed-off-by: Paulo Alcantara Signed-off-by: Steve French --- fs/smb/client/cifsglob.h | 2 +- fs/smb/client/transport.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 9093c507042f..c86a72c9d9ec 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -87,7 +87,7 @@ #define SMB_INTERFACE_POLL_INTERVAL 600 /* maximum number of PDUs in one compound */ -#define MAX_COMPOUND 5 +#define MAX_COMPOUND 7 /* * Default number of credits to keep available for SMB3. diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index e00278fcfa4f..994d70193432 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -435,8 +435,8 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (!(flags & CIFS_TRANSFORM_REQ)) return __smb_send_rqst(server, num_rqst, rqst); - if (num_rqst > MAX_COMPOUND - 1) - return -ENOMEM; + if (WARN_ON_ONCE(num_rqst > MAX_COMPOUND - 1)) + return -EIO; if (!server->ops->init_transform_rq) { cifs_server_dbg(VFS, "Encryption requested but transform callback is missing\n"); -- cgit v1.2.3 From 3fcc2b887a1ba4c1f45319cd8c54daa263ecbc36 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Sat, 27 Jan 2024 09:58:00 +0800 Subject: ext4: refactor ext4_da_map_blocks() Refactor and cleanup ext4_da_map_blocks(), reduce some unnecessary parameters and branches, no logic changes. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240127015825.1608160-2-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 39 +++++++++++++++++---------------------- 1 file changed, 17 insertions(+), 22 deletions(-) (limited to 'fs') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4cae8698f70c..bbd5ee6dd3f3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1704,7 +1704,6 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { if (ext4_es_is_hole(&es)) { - retval = 0; down_read(&EXT4_I(inode)->i_data_sem); goto add_delayed; } @@ -1749,26 +1748,9 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, retval = ext4_ext_map_blocks(NULL, inode, map, 0); else retval = ext4_ind_map_blocks(NULL, inode, map, 0); - -add_delayed: - if (retval == 0) { - int ret; - - /* - * XXX: __block_prepare_write() unmaps passed block, - * is it OK? - */ - - ret = ext4_insert_delayed_block(inode, map->m_lblk); - if (ret != 0) { - retval = ret; - goto out_unlock; - } - - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); - } else if (retval > 0) { + if (retval < 0) + goto out_unlock; + if (retval > 0) { unsigned int status; if (unlikely(retval != map->m_len)) { @@ -1783,11 +1765,24 @@ add_delayed: EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); + goto out_unlock; } +add_delayed: + /* + * XXX: __block_prepare_write() unmaps passed block, + * is it OK? + */ + retval = ext4_insert_delayed_block(inode, map->m_lblk); + if (retval) + goto out_unlock; + + map_bh(bh, inode->i_sb, invalid_block); + set_buffer_new(bh); + set_buffer_delay(bh); + out_unlock: up_read((&EXT4_I(inode)->i_data_sem)); - return retval; } -- cgit v1.2.3 From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Sat, 27 Jan 2024 09:58:01 +0800 Subject: ext4: convert to exclusive lock while inserting delalloc extents ext4_da_map_blocks() only hold i_data_sem in shared mode and i_rwsem when inserting delalloc extents, it could be raced by another querying path of ext4_map_blocks() without i_rwsem, .e.g buffered read path. Suppose we buffered read a file containing just a hole, and without any cached extents tree, then it is raced by another delayed buffered write to the same area or the near area belongs to the same hole, and the new delalloc extent could be overwritten to a hole extent. pread() pwrite() filemap_read_folio() ext4_mpage_readpages() ext4_map_blocks() down_read(i_data_sem) ext4_ext_determine_hole() //find hole ext4_ext_put_gap_in_cache() ext4_es_find_extent_range() //no delalloc extent ext4_da_map_blocks() down_read(i_data_sem) ext4_insert_delayed_block() //insert delalloc extent ext4_es_insert_extent() //overwrite delalloc extent to hole This race could lead to inconsistent delalloc extents tree and incorrect reserved space counter. Fix this by converting to hold i_data_sem in exclusive mode when adding a new delalloc extent in ext4_da_map_blocks(). Cc: stable@vger.kernel.org Signed-off-by: Zhang Yi Suggested-by: Jan Kara Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-) (limited to 'fs') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bbd5ee6dd3f3..b040337501e3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1703,10 +1703,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { - if (ext4_es_is_hole(&es)) { - down_read(&EXT4_I(inode)->i_data_sem); + if (ext4_es_is_hole(&es)) goto add_delayed; - } /* * Delayed extent could be allocated by fallocate. @@ -1748,8 +1746,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, retval = ext4_ext_map_blocks(NULL, inode, map, 0); else retval = ext4_ind_map_blocks(NULL, inode, map, 0); - if (retval < 0) - goto out_unlock; + if (retval < 0) { + up_read(&EXT4_I(inode)->i_data_sem); + return retval; + } if (retval > 0) { unsigned int status; @@ -1765,24 +1765,21 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status); - goto out_unlock; + up_read(&EXT4_I(inode)->i_data_sem); + return retval; } + up_read(&EXT4_I(inode)->i_data_sem); add_delayed: - /* - * XXX: __block_prepare_write() unmaps passed block, - * is it OK? - */ + down_write(&EXT4_I(inode)->i_data_sem); retval = ext4_insert_delayed_block(inode, map->m_lblk); + up_write(&EXT4_I(inode)->i_data_sem); if (retval) - goto out_unlock; + return retval; map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); set_buffer_delay(bh); - -out_unlock: - up_read((&EXT4_I(inode)->i_data_sem)); return retval; } -- cgit v1.2.3 From 6430dea07e85958fa87d0276c0c4388dd51e630b Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Sat, 27 Jan 2024 09:58:02 +0800 Subject: ext4: correct the hole length returned by ext4_map_blocks() In ext4_map_blocks(), if we can't find a range of mapping in the extents cache, we are calling ext4_ext_map_blocks() to search the real path and ext4_ext_determine_hole() to determine the hole range. But if the querying range was partially or completely overlaped by a delalloc extent, we can't find it in the real extent path, so the returned hole length could be incorrect. Fortunately, ext4_ext_put_gap_in_cache() have already handle delalloc extent, but it searches start from the expanded hole_start, doesn't start from the querying range, so the delalloc extent found could not be the one that overlaped the querying range, plus, it also didn't adjust the hole length. Let's just remove ext4_ext_put_gap_in_cache(), handle delalloc and insert adjusted hole extent in ext4_ext_determine_hole(). Signed-off-by: Zhang Yi Suggested-by: Jan Kara Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240127015825.1608160-4-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 111 ++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 70 insertions(+), 41 deletions(-) (limited to 'fs') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9106715254ac..c5b54fb9eb8b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2229,7 +2229,7 @@ static int ext4_fill_es_cache_info(struct inode *inode, /* - * ext4_ext_determine_hole - determine hole around given block + * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole @@ -2241,9 +2241,9 @@ static int ext4_fill_es_cache_info(struct inode *inode, * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ -static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, - struct ext4_ext_path *path, - ext4_lblk_t *lblk) +static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; @@ -2270,30 +2270,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, return len; } -/* - * ext4_ext_put_gap_in_cache: - * calculate boundaries of the gap that the requested block fits into - * and cache this gap - */ -static void -ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, - ext4_lblk_t hole_len) -{ - struct extent_status es; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, - hole_start + hole_len - 1, &es); - if (es.es_len) { - /* There's delayed extent containing lblock? */ - if (es.es_lblk <= hole_start) - return; - hole_len = min(es.es_lblk - hole_start, hole_len); - } - ext_debug(inode, " -> %u:%u\n", hole_start, hole_len); - ext4_es_insert_extent(inode, hole_start, hole_len, ~0, - EXTENT_STATUS_HOLE); -} - /* * ext4_ext_rm_idx: * removes index from the index block. @@ -4062,6 +4038,69 @@ static int get_implied_cluster_alloc(struct super_block *sb, return 0; } +/* + * Determine hole length around the given logical block, first try to + * locate and expand the hole from the given @path, and then adjust it + * if it's partially or completely converted to delayed extents, insert + * it into the extent cache tree if it's indeed a hole, finally return + * the length of the determined extent. + */ +static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t lblk) +{ + ext4_lblk_t hole_start, len; + struct extent_status es; + + hole_start = lblk; + len = ext4_ext_find_hole(inode, path, &hole_start); +again: + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, + hole_start + len - 1, &es); + if (!es.es_len) + goto insert_hole; + + /* + * There's a delalloc extent in the hole, handle it if the delalloc + * extent is in front of, behind and straddle the queried range. + */ + if (lblk >= es.es_lblk + es.es_len) { + /* + * The delalloc extent is in front of the queried range, + * find again from the queried start block. + */ + len -= lblk - hole_start; + hole_start = lblk; + goto again; + } else if (in_range(lblk, es.es_lblk, es.es_len)) { + /* + * The delalloc extent containing lblk, it must have been + * added after ext4_map_blocks() checked the extent status + * tree, adjust the length to the delalloc extent's after + * lblk. + */ + len = es.es_lblk + es.es_len - lblk; + return len; + } else { + /* + * The delalloc extent is partially or completely behind + * the queried range, update hole length until the + * beginning of the delalloc extent. + */ + len = min(es.es_lblk - hole_start, len); + } + +insert_hole: + /* Put just found gap into cache to speed up subsequent requests */ + ext_debug(inode, " -> %u:%u\n", hole_start, len); + ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE); + + /* Update hole_len to reflect hole size after lblk */ + if (hole_start != lblk) + len -= lblk - hole_start; + + return len; +} /* * Block allocation/map/preallocation routine for extents based files @@ -4179,22 +4218,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * we couldn't try to create block if create flag is zero */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { - ext4_lblk_t hole_start, hole_len; + ext4_lblk_t len; - hole_start = map->m_lblk; - hole_len = ext4_ext_determine_hole(inode, path, &hole_start); - /* - * put just found gap into cache to speed up - * subsequent requests - */ - ext4_ext_put_gap_in_cache(inode, hole_start, hole_len); + len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); - /* Update hole_len to reflect hole size after map->m_lblk */ - if (hole_start != map->m_lblk) - hole_len -= map->m_lblk - hole_start; map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, hole_len); - + map->m_len = min_t(unsigned int, map->m_len, len); goto out; } -- cgit v1.2.3 From 9f1118223aa080021fe9751fa221590654d27669 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Sat, 27 Jan 2024 09:58:03 +0800 Subject: ext4: add a hole extent entry in cache after punch In order to cache hole extents in the extent status tree and keep the hole length as long as possible, re-add a hole entry to the cache just after punching a hole. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240127015825.1608160-5-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b040337501e3..af205b416794 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4007,12 +4007,12 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) /* If there are blocks to remove, do it */ if (stop_block > first_block) { + ext4_lblk_t hole_len = stop_block - first_block; down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); - ext4_es_remove_extent(inode, first_block, - stop_block - first_block); + ext4_es_remove_extent(inode, first_block, hole_len); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_remove_space(inode, first_block, @@ -4021,6 +4021,8 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) ret = ext4_ind_remove_space(handle, inode, first_block, stop_block); + ext4_es_insert_extent(inode, first_block, hole_len, ~0, + EXTENT_STATUS_HOLE); up_write(&EXT4_I(inode)->i_data_sem); } ext4_fc_track_range(handle, inode, first_block, stop_block); -- cgit v1.2.3 From 874eaba96d39334fe9c729ff631e65523616d4d8 Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Sat, 27 Jan 2024 09:58:04 +0800 Subject: ext4: make ext4_map_blocks() distinguish delalloc only extent Add a new map flag EXT4_MAP_DELAYED to indicate the mapping range is a delayed allocated only (not unwritten) one, and making ext4_map_blocks() can distinguish it, no longer mixing it with holes. Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240127015825.1608160-6-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 4 +++- fs/ext4/extents.c | 7 +++++-- fs/ext4/inode.c | 2 ++ 3 files changed, 10 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 786b6857ab47..023571f8dd1b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -252,8 +252,10 @@ struct ext4_allocation_request { #define EXT4_MAP_MAPPED BIT(BH_Mapped) #define EXT4_MAP_UNWRITTEN BIT(BH_Unwritten) #define EXT4_MAP_BOUNDARY BIT(BH_Boundary) +#define EXT4_MAP_DELAYED BIT(BH_Delay) #define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\ - EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY) + EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\ + EXT4_MAP_DELAYED) struct ext4_map_blocks { ext4_fsblk_t m_pblk; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c5b54fb9eb8b..7669d154c05e 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4076,8 +4076,11 @@ again: /* * The delalloc extent containing lblk, it must have been * added after ext4_map_blocks() checked the extent status - * tree, adjust the length to the delalloc extent's after - * lblk. + * tree so we are not holding i_rwsem and delalloc info is + * only stabilized by i_data_sem we are going to release + * soon. Don't modify the extent status tree and report + * extent as a hole, just adjust the length to the delalloc + * extent's after lblk. */ len = es.es_lblk + es.es_len - lblk; return len; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index af205b416794..60f0d2dc1c37 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -515,6 +515,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, map->m_len = retval; } else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) { map->m_pblk = 0; + map->m_flags |= ext4_es_is_delayed(&es) ? + EXT4_MAP_DELAYED : 0; retval = es.es_len - (map->m_lblk - es.es_lblk); if (retval > map->m_len) retval = map->m_len; -- cgit v1.2.3 From ec9d669eba4c276d00af88951947fe0e82a6b84c Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Sat, 27 Jan 2024 09:58:05 +0800 Subject: ext4: make ext4_set_iomap() recognize IOMAP_DELALLOC map type Since ext4_map_blocks() can recognize a delayed allocated only extent, make ext4_set_iomap() can also recognize it, and remove the useless separate check in ext4_iomap_begin_report(). Signed-off-by: Zhang Yi Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20240127015825.1608160-7-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 32 +++----------------------------- 1 file changed, 3 insertions(+), 29 deletions(-) (limited to 'fs') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 60f0d2dc1c37..2ccf3b5e3a7c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3262,6 +3262,9 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, iomap->addr = (u64) map->m_pblk << blkbits; if (flags & IOMAP_DAX) iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; + } else if (map->m_flags & EXT4_MAP_DELAYED) { + iomap->type = IOMAP_DELALLOC; + iomap->addr = IOMAP_NULL_ADDR; } else { iomap->type = IOMAP_HOLE; iomap->addr = IOMAP_NULL_ADDR; @@ -3424,35 +3427,11 @@ const struct iomap_ops ext4_iomap_overwrite_ops = { .iomap_end = ext4_iomap_end, }; -static bool ext4_iomap_is_delalloc(struct inode *inode, - struct ext4_map_blocks *map) -{ - struct extent_status es; - ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, - map->m_lblk, end, &es); - - if (!es.es_len || es.es_lblk > end) - return false; - - if (es.es_lblk > map->m_lblk) { - map->m_len = es.es_lblk - map->m_lblk; - return false; - } - - offset = map->m_lblk - es.es_lblk; - map->m_len = es.es_len - offset; - - return true; -} - static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { int ret; - bool delalloc = false; struct ext4_map_blocks map; u8 blkbits = inode->i_blkbits; @@ -3493,13 +3472,8 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return ret; - if (ret == 0) - delalloc = ext4_iomap_is_delalloc(inode, &map); - set_iomap: ext4_set_iomap(inode, iomap, &map, offset, length, flags); - if (delalloc && iomap->type == IOMAP_HOLE) - iomap->type = IOMAP_DELALLOC; return 0; } -- cgit v1.2.3 From e9f1e6bb55bea4f8cb48f8f7443bbac99b60d285 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 2 Feb 2024 17:11:25 +0100 Subject: Revert "gfs2: Use GL_NOBLOCK flag for non-blocking lookups" Commit "gfs2: Use GL_NOBLOCK flag for non-blocking lookups" has several issues, some of which are non-trivial to fix, so revert it for now: https://lore.kernel.org/gfs2/20240202050230.GA875515@ZenIV/T/ This reverts commit dd00aaeb343255a8a30de671bd27bde79a47c8e5. Signed-off-by: Andreas Gruenbacher --- fs/gfs2/dentry.c | 23 +++++++++-------------- fs/gfs2/inode.c | 8 ++++---- 2 files changed, 13 insertions(+), 18 deletions(-) (limited to 'fs') diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 177f1f41f225..2e215e8c3c88 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -32,25 +32,21 @@ static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags) { - struct dentry *parent = NULL; + struct dentry *parent; struct gfs2_sbd *sdp; struct gfs2_inode *dip; - struct inode *dinode, *inode; + struct inode *inode; struct gfs2_holder d_gh; struct gfs2_inode *ip = NULL; int error, valid = 0; int had_lock = 0; - if (flags & LOOKUP_RCU) { - dinode = d_inode_rcu(READ_ONCE(dentry->d_parent)); - if (!dinode) - return -ECHILD; - } else { - parent = dget_parent(dentry); - dinode = d_inode(parent); - } - sdp = GFS2_SB(dinode); - dip = GFS2_I(dinode); + if (flags & LOOKUP_RCU) + return -ECHILD; + + parent = dget_parent(dentry); + sdp = GFS2_SB(d_inode(parent)); + dip = GFS2_I(d_inode(parent)); inode = d_inode(dentry); if (inode) { @@ -66,8 +62,7 @@ static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags) had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL); if (!had_lock) { - error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, - flags & LOOKUP_RCU ? GL_NOBLOCK : 0, &d_gh); + error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh); if (error) goto out; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 6bfc9383b7b8..1b95db2c3aac 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1882,10 +1882,10 @@ int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode, WARN_ON_ONCE(!may_not_block); return -ECHILD; } - if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) { - int noblock = may_not_block ? GL_NOBLOCK : 0; - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, - LM_FLAG_ANY | noblock, &i_gh); + if (gfs2_glock_is_locked_by_me(gl) == NULL) { + if (may_not_block) + return -ECHILD; + error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); if (error) return error; } -- cgit v1.2.3 From dd839f31d7cd5e04f4111a219024268c6f6973f0 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Sun, 4 Feb 2024 08:51:52 +0100 Subject: bcachefs: install fd later to avoid race with close Calling fd_install() makes a file reachable for userland, including the possibility to close the file descriptor, which leads to calling its 'release' hook. If that happens before the code had a chance to bump the reference of the newly created task struct, the release callback will call put_task_struct() too early, leading to the premature destruction of the kernel thread. Avoid that race by calling fd_install() later, after all the setup is done. Fixes: 1c6fdbd8f246 ("bcachefs: Initial commit") Signed-off-by: Mathias Krause Signed-off-by: Kent Overstreet --- fs/bcachefs/thread_with_file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c index b1c867aa2b58..9220d7de10db 100644 --- a/fs/bcachefs/thread_with_file.c +++ b/fs/bcachefs/thread_with_file.c @@ -53,9 +53,9 @@ int bch2_run_thread_with_file(struct thread_with_file *thr, if (ret) goto err; - fd_install(fd, file); get_task_struct(thr->task); wake_up_process(thr->task); + fd_install(fd, file); return fd; err: if (fd >= 0) -- cgit v1.2.3 From 7b508b323b2ec45be59769bd4e4aeba729c52cf6 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 1 Feb 2024 21:01:02 -0500 Subject: bcachefs: time_stats: Check for last_event == 0 when updating freq stats This fixes spurious outliers in the frequency stats. Signed-off-by: Kent Overstreet --- fs/bcachefs/util.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c index 56b815fd9fc6..231003b405ef 100644 --- a/fs/bcachefs/util.c +++ b/fs/bcachefs/util.c @@ -418,14 +418,15 @@ static inline void bch2_time_stats_update_one(struct bch2_time_stats *stats, bch2_quantiles_update(&stats->quantiles, duration); } - if (time_after64(end, stats->last_event)) { + if (stats->last_event && time_after64(end, stats->last_event)) { freq = end - stats->last_event; mean_and_variance_update(&stats->freq_stats, freq); mean_and_variance_weighted_update(&stats->freq_stats_weighted, freq); stats->max_freq = max(stats->max_freq, freq); stats->min_freq = min(stats->min_freq, freq); - stats->last_event = end; } + + stats->last_event = end; } static void __bch2_time_stats_clear_buffer(struct bch2_time_stats *stats, -- cgit v1.2.3 From 5ea9a7c5fe4149f165f0e3b624fe08df02b6c301 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 5 Feb 2024 13:22:39 +1100 Subject: nfsd: don't take fi_lock in nfsd_break_deleg_cb() A recent change to check_for_locks() changed it to take ->flc_lock while holding ->fi_lock. This creates a lock inversion (reported by lockdep) because there is a case where ->fi_lock is taken while holding ->flc_lock. ->flc_lock is held across ->fl_lmops callbacks, and nfsd_break_deleg_cb() is one of those and does take ->fi_lock. However it doesn't need to. Prior to v4.17-rc1~110^2~22 ("nfsd: create a separate lease for each delegation") nfsd_break_deleg_cb() would walk the ->fi_delegations list and so needed the lock. Since then it doesn't walk the list and doesn't need the lock. Two actions are performed under the lock. One is to call nfsd_break_one_deleg which calls nfsd4_run_cb(). These doesn't act on the nfs4_file at all, so don't need the lock. The other is to set ->fi_had_conflict which is in the nfs4_file. This field is only ever set here (except when initialised to false) so there is no possible problem will multiple threads racing when setting it. The field is tested twice in nfs4_set_delegation(). The first test does not hold a lock and is documented as an opportunistic optimisation, so it doesn't impose any need to hold ->fi_lock while setting ->fi_had_conflict. The second test in nfs4_set_delegation() *is* make under ->fi_lock, so removing the locking when ->fi_had_conflict is set could make a change. The change could only be interesting if ->fi_had_conflict tested as false even though nfsd_break_one_deleg() ran before ->fi_lock was unlocked. i.e. while hash_delegation_locked() was running. As hash_delegation_lock() doesn't interact in any way with nfs4_run_cb() there can be no importance to this interaction. So this patch removes the locking from nfsd_break_one_deleg() and moves the final test on ->fi_had_conflict out of the locked region to make it clear that locking isn't important to the test. It is still tested *after* vfs_setlease() has succeeded. This might be significant and as vfs_setlease() takes ->flc_lock, and nfsd_break_one_deleg() is called under ->flc_lock this "after" is a true ordering provided by a spinlock. Fixes: edcf9725150e ("nfsd: fix RELEASE_LOCKOWNER") Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/nfs4state.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'fs') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6dc6340e2852..7d6c657e0409 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4945,10 +4945,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); return false; } @@ -5557,12 +5555,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (status) goto out_unlock; + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); -- cgit v1.2.3