February 2024 - Linux-stable-mirror

FAILED: patch "[PATCH] tracing: Fix wasted memory in saved_cmdlines logic" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 44dc5c41b5b1267d4dd037d26afc0c4d3a568acb # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021909-compacted-account-af9d@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: 44dc5c41b5b1 ("tracing: Fix wasted memory in saved_cmdlines logic") c0a581d7126c ("tracing: Disable interrupt or preemption before acquiring arch_spinlock_t") a35873a0993b ("tracing: Add conditional snapshot") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 44dc5c41b5b1267d4dd037d26afc0c4d3a568acb Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org> Date: Fri, 9 Feb 2024 06:36:22 -0500 Subject: [PATCH] tracing: Fix wasted memory in saved_cmdlines logic While looking at improving the saved_cmdlines cache I found a huge amount of wasted memory that should be used for the cmdlines. The tracing data saves pids during the trace. At sched switch, if a trace occurred, it will save the comm of the task that did the trace. This is saved in a "cache" that maps pids to comms and exposed to user space via the /sys/kernel/tracing/saved_cmdlines file. Currently it only caches by default 128 comms. The structure that uses this creates an array to store the pids using PID_MAX_DEFAULT (which is usually set to 32768). This causes the structure to be of the size of 131104 bytes on 64 bit machines. In hex: 131104 = 0x20020, and since the kernel allocates generic memory in powers of two, the kernel would allocate 0x40000 or 262144 bytes to store this structure. That leaves 131040 bytes of wasted space. Worse, the structure points to an allocated array to store the comm names, which is 16 bytes times the amount of names to save (currently 128), which is 2048 bytes. Instead of allocating a separate array, make the structure end with a variable length string and use the extra space for that. This is similar to a recommendation that Linus had made about eventfs_inode names: https://lore.kernel.org/all/20240130190355.11486-5-torvalds@linux-foundatio… Instead of allocating a separate string array to hold the saved comms, have the structure end with: char saved_cmdlines[]; and round up to the next power of two over sizeof(struct saved_cmdline_buffers) + num_cmdlines * TASK_COMM_LEN It will use this extra space for the saved_cmdline portion. Now, instead of saving only 128 comms by default, by using this wasted space at the end of the structure it can save over 8000 comms and even saves space by removing the need for allocating the other array. Link: https://lore.kernel.org/linux-trace-kernel/20240209063622.1f7b6d5f@rorschac… Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Vincent Donnefort <vdonnefort(a)google.com> Cc: Sven Schnelle <svens(a)linux.ibm.com> Cc: Mete Durlu <meted(a)linux.ibm.com> Fixes: 939c7a4f04fcd ("tracing: Introduce saved_cmdlines_size file") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2a7c6fd934e9..9ff8a439d674 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2320,7 +2320,7 @@ struct saved_cmdlines_buffer { unsigned *map_cmdline_to_pid; unsigned cmdline_num; int cmdline_idx; - char *saved_cmdlines; + char saved_cmdlines[]; }; static struct saved_cmdlines_buffer *savedcmd; @@ -2334,47 +2334,58 @@ static inline void set_cmdline(int idx, const char *cmdline) strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN); } -static int allocate_cmdlines_buffer(unsigned int val, - struct saved_cmdlines_buffer *s) +static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) { + int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); + + kfree(s->map_cmdline_to_pid); + free_pages((unsigned long)s, order); +} + +static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) +{ + struct saved_cmdlines_buffer *s; + struct page *page; + int orig_size, size; + int order; + + /* Figure out how much is needed to hold the given number of cmdlines */ + orig_size = sizeof(*s) + val * TASK_COMM_LEN; + order = get_order(orig_size); + size = 1 << (order + PAGE_SHIFT); + page = alloc_pages(GFP_KERNEL, order); + if (!page) + return NULL; + + s = page_address(page); + memset(s, 0, sizeof(*s)); + + /* Round up to actual allocation */ + val = (size - sizeof(*s)) / TASK_COMM_LEN; + s->cmdline_num = val; + s->map_cmdline_to_pid = kmalloc_array(val, sizeof(*s->map_cmdline_to_pid), GFP_KERNEL); - if (!s->map_cmdline_to_pid) - return -ENOMEM; - - s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL); - if (!s->saved_cmdlines) { - kfree(s->map_cmdline_to_pid); - return -ENOMEM; + if (!s->map_cmdline_to_pid) { + free_saved_cmdlines_buffer(s); + return NULL; } s->cmdline_idx = 0; - s->cmdline_num = val; memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(s->map_pid_to_cmdline)); memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP, val * sizeof(*s->map_cmdline_to_pid)); - return 0; + return s; } static int trace_create_savedcmd(void) { - int ret; + savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT); - savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL); - if (!savedcmd) - return -ENOMEM; - - ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd); - if (ret < 0) { - kfree(savedcmd); - savedcmd = NULL; - return -ENOMEM; - } - - return 0; + return savedcmd ? 0 : -ENOMEM; } int is_tracing_stopped(void) @@ -6056,26 +6067,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) -{ - kfree(s->saved_cmdlines); - kfree(s->map_cmdline_to_pid); - kfree(s); -} - static int tracing_resize_saved_cmdlines(unsigned int val) { struct saved_cmdlines_buffer *s, *savedcmd_temp; - s = kmalloc(sizeof(*s), GFP_KERNEL); + s = allocate_cmdlines_buffer(val); if (!s) return -ENOMEM; - if (allocate_cmdlines_buffer(val, s) < 0) { - kfree(s); - return -ENOMEM; - } - preempt_disable(); arch_spin_lock(&trace_cmdline_lock); savedcmd_temp = savedcmd;

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: convert to exclusive lock while inserting delalloc" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x acf795dc161f3cf481db20f05db4250714e375e5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021929-surreal-snippet-dc79@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: acf795dc161f ("ext4: convert to exclusive lock while inserting delalloc extents") 3fcc2b887a1b ("ext4: refactor ext4_da_map_blocks()") 6c120399cde6 ("ext4: make ext4_es_insert_extent() return void") 2a69c450083d ("ext4: using nofail preallocation in ext4_es_insert_extent()") bda3efaf774f ("ext4: use pre-allocated es in __es_remove_extent()") 95f0b320339a ("ext4: use pre-allocated es in __es_insert_extent()") 73a2f033656b ("ext4: factor out __es_alloc_extent() and __es_free_extent()") 9649eb18c628 ("ext4: add a new helper to check if es must be kept") 8016e29f4362 ("ext4: fast commit recovery path") 5b849b5f96b4 ("jbd2: fast commit recovery path") aa75f4d3daae ("ext4: main fast-commit commit path") ff780b91efe9 ("jbd2: add fast commit machinery") 6866d7b3f2bb ("ext4 / jbd2: add fast commit initialization") 995a3ed67fc8 ("ext4: add fast_commit feature and handling for extended mount options") 2d069c0889ef ("ext4: use common helpers in all places reading metadata buffers") d9befedaafcf ("ext4: clear buffer verified flag if read meta block from disk") 15ed2851b0f4 ("ext4: remove unused argument from ext4_(inc|dec)_count") 3d392b2676bf ("ext4: add prefetch_block_bitmaps mount option") ab74c7b23f37 ("ext4: indicate via a block bitmap read is prefetched via a tracepoint") bc71726c7257 ("ext4: abort the filesystem if failed to async write metadata buffer") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001 From: Zhang Yi <yi.zhang(a)huawei.com> Date: Sat, 27 Jan 2024 09:58:01 +0800 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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; }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: convert to exclusive lock while inserting delalloc" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x acf795dc161f3cf481db20f05db4250714e375e5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021928-heftiness-neutron-2774@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: acf795dc161f ("ext4: convert to exclusive lock while inserting delalloc extents") 3fcc2b887a1b ("ext4: refactor ext4_da_map_blocks()") 6c120399cde6 ("ext4: make ext4_es_insert_extent() return void") 2a69c450083d ("ext4: using nofail preallocation in ext4_es_insert_extent()") bda3efaf774f ("ext4: use pre-allocated es in __es_remove_extent()") 95f0b320339a ("ext4: use pre-allocated es in __es_insert_extent()") 73a2f033656b ("ext4: factor out __es_alloc_extent() and __es_free_extent()") 9649eb18c628 ("ext4: add a new helper to check if es must be kept") 8016e29f4362 ("ext4: fast commit recovery path") 5b849b5f96b4 ("jbd2: fast commit recovery path") aa75f4d3daae ("ext4: main fast-commit commit path") ff780b91efe9 ("jbd2: add fast commit machinery") 6866d7b3f2bb ("ext4 / jbd2: add fast commit initialization") 995a3ed67fc8 ("ext4: add fast_commit feature and handling for extended mount options") 2d069c0889ef ("ext4: use common helpers in all places reading metadata buffers") d9befedaafcf ("ext4: clear buffer verified flag if read meta block from disk") 15ed2851b0f4 ("ext4: remove unused argument from ext4_(inc|dec)_count") 3d392b2676bf ("ext4: add prefetch_block_bitmaps mount option") ab74c7b23f37 ("ext4: indicate via a block bitmap read is prefetched via a tracepoint") bc71726c7257 ("ext4: abort the filesystem if failed to async write metadata buffer") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001 From: Zhang Yi <yi.zhang(a)huawei.com> Date: Sat, 27 Jan 2024 09:58:01 +0800 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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; }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: convert to exclusive lock while inserting delalloc" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x acf795dc161f3cf481db20f05db4250714e375e5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021927-encrypt-tipping-e3ec@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: acf795dc161f ("ext4: convert to exclusive lock while inserting delalloc extents") 3fcc2b887a1b ("ext4: refactor ext4_da_map_blocks()") 6c120399cde6 ("ext4: make ext4_es_insert_extent() return void") 2a69c450083d ("ext4: using nofail preallocation in ext4_es_insert_extent()") bda3efaf774f ("ext4: use pre-allocated es in __es_remove_extent()") 95f0b320339a ("ext4: use pre-allocated es in __es_insert_extent()") 73a2f033656b ("ext4: factor out __es_alloc_extent() and __es_free_extent()") 9649eb18c628 ("ext4: add a new helper to check if es must be kept") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001 From: Zhang Yi <yi.zhang(a)huawei.com> Date: Sat, 27 Jan 2024 09:58:01 +0800 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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; }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: convert to exclusive lock while inserting delalloc" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x acf795dc161f3cf481db20f05db4250714e375e5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021925-sultry-pointer-db19@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: acf795dc161f ("ext4: convert to exclusive lock while inserting delalloc extents") 3fcc2b887a1b ("ext4: refactor ext4_da_map_blocks()") 6c120399cde6 ("ext4: make ext4_es_insert_extent() return void") 2a69c450083d ("ext4: using nofail preallocation in ext4_es_insert_extent()") bda3efaf774f ("ext4: use pre-allocated es in __es_remove_extent()") 95f0b320339a ("ext4: use pre-allocated es in __es_insert_extent()") 73a2f033656b ("ext4: factor out __es_alloc_extent() and __es_free_extent()") 9649eb18c628 ("ext4: add a new helper to check if es must be kept") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001 From: Zhang Yi <yi.zhang(a)huawei.com> Date: Sat, 27 Jan 2024 09:58:01 +0800 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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; }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: convert to exclusive lock while inserting delalloc" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x acf795dc161f3cf481db20f05db4250714e375e5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021924-snugly-vineyard-bf17@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: acf795dc161f ("ext4: convert to exclusive lock while inserting delalloc extents") 3fcc2b887a1b ("ext4: refactor ext4_da_map_blocks()") 6c120399cde6 ("ext4: make ext4_es_insert_extent() return void") 2a69c450083d ("ext4: using nofail preallocation in ext4_es_insert_extent()") bda3efaf774f ("ext4: use pre-allocated es in __es_remove_extent()") 95f0b320339a ("ext4: use pre-allocated es in __es_insert_extent()") 73a2f033656b ("ext4: factor out __es_alloc_extent() and __es_free_extent()") 9649eb18c628 ("ext4: add a new helper to check if es must be kept") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001 From: Zhang Yi <yi.zhang(a)huawei.com> Date: Sat, 27 Jan 2024 09:58:01 +0800 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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; }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: convert to exclusive lock while inserting delalloc" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x acf795dc161f3cf481db20f05db4250714e375e5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021923-unlined-visibly-5e4c@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: acf795dc161f ("ext4: convert to exclusive lock while inserting delalloc extents") 3fcc2b887a1b ("ext4: refactor ext4_da_map_blocks()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001 From: Zhang Yi <yi.zhang(a)huawei.com> Date: Sat, 27 Jan 2024 09:58:01 +0800 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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; }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: convert to exclusive lock while inserting delalloc" failed to apply to 6.7-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.7-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.7.y git checkout FETCH_HEAD git cherry-pick -x acf795dc161f3cf481db20f05db4250714e375e5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021921-radar-dormitory-3b49@gregkh' --subject-prefix 'PATCH 6.7.y' HEAD^.. Possible dependencies: acf795dc161f ("ext4: convert to exclusive lock while inserting delalloc extents") 3fcc2b887a1b ("ext4: refactor ext4_da_map_blocks()") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From acf795dc161f3cf481db20f05db4250714e375e5 Mon Sep 17 00:00:00 2001 From: Zhang Yi <yi.zhang(a)huawei.com> Date: Sat, 27 Jan 2024 09:58:01 +0800 Subject: [PATCH] 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(a)vger.kernel.org Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240127015825.1608160-3-yi.zhang@huaweicloud.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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; }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: avoid bb_free and bb_fragments inconsistency in" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 2331fd4a49864e1571b4f50aa3aa1536ed6220d0 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021911-vibes-blitz-7944@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: 2331fd4a4986 ("ext4: avoid bb_free and bb_fragments inconsistency in mb_free_blocks()") c9b528c35795 ("ext4: regenerate buddy after block freeing failed if under fc replay") 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning") 4b68f6df1059 ("ext4: add MB_NUM_ORDERS macro") a6c75eaf1103 ("ext4: add mballoc stats proc file") b237e3044450 ("ext4: add ability to return parsed options from parse_options") 67d251860461 ("ext4: drop s_mb_bal_lock and convert protected fields to atomic") 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") a72b38eebea4 ("ext4: handle dax mount option collision") 99c880decf27 ("ext4: cleanup fast commit mount options") 0f0672ffb61a ("ext4: add a mount opt to forcefully turn fast commits on") 8016e29f4362 ("ext4: fast commit recovery path") 5b849b5f96b4 ("jbd2: fast commit recovery path") aa75f4d3daae ("ext4: main fast-commit commit path") ff780b91efe9 ("jbd2: add fast commit machinery") 6866d7b3f2bb ("ext4 / jbd2: add fast commit initialization") 995a3ed67fc8 ("ext4: add fast_commit feature and handling for extended mount options") 2d069c0889ef ("ext4: use common helpers in all places reading metadata buffers") d9befedaafcf ("ext4: clear buffer verified flag if read meta block from disk") 15ed2851b0f4 ("ext4: remove unused argument from ext4_(inc|dec)_count") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2331fd4a49864e1571b4f50aa3aa1536ed6220d0 Mon Sep 17 00:00:00 2001 From: Baokun Li <libaokun1(a)huawei.com> Date: Thu, 4 Jan 2024 22:20:36 +0800 Subject: [PATCH] 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: <stable(a)vger.kernel.org> # 3.10 Suggested-by: Jan Kara <jack(a)suse.cz> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240104142040.2835097-5-libaokun1@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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); }

1 year, 8 months

1
0
0 0

FAILED: patch "[PATCH] ext4: avoid bb_free and bb_fragments inconsistency in" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 2331fd4a49864e1571b4f50aa3aa1536ed6220d0 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021910-handbrake-gave-712f@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: 2331fd4a4986 ("ext4: avoid bb_free and bb_fragments inconsistency in mb_free_blocks()") c9b528c35795 ("ext4: regenerate buddy after block freeing failed if under fc replay") 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning") 4b68f6df1059 ("ext4: add MB_NUM_ORDERS macro") a6c75eaf1103 ("ext4: add mballoc stats proc file") b237e3044450 ("ext4: add ability to return parsed options from parse_options") 67d251860461 ("ext4: drop s_mb_bal_lock and convert protected fields to atomic") 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") a72b38eebea4 ("ext4: handle dax mount option collision") 99c880decf27 ("ext4: cleanup fast commit mount options") 0f0672ffb61a ("ext4: add a mount opt to forcefully turn fast commits on") 8016e29f4362 ("ext4: fast commit recovery path") 5b849b5f96b4 ("jbd2: fast commit recovery path") aa75f4d3daae ("ext4: main fast-commit commit path") ff780b91efe9 ("jbd2: add fast commit machinery") 6866d7b3f2bb ("ext4 / jbd2: add fast commit initialization") 995a3ed67fc8 ("ext4: add fast_commit feature and handling for extended mount options") 2d069c0889ef ("ext4: use common helpers in all places reading metadata buffers") d9befedaafcf ("ext4: clear buffer verified flag if read meta block from disk") 15ed2851b0f4 ("ext4: remove unused argument from ext4_(inc|dec)_count") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2331fd4a49864e1571b4f50aa3aa1536ed6220d0 Mon Sep 17 00:00:00 2001 From: Baokun Li <libaokun1(a)huawei.com> Date: Thu, 4 Jan 2024 22:20:36 +0800 Subject: [PATCH] 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: <stable(a)vger.kernel.org> # 3.10 Suggested-by: Jan Kara <jack(a)suse.cz> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20240104142040.2835097-5-libaokun1@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> 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); }

1 year, 8 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2024