- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] btrfs: sysfs: fix direct super block member reads" 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 fca432e73db2bec0fdbfbf6d98d3ebcd5388a977 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123002-nylon-baffle-a6ad@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From fca432e73db2bec0fdbfbf6d98d3ebcd5388a977 Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Wed, 18 Dec 2024 17:00:56 +1030 Subject: [PATCH] btrfs: sysfs: fix direct super block member reads The following sysfs entries are reading super block member directly, which can have a different endian and cause wrong values: - sys/fs/btrfs/<uuid>/nodesize - sys/fs/btrfs/<uuid>/sectorsize - sys/fs/btrfs/<uuid>/clone_alignment Thankfully those values (nodesize and sectorsize) are always aligned inside the btrfs_super_block, so it won't trigger unaligned read errors, just endian problems. Fix them by using the native cached members instead. Fixes: df93589a1737 ("btrfs: export more from FS_INFO to sysfs") CC: stable(a)vger.kernel.org Reviewed-by: Naohiro Aota <naohiro.aota(a)wdc.com> Reviewed-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index fdcbf650ac31..7f09b6c9cc2d 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1118,7 +1118,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->nodesize); + return sysfs_emit(buf, "%u\n", fs_info->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); @@ -1128,7 +1128,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); @@ -1180,7 +1180,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix transaction atomicity bug when enabling simple" 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 f2363e6fcc7938c5f0f6ac066fad0dd247598b51 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123034-luxury-clumsily-dce2@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f2363e6fcc7938c5f0f6ac066fad0dd247598b51 Mon Sep 17 00:00:00 2001 From: Julian Sun <sunjunchao2870(a)gmail.com> Date: Wed, 11 Dec 2024 19:13:15 +0800 Subject: [PATCH] btrfs: fix transaction atomicity bug when enabling simple quotas Set squota incompat bit before committing the transaction that enables the feature. With the config CONFIG_BTRFS_ASSERT enabled, an assertion failure occurs regarding the simple quota feature. [5.596534] assertion failed: btrfs_fs_incompat(fs_info, SIMPLE_QUOTA), in fs/btrfs/qgroup.c:365 [5.597098] ------------[ cut here ]------------ [5.597371] kernel BUG at fs/btrfs/qgroup.c:365! [5.597946] CPU: 1 UID: 0 PID: 268 Comm: mount Not tainted 6.13.0-rc2-00031-gf92f4749861b #146 [5.598450] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 [5.599008] RIP: 0010:btrfs_read_qgroup_config+0x74d/0x7a0 [5.604303] <TASK> [5.605230] ? btrfs_read_qgroup_config+0x74d/0x7a0 [5.605538] ? exc_invalid_op+0x56/0x70 [5.605775] ? btrfs_read_qgroup_config+0x74d/0x7a0 [5.606066] ? asm_exc_invalid_op+0x1f/0x30 [5.606441] ? btrfs_read_qgroup_config+0x74d/0x7a0 [5.606741] ? btrfs_read_qgroup_config+0x74d/0x7a0 [5.607038] ? try_to_wake_up+0x317/0x760 [5.607286] open_ctree+0xd9c/0x1710 [5.607509] btrfs_get_tree+0x58a/0x7e0 [5.608002] vfs_get_tree+0x2e/0x100 [5.608224] fc_mount+0x16/0x60 [5.608420] btrfs_get_tree+0x2f8/0x7e0 [5.608897] vfs_get_tree+0x2e/0x100 [5.609121] path_mount+0x4c8/0xbc0 [5.609538] __x64_sys_mount+0x10d/0x150 The issue can be easily reproduced using the following reproducer: root@q:linux# cat repro.sh set -e mkfs.btrfs -q -f /dev/sdb mount /dev/sdb /mnt/btrfs btrfs quota enable -s /mnt/btrfs umount /mnt/btrfs mount /dev/sdb /mnt/btrfs The issue is that when enabling quotas, at btrfs_quota_enable(), we set BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE at fs_info->qgroup_flags and persist it in the quota root in the item with the key BTRFS_QGROUP_STATUS_KEY, but we only set the incompat bit BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA after we commit the transaction used to enable simple quotas. This means that if after that transaction commit we unmount the filesystem without starting and committing any other transaction, or we have a power failure, the next time we mount the filesystem we will find the flag BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE set in the item with the key BTRFS_QGROUP_STATUS_KEY but we will not find the incompat bit BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA set in the superblock, triggering an assertion failure at: btrfs_read_qgroup_config() -> qgroup_read_enable_gen() To fix this issue, set the BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA flag immediately after setting the BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE. This ensures that both flags are flushed to disk within the same transaction. Fixes: 182940f4f4db ("btrfs: qgroup: add new quota mode for simple quotas") CC: stable(a)vger.kernel.org # 6.6+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Julian Sun <sunjunchao2870(a)gmail.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a6f92836c9b1..f9b214992212 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1121,6 +1121,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; + btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -1254,8 +1255,6 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (simple) - btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); spin_unlock(&fs_info->qgroup_lock); /* Skip rescan for simple qgroups. */

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix swap file activation failure due to extents that" 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 03018e5d8508254534511d40fb57bc150e6a87f2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123028-alibi-limpness-1931@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 03018e5d8508254534511d40fb57bc150e6a87f2 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 9 Dec 2024 12:54:14 +0000 Subject: [PATCH] btrfs: fix swap file activation failure due to extents that used to be shared When activating a swap file, to determine if an extent is shared we use can_nocow_extent(), which ends up at btrfs_cross_ref_exist(). That helper is meant to be quick because it's used in the NOCOW write path, when flushing delalloc and when doing a direct IO write, however it does return some false positives, meaning it may indicate that an extent is shared even if it's no longer the case. For the write path this is fine, we just do a unnecessary COW operation instead of doing a more rigorous check which would be too heavy (calling btrfs_is_data_extent_shared()). However when activating a swap file, the false positives simply result in a failure, which is confusing for users/applications. One particular case where this happens is when a data extent only has 1 reference but that reference is not inlined in the extent item located in the extent tree - this happens when we create more than 33 references for an extent and then delete those 33 references plus every other non-inline reference except one. The function check_committed_ref() assumes that if the size of an extent item doesn't match the size of struct btrfs_extent_item plus the size of an inline reference (plus an owner reference in case simple quotas are enabled), then the extent is shared - that is not the case however, we can have a single reference but it's not inlined - the reason we do this is to be fast and avoid inspecting non-inline references which may be located in another leaf of the extent tree, slowing down write paths. The following test script reproduces the bug: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi NUM_CLONES=50 umount $DEV &> /dev/null run_test() { local sync_after_add_reflinks=$1 local sync_after_remove_reflinks=$2 mkfs.btrfs -f $DEV > /dev/null #mkfs.xfs -f $DEV > /dev/null mount $DEV $MNT touch $MNT/foo chmod 0600 $MNT/foo # On btrfs the file must be NOCOW. chattr +C $MNT/foo &> /dev/null xfs_io -s -c "pwrite -b 1M 0 1M" $MNT/foo mkswap $MNT/foo for ((i = 1; i <= $NUM_CLONES; i++)); do touch $MNT/foo_clone_$i chmod 0600 $MNT/foo_clone_$i # On btrfs the file must be NOCOW. chattr +C $MNT/foo_clone_$i &> /dev/null cp --reflink=always $MNT/foo $MNT/foo_clone_$i done if [ $sync_after_add_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Remove the original file and all clones except the last. rm -f $MNT/foo for ((i = 1; i < $NUM_CLONES; i++)); do rm -f $MNT/foo_clone_$i done if [ $sync_after_remove_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Now use the last clone as a swap file. It should work since # its extent are not shared anymore. swapon $MNT/foo_clone_${NUM_CLONES} swapoff $MNT/foo_clone_${NUM_CLONES} umount $MNT } echo -e "\nTest without sync after creating and removing clones" run_test 0 0 echo -e "\nTest with sync after creating clones" run_test 1 0 echo -e "\nTest with sync after removing clones" run_test 0 1 echo -e "\nTest with sync after creating and removing clones" run_test 1 1 Running the test: $ ./test.sh Test without sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0017 sec (556.793 MiB/sec and 556.7929 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=a6b9c29e-5ef4-4689-a8ac-bc199c750f02 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after creating clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0036 sec (271.739 MiB/sec and 271.7391 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=5e9008d6-1f7a-4948-a1b4-3f30aba20a33 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0103 sec (96.665 MiB/sec and 96.6651 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=916c2740-fa9f-4385-9f06-29c3f89e4764 Test with sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0031 sec (314.268 MiB/sec and 314.2678 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=06aab1dd-4d90-49c0-bd9f-3a8db4e2f912 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Fix this by reworking btrfs_swap_activate() to instead of using extent maps and checking for shared extents with can_nocow_extent(), iterate over the inode's file extent items and use the accurate btrfs_is_data_extent_shared(). CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b2abc0aa5300..b87f19630b00 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9799,15 +9799,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; /* * Acquire the inode's mmap lock to prevent races with memory mapped @@ -9846,6 +9847,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, goto out_unlock_mmap; } + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; + } + /* * Balance or device remove/replace/resize can move stuff around from * under us. The exclop protection makes sure they aren't running/won't @@ -9904,24 +9912,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9933,23 +9956,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); + + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9984,7 +10029,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10025,20 +10069,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - - start += len; } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10053,6 +10093,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, out_unlock_mmap: up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret;

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix swap file activation failure due to extents that" 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 03018e5d8508254534511d40fb57bc150e6a87f2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123021-swimmable-curled-c1b6@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 03018e5d8508254534511d40fb57bc150e6a87f2 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 9 Dec 2024 12:54:14 +0000 Subject: [PATCH] btrfs: fix swap file activation failure due to extents that used to be shared When activating a swap file, to determine if an extent is shared we use can_nocow_extent(), which ends up at btrfs_cross_ref_exist(). That helper is meant to be quick because it's used in the NOCOW write path, when flushing delalloc and when doing a direct IO write, however it does return some false positives, meaning it may indicate that an extent is shared even if it's no longer the case. For the write path this is fine, we just do a unnecessary COW operation instead of doing a more rigorous check which would be too heavy (calling btrfs_is_data_extent_shared()). However when activating a swap file, the false positives simply result in a failure, which is confusing for users/applications. One particular case where this happens is when a data extent only has 1 reference but that reference is not inlined in the extent item located in the extent tree - this happens when we create more than 33 references for an extent and then delete those 33 references plus every other non-inline reference except one. The function check_committed_ref() assumes that if the size of an extent item doesn't match the size of struct btrfs_extent_item plus the size of an inline reference (plus an owner reference in case simple quotas are enabled), then the extent is shared - that is not the case however, we can have a single reference but it's not inlined - the reason we do this is to be fast and avoid inspecting non-inline references which may be located in another leaf of the extent tree, slowing down write paths. The following test script reproduces the bug: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi NUM_CLONES=50 umount $DEV &> /dev/null run_test() { local sync_after_add_reflinks=$1 local sync_after_remove_reflinks=$2 mkfs.btrfs -f $DEV > /dev/null #mkfs.xfs -f $DEV > /dev/null mount $DEV $MNT touch $MNT/foo chmod 0600 $MNT/foo # On btrfs the file must be NOCOW. chattr +C $MNT/foo &> /dev/null xfs_io -s -c "pwrite -b 1M 0 1M" $MNT/foo mkswap $MNT/foo for ((i = 1; i <= $NUM_CLONES; i++)); do touch $MNT/foo_clone_$i chmod 0600 $MNT/foo_clone_$i # On btrfs the file must be NOCOW. chattr +C $MNT/foo_clone_$i &> /dev/null cp --reflink=always $MNT/foo $MNT/foo_clone_$i done if [ $sync_after_add_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Remove the original file and all clones except the last. rm -f $MNT/foo for ((i = 1; i < $NUM_CLONES; i++)); do rm -f $MNT/foo_clone_$i done if [ $sync_after_remove_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Now use the last clone as a swap file. It should work since # its extent are not shared anymore. swapon $MNT/foo_clone_${NUM_CLONES} swapoff $MNT/foo_clone_${NUM_CLONES} umount $MNT } echo -e "\nTest without sync after creating and removing clones" run_test 0 0 echo -e "\nTest with sync after creating clones" run_test 1 0 echo -e "\nTest with sync after removing clones" run_test 0 1 echo -e "\nTest with sync after creating and removing clones" run_test 1 1 Running the test: $ ./test.sh Test without sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0017 sec (556.793 MiB/sec and 556.7929 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=a6b9c29e-5ef4-4689-a8ac-bc199c750f02 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after creating clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0036 sec (271.739 MiB/sec and 271.7391 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=5e9008d6-1f7a-4948-a1b4-3f30aba20a33 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0103 sec (96.665 MiB/sec and 96.6651 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=916c2740-fa9f-4385-9f06-29c3f89e4764 Test with sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0031 sec (314.268 MiB/sec and 314.2678 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=06aab1dd-4d90-49c0-bd9f-3a8db4e2f912 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Fix this by reworking btrfs_swap_activate() to instead of using extent maps and checking for shared extents with can_nocow_extent(), iterate over the inode's file extent items and use the accurate btrfs_is_data_extent_shared(). CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b2abc0aa5300..b87f19630b00 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9799,15 +9799,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; /* * Acquire the inode's mmap lock to prevent races with memory mapped @@ -9846,6 +9847,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, goto out_unlock_mmap; } + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; + } + /* * Balance or device remove/replace/resize can move stuff around from * under us. The exclop protection makes sure they aren't running/won't @@ -9904,24 +9912,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9933,23 +9956,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); + + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9984,7 +10029,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10025,20 +10069,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - - start += len; } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10053,6 +10093,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, out_unlock_mmap: up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret;

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix swap file activation failure due to extents that" 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 03018e5d8508254534511d40fb57bc150e6a87f2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123015-briar-craftily-a6d3@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 03018e5d8508254534511d40fb57bc150e6a87f2 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 9 Dec 2024 12:54:14 +0000 Subject: [PATCH] btrfs: fix swap file activation failure due to extents that used to be shared When activating a swap file, to determine if an extent is shared we use can_nocow_extent(), which ends up at btrfs_cross_ref_exist(). That helper is meant to be quick because it's used in the NOCOW write path, when flushing delalloc and when doing a direct IO write, however it does return some false positives, meaning it may indicate that an extent is shared even if it's no longer the case. For the write path this is fine, we just do a unnecessary COW operation instead of doing a more rigorous check which would be too heavy (calling btrfs_is_data_extent_shared()). However when activating a swap file, the false positives simply result in a failure, which is confusing for users/applications. One particular case where this happens is when a data extent only has 1 reference but that reference is not inlined in the extent item located in the extent tree - this happens when we create more than 33 references for an extent and then delete those 33 references plus every other non-inline reference except one. The function check_committed_ref() assumes that if the size of an extent item doesn't match the size of struct btrfs_extent_item plus the size of an inline reference (plus an owner reference in case simple quotas are enabled), then the extent is shared - that is not the case however, we can have a single reference but it's not inlined - the reason we do this is to be fast and avoid inspecting non-inline references which may be located in another leaf of the extent tree, slowing down write paths. The following test script reproduces the bug: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi NUM_CLONES=50 umount $DEV &> /dev/null run_test() { local sync_after_add_reflinks=$1 local sync_after_remove_reflinks=$2 mkfs.btrfs -f $DEV > /dev/null #mkfs.xfs -f $DEV > /dev/null mount $DEV $MNT touch $MNT/foo chmod 0600 $MNT/foo # On btrfs the file must be NOCOW. chattr +C $MNT/foo &> /dev/null xfs_io -s -c "pwrite -b 1M 0 1M" $MNT/foo mkswap $MNT/foo for ((i = 1; i <= $NUM_CLONES; i++)); do touch $MNT/foo_clone_$i chmod 0600 $MNT/foo_clone_$i # On btrfs the file must be NOCOW. chattr +C $MNT/foo_clone_$i &> /dev/null cp --reflink=always $MNT/foo $MNT/foo_clone_$i done if [ $sync_after_add_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Remove the original file and all clones except the last. rm -f $MNT/foo for ((i = 1; i < $NUM_CLONES; i++)); do rm -f $MNT/foo_clone_$i done if [ $sync_after_remove_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Now use the last clone as a swap file. It should work since # its extent are not shared anymore. swapon $MNT/foo_clone_${NUM_CLONES} swapoff $MNT/foo_clone_${NUM_CLONES} umount $MNT } echo -e "\nTest without sync after creating and removing clones" run_test 0 0 echo -e "\nTest with sync after creating clones" run_test 1 0 echo -e "\nTest with sync after removing clones" run_test 0 1 echo -e "\nTest with sync after creating and removing clones" run_test 1 1 Running the test: $ ./test.sh Test without sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0017 sec (556.793 MiB/sec and 556.7929 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=a6b9c29e-5ef4-4689-a8ac-bc199c750f02 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after creating clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0036 sec (271.739 MiB/sec and 271.7391 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=5e9008d6-1f7a-4948-a1b4-3f30aba20a33 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0103 sec (96.665 MiB/sec and 96.6651 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=916c2740-fa9f-4385-9f06-29c3f89e4764 Test with sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0031 sec (314.268 MiB/sec and 314.2678 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=06aab1dd-4d90-49c0-bd9f-3a8db4e2f912 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Fix this by reworking btrfs_swap_activate() to instead of using extent maps and checking for shared extents with can_nocow_extent(), iterate over the inode's file extent items and use the accurate btrfs_is_data_extent_shared(). CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b2abc0aa5300..b87f19630b00 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9799,15 +9799,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; /* * Acquire the inode's mmap lock to prevent races with memory mapped @@ -9846,6 +9847,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, goto out_unlock_mmap; } + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; + } + /* * Balance or device remove/replace/resize can move stuff around from * under us. The exclop protection makes sure they aren't running/won't @@ -9904,24 +9912,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9933,23 +9956,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); + + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9984,7 +10029,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10025,20 +10069,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - - start += len; } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10053,6 +10093,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, out_unlock_mmap: up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret;

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix swap file activation failure due to extents that" 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 03018e5d8508254534511d40fb57bc150e6a87f2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123009-curve-huntsman-5a05@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 03018e5d8508254534511d40fb57bc150e6a87f2 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 9 Dec 2024 12:54:14 +0000 Subject: [PATCH] btrfs: fix swap file activation failure due to extents that used to be shared When activating a swap file, to determine if an extent is shared we use can_nocow_extent(), which ends up at btrfs_cross_ref_exist(). That helper is meant to be quick because it's used in the NOCOW write path, when flushing delalloc and when doing a direct IO write, however it does return some false positives, meaning it may indicate that an extent is shared even if it's no longer the case. For the write path this is fine, we just do a unnecessary COW operation instead of doing a more rigorous check which would be too heavy (calling btrfs_is_data_extent_shared()). However when activating a swap file, the false positives simply result in a failure, which is confusing for users/applications. One particular case where this happens is when a data extent only has 1 reference but that reference is not inlined in the extent item located in the extent tree - this happens when we create more than 33 references for an extent and then delete those 33 references plus every other non-inline reference except one. The function check_committed_ref() assumes that if the size of an extent item doesn't match the size of struct btrfs_extent_item plus the size of an inline reference (plus an owner reference in case simple quotas are enabled), then the extent is shared - that is not the case however, we can have a single reference but it's not inlined - the reason we do this is to be fast and avoid inspecting non-inline references which may be located in another leaf of the extent tree, slowing down write paths. The following test script reproduces the bug: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi NUM_CLONES=50 umount $DEV &> /dev/null run_test() { local sync_after_add_reflinks=$1 local sync_after_remove_reflinks=$2 mkfs.btrfs -f $DEV > /dev/null #mkfs.xfs -f $DEV > /dev/null mount $DEV $MNT touch $MNT/foo chmod 0600 $MNT/foo # On btrfs the file must be NOCOW. chattr +C $MNT/foo &> /dev/null xfs_io -s -c "pwrite -b 1M 0 1M" $MNT/foo mkswap $MNT/foo for ((i = 1; i <= $NUM_CLONES; i++)); do touch $MNT/foo_clone_$i chmod 0600 $MNT/foo_clone_$i # On btrfs the file must be NOCOW. chattr +C $MNT/foo_clone_$i &> /dev/null cp --reflink=always $MNT/foo $MNT/foo_clone_$i done if [ $sync_after_add_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Remove the original file and all clones except the last. rm -f $MNT/foo for ((i = 1; i < $NUM_CLONES; i++)); do rm -f $MNT/foo_clone_$i done if [ $sync_after_remove_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Now use the last clone as a swap file. It should work since # its extent are not shared anymore. swapon $MNT/foo_clone_${NUM_CLONES} swapoff $MNT/foo_clone_${NUM_CLONES} umount $MNT } echo -e "\nTest without sync after creating and removing clones" run_test 0 0 echo -e "\nTest with sync after creating clones" run_test 1 0 echo -e "\nTest with sync after removing clones" run_test 0 1 echo -e "\nTest with sync after creating and removing clones" run_test 1 1 Running the test: $ ./test.sh Test without sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0017 sec (556.793 MiB/sec and 556.7929 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=a6b9c29e-5ef4-4689-a8ac-bc199c750f02 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after creating clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0036 sec (271.739 MiB/sec and 271.7391 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=5e9008d6-1f7a-4948-a1b4-3f30aba20a33 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0103 sec (96.665 MiB/sec and 96.6651 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=916c2740-fa9f-4385-9f06-29c3f89e4764 Test with sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0031 sec (314.268 MiB/sec and 314.2678 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=06aab1dd-4d90-49c0-bd9f-3a8db4e2f912 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Fix this by reworking btrfs_swap_activate() to instead of using extent maps and checking for shared extents with can_nocow_extent(), iterate over the inode's file extent items and use the accurate btrfs_is_data_extent_shared(). CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b2abc0aa5300..b87f19630b00 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9799,15 +9799,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; /* * Acquire the inode's mmap lock to prevent races with memory mapped @@ -9846,6 +9847,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, goto out_unlock_mmap; } + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; + } + /* * Balance or device remove/replace/resize can move stuff around from * under us. The exclop protection makes sure they aren't running/won't @@ -9904,24 +9912,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9933,23 +9956,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); + + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9984,7 +10029,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10025,20 +10069,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - - start += len; } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10053,6 +10093,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, out_unlock_mmap: up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret;

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix swap file activation failure due to extents that" 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 03018e5d8508254534511d40fb57bc150e6a87f2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123002-remedial-drainpipe-efb2@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 03018e5d8508254534511d40fb57bc150e6a87f2 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Mon, 9 Dec 2024 12:54:14 +0000 Subject: [PATCH] btrfs: fix swap file activation failure due to extents that used to be shared When activating a swap file, to determine if an extent is shared we use can_nocow_extent(), which ends up at btrfs_cross_ref_exist(). That helper is meant to be quick because it's used in the NOCOW write path, when flushing delalloc and when doing a direct IO write, however it does return some false positives, meaning it may indicate that an extent is shared even if it's no longer the case. For the write path this is fine, we just do a unnecessary COW operation instead of doing a more rigorous check which would be too heavy (calling btrfs_is_data_extent_shared()). However when activating a swap file, the false positives simply result in a failure, which is confusing for users/applications. One particular case where this happens is when a data extent only has 1 reference but that reference is not inlined in the extent item located in the extent tree - this happens when we create more than 33 references for an extent and then delete those 33 references plus every other non-inline reference except one. The function check_committed_ref() assumes that if the size of an extent item doesn't match the size of struct btrfs_extent_item plus the size of an inline reference (plus an owner reference in case simple quotas are enabled), then the extent is shared - that is not the case however, we can have a single reference but it's not inlined - the reason we do this is to be fast and avoid inspecting non-inline references which may be located in another leaf of the extent tree, slowing down write paths. The following test script reproduces the bug: $ cat test.sh #!/bin/bash DEV=/dev/sdi MNT=/mnt/sdi NUM_CLONES=50 umount $DEV &> /dev/null run_test() { local sync_after_add_reflinks=$1 local sync_after_remove_reflinks=$2 mkfs.btrfs -f $DEV > /dev/null #mkfs.xfs -f $DEV > /dev/null mount $DEV $MNT touch $MNT/foo chmod 0600 $MNT/foo # On btrfs the file must be NOCOW. chattr +C $MNT/foo &> /dev/null xfs_io -s -c "pwrite -b 1M 0 1M" $MNT/foo mkswap $MNT/foo for ((i = 1; i <= $NUM_CLONES; i++)); do touch $MNT/foo_clone_$i chmod 0600 $MNT/foo_clone_$i # On btrfs the file must be NOCOW. chattr +C $MNT/foo_clone_$i &> /dev/null cp --reflink=always $MNT/foo $MNT/foo_clone_$i done if [ $sync_after_add_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Remove the original file and all clones except the last. rm -f $MNT/foo for ((i = 1; i < $NUM_CLONES; i++)); do rm -f $MNT/foo_clone_$i done if [ $sync_after_remove_reflinks -ne 0 ]; then # Flush delayed refs and commit current transaction. sync -f $MNT fi # Now use the last clone as a swap file. It should work since # its extent are not shared anymore. swapon $MNT/foo_clone_${NUM_CLONES} swapoff $MNT/foo_clone_${NUM_CLONES} umount $MNT } echo -e "\nTest without sync after creating and removing clones" run_test 0 0 echo -e "\nTest with sync after creating clones" run_test 1 0 echo -e "\nTest with sync after removing clones" run_test 0 1 echo -e "\nTest with sync after creating and removing clones" run_test 1 1 Running the test: $ ./test.sh Test without sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0017 sec (556.793 MiB/sec and 556.7929 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=a6b9c29e-5ef4-4689-a8ac-bc199c750f02 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after creating clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0036 sec (271.739 MiB/sec and 271.7391 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=5e9008d6-1f7a-4948-a1b4-3f30aba20a33 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Test with sync after removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0103 sec (96.665 MiB/sec and 96.6651 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=916c2740-fa9f-4385-9f06-29c3f89e4764 Test with sync after creating and removing clones wrote 1048576/1048576 bytes at offset 0 1 MiB, 1 ops; 0.0031 sec (314.268 MiB/sec and 314.2678 ops/sec) Setting up swapspace version 1, size = 1020 KiB (1044480 bytes) no label, UUID=06aab1dd-4d90-49c0-bd9f-3a8db4e2f912 swapon: /mnt/sdi/foo_clone_50: swapon failed: Invalid argument swapoff: /mnt/sdi/foo_clone_50: swapoff failed: Invalid argument Fix this by reworking btrfs_swap_activate() to instead of using extent maps and checking for shared extents with can_nocow_extent(), iterate over the inode's file extent items and use the accurate btrfs_is_data_extent_shared(). CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b2abc0aa5300..b87f19630b00 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9799,15 +9799,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; /* * Acquire the inode's mmap lock to prevent races with memory mapped @@ -9846,6 +9847,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, goto out_unlock_mmap; } + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; + } + /* * Balance or device remove/replace/resize can move stuff around from * under us. The exclop protection makes sure they aren't running/won't @@ -9904,24 +9912,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9933,23 +9956,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); + + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9984,7 +10029,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -10025,20 +10069,16 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - - start += len; } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10053,6 +10093,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, out_unlock_mmap: up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret;

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] x86/fred: Clear WFE in missing-ENDBRANCH #CPs" 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 dc81e556f2a017d681251ace21bf06c126d5a192 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123023-arise-undercook-60f9@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From dc81e556f2a017d681251ace21bf06c126d5a192 Mon Sep 17 00:00:00 2001 From: "Xin Li (Intel)" <xin(a)zytor.com> Date: Wed, 13 Nov 2024 09:59:34 -0800 Subject: [PATCH] x86/fred: Clear WFE in missing-ENDBRANCH #CPs An indirect branch instruction sets the CPU indirect branch tracker (IBT) into WAIT_FOR_ENDBRANCH (WFE) state and WFE stays asserted across the instruction boundary. When the decoder finds an inappropriate instruction while WFE is set ENDBR, the CPU raises a #CP fault. For the "kernel IBT no ENDBR" selftest where #CPs are deliberately triggered, the WFE state of the interrupted context needs to be cleared to let execution continue. Otherwise when the CPU resumes from the instruction that just caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU enters a dead loop. This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't set WFE. But FRED provides space on the entry stack (in an expanded CS area) to save and restore the WFE state, thus the WFE state is no longer clobbered, so software must clear it. Clear WFE to avoid dead looping in ibt_clear_fred_wfe() and the !ibt_fatal code path when execution is allowed to continue. Clobbering WFE in any other circumstance is a security-relevant bug. [ dhansen: changelog rewording ] Fixes: a5f6c2ace997 ("x86/shstk: Add user control-protection fault handler") Signed-off-by: Xin Li (Intel) <xin(a)zytor.com> Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Acked-by: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/all/20241113175934.3897541-1-xin%40zytor.com diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c index d2c732a34e5d..303bf74d175b 100644 --- a/arch/x86/kernel/cet.c +++ b/arch/x86/kernel/cet.c @@ -81,6 +81,34 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code) static __ro_after_init bool ibt_fatal = true; +/* + * By definition, all missing-ENDBRANCH #CPs are a result of WFE && !ENDBR. + * + * For the kernel IBT no ENDBR selftest where #CPs are deliberately triggered, + * the WFE state of the interrupted context needs to be cleared to let execution + * continue. Otherwise when the CPU resumes from the instruction that just + * caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU + * enters a dead loop. + * + * This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't + * set WFE. But FRED provides space on the entry stack (in an expanded CS area) + * to save and restore the WFE state, thus the WFE state is no longer clobbered, + * so software must clear it. + */ +static void ibt_clear_fred_wfe(struct pt_regs *regs) +{ + /* + * No need to do any FRED checks. + * + * For IDT event delivery, the high-order 48 bits of CS are pushed + * as 0s into the stack, and later IRET ignores these bits. + * + * For FRED, a test to check if fred_cs.wfe is set would be dropped + * by compilers. + */ + regs->fred_cs.wfe = 0; +} + static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) { if ((error_code & CP_EC) != CP_ENDBR) { @@ -90,6 +118,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) { regs->ax = 0; + ibt_clear_fred_wfe(regs); return; } @@ -97,6 +126,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (!ibt_fatal) { printk(KERN_DEFAULT CUT_HERE); __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + ibt_clear_fred_wfe(regs); return; } BUG();

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix race with memory mapped writes when activating" 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 0525064bb82e50d59543b62b9d41a606198a4a44 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123011-designed-giving-6a82@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0525064bb82e50d59543b62b9d41a606198a4a44 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Fri, 29 Nov 2024 12:25:30 +0000 Subject: [PATCH] btrfs: fix race with memory mapped writes when activating swap file When activating the swap file we flush all delalloc and wait for ordered extent completion, so that we don't miss any delalloc and extents before we check that the file's extent layout is usable for a swap file and activate the swap file. We are called with the inode's VFS lock acquired, so we won't race with buffered and direct IO writes, however we can still race with memory mapped writes since they don't acquire the inode's VFS lock. The race window is between flushing all delalloc and locking the whole file's extent range, since memory mapped writes lock an extent range with the length of a page. Fix this by acquiring the inode's mmap lock before we flush delalloc. CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6baa0269a85b..b2abc0aa5300 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9809,6 +9809,15 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, u64 isize; u64 start; + /* + * Acquire the inode's mmap lock to prevent races with memory mapped + * writes, as they could happen after we flush delalloc below and before + * we lock the extent range further below. The inode was already locked + * up in the call chain. + */ + btrfs_assert_inode_locked(BTRFS_I(inode)); + down_write(&BTRFS_I(inode)->i_mmap_lock); + /* * If the swap file was just created, make sure delalloc is done. If the * file changes again after this, the user is doing something stupid and @@ -9816,22 +9825,25 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, */ ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1); if (ret) - return ret; + goto out_unlock_mmap; /* * The inode is locked, so these flags won't change after we check them. */ if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) { btrfs_warn(fs_info, "swapfile must not be compressed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { btrfs_warn(fs_info, "swapfile must not be checksummed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* @@ -9846,7 +9858,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) { btrfs_warn(fs_info, "cannot activate swapfile while exclusive operation is running"); - return -EBUSY; + ret = -EBUSY; + goto out_unlock_mmap; } /* @@ -9860,7 +9873,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); btrfs_warn(fs_info, "cannot activate swapfile because snapshot creation is in progress"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* * Snapshots can create extents which require COW even if NODATACOW is @@ -9881,7 +9895,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_warn(fs_info, "cannot activate swapfile because subvolume %llu is being deleted", btrfs_root_id(root)); - return -EPERM; + ret = -EPERM; + goto out_unlock_mmap; } atomic_inc(&root->nr_swapfiles); spin_unlock(&root->root_item_lock); @@ -10036,6 +10051,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); +out_unlock_mmap: + up_write(&BTRFS_I(inode)->i_mmap_lock); if (ret) return ret;

10 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] btrfs: fix race with memory mapped writes when activating" 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 0525064bb82e50d59543b62b9d41a606198a4a44 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024123012-thyself-commodity-0069@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0525064bb82e50d59543b62b9d41a606198a4a44 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Fri, 29 Nov 2024 12:25:30 +0000 Subject: [PATCH] btrfs: fix race with memory mapped writes when activating swap file When activating the swap file we flush all delalloc and wait for ordered extent completion, so that we don't miss any delalloc and extents before we check that the file's extent layout is usable for a swap file and activate the swap file. We are called with the inode's VFS lock acquired, so we won't race with buffered and direct IO writes, however we can still race with memory mapped writes since they don't acquire the inode's VFS lock. The race window is between flushing all delalloc and locking the whole file's extent range, since memory mapped writes lock an extent range with the length of a page. Fix this by acquiring the inode's mmap lock before we flush delalloc. CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6baa0269a85b..b2abc0aa5300 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9809,6 +9809,15 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, u64 isize; u64 start; + /* + * Acquire the inode's mmap lock to prevent races with memory mapped + * writes, as they could happen after we flush delalloc below and before + * we lock the extent range further below. The inode was already locked + * up in the call chain. + */ + btrfs_assert_inode_locked(BTRFS_I(inode)); + down_write(&BTRFS_I(inode)->i_mmap_lock); + /* * If the swap file was just created, make sure delalloc is done. If the * file changes again after this, the user is doing something stupid and @@ -9816,22 +9825,25 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, */ ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1); if (ret) - return ret; + goto out_unlock_mmap; /* * The inode is locked, so these flags won't change after we check them. */ if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) { btrfs_warn(fs_info, "swapfile must not be compressed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { btrfs_warn(fs_info, "swapfile must not be checksummed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* @@ -9846,7 +9858,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) { btrfs_warn(fs_info, "cannot activate swapfile while exclusive operation is running"); - return -EBUSY; + ret = -EBUSY; + goto out_unlock_mmap; } /* @@ -9860,7 +9873,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); btrfs_warn(fs_info, "cannot activate swapfile because snapshot creation is in progress"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* * Snapshots can create extents which require COW even if NODATACOW is @@ -9881,7 +9895,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_warn(fs_info, "cannot activate swapfile because subvolume %llu is being deleted", btrfs_root_id(root)); - return -EPERM; + ret = -EPERM; + goto out_unlock_mmap; } atomic_inc(&root->nr_swapfiles); spin_unlock(&root->root_item_lock); @@ -10036,6 +10051,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); +out_unlock_mmap: + up_write(&BTRFS_I(inode)->i_mmap_lock); if (ret) return ret;

10 months, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror