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

FAILED: patch "[PATCH] ALSA: hda/ca0132 - Fix work handling in delayed HP detection" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 42fb6b1d41eb5905d77c06cad2e87b70289bdb76 Mon Sep 17 00:00:00 2001 From: Takashi Iwai <tiwai(a)suse.de> Date: Fri, 13 Dec 2019 09:51:11 +0100 Subject: [PATCH] ALSA: hda/ca0132 - Fix work handling in delayed HP detection CA0132 has the delayed HP jack detection code that is invoked from the unsol handler, but it does a few weird things: it contains the cancel of a work inside the work handler, and yet it misses the cancel-sync call at (runtime-)suspend. This patch addresses those issues. Fixes: 15c2b3cc09a3 ("ALSA: hda/ca0132 - Fix possible workqueue stall") Cc: <stable(a)vger.kernel.org> Link: https://lore.kernel.org/r/20191213085111.22855-4-tiwai@suse.de Signed-off-by: Takashi Iwai <tiwai(a)suse.de> diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 8d0209fff8f5..32ed46464af7 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -7607,11 +7607,10 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ - cancel_delayed_work(&spec->unsol_hp_work); - schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); tbl = snd_hda_jack_tbl_get(codec, cb->nid); if (tbl) tbl->block_report = 1; + schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); } static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb) @@ -8457,12 +8456,25 @@ static void ca0132_reboot_notify(struct hda_codec *codec) codec->patch_ops.free(codec); } +#ifdef CONFIG_PM +static int ca0132_suspend(struct hda_codec *codec) +{ + struct ca0132_spec *spec = codec->spec; + + cancel_delayed_work_sync(&spec->unsol_hp_work); + return 0; +} +#endif + static const struct hda_codec_ops ca0132_patch_ops = { .build_controls = ca0132_build_controls, .build_pcms = ca0132_build_pcms, .init = ca0132_init, .free = ca0132_free, .unsol_event = snd_hda_jack_unsol_event, +#ifdef CONFIG_PM + .suspend = ca0132_suspend, +#endif .reboot_notify = ca0132_reboot_notify, };

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] ALSA: hda/ca0132 - Fix work handling in delayed HP detection" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 42fb6b1d41eb5905d77c06cad2e87b70289bdb76 Mon Sep 17 00:00:00 2001 From: Takashi Iwai <tiwai(a)suse.de> Date: Fri, 13 Dec 2019 09:51:11 +0100 Subject: [PATCH] ALSA: hda/ca0132 - Fix work handling in delayed HP detection CA0132 has the delayed HP jack detection code that is invoked from the unsol handler, but it does a few weird things: it contains the cancel of a work inside the work handler, and yet it misses the cancel-sync call at (runtime-)suspend. This patch addresses those issues. Fixes: 15c2b3cc09a3 ("ALSA: hda/ca0132 - Fix possible workqueue stall") Cc: <stable(a)vger.kernel.org> Link: https://lore.kernel.org/r/20191213085111.22855-4-tiwai@suse.de Signed-off-by: Takashi Iwai <tiwai(a)suse.de> diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 8d0209fff8f5..32ed46464af7 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -7607,11 +7607,10 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ - cancel_delayed_work(&spec->unsol_hp_work); - schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); tbl = snd_hda_jack_tbl_get(codec, cb->nid); if (tbl) tbl->block_report = 1; + schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); } static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb) @@ -8457,12 +8456,25 @@ static void ca0132_reboot_notify(struct hda_codec *codec) codec->patch_ops.free(codec); } +#ifdef CONFIG_PM +static int ca0132_suspend(struct hda_codec *codec) +{ + struct ca0132_spec *spec = codec->spec; + + cancel_delayed_work_sync(&spec->unsol_hp_work); + return 0; +} +#endif + static const struct hda_codec_ops ca0132_patch_ops = { .build_controls = ca0132_build_controls, .build_pcms = ca0132_build_pcms, .init = ca0132_init, .free = ca0132_free, .unsol_event = snd_hda_jack_unsol_event, +#ifdef CONFIG_PM + .suspend = ca0132_suspend, +#endif .reboot_notify = ca0132_reboot_notify, };

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] ALSA: hda/ca0132 - Fix work handling in delayed HP detection" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 42fb6b1d41eb5905d77c06cad2e87b70289bdb76 Mon Sep 17 00:00:00 2001 From: Takashi Iwai <tiwai(a)suse.de> Date: Fri, 13 Dec 2019 09:51:11 +0100 Subject: [PATCH] ALSA: hda/ca0132 - Fix work handling in delayed HP detection CA0132 has the delayed HP jack detection code that is invoked from the unsol handler, but it does a few weird things: it contains the cancel of a work inside the work handler, and yet it misses the cancel-sync call at (runtime-)suspend. This patch addresses those issues. Fixes: 15c2b3cc09a3 ("ALSA: hda/ca0132 - Fix possible workqueue stall") Cc: <stable(a)vger.kernel.org> Link: https://lore.kernel.org/r/20191213085111.22855-4-tiwai@suse.de Signed-off-by: Takashi Iwai <tiwai(a)suse.de> diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 8d0209fff8f5..32ed46464af7 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -7607,11 +7607,10 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ - cancel_delayed_work(&spec->unsol_hp_work); - schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); tbl = snd_hda_jack_tbl_get(codec, cb->nid); if (tbl) tbl->block_report = 1; + schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); } static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb) @@ -8457,12 +8456,25 @@ static void ca0132_reboot_notify(struct hda_codec *codec) codec->patch_ops.free(codec); } +#ifdef CONFIG_PM +static int ca0132_suspend(struct hda_codec *codec) +{ + struct ca0132_spec *spec = codec->spec; + + cancel_delayed_work_sync(&spec->unsol_hp_work); + return 0; +} +#endif + static const struct hda_codec_ops ca0132_patch_ops = { .build_controls = ca0132_build_controls, .build_pcms = ca0132_build_pcms, .init = ca0132_init, .free = ca0132_free, .unsol_event = snd_hda_jack_unsol_event, +#ifdef CONFIG_PM + .suspend = ca0132_suspend, +#endif .reboot_notify = ca0132_reboot_notify, };

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix removal logic of the tree mod log that leads to" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 6609fee8897ac475378388238456c84298bff802 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Fri, 6 Dec 2019 12:27:39 +0000 Subject: [PATCH] Btrfs: fix removal logic of the tree mod log that leads to use-after-free issues When a tree mod log user no longer needs to use the tree it calls btrfs_put_tree_mod_seq() to remove itself from the list of users and delete all no longer used elements of the tree's red black tree, which should be all elements with a sequence number less then our equals to the caller's sequence number. However the logic is broken because it can delete and free elements from the red black tree that have a sequence number greater then the caller's sequence number: 1) At a point in time we have sequence numbers 1, 2, 3 and 4 in the tree mod log; 2) The task which got assigned the sequence number 1 calls btrfs_put_tree_mod_seq(); 3) Sequence number 1 is deleted from the list of sequence numbers; 4) The current minimum sequence number is computed to be the sequence number 2; 5) A task using sequence number 2 is at tree_mod_log_rewind() and gets a pointer to one of its elements from the red black tree through a call to tree_mod_log_search(); 6) The task with sequence number 1 iterates the red black tree of tree modification elements and deletes (and frees) all elements with a sequence number less then or equals to 2 (the computed minimum sequence number) - it ends up only leaving elements with sequence numbers of 3 and 4; 7) The task with sequence number 2 now uses the pointer to its element, already freed by the other task, at __tree_mod_log_rewind(), resulting in a use-after-free issue. When CONFIG_DEBUG_PAGEALLOC=y it produces a trace like the following: [16804.546854] general protection fault: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI [16804.547451] CPU: 0 PID: 28257 Comm: pool Tainted: G W 5.4.0-rc8-btrfs-next-51 #1 [16804.548059] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014 [16804.548666] RIP: 0010:rb_next+0x16/0x50 (...) [16804.550581] RSP: 0018:ffffb948418ef9b0 EFLAGS: 00010202 [16804.551227] RAX: 6b6b6b6b6b6b6b6b RBX: ffff90e0247f6600 RCX: 6b6b6b6b6b6b6b6b [16804.551873] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff90e0247f6600 [16804.552504] RBP: ffff90dffe0d4688 R08: 0000000000000001 R09: 0000000000000000 [16804.553136] R10: ffff90dffa4a0040 R11: 0000000000000000 R12: 000000000000002e [16804.553768] R13: ffff90e0247f6600 R14: 0000000000001663 R15: ffff90dff77862b8 [16804.554399] FS: 00007f4b197ae700(0000) GS:ffff90e036a00000(0000) knlGS:0000000000000000 [16804.555039] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [16804.555683] CR2: 00007f4b10022000 CR3: 00000002060e2004 CR4: 00000000003606f0 [16804.556336] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [16804.556968] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [16804.557583] Call Trace: [16804.558207] __tree_mod_log_rewind+0xbf/0x280 [btrfs] [16804.558835] btrfs_search_old_slot+0x105/0xd00 [btrfs] [16804.559468] resolve_indirect_refs+0x1eb/0xc70 [btrfs] [16804.560087] ? free_extent_buffer.part.19+0x5a/0xc0 [btrfs] [16804.560700] find_parent_nodes+0x388/0x1120 [btrfs] [16804.561310] btrfs_check_shared+0x115/0x1c0 [btrfs] [16804.561916] ? extent_fiemap+0x59d/0x6d0 [btrfs] [16804.562518] extent_fiemap+0x59d/0x6d0 [btrfs] [16804.563112] ? __might_fault+0x11/0x90 [16804.563706] do_vfs_ioctl+0x45a/0x700 [16804.564299] ksys_ioctl+0x70/0x80 [16804.564885] ? trace_hardirqs_off_thunk+0x1a/0x20 [16804.565461] __x64_sys_ioctl+0x16/0x20 [16804.566020] do_syscall_64+0x5c/0x250 [16804.566580] entry_SYSCALL_64_after_hwframe+0x49/0xbe [16804.567153] RIP: 0033:0x7f4b1ba2add7 (...) [16804.568907] RSP: 002b:00007f4b197adc88 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [16804.569513] RAX: ffffffffffffffda RBX: 00007f4b100210d8 RCX: 00007f4b1ba2add7 [16804.570133] RDX: 00007f4b100210d8 RSI: 00000000c020660b RDI: 0000000000000003 [16804.570726] RBP: 000055de05a6cfe0 R08: 0000000000000000 R09: 00007f4b197add44 [16804.571314] R10: 0000000000000000 R11: 0000000000000246 R12: 00007f4b197add48 [16804.571905] R13: 00007f4b197add40 R14: 00007f4b100210d0 R15: 00007f4b197add50 (...) [16804.575623] ---[ end trace 87317359aad4ba50 ]--- Fix this by making btrfs_put_tree_mod_seq() skip deletion of elements that have a sequence number equals to the computed minimum sequence number, and not just elements with a sequence number greater then that minimum. Fixes: bd989ba359f2ac ("Btrfs: add tree modification log functions") CC: stable(a)vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5b6e86aaf2e1..24658b5a5787 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -379,7 +379,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, for (node = rb_first(tm_root); node; node = next) { next = rb_next(node); tm = rb_entry(node, struct tree_mod_elem, node); - if (tm->seq > min_seq) + if (tm->seq >= min_seq) continue; rb_erase(node, tm_root); kfree(tm);

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: skip log replay on orphaned roots" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 9bc574de590510eff899c3ca8dbaf013566b5efe Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Fri, 6 Dec 2019 09:37:17 -0500 Subject: [PATCH] btrfs: skip log replay on orphaned roots My fsstress modifications coupled with generic/475 uncovered a failure to mount and replay the log if we hit a orphaned root. We do not want to replay the log for an orphan root, but it's completely legitimate to have an orphaned root with a log attached. Fix this by simply skipping replaying the log. We still need to pin it's root node so that we do not overwrite it while replaying other logs, as we re-read the log root at every stage of the replay. CC: stable(a)vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 79866f1b33d6..d3f115909ff0 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6317,9 +6317,28 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key); if (IS_ERR(wc.replay_dest)) { ret = PTR_ERR(wc.replay_dest); + + /* + * We didn't find the subvol, likely because it was + * deleted. This is ok, simply skip this log and go to + * the next one. + * + * We need to exclude the root because we can't have + * other log replays overwriting this log as we'll read + * it back in a few more times. This will keep our + * block from being modified, and we'll just bail for + * each subsequent pass. + */ + if (ret == -ENOENT) + ret = btrfs_pin_extent_for_log_replay(fs_info, + log->node->start, + log->node->len); free_extent_buffer(log->node); free_extent_buffer(log->commit_root); kfree(log); + + if (!ret) + goto next; btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root for tree log recovery."); goto error; @@ -6351,7 +6370,6 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) &root->highest_objectid); } - key.offset = found_key.offset - 1; wc.replay_dest->log_root = NULL; free_extent_buffer(log->node); free_extent_buffer(log->commit_root); @@ -6359,9 +6377,10 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) if (ret) goto error; - +next: if (found_key.offset == 0) break; + key.offset = found_key.offset - 1; } btrfs_release_path(path);

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: abort transaction after failed inode updates in" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From c7e54b5102bf3614cadb9ca32d7be73bad6cecf0 Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Fri, 6 Dec 2019 09:37:15 -0500 Subject: [PATCH] btrfs: abort transaction after failed inode updates in create_subvol We can just abort the transaction here, and in fact do that for every other failure in this function except these two cases. CC: stable(a)vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: Johannes Thumshirn <jthumshirn(a)suse.de> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3418decb9e61..18e328ce4b54 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -704,11 +704,17 @@ static noinline int create_subvol(struct inode *dir, btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2); ret = btrfs_update_inode(trans, root, dir); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid, btrfs_ino(BTRFS_I(dir)), index, name, namelen); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_uuid_tree_add(trans, root_item->uuid, BTRFS_UUID_KEY_SUBVOL, objectid);

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: abort transaction after failed inode updates in" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From c7e54b5102bf3614cadb9ca32d7be73bad6cecf0 Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Fri, 6 Dec 2019 09:37:15 -0500 Subject: [PATCH] btrfs: abort transaction after failed inode updates in create_subvol We can just abort the transaction here, and in fact do that for every other failure in this function except these two cases. CC: stable(a)vger.kernel.org # 4.4+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: Johannes Thumshirn <jthumshirn(a)suse.de> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3418decb9e61..18e328ce4b54 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -704,11 +704,17 @@ static noinline int create_subvol(struct inode *dir, btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2); ret = btrfs_update_inode(trans, root, dir); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid, btrfs_ino(BTRFS_I(dir)), index, name, namelen); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto fail; + } ret = btrfs_uuid_tree_add(trans, root_item->uuid, BTRFS_UUID_KEY_SUBVOL, objectid);

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix missing data checksums after replaying a log tree" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 40e046acbd2f369cfbf93c3413639c66514cec2d Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Thu, 5 Dec 2019 16:58:30 +0000 Subject: [PATCH] Btrfs: fix missing data checksums after replaying a log tree When logging a file that has shared extents (reflinked with other files or with itself), we can end up logging multiple checksum items that cover overlapping ranges. This confuses the search for checksums at log replay time causing some checksums to never be added to the fs/subvolume tree. Consider the following example of a file that shares the same extent at offsets 0 and 256Kb: [ bytenr 13893632, offset 64Kb, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 13893632, offset 0, len 256Kb ] 256Kb 512Kb When logging the inode, at tree-log.c:copy_items(), when processing the file extent item at offset 0, we log a checksum item covering the range 13959168 to 14024704, which corresponds to 13893632 + 64Kb and 13893632 + 64Kb + 64Kb, respectively. Later when processing the extent item at offset 256K, we log the checksums for the range from 13893632 to 14155776 (which corresponds to 13893632 + 256Kb). These checksums get merged with the checksum item for the range from 13631488 to 13893632 (13631488 + 256Kb), logged by a previous fsync. So after this we get the two following checksum items in the log tree: (...) item 6 key (EXTENT_CSUM EXTENT_CSUM 13631488) itemoff 3095 itemsize 512 range start 13631488 end 14155776 length 524288 item 7 key (EXTENT_CSUM EXTENT_CSUM 13959168) itemoff 3031 itemsize 64 range start 13959168 end 14024704 length 65536 The first one covers the range from the second one, they overlap. So far this does not cause a problem after replaying the log, because when replaying the file extent item for offset 256K, we copy all the checksums for the extent 13893632 from the log tree to the fs/subvolume tree, since searching for an checksum item for bytenr 13893632 leaves us at the first checksum item, which covers the whole range of the extent. However if we write 64Kb to file offset 256Kb for example, we will not be able to find and copy the checksums for the last 128Kb of the extent at bytenr 13893632, referenced by the file range 384Kb to 512Kb. After writing 64Kb into file offset 256Kb we get the following extent layout for our file: [ bytenr 13893632, offset 64K, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 14155776, offset 0, len 64Kb ] 256Kb 320Kb [ bytenr 13893632, offset 64Kb, len 192Kb ] 320Kb 512Kb After fsync'ing the file, if we have a power failure and then mount the filesystem to replay the log, the following happens: 1) When replaying the file extent item for file offset 320Kb, we lookup for the checksums for the extent range from 13959168 (13893632 + 64Kb) to 14155776 (13893632 + 256Kb), through a call to btrfs_lookup_csums_range(); 2) btrfs_lookup_csums_range() finds the checksum item that starts precisely at offset 13959168 (item 7 in the log tree, shown before); 3) However that checksum item only covers 64Kb of data, and not 192Kb of data; 4) As a result only the checksums for the first 64Kb of data referenced by the file extent item are found and copied to the fs/subvolume tree. The remaining 128Kb of data, file range 384Kb to 512Kb, doesn't get the corresponding data checksums found and copied to the fs/subvolume tree. 5) After replaying the log userspace will not be able to read the file range from 384Kb to 512Kb, because the checksums are missing and resulting in an -EIO error. The following steps reproduce this scenario: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt/sdc $ xfs_io -f -c "pwrite -S 0xa3 0 256K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xc7 256K 256K" /mnt/sdc/foobar $ xfs_io -c "reflink /mnt/sdc/foobar 320K 0 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xe5 256K 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar <power failure> $ mount /dev/sdc /mnt/sdc $ md5sum /mnt/sdc/foobar md5sum: /mnt/sdc/foobar: Input/output error $ dmesg | tail [165305.003464] BTRFS info (device sdc): no csum found for inode 257 start 401408 [165305.004014] BTRFS info (device sdc): no csum found for inode 257 start 405504 [165305.004559] BTRFS info (device sdc): no csum found for inode 257 start 409600 [165305.005101] BTRFS info (device sdc): no csum found for inode 257 start 413696 [165305.005627] BTRFS info (device sdc): no csum found for inode 257 start 417792 [165305.006134] BTRFS info (device sdc): no csum found for inode 257 start 421888 [165305.006625] BTRFS info (device sdc): no csum found for inode 257 start 425984 [165305.007278] BTRFS info (device sdc): no csum found for inode 257 start 430080 [165305.008248] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 [165305.009550] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 Fix this simply by deleting first any checksums, from the log tree, for the range of the extent we are logging at copy_items(). This ensures we do not get checksum items in the log tree that have overlapping ranges. This is a long time issue that has been present since we have the clone (and deduplication) ioctl, and can happen both when an extent is shared between different files and within the same file. A test case for fstests follows soon. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b2e8fd8a8e59..54efb21c2727 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2787,7 +2787,7 @@ struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( /* file-item.c */ struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len); + struct btrfs_root *root, u64 bytenr, u64 len); blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst); blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 18df434bfe52..274318e9114e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1869,8 +1869,8 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, btrfs_pin_extent(fs_info, head->bytenr, head->num_bytes, 1); if (head->is_data) { - ret = btrfs_del_csums(trans, fs_info, head->bytenr, - head->num_bytes); + ret = btrfs_del_csums(trans, fs_info->csum_root, + head->bytenr, head->num_bytes); } } @@ -3175,7 +3175,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_release_path(path); if (is_data) { - ret = btrfs_del_csums(trans, info, bytenr, num_bytes); + ret = btrfs_del_csums(trans, info->csum_root, bytenr, + num_bytes); if (ret) { btrfs_abort_transaction(trans, ret); goto out; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 3270a40b0777..b1bfdc5c1387 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -590,9 +590,9 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, * range of bytes. */ int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len) + struct btrfs_root *root, u64 bytenr, u64 len) { - struct btrfs_root *root = fs_info->csum_root; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *path; struct btrfs_key key; u64 end_byte = bytenr + len; @@ -602,6 +602,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int blocksize_bits = fs_info->sb->s_blocksize_bits; + ASSERT(root == fs_info->csum_root || + root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); + path = btrfs_alloc_path(); if (!path) return -ENOMEM; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 6f757361db53..79866f1b33d6 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -808,7 +808,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_del_csums(trans, fs_info, + ret = btrfs_del_csums(trans, + fs_info->csum_root, sums->bytenr, sums->len); if (!ret) @@ -3909,6 +3910,28 @@ static int log_inode_item(struct btrfs_trans_handle *trans, return 0; } +static int log_csums(struct btrfs_trans_handle *trans, + struct btrfs_root *log_root, + struct btrfs_ordered_sum *sums) +{ + int ret; + + /* + * Due to extent cloning, we might have logged a csum item that covers a + * subrange of a cloned extent, and later we can end up logging a csum + * item for a larger subrange of the same extent or the entire range. + * This would leave csum items in the log tree that cover the same range + * and break the searches for checksums in the log tree, resulting in + * some checksums missing in the fs/subvolume tree. So just delete (or + * trim and adjust) any existing csum items in the log for this range. + */ + ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len); + if (ret) + return ret; + + return btrfs_csum_file_blocks(trans, log_root, sums); +} + static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *dst_path, @@ -4054,7 +4077,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log, sums); + ret = log_csums(trans, log, sums); list_del(&sums->list); kfree(sums); } @@ -4274,7 +4297,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log_root, sums); + ret = log_csums(trans, log_root, sums); list_del(&sums->list); kfree(sums); }

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix missing data checksums after replaying a log tree" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 40e046acbd2f369cfbf93c3413639c66514cec2d Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Thu, 5 Dec 2019 16:58:30 +0000 Subject: [PATCH] Btrfs: fix missing data checksums after replaying a log tree When logging a file that has shared extents (reflinked with other files or with itself), we can end up logging multiple checksum items that cover overlapping ranges. This confuses the search for checksums at log replay time causing some checksums to never be added to the fs/subvolume tree. Consider the following example of a file that shares the same extent at offsets 0 and 256Kb: [ bytenr 13893632, offset 64Kb, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 13893632, offset 0, len 256Kb ] 256Kb 512Kb When logging the inode, at tree-log.c:copy_items(), when processing the file extent item at offset 0, we log a checksum item covering the range 13959168 to 14024704, which corresponds to 13893632 + 64Kb and 13893632 + 64Kb + 64Kb, respectively. Later when processing the extent item at offset 256K, we log the checksums for the range from 13893632 to 14155776 (which corresponds to 13893632 + 256Kb). These checksums get merged with the checksum item for the range from 13631488 to 13893632 (13631488 + 256Kb), logged by a previous fsync. So after this we get the two following checksum items in the log tree: (...) item 6 key (EXTENT_CSUM EXTENT_CSUM 13631488) itemoff 3095 itemsize 512 range start 13631488 end 14155776 length 524288 item 7 key (EXTENT_CSUM EXTENT_CSUM 13959168) itemoff 3031 itemsize 64 range start 13959168 end 14024704 length 65536 The first one covers the range from the second one, they overlap. So far this does not cause a problem after replaying the log, because when replaying the file extent item for offset 256K, we copy all the checksums for the extent 13893632 from the log tree to the fs/subvolume tree, since searching for an checksum item for bytenr 13893632 leaves us at the first checksum item, which covers the whole range of the extent. However if we write 64Kb to file offset 256Kb for example, we will not be able to find and copy the checksums for the last 128Kb of the extent at bytenr 13893632, referenced by the file range 384Kb to 512Kb. After writing 64Kb into file offset 256Kb we get the following extent layout for our file: [ bytenr 13893632, offset 64K, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 14155776, offset 0, len 64Kb ] 256Kb 320Kb [ bytenr 13893632, offset 64Kb, len 192Kb ] 320Kb 512Kb After fsync'ing the file, if we have a power failure and then mount the filesystem to replay the log, the following happens: 1) When replaying the file extent item for file offset 320Kb, we lookup for the checksums for the extent range from 13959168 (13893632 + 64Kb) to 14155776 (13893632 + 256Kb), through a call to btrfs_lookup_csums_range(); 2) btrfs_lookup_csums_range() finds the checksum item that starts precisely at offset 13959168 (item 7 in the log tree, shown before); 3) However that checksum item only covers 64Kb of data, and not 192Kb of data; 4) As a result only the checksums for the first 64Kb of data referenced by the file extent item are found and copied to the fs/subvolume tree. The remaining 128Kb of data, file range 384Kb to 512Kb, doesn't get the corresponding data checksums found and copied to the fs/subvolume tree. 5) After replaying the log userspace will not be able to read the file range from 384Kb to 512Kb, because the checksums are missing and resulting in an -EIO error. The following steps reproduce this scenario: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt/sdc $ xfs_io -f -c "pwrite -S 0xa3 0 256K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xc7 256K 256K" /mnt/sdc/foobar $ xfs_io -c "reflink /mnt/sdc/foobar 320K 0 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xe5 256K 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar <power failure> $ mount /dev/sdc /mnt/sdc $ md5sum /mnt/sdc/foobar md5sum: /mnt/sdc/foobar: Input/output error $ dmesg | tail [165305.003464] BTRFS info (device sdc): no csum found for inode 257 start 401408 [165305.004014] BTRFS info (device sdc): no csum found for inode 257 start 405504 [165305.004559] BTRFS info (device sdc): no csum found for inode 257 start 409600 [165305.005101] BTRFS info (device sdc): no csum found for inode 257 start 413696 [165305.005627] BTRFS info (device sdc): no csum found for inode 257 start 417792 [165305.006134] BTRFS info (device sdc): no csum found for inode 257 start 421888 [165305.006625] BTRFS info (device sdc): no csum found for inode 257 start 425984 [165305.007278] BTRFS info (device sdc): no csum found for inode 257 start 430080 [165305.008248] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 [165305.009550] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 Fix this simply by deleting first any checksums, from the log tree, for the range of the extent we are logging at copy_items(). This ensures we do not get checksum items in the log tree that have overlapping ranges. This is a long time issue that has been present since we have the clone (and deduplication) ioctl, and can happen both when an extent is shared between different files and within the same file. A test case for fstests follows soon. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b2e8fd8a8e59..54efb21c2727 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2787,7 +2787,7 @@ struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( /* file-item.c */ struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len); + struct btrfs_root *root, u64 bytenr, u64 len); blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst); blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 18df434bfe52..274318e9114e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1869,8 +1869,8 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, btrfs_pin_extent(fs_info, head->bytenr, head->num_bytes, 1); if (head->is_data) { - ret = btrfs_del_csums(trans, fs_info, head->bytenr, - head->num_bytes); + ret = btrfs_del_csums(trans, fs_info->csum_root, + head->bytenr, head->num_bytes); } } @@ -3175,7 +3175,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_release_path(path); if (is_data) { - ret = btrfs_del_csums(trans, info, bytenr, num_bytes); + ret = btrfs_del_csums(trans, info->csum_root, bytenr, + num_bytes); if (ret) { btrfs_abort_transaction(trans, ret); goto out; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 3270a40b0777..b1bfdc5c1387 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -590,9 +590,9 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, * range of bytes. */ int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len) + struct btrfs_root *root, u64 bytenr, u64 len) { - struct btrfs_root *root = fs_info->csum_root; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *path; struct btrfs_key key; u64 end_byte = bytenr + len; @@ -602,6 +602,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int blocksize_bits = fs_info->sb->s_blocksize_bits; + ASSERT(root == fs_info->csum_root || + root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); + path = btrfs_alloc_path(); if (!path) return -ENOMEM; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 6f757361db53..79866f1b33d6 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -808,7 +808,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_del_csums(trans, fs_info, + ret = btrfs_del_csums(trans, + fs_info->csum_root, sums->bytenr, sums->len); if (!ret) @@ -3909,6 +3910,28 @@ static int log_inode_item(struct btrfs_trans_handle *trans, return 0; } +static int log_csums(struct btrfs_trans_handle *trans, + struct btrfs_root *log_root, + struct btrfs_ordered_sum *sums) +{ + int ret; + + /* + * Due to extent cloning, we might have logged a csum item that covers a + * subrange of a cloned extent, and later we can end up logging a csum + * item for a larger subrange of the same extent or the entire range. + * This would leave csum items in the log tree that cover the same range + * and break the searches for checksums in the log tree, resulting in + * some checksums missing in the fs/subvolume tree. So just delete (or + * trim and adjust) any existing csum items in the log for this range. + */ + ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len); + if (ret) + return ret; + + return btrfs_csum_file_blocks(trans, log_root, sums); +} + static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *dst_path, @@ -4054,7 +4077,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log, sums); + ret = log_csums(trans, log, sums); list_del(&sums->list); kfree(sums); } @@ -4274,7 +4297,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log_root, sums); + ret = log_csums(trans, log_root, sums); list_del(&sums->list); kfree(sums); }

5 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] Btrfs: fix missing data checksums after replaying a log tree" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 40e046acbd2f369cfbf93c3413639c66514cec2d Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Thu, 5 Dec 2019 16:58:30 +0000 Subject: [PATCH] Btrfs: fix missing data checksums after replaying a log tree When logging a file that has shared extents (reflinked with other files or with itself), we can end up logging multiple checksum items that cover overlapping ranges. This confuses the search for checksums at log replay time causing some checksums to never be added to the fs/subvolume tree. Consider the following example of a file that shares the same extent at offsets 0 and 256Kb: [ bytenr 13893632, offset 64Kb, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 13893632, offset 0, len 256Kb ] 256Kb 512Kb When logging the inode, at tree-log.c:copy_items(), when processing the file extent item at offset 0, we log a checksum item covering the range 13959168 to 14024704, which corresponds to 13893632 + 64Kb and 13893632 + 64Kb + 64Kb, respectively. Later when processing the extent item at offset 256K, we log the checksums for the range from 13893632 to 14155776 (which corresponds to 13893632 + 256Kb). These checksums get merged with the checksum item for the range from 13631488 to 13893632 (13631488 + 256Kb), logged by a previous fsync. So after this we get the two following checksum items in the log tree: (...) item 6 key (EXTENT_CSUM EXTENT_CSUM 13631488) itemoff 3095 itemsize 512 range start 13631488 end 14155776 length 524288 item 7 key (EXTENT_CSUM EXTENT_CSUM 13959168) itemoff 3031 itemsize 64 range start 13959168 end 14024704 length 65536 The first one covers the range from the second one, they overlap. So far this does not cause a problem after replaying the log, because when replaying the file extent item for offset 256K, we copy all the checksums for the extent 13893632 from the log tree to the fs/subvolume tree, since searching for an checksum item for bytenr 13893632 leaves us at the first checksum item, which covers the whole range of the extent. However if we write 64Kb to file offset 256Kb for example, we will not be able to find and copy the checksums for the last 128Kb of the extent at bytenr 13893632, referenced by the file range 384Kb to 512Kb. After writing 64Kb into file offset 256Kb we get the following extent layout for our file: [ bytenr 13893632, offset 64K, len 64Kb ] 0 64Kb [ bytenr 13631488, offset 64Kb, len 192Kb ] 64Kb 256Kb [ bytenr 14155776, offset 0, len 64Kb ] 256Kb 320Kb [ bytenr 13893632, offset 64Kb, len 192Kb ] 320Kb 512Kb After fsync'ing the file, if we have a power failure and then mount the filesystem to replay the log, the following happens: 1) When replaying the file extent item for file offset 320Kb, we lookup for the checksums for the extent range from 13959168 (13893632 + 64Kb) to 14155776 (13893632 + 256Kb), through a call to btrfs_lookup_csums_range(); 2) btrfs_lookup_csums_range() finds the checksum item that starts precisely at offset 13959168 (item 7 in the log tree, shown before); 3) However that checksum item only covers 64Kb of data, and not 192Kb of data; 4) As a result only the checksums for the first 64Kb of data referenced by the file extent item are found and copied to the fs/subvolume tree. The remaining 128Kb of data, file range 384Kb to 512Kb, doesn't get the corresponding data checksums found and copied to the fs/subvolume tree. 5) After replaying the log userspace will not be able to read the file range from 384Kb to 512Kb, because the checksums are missing and resulting in an -EIO error. The following steps reproduce this scenario: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt/sdc $ xfs_io -f -c "pwrite -S 0xa3 0 256K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xc7 256K 256K" /mnt/sdc/foobar $ xfs_io -c "reflink /mnt/sdc/foobar 320K 0 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar $ xfs_io -c "pwrite -S 0xe5 256K 64K" /mnt/sdc/foobar $ xfs_io -c "fsync" /mnt/sdc/foobar <power failure> $ mount /dev/sdc /mnt/sdc $ md5sum /mnt/sdc/foobar md5sum: /mnt/sdc/foobar: Input/output error $ dmesg | tail [165305.003464] BTRFS info (device sdc): no csum found for inode 257 start 401408 [165305.004014] BTRFS info (device sdc): no csum found for inode 257 start 405504 [165305.004559] BTRFS info (device sdc): no csum found for inode 257 start 409600 [165305.005101] BTRFS info (device sdc): no csum found for inode 257 start 413696 [165305.005627] BTRFS info (device sdc): no csum found for inode 257 start 417792 [165305.006134] BTRFS info (device sdc): no csum found for inode 257 start 421888 [165305.006625] BTRFS info (device sdc): no csum found for inode 257 start 425984 [165305.007278] BTRFS info (device sdc): no csum found for inode 257 start 430080 [165305.008248] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 [165305.009550] BTRFS warning (device sdc): csum failed root 5 ino 257 off 393216 csum 0x1337385e expected csum 0x00000000 mirror 1 Fix this simply by deleting first any checksums, from the log tree, for the range of the extent we are logging at copy_items(). This ensures we do not get checksum items in the log tree that have overlapping ranges. This is a long time issue that has been present since we have the clone (and deduplication) ioctl, and can happen both when an extent is shared between different files and within the same file. A test case for fstests follows soon. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b2e8fd8a8e59..54efb21c2727 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2787,7 +2787,7 @@ struct btrfs_inode_extref *btrfs_find_name_in_ext_backref( /* file-item.c */ struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len); + struct btrfs_root *root, u64 bytenr, u64 len); blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst); blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 18df434bfe52..274318e9114e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1869,8 +1869,8 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, btrfs_pin_extent(fs_info, head->bytenr, head->num_bytes, 1); if (head->is_data) { - ret = btrfs_del_csums(trans, fs_info, head->bytenr, - head->num_bytes); + ret = btrfs_del_csums(trans, fs_info->csum_root, + head->bytenr, head->num_bytes); } } @@ -3175,7 +3175,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_release_path(path); if (is_data) { - ret = btrfs_del_csums(trans, info, bytenr, num_bytes); + ret = btrfs_del_csums(trans, info->csum_root, bytenr, + num_bytes); if (ret) { btrfs_abort_transaction(trans, ret); goto out; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 3270a40b0777..b1bfdc5c1387 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -590,9 +590,9 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, * range of bytes. */ int btrfs_del_csums(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, u64 len) + struct btrfs_root *root, u64 bytenr, u64 len) { - struct btrfs_root *root = fs_info->csum_root; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_path *path; struct btrfs_key key; u64 end_byte = bytenr + len; @@ -602,6 +602,9 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); int blocksize_bits = fs_info->sb->s_blocksize_bits; + ASSERT(root == fs_info->csum_root || + root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID); + path = btrfs_alloc_path(); if (!path) return -ENOMEM; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 6f757361db53..79866f1b33d6 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -808,7 +808,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_del_csums(trans, fs_info, + ret = btrfs_del_csums(trans, + fs_info->csum_root, sums->bytenr, sums->len); if (!ret) @@ -3909,6 +3910,28 @@ static int log_inode_item(struct btrfs_trans_handle *trans, return 0; } +static int log_csums(struct btrfs_trans_handle *trans, + struct btrfs_root *log_root, + struct btrfs_ordered_sum *sums) +{ + int ret; + + /* + * Due to extent cloning, we might have logged a csum item that covers a + * subrange of a cloned extent, and later we can end up logging a csum + * item for a larger subrange of the same extent or the entire range. + * This would leave csum items in the log tree that cover the same range + * and break the searches for checksums in the log tree, resulting in + * some checksums missing in the fs/subvolume tree. So just delete (or + * trim and adjust) any existing csum items in the log for this range. + */ + ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len); + if (ret) + return ret; + + return btrfs_csum_file_blocks(trans, log_root, sums); +} + static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_path *dst_path, @@ -4054,7 +4077,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log, sums); + ret = log_csums(trans, log, sums); list_del(&sums->list); kfree(sums); } @@ -4274,7 +4297,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans, struct btrfs_ordered_sum, list); if (!ret) - ret = btrfs_csum_file_blocks(trans, log_root, sums); + ret = log_csums(trans, log_root, sums); list_del(&sums->list); kfree(sums); }

5 years, 10 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror