diff options
author | graysky | 2021-01-15 07:44:09 -0500 |
---|---|---|
committer | graysky | 2021-01-15 07:44:09 -0500 |
commit | b11349b019bde81c4e0f4578d07d92923350d751 (patch) | |
tree | 7102ef5ac5a4d9dd9328ab0b71b5bb1f8266ac29 | |
parent | 77ba5aba0d4817b913588e21efb8f4fa2f27cc4b (diff) | |
download | aur-b11349b019bde81c4e0f4578d07d92923350d751.tar.gz |
Update to 5.10.8rc1-1
-rw-r--r-- | .SRCINFO | 18 | ||||
-rw-r--r-- | 0004-btrfs-fix-deadlock-when-cloning-inline-extent-and-lo.patch | 325 | ||||
-rw-r--r-- | 0005-btrfs-shrink-delalloc-pages-instead-of-full-inodes.patch | 184 | ||||
-rw-r--r-- | PKGBUILD | 19 |
4 files changed, 14 insertions, 532 deletions
@@ -1,5 +1,5 @@ pkgbase = linux-rc - pkgver = 5.10.7rc2 + pkgver = 5.10.8rc1 pkgrel = 1 url = https://www.kernel.org/ arch = x86_64 @@ -12,28 +12,24 @@ pkgbase = linux-rc makedepends = tar makedepends = xz options = !strip - source = https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.7-rc2.xz - source = https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.7-rc2.sign - source = https://www.kernel.org/pub/linux/kernel/v5.x/linux-5.10.6.tar.xz - source = https://www.kernel.org/pub/linux/kernel/v5.x/linux-5.10.6.tar.sign + source = https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.8-rc1.xz + source = https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.8-rc1.sign + source = https://www.kernel.org/pub/linux/kernel/v5.x/linux-5.10.7.tar.xz + source = https://www.kernel.org/pub/linux/kernel/v5.x/linux-5.10.7.tar.sign source = config source = 0001-ZEN-Add-sysctl-and-CONFIG-to-disallow-unprivileged-C.patch source = 0002-HID-quirks-Add-Apple-Magic-Trackpad-2-to-hid_have_sp.patch source = 0003-iwlwifi-Fix-regression-from-UDP-segmentation-support.patch - source = 0004-btrfs-fix-deadlock-when-cloning-inline-extent-and-lo.patch - source = 0005-btrfs-shrink-delalloc-pages-instead-of-full-inodes.patch validpgpkeys = ABAF11C65A2970B130ABE3C479BE3E4300411886 validpgpkeys = 647F28654894E3BD457199BE38DBBDC86092693E - b2sums = 22df6754e677527bf1fa41609b69223491e57dc3166fff72a8d3e610b89fced23101d51ad781c16d7f283ce2d46f2dfc560c1c726afc029c39aef29eb417d21f + b2sums = ac3fdff334b8716617ada28b8681d218b1cf6d2eb9cb6c86248e5b2e75fecd6bc46d3a87f6d1e1b463241ce0d8f56648845db5dc43bcd7b603a1864f20a29397 b2sums = SKIP - b2sums = 2da9e47f6524ecb50db9f515b9f281f08fbcb323f6e4ddb225c2b2f6379787c37efee25589e49286e13ff663c414a422b680912739400afab89f0ebaf741d33b + b2sums = c3a222cf56350a3778bd825ba8434d27266412ffe921429be189d51fa97ec66b6aaf336bfd67c20d44828e4b150afade9659b341e9c499f63d6dc01fc2a4fb03 b2sums = SKIP b2sums = cb3a58e4eef8395b75887d94a84bba25f05fbec8f576a791623057a190a1d51b412a19ecf1b600ac3f9f6c46968eb0e130d571743e61afc231a97146ee4b52d0 b2sums = b42730a806a63dbf905f448a3282dec72a950ef7d16a3531d977dcae3b5c2685a5c5dd10a58e345d57084a6212353dc2f2f0102021d13c1557092e564f81eaf5 b2sums = a5dea5bb6df6fb517009ad5b104c2ea8e93ed880393a1412ca2d7fc8047abccc9c72076e40d1d4133cadc9048040846cc9bdc91e30c4d601ad5963d13498503e b2sums = 9a8723104239ba4646dd0c76c5a60128892954dd2faee69ca5c5d1251c9694de8fd528ca063a2add1401ad1375ad0dcc2560ca03a1bfd03b161d34ccd25b686a - b2sums = e0da90b08fb03658dca9c42ac287c04d9b35969a15165c0f1fc7e11290de272b892abb58f5c7aabe22899f53f5bc39539f58768b8012d92145ba2fd8b89898a7 - b2sums = 2b180269f934469d6ef6f0f8474dd947c7a8e9344cf3bbecac6a9c325d7bfb89d234eb15c4422709acaffd30ebeda2ec06c91a8c1128631a839186e8b273eb65 pkgname = linux-rc pkgdesc = The release candidate kernel and modules diff --git a/0004-btrfs-fix-deadlock-when-cloning-inline-extent-and-lo.patch b/0004-btrfs-fix-deadlock-when-cloning-inline-extent-and-lo.patch deleted file mode 100644 index 97ea363cf296..000000000000 --- a/0004-btrfs-fix-deadlock-when-cloning-inline-extent-and-lo.patch +++ /dev/null @@ -1,325 +0,0 @@ -From e763d7a19f256a8861ee2c1eedaaf42f603488d2 Mon Sep 17 00:00:00 2001 -From: Filipe Manana <fdmanana@suse.com> -Date: Wed, 2 Dec 2020 11:55:58 +0000 -Subject: [PATCH 4/6] btrfs: fix deadlock when cloning inline extent and low on - free metadata space - -When cloning an inline extent there are cases where we can not just copy -the inline extent from the source range to the target range (e.g. when the -target range starts at an offset greater than zero). In such cases we copy -the inline extent's data into a page of the destination inode and then -dirty that page. However, after that we will need to start a transaction -for each processed extent and, if we are ever low on available metadata -space, we may need to flush existing delalloc for all dirty inodes in an -attempt to release metadata space - if that happens we may deadlock: - -* the async reclaim task queued a delalloc work to flush delalloc for - the destination inode of the clone operation; - -* the task executing that delalloc work gets blocked waiting for the - range with the dirty page to be unlocked, which is currently locked - by the task doing the clone operation; - -* the async reclaim task blocks waiting for the delalloc work to complete; - -* the cloning task is waiting on the waitqueue of its reservation ticket - while holding the range with the dirty page locked in the inode's - io_tree; - -* if metadata space is not released by some other task (like delalloc for - some other inode completing for example), the clone task waits forever - and as a consequence the delalloc work and async reclaim tasks will hang - forever as well. Releasing more space on the other hand may require - starting a transaction, which will hang as well when trying to reserve - metadata space, resulting in a deadlock between all these tasks. - -When this happens, traces like the following show up in dmesg/syslog: - - [87452.323003] INFO: task kworker/u16:11:1810830 blocked for more than 120 seconds. - [87452.323644] Tainted: G B W 5.10.0-rc4-btrfs-next-73 #1 - [87452.324248] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. - [87452.324852] task:kworker/u16:11 state:D stack: 0 pid:1810830 ppid: 2 flags:0x00004000 - [87452.325520] Workqueue: btrfs-flush_delalloc btrfs_work_helper [btrfs] - [87452.326136] Call Trace: - [87452.326737] __schedule+0x5d1/0xcf0 - [87452.327390] schedule+0x45/0xe0 - [87452.328174] lock_extent_bits+0x1e6/0x2d0 [btrfs] - [87452.328894] ? finish_wait+0x90/0x90 - [87452.329474] btrfs_invalidatepage+0x32c/0x390 [btrfs] - [87452.330133] ? __mod_memcg_state+0x8e/0x160 - [87452.330738] __extent_writepage+0x2d4/0x400 [btrfs] - [87452.331405] extent_write_cache_pages+0x2b2/0x500 [btrfs] - [87452.332007] ? lock_release+0x20e/0x4c0 - [87452.332557] ? trace_hardirqs_on+0x1b/0xf0 - [87452.333127] extent_writepages+0x43/0x90 [btrfs] - [87452.333653] ? lock_acquire+0x1a3/0x490 - [87452.334177] do_writepages+0x43/0xe0 - [87452.334699] ? __filemap_fdatawrite_range+0xa4/0x100 - [87452.335720] __filemap_fdatawrite_range+0xc5/0x100 - [87452.336500] btrfs_run_delalloc_work+0x17/0x40 [btrfs] - [87452.337216] btrfs_work_helper+0xf1/0x600 [btrfs] - [87452.337838] process_one_work+0x24e/0x5e0 - [87452.338437] worker_thread+0x50/0x3b0 - [87452.339137] ? process_one_work+0x5e0/0x5e0 - [87452.339884] kthread+0x153/0x170 - [87452.340507] ? kthread_mod_delayed_work+0xc0/0xc0 - [87452.341153] ret_from_fork+0x22/0x30 - [87452.341806] INFO: task kworker/u16:1:2426217 blocked for more than 120 seconds. - [87452.342487] Tainted: G B W 5.10.0-rc4-btrfs-next-73 #1 - [87452.343274] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. - [87452.344049] task:kworker/u16:1 state:D stack: 0 pid:2426217 ppid: 2 flags:0x00004000 - [87452.344974] Workqueue: events_unbound btrfs_async_reclaim_metadata_space [btrfs] - [87452.345655] Call Trace: - [87452.346305] __schedule+0x5d1/0xcf0 - [87452.346947] ? kvm_clock_read+0x14/0x30 - [87452.347676] ? wait_for_completion+0x81/0x110 - [87452.348389] schedule+0x45/0xe0 - [87452.349077] schedule_timeout+0x30c/0x580 - [87452.349718] ? _raw_spin_unlock_irqrestore+0x3c/0x60 - [87452.350340] ? lock_acquire+0x1a3/0x490 - [87452.351006] ? try_to_wake_up+0x7a/0xa20 - [87452.351541] ? lock_release+0x20e/0x4c0 - [87452.352040] ? lock_acquired+0x199/0x490 - [87452.352517] ? wait_for_completion+0x81/0x110 - [87452.353000] wait_for_completion+0xab/0x110 - [87452.353490] start_delalloc_inodes+0x2af/0x390 [btrfs] - [87452.353973] btrfs_start_delalloc_roots+0x12d/0x250 [btrfs] - [87452.354455] flush_space+0x24f/0x660 [btrfs] - [87452.355063] btrfs_async_reclaim_metadata_space+0x1bb/0x480 [btrfs] - [87452.355565] process_one_work+0x24e/0x5e0 - [87452.356024] worker_thread+0x20f/0x3b0 - [87452.356487] ? process_one_work+0x5e0/0x5e0 - [87452.356973] kthread+0x153/0x170 - [87452.357434] ? kthread_mod_delayed_work+0xc0/0xc0 - [87452.357880] ret_from_fork+0x22/0x30 - (...) - < stack traces of several tasks waiting for the locks of the inodes of the - clone operation > - (...) - [92867.444138] RSP: 002b:00007ffc3371bbe8 EFLAGS: 00000246 ORIG_RAX: 0000000000000052 - [92867.444624] RAX: ffffffffffffffda RBX: 00007ffc3371bea0 RCX: 00007f61efe73f97 - [92867.445116] RDX: 0000000000000000 RSI: 0000560fbd5d7a40 RDI: 0000560fbd5d8960 - [92867.445595] RBP: 00007ffc3371beb0 R08: 0000000000000001 R09: 0000000000000003 - [92867.446070] R10: 00007ffc3371b996 R11: 0000000000000246 R12: 0000000000000000 - [92867.446820] R13: 000000000000001f R14: 00007ffc3371bea0 R15: 00007ffc3371beb0 - [92867.447361] task:fsstress state:D stack: 0 pid:2508238 ppid:2508153 flags:0x00004000 - [92867.447920] Call Trace: - [92867.448435] __schedule+0x5d1/0xcf0 - [92867.448934] ? _raw_spin_unlock_irqrestore+0x3c/0x60 - [92867.449423] schedule+0x45/0xe0 - [92867.449916] __reserve_bytes+0x4a4/0xb10 [btrfs] - [92867.450576] ? finish_wait+0x90/0x90 - [92867.451202] btrfs_reserve_metadata_bytes+0x29/0x190 [btrfs] - [92867.451815] btrfs_block_rsv_add+0x1f/0x50 [btrfs] - [92867.452412] start_transaction+0x2d1/0x760 [btrfs] - [92867.453216] clone_copy_inline_extent+0x333/0x490 [btrfs] - [92867.453848] ? lock_release+0x20e/0x4c0 - [92867.454539] ? btrfs_search_slot+0x9a7/0xc30 [btrfs] - [92867.455218] btrfs_clone+0x569/0x7e0 [btrfs] - [92867.455952] btrfs_clone_files+0xf6/0x150 [btrfs] - [92867.456588] btrfs_remap_file_range+0x324/0x3d0 [btrfs] - [92867.457213] do_clone_file_range+0xd4/0x1f0 - [92867.457828] vfs_clone_file_range+0x4d/0x230 - [92867.458355] ? lock_release+0x20e/0x4c0 - [92867.458890] ioctl_file_clone+0x8f/0xc0 - [92867.459377] do_vfs_ioctl+0x342/0x750 - [92867.459913] __x64_sys_ioctl+0x62/0xb0 - [92867.460377] do_syscall_64+0x33/0x80 - [92867.460842] entry_SYSCALL_64_after_hwframe+0x44/0xa9 - (...) - < stack traces of more tasks blocked on metadata reservation like the clone - task above, because the async reclaim task has deadlocked > - (...) - -Another thing to notice is that the worker task that is deadlocked when -trying to flush the destination inode of the clone operation is at -btrfs_invalidatepage(). This is simply because the clone operation has a -destination offset greater than the i_size and we only update the i_size -of the destination file after cloning an extent (just like we do in the -buffered write path). - -Since the async reclaim path uses btrfs_start_delalloc_roots() to trigger -the flushing of delalloc for all inodes that have delalloc, add a runtime -flag to an inode to signal it should not be flushed, and for inodes with -that flag set, start_delalloc_inodes() will simply skip them. When the -cloning code needs to dirty a page to copy an inline extent, set that flag -on the inode and then clear it when the clone operation finishes. - -This could be sporadically triggered with test case generic/269 from -fstests, which exercises many fsstress processes running in parallel with -several dd processes filling up the entire filesystem. - -CC: stable@vger.kernel.org # 5.9+ -Fixes: 05a5a7621ce6 ("Btrfs: implement full reflink support for inline extents") -Reviewed-by: Josef Bacik <josef@toxicpanda.com> -Signed-off-by: Filipe Manana <fdmanana@suse.com> -Reviewed-by: David Sterba <dsterba@suse.com> -Signed-off-by: David Sterba <dsterba@suse.com> ---- - fs/btrfs/btrfs_inode.h | 9 +++++++++ - fs/btrfs/ctree.h | 3 ++- - fs/btrfs/dev-replace.c | 2 +- - fs/btrfs/inode.c | 15 +++++++++++---- - fs/btrfs/ioctl.c | 2 +- - fs/btrfs/reflink.c | 15 +++++++++++++++ - fs/btrfs/space-info.c | 2 +- - 7 files changed, 40 insertions(+), 8 deletions(-) - -diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h -index 92dd86bceae3..7e86ab4841dd 100644 ---- a/fs/btrfs/btrfs_inode.h -+++ b/fs/btrfs/btrfs_inode.h -@@ -35,6 +35,15 @@ enum { - BTRFS_INODE_IN_DELALLOC_LIST, - BTRFS_INODE_HAS_PROPS, - BTRFS_INODE_SNAPSHOT_FLUSH, -+ /* -+ * Set when we are in a context where we need to start a transaction and -+ * have dirty pages with the respective file range locked. This is to -+ * ensure that when reserving space for the transaction, if we are low -+ * on available space and need to flush delalloc, we will not flush -+ * delalloc for this inode, because that could result in a deadlock (on -+ * the file range, inode's io_tree). -+ */ -+ BTRFS_INODE_NO_DELALLOC_FLUSH, - }; - - /* in memory btrfs inode */ -diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h -index 62461239600f..e01545538e07 100644 ---- a/fs/btrfs/ctree.h -+++ b/fs/btrfs/ctree.h -@@ -3001,7 +3001,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, - u32 min_type); - - int btrfs_start_delalloc_snapshot(struct btrfs_root *root); --int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr); -+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, -+ bool in_reclaim_context); - int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, - unsigned int extra_bits, - struct extent_state **cached_state); -diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c -index 10638537b9ef..d29780463182 100644 ---- a/fs/btrfs/dev-replace.c -+++ b/fs/btrfs/dev-replace.c -@@ -703,7 +703,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, - * flush all outstanding I/O and inode extent mappings before the - * copy operation is declared as being finished - */ -- ret = btrfs_start_delalloc_roots(fs_info, U64_MAX); -+ ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false); - if (ret) { - mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); - return ret; -diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c -index 7e8d8169779d..07479250221d 100644 ---- a/fs/btrfs/inode.c -+++ b/fs/btrfs/inode.c -@@ -9389,7 +9389,8 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode - * some fairly slow code that needs optimization. This walks the list - * of all the inodes with pending delalloc and forces them to disk. - */ --static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot) -+static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot, -+ bool in_reclaim_context) - { - struct btrfs_inode *binode; - struct inode *inode; -@@ -9410,6 +9411,11 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot - - list_move_tail(&binode->delalloc_inodes, - &root->delalloc_inodes); -+ -+ if (in_reclaim_context && -+ test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags)) -+ continue; -+ - inode = igrab(&binode->vfs_inode); - if (!inode) { - cond_resched_lock(&root->delalloc_lock); -@@ -9463,10 +9469,11 @@ int btrfs_start_delalloc_snapshot(struct btrfs_root *root) - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) - return -EROFS; - -- return start_delalloc_inodes(root, &nr, true); -+ return start_delalloc_inodes(root, &nr, true, false); - } - --int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) -+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, -+ bool in_reclaim_context) - { - struct btrfs_root *root; - struct list_head splice; -@@ -9489,7 +9496,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr) - &fs_info->delalloc_roots); - spin_unlock(&fs_info->delalloc_root_lock); - -- ret = start_delalloc_inodes(root, &nr, false); -+ ret = start_delalloc_inodes(root, &nr, false, in_reclaim_context); - btrfs_put_root(root); - if (ret < 0) - goto out; -diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c -index e8ca229a216b..bd46e107f955 100644 ---- a/fs/btrfs/ioctl.c -+++ b/fs/btrfs/ioctl.c -@@ -4940,7 +4940,7 @@ long btrfs_ioctl(struct file *file, unsigned int - case BTRFS_IOC_SYNC: { - int ret; - -- ret = btrfs_start_delalloc_roots(fs_info, U64_MAX); -+ ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false); - if (ret) - return ret; - ret = btrfs_sync_fs(inode->i_sb, 1); -diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c -index 99aa87c08912..a646af95dd10 100644 ---- a/fs/btrfs/reflink.c -+++ b/fs/btrfs/reflink.c -@@ -89,6 +89,19 @@ static int copy_inline_to_page(struct btrfs_inode *inode, - if (ret) - goto out_unlock; - -+ /* -+ * After dirtying the page our caller will need to start a transaction, -+ * and if we are low on metadata free space, that can cause flushing of -+ * delalloc for all inodes in order to get metadata space released. -+ * However we are holding the range locked for the whole duration of -+ * the clone/dedupe operation, so we may deadlock if that happens and no -+ * other task releases enough space. So mark this inode as not being -+ * possible to flush to avoid such deadlock. We will clear that flag -+ * when we finish cloning all extents, since a transaction is started -+ * after finding each extent to clone. -+ */ -+ set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags); -+ - if (comp_type == BTRFS_COMPRESS_NONE) { - char *map; - -@@ -547,6 +560,8 @@ static int btrfs_clone(struct inode *src, struct inode *inode, - out: - btrfs_free_path(path); - kvfree(buf); -+ clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags); -+ - return ret; - } - -diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c -index 64099565ab8f..67e55c5479b8 100644 ---- a/fs/btrfs/space-info.c -+++ b/fs/btrfs/space-info.c -@@ -532,7 +532,7 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, - - loops = 0; - while ((delalloc_bytes || dio_bytes) && loops < 3) { -- btrfs_start_delalloc_roots(fs_info, items); -+ btrfs_start_delalloc_roots(fs_info, items, true); - - loops++; - if (wait_ordered && !trans) { --- -2.30.0 - diff --git a/0005-btrfs-shrink-delalloc-pages-instead-of-full-inodes.patch b/0005-btrfs-shrink-delalloc-pages-instead-of-full-inodes.patch deleted file mode 100644 index e06f23cc27ed..000000000000 --- a/0005-btrfs-shrink-delalloc-pages-instead-of-full-inodes.patch +++ /dev/null @@ -1,184 +0,0 @@ -From 0397aa4e6205543d9b3da11794037e94f8735867 Mon Sep 17 00:00:00 2001 -From: Josef Bacik <josef@toxicpanda.com> -Date: Mon, 4 Jan 2021 15:24:11 -0500 -Subject: [PATCH 5/6] btrfs: shrink delalloc pages instead of full inodes -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -Commit 38d715f494f2 ("btrfs: use btrfs_start_delalloc_roots in -shrink_delalloc") cleaned up how we do delalloc shrinking by utilizing -some infrastructure we have in place to flush inodes that we use for -device replace and snapshot. However this introduced a pretty serious -performance regression. The root cause is because before we would -generally use the normal writeback path to reclaim delalloc space, and -for this we would provide it with the number of pages we wanted to -flush. The referenced commit changed this to flush that many inodes, -which drastically increased the amount of space we were flushing in -certain cases, which severely affected performance. - -We cannot revert this patch unfortunately, because Filipe has another -fix that requires the ability to skip flushing inodes that are being -cloned in certain scenarios, which means we need to keep using our -flushing infrastructure or risk re-introducing the deadlock. - -Instead to fix this problem we can go back to providing -btrfs_start_delalloc_roots with a number of pages to flush, and then set -up a writeback_control and utilize sync_inode() to handle the flushing -for us. This gives us the same behavior we had prior to the fix, while -still allowing us to avoid the deadlock that was fixed by Filipe. The -user reported reproducer was a simple untarring of a large tarball of -the source code for Firefox. The results are as follows - -5.9 0m54.258s -5.10 1m26.212s -Patch 0m38.800s - -We are significantly faster because of the work I did around improving -ENOSPC flushing in 5.10 and 5.11, so reverting to the previous write out -behavior gave us a pretty big boost. - -CC: stable@vger.kernel.org # 5.10 -Reported-by: René Rebe <rene@exactcode.de> -Fixes: 38d715f494f2 ("btrfs: use btrfs_start_delalloc_roots in shrink_delalloc") -Signed-off-by: Josef Bacik <josef@toxicpanda.com> ---- - fs/btrfs/inode.c | 60 +++++++++++++++++++++++++++++++------------ - fs/btrfs/space-info.c | 4 ++- - 2 files changed, 46 insertions(+), 18 deletions(-) - -diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c -index 07479250221d..acc47e2ffb46 100644 ---- a/fs/btrfs/inode.c -+++ b/fs/btrfs/inode.c -@@ -9389,7 +9389,8 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode - * some fairly slow code that needs optimization. This walks the list - * of all the inodes with pending delalloc and forces them to disk. - */ --static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot, -+static int start_delalloc_inodes(struct btrfs_root *root, -+ struct writeback_control *wbc, bool snapshot, - bool in_reclaim_context) - { - struct btrfs_inode *binode; -@@ -9398,6 +9399,7 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot - struct list_head works; - struct list_head splice; - int ret = 0; -+ bool full_flush = wbc->nr_to_write == LONG_MAX; - - INIT_LIST_HEAD(&works); - INIT_LIST_HEAD(&splice); -@@ -9426,18 +9428,24 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot - if (snapshot) - set_bit(BTRFS_INODE_SNAPSHOT_FLUSH, - &binode->runtime_flags); -- work = btrfs_alloc_delalloc_work(inode); -- if (!work) { -- iput(inode); -- ret = -ENOMEM; -- goto out; -- } -- list_add_tail(&work->list, &works); -- btrfs_queue_work(root->fs_info->flush_workers, -- &work->work); -- if (*nr != U64_MAX) { -- (*nr)--; -- if (*nr == 0) -+ if (full_flush) { -+ work = btrfs_alloc_delalloc_work(inode); -+ if (!work) { -+ iput(inode); -+ ret = -ENOMEM; -+ goto out; -+ } -+ list_add_tail(&work->list, &works); -+ btrfs_queue_work(root->fs_info->flush_workers, -+ &work->work); -+ } else { -+ ret = sync_inode(inode, wbc); -+ if (!ret && -+ test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, -+ &BTRFS_I(inode)->runtime_flags)) -+ ret = sync_inode(inode, wbc); -+ btrfs_add_delayed_iput(inode); -+ if (ret || wbc->nr_to_write <= 0) - goto out; - } - cond_resched(); -@@ -9463,18 +9471,29 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot - - int btrfs_start_delalloc_snapshot(struct btrfs_root *root) - { -+ struct writeback_control wbc = { -+ .nr_to_write = LONG_MAX, -+ .sync_mode = WB_SYNC_NONE, -+ .range_start = 0, -+ .range_end = LLONG_MAX, -+ }; - struct btrfs_fs_info *fs_info = root->fs_info; -- u64 nr = U64_MAX; - - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) - return -EROFS; - -- return start_delalloc_inodes(root, &nr, true, false); -+ return start_delalloc_inodes(root, &wbc, true, false); - } - - int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, - bool in_reclaim_context) - { -+ struct writeback_control wbc = { -+ .nr_to_write = (nr == U64_MAX) ? LONG_MAX : (unsigned long)nr, -+ .sync_mode = WB_SYNC_NONE, -+ .range_start = 0, -+ .range_end = LLONG_MAX, -+ }; - struct btrfs_root *root; - struct list_head splice; - int ret; -@@ -9488,6 +9507,13 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, - spin_lock(&fs_info->delalloc_root_lock); - list_splice_init(&fs_info->delalloc_roots, &splice); - while (!list_empty(&splice) && nr) { -+ /* -+ * Reset nr_to_write here so we know that we're doing a full -+ * flush. -+ */ -+ if (nr == U64_MAX) -+ wbc.nr_to_write = LONG_MAX; -+ - root = list_first_entry(&splice, struct btrfs_root, - delalloc_root); - root = btrfs_grab_root(root); -@@ -9496,9 +9522,9 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, - &fs_info->delalloc_roots); - spin_unlock(&fs_info->delalloc_root_lock); - -- ret = start_delalloc_inodes(root, &nr, false, in_reclaim_context); -+ ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context); - btrfs_put_root(root); -- if (ret < 0) -+ if (ret < 0 || wbc.nr_to_write <= 0) - goto out; - spin_lock(&fs_info->delalloc_root_lock); - } -diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c -index 67e55c5479b8..e8347461c8dd 100644 ---- a/fs/btrfs/space-info.c -+++ b/fs/btrfs/space-info.c -@@ -532,7 +532,9 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info, - - loops = 0; - while ((delalloc_bytes || dio_bytes) && loops < 3) { -- btrfs_start_delalloc_roots(fs_info, items, true); -+ u64 nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT; -+ -+ btrfs_start_delalloc_roots(fs_info, nr_pages, true); - - loops++; - if (wait_ordered && !trans) { --- -2.30.0 - @@ -7,12 +7,12 @@ _srcname=linux-5.10 _major=5.10 ### on initial release this is null otherwise it is the current stable subversion ### ie 1,2,3 corresponding $_major.1, $_major.3 etc -_minor=6 +_minor=7 _minorc=$((_minor+1)) ### on initial release this is just $_major _fullver=$_major.$_minor #_fullver=$_major -_rcver=2 +_rcver=1 _rcpatch=patch-${_major}.${_minorc}-rc${_rcver} pkgver=${_major}.${_minorc}rc${_rcver} arch=(x86_64) @@ -30,26 +30,21 @@ source=( https://www.kernel.org/pub/linux/kernel/v5.x/linux-$_fullver.tar.{xz,sign} config # the main kernel config file 0001-ZEN-Add-sysctl-and-CONFIG-to-disallow-unprivileged-C.patch -0002-HID-quirks-Add-Apple-Magic-Trackpad-2-to-hid_have_sp.patch -0003-iwlwifi-Fix-regression-from-UDP-segmentation-support.patch -0004-btrfs-fix-deadlock-when-cloning-inline-extent-and-lo.patch -0005-btrfs-shrink-delalloc-pages-instead-of-full-inodes.patch - + 0002-HID-quirks-Add-Apple-Magic-Trackpad-2-to-hid_have_sp.patch + 0003-iwlwifi-Fix-regression-from-UDP-segmentation-support.patch ) validpgpkeys=( 'ABAF11C65A2970B130ABE3C479BE3E4300411886' # Linus Torvalds '647F28654894E3BD457199BE38DBBDC86092693E' # Greg Kroah-Hartman ) -b2sums=('22df6754e677527bf1fa41609b69223491e57dc3166fff72a8d3e610b89fced23101d51ad781c16d7f283ce2d46f2dfc560c1c726afc029c39aef29eb417d21f' +b2sums=('ac3fdff334b8716617ada28b8681d218b1cf6d2eb9cb6c86248e5b2e75fecd6bc46d3a87f6d1e1b463241ce0d8f56648845db5dc43bcd7b603a1864f20a29397' 'SKIP' - '2da9e47f6524ecb50db9f515b9f281f08fbcb323f6e4ddb225c2b2f6379787c37efee25589e49286e13ff663c414a422b680912739400afab89f0ebaf741d33b' + 'c3a222cf56350a3778bd825ba8434d27266412ffe921429be189d51fa97ec66b6aaf336bfd67c20d44828e4b150afade9659b341e9c499f63d6dc01fc2a4fb03' 'SKIP' 'cb3a58e4eef8395b75887d94a84bba25f05fbec8f576a791623057a190a1d51b412a19ecf1b600ac3f9f6c46968eb0e130d571743e61afc231a97146ee4b52d0' 'b42730a806a63dbf905f448a3282dec72a950ef7d16a3531d977dcae3b5c2685a5c5dd10a58e345d57084a6212353dc2f2f0102021d13c1557092e564f81eaf5' 'a5dea5bb6df6fb517009ad5b104c2ea8e93ed880393a1412ca2d7fc8047abccc9c72076e40d1d4133cadc9048040846cc9bdc91e30c4d601ad5963d13498503e' - '9a8723104239ba4646dd0c76c5a60128892954dd2faee69ca5c5d1251c9694de8fd528ca063a2add1401ad1375ad0dcc2560ca03a1bfd03b161d34ccd25b686a' - 'e0da90b08fb03658dca9c42ac287c04d9b35969a15165c0f1fc7e11290de272b892abb58f5c7aabe22899f53f5bc39539f58768b8012d92145ba2fd8b89898a7' - '2b180269f934469d6ef6f0f8474dd947c7a8e9344cf3bbecac6a9c325d7bfb89d234eb15c4422709acaffd30ebeda2ec06c91a8c1128631a839186e8b273eb65') + '9a8723104239ba4646dd0c76c5a60128892954dd2faee69ca5c5d1251c9694de8fd528ca063a2add1401ad1375ad0dcc2560ca03a1bfd03b161d34ccd25b686a') export KBUILD_BUILD_HOST=archlinux |