From: Joerg Roedel <jroedel(a)suse.de>
The trampoline_pgd only maps the 0xfffffff000000000-0xffffffffffffffff
range of kernel memory (with 4-level paging). This range contains the
kernels text+data+bss mappings and the module mapping space, but not the
direct mapping and the vmalloc area.
This is enough to get an application processors out of real-mode, but
for code that switches back to real-mode the trampoline_pgd is missing
important parts of the address space. For example, consider this code
from arch/x86/kernel/reboot.c, function machine_real_restart() for a
64-bit kernel:
#ifdef CONFIG_X86_32
load_cr3(initial_page_table);
#else
write_cr3(real_mode_header->trampoline_pgd);
/* Exiting long mode will fail if CR4.PCIDE is set. */
if (boot_cpu_has(X86_FEATURE_PCID))
cr4_clear_bits(X86_CR4_PCIDE);
#endif
/* Jump to the identity-mapped low memory code */
#ifdef CONFIG_X86_32
asm volatile("jmpl *%0" : :
"rm" (real_mode_header->machine_real_restart_asm),
"a" (type));
#else
asm volatile("ljmpl *%0" : :
"m" (real_mode_header->machine_real_restart_asm),
"D" (type));
#endif
The code switches to the trampoline_pgd, which unmaps the direct mapping
and also the kernel stack. The call to cr4_clear_bits() will find no
stack and crash the machine. The real_mode_header pointer below points
into the direct mapping, and dereferencing it also causes a crash.
The reason this does not crash always is only that kernel mappings are
global and the CR3 switch does not flush those mappings. But if theses
mappings are not in the TLB already, the above code will crash before it
can jump to the real-mode stub.
Extend the trampoline_pgd to contain all kernel mappings to prevent
these crashes and to make code which runs on this page-table more
robust.
Cc: stable(a)vger.kernel.org
Signed-off-by: Joerg Roedel <jroedel(a)suse.de>
---
arch/x86/realmode/init.c | 12 +++++++++++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 31b5856010cb..7a08c96cb42a 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -72,6 +72,7 @@ static void __init setup_real_mode(void)
#ifdef CONFIG_X86_64
u64 *trampoline_pgd;
u64 efer;
+ int i;
#endif
base = (unsigned char *)real_mode_header;
@@ -128,8 +129,17 @@ static void __init setup_real_mode(void)
trampoline_header->flags = 0;
trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
+
+ /*
+ * Map all of kernel memory into the trampoline PGD so that it includes
+ * the direct mapping and vmalloc space. This is needed to keep the
+ * stack and real_mode_header mapped when switching to this page table.
+ */
+ for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++)
+ trampoline_pgd[i] = init_top_pgt[i].pgd;
+
+ /* Map the real mode stub as virtual == physical */
trampoline_pgd[0] = trampoline_pgd_entry.pgd;
- trampoline_pgd[511] = init_top_pgt[511].pgd;
#endif
sme_sev_setup_real_mode(trampoline_header);
--
2.33.0
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 6f93e834fa7c5faa0372e46828b4b2a966ac61d7 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain(a)oracle.com>
Date: Tue, 10 Aug 2021 23:23:44 +0800
Subject: [PATCH] btrfs: fix upper limit for max_inline for page size 64K
The mount option max_inline ranges from 0 to the sectorsize (which is
now equal to page size). But we parse the mount options too early and
before the actual sectorsize is read from the superblock. So the upper
limit of max_inline is unaware of the actual sectorsize and is limited
by the temporary sectorsize 4096, even on a system where the default
sectorsize is 64K.
Fix this by reading the superblock sectorsize before the mount option
parse.
Reported-by: Alexander Tsvetkov <alexander.tsvetkov(a)oracle.com>
CC: stable(a)vger.kernel.org # 5.4+
Signed-off-by: Anand Jain <anand.jain(a)oracle.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2f9515dccce0..355ea88d5c5f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3314,6 +3314,30 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
*/
fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
+ /*
+ * Flag our filesystem as having big metadata blocks if they are bigger
+ * than the page size.
+ */
+ if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
+ if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
+ btrfs_info(fs_info,
+ "flagging fs with big metadata feature");
+ features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
+ }
+
+ /* Set up fs_info before parsing mount options */
+ nodesize = btrfs_super_nodesize(disk_super);
+ sectorsize = btrfs_super_sectorsize(disk_super);
+ stripesize = sectorsize;
+ fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
+ fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
+
+ fs_info->nodesize = nodesize;
+ fs_info->sectorsize = sectorsize;
+ fs_info->sectorsize_bits = ilog2(sectorsize);
+ fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size;
+ fs_info->stripesize = stripesize;
+
ret = btrfs_parse_options(fs_info, options, sb->s_flags);
if (ret) {
err = ret;
@@ -3340,30 +3364,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
btrfs_info(fs_info, "has skinny extents");
- /*
- * flag our filesystem as having big metadata blocks if
- * they are bigger than the page size
- */
- if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
- if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
- btrfs_info(fs_info,
- "flagging fs with big metadata feature");
- features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
- }
-
- nodesize = btrfs_super_nodesize(disk_super);
- sectorsize = btrfs_super_sectorsize(disk_super);
- stripesize = sectorsize;
- fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
- fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
-
- /* Cache block sizes */
- fs_info->nodesize = nodesize;
- fs_info->sectorsize = sectorsize;
- fs_info->sectorsize_bits = ilog2(sectorsize);
- fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size;
- fs_info->stripesize = stripesize;
-
/*
* mixed block groups end up with duplicate but slightly offset
* extent buffers for the same range. It leads to corruptions
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 6f93e834fa7c5faa0372e46828b4b2a966ac61d7 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain(a)oracle.com>
Date: Tue, 10 Aug 2021 23:23:44 +0800
Subject: [PATCH] btrfs: fix upper limit for max_inline for page size 64K
The mount option max_inline ranges from 0 to the sectorsize (which is
now equal to page size). But we parse the mount options too early and
before the actual sectorsize is read from the superblock. So the upper
limit of max_inline is unaware of the actual sectorsize and is limited
by the temporary sectorsize 4096, even on a system where the default
sectorsize is 64K.
Fix this by reading the superblock sectorsize before the mount option
parse.
Reported-by: Alexander Tsvetkov <alexander.tsvetkov(a)oracle.com>
CC: stable(a)vger.kernel.org # 5.4+
Signed-off-by: Anand Jain <anand.jain(a)oracle.com>
Reviewed-by: David Sterba <dsterba(a)suse.com>
Signed-off-by: David Sterba <dsterba(a)suse.com>
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2f9515dccce0..355ea88d5c5f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3314,6 +3314,30 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
*/
fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
+ /*
+ * Flag our filesystem as having big metadata blocks if they are bigger
+ * than the page size.
+ */
+ if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
+ if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
+ btrfs_info(fs_info,
+ "flagging fs with big metadata feature");
+ features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
+ }
+
+ /* Set up fs_info before parsing mount options */
+ nodesize = btrfs_super_nodesize(disk_super);
+ sectorsize = btrfs_super_sectorsize(disk_super);
+ stripesize = sectorsize;
+ fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
+ fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
+
+ fs_info->nodesize = nodesize;
+ fs_info->sectorsize = sectorsize;
+ fs_info->sectorsize_bits = ilog2(sectorsize);
+ fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size;
+ fs_info->stripesize = stripesize;
+
ret = btrfs_parse_options(fs_info, options, sb->s_flags);
if (ret) {
err = ret;
@@ -3340,30 +3364,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
btrfs_info(fs_info, "has skinny extents");
- /*
- * flag our filesystem as having big metadata blocks if
- * they are bigger than the page size
- */
- if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
- if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
- btrfs_info(fs_info,
- "flagging fs with big metadata feature");
- features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
- }
-
- nodesize = btrfs_super_nodesize(disk_super);
- sectorsize = btrfs_super_sectorsize(disk_super);
- stripesize = sectorsize;
- fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
- fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
-
- /* Cache block sizes */
- fs_info->nodesize = nodesize;
- fs_info->sectorsize = sectorsize;
- fs_info->sectorsize_bits = ilog2(sectorsize);
- fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size;
- fs_info->stripesize = stripesize;
-
/*
* mixed block groups end up with duplicate but slightly offset
* extent buffers for the same range. It leads to corruptions
Hi,
please add the following patches to 5.14 queue. All apply cleanly, thanks.
03fe78cc2942c55 btrfs: use delalloc_bytes to determine flush amount for shrink_delalloc
e16460707e94c3d btrfs: wait on async extents when flushing delalloc
93c60b17f2b5fca btrfs: reduce the preemptive flushing threshold to 90%
114623979405abf btrfs: do not do preemptive flushing if the majority is global rsv
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From e16460707e94c3d4c1b5418cb68b28b8efa903b2 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef(a)toxicpanda.com>
Date: Wed, 14 Jul 2021 14:47:21 -0400
Subject: [PATCH] btrfs: wait on async extents when flushing delalloc
I've been debugging an early ENOSPC problem in production and finally
root caused it to this problem. When we switched to the per-inode in
38d715f494f2 ("btrfs: use btrfs_start_delalloc_roots in
shrink_delalloc") I pulled out the async extent handling, because we
were doing the correct thing by calling filemap_flush() if we had async
extents set. This would properly wait on any async extents by locking
the page in the second flush, thus making sure our ordered extents were
properly set up.
However when I switched us back to page based flushing, I used
sync_inode(), which allows us to pass in our own wbc. The problem here
is that sync_inode() is smarter than the filemap_* helpers, it tries to
avoid calling writepages at all. This means that our second call could
skip calling do_writepages altogether, and thus not wait on the pagelock
for the async helpers. This means we could come back before any ordered
extents were created and then simply continue on in our flushing
mechanisms and ENOSPC out when we have plenty of space to use.
Fix this by putting back the async pages logic in shrink_delalloc. This
allows us to bulk write out everything that we need to, and then we can
wait in one place for the async helpers to catch up, and then wait on
any ordered extents that are created.
Fixes: e076ab2a2ca7 ("btrfs: shrink delalloc pages instead of full inodes")
CC: stable(a)vger.kernel.org # 5.10+
Reviewed-by: Nikolay Borisov <nborisov(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/inode.c b/fs/btrfs/inode.c
index 73b6413cc9af..25eb214f56ac 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9879,10 +9879,6 @@ static int start_delalloc_inodes(struct btrfs_root *root,
&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;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index eb90a262563f..d9c8d738678f 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -532,9 +532,49 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
while ((delalloc_bytes || ordered_bytes) && loops < 3) {
u64 temp = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
long nr_pages = min_t(u64, temp, LONG_MAX);
+ int async_pages;
btrfs_start_delalloc_roots(fs_info, nr_pages, true);
+ /*
+ * We need to make sure any outstanding async pages are now
+ * processed before we continue. This is because things like
+ * sync_inode() try to be smart and skip writing if the inode is
+ * marked clean. We don't use filemap_fwrite for flushing
+ * because we want to control how many pages we write out at a
+ * time, thus this is the only safe way to make sure we've
+ * waited for outstanding compressed workers to have started
+ * their jobs and thus have ordered extents set up properly.
+ *
+ * This exists because we do not want to wait for each
+ * individual inode to finish its async work, we simply want to
+ * start the IO on everybody, and then come back here and wait
+ * for all of the async work to catch up. Once we're done with
+ * that we know we'll have ordered extents for everything and we
+ * can decide if we wait for that or not.
+ *
+ * If we choose to replace this in the future, make absolutely
+ * sure that the proper waiting is being done in the async case,
+ * as there have been bugs in that area before.
+ */
+ async_pages = atomic_read(&fs_info->async_delalloc_pages);
+ if (!async_pages)
+ goto skip_async;
+
+ /*
+ * We don't want to wait forever, if we wrote less pages in this
+ * loop than we have outstanding, only wait for that number of
+ * pages, otherwise we can wait for all async pages to finish
+ * before continuing.
+ */
+ if (async_pages > nr_pages)
+ async_pages -= nr_pages;
+ else
+ async_pages = 0;
+ wait_event(fs_info->async_submit_wait,
+ atomic_read(&fs_info->async_delalloc_pages) <=
+ async_pages);
+skip_async:
loops++;
if (wait_ordered && !trans) {
btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
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>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 03fe78cc2942c55cc13be5ca42578750f17204a1 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef(a)toxicpanda.com>
Date: Wed, 14 Jul 2021 14:47:20 -0400
Subject: [PATCH] btrfs: use delalloc_bytes to determine flush amount for
shrink_delalloc
We have been hitting some early ENOSPC issues in production with more
recent kernels, and I tracked it down to us simply not flushing delalloc
as aggressively as we should be. With tracing I was seeing us failing
all tickets with all of the block rsvs at or around 0, with very little
pinned space, but still around 120MiB of outstanding bytes_may_used.
Upon further investigation I saw that we were flushing around 14 pages
per shrink call for delalloc, despite having around 2GiB of delalloc
outstanding.
Consider the example of a 8 way machine, all CPUs trying to create a
file in parallel, which at the time of this commit requires 5 items to
do. Assuming a 16k leaf size, we have 10MiB of total metadata reclaim
size waiting on reservations. Now assume we have 128MiB of delalloc
outstanding. With our current math we would set items to 20, and then
set to_reclaim to 20 * 256k, or 5MiB.
Assuming that we went through this loop all 3 times, for both
FLUSH_DELALLOC and FLUSH_DELALLOC_WAIT, and then did the full loop
twice, we'd only flush 60MiB of the 128MiB delalloc space. This could
leave a fair bit of delalloc reservations still hanging around by the
time we go to ENOSPC out all the remaining tickets.
Fix this two ways. First, change the calculations to be a fraction of
the total delalloc bytes on the system. Prior to this change we were
calculating based on dirty inodes so our math made more sense, now it's
just completely unrelated to what we're actually doing.
Second add a FLUSH_DELALLOC_FULL state, that we hold off until we've
gone through the flush states at least once. This will empty the system
of all delalloc so we're sure to be truly out of space when we start
failing tickets.
I'm tagging stable 5.10 and forward, because this is where we started
using the page stuff heavily again. This affects earlier kernel
versions as well, but would be a pain to backport to them as the
flushing mechanisms aren't the same.
CC: stable(a)vger.kernel.org # 5.10+
Reviewed-by: Nikolay Borisov <nborisov(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/ctree.h b/fs/btrfs/ctree.h
index 3cccf0f05666..fd3084feb4b5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2779,10 +2779,11 @@ enum btrfs_flush_state {
FLUSH_DELAYED_REFS = 4,
FLUSH_DELALLOC = 5,
FLUSH_DELALLOC_WAIT = 6,
- ALLOC_CHUNK = 7,
- ALLOC_CHUNK_FORCE = 8,
- RUN_DELAYED_IPUTS = 9,
- COMMIT_TRANS = 10,
+ FLUSH_DELALLOC_FULL = 7,
+ ALLOC_CHUNK = 8,
+ ALLOC_CHUNK_FORCE = 9,
+ RUN_DELAYED_IPUTS = 10,
+ COMMIT_TRANS = 11,
};
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index fbd492fe87f9..eb90a262563f 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -493,6 +493,11 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
long time_left;
int loops;
+ delalloc_bytes = percpu_counter_sum_positive(&fs_info->delalloc_bytes);
+ ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes);
+ if (delalloc_bytes == 0 && ordered_bytes == 0)
+ return;
+
/* Calc the number of the pages we need flush for space reservation */
if (to_reclaim == U64_MAX) {
items = U64_MAX;
@@ -500,22 +505,21 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
/*
* to_reclaim is set to however much metadata we need to
* reclaim, but reclaiming that much data doesn't really track
- * exactly, so increase the amount to reclaim by 2x in order to
- * make sure we're flushing enough delalloc to hopefully reclaim
- * some metadata reservations.
+ * exactly. What we really want to do is reclaim full inode's
+ * worth of reservations, however that's not available to us
+ * here. We will take a fraction of the delalloc bytes for our
+ * flushing loops and hope for the best. Delalloc will expand
+ * the amount we write to cover an entire dirty extent, which
+ * will reclaim the metadata reservation for that range. If
+ * it's not enough subsequent flush stages will be more
+ * aggressive.
*/
+ to_reclaim = max(to_reclaim, delalloc_bytes >> 3);
items = calc_reclaim_items_nr(fs_info, to_reclaim) * 2;
- to_reclaim = items * EXTENT_SIZE_PER_ITEM;
}
trans = (struct btrfs_trans_handle *)current->journal_info;
- delalloc_bytes = percpu_counter_sum_positive(
- &fs_info->delalloc_bytes);
- ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes);
- if (delalloc_bytes == 0 && ordered_bytes == 0)
- return;
-
/*
* If we are doing more ordered than delalloc we need to just wait on
* ordered extents, otherwise we'll waste time trying to flush delalloc
@@ -595,8 +599,11 @@ static void flush_space(struct btrfs_fs_info *fs_info,
break;
case FLUSH_DELALLOC:
case FLUSH_DELALLOC_WAIT:
+ case FLUSH_DELALLOC_FULL:
+ if (state == FLUSH_DELALLOC_FULL)
+ num_bytes = U64_MAX;
shrink_delalloc(fs_info, space_info, num_bytes,
- state == FLUSH_DELALLOC_WAIT, for_preempt);
+ state != FLUSH_DELALLOC, for_preempt);
break;
case FLUSH_DELAYED_REFS_NR:
case FLUSH_DELAYED_REFS:
@@ -906,6 +913,14 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
commit_cycles--;
}
+ /*
+ * We do not want to empty the system of delalloc unless we're
+ * under heavy pressure, so allow one trip through the flushing
+ * logic before we start doing a FLUSH_DELALLOC_FULL.
+ */
+ if (flush_state == FLUSH_DELALLOC_FULL && !commit_cycles)
+ flush_state++;
+
/*
* We don't want to force a chunk allocation until we've tried
* pretty hard to reclaim space. Think of the case where we
@@ -1069,7 +1084,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
* so if we now have space to allocate do the force chunk allocation.
*/
static const enum btrfs_flush_state data_flush_states[] = {
- FLUSH_DELALLOC_WAIT,
+ FLUSH_DELALLOC_FULL,
RUN_DELAYED_IPUTS,
COMMIT_TRANS,
ALLOC_CHUNK_FORCE,
@@ -1158,6 +1173,7 @@ static const enum btrfs_flush_state evict_flush_states[] = {
FLUSH_DELAYED_REFS,
FLUSH_DELALLOC,
FLUSH_DELALLOC_WAIT,
+ FLUSH_DELALLOC_FULL,
ALLOC_CHUNK,
COMMIT_TRANS,
};
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index c7d19eadecc5..8f58fd95efc7 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -94,6 +94,7 @@ struct btrfs_space_info;
EM( FLUSH_DELAYED_ITEMS, "FLUSH_DELAYED_ITEMS") \
EM( FLUSH_DELALLOC, "FLUSH_DELALLOC") \
EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \
+ EM( FLUSH_DELALLOC_FULL, "FLUSH_DELALLOC_FULL") \
EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \
EM( FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS") \
EM( ALLOC_CHUNK, "ALLOC_CHUNK") \