[PATCH] btrfs: zoned: wait extent buffer IOs before finishing a zone

[PATCH] btrfs: zoned: wait extent buffer IOs before finishing a zone

[Naohiro Aota]

Before sending REQ_OP_ZONE_FINISH to a zone, we need to ensure that ongoing
IOs already finished. Or, we will see a "Zone Is Full" error for the IOs,
as the ZONE_FINISH command makes the zone full.

We ensure that with btrfs_wait_block_group_reservations() and
btrfs_wait_ordered_roots() for a data block group. And, for a metadata
block group, the comparison of alloc_offset vs meta_write_pointer mostly
ensures IOs for the allocated region already sent. However, there still can
be a little time-frame where the IOs are sent but not yet completed.

Introduce wait_eb_writebacks() to ensure such IOs are completed for a
metadata block group. It walks the buffer_radix to find extent buffers in
the block group and wait_on_extent_buffer_writeback() on them.

Fixes: afba2bc036b0 ("btrfs: zoned: implement active zone tracking")
CC: stable@vger.kernel.org # 5.19+
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
---
 fs/btrfs/zoned.c | 40 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index e12c0ca509fb..c8315fe16214 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1921,10 +1921,44 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 	return ret;
 }
 
+static void wait_eb_writebacks(struct btrfs_block_group *block_group)
+{
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+	const u64 end = block_group->start + block_group->length;
+	struct radix_tree_iter iter;
+	struct extent_buffer *eb;
+	void **slot;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter,
+				 block_group->start >> fs_info->sectorsize_bits) {
+		eb = radix_tree_deref_slot(slot);
+		if (!eb)
+			continue;
+		if (radix_tree_deref_retry(eb)) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
+
+		if (eb->start < block_group->start)
+			continue;
+		if (eb->start >= end)
+			break;
+
+		slot = radix_tree_iter_resume(slot, &iter);
+		rcu_read_unlock();
+		wait_on_extent_buffer_writeback(eb);
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+}
+
 static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct map_lookup *map;
+	const bool is_metadata = block_group->flags &
+		(BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM);
 	int ret = 0;
 	int i;
 
@@ -1935,8 +1969,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	}
 
 	/* Check if we have unwritten allocated space */
-	if ((block_group->flags &
-	     (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) &&
+	if (is_metadata &&
 	    block_group->start + block_group->alloc_offset > block_group->meta_write_pointer) {
 		spin_unlock(&block_group->lock);
 		return -EAGAIN;
@@ -1961,6 +1994,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 		/* No need to wait for NOCOW writers. Zoned mode does not allow that */
 		btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start,
 					 block_group->length);
+		/* Wait for extent buffers to be written. */
+		if (is_metadata)
+			wait_eb_writebacks(block_group);
 
 		spin_lock(&block_group->lock);
 
-- 
2.37.3

Re: [PATCH] btrfs: zoned: wait extent buffer IOs before finishing a zone

[kernel test robot]

Hi Naohiro,

I love your patch! Perhaps something to improve:

[auto build test WARNING on kdave/for-next]
[also build test WARNING on linus/master v6.0-rc4 next-20220907]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Naohiro-Aota/btrfs-zoned-wait-extent-buffer-IOs-before-finishing-a-zone/20220907-224702
base:   https://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git for-next
config: s390-randconfig-s041-20220907 (https://download.01.org/0day-ci/archive/20220908/202209080826.AuNlP9ys-lkp@intel.com/config)
compiler: s390-linux-gcc (GCC) 12.1.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # apt-get install sparse
        # sparse version: v0.6.4-39-gce1a6720-dirty
        # https://github.com/intel-lab-lkp/linux/commit/f858e96a8ad7eb5499e18501bfbcaad594eace1f
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Naohiro-Aota/btrfs-zoned-wait-extent-buffer-IOs-before-finishing-a-zone/20220907-224702
        git checkout f858e96a8ad7eb5499e18501bfbcaad594eace1f
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross C=1 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__' O=build_dir ARCH=s390 SHELL=/bin/bash

If you fix the issue, kindly add following tag where applicable
Reported-by: kernel test robot <lkp@intel.com>

sparse warnings: (new ones prefixed by >>)
   fs/btrfs/zoned.c:137:29: sparse: sparse: restricted __le64 degrades to integer
   fs/btrfs/zoned.c:137:52: sparse: sparse: restricted __le64 degrades to integer
>> fs/btrfs/zoned.c:1932:9: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected void **slot @@     got void [noderef] __rcu ** @@
   fs/btrfs/zoned.c:1932:9: sparse:     expected void **slot
   fs/btrfs/zoned.c:1932:9: sparse:     got void [noderef] __rcu **
>> fs/btrfs/zoned.c:1932:9: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected void **slot @@     got void [noderef] __rcu ** @@
   fs/btrfs/zoned.c:1932:9: sparse:     expected void **slot
   fs/btrfs/zoned.c:1932:9: sparse:     got void [noderef] __rcu **
>> fs/btrfs/zoned.c:1934:44: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected void [noderef] __rcu **slot @@     got void **slot @@
   fs/btrfs/zoned.c:1934:44: sparse:     expected void [noderef] __rcu **slot
   fs/btrfs/zoned.c:1934:44: sparse:     got void **slot
   fs/btrfs/zoned.c:1938:30: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected void **slot @@     got void [noderef] __rcu ** @@
   fs/btrfs/zoned.c:1938:30: sparse:     expected void **slot
   fs/btrfs/zoned.c:1938:30: sparse:     got void [noderef] __rcu **
   fs/btrfs/zoned.c:1947:47: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected void [noderef] __rcu **slot @@     got void **slot @@
   fs/btrfs/zoned.c:1947:47: sparse:     expected void [noderef] __rcu **slot
   fs/btrfs/zoned.c:1947:47: sparse:     got void **slot
   fs/btrfs/zoned.c:1947:22: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected void **slot @@     got void [noderef] __rcu ** @@
   fs/btrfs/zoned.c:1947:22: sparse:     expected void **slot
   fs/btrfs/zoned.c:1947:22: sparse:     got void [noderef] __rcu **
   fs/btrfs/zoned.c:1932:9: sparse: sparse: incorrect type in argument 1 (different address spaces) @@     expected void [noderef] __rcu **slot @@     got void **slot @@
   fs/btrfs/zoned.c:1932:9: sparse:     expected void [noderef] __rcu **slot
   fs/btrfs/zoned.c:1932:9: sparse:     got void **slot
>> fs/btrfs/zoned.c:1932:9: sparse: sparse: incorrect type in assignment (different address spaces) @@     expected void **slot @@     got void [noderef] __rcu ** @@
   fs/btrfs/zoned.c:1932:9: sparse:     expected void **slot
   fs/btrfs/zoned.c:1932:9: sparse:     got void [noderef] __rcu **
   fs/btrfs/zoned.c:2303:25: sparse: sparse: context imbalance in 'btrfs_zoned_activate_one_bg' - different lock contexts for basic block

vim +1932 fs/btrfs/zoned.c

  1922	
  1923	static void wait_eb_writebacks(struct btrfs_block_group *block_group)
  1924	{
  1925		struct btrfs_fs_info *fs_info = block_group->fs_info;
  1926		const u64 end = block_group->start + block_group->length;
  1927		struct radix_tree_iter iter;
  1928		struct extent_buffer *eb;
  1929		void **slot;
  1930	
  1931		rcu_read_lock();
> 1932		radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter,
  1933					 block_group->start >> fs_info->sectorsize_bits) {
> 1934			eb = radix_tree_deref_slot(slot);
  1935			if (!eb)
  1936				continue;
  1937			if (radix_tree_deref_retry(eb)) {
  1938				slot = radix_tree_iter_retry(&iter);
  1939				continue;
  1940			}
  1941	
  1942			if (eb->start < block_group->start)
  1943				continue;
  1944			if (eb->start >= end)
  1945				break;
  1946	
  1947			slot = radix_tree_iter_resume(slot, &iter);
  1948			rcu_read_unlock();
  1949			wait_on_extent_buffer_writeback(eb);
  1950			rcu_read_lock();
  1951		}
  1952		rcu_read_unlock();
  1953	}
  1954	

-- 
0-DAY CI Kernel Test Service
https://01.org/lkp