Sometimes the system isn't able to suspend because the task
responsible for trimming the device isn't able to finish in
time, especially since we have a free extent discarding phase,
which can trim a lot of unallocated space, and there is no
limits on the trim size (unlike the block group part).

Since discard isn't a critical call it can be interrupted
at any time, in such cases we stop the trim, report the amount
of discarded bytes and return failure.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=219180
Link: https://bugzilla.suse.com/show_bug.cgi?id=1229737
Signed-off-by: Luca Stefani <luca.stefani.ge1@gmail.com>
---
 fs/btrfs/extent-tree.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 894684f4f497..7c78ed4044db 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -16,6 +16,7 @@
 #include <linux/percpu_counter.h>
 #include <linux/lockdep.h>
 #include <linux/crc32c.h>
+#include <linux/freezer.h>
 #include "ctree.h"
 #include "extent-tree.h"
 #include "transaction.h"
@@ -1235,6 +1236,11 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+static bool btrfs_trim_interrupted(void)
+{
+	return fatal_signal_pending(current) || freezing(current);
+}
+
 static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 			       u64 *discarded_bytes)
 {
@@ -1302,6 +1308,9 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
 	}
 
 	while (bytes_left) {
+		if (btrfs_trim_interrupted())
+			break;
+
 		sector = start >> SECTOR_SHIFT;
 		nr_sects = bytes_left >> SECTOR_SHIFT;
 		bio_sects = min(nr_sects, bio_discard_limit(bdev, sector));
@@ -6470,7 +6479,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
 		start += len;
 		*trimmed += bytes;
 
-		if (fatal_signal_pending(current)) {
+		if (btrfs_trim_interrupted()) {
 			ret = -ERESTARTSYS;
 			break;
 		}
@@ -6519,6 +6528,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 	cache = btrfs_lookup_first_block_group(fs_info, range->start);
 	for (; cache; cache = btrfs_next_block_group(cache)) {
+		if (btrfs_trim_interrupted())
+			break;
+
 		if (cache->start >= range_end) {
 			btrfs_put_block_group(cache);
 			break;
@@ -6558,6 +6570,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+		if (btrfs_trim_interrupted())
+			break;
+
 		if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
 			continue;
 
-- 
2.46.0

在 2024/9/3 06:26, Luca Stefani 写道:
> Sometimes the system isn't able to suspend because the task
> responsible for trimming the device isn't able to finish in
> time, especially since we have a free extent discarding phase,
> which can trim a lot of unallocated space, and there is no
> limits on the trim size (unlike the block group part).
> 
> Since discard isn't a critical call it can be interrupted
> at any time, in such cases we stop the trim, report the amount
> of discarded bytes and return failure.
> 
> Link: https://bugzilla.kernel.org/show_bug.cgi?id=219180
> Link: https://bugzilla.suse.com/show_bug.cgi?id=1229737
> Signed-off-by: Luca Stefani <luca.stefani.ge1@gmail.com>
> ---
>   fs/btrfs/extent-tree.c | 17 ++++++++++++++++-
>   1 file changed, 16 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
> index 894684f4f497..7c78ed4044db 100644
> --- a/fs/btrfs/extent-tree.c
> +++ b/fs/btrfs/extent-tree.c
> @@ -16,6 +16,7 @@
>   #include <linux/percpu_counter.h>
>   #include <linux/lockdep.h>
>   #include <linux/crc32c.h>
> +#include <linux/freezer.h>
>   #include "ctree.h"
>   #include "extent-tree.h"
>   #include "transaction.h"
> @@ -1235,6 +1236,11 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
>   	return ret;
>   }
>   
> +static bool btrfs_trim_interrupted(void)
> +{
> +	return fatal_signal_pending(current) || freezing(current);
> +}
> +
>   static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
>   			       u64 *discarded_bytes)
>   {
> @@ -1302,6 +1308,9 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
>   	}
>   
>   	while (bytes_left) {
> +		if (btrfs_trim_interrupted())
> +			break;
> +

Although with this change, the check should be more than enough to cover 
everything, better than the existing per-block-group check and the 
possibly large discard for the free extents.

Thus just this check would be enough.

The other thing is the old return value, I guess you can just add "ret = 
-EERESTARTSYS;" before the break.

Thanks,
Qu
>   		sector = start >> SECTOR_SHIFT;
>   		nr_sects = bytes_left >> SECTOR_SHIFT;
>   		bio_sects = min(nr_sects, bio_discard_limit(bdev, sector));
> @@ -6470,7 +6479,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
>   		start += len;
>   		*trimmed += bytes;
>   
> -		if (fatal_signal_pending(current)) {
> +		if (btrfs_trim_interrupted()) {
>   			ret = -ERESTARTSYS;
>   			break;
>   		}
> @@ -6519,6 +6528,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
>   
>   	cache = btrfs_lookup_first_block_group(fs_info, range->start);
>   	for (; cache; cache = btrfs_next_block_group(cache)) {
> +		if (btrfs_trim_interrupted())
> +			break;
> +
>   		if (cache->start >= range_end) {
>   			btrfs_put_block_group(cache);
>   			break;
> @@ -6558,6 +6570,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
>   
>   	mutex_lock(&fs_devices->device_list_mutex);
>   	list_for_each_entry(device, &fs_devices->devices, dev_list) {
> +		if (btrfs_trim_interrupted())
> +			break;
> +
>   		if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
>   			continue;
>