f2fs: Add bggc_io_aware to adjust the priority of BG_GC when issuing IO

Currently, we have encountered some issues while testing ZUFS. In
situations near the storage limit (e.g., 50GB remaining), and after
simulating fragmentation by repeatedly writing and deleting data, we found
that application installation and startup tests conducted after idling for
a few minutes take significantly longer several times that of traditional
UFS. Tracing the operations revealed that the majority of I/Os were issued
by background GC, which blocks normal I/O operations.

Under normal circumstances, ZUFS indeed requires more background GC and
employs a more aggressive GC strategy. However, I aim to find a way to
minimize the impact on regular I/O operations under these near-limit
conditions. To address this, I have introduced a bggc_io_aware feature,
which controls the prioritization of background GC in the presence of I/Os.
This switch can be adjusted at the framework level to implement different
strategies. If set to AWARE_ALL_IO, all background GC operations will be
skipped during active I/O issuance. The default option remains consistent
with the current strategy, ensuring no change in behavior.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

4 files changed, 35 insertions, 7 deletions

diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index ce189acd1908..66ee15681983 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -898,3 +898,16 @@ Description:
 		- "compat": Hash-based lookup with a linear search fallback enabled
 		- "auto:perf": lookup_mode is auto and fallback is disabled on-disk
 		- "auto:compat": lookup_mode is auto and fallback is enabled on-disk
+
+What:		/sys/fs/f2fs/<disk>/bggc_io_aware
+Date:		August 2025
+Contact:	"Liao Yuanhong" <liaoyuanhong@vivo.com>
+Description:	Used to adjust the BG_GC priority when pending IO, with a default value
+		of 0. Specifically, for ZUFS, the default value is 1.
+
+		==================  ======================================================
+		value				description
+		bggc_io_aware = 0   skip background GC if there is any kind of pending IO
+		bggc_io_aware = 1   skip background GC if there is pending read IO
+		bggc_io_aware = 2   don't aware IO for background GC
+		==================  ======================================================
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 0655c5c20eee..dba391b72119 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -155,6 +155,12 @@ enum blkzone_allocation_policy {
 	BLKZONE_ALLOC_PRIOR_CONV,	/* Prioritize writing to conventional zones */
 };
 
+enum bggc_io_aware_policy {
+	AWARE_ALL_IO,		/* skip background GC if there is any kind of pending IO */
+	AWARE_READ_IO,		/* skip background GC if there is pending read IO */
+	AWARE_NONE,			/* don't aware IO for background GC */
+};
+
 /*
  * An implementation of an rwsem that is explicitly unfair to readers. This
  * prevents priority inversion when a low-priority reader acquires the read lock
@@ -1841,6 +1847,7 @@ struct f2fs_sb_info {
 	spinlock_t dev_lock;			/* protect dirty_device */
 	bool aligned_blksize;			/* all devices has the same logical blksize */
 	unsigned int first_seq_zone_segno;	/* first segno in sequential zone */
+	unsigned int bggc_io_aware;		/* For adjust the BG_GC priority when pending IO */
 
 	/* For write statistics */
 	u64 sectors_written_start;
@@ -3033,13 +3040,10 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
 	if (sbi->gc_mode == GC_URGENT_HIGH)
 		return true;
 
-	if (zoned_gc) {
-		if (is_inflight_read_io(sbi))
-			return false;
-	} else {
-		if (is_inflight_io(sbi, type))
-			return false;
-	}
+	if (sbi->bggc_io_aware == AWARE_READ_IO && is_inflight_read_io(sbi))
+		return false;
+	if (sbi->bggc_io_aware == AWARE_ALL_IO && is_inflight_io(sbi, type))
+		return false;
 
 	if (sbi->gc_mode == GC_URGENT_MID)
 		return true;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 87f6490d9247..2000880b7dca 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -4683,9 +4683,11 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 
 	logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev);
 	sbi->aligned_blksize = true;
+	sbi->bggc_io_aware = AWARE_ALL_IO;
 #ifdef CONFIG_BLK_DEV_ZONED
 	sbi->max_open_zones = UINT_MAX;
 	sbi->blkzone_alloc_policy = BLKZONE_ALLOC_PRIOR_SEQ;
+	sbi->bggc_io_aware = AWARE_READ_IO;
 #endif
 
 	for (i = 0; i < max_devices; i++) {
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 82489c78aeda..1ffaf9e74ce9 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -882,6 +882,13 @@ out:
 		return count;
 	}
 
+	if (!strcmp(a->attr.name, "bggc_io_aware")) {
+		if (t < AWARE_ALL_IO || t > AWARE_NONE)
+			return -EINVAL;
+		sbi->bggc_io_aware = t;
+		return count;
+	}
+
 	*ui = (unsigned int)t;
 
 	return count;
@@ -1191,6 +1198,7 @@ F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy);
 #endif
 F2FS_SBI_GENERAL_RW_ATTR(carve_out);
 F2FS_SBI_GENERAL_RW_ATTR(reserved_pin_section);
+F2FS_SBI_GENERAL_RW_ATTR(bggc_io_aware);
 
 /* STAT_INFO ATTR */
 #ifdef CONFIG_F2FS_STAT_FS
@@ -1320,6 +1328,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(discard_idle_interval),
 	ATTR_LIST(gc_idle_interval),
 	ATTR_LIST(umount_discard_timeout),
+	ATTR_LIST(bggc_io_aware),
 #ifdef CONFIG_F2FS_IOSTAT
 	ATTR_LIST(iostat_enable),
 	ATTR_LIST(iostat_period_ms),