cgroup: rstat: fix A-A deadlock on 32bit around u64_stats_sync

0fa294fb1985 ("cgroup: Replace cgroup_rstat_mutex with a spinlock") added
cgroup_rstat_flush_irqsafe() allowing flushing to happen from the irq
context. However, rstat paths use u64_stats_sync to synchronize access to
64bit stat counters on 32bit machines. u64_stats_sync is implemented using
seq_lock and trying to read from an irq context can lead to A-A deadlock if
the irq happens to interrupt the stat update.

Fix it by using the irqsafe variants - u64_stats_update_begin_irqsave() and
u64_stats_update_end_irqrestore() - in the update paths. Note that none of
this matters on 64bit machines. All these are just for 32bit SMP setups.

Note that the interface was introduced way back, its first and currently
only use was recently added by 2d146aa3aa84 ("mm: memcontrol: switch to
rstat"). Stable tagging targets this commit.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Rik van Riel <riel@surriel.com>
Fixes: 2d146aa3aa84 ("mm: memcontrol: switch to rstat")
Cc: stable@vger.kernel.org # v5.13+

1 files changed, 8 insertions, 6 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 575d7a2e7203..31fe9be179d9 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -790,6 +790,7 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 		struct blkcg_gq *parent = blkg->parent;
 		struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu);
 		struct blkg_iostat cur, delta;
+		unsigned long flags;
 		unsigned int seq;
 
 		/* fetch the current per-cpu values */
@@ -799,21 +800,21 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu)
 		} while (u64_stats_fetch_retry(&bisc->sync, seq));
 
 		/* propagate percpu delta to global */
-		u64_stats_update_begin(&blkg->iostat.sync);
+		flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
 		blkg_iostat_set(&delta, &cur);
 		blkg_iostat_sub(&delta, &bisc->last);
 		blkg_iostat_add(&blkg->iostat.cur, &delta);
 		blkg_iostat_add(&bisc->last, &delta);
-		u64_stats_update_end(&blkg->iostat.sync);
+		u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
 
 		/* propagate global delta to parent (unless that's root) */
 		if (parent && parent->parent) {
-			u64_stats_update_begin(&parent->iostat.sync);
+			flags = u64_stats_update_begin_irqsave(&parent->iostat.sync);
 			blkg_iostat_set(&delta, &blkg->iostat.cur);
 			blkg_iostat_sub(&delta, &blkg->iostat.last);
 			blkg_iostat_add(&parent->iostat.cur, &delta);
 			blkg_iostat_add(&blkg->iostat.last, &delta);
-			u64_stats_update_end(&parent->iostat.sync);
+			u64_stats_update_end_irqrestore(&parent->iostat.sync, flags);
 		}
 	}
 
@@ -848,6 +849,7 @@ static void blkcg_fill_root_iostats(void)
 		memset(&tmp, 0, sizeof(tmp));
 		for_each_possible_cpu(cpu) {
 			struct disk_stats *cpu_dkstats;
+			unsigned long flags;
 
 			cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu);
 			tmp.ios[BLKG_IOSTAT_READ] +=
@@ -864,9 +866,9 @@ static void blkcg_fill_root_iostats(void)
 			tmp.bytes[BLKG_IOSTAT_DISCARD] +=
 				cpu_dkstats->sectors[STAT_DISCARD] << 9;
 
-			u64_stats_update_begin(&blkg->iostat.sync);
+			flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync);
 			blkg_iostat_set(&blkg->iostat.cur, &tmp);
-			u64_stats_update_end(&blkg->iostat.sync);
+			u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
 		}
 	}
 }