Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   linan666@huaweicloud.com
To:     song@kernel.org
Cc:     linux-raid@vger.kernel.org, linux-kernel@vger.kernel.org,
        linan122@huawei.com, yukuai3@huawei.com, yi.zhang@huawei.com,
        houtao1@huawei.com, yangerkun@huawei.com
Subject: [PATCH 1/2] md: factor out a helper exceed_read_errors() to check read_errors
Date:   Mon,  4 Dec 2023 15:03:26 +0800
Message-Id: <20231204070327.3150356-2-linan666@huaweicloud.com>
In-Reply-To: <20231204070327.3150356-1-linan666@huaweicloud.com>
References: <20231204070327.3150356-1-linan666@huaweicloud.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Li Nan <linan122@huawei.com>

Move check_decay_read_errors() to raid1-10.c and factor out a helper
exceed_read_errors() to check if read_errors exceeds the limit, so that
raid1 can also use it. There are no functional changes.

Signed-off-by: Li Nan <linan122@huawei.com>
---
 drivers/md/raid1-10.c | 54 +++++++++++++++++++++++++++++++++++++++++++
 drivers/md/raid10.c   | 47 +------------------------------------
 2 files changed, 55 insertions(+), 46 deletions(-)

diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
index 3f22edec70e7..9e17eab915f5 100644
--- a/drivers/md/raid1-10.c
+++ b/drivers/md/raid1-10.c
@@ -173,3 +173,57 @@ static inline void raid1_prepare_flush_writes(struct bitmap *bitmap)
 	else
 		md_bitmap_unplug(bitmap);
 }
+
+/*
+ * Used by fix_read_error() to decay the per rdev read_errors.
+ * We halve the read error count for every hour that has elapsed
+ * since the last recorded read error.
+ */
+static inline void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev)
+{
+	long cur_time_mon;
+	unsigned long hours_since_last;
+	unsigned int read_errors = atomic_read(&rdev->read_errors);
+
+	cur_time_mon = ktime_get_seconds();
+
+	if (rdev->last_read_error == 0) {
+		/* first time we've seen a read error */
+		rdev->last_read_error = cur_time_mon;
+		return;
+	}
+
+	hours_since_last = (long)(cur_time_mon -
+			    rdev->last_read_error) / 3600;
+
+	rdev->last_read_error = cur_time_mon;
+
+	/*
+	 * if hours_since_last is > the number of bits in read_errors
+	 * just set read errors to 0. We do this to avoid
+	 * overflowing the shift of read_errors by hours_since_last.
+	 */
+	if (hours_since_last >= 8 * sizeof(read_errors))
+		atomic_set(&rdev->read_errors, 0);
+	else
+		atomic_set(&rdev->read_errors, read_errors >> hours_since_last);
+}
+
+static inline bool exceed_read_errors(struct mddev *mddev, struct md_rdev *rdev)
+{
+	int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
+	int read_errors;
+
+	check_decay_read_errors(mddev, rdev);
+	read_errors =  atomic_inc_return(&rdev->read_errors);
+	if (read_errors > max_read_errors) {
+		pr_notice("md:%s: %pg: Raid device exceeded read_error threshold [cur %d:max %d]\n",
+			  mdname(mddev), rdev->bdev, read_errors, max_read_errors);
+		pr_notice("md:%s: %pg: Failing raid device\n",
+			  mdname(mddev), rdev->bdev);
+		md_error(mddev, rdev);
+		return true;
+	}
+
+	return false;
+}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 375c11d6159f..8ea4974fb91c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2592,42 +2592,6 @@ static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 	}
 }
 
-/*
- * Used by fix_read_error() to decay the per rdev read_errors.
- * We halve the read error count for every hour that has elapsed
- * since the last recorded read error.
- *
- */
-static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev)
-{
-	long cur_time_mon;
-	unsigned long hours_since_last;
-	unsigned int read_errors = atomic_read(&rdev->read_errors);
-
-	cur_time_mon = ktime_get_seconds();
-
-	if (rdev->last_read_error == 0) {
-		/* first time we've seen a read error */
-		rdev->last_read_error = cur_time_mon;
-		return;
-	}
-
-	hours_since_last = (long)(cur_time_mon -
-			    rdev->last_read_error) / 3600;
-
-	rdev->last_read_error = cur_time_mon;
-
-	/*
-	 * if hours_since_last is > the number of bits in read_errors
-	 * just set read errors to 0. We do this to avoid
-	 * overflowing the shift of read_errors by hours_since_last.
-	 */
-	if (hours_since_last >= 8 * sizeof(read_errors))
-		atomic_set(&rdev->read_errors, 0);
-	else
-		atomic_set(&rdev->read_errors, read_errors >> hours_since_last);
-}
-
 static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector,
 			    int sectors, struct page *page, enum req_op op)
 {
@@ -2665,7 +2629,6 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 	int sect = 0; /* Offset from r10_bio->sector */
 	int sectors = r10_bio->sectors, slot = r10_bio->read_slot;
 	struct md_rdev *rdev;
-	int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
 	int d = r10_bio->devs[slot].devnum;
 
 	/* still own a reference to this rdev, so it cannot
@@ -2678,15 +2641,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 		   more fix_read_error() attempts */
 		return;
 
-	check_decay_read_errors(mddev, rdev);
-	atomic_inc(&rdev->read_errors);
-	if (atomic_read(&rdev->read_errors) > max_read_errors) {
-		pr_notice("md/raid10:%s: %pg: Raid device exceeded read_error threshold [cur %d:max %d]\n",
-			  mdname(mddev), rdev->bdev,
-			  atomic_read(&rdev->read_errors), max_read_errors);
-		pr_notice("md/raid10:%s: %pg: Failing raid device\n",
-			  mdname(mddev), rdev->bdev);
-		md_error(mddev, rdev);
+	if (exceed_read_errors(mddev, rdev)) {
 		r10_bio->devs[slot].bio = IO_BLOCKED;
 		return;
 	}
-- 
2.39.2