Merge tag 'block-6.6-2023-09-08' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - Fix null_blk polled IO timeout handling (Chengming)

 - Regression fix for swapped arguments in drbd bvec_set_page()
   (Christoph)

 - String length handling fix for s390 dasd (Heiko)

 - Fixes for blk-throttle accounting (Yu)

 - Fix page pinning issue for same page segments (Christoph)

 - Remove redundant file_remove_privs() call (Christoph)

 - Fix a regression in partition handling for devices not supporting
   partitions (Li)

* tag 'block-6.6-2023-09-08' of git://git.kernel.dk/linux:
  drbd: swap bvec_set_page len and offset
  block: fix pin count management when merging same-page segments
  null_blk: fix poll request timeout handling
  s390/dasd: fix string length handling
  block: don't add or resize partition on the disk with GENHD_FL_NO_PART
  block: remove the call to file_remove_privs in blkdev_write_iter
  blk-throttle: consider 'carryover_ios/bytes' in throtl_trim_slice()
  blk-throttle: use calculate_io/bytes_allowed() for throtl_trim_slice()
  blk-throttle: fix wrong comparation while 'carryover_ios/bytes' is negative
  blk-throttle: print signed value 'carryover_bytes/ios' for user

10 files changed, 84 insertions, 79 deletions

diff --git a/block/blk-map.c b/block/blk-map.c
index 44d74a30ddac0..8584babf3ea0c 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -315,12 +315,11 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter,
 					n = bytes;
 
 				if (!bio_add_hw_page(rq->q, bio, page, n, offs,
-						     max_sectors, &same_page)) {
-					if (same_page)
-						bio_release_page(bio, page);
+						     max_sectors, &same_page))
 					break;
-				}
 
+				if (same_page)
+					bio_release_page(bio, page);
 				bytes -= n;
 				offs = 0;
 			}
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 7397ff199d669..38a881cf97d0b 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -697,11 +697,41 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw)
 	return true;
 }
 
+static unsigned int calculate_io_allowed(u32 iops_limit,
+					 unsigned long jiffy_elapsed)
+{
+	unsigned int io_allowed;
+	u64 tmp;
+
+	/*
+	 * jiffy_elapsed should not be a big value as minimum iops can be
+	 * 1 then at max jiffy elapsed should be equivalent of 1 second as we
+	 * will allow dispatch after 1 second and after that slice should
+	 * have been trimmed.
+	 */
+
+	tmp = (u64)iops_limit * jiffy_elapsed;
+	do_div(tmp, HZ);
+
+	if (tmp > UINT_MAX)
+		io_allowed = UINT_MAX;
+	else
+		io_allowed = tmp;
+
+	return io_allowed;
+}
+
+static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed)
+{
+	return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ);
+}
+
 /* Trim the used slices and adjust slice start accordingly */
 static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 {
-	unsigned long nr_slices, time_elapsed, io_trim;
-	u64 bytes_trim, tmp;
+	unsigned long time_elapsed;
+	long long bytes_trim;
+	int io_trim;
 
 	BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
 
@@ -723,67 +753,38 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 
 	throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);
 
-	time_elapsed = jiffies - tg->slice_start[rw];
-
-	nr_slices = time_elapsed / tg->td->throtl_slice;
-
-	if (!nr_slices)
+	time_elapsed = rounddown(jiffies - tg->slice_start[rw],
+				 tg->td->throtl_slice);
+	if (!time_elapsed)
 		return;
-	tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
-	do_div(tmp, HZ);
-	bytes_trim = tmp;
 
-	io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
-		HZ;
-
-	if (!bytes_trim && !io_trim)
+	bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw),
+					     time_elapsed) +
+		     tg->carryover_bytes[rw];
+	io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) +
+		  tg->carryover_ios[rw];
+	if (bytes_trim <= 0 && io_trim <= 0)
 		return;
 
-	if (tg->bytes_disp[rw] >= bytes_trim)
+	tg->carryover_bytes[rw] = 0;
+	if ((long long)tg->bytes_disp[rw] >= bytes_trim)
 		tg->bytes_disp[rw] -= bytes_trim;
 	else
 		tg->bytes_disp[rw] = 0;
 
-	if (tg->io_disp[rw] >= io_trim)
+	tg->carryover_ios[rw] = 0;
+	if ((int)tg->io_disp[rw] >= io_trim)
 		tg->io_disp[rw] -= io_trim;
 	else
 		tg->io_disp[rw] = 0;
 
-	tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;
+	tg->slice_start[rw] += time_elapsed;
 
 	throtl_log(&tg->service_queue,
-		   "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
-		   rw == READ ? 'R' : 'W', nr_slices, bytes_trim, io_trim,
-		   tg->slice_start[rw], tg->slice_end[rw], jiffies);
-}
-
-static unsigned int calculate_io_allowed(u32 iops_limit,
-					 unsigned long jiffy_elapsed)
-{
-	unsigned int io_allowed;
-	u64 tmp;
-
-	/*
-	 * jiffy_elapsed should not be a big value as minimum iops can be
-	 * 1 then at max jiffy elapsed should be equivalent of 1 second as we
-	 * will allow dispatch after 1 second and after that slice should
-	 * have been trimmed.
-	 */
-
-	tmp = (u64)iops_limit * jiffy_elapsed;
-	do_div(tmp, HZ);
-
-	if (tmp > UINT_MAX)
-		io_allowed = UINT_MAX;
-	else
-		io_allowed = tmp;
-
-	return io_allowed;
-}
-
-static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed)
-{
-	return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ);
+		   "[%c] trim slice nr=%lu bytes=%lld io=%d start=%lu end=%lu jiffies=%lu",
+		   rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice,
+		   bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw],
+		   jiffies);
 }
 
 static void __tg_update_carryover(struct throtl_grp *tg, bool rw)
@@ -816,7 +817,7 @@ static void tg_update_carryover(struct throtl_grp *tg)
 		__tg_update_carryover(tg, WRITE);
 
 	/* see comments in struct throtl_grp for meaning of these fields. */
-	throtl_log(&tg->service_queue, "%s: %llu %llu %u %u\n", __func__,
+	throtl_log(&tg->service_queue, "%s: %lld %lld %d %d\n", __func__,
 		   tg->carryover_bytes[READ], tg->carryover_bytes[WRITE],
 		   tg->carryover_ios[READ], tg->carryover_ios[WRITE]);
 }
@@ -825,7 +826,7 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio
 				 u32 iops_limit)
 {
 	bool rw = bio_data_dir(bio);
-	unsigned int io_allowed;
+	int io_allowed;
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 
 	if (iops_limit == UINT_MAX) {
@@ -838,9 +839,8 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio
 	jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice);
 	io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd) +
 		     tg->carryover_ios[rw];
-	if (tg->io_disp[rw] + 1 <= io_allowed) {
+	if (io_allowed > 0 && tg->io_disp[rw] + 1 <= io_allowed)
 		return 0;
-	}
 
 	/* Calc approx time to dispatch */
 	jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;
@@ -851,7 +851,8 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio,
 				u64 bps_limit)
 {
 	bool rw = bio_data_dir(bio);
-	u64 bytes_allowed, extra_bytes;
+	long long bytes_allowed;
+	u64 extra_bytes;
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 	unsigned int bio_size = throtl_bio_data_size(bio);
 
@@ -869,9 +870,8 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio,
 	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
 	bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd) +
 			tg->carryover_bytes[rw];
-	if (tg->bytes_disp[rw] + bio_size <= bytes_allowed) {
+	if (bytes_allowed > 0 && tg->bytes_disp[rw] + bio_size <= bytes_allowed)
 		return 0;
-	}
 
 	/* Calc approx time to dispatch */
 	extra_bytes = tg->bytes_disp[rw] + bio_size - bytes_allowed;
diff --git a/block/blk-throttle.h b/block/blk-throttle.h
index d1ccbfe9f7978..bffbc9cfc8ab6 100644
--- a/block/blk-throttle.h
+++ b/block/blk-throttle.h
@@ -127,8 +127,8 @@ struct throtl_grp {
 	 * bytes/ios are waited already in previous configuration, and they will
 	 * be used to calculate wait time under new configuration.
 	 */
-	uint64_t carryover_bytes[2];
-	unsigned int carryover_ios[2];
+	long long carryover_bytes[2];
+	int carryover_ios[2];
 
 	unsigned long last_check_time;
 
diff --git a/block/fops.c b/block/fops.c
index a24a624d3bf71..acff3d5d22d46 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -671,10 +671,6 @@ static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		iov_iter_truncate(from, size);
 	}
 
-	ret = file_remove_privs(file);
-	if (ret)
-		return ret;
-
 	ret = file_update_time(file);
 	if (ret)
 		return ret;
diff --git a/block/ioctl.c b/block/ioctl.c
index 648670ddb164a..d5f5cd61efd7f 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -20,6 +20,8 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	struct blkpg_partition p;
 	long long start, length;
 
+	if (disk->flags & GENHD_FL_NO_PART)
+		return -EINVAL;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 79ab532aabafb..6bc86106c7b2a 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1557,7 +1557,7 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa
 	do {
 		int sent;
 
-		bvec_set_page(&bvec, page, offset, len);
+		bvec_set_page(&bvec, page, len, offset);
 		iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len);
 
 		sent = sock_sendmsg(socket, &msg);
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 864013019d6b6..968090935eb23 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1643,9 +1643,12 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	struct nullb_queue *nq = hctx->driver_data;
 	LIST_HEAD(list);
 	int nr = 0;
+	struct request *rq;
 
 	spin_lock(&nq->poll_lock);
 	list_splice_init(&nq->poll_list, &list);
+	list_for_each_entry(rq, &list, queuelist)
+		blk_mq_set_request_complete(rq);
 	spin_unlock(&nq->poll_lock);
 
 	while (!list_empty(&list)) {
@@ -1671,16 +1674,21 @@ static enum blk_eh_timer_return null_timeout_rq(struct request *rq)
 	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
-	pr_info("rq %p timed out\n", rq);
-
 	if (hctx->type == HCTX_TYPE_POLL) {
 		struct nullb_queue *nq = hctx->driver_data;
 
 		spin_lock(&nq->poll_lock);
+		/* The request may have completed meanwhile. */
+		if (blk_mq_request_completed(rq)) {
+			spin_unlock(&nq->poll_lock);
+			return BLK_EH_DONE;
+		}
 		list_del_init(&rq->queuelist);
 		spin_unlock(&nq->poll_lock);
 	}
 
+	pr_info("rq %p timed out\n", rq);
+
 	/*
 	 * If the device is marked as blocking (i.e. memory backed or zoned
 	 * device), the submission path may be blocked waiting for resources
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 620fab01b710b..c4e36650c4264 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -1378,16 +1378,12 @@ static ssize_t dasd_vendor_show(struct device *dev,
 
 static DEVICE_ATTR(vendor, 0444, dasd_vendor_show, NULL);
 
-#define UID_STRLEN ( /* vendor */ 3 + 1 + /* serial    */ 14 + 1 +\
-		     /* SSID   */ 4 + 1 + /* unit addr */ 2 + 1 +\
-		     /* vduit */ 32 + 1)
-
 static ssize_t
 dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
+	char uid_string[DASD_UID_STRLEN];
 	struct dasd_device *device;
 	struct dasd_uid uid;
-	char uid_string[UID_STRLEN];
 	char ua_string[3];
 
 	device = dasd_device_from_cdev(to_ccwdev(dev));
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 8587e423169ec..bd89b032968a4 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1079,12 +1079,12 @@ static void dasd_eckd_get_uid_string(struct dasd_conf *conf,
 
 	create_uid(conf, &uid);
 	if (strlen(uid.vduit) > 0)
-		snprintf(print_uid, sizeof(*print_uid),
+		snprintf(print_uid, DASD_UID_STRLEN,
 			 "%s.%s.%04x.%02x.%s",
 			 uid.vendor, uid.serial, uid.ssid,
 			 uid.real_unit_addr, uid.vduit);
 	else
-		snprintf(print_uid, sizeof(*print_uid),
+		snprintf(print_uid, DASD_UID_STRLEN,
 			 "%s.%s.%04x.%02x",
 			 uid.vendor, uid.serial, uid.ssid,
 			 uid.real_unit_addr);
@@ -1093,8 +1093,8 @@ static void dasd_eckd_get_uid_string(struct dasd_conf *conf,
 static int dasd_eckd_check_cabling(struct dasd_device *device,
 				   void *conf_data, __u8 lpm)
 {
+	char print_path_uid[DASD_UID_STRLEN], print_device_uid[DASD_UID_STRLEN];
 	struct dasd_eckd_private *private = device->private;
-	char print_path_uid[60], print_device_uid[60];
 	struct dasd_conf path_conf;
 
 	path_conf.data = conf_data;
@@ -1293,9 +1293,9 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
 	__u8 path_rcd_buf[DASD_ECKD_RCD_DATA_SIZE];
 	__u8 lpm, opm, npm, ppm, epm, hpfpm, cablepm;
 	struct dasd_conf_data *conf_data;
+	char print_uid[DASD_UID_STRLEN];
 	struct dasd_conf path_conf;
 	unsigned long flags;
-	char print_uid[60];
 	int rc, pos;
 
 	opm = 0;
@@ -5855,8 +5855,8 @@ static void dasd_eckd_dump_sense(struct dasd_device *device,
 static int dasd_eckd_reload_device(struct dasd_device *device)
 {
 	struct dasd_eckd_private *private = device->private;
+	char print_uid[DASD_UID_STRLEN];
 	int rc, old_base;
-	char print_uid[60];
 	struct dasd_uid uid;
 	unsigned long flags;
 
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 0aa56351da720..8a4dbe9d77411 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -259,6 +259,10 @@ struct dasd_uid {
 	char vduit[33];
 };
 
+#define DASD_UID_STRLEN ( /* vendor */ 3 + 1 + /* serial    */ 14 + 1 +	\
+			  /* SSID   */ 4 + 1 + /* unit addr */ 2 + 1 +	\
+			  /* vduit */ 32 + 1)
+
 /*
  * PPRC Status data
  */