Merge branch 'for-6.11/block' into for-next

* for-6.11/block:
  nvme: don't set io_opt if NOWS is zero
  block: don't reduce max_sectors based on io_opt
  block: remove a duplicate io_min check in blk_validate_limits
  blk-wbt: don't throttle swap writes in direct reclaim

Author: axboe

block/blk-settings.c

@@ -276,11 +276,10 @@ static int blk_validate_limits(struct queue_limits *lim)
 		if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
 			return -EINVAL;
 		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
-	} else if (lim->io_opt) {
+	} else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
 		lim->max_sectors =
 			min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT);
-	} else if (lim->io_min &&
-		   lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
+	} else if (lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
 		lim->max_sectors =
 			min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT);
 	} else {

block/blk-wbt.c

@@ -37,15 +37,15 @@
 enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
 	WBT_READ		= 2,	/* read */
-	WBT_KSWAPD		= 4,	/* write, from kswapd */
+	WBT_SWAP		= 4,	/* write, from swap_writepage() */
 	WBT_DISCARD		= 8,	/* discard */
 
 	WBT_NR_BITS		= 4,	/* number of bits */
 };
 
 enum {
 	WBT_RWQ_BG		= 0,
-	WBT_RWQ_KSWAPD,
+	WBT_RWQ_SWAP,
 	WBT_RWQ_DISCARD,
 	WBT_NUM_RWQ,
 };
@@ -172,8 +172,8 @@ static bool wb_recent_wait(struct rq_wb *rwb)
 static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
 					  enum wbt_flags wb_acct)
 {
-	if (wb_acct & WBT_KSWAPD)
-		return &rwb->rq_wait[WBT_RWQ_KSWAPD];
+	if (wb_acct & WBT_SWAP)
+		return &rwb->rq_wait[WBT_RWQ_SWAP];
 	else if (wb_acct & WBT_DISCARD)
 		return &rwb->rq_wait[WBT_RWQ_DISCARD];
 
@@ -528,7 +528,7 @@ static bool close_io(struct rq_wb *rwb)
 		time_before(now, rwb->last_comp + HZ / 10);
 }
 
-#define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO)
+#define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO | REQ_SWAP)
 
 static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf)
 {
@@ -539,13 +539,13 @@ static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf)
 
 	/*
 	 * At this point we know it's a buffered write. If this is
-	 * kswapd trying to free memory, or REQ_SYNC is set, then
+	 * swap trying to free memory, or REQ_SYNC is set, then
 	 * it's WB_SYNC_ALL writeback, and we'll use the max limit for
 	 * that. If the write is marked as a background write, then use
 	 * the idle limit, or go to normal if we haven't had competing
 	 * IO for a bit.
 	 */
-	if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
+	if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb))
 		limit = rwb->rq_depth.max_depth;
 	else if ((opf & REQ_BACKGROUND) || close_io(rwb)) {
 		/*
@@ -622,8 +622,8 @@ static enum wbt_flags bio_to_wbt_flags(struct rq_wb *rwb, struct bio *bio)
 	if (bio_op(bio) == REQ_OP_READ) {
 		flags = WBT_READ;
 	} else if (wbt_should_throttle(bio)) {
-		if (current_is_kswapd())
-			flags |= WBT_KSWAPD;
+		if (bio->bi_opf & REQ_SWAP)
+			flags |= WBT_SWAP;
 		if (bio_op(bio) == REQ_OP_DISCARD)
 			flags |= WBT_DISCARD;
 		flags |= WBT_TRACKED;

drivers/nvme/host/core.c

@@ -2025,7 +2025,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
 		/* NPWG = Namespace Preferred Write Granularity */
 		phys_bs = bs * (1 + le16_to_cpu(id->npwg));
 		/* NOWS = Namespace Optimal Write Size */
-		io_opt = bs * (1 + le16_to_cpu(id->nows));
+		if (id->nows)
+			io_opt = bs * (1 + le16_to_cpu(id->nows));
 	}
 
 	/*