diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 86a2a0099178..f0b49da2a64f 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2127,6 +2127,7 @@ IO Interface Files
 	  [r|w]bps	The maximum sequential IO throughput
 	  [r|w]seqiops	The maximum 4k sequential IOs per second
 	  [r|w]randiops	The maximum 4k random IOs per second
+	  flushiops	The maximum flushes per second
 	  =============	========================================
 
 	From the above, the builtin linear model determines the base
@@ -2134,6 +2135,12 @@ IO Interface Files
 	for the IO size.  While simple, this model can cover most
 	common device classes acceptably.
 
+	"flushiops" determines the cost of a cache flush: a write with
+	a preceding cache flush is charged one flush on top of its data
+	cost, and a FUA write one more flush on devices without native
+	FUA support.  It is zero in the builtin profiles, so flushes
+	stay free until it is configured.
+
 	The IO cost model isn't expected to be accurate in absolute
 	sense and is scaled to the device behavior dynamically.
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 2745bffcd5ee..a81488c755ca 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -353,6 +353,7 @@ enum {
 	I_LCOEF_WBPS,
 	I_LCOEF_WSEQIOPS,
 	I_LCOEF_WRANDIOPS,
+	I_LCOEF_FLUSHIOPS,
 	NR_I_LCOEFS,
 };
 
@@ -363,6 +364,7 @@ enum {
 	LCOEF_WPAGE,
 	LCOEF_WSEQIO,
 	LCOEF_WRANDIO,
+	LCOEF_FLUSH,
 	NR_LCOEFS,
 };
 
@@ -883,6 +885,9 @@ static void ioc_refresh_lcoefs(struct ioc *ioc)
 		    &c[LCOEF_RPAGE], &c[LCOEF_RSEQIO], &c[LCOEF_RRANDIO]);
 	calc_lcoefs(u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS],
 		    &c[LCOEF_WPAGE], &c[LCOEF_WSEQIO], &c[LCOEF_WRANDIO]);
+
+	c[LCOEF_FLUSH] = u[I_LCOEF_FLUSHIOPS] ?
+		DIV64_U64_ROUND_UP(VTIME_PER_SEC, u[I_LCOEF_FLUSHIOPS]) : 0;
 }
 
 /*
@@ -2533,7 +2538,16 @@ static void calc_vtime_cost_builtin(struct bio *bio, struct ioc_gq *iocg,
 	u64 seek_pages = 0;
 	u64 cost = 0;
 
-	/* Can't calculate cost for empty bio */
+	/*
+	 * FUA on a device without native support becomes a post-flush;
+	 * charge it like PREFLUSH from the flush coefficient.
+	 */
+	if (bio->bi_opf & REQ_PREFLUSH)
+		cost += ioc->params.lcoefs[LCOEF_FLUSH];
+	if ((bio->bi_opf & REQ_FUA) && !bdev_fua(bio->bi_bdev))
+		cost += ioc->params.lcoefs[LCOEF_FLUSH];
+
+	/* Can't calculate data cost for empty bio */
 	if (!bio->bi_iter.bi_size)
 		goto out;
 
@@ -2543,6 +2557,7 @@ static void calc_vtime_cost_builtin(struct bio *bio, struct ioc_gq *iocg,
 		coef_randio	= ioc->params.lcoefs[LCOEF_RRANDIO];
 		coef_page	= ioc->params.lcoefs[LCOEF_RPAGE];
 		break;
+	case REQ_OP_ZONE_APPEND:
 	case REQ_OP_WRITE:
 		coef_seqio	= ioc->params.lcoefs[LCOEF_WSEQIO];
 		coef_randio	= ioc->params.lcoefs[LCOEF_WRANDIO];
@@ -2586,6 +2601,7 @@ static void calc_size_vtime_cost_builtin(struct request *rq, struct ioc *ioc,
 	case REQ_OP_READ:
 		*costp = pages * ioc->params.lcoefs[LCOEF_RPAGE];
 		break;
+	case REQ_OP_ZONE_APPEND:
 	case REQ_OP_WRITE:
 		*costp = pages * ioc->params.lcoefs[LCOEF_WPAGE];
 		break;
@@ -2708,7 +2724,9 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 	if (!iocg_activate(iocg, &now))
 		return;
 
-	iocg->cursor = bio_end_sector(bio);
+	/* dataless bios have no meaningful position for seq/rand detection */
+	if (bio->bi_iter.bi_size)
+		iocg->cursor = bio_end_sector(bio);
 	vtime = atomic64_read(&iocg->vtime);
 	cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now);
 
@@ -2725,10 +2743,11 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio)
 
 	/*
 	 * We're over budget. This can be handled in two ways. IOs which may
-	 * cause priority inversions are punted to @ioc->aux_iocg and charged as
-	 * debt. Otherwise, the issuer is blocked on @iocg->waitq. Debt handling
-	 * requires @ioc->lock, waitq handling @iocg->waitq.lock. Determine
-	 * whether debt handling is needed and acquire locks accordingly.
+	 * cause priority inversions are issued regardless and charged against
+	 * @iocg->abs_vdebt as debt. Otherwise, the issuer is blocked on
+	 * @iocg->waitq. Debt handling requires @ioc->lock, waitq handling
+	 * @iocg->waitq.lock. Determine whether debt handling is needed and
+	 * acquire locks accordingly.
 	 */
 	use_debt = bio_issue_as_root_blkg(bio) || fatal_signal_pending(current);
 	ioc_locked = use_debt || READ_ONCE(iocg->abs_vdebt);
@@ -2854,6 +2873,7 @@ static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq)
 		pidx = QOS_RLAT;
 		rw = READ;
 		break;
+	case REQ_OP_ZONE_APPEND:
 	case REQ_OP_WRITE:
 		pidx = QOS_WLAT;
 		rw = WRITE;
@@ -3440,10 +3460,12 @@ static u64 ioc_cost_model_prfill(struct seq_file *sf,
 	spin_lock_irq(&ioc->lock);
 	seq_printf(sf, "%s ctrl=%s model=linear "
 		   "rbps=%llu rseqiops=%llu rrandiops=%llu "
-		   "wbps=%llu wseqiops=%llu wrandiops=%llu\n",
+		   "wbps=%llu wseqiops=%llu wrandiops=%llu "
+		   "flushiops=%llu\n",
 		   dname, ioc->user_cost_model ? "user" : "auto",
 		   u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS],
-		   u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS]);
+		   u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS],
+		   u[I_LCOEF_FLUSHIOPS]);
 	spin_unlock_irq(&ioc->lock);
 	return 0;
 }
@@ -3470,6 +3492,7 @@ static const match_table_t i_lcoef_tokens = {
 	{ I_LCOEF_WBPS,		"wbps=%u"	},
 	{ I_LCOEF_WSEQIOPS,	"wseqiops=%u"	},
 	{ I_LCOEF_WRANDIOPS,	"wrandiops=%u"	},
+	{ I_LCOEF_FLUSHIOPS,	"flushiops=%u"	},
 	{ NR_I_LCOEFS,		NULL		},
 };