Merge branch 'for-4.21/block' into for-4.21/aio

* for-4.21/block: (351 commits)
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  block: fix blk-iolatency accounting underflow
  blk-mq: fix dispatch from sw queue
  block: mq-deadline: Fix write completion handling
  nvme-pci: don't share queue maps
  blk-mq: only dispatch to non-defauly queue maps if they have queues
  blk-mq: export hctx->type in debugfs instead of sysfs
  blk-mq: fix allocation for queue mapping table
  blk-wbt: export internal state via debugfs
  blk-mq-debugfs: support rq_qos
  block: update sysfs documentation
  block: loop: check error using IS_ERR instead of IS_ERR_OR_NULL in loop_add()
  aoe: add __exit annotation
  block: clear REQ_HIPRI if polling is not supported
  blk-mq: replace and kill blk_mq_request_issue_directly
  blk-mq: issue directly with bypass 'false' in blk_mq_sched_insert_requests
  blk-mq: refactor the code of issue request directly
  block: remove the bio_integrity_advance export
  ...

3 files changed, 141 insertions, 59 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 6aaf5dd5383b..8b79318810ad 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -493,7 +493,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
 }
 
 /**
- * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
+ * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss
  * @cgrp: the cgroup of interest
  * @ss: the subsystem of interest (%NULL returns @cgrp->self)
  *
@@ -502,8 +502,8 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
  * enabled.  If @ss is associated with the hierarchy @cgrp is on, this
  * function is guaranteed to return non-NULL css.
  */
-static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
-						struct cgroup_subsys *ss)
+static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp,
+							struct cgroup_subsys *ss)
 {
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -524,6 +524,35 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 }
 
 /**
+ * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest
+ *
+ * Find and get the effective css of @cgrp for @ss.  The effective css is
+ * defined as the matching css of the nearest ancestor including self which
+ * has @ss enabled.  If @ss is not mounted on the hierarchy @cgrp is on,
+ * the root css is returned, so this function always returns a valid css.
+ *
+ * The returned css is not guaranteed to be online, and therefore it is the
+ * callers responsiblity to tryget a reference for it.
+ */
+struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
+					 struct cgroup_subsys *ss)
+{
+	struct cgroup_subsys_state *css;
+
+	do {
+		css = cgroup_css(cgrp, ss);
+
+		if (css)
+			return css;
+		cgrp = cgroup_parent(cgrp);
+	} while (cgrp);
+
+	return init_css_set.subsys[ss->id];
+}
+
+/**
  * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem
  * @cgrp: the cgroup of interest
  * @ss: the subsystem of interest
@@ -605,10 +634,11 @@ EXPORT_SYMBOL_GPL(of_css);
  *
  * Should be called under cgroup_[tree_]mutex.
  */
-#define for_each_e_css(css, ssid, cgrp)					\
-	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	\
-		if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \
-			;						\
+#define for_each_e_css(css, ssid, cgrp)					    \
+	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	    \
+		if (!((css) = cgroup_e_css_by_mask(cgrp,		    \
+						   cgroup_subsys[(ssid)]))) \
+			;						    \
 		else
 
 /**
@@ -1007,7 +1037,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 			 * @ss is in this hierarchy, so we want the
 			 * effective css from @cgrp.
 			 */
-			template[i] = cgroup_e_css(cgrp, ss);
+			template[i] = cgroup_e_css_by_mask(cgrp, ss);
 		} else {
 			/*
 			 * @ss is not in this hierarchy, so we don't want
@@ -3024,7 +3054,7 @@ static int cgroup_apply_control(struct cgroup *cgrp)
 		return ret;
 
 	/*
-	 * At this point, cgroup_e_css() results reflect the new csses
+	 * At this point, cgroup_e_css_by_mask() results reflect the new csses
 	 * making the following cgroup_update_dfl_csses() properly update
 	 * css associations of all tasks in the subtree.
 	 */
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index f4f29b9d90ee..08c904eb7279 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -94,15 +94,15 @@ static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask,
 	return nodes;
 }
 
-static int irq_build_affinity_masks(const struct irq_affinity *affd,
-				    int startvec, int numvecs,
+static int __irq_build_affinity_masks(const struct irq_affinity *affd,
+				    int startvec, int numvecs, int firstvec,
 				    cpumask_var_t *node_to_cpumask,
 				    const struct cpumask *cpu_mask,
 				    struct cpumask *nmsk,
 				    struct cpumask *masks)
 {
 	int n, nodes, cpus_per_vec, extra_vecs, done = 0;
-	int last_affv = affd->pre_vectors + numvecs;
+	int last_affv = firstvec + numvecs;
 	int curvec = startvec;
 	nodemask_t nodemsk = NODE_MASK_NONE;
 
@@ -117,12 +117,11 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
 	 */
 	if (numvecs <= nodes) {
 		for_each_node_mask(n, nodemsk) {
-			cpumask_copy(masks + curvec, node_to_cpumask[n]);
-			if (++done == numvecs)
-				break;
+			cpumask_or(masks + curvec, masks + curvec, node_to_cpumask[n]);
 			if (++curvec == last_affv)
-				curvec = affd->pre_vectors;
+				curvec = firstvec;
 		}
+		done = numvecs;
 		goto out;
 	}
 
@@ -130,7 +129,7 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
 		int ncpus, v, vecs_to_assign, vecs_per_node;
 
 		/* Spread the vectors per node */
-		vecs_per_node = (numvecs - (curvec - affd->pre_vectors)) / nodes;
+		vecs_per_node = (numvecs - (curvec - firstvec)) / nodes;
 
 		/* Get the cpus on this node which are in the mask */
 		cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
@@ -158,7 +157,7 @@ static int irq_build_affinity_masks(const struct irq_affinity *affd,
 		if (done >= numvecs)
 			break;
 		if (curvec >= last_affv)
-			curvec = affd->pre_vectors;
+			curvec = firstvec;
 		--nodes;
 	}
 
@@ -166,6 +165,62 @@ out:
 	return done;
 }
 
+/*
+ * build affinity in two stages:
+ *	1) spread present CPU on these vectors
+ *	2) spread other possible CPUs on these vectors
+ */
+static int irq_build_affinity_masks(const struct irq_affinity *affd,
+				    int startvec, int numvecs, int firstvec,
+				    cpumask_var_t *node_to_cpumask,
+				    struct cpumask *masks)
+{
+	int curvec = startvec, nr_present, nr_others;
+	int ret = -ENOMEM;
+	cpumask_var_t nmsk, npresmsk;
+
+	if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
+			return ret;
+
+	if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
+			goto fail;
+
+	ret = 0;
+	/* Stabilize the cpumasks */
+	get_online_cpus();
+	build_node_to_cpumask(node_to_cpumask);
+
+	/* Spread on present CPUs starting from affd->pre_vectors */
+	nr_present = __irq_build_affinity_masks(affd, curvec, numvecs,
+						firstvec, node_to_cpumask,
+						cpu_present_mask, nmsk, masks);
+
+	/*
+	 * Spread on non present CPUs starting from the next vector to be
+	 * handled. If the spreading of present CPUs already exhausted the
+	 * vector space, assign the non present CPUs to the already spread
+	 * out vectors.
+	 */
+	if (nr_present >= numvecs)
+		curvec = firstvec;
+	else
+		curvec = firstvec + nr_present;
+	cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
+	nr_others = __irq_build_affinity_masks(affd, curvec, numvecs,
+					       firstvec, node_to_cpumask,
+					       npresmsk, nmsk, masks);
+	put_online_cpus();
+
+	if (nr_present < numvecs)
+			WARN_ON(nr_present + nr_others < numvecs);
+
+	free_cpumask_var(npresmsk);
+
+ fail:
+	free_cpumask_var(nmsk);
+	return ret;
+}
+
 /**
  * irq_create_affinity_masks - Create affinity masks for multiqueue spreading
  * @nvecs:	The total number of vectors
@@ -178,8 +233,9 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 {
 	int affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
 	int curvec, usedvecs;
-	cpumask_var_t nmsk, npresmsk, *node_to_cpumask;
+	cpumask_var_t *node_to_cpumask;
 	struct cpumask *masks = NULL;
+	int i, nr_sets;
 
 	/*
 	 * If there aren't any vectors left after applying the pre/post
@@ -188,15 +244,9 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 	if (nvecs == affd->pre_vectors + affd->post_vectors)
 		return NULL;
 
-	if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
-		return NULL;
-
-	if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
-		goto outcpumsk;
-
 	node_to_cpumask = alloc_node_to_cpumask();
 	if (!node_to_cpumask)
-		goto outnpresmsk;
+		return NULL;
 
 	masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL);
 	if (!masks)
@@ -206,30 +256,28 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 	for (curvec = 0; curvec < affd->pre_vectors; curvec++)
 		cpumask_copy(masks + curvec, irq_default_affinity);
 
-	/* Stabilize the cpumasks */
-	get_online_cpus();
-	build_node_to_cpumask(node_to_cpumask);
-
-	/* Spread on present CPUs starting from affd->pre_vectors */
-	usedvecs = irq_build_affinity_masks(affd, curvec, affvecs,
-					    node_to_cpumask, cpu_present_mask,
-					    nmsk, masks);
-
 	/*
-	 * Spread on non present CPUs starting from the next vector to be
-	 * handled. If the spreading of present CPUs already exhausted the
-	 * vector space, assign the non present CPUs to the already spread
-	 * out vectors.
+	 * Spread on present CPUs starting from affd->pre_vectors. If we
+	 * have multiple sets, build each sets affinity mask separately.
 	 */
-	if (usedvecs >= affvecs)
-		curvec = affd->pre_vectors;
-	else
-		curvec = affd->pre_vectors + usedvecs;
-	cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
-	usedvecs += irq_build_affinity_masks(affd, curvec, affvecs,
-					     node_to_cpumask, npresmsk,
-					     nmsk, masks);
-	put_online_cpus();
+	nr_sets = affd->nr_sets;
+	if (!nr_sets)
+		nr_sets = 1;
+
+	for (i = 0, usedvecs = 0; i < nr_sets; i++) {
+		int this_vecs = affd->sets ? affd->sets[i] : affvecs;
+		int ret;
+
+		ret = irq_build_affinity_masks(affd, curvec, this_vecs,
+						curvec, node_to_cpumask, masks);
+		if (ret) {
+				kfree(masks);
+				masks = NULL;
+				goto outnodemsk;
+		}
+		curvec += this_vecs;
+		usedvecs += this_vecs;
+	}
 
 	/* Fill out vectors at the end that don't need affinity */
 	if (usedvecs >= affvecs)
@@ -241,10 +289,6 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 
 outnodemsk:
 	free_node_to_cpumask(node_to_cpumask);
-outnpresmsk:
-	free_cpumask_var(npresmsk);
-outcpumsk:
-	free_cpumask_var(nmsk);
 	return masks;
 }
 
@@ -258,13 +302,21 @@ int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity
 {
 	int resv = affd->pre_vectors + affd->post_vectors;
 	int vecs = maxvec - resv;
-	int ret;
+	int set_vecs;
 
 	if (resv > minvec)
 		return 0;
 
-	get_online_cpus();
-	ret = min_t(int, cpumask_weight(cpu_possible_mask), vecs) + resv;
-	put_online_cpus();
-	return ret;
+	if (affd->nr_sets) {
+		int i;
+
+		for (i = 0, set_vecs = 0;  i < affd->nr_sets; i++)
+			set_vecs += affd->sets[i];
+	} else {
+		get_online_cpus();
+		set_vecs = cpumask_weight(cpu_possible_mask);
+		put_online_cpus();
+	}
+
+	return resv + min(set_vecs, vecs);
 }
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 2868d85f1fb1..fac0ddf8a8e2 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -764,9 +764,9 @@ blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 	if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP))
 		return NULL;
 
-	if (!bio->bi_css)
+	if (!bio->bi_blkg)
 		return NULL;
-	return cgroup_get_kernfs_id(bio->bi_css->cgroup);
+	return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup);
 }
 #else
 static union kernfs_node_id *