[rocky8_10] History rebuild for kernel-4.18.0-553.92.1.el8_10

Makefile.rhelver

@@ -12,7 +12,7 @@ RHEL_MINOR = 10
 #
 # Use this spot to avoid future merge conflicts.
 # Do not trim this comment.
-RHEL_RELEASE = 553.89.1
+RHEL_RELEASE = 553.92.1
 
 #
 # ZSTREAM

arch/x86/events/intel/ds.c

@@ -2,12 +2,14 @@
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/sched/clock.h>
 
 #include <asm/cpu_entry_area.h>
 #include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/insn.h>
 #include <asm/io.h>
+#include <asm/timer.h>
 
 #include "../perf_event.h"
 
@@ -1541,6 +1543,27 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
 	return val;
 }
 
+static void setup_pebs_time(struct perf_event *event,
+			    struct perf_sample_data *data,
+			    u64 tsc)
+{
+	/* Converting to a user-defined clock is not supported yet. */
+	if (event->attr.use_clockid != 0)
+		return;
+
+	/*
+	 * Doesn't support the conversion when the TSC is unstable.
+	 * The TSC unstable case is a corner case and very unlikely to
+	 * happen. If it happens, the TSC in a PEBS record will be
+	 * dropped and fall back to perf_event_clock().
+	 */
+	if (!using_native_sched_clock() || !sched_clock_stable())
+		return;
+
+	data->time = native_sched_clock_from_tsc(tsc) + __sched_clock_offset;
+	data->sample_flags |= PERF_SAMPLE_TIME;
+}
+
 static void setup_pebs_fixed_sample_data(struct perf_event *event,
 				   struct pt_regs *iregs, void *__pebs,
 				   struct perf_sample_data *data,
@@ -1675,9 +1698,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	 *
 	 * We can only do this for the default trace clock.
 	 */
-	if (x86_pmu.intel_cap.pebs_format >= 3 &&
-		event->attr.use_clockid == 0)
-		data->time = native_sched_clock_from_tsc(pebs->tsc);
+	if (x86_pmu.intel_cap.pebs_format >= 3)
+		setup_pebs_time(event, data, pebs->tsc);
 
 	if (has_branch_stack(event))
 		data->br_stack = &cpuc->lbr_stack;
@@ -1739,8 +1761,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	perf_sample_data_init(data, 0, event->hw.last_period);
 	data->period = event->hw.last_period;
 
-	if (event->attr.use_clockid == 0)
-		data->time = native_sched_clock_from_tsc(basic->tsc);
+	setup_pebs_time(event, data, basic->tsc);
 
 	/*
 	 * We must however always use iregs for the unwinder to stay sane; the

block/blk-mq.c

@@ -25,6 +25,7 @@
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
 #include <linux/prefetch.h>
+#include RH_KABI_HIDE_INCLUDE(<linux/sched/isolation.h>)
 
 #include <trace/events/block.h>
 
@@ -1611,6 +1612,15 @@ static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx)
 	return cpu;
 }
 
+/*
+ * ->next_cpu is always calculated from hctx->cpumask, so simply use
+ * it for speeding up the check
+ */
+static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx)
+{
+        return hctx->next_cpu >= nr_cpu_ids;
+}
+
 /*
  * It'd be great if the workqueue API had a way to pass
  * in a mask and had some smarts for more clever placement.
@@ -1622,7 +1632,8 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 	bool tried = false;
 	int next_cpu = hctx->next_cpu;
 
-	if (hctx->queue->nr_hw_queues == 1)
+	/* Switch to unbound if no allowable CPUs in this hctx */
+	if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx))
 		return WORK_CPU_UNBOUND;
 
 	if (--hctx->next_cpu_batch <= 0) {
@@ -2648,23 +2659,38 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx)
 	return data.has_rq;
 }
 
-static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu,
-		struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx,
+		unsigned int this_cpu)
 {
-	if (cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) != cpu)
-		return false;
-	if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids)
-		return false;
-	return true;
+	enum hctx_type type = hctx->type;
+	int cpu;
+
+	/*
+	 * hctx->cpumask has to rule out isolated CPUs, but userspace still
+	 * might submit IOs on these isolated CPUs, so use the queue map to
+	 * check if all CPUs mapped to this hctx are offline
+	 */
+	for_each_online_cpu(cpu) {
+		struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue,
+				type, cpu);
+
+		if (h != hctx)
+			continue;
+
+		/* this hctx has at least one online CPU */
+		if (this_cpu != cpu)
+			return true;
+	}
+
+	return false;
 }
 
 static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 {
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
 
-	if (!cpumask_test_cpu(cpu, hctx->cpumask) ||
-	    !blk_mq_last_cpu_in_hctx(cpu, hctx))
+	if (blk_mq_hctx_has_online_cpu(hctx, cpu))
 		return 0;
 
 	/*
@@ -2691,12 +2717,28 @@ static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
+/*
+ * Check if one CPU is mapped to the specified hctx
+ *
+ * Isolated CPUs have been ruled out from hctx->cpumask, which is supposed
+ * to be used for scheduling kworker only. For other usage, please call this
+ * helper for checking if one CPU belongs to the specified hctx
+ */
+static bool blk_mq_cpu_mapped_to_hctx(unsigned int cpu,
+		const struct blk_mq_hw_ctx *hctx)
+{
+	struct blk_mq_hw_ctx *mapped_hctx = blk_mq_map_queue_type(hctx->queue,
+			hctx->type, cpu);
+
+	return mapped_hctx == hctx;
+}
+
 static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node)
 {
 	struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node,
 			struct blk_mq_hw_ctx, cpuhp_online);
 
-	if (cpumask_test_cpu(cpu, hctx->cpumask))
+	if (blk_mq_cpu_mapped_to_hctx(cpu, hctx))
 		clear_bit(BLK_MQ_S_INACTIVE, &hctx->state);
 	return 0;
 }
@@ -2714,7 +2756,7 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node)
 	enum hctx_type type;
 
 	hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead);
-	if (!cpumask_test_cpu(cpu, hctx->cpumask))
+	if (!blk_mq_cpu_mapped_to_hctx(cpu, hctx))
 		return 0;
 
 	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
@@ -3057,6 +3099,8 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
+		int cpu;
+
 		/*
 		 * If no software queues are mapped to this hardware queue,
 		 * disable it and free the request entries.
@@ -3083,6 +3127,15 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		 */
 		sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx);
 
+		/*
+		 * Rule out isolated CPUs from hctx->cpumask to avoid
+		 * running block kworker on isolated CPUs
+		 */
+		for_each_cpu(cpu, hctx->cpumask) {
+			if (cpu_is_isolated(cpu))
+				cpumask_clear_cpu(cpu, hctx->cpumask);
+		}
+
 		/*
 		 * Initialize batch roundrobin counts
 		 */
@@ -3392,6 +3445,12 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	if (!q->poll_cb)
 		goto err_exit;
 
+	/*
+	 * ->tag_set has to be setup before initialize hctx, which cpuphp
+	 * handler needs it for checking queue mapping
+	 */
+	q->tag_set = set;
+
 	if (blk_mq_alloc_ctxs(q))
 		goto err_exit;
 
@@ -3408,8 +3467,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	INIT_WORK(&q->timeout_work, blk_mq_timeout_work);
 	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
-	q->tag_set = set;
-
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
 	if (set->nr_maps > HCTX_TYPE_POLL &&
 	    set->map[HCTX_TYPE_POLL].nr_queues)