[PATCH v8 09/10] nvme-multipath: add debugfs attribute latency_stat

[Nilay Shroff <nilay@linux.ibm.com>]

This commit introduces a new debugfs attribute, "latency_stat", under
both per-path and head debugfs directories (defined under /sys/kernel/
debug/block/). This attribute provides visibility into the internal
state of the latency I/O policy to aid in debugging and performance
analysis.

For per-path entries, "latency_stat" reports the corresponding path
statistics such as I/O weight, selection count, processed samples, and
ignored samples.

For head entries, it reports per-CPU statistics for each reachable path,
including I/O weight, path score, smoothed (EWMA) latency, selection
count, processed samples, and ignored samples.

These additions enhance observability of the I/O path selection behavior
and help diagnose imbalance or instability in multipath performance.

Reviewed-by: Guixin Liu <kanie@linux.alibaba.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 drivers/nvme/host/debugfs.c | 123 ++++++++++++++++++++++++++++++++++++
 1 file changed, 123 insertions(+)

diff --git a/drivers/nvme/host/debugfs.c b/drivers/nvme/host/debugfs.c
index b8850d37edce..b3496951f0b1 100644
--- a/drivers/nvme/host/debugfs.c
+++ b/drivers/nvme/host/debugfs.c
@@ -184,6 +184,125 @@ static ssize_t nvme_latency_batch_timeout_store(void *data,
 	WRITE_ONCE(head->latency_batch_timeout, res * NSEC_PER_SEC);
 	return count;
 }
+
+#define TO_CTX(m)       ((struct nvme_debugfs_ctx *)m->private)
+#define TO_NS_HEAD(m)   ((struct nvme_ns_head *)(TO_CTX(m)->data))
+
+static void *nvme_mpath_latency_stat_start(struct seq_file *m, loff_t *pos)
+	__acquires_shared(&TO_NS_HEAD(m)->srcu)
+{
+	struct nvme_ns *ns;
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns_head *head = ctx->data;
+	loff_t n = *pos;
+
+	/* Remember srcu index, so we can unlock later. */
+	ctx->srcu_idx = srcu_read_lock(&head->srcu);
+	ns = list_first_or_null_rcu(&head->list, struct nvme_ns, siblings);
+
+	while (n && ns) {
+		ns = list_next_or_null_rcu(&head->list, &ns->siblings,
+				struct nvme_ns, siblings);
+		n--;
+	}
+
+	return ns;
+}
+
+static void *nvme_mpath_latency_stat_next(struct seq_file *m, void *v,
+		loff_t *pos)
+{
+	struct nvme_ns *ns = v;
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns_head *head = ctx->data;
+
+	(*pos)++;
+
+	return list_next_or_null_rcu(&head->list, &ns->siblings,
+			struct nvme_ns, siblings);
+}
+
+static void nvme_mpath_latency_stat_stop(struct seq_file *m, void *v)
+	__releases_shared(&TO_NS_HEAD(m)->srcu)
+{
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns_head *head = ctx->data;
+
+	srcu_read_unlock(&head->srcu, ctx->srcu_idx);
+}
+
+static int nvme_mpath_latency_stat_show(struct seq_file *m, void *v)
+{
+	int i, cpu;
+	struct nvme_path_lat_stat *stat;
+	struct nvme_ns *ns = v;
+
+	seq_printf(m, "%s:\n", ns->disk->disk_name);
+	for_each_online_cpu(cpu) {
+		seq_printf(m, "cpu %d : ", cpu);
+		for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+			stat = &per_cpu_ptr(ns->path_lat, cpu)[i].stat;
+			seq_printf(m, "%u %u %llu %llu %llu %llu %llu ",
+				stat->weight, stat->credit, stat->score,
+				stat->slat_ns, stat->sel,
+				stat->nr_samples, stat->nr_ignored);
+		}
+		seq_putc(m, '\n');
+	}
+	return 0;
+}
+
+static const struct seq_operations nvme_mpath_latency_stat_seq_ops = {
+	.start = nvme_mpath_latency_stat_start,
+	.next  = nvme_mpath_latency_stat_next,
+	.stop  = nvme_mpath_latency_stat_stop,
+	.show  = nvme_mpath_latency_stat_show
+};
+
+static void nvme_latency_stat_read_all(struct nvme_ns *ns,
+		struct nvme_path_lat_stat *batch)
+{
+	int i, cpu;
+	u32 ncpu[NVME_NUM_STAT_GROUPS] = {0};
+	struct nvme_path_lat_stat *stat;
+
+	for_each_online_cpu(cpu) {
+		for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+			stat = &per_cpu_ptr(ns->path_lat, cpu)[i].stat;
+			batch[i].sel += stat->sel;
+			batch[i].nr_samples += stat->nr_samples;
+			batch[i].nr_ignored += stat->nr_ignored;
+			batch[i].weight += stat->weight;
+			if (stat->weight)
+				ncpu[i]++;
+		}
+	}
+
+	for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+		if (!ncpu[i])
+			continue;
+		batch[i].weight = DIV_U64_ROUND_CLOSEST(batch[i].weight,
+				ncpu[i]);
+	}
+}
+
+static int nvme_ns_latency_stat_show(void *data, struct seq_file *m)
+{
+	int i;
+	struct nvme_path_lat_stat stat[NVME_NUM_STAT_GROUPS] = {0};
+	struct nvme_ns *ns = (struct nvme_ns *)data;
+
+	if (!ns->head->disk)
+		return 0;
+
+	nvme_latency_stat_read_all(ns, stat);
+	for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+		seq_printf(m, "%u %llu %llu %llu ",
+			stat[i].weight, stat[i].sel,
+			stat[i].nr_samples, stat[i].nr_ignored);
+	}
+	return 0;
+}
 #endif
 
 static const struct nvme_debugfs_attr nvme_mpath_debugfs_attrs[] = {
@@ -192,11 +311,15 @@ static const struct nvme_debugfs_attr nvme_mpath_debugfs_attrs[] = {
 			nvme_latency_ewma_shift_store},
 	{"latency_batch_timeout", 0600, nvme_latency_batch_timeout_show,
 			nvme_latency_batch_timeout_store},
+	{"latency_stat", 0400, .seq_ops = &nvme_mpath_latency_stat_seq_ops},
 #endif
 	{},
 };
 
 static const struct nvme_debugfs_attr nvme_ns_debugfs_attrs[] = {
+#ifdef CONFIG_NVME_MULTIPATH
+	{"latency_stat", 0400, nvme_ns_latency_stat_show},
+#endif
 	{},
 };
 
-- 
2.53.0