[PATCH v5 14/19] mm, swap: add debugfs counters for xswap

[Baoquan He <baoquan.he@linux.dev>]

From: Baoquan He <hebaoquan@kylinos.cn>

The mapped range and the grow count are not visible from userspace.
This makes it hard to check if the grow thresholds work: we cannot see
how large the mapped range is, how much it grows, or how much free tail
it keeps.

Put this information in debugfs. It is a debugging aid, not a stable
interface, so it does not belong in sysfs or the ABI:

  # cat /sys/kernel/debug/xswap/xswap1
  type 0
  clusters_max 2038783
  clusters_mapped 292
  usage_pages 91456
  tail_free 16
  grows 3
  shrinks 0

The shrink counter is initialized here. It will start to increase when
the shrink path is added.

Signed-off-by: Baoquan He <hebaoquan@kylinos.cn>
---
 include/linux/swap.h |  3 ++
 mm/swapfile.c        | 78 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index f4eb1912d1e6..29623c5138ab 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -248,6 +248,9 @@ struct swap_info_struct {
 	unsigned long		nr_clusters_max;/* total clusters in the xswap address space */
 	unsigned long		nr_clusters_mapped; /* currently mapped cluster count */
 	struct mutex		xswap_lock;	/* serialize map/unmap operations */
+	struct dentry		*xswap_debugfs;	/* mapped range and counters */
+	atomic_long_t		xswap_grows;	/* grow operations so far */
+	atomic_long_t		xswap_shrinks;	/* shrink operations so far */
 #endif
 	struct list_head free_clusters; /* free clusters list */
 	struct list_head full_clusters; /* full clusters list */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index ba730fa19194..2624233b4fc2 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -46,12 +46,14 @@
 #include <linux/suspend.h>
 #include <linux/zswap.h>
 #include <linux/plist.h>
+#include <linux/debugfs.h>
 
 #include <asm/tlbflush.h>
 #include <linux/leafops.h>
 #include "swap_table.h"
 #include "internal.h"
 #include "swap.h"
+
 #define DEF_SWAP_PRIO  -1
 
 /*
@@ -92,6 +94,7 @@
 
 static bool xswap_should_grow(struct swap_info_struct *si);
 static unsigned long xswap_grow(struct swap_info_struct *si);
+static void xswap_debugfs_del(struct swap_info_struct *si);
 static int xswap_map_clusters(struct swap_info_struct *si,
 			      unsigned long start_idx, unsigned long nr);
 static void xswap_unmap_clusters(struct swap_info_struct *si,
@@ -3488,6 +3491,7 @@ static void free_swap_cluster_info(struct swap_info_struct *si)
 		 * pages, and the unmap helper handles an empty range.
 		 */
 		xswap_unmap_clusters(si, 0, si->nr_clusters_mapped);
+		xswap_debugfs_del(si);
 		free_vm_area(si->cluster_vm);
 		si->cluster_vm = NULL;
 		si->cluster_info = NULL;
@@ -4265,6 +4269,7 @@ static unsigned long xswap_grow(struct swap_info_struct *si)
 		spin_unlock(&ci->lock);
 	}
 
+	atomic_long_inc(&si->xswap_grows);
 	return nr_new;
 }
 
@@ -4336,6 +4341,73 @@ static int xswap_mapped_end(pte_t *pte, unsigned long addr, void *data)
 	*mapped_end = addr + PAGE_SIZE;
 	return 0;
 }
+static ssize_t xswap_debugfs_read(struct file *file, char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct swap_info_struct *si = file->private_data;
+	struct swap_cluster_info *ci;
+	unsigned long mapped, tail = 0;
+	char tmp[192];
+	int len;
+
+	/*
+	 * The same scan the shrink does.  xswap_lock is what keeps
+	 * cluster_info from being unmapped under it.
+	 */
+	mutex_lock(&si->xswap_lock);
+	mapped = READ_ONCE(si->nr_clusters_mapped);
+	if (si->cluster_info) {
+		while (mapped - tail > 1) {
+			ci = &si->cluster_info[mapped - tail - 1];
+			if (READ_ONCE(ci->count) ||
+			    READ_ONCE(ci->flags) != CLUSTER_FLAG_FREE)
+				break;
+			tail++;
+		}
+	}
+	len = scnprintf(tmp, sizeof(tmp),
+			"type %d\nclusters_max %lu\nclusters_mapped %lu\nusage_pages %lu\ntail_free %lu\ngrows %lu\nshrinks %lu\n",
+			si->type, READ_ONCE(si->nr_clusters_max), mapped,
+			swap_usage_in_pages(si), tail,
+			atomic_long_read(&si->xswap_grows),
+			atomic_long_read(&si->xswap_shrinks));
+	mutex_unlock(&si->xswap_lock);
+
+	return simple_read_from_buffer(buf, count, ppos, tmp, len);
+}
+
+static const struct file_operations xswap_debugfs_fops = {
+	.read	= xswap_debugfs_read,
+	.open	= simple_open,
+	.llseek	= default_llseek,
+};
+
+static struct dentry *xswap_debugfs_root;
+
+static void xswap_debugfs_add(struct swap_info_struct *si)
+{
+	char name[32];
+
+	if (!xswap_debugfs_root)
+		xswap_debugfs_root = debugfs_create_dir("xswap", NULL);
+	if (IS_ERR_OR_NULL(xswap_debugfs_root))
+		return;
+
+	/* debugfs_create_file() takes the name as it is; no formatting. */
+	snprintf(name, sizeof(name), "xswap%llu",
+		 (unsigned long long)si->xswap_id);
+	si->xswap_debugfs = debugfs_create_file(name, 0444,
+						xswap_debugfs_root, si,
+						&xswap_debugfs_fops);
+	if (IS_ERR(si->xswap_debugfs))
+		si->xswap_debugfs = NULL;
+}
+
+static void xswap_debugfs_del(struct swap_info_struct *si)
+{
+	debugfs_remove(si->xswap_debugfs);
+	si->xswap_debugfs = NULL;
+}
 #endif /* CONFIG_XSWAP */
 
 static int setup_swap_clusters_info(struct swap_info_struct *si,
@@ -4552,6 +4624,10 @@ static int xswap_create(int prio)
 	 */
 	si->ops = &swap_bdev_ops;
 
+	si->xswap_debugfs = NULL;
+	atomic_long_set(&si->xswap_grows, 0);
+	atomic_long_set(&si->xswap_shrinks, 0);
+
 	error = setup_swap_clusters_info(si, NULL, maxpages);
 	if (error)
 		goto bad_swap;
@@ -4561,6 +4637,8 @@ static int xswap_create(int prio)
 		goto bad_swap;
 
 	mutex_lock(&swapon_mutex);
+	/* Two creates would race to make the root directory. */
+	xswap_debugfs_add(si);
 	si->prio = prio;
 	si->list.prio = -si->prio;
 	si->avail_list.prio = -si->prio;
-- 
2.54.0