@@ -15,6 +15,14 @@ config VALIDATE_FS_PARSER
Enable this to perform validation of the parameter description for a
filesystem when it is registered.
+config FS_IOSTATS
+ bool "Enable generic filesystem I/O statistics"
+ help
+ Enable this to allow collecting filesystem I/O statistics and display
+ them in /proc/<pid>/mountstats.
+
+ Say N if unsure.
+
config FS_IOMAP
bool
@@ -36,6 +36,7 @@
#include <linux/lockdep.h>
#include <linux/user_namespace.h>
#include <linux/fs_context.h>
+#include <linux/fs_iostats.h>
#include <uapi/linux/mount.h>
#include "internal.h"
@@ -179,6 +180,7 @@ static void destroy_unused_super(struct super_block *s)
up_write(&s->s_umount);
list_lru_destroy(&s->s_dentry_lru);
list_lru_destroy(&s->s_inode_lru);
+ sb_iostats_destroy(s);
security_sb_free(s);
put_user_ns(s->s_user_ns);
kfree(s->s_subtype);
@@ -230,6 +232,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
if (security_sb_alloc(s))
goto fail;
+ if (type->fs_flags & FS_SB_IOSTATS && sb_iostats_init(s))
+ goto fail;
+
for (i = 0; i < SB_FREEZE_LEVELS; i++) {
if (__percpu_init_rwsem(&s->s_writers.rw_sem[i],
sb_writers_name[i],
@@ -290,6 +295,7 @@ static void __put_super(struct super_block *s)
WARN_ON(s->s_dentry_lru.node);
WARN_ON(s->s_inode_lru.node);
WARN_ON(!list_empty(&s->s_mounts));
+ sb_iostats_destroy(s);
security_sb_free(s);
fscrypt_sb_free(s);
put_user_ns(s->s_user_ns);
@@ -1455,6 +1455,8 @@ struct sb_writers {
struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS];
};
+struct sb_iostats;
+
struct super_block {
struct list_head s_list; /* Keep this first */
dev_t s_dev; /* search index; _not_ kdev_t */
@@ -1509,8 +1511,12 @@ struct super_block {
/* Granularity of c/m/atime in ns (cannot be worse than a second) */
u32 s_time_gran;
/* Time limits for c/m/atime in seconds */
- time64_t s_time_min;
- time64_t s_time_max;
+ time64_t s_time_min;
+ time64_t s_time_max;
+#ifdef CONFIG_FS_IOSTATS
+ /* Optional per-sb I/O stats */
+ struct sb_iostats *s_iostats;
+#endif
#ifdef CONFIG_FSNOTIFY
__u32 s_fsnotify_mask;
struct fsnotify_mark_connector __rcu *s_fsnotify_marks;
@@ -2435,6 +2441,7 @@ struct file_system_type {
#define FS_USERNS_MOUNT (1<<3) /* Can be mounted by userns root */
#define FS_DISALLOW_NOTIFY_PERM (1<<4) /* Disable fanotify permission events */
#define FS_ALLOW_IDMAP (1<<5) /* FS can handle vfs idmappings */
+#define FS_SB_IOSTATS (1<<6) /* FS has generic per-sb I/O stats */
#define FS_RENAME_DOES_D_MOVE (1<<15) /* FS will handle d_move() internally */
int (*init_fs_context)(struct fs_context *);
const struct fs_parameter_spec *parameters;
new file mode 100644
@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_FS_IOSTATS_H
+#define _LINUX_FS_IOSTATS_H
+
+#include <linux/fs.h>
+#include <linux/percpu_counter.h>
+#include <linux/slab.h>
+
+/* Similar to task_io_accounting members */
+enum {
+ SB_IOSTATS_CHARS_RD, /* bytes read via syscalls */
+ SB_IOSTATS_CHARS_WR, /* bytes written via syscalls */
+ SB_IOSTATS_SYSCALLS_RD, /* # of read syscalls */
+ SB_IOSTATS_SYSCALLS_WR, /* # of write syscalls */
+ SB_IOSTATS_COUNTERS_NUM
+};
+
+struct sb_iostats {
+ time64_t start_time;
+ struct percpu_counter counter[SB_IOSTATS_COUNTERS_NUM];
+};
+
+#ifdef CONFIG_FS_IOSTATS
+static inline struct sb_iostats *sb_iostats(struct super_block *sb)
+{
+ return sb->s_iostats;
+}
+
+static inline bool sb_has_iostats(struct super_block *sb)
+{
+ return !!sb->s_iostats;
+}
+
+/* Initialize per-sb I/O stats */
+static inline int sb_iostats_init(struct super_block *sb)
+{
+ int err;
+
+ if (sb->s_iostats)
+ return 0;
+
+ sb->s_iostats = kmalloc(sizeof(struct sb_iostats), GFP_KERNEL);
+ if (!sb->s_iostats)
+ return -ENOMEM;
+
+ err = percpu_counters_init(sb->s_iostats->counter,
+ SB_IOSTATS_COUNTERS_NUM, 0, GFP_KERNEL);
+ if (err) {
+ kfree(sb->s_iostats);
+ sb->s_iostats = NULL;
+ return err;
+ }
+
+ sb->s_iostats->start_time = ktime_get_seconds();
+ return 0;
+}
+
+static inline void sb_iostats_destroy(struct super_block *sb)
+{
+ if (!sb->s_iostats)
+ return;
+
+ percpu_counters_destroy(sb->s_iostats->counter,
+ SB_IOSTATS_COUNTERS_NUM);
+ kfree(sb->s_iostats);
+ sb->s_iostats = NULL;
+}
+
+static inline void sb_iostats_counter_inc(struct super_block *sb, int id)
+{
+ if (!sb->s_iostats)
+ return;
+
+ percpu_counter_inc_relaxed(&sb->s_iostats->counter[id]);
+}
+
+static inline void sb_iostats_counter_add(struct super_block *sb, int id,
+ s64 amt)
+{
+ if (!sb->s_iostats)
+ return;
+
+ percpu_counter_add_relaxed(&sb->s_iostats->counter[id], amt);
+}
+
+static inline s64 sb_iostats_counter_read(struct super_block *sb, int id)
+{
+ if (!sb->s_iostats)
+ return 0;
+
+ return percpu_counter_sum_positive(&sb->s_iostats->counter[id]);
+}
+
+#else /* !CONFIG_FS_IOSTATS */
+
+static inline struct sb_iostats *sb_iostats(struct super_block *sb)
+{
+ return NULL;
+}
+
+static inline bool sb_has_iostats(struct super_block *sb)
+{
+ return false;
+}
+
+static inline int sb_iostats_init(struct super_block *sb)
+{
+ return 0;
+}
+
+static inline void sb_iostats_destroy(struct super_block *sb)
+{
+}
+
+static inline void sb_iostats_counter_inc(struct super_block *sb, int id)
+{
+}
+
+static inline void sb_iostats_counter_add(struct super_block *sb, int id,
+ s64 amt)
+{
+}
+
+static inline s64 sb_iostats_counter_read(struct super_block *sb, int id)
+{
+ return 0;
+}
+#endif
+
+#endif /* _LINUX_FS_IOSTATS_H */
With CONFIG_FS_IOSTATS, filesystems can opt-in to generic per-sb I/O statistics by setting the FS_SB_IOSTATS fstype flag. These counters will be used to collect per-sb I/O statistics and display them in /proc/<pid>/mountstats. Signed-off-by: Amir Goldstein <amir73il@gmail.com> --- fs/Kconfig | 8 +++ fs/super.c | 6 ++ include/linux/fs.h | 11 +++- include/linux/fs_iostats.h | 130 +++++++++++++++++++++++++++++++++++++ 4 files changed, 153 insertions(+), 2 deletions(-) create mode 100644 include/linux/fs_iostats.h