Merge tag 'zonefs-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs

Pull zonefs updates from Damien Le Moal:
 "This improves zonefs open sequential file accounting and adds
  accounting for active sequential files to allow the user to handle the
  maximum number of active zones of an NVMe ZNS drive.

  sysfs attributes for both open and active sequential files are also
  added to facilitate access to this information from applications
  without resorting to inspecting the block device limits"

* tag 'zonefs-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs:
  documentation: zonefs: Document sysfs attributes
  documentation: zonefs: Cleanup the mount options section
  zonefs: Add active seq file accounting
  zonefs: Export open zone resource information through sysfs
  zonefs: Always do seq file write open accounting
  zonefs: Rename super block information fields
  zonefs: Fix management of open zones
  zonefs: Clear inode information flags on inode creation

Documentation/filesystems/zonefs.rst

@@ -306,8 +306,15 @@ Further notes:
 Mount options
 -------------
 
-zonefs define the "errors=<behavior>" mount option to allow the user to specify
-zonefs behavior in response to I/O errors, inode size inconsistencies or zone
+zonefs defines several mount options:
+* errors=<behavior>
+* explicit-open
+
+"errors=<behavior>" option
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The "errors=<behavior>" option mount option allows the user to specify zonefs
+behavior in response to I/O errors, inode size inconsistencies or zone
 condition changes. The defined behaviors are as follow:
 
 * remount-ro (default)
@@ -326,6 +333,9 @@ discover the amount of data that has been written to the zone. In the case of a
 read-only zone discovered at run-time, as indicated in the previous section.
 The size of the zone file is left unchanged from its last updated value.
 
+"explicit-open" option
+~~~~~~~~~~~~~~~~~~~~~~
+
 A zoned block device (e.g. an NVMe Zoned Namespace device) may have limits on
 the number of zones that can be active, that is, zones that are in the
 implicit open, explicit open or closed conditions.  This potential limitation
@@ -341,6 +351,44 @@ guaranteed that write requests can be processed. Conversely, the
 to the device on the last close() of a zone file if the zone is not full nor
 empty.
 
+Runtime sysfs attributes
+------------------------
+
+zonefs defines several sysfs attributes for mounted devices.  All attributes
+are user readable and can be found in the directory /sys/fs/zonefs/<dev>/,
+where <dev> is the name of the mounted zoned block device.
+
+The attributes defined are as follows.
+
+* **max_wro_seq_files**:  This attribute reports the maximum number of
+  sequential zone files that can be open for writing.  This number corresponds
+  to the maximum number of explicitly or implicitly open zones that the device
+  supports.  A value of 0 means that the device has no limit and that any zone
+  (any file) can be open for writing and written at any time, regardless of the
+  state of other zones.  When the *explicit-open* mount option is used, zonefs
+  will fail any open() system call requesting to open a sequential zone file for
+  writing when the number of sequential zone files already open for writing has
+  reached the *max_wro_seq_files* limit.
+* **nr_wro_seq_files**:  This attribute reports the current number of sequential
+  zone files open for writing.  When the "explicit-open" mount option is used,
+  this number can never exceed *max_wro_seq_files*.  If the *explicit-open*
+  mount option is not used, the reported number can be greater than
+  *max_wro_seq_files*.  In such case, it is the responsibility of the
+  application to not write simultaneously more than *max_wro_seq_files*
+  sequential zone files.  Failure to do so can result in write errors.
+* **max_active_seq_files**:  This attribute reports the maximum number of
+  sequential zone files that are in an active state, that is, sequential zone
+  files that are partially writen (not empty nor full) or that have a zone that
+  is explicitly open (which happens only if the *explicit-open* mount option is
+  used).  This number is always equal to the maximum number of active zones that
+  the device supports.  A value of 0 means that the mounted device has no limit
+  on the number of sequential zone files that can be active.
+* **nr_active_seq_files**:  This attributes reports the current number of
+  sequential zone files that are active. If *max_active_seq_files* is not 0,
+  then the value of *nr_active_seq_files* can never exceed the value of
+  *nr_active_seq_files*, regardless of the use of the *explicit-open* mount
+  option.
+
 Zonefs User Space Tools
 =======================
 

fs/zonefs/Makefile

@@ -3,4 +3,4 @@ ccflags-y				+= -I$(src)
 
 obj-$(CONFIG_ZONEFS_FS) += zonefs.o
 
-zonefs-y	:= super.o
+zonefs-y	:= super.o sysfs.o

fs/zonefs/sysfs.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Simple file system for zoned block devices exposing zones as files.
+ *
+ * Copyright (C) 2022 Western Digital Corporation or its affiliates.
+ */
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/blkdev.h>
+
+#include "zonefs.h"
+
+struct zonefs_sysfs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct zonefs_sb_info *sbi, char *buf);
+};
+
+static inline struct zonefs_sysfs_attr *to_attr(struct attribute *attr)
+{
+	return container_of(attr, struct zonefs_sysfs_attr, attr);
+}
+
+#define ZONEFS_SYSFS_ATTR_RO(name) \
+static struct zonefs_sysfs_attr zonefs_sysfs_attr_##name = __ATTR_RO(name)
+
+#define ATTR_LIST(name) &zonefs_sysfs_attr_##name.attr
+
+static ssize_t zonefs_sysfs_attr_show(struct kobject *kobj,
+				      struct attribute *attr, char *buf)
+{
+	struct zonefs_sb_info *sbi =
+		container_of(kobj, struct zonefs_sb_info, s_kobj);
+	struct zonefs_sysfs_attr *zonefs_attr =
+		container_of(attr, struct zonefs_sysfs_attr, attr);
+
+	if (!zonefs_attr->show)
+		return 0;
+
+	return zonefs_attr->show(sbi, buf);
+}
+
+static ssize_t max_wro_seq_files_show(struct zonefs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", sbi->s_max_wro_seq_files);
+}
+ZONEFS_SYSFS_ATTR_RO(max_wro_seq_files);
+
+static ssize_t nr_wro_seq_files_show(struct zonefs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", atomic_read(&sbi->s_wro_seq_files));
+}
+ZONEFS_SYSFS_ATTR_RO(nr_wro_seq_files);
+
+static ssize_t max_active_seq_files_show(struct zonefs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", sbi->s_max_active_seq_files);
+}
+ZONEFS_SYSFS_ATTR_RO(max_active_seq_files);
+
+static ssize_t nr_active_seq_files_show(struct zonefs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", atomic_read(&sbi->s_active_seq_files));
+}
+ZONEFS_SYSFS_ATTR_RO(nr_active_seq_files);
+
+static struct attribute *zonefs_sysfs_attrs[] = {
+	ATTR_LIST(max_wro_seq_files),
+	ATTR_LIST(nr_wro_seq_files),
+	ATTR_LIST(max_active_seq_files),
+	ATTR_LIST(nr_active_seq_files),
+	NULL,
+};
+ATTRIBUTE_GROUPS(zonefs_sysfs);
+
+static void zonefs_sysfs_sb_release(struct kobject *kobj)
+{
+	struct zonefs_sb_info *sbi =
+		container_of(kobj, struct zonefs_sb_info, s_kobj);
+
+	complete(&sbi->s_kobj_unregister);
+}
+
+static const struct sysfs_ops zonefs_sysfs_attr_ops = {
+	.show	= zonefs_sysfs_attr_show,
+};
+
+static struct kobj_type zonefs_sb_ktype = {
+	.default_groups = zonefs_sysfs_groups,
+	.sysfs_ops	= &zonefs_sysfs_attr_ops,
+	.release	= zonefs_sysfs_sb_release,
+};
+
+static struct kobject *zonefs_sysfs_root;
+
+int zonefs_sysfs_register(struct super_block *sb)
+{
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	int ret;
+
+	init_completion(&sbi->s_kobj_unregister);
+	ret = kobject_init_and_add(&sbi->s_kobj, &zonefs_sb_ktype,
+				   zonefs_sysfs_root, "%s", sb->s_id);
+	if (ret) {
+		kobject_put(&sbi->s_kobj);
+		wait_for_completion(&sbi->s_kobj_unregister);
+		return ret;
+	}
+
+	sbi->s_sysfs_registered = true;
+
+	return 0;
+}
+
+void zonefs_sysfs_unregister(struct super_block *sb)
+{
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+
+	if (!sbi || !sbi->s_sysfs_registered)
+		return;
+
+	kobject_del(&sbi->s_kobj);
+	kobject_put(&sbi->s_kobj);
+	wait_for_completion(&sbi->s_kobj_unregister);
+}
+
+int __init zonefs_sysfs_init(void)
+{
+	zonefs_sysfs_root = kobject_create_and_add("zonefs", fs_kobj);
+	if (!zonefs_sysfs_root)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void zonefs_sysfs_exit(void)
+{
+	kobject_put(zonefs_sysfs_root);
+	zonefs_sysfs_root = NULL;
+}

fs/zonefs/zonefs.h

@@ -12,6 +12,7 @@
 #include <linux/uuid.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
+#include <linux/kobject.h>
 
 /*
  * Maximum length of file names: this only needs to be large enough to fit
@@ -39,6 +40,7 @@ static inline enum zonefs_ztype zonefs_zone_type(struct blk_zone *zone)
 }
 
 #define ZONEFS_ZONE_OPEN	(1 << 0)
+#define ZONEFS_ZONE_ACTIVE	(1 << 1)
 
 /*
  * In-memory inode data.
@@ -182,8 +184,15 @@ struct zonefs_sb_info {
 	loff_t			s_blocks;
 	loff_t			s_used_blocks;
 
-	unsigned int		s_max_open_zones;
-	atomic_t		s_open_zones;
+	unsigned int		s_max_wro_seq_files;
+	atomic_t		s_wro_seq_files;
+
+	unsigned int		s_max_active_seq_files;
+	atomic_t		s_active_seq_files;
+
+	bool			s_sysfs_registered;
+	struct kobject		s_kobj;
+	struct completion	s_kobj_unregister;
 };
 
 static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb)
@@ -198,4 +207,9 @@ static inline struct zonefs_sb_info *ZONEFS_SB(struct super_block *sb)
 #define zonefs_warn(sb, format, args...)	\
 	pr_warn("zonefs (%s) WARNING: " format, sb->s_id, ## args)
 
+int zonefs_sysfs_register(struct super_block *sb);
+void zonefs_sysfs_unregister(struct super_block *sb);
+int zonefs_sysfs_init(void);
+void zonefs_sysfs_exit(void);
+
 #endif