* [PATCH 4/6] vfs: Allow mount information to be queried by fsinfo() [ver #15]
From: David Howells @ 2019-06-28 15:47 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173681842.14728.9331700785061885270.stgit@warthog.procyon.org.uk>
Allow mount information, including information about the topology tree to
be queried with the fsinfo() system call. Usage of AT_FSINFO_MOUNTID_PATH
allows overlapping mounts to be queried.
To this end, four fsinfo() attributes are provided:
(1) FSINFO_ATTR_MOUNT_INFO.
This is a structure providing information about a mount, including:
- Mounted superblock ID.
- Mount ID (as AT_FSINFO_MOUNTID_PATH).
- Parent mount ID.
- Mount attributes (eg. R/O, NOEXEC).
- A change counter.
Note that the parent mount ID is overridden to the ID of the queried
mount if the parent lies outside of the chroot or dfd tree.
(2) FSINFO_ATTR_MOUNT_DEVNAME.
This a string providing the device name associated with the mount.
Note that the device name may be a path that lies outside of the root.
(3) FSINFO_ATTR_MOUNT_CHILDREN.
This produces an array of structures, one for each child and capped
with one for the argument mount (checked after listing all the
children). Each element contains the mount ID and the change counter
of the respective mount object.
(4) FSINFO_ATTR_MOUNT_SUBMOUNT.
This is a 1D array of strings, indexed with struct fsinfo_params::Nth.
Each string is the relative pathname of the corresponding child
returned by FSINFO_ATTR_MOUNT_CHILDREN.
Note that paths in the mount at the base of the tree (whether that be
dfd or chroot) are relative to the base of the tree, not the root
directory of that mount.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/d_path.c | 2
fs/fsinfo.c | 8 ++
fs/internal.h | 9 ++
fs/namespace.c | 177 +++++++++++++++++++++++++++++++++++++++++++
include/uapi/linux/fsinfo.h | 28 +++++++
samples/vfs/test-fsinfo.c | 47 +++++++++++
6 files changed, 267 insertions(+), 4 deletions(-)
diff --git a/fs/d_path.c b/fs/d_path.c
index e8fce6b1174f..71b3e8cd79b8 100644
--- a/fs/d_path.c
+++ b/fs/d_path.c
@@ -227,7 +227,7 @@ static int prepend_unreachable(char **buffer, int *buflen)
return prepend(buffer, buflen, "(unreachable)", 13);
}
-static void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
+void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
{
unsigned seq;
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index aee7fedace19..758d1cbf8eba 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -353,6 +353,10 @@ int generic_fsinfo(struct path *path, struct fsinfo_kparams *params)
case _genf(PARAM_SPECIFICATION, param_specification);
case _genf(PARAM_ENUM, param_enum);
case _genp(PARAMETERS, parameters);
+ case _genp(MOUNT_INFO, mount_info);
+ case _genp(MOUNT_DEVNAME, mount_devname);
+ case _genp(MOUNT_CHILDREN, mount_children);
+ case _genp(MOUNT_SUBMOUNT, mount_submount);
default:
return -EOPNOTSUPP;
}
@@ -637,6 +641,10 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRING_N (SERVER_NAME),
FSINFO_STRUCT_NM (SERVER_ADDRESS, server_address),
FSINFO_STRING (AFS_CELL_NAME),
+ FSINFO_STRUCT (MOUNT_INFO, mount_info),
+ FSINFO_STRING (MOUNT_DEVNAME),
+ FSINFO_STRUCT_ARRAY (MOUNT_CHILDREN, mount_child),
+ FSINFO_STRING_N (MOUNT_SUBMOUNT),
};
/**
diff --git a/fs/internal.h b/fs/internal.h
index d5283a55b25d..d75bdd97cdd9 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -52,6 +52,11 @@ void __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
*/
extern void __init chrdev_init(void);
+/*
+ * d_path.c
+ */
+extern void get_fs_root_rcu(struct fs_struct *fs, struct path *root);
+
/*
* fs_context.c
*/
@@ -97,6 +102,10 @@ extern void __mnt_drop_write_file(struct file *);
extern void dissolve_on_fput(struct vfsmount *);
extern int lookup_mount_object(struct path *, int, struct path *);
+extern int fsinfo_generic_mount_info(struct path *, struct fsinfo_kparams *);
+extern int fsinfo_generic_mount_devname(struct path *, struct fsinfo_kparams *);
+extern int fsinfo_generic_mount_children(struct path *, struct fsinfo_kparams *);
+extern int fsinfo_generic_mount_submount(struct path *, struct fsinfo_kparams *);
/*
* fs_struct.c
diff --git a/fs/namespace.c b/fs/namespace.c
index c306e9362604..925602b8c329 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -29,6 +29,7 @@
#include <linux/sched/task.h>
#include <uapi/linux/mount.h>
#include <linux/fs_context.h>
+#include <linux/fsinfo.h>
#include "pnode.h"
#include "internal.h"
@@ -4108,3 +4109,179 @@ int lookup_mount_object(struct path *root, int mnt_id, struct path *_mntpt)
unlock_mount_hash();
goto out_unlock;
}
+
+#ifdef CONFIG_FSINFO
+int fsinfo_generic_mount_info(struct path *path, struct fsinfo_kparams *params)
+{
+ struct fsinfo_mount_info *p = params->buffer;
+ struct super_block *sb;
+ struct mount *m;
+ struct path root;
+ unsigned int flags;
+
+ if (!path->mnt)
+ return -ENODATA;
+
+ m = real_mount(path->mnt);
+ sb = m->mnt.mnt_sb;
+
+ p->f_sb_id = sb->s_unique_id;
+ p->mnt_id = m->mnt_id;
+ p->parent_id = m->mnt_parent->mnt_id;
+ p->change_counter = atomic_read(&m->mnt_change_counter);
+
+ get_fs_root(current->fs, &root);
+ if (path->mnt == root.mnt) {
+ p->parent_id = p->mnt_id;
+ } else {
+ rcu_read_lock();
+ if (!are_paths_connected(&root, path))
+ p->parent_id = p->mnt_id;
+ rcu_read_unlock();
+ }
+ if (IS_MNT_SHARED(m))
+ p->group_id = m->mnt_group_id;
+ if (IS_MNT_SLAVE(m)) {
+ int master = m->mnt_master->mnt_group_id;
+ int dom = get_dominating_id(m, &root);
+ p->master_id = master;
+ if (dom && dom != master)
+ p->from_id = dom;
+ }
+ path_put(&root);
+
+ flags = READ_ONCE(m->mnt.mnt_flags);
+ if (flags & MNT_READONLY)
+ p->attr |= MOUNT_ATTR_RDONLY;
+ if (flags & MNT_NOSUID)
+ p->attr |= MOUNT_ATTR_NOSUID;
+ if (flags & MNT_NODEV)
+ p->attr |= MOUNT_ATTR_NODEV;
+ if (flags & MNT_NOEXEC)
+ p->attr |= MOUNT_ATTR_NOEXEC;
+ if (flags & MNT_NODIRATIME)
+ p->attr |= MOUNT_ATTR_NODIRATIME;
+
+ if (flags & MNT_NOATIME)
+ p->attr |= MOUNT_ATTR_NOATIME;
+ else if (flags & MNT_RELATIME)
+ p->attr |= MOUNT_ATTR_RELATIME;
+ else
+ p->attr |= MOUNT_ATTR_STRICTATIME;
+ return sizeof(*p);
+}
+
+int fsinfo_generic_mount_devname(struct path *path, struct fsinfo_kparams *params)
+{
+ struct mount *m;
+ size_t len;
+
+ if (!path->mnt)
+ return -ENODATA;
+
+ m = real_mount(path->mnt);
+ len = strlen(m->mnt_devname);
+ memcpy(params->buffer, m->mnt_devname, len);
+ return len;
+}
+
+/*
+ * Store a mount record into the fsinfo buffer.
+ */
+static void store_mount_fsinfo(struct fsinfo_kparams *params,
+ struct fsinfo_mount_child *child)
+{
+ unsigned int usage = params->usage;
+ unsigned int total = sizeof(*child);
+
+ if (params->usage >= INT_MAX)
+ return;
+ params->usage = usage + total;
+ if (params->buffer && params->usage <= params->buf_size)
+ memcpy(params->buffer + usage, child, total);
+}
+
+/*
+ * Return information about the submounts relative to path.
+ */
+int fsinfo_generic_mount_children(struct path *path, struct fsinfo_kparams *params)
+{
+ struct fsinfo_mount_child record;
+ struct mount *m, *child;
+
+ if (!path->mnt)
+ return -ENODATA;
+
+ m = real_mount(path->mnt);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(child, &m->mnt_mounts, mnt_child) {
+ if (child->mnt_parent != m)
+ continue;
+ record.mnt_id = child->mnt_id;
+ record.change_counter = atomic_read(&child->mnt_change_counter);
+ store_mount_fsinfo(params, &record);
+ }
+ rcu_read_unlock();
+
+ /* End the list with a copy of the parameter mount's details so that
+ * userspace can quickly check for changes.
+ */
+ record.mnt_id = m->mnt_id;
+ record.change_counter = atomic_read(&m->mnt_change_counter);
+ store_mount_fsinfo(params, &record);
+ return params->usage;
+}
+
+/*
+ * Return the path of the Nth submount relative to path. This is derived from
+ * d_path(), but the root determination is more complicated.
+ */
+int fsinfo_generic_mount_submount(struct path *path, struct fsinfo_kparams *params)
+{
+ struct mountpoint *mp;
+ struct mount *m, *child;
+ struct path mountpoint, root;
+ unsigned int n = params->Nth;
+ size_t len;
+ void *p;
+
+ if (!path->mnt)
+ return -ENODATA;
+
+ rcu_read_lock();
+
+ m = real_mount(path->mnt);
+ list_for_each_entry_rcu(child, &m->mnt_mounts, mnt_child) {
+ mp = READ_ONCE(child->mnt_mp);
+ if (child->mnt_parent != m || !mp)
+ continue;
+ if (n-- == 0)
+ goto found;
+ }
+ rcu_read_unlock();
+ return -ENODATA;
+
+found:
+ mountpoint.mnt = path->mnt;
+ mountpoint.dentry = READ_ONCE(mp->m_dentry);
+
+ get_fs_root_rcu(current->fs, &root);
+ if (root.mnt != path->mnt) {
+ root.mnt = path->mnt;
+ root.dentry = path->mnt->mnt_root;
+ }
+
+ p = __d_path(&mountpoint, &root, params->buffer, params->buf_size);
+ rcu_read_unlock();
+
+ if (IS_ERR(p))
+ return PTR_ERR(p);
+ if (!p)
+ return -EPERM;
+
+ len = (params->buffer + params->buf_size) - p;
+ memmove(params->buffer, p, len);
+ return len;
+}
+#endif /* CONFIG_FSINFO */
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index 58a50207256f..401ad9625c11 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -35,6 +35,10 @@ enum fsinfo_attribute {
FSINFO_ATTR_SERVER_NAME = 17, /* Name of the Nth server (string) */
FSINFO_ATTR_SERVER_ADDRESS = 18, /* Mth address of the Nth server */
FSINFO_ATTR_AFS_CELL_NAME = 19, /* AFS cell name (string) */
+ FSINFO_ATTR_MOUNT_INFO = 20, /* Mount object information */
+ FSINFO_ATTR_MOUNT_DEVNAME = 21, /* Mount object device name (string) */
+ FSINFO_ATTR_MOUNT_CHILDREN = 22, /* Submount list (array) */
+ FSINFO_ATTR_MOUNT_SUBMOUNT = 23, /* Relative path of Nth submount (string) */
FSINFO_ATTR__NR
};
@@ -288,4 +292,28 @@ struct fsinfo_server_address {
struct __kernel_sockaddr_storage address;
};
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_MOUNT_INFO).
+ */
+struct fsinfo_mount_info {
+ __u64 f_sb_id; /* Superblock ID */
+ __u32 mnt_id; /* Mount identifier (use with AT_FSINFO_MOUNTID_PATH) */
+ __u32 parent_id; /* Parent mount identifier */
+ __u32 group_id; /* Mount group ID */
+ __u32 master_id; /* Slave master group ID */
+ __u32 from_id; /* Slave propagated from ID */
+ __u32 attr; /* MOUNT_ATTR_* flags */
+ __u32 change_counter; /* Number of changed applied. */
+ __u32 __reserved[1];
+};
+
+/*
+ * Information struct element for fsinfo(FSINFO_ATTR_MOUNT_CHILDREN).
+ * - An extra element is placed on the end representing the parent mount.
+ */
+struct fsinfo_mount_child {
+ __u32 mnt_id; /* Mount identifier (use with AT_FSINFO_MOUNTID_PATH) */
+ __u32 change_counter; /* Number of changes applied to mount. */
+};
+
#endif /* _UAPI_LINUX_FSINFO_H */
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index 27c4bb93c219..28c9f3cd2c8c 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -21,10 +21,10 @@
#include <errno.h>
#include <time.h>
#include <math.h>
-#include <fcntl.h>
#include <sys/syscall.h>
#include <linux/fsinfo.h>
#include <linux/socket.h>
+#include <linux/fcntl.h>
#include <sys/stat.h>
#include <arpa/inet.h>
@@ -86,6 +86,10 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRING_N (SERVER_NAME, server_name),
FSINFO_STRUCT_NM (SERVER_ADDRESS, server_address),
FSINFO_STRING (AFS_CELL_NAME, -),
+ FSINFO_STRUCT (MOUNT_INFO, mount_info),
+ FSINFO_STRING (MOUNT_DEVNAME, mount_devname),
+ FSINFO_STRUCT_ARRAY (MOUNT_CHILDREN, mount_child),
+ FSINFO_STRING_N (MOUNT_SUBMOUNT, mount_submount),
};
#define FSINFO_NAME(X,Y) [FSINFO_ATTR_##X] = #Y
@@ -110,6 +114,10 @@ static const char *fsinfo_attr_names[FSINFO_ATTR__NR] = {
FSINFO_NAME (SERVER_NAME, server_name),
FSINFO_NAME (SERVER_ADDRESS, server_address),
FSINFO_NAME (AFS_CELL_NAME, afs_cell_name),
+ FSINFO_NAME (MOUNT_INFO, mount_info),
+ FSINFO_NAME (MOUNT_DEVNAME, mount_devname),
+ FSINFO_NAME (MOUNT_CHILDREN, mount_children),
+ FSINFO_NAME (MOUNT_SUBMOUNT, mount_submount),
};
union reply {
@@ -123,6 +131,8 @@ union reply {
struct fsinfo_timestamp_info timestamps;
struct fsinfo_volume_uuid uuid;
struct fsinfo_server_address srv_addr;
+ struct fsinfo_mount_info mount_info;
+ struct fsinfo_mount_child mount_children[1];
};
static void dump_hex(unsigned int *data, int from, int to)
@@ -351,6 +361,29 @@ static void dump_attr_SERVER_ADDRESS(union reply *r, int size)
printf("family=%u\n", f->address.ss_family);
}
+static void dump_attr_MOUNT_INFO(union reply *r, int size)
+{
+ struct fsinfo_mount_info *f = &r->mount_info;
+
+ printf("\n");
+ printf("\tsb_id : %llx\n", (unsigned long long)f->f_sb_id);
+ printf("\tmnt_id : %x\n", f->mnt_id);
+ printf("\tparent : %x\n", f->parent_id);
+ printf("\tgroup : %x\n", f->group_id);
+ printf("\tattr : %x\n", f->attr);
+ printf("\tchanges : %x\n", f->change_counter);
+}
+
+static void dump_attr_MOUNT_CHILDREN(union reply *r, int size)
+{
+ struct fsinfo_mount_child *f = r->mount_children;
+ int i = 0;
+
+ printf("\n");
+ for (; size >= sizeof(*f); size -= sizeof(*f), f++)
+ printf("\t[%u] %8x %8x\n", i++, f->mnt_id, f->change_counter);
+}
+
/*
*
*/
@@ -367,6 +400,8 @@ static const dumper_t fsinfo_attr_dumper[FSINFO_ATTR__NR] = {
FSINFO_DUMPER(TIMESTAMP_INFO),
FSINFO_DUMPER(VOLUME_UUID),
FSINFO_DUMPER(SERVER_ADDRESS),
+ FSINFO_DUMPER(MOUNT_INFO),
+ FSINFO_DUMPER(MOUNT_CHILDREN),
};
static void dump_fsinfo(enum fsinfo_attribute attr,
@@ -569,16 +604,21 @@ int main(int argc, char **argv)
unsigned int attr;
int raw = 0, opt, Nth, Mth;
- while ((opt = getopt(argc, argv, "adlr"))) {
+ while ((opt = getopt(argc, argv, "Madlr"))) {
switch (opt) {
+ case 'M':
+ params.at_flags = AT_FSINFO_MOUNTID_PATH;
+ continue;
case 'a':
params.at_flags |= AT_NO_AUTOMOUNT;
+ params.at_flags &= ~AT_FSINFO_MOUNTID_PATH;
continue;
case 'd':
debug = true;
continue;
case 'l':
params.at_flags &= ~AT_SYMLINK_NOFOLLOW;
+ params.at_flags &= ~AT_FSINFO_MOUNTID_PATH;
continue;
case 'r':
raw = 1;
@@ -591,7 +631,8 @@ int main(int argc, char **argv)
argv += optind;
if (argc != 1) {
- printf("Format: test-fsinfo [-alr] <file>\n");
+ printf("Format: test-fsinfo [-adlr] <file>\n");
+ printf("Format: test-fsinfo [-dr] -M <mnt_id>\n");
exit(2);
}
^ permalink raw reply related
* [PATCH 3/6] vfs: Add mount change counter [ver #15]
From: David Howells @ 2019-06-28 15:47 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173681842.14728.9331700785061885270.stgit@warthog.procyon.org.uk>
Add a change counter on each mount object so that the user can easily check
to see if a mount has changed its attributes or its children.
Future patches will:
(1) Provide this value through fsinfo() attributes.
(2) Implement a watch_mount() system call to provide a notification
interface for userspace monitoring.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/mount.h | 22 ++++++++++++++++++++++
fs/namespace.c | 11 +++++++++++
2 files changed, 33 insertions(+)
diff --git a/fs/mount.h b/fs/mount.h
index 6250de544760..65cb51f47c8c 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -70,6 +70,7 @@ struct mount {
struct hlist_head mnt_pins;
struct fs_pin mnt_umount;
struct dentry *mnt_ex_mountpoint;
+ atomic_t mnt_change_counter; /* Number of changed applied */
} __randomize_layout;
#define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
@@ -151,3 +152,24 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
{
return ns->seq == 0;
}
+
+/*
+ * Type of mount topology change notification.
+ */
+enum mount_notification_subtype {
+ NOTIFY_MOUNT_NEW_MOUNT = 0, /* New mount added */
+ NOTIFY_MOUNT_UNMOUNT = 1, /* Mount removed manually */
+ NOTIFY_MOUNT_EXPIRY = 2, /* Automount expired */
+ NOTIFY_MOUNT_READONLY = 3, /* Mount R/O state changed */
+ NOTIFY_MOUNT_SETATTR = 4, /* Mount attributes changed */
+ NOTIFY_MOUNT_MOVE_FROM = 5, /* Mount moved from here */
+ NOTIFY_MOUNT_MOVE_TO = 6, /* Mount moved to here (compare op_id) */
+};
+
+static inline void notify_mount(struct mount *changed,
+ struct mount *aux,
+ enum mount_notification_subtype subtype,
+ u32 info_flags)
+{
+ atomic_inc(&changed->mnt_change_counter);
+}
diff --git a/fs/namespace.c b/fs/namespace.c
index d96bc1dfab03..c306e9362604 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -513,6 +513,8 @@ static int mnt_make_readonly(struct mount *mnt)
smp_wmb();
mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
unlock_mount_hash();
+ if (ret == 0)
+ notify_mount(mnt, NULL, NOTIFY_MOUNT_READONLY, 0x10000);
return ret;
}
@@ -521,6 +523,7 @@ static int __mnt_unmake_readonly(struct mount *mnt)
lock_mount_hash();
mnt->mnt.mnt_flags &= ~MNT_READONLY;
unlock_mount_hash();
+ notify_mount(mnt, NULL, NOTIFY_MOUNT_READONLY, 0);
return 0;
}
@@ -833,6 +836,7 @@ static void umount_mnt(struct mount *mnt)
{
/* old mountpoint will be dropped when we can do that */
mnt->mnt_ex_mountpoint = mnt->mnt_mountpoint;
+ notify_mount(mnt->mnt_parent, mnt, NOTIFY_MOUNT_UNMOUNT, 0);
unhash_mnt(mnt);
}
@@ -1472,6 +1476,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
p = list_first_entry(&tmp_list, struct mount, mnt_list);
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
+
ns = p->mnt_ns;
if (ns) {
ns->mounts--;
@@ -2095,7 +2100,10 @@ static int attach_recursive_mnt(struct mount *source_mnt,
lock_mount_hash();
}
if (parent_path) {
+ notify_mount(source_mnt->mnt_parent, source_mnt,
+ NOTIFY_MOUNT_MOVE_FROM, 0);
detach_mnt(source_mnt, parent_path);
+ notify_mount(dest_mnt, source_mnt, NOTIFY_MOUNT_MOVE_TO, 0);
attach_mnt(source_mnt, dest_mnt, dest_mp);
touch_mnt_namespace(source_mnt->mnt_ns);
} else {
@@ -2104,6 +2112,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
list_del_init(&source_mnt->mnt_ns->list);
}
mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
+ notify_mount(dest_mnt, source_mnt, NOTIFY_MOUNT_NEW_MOUNT, 0);
commit_tree(source_mnt);
}
@@ -2480,6 +2489,7 @@ static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags)
mnt->mnt.mnt_flags = mnt_flags;
touch_mnt_namespace(mnt->mnt_ns);
unlock_mount_hash();
+ notify_mount(mnt, NULL, NOTIFY_MOUNT_SETATTR, 0);
}
/*
@@ -2878,6 +2888,7 @@ void mark_mounts_for_expiry(struct list_head *mounts)
if (!xchg(&mnt->mnt_expiry_mark, 1) ||
propagate_mount_busy(mnt, 1))
continue;
+ notify_mount(mnt, NULL, NOTIFY_MOUNT_EXPIRY, 0);
list_move(&mnt->mnt_expire, &graveyard);
}
while (!list_empty(&graveyard)) {
^ permalink raw reply related
* [PATCH 2/6] vfs: Introduce a non-repeating system-unique superblock ID [ver #15]
From: David Howells @ 2019-06-28 15:47 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173681842.14728.9331700785061885270.stgit@warthog.procyon.org.uk>
Introduce an (effectively) non-repeating system-unique superblock ID that
can be used to determine that two object are in the same superblock without
risking reuse of the ID in the meantime (as is possible with device IDs).
The ID is time-based to make it harder to use it as a covert communications
channel.
Also make it so that this ID can be fetched by the fsinfo() system call.
The ID added so that superblock notification messages will also be able to
be tagged with it.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 1 +
fs/super.c | 24 ++++++++++++++++++++++++
include/linux/fs.h | 3 +++
samples/vfs/test-fsinfo.c | 1 +
4 files changed, 29 insertions(+)
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index 4eaa33b2188b..aee7fedace19 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -87,6 +87,7 @@ static int fsinfo_generic_ids(struct path *path, struct fsinfo_ids *p)
p->f_fstype = sb->s_magic;
p->f_dev_major = MAJOR(sb->s_dev);
p->f_dev_minor = MINOR(sb->s_dev);
+ p->f_sb_id = sb->s_unique_id;
memcpy(&p->f_fsid, &buf.f_fsid, sizeof(p->f_fsid));
strlcpy(p->f_fs_name, path->dentry->d_sb->s_type->name,
diff --git a/fs/super.c b/fs/super.c
index 2739f57515f8..c04f9481a708 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -43,6 +43,8 @@ static int thaw_super_locked(struct super_block *sb);
static LIST_HEAD(super_blocks);
static DEFINE_SPINLOCK(sb_lock);
+static u64 sb_last_identifier;
+static u64 sb_identifier_offset;
static char *sb_writers_name[SB_FREEZE_LEVELS] = {
"sb_writers",
@@ -187,6 +189,27 @@ static void destroy_unused_super(struct super_block *s)
destroy_super_work(&s->destroy_work);
}
+/*
+ * Generate a unique identifier for a superblock.
+ */
+static void generate_super_id(struct super_block *s)
+{
+ u64 id = ktime_to_ns(ktime_get());
+
+ spin_lock(&sb_lock);
+
+ id += sb_identifier_offset;
+ if (id <= sb_last_identifier) {
+ id = sb_last_identifier + 1;
+ sb_identifier_offset = sb_last_identifier - id;
+ }
+
+ sb_last_identifier = id;
+ spin_unlock(&sb_lock);
+
+ s->s_unique_id = id;
+}
+
/**
* alloc_super - create new superblock
* @type: filesystem type superblock should belong to
@@ -270,6 +293,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
goto fail;
if (list_lru_init_memcg(&s->s_inode_lru, &s->s_shrink))
goto fail;
+ generate_super_id(s);
return s;
fail:
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 50f58eac3e1f..61098cded376 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1527,6 +1527,9 @@ struct super_block {
spinlock_t s_inode_wblist_lock;
struct list_head s_inodes_wb; /* writeback inodes */
+
+ /* Superblock event notifications */
+ u64 s_unique_id;
} __randomize_layout;
/* Helper functions so that in most cases filesystems will
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index 6389ae781cbb..27c4bb93c219 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -185,6 +185,7 @@ static void dump_attr_IDS(union reply *r, int size)
printf("\tdev : %02x:%02x\n", f->f_dev_major, f->f_dev_minor);
printf("\tfs : type=%x name=%s\n", f->f_fstype, f->f_fs_name);
printf("\tfsid : %llx\n", (unsigned long long)f->f_fsid);
+ printf("\tsbid : %llx\n", (unsigned long long)f->f_sb_id);
}
static void dump_attr_LIMITS(union reply *r, int size)
^ permalink raw reply related
* [PATCH 1/6] vfs: Allow fsinfo() to look up a mount object by ID [ver #15]
From: David Howells @ 2019-06-28 15:47 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173681842.14728.9331700785061885270.stgit@warthog.procyon.org.uk>
Allow the fsinfo() syscall to look up a mount object by ID rather than by
pathname. This is necessary as there can be multiple mounts stacked up at
the same pathname and there's no way to look through them otherwise.
This is done by passing AT_FSINFO_MOUNTID_PATH to fsinfo() in the
parameters and then passing the mount ID as a string to fsinfo() in place
of the filename:
struct fsinfo_params params = {
.at_flags = AT_FSINFO_MOUNTID_PATH,
.request = FSINFO_ATTR_IDS,
};
ret = fsinfo(AT_FDCWD, "21", ¶ms, buffer, sizeof(buffer));
The caller is only permitted to query a mount object if the root directory
of that mount connects directly to the current chroot if dfd == AT_FDCWD[*]
or the directory specified by dfd otherwise. Note that this is not
available to the pathwalk of any other syscall.
[*] This needs to be something other than AT_FDCWD, perhaps AT_FDROOT.
[!] This probably needs an LSM hook.
[!] This might want to check the permissions on all the intervening dirs -
but it would have to do that under RCU conditions.
[!] This might want to check a CAP_* flag.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 56 +++++++++++++++++++++
fs/internal.h | 2 +
fs/namespace.c | 117 +++++++++++++++++++++++++++++++++++++++++++-
include/uapi/linux/fcntl.h | 1
4 files changed, 173 insertions(+), 3 deletions(-)
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index b3f605c39eb5..4eaa33b2188b 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -522,6 +522,57 @@ static int vfs_fsinfo_fscontext(int fd, struct fsinfo_kparams *params)
return ret;
}
+/*
+ * Look up the root of a mount object. This allows access to mount objects
+ * (and their attached superblocks) that can't be retrieved by path because
+ * they're entirely covered.
+ *
+ * We only permit access to a mount that has a direct path between either the
+ * dentry pointed to by dfd or to our chroot (if dfd is AT_FDCWD).
+ */
+static int vfs_fsinfo_mount(int dfd, const char __user *filename,
+ struct fsinfo_kparams *params)
+{
+ struct path path;
+ struct fd f = {};
+ char *name;
+ long mnt_id;
+ int ret;
+
+ if ((params->at_flags & ~AT_FSINFO_MOUNTID_PATH) ||
+ !filename)
+ return -EINVAL;
+
+ name = strndup_user(filename, 32);
+ if (IS_ERR(name))
+ return PTR_ERR(name);
+ ret = kstrtoul(name, 0, &mnt_id);
+ if (ret < 0)
+ goto out_name;
+ if (mnt_id > INT_MAX)
+ goto out_name;
+
+ if (dfd != AT_FDCWD) {
+ ret = -EBADF;
+ f = fdget_raw(dfd);
+ if (!f.file)
+ goto out_name;
+ }
+
+ ret = lookup_mount_object(f.file ? &f.file->f_path : NULL,
+ mnt_id, &path);
+ if (ret < 0)
+ goto out_fd;
+
+ ret = vfs_fsinfo(&path, params);
+ path_put(&path);
+out_fd:
+ fdput(f);
+out_name:
+ kfree(name);
+ return ret;
+}
+
/*
* Return buffer information by requestable attribute.
*
@@ -638,6 +689,9 @@ SYSCALL_DEFINE5(fsinfo,
if ((kparams.at_flags & AT_FSINFO_FROM_FSOPEN) && pathname)
return -EINVAL;
+ if ((kparams.at_flags & (AT_FSINFO_FROM_FSOPEN | AT_FSINFO_MOUNTID_PATH)) ==
+ (AT_FSINFO_FROM_FSOPEN | AT_FSINFO_MOUNTID_PATH))
+ return -EINVAL;
} else {
kparams.request = FSINFO_ATTR_STATFS;
}
@@ -696,6 +750,8 @@ SYSCALL_DEFINE5(fsinfo,
if (kparams.at_flags & AT_FSINFO_FROM_FSOPEN)
ret = vfs_fsinfo_fscontext(dfd, &kparams);
+ else if (kparams.at_flags & AT_FSINFO_MOUNTID_PATH)
+ ret = vfs_fsinfo_mount(dfd, pathname, &kparams);
else if (pathname)
ret = vfs_fsinfo_path(dfd, pathname, &kparams);
else
diff --git a/fs/internal.h b/fs/internal.h
index 0010889f2e85..d5283a55b25d 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -96,6 +96,8 @@ extern int __mnt_want_write_file(struct file *);
extern void __mnt_drop_write_file(struct file *);
extern void dissolve_on_fput(struct vfsmount *);
+extern int lookup_mount_object(struct path *, int, struct path *);
+
/*
* fs_struct.c
*/
diff --git a/fs/namespace.c b/fs/namespace.c
index ffb13f0562b0..d96bc1dfab03 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -62,7 +62,7 @@ static int __init set_mphash_entries(char *str)
__setup("mphash_entries=", set_mphash_entries);
static u64 event;
-static DEFINE_IDA(mnt_id_ida);
+static DEFINE_IDR(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);
static struct hlist_head *mount_hashtable __read_mostly;
@@ -101,17 +101,27 @@ static inline struct hlist_head *mp_hash(struct dentry *dentry)
static int mnt_alloc_id(struct mount *mnt)
{
- int res = ida_alloc(&mnt_id_ida, GFP_KERNEL);
+ int res;
+ /* Allocate an ID, but don't set the pointer back to the mount until
+ * later, as once we do that, we have to follow RCU protocols to get
+ * rid of the mount struct.
+ */
+ res = idr_alloc(&mnt_id_ida, NULL, 0, INT_MAX, GFP_KERNEL);
if (res < 0)
return res;
mnt->mnt_id = res;
return 0;
}
+static void mnt_publish_id(struct mount *mnt)
+{
+ idr_replace(&mnt_id_ida, mnt, mnt->mnt_id);
+}
+
static void mnt_free_id(struct mount *mnt)
{
- ida_free(&mnt_id_ida, mnt->mnt_id);
+ idr_remove(&mnt_id_ida, mnt->mnt_id);
}
/*
@@ -974,6 +984,7 @@ struct vfsmount *vfs_create_mount(struct fs_context *fc)
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts);
unlock_mount_hash();
+ mnt_publish_id(mnt);
return &mnt->mnt;
}
EXPORT_SYMBOL(vfs_create_mount);
@@ -1067,6 +1078,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
unlock_mount_hash();
+ mnt_publish_id(mnt);
if ((flag & CL_SLAVE) ||
((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) {
@@ -3986,3 +3998,102 @@ const struct proc_ns_operations mntns_operations = {
.install = mntns_install,
.owner = mntns_owner,
};
+
+/*
+ * See if one path point connects directly to another by ancestral relationship
+ * across mountpoints. Must call with the RCU read lock held.
+ */
+static bool are_paths_connected(struct path *ancestor, struct path *to_check)
+{
+ struct mount *mnt, *parent;
+ struct path cursor;
+ unsigned seq;
+ bool connected;
+
+ seq = 0;
+restart:
+ cursor = *to_check;
+
+ read_seqbegin_or_lock(&rename_lock, &seq);
+ while (cursor.mnt != ancestor->mnt) {
+ mnt = real_mount(cursor.mnt);
+ parent = READ_ONCE(mnt->mnt_parent);
+ if (mnt == parent)
+ goto failed;
+ cursor.dentry = READ_ONCE(mnt->mnt_mountpoint);
+ cursor.mnt = &parent->mnt;
+ }
+
+ while (cursor.dentry != ancestor->dentry) {
+ if (cursor.dentry == cursor.mnt->mnt_root ||
+ IS_ROOT(cursor.dentry))
+ goto failed;
+ cursor.dentry = READ_ONCE(cursor.dentry->d_parent);
+ }
+
+ connected = true;
+out:
+ done_seqretry(&rename_lock, seq);
+ return connected;
+
+failed:
+ if (need_seqretry(&rename_lock, seq)) {
+ seq = 1;
+ goto restart;
+ }
+ connected = false;
+ goto out;
+}
+
+/**
+ * lookup_mount_object - Look up a vfsmount object by ID
+ * @root: The mount root must connect backwards to this point (or chroot if NULL).
+ * @id: The ID of the mountpoint.
+ * @_mntpt: Where to return the resulting mountpoint path.
+ *
+ * Look up the root of the mount with the corresponding ID. This is only
+ * permitted if that mount connects directly to the specified root/chroot.
+ */
+int lookup_mount_object(struct path *root, int mnt_id, struct path *_mntpt)
+{
+ struct mount *mnt;
+ struct path stop, mntpt = {};
+ int ret = -EPERM;
+
+ if (!root)
+ get_fs_root(current->fs, &stop);
+ else
+ stop = *root;
+
+ rcu_read_lock();
+ lock_mount_hash();
+ mnt = idr_find(&mnt_id_ida, mnt_id);
+ if (!mnt)
+ goto out_unlock_mh;
+ if (mnt->mnt.mnt_flags & (MNT_SYNC_UMOUNT | MNT_UMOUNT | MNT_DOOMED))
+ goto out_unlock_mh;
+ if (mnt_get_count(mnt) == 0)
+ goto out_unlock_mh;
+ mnt_add_count(mnt, 1);
+ mntpt.mnt = &mnt->mnt;
+ mntpt.dentry = dget(mnt->mnt.mnt_root);
+ unlock_mount_hash();
+
+ if (are_paths_connected(&stop, &mntpt)) {
+ *_mntpt = mntpt;
+ mntpt.mnt = NULL;
+ mntpt.dentry = NULL;
+ ret = 0;
+ }
+
+out_unlock:
+ rcu_read_unlock();
+ if (!root)
+ path_put(&stop);
+ path_put(&mntpt);
+ return ret;
+
+out_unlock_mh:
+ unlock_mount_hash();
+ goto out_unlock;
+}
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 6a2402a8fa30..5fda91cfca8a 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -92,6 +92,7 @@
#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */
#define AT_FSINFO_FROM_FSOPEN 0x2000 /* Examine the fs_context attached to dfd by fsopen() */
+#define AT_FSINFO_MOUNTID_PATH 0x4000 /* The path is a mount object ID, not an actual path */
#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
^ permalink raw reply related
* [PATCH 0/6] fsinfo: Add mount topology query [ver #15]
From: David Howells @ 2019-06-28 15:46 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
Here's a set of patches that builds upon the previously posted fsinfo()
interface to:
(a) Make it possible to invoke a query based on a mount ID rather than a
path. This is done by setting AT_FSINFO_MOUNTID_PATH and pointing the
pathname argument to the mount ID as a string.
A pathname is not a unique handle into the mount topology tree. It's
possible for there to be multiple overlying mounts at any particular
point in the tree, and only the topmost can be directly accessed (the
bottom might be inferrable from the parent).
Usage of the mount ID permits all mount objects to be queried. It
would be possible to restrict the query based on the method used to
address the object, though I haven't done this for now.
(b) Provide a change ID for each mount object that is incremented each
time a change is applied to that mount object.
(c) Allow the mount topology to be queried. The mount topology
information returned is sprinkled with change IDs to make it easier to
check for changes during multiple queries. A future notification
mechanism will also help with this.
(d) Provide a system-unique superblock identifier that can be used to
check to see if a mount object references the same superblock as it
used to or as another mount object without relying on device numbers -
which might not be seen to change over an unmount-mount combo.
A sample is also provided that allows the mount topology tree at a point to
be listed.
The patches can be found here also:
https://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git
on branch:
fsinfo-mount
[!] Note that this depends on the fsinfo branch.
===================
SIGNIFICANT CHANGES
===================
ver #15:
(*) Split from the fsinfo-core branch.
(*) Rename notify_counter to change_counter as there's no notification
stuff here (that's in separate branches).
^ permalink raw reply
* [PATCH 11/11] fsinfo: proc - add sb operation fsinfo() [ver #15]
From: David Howells @ 2019-06-28 15:45 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
From: Ian Kent <raven@themaw.net>
The new fsinfo() system call adds a new super block operation
->fsinfo() which is used by file systems to provide file
system specific information for fsinfo() requests.
The fsinfo() request FSINFO_ATTR_PARAMETERS provides the same
function as sb operation ->show_options() so it needs to be
implemented by any file system that provides ->show_options()
as a minimum.
Also add a simple FSINFO_ATTR_CAPABILITIES implementation.
Signed-off-by: Ian Kent <raven@themaw.net>
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/proc/inode.c | 37 +++++++++++++++++++++++++++++++++++++
1 file changed, 37 insertions(+)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 5f8d215b3fd0..28c287aff6aa 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -24,6 +24,7 @@
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/mount.h>
+#include <linux/fsinfo.h>
#include <linux/uaccess.h>
@@ -115,6 +116,39 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root)
return 0;
}
+#ifdef CONFIG_FSINFO
+/*
+ * Get filesystem information.
+ */
+static int proc_fsinfo(struct path *path, struct fsinfo_kparams *params)
+{
+ struct super_block *sb = path->dentry->d_sb;
+ struct pid_namespace *pid = sb->s_fs_info;
+ struct fsinfo_capabilities *caps;
+
+ switch (params->request) {
+ case FSINFO_ATTR_CAPABILITIES:
+ caps = params->buffer;
+ fsinfo_set_cap(caps, FSINFO_CAP_IS_KERNEL_FS);
+ fsinfo_set_cap(caps, FSINFO_CAP_NOT_PERSISTENT);
+ return sizeof(*caps);
+
+ case FSINFO_ATTR_PARAMETERS:
+ fsinfo_note_sb_params(params, sb->s_flags);
+ if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
+ fsinfo_note_paramf(params, "gid", "%u",
+ from_kgid_munged(&init_user_ns, pid->pid_gid));
+ if (pid->hide_pid != HIDEPID_OFF)
+ fsinfo_note_paramf(params, "hidepid",
+ "%u", pid->hide_pid);
+ return params->usage;
+
+ default:
+ return generic_fsinfo(path, params);
+ }
+}
+#endif /* CONFIG_FSINFO */
+
const struct super_operations proc_sops = {
.alloc_inode = proc_alloc_inode,
.free_inode = proc_free_inode,
@@ -122,6 +156,9 @@ const struct super_operations proc_sops = {
.evict_inode = proc_evict_inode,
.statfs = simple_statfs,
.show_options = proc_show_options,
+#ifdef CONFIG_FSINFO
+ .fsinfo = proc_fsinfo,
+#endif
};
enum {BIAS = -1U<<31};
^ permalink raw reply related
* [PATCH 10/11] kernfs, cgroup: Add fsinfo support [ver #15]
From: David Howells @ 2019-06-28 15:45 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Add support for fsinfo() to kernfs and cgroup.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/kernfs/mount.c | 20 ++++++++++++++++++++
include/linux/kernfs.h | 4 ++++
kernel/cgroup/cgroup-v1.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
kernel/cgroup/cgroup.c | 19 +++++++++++++++++++
4 files changed, 87 insertions(+)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 9a4646eecb71..f40d467d274b 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -17,6 +17,7 @@
#include <linux/namei.h>
#include <linux/seq_file.h>
#include <linux/exportfs.h>
+#include <linux/fsinfo.h>
#include "kernfs-internal.h"
@@ -45,6 +46,22 @@ static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry)
return 0;
}
+#ifdef CONFIG_FSINFO
+static int kernfs_sop_fsinfo(struct path *path, struct fsinfo_kparams *params)
+{
+ struct kernfs_root *root = kernfs_root(kernfs_dentry_node(path->dentry));
+ struct kernfs_syscall_ops *scops = root->syscall_ops;
+ int ret;
+
+ if (scops && scops->fsinfo) {
+ ret = scops->fsinfo(root, params);
+ if (ret != -EAGAIN)
+ return ret;
+ }
+ return generic_fsinfo(path, params);
+}
+#endif
+
const struct super_operations kernfs_sops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
@@ -52,6 +69,9 @@ const struct super_operations kernfs_sops = {
.show_options = kernfs_sop_show_options,
.show_path = kernfs_sop_show_path,
+#ifdef CONFIG_FSINFO
+ .fsinfo = kernfs_sop_fsinfo,
+#endif
};
/*
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 2bf477f86eb1..d01ec4dc2db1 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -27,6 +27,7 @@ struct super_block;
struct file_system_type;
struct poll_table_struct;
struct fs_context;
+struct fsinfo_kparams;
struct kernfs_fs_context;
struct kernfs_open_node;
@@ -171,6 +172,9 @@ struct kernfs_node {
*/
struct kernfs_syscall_ops {
int (*show_options)(struct seq_file *sf, struct kernfs_root *root);
+#ifdef CONFIG_FSINFO
+ int (*fsinfo)(struct kernfs_root *root, struct fsinfo_kparams *params);
+#endif
int (*mkdir)(struct kernfs_node *parent, const char *name,
umode_t mode);
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 68ca5de7ec27..c8a85dfcac87 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -14,6 +14,7 @@
#include <linux/pid_namespace.h>
#include <linux/cgroupstats.h>
#include <linux/fs_parser.h>
+#include <linux/fsinfo.h>
#include <trace/events/cgroup.h>
@@ -921,6 +922,46 @@ const struct fs_parameter_description cgroup1_fs_parameters = {
.specs = cgroup1_param_specs,
};
+#ifdef CONFIG_FSINFO
+static int cgroup1_fsinfo(struct kernfs_root *kf_root, struct fsinfo_kparams *params)
+{
+ struct cgroup_root *root = cgroup_root_from_kf(kf_root);
+ struct cgroup_subsys *ss;
+ int ssid;
+
+ switch (params->request) {
+ case FSINFO_ATTR_PARAMETERS:
+ if (root->name[0])
+ fsinfo_note_param(params, "name", root->name);
+
+ if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
+ fsinfo_note_param(params, "clone_children", NULL);
+ if (root->flags & CGRP_ROOT_CPUSET_V2_MODE)
+ fsinfo_note_param(params, "noprefix", NULL);
+ if (root->flags & CGRP_ROOT_NOPREFIX)
+ fsinfo_note_param(params, "noprefix", NULL);
+ if (root->flags & CGRP_ROOT_XATTR)
+ fsinfo_note_param(params, "xattr", NULL);
+
+ spin_lock(&release_agent_path_lock);
+ if (root->release_agent_path[0])
+ fsinfo_note_param(params, "release_agent",
+ root->release_agent_path);
+ spin_unlock(&release_agent_path_lock);
+
+
+ for_each_subsys(ss, ssid) {
+ if (root->subsys_mask & (1 << ssid))
+ fsinfo_note_param(params, ss->legacy_name, NULL);
+ }
+ return params->usage;
+
+ default:
+ return -EAGAIN; /* Tell kernfs to call generic_fsinfo() */
+ }
+}
+#endif /* CONFIG_FSINFO */
+
int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
@@ -1114,6 +1155,9 @@ int cgroup1_reconfigure(struct fs_context *fc)
struct kernfs_syscall_ops cgroup1_kf_syscall_ops = {
.rename = cgroup1_rename,
.show_options = cgroup1_show_options,
+#ifdef CONFIG_FSINFO
+ .fsinfo = cgroup1_fsinfo,
+#endif
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,
.show_path = cgroup_show_path,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 217cec4e22c6..2e18e5f9ad70 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -55,6 +55,7 @@
#include <linux/nsproxy.h>
#include <linux/file.h>
#include <linux/fs_parser.h>
+#include <linux/fsinfo.h>
#include <linux/sched/cputime.h>
#include <linux/psi.h>
#include <net/sock.h>
@@ -1858,6 +1859,21 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
return 0;
}
+#ifdef CONFIG_FSINFO
+static int cgroup_fsinfo(struct kernfs_root *kf_root, struct fsinfo_kparams *params)
+{
+ switch (params->request) {
+ case FSINFO_ATTR_PARAMETERS:
+ if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
+ fsinfo_note_param(params, "nsdelegate", NULL);
+ return params->usage;
+
+ default:
+ return -EAGAIN; /* Tell kernfs to call generic_fsinfo() */
+ }
+}
+#endif /* CONFIG_FSINFO */
+
static int cgroup_reconfigure(struct fs_context *fc)
{
struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
@@ -5507,6 +5523,9 @@ int cgroup_rmdir(struct kernfs_node *kn)
static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
.show_options = cgroup_show_options,
+#ifdef CONFIG_FSINFO
+ .fsinfo = cgroup_fsinfo,
+#endif
.mkdir = cgroup_mkdir,
.rmdir = cgroup_rmdir,
.show_path = cgroup_show_path,
^ permalink raw reply related
* [PATCH 09/11] hugetlbfs: Add support for fsinfo() [ver #15]
From: David Howells @ 2019-06-28 15:45 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Add support for fsinfo().
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/hugetlbfs/inode.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 57 insertions(+)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 1dcc57189382..62d5d5dec447 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -28,6 +28,7 @@
#include <linux/hugetlb.h>
#include <linux/pagevec.h>
#include <linux/fs_parser.h>
+#include <linux/fsinfo.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
@@ -958,6 +959,59 @@ static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root)
return 0;
}
+#ifdef CONFIG_FSINFO
+static int hugetlbfs_fsinfo(struct path *path, struct fsinfo_kparams *params)
+{
+ struct dentry *dentry = path->dentry;
+ struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
+ struct hugepage_subpool *spool = sbinfo->spool;
+ unsigned long hpage_size = huge_page_size(sbinfo->hstate);
+ unsigned hpage_shift = huge_page_shift(sbinfo->hstate);
+ char mod;
+
+ switch (params->request) {
+ case FSINFO_ATTR_PARAMETERS:
+ fsinfo_note_sb_params(params, dentry->d_sb->s_flags);
+ if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID))
+ fsinfo_note_paramf(params, "uid", "%u",
+ from_kuid_munged(&init_user_ns,
+ sbinfo->uid));
+
+ if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
+ fsinfo_note_paramf(params, "gid", "%u",
+ from_kgid_munged(&init_user_ns,
+ sbinfo->gid));
+
+ if (spool && spool->max_hpages != -1)
+ fsinfo_note_paramf(params, "size", "%llu",
+ (unsigned long long)spool->max_hpages << hpage_shift);
+
+ if (spool && spool->min_hpages != -1)
+ fsinfo_note_paramf(params, "min_size", "%llu",
+ (unsigned long long)spool->min_hpages << hpage_shift);
+
+ hpage_size /= 1024;
+ mod = 'K';
+ if (hpage_size >= 1024) {
+ hpage_size /= 1024;
+ mod = 'M';
+ }
+ fsinfo_note_paramf(params, "pagesize", "%lu%c", hpage_size, mod);
+
+ if (sbinfo->mode != 0755)
+ fsinfo_note_paramf(params, "mode", "%o", sbinfo->mode);
+
+ if (sbinfo->max_inodes != -1)
+ fsinfo_note_paramf(params, "nr_inodes", "%lu",
+ sbinfo->max_inodes);
+ return params->usage;
+
+ default:
+ return generic_fsinfo(path, params);
+ }
+}
+#endif /* CONFIG_FSINFO */
+
static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
@@ -1116,6 +1170,9 @@ static const struct super_operations hugetlbfs_ops = {
.statfs = hugetlbfs_statfs,
.put_super = hugetlbfs_put_super,
.show_options = hugetlbfs_show_options,
+#ifdef CONFIG_FSINFO
+ .fsinfo = hugetlbfs_fsinfo,
+#endif
};
/*
^ permalink raw reply related
* [PATCH 08/11] fsinfo: Add API documentation [ver #15]
From: David Howells @ 2019-06-28 15:45 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Add API documentation for fsinfo.
Signed-off-by: David Howells <dhowells@redhat.com>
---
Documentation/filesystems/fsinfo.rst | 561 ++++++++++++++++++++++++++++++++++
1 file changed, 561 insertions(+)
create mode 100644 Documentation/filesystems/fsinfo.rst
diff --git a/Documentation/filesystems/fsinfo.rst b/Documentation/filesystems/fsinfo.rst
new file mode 100644
index 000000000000..86c187a46396
--- /dev/null
+++ b/Documentation/filesystems/fsinfo.rst
@@ -0,0 +1,561 @@
+================================
+Filesystem Information Retrieval
+================================
+
+The fsinfo() system call allows the retrieval of filesystem and filesystem
+security information beyond what stat(), statx() and statfs() can query. It
+does not require a file to be opened as does ioctl().
+
+fsinfo() may be called on a path, an open file descriptor, a filesystem-context
+file descriptor as allocated by fsopen() or fspick().
+
+The fsinfo() system call needs to be configured on by enabling:
+
+ "File systems"/"Enable the fsinfo() system call" (CONFIG_FSINFO)
+
+This document has the following sections:
+
+.. contents:: :local:
+
+
+Overview
+========
+
+The fsinfo() system call retrieves one of a number of attributes, specified by
+the "fsinfo_attribute" enumeration::
+
+ FSINFO_ATTR_STATFS - statfs()-style state
+ FSINFO_ATTR_FSINFO - Information about fsinfo() itself
+ FSINFO_ATTR_IDS - Filesystem IDs
+ FSINFO_ATTR_LIMITS - Filesystem limits
+ ...
+
+Each attribute can have a single value, a sequence of values or a
+sequence-of-sequences of values. All of the values of an attribute must be of
+the same type - and this is an inherent property of the attribute. The
+available types are:
+
+ * ``Struct``. This is a structure with a version-dependent length. New
+ versions of the kernel may append more fields, though they are not
+ permitted to remove or replace old ones.
+
+ Older applications, expecting an older version of the field, can ask for a
+ shorter struct and will only get the fields they requested; newer
+ applications running on an older kernel will get the extra fields they
+ requested filled with zeros. Either way, the kernel returns the actual size
+ of the internal struct, regardless of how much data it returned.
+
+ This allows for struct-type fields to be extended in future.
+
+ * ``String``. This is a variable-length string of up to 4096 characters (no
+ NUL character is included). The returned string will be truncated if the
+ output buffer is too small. The total size of the string is returned,
+ regardless of any truncation.
+
+ * ``Array``. This is a variable-length array of fixed-size structures. The
+ element size may not vary over time, so the element format must be designed
+ with care. The maximum length is INT_MAX bytes, though this depends on the
+ kernel being able to allocate an internal buffer large enough.
+
+ * ``Opaque``. This is a variable-length blob of indeterminate structure. It
+ may be up to INT_MAX bytes in size.
+
+
+Filesystem API
+==============
+
+The filesystem is called through a superblock_operations method::
+
+ int (*fsinfo) (struct path *path, struct fsinfo_kparams *params);
+
+where "path" indicates the object to be queried and params indicates the
+parameters and the output buffer description. The function should return the
+total size of the data it would like to produce or an error.
+
+The parameter struct looks like::
+
+ struct fsinfo_kparams {
+ enum fsinfo_attribute request;
+ __u32 Nth;
+ __u32 Mth;
+ unsigned int buf_size;
+ unsigned int usage;
+ void *buffer;
+ char *scratch_buffer;
+ ...
+ };
+
+The fields relevant to the filesystem are as follows:
+
+ * ``request``
+
+ Which attribute is being requested. EOPNOTSUPP should be returned if the
+ attribute is not supported by the filesystem or the LSM.
+
+ * ``Nth`` and ``Mth``
+
+ Which value of an attribute is being requested.
+
+ For a single-value attribute Nth and Mth will both be 0.
+
+ For a "1D" attribute, Nth will indicate which value and Mth will always
+ be 0. Take, for example, FSINFO_ATTR_SERVER_NAME - for a network
+ filesystem, the superblock will be backed by a number of servers. This will
+ return the name of the Nth server. ENODATA will be returned if Nth goes
+ beyond the end of the array.
+
+ For a "2D" attribute, Mth will indicate the index in the Nth set of values.
+ Take, for example, Take, for example, FSINFO_ATTR_SERVER_ADDRESS - each
+ server listed by FSINFO_ATTR_SERVER_NAME may have one or more addresses.
+ This will return the Mth address of the Nth server. ENODATA will be
+ returned if the Nth set doesn't exist or the Mth element of the Nth set
+ doesn't exist.
+
+ * ``buf_size``
+
+ This indicates the current size of the buffer. For the array type and the
+ opaque type this will be increased if the current buffer won't hold the
+ value and the filesystem will be called again.
+
+ * ``usage``
+
+ This indicates how much of the buffer has been used so far for an array or
+ opaque type attribute. This is updated by the fsinfo_note_param*()
+ functions.
+
+ * ``buffer``
+
+ This points to the output buffer. For struct-type and string-type
+ attributes it will always be big enough; for array- and opaque-type, it will
+ be buf_size in size and will be resized if the returned size is larger than
+ this.
+
+ * ``scratch_buffer``
+
+ For array- and opaque-type attributes, this will point to a 4096-byte
+ scratch buffer. Sometimes the value needs to be generated by sprintf(),
+ say, to find out how big is going to be, but that might not be possible in
+ the main buffer without risking an overrun.
+
+To simplify filesystem code, there will always be at least a minimal buffer
+available if the ->fsinfo() method gets called - and the filesystem should
+always write what it can into the buffer. It's possible that the fsinfo()
+system call will then throw the contents away and just return the length.
+
+
+Helper Functions
+================
+
+The API includes a number of helper functions:
+
+ * ``int generic_fsinfo(struct path *path, struct fsinfo_kparams *params);``
+
+ This is the function that does default actions for filling out attribute
+ values from standard data, such as may be found in the file_system_type
+ struct and the super_block struct. It also generates -EOPNOTSUPP for
+ unsupported attributes.
+
+ This should be called by a filesystem if it doesn't want to handle an
+ attribute. The filesystem may also call this function and then adjust the
+ information returned, such as changing the listed capability flags.
+
+ * ``void fsinfo_set_cap(struct fsinfo_capabilities *c,
+ enum fsinfo_capability cap);``
+
+ This function sets a capability flag.
+
+ * ``void fsinfo_clear_cap(struct fsinfo_capabilities *c,
+ enum fsinfo_capability cap);``
+
+ This function clears a capability flag.
+
+ * ``void fsinfo_set_unix_caps(struct fsinfo_capabilities *caps);``
+
+ Set capability flags appropriate to the features of a standard UNIX
+ filesystem, such as having numeric UIDS and GIDS; allowing the creation of
+ directories, symbolic links, hard links, device files, FIFO and socket
+ files; permitting sparse files; and having access, change and modification
+ times.
+
+ * ``void fsinfo_note_sb_params(struct fsinfo_kparams *params,
+ unsigned int s_flags);``
+
+ This function notes the standard parameters corresponding to certain
+ ``SB_*`` flags in ``sb->s_flags`` into the parameter buffer. The filesystem
+ is at liberty to adjust the s_flags mask as it sees fit.
+
+ This is intended for use with FSINFO_ATTR_PARAMETERS.
+
+ * ``void fsinfo_note_param(struct fsinfo_kparams *params, const char *key,
+ const char *val);``
+
+ This function writes a pair of strings with prepended lengths into
+ params->buffer, if there's space, and always updates params->usage. The
+ assumption is that the caller of s->s_op->fsinfo() will resize the buffer if
+ the usage grew too large and call again.
+
+ This is intended for use with FSINFO_ATTR_{,LSM_}PARAMETERS, but is not
+ limited to those. The format allows binary data, though this API function
+ does not support anything with NUL characters in it.
+
+ Note that this function will not sleep, so is safe to take with locks held.
+
+ * ``void fsinfo_note_paramf(struct fsinfo_kparams *params, const char *key,
+ const char *val_fmt, ...);``
+
+ This function is a simple wrapper around fsinfo_note_param(), writing the
+ value using vsnprintf() into params->scratch_buffer and then jumping to
+ fsinfo_note_param().
+
+
+Attribute Summary
+=================
+
+To summarise the attributes that are defined::
+
+ Symbolic name Type
+ ===================================== ===============
+ FSINFO_ATTR_STATFS struct
+ FSINFO_ATTR_FSINFO struct
+ FSINFO_ATTR_IDS struct
+ FSINFO_ATTR_LIMITS struct
+ FSINFO_ATTR_SUPPORTS struct
+ FSINFO_ATTR_CAPABILITIES struct
+ FSINFO_ATTR_TIMESTAMP_INFO struct
+ FSINFO_ATTR_VOLUME_ID string
+ FSINFO_ATTR_VOLUME_UUID struct
+ FSINFO_ATTR_VOLUME_NAME string
+ FSINFO_ATTR_NAME_ENCODING string
+ FSINFO_ATTR_NAME_CODEPAGE string
+ FSINFO_ATTR_PARAM_DESCRIPTION struct
+ FSINFO_ATTR_PARAM_SPECIFICATION N × struct
+ FSINFO_ATTR_PARAM_ENUM N × struct
+ FSINFO_ATTR_PARAMETERS opaque
+ FSINFO_ATTR_LSM_PARAMETERS opaque
+ FSINFO_ATTR_SERVER_NAME N × string
+ FSINFO_ATTR_SERVER_ADDRESS N × M × struct
+ FSINFO_ATTR_AFS_CELL_NAME string
+
+
+Attribute Catalogue
+===================
+
+A number of the attributes convey information about a filesystem superblock:
+
+ * ``FSINFO_ATTR_STATFS``
+
+ This struct-type attribute gives most of the equivalent data to statfs(),
+ but with all the fields as unconditional 64-bit or 128-bit integers. Note
+ that static data like IDs that don't change are retrieved with
+ FSINFO_ATTR_IDS instead.
+
+ Further, superblock flags (such as MS_RDONLY) are not exposed by this
+ attribute; rather the parameters must be listed and the attributes picked
+ out from that.
+
+ * ``FSINFO_ATTR_IDS``
+
+ This struct-type attribute conveys various identifiers used by the target
+ filesystem. This includes the filesystem name, the NFS filesystem ID, the
+ superblock ID used in notifications, the filesystem magic type number and
+ the primary device ID.
+
+ * ``FSINFO_ATTR_LIMITS``
+
+ This struct-type attribute conveys the limits on various aspects of a
+ filesystem, such as maximum file, symlink and xattr sizes, maxiumm filename
+ and xattr name length, maximum number of symlinks, maximum device major and
+ minor numbers and maximum UID, GID and project ID numbers.
+
+ * ``FSINFO_ATTR_SUPPORTS``
+
+ This struct-type attribute conveys information about the support the
+ filesystem has for various UAPI features of a filesystem. This includes
+ information about which bits are supported in various masks employed by the
+ statx system call, what FS_IOC_* flags are supported by ioctls and what
+ DOS/Windows file attribute flags are supported.
+
+ * ``FSINFO_ATTR_CAPABILITIES``
+
+ This is a special attribute, being a set of single-bit capability flags,
+ formatted as struct-type attribute. The meanings of the capability bits
+ are listed below - see the "Capability Bit Catalogue" section. The
+ capability bits are grouped numerically into bytes, such that capilities
+ 0-7 are in byte 0, 8-15 are in byte 1, 16-23 in byte 2 and so on.
+
+ Any capability bit that's not supported by the kernel will be set to false
+ if asked for. The highest supported capability can be obtained from
+ attribute "FSINFO_ATTR_FSINFO".
+
+ * ``FSINFO_ATTR_TIMESTAMP_INFO``
+
+ This struct-type attribute conveys information about the resolution and
+ range of the timestamps available in a filesystem. The resolutions are
+ given as a mantissa and exponent (resolution = mantissa * 10^exponent
+ seconds), where the exponent can be negative to indicate a sub-second
+ resolution (-9 being nanoseconds, for example).
+
+ * ``FSINFO_ATTR_VOLUME_ID``
+
+ This is a string-type attribute that conveys the superblock identifier for
+ the volume. By default it will be filled in from the contents of s_id from
+ the superblock. For a block-based filesystem, for example, this might be
+ the name of the primary block device.
+
+ * ``FSINFO_ATTR_VOLUME_UUID``
+
+ This is a struct-type attribute that conveys the UUID identifier for the
+ volume. By default it will be filled in from the contents of s_uuid from
+ the superblock. If this doesn't exist, it will be an entirely zeros.
+
+ * ``FSINFO_ATTR_VOLUME_NAME``
+
+ This is a string-type attribute that conveys the name of the volume. By
+ default it will return EOPNOTSUPP. For a disk-based filesystem, it might
+ convey the partition label; for a network-based filesystem, it might convey
+ the name of the remote volume.
+
+ * ``FSINFO_ATTR_NAME_ENCODING``
+
+ This is a string-type attribute that returns the type of encoding used for
+ filenames in the medium. By default this will be filled in with "utf8".
+ Not all filesystems can support that, however, so this may indicate a
+ restriction on what characters can be used.
+
+ * ``FSINFO_ATTR_NAME_CODEPAGE``
+
+ This is a string-type attribute that returns the name of the codepage used
+ to transliterate a Linux utf8 filename into whatever the medium supports.
+ By default it returns EOPNOTSUPP.
+
+
+The next attributes give information about the mount parameter parsers and the
+mount parameters values stored in a superblock and its security data. The
+first few of these can be queried on the file descriptor returned by fsopen()
+before any superblock is attached:
+
+ * ``FSINFO_ATTR_PARAM_DESCRIPTION``
+
+ This is a struct-type attribute that returns summary information about what
+ mount options are available on a filesystem, including the number of
+ parameters and the number of enum symbols.
+
+ * ``FSINFO_ATTR_PARAM_SPECIFICATION``
+
+ This is a 1D array of struct-type attributes, indicating the type,
+ qualifiers, name and an option ID for the Nth mount parameter. Parameters
+ that have the same option ID are presumed to be synonyms.
+
+ * ``FSINFO_ATTR_PARAM_ENUM``
+
+ This is a 1D array of struct-type attributes, indicating the Nth value
+ symbol for the set of enumeration-type parameters. All the values are in
+ the same table, so they can be matched to the parameter by option ID, and
+ each option ID may have several entries, each with a different name.
+
+ * ``FSINFO_ATTR_PARAMETERS``
+ * ``FSINFO_ATTR_LSM_PARAMETERS``
+
+ These are a pair of opaque blobs that list all the mount parameter values
+ currently set on a superblock. The first set come from the filesystem and
+ the second is from the LSMs - and, as such, convey security information,
+ such as labelling.
+
+ Inside the filesystem or LSM, the parameter values should be read in one go
+ under lock to avoid races with remount if necessary.
+
+ Each opaque blob is encoded as a series of pairs of elements, where each
+ element begins with a length. The first element of each pair is the key
+ name and the second is the value (which may contain commas, binary data,
+ NUL chars).
+
+ An element length is encoded as a series of bytes in most->least signifcant
+ order. Each byte contributes 7 bits to the length. The MSB in each byte
+ is set if there's another byte of length information following on (ie. all
+ but the last byte in the length have the MSB set).
+
+ A number of helper functions are provided to help record the parameters::
+
+ fsinfo_note_sb_params()
+ fsinfo_note_param()
+ fsinfo_note_paramf()
+
+ Note that the first is not applicable to LSM parameters. It is called
+ automatically if the filesystem doesn't implement the attribute, but must,
+ and should, be called manually otherwise. It should also be called first,
+ before noting any other parameters.
+
+
+Then there are filesystem-specific attributes.
+
+ * ``FSINFO_ATTR_SERVER_NAME``
+
+ This is a string-type attribute that conveys the name of the Nth server
+ backing a network-filesystem superblock.
+
+ * ``FSINFO_ATTR_SERVER_ADDRESS``
+
+ This is a struct-type attribute that conveys the Mth address of the Nth
+ server, as returned by FSINFO_ATTR_SERVER_NAME.
+
+ * ``FSINFO_ATTR_AFS_CELL_NAME``
+
+ This is a string-type attribute that retrieves the AFS cell name of the
+ target object.
+
+
+Lastly, one attribute gives information about fsinfo() itself:
+
+ * ``FSINFO_ATTR_FSINFO``
+
+ This struct-type attribute gives information about the fsinfo() system call
+ itself, including the maximum number of attributes supported and the
+ maximum number of capability bits supported.
+
+
+Capability Bit Catalogue
+========================
+
+The capability bits convey single true/false assertions about a specific
+instance of a filesystem (ie. a specific superblock). They are accessed using
+the "FSINFO_ATTR_CAPABILITY" attribute:
+
+ * ``FSINFO_CAP_IS_KERNEL_FS``
+ * ``FSINFO_CAP_IS_BLOCK_FS``
+ * ``FSINFO_CAP_IS_FLASH_FS``
+ * ``FSINFO_CAP_IS_NETWORK_FS``
+ * ``FSINFO_CAP_IS_AUTOMOUNTER_FS``
+ * ``FSINFO_CAP_IS_MEMORY_FS``
+
+ These indicate what kind of filesystem the target is: kernel API (proc),
+ block-based (ext4), flash/nvm-based (jffs2), remote over the network (NFS),
+ local quasi-filesystem that acts as a tray of mountpoints (autofs), plain
+ in-memory filesystem (shmem).
+
+ * ``FSINFO_CAP_AUTOMOUNTS``
+
+ This indicate if a filesystem may have objects that are automount points.
+
+ * ``FSINFO_CAP_ADV_LOCKS``
+ * ``FSINFO_CAP_MAND_LOCKS``
+ * ``FSINFO_CAP_LEASES``
+
+ These indicate if a filesystem supports advisory locks, mandatory locks or
+ leases.
+
+ * ``FSINFO_CAP_UIDS``
+ * ``FSINFO_CAP_GIDS``
+ * ``FSINFO_CAP_PROJIDS``
+
+ These indicate if a filesystem supports/stores/transports numeric user IDs,
+ group IDs or project IDs. The "FSINFO_ATTR_LIMITS" attribute can be used
+ to find out the upper limits on the IDs values.
+
+ * ``FSINFO_CAP_STRING_USER_IDS``
+
+ This indicates if a filesystem supports/stores/transports string user
+ identifiers.
+
+ * ``FSINFO_CAP_GUID_USER_IDS``
+
+ This indicates if a filesystem supports/stores/transports Windows GUIDs as
+ user identifiers (eg. ntfs).
+
+ * ``FSINFO_CAP_WINDOWS_ATTRS``
+
+ This indicates if a filesystem supports Windows FILE_* attribute bits
+ (eg. cifs, jfs). The "FSINFO_ATTR_SUPPORTS" attribute can be used to find
+ out which windows file attributes are supported by the filesystem.
+
+ * ``FSINFO_CAP_USER_QUOTAS``
+ * ``FSINFO_CAP_GROUP_QUOTAS``
+ * ``FSINFO_CAP_PROJECT_QUOTAS``
+
+ These indicate if a filesystem supports quotas for users, groups or
+ projects.
+
+ * ``FSINFO_CAP_XATTRS``
+
+ These indicate if a filesystem supports extended attributes. The
+ "FSINFO_ATTR_LIMITS" attribute can be used to find out the upper limits on
+ the supported name and body lengths.
+
+ * ``FSINFO_CAP_JOURNAL``
+ * ``FSINFO_CAP_DATA_IS_JOURNALLED``
+
+ These indicate whether the filesystem has a journal and whether data
+ changes are logged to it.
+
+ * ``FSINFO_CAP_O_SYNC``
+ * ``FSINFO_CAP_O_DIRECT``
+
+ These indicate whether the filesystem supports the O_SYNC and O_DIRECT
+ flags.
+
+ * ``FSINFO_CAP_VOLUME_ID``
+ * ``FSINFO_CAP_VOLUME_UUID``
+ * ``FSINFO_CAP_VOLUME_NAME``
+ * ``FSINFO_CAP_VOLUME_FSID``
+
+ These indicate whether ID, UUID, name and FSID identifiers actually exist
+ in the filesystem and thus might be considered persistent.
+
+ * ``FSINFO_CAP_IVER_ALL_CHANGE``
+ * ``FSINFO_CAP_IVER_DATA_CHANGE``
+ * ``FSINFO_CAP_IVER_MONO_INCR``
+
+ These indicate whether i_version in the inode is supported and, if so, what
+ mode it operates in. The first two indicate if it's changed for any data
+ or metadata change, or whether it's only changed for any data changes; the
+ last indicates whether or not it's monotonically increasing for each such
+ change.
+
+ * ``FSINFO_CAP_HARD_LINKS``
+ * ``FSINFO_CAP_HARD_LINKS_1DIR``
+
+ These indicate whether the filesystem can have hard links made in it, and
+ whether they can be made between directory or only within the same
+ directory.
+
+ * ``FSINFO_CAP_DIRECTORIES``
+ * ``FSINFO_CAP_SYMLINKS``
+ * ``FSINFO_CAP_DEVICE_FILES``
+ * ``FSINFO_CAP_UNIX_SPECIALS``
+
+ These indicate whether directories; symbolic links; device files; or pipes
+ and sockets can be made within the filesystem.
+
+ * ``FSINFO_CAP_RESOURCE_FORKS``
+
+ This indicates if the filesystem supports resource forks.
+
+ * ``FSINFO_CAP_NAME_CASE_INDEP``
+ * ``FSINFO_CAP_NAME_NON_UTF8``
+ * ``FSINFO_CAP_NAME_HAS_CODEPAGE``
+
+ These indicate if the filesystem supports case-independent file names,
+ whether the filenames are non-utf8 (see the "FSINFO_ATTR_NAME_ENCODING"
+ attribute) and whether a codepage is in use to transliterate them (see
+ the "FSINFO_ATTR_NAME_CODEPAGE" attribute).
+
+ * ``FSINFO_CAP_SPARSE``
+
+ This indicates if a filesystem supports sparse files.
+
+ * ``FSINFO_CAP_NOT_PERSISTENT``
+
+ This indicates if a filesystem is not persistent.
+
+ * ``FSINFO_CAP_NO_UNIX_MODE``
+
+ This indicates if a filesystem doesn't support UNIX mode bits (though they
+ may be manufactured from other bits, such as Windows file attribute flags).
+
+ * ``FSINFO_CAP_HAS_ATIME``
+ * ``FSINFO_CAP_HAS_BTIME``
+ * ``FSINFO_CAP_HAS_CTIME``
+ * ``FSINFO_CAP_HAS_MTIME``
+
+ These indicate which timestamps a filesystem supports (access, birth,
+ change, modify). The range and resolutions can be queried with the
+ "FSINFO_ATTR_TIMESTAMPS" attribute).
^ permalink raw reply related
* [PATCH 07/11] afs: Support fsinfo() [ver #15]
From: David Howells @ 2019-06-28 15:45 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Add fsinfo support to the AFS filesystem.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/afs/internal.h | 1
fs/afs/super.c | 180 +++++++++++++++++++++++++++++++++++++++++++
fs/fsinfo.c | 3 +
include/uapi/linux/fsinfo.h | 12 +++
samples/vfs/test-fsinfo.c | 33 ++++++++
5 files changed, 227 insertions(+), 2 deletions(-)
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 2073c1a3ab4b..da40ea036c6a 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -254,6 +254,7 @@ struct afs_super_info {
struct afs_volume *volume; /* volume record */
enum afs_flock_mode flock_mode:8; /* File locking emulation mode */
bool dyn_root; /* True if dynamic root */
+ bool autocell; /* True if autocell */
};
static inline struct afs_super_info *AFS_FS_S(struct super_block *sb)
diff --git a/fs/afs/super.c b/fs/afs/super.c
index f18911e8d770..d6c9742c0165 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -26,6 +26,7 @@
#include <linux/sched.h>
#include <linux/nsproxy.h>
#include <linux/magic.h>
+#include <linux/fsinfo.h>
#include <net/net_namespace.h>
#include "internal.h"
@@ -35,6 +36,9 @@ static struct inode *afs_alloc_inode(struct super_block *sb);
static void afs_destroy_inode(struct inode *inode);
static void afs_free_inode(struct inode *inode);
static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
+#ifdef CONFIG_FSINFO
+static int afs_fsinfo(struct path *path, struct fsinfo_kparams *params);
+#endif
static int afs_show_devname(struct seq_file *m, struct dentry *root);
static int afs_show_options(struct seq_file *m, struct dentry *root);
static int afs_init_fs_context(struct fs_context *fc);
@@ -54,6 +58,9 @@ int afs_net_id;
static const struct super_operations afs_super_ops = {
.statfs = afs_statfs,
+#ifdef CONFIG_FSINFO
+ .fsinfo = afs_fsinfo,
+#endif
.alloc_inode = afs_alloc_inode,
.drop_inode = afs_drop_inode,
.destroy_inode = afs_destroy_inode,
@@ -199,7 +206,7 @@ static int afs_show_options(struct seq_file *m, struct dentry *root)
if (as->dyn_root)
seq_puts(m, ",dyn");
- if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags))
+ if (as->autocell)
seq_puts(m, ",autocell");
switch (as->flock_mode) {
case afs_flock_mode_unset: break;
@@ -463,7 +470,7 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx)
if (IS_ERR(inode))
return PTR_ERR(inode);
- if (ctx->autocell || as->dyn_root)
+ if (as->autocell || as->dyn_root)
set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags);
ret = -ENOMEM;
@@ -503,6 +510,8 @@ static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc)
as->cell = afs_get_cell(ctx->cell);
as->volume = __afs_get_volume(ctx->volume);
}
+ if (ctx->autocell)
+ as->autocell = true;
}
return as;
}
@@ -765,3 +774,170 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
return ret;
}
+
+#ifdef CONFIG_FSINFO
+static const struct fsinfo_timestamp_info afs_timestamp_info = {
+ .atime = {
+ .minimum = 0,
+ .maximum = UINT_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .mtime = {
+ .minimum = 0,
+ .maximum = UINT_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .ctime = {
+ .minimum = 0,
+ .maximum = UINT_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .btime = {
+ .minimum = 0,
+ .maximum = UINT_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+};
+
+/*
+ * Get filesystem information.
+ */
+static int afs_fsinfo(struct path *path, struct fsinfo_kparams *params)
+{
+ struct fsinfo_timestamp_info *tsinfo;
+ struct fsinfo_server_address *addr;
+ struct fsinfo_capabilities *caps;
+ struct fsinfo_supports *sup;
+ struct dentry *dentry = path->dentry;
+ struct afs_server_list *slist;
+ struct afs_super_info *as = AFS_FS_S(dentry->d_sb);
+ struct afs_addr_list *alist;
+ struct afs_server *server;
+ struct afs_volume *volume = as->volume;
+ struct afs_cell *cell = as->cell;
+ struct afs_net *net = afs_d2net(dentry);
+ bool dyn_root = as->dyn_root;
+ int ret;
+
+ switch (params->request) {
+ case FSINFO_ATTR_TIMESTAMP_INFO:
+ tsinfo = params->buffer;
+ *tsinfo = afs_timestamp_info;
+ return sizeof(*tsinfo);
+
+ case FSINFO_ATTR_SUPPORTS:
+ sup = params->buffer;
+ sup->stx_mask = (STATX_TYPE | STATX_MODE |
+ STATX_NLINK |
+ STATX_UID | STATX_GID |
+ STATX_MTIME | STATX_INO |
+ STATX_SIZE);
+ sup->stx_attributes = STATX_ATTR_AUTOMOUNT;
+ return sizeof(*sup);
+
+ case FSINFO_ATTR_CAPABILITIES:
+ caps = params->buffer;
+ if (dyn_root) {
+ fsinfo_set_cap(caps, FSINFO_CAP_IS_AUTOMOUNTER_FS);
+ fsinfo_set_cap(caps, FSINFO_CAP_AUTOMOUNTS);
+ } else {
+ fsinfo_set_cap(caps, FSINFO_CAP_IS_NETWORK_FS);
+ fsinfo_set_cap(caps, FSINFO_CAP_AUTOMOUNTS);
+ fsinfo_set_cap(caps, FSINFO_CAP_ADV_LOCKS);
+ fsinfo_set_cap(caps, FSINFO_CAP_UIDS);
+ fsinfo_set_cap(caps, FSINFO_CAP_GIDS);
+ fsinfo_set_cap(caps, FSINFO_CAP_VOLUME_ID);
+ fsinfo_set_cap(caps, FSINFO_CAP_VOLUME_NAME);
+ fsinfo_set_cap(caps, FSINFO_CAP_IVER_MONO_INCR);
+ fsinfo_set_cap(caps, FSINFO_CAP_SYMLINKS);
+ fsinfo_set_cap(caps, FSINFO_CAP_HARD_LINKS_1DIR);
+ fsinfo_set_cap(caps, FSINFO_CAP_HAS_MTIME);
+ }
+ return sizeof(*caps);
+
+ case FSINFO_ATTR_VOLUME_NAME:
+ if (dyn_root)
+ return -EOPNOTSUPP;
+ memcpy(params->buffer, volume->name, volume->name_len);
+ return volume->name_len;
+
+ case FSINFO_ATTR_AFS_CELL_NAME:
+ if (dyn_root)
+ return -EOPNOTSUPP;
+ memcpy(params->buffer, cell->name, cell->name_len);
+ return cell->name_len;
+
+ case FSINFO_ATTR_SERVER_NAME:
+ if (dyn_root)
+ return -EOPNOTSUPP;
+ read_lock(&volume->servers_lock);
+ slist = afs_get_serverlist(volume->servers);
+ read_unlock(&volume->servers_lock);
+
+ if (params->Nth < slist->nr_servers) {
+ server = slist->servers[params->Nth].server;
+ ret = sprintf(params->buffer, "%pU", &server->uuid);
+ } else {
+ ret = -ENODATA;
+ }
+
+ afs_put_serverlist(net, slist);
+ return ret;
+
+ case FSINFO_ATTR_SERVER_ADDRESS:
+ addr = params->buffer;
+ if (dyn_root)
+ return -EOPNOTSUPP;
+ read_lock(&volume->servers_lock);
+ slist = afs_get_serverlist(volume->servers);
+ read_unlock(&volume->servers_lock);
+
+ ret = -ENODATA;
+ if (params->Nth >= slist->nr_servers)
+ goto put_slist;
+ server = slist->servers[params->Nth].server;
+
+ read_lock(&server->fs_lock);
+ alist = afs_get_addrlist(rcu_access_pointer(server->addresses));
+ read_unlock(&server->fs_lock);
+ if (!alist)
+ goto put_slist;
+
+ if (params->Mth >= alist->nr_addrs)
+ goto put_alist;
+
+ memcpy(addr, &alist->addrs[params->Mth],
+ sizeof(struct sockaddr_rxrpc));
+ ret = sizeof(*addr);
+
+ put_alist:
+ afs_put_addrlist(alist);
+ put_slist:
+ afs_put_serverlist(net, slist);
+ return ret;
+
+ case FSINFO_ATTR_PARAMETERS:
+ fsinfo_note_sb_params(params, dentry->d_sb->s_flags);
+ if (!dyn_root)
+ fsinfo_note_paramf(params, "source", "%c%s:%s%s",
+ volume->type == AFSVL_RWVOL ? '%' : '#',
+ cell->name,
+ volume->name,
+ volume->type == AFSVL_RWVOL ? "" :
+ volume->type == AFSVL_ROVOL ? ".readonly" :
+ ".backup");
+ if (as->autocell)
+ fsinfo_note_param(params, "autocell", NULL);
+ if (dyn_root)
+ fsinfo_note_param(params, "dyn", NULL);
+ return params->usage;
+
+ default:
+ return generic_fsinfo(path, params);
+ }
+}
+#endif /* CONFIG_FSINFO */
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index 45bfb10eb8d9..b3f605c39eb5 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -582,6 +582,9 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRUCT_N (PARAM_ENUM, param_enum),
FSINFO_OPAQUE (PARAMETERS),
FSINFO_OPAQUE (LSM_PARAMETERS),
+ FSINFO_STRING_N (SERVER_NAME),
+ FSINFO_STRUCT_NM (SERVER_ADDRESS, server_address),
+ FSINFO_STRING (AFS_CELL_NAME),
};
/**
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index 0d57d37311fc..58a50207256f 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -32,6 +32,9 @@ enum fsinfo_attribute {
FSINFO_ATTR_PARAM_ENUM = 14, /* Nth enum-to-val */
FSINFO_ATTR_PARAMETERS = 15, /* Mount parameters (large string) */
FSINFO_ATTR_LSM_PARAMETERS = 16, /* LSM Mount parameters (large string) */
+ FSINFO_ATTR_SERVER_NAME = 17, /* Name of the Nth server (string) */
+ FSINFO_ATTR_SERVER_ADDRESS = 18, /* Mth address of the Nth server */
+ FSINFO_ATTR_AFS_CELL_NAME = 19, /* AFS cell name (string) */
FSINFO_ATTR__NR
};
@@ -276,4 +279,13 @@ struct fsinfo_param_enum {
char name[252]; /* Name of the enum value */
};
+/*
+ * Information struct for fsinfo(fsinfo_attr_server_addresses).
+ *
+ * Find the Mth address of the Nth server for a network mount.
+ */
+struct fsinfo_server_address {
+ struct __kernel_sockaddr_storage address;
+};
+
#endif /* _UAPI_LINUX_FSINFO_H */
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index f865bc1af16f..6389ae781cbb 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -83,6 +83,9 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRUCT_N (PARAM_ENUM, param_enum),
FSINFO_OVERLARGE (PARAMETERS, -),
FSINFO_OVERLARGE (LSM_PARAMETERS, -),
+ FSINFO_STRING_N (SERVER_NAME, server_name),
+ FSINFO_STRUCT_NM (SERVER_ADDRESS, server_address),
+ FSINFO_STRING (AFS_CELL_NAME, -),
};
#define FSINFO_NAME(X,Y) [FSINFO_ATTR_##X] = #Y
@@ -104,6 +107,9 @@ static const char *fsinfo_attr_names[FSINFO_ATTR__NR] = {
FSINFO_NAME (PARAM_ENUM, param_enum),
FSINFO_NAME (PARAMETERS, parameters),
FSINFO_NAME (LSM_PARAMETERS, lsm_parameters),
+ FSINFO_NAME (SERVER_NAME, server_name),
+ FSINFO_NAME (SERVER_ADDRESS, server_address),
+ FSINFO_NAME (AFS_CELL_NAME, afs_cell_name),
};
union reply {
@@ -116,6 +122,7 @@ union reply {
struct fsinfo_capabilities caps;
struct fsinfo_timestamp_info timestamps;
struct fsinfo_volume_uuid uuid;
+ struct fsinfo_server_address srv_addr;
};
static void dump_hex(unsigned int *data, int from, int to)
@@ -318,6 +325,31 @@ static void dump_attr_VOLUME_UUID(union reply *r, int size)
f->uuid[14], f->uuid[15]);
}
+static void dump_attr_SERVER_ADDRESS(union reply *r, int size)
+{
+ struct fsinfo_server_address *f = &r->srv_addr;
+ struct sockaddr_in6 *sin6;
+ struct sockaddr_in *sin;
+ char buf[1024];
+
+ switch (f->address.ss_family) {
+ case AF_INET:
+ sin = (struct sockaddr_in *)&f->address;
+ if (!inet_ntop(AF_INET, &sin->sin_addr, buf, sizeof(buf)))
+ break;
+ printf("IPv4: %s\n", buf);
+ return;
+ case AF_INET6:
+ sin6 = (struct sockaddr_in6 *)&f->address;
+ if (!inet_ntop(AF_INET6, &sin6->sin6_addr, buf, sizeof(buf)))
+ break;
+ printf("IPv6: %s\n", buf);
+ return;
+ }
+
+ printf("family=%u\n", f->address.ss_family);
+}
+
/*
*
*/
@@ -333,6 +365,7 @@ static const dumper_t fsinfo_attr_dumper[FSINFO_ATTR__NR] = {
FSINFO_DUMPER(CAPABILITIES),
FSINFO_DUMPER(TIMESTAMP_INFO),
FSINFO_DUMPER(VOLUME_UUID),
+ FSINFO_DUMPER(SERVER_ADDRESS),
};
static void dump_fsinfo(enum fsinfo_attribute attr,
^ permalink raw reply related
* [PATCH 06/11] fsinfo: Implement retrieval of LSM parameters with fsinfo() [ver #15]
From: David Howells @ 2019-06-28 15:44 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Implement LSM parameter value retrieval with fsinfo() - akin to parsing
/proc/mounts. This allows all the LSM parameters to be retrieved in one go
with:
struct fsinfo_params params = {
.request = FSINFO_ATTR_LSM_PARAMETER,
};
The format is a blob containing pairs of length-prefixed strings to avoid
the need to escape commas and suchlike in the values. This is the same as
for FSINFO_ATTR_PARAMETER.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 21 +++++++++++++++------
include/linux/lsm_hooks.h | 13 +++++++++++++
include/linux/security.h | 11 +++++++++++
include/uapi/linux/fsinfo.h | 1 +
samples/vfs/test-fsinfo.c | 6 +++++-
security/security.c | 12 ++++++++++++
6 files changed, 57 insertions(+), 7 deletions(-)
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index 92906a3f4010..45bfb10eb8d9 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -368,7 +368,8 @@ static int vfs_fsinfo(struct path *path, struct fsinfo_kparams *params)
int (*fsinfo)(struct path *, struct fsinfo_kparams *);
int ret;
- if (params->request == FSINFO_ATTR_FSINFO) {
+ switch (params->request) {
+ case FSINFO_ATTR_FSINFO: {
struct fsinfo_fsinfo *info = params->buffer;
info->max_attr = FSINFO_ATTR__NR;
@@ -376,11 +377,18 @@ static int vfs_fsinfo(struct path *path, struct fsinfo_kparams *params)
return sizeof(*info);
}
- fsinfo = dentry->d_sb->s_op->fsinfo;
- if (!fsinfo) {
- if (!dentry->d_sb->s_op->statfs)
- return -EOPNOTSUPP;
- fsinfo = generic_fsinfo;
+ case FSINFO_ATTR_LSM_PARAMETERS:
+ fsinfo = security_sb_fsinfo;
+ break;
+
+ default:
+ fsinfo = dentry->d_sb->s_op->fsinfo;
+ if (!fsinfo) {
+ if (!dentry->d_sb->s_op->statfs)
+ return -EOPNOTSUPP;
+ fsinfo = generic_fsinfo;
+ }
+ break;
}
ret = security_sb_statfs(dentry);
@@ -573,6 +581,7 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRUCT_N (PARAM_SPECIFICATION, param_specification),
FSINFO_STRUCT_N (PARAM_ENUM, param_enum),
FSINFO_OPAQUE (PARAMETERS),
+ FSINFO_OPAQUE (LSM_PARAMETERS),
};
/**
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 47f58cfb6a19..2474c3f785ca 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -108,6 +108,13 @@
* mountpoint.
* @dentry is a handle on the superblock for the filesystem.
* Return 0 if permission is granted.
+ * @sb_fsinfo:
+ * Query LSM information for a filesystem.
+ * @path is a handle on the superblock for the filesystem.
+ * @params is the fsinfo parameter and buffer block.
+ * - Currently, params->request can only be FSINFO_ATTR_LSM_PARAMETERS.
+ * Return the length of the data in the buffer (and can return -ENODATA to
+ * indicate no value under certain circumstances).
* @sb_mount:
* Check permission before an object specified by @dev_name is mounted on
* the mount point named by @nd. For an ordinary mount, @dev_name
@@ -1492,6 +1499,9 @@ union security_list_options {
int (*sb_kern_mount)(struct super_block *sb);
int (*sb_show_options)(struct seq_file *m, struct super_block *sb);
int (*sb_statfs)(struct dentry *dentry);
+#ifdef CONFIG_FSINFO
+ int (*sb_fsinfo)(struct path *path, struct fsinfo_kparams *params);
+#endif
int (*sb_mount)(const char *dev_name, const struct path *path,
const char *type, unsigned long flags, void *data);
int (*sb_umount)(struct vfsmount *mnt, int flags);
@@ -1838,6 +1848,9 @@ struct security_hook_heads {
struct hlist_head sb_kern_mount;
struct hlist_head sb_show_options;
struct hlist_head sb_statfs;
+#ifdef CONFIG_FSINFO
+ struct hlist_head sb_fsinfo;
+#endif
struct hlist_head sb_mount;
struct hlist_head sb_umount;
struct hlist_head sb_pivotroot;
diff --git a/include/linux/security.h b/include/linux/security.h
index 659071c2e57c..23c8b602c0ab 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -57,6 +57,7 @@ struct mm_struct;
struct fs_context;
struct fs_parameter;
enum fs_value_type;
+struct fsinfo_kparams;
/* Default (no) options for the capable function */
#define CAP_OPT_NONE 0x0
@@ -237,6 +238,9 @@ int security_sb_remount(struct super_block *sb, void *mnt_opts);
int security_sb_kern_mount(struct super_block *sb);
int security_sb_show_options(struct seq_file *m, struct super_block *sb);
int security_sb_statfs(struct dentry *dentry);
+#ifdef CONFIG_FSINFO
+int security_sb_fsinfo(struct path *path, struct fsinfo_kparams *params);
+#endif
int security_sb_mount(const char *dev_name, const struct path *path,
const char *type, unsigned long flags, void *data);
int security_sb_umount(struct vfsmount *mnt, int flags);
@@ -575,6 +579,13 @@ static inline int security_sb_statfs(struct dentry *dentry)
return 0;
}
+#ifdef CONFIG_FSINFO
+static inline int security_sb_fsinfo(struct path *path, struct fsinfo_kparams *params)
+{
+ return 0;
+}
+#endif
+
static inline int security_sb_mount(const char *dev_name, const struct path *path,
const char *type, unsigned long flags,
void *data)
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index 11c4a74638b0..0d57d37311fc 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -31,6 +31,7 @@ enum fsinfo_attribute {
FSINFO_ATTR_PARAM_SPECIFICATION = 13, /* Nth parameter specification */
FSINFO_ATTR_PARAM_ENUM = 14, /* Nth enum-to-val */
FSINFO_ATTR_PARAMETERS = 15, /* Mount parameters (large string) */
+ FSINFO_ATTR_LSM_PARAMETERS = 16, /* LSM Mount parameters (large string) */
FSINFO_ATTR__NR
};
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index 8cf5b02e333a..f865bc1af16f 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -82,6 +82,7 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRUCT_N (PARAM_SPECIFICATION, param_specification),
FSINFO_STRUCT_N (PARAM_ENUM, param_enum),
FSINFO_OVERLARGE (PARAMETERS, -),
+ FSINFO_OVERLARGE (LSM_PARAMETERS, -),
};
#define FSINFO_NAME(X,Y) [FSINFO_ATTR_##X] = #Y
@@ -102,6 +103,7 @@ static const char *fsinfo_attr_names[FSINFO_ATTR__NR] = {
FSINFO_NAME (PARAM_SPECIFICATION, param_specification),
FSINFO_NAME (PARAM_ENUM, param_enum),
FSINFO_NAME (PARAMETERS, parameters),
+ FSINFO_NAME (LSM_PARAMETERS, lsm_parameters),
};
union reply {
@@ -459,6 +461,7 @@ static int try_one(const char *file, struct fsinfo_params *params, bool raw)
switch (params->request) {
case FSINFO_ATTR_PARAMETERS:
+ case FSINFO_ATTR_LSM_PARAMETERS:
if (ret == 0)
return 0;
}
@@ -505,7 +508,8 @@ static int try_one(const char *file, struct fsinfo_params *params, bool raw)
return 0;
case __FSINFO_OVER:
- if (params->request == FSINFO_ATTR_PARAMETERS)
+ if (params->request == FSINFO_ATTR_PARAMETERS ||
+ params->request == FSINFO_ATTR_LSM_PARAMETERS)
dump_params(about, r, ret);
return 0;
diff --git a/security/security.c b/security/security.c
index 613a5c00e602..3af886e8fced 100644
--- a/security/security.c
+++ b/security/security.c
@@ -25,6 +25,7 @@
#include <linux/ima.h>
#include <linux/evm.h>
#include <linux/fsnotify.h>
+#include <linux/fsinfo.h>
#include <linux/mman.h>
#include <linux/mount.h>
#include <linux/personality.h>
@@ -821,6 +822,17 @@ int security_sb_statfs(struct dentry *dentry)
return call_int_hook(sb_statfs, 0, dentry);
}
+#ifdef CONFIG_FSINFO
+int security_sb_fsinfo(struct path *path, struct fsinfo_kparams *params)
+{
+ int ret = -ENODATA;
+
+ if (params->request == FSINFO_ATTR_LSM_PARAMETERS)
+ ret = 0; /* This is cumulative amongst all LSMs */
+ return call_int_hook(sb_fsinfo, ret, path, params);
+}
+#endif
+
int security_sb_mount(const char *dev_name, const struct path *path,
const char *type, unsigned long flags, void *data)
{
^ permalink raw reply related
* [PATCH 05/11] vfs: Implement parameter value retrieval with fsinfo() [ver #15]
From: David Howells @ 2019-06-28 15:44 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Implement parameter value retrieval with fsinfo() - akin to parsing
/proc/mounts.
This allows all the parameters to be retrieved in one go with:
struct fsinfo_params params = {
.request = FSINFO_ATTR_PARAMETER,
};
Each parameter comes as a pair of blobs with a length tacked on the front
rather than using separators, since any printable character that could be
used as a separator can be found in some value somewhere (including comma).
In fact, cifs allows the separator to be set using the "sep=" option in
parameter parsing.
The length on the front of each blob is 1-3 bytes long. Each byte has a
flag in bit 7 that's set if there are more bytes and clear on the last
byte; bits 0-6 should be shifted and OR'd into the length count. The bytes
are most-significant first.
For example, 0x83 0xf5 0x06 is the length (0x03<<14 | 0x75<<7 | 0x06).
As mentioned, each parameter comes as a pair of blobs in key, value order.
The value has length zero if not present. So, for example:
\x08compress\x04zlib
from btrfs would be equivalent to "compress=zlib" and:
\x02ro\x00\x06noexec\x00
would be equivalent to "ro,noexec".
The test-fsinfo sample program is modified to dump the parameters.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 122 +++++++++++++++++++++++++++++++++++++++++++
include/linux/fsinfo.h | 4 +
include/uapi/linux/fsinfo.h | 1
samples/vfs/test-fsinfo.c | 38 +++++++++++++
4 files changed, 165 insertions(+)
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index 3218968c5fee..92906a3f4010 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -301,6 +301,32 @@ static int fsinfo_generic_param_enum(struct file_system_type *f,
return sizeof(*p);
}
+void fsinfo_note_sb_params(struct fsinfo_kparams *params, unsigned int s_flags)
+{
+ if (s_flags & SB_DIRSYNC)
+ fsinfo_note_param(params, "dirsync", NULL);
+ if (s_flags & SB_LAZYTIME)
+ fsinfo_note_param(params, "lazytime", NULL);
+ if (s_flags & SB_MANDLOCK)
+ fsinfo_note_param(params, "mand", NULL);
+ if (s_flags & SB_POSIXACL)
+ fsinfo_note_param(params, "posixacl", NULL);
+ if (s_flags & SB_RDONLY)
+ fsinfo_note_param(params, "ro", NULL);
+ else
+ fsinfo_note_param(params, "rw", NULL);
+ if (s_flags & SB_SYNCHRONOUS)
+ fsinfo_note_param(params, "sync", NULL);
+}
+EXPORT_SYMBOL(fsinfo_note_sb_params);
+
+static int fsinfo_generic_parameters(struct path *path,
+ struct fsinfo_kparams *params)
+{
+ fsinfo_note_sb_params(params, READ_ONCE(path->dentry->d_sb->s_flags));
+ return params->usage;
+}
+
/*
* Implement some queries generically from stuff in the superblock.
*/
@@ -309,6 +335,7 @@ int generic_fsinfo(struct path *path, struct fsinfo_kparams *params)
struct file_system_type *fs = path->dentry->d_sb->s_type;
#define _gen(X, Y) FSINFO_ATTR_##X: return fsinfo_generic_##Y(path, params->buffer)
+#define _genp(X, Y) FSINFO_ATTR_##X: return fsinfo_generic_##Y(path, params)
#define _genf(X, Y) FSINFO_ATTR_##X: return fsinfo_generic_##Y(fs, params)
switch (params->request) {
@@ -324,6 +351,7 @@ int generic_fsinfo(struct path *path, struct fsinfo_kparams *params)
case _genf(PARAM_DESCRIPTION, param_description);
case _genf(PARAM_SPECIFICATION, param_specification);
case _genf(PARAM_ENUM, param_enum);
+ case _genp(PARAMETERS, parameters);
default:
return -EOPNOTSUPP;
}
@@ -363,8 +391,16 @@ static int vfs_fsinfo(struct path *path, struct fsinfo_kparams *params)
return fsinfo(path, params);
while (!signal_pending(current)) {
+ if (params->request == FSINFO_ATTR_PARAMETERS) {
+ if (down_read_killable(&dentry->d_sb->s_umount) < 0)
+ return -ERESTARTSYS;
+ }
+
params->usage = 0;
ret = fsinfo(path, params);
+ if (params->request == FSINFO_ATTR_PARAMETERS)
+ up_read(&dentry->d_sb->s_umount);
+
if (IS_ERR_VALUE((long)ret))
return ret; /* Error */
if ((unsigned int)ret <= params->buf_size)
@@ -536,6 +572,7 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRUCT (PARAM_DESCRIPTION, param_description),
FSINFO_STRUCT_N (PARAM_SPECIFICATION, param_specification),
FSINFO_STRUCT_N (PARAM_ENUM, param_enum),
+ FSINFO_OPAQUE (PARAMETERS),
};
/**
@@ -682,3 +719,88 @@ SYSCALL_DEFINE5(fsinfo,
error:
return ret;
}
+
+/*
+ * Store a parameter into the user's parameter buffer. The key is prefixed by
+ * a single byte length (1-127) and the value by one (0-0x7f) or two bytes
+ * (0x80-0x3fff) or three bytes (0x4000-0x1fffff).
+ *
+ * Note that we must always make the size determination, even if the buffer is
+ * already full, so that we can tell the caller how much buffer we actually
+ * need.
+ */
+static void __fsinfo_note_param(struct fsinfo_kparams *params, const char *key,
+ const char *val, unsigned int vlen)
+{
+ char *p;
+ unsigned int usage;
+ int klen, total, vmeta;
+ u8 x;
+
+ klen = strlen(key);
+ BUG_ON(klen < 1 || klen > 127);
+ BUG_ON(vlen > (1 << 21) - 1);
+ BUG_ON(vlen > 0 && !val);
+
+ vmeta = (vlen <= 127) ? 1 : (vlen <= 127 * 127) ? 2 : 3;
+
+ total = 1 + klen + vmeta + vlen;
+
+ usage = params->usage;
+ params->usage = usage + total;
+ if (!params->buffer || params->usage > params->buf_size)
+ return;
+
+ p = params->buffer + usage;
+ *p++ = klen;
+ p = memcpy(p, key, klen);
+ p += klen;
+
+ /* The more significant groups of 7 bits in the size are included in
+ * most->least order with 0x80 OR'd in. The least significant 7 bits
+ * are last with the top bit clear.
+ */
+ x = vlen >> 14;
+ if (x & 0x7f)
+ *p++ = 0x80 | x;
+
+ x = vlen >> 7;
+ if (x & 0x7f)
+ *p++ = 0x80 | x;
+
+ *p++ = vlen & 0x7f;
+ memcpy(p, val, vlen);
+}
+
+/**
+ * fsinfo_note_param - Store a parameter for FSINFO_ATTR_PARAMETERS
+ * @params: The parameter buffer
+ * @key: The parameter's key
+ * @val: The parameter's value (or NULL)
+ */
+void fsinfo_note_param(struct fsinfo_kparams *params, const char *key,
+ const char *val)
+{
+ __fsinfo_note_param(params, key, val, val ? strlen(val) : 0);
+}
+EXPORT_SYMBOL(fsinfo_note_param);
+
+/**
+ * fsinfo_note_paramf - Store a formatted parameter for FSINFO_ATTR_PARAMETERS
+ * @params: The parameter buffer
+ * @key: The parameter's key
+ * @val_fmt: Format string for the parameter's value
+ */
+void fsinfo_note_paramf(struct fsinfo_kparams *params, const char *key,
+ const char *val_fmt, ...)
+{
+ va_list va;
+ int n;
+
+ va_start(va, val_fmt);
+ n = vsnprintf(params->scratch_buffer, 4096, val_fmt, va);
+ va_end(va);
+
+ __fsinfo_note_param(params, key, params->scratch_buffer, n);
+}
+EXPORT_SYMBOL(fsinfo_note_paramf);
diff --git a/include/linux/fsinfo.h b/include/linux/fsinfo.h
index 4c250136d693..9936ba90f1c9 100644
--- a/include/linux/fsinfo.h
+++ b/include/linux/fsinfo.h
@@ -28,6 +28,10 @@ struct fsinfo_kparams {
};
extern int generic_fsinfo(struct path *, struct fsinfo_kparams *);
+extern void fsinfo_note_sb_params(struct fsinfo_kparams *, unsigned int);
+extern void fsinfo_note_param(struct fsinfo_kparams *, const char *, const char *);
+extern void fsinfo_note_paramf(struct fsinfo_kparams *, const char *, const char *, ...)
+ __printf(3, 4);
static inline void fsinfo_set_cap(struct fsinfo_capabilities *c,
enum fsinfo_capability cap)
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index 204ab25ec75d..11c4a74638b0 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -30,6 +30,7 @@ enum fsinfo_attribute {
FSINFO_ATTR_PARAM_DESCRIPTION = 12, /* General fs parameter description */
FSINFO_ATTR_PARAM_SPECIFICATION = 13, /* Nth parameter specification */
FSINFO_ATTR_PARAM_ENUM = 14, /* Nth enum-to-val */
+ FSINFO_ATTR_PARAMETERS = 15, /* Mount parameters (large string) */
FSINFO_ATTR__NR
};
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index 3c6ea3a5c157..8cf5b02e333a 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -81,6 +81,7 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRUCT (PARAM_DESCRIPTION, param_description),
FSINFO_STRUCT_N (PARAM_SPECIFICATION, param_specification),
FSINFO_STRUCT_N (PARAM_ENUM, param_enum),
+ FSINFO_OVERLARGE (PARAMETERS, -),
};
#define FSINFO_NAME(X,Y) [FSINFO_ATTR_##X] = #Y
@@ -100,6 +101,7 @@ static const char *fsinfo_attr_names[FSINFO_ATTR__NR] = {
FSINFO_NAME (PARAM_DESCRIPTION, param_description),
FSINFO_NAME (PARAM_SPECIFICATION, param_specification),
FSINFO_NAME (PARAM_ENUM, param_enum),
+ FSINFO_NAME (PARAMETERS, parameters),
};
union reply {
@@ -352,6 +354,34 @@ static void dump_fsinfo(enum fsinfo_attribute attr,
dumper(r, size);
}
+static void dump_params(struct fsinfo_attr_info about, union reply *r, int size)
+{
+ int len;
+ char *p = r->buffer, *e = p + size;
+ bool is_key = true;
+
+ while (p < e) {
+ len = 0;
+ while (p[0] & 0x80) {
+ len <<= 7;
+ len |= *p++ & 0x7f;
+ }
+
+ len <<= 7;
+ len |= *p++;
+ if (len > e - p)
+ break;
+ if (is_key || len)
+ printf("%s%*.*s", is_key ? "[PARM] " : "= ", len, len, p);
+ if (is_key)
+ putchar(' ');
+ else
+ putchar('\n');
+ p += len;
+ is_key = !is_key;
+ }
+}
+
/*
* Try one subinstance of an attribute.
*/
@@ -427,6 +457,12 @@ static int try_one(const char *file, struct fsinfo_params *params, bool raw)
return 0;
}
+ switch (params->request) {
+ case FSINFO_ATTR_PARAMETERS:
+ if (ret == 0)
+ return 0;
+ }
+
switch (about.flags & (__FSINFO_N | __FSINFO_NM)) {
case 0:
printf("\e[33m%s\e[m: ",
@@ -469,6 +505,8 @@ static int try_one(const char *file, struct fsinfo_params *params, bool raw)
return 0;
case __FSINFO_OVER:
+ if (params->request == FSINFO_ATTR_PARAMETERS)
+ dump_params(about, r, ret);
return 0;
case __FSINFO_STRUCT_ARRAY:
^ permalink raw reply related
* [PATCH 04/11] vfs: Allow fsinfo() to be used to query an fs parameter description [ver #15]
From: David Howells @ 2019-06-28 15:44 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Provide fsinfo() attributes that can be used to query a filesystem
parameter description. To do this, fsinfo() can be called on an
fs_context that doesn't yet have a superblock created and attached.
It can be obtained by doing, for example:
fd = fsopen("ext4", 0);
struct fsinfo_param_name name;
struct fsinfo_params params = {
.at_flags = AT_FSINFO_FROM_FSOPEN,
.request = fsinfo_attr_param_name,
.Nth = 3,
};
fsinfo(fd, NULL, ¶ms, &name, sizeof(name));
to query the 4th parameter name in the name to parameter ID mapping table.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 99 +++++++++++++++++++++++++++++++
include/uapi/linux/fsinfo.h | 58 ++++++++++++++++++
samples/vfs/Makefile | 2 +
samples/vfs/test-fs-query.c | 138 +++++++++++++++++++++++++++++++++++++++++++
samples/vfs/test-fsinfo.c | 14 ++++
5 files changed, 310 insertions(+), 1 deletion(-)
create mode 100644 samples/vfs/test-fs-query.c
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index d419cccbf3db..3218968c5fee 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -14,6 +14,7 @@
#include <linux/uaccess.h>
#include <linux/fsinfo.h>
#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <uapi/linux/mount.h>
#include "internal.h"
@@ -228,12 +229,87 @@ static int fsinfo_generic_name_encoding(struct path *path, char *buf)
return sizeof(encoding) - 1;
}
+static int fsinfo_generic_param_description(struct file_system_type *f,
+ struct fsinfo_kparams *params)
+{
+ const struct fs_parameter_description *desc = f->parameters;
+ const struct fs_parameter_spec *s;
+ const struct fs_parameter_enum *e;
+ struct fsinfo_param_description *p = params->buffer;
+
+ if (desc && desc->specs) {
+ for (s = desc->specs; s->name; s++) {}
+ p->nr_params = s - desc->specs;
+ if (desc->enums) {
+ for (e = desc->enums; e->name[0]; e++) {}
+ p->nr_enum_names = e - desc->enums;
+ }
+ }
+
+ return sizeof(*p);
+}
+
+static int fsinfo_generic_param_specification(struct file_system_type *f,
+ struct fsinfo_kparams *params)
+{
+ const struct fs_parameter_description *desc = f->parameters;
+ const struct fs_parameter_spec *s;
+ struct fsinfo_param_specification *p = params->buffer;
+ unsigned int nth = params->Nth;
+
+ if (!desc || !desc->specs)
+ return -ENODATA;
+
+ for (s = desc->specs; s->name; s++) {
+ if (nth == 0)
+ goto found;
+ nth--;
+ }
+
+ return -ENODATA;
+
+found:
+ p->type = s->type;
+ p->flags = s->flags;
+ p->opt = s->opt;
+ strlcpy(p->name, s->name, sizeof(p->name));
+ return sizeof(*p);
+}
+
+static int fsinfo_generic_param_enum(struct file_system_type *f,
+ struct fsinfo_kparams *params)
+{
+ const struct fs_parameter_description *desc = f->parameters;
+ const struct fs_parameter_enum *e;
+ struct fsinfo_param_enum *p = params->buffer;
+ unsigned int nth = params->Nth;
+
+ if (!desc || !desc->enums)
+ return -ENODATA;
+
+ for (e = desc->enums; e->name; e++) {
+ if (nth == 0)
+ goto found;
+ nth--;
+ }
+
+ return -ENODATA;
+
+found:
+ p->opt = e->opt;
+ strlcpy(p->name, e->name, sizeof(p->name));
+ return sizeof(*p);
+}
+
/*
* Implement some queries generically from stuff in the superblock.
*/
int generic_fsinfo(struct path *path, struct fsinfo_kparams *params)
{
+ struct file_system_type *fs = path->dentry->d_sb->s_type;
+
#define _gen(X, Y) FSINFO_ATTR_##X: return fsinfo_generic_##Y(path, params->buffer)
+#define _genf(X, Y) FSINFO_ATTR_##X: return fsinfo_generic_##Y(fs, params)
switch (params->request) {
case _gen(STATFS, statfs);
@@ -245,6 +321,9 @@ int generic_fsinfo(struct path *path, struct fsinfo_kparams *params)
case _gen(VOLUME_UUID, volume_uuid);
case _gen(VOLUME_ID, volume_id);
case _gen(NAME_ENCODING, name_encoding);
+ case _genf(PARAM_DESCRIPTION, param_description);
+ case _genf(PARAM_SPECIFICATION, param_specification);
+ case _genf(PARAM_ENUM, param_enum);
default:
return -EOPNOTSUPP;
}
@@ -349,10 +428,11 @@ static int vfs_fsinfo_fd(unsigned int fd, struct fsinfo_kparams *params)
}
/*
- * Allow access to an fs_context object as created by fsopen() or fspick().
+ * Allow an fs_context object as created by fsopen() or fspick() to be queried.
*/
static int vfs_fsinfo_fscontext(int fd, struct fsinfo_kparams *params)
{
+ struct file_system_type *fs;
struct fs_context *fc;
struct fd f = fdget(fd);
int ret;
@@ -363,10 +443,24 @@ static int vfs_fsinfo_fscontext(int fd, struct fsinfo_kparams *params)
ret = -EINVAL;
if (f.file->f_op != &fscontext_fops)
goto out_f;
+ fc = f.file->private_data;
+ fs = fc->fs_type;
+
ret = -EOPNOTSUPP;
if (fc->ops == &legacy_fs_context_ops)
goto out_f;
+ /* Filesystem parameter query is static information and doesn't need a
+ * lock to read it, nor even a dentry or superblock.
+ */
+ switch (params->request) {
+ case _genf(PARAM_DESCRIPTION, param_description);
+ case _genf(PARAM_SPECIFICATION, param_specification);
+ case _genf(PARAM_ENUM, param_enum);
+ default:
+ break;
+ }
+
ret = mutex_lock_interruptible(&fc->uapi_mutex);
if (ret == 0) {
ret = -EBADFD;
@@ -439,6 +533,9 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRING (VOLUME_NAME),
FSINFO_STRING (NAME_ENCODING),
FSINFO_STRING (NAME_CODEPAGE),
+ FSINFO_STRUCT (PARAM_DESCRIPTION, param_description),
+ FSINFO_STRUCT_N (PARAM_SPECIFICATION, param_specification),
+ FSINFO_STRUCT_N (PARAM_ENUM, param_enum),
};
/**
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index cc7e13a9b95f..204ab25ec75d 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -27,6 +27,9 @@ enum fsinfo_attribute {
FSINFO_ATTR_VOLUME_NAME = 9, /* Volume name (string) */
FSINFO_ATTR_NAME_ENCODING = 10, /* Filename encoding (string) */
FSINFO_ATTR_NAME_CODEPAGE = 11, /* Filename codepage (string) */
+ FSINFO_ATTR_PARAM_DESCRIPTION = 12, /* General fs parameter description */
+ FSINFO_ATTR_PARAM_SPECIFICATION = 13, /* Nth parameter specification */
+ FSINFO_ATTR_PARAM_ENUM = 14, /* Nth enum-to-val */
FSINFO_ATTR__NR
};
@@ -216,4 +219,59 @@ struct fsinfo_fsinfo {
__u32 max_cap; /* Number of supported capabilities (fsinfo_cap__nr) */
};
+/*
+ * Information struct for fsinfo(fsinfo_attr_param_description).
+ *
+ * Query the parameter set for a filesystem.
+ */
+struct fsinfo_param_description {
+ __u32 nr_params; /* Number of individual parameters */
+ __u32 nr_enum_names; /* Number of enum names */
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_param_specification).
+ *
+ * Query the specification of the Nth filesystem parameter.
+ */
+struct fsinfo_param_specification {
+ __u32 type; /* enum fsinfo_param_specification_type */
+ __u32 flags; /* Qualifiers */
+ __u32 opt; /* Corresponding params have same ID here */
+ char name[240];
+};
+
+enum fsinfo_param_specification_type {
+ FSINFO_PARAM_SPEC_NOT_DEFINED = 0,
+ FSINFO_PARAM_SPEC_IS_FLAG = 1,
+ FSINFO_PARAM_SPEC_IS_BOOL = 2,
+ FSINFO_PARAM_SPEC_IS_U32 = 3,
+ FSINFO_PARAM_SPEC_IS_U32_OCTAL = 4,
+ FSINFO_PARAM_SPEC_IS_U32_HEX = 5,
+ FSINFO_PARAM_SPEC_IS_S32 = 6,
+ FSINFO_PARAM_SPEC_IS_U64 = 7,
+ FSINFO_PARAM_SPEC_IS_ENUM = 8,
+ FSINFO_PARAM_SPEC_IS_STRING = 9,
+ FSINFO_PARAM_SPEC_IS_BLOB = 10,
+ FSINFO_PARAM_SPEC_IS_BLOCKDEV = 11,
+ FSINFO_PARAM_SPEC_IS_PATH = 12,
+ FSINFO_PARAM_SPEC_IS_FD = 13,
+ NR__FSINFO_PARAM_SPEC
+};
+
+#define FSINFO_PARAM_SPEC_VALUE_IS_OPTIONAL 0X00000001
+#define FSINFO_PARAM_SPEC_PREFIX_NO_IS_NEG 0X00000002
+#define FSINFO_PARAM_SPEC_EMPTY_STRING_IS_NEG 0X00000004
+#define FSINFO_PARAM_SPEC_DEPRECATED 0X00000008
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_param_enum).
+ *
+ * Query the Nth filesystem enum parameter value name.
+ */
+struct fsinfo_param_enum {
+ __u32 opt; /* ->opt of the relevant parameter specification */
+ char name[252]; /* Name of the enum value */
+};
+
#endif /* _UAPI_LINUX_FSINFO_H */
diff --git a/samples/vfs/Makefile b/samples/vfs/Makefile
index d3cc8e9a4fd8..3c542d3b9479 100644
--- a/samples/vfs/Makefile
+++ b/samples/vfs/Makefile
@@ -1,6 +1,7 @@
# List of programs to build
hostprogs-y := \
test-fsinfo \
+ test-fs-query \
test-fsmount \
test-statx
@@ -10,5 +11,6 @@ always := $(hostprogs-y)
HOSTCFLAGS_test-fsinfo.o += -I$(objtree)/usr/include
HOSTLDLIBS_test-fsinfo += -lm
+HOSTCFLAGS_test-fs-query.o += -I$(objtree)/usr/include
HOSTCFLAGS_test-fsmount.o += -I$(objtree)/usr/include
HOSTCFLAGS_test-statx.o += -I$(objtree)/usr/include
diff --git a/samples/vfs/test-fs-query.c b/samples/vfs/test-fs-query.c
new file mode 100644
index 000000000000..7572411ddb7e
--- /dev/null
+++ b/samples/vfs/test-fs-query.c
@@ -0,0 +1,138 @@
+/* Test using the fsinfo() system call to query mount parameters.
+ *
+ * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define _GNU_SOURCE
+#define _ATFILE_SOURCE
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <time.h>
+#include <math.h>
+#include <sys/syscall.h>
+#include <linux/fsinfo.h>
+#include <linux/fcntl.h>
+#include <sys/stat.h>
+
+#ifndef __NR_fsopen
+#define __NR_fsopen -1
+#endif
+#ifndef __NR_fsinfo
+#define __NR_fsinfo -1
+#endif
+
+static int fsopen(const char *fs_name, unsigned int flags)
+{
+ return syscall(__NR_fsopen, fs_name, flags);
+}
+
+static ssize_t fsinfo(int dfd, const char *filename, struct fsinfo_params *params,
+ void *buffer, size_t buf_size)
+{
+ return syscall(__NR_fsinfo, dfd, filename, params, buffer, buf_size);
+}
+
+static const char *param_types[NR__FSINFO_PARAM_SPEC] = {
+ [FSINFO_PARAM_SPEC_NOT_DEFINED] = "?undef",
+ [FSINFO_PARAM_SPEC_IS_FLAG] = "flag",
+ [FSINFO_PARAM_SPEC_IS_BOOL] = "bool",
+ [FSINFO_PARAM_SPEC_IS_U32] = "u32",
+ [FSINFO_PARAM_SPEC_IS_U32_OCTAL] = "octal",
+ [FSINFO_PARAM_SPEC_IS_U32_HEX] = "hex",
+ [FSINFO_PARAM_SPEC_IS_S32] = "s32",
+ [FSINFO_PARAM_SPEC_IS_U64] = "u64",
+ [FSINFO_PARAM_SPEC_IS_ENUM] = "enum",
+ [FSINFO_PARAM_SPEC_IS_STRING] = "string",
+ [FSINFO_PARAM_SPEC_IS_BLOB] = "binary",
+ [FSINFO_PARAM_SPEC_IS_BLOCKDEV] = "blockdev",
+ [FSINFO_PARAM_SPEC_IS_PATH] = "path",
+ [FSINFO_PARAM_SPEC_IS_FD] = "fd",
+};
+
+/*
+ *
+ */
+int main(int argc, char **argv)
+{
+ struct fsinfo_param_description desc;
+ struct fsinfo_param_specification spec;
+ struct fsinfo_param_enum enum_name;
+
+ struct fsinfo_params params = {
+ .at_flags = AT_FSINFO_FROM_FSOPEN,
+ };
+ int fd;
+
+ if (argc != 2) {
+ printf("Format: test-fs-query <fs_name>\n");
+ exit(2);
+ }
+
+ fd = fsopen(argv[1], 0);
+ if (fd == -1) {
+ perror(argv[1]);
+ exit(1);
+ }
+
+ params.request = FSINFO_ATTR_PARAM_DESCRIPTION;
+ if (fsinfo(fd, NULL, ¶ms, &desc, sizeof(desc)) == -1) {
+ perror("fsinfo/desc");
+ exit(1);
+ }
+
+ printf("Filesystem %s has %u parameters\n", argv[1], desc.nr_params);
+
+ params.request = FSINFO_ATTR_PARAM_SPECIFICATION;
+ for (params.Nth = 0; params.Nth < desc.nr_params; params.Nth++) {
+ char type[32];
+
+ if (fsinfo(fd, NULL, ¶ms, &spec, sizeof(spec)) == -1) {
+ if (errno == ENODATA)
+ break;
+ perror("fsinfo/spec");
+ exit(1);
+ }
+
+ if (spec.type < NR__FSINFO_PARAM_SPEC)
+ strcpy(type, param_types[spec.type]);
+ else
+ sprintf(type, "?%u", spec.type);
+
+ printf("- PARAM[%3u] %-20s %3u %s%s%s%s%s\n",
+ params.Nth,
+ spec.name,
+ spec.opt,
+ type,
+ spec.flags & FSINFO_PARAM_SPEC_VALUE_IS_OPTIONAL ? ",opt" : "",
+ spec.flags & FSINFO_PARAM_SPEC_PREFIX_NO_IS_NEG ? ",neg-no" : "",
+ spec.flags & FSINFO_PARAM_SPEC_EMPTY_STRING_IS_NEG ? ",neg-empty" : "",
+ spec.flags & FSINFO_PARAM_SPEC_DEPRECATED ? ",dep" : "");
+ }
+
+ printf("Filesystem has %u enumeration values\n", desc.nr_enum_names);
+
+ params.request = FSINFO_ATTR_PARAM_ENUM;
+ for (params.Nth = 0; params.Nth < desc.nr_enum_names; params.Nth++) {
+ if (fsinfo(fd, NULL, ¶ms, &enum_name, sizeof(enum_name)) == -1) {
+ if (errno == ENODATA)
+ break;
+ perror("fsinfo/enum");
+ exit(1);
+ }
+ printf("- ENUM[%3u] %3u: %s\n",
+ params.Nth, enum_name.opt, enum_name.name);
+ }
+ return 0;
+}
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index 8cce1986df7e..3c6ea3a5c157 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -78,6 +78,9 @@ static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
FSINFO_STRING (VOLUME_NAME, volume_name),
FSINFO_STRING (NAME_ENCODING, name_encoding),
FSINFO_STRING (NAME_CODEPAGE, name_codepage),
+ FSINFO_STRUCT (PARAM_DESCRIPTION, param_description),
+ FSINFO_STRUCT_N (PARAM_SPECIFICATION, param_specification),
+ FSINFO_STRUCT_N (PARAM_ENUM, param_enum),
};
#define FSINFO_NAME(X,Y) [FSINFO_ATTR_##X] = #Y
@@ -94,6 +97,9 @@ static const char *fsinfo_attr_names[FSINFO_ATTR__NR] = {
FSINFO_NAME (VOLUME_NAME, volume_name),
FSINFO_NAME (NAME_ENCODING, name_encoding),
FSINFO_NAME (NAME_CODEPAGE, name_codepage),
+ FSINFO_NAME (PARAM_DESCRIPTION, param_description),
+ FSINFO_NAME (PARAM_SPECIFICATION, param_specification),
+ FSINFO_NAME (PARAM_ENUM, param_enum),
};
union reply {
@@ -514,6 +520,14 @@ int main(int argc, char **argv)
}
for (attr = 0; attr <= FSINFO_ATTR__NR; attr++) {
+ switch (attr) {
+ case FSINFO_ATTR_PARAM_DESCRIPTION:
+ case FSINFO_ATTR_PARAM_SPECIFICATION:
+ case FSINFO_ATTR_PARAM_ENUM:
+ /* See test-fs-query.c instead */
+ continue;
+ }
+
Nth = 0;
do {
Mth = 0;
^ permalink raw reply related
* [PATCH 03/11] vfs: Allow fsinfo() to query what's in an fs_context [ver #15]
From: David Howells @ 2019-06-28 15:44 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Allow fsinfo() to be used to query the filesystem attached to an fs_context
once a superblock has been created or if it comes from fspick().
The caller must specify AT_FSINFO_FROM_FSOPEN in the parameters and must
supply the fd from fsopen() as dfd and must set filename to NULL.
This is done with something like:
fd = fsopen("ext4", 0);
...
struct fsinfo_params params = {
.at_flags = AT_FSINFO_FROM_FSOPEN;
...
};
fsinfo(fd, NULL, ¶ms, ...);
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
fs/statfs.c | 2 +-
include/uapi/linux/fcntl.h | 2 ++
3 files changed, 46 insertions(+), 2 deletions(-)
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index 09e743b16235..d419cccbf3db 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -13,6 +13,7 @@
#include <linux/security.h>
#include <linux/uaccess.h>
#include <linux/fsinfo.h>
+#include <linux/fs_context.h>
#include <uapi/linux/mount.h>
#include "internal.h"
@@ -347,6 +348,42 @@ static int vfs_fsinfo_fd(unsigned int fd, struct fsinfo_kparams *params)
return ret;
}
+/*
+ * Allow access to an fs_context object as created by fsopen() or fspick().
+ */
+static int vfs_fsinfo_fscontext(int fd, struct fsinfo_kparams *params)
+{
+ struct fs_context *fc;
+ struct fd f = fdget(fd);
+ int ret;
+
+ if (!f.file)
+ return -EBADF;
+
+ ret = -EINVAL;
+ if (f.file->f_op != &fscontext_fops)
+ goto out_f;
+ ret = -EOPNOTSUPP;
+ if (fc->ops == &legacy_fs_context_ops)
+ goto out_f;
+
+ ret = mutex_lock_interruptible(&fc->uapi_mutex);
+ if (ret == 0) {
+ ret = -EBADFD;
+ if (fc->root) {
+ struct path path = { .dentry = fc->root };
+
+ ret = vfs_fsinfo(&path, params);
+ }
+
+ mutex_unlock(&fc->uapi_mutex);
+ }
+
+out_f:
+ fdput(f);
+ return ret;
+}
+
/*
* Return buffer information by requestable attribute.
*
@@ -452,6 +489,9 @@ SYSCALL_DEFINE5(fsinfo,
kparams.request = user_params.request;
kparams.Nth = user_params.Nth;
kparams.Mth = user_params.Mth;
+
+ if ((kparams.at_flags & AT_FSINFO_FROM_FSOPEN) && pathname)
+ return -EINVAL;
} else {
kparams.request = FSINFO_ATTR_STATFS;
}
@@ -508,7 +548,9 @@ SYSCALL_DEFINE5(fsinfo,
if (!kparams.buffer)
goto error_scratch;
- if (pathname)
+ if (kparams.at_flags & AT_FSINFO_FROM_FSOPEN)
+ ret = vfs_fsinfo_fscontext(dfd, &kparams);
+ else if (pathname)
ret = vfs_fsinfo_path(dfd, pathname, &kparams);
else
ret = vfs_fsinfo_fd(dfd, &kparams);
diff --git a/fs/statfs.c b/fs/statfs.c
index eea7af6f2f22..b9b63d9f4f24 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -86,7 +86,7 @@ int vfs_statfs(const struct path *path, struct kstatfs *buf)
int error;
error = statfs_by_dentry(path->dentry, buf);
- if (!error)
+ if (!error && path->mnt)
buf->f_flags = calculate_f_flags(path->mnt);
return error;
}
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 1d338357df8a..6a2402a8fa30 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -91,6 +91,8 @@
#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */
#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */
+#define AT_FSINFO_FROM_FSOPEN 0x2000 /* Examine the fs_context attached to dfd by fsopen() */
+
#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
^ permalink raw reply related
* [PATCH 02/11] fsinfo: Add syscalls to other arches [ver #15]
From: David Howells @ 2019-06-28 15:43 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Add the fsinfo syscall to the other arches.
Signed-off-by: David Howells <dhowells@redhat.com>
---
arch/alpha/kernel/syscalls/syscall.tbl | 1 +
arch/arm/tools/syscall.tbl | 1 +
arch/arm64/include/asm/unistd.h | 2 +-
arch/arm64/include/asm/unistd32.h | 2 +-
arch/ia64/kernel/syscalls/syscall.tbl | 1 +
arch/m68k/kernel/syscalls/syscall.tbl | 1 +
arch/microblaze/kernel/syscalls/syscall.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n32.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n64.tbl | 1 +
arch/mips/kernel/syscalls/syscall_o32.tbl | 1 +
arch/parisc/kernel/syscalls/syscall.tbl | 1 +
arch/powerpc/kernel/syscalls/syscall.tbl | 1 +
arch/s390/kernel/syscalls/syscall.tbl | 1 +
arch/sh/kernel/syscalls/syscall.tbl | 1 +
arch/sparc/kernel/syscalls/syscall.tbl | 1 +
arch/xtensa/kernel/syscalls/syscall.tbl | 1 +
16 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 9e7704e44f6d..624d01c3c8eb 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -473,3 +473,4 @@
541 common fsconfig sys_fsconfig
542 common fsmount sys_fsmount
543 common fspick sys_fspick
+544 common fsinfo sys_fsinfo
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index aaf479a9e92d..ad608b49808c 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -447,3 +447,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 70e6882853c0..e8f7d95a1481 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 434
+#define __NR_compat_syscalls 435
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index c39e90600bb3..52d0c148b557 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -884,7 +884,7 @@ __SYSCALL(__NR_fsopen, sys_fsopen)
__SYSCALL(__NR_fsconfig, sys_fsconfig)
#define __NR_fsmount 432
__SYSCALL(__NR_fsmount, sys_fsmount)
-#define __NR_fspick 433
+#define __NR_fspick 434
__SYSCALL(__NR_fspick, sys_fspick)
/*
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index e01df3f2f80d..68314763ad16 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -354,3 +354,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 7e3d0734b2f3..ee73a7534b1b 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -433,3 +433,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 26339e417695..7bc067f4b713 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 0e2dd68ade57..29b76bd67cc0 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -372,3 +372,4 @@
431 n32 fsconfig sys_fsconfig
432 n32 fsmount sys_fsmount
433 n32 fspick sys_fspick
+434 n32 fsinfo sys_fsinfo
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 5eebfa0d155c..349fb30bb8b5 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -348,3 +348,4 @@
431 n64 fsconfig sys_fsconfig
432 n64 fsmount sys_fsmount
433 n64 fspick sys_fspick
+434 n64 fsinfo sys_fsinfo
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 3cc1374e02d0..71057426b503 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -421,3 +421,4 @@
431 o32 fsconfig sys_fsconfig
432 o32 fsmount sys_fsmount
433 o32 fspick sys_fspick
+434 o32 fsinfo sys_fsinfo
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index c9e377d59232..32cff48a1ebd 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -430,3 +430,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 103655d84b4b..e5755eb6fb84 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -515,3 +515,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index e822b2964a83..bcd54116e107 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -436,3 +436,4 @@
431 common fsconfig sys_fsconfig sys_fsconfig
432 common fsmount sys_fsmount sys_fsmount
433 common fspick sys_fspick sys_fspick
+434 common fsinfo sys_fsinfo sys_fsinfo
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 016a727d4357..0320a5c63cbd 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -436,3 +436,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index e047480b1605..f81b1f9402bd 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -479,3 +479,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 5fa0ee1c8e00..729795148850 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -404,3 +404,4 @@
431 common fsconfig sys_fsconfig
432 common fsmount sys_fsmount
433 common fspick sys_fspick
+434 common fsinfo sys_fsinfo
^ permalink raw reply related
* [PATCH 01/11] vfs: syscall: Add fsinfo() to query filesystem information [ver #15]
From: David Howells @ 2019-06-28 15:43 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
In-Reply-To: <156173661696.14042.17822154531324224780.stgit@warthog.procyon.org.uk>
Add a system call to allow filesystem information to be queried. A request
value can be given to indicate the desired attribute. Support is provided
for enumerating multi-value attributes.
===============
NEW SYSTEM CALL
===============
The new system call looks like:
int ret = fsinfo(int dfd,
const char *filename,
const struct fsinfo_params *params,
void *buffer,
size_t buf_size);
The params parameter optionally points to a block of parameters:
struct fsinfo_params {
__u32 at_flags;
__u32 request;
__u32 Nth;
__u32 Mth;
__u64 __reserved[3];
};
If params is NULL, it is assumed params->request should be
fsinfo_attr_statfs, params->Nth should be 0, params->Mth should be 0 and
params->at_flags should be 0.
If params is given, all of params->__reserved[] must be 0.
dfd, filename and params->at_flags indicate the file to query. There is no
equivalent of lstat() as that can be emulated with fsinfo() by setting
AT_SYMLINK_NOFOLLOW in params->at_flags. There is also no equivalent of
fstat() as that can be emulated by passing a NULL filename to fsinfo() with
the fd of interest in dfd. AT_NO_AUTOMOUNT can also be used to an allow
automount point to be queried without triggering it.
params->request indicates the attribute/attributes to be queried. This can
be one of:
FSINFO_ATTR_STATFS - statfs-style info
FSINFO_ATTR_FSINFO - Information about fsinfo()
FSINFO_ATTR_IDS - Filesystem IDs
FSINFO_ATTR_LIMITS - Filesystem limits
FSINFO_ATTR_SUPPORTS - What's supported in statx(), IOC flags
FSINFO_ATTR_CAPABILITIES - Filesystem capabilities
FSINFO_ATTR_TIMESTAMP_INFO - Inode timestamp info
FSINFO_ATTR_VOLUME_ID - Volume ID (string)
FSINFO_ATTR_VOLUME_UUID - Volume UUID
FSINFO_ATTR_VOLUME_NAME - Volume name (string)
FSINFO_ATTR_NAME_ENCODING - Filename encoding (string)
FSINFO_ATTR_NAME_CODEPAGE - Filename codepage (string)
Some attributes (such as the servers backing a network filesystem) can have
multiple values. These can be enumerated by setting params->Nth and
params->Mth to 0, 1, ... until ENODATA is returned.
buffer and buf_size point to the reply buffer. The buffer is filled up to
the specified size, even if this means truncating the reply. The full size
of the reply is returned. In future versions, this will allow extra fields
to be tacked on to the end of the reply, but anyone not expecting them will
only get the subset they're expecting. If either buffer of buf_size are 0,
no copy will take place and the data size will be returned.
At the moment, this will only work on x86_64 and i386 as it requires the
system call to be wired up.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
---
arch/x86/entry/syscalls/syscall_32.tbl | 1
arch/x86/entry/syscalls/syscall_64.tbl | 1
fs/Kconfig | 7
fs/Makefile | 1
fs/fsinfo.c | 545 ++++++++++++++++++++++++++++++++
include/linux/fs.h | 5
include/linux/fsinfo.h | 65 ++++
include/linux/syscalls.h | 4
include/uapi/asm-generic/unistd.h | 4
include/uapi/linux/fsinfo.h | 219 +++++++++++++
kernel/sys_ni.c | 1
samples/vfs/Makefile | 4
samples/vfs/test-fsinfo.c | 551 ++++++++++++++++++++++++++++++++
13 files changed, 1407 insertions(+), 1 deletion(-)
create mode 100644 fs/fsinfo.c
create mode 100644 include/linux/fsinfo.h
create mode 100644 include/uapi/linux/fsinfo.h
create mode 100644 samples/vfs/test-fsinfo.c
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ad968b7bac72..03decae51513 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -438,3 +438,4 @@
431 i386 fsconfig sys_fsconfig __ia32_sys_fsconfig
432 i386 fsmount sys_fsmount __ia32_sys_fsmount
433 i386 fspick sys_fspick __ia32_sys_fspick
+434 i386 fsinfo sys_fsinfo __ia32_sys_fsinfo
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index b4e6f9e6204a..ea63df9a1020 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -355,6 +355,7 @@
431 common fsconfig __x64_sys_fsconfig
432 common fsmount __x64_sys_fsmount
433 common fspick __x64_sys_fspick
+434 common fsinfo __x64_sys_fsinfo
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/Kconfig b/fs/Kconfig
index cbbffc8b9ef5..9e7d2f2c0111 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -15,6 +15,13 @@ config VALIDATE_FS_PARSER
Enable this to perform validation of the parameter description for a
filesystem when it is registered.
+config FSINFO
+ bool "Enable the fsinfo() system call"
+ help
+ Enable the file system information querying system call to allow
+ comprehensive information to be retrieved about a filesystem,
+ superblock or mount object.
+
if BLOCK
config FS_IOMAP
diff --git a/fs/Makefile b/fs/Makefile
index c9aea23aba56..26eaeae4b9a1 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -53,6 +53,7 @@ obj-$(CONFIG_SYSCTL) += drop_caches.o
obj-$(CONFIG_FHANDLE) += fhandle.o
obj-$(CONFIG_FS_IOMAP) += iomap.o
+obj-$(CONFIG_FSINFO) += fsinfo.o
obj-y += quota/
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
new file mode 100644
index 000000000000..09e743b16235
--- /dev/null
+++ b/fs/fsinfo.c
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Filesystem information query.
+ *
+ * Copyright (C) 2019 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#include <linux/syscalls.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/statfs.h>
+#include <linux/security.h>
+#include <linux/uaccess.h>
+#include <linux/fsinfo.h>
+#include <uapi/linux/mount.h>
+#include "internal.h"
+
+static u32 calc_mount_attrs(u32 mnt_flags)
+{
+ u32 attrs = 0;
+
+ if (mnt_flags & MNT_READONLY)
+ attrs |= MOUNT_ATTR_RDONLY;
+ if (mnt_flags & MNT_NOSUID)
+ attrs |= MOUNT_ATTR_NOSUID;
+ if (mnt_flags & MNT_NODEV)
+ attrs |= MOUNT_ATTR_NODEV;
+ if (mnt_flags & MNT_NOEXEC)
+ attrs |= MOUNT_ATTR_NOEXEC;
+ if (mnt_flags & MNT_NODIRATIME)
+ attrs |= MOUNT_ATTR_NODIRATIME;
+
+ if (mnt_flags & MNT_NOATIME)
+ attrs |= MOUNT_ATTR_NOATIME;
+ else if (mnt_flags & MNT_RELATIME)
+ attrs |= MOUNT_ATTR_RELATIME;
+ else
+ attrs |= MOUNT_ATTR_STRICTATIME;
+ return attrs;
+}
+
+/*
+ * Get basic filesystem stats from statfs.
+ */
+static int fsinfo_generic_statfs(struct path *path, struct fsinfo_statfs *p)
+{
+ struct kstatfs buf;
+ int ret;
+
+ ret = vfs_statfs(path, &buf);
+ if (ret < 0)
+ return ret;
+
+ p->f_blocks.hi = 0;
+ p->f_blocks.lo = buf.f_blocks;
+ p->f_bfree.hi = 0;
+ p->f_bfree.lo = buf.f_bfree;
+ p->f_bavail.hi = 0;
+ p->f_bavail.lo = buf.f_bavail;
+ p->f_files.hi = 0;
+ p->f_files.lo = buf.f_files;
+ p->f_ffree.hi = 0;
+ p->f_ffree.lo = buf.f_ffree;
+ p->f_favail.hi = 0;
+ p->f_favail.lo = buf.f_ffree;
+ p->f_bsize = buf.f_bsize;
+ p->f_frsize = buf.f_frsize;
+
+ p->mnt_attrs = calc_mount_attrs(path->mnt->mnt_flags);
+ return sizeof(*p);
+}
+
+static int fsinfo_generic_ids(struct path *path, struct fsinfo_ids *p)
+{
+ struct super_block *sb;
+ struct kstatfs buf;
+ int ret;
+
+ ret = vfs_statfs(path, &buf);
+ if (ret < 0 && ret != -ENOSYS)
+ return ret;
+
+ sb = path->dentry->d_sb;
+ p->f_fstype = sb->s_magic;
+ p->f_dev_major = MAJOR(sb->s_dev);
+ p->f_dev_minor = MINOR(sb->s_dev);
+
+ memcpy(&p->f_fsid, &buf.f_fsid, sizeof(p->f_fsid));
+ strlcpy(p->f_fs_name, path->dentry->d_sb->s_type->name,
+ sizeof(p->f_fs_name));
+ return sizeof(*p);
+}
+
+static int fsinfo_generic_limits(struct path *path, struct fsinfo_limits *lim)
+{
+ struct super_block *sb = path->dentry->d_sb;
+
+ lim->max_file_size.hi = 0;
+ lim->max_file_size.lo = sb->s_maxbytes;
+ lim->max_hard_links = sb->s_max_links;
+ lim->max_uid = UINT_MAX;
+ lim->max_gid = UINT_MAX;
+ lim->max_projid = UINT_MAX;
+ lim->max_filename_len = NAME_MAX;
+ lim->max_symlink_len = PAGE_SIZE;
+ lim->max_xattr_name_len = XATTR_NAME_MAX;
+ lim->max_xattr_body_len = XATTR_SIZE_MAX;
+ lim->max_dev_major = 0xffffff;
+ lim->max_dev_minor = 0xff;
+ return sizeof(*lim);
+}
+
+static int fsinfo_generic_supports(struct path *path, struct fsinfo_supports *c)
+{
+ struct super_block *sb = path->dentry->d_sb;
+
+ c->stx_mask = STATX_BASIC_STATS;
+ if (sb->s_d_op && sb->s_d_op->d_automount)
+ c->stx_attributes |= STATX_ATTR_AUTOMOUNT;
+ return sizeof(*c);
+}
+
+static int fsinfo_generic_capabilities(struct path *path,
+ struct fsinfo_capabilities *c)
+{
+ struct super_block *sb = path->dentry->d_sb;
+
+ if (sb->s_mtd)
+ fsinfo_set_cap(c, FSINFO_CAP_IS_FLASH_FS);
+ else if (sb->s_bdev)
+ fsinfo_set_cap(c, FSINFO_CAP_IS_BLOCK_FS);
+
+ if (sb->s_quota_types & QTYPE_MASK_USR)
+ fsinfo_set_cap(c, FSINFO_CAP_USER_QUOTAS);
+ if (sb->s_quota_types & QTYPE_MASK_GRP)
+ fsinfo_set_cap(c, FSINFO_CAP_GROUP_QUOTAS);
+ if (sb->s_quota_types & QTYPE_MASK_PRJ)
+ fsinfo_set_cap(c, FSINFO_CAP_PROJECT_QUOTAS);
+ if (sb->s_d_op && sb->s_d_op->d_automount)
+ fsinfo_set_cap(c, FSINFO_CAP_AUTOMOUNTS);
+ if (sb->s_id[0])
+ fsinfo_set_cap(c, FSINFO_CAP_VOLUME_ID);
+
+ fsinfo_set_cap(c, FSINFO_CAP_HAS_ATIME);
+ fsinfo_set_cap(c, FSINFO_CAP_HAS_CTIME);
+ fsinfo_set_cap(c, FSINFO_CAP_HAS_MTIME);
+ return sizeof(*c);
+}
+
+static const struct fsinfo_timestamp_info fsinfo_default_timestamp_info = {
+ .atime = {
+ .minimum = S64_MIN,
+ .maximum = S64_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .mtime = {
+ .minimum = S64_MIN,
+ .maximum = S64_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .ctime = {
+ .minimum = S64_MIN,
+ .maximum = S64_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .btime = {
+ .minimum = S64_MIN,
+ .maximum = S64_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+};
+
+static int fsinfo_generic_timestamp_info(struct path *path,
+ struct fsinfo_timestamp_info *ts)
+{
+ struct super_block *sb = path->dentry->d_sb;
+ s8 exponent;
+
+ *ts = fsinfo_default_timestamp_info;
+
+
+ if (sb->s_time_gran < 1000000000) {
+ if (sb->s_time_gran < 1000)
+ exponent = -9;
+ else if (sb->s_time_gran < 1000000)
+ exponent = -6;
+ else
+ exponent = -3;
+
+ ts->atime.gran_exponent = exponent;
+ ts->mtime.gran_exponent = exponent;
+ ts->ctime.gran_exponent = exponent;
+ ts->btime.gran_exponent = exponent;
+ }
+
+ return sizeof(*ts);
+}
+
+static int fsinfo_generic_volume_uuid(struct path *path,
+ struct fsinfo_volume_uuid *vu)
+{
+ struct super_block *sb = path->dentry->d_sb;
+
+ memcpy(vu, &sb->s_uuid, sizeof(*vu));
+ return sizeof(*vu);
+}
+
+static int fsinfo_generic_volume_id(struct path *path, char *buf)
+{
+ struct super_block *sb = path->dentry->d_sb;
+ size_t len = strlen(sb->s_id);
+
+ memcpy(buf, sb->s_id, len + 1);
+ return len;
+}
+
+static int fsinfo_generic_name_encoding(struct path *path, char *buf)
+{
+ static const char encoding[] = "utf8";
+
+ memcpy(buf, encoding, sizeof(encoding) - 1);
+ return sizeof(encoding) - 1;
+}
+
+/*
+ * Implement some queries generically from stuff in the superblock.
+ */
+int generic_fsinfo(struct path *path, struct fsinfo_kparams *params)
+{
+#define _gen(X, Y) FSINFO_ATTR_##X: return fsinfo_generic_##Y(path, params->buffer)
+
+ switch (params->request) {
+ case _gen(STATFS, statfs);
+ case _gen(IDS, ids);
+ case _gen(LIMITS, limits);
+ case _gen(SUPPORTS, supports);
+ case _gen(CAPABILITIES, capabilities);
+ case _gen(TIMESTAMP_INFO, timestamp_info);
+ case _gen(VOLUME_UUID, volume_uuid);
+ case _gen(VOLUME_ID, volume_id);
+ case _gen(NAME_ENCODING, name_encoding);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+EXPORT_SYMBOL(generic_fsinfo);
+
+/*
+ * Retrieve the filesystem info. We make some stuff up if the operation is not
+ * supported.
+ */
+static int vfs_fsinfo(struct path *path, struct fsinfo_kparams *params)
+{
+ struct dentry *dentry = path->dentry;
+ int (*fsinfo)(struct path *, struct fsinfo_kparams *);
+ int ret;
+
+ if (params->request == FSINFO_ATTR_FSINFO) {
+ struct fsinfo_fsinfo *info = params->buffer;
+
+ info->max_attr = FSINFO_ATTR__NR;
+ info->max_cap = FSINFO_CAP__NR;
+ return sizeof(*info);
+ }
+
+ fsinfo = dentry->d_sb->s_op->fsinfo;
+ if (!fsinfo) {
+ if (!dentry->d_sb->s_op->statfs)
+ return -EOPNOTSUPP;
+ fsinfo = generic_fsinfo;
+ }
+
+ ret = security_sb_statfs(dentry);
+ if (ret)
+ return ret;
+
+ if (!params->overlarge)
+ return fsinfo(path, params);
+
+ while (!signal_pending(current)) {
+ params->usage = 0;
+ ret = fsinfo(path, params);
+ if (IS_ERR_VALUE((long)ret))
+ return ret; /* Error */
+ if ((unsigned int)ret <= params->buf_size)
+ return ret; /* It fitted */
+ kvfree(params->buffer);
+ params->buffer = NULL;
+ params->buf_size = roundup(ret, PAGE_SIZE);
+ if (params->buf_size > INT_MAX)
+ return -ETOOSMALL;
+ params->buffer = kvmalloc(params->buf_size, GFP_KERNEL);
+ if (!params->buffer)
+ return -ENOMEM;
+ }
+
+ return -ERESTARTSYS;
+}
+
+static int vfs_fsinfo_path(int dfd, const char __user *pathname,
+ struct fsinfo_kparams *params)
+{
+ struct path path;
+ unsigned lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+ int ret = -EINVAL;
+
+ if ((params->at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+ AT_EMPTY_PATH)) != 0)
+ return -EINVAL;
+
+ if (params->at_flags & AT_SYMLINK_NOFOLLOW)
+ lookup_flags &= ~LOOKUP_FOLLOW;
+ if (params->at_flags & AT_NO_AUTOMOUNT)
+ lookup_flags &= ~LOOKUP_AUTOMOUNT;
+ if (params->at_flags & AT_EMPTY_PATH)
+ lookup_flags |= LOOKUP_EMPTY;
+
+retry:
+ ret = user_path_at(dfd, pathname, lookup_flags, &path);
+ if (ret)
+ goto out;
+
+ ret = vfs_fsinfo(&path, params);
+ path_put(&path);
+ if (retry_estale(ret, lookup_flags)) {
+ lookup_flags |= LOOKUP_REVAL;
+ goto retry;
+ }
+out:
+ return ret;
+}
+
+static int vfs_fsinfo_fd(unsigned int fd, struct fsinfo_kparams *params)
+{
+ struct fd f = fdget_raw(fd);
+ int ret = -EBADF;
+
+ if (f.file) {
+ ret = vfs_fsinfo(&f.file->f_path, params);
+ fdput(f);
+ }
+ return ret;
+}
+
+/*
+ * Return buffer information by requestable attribute.
+ *
+ * STRUCT - a fixed-size structure with only one instance.
+ * STRUCT_N - a sequence of STRUCTs, indexed by Nth
+ * STRUCT_NM - a sequence of sequences of STRUCTs, indexed by Nth, Mth
+ * STRING - a string with only one instance.
+ * STRING_N - a sequence of STRING, indexed by Nth
+ * STRING_NM - a sequence of sequences of STRING, indexed by Nth, Mth
+ * OPAQUE - a blob that can be larger than 4K.
+ * STRUCT_ARRAY - an array of structs that can be larger than 4K
+ *
+ * If an entry is marked STRUCT, STRUCT_N or STRUCT_NM then if no buffer is
+ * supplied to sys_fsinfo(), sys_fsinfo() will handle returning the buffer size
+ * without calling vfs_fsinfo() and the filesystem.
+ *
+ * No struct may have more than 4K bytes.
+ */
+struct fsinfo_attr_info {
+ u8 type;
+ u8 flags;
+ u16 size;
+};
+
+#define __FSINFO_STRUCT 0
+#define __FSINFO_STRING 1
+#define __FSINFO_OPAQUE 2
+#define __FSINFO_STRUCT_ARRAY 3
+#define __FSINFO_0 0
+#define __FSINFO_N 0x0001
+#define __FSINFO_NM 0x0002
+
+#define _Z(T, F, S) { .type = __FSINFO_##T, .flags = __FSINFO_##F, .size = S }
+#define FSINFO_STRING(X) [FSINFO_ATTR_##X] = _Z(STRING, 0, 0)
+#define FSINFO_STRUCT(X,Y) [FSINFO_ATTR_##X] = _Z(STRUCT, 0, sizeof(struct fsinfo_##Y))
+#define FSINFO_STRING_N(X) [FSINFO_ATTR_##X] = _Z(STRING, N, 0)
+#define FSINFO_STRUCT_N(X,Y) [FSINFO_ATTR_##X] = _Z(STRUCT, N, sizeof(struct fsinfo_##Y))
+#define FSINFO_STRING_NM(X) [FSINFO_ATTR_##X] = _Z(STRING, NM, 0)
+#define FSINFO_STRUCT_NM(X,Y) [FSINFO_ATTR_##X] = _Z(STRUCT, NM, sizeof(struct fsinfo_##Y))
+#define FSINFO_OPAQUE(X) [FSINFO_ATTR_##X] = _Z(OPAQUE, 0, 0)
+#define FSINFO_STRUCT_ARRAY(X,Y) [FSINFO_ATTR_##X] = _Z(STRUCT_ARRAY, 0, sizeof(struct fsinfo_##Y))
+
+static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
+ FSINFO_STRUCT (STATFS, statfs),
+ FSINFO_STRUCT (FSINFO, fsinfo),
+ FSINFO_STRUCT (IDS, ids),
+ FSINFO_STRUCT (LIMITS, limits),
+ FSINFO_STRUCT (CAPABILITIES, capabilities),
+ FSINFO_STRUCT (SUPPORTS, supports),
+ FSINFO_STRUCT (TIMESTAMP_INFO, timestamp_info),
+ FSINFO_STRING (VOLUME_ID),
+ FSINFO_STRUCT (VOLUME_UUID, volume_uuid),
+ FSINFO_STRING (VOLUME_NAME),
+ FSINFO_STRING (NAME_ENCODING),
+ FSINFO_STRING (NAME_CODEPAGE),
+};
+
+/**
+ * sys_fsinfo - System call to get filesystem information
+ * @dfd: Base directory to pathwalk from or fd referring to filesystem.
+ * @pathname: Filesystem to query or NULL.
+ * @_params: Parameters to define request (or NULL for enhanced statfs).
+ * @user_buffer: Result buffer.
+ * @user_buf_size: Size of result buffer.
+ *
+ * Get information on a filesystem. The filesystem attribute to be queried is
+ * indicated by @_params->request, and some of the attributes can have multiple
+ * values, indexed by @_params->Nth and @_params->Mth. If @_params is NULL,
+ * then the 0th fsinfo_attr_statfs attribute is queried. If an attribute does
+ * not exist, EOPNOTSUPP is returned; if the Nth,Mth value does not exist,
+ * ENODATA is returned.
+ *
+ * On success, the size of the attribute's value is returned. If
+ * @user_buf_size is 0 or @user_buffer is NULL, only the size is returned. If
+ * the size of the value is larger than @user_buf_size, it will be truncated by
+ * the copy. If the size of the value is smaller than @user_buf_size then the
+ * excess buffer space will be cleared. The full size of the value will be
+ * returned, irrespective of how much data is actually placed in the buffer.
+ */
+SYSCALL_DEFINE5(fsinfo,
+ int, dfd, const char __user *, pathname,
+ struct fsinfo_params __user *, params,
+ void __user *, user_buffer, size_t, user_buf_size)
+{
+ struct fsinfo_attr_info info;
+ struct fsinfo_params user_params;
+ struct fsinfo_kparams kparams;
+ unsigned int result_size;
+ int ret;
+
+ memset(&kparams, 0, sizeof(kparams));
+
+ if (params) {
+ if (copy_from_user(&user_params, params, sizeof(user_params)))
+ return -EFAULT;
+ if (user_params.__reserved[0] ||
+ user_params.__reserved[1] ||
+ user_params.__reserved[2])
+ return -EINVAL;
+ if (user_params.request >= FSINFO_ATTR__NR)
+ return -EOPNOTSUPP;
+ kparams.at_flags = user_params.at_flags;
+ kparams.request = user_params.request;
+ kparams.Nth = user_params.Nth;
+ kparams.Mth = user_params.Mth;
+ } else {
+ kparams.request = FSINFO_ATTR_STATFS;
+ }
+
+ if (!user_buffer || !user_buf_size) {
+ user_buf_size = 0;
+ user_buffer = NULL;
+ }
+
+ /* Allocate an appropriately-sized buffer. We will truncate the
+ * contents when we write the contents back to userspace.
+ */
+ info = fsinfo_buffer_info[kparams.request];
+ if (kparams.Nth != 0 && !(info.flags & (__FSINFO_N | __FSINFO_NM)))
+ return -ENODATA;
+ if (kparams.Mth != 0 && !(info.flags & __FSINFO_NM))
+ return -ENODATA;
+
+ switch (info.type) {
+ case __FSINFO_STRUCT:
+ kparams.buf_size = info.size;
+ if (user_buf_size == 0)
+ return info.size; /* We know how big the buffer should be */
+ break;
+
+ case __FSINFO_STRING:
+ kparams.buf_size = FSINFO_NORMAL_ATTR_MAX_SIZE;
+ break;
+
+ case __FSINFO_OPAQUE:
+ case __FSINFO_STRUCT_ARRAY:
+ /* Opaque blob or array of struct elements. We also create a
+ * buffer that can be used for scratch space.
+ */
+ ret = -ENOMEM;
+ kparams.scratch_buffer = kmalloc(FSINFO_SCRATCH_BUFFER_SIZE,
+ GFP_KERNEL);
+ if (!kparams.scratch_buffer)
+ goto error;
+ kparams.overlarge = true;
+ kparams.buf_size = FSINFO_NORMAL_ATTR_MAX_SIZE;
+ break;
+
+ default:
+ return -ENOBUFS;
+ }
+
+ /* We always allocate a buffer for a string, even if buf_size == 0 and
+ * we're not going to return any data. This means that the filesystem
+ * code needn't care about whether the buffer actually exists or not.
+ */
+ ret = -ENOMEM;
+ kparams.buffer = kvzalloc(kparams.buf_size, GFP_KERNEL);
+ if (!kparams.buffer)
+ goto error_scratch;
+
+ if (pathname)
+ ret = vfs_fsinfo_path(dfd, pathname, &kparams);
+ else
+ ret = vfs_fsinfo_fd(dfd, &kparams);
+ if (ret < 0)
+ goto error_buffer;
+
+ result_size = ret;
+ if (result_size > user_buf_size)
+ result_size = user_buf_size;
+
+ if (result_size > 0 &&
+ copy_to_user(user_buffer, kparams.buffer, result_size) != 0) {
+ ret = -EFAULT;
+ goto error_buffer;
+ }
+
+ /* Clear any part of the buffer that we won't fill if we're putting a
+ * struct in there. Strings, opaque objects and arrays are expected to
+ * be variable length.
+ */
+ if (info.type == __FSINFO_STRUCT &&
+ user_buf_size > result_size &&
+ clear_user(user_buffer + result_size, user_buf_size - result_size) != 0) {
+ ret = -EFAULT;
+ goto error_buffer;
+ }
+
+error_buffer:
+ kvfree(kparams.buffer);
+error_scratch:
+ kfree(kparams.scratch_buffer);
+error:
+ return ret;
+}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f7fdfe93e25d..50f58eac3e1f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -66,6 +66,8 @@ struct fscrypt_info;
struct fscrypt_operations;
struct fs_context;
struct fs_parameter_description;
+struct fsinfo_kparams;
+enum fsinfo_attribute;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -1922,6 +1924,9 @@ struct super_operations {
int (*thaw_super) (struct super_block *);
int (*unfreeze_fs) (struct super_block *);
int (*statfs) (struct dentry *, struct kstatfs *);
+#ifdef CONFIG_FSINFO
+ int (*fsinfo) (struct path *, struct fsinfo_kparams *);
+#endif
int (*remount_fs) (struct super_block *, int *, char *);
void (*umount_begin) (struct super_block *);
diff --git a/include/linux/fsinfo.h b/include/linux/fsinfo.h
new file mode 100644
index 000000000000..4c250136d693
--- /dev/null
+++ b/include/linux/fsinfo.h
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Filesystem information query
+ *
+ * Copyright (C) 2019 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#ifndef _LINUX_FSINFO_H
+#define _LINUX_FSINFO_H
+
+#ifdef CONFIG_FSINFO
+
+#include <uapi/linux/fsinfo.h>
+
+#define FSINFO_NORMAL_ATTR_MAX_SIZE 4096
+#define FSINFO_SCRATCH_BUFFER_SIZE 4096
+
+struct fsinfo_kparams {
+ __u32 at_flags; /* AT_SYMLINK_NOFOLLOW and similar */
+ enum fsinfo_attribute request; /* What is being asking for */
+ __u32 Nth; /* Instance of it (some may have multiple) */
+ __u32 Mth; /* Subinstance */
+ bool overlarge; /* T if the buffer may be resized */
+ unsigned int usage; /* Amount of buffer used (if overlarge=T) */
+ unsigned int buf_size; /* Size of ->buffer[] */
+ void *buffer; /* Where to place the reply */
+ char *scratch_buffer; /* 4K scratch buffer (if overlarge=T) */
+};
+
+extern int generic_fsinfo(struct path *, struct fsinfo_kparams *);
+
+static inline void fsinfo_set_cap(struct fsinfo_capabilities *c,
+ enum fsinfo_capability cap)
+{
+ c->capabilities[cap / 8] |= 1 << (cap % 8);
+}
+
+static inline void fsinfo_clear_cap(struct fsinfo_capabilities *c,
+ enum fsinfo_capability cap)
+{
+ c->capabilities[cap / 8] &= ~(1 << (cap % 8));
+}
+
+/**
+ * fsinfo_set_unix_caps - Set standard UNIX capabilities.
+ * @c: The capabilities mask to alter
+ */
+static inline void fsinfo_set_unix_caps(struct fsinfo_capabilities *caps)
+{
+ fsinfo_set_cap(caps, FSINFO_CAP_UIDS);
+ fsinfo_set_cap(caps, FSINFO_CAP_GIDS);
+ fsinfo_set_cap(caps, FSINFO_CAP_DIRECTORIES);
+ fsinfo_set_cap(caps, FSINFO_CAP_SYMLINKS);
+ fsinfo_set_cap(caps, FSINFO_CAP_HARD_LINKS);
+ fsinfo_set_cap(caps, FSINFO_CAP_DEVICE_FILES);
+ fsinfo_set_cap(caps, FSINFO_CAP_UNIX_SPECIALS);
+ fsinfo_set_cap(caps, FSINFO_CAP_SPARSE);
+ fsinfo_set_cap(caps, FSINFO_CAP_HAS_ATIME);
+ fsinfo_set_cap(caps, FSINFO_CAP_HAS_CTIME);
+ fsinfo_set_cap(caps, FSINFO_CAP_HAS_MTIME);
+}
+
+#endif /* CONFIG_FSINFO */
+
+#endif /* _LINUX_FSINFO_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e2870fe1be5b..958ac427ff37 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -50,6 +50,7 @@ struct stat64;
struct statfs;
struct statfs64;
struct statx;
+struct fsinfo_params;
struct __sysctl_args;
struct sysinfo;
struct timespec;
@@ -997,6 +998,9 @@ asmlinkage long sys_fspick(int dfd, const char __user *path, unsigned int flags)
asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
siginfo_t __user *info,
unsigned int flags);
+asmlinkage long sys_fsinfo(int dfd, const char __user *pathname,
+ struct fsinfo_params __user *params,
+ void __user *buffer, size_t buf_size);
/*
* Architecture-specific system calls
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index a87904daf103..50ddf5f25122 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -844,9 +844,11 @@ __SYSCALL(__NR_fsconfig, sys_fsconfig)
__SYSCALL(__NR_fsmount, sys_fsmount)
#define __NR_fspick 433
__SYSCALL(__NR_fspick, sys_fspick)
+#define __NR_fsinfo 434
+__SYSCALL(__NR_fsinfo, sys_fsinfo)
#undef __NR_syscalls
-#define __NR_syscalls 434
+#define __NR_syscalls 435
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
new file mode 100644
index 000000000000..cc7e13a9b95f
--- /dev/null
+++ b/include/uapi/linux/fsinfo.h
@@ -0,0 +1,219 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* fsinfo() definitions.
+ *
+ * Copyright (C) 2019 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#ifndef _UAPI_LINUX_FSINFO_H
+#define _UAPI_LINUX_FSINFO_H
+
+#include <linux/types.h>
+#include <linux/socket.h>
+
+/*
+ * The filesystem attributes that can be requested. Note that some attributes
+ * may have multiple instances which can be switched in the parameter block.
+ */
+enum fsinfo_attribute {
+ FSINFO_ATTR_STATFS = 0, /* statfs()-style state */
+ FSINFO_ATTR_FSINFO = 1, /* Information about fsinfo() */
+ FSINFO_ATTR_IDS = 2, /* Filesystem IDs */
+ FSINFO_ATTR_LIMITS = 3, /* Filesystem limits */
+ FSINFO_ATTR_SUPPORTS = 4, /* What's supported in statx, iocflags, ... */
+ FSINFO_ATTR_CAPABILITIES = 5, /* Filesystem capabilities (bits) */
+ FSINFO_ATTR_TIMESTAMP_INFO = 6, /* Inode timestamp info */
+ FSINFO_ATTR_VOLUME_ID = 7, /* Volume ID (string) */
+ FSINFO_ATTR_VOLUME_UUID = 8, /* Volume UUID (LE uuid) */
+ FSINFO_ATTR_VOLUME_NAME = 9, /* Volume name (string) */
+ FSINFO_ATTR_NAME_ENCODING = 10, /* Filename encoding (string) */
+ FSINFO_ATTR_NAME_CODEPAGE = 11, /* Filename codepage (string) */
+ FSINFO_ATTR__NR
+};
+
+/*
+ * Optional fsinfo() parameter structure.
+ *
+ * If this is not given, it is assumed that fsinfo_attr_statfs instance 0,0 is
+ * desired.
+ */
+struct fsinfo_params {
+ __u32 at_flags; /* AT_SYMLINK_NOFOLLOW and similar flags */
+ __u32 request; /* What is being asking for (enum fsinfo_attribute) */
+ __u32 Nth; /* Instance of it (some may have multiple) */
+ __u32 Mth; /* Subinstance of Nth instance */
+ __u64 __reserved[3]; /* Reserved params; all must be 0 */
+};
+
+struct fsinfo_u128 {
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+ __u64 hi;
+ __u64 lo;
+#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+ __u64 lo;
+ __u64 hi;
+#endif
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_statfs).
+ * - This gives extended filesystem information.
+ */
+struct fsinfo_statfs {
+ struct fsinfo_u128 f_blocks; /* Total number of blocks in fs */
+ struct fsinfo_u128 f_bfree; /* Total number of free blocks */
+ struct fsinfo_u128 f_bavail; /* Number of free blocks available to ordinary user */
+ struct fsinfo_u128 f_files; /* Total number of file nodes in fs */
+ struct fsinfo_u128 f_ffree; /* Number of free file nodes */
+ struct fsinfo_u128 f_favail; /* Number of file nodes available to ordinary user */
+ __u64 f_bsize; /* Optimal block size */
+ __u64 f_frsize; /* Fragment size */
+ __u64 mnt_attrs; /* Mount attributes (MOUNT_ATTR_*) */
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_ids).
+ *
+ * List of basic identifiers as is normally found in statfs().
+ */
+struct fsinfo_ids {
+ char f_fs_name[15 + 1]; /* Filesystem name */
+ __u64 f_fsid; /* Short 64-bit Filesystem ID (as statfs) */
+ __u64 f_sb_id; /* Internal superblock ID for sbnotify()/mntnotify() */
+ __u32 f_fstype; /* Filesystem type from linux/magic.h [uncond] */
+ __u32 f_dev_major; /* As st_dev_* from struct statx [uncond] */
+ __u32 f_dev_minor;
+ __u32 __reserved[1];
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_limits).
+ *
+ * List of supported filesystem limits.
+ */
+struct fsinfo_limits {
+ struct fsinfo_u128 max_file_size; /* Maximum file size */
+ struct fsinfo_u128 max_ino; /* Maximum inode number */
+ __u64 max_uid; /* Maximum UID supported */
+ __u64 max_gid; /* Maximum GID supported */
+ __u64 max_projid; /* Maximum project ID supported */
+ __u64 max_hard_links; /* Maximum number of hard links on a file */
+ __u64 max_xattr_body_len; /* Maximum xattr content length */
+ __u32 max_xattr_name_len; /* Maximum xattr name length */
+ __u32 max_filename_len; /* Maximum filename length */
+ __u32 max_symlink_len; /* Maximum symlink content length */
+ __u32 max_dev_major; /* Maximum device major representable */
+ __u32 max_dev_minor; /* Maximum device minor representable */
+ __u32 __reserved[1];
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_supports).
+ *
+ * What's supported in various masks, such as statx() attribute and mask bits
+ * and IOC flags.
+ */
+struct fsinfo_supports {
+ __u64 stx_attributes; /* What statx::stx_attributes are supported */
+ __u32 stx_mask; /* What statx::stx_mask bits are supported */
+ __u32 ioc_flags; /* What FS_IOC_* flags are supported */
+ __u32 win_file_attrs; /* What DOS/Windows FILE_* attributes are supported */
+ __u32 __reserved[1];
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_capabilities).
+ *
+ * Bitmask indicating filesystem capabilities where renderable as single bits.
+ */
+enum fsinfo_capability {
+ FSINFO_CAP_IS_KERNEL_FS = 0, /* fs is kernel-special filesystem */
+ FSINFO_CAP_IS_BLOCK_FS = 1, /* fs is block-based filesystem */
+ FSINFO_CAP_IS_FLASH_FS = 2, /* fs is flash filesystem */
+ FSINFO_CAP_IS_NETWORK_FS = 3, /* fs is network filesystem */
+ FSINFO_CAP_IS_AUTOMOUNTER_FS = 4, /* fs is automounter special filesystem */
+ FSINFO_CAP_IS_MEMORY_FS = 5, /* fs is memory-based filesystem */
+ FSINFO_CAP_AUTOMOUNTS = 6, /* fs supports automounts */
+ FSINFO_CAP_ADV_LOCKS = 7, /* fs supports advisory file locking */
+ FSINFO_CAP_MAND_LOCKS = 8, /* fs supports mandatory file locking */
+ FSINFO_CAP_LEASES = 9, /* fs supports file leases */
+ FSINFO_CAP_UIDS = 10, /* fs supports numeric uids */
+ FSINFO_CAP_GIDS = 11, /* fs supports numeric gids */
+ FSINFO_CAP_PROJIDS = 12, /* fs supports numeric project ids */
+ FSINFO_CAP_STRING_USER_IDS = 13, /* fs supports string user identifiers */
+ FSINFO_CAP_GUID_USER_IDS = 14, /* fs supports GUID user identifiers */
+ FSINFO_CAP_WINDOWS_ATTRS = 15, /* fs has windows attributes */
+ FSINFO_CAP_USER_QUOTAS = 16, /* fs has per-user quotas */
+ FSINFO_CAP_GROUP_QUOTAS = 17, /* fs has per-group quotas */
+ FSINFO_CAP_PROJECT_QUOTAS = 18, /* fs has per-project quotas */
+ FSINFO_CAP_XATTRS = 19, /* fs has xattrs */
+ FSINFO_CAP_JOURNAL = 20, /* fs has a journal */
+ FSINFO_CAP_DATA_IS_JOURNALLED = 21, /* fs is using data journalling */
+ FSINFO_CAP_O_SYNC = 22, /* fs supports O_SYNC */
+ FSINFO_CAP_O_DIRECT = 23, /* fs supports O_DIRECT */
+ FSINFO_CAP_VOLUME_ID = 24, /* fs has a volume ID */
+ FSINFO_CAP_VOLUME_UUID = 25, /* fs has a volume UUID */
+ FSINFO_CAP_VOLUME_NAME = 26, /* fs has a volume name */
+ FSINFO_CAP_VOLUME_FSID = 27, /* fs has a volume FSID */
+ FSINFO_CAP_IVER_ALL_CHANGE = 28, /* i_version represents data + meta changes */
+ FSINFO_CAP_IVER_DATA_CHANGE = 29, /* i_version represents data changes only */
+ FSINFO_CAP_IVER_MONO_INCR = 30, /* i_version incremented monotonically */
+ FSINFO_CAP_DIRECTORIES = 31, /* fs supports (sub)directories */
+ FSINFO_CAP_SYMLINKS = 32, /* fs supports symlinks */
+ FSINFO_CAP_HARD_LINKS = 33, /* fs supports hard links */
+ FSINFO_CAP_HARD_LINKS_1DIR = 34, /* fs supports hard links in same dir only */
+ FSINFO_CAP_DEVICE_FILES = 35, /* fs supports bdev, cdev */
+ FSINFO_CAP_UNIX_SPECIALS = 36, /* fs supports pipe, fifo, socket */
+ FSINFO_CAP_RESOURCE_FORKS = 37, /* fs supports resource forks/streams */
+ FSINFO_CAP_NAME_CASE_INDEP = 38, /* Filename case independence is mandatory */
+ FSINFO_CAP_NAME_NON_UTF8 = 39, /* fs has non-utf8 names */
+ FSINFO_CAP_NAME_HAS_CODEPAGE = 40, /* fs has a filename codepage */
+ FSINFO_CAP_SPARSE = 41, /* fs supports sparse files */
+ FSINFO_CAP_NOT_PERSISTENT = 42, /* fs is not persistent */
+ FSINFO_CAP_NO_UNIX_MODE = 43, /* fs does not support unix mode bits */
+ FSINFO_CAP_HAS_ATIME = 44, /* fs supports access time */
+ FSINFO_CAP_HAS_BTIME = 45, /* fs supports birth/creation time */
+ FSINFO_CAP_HAS_CTIME = 46, /* fs supports change time */
+ FSINFO_CAP_HAS_MTIME = 47, /* fs supports modification time */
+ FSINFO_CAP__NR
+};
+
+struct fsinfo_capabilities {
+ __u8 capabilities[(FSINFO_CAP__NR + 7) / 8];
+};
+
+struct fsinfo_timestamp_one {
+ __s64 minimum; /* Minimum timestamp value in seconds */
+ __u64 maximum; /* Maximum timestamp value in seconds */
+ __u16 gran_mantissa; /* Granularity(secs) = mant * 10^exp */
+ __s8 gran_exponent;
+ __u8 reserved[5];
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_timestamp_info).
+ */
+struct fsinfo_timestamp_info {
+ struct fsinfo_timestamp_one atime; /* Access time */
+ struct fsinfo_timestamp_one mtime; /* Modification time */
+ struct fsinfo_timestamp_one ctime; /* Change time */
+ struct fsinfo_timestamp_one btime; /* Birth/creation time */
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_volume_uuid).
+ */
+struct fsinfo_volume_uuid {
+ __u8 uuid[16];
+};
+
+/*
+ * Information struct for fsinfo(fsinfo_attr_fsinfo).
+ *
+ * This gives information about fsinfo() itself.
+ */
+struct fsinfo_fsinfo {
+ __u32 max_attr; /* Number of supported attributes (fsinfo_attr__nr) */
+ __u32 max_cap; /* Number of supported capabilities (fsinfo_cap__nr) */
+};
+
+#endif /* _UAPI_LINUX_FSINFO_H */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 4d9ae5ea6caf..93927072396c 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -51,6 +51,7 @@ COND_SYSCALL_COMPAT(io_pgetevents);
COND_SYSCALL(io_uring_setup);
COND_SYSCALL(io_uring_enter);
COND_SYSCALL(io_uring_register);
+COND_SYSCALL(fsinfo);
/* fs/xattr.c */
diff --git a/samples/vfs/Makefile b/samples/vfs/Makefile
index a3e4ffd4c773..d3cc8e9a4fd8 100644
--- a/samples/vfs/Makefile
+++ b/samples/vfs/Makefile
@@ -1,10 +1,14 @@
# List of programs to build
hostprogs-y := \
+ test-fsinfo \
test-fsmount \
test-statx
# Tell kbuild to always build the programs
always := $(hostprogs-y)
+HOSTCFLAGS_test-fsinfo.o += -I$(objtree)/usr/include
+HOSTLDLIBS_test-fsinfo += -lm
+
HOSTCFLAGS_test-fsmount.o += -I$(objtree)/usr/include
HOSTCFLAGS_test-statx.o += -I$(objtree)/usr/include
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
new file mode 100644
index 000000000000..8cce1986df7e
--- /dev/null
+++ b/samples/vfs/test-fsinfo.c
@@ -0,0 +1,551 @@
+/* Test the fsinfo() system call
+ *
+ * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define _GNU_SOURCE
+#define _ATFILE_SOURCE
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <time.h>
+#include <math.h>
+#include <fcntl.h>
+#include <sys/syscall.h>
+#include <linux/fsinfo.h>
+#include <linux/socket.h>
+#include <sys/stat.h>
+#include <arpa/inet.h>
+
+#ifndef __NR_fsinfo
+#define __NR_fsinfo -1
+#endif
+
+static bool debug = 0;
+
+static __attribute__((unused))
+ssize_t fsinfo(int dfd, const char *filename, struct fsinfo_params *params,
+ void *buffer, size_t buf_size)
+{
+ return syscall(__NR_fsinfo, dfd, filename, params, buffer, buf_size);
+}
+
+struct fsinfo_attr_info {
+ unsigned char type;
+ unsigned char flags;
+ unsigned short size;
+};
+
+#define __FSINFO_STRUCT 0
+#define __FSINFO_STRING 1
+#define __FSINFO_OVER 2
+#define __FSINFO_STRUCT_ARRAY 3
+#define __FSINFO_0 0
+#define __FSINFO_N 0x0001
+#define __FSINFO_NM 0x0002
+
+#define _Z(T, F, S) { .type = __FSINFO_##T, .flags = __FSINFO_##F, .size = S }
+#define FSINFO_STRING(X,Y) [FSINFO_ATTR_##X] = _Z(STRING, 0, 0)
+#define FSINFO_STRUCT(X,Y) [FSINFO_ATTR_##X] = _Z(STRUCT, 0, sizeof(struct fsinfo_##Y))
+#define FSINFO_STRING_N(X,Y) [FSINFO_ATTR_##X] = _Z(STRING, N, 0)
+#define FSINFO_STRUCT_N(X,Y) [FSINFO_ATTR_##X] = _Z(STRUCT, N, sizeof(struct fsinfo_##Y))
+#define FSINFO_STRING_NM(X,Y) [FSINFO_ATTR_##X] = _Z(STRING, NM, 0)
+#define FSINFO_STRUCT_NM(X,Y) [FSINFO_ATTR_##X] = _Z(STRUCT, NM, sizeof(struct fsinfo_##Y))
+#define FSINFO_OVERLARGE(X,Y) [FSINFO_ATTR_##X] = _Z(OVER, 0, 0)
+#define FSINFO_STRUCT_ARRAY(X,Y) [FSINFO_ATTR_##X] = _Z(STRUCT_ARRAY, 0, sizeof(struct fsinfo_##Y))
+
+static const struct fsinfo_attr_info fsinfo_buffer_info[FSINFO_ATTR__NR] = {
+ FSINFO_STRUCT (STATFS, statfs),
+ FSINFO_STRUCT (FSINFO, fsinfo),
+ FSINFO_STRUCT (IDS, ids),
+ FSINFO_STRUCT (LIMITS, limits),
+ FSINFO_STRUCT (CAPABILITIES, capabilities),
+ FSINFO_STRUCT (SUPPORTS, supports),
+ FSINFO_STRUCT (TIMESTAMP_INFO, timestamp_info),
+ FSINFO_STRING (VOLUME_ID, volume_id),
+ FSINFO_STRUCT (VOLUME_UUID, volume_uuid),
+ FSINFO_STRING (VOLUME_NAME, volume_name),
+ FSINFO_STRING (NAME_ENCODING, name_encoding),
+ FSINFO_STRING (NAME_CODEPAGE, name_codepage),
+};
+
+#define FSINFO_NAME(X,Y) [FSINFO_ATTR_##X] = #Y
+static const char *fsinfo_attr_names[FSINFO_ATTR__NR] = {
+ FSINFO_NAME (STATFS, statfs),
+ FSINFO_NAME (FSINFO, fsinfo),
+ FSINFO_NAME (IDS, ids),
+ FSINFO_NAME (LIMITS, limits),
+ FSINFO_NAME (CAPABILITIES, capabilities),
+ FSINFO_NAME (SUPPORTS, supports),
+ FSINFO_NAME (TIMESTAMP_INFO, timestamp_info),
+ FSINFO_NAME (VOLUME_ID, volume_id),
+ FSINFO_NAME (VOLUME_UUID, volume_uuid),
+ FSINFO_NAME (VOLUME_NAME, volume_name),
+ FSINFO_NAME (NAME_ENCODING, name_encoding),
+ FSINFO_NAME (NAME_CODEPAGE, name_codepage),
+};
+
+union reply {
+ char buffer[4096];
+ struct fsinfo_statfs statfs;
+ struct fsinfo_fsinfo fsinfo;
+ struct fsinfo_ids ids;
+ struct fsinfo_limits limits;
+ struct fsinfo_supports supports;
+ struct fsinfo_capabilities caps;
+ struct fsinfo_timestamp_info timestamps;
+ struct fsinfo_volume_uuid uuid;
+};
+
+static void dump_hex(unsigned int *data, int from, int to)
+{
+ unsigned offset, print_offset = 1, col = 0;
+
+ from /= 4;
+ to = (to + 3) / 4;
+
+ for (offset = from; offset < to; offset++) {
+ if (print_offset) {
+ printf("%04x: ", offset * 8);
+ print_offset = 0;
+ }
+ printf("%08x", data[offset]);
+ col++;
+ if ((col & 3) == 0) {
+ printf("\n");
+ print_offset = 1;
+ } else {
+ printf(" ");
+ }
+ }
+
+ if (!print_offset)
+ printf("\n");
+}
+
+static void dump_attr_STATFS(union reply *r, int size)
+{
+ struct fsinfo_statfs *f = &r->statfs;
+
+ printf("\n");
+ printf("\tblocks: n=%llu fr=%llu av=%llu\n",
+ (unsigned long long)f->f_blocks.lo,
+ (unsigned long long)f->f_bfree.lo,
+ (unsigned long long)f->f_bavail.lo);
+
+ printf("\tfiles : n=%llu fr=%llu av=%llu\n",
+ (unsigned long long)f->f_files.lo,
+ (unsigned long long)f->f_ffree.lo,
+ (unsigned long long)f->f_favail.lo);
+ printf("\tbsize : %llu\n", f->f_bsize);
+ printf("\tfrsize: %llu\n", f->f_frsize);
+ printf("\tmntfl : %llx\n", (unsigned long long)f->mnt_attrs);
+}
+
+static void dump_attr_FSINFO(union reply *r, int size)
+{
+ struct fsinfo_fsinfo *f = &r->fsinfo;
+
+ printf("max_attr=%u max_cap=%u\n", f->max_attr, f->max_cap);
+}
+
+static void dump_attr_IDS(union reply *r, int size)
+{
+ struct fsinfo_ids *f = &r->ids;
+
+ printf("\n");
+ printf("\tdev : %02x:%02x\n", f->f_dev_major, f->f_dev_minor);
+ printf("\tfs : type=%x name=%s\n", f->f_fstype, f->f_fs_name);
+ printf("\tfsid : %llx\n", (unsigned long long)f->f_fsid);
+}
+
+static void dump_attr_LIMITS(union reply *r, int size)
+{
+ struct fsinfo_limits *f = &r->limits;
+
+ printf("\n");
+ printf("\tmax file size: %llx%016llx\n",
+ (unsigned long long)f->max_file_size.hi,
+ (unsigned long long)f->max_file_size.lo);
+ printf("\tmax ino: %llx%016llx\n",
+ (unsigned long long)f->max_ino.hi,
+ (unsigned long long)f->max_ino.lo);
+ printf("\tmax ids : u=%llx g=%llx p=%llx\n",
+ (unsigned long long)f->max_uid,
+ (unsigned long long)f->max_gid,
+ (unsigned long long)f->max_projid);
+ printf("\tmax dev : maj=%x min=%x\n",
+ f->max_dev_major, f->max_dev_minor);
+ printf("\tmax links : %llx\n",
+ (unsigned long long)f->max_hard_links);
+ printf("\tmax xattr : n=%x b=%llx\n",
+ f->max_xattr_name_len,
+ (unsigned long long)f->max_xattr_body_len);
+ printf("\tmax len : file=%x sym=%x\n",
+ f->max_filename_len, f->max_symlink_len);
+}
+
+static void dump_attr_SUPPORTS(union reply *r, int size)
+{
+ struct fsinfo_supports *f = &r->supports;
+
+ printf("\n");
+ printf("\tstx_attr=%llx\n", (unsigned long long)f->stx_attributes);
+ printf("\tstx_mask=%x\n", f->stx_mask);
+ printf("\tioc_flags=%x\n", f->ioc_flags);
+ printf("\twin_fattrs=%x\n", f->win_file_attrs);
+}
+
+#define FSINFO_CAP_NAME(C) [FSINFO_CAP_##C] = #C
+static const char *fsinfo_cap_names[FSINFO_CAP__NR] = {
+ FSINFO_CAP_NAME(IS_KERNEL_FS),
+ FSINFO_CAP_NAME(IS_BLOCK_FS),
+ FSINFO_CAP_NAME(IS_FLASH_FS),
+ FSINFO_CAP_NAME(IS_NETWORK_FS),
+ FSINFO_CAP_NAME(IS_AUTOMOUNTER_FS),
+ FSINFO_CAP_NAME(IS_MEMORY_FS),
+ FSINFO_CAP_NAME(AUTOMOUNTS),
+ FSINFO_CAP_NAME(ADV_LOCKS),
+ FSINFO_CAP_NAME(MAND_LOCKS),
+ FSINFO_CAP_NAME(LEASES),
+ FSINFO_CAP_NAME(UIDS),
+ FSINFO_CAP_NAME(GIDS),
+ FSINFO_CAP_NAME(PROJIDS),
+ FSINFO_CAP_NAME(STRING_USER_IDS),
+ FSINFO_CAP_NAME(GUID_USER_IDS),
+ FSINFO_CAP_NAME(WINDOWS_ATTRS),
+ FSINFO_CAP_NAME(USER_QUOTAS),
+ FSINFO_CAP_NAME(GROUP_QUOTAS),
+ FSINFO_CAP_NAME(PROJECT_QUOTAS),
+ FSINFO_CAP_NAME(XATTRS),
+ FSINFO_CAP_NAME(JOURNAL),
+ FSINFO_CAP_NAME(DATA_IS_JOURNALLED),
+ FSINFO_CAP_NAME(O_SYNC),
+ FSINFO_CAP_NAME(O_DIRECT),
+ FSINFO_CAP_NAME(VOLUME_ID),
+ FSINFO_CAP_NAME(VOLUME_UUID),
+ FSINFO_CAP_NAME(VOLUME_NAME),
+ FSINFO_CAP_NAME(VOLUME_FSID),
+ FSINFO_CAP_NAME(IVER_ALL_CHANGE),
+ FSINFO_CAP_NAME(IVER_DATA_CHANGE),
+ FSINFO_CAP_NAME(IVER_MONO_INCR),
+ FSINFO_CAP_NAME(DIRECTORIES),
+ FSINFO_CAP_NAME(SYMLINKS),
+ FSINFO_CAP_NAME(HARD_LINKS),
+ FSINFO_CAP_NAME(HARD_LINKS_1DIR),
+ FSINFO_CAP_NAME(DEVICE_FILES),
+ FSINFO_CAP_NAME(UNIX_SPECIALS),
+ FSINFO_CAP_NAME(RESOURCE_FORKS),
+ FSINFO_CAP_NAME(NAME_CASE_INDEP),
+ FSINFO_CAP_NAME(NAME_NON_UTF8),
+ FSINFO_CAP_NAME(NAME_HAS_CODEPAGE),
+ FSINFO_CAP_NAME(SPARSE),
+ FSINFO_CAP_NAME(NOT_PERSISTENT),
+ FSINFO_CAP_NAME(NO_UNIX_MODE),
+ FSINFO_CAP_NAME(HAS_ATIME),
+ FSINFO_CAP_NAME(HAS_BTIME),
+ FSINFO_CAP_NAME(HAS_CTIME),
+ FSINFO_CAP_NAME(HAS_MTIME),
+};
+
+static void dump_attr_CAPABILITIES(union reply *r, int size)
+{
+ struct fsinfo_capabilities *f = &r->caps;
+ int i;
+
+ for (i = 0; i < sizeof(f->capabilities); i++)
+ printf("%02x", f->capabilities[i]);
+ printf("\n");
+ for (i = 0; i < FSINFO_CAP__NR; i++)
+ if (f->capabilities[i / 8] & (1 << (i % 8)))
+ printf("\t- %s\n", fsinfo_cap_names[i]);
+}
+
+static void print_time(struct fsinfo_timestamp_one *t, char stamp)
+{
+ printf("\t%ctime : gran=%gs range=%llx-%llx\n",
+ stamp,
+ t->gran_mantissa * pow(10., t->gran_exponent),
+ (long long)t->minimum,
+ (long long)t->maximum);
+}
+
+static void dump_attr_TIMESTAMP_INFO(union reply *r, int size)
+{
+ struct fsinfo_timestamp_info *f = &r->timestamps;
+
+ printf("\n");
+ print_time(&f->atime, 'a');
+ print_time(&f->mtime, 'm');
+ print_time(&f->ctime, 'c');
+ print_time(&f->btime, 'b');
+}
+
+static void dump_attr_VOLUME_UUID(union reply *r, int size)
+{
+ struct fsinfo_volume_uuid *f = &r->uuid;
+
+ printf("%02x%02x%02x%02x-%02x%02x-%02x%02x-%02x%02x"
+ "-%02x%02x%02x%02x%02x%02x\n",
+ f->uuid[ 0], f->uuid[ 1],
+ f->uuid[ 2], f->uuid[ 3],
+ f->uuid[ 4], f->uuid[ 5],
+ f->uuid[ 6], f->uuid[ 7],
+ f->uuid[ 8], f->uuid[ 9],
+ f->uuid[10], f->uuid[11],
+ f->uuid[12], f->uuid[13],
+ f->uuid[14], f->uuid[15]);
+}
+
+/*
+ *
+ */
+typedef void (*dumper_t)(union reply *r, int size);
+
+#define FSINFO_DUMPER(N) [FSINFO_ATTR_##N] = dump_attr_##N
+static const dumper_t fsinfo_attr_dumper[FSINFO_ATTR__NR] = {
+ FSINFO_DUMPER(STATFS),
+ FSINFO_DUMPER(FSINFO),
+ FSINFO_DUMPER(IDS),
+ FSINFO_DUMPER(LIMITS),
+ FSINFO_DUMPER(SUPPORTS),
+ FSINFO_DUMPER(CAPABILITIES),
+ FSINFO_DUMPER(TIMESTAMP_INFO),
+ FSINFO_DUMPER(VOLUME_UUID),
+};
+
+static void dump_fsinfo(enum fsinfo_attribute attr,
+ struct fsinfo_attr_info about,
+ union reply *r, int size)
+{
+ dumper_t dumper = fsinfo_attr_dumper[attr];
+ unsigned int len;
+
+ if (!dumper) {
+ printf("<no dumper>\n");
+ return;
+ }
+
+ len = about.size;
+ if (about.type == __FSINFO_STRUCT && size < len) {
+ printf("<short data %u/%u>\n", size, len);
+ return;
+ }
+
+ dumper(r, size);
+}
+
+/*
+ * Try one subinstance of an attribute.
+ */
+static int try_one(const char *file, struct fsinfo_params *params, bool raw)
+{
+ struct fsinfo_attr_info about;
+ union reply *r;
+ size_t buf_size = 4096;
+ char *p;
+ int ret;
+
+ for (;;) {
+ r = malloc(buf_size);
+ if (!r) {
+ perror("malloc");
+ exit(1);
+ }
+ memset(r->buffer, 0xbd, buf_size);
+
+ errno = 0;
+ ret = fsinfo(AT_FDCWD, file, params, r->buffer, buf_size);
+ if (params->request >= FSINFO_ATTR__NR) {
+ if (ret == -1 && errno == EOPNOTSUPP)
+ exit(0);
+ fprintf(stderr, "Unexpected error for too-large command %u: %m\n",
+ params->request);
+ exit(1);
+ }
+ if (ret == -1)
+ break;
+
+ if (ret <= buf_size)
+ break;
+ buf_size = (ret + 4096 - 1) & ~(4096 - 1);
+ }
+
+ if (debug)
+ printf("fsinfo(%s,%s,%u,%u) = %d: %m\n",
+ file, fsinfo_attr_names[params->request],
+ params->Nth, params->Mth, ret);
+
+ about = fsinfo_buffer_info[params->request];
+ if (ret == -1) {
+ if (errno == ENODATA) {
+ if (!(about.flags & (__FSINFO_N | __FSINFO_NM)) &&
+ params->Nth == 0 && params->Mth == 0) {
+ fprintf(stderr,
+ "Unexpected ENODATA (%u[%u][%u])\n",
+ params->request, params->Nth, params->Mth);
+ exit(1);
+ }
+ return (params->Mth == 0) ? 2 : 1;
+ }
+ if (errno == EOPNOTSUPP) {
+ if (params->Nth > 0 || params->Mth > 0) {
+ fprintf(stderr,
+ "Should return -ENODATA (%u[%u][%u])\n",
+ params->request, params->Nth, params->Mth);
+ exit(1);
+ }
+ //printf("\e[33m%s\e[m: <not supported>\n",
+ // fsinfo_attr_names[attr]);
+ return 2;
+ }
+ perror(file);
+ exit(1);
+ }
+
+ if (raw) {
+ if (ret > 4096)
+ ret = 4096;
+ dump_hex((unsigned int *)r->buffer, 0, ret);
+ return 0;
+ }
+
+ switch (about.flags & (__FSINFO_N | __FSINFO_NM)) {
+ case 0:
+ printf("\e[33m%s\e[m: ",
+ fsinfo_attr_names[params->request]);
+ break;
+ case __FSINFO_N:
+ printf("\e[33m%s[%u]\e[m: ",
+ fsinfo_attr_names[params->request],
+ params->Nth);
+ break;
+ case __FSINFO_NM:
+ printf("\e[33m%s[%u][%u]\e[m: ",
+ fsinfo_attr_names[params->request],
+ params->Nth, params->Mth);
+ break;
+ }
+
+ switch (about.type) {
+ case __FSINFO_STRUCT:
+ dump_fsinfo(params->request, about, r, ret);
+ return 0;
+
+ case __FSINFO_STRING:
+ if (ret >= 4096) {
+ ret = 4096;
+ r->buffer[4092] = '.';
+ r->buffer[4093] = '.';
+ r->buffer[4094] = '.';
+ r->buffer[4095] = 0;
+ } else {
+ r->buffer[ret] = 0;
+ }
+ for (p = r->buffer; *p; p++) {
+ if (!isprint(*p)) {
+ printf("<non-printable>\n");
+ continue;
+ }
+ }
+ printf("%s\n", r->buffer);
+ return 0;
+
+ case __FSINFO_OVER:
+ return 0;
+
+ case __FSINFO_STRUCT_ARRAY:
+ dump_fsinfo(params->request, about, r, ret);
+ return 0;
+
+ default:
+ fprintf(stderr, "Fishy about %u %u,%u,%u\n",
+ params->request, about.type, about.flags, about.size);
+ exit(1);
+ }
+}
+
+/*
+ *
+ */
+int main(int argc, char **argv)
+{
+ struct fsinfo_params params = {
+ .at_flags = AT_SYMLINK_NOFOLLOW,
+ };
+ unsigned int attr;
+ int raw = 0, opt, Nth, Mth;
+
+ while ((opt = getopt(argc, argv, "adlr"))) {
+ switch (opt) {
+ case 'a':
+ params.at_flags |= AT_NO_AUTOMOUNT;
+ continue;
+ case 'd':
+ debug = true;
+ continue;
+ case 'l':
+ params.at_flags &= ~AT_SYMLINK_NOFOLLOW;
+ continue;
+ case 'r':
+ raw = 1;
+ continue;
+ }
+ break;
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ if (argc != 1) {
+ printf("Format: test-fsinfo [-alr] <file>\n");
+ exit(2);
+ }
+
+ for (attr = 0; attr <= FSINFO_ATTR__NR; attr++) {
+ Nth = 0;
+ do {
+ Mth = 0;
+ do {
+ params.request = attr;
+ params.Nth = Nth;
+ params.Mth = Mth;
+
+ switch (try_one(argv[0], ¶ms, raw)) {
+ case 0:
+ continue;
+ case 1:
+ goto done_M;
+ case 2:
+ goto done_N;
+ }
+ } while (++Mth < 100);
+
+ done_M:
+ if (Mth >= 100) {
+ fprintf(stderr, "Fishy: Mth == %u\n", Mth);
+ break;
+ }
+
+ } while (++Nth < 100);
+
+ done_N:
+ if (Nth >= 100) {
+ fprintf(stderr, "Fishy: Nth == %u\n", Nth);
+ break;
+ }
+ }
+
+ return 0;
+}
^ permalink raw reply related
* [PATCH 00/11] VFS: Introduce filesystem information query syscall [ver #15]
From: David Howells @ 2019-06-28 15:43 UTC (permalink / raw)
To: viro
Cc: dhowells, raven, mszeredi, christian, linux-api, linux-fsdevel,
linux-kernel
Here are a set of patches that adds a syscall, fsinfo(), that allows
attributes of a filesystem/superblock to be queried. Attribute values are
of four basic types:
(1) Version dependent-length structure (size defined by type).
(2) Variable-length string (up to 4096, no NUL).
(3) Array of fixed-length structures (up to INT_MAX size).
(4) Opaque blob (up to INT_MAX size).
Attributes can have multiple values either as a sequence of values or a
sequence-of-sequences of values and all the values of a particular
attribute must be of the same type.
Note that the values of an attribute *are* allowed to vary between dentries
within a single superblock, depending on the specific dentry that you're
looking at.
I've tried to make the interface as light as possible, so integer/enum
attribute selector rather than string and the core does all the allocation
and extensibility support work rather than leaving that to the filesystems.
That means that for the first two attribute types, sb->s_op->fsinfo() may
assume that the provided buffer is always present and always big enough.
Further, this removes the possibility of the filesystem gaining access to the
userspace buffer.
fsinfo() allows a variety of information to be retrieved about a filesystem
and the mount topology:
(1) General superblock attributes:
- The amount of space/free space in a filesystem (as statfs()).
- Filesystem identifiers (UUID, volume label, device numbers, ...)
- The limits on a filesystem's capabilities
- Information on supported statx fields and attributes and IOC flags.
- A variety single-bit flags indicating supported capabilities.
- Timestamp resolution and range.
- Sources (as per mount(2), but fsconfig() allows multiple sources).
- In-filesystem filename format information.
- Filesystem parameters ("mount -o xxx"-type things).
- LSM parameters (again "mount -o xxx"-type things).
(2) Filesystem-specific superblock attributes:
- Server names and addresses.
- Cell name.
(3) Filesystem configuration metadata attributes:
- Filesystem parameter type descriptions.
- Name -> parameter mappings.
- Simple enumeration name -> value mappings.
(4) Information about what the fsinfo() syscall itself supports, including
the number of attibutes supported and the number of capability bits
supported.
(5) Future patches will include information about the mount topology.
The system is extensible:
(1) New attributes can be added. There is no requirement that a
filesystem implement every attribute. Note that the core VFS keeps a
table of types and sizes so it can handle future extensibility rather
than delegating this to the filesystems.
(2) Version length-dependent structure attributes can be made larger and
have additional information tacked on the end, provided it keeps the
layout of the existing fields. If an older process asks for a shorter
structure, it will only be given the bits it asks for. If a newer
process asks for a longer structure on an older kernel, the extra
space will be set to 0. In all cases, the size of the data actually
available is returned.
In essence, the size of a structure is that structure's version: a
smaller size is an earlier version and a later version includes
everything that the earlier version did.
(3) New single-bit capability flags can be added. This is a structure-typed
attribute and, as such, (2) applies. Any bits you wanted but the kernel
doesn't support are automatically set to 0.
If a filesystem-specific attribute is added, it should just take up the next
number in the enumeration. Currently, I do not intend that the number space
should be subdivided between interested parties.
fsinfo() may be called like the following, for example:
struct fsinfo_params params = {
.at_flags = AT_SYMLINK_NOFOLLOW,
.request = FSINFO_ATTR_SERVER_ADDRESS;
.Nth = 2;
.Mth = 1;
};
struct fsinfo_server_address address;
len = fsinfo(AT_FDCWD, "/afs/grand.central.org/doc", ¶ms,
&address, sizeof(address));
The above example would query a network filesystem, such as AFS or NFS, and
ask what the 2nd address (Mth) of the 3rd server (Nth) that the superblock is
using is. Whereas:
struct fsinfo_params params = {
.at_flags = AT_SYMLINK_NOFOLLOW,
.request = FSINFO_ATTR_AFS_CELL_NAME;
};
char cell_name[256];
len = fsinfo(AT_FDCWD, "/afs/grand.central.org/doc", ¶ms,
&cell_name, sizeof(cell_name));
would retrieve the name of an AFS cell as a string.
fsinfo() can also be used to query a context from fsopen() or fspick():
fd = fsopen("ext4", 0);
struct fsinfo_params params = {
.request = FSINFO_ATTR_PARAM_DESCRIPTION;
};
struct fsinfo_param_description desc;
fsinfo(fd, NULL, ¶ms, &desc, sizeof(desc));
even if that context doesn't currently have a superblock attached (though if
there's no superblock attached, only filesystem-specific things like parameter
descriptions can be accessed).
The patches can be found here also:
https://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git
on branch:
fsinfo-core
===================
SIGNIFICANT CHANGES
===================
ver #15:
(*) Rebase the patchset to v5.2-rc1 to remove the dependencies on my
mount-api-viro branch. Al has remunged the patches, but has not
exposed what he might send upstream.
(*) Split out various of the individual filesystem implementation patches
that depend on mount API changes having been made.
(*) Split out the specify-by-mount-ID patch and the mount-topology query
patches into the fsinfo-mount branch.
ver #14:
(*) Increase to 128-bit the fields for number of blocks and files in the
filesystem and also the max file size and max inode number fields.
(*) Increase to 64-bit the fields for max hard links and max xattr body
length.
(*) Provide struct fsinfo_timestamp_one to represent the characteristics
of a single timestamp and move the range into it. FAT, for example,
has different ranges for different timestamps. Each timestamp is then
represented by one of these structs.
(*) Don't expose MS_* flags (such as MS_RDONLY) through this interface as
they ought to be considered deprecated; instead anyone who wants them
should parse FSINFO_ATTR_PARAMETERS for the string equivalents.
(*) Add a flag, AT_FSINFO_FROM_FSOPEN, to indicate that the fd being
accessed is from fsopen()/fspick() and that fsinfo() should look
inside and access the filesystem referred to by the fs_context.
(*) If the filesystem implements FSINFO_ATTR_PARAMETERS for itself, don't
automatically include flags for the SB_* bits that are normally
rendered by, say, /proc/mounts (such as SB_RDONLY). Rather, a helper
is provided that the filesystem must call with an appropriately
wangled s_flags.
(*) Drop the NFS fsinfo patch for now as NFS fs_context support is
unlikely to get upstream in the upcoming merge window.
ver #13:
(*) Provided a "fixed-struct array" type so that the list of children of a
mount and all their change counters can be read atomically.
(*) Additional filesystem examples.
(*) Documented the API.
ver #12:
(*) Rename ->get_fsinfo() to ->fsinfo().
(*) Pass the path through to to ->fsinfo() as it's needed for NFS to
retrocalculate the source name.
(*) Indicated which is the source parameter in the param-description
attribute.
(*) Dropped the realm attribute.
David
---
David Howells (10):
vfs: syscall: Add fsinfo() to query filesystem information
fsinfo: Add syscalls to other arches
vfs: Allow fsinfo() to query what's in an fs_context
vfs: Allow fsinfo() to be used to query an fs parameter description
vfs: Implement parameter value retrieval with fsinfo()
fsinfo: Implement retrieval of LSM parameters with fsinfo()
afs: Support fsinfo()
fsinfo: Add API documentation
hugetlbfs: Add support for fsinfo()
kernfs, cgroup: Add fsinfo support
Ian Kent (1):
fsinfo: proc - add sb operation fsinfo()
Documentation/filesystems/fsinfo.rst | 561 +++++++++++++++++++
arch/alpha/kernel/syscalls/syscall.tbl | 1
arch/arm/tools/syscall.tbl | 1
arch/arm64/include/asm/unistd.h | 2
arch/arm64/include/asm/unistd32.h | 2
arch/ia64/kernel/syscalls/syscall.tbl | 1
arch/m68k/kernel/syscalls/syscall.tbl | 1
arch/microblaze/kernel/syscalls/syscall.tbl | 1
arch/mips/kernel/syscalls/syscall_n32.tbl | 1
arch/mips/kernel/syscalls/syscall_n64.tbl | 1
arch/mips/kernel/syscalls/syscall_o32.tbl | 1
arch/parisc/kernel/syscalls/syscall.tbl | 1
arch/powerpc/kernel/syscalls/syscall.tbl | 1
arch/s390/kernel/syscalls/syscall.tbl | 1
arch/sh/kernel/syscalls/syscall.tbl | 1
arch/sparc/kernel/syscalls/syscall.tbl | 1
arch/x86/entry/syscalls/syscall_32.tbl | 1
arch/x86/entry/syscalls/syscall_64.tbl | 1
arch/xtensa/kernel/syscalls/syscall.tbl | 1
fs/Kconfig | 7
fs/Makefile | 1
fs/afs/internal.h | 1
fs/afs/super.c | 180 ++++++
fs/fsinfo.c | 818 +++++++++++++++++++++++++++
fs/hugetlbfs/inode.c | 57 ++
fs/kernfs/mount.c | 20 +
fs/proc/inode.c | 37 +
fs/statfs.c | 2
include/linux/fs.h | 5
include/linux/fsinfo.h | 69 ++
include/linux/kernfs.h | 4
include/linux/lsm_hooks.h | 13
include/linux/security.h | 11
include/linux/syscalls.h | 4
include/uapi/asm-generic/unistd.h | 4
include/uapi/linux/fcntl.h | 2
include/uapi/linux/fsinfo.h | 291 ++++++++++
kernel/cgroup/cgroup-v1.c | 44 +
kernel/cgroup/cgroup.c | 19 +
kernel/sys_ni.c | 1
samples/vfs/Makefile | 6
samples/vfs/test-fs-query.c | 138 +++++
samples/vfs/test-fsinfo.c | 640 +++++++++++++++++++++
security/security.c | 12
44 files changed, 2961 insertions(+), 6 deletions(-)
create mode 100644 Documentation/filesystems/fsinfo.rst
create mode 100644 fs/fsinfo.c
create mode 100644 include/linux/fsinfo.h
create mode 100644 include/uapi/linux/fsinfo.h
create mode 100644 samples/vfs/test-fs-query.c
create mode 100644 samples/vfs/test-fsinfo.c
^ permalink raw reply
* Re: [PATCH bpf-next v9 05/10] bpf,landlock: Add a new map type: inode
From: Mickaël Salaün @ 2019-06-28 13:17 UTC (permalink / raw)
To: Al Viro
Cc: Mickaël Salaün, linux-kernel, Aleksa Sarai,
Alexei Starovoitov, Andrew Morton, Andy Lutomirski,
Arnaldo Carvalho de Melo, Casey Schaufler, Daniel Borkmann,
David Drysdale, David S . Miller, Eric W . Biederman,
James Morris, Jann Horn, John Johansen, Jonathan Corbet,
Kees Cook, Michael Kerrisk, Paul Moore
In-Reply-To: <20190627165640.GQ17978@ZenIV.linux.org.uk>
On 27/06/2019 18:56, Al Viro wrote:
> On Thu, Jun 27, 2019 at 06:18:12PM +0200, Mickaël Salaün wrote:
>
>>>> +/* called from syscall */
>>>> +static int sys_inode_map_delete_elem(struct bpf_map *map, struct inode *key)
>>>> +{
>>>> + struct inode_array *array = container_of(map, struct inode_array, map);
>>>> + struct inode *inode;
>>>> + int i;
>>>> +
>>>> + WARN_ON_ONCE(!rcu_read_lock_held());
>>>> + for (i = 0; i < array->map.max_entries; i++) {
>>>> + if (array->elems[i].inode == key) {
>>>> + inode = xchg(&array->elems[i].inode, NULL);
>>>> + array->nb_entries--;
>>>
>>> Umm... Is that intended to be atomic in any sense?
>>
>> nb_entries is not used as a bound check but to avoid walking uselessly
>> through the (pre-allocated) array when adding a new element, but I'll
>> use an atomic to avoid inconsistencies anyway.
>
>
>>> Wait a sec... So we have those beasties that can have long-term
>>> references to arbitrary inodes stuck in them? What will happen
>>> if you get umount(2) called while such a thing exists?
>>
>> I though an umount would be denied but no, we get a self-destructed busy
>> inode and a bug!
>> What about wrapping the inode's superblock->s_op->destroy_inode() to
>> first remove the element from the map and then call the real
>> destroy_inode(), if any?
>
> What do you mean, _the_ map? I don't see anything to prevent insertion
> of references to the same inode into any number of those...
Indeed, the current design needs to check for duplicate inode references
to avoid unused entries (until a reference is removed). I was planning
to use an rbtree but I'm working on using a hash table instead (cf.
bpf/hashtab.c), which will solve the issue anyway.
>
>> Or I could update fs/inode.c:destroy_inode() to call inode->free_inode()
>> if it is set, and set it when such inode is referenced by a map?
>> Or maybe I could hold the referencing file in the map and then wrap its
>> f_op?
>
> First of all, anything including the word "wrap" is a non-starter.
> We really don't need the headache associated with the locking needed
> to replace the method tables on the fly, or with the code checking that
> ->f_op points to given method table, etc. That's not going to fly,
> especially since you'd end up _chaining_ those (again, the same reference
> can go in more than once).
>
> Nothing is allowed to change the method tables of live objects, period.
> Once a struct file is opened, its ->f_op is never going to change and
> it entirely belongs to the device driver or filesystem it resides on.
> Nothing else (not VFS, not VM, not some LSM module, etc.) has any business
> touching that. The same goes for inodes, dentries, etc.
>
> What kind of behaviour do you want there? Do you want the inodes you've
> referenced there to be forgotten on e.g. memory pressure? The thing is,
> I don't see how "it's getting freed" could map onto any semantics that
> might be useful for you - it looks like the wrong event for that.
At least, I would like to be able to compare an inode with the reference
one if this reference may be accessible somewhere on the system. Being
able to keep the inode reference as long as its superblock is alive
seems to solve the problem. This enable for example to compare inodes
from two bind mounts of the same file system even if one mount point is
unmounted.
Storing and using the device ID and the inode number bring a new problem
when an inode is removed and when its number is recycled. However, if I
can be notified when such an inode is removed (preferably without using
an LSM hook) and if I can know when the backing device go out of the
scope of the (live) system (e.g. hot unplugging an USB drive), this
should solve the problem and also enable to keep a reference to an inode
as long as possible without any dangling pointer nor wrapper.
^ permalink raw reply
* Re: [PATCH v2 bpf-next 1/4] bpf: unprivileged BPF access via /dev/bpf
From: Christian Brauner @ 2019-06-28 10:28 UTC (permalink / raw)
To: Andy Lutomirski
Cc: Kees Cook, Linux API, Song Liu, Network Development, bpf,
Alexei Starovoitov, Daniel Borkmann, kernel-team, lmb, Jann Horn,
Greg KH, casey, sds, linux-security
In-Reply-To: <CALCETrUp3Tj062wG-noNdsY-sU9gsob_kVK=W_DxWciMpZFvyA@mail.gmail.com>
On Thu, Jun 27, 2019 at 04:42:18PM -0700, Andy Lutomirski wrote:
> [sigh, I finally set up lore nntp, and I goofed some addresses. Hi
> Kees and linux-api.]
Love it or hate it but that should probably also Cc linux-security...
>
> On Thu, Jun 27, 2019 at 4:40 PM Andy Lutomirski <luto@kernel.org> wrote:
> >
> > On 6/27/19 1:19 PM, Song Liu wrote:
> > > This patch introduce unprivileged BPF access. The access control is
> > > achieved via device /dev/bpf. Users with write access to /dev/bpf are able
> > > to call sys_bpf().
> > >
> > > Two ioctl command are added to /dev/bpf:
> > >
> > > The two commands enable/disable permission to call sys_bpf() for current
> > > task. This permission is noted by bpf_permitted in task_struct. This
> > > permission is inherited during clone(CLONE_THREAD).
> > >
> > > Helper function bpf_capable() is added to check whether the task has got
> > > permission via /dev/bpf.
> > >
> >
> > > diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> > > index 0e079b2298f8..79dc4d641cf3 100644
> > > --- a/kernel/bpf/verifier.c
> > > +++ b/kernel/bpf/verifier.c
> > > @@ -9134,7 +9134,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
> > > env->insn_aux_data[i].orig_idx = i;
> > > env->prog = *prog;
> > > env->ops = bpf_verifier_ops[env->prog->type];
> > > - is_priv = capable(CAP_SYS_ADMIN);
> > > + is_priv = bpf_capable(CAP_SYS_ADMIN);
> >
> > Huh? This isn't a hardening measure -- the "is_priv" verifier mode
> > allows straight-up leaks of private kernel state to user mode.
> >
> > (For that matter, the pending lockdown stuff should possibly consider
> > this a "confidentiality" issue.)
> >
> >
> > I have a bigger issue with this patch, though: it's a really awkward way
> > to pretend to have capabilities. For bpf, it seems like you could make
> > this be a *real* capability without too much pain since there's only one
> > syscall there. Just find a way to pass an fd to /dev/bpf into the
> > syscall. If this means you need a new bpf_with_cap() syscall that takes
> > an extra argument, so be it. The old bpf() syscall can just translate
> > to bpf_with_cap(..., -1).
> >
> > For a while, I've considered a scheme I call "implicit rights". There
> > would be a directory in /dev called /dev/implicit_rights. This would
> > either be part of devtmpfs or a whole new filesystem -- it would *not*
> > be any other filesystem. The contents would be files that can't be read
> > or written and exist only in memory. You create them with a privileged
> > syscall. Certain actions that are sensitive but not at the level of
> > CAP_SYS_ADMIN (use of large-attack-surface bpf stuff, creation of user
> > namespaces, profiling the kernel, etc) could require an "implicit
> > right". When you do them, if you don't have CAP_SYS_ADMIN, the kernel
> > would do a path walk for, say, /dev/implicit_rights/bpf and, if the
> > object exists, can be opened, and actually refers to the "bpf" rights
> > object, then the action is allowed. Otherwise it's denied.
> >
> > This is extensible, and it doesn't require the rather ugly per-task
> > state of whether it's enabled.
> >
> > For things like creation of user namespaces, there's an existing API,
> > and the default is that it works without privilege. Switching it to an
> > implicit right has the benefit of not requiring code changes to programs
> > that already work as non-root.
> >
> > But, for BPF in particular, this type of compatibility issue doesn't
> > exist now. You already can't use most eBPF functionality without
> > privilege. New bpf-using programs meant to run without privilege are
> > *new*, so they can use a new improved API. So, rather than adding this
> > obnoxious ioctl, just make the API explicit, please.
> >
> > Also, please cc: linux-abi next time.
^ permalink raw reply
* Re: [PATCH v5 17/18] kernel/sysctl-test: Add null pointer test for sysctl.c:proc_dointvec()
From: Brendan Higgins @ 2019-06-28 8:01 UTC (permalink / raw)
To: Luis Chamberlain
Cc: Petr Mladek, open list:DOCUMENTATION, Peter Zijlstra,
Amir Goldstein, dri-devel, Sasha Levin, Masahiro Yamada,
Michael Ellerman, open list:KERNEL SELFTEST FRAMEWORK, shuah,
Rob Herring, linux-nvdimm, Frank Rowand, Knut Omang,
Kieran Bingham, wfg-VuQAYsv1563Yd54FQh9/CA,
Michael Kerrisk (man-pages), David Rientjes, Iurii Zaikin,
Jeff Dike, Dan Carpenter, Joel Stanley <joel>
In-Reply-To: <20190627061021.GE19023-24ieFPqdLRAUX4Zk0b6cZUEOCMrvLtNR@public.gmane.org>
On Wed, Jun 26, 2019 at 11:10 PM Luis Chamberlain <mcgrof-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org> wrote:
>
> On Wed, Jun 26, 2019 at 09:07:43PM -0700, Iurii Zaikin wrote:
> > On Tue, Jun 25, 2019 at 7:17 PM Luis Chamberlain <mcgrof-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org> wrote:
> > > > +static void sysctl_test_dointvec_table_maxlen_unset(struct kunit *test)
> > > > +{
> > > > + struct ctl_table table = {
> > > > + .procname = "foo",
> > > > + .data = &test_data.int_0001,
> > > > + .maxlen = 0,
> > > > + .mode = 0644,
> > > > + .proc_handler = proc_dointvec,
> > > > + .extra1 = &i_zero,
> > > > + .extra2 = &i_one_hundred,
> > > > + };
> > > > + void *buffer = kunit_kzalloc(test, sizeof(int), GFP_USER);
> > > > + size_t len;
> > > > + loff_t pos;
> > > > +
> > > > + len = 1234;
> > > > + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, 0, buffer, &len, &pos));
> > > > + KUNIT_EXPECT_EQ(test, (size_t)0, len);
> > > > + len = 1234;
> > > > + KUNIT_EXPECT_EQ(test, 0, proc_dointvec(&table, 1, buffer, &len, &pos));
> > > > + KUNIT_EXPECT_EQ(test, (size_t)0, len);
> > > > +}
> > >
> > > In a way this is also testing for general kernel API changes. This is and the
> > > last one were good examples. So this is not just testing functionality
> > > here. There is no wrong or write answer if 0 or -EINVAL was returned
> > > other than the fact that we have been doing this for years.
> > >
> > > Its a perhaps small but important difference for some of these tests. I
> > > *do* think its worth clarifying through documentation which ones are
> > > testing for API consistency Vs proper correctness.
> >
> > You make a good point that the test codifies the existing behavior of
> > the function in lieu of formal documentation. However, the test cases
> > were derived from examining the source code of the function under test
> > and attempting to cover all branches. The assertions were added only
> > for the values that appeared to be set deliberately in the
> > implementation. And it makes sense to me to test that the code does
> > exactly what the implementation author intended.
>
> I'm not arguing against adding them. I'm suggesting that it is different
> to test for API than for correctness of intended functionality, and
> it would be wise to make it clear which test cases are for API and which
> for correctness.
I see later on that some of the API stuff you are talking about is
public APIs from the standpoint of user (outside of LInux) visible. To
be clear, is that what you mean by public APIs throughout, or would
you distinguish between correctness tests, internal API tests, and
external API tests?
> This will come up later for other kunit tests and it would be great
> to set precendent so that other kunit tests can follow similar
> practices to ensure its clear what is API realted Vs correctness of
> intended functionality.
>
> In fact, I'm not yet sure if its possible to test public kernel API to
> userspace with kunit, but if it is possible... well, that could make
> linux-api folks happy as they could enable us to codify interpreation of
> what is expected into kunit test cases, and we'd ensure that the
> codified interpretation is not only documented in man pages but also
> through formal kunit test cases.
>
> A regression in linux-api then could be formalized through a proper
> kunit tests case. And if an API evolves, it would force developers to
> update the respective kunit which codifies that contract.
Yep, I think that is long term hope. Some of the file system interface
stuff that requires a filesystem to be mounted somewhere might get a
little weird/difficult, but I suspect we should be able to do it
eventually. I mean it's all just C code right? Should mostly boil down
to someone figuring out how to do it the first time.
> > > > +static void sysctl_test_dointvec_single_less_int_min(struct kunit *test)
> > > > +{
> > > > + struct ctl_table table = {
> > > > + .procname = "foo",
> > > > + .data = &test_data.int_0001,
> > > > + .maxlen = sizeof(int),
> > > > + .mode = 0644,
> > > > + .proc_handler = proc_dointvec,
> > > > + .extra1 = &i_zero,
> > > > + .extra2 = &i_one_hundred,
> > > > + };
> > > > + char input[32];
> > > > + size_t len = sizeof(input) - 1;
> > > > + loff_t pos = 0;
> > > > + unsigned long abs_of_less_than_min = (unsigned long)INT_MAX
> > > > + - (INT_MAX + INT_MIN) + 1;
> > > > +
> > > > + KUNIT_EXPECT_LT(test,
> > > > + (size_t)snprintf(input, sizeof(input), "-%lu",
> > > > + abs_of_less_than_min),
> > > > + sizeof(input));
> > > > +
> > > > + table.data = kunit_kzalloc(test, sizeof(int), GFP_USER);
> > > > + KUNIT_EXPECT_EQ(test, -EINVAL,
> > > > + proc_dointvec(&table, 1, input, &len, &pos));
> > > > + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len);
> > > > + KUNIT_EXPECT_EQ(test, 0, ((int *)table.data)[0]);
> > > > +}
> > >
> > > API test.
> > >
> > Not sure why.
>
> Because you are codifying that we *definitely* return -EINVAL on
> overlow. Some parts of the kernel return -ERANGE for overflows for
> instance.
>
> It would be a generic test for overflow if it would just test
> for any error.
>
> It is a fine and good test to keep. All these tests are good to keep.
>
> > I believe there has been a real bug with int overflow in
> > proc_dointvec.
> > Covering it with test seems like a good idea.
>
> Oh definitely.
>
> > > > +static void sysctl_test_dointvec_single_greater_int_max(struct kunit *test)
> > > > +{
> > > > + struct ctl_table table = {
> > > > + .procname = "foo",
> > > > + .data = &test_data.int_0001,
> > > > + .maxlen = sizeof(int),
> > > > + .mode = 0644,
> > > > + .proc_handler = proc_dointvec,
> > > > + .extra1 = &i_zero,
> > > > + .extra2 = &i_one_hundred,
> > > > + };
> > > > + char input[32];
> > > > + size_t len = sizeof(input) - 1;
> > > > + loff_t pos = 0;
> > > > + unsigned long greater_than_max = (unsigned long)INT_MAX + 1;
> > > > +
> > > > + KUNIT_EXPECT_GT(test, greater_than_max, (unsigned long)INT_MAX);
> > > > + KUNIT_EXPECT_LT(test, (size_t)snprintf(input, sizeof(input), "%lu",
> > > > + greater_than_max),
> > > > + sizeof(input));
> > > > + table.data = kunit_kzalloc(test, sizeof(int), GFP_USER);
> > > > + KUNIT_EXPECT_EQ(test, -EINVAL,
> > > > + proc_dointvec(&table, 1, input, &len, &pos));
> > > > + KUNIT_EXPECT_EQ(test, sizeof(input) - 1, len);
> > > > + KUNIT_EXPECT_EQ(test, 0, ((int *)table.data)[0]);
> > > > +}
> > > > +
> > >
> > > API test.
> > >
> > > > +static struct kunit_case sysctl_test_cases[] = {
> > > > + KUNIT_CASE(sysctl_test_dointvec_null_tbl_data),
> > > > + KUNIT_CASE(sysctl_test_dointvec_table_maxlen_unset),
> > > > + KUNIT_CASE(sysctl_test_dointvec_table_len_is_zero),
> > > > + KUNIT_CASE(sysctl_test_dointvec_table_read_but_position_set),
> > > > + KUNIT_CASE(sysctl_test_dointvec_happy_single_positive),
> > > > + KUNIT_CASE(sysctl_test_dointvec_happy_single_negative),
> > > > + KUNIT_CASE(sysctl_test_dointvec_single_less_int_min),
> > > > + KUNIT_CASE(sysctl_test_dointvec_single_greater_int_max),
> > > > + {}
> > > > +};
> > >
> > > Oh all are API tests.. perhaps then just rename then
> > > sysctl_test_cases to sysctl_api_test_cases.
> > >
> > > Would be good to add at least *two* other tests cases for this
> > > example, one which does a valid read and one which does a valid write.
> > Added valid reads. There already are 2 valid writes.
>
> Thanks.
>
> > > If that is done either we add another kunit test module for correctness
> > > or just extend the above and use prefix / postfixes on the functions
> > > to distinguish between API / correctness somehow.
> > >
> > > > +
> > > > +static struct kunit_module sysctl_test_module = {
> > > > + .name = "sysctl_test",
> > > > + .test_cases = sysctl_test_cases,
> > > > +};
> > > > +
> > > > +module_test(sysctl_test_module);
> > > > diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
> > > > index cbdfae3798965..389b8986f5b77 100644
> > > > --- a/lib/Kconfig.debug
> > > > +++ b/lib/Kconfig.debug
> > > > @@ -1939,6 +1939,16 @@ config TEST_SYSCTL
> > > >
> > > > If unsure, say N.
> > > >
> > > > +config SYSCTL_KUNIT_TEST
> > > > + bool "KUnit test for sysctl"
> > > > + depends on KUNIT
> > > > + help
> > > > + This builds the proc sysctl unit test, which runs on boot. For more
> > > > + information on KUnit and unit tests in general please refer to the
> > > > + KUnit documentation in Documentation/dev-tools/kunit/.
> > >
> > > A little more description here would help. It is testing for API and
> > > hopefully also correctness (if extended with those two examples I
> > > mentioned).
> > >
> > Added "Tests the API contract and implementation correctness of sysctl."
>
> Yes, much clearer, thanks!
Cheers!
^ permalink raw reply
* Re: [PATCH v4 05/15] Documentation: fpga: dfl: add descriptions for virtualization and new interfaces.
From: Wu Hao @ 2019-06-28 2:13 UTC (permalink / raw)
To: Moritz Fischer
Cc: linux-fpga, linux-kernel, linux-api, yilun.xu, gregkh, atull
In-Reply-To: <20190628011256.GB5671@archbook>
On Thu, Jun 27, 2019 at 06:12:56PM -0700, Moritz Fischer wrote:
> Hi Wu,
>
> On Thu, Jun 27, 2019 at 12:44:45PM +0800, Wu Hao wrote:
> > This patch adds virtualization support description for DFL based
> > FPGA devices (based on PCIe SRIOV), and introductions to new
> > interfaces added by new dfl private feature drivers.
> >
> > Signed-off-by: Xu Yilun <yilun.xu@intel.com>
> > Signed-off-by: Wu Hao <hao.wu@intel.com>
> > Acked-by: Alan Tull <atull@kernel.org>
> > ---
> > Documentation/fpga/dfl.txt | 101 +++++++++++++++++++++++++++++++++++++++++++++
> > 1 file changed, 101 insertions(+)
> >
> > diff --git a/Documentation/fpga/dfl.txt b/Documentation/fpga/dfl.txt
> > index 6df4621..a22631f 100644
> > --- a/Documentation/fpga/dfl.txt
> > +++ b/Documentation/fpga/dfl.txt
>
> This got re{named,formatted} in linux-next. I've tried to fix it before sending it
> to Greg.
Many Thanks for the help! :)
I think I need rebase thermal/power management (hwmon) and perf support
patchsets as they update this documentation file too. But I feel we
can go ahead on code review for the other patches, if there are some
comments received and something need to fix, i can put fixes together in
the next version.
Thanks
Hao
>
> Thanks,
> Moritz
^ permalink raw reply
* Re: [PATCH v4 05/15] Documentation: fpga: dfl: add descriptions for virtualization and new interfaces.
From: Moritz Fischer @ 2019-06-28 1:12 UTC (permalink / raw)
To: Wu Hao; +Cc: mdf, linux-fpga, linux-kernel, linux-api, yilun.xu, gregkh, atull
In-Reply-To: <1561610695-5414-6-git-send-email-hao.wu@intel.com>
Hi Wu,
On Thu, Jun 27, 2019 at 12:44:45PM +0800, Wu Hao wrote:
> This patch adds virtualization support description for DFL based
> FPGA devices (based on PCIe SRIOV), and introductions to new
> interfaces added by new dfl private feature drivers.
>
> Signed-off-by: Xu Yilun <yilun.xu@intel.com>
> Signed-off-by: Wu Hao <hao.wu@intel.com>
> Acked-by: Alan Tull <atull@kernel.org>
> ---
> Documentation/fpga/dfl.txt | 101 +++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 101 insertions(+)
>
> diff --git a/Documentation/fpga/dfl.txt b/Documentation/fpga/dfl.txt
> index 6df4621..a22631f 100644
> --- a/Documentation/fpga/dfl.txt
> +++ b/Documentation/fpga/dfl.txt
This got re{named,formatted} in linux-next. I've tried to fix it before sending it
to Greg.
Thanks,
Moritz
^ permalink raw reply
* Re: [PATCH v4 2/2] fpga: dfl: fme: add performance reporting support
From: Wu Hao @ 2019-06-28 0:13 UTC (permalink / raw)
To: Greg KH
Cc: mdf, linux-fpga, linux-kernel, linux-api, atull, Luwei Kang,
Xu Yilun
In-Reply-To: <20190627165329.GB9855@kroah.com>
On Fri, Jun 28, 2019 at 12:53:29AM +0800, Greg KH wrote:
> On Thu, Jun 27, 2019 at 01:09:55PM +0800, Wu Hao wrote:
> > This patch adds support for performance reporting private feature
> > for FPGA Management Engine (FME). Now it supports several different
> > performance counters, including 'basic', 'cache', 'fabric', 'vtd'
> > and 'vtd_sip'. It allows user to use standard linux tools to access
> > these performance counters.
> >
> > e.g. List all events by "perf list"
> >
> > perf list | grep fme
> >
> > fme0/cache_read_hit/ [Kernel PMU event]
> > fme0/cache_read_miss/ [Kernel PMU event]
> > ...
> >
> > fme0/fab_mmio_read/ [Kernel PMU event]
> > fme0/fab_mmio_write/ [Kernel PMU event]
> > ...
> >
> > fme0/fab_port_mmio_read,portid=?/ [Kernel PMU event]
> > fme0/fab_port_mmio_write,portid=?/ [Kernel PMU event]
> > ...
> >
> > fme0/vtd_port_devtlb_1g_fill,portid=?/ [Kernel PMU event]
> > fme0/vtd_port_devtlb_2m_fill,portid=?/ [Kernel PMU event]
> > ...
> >
> > fme0/vtd_sip_iotlb_1g_hit/ [Kernel PMU event]
> > fme0/vtd_sip_iotlb_1g_miss/ [Kernel PMU event]
> > ...
> >
> > fme0/clock [Kernel PMU event]
> > ...
> >
> > e.g. check increased counter value after run one application using
> > "perf stat" command.
> >
> > perf stat -e fme0/fab_mmio_read/,fme0/fab_mmio_write/, ./test
> >
> > Performance counter stats for './test':
> >
> > 1 fme0/fab_mmio_read/
> > 2 fme0/fab_mmio_write/
> >
> > 1.009496520 seconds time elapsed
> >
> > Please note that fabric counters support both fab_* and fab_port_*, but
> > actually they are sharing one set of performance counters in hardware.
> > If user wants to monitor overall data events on fab_* then fab_port_*
> > can't be supported at the same time, see example below:
> >
> > perf stat -e fme0/fab_mmio_read/,fme0/fab_port_mmio_write,portid=0/
> >
> > Performance counter stats for 'system wide':
> >
> > 0 fme0/fab_mmio_read/
> > <not supported> fme0/fab_port_mmio_write,portid=0/
> >
> > 2.141064085 seconds time elapsed
> >
> > Signed-off-by: Luwei Kang <luwei.kang@intel.com>
> > Signed-off-by: Xu Yilun <yilun.xu@intel.com>
> > Signed-off-by: Wu Hao <hao.wu@intel.com>
> > ---
> > v3: replace scnprintf with sprintf in sysfs interfaces.
> > update sysfs doc kernel version and date.
> > fix sysfs doc issue for fabric counter.
> > refine PERF_OBJ_ATTR_* macro, doesn't count on __ATTR anymore.
> > introduce PERF_OBJ_ATTR_F_* macro, as it needs to use different
> > filenames for some of the sysfs attributes.
> > remove kobject_del when destroy kobject, kobject_put is enough.
> > do sysfs_remove_groups first when destroying perf_obj.
> > WARN_ON_ONCE in case internal parms are wrong in read_*_count().
> > v4: rework this patch to use standard perf API as user interfaces.
> > ---
> > drivers/fpga/Makefile | 1 +
> > drivers/fpga/dfl-fme-main.c | 4 +
> > drivers/fpga/dfl-fme-perf.c | 871 ++++++++++++++++++++++++++++++++++++++++++++
> > drivers/fpga/dfl-fme.h | 2 +
> > 4 files changed, 878 insertions(+)
> > create mode 100644 drivers/fpga/dfl-fme-perf.c
> >
> > diff --git a/drivers/fpga/Makefile b/drivers/fpga/Makefile
> > index 4865b74..d8e21df 100644
> > --- a/drivers/fpga/Makefile
> > +++ b/drivers/fpga/Makefile
> > @@ -40,6 +40,7 @@ obj-$(CONFIG_FPGA_DFL_FME_REGION) += dfl-fme-region.o
> > obj-$(CONFIG_FPGA_DFL_AFU) += dfl-afu.o
> >
> > dfl-fme-objs := dfl-fme-main.o dfl-fme-pr.o dfl-fme-error.o
> > +dfl-fme-objs += dfl-fme-perf.o
> > dfl-afu-objs := dfl-afu-main.o dfl-afu-region.o dfl-afu-dma-region.o
> > dfl-afu-objs += dfl-afu-error.o
> >
> > diff --git a/drivers/fpga/dfl-fme-main.c b/drivers/fpga/dfl-fme-main.c
> > index 9225b68..a11c112 100644
> > --- a/drivers/fpga/dfl-fme-main.c
> > +++ b/drivers/fpga/dfl-fme-main.c
> > @@ -639,6 +639,10 @@ static void fme_power_mgmt_uinit(struct platform_device *pdev,
> > .ops = &fme_power_mgmt_ops,
> > },
> > {
> > + .id_table = fme_perf_id_table,
> > + .ops = &fme_perf_ops,
> > + },
> > + {
> > .ops = NULL,
> > },
> > };
> > diff --git a/drivers/fpga/dfl-fme-perf.c b/drivers/fpga/dfl-fme-perf.c
> > new file mode 100644
> > index 0000000..0d7768a
> > --- /dev/null
> > +++ b/drivers/fpga/dfl-fme-perf.c
> > @@ -0,0 +1,871 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Driver for FPGA Management Engine (FME) Global Performance Reporting
> > + *
> > + * Copyright 2019 Intel Corporation, Inc.
> > + *
> > + * Authors:
> > + * Kang Luwei <luwei.kang@intel.com>
> > + * Xiao Guangrong <guangrong.xiao@linux.intel.com>
> > + * Wu Hao <hao.wu@intel.com>
> > + * Xu Yilun <yilun.xu@intel.com>
> > + * Joseph Grecco <joe.grecco@intel.com>
> > + * Enno Luebbers <enno.luebbers@intel.com>
> > + * Tim Whisonant <tim.whisonant@intel.com>
> > + * Ananda Ravuri <ananda.ravuri@intel.com>
> > + * Mitchel, Henry <henry.mitchel@intel.com>
> > + */
> > +
> > +#include <linux/perf_event.h>
> > +#include "dfl.h"
> > +#include "dfl-fme.h"
> > +
> > +/*
> > + * Performance Counter Registers for Cache.
> > + *
> > + * Cache Events are listed below as CACHE_EVNT_*.
> > + */
> > +#define CACHE_CTRL 0x8
> > +#define CACHE_RESET_CNTR BIT_ULL(0)
> > +#define CACHE_FREEZE_CNTR BIT_ULL(8)
> > +#define CACHE_CTRL_EVNT GENMASK_ULL(19, 16)
> > +#define CACHE_EVNT_RD_HIT 0x0
> > +#define CACHE_EVNT_WR_HIT 0x1
> > +#define CACHE_EVNT_RD_MISS 0x2
> > +#define CACHE_EVNT_WR_MISS 0x3
> > +#define CACHE_EVNT_RSVD 0x4
> > +#define CACHE_EVNT_HOLD_REQ 0x5
> > +#define CACHE_EVNT_DATA_WR_PORT_CONTEN 0x6
> > +#define CACHE_EVNT_TAG_WR_PORT_CONTEN 0x7
> > +#define CACHE_EVNT_TX_REQ_STALL 0x8
> > +#define CACHE_EVNT_RX_REQ_STALL 0x9
> > +#define CACHE_EVNT_EVICTIONS 0xa
> > +#define CACHE_CHANNEL_SEL BIT_ULL(20)
> > +#define CACHE_CHANNEL_RD 0
> > +#define CACHE_CHANNEL_WR 1
> > +#define CACHE_CNTR0 0x10
> > +#define CACHE_CNTR1 0x18
> > +#define CACHE_CNTR_EVNT_CNTR GENMASK_ULL(47, 0)
> > +#define CACHE_CNTR_EVNT GENMASK_ULL(63, 60)
> > +
> > +/*
> > + * Performance Counter Registers for Fabric.
> > + *
> > + * Fabric Events are listed below as FAB_EVNT_*
> > + */
> > +#define FAB_CTRL 0x20
> > +#define FAB_RESET_CNTR BIT_ULL(0)
> > +#define FAB_FREEZE_CNTR BIT_ULL(8)
> > +#define FAB_CTRL_EVNT GENMASK_ULL(19, 16)
> > +#define FAB_EVNT_PCIE0_RD 0x0
> > +#define FAB_EVNT_PCIE0_WR 0x1
> > +#define FAB_EVNT_PCIE1_RD 0x2
> > +#define FAB_EVNT_PCIE1_WR 0x3
> > +#define FAB_EVNT_UPI_RD 0x4
> > +#define FAB_EVNT_UPI_WR 0x5
> > +#define FAB_EVNT_MMIO_RD 0x6
> > +#define FAB_EVNT_MMIO_WR 0x7
> > +#define FAB_PORT_ID GENMASK_ULL(21, 20)
> > +#define FAB_PORT_FILTER BIT_ULL(23)
> > +#define FAB_PORT_FILTER_DISABLE 0
> > +#define FAB_PORT_FILTER_ENABLE 1
> > +#define FAB_CNTR 0x28
> > +#define FAB_CNTR_EVNT_CNTR GENMASK_ULL(59, 0)
> > +#define FAB_CNTR_EVNT GENMASK_ULL(63, 60)
> > +
> > +/*
> > + * Performance Counter Registers for Clock.
> > + *
> > + * Clock Counter can't be reset or frozen by SW.
> > + */
> > +#define CLK_CNTR 0x30
> > +#define BASIC_EVNT_CLK 0x0
> > +
> > +/*
> > + * Performance Counter Registers for IOMMU / VT-D.
> > + *
> > + * VT-D Events are listed below as VTD_EVNT_* and VTD_SIP_EVNT_*
> > + */
> > +#define VTD_CTRL 0x38
> > +#define VTD_RESET_CNTR BIT_ULL(0)
> > +#define VTD_FREEZE_CNTR BIT_ULL(8)
> > +#define VTD_CTRL_EVNT GENMASK_ULL(19, 16)
> > +#define VTD_EVNT_AFU_MEM_RD_TRANS 0x0
> > +#define VTD_EVNT_AFU_MEM_WR_TRANS 0x1
> > +#define VTD_EVNT_AFU_DEVTLB_RD_HIT 0x2
> > +#define VTD_EVNT_AFU_DEVTLB_WR_HIT 0x3
> > +#define VTD_EVNT_DEVTLB_4K_FILL 0x4
> > +#define VTD_EVNT_DEVTLB_2M_FILL 0x5
> > +#define VTD_EVNT_DEVTLB_1G_FILL 0x6
> > +#define VTD_CNTR 0x40
> > +#define VTD_CNTR_EVNT_CNTR GENMASK_ULL(47, 0)
> > +#define VTD_CNTR_EVNT GENMASK_ULL(63, 60)
> > +
> > +#define VTD_SIP_CTRL 0x48
> > +#define VTD_SIP_RESET_CNTR BIT_ULL(0)
> > +#define VTD_SIP_FREEZE_CNTR BIT_ULL(8)
> > +#define VTD_SIP_CTRL_EVNT GENMASK_ULL(19, 16)
> > +#define VTD_SIP_EVNT_IOTLB_4K_HIT 0x0
> > +#define VTD_SIP_EVNT_IOTLB_2M_HIT 0x1
> > +#define VTD_SIP_EVNT_IOTLB_1G_HIT 0x2
> > +#define VTD_SIP_EVNT_SLPWC_L3_HIT 0x3
> > +#define VTD_SIP_EVNT_SLPWC_L4_HIT 0x4
> > +#define VTD_SIP_EVNT_RCC_HIT 0x5
> > +#define VTD_SIP_EVNT_IOTLB_4K_MISS 0x6
> > +#define VTD_SIP_EVNT_IOTLB_2M_MISS 0x7
> > +#define VTD_SIP_EVNT_IOTLB_1G_MISS 0x8
> > +#define VTD_SIP_EVNT_SLPWC_L3_MISS 0x9
> > +#define VTD_SIP_EVNT_SLPWC_L4_MISS 0xa
> > +#define VTD_SIP_EVNT_RCC_MISS 0xb
> > +#define VTD_SIP_CNTR 0X50
> > +#define VTD_SIP_CNTR_EVNT_CNTR GENMASK_ULL(47, 0)
> > +#define VTD_SIP_CNTR_EVNT GENMASK_ULL(63, 60)
> > +
> > +#define PERF_TIMEOUT 30
> > +
> > +#define PERF_MAX_PORT_NUM 1
> > +
> > +/**
> > + * struct fme_perf_priv - priv data structure for fme perf driver
> > + *
> > + * @dev: parent device.
> > + * @ioaddr: mapped base address of mmio region.
> > + * @pmu: pmu data structure for fme perf counters.
> > + * @id: id of this fme performance report private feature.
> > + * @fab_users: current user number on fabric counters.
> > + * @fab_port_id: used to indicate current working mode of fabric counters.
> > + * @fab_lock: lock to protect fabric counters working mode.
> > + * @events_group: events attribute group for fme perf pmu.
> > + * @attr_groups: attribute groups for fme perf pmu.
> > + */
> > +struct fme_perf_priv {
> > + struct device *dev;
> > + void __iomem *ioaddr;
> > + struct pmu pmu;
> > + u64 id;
> > +
> > + u32 fab_users;
> > + u32 fab_port_id;
> > + spinlock_t fab_lock;
> > +
> > + struct attribute_group events_group;
> > + const struct attribute_group *attr_groups[4];
> > +};
> > +
> > +/**
> > + * struct fme_perf_event_attr - fme perf event attribute
> > + *
> > + * @attr: device attribute of fme perf event.
> > + * @event_id: id of fme perf event.
> > + * @event_type: type of fme perf event.
> > + * @is_port_event: indicate if this is a port based event.
> > + * @data: private data for fme perf event.
> > + */
> > +struct fme_perf_event_attr {
> > + struct device_attribute attr;
> > + u32 event_id;
> > + u32 event_type;
> > + bool is_port_event;
> > + u64 data;
> > +};
> > +
> > +/**
> > + * struct fme_perf_event_ops - callbacks for fme perf events
> > + *
> > + * @event_init: callback invoked during event init.
> > + * @event_destroy: callback invoked during event destroy.
> > + * @read_counter: callback to read hardware counters.
> > + */
> > +struct fme_perf_event_ops {
> > + int (*event_init)(struct fme_perf_priv *priv, u32 event,
> > + u32 port_id, u64 data);
> > + void (*event_destroy)(struct fme_perf_priv *priv, u32 event,
> > + u32 port_id, u64 data);
> > + u64 (*read_counter)(struct fme_perf_priv *priv, u32 event,
> > + u32 port_id, u64 data);
> > +};
> > +
> > +/**
> > + * struct fme_perf_event_group - fme perf groups
> > + *
> > + * @ev_attrs: fme perf event attributes.
> > + * @num: events number in this group.
> > + * @ops: same callbacks shared by all fme perf events in this group.
> > + */
> > +struct fme_perf_event_group {
> > + struct fme_perf_event_attr *ev_attrs;
> > + unsigned int num;
> > + struct fme_perf_event_ops *ops;
> > +};
> > +
> > +#define to_fme_perf_priv(_pmu) container_of(_pmu, struct fme_perf_priv, pmu)
> > +
> > +static cpumask_t fme_perf_cpumask = CPU_MASK_CPU0;
> > +
> > +static ssize_t cpumask_show(struct device *dev,
> > + struct device_attribute *attr, char *buf)
> > +{
> > + return cpumap_print_to_pagebuf(true, buf, &fme_perf_cpumask);
> > +}
> > +static DEVICE_ATTR_RO(cpumask);
> > +
> > +static struct attribute *fme_perf_cpumask_attrs[] = {
> > + &dev_attr_cpumask.attr,
> > + NULL,
> > +};
> > +
> > +static struct attribute_group fme_perf_cpumask_group = {
> > + .attrs = fme_perf_cpumask_attrs,
> > +};
> > +
> > +#define FME_EVENT_MASK GENMASK_ULL(11, 0)
> > +#define FME_EVTYPE_MASK GENMASK_ULL(15, 12)
> > +#define FME_EVTYPE_BASIC 0
> > +#define FME_EVTYPE_CACHE 1
> > +#define FME_EVTYPE_FABRIC 2
> > +#define FME_EVTYPE_VTD 3
> > +#define FME_EVTYPE_VTD_SIP 4
> > +#define FME_EVTYPE_MAX FME_EVTYPE_VTD_SIP
> > +#define FME_PORTID_MASK GENMASK_ULL(23, 16)
> > +#define FME_PORTID_ROOT (0xffU)
> > +
> > +PMU_FORMAT_ATTR(event, "config:0-11");
> > +PMU_FORMAT_ATTR(evtype, "config:12-15");
> > +PMU_FORMAT_ATTR(portid, "config:16-23");
> > +
> > +static struct attribute *fme_perf_format_attrs[] = {
> > + &format_attr_event.attr,
> > + &format_attr_evtype.attr,
> > + &format_attr_portid.attr,
> > + NULL,
> > +};
> > +
> > +static struct attribute_group fme_perf_format_group = {
> > + .name = "format",
> > + .attrs = fme_perf_format_attrs,
> > +};
>
> No Documentation/ABI/ entries for these sysfs files?
Hi Greg,
Thanks for the review.
I think those sysfs groups are all common ones to pmu, actually group
"events" and "format" are covered by these two ABI docs
Documentation/ABI/testing/sysfs-bus-event_source-devices-events
Documentation/ABI/testing/sysfs-bus-event_source-devices-format
For cpumask, i believe it's a common sysfs interface too, almost everybody
uses it (e.g. drivers/perf/*, and also perf tool). So we didn't introduce
a new ABI doc for these common ones.
As you see in this patchset, we add some descriptions in fpga/dfl.txt
doc file, it's following the same way as other Documentation/perf/*, as
we think it would help, and may be easier for FPGA user to find it.
Thanks
Hao
>
> thanks,
>
> greg k-h
^ permalink raw reply
* Re: [PATCH v3 1/5] mm: introduce MADV_COLD
From: Minchan Kim @ 2019-06-27 23:56 UTC (permalink / raw)
To: Michal Hocko
Cc: Dave Hansen, Andrew Morton, linux-mm, LKML, linux-api,
Johannes Weiner, Tim Murray, Joel Fernandes, Suren Baghdasaryan,
Daniel Colascione, Shakeel Butt, Sonny Rao, oleksandr, hdanton,
lizeb, Kirill A . Shutemov
In-Reply-To: <20190627145302.GC5303@dhcp22.suse.cz>
On Thu, Jun 27, 2019 at 04:53:02PM +0200, Michal Hocko wrote:
> On Thu 27-06-19 07:36:50, Dave Hansen wrote:
> [...]
> > For MADV_COLD, if we defined it like this, I think we could use it for
> > both purposes (demotion and LRU movement):
> >
> > Pages in the specified regions will be treated as less-recently-
> > accessed compared to pages in the system with similar access
> > frequencies. In contrast to MADV_DONTNEED, the contents of the
>
> you meant s@MADV_DONTNEED@MADV_FREE@ I suppose
Right, MADV_FREE is more proper because it's aging related.
>
> > region are preserved.
> >
> > It would be nice not to talk about reclaim at all since we're not
> > promising reclaim per se.
Your suggestion doesn't expose any implementation detail and could meet your
needs later. I'm okay. I will change it if others are not against of it.
Thanks, Dave.
^ permalink raw reply
* Re: [PATCH v3 1/5] mm: introduce MADV_COLD
From: Minchan Kim @ 2019-06-27 23:46 UTC (permalink / raw)
To: Dave Hansen
Cc: Andrew Morton, linux-mm, LKML, linux-api, Michal Hocko,
Johannes Weiner, Tim Murray, Joel Fernandes, Suren Baghdasaryan,
Daniel Colascione, Shakeel Butt, Sonny Rao, oleksandr, hdanton,
lizeb, Kirill A . Shutemov
In-Reply-To: <343599f9-3d99-b74f-1732-368e584fa5ef@intel.com>
On Thu, Jun 27, 2019 at 06:13:36AM -0700, Dave Hansen wrote:
> On 6/27/19 4:54 AM, Minchan Kim wrote:
> > This patch introduces the new MADV_COLD hint to madvise(2) syscall.
> > MADV_COLD can be used by a process to mark a memory range as not expected
> > to be used in the near future. The hint can help kernel in deciding which
> > pages to evict early during memory pressure.
> >
> > It works for every LRU pages like MADV_[DONTNEED|FREE]. IOW, It moves
> >
> > active file page -> inactive file LRU
> > active anon page -> inacdtive anon LRU
>
> Is the LRU behavior part of the interface or the implementation?
It's a just implementation. What user should expect with this API is they just
informs to the kernel "this memory in the regions wouldn't access in the near
future" so how kernel will handle memory in there is up to the kernel.
>
> I ask because we've got something in between tossing something down the
> LRU and swapping it: page migration. Specifically, on a system with
> slower memory media (like persistent memory) we just migrate a page
> instead of discarding it at reclaim:
>
> > https://lore.kernel.org/linux-mm/20190321200157.29678-4-keith.busch@intel.com/
>
> So let's say I have a page I want to evict from DRAM to the next slower
> tier of memory. Do I use MADV_COLD or MADV_PAGEOUT? If the LRU
> behavior is part of the interface itself, then MADV_COLD doesn't work.
IMHO, if it's one of storage in the memory hierarchy, that shouldn't be transparent
for the user? What I meant is VM moves inactive pages to the persistent memory
before the reclaiming. IOW, VM would have one more level LRU or extened inactive
LRU to cover the persistent memory.
>
> Do you think we'll need a third MADV_ flag for our automatic migration
> behavior? MADV_REALLYCOLD? MADV_MIGRATEOUT?
I believe it depends on how we abstract the persistent memory of cache hierarchy.
If we abstract it as diffrent storage with DRAM, manybe, that should be part of
other syscall like like move_pages.
If we abstract it as part of DRAM, that should be part of additional LRU
or extended inactive LRU.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox