The original thread is at https://lkml.org/lkml/2016/11/2/294
The branch is available at https://github.com/deepa-hub/vfs.git refs/heads/vfs_timestamp_policy
Changes since v1: * return EROFS on mount errors * fix mtime copy/paste error in utimes
Deepa Dinamani (6): vfs: Add file timestamp range support vfs: Add checks for filesystem timestamp limits afs: Add time limits in the super block ext4: Initialize timestamps limits vfs: Add timestamp_truncate() api utimes: Clamp the timestamps before update
fs/afs/super.c | 2 ++ fs/ext4/ext4.h | 4 ++++ fs/ext4/super.c | 7 ++++++- fs/inode.c | 37 ++++++++++++++++++++++++++++++++++++- fs/internal.h | 2 ++ fs/libfs.c | 4 ++++ fs/namespace.c | 12 ++++++++++++ fs/super.c | 9 +++++++++ fs/utimes.c | 17 +++++++++++++---- include/linux/fs.h | 4 ++++ include/linux/time64.h | 6 ++++++ include/uapi/linux/fs.h | 6 +++++- kernel/sysctl.c | 7 +++++++ 13 files changed, 110 insertions(+), 7 deletions(-)
Add fields to the superblock to track the min and max timestamps supported by filesystems.
Initially, when a superblock is allocated, initialize it to the max and min values the fields can hold. Individual filesystems override these to match their actual limits.
Pseudo filesystems are assumed to always support the min and max allowable values for the fields.
Note that the time ranges are save in type time64_t rather than time_t. This is required because if we save ranges in time_t then we would not be able to save timestamp ranges for files that support timestamps beyond y2038.
Signed-off-by: Deepa Dinamani deepa.kernel@gmail.com --- fs/libfs.c | 4 ++++ fs/super.c | 2 ++ include/linux/fs.h | 3 +++ include/linux/time64.h | 2 ++ 4 files changed, 11 insertions(+)
diff --git a/fs/libfs.c b/fs/libfs.c index 48826d4..f03c904 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -256,6 +256,8 @@ struct dentry *mount_pseudo_xattr(struct file_system_type *fs_type, char *name, s->s_op = ops ? ops : &simple_super_operations; s->s_xattr = xattr; s->s_time_gran = 1; + s->s_time_min = TIME64_MIN; + s->s_time_max = TIME64_MAX; root = new_inode(s); if (!root) goto Enomem; @@ -515,6 +517,8 @@ int simple_fill_super(struct super_block *s, unsigned long magic, s->s_magic = magic; s->s_op = &simple_super_operations; s->s_time_gran = 1; + s->s_time_min = TIME64_MIN; + s->s_time_max = TIME64_MAX;
inode = new_inode(s); if (!inode) diff --git a/fs/super.c b/fs/super.c index c183835..27c973e 100644 --- a/fs/super.c +++ b/fs/super.c @@ -248,6 +248,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_maxbytes = MAX_NON_LFS; s->s_op = &default_op; s->s_time_gran = 1000000000; + s->s_time_min = TIME64_MIN; + s->s_time_max = TIME64_MAX; s->cleancache_poolid = CLEANCACHE_NO_POOL;
s->s_shrink.seeks = DEFAULT_SEEKS; diff --git a/include/linux/fs.h b/include/linux/fs.h index 03a5a39..8eba822 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1329,6 +1329,9 @@ struct super_block { /* Granularity of c/m/atime in ns. Cannot be worse than a second */ u32 s_time_gran; + /* Time limits for c/m/atime in seconds. */ + time64_t s_time_min; + time64_t s_time_max;
/* * The next field is for VFS *only*. No filesystems have any business diff --git a/include/linux/time64.h b/include/linux/time64.h index 980c71b..25433b18 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -38,6 +38,8 @@ struct itimerspec64 {
/* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) +#define TIME64_MIN (-TIME64_MAX - 1) + #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC)
Allow read only mounts for filesystems that do not have maximum timestamps beyond the y2038 expiry timestamp.
Also, allow a sysctl override to all such filesystems to be mounted with write permissions.
Alternatively, a mount option can be created to allow or disallow range check based clamps and the least max timestamp supported.
If we take the sysctl approach, then the plan is to also add a boot param to support initial override of these checks without recompilation.
Suggested-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Deepa Dinamani deepa.kernel@gmail.com --- fs/inode.c | 5 +++++ fs/internal.h | 2 ++ fs/namespace.c | 12 ++++++++++++ fs/super.c | 7 +++++++ include/linux/fs.h | 1 + include/linux/time64.h | 4 ++++ include/uapi/linux/fs.h | 6 +++++- kernel/sysctl.c | 7 +++++++ 8 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/fs/inode.c b/fs/inode.c index 88110fd..7b2b78d 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -75,6 +75,11 @@ static DEFINE_PER_CPU(unsigned long, nr_unused);
static struct kmem_cache *inode_cachep __read_mostly;
+struct vfs_max_timestamp_check timestamp_check = { + .timestamp_supported = Y2038_EXPIRY_TIMESTAMP, + .check_on = 1, +}; + static long get_nr_inodes(void) { int i; diff --git a/fs/internal.h b/fs/internal.h index f4da334..5a144a8 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -67,6 +67,8 @@ extern int finish_automount(struct vfsmount *, struct path *);
extern int sb_prepare_remount_readonly(struct super_block *);
+extern bool sb_file_times_updatable(struct super_block *sb); + extern void __init mnt_init(void);
extern int __mnt_want_write(struct vfsmount *); diff --git a/fs/namespace.c b/fs/namespace.c index 5ef9618..27eab32 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -543,6 +543,18 @@ static void __mnt_unmake_readonly(struct mount *mnt) unlock_mount_hash(); }
+bool sb_file_times_updatable(struct super_block *sb) +{ + + if (!timestamp_check.check_on) + return true; + + if (sb->s_time_max > timestamp_check.timestamp_supported) + return true; + + return false; +} + int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; diff --git a/fs/super.c b/fs/super.c index 27c973e..d21327f 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1199,6 +1199,13 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to " "negative value (%lld)\n", type->name, sb->s_maxbytes);
+ if (!(sb->s_flags & MS_RDONLY) && !sb_file_times_updatable(sb)) { + WARN(1, "File times cannot be updated on the filesystem.\n"); + WARN(1, "Retry mounting the filesystem readonly.\n"); + error = -EROFS; + goto out_sb; + } + up_write(&sb->s_umount); free_secdata(secdata); return root; diff --git a/include/linux/fs.h b/include/linux/fs.h index 8eba822..b80d1e2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -68,6 +68,7 @@ extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; +extern struct vfs_max_timestamp_check timestamp_check;
struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, diff --git a/include/linux/time64.h b/include/linux/time64.h index 25433b18..906e0b3 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -43,6 +43,10 @@ struct itimerspec64 { #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC)
+/* Timestamps on boundary */ +#define Y2038_EXPIRY_TIMESTAMP S32_MAX /* 2147483647 */ +#define Y2106_EXPIRY_TIMESTAMP U32_MAX /* 4294967295 */ + #if __BITS_PER_LONG == 64
static inline struct timespec timespec64_to_timespec(const struct timespec64 ts64) diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index c1d11df..07d225c 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -91,6 +91,11 @@ struct files_stat_struct { unsigned long max_files; /* tunable */ };
+struct vfs_max_timestamp_check { + time64_t timestamp_supported; + int check_on; +}; + struct inodes_stat_t { long nr_inodes; long nr_unused; @@ -100,7 +105,6 @@ struct inodes_stat_t {
#define NR_FILE 8192 /* this can well be larger on a larger system */
- /* * These are the fs-independent mount-flags: up to 32 flags are supported */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 1475d25..b6030d5 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1667,6 +1667,13 @@ static struct ctl_table fs_table[] = { .proc_handler = proc_doulongvec_minmax, }, { + .procname = "fs-timestamp-check-on", + .data = ×tamp_check.check_on, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "nr_open", .data = &sysctl_nr_open, .maxlen = sizeof(unsigned int),
Note that all the filesystems that have such simple limits will be initialized in the same patch.
Signed-off-by: Deepa Dinamani deepa.kernel@gmail.com Cc: linux-afs@lists.infradead.org --- fs/afs/super.c | 2 ++ 1 file changed, 2 insertions(+)
diff --git a/fs/afs/super.c b/fs/afs/super.c index fbdb022..ab00434 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -321,6 +321,8 @@ static int afs_fill_super(struct super_block *sb, sb->s_op = &afs_super_ops; sb->s_bdi = &as->volume->bdi; strlcpy(sb->s_id, as->volume->vlocation->vldb.name, sizeof(sb->s_id)); + sb->s_time_max = Y2106_EXPIRY_TIMESTAMP; + sb->s_time_min = 0;
/* allocate the root inode and dentry */ fid.vid = as->volume->vid;
ext4 has different overflow limits for max filesystem timestamps based on the extra bytes available.
Signed-off-by: Deepa Dinamani deepa.kernel@gmail.com Cc: "Theodore Ts'o" tytso@mit.edu Cc: Andreas Dilger adilger.kernel@dilger.ca Cc: linux-ext4@vger.kernel.org --- fs/ext4/ext4.h | 4 ++++ fs/ext4/super.c | 7 ++++++- 2 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index aff204f..e15c081 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1636,6 +1636,10 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
#define EXT4_GOOD_OLD_INODE_SIZE 128
+#define EXT4_EXTRA_TIMESTAMP_MAX (((s64)1 << 34) - 1 + S32_MIN) +#define EXT4_NON_EXTRA_TIMESTAMP_MAX Y2038_EXPIRY_TIMESTAMP +#define EXT4_TIMESTAMP_MIN S32_MIN + /* * Feature set definitions */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 72b459d..0519c52 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3672,8 +3672,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_inode_size); goto failed_mount; } - if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) + if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2); + sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX; + } else + sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX; + + sb->s_time_min = EXT4_TIMESTAMP_MIN; }
sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
timespec_trunc() function is used to truncate a filesystem timestamp to the right granularity. But, the function does not clamp tv_sec part of the timestamps according to the filesystem timestamp limits.
Also, timespec_trunc() is exclusively used for filesystem timestamps. Move the api to be part of vfs.
The replacement api: timestamp_truncate() also alters the signature of the function to accommodate filesystem timestamp clamping according to flesystem limits.
Note that clamp_t macro is used for clamping here as vfs is not yet using struct timespec64 internally. This is only for compilation purposes. The actual patch can only be merged after the vfs is transitioned to use timespec64 for correct operation of clamp macro. At which point, clamp_t() will be replaced by clamp().
Signed-off-by: Deepa Dinamani deepa.kernel@gmail.com --- fs/inode.c | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-)
diff --git a/fs/inode.c b/fs/inode.c index 7b2b78d..f9285f2 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2106,6 +2106,36 @@ void inode_nohighmem(struct inode *inode) EXPORT_SYMBOL(inode_nohighmem);
/** + * fs_timespec_trunc - Truncate timespec to a granularity + * @t: Timespec + * @gran: Granularity in ns. + * + * Truncate a timespec to a granularity. Always rounds down. gran must + * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). + */ +struct timespec timestamp_truncate(struct timespec t, struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + unsigned int gran = sb->s_time_gran; + + t.tv_sec = clamp_t(time64_t, t.tv_sec, sb->s_time_min, sb->s_time_max); + + /* Avoid division in the common cases 1 ns and 1 s. */ + if (gran == 1) { + /* nothing */ + } else if (gran == NSEC_PER_SEC) { + t.tv_nsec = 0; + } else if (gran > 1 && gran < NSEC_PER_SEC) { + t.tv_nsec -= t.tv_nsec % gran; + } else { + WARN(1, "illegal file time granularity: %u", gran); + } + return t; +} +EXPORT_SYMBOL(timestamp_truncate); + + +/** * current_time - Return FS time * @inode: inode. * @@ -2124,6 +2154,6 @@ struct timespec current_time(struct inode *inode) return now; }
- return timespec_trunc(now, inode->i_sb->s_time_gran); + return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time);
POSIX.1 section for futimens, utimensat and utimes says: The file's relevant timestamp shall be set to the greatest value supported by the file system that is not greater than the specified time.
Clamp the timestamps accordingly before assignment.
Note that clamp_t macro is used for clamping here as vfs is not yet using struct timespec64 internally. This is for compilation purposes only. The actual patch can only be merged only after vfs is transitioned to use timespec64 for correct operation of clamp macro. At which point, clamp_t() will be replaced by clamp().
Signed-off-by: Deepa Dinamani deepa.kernel@gmail.com --- fs/utimes.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-)
diff --git a/fs/utimes.c b/fs/utimes.c index 22307cd..4378378 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -53,6 +53,7 @@ static int utimes_common(struct path *path, struct timespec *times) int error; struct iattr newattrs; struct inode *inode = path->dentry->d_inode; + struct super_block *sb = inode->i_sb; struct inode *delegated_inode = NULL;
error = mnt_want_write(path->mnt); @@ -68,16 +69,24 @@ static int utimes_common(struct path *path, struct timespec *times) if (times[0].tv_nsec == UTIME_OMIT) newattrs.ia_valid &= ~ATTR_ATIME; else if (times[0].tv_nsec != UTIME_NOW) { - newattrs.ia_atime.tv_sec = times[0].tv_sec; - newattrs.ia_atime.tv_nsec = times[0].tv_nsec; + newattrs.ia_atime.tv_sec = + clamp_t(time64_t, times[0].tv_sec, sb->s_time_min, sb->s_time_max); + if (times[0].tv_sec >= sb->s_time_max) + newattrs.ia_atime.tv_nsec = 0; + else + newattrs.ia_atime.tv_nsec = times[0].tv_nsec; newattrs.ia_valid |= ATTR_ATIME_SET; }
if (times[1].tv_nsec == UTIME_OMIT) newattrs.ia_valid &= ~ATTR_MTIME; else if (times[1].tv_nsec != UTIME_NOW) { - newattrs.ia_mtime.tv_sec = times[1].tv_sec; - newattrs.ia_mtime.tv_nsec = times[1].tv_nsec; + newattrs.ia_mtime.tv_sec = + clamp_t(time64_t, times[1].tv_sec, sb->s_time_min, sb->s_time_max); + if (times[1].tv_sec >= sb->s_time_max) + newattrs.ia_mtime.tv_nsec = 0; + else + newattrs.ia_mtime.tv_nsec = times[1].tv_nsec; newattrs.ia_valid |= ATTR_MTIME_SET; } /*
-
Deepa Dinamani