On Fri 13-01-23 16:33:50, Luis Chamberlain wrote:
> Add support to automatically handle freezing and thawing filesystems
> during the kernel's suspend/resume cycle.
>
> This is needed so that we properly really stop IO in flight without
> races after userspace has been frozen. Without this we rely on
> kthread freezing and its semantics are loose and error prone.
> For instance, even though a kthread may use try_to_freeze() and end
> up being frozen we have no way of being sure that everything that
> has been spawned asynchronously from it (such as timers) have also
> been stopped as well.
>
> A long term advantage of also adding filesystem freeze / thawing
> supporting during suspend / hibernation is that long term we may
> be able to eventually drop the kernel's thread freezing completely
> as it was originally added to stop disk IO in flight as we hibernate
> or suspend.
>
> This does not remove the superflous freezer calls on all filesystems.
> Each filesystem must remove all the kthread freezer stuff and peg
> the fs_type flags as supporting auto-freezing with the FS_AUTOFREEZE
> flag.
>
> Subsequent patches remove the kthread freezer usage from each
> filesystem, one at a time to make all this work bisectable.
> Once all filesystems remove the usage of the kthread freezer we
> can remove the FS_AUTOFREEZE flag.
>
> Signed-off-by: Luis Chamberlain <mcgrof@xxxxxxxxxx>
Looks good to me. Feel free to add:
Reviewed-by: Jan Kara <jack@xxxxxxx>
Honza
> ---
> fs/super.c | 69 ++++++++++++++++++++++++++++++++++++++++++
> include/linux/fs.h | 14 +++++++++
> kernel/power/process.c | 15 ++++++++-
> 3 files changed, 97 insertions(+), 1 deletion(-)
>
> diff --git a/fs/super.c b/fs/super.c
> index 2f77fcb6e555..e8af4c8269ad 100644
> --- a/fs/super.c
> +++ b/fs/super.c
> @@ -1853,3 +1853,72 @@ int thaw_super(struct super_block *sb, bool usercall)
> return 0;
> }
> EXPORT_SYMBOL(thaw_super);
> +
> +#ifdef CONFIG_PM_SLEEP
> +static bool super_should_freeze(struct super_block *sb)
> +{
> + if (!(sb->s_type->fs_flags & FS_AUTOFREEZE))
> + return false;
> + /*
> + * We don't freeze virtual filesystems, we skip those filesystems with
> + * no backing device.
> + */
> + if (sb->s_bdi == &noop_backing_dev_info)
> + return false;
> +
> + return true;
> +}
> +
> +int fs_suspend_freeze_sb(struct super_block *sb, void *priv)
> +{
> + int error = 0;
> +
> + if (!grab_lock_super(sb)) {
> + pr_err("%s (%s): freezing failed to grab_super()\n",
> + sb->s_type->name, sb->s_id);
> + return -ENOTTY;
> + }
> +
> + if (!super_should_freeze(sb))
> + goto out;
> +
> + pr_info("%s (%s): freezing\n", sb->s_type->name, sb->s_id);
> +
> + error = freeze_super(sb, false);
> + if (!error)
> + lockdep_sb_freeze_release(sb);
> + else if (error != -EBUSY)
> + pr_notice("%s (%s): Unable to freeze, error=%d",
> + sb->s_type->name, sb->s_id, error);
> +
> +out:
> + deactivate_locked_super(sb);
> + return error;
> +}
> +
> +int fs_suspend_thaw_sb(struct super_block *sb, void *priv)
> +{
> + int error = 0;
> +
> + if (!grab_lock_super(sb)) {
> + pr_err("%s (%s): thawing failed to grab_super()\n",
> + sb->s_type->name, sb->s_id);
> + return -ENOTTY;
> + }
> +
> + if (!super_should_freeze(sb))
> + goto out;
> +
> + pr_info("%s (%s): thawing\n", sb->s_type->name, sb->s_id);
> +
> + error = thaw_super(sb, false);
> + if (error && error != -EBUSY)
> + pr_notice("%s (%s): Unable to unfreeze, error=%d",
> + sb->s_type->name, sb->s_id, error);
> +
> +out:
> + deactivate_locked_super(sb);
> + return error;
> +}
> +
> +#endif
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index f168e72f6ca1..e5bee359e804 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -2231,6 +2231,7 @@ struct file_system_type {
> #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */
> #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */
> #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
> +#define FS_AUTOFREEZE (1<<16) /* temporary as we phase kthread freezer out */
> int (*init_fs_context)(struct fs_context *);
> const struct fs_parameter_spec *parameters;
> struct dentry *(*mount) (struct file_system_type *, int,
> @@ -2306,6 +2307,19 @@ extern int user_statfs(const char __user *, struct kstatfs *);
> extern int fd_statfs(int, struct kstatfs *);
> extern int freeze_super(struct super_block *super, bool usercall);
> extern int thaw_super(struct super_block *super, bool usercall);
> +#ifdef CONFIG_PM_SLEEP
> +int fs_suspend_freeze_sb(struct super_block *sb, void *priv);
> +int fs_suspend_thaw_sb(struct super_block *sb, void *priv);
> +#else
> +static inline int fs_suspend_freeze_sb(struct super_block *sb, void *priv)
> +{
> + return 0;
> +}
> +static inline int fs_suspend_thaw_sb(struct super_block *sb, void *priv)
> +{
> + return 0;
> +}
> +#endif
> extern __printf(2, 3)
> int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
> extern int super_setup_bdi(struct super_block *sb);
> diff --git a/kernel/power/process.c b/kernel/power/process.c
> index 6c1c7e566d35..1dd6b0b6b4e5 100644
> --- a/kernel/power/process.c
> +++ b/kernel/power/process.c
> @@ -140,6 +140,16 @@ int freeze_processes(void)
>
> BUG_ON(in_atomic());
>
> + pr_info("Freezing filesystems ... ");
> + error = iterate_supers_reverse_excl(fs_suspend_freeze_sb, NULL);
> + if (error) {
> + pr_cont("failed\n");
> + iterate_supers_excl(fs_suspend_thaw_sb, NULL);
> + thaw_processes();
> + return error;
> + }
> + pr_cont("done.\n");
> +
> /*
> * Now that the whole userspace is frozen we need to disable
> * the OOM killer to disallow any further interference with
> @@ -149,8 +159,10 @@ int freeze_processes(void)
> if (!error && !oom_killer_disable(msecs_to_jiffies(freeze_timeout_msecs)))
> error = -EBUSY;
>
> - if (error)
> + if (error) {
> + iterate_supers_excl(fs_suspend_thaw_sb, NULL);
> thaw_processes();
> + }
> return error;
> }
>
> @@ -188,6 +200,7 @@ void thaw_processes(void)
> pm_nosig_freezing = false;
>
> oom_killer_enable();
> + iterate_supers_excl(fs_suspend_thaw_sb, NULL);
>
> pr_info("Restarting tasks ... ");
>
> --
> 2.35.1
>
--
Jan Kara <jack@xxxxxxxx>
SUSE Labs, CR
_______________________________________________
kexec mailing list
kexec@xxxxxxxxxxxxxxxxxxx
http://lists.infradead.org/mailman/listinfo/kexec
