From: Luis Chamberlain <mcgrof@kernel.org>

The kernel power management now supports allowing the VFS

to handle filesystem freezing freezes and thawing. Take advantage

of that and remove the kthread freezing. 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.

The filesystem therefore is in charge of properly dealing with

quiescing of the filesystem through its callbacks if it thinks

it knows better than how the VFS handles it.

The following Coccinelle rule was used as to remove the now superfluous

freezer calls:

make coccicheck MODE=patch SPFLAGS="--in-place --no-show-diff" COCCI=./fs-freeze-cleanup.cocci M=fs/ext4

virtual patch

@ remove_set_freezable @

expression time;

statement S, S2;

expression task, current;

@@

(

- set_freezable();

|

- if (try_to_freeze())

- continue;

|

- try_to_freeze();

|

- freezable_schedule();

+ schedule();

|

- freezable_schedule_timeout(time);

+ schedule_timeout(time);

|

- if (freezing(task)) { S }

|

- if (freezing(task)) { S }

- else

     { S2 }

|

- freezing(current)

)

@ remove_wq_freezable @

expression WQ_E, WQ_ARG1, WQ_ARG2, WQ_ARG3, WQ_ARG4;

identifier fs_wq_fn;

@@

(

WQ_E = alloc_workqueue(WQ_ARG1,

- WQ_ARG2 | WQ_FREEZABLE,

+ WQ_ARG2,

             ...);

|

WQ_E = alloc_workqueue(WQ_ARG1,

- WQ_ARG2 | WQ_FREEZABLE | WQ_ARG3,

+ WQ_ARG2 | WQ_ARG3,

             ...);

|

WQ_E = alloc_workqueue(WQ_ARG1,

- WQ_ARG2 | WQ_ARG3 | WQ_FREEZABLE,

+ WQ_ARG2 | WQ_ARG3,

             ...);

|

WQ_E = alloc_workqueue(WQ_ARG1,

- WQ_ARG2 | WQ_ARG3 | WQ_FREEZABLE | WQ_ARG4,

+ WQ_ARG2 | WQ_ARG3 | WQ_ARG4,

             ...);

|

     WQ_E =

- WQ_ARG1 | WQ_FREEZABLE

+ WQ_ARG1

|

     WQ_E =

- WQ_ARG1 | WQ_FREEZABLE | WQ_ARG3

+ WQ_ARG1 | WQ_ARG3

|

fs_wq_fn(

- WQ_FREEZABLE | WQ_ARG2 | WQ_ARG3

+ WQ_ARG2 | WQ_ARG3

)

|

fs_wq_fn(

- WQ_FREEZABLE | WQ_ARG2

+ WQ_ARG2

)

|

fs_wq_fn(

- WQ_FREEZABLE

+ 0

)

)

@ add_auto_flag @

expression E1;

identifier fs_type;

@@

struct file_system_type fs_type = {

    .fs_flags = E1

+ | FS_AUTOFREEZE

    ,

};

Generated-by: Coccinelle SmPL

Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>

Link: https://lore.kernel.org/r/20250326112220.1988619-5-mcgrof@kernel.org

Signed-off-by: Christian Brauner <brauner@kernel.org>

---

fs/ext4/mballoc.c | 2 +-

fs/ext4/super.c | 3 ---

2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c

index XXXXXXX..XXXXXXX 100644

--- a/fs/ext4/mballoc.c

+++ b/fs/ext4/mballoc.c

@@ -XXX,XX +XXX,XX @@ static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb,

static bool ext4_trim_interrupted(void)

{

-    return fatal_signal_pending(current) || freezing(current);

+    return fatal_signal_pending(current);

}

static int ext4_try_to_trim_range(struct super_block *sb,

diff --git a/fs/ext4/super.c b/fs/ext4/super.c

index XXXXXXX..XXXXXXX 100644

--- a/fs/ext4/super.c

+++ b/fs/ext4/super.c

@@ -XXX,XX +XXX,XX @@ static int ext4_lazyinit_thread(void *arg)

    unsigned long next_wakeup, cur;

    BUG_ON(NULL == eli);

-    set_freezable();

cont_thread:

    while (true) {

@@ -XXX,XX +XXX,XX @@ static int ext4_lazyinit_thread(void *arg)

        }

        mutex_unlock(&eli->li_list_mtx);

-        try_to_freeze();

-

        cur = jiffies;

        if (!next_wakeup_initialized || time_after_eq(cur, next_wakeup)) {

            cond_resched();

--

2.47.2

From: Luis Chamberlain <mcgrof@kernel.org>

The kernel power management now supports allowing the VFS

to handle filesystem freezing freezes and thawing. Take advantage

of that and remove the kthread freezing. 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.

The filesystem therefore is in charge of properly dealing with

quiescing of the filesystem through its callbacks if it thinks

it knows better than how the VFS handles it.

The following Coccinelle rule was used as to remove the now superfluous

freezer calls:

make coccicheck MODE=patch SPFLAGS="--in-place --no-show-diff" COCCI=./fs-freeze-cleanup.cocci M=fs/btrfs

virtual patch

@ remove_set_freezable @

expression time;

statement S, S2;

expression task, current;

@@

(

- set_freezable();

|

- if (try_to_freeze())

- continue;

|

- try_to_freeze();

|

- freezable_schedule();

+ schedule();

|

- freezable_schedule_timeout(time);

+ schedule_timeout(time);

|

- if (freezing(task)) { S }

|

- if (freezing(task)) { S }

- else

     { S2 }

|

- freezing(current)

)

@ remove_wq_freezable @

expression WQ_E, WQ_ARG1, WQ_ARG2, WQ_ARG3, WQ_ARG4;

identifier fs_wq_fn;

@@

(

WQ_E = alloc_workqueue(WQ_ARG1,

- WQ_ARG2 | WQ_FREEZABLE,

+ WQ_ARG2,

             ...);

|

WQ_E = alloc_workqueue(WQ_ARG1,

- WQ_ARG2 | WQ_FREEZABLE | WQ_ARG3,

+ WQ_ARG2 | WQ_ARG3,

             ...);

|

WQ_E = alloc_workqueue(WQ_ARG1,

- WQ_ARG2 | WQ_ARG3 | WQ_FREEZABLE,

+ WQ_ARG2 | WQ_ARG3,

             ...);

|

WQ_E = alloc_workqueue(WQ_ARG1,

- WQ_ARG2 | WQ_ARG3 | WQ_FREEZABLE | WQ_ARG4,

+ WQ_ARG2 | WQ_ARG3 | WQ_ARG4,

             ...);

|

     WQ_E =

- WQ_ARG1 | WQ_FREEZABLE

+ WQ_ARG1

|

     WQ_E =

- WQ_ARG1 | WQ_FREEZABLE | WQ_ARG3

+ WQ_ARG1 | WQ_ARG3

|

fs_wq_fn(

- WQ_FREEZABLE | WQ_ARG2 | WQ_ARG3

+ WQ_ARG2 | WQ_ARG3

)

|

fs_wq_fn(

- WQ_FREEZABLE | WQ_ARG2

+ WQ_ARG2

)

|

fs_wq_fn(

- WQ_FREEZABLE

+ 0

)

)

@ add_auto_flag @

expression E1;

identifier fs_type;

@@

struct file_system_type fs_type = {

    .fs_flags = E1

+ | FS_AUTOFREEZE

    ,

};

Generated-by: Coccinelle SmPL

Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>

Link: https://lore.kernel.org/r/20250326112220.1988619-6-mcgrof@kernel.org

Signed-off-by: Christian Brauner <brauner@kernel.org>

---

fs/btrfs/disk-io.c | 4 ++--

fs/btrfs/scrub.c | 2 +-

2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c

index XXXXXXX..XXXXXXX 100644

--- a/fs/btrfs/disk-io.c

+++ b/fs/btrfs/disk-io.c

@@ -XXX,XX +XXX,XX @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)

static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info)

{

    u32 max_active = fs_info->thread_pool_size;

-    unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;

-    unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE;

+    unsigned int flags = WQ_MEM_RECLAIM | WQ_UNBOUND;

+    unsigned int ordered_flags = WQ_MEM_RECLAIM;

    fs_info->workers =

        btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16);

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c

index XXXXXXX..XXXXXXX 100644

--- a/fs/btrfs/scrub.c

+++ b/fs/btrfs/scrub.c

@@ -XXX,XX +XXX,XX @@ static void scrub_workers_put(struct btrfs_fs_info *fs_info)

static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info)

{

    struct workqueue_struct *scrub_workers = NULL;

-    unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND;

+    unsigned int flags = WQ_UNBOUND;

    int max_active = fs_info->thread_pool_size;

    int ret = -ENOMEM;

--

2.47.2