Merge tag 'vfs-6.16-rc1.super' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs freezing updates from Christian Brauner:
 "This contains various filesystem freezing related work for this cycle:

   - Allow the power subsystem to support filesystem freeze for suspend
     and hibernate.

     Now all the pieces are in place to actually allow the power
     subsystem to freeze/thaw filesystems during suspend/resume.
     Filesystems are only frozen and thawed if the power subsystem does
     actually own the freeze.

     If the filesystem is already frozen by the time we've frozen all
     userspace processes we don't care to freeze it again. That's
     userspace's job once the process resumes. We only actually freeze
     filesystems if we absolutely have to and we ignore other failures
     to freeze.

     We could bubble up errors and fail suspend/resume if the error
     isn't EBUSY (aka it's already frozen) but I don't think that this
     is worth it. Filesystem freezing during suspend/resume is
     best-effort. If the user has 500 ext4 filesystems mounted and 4
     fail to freeze for whatever reason then we simply skip them.

     What we have now is already a big improvement and let's see how we
     fare with it before making our lives even harder (and uglier) than
     we have to.

   - Allow efivars to support freeze and thaw

     Allow efivarfs to partake to resync variable state during system
     hibernation and suspend. Add freeze/thaw support.

     This is a pretty straightforward implementation. We simply add
     regular freeze/thaw support for both userspace and the kernel.
     efivars is the first pseudofilesystem that adds support for
     filesystem freezing and thawing.

     The simplicity comes from the fact that we simply always resync
     variable state after efivarfs has been frozen. It doesn't matter
     whether that's because of suspend, userspace initiated freeze or
     hibernation. Efivars is simple enough that it doesn't matter that
     we walk all dentries. There are no directories and there aren't
     insane amounts of entries and both freeze/thaw are already
     heavy-handed operations. If userspace initiated a freeze/thaw cycle
     they would need CAP_SYS_ADMIN in the initial user namespace (as
     that's where efivarfs is mounted) so it can't be triggered by
     random userspace. IOW, we really really don't care"

* tag 'vfs-6.16-rc1.super' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  f2fs: fix freezing filesystem during resize
  kernfs: add warning about implementing freeze/thaw
  efivarfs: support freeze/thaw
  power: freeze filesystems during suspend/resume
  libfs: export find_next_child()
  super: add filesystem freezing helpers for suspend and hibernate
  gfs2: pass through holder from the VFS for freeze/thaw
  super: use common iterator (Part 2)
  super: use a common iterator (Part 1)
  super: skip dying superblocks early
  super: simplify user_get_super()
  super: remove pointless s_root checks
  fs: allow all writers to be frozen
  locking/percpu-rwsem: add freezable alternative to down_read

5 files changed, 65 insertions, 6 deletions

diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index d6964fc29f51..ef234469baac 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -138,7 +138,8 @@ static int percpu_rwsem_wake_function(struct wait_queue_entry *wq_entry,
 	return !reader; /* wake (readers until) 1 writer */
 }
 
-static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
+static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader,
+			      bool freeze)
 {
 	DEFINE_WAIT_FUNC(wq_entry, percpu_rwsem_wake_function);
 	bool wait;
@@ -156,7 +157,8 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
 	spin_unlock_irq(&sem->waiters.lock);
 
 	while (wait) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE |
+				  (freeze ? TASK_FREEZABLE : 0));
 		if (!smp_load_acquire(&wq_entry.private))
 			break;
 		schedule();
@@ -164,7 +166,8 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
 	__set_current_state(TASK_RUNNING);
 }
 
-bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
+bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try,
+				bool freeze)
 {
 	if (__percpu_down_read_trylock(sem))
 		return true;
@@ -174,7 +177,7 @@ bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
 
 	trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_READ);
 	preempt_enable();
-	percpu_rwsem_wait(sem, /* .reader = */ true);
+	percpu_rwsem_wait(sem, /* .reader = */ true, freeze);
 	preempt_disable();
 	trace_contention_end(sem, 0);
 
@@ -237,7 +240,7 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 	 */
 	if (!__percpu_down_write_trylock(sem)) {
 		trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE);
-		percpu_rwsem_wait(sem, /* .reader = */ false);
+		percpu_rwsem_wait(sem, /* .reader = */ false, false);
 		contended = true;
 	}
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 23c0f4e6cb2f..338c9917d4ee 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -778,6 +778,8 @@ int hibernate(void)
 		goto Restore;
 
 	ksys_sync_helper();
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
 
 	error = freeze_processes();
 	if (error)
@@ -846,6 +848,7 @@ int hibernate(void)
 	/* Don't bother checking whether freezer_test_done is true */
 	freezer_test_done = false;
  Exit:
+	filesystems_thaw();
 	pm_notifier_call_chain(PM_POST_HIBERNATION);
  Restore:
 	pm_restore_console();
@@ -882,6 +885,9 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data)
 	if (error)
 		goto restore;
 
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
+
 	error = freeze_processes();
 	if (error)
 		goto exit;
@@ -941,6 +947,7 @@ thaw:
 	thaw_processes();
 
 exit:
+	filesystems_thaw();
 	pm_notifier_call_chain(PM_POST_HIBERNATION);
 
 restore:
@@ -1029,19 +1036,26 @@ static int software_resume(void)
 	if (error)
 		goto Restore;
 
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
+
 	pm_pr_dbg("Preparing processes for hibernation restore.\n");
 	error = freeze_processes();
-	if (error)
+	if (error) {
+		filesystems_thaw();
 		goto Close_Finish;
+	}
 
 	error = freeze_kernel_threads();
 	if (error) {
 		thaw_processes();
+		filesystems_thaw();
 		goto Close_Finish;
 	}
 
 	error = load_image_and_restore();
 	thaw_processes();
+	filesystems_thaw();
  Finish:
 	pm_notifier_call_chain(PM_POST_RESTORE);
  Restore:
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 6254814d4817..0b0e76324c43 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -962,6 +962,34 @@ power_attr(pm_freeze_timeout);
 
 #endif	/* CONFIG_FREEZER*/
 
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+bool filesystem_freeze_enabled = false;
+
+static ssize_t freeze_filesystems_show(struct kobject *kobj,
+				       struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", filesystem_freeze_enabled);
+}
+
+static ssize_t freeze_filesystems_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t n)
+{
+	unsigned long val;
+
+	if (kstrtoul(buf, 10, &val))
+		return -EINVAL;
+
+	if (val > 1)
+		return -EINVAL;
+
+	filesystem_freeze_enabled = !!val;
+	return n;
+}
+
+power_attr(freeze_filesystems);
+#endif /* CONFIG_SUSPEND || CONFIG_HIBERNATION */
+
 static struct attribute * g[] = {
 	&state_attr.attr,
 #ifdef CONFIG_PM_TRACE
@@ -992,6 +1020,9 @@ static struct attribute * g[] = {
 #ifdef CONFIG_FREEZER
 	&pm_freeze_timeout_attr.attr,
 #endif
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+	&freeze_filesystems_attr.attr,
+#endif
 	NULL,
 };
 
diff --git a/kernel/power/power.h b/kernel/power/power.h
index c352dea2f67b..2eb81662b8fa 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -18,6 +18,10 @@ struct swsusp_info {
 	unsigned long		size;
 } __aligned(PAGE_SIZE);
 
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+extern bool filesystem_freeze_enabled;
+#endif
+
 #ifdef CONFIG_HIBERNATION
 /* kernel/power/snapshot.c */
 extern void __init hibernate_reserved_size_init(void);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 8eaec4ab121d..76b141b9aac0 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -30,6 +30,7 @@
 #include <trace/events/power.h>
 #include <linux/compiler.h>
 #include <linux/moduleparam.h>
+#include <linux/fs.h>
 
 #include "power.h"
 
@@ -374,6 +375,8 @@ static int suspend_prepare(suspend_state_t state)
 	if (error)
 		goto Restore;
 
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
 	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
 	trace_suspend_resume(TPS("freeze_processes"), 0, false);
@@ -550,6 +553,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 static void suspend_finish(void)
 {
 	suspend_thaw_processes();
+	filesystems_thaw();
 	pm_notifier_call_chain(PM_POST_SUSPEND);
 	pm_restore_console();
 }
@@ -588,6 +592,8 @@ static int enter_state(suspend_state_t state)
 		ksys_sync_helper();
 		trace_suspend_resume(TPS("sync_filesystems"), 0, false);
 	}
+	if (filesystem_freeze_enabled)
+		filesystems_freeze();
 
 	pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]);
 	pm_suspend_clear_flags();
@@ -609,6 +615,7 @@ static int enter_state(suspend_state_t state)
 	pm_pr_dbg("Finishing wakeup.\n");
 	suspend_finish();
  Unlock:
+	filesystems_thaw();
 	mutex_unlock(&system_transition_mutex);
 	return error;
 }