freezer,sched: Rewrite core freezer logic

Rewrite the core freezer to behave better wrt thawing and be simpler
in general.

By replacing PF_FROZEN with TASK_FROZEN, a special block state, it is
ensured frozen tasks stay frozen until thawed and don't randomly wake
up early, as is currently possible.

As such, it does away with PF_FROZEN and PF_FREEZER_SKIP, freeing up
two PF_flags (yay!).

Specifically; the current scheme works a little like:

	freezer_do_not_count();
	schedule();
	freezer_count();

And either the task is blocked, or it lands in try_to_freezer()
through freezer_count(). Now, when it is blocked, the freezer
considers it frozen and continues.

However, on thawing, once pm_freezing is cleared, freezer_count()
stops working, and any random/spurious wakeup will let a task run
before its time.

That is, thawing tries to thaw things in explicit order; kernel
threads and workqueues before doing bringing SMP back before userspace
etc.. However due to the above mentioned races it is entirely possible
for userspace tasks to thaw (by accident) before SMP is back.

This can be a fatal problem in asymmetric ISA architectures (eg ARMv9)
where the userspace task requires a special CPU to run.

As said; replace this with a special task state TASK_FROZEN and add
the following state transitions:

	TASK_FREEZABLE	-> TASK_FROZEN
	__TASK_STOPPED	-> TASK_FROZEN
	__TASK_TRACED	-> TASK_FROZEN

The new TASK_FREEZABLE can be set on any state part of TASK_NORMAL
(IOW. TASK_INTERRUPTIBLE and TASK_UNINTERRUPTIBLE) -- any such state
is already required to deal with spurious wakeups and the freezer
causes one such when thawing the task (since the original state is
lost).

The special __TASK_{STOPPED,TRACED} states *can* be restored since
their canonical state is in ->jobctl.

With this, frozen tasks need an explicit TASK_FROZEN wakeup and are
free of undue (early / spurious) wakeups.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20220822114649.055452969@infradead.org

10 files changed, 30 insertions, 31 deletions

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index eeeaba3dec05..54e6bfc6a5a6 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2326,7 +2326,7 @@ cifs_invalidate_mapping(struct inode *inode)
 static int
 cifs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-	freezable_schedule_unsafe();
+	schedule();
 	if (signal_pending_state(mode, current))
 		return -ERESTARTSYS;
 	return 0;
@@ -2344,7 +2344,7 @@ cifs_revalidate_mapping(struct inode *inode)
 		return 0;
 
 	rc = wait_on_bit_lock_action(flags, CIFS_INO_LOCK, cifs_wait_bit_killable,
-				     TASK_KILLABLE);
+				     TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 	if (rc)
 		return rc;
 
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index de7aeced7e16..eda09fba1550 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -757,8 +757,9 @@ wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ)
 {
 	int error;
 
-	error = wait_event_freezekillable_unsafe(server->response_q,
-				    midQ->mid_state != MID_REQUEST_SUBMITTED);
+	error = wait_event_state(server->response_q,
+				 midQ->mid_state != MID_REQUEST_SUBMITTED,
+				 (TASK_KILLABLE|TASK_FREEZABLE_UNSAFE));
 	if (error < 0)
 		return -ERESTARTSYS;
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 3d9054c49a11..9ce59f212a4a 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -402,9 +402,8 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 	if (core_waiters > 0) {
 		struct core_thread *ptr;
 
-		freezer_do_not_count();
-		wait_for_completion(&core_state->startup);
-		freezer_count();
+		wait_for_completion_state(&core_state->startup,
+					  TASK_UNINTERRUPTIBLE|TASK_FREEZABLE);
 		/*
 		 * Wait for all the threads to become inactive, so that
 		 * all the thread context (extended register state, like
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index d2bcd4834c0e..e8301a372738 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -570,7 +570,8 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf)
 	}
 
 	wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
+			   nfs_wait_bit_killable,
+			   TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 
 	lock_page(page);
 	mapping = page_file_mapping(page);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b4e46b0ffa2d..a6058f5787a5 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -72,18 +72,13 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
 	return nfs_fileid_to_ino_t(fattr->fileid);
 }
 
-static int nfs_wait_killable(int mode)
+int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-	freezable_schedule_unsafe();
+	schedule();
 	if (signal_pending_state(mode, current))
 		return -ERESTARTSYS;
 	return 0;
 }
-
-int nfs_wait_bit_killable(struct wait_bit_key *key, int mode)
-{
-	return nfs_wait_killable(mode);
-}
 EXPORT_SYMBOL_GPL(nfs_wait_bit_killable);
 
 /**
@@ -1331,7 +1326,8 @@ int nfs_clear_invalid_mapping(struct address_space *mapping)
 	 */
 	for (;;) {
 		ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING,
-					 nfs_wait_bit_killable, TASK_KILLABLE);
+					 nfs_wait_bit_killable,
+					 TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 		if (ret)
 			goto out;
 		spin_lock(&inode->i_lock);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 1597eef40d54..2e7579626cf0 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -36,7 +36,8 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags)
 		res = rpc_call_sync(clnt, msg, flags);
 		if (res != -EJUKEBOX)
 			break;
-		freezable_schedule_timeout_killable_unsafe(NFS_JUKEBOX_RETRY_TIME);
+		__set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
+		schedule_timeout(NFS_JUKEBOX_RETRY_TIME);
 		res = -ERESTARTSYS;
 	} while (!fatal_signal_pending(current));
 	return res;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 3ed14a2a84a4..4553803538e5 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -416,8 +416,8 @@ static int nfs4_delay_killable(long *timeout)
 {
 	might_sleep();
 
-	freezable_schedule_timeout_killable_unsafe(
-		nfs4_update_delay(timeout));
+	__set_current_state(TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
+	schedule_timeout(nfs4_update_delay(timeout));
 	if (!__fatal_signal_pending(current))
 		return 0;
 	return -EINTR;
@@ -427,7 +427,8 @@ static int nfs4_delay_interruptible(long *timeout)
 {
 	might_sleep();
 
-	freezable_schedule_timeout_interruptible_unsafe(nfs4_update_delay(timeout));
+	__set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE_UNSAFE);
+	schedule_timeout(nfs4_update_delay(timeout));
 	if (!signal_pending(current))
 		return 0;
 	return __fatal_signal_pending(current) ? -EINTR :-ERESTARTSYS;
@@ -7406,7 +7407,8 @@ nfs4_retry_setlk_simple(struct nfs4_state *state, int cmd,
 		status = nfs4_proc_setlk(state, cmd, request);
 		if ((status != -EAGAIN) || IS_SETLK(cmd))
 			break;
-		freezable_schedule_timeout_interruptible(timeout);
+		__set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
+		schedule_timeout(timeout);
 		timeout *= 2;
 		timeout = min_t(unsigned long, NFS4_LOCK_MAXTIMEOUT, timeout);
 		status = -ERESTARTSYS;
@@ -7474,10 +7476,8 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 			break;
 
 		status = -ERESTARTSYS;
-		freezer_do_not_count();
-		wait_woken(&waiter.wait, TASK_INTERRUPTIBLE,
+		wait_woken(&waiter.wait, TASK_INTERRUPTIBLE|TASK_FREEZABLE,
 			   NFS4_LOCK_MAXTIMEOUT);
-		freezer_count();
 	} while (!signalled());
 
 	remove_wait_queue(q, &waiter.wait);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9bab3e9c702a..7e185f7eb260 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1314,7 +1314,8 @@ int nfs4_wait_clnt_recover(struct nfs_client *clp)
 
 	refcount_inc(&clp->cl_count);
 	res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
-				 nfs_wait_bit_killable, TASK_KILLABLE);
+				 nfs_wait_bit_killable,
+				 TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 	if (res)
 		goto out;
 	if (clp->cl_cons_state < 0)
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 41a9b6b58fb9..70706db317f3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1908,7 +1908,7 @@ static int pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
 	pnfs_layoutcommit_inode(lo->plh_inode, false);
 	return wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN,
 				   nfs_wait_bit_killable,
-				   TASK_KILLABLE);
+				   TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 }
 
 static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo)
@@ -3193,7 +3193,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 		status = wait_on_bit_lock_action(&nfsi->flags,
 				NFS_INO_LAYOUTCOMMITTING,
 				nfs_wait_bit_killable,
-				TASK_KILLABLE);
+				TASK_KILLABLE|TASK_FREEZABLE_UNSAFE);
 		if (status)
 			goto out;
 	}
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index d3a97a028560..16fbf2a1144c 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -602,9 +602,9 @@ xfsaild(
 
 	while (1) {
 		if (tout && tout <= 20)
-			set_current_state(TASK_KILLABLE);
+			set_current_state(TASK_KILLABLE|TASK_FREEZABLE);
 		else
-			set_current_state(TASK_INTERRUPTIBLE);
+			set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
 
 		/*
 		 * Check kthread_should_stop() after we set the task state to
@@ -653,14 +653,14 @@ xfsaild(
 		    ailp->ail_target == ailp->ail_target_prev &&
 		    list_empty(&ailp->ail_buf_list)) {
 			spin_unlock(&ailp->ail_lock);
-			freezable_schedule();
+			schedule();
 			tout = 0;
 			continue;
 		}
 		spin_unlock(&ailp->ail_lock);
 
 		if (tout)
-			freezable_schedule_timeout(msecs_to_jiffies(tout));
+			schedule_timeout(msecs_to_jiffies(tout));
 
 		__set_current_state(TASK_RUNNING);