Merge tag 'mm-nonmm-stable-2022-10-11' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-MM updates from Andrew Morton:

 - hfs and hfsplus kmap API modernization (Fabio Francesco)

 - make crash-kexec work properly when invoked from an NMI-time panic
   (Valentin Schneider)

 - ntfs bugfixes (Hawkins Jiawei)

 - improve IPC msg scalability by replacing atomic_t's with percpu
   counters (Jiebin Sun)

 - nilfs2 cleanups (Minghao Chi)

 - lots of other single patches all over the tree!

* tag 'mm-nonmm-stable-2022-10-11' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (71 commits)
  include/linux/entry-common.h: remove has_signal comment of arch_do_signal_or_restart() prototype
  proc: test how it holds up with mapping'less process
  mailmap: update Frank Rowand email address
  ia64: mca: use strscpy() is more robust and safer
  init/Kconfig: fix unmet direct dependencies
  ia64: update config files
  nilfs2: replace WARN_ONs by nilfs_error for checkpoint acquisition failure
  fork: remove duplicate included header files
  init/main.c: remove unnecessary (void*) conversions
  proc: mark more files as permanent
  nilfs2: remove the unneeded result variable
  nilfs2: delete unnecessary checks before brelse()
  checkpatch: warn for non-standard fixes tag style
  usr/gen_init_cpio.c: remove unnecessary -1 values from int file
  ipc/msg: mitigate the lock contention with percpu counter
  percpu: add percpu_counter_add_local and percpu_counter_sub_local
  fs/ocfs2: fix repeated words in comments
  relay: use kvcalloc to alloc page array in relay_alloc_page_array
  proc: make config PROC_CHILDREN depend on PROC_FS
  fs: uninline inode_maybe_inc_iversion()
  ...

8 files changed, 53 insertions, 75 deletions

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index d7dd83fafeba..2ba557e067fe 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -347,10 +347,10 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
 	const typeof(*(ptr)) mask__ = (mask), bits__ = (bits);	\
 	typeof(*(ptr)) old__, new__;				\
 								\
+	old__ = READ_ONCE(*(ptr));				\
 	do {							\
-		old__ = READ_ONCE(*(ptr));			\
 		new__ = (old__ & ~mask__) | bits__;		\
-	} while (cmpxchg(ptr, old__, new__) != old__);		\
+	} while (!try_cmpxchg(ptr, &old__, new__));		\
 								\
 	old__;							\
 })
@@ -362,11 +362,12 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
 	const typeof(*(ptr)) clear__ = (clear), test__ = (test);\
 	typeof(*(ptr)) old__, new__;				\
 								\
+	old__ = READ_ONCE(*(ptr));				\
 	do {							\
-		old__ = READ_ONCE(*(ptr));			\
+		if (old__ & test__)				\
+			break;					\
 		new__ = old__ & ~clear__;			\
-	} while (!(old__ & test__) &&				\
-		 cmpxchg(ptr, old__, new__) != old__);		\
+	} while (!try_cmpxchg(ptr, &old__, new__));		\
 								\
 	!(old__ & test__);					\
 })
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 84a466b176cf..d95ab85f96ba 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -253,7 +253,6 @@ static __always_inline void arch_exit_to_user_mode(void) { }
 /**
  * arch_do_signal_or_restart -  Architecture specific signal delivery function
  * @regs:	Pointer to currents pt_regs
- * @has_signal:	actual signal to handle
  *
  * Invoked from exit_to_user_mode_loop().
  */
diff --git a/include/linux/init.h b/include/linux/init.h
index a0a90cd73ebe..077d7f93b402 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -134,7 +134,7 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry)
 
 extern initcall_entry_t __con_initcall_start[], __con_initcall_end[];
 
-/* Used for contructor calls. */
+/* Used for constructor calls. */
 typedef void (*ctor_fn_t)(void);
 
 struct file_system_type;
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index e3e8c8662b49..e8240cf2611a 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -11,6 +11,7 @@
 #include <linux/refcount.h>
 #include <linux/rhashtable-types.h>
 #include <linux/sysctl.h>
+#include <linux/percpu_counter.h>
 
 struct user_namespace;
 
@@ -36,8 +37,8 @@ struct ipc_namespace {
 	unsigned int	msg_ctlmax;
 	unsigned int	msg_ctlmnb;
 	unsigned int	msg_ctlmni;
-	atomic_t	msg_bytes;
-	atomic_t	msg_hdrs;
+	struct percpu_counter percpu_msg_bytes;
+	struct percpu_counter percpu_msg_hdrs;
 
 	size_t		shm_ctlmax;
 	size_t		shm_ctlall;
diff --git a/include/linux/iversion.h b/include/linux/iversion.h
index 3bfebde5a1a6..e27bd4f55d84 100644
--- a/include/linux/iversion.h
+++ b/include/linux/iversion.h
@@ -123,17 +123,12 @@ inode_peek_iversion_raw(const struct inode *inode)
 static inline void
 inode_set_max_iversion_raw(struct inode *inode, u64 val)
 {
-	u64 cur, old;
+	u64 cur = inode_peek_iversion_raw(inode);
 
-	cur = inode_peek_iversion_raw(inode);
-	for (;;) {
+	do {
 		if (cur > val)
 			break;
-		old = atomic64_cmpxchg(&inode->i_version, cur, val);
-		if (likely(old == cur))
-			break;
-		cur = old;
-	}
+	} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val));
 }
 
 /**
@@ -177,56 +172,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val)
 				I_VERSION_QUERIED);
 }
 
-/**
- * inode_maybe_inc_iversion - increments i_version
- * @inode: inode with the i_version that should be updated
- * @force: increment the counter even if it's not necessary?
- *
- * Every time the inode is modified, the i_version field must be seen to have
- * changed by any observer.
- *
- * If "force" is set or the QUERIED flag is set, then ensure that we increment
- * the value, and clear the queried flag.
- *
- * In the common case where neither is set, then we can return "false" without
- * updating i_version.
- *
- * If this function returns false, and no other metadata has changed, then we
- * can avoid logging the metadata.
- */
-static inline bool
-inode_maybe_inc_iversion(struct inode *inode, bool force)
-{
-	u64 cur, old, new;
-
-	/*
-	 * The i_version field is not strictly ordered with any other inode
-	 * information, but the legacy inode_inc_iversion code used a spinlock
-	 * to serialize increments.
-	 *
-	 * Here, we add full memory barriers to ensure that any de-facto
-	 * ordering with other info is preserved.
-	 *
-	 * This barrier pairs with the barrier in inode_query_iversion()
-	 */
-	smp_mb();
-	cur = inode_peek_iversion_raw(inode);
-	for (;;) {
-		/* If flag is clear then we needn't do anything */
-		if (!force && !(cur & I_VERSION_QUERIED))
-			return false;
-
-		/* Since lowest bit is flag, add 2 to avoid it */
-		new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT;
-
-		old = atomic64_cmpxchg(&inode->i_version, cur, new);
-		if (likely(old == cur))
-			break;
-		cur = old;
-	}
-	return true;
-}
-
+bool inode_maybe_inc_iversion(struct inode *inode, bool force);
 
 /**
  * inode_inc_iversion - forcibly increment i_version
@@ -304,10 +250,10 @@ inode_peek_iversion(const struct inode *inode)
 static inline u64
 inode_query_iversion(struct inode *inode)
 {
-	u64 cur, old, new;
+	u64 cur, new;
 
 	cur = inode_peek_iversion_raw(inode);
-	for (;;) {
+	do {
 		/* If flag is already set, then no need to swap */
 		if (cur & I_VERSION_QUERIED) {
 			/*
@@ -320,11 +266,7 @@ inode_query_iversion(struct inode *inode)
 		}
 
 		new = cur | I_VERSION_QUERIED;
-		old = atomic64_cmpxchg(&inode->i_version, cur, new);
-		if (likely(old == cur))
-			break;
-		cur = old;
-	}
+	} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new));
 	return cur >> I_VERSION_QUERIED_SHIFT;
 }
 
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 13e6c4b58f07..41a686996aaa 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -427,7 +427,7 @@ extern int kexec_load_disabled;
 extern bool kexec_in_progress;
 
 int crash_shrink_memory(unsigned long new_size);
-size_t crash_get_memory_size(void);
+ssize_t crash_get_memory_size(void);
 
 #ifndef arch_kexec_protect_crashkres
 /*
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 01861eebed79..8ed5fba6d156 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -15,6 +15,9 @@
 #include <linux/types.h>
 #include <linux/gfp.h>
 
+/* percpu_counter batch for local add or sub */
+#define PERCPU_COUNTER_LOCAL_BATCH	INT_MAX
+
 #ifdef CONFIG_SMP
 
 struct percpu_counter {
@@ -56,6 +59,22 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 	percpu_counter_add_batch(fbc, amount, percpu_counter_batch);
 }
 
+/*
+ * With percpu_counter_add_local() and percpu_counter_sub_local(), counts
+ * are accumulated in local per cpu counter and not in fbc->count until
+ * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter
+ * write efficient.
+ * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be
+ * used to add up the counts from each CPU to account for all the local
+ * counts. So percpu_counter_add_local() and percpu_counter_sub_local()
+ * should be used when a counter is updated frequently and read rarely.
+ */
+static inline void
+percpu_counter_add_local(struct percpu_counter *fbc, s64 amount)
+{
+	percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH);
+}
+
 static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
 {
 	s64 ret = __percpu_counter_sum(fbc);
@@ -138,6 +157,13 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 	preempt_enable();
 }
 
+/* non-SMP percpu_counter_add_local is the same with percpu_counter_add */
+static inline void
+percpu_counter_add_local(struct percpu_counter *fbc, s64 amount)
+{
+	percpu_counter_add(fbc, amount);
+}
+
 static inline void
 percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
@@ -193,4 +219,10 @@ static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount)
 	percpu_counter_add(fbc, -amount);
 }
 
+static inline void
+percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount)
+{
+	percpu_counter_add_local(fbc, -amount);
+}
+
 #endif /* _LINUX_PERCPU_COUNTER_H */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 81cab4b01edc..d6c48163c6de 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -127,6 +127,9 @@ static inline void put_task_struct_many(struct task_struct *t, int nr)
 
 void put_task_struct_rcu_user(struct task_struct *task);
 
+/* Free all architecture-specific resources held by a thread. */
+void release_thread(struct task_struct *dead_task);
+
 #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
 extern int arch_task_struct_size __read_mostly;
 #else