locking/barriers: Convert users of lockless_dereference() to READ_ONCE()

[ Note, this is a Git cherry-pick of the following commit:

    506458efaf ("locking/barriers: Convert users of lockless_dereference() to READ_ONCE()")

  ... for easier x86 PTI code testing and back-porting. ]

READ_ONCE() now has an implicit smp_read_barrier_depends() call, so it
can be used instead of lockless_dereference() without any change in
semantics.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1508840570-22169-4-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/events/core.c

@@ -2371,7 +2371,7 @@ static unsigned long get_segment_base(unsigned int segment)
 		struct ldt_struct *ldt;
 
 		/* IRQs are off, so this synchronizes with smp_store_release */
-		ldt = lockless_dereference(current->active_mm->context.ldt);
+		ldt = READ_ONCE(current->active_mm->context.ldt);
 		if (!ldt || idx >= ldt->nr_entries)
 			return 0;
 

arch/x86/include/asm/mmu_context.h

@@ -73,8 +73,8 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
 
-	/* lockless_dereference synchronizes with smp_store_release */
-	ldt = lockless_dereference(mm->context.ldt);
+	/* READ_ONCE synchronizes with smp_store_release */
+	ldt = READ_ONCE(mm->context.ldt);
 
 	/*
 	 * Any change to mm->context.ldt is followed by an IPI to all

arch/x86/kernel/ldt.c

@@ -103,7 +103,7 @@ static void finalize_ldt_struct(struct ldt_struct *ldt)
 static void install_ldt(struct mm_struct *current_mm,
 			struct ldt_struct *ldt)
 {
-	/* Synchronizes with lockless_dereference in load_mm_ldt. */
+	/* Synchronizes with READ_ONCE in load_mm_ldt. */
 	smp_store_release(&current_mm->context.ldt, ldt);
 
 	/* Activate the LDT for all CPUs using current_mm. */

drivers/md/dm-mpath.c

@@ -366,7 +366,7 @@ static struct pgpath *choose_path_in_pg(struct multipath *m,
 
 	pgpath = path_to_pgpath(path);
 
-	if (unlikely(lockless_dereference(m->current_pg) != pg)) {
+	if (unlikely(READ_ONCE(m->current_pg) != pg)) {
 		/* Only update current_pgpath if pg changed */
 		spin_lock_irqsave(&m->lock, flags);
 		m->current_pgpath = pgpath;
@@ -390,7 +390,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 	}
 
 	/* Were we instructed to switch PG? */
-	if (lockless_dereference(m->next_pg)) {
+	if (READ_ONCE(m->next_pg)) {
 		spin_lock_irqsave(&m->lock, flags);
 		pg = m->next_pg;
 		if (!pg) {
@@ -406,7 +406,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 
 	/* Don't change PG until it has no remaining paths */
 check_current_pg:
-	pg = lockless_dereference(m->current_pg);
+	pg = READ_ONCE(m->current_pg);
 	if (pg) {
 		pgpath = choose_path_in_pg(m, pg, nr_bytes);
 		if (!IS_ERR_OR_NULL(pgpath))
@@ -473,7 +473,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 	struct request *clone;
 
 	/* Do we need to select a new pgpath? */
-	pgpath = lockless_dereference(m->current_pgpath);
+	pgpath = READ_ONCE(m->current_pgpath);
 	if (!pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags))
 		pgpath = choose_pgpath(m, nr_bytes);
 
@@ -535,7 +535,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
 	bool queue_io;
 
 	/* Do we need to select a new pgpath? */
-	pgpath = lockless_dereference(m->current_pgpath);
+	pgpath = READ_ONCE(m->current_pgpath);
 	queue_io = test_bit(MPATHF_QUEUE_IO, &m->flags);
 	if (!pgpath || !queue_io)
 		pgpath = choose_pgpath(m, nr_bytes);
@@ -1804,7 +1804,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 	struct pgpath *current_pgpath;
 	int r;
 
-	current_pgpath = lockless_dereference(m->current_pgpath);
+	current_pgpath = READ_ONCE(m->current_pgpath);
 	if (!current_pgpath)
 		current_pgpath = choose_pgpath(m, 0);
 
@@ -1826,7 +1826,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 	}
 
 	if (r == -ENOTCONN) {
-		if (!lockless_dereference(m->current_pg)) {
+		if (!READ_ONCE(m->current_pg)) {
 			/* Path status changed, redo selection */
 			(void) choose_pgpath(m, 0);
 		}
@@ -1895,9 +1895,9 @@ static int multipath_busy(struct dm_target *ti)
 		return (m->queue_mode != DM_TYPE_MQ_REQUEST_BASED);
 
 	/* Guess which priority_group will be used at next mapping time */
-	pg = lockless_dereference(m->current_pg);
-	next_pg = lockless_dereference(m->next_pg);
-	if (unlikely(!lockless_dereference(m->current_pgpath) && next_pg))
+	pg = READ_ONCE(m->current_pg);
+	next_pg = READ_ONCE(m->next_pg);
+	if (unlikely(!READ_ONCE(m->current_pgpath) && next_pg))
 		pg = next_pg;
 
 	if (!pg) {

fs/dcache.c

@@ -231,7 +231,7 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
 {
 	/*
 	 * Be careful about RCU walk racing with rename:
-	 * use 'lockless_dereference' to fetch the name pointer.
+	 * use 'READ_ONCE' to fetch the name pointer.
 	 *
 	 * NOTE! Even if a rename will mean that the length
 	 * was not loaded atomically, we don't care. The
@@ -245,7 +245,7 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
 	 * early because the data cannot match (there can
 	 * be no NUL in the ct/tcount data)
 	 */
-	const unsigned char *cs = lockless_dereference(dentry->d_name.name);
+	const unsigned char *cs = READ_ONCE(dentry->d_name.name);
 
 	return dentry_string_cmp(cs, ct, tcount);
 }

fs/overlayfs/ovl_entry.h

@@ -77,5 +77,5 @@ static inline struct ovl_inode *OVL_I(struct inode *inode)
 
 static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi)
 {
-	return lockless_dereference(oi->__upperdentry);
+	return READ_ONCE(oi->__upperdentry);
 }

fs/overlayfs/readdir.c

@@ -754,7 +754,7 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
 	if (!od->is_upper && OVL_TYPE_UPPER(ovl_path_type(dentry))) {
 		struct inode *inode = file_inode(file);
 
-		realfile = lockless_dereference(od->upperfile);
+		realfile = READ_ONCE(od->upperfile);
 		if (!realfile) {
 			struct path upperpath;
 

include/linux/rculist.h

@@ -275,7 +275,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
 #define list_entry_rcu(ptr, type, member) \
-	container_of(lockless_dereference(ptr), type, member)
+	container_of(READ_ONCE(ptr), type, member)
 
 /*
  * Where are list_empty_rcu() and list_first_entry_rcu()?
@@ -368,7 +368,7 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * example is when items are added to the list, but never deleted.
  */
 #define list_entry_lockless(ptr, type, member) \
-	container_of((typeof(ptr))lockless_dereference(ptr), type, member)
+	container_of((typeof(ptr))READ_ONCE(ptr), type, member)
 
 /**
  * list_for_each_entry_lockless - iterate over rcu list of given type

include/linux/rcupdate.h

@@ -346,7 +346,7 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define __rcu_dereference_check(p, c, space) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
+	typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \
 	RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \
 	rcu_dereference_sparse(p, space); \
 	((typeof(*p) __force __kernel *)(________p1)); \
@@ -360,7 +360,7 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_dereference_raw(p) \
 ({ \
 	/* Dependency order vs. p above. */ \
-	typeof(p) ________p1 = lockless_dereference(p); \
+	typeof(p) ________p1 = READ_ONCE(p); \
 	((typeof(*p) __force __kernel *)(________p1)); \
 })
 

kernel/events/core.c

@@ -4233,7 +4233,7 @@ static void perf_remove_from_owner(struct perf_event *event)
 	 * indeed free this event, otherwise we need to serialize on
 	 * owner->perf_event_mutex.
 	 */
-	owner = lockless_dereference(event->owner);
+	owner = READ_ONCE(event->owner);
 	if (owner) {
 		/*
 		 * Since delayed_put_task_struct() also drops the last
@@ -4330,7 +4330,7 @@ again:
 		 * Cannot change, child events are not migrated, see the
 		 * comment with perf_event_ctx_lock_nested().
 		 */
-		ctx = lockless_dereference(child->ctx);
+		ctx = READ_ONCE(child->ctx);
 		/*
 		 * Since child_mutex nests inside ctx::mutex, we must jump
 		 * through hoops. We start by grabbing a reference on the ctx.

kernel/seccomp.c

@@ -190,7 +190,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd,
 	u32 ret = SECCOMP_RET_ALLOW;
 	/* Make sure cross-thread synced filter points somewhere sane. */
 	struct seccomp_filter *f =
-			lockless_dereference(current->seccomp.filter);
+			READ_ONCE(current->seccomp.filter);
 
 	/* Ensure unexpected behavior doesn't result in failing open. */
 	if (unlikely(WARN_ON(f == NULL)))

kernel/task_work.c

@@ -68,7 +68,7 @@ task_work_cancel(struct task_struct *task, task_work_func_t func)
 	 * we raced with task_work_run(), *pprev == NULL/exited.
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	while ((work = lockless_dereference(*pprev))) {
+	while ((work = READ_ONCE(*pprev))) {
 		if (work->func != func)
 			pprev = &work->next;
 		else if (cmpxchg(pprev, work, work->next) == work)

mm/slab.h

@@ -259,7 +259,7 @@ cache_from_memcg_idx(struct kmem_cache *s, int idx)
 	 * memcg_caches issues a write barrier to match this (see
 	 * memcg_create_kmem_cache()).
 	 */
-	cachep = lockless_dereference(arr->entries[idx]);
+	cachep = READ_ONCE(arr->entries[idx]);
 	rcu_read_unlock();
 
 	return cachep;