Merge tip:locking/core into tip:ras/core

Pick up helpers inlining work in order to address more noinstr fallout
in the MCE code.
Signed-off-by: Borislav Petkov <bp@suse.de>

MAINTAINERS

@@ -3200,6 +3200,7 @@ ATOMIC INFRASTRUCTURE
 M:	Will Deacon <will@kernel.org>
 M:	Peter Zijlstra <peterz@infradead.org>
 R:	Boqun Feng <boqun.feng@gmail.com>
+R:	Mark Rutland <mark.rutland@arm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	arch/*/include/asm/atomic*.h

arch/x86/include/asm/cpumask.h

@@ -20,11 +20,21 @@ static __always_inline bool arch_cpu_online(int cpu)
 {
 	return arch_test_bit(cpu, cpumask_bits(cpu_online_mask));
 }
+
+static __always_inline void arch_cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+{
+	arch_clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
+}
 #else
 static __always_inline bool arch_cpu_online(int cpu)
 {
 	return cpu == 0;
 }
+
+static __always_inline void arch_cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+{
+	return;
+}
 #endif
 
 #define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))

arch/x86/include/asm/ptrace.h

@@ -137,7 +137,7 @@ static __always_inline int user_mode(struct pt_regs *regs)
 #endif
 }
 
-static inline int v8086_mode(struct pt_regs *regs)
+static __always_inline int v8086_mode(struct pt_regs *regs)
 {
 #ifdef CONFIG_X86_32
 	return (regs->flags & X86_VM_MASK);

include/asm-generic/bitops/instrumented-atomic.h

@@ -23,7 +23,7 @@
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void set_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_set_bit(nr, addr);
@@ -36,7 +36,7 @@ static inline void set_bit(long nr, volatile unsigned long *addr)
  *
  * This is a relaxed atomic operation (no implied memory barriers).
  */
-static inline void clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void clear_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_clear_bit(nr, addr);
@@ -52,7 +52,7 @@ static inline void clear_bit(long nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
 	arch_change_bit(nr, addr);
@@ -65,7 +65,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
@@ -79,7 +79,7 @@ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
@@ -93,7 +93,7 @@ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
  *
  * This is an atomic fully-ordered operation (implied full memory barrier).
  */
-static inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));

include/asm-generic/bitops/instrumented-non-atomic.h

@@ -22,7 +22,7 @@
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___set_bit(nr, addr);
@@ -37,7 +37,7 @@ static inline void __set_bit(long nr, volatile unsigned long *addr)
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___clear_bit(nr, addr);
@@ -52,13 +52,13 @@ static inline void __clear_bit(long nr, volatile unsigned long *addr)
  * region of memory concurrently, the effect may be that only one operation
  * succeeds.
  */
-static inline void __change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
 	instrument_write(addr + BIT_WORD(nr), sizeof(long));
 	arch___change_bit(nr, addr);
 }
 
-static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr)
+static __always_inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr)
 {
 	if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) {
 		/*
@@ -90,7 +90,7 @@ static inline void __instrument_read_write_bitop(long nr, volatile unsigned long
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_set_bit(nr, addr);
@@ -104,7 +104,7 @@ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_clear_bit(nr, addr);
@@ -118,7 +118,7 @@ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
  * This operation is non-atomic. If two instances of this operation race, one
  * can appear to succeed but actually fail.
  */
-static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	__instrument_read_write_bitop(nr, addr);
 	return arch___test_and_change_bit(nr, addr);
@@ -129,7 +129,7 @@ static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static inline bool test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool test_bit(long nr, const volatile unsigned long *addr)
 {
 	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
 	return arch_test_bit(nr, addr);

include/linux/atomic/atomic-arch-fallback.h

@@ -151,7 +151,16 @@
 static __always_inline int
 arch_atomic_read_acquire(const atomic_t *v)
 {
-	return smp_load_acquire(&(v)->counter);
+	int ret;
+
+	if (__native_word(atomic_t)) {
+		ret = smp_load_acquire(&(v)->counter);
+	} else {
+		ret = arch_atomic_read(v);
+		__atomic_acquire_fence();
+	}
+
+	return ret;
 }
 #define arch_atomic_read_acquire arch_atomic_read_acquire
 #endif
@@ -160,7 +169,12 @@ arch_atomic_read_acquire(const atomic_t *v)
 static __always_inline void
 arch_atomic_set_release(atomic_t *v, int i)
 {
-	smp_store_release(&(v)->counter, i);
+	if (__native_word(atomic_t)) {
+		smp_store_release(&(v)->counter, i);
+	} else {
+		__atomic_release_fence();
+		arch_atomic_set(v, i);
+	}
 }
 #define arch_atomic_set_release arch_atomic_set_release
 #endif
@@ -1258,7 +1272,16 @@ arch_atomic_dec_if_positive(atomic_t *v)
 static __always_inline s64
 arch_atomic64_read_acquire(const atomic64_t *v)
 {
-	return smp_load_acquire(&(v)->counter);
+	s64 ret;
+
+	if (__native_word(atomic64_t)) {
+		ret = smp_load_acquire(&(v)->counter);
+	} else {
+		ret = arch_atomic64_read(v);
+		__atomic_acquire_fence();
+	}
+
+	return ret;
 }
 #define arch_atomic64_read_acquire arch_atomic64_read_acquire
 #endif
@@ -1267,7 +1290,12 @@ arch_atomic64_read_acquire(const atomic64_t *v)
 static __always_inline void
 arch_atomic64_set_release(atomic64_t *v, s64 i)
 {
-	smp_store_release(&(v)->counter, i);
+	if (__native_word(atomic64_t)) {
+		smp_store_release(&(v)->counter, i);
+	} else {
+		__atomic_release_fence();
+		arch_atomic64_set(v, i);
+	}
 }
 #define arch_atomic64_set_release arch_atomic64_set_release
 #endif
@@ -2358,4 +2386,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v)
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// cca554917d7ea73d5e3e7397dd70c484cad9b2c4
+// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae

include/linux/cpumask.h

@@ -102,7 +102,7 @@ extern atomic_t __num_online_cpus;
 
 extern cpumask_t cpus_booted_once_mask;
 
-static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
+static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
 {
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 	WARN_ON_ONCE(cpu >= bits);
@@ -110,7 +110,7 @@ static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
 }
 
 /* verify cpu argument to cpumask_* operators */
-static inline unsigned int cpumask_check(unsigned int cpu)
+static __always_inline unsigned int cpumask_check(unsigned int cpu)
 {
 	cpu_max_bits_warn(cpu, nr_cpumask_bits);
 	return cpu;
@@ -341,12 +341,12 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool
  * @cpu: cpu number (< nr_cpu_ids)
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
@@ -357,12 +357,12 @@ static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
  * @cpu: cpu number (< nr_cpu_ids)
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 {
 	clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
+static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 {
 	__clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
@@ -374,7 +374,7 @@ static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
  *
  * Returns 1 if @cpu is set in @cpumask, else returns 0
  */
-static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
+static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
 {
 	return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
 }
@@ -388,7 +388,7 @@ static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
  *
  * test_and_set_bit wrapper for cpumasks.
  */
-static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -402,7 +402,7 @@ static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
  *
  * test_and_clear_bit wrapper for cpumasks.
  */
-static inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }

include/linux/local_lock_internal.h

@@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l)
 }
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
 # define LOCAL_LOCK_DEBUG_INIT(lockname)
-static inline void local_lock_acquire(local_lock_t *l) { }
-static inline void local_lock_release(local_lock_t *l) { }
-static inline void local_lock_debug_init(local_lock_t *l) { }
+# define local_lock_acquire(__ll)  do { typecheck(local_lock_t *, __ll); } while (0)
+# define local_lock_release(__ll)  do { typecheck(local_lock_t *, __ll); } while (0)
+# define local_lock_debug_init(__ll)  do { typecheck(local_lock_t *, __ll); } while (0)
 #endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 #define INIT_LOCAL_LOCK(lockname)	{ LOCAL_LOCK_DEBUG_INIT(lockname) }

init/Kconfig

@@ -2054,6 +2054,7 @@ source "arch/Kconfig"
 
 config RT_MUTEXES
 	bool
+	default y if PREEMPT_RT
 
 config BASE_SMALL
 	int

kernel/locking/lockdep.c

@@ -6011,13 +6011,10 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
 
 static void reinit_class(struct lock_class *class)
 {
-	void *const p = class;
-	const unsigned int offset = offsetof(struct lock_class, key);
-
 	WARN_ON_ONCE(!class->lock_entry.next);
 	WARN_ON_ONCE(!list_empty(&class->locks_after));
 	WARN_ON_ONCE(!list_empty(&class->locks_before));
-	memset(p + offset, 0, sizeof(*class) - offset);
+	memset_startat(class, 0, key);
 	WARN_ON_ONCE(!class->lock_entry.next);
 	WARN_ON_ONCE(!list_empty(&class->locks_after));
 	WARN_ON_ONCE(!list_empty(&class->locks_before));
@@ -6290,7 +6287,13 @@ void lockdep_reset_lock(struct lockdep_map *lock)
 		lockdep_reset_lock_reg(lock);
 }
 
-/* Unregister a dynamically allocated key. */
+/*
+ * Unregister a dynamically allocated key.
+ *
+ * Unlike lockdep_register_key(), a search is always done to find a matching
+ * key irrespective of debug_locks to avoid potential invalid access to freed
+ * memory in lock_class entry.
+ */
 void lockdep_unregister_key(struct lock_class_key *key)
 {
 	struct hlist_head *hash_head = keyhashentry(key);
@@ -6305,10 +6308,8 @@ void lockdep_unregister_key(struct lock_class_key *key)
 		return;
 
 	raw_local_irq_save(flags);
-	if (!graph_lock())
-		goto out_irq;
+	lockdep_lock();
 
-	pf = get_pending_free();
 	hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
 		if (k == key) {
 			hlist_del_rcu(&k->hash_entry);
@@ -6316,11 +6317,13 @@ void lockdep_unregister_key(struct lock_class_key *key)
 			break;
 		}
 	}
-	WARN_ON_ONCE(!found);
-	__lockdep_free_key_range(pf, key, 1);
-	call_rcu_zapped(pf);
-	graph_unlock();
-out_irq:
+	WARN_ON_ONCE(!found && debug_locks);
+	if (found) {
+		pf = get_pending_free();
+		__lockdep_free_key_range(pf, key, 1);
+		call_rcu_zapped(pf);
+	}
+	lockdep_unlock();
 	raw_local_irq_restore(flags);
 
 	/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */

kernel/locking/percpu-rwsem.c

@@ -7,6 +7,7 @@
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/sched/task.h>
+#include <linux/sched/debug.h>
 #include <linux/errno.h>
 
 int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
@@ -162,7 +163,7 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader)
 	__set_current_state(TASK_RUNNING);
 }
 
-bool __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
+bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try)
 {
 	if (__percpu_down_read_trylock(sem))
 		return true;
@@ -211,7 +212,7 @@ static bool readers_active_check(struct percpu_rw_semaphore *sem)
 	return true;
 }
 
-void percpu_down_write(struct percpu_rw_semaphore *sem)
+void __sched percpu_down_write(struct percpu_rw_semaphore *sem)
 {
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);

kernel/locking/rwsem.c

@@ -1048,7 +1048,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 /*
  * Wait until we successfully acquire the write lock
  */
-static struct rw_semaphore *
+static struct rw_semaphore __sched *
 rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 {
 	long count;

scripts/atomic/fallbacks/read_acquire

@@ -2,6 +2,15 @@ cat <<EOF
 static __always_inline ${ret}
 arch_${atomic}_read_acquire(const ${atomic}_t *v)
 {
-	return smp_load_acquire(&(v)->counter);
+	${int} ret;
+
+	if (__native_word(${atomic}_t)) {
+		ret = smp_load_acquire(&(v)->counter);
+	} else {
+		ret = arch_${atomic}_read(v);
+		__atomic_acquire_fence();
+	}
+
+	return ret;
 }
 EOF

scripts/atomic/fallbacks/set_release

@@ -2,6 +2,11 @@ cat <<EOF
 static __always_inline void
 arch_${atomic}_set_release(${atomic}_t *v, ${int} i)
 {
-	smp_store_release(&(v)->counter, i);
+	if (__native_word(${atomic}_t)) {
+		smp_store_release(&(v)->counter, i);
+	} else {
+		__atomic_release_fence();
+		arch_${atomic}_set(v, i);
+	}
 }
 EOF