Merge tag 'locking-core-2021-02-17' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Core locking primitives updates:
    - Remove mutex_trylock_recursive() from the API - no users left
    - Simplify + constify the futex code a bit

  Lockdep updates:
    - Teach lockdep about local_lock_t
    - Add CONFIG_DEBUG_IRQFLAGS=y debug config option to check for
      potentially unsafe IRQ mask restoration patterns. (I.e.
      calling raw_local_irq_restore() with IRQs enabled.)
    - Add wait context self-tests
    - Fix graph lock corner case corrupting internal data structures
    - Fix noinstr annotations

  LKMM updates:
    - Simplify the litmus tests
    - Documentation fixes

  KCSAN updates:
    - Re-enable KCSAN instrumentation in lib/random32.c

  Misc fixes:
    - Don't branch-trace static label APIs
    - DocBook fix
    - Remove stale leftover empty file"

* tag 'locking-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  checkpatch: Don't check for mutex_trylock_recursive()
  locking/mutex: Kill mutex_trylock_recursive()
  s390: Use arch_local_irq_{save,restore}() in early boot code
  lockdep: Noinstr annotate warn_bogus_irq_restore()
  locking/lockdep: Avoid unmatched unlock
  locking/rwsem: Remove empty rwsem.h
  locking/rtmutex: Add missing kernel-doc markup
  futex: Remove unneeded gotos
  futex: Change utime parameter to be 'const ... *'
  lockdep: report broken irq restoration
  jump_label: Do not profile branch annotations
  locking: Add Reviewers
  locking/selftests: Add local_lock inversion tests
  locking/lockdep: Exclude local_lock_t from IRQ inversions
  locking/lockdep: Clean up check_redundant() a bit
  locking/lockdep: Add a skip() function to __bfs()
  locking/lockdep: Mark local_lock_t
  locking/selftests: More granular debug_locks_verbose
  lockdep/selftest: Add wait context selftests
  tools/memory-model: Fix typo in klitmus7 compatibility table
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -802,13 +802,14 @@
 			insecure, please do not use on production kernels.
 
 	debug_locks_verbose=
-			[KNL] verbose self-tests
-			Format=<0|1>
+			[KNL] verbose locking self-tests
+			Format: <int>
 			Print debugging info while doing the locking API
 			self-tests.
-			We default to 0 (no extra messages), setting it to
-			1 will print _a lot_ more information - normally
-			only useful to kernel developers.
+			Bitmask for the various LOCKTYPE_ tests. Defaults to 0
+			(no extra messages), setting it to -1 (all bits set)
+			will print _a_lot_ more information - normally only
+			useful to lockdep developers.
 
 	debug_objects	[KNL] Enable object debugging
 

MAINTAINERS

@@ -10342,6 +10342,8 @@ LOCKING PRIMITIVES
 M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Will Deacon <will@kernel.org>
+R:	Waiman Long <longman@redhat.com>
+R:	Boqun Feng <boqun.feng@gmail.com> (LOCKDEP)
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core

drivers/s390/char/sclp_early_core.c

@@ -66,13 +66,13 @@ int sclp_early_cmd(sclp_cmdw_t cmd, void *sccb)
 	unsigned long flags;
 	int rc;
 
-	raw_local_irq_save(flags);
+	flags = arch_local_irq_save();
 	rc = sclp_service_call(cmd, sccb);
 	if (rc)
 		goto out;
 	sclp_early_wait_irq();
 out:
-	raw_local_irq_restore(flags);
+	arch_local_irq_restore(flags);
 	return rc;
 }
 

include/linux/compiler.h

@@ -76,6 +76,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 #else
 # define likely(x)	__builtin_expect(!!(x), 1)
 # define unlikely(x)	__builtin_expect(!!(x), 0)
+# define likely_notrace(x)	likely(x)
+# define unlikely_notrace(x)	unlikely(x)
 #endif
 
 /* Optimization barrier */

include/linux/irqflags.h

@@ -149,6 +149,17 @@ do {						\
 # define start_critical_timings() do { } while (0)
 #endif
 
+#ifdef CONFIG_DEBUG_IRQFLAGS
+extern void warn_bogus_irq_restore(void);
+#define raw_check_bogus_irq_restore()			\
+	do {						\
+		if (unlikely(!arch_irqs_disabled()))	\
+			warn_bogus_irq_restore();	\
+	} while (0)
+#else
+#define raw_check_bogus_irq_restore() do { } while (0)
+#endif
+
 /*
  * Wrap the arch provided IRQ routines to provide appropriate checks.
  */
@@ -162,6 +173,7 @@ do {						\
 #define raw_local_irq_restore(flags)			\
 	do {						\
 		typecheck(unsigned long, flags);	\
+		raw_check_bogus_irq_restore();		\
 		arch_local_irq_restore(flags);		\
 	} while (0)
 #define raw_local_save_flags(flags)			\

include/linux/jump_label.h

@@ -261,14 +261,14 @@ static __always_inline void jump_label_init(void)
 
 static __always_inline bool static_key_false(struct static_key *key)
 {
-	if (unlikely(static_key_count(key) > 0))
+	if (unlikely_notrace(static_key_count(key) > 0))
 		return true;
 	return false;
 }
 
 static __always_inline bool static_key_true(struct static_key *key)
 {
-	if (likely(static_key_count(key) > 0))
+	if (likely_notrace(static_key_count(key) > 0))
 		return true;
 	return false;
 }
@@ -460,7 +460,7 @@ extern bool ____wrong_branch_error(void);
 		branch = !arch_static_branch_jump(&(x)->key, true);		\
 	else									\
 		branch = ____wrong_branch_error();				\
-	likely(branch);								\
+	likely_notrace(branch);								\
 })
 
 #define static_branch_unlikely(x)						\
@@ -472,13 +472,13 @@ extern bool ____wrong_branch_error(void);
 		branch = arch_static_branch(&(x)->key, false);			\
 	else									\
 		branch = ____wrong_branch_error();				\
-	unlikely(branch);							\
+	unlikely_notrace(branch);							\
 })
 
 #else /* !CONFIG_JUMP_LABEL */
 
-#define static_branch_likely(x)		likely(static_key_enabled(&(x)->key))
-#define static_branch_unlikely(x)	unlikely(static_key_enabled(&(x)->key))
+#define static_branch_likely(x)		likely_notrace(static_key_enabled(&(x)->key))
+#define static_branch_unlikely(x)	unlikely_notrace(static_key_enabled(&(x)->key))
 
 #endif /* CONFIG_JUMP_LABEL */
 

include/linux/local_lock_internal.h

@@ -18,6 +18,7 @@ typedef struct {
 	.dep_map = {					\
 		.name = #lockname,			\
 		.wait_type_inner = LD_WAIT_CONFIG,	\
+		.lock_type = LD_LOCK_PERCPU,			\
 	}
 #else
 # define LL_DEP_MAP_INIT(lockname)
@@ -30,7 +31,9 @@ do {								\
 	static struct lock_class_key __key;			\
 								\
 	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
-	lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\
+	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \
+			      LD_WAIT_CONFIG, LD_WAIT_INV,	\
+			      LD_LOCK_PERCPU);			\
 } while (0)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC

include/linux/lockdep.h

@@ -185,12 +185,19 @@ extern void lockdep_unregister_key(struct lock_class_key *key);
  * to lockdep:
  */
 
-extern void lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
-	struct lock_class_key *key, int subclass, short inner, short outer);
+extern void lockdep_init_map_type(struct lockdep_map *lock, const char *name,
+	struct lock_class_key *key, int subclass, u8 inner, u8 outer, u8 lock_type);
+
+static inline void
+lockdep_init_map_waits(struct lockdep_map *lock, const char *name,
+		       struct lock_class_key *key, int subclass, u8 inner, u8 outer)
+{
+	lockdep_init_map_type(lock, name, key, subclass, inner, LD_WAIT_INV, LD_LOCK_NORMAL);
+}
 
 static inline void
 lockdep_init_map_wait(struct lockdep_map *lock, const char *name,
-		      struct lock_class_key *key, int subclass, short inner)
+		      struct lock_class_key *key, int subclass, u8 inner)
 {
 	lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV);
 }
@@ -340,6 +347,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
 # define lockdep_init()				do { } while (0)
+# define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \
+		do { (void)(name); (void)(key); } while (0)
 # define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \
 		do { (void)(name); (void)(key); } while (0)
 # define lockdep_init_map_wait(lock, name, key, sub, inner) \

include/linux/lockdep_types.h

@@ -30,6 +30,12 @@ enum lockdep_wait_type {
 	LD_WAIT_MAX,		/* must be last */
 };
 
+enum lockdep_lock_type {
+	LD_LOCK_NORMAL = 0,	/* normal, catch all */
+	LD_LOCK_PERCPU,		/* percpu */
+	LD_LOCK_MAX,
+};
+
 #ifdef CONFIG_LOCKDEP
 
 /*
@@ -119,8 +125,10 @@ struct lock_class {
 	int				name_version;
 	const char			*name;
 
-	short				wait_type_inner;
-	short				wait_type_outer;
+	u8				wait_type_inner;
+	u8				wait_type_outer;
+	u8				lock_type;
+	/* u8				hole; */
 
 #ifdef CONFIG_LOCK_STAT
 	unsigned long			contention_point[LOCKSTAT_POINTS];
@@ -169,8 +177,10 @@ struct lockdep_map {
 	struct lock_class_key		*key;
 	struct lock_class		*class_cache[NR_LOCKDEP_CACHING_CLASSES];
 	const char			*name;
-	short				wait_type_outer; /* can be taken in this context */
-	short				wait_type_inner; /* presents this context */
+	u8				wait_type_outer; /* can be taken in this context */
+	u8				wait_type_inner; /* presents this context */
+	u8				lock_type;
+	/* u8				hole; */
 #ifdef CONFIG_LOCK_STAT
 	int				cpu;
 	unsigned long			ip;

include/linux/mutex.h

@@ -199,29 +199,4 @@ extern void mutex_unlock(struct mutex *lock);
 
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
-/*
- * These values are chosen such that FAIL and SUCCESS match the
- * values of the regular mutex_trylock().
- */
-enum mutex_trylock_recursive_enum {
-	MUTEX_TRYLOCK_FAILED    = 0,
-	MUTEX_TRYLOCK_SUCCESS   = 1,
-	MUTEX_TRYLOCK_RECURSIVE,
-};
-
-/**
- * mutex_trylock_recursive - trylock variant that allows recursive locking
- * @lock: mutex to be locked
- *
- * This function should not be used, _ever_. It is purely for hysterical GEM
- * raisins, and once those are gone this will be removed.
- *
- * Returns:
- *  - MUTEX_TRYLOCK_FAILED    - trylock failed,
- *  - MUTEX_TRYLOCK_SUCCESS   - lock acquired,
- *  - MUTEX_TRYLOCK_RECURSIVE - we already owned the lock.
- */
-extern /* __deprecated */ __must_check enum mutex_trylock_recursive_enum
-mutex_trylock_recursive(struct mutex *lock);
-
 #endif /* __LINUX_MUTEX_H */

include/linux/syscalls.h

@@ -607,11 +607,11 @@ asmlinkage long sys_unshare(unsigned long unshare_flags);
 
 /* kernel/futex.c */
 asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val,
-			struct __kernel_timespec __user *utime, u32 __user *uaddr2,
-			u32 val3);
+			  const struct __kernel_timespec __user *utime,
+			  u32 __user *uaddr2, u32 val3);
 asmlinkage long sys_futex_time32(u32 __user *uaddr, int op, u32 val,
-			struct old_timespec32 __user *utime, u32 __user *uaddr2,
-			u32 val3);
+				 const struct old_timespec32 __user *utime,
+				 u32 __user *uaddr2, u32 val3);
 asmlinkage long sys_get_robust_list(int pid,
 				    struct robust_list_head __user * __user *head_ptr,
 				    size_t __user *len_ptr);

kernel/futex.c

@@ -3012,7 +3012,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 		 * Success, we're done! No tricky corner cases.
 		 */
 		if (!ret)
-			goto out_putkey;
+			return ret;
 		/*
 		 * The atomic access to the futex value generated a
 		 * pagefault, so retry the user-access and the wakeup:
@@ -3029,7 +3029,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
 		 */
-		goto out_putkey;
+		return ret;
 	}
 
 	/*
@@ -3050,7 +3050,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 
 		default:
 			WARN_ON_ONCE(1);
-			goto out_putkey;
+			return ret;
 		}
 	}
 
@@ -3061,7 +3061,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 
 out_unlock:
 	spin_unlock(&hb->lock);
-out_putkey:
 	return ret;
 
 pi_retry:
@@ -3763,8 +3762,8 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 
 
 SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
-		struct __kernel_timespec __user *, utime, u32 __user *, uaddr2,
-		u32, val3)
+		const struct __kernel_timespec __user *, utime,
+		u32 __user *, uaddr2, u32, val3)
 {
 	struct timespec64 ts;
 	ktime_t t, *tp = NULL;
@@ -3959,7 +3958,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
 
 #ifdef CONFIG_COMPAT_32BIT_TIME
 SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
-		struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
+		const struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
 		u32, val3)
 {
 	struct timespec64 ts;

kernel/kcsan/core.c

@@ -12,7 +12,6 @@
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/preempt.h>
-#include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
@@ -101,7 +100,7 @@ static atomic_long_t watchpoints[CONFIG_KCSAN_NUM_WATCHPOINTS + NUM_SLOTS-1];
 static DEFINE_PER_CPU(long, kcsan_skip);
 
 /* For kcsan_prandom_u32_max(). */
-static DEFINE_PER_CPU(struct rnd_state, kcsan_rand_state);
+static DEFINE_PER_CPU(u32, kcsan_rand_state);
 
 static __always_inline atomic_long_t *find_watchpoint(unsigned long addr,
 						      size_t size,
@@ -275,20 +274,17 @@ should_watch(const volatile void *ptr, size_t size, int type, struct kcsan_ctx *
 }
 
 /*
- * Returns a pseudo-random number in interval [0, ep_ro). See prandom_u32_max()
- * for more details.
- *
- * The open-coded version here is using only safe primitives for all contexts
- * where we can have KCSAN instrumentation. In particular, we cannot use
- * prandom_u32() directly, as its tracepoint could cause recursion.
+ * Returns a pseudo-random number in interval [0, ep_ro). Simple linear
+ * congruential generator, using constants from "Numerical Recipes".
  */
 static u32 kcsan_prandom_u32_max(u32 ep_ro)
 {
-	struct rnd_state *state = &get_cpu_var(kcsan_rand_state);
-	const u32 res = prandom_u32_state(state);
+	u32 state = this_cpu_read(kcsan_rand_state);
+
+	state = 1664525 * state + 1013904223;
+	this_cpu_write(kcsan_rand_state, state);
 
-	put_cpu_var(kcsan_rand_state);
-	return (u32)(((u64) res * ep_ro) >> 32);
+	return state % ep_ro;
 }
 
 static inline void reset_kcsan_skip(void)
@@ -639,10 +635,14 @@ static __always_inline void check_access(const volatile void *ptr, size_t size,
 
 void __init kcsan_init(void)
 {
+	int cpu;
+
 	BUG_ON(!in_task());
 
 	kcsan_debugfs_init();
-	prandom_seed_full_state(&kcsan_rand_state);
+
+	for_each_possible_cpu(cpu)
+		per_cpu(kcsan_rand_state, cpu) = (u32)get_cycles();
 
 	/*
 	 * We are in the init task, and no other tasks should be running;

kernel/locking/Makefile

@@ -15,6 +15,7 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE)
 endif
 
+obj-$(CONFIG_DEBUG_IRQFLAGS) += irqflag-debug.o
 obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
 obj-$(CONFIG_LOCKDEP) += lockdep.o
 ifeq ($(CONFIG_PROC_FS),y)

kernel/locking/irqflag-debug.c

@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/bug.h>
+#include <linux/export.h>
+#include <linux/irqflags.h>
+
+noinstr void warn_bogus_irq_restore(void)
+{
+	instrumentation_begin();
+	WARN_ONCE(1, "raw_local_irq_restore() called with IRQs enabled\n");
+	instrumentation_end();
+}
+EXPORT_SYMBOL(warn_bogus_irq_restore);