Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "The main changes in the locking subsystem in this cycle were:

   - Add the Linux Kernel Memory Consistency Model (LKMM) subsystem,
     which is an an array of tools in tools/memory-model/ that formally
     describe the Linux memory coherency model (a.k.a.
     Documentation/memory-barriers.txt), and also produce 'litmus tests'
     in form of kernel code which can be directly executed and tested.

     Here's a high level background article about an earlier version of
     this work on LWN.net:

        https://lwn.net/Articles/718628/

     The design principles:

      "There is reason to believe that Documentation/memory-barriers.txt
       could use some help, and a major purpose of this patch is to
       provide that help in the form of a design-time tool that can
       produce all valid executions of a small fragment of concurrent
       Linux-kernel code, which is called a "litmus test". This tool's
       functionality is roughly similar to a full state-space search.
       Please note that this is a design-time tool, not useful for
       regression testing. However, we hope that the underlying
       Linux-kernel memory model will be incorporated into other tools
       capable of analyzing large bodies of code for regression-testing
       purposes."

     [...]

      "A second tool is klitmus7, which converts litmus tests to
       loadable kernel modules for direct testing. As with herd7, the
       klitmus7 code is freely available from

         http://diy.inria.fr/sources/index.html

       (and via "git" at https://github.com/herd/herdtools7)"

     [...]

     Credits go to:

      "This patch was the result of a most excellent collaboration
       founded by Jade Alglave and also including Alan Stern, Andrea
       Parri, and Luc Maranget."

     ... and to the gents listed in the MAINTAINERS entry:

        LINUX KERNEL MEMORY CONSISTENCY MODEL (LKMM)
        M:      Alan Stern <stern@rowland.harvard.edu>
        M:      Andrea Parri <parri.andrea@gmail.com>
        M:      Will Deacon <will.deacon@arm.com>
        M:      Peter Zijlstra <peterz@infradead.org>
        M:      Boqun Feng <boqun.feng@gmail.com>
        M:      Nicholas Piggin <npiggin@gmail.com>
        M:      David Howells <dhowells@redhat.com>
        M:      Jade Alglave <j.alglave@ucl.ac.uk>
        M:      Luc Maranget <luc.maranget@inria.fr>
        M:      "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

     The LKMM project already found several bugs in Linux locking
     primitives and improved the understanding and the documentation of
     the Linux memory model all around.

   - Add KASAN instrumentation to atomic APIs (Dmitry Vyukov)

   - Add RWSEM API debugging and reorganize the lock debugging Kconfig
     (Waiman Long)

   - ... misc cleanups and other smaller changes"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (31 commits)
  locking/Kconfig: Restructure the lock debugging menu
  locking/Kconfig: Add LOCK_DEBUGGING_SUPPORT to make it more readable
  locking/rwsem: Add DEBUG_RWSEMS to look for lock/unlock mismatches
  lockdep: Make the lock debug output more useful
  locking/rtmutex: Handle non enqueued waiters gracefully in remove_waiter()
  locking/atomic, asm-generic, x86: Add comments for atomic instrumentation
  locking/atomic, asm-generic: Add KASAN instrumentation to atomic operations
  locking/atomic/x86: Switch atomic.h to use atomic-instrumented.h
  locking/atomic, asm-generic: Add asm-generic/atomic-instrumented.h
  locking/xchg/alpha: Remove superfluous memory barriers from the _local() variants
  tools/memory-model: Finish the removal of rb-dep, smp_read_barrier_depends(), and lockless_dereference()
  tools/memory-model: Add documentation of new litmus test
  tools/memory-model: Remove mention of docker/gentoo image
  locking/memory-barriers: De-emphasize smp_read_barrier_depends() some more
  locking/lockdep: Show unadorned pointers
  mutex: Drop linkage.h from mutex.h
  tools/memory-model: Remove rb-dep, smp_read_barrier_depends, and lockless_dereference
  tools/memory-model: Convert underscores to hyphens
  tools/memory-model: Add a S lock-based external-view litmus test
  tools/memory-model: Add required herd7 version to README file
  ...

2 files changed, 476 insertions, 1 deletions

diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
new file mode 100644
index 000000000000..ec07f23678ea
--- /dev/null
+++ b/include/asm-generic/atomic-instrumented.h
@@ -0,0 +1,476 @@
+/*
+ * This file provides wrappers with KASAN instrumentation for atomic operations.
+ * To use this functionality an arch's atomic.h file needs to define all
+ * atomic operations with arch_ prefix (e.g. arch_atomic_read()) and include
+ * this file at the end. This file provides atomic_read() that forwards to
+ * arch_atomic_read() for actual atomic operation.
+ * Note: if an arch atomic operation is implemented by means of other atomic
+ * operations (e.g. atomic_read()/atomic_cmpxchg() loop), then it needs to use
+ * arch_ variants (i.e. arch_atomic_read()/arch_atomic_cmpxchg()) to avoid
+ * double instrumentation.
+ */
+
+#ifndef _LINUX_ATOMIC_INSTRUMENTED_H
+#define _LINUX_ATOMIC_INSTRUMENTED_H
+
+#include <linux/build_bug.h>
+#include <linux/kasan-checks.h>
+
+static __always_inline int atomic_read(const atomic_t *v)
+{
+	kasan_check_read(v, sizeof(*v));
+	return arch_atomic_read(v);
+}
+
+static __always_inline s64 atomic64_read(const atomic64_t *v)
+{
+	kasan_check_read(v, sizeof(*v));
+	return arch_atomic64_read(v);
+}
+
+static __always_inline void atomic_set(atomic_t *v, int i)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic_set(v, i);
+}
+
+static __always_inline void atomic64_set(atomic64_t *v, s64 i)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic64_set(v, i);
+}
+
+static __always_inline int atomic_xchg(atomic_t *v, int i)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_xchg(v, i);
+}
+
+static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_xchg(v, i);
+}
+
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_cmpxchg(v, old, new);
+}
+
+static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_cmpxchg(v, old, new);
+}
+
+#ifdef arch_atomic_try_cmpxchg
+#define atomic_try_cmpxchg atomic_try_cmpxchg
+static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+{
+	kasan_check_write(v, sizeof(*v));
+	kasan_check_read(old, sizeof(*old));
+	return arch_atomic_try_cmpxchg(v, old, new);
+}
+#endif
+
+#ifdef arch_atomic64_try_cmpxchg
+#define atomic64_try_cmpxchg atomic64_try_cmpxchg
+static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
+{
+	kasan_check_write(v, sizeof(*v));
+	kasan_check_read(old, sizeof(*old));
+	return arch_atomic64_try_cmpxchg(v, old, new);
+}
+#endif
+
+static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	kasan_check_write(v, sizeof(*v));
+	return __arch_atomic_add_unless(v, a, u);
+}
+
+
+static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_add_unless(v, a, u);
+}
+
+static __always_inline void atomic_inc(atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic_inc(v);
+}
+
+static __always_inline void atomic64_inc(atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic64_inc(v);
+}
+
+static __always_inline void atomic_dec(atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic_dec(v);
+}
+
+static __always_inline void atomic64_dec(atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic64_dec(v);
+}
+
+static __always_inline void atomic_add(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic_add(i, v);
+}
+
+static __always_inline void atomic64_add(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic64_add(i, v);
+}
+
+static __always_inline void atomic_sub(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic_sub(i, v);
+}
+
+static __always_inline void atomic64_sub(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic64_sub(i, v);
+}
+
+static __always_inline void atomic_and(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic_and(i, v);
+}
+
+static __always_inline void atomic64_and(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic64_and(i, v);
+}
+
+static __always_inline void atomic_or(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic_or(i, v);
+}
+
+static __always_inline void atomic64_or(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic64_or(i, v);
+}
+
+static __always_inline void atomic_xor(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic_xor(i, v);
+}
+
+static __always_inline void atomic64_xor(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	arch_atomic64_xor(i, v);
+}
+
+static __always_inline int atomic_inc_return(atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_inc_return(v);
+}
+
+static __always_inline s64 atomic64_inc_return(atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_inc_return(v);
+}
+
+static __always_inline int atomic_dec_return(atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_dec_return(v);
+}
+
+static __always_inline s64 atomic64_dec_return(atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_dec_return(v);
+}
+
+static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_inc_not_zero(v);
+}
+
+static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_dec_if_positive(v);
+}
+
+static __always_inline bool atomic_dec_and_test(atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_dec_and_test(v);
+}
+
+static __always_inline bool atomic64_dec_and_test(atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_dec_and_test(v);
+}
+
+static __always_inline bool atomic_inc_and_test(atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_inc_and_test(v);
+}
+
+static __always_inline bool atomic64_inc_and_test(atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_inc_and_test(v);
+}
+
+static __always_inline int atomic_add_return(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_add_return(i, v);
+}
+
+static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_add_return(i, v);
+}
+
+static __always_inline int atomic_sub_return(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_sub_return(i, v);
+}
+
+static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_sub_return(i, v);
+}
+
+static __always_inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_fetch_add(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_fetch_add(i, v);
+}
+
+static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_fetch_sub(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_fetch_sub(i, v);
+}
+
+static __always_inline int atomic_fetch_and(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_fetch_and(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_fetch_and(i, v);
+}
+
+static __always_inline int atomic_fetch_or(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_fetch_or(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_fetch_or(i, v);
+}
+
+static __always_inline int atomic_fetch_xor(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_fetch_xor(i, v);
+}
+
+static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_fetch_xor(i, v);
+}
+
+static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_sub_and_test(i, v);
+}
+
+static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_sub_and_test(i, v);
+}
+
+static __always_inline bool atomic_add_negative(int i, atomic_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic_add_negative(i, v);
+}
+
+static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_add_negative(i, v);
+}
+
+static __always_inline unsigned long
+cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size)
+{
+	kasan_check_write(ptr, size);
+	switch (size) {
+	case 1:
+		return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
+	case 2:
+		return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
+	case 4:
+		return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
+	case 8:
+		BUILD_BUG_ON(sizeof(unsigned long) != 8);
+		return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
+	}
+	BUILD_BUG();
+	return 0;
+}
+
+#define cmpxchg(ptr, old, new)						\
+({									\
+	((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old),	\
+		(unsigned long)(new), sizeof(*(ptr))));			\
+})
+
+static __always_inline unsigned long
+sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new,
+		  int size)
+{
+	kasan_check_write(ptr, size);
+	switch (size) {
+	case 1:
+		return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
+	case 2:
+		return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
+	case 4:
+		return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
+	case 8:
+		BUILD_BUG_ON(sizeof(unsigned long) != 8);
+		return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
+	}
+	BUILD_BUG();
+	return 0;
+}
+
+#define sync_cmpxchg(ptr, old, new)					\
+({									\
+	((__typeof__(*(ptr)))sync_cmpxchg_size((ptr),			\
+		(unsigned long)(old), (unsigned long)(new),		\
+		sizeof(*(ptr))));					\
+})
+
+static __always_inline unsigned long
+cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new,
+		   int size)
+{
+	kasan_check_write(ptr, size);
+	switch (size) {
+	case 1:
+		return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new);
+	case 2:
+		return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new);
+	case 4:
+		return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new);
+	case 8:
+		BUILD_BUG_ON(sizeof(unsigned long) != 8);
+		return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new);
+	}
+	BUILD_BUG();
+	return 0;
+}
+
+#define cmpxchg_local(ptr, old, new)					\
+({									\
+	((__typeof__(*(ptr)))cmpxchg_local_size((ptr),			\
+		(unsigned long)(old), (unsigned long)(new),		\
+		sizeof(*(ptr))));					\
+})
+
+static __always_inline u64
+cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new)
+{
+	kasan_check_write(ptr, sizeof(*ptr));
+	return arch_cmpxchg64(ptr, old, new);
+}
+
+#define cmpxchg64(ptr, old, new)					\
+({									\
+	((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old),		\
+		(u64)(new)));						\
+})
+
+static __always_inline u64
+cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new)
+{
+	kasan_check_write(ptr, sizeof(*ptr));
+	return arch_cmpxchg64_local(ptr, old, new);
+}
+
+#define cmpxchg64_local(ptr, old, new)					\
+({									\
+	((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old),	\
+		(u64)(new)));						\
+})
+
+/*
+ * Originally we had the following code here:
+ *     __typeof__(p1) ____p1 = (p1);
+ *     kasan_check_write(____p1, 2 * sizeof(*____p1));
+ *     arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2));
+ * But it leads to compilation failures (see gcc issue 72873).
+ * So for now it's left non-instrumented.
+ * There are few callers of cmpxchg_double(), so it's not critical.
+ */
+#define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
+({									\
+	arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2));	\
+})
+
+#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)			\
+({									\
+	arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2));	\
+})
+
+#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index cb3bbed4e633..14bc0d5d0ee5 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -14,7 +14,6 @@
 #include <asm/current.h>
 #include <linux/list.h>
 #include <linux/spinlock_types.h>
-#include <linux/linkage.h>
 #include <linux/lockdep.h>
 #include <linux/atomic.h>
 #include <asm/processor.h>