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

Pull locking and atomic updates from Ingo Molnar:
 "Main changes in this cycle are:

   - Extend atomic primitives with coherent logic op primitives
     (atomic_{or,and,xor}()) and deprecate the old partial APIs
     (atomic_{set,clear}_mask())

     The old ops were incoherent with incompatible signatures across
     architectures and with incomplete support.  Now every architecture
     supports the primitives consistently (by Peter Zijlstra)

   - Generic support for 'relaxed atomics':

       - _acquire/release/relaxed() flavours of xchg(), cmpxchg() and {add,sub}_return()
       - atomic_read_acquire()
       - atomic_set_release()

     This came out of porting qwrlock code to arm64 (by Will Deacon)

   - Clean up the fragile static_key APIs that were causing repeat bugs,
     by introducing a new one:

       DEFINE_STATIC_KEY_TRUE(name);
       DEFINE_STATIC_KEY_FALSE(name);

     which define a key of different types with an initial true/false
     value.

     Then allow:

       static_branch_likely()
       static_branch_unlikely()

     to take a key of either type and emit the right instruction for the
     case.  To be able to know the 'type' of the static key we encode it
     in the jump entry (by Peter Zijlstra)

   - Static key self-tests (by Jason Baron)

   - qrwlock optimizations (by Waiman Long)

   - small futex enhancements (by Davidlohr Bueso)

   - ... and misc other changes"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  jump_label/x86: Work around asm build bug on older/backported GCCs
  locking, ARM, atomics: Define our SMP atomics in terms of _relaxed() operations
  locking, include/llist: Use linux/atomic.h instead of asm/cmpxchg.h
  locking/qrwlock: Make use of _{acquire|release|relaxed}() atomics
  locking/qrwlock: Implement queue_write_unlock() using smp_store_release()
  locking/lockref: Remove homebrew cmpxchg64_relaxed() macro definition
  locking, asm-generic: Add _{relaxed|acquire|release}() variants for 'atomic_long_t'
  locking, asm-generic: Rework atomic-long.h to avoid bulk code duplication
  locking/atomics: Add _{acquire|release|relaxed}() variants of some atomic operations
  locking, compiler.h: Cast away attributes in the WRITE_ONCE() magic
  locking/static_keys: Make verify_keys() static
  jump label, locking/static_keys: Update docs
  locking/static_keys: Provide a selftest
  jump_label: Provide a self-test
  s390/uaccess, locking/static_keys: employ static_branch_likely()
  x86, tsc, locking/static_keys: Employ static_branch_likely()
  locking/static_keys: Add selftest
  locking/static_keys: Add a new static_key interface
  locking/static_keys: Rework update logic
  locking/static_keys: Add static_key_{en,dis}able() helpers
  ...

5 files changed, 27 insertions, 24 deletions

diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 512d2782b043..55f106ed12bf 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -67,6 +67,10 @@ static __inline__ int atomic_##op##_return(int a, atomic_t *v)		\
 ATOMIC_OPS(add, add)
 ATOMIC_OPS(sub, subf)
 
+ATOMIC_OP(and, and)
+ATOMIC_OP(or, or)
+ATOMIC_OP(xor, xor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -304,6 +308,9 @@ static __inline__ long atomic64_##op##_return(long a, atomic64_t *v)	\
 
 ATOMIC64_OPS(add, add)
 ATOMIC64_OPS(sub, subf)
+ATOMIC64_OP(and, and)
+ATOMIC64_OP(or, or)
+ATOMIC64_OP(xor, xor)
 
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index 51ccc7232042..0eca6efc0631 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -76,12 +76,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_lwsync();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_lwsync();							\
 	___p1;								\
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index efbf9a322a23..47e155f15433 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -18,14 +18,29 @@
 #define JUMP_ENTRY_TYPE		stringify_in_c(FTR_ENTRY_LONG)
 #define JUMP_LABEL_NOP_SIZE	4
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\n\t"
 		 "nop\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
 		 ".popsection \n\t"
-		 : :  "i" (key) : : l_yes);
+		 : :  "i" (&((char *)key)[branch]) : : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:\n\t"
+		 "b %l[l_yes]\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
+		 ".popsection \n\t"
+		 : :  "i" (&((char *)key)[branch]) : : l_yes);
+
 	return false;
 l_yes:
 	return true;
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index a1ed8a8c7cb4..6472472093d0 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -17,7 +17,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 {
 	u32 *addr = (u32 *)(unsigned long)entry->code;
 
-	if (type == JUMP_LABEL_ENABLE)
+	if (type == JUMP_LABEL_JMP)
 		patch_branch(addr, entry->target, 0);
 	else
 		patch_instruction(addr, PPC_INST_NOP);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 7c6bb4b17b49..ed3ab509faca 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -596,25 +596,6 @@ _GLOBAL(copy_page)
 	b	2b
 
 /*
- * void atomic_clear_mask(atomic_t mask, atomic_t *addr)
- * void atomic_set_mask(atomic_t mask, atomic_t *addr);
- */
-_GLOBAL(atomic_clear_mask)
-10:	lwarx	r5,0,r4
-	andc	r5,r5,r3
-	PPC405_ERR77(0,r4)
-	stwcx.	r5,0,r4
-	bne-	10b
-	blr
-_GLOBAL(atomic_set_mask)
-10:	lwarx	r5,0,r4
-	or	r5,r5,r3
-	PPC405_ERR77(0,r4)
-	stwcx.	r5,0,r4
-	bne-	10b
-	blr
-
-/*
  * Extended precision shifts.
  *
  * Updated to be valid for shift counts from 0 to 63 inclusive.