[PATCH 1/4] x86/percpu: Update arch/x86/include/asm/percpu.h to the current tip

[Uros Bizjak <ubizjak@gmail.com>]

This is just a convenient patch that brings current mainline version
of arch/x86/include/asm/percpu.h to the version in the current tip tree.

Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
---
 arch/x86/include/asm/percpu.h | 110 ++++++++++++++++++++++++++++++++--
 1 file changed, 104 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 34734d730463..20624b80f890 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -210,6 +210,25 @@ do {									\
 	(typeof(_var))(unsigned long) pco_old__;			\
 })
 
+#define percpu_try_cmpxchg_op(size, qual, _var, _ovalp, _nval)		\
+({									\
+	bool success;							\
+	__pcpu_type_##size *pco_oval__ = (__pcpu_type_##size *)(_ovalp); \
+	__pcpu_type_##size pco_old__ = *pco_oval__;			\
+	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
+	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
+				    __percpu_arg([var]))		\
+		  CC_SET(z)						\
+		  : CC_OUT(z) (success),				\
+		    [oval] "+a" (pco_old__),				\
+		    [var] "+m" (_var)					\
+		  : [nval] __pcpu_reg_##size(, pco_new__)		\
+		  : "memory");						\
+	if (unlikely(!success))						\
+		*pco_oval__ = pco_old__;				\
+	likely(success);						\
+})
+
 #if defined(CONFIG_X86_32) && !defined(CONFIG_UML)
 #define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval)		\
 ({									\
@@ -223,26 +242,63 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("leal %P[var], %%esi; call this_cpu_cmpxchg8b_emu", \
+	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
 		  : [var] "+m" (_var),					\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
-		    "c" (new__.high)					\
-		  : "memory", "esi");					\
+		    "c" (new__.high),					\
+		    "S" (&(_var))					\
+		  : "memory");						\
 									\
 	old__.var;							\
 })
 
 #define raw_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg64_op(8,         , pcp, oval, nval)
 #define this_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg64_op(8, volatile, pcp, oval, nval)
+
+#define percpu_try_cmpxchg64_op(size, qual, _var, _ovalp, _nval)	\
+({									\
+	bool success;							\
+	u64 *_oval = (u64 *)(_ovalp);					\
+	union {								\
+		u64 var;						\
+		struct {						\
+			u32 low, high;					\
+		};							\
+	} old__, new__;							\
+									\
+	old__.var = *_oval;						\
+	new__.var = _nval;						\
+									\
+	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		  CC_SET(z)						\
+		  : CC_OUT(z) (success),				\
+		    [var] "+m" (_var),					\
+		    "+a" (old__.low),					\
+		    "+d" (old__.high)					\
+		  : "b" (new__.low),					\
+		    "c" (new__.high),					\
+		    "S" (&(_var))					\
+		  : "memory");						\
+	if (unlikely(!success))						\
+		*_oval = old__.var;					\
+	likely(success);						\
+})
+
+#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval)		percpu_try_cmpxchg64_op(8,         , pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval)	percpu_try_cmpxchg64_op(8, volatile, pcp, ovalp, nval)
 #endif
 
 #ifdef CONFIG_X86_64
 #define raw_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg_op(8,         , pcp, oval, nval);
 #define this_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval);
 
+#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval)		percpu_try_cmpxchg_op(8,         , pcp, ovalp, nval);
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval);
+
 #define percpu_cmpxchg128_op(size, qual, _var, _oval, _nval)		\
 ({									\
 	union {								\
@@ -255,20 +311,54 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("leaq %P[var], %%rsi; call this_cpu_cmpxchg16b_emu", \
+	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
 		  : [var] "+m" (_var),					\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
-		    "c" (new__.high)					\
-		  : "memory", "rsi");					\
+		    "c" (new__.high),					\
+		    "S" (&(_var))					\
+		  : "memory");						\
 									\
 	old__.var;							\
 })
 
 #define raw_cpu_cmpxchg128(pcp, oval, nval)	percpu_cmpxchg128_op(16,         , pcp, oval, nval)
 #define this_cpu_cmpxchg128(pcp, oval, nval)	percpu_cmpxchg128_op(16, volatile, pcp, oval, nval)
+
+#define percpu_try_cmpxchg128_op(size, qual, _var, _ovalp, _nval)	\
+({									\
+	bool success;							\
+	u128 *_oval = (u128 *)(_ovalp);					\
+	union {								\
+		u128 var;						\
+		struct {						\
+			u64 low, high;					\
+		};							\
+	} old__, new__;							\
+									\
+	old__.var = *_oval;						\
+	new__.var = _nval;						\
+									\
+	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		  CC_SET(z)						\
+		  : CC_OUT(z) (success),				\
+		    [var] "+m" (_var),					\
+		    "+a" (old__.low),					\
+		    "+d" (old__.high)					\
+		  : "b" (new__.low),					\
+		    "c" (new__.high),					\
+		    "S" (&(_var))					\
+		  : "memory");						\
+	if (unlikely(!success))						\
+		*_oval = old__.var;					\
+	likely(success);						\
+})
+
+#define raw_cpu_try_cmpxchg128(pcp, ovalp, nval)	percpu_try_cmpxchg128_op(16,         , pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg128(pcp, ovalp, nval)	percpu_try_cmpxchg128_op(16, volatile, pcp, ovalp, nval)
 #endif
 
 /*
@@ -343,6 +433,9 @@ do {									\
 #define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, , pcp, oval, nval)
 #define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, , pcp, oval, nval)
 #define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval)	percpu_try_cmpxchg_op(1, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval)	percpu_try_cmpxchg_op(2, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval)	percpu_try_cmpxchg_op(4, , pcp, ovalp, nval)
 
 #define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(1, volatile, pcp, val)
 #define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(2, volatile, pcp, val)
@@ -350,6 +443,9 @@ do {									\
 #define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval)	percpu_try_cmpxchg_op(1, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval)	percpu_try_cmpxchg_op(2, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval)	percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval)
 
 /*
  * Per cpu atomic 64 bit operations are only available under 64 bit.
@@ -364,6 +460,7 @@ do {									\
 #define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, , pcp, val)
 #define raw_cpu_xchg_8(pcp, nval)		raw_percpu_xchg_op(pcp, nval)
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
 
 #define this_cpu_read_8(pcp)			percpu_from_op(8, volatile, "mov", pcp)
 #define this_cpu_write_8(pcp, val)		percpu_to_op(8, volatile, "mov", (pcp), val)
@@ -373,6 +470,7 @@ do {									\
 #define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, volatile, pcp, val)
 #define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(8, volatile, pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
 #endif
 
 static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
-- 
2.41.0