[PATCH v3 05/11] percpu: Wire up cmpxchg128

[Peter Zijlstra <peterz@infradead.org>]

In order to replace cmpxchg_double() with the newly minted
cmpxchg128() family of functions, wire it up in this_cpu_cmpxchg().

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/arm64/include/asm/percpu.h |   20 +++++++++++++
 arch/s390/include/asm/percpu.h  |   16 ++++++++++
 arch/x86/include/asm/percpu.h   |   59 ++++++++++++++++++++++++++++++++++++++++
 include/asm-generic/percpu.h    |   16 ++++++++++
 4 files changed, 111 insertions(+)

--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -140,6 +140,10 @@ PERCPU_RET_OP(add, add, ldadd)
  * re-enabling preemption for preemptible kernels, but doing that in a way
  * which builds inside a module would mean messing directly with the preempt
  * count. If you do this, peterz and tglx will hunt you down.
+ *
+ * Not to mention it'll break the actual preemption model for missing a
+ * preemption point when TIF_NEED_RESCHED gets set while preemption is
+ * disabled.
  */
 #define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)		\
 ({									\
@@ -240,6 +244,22 @@ PERCPU_RET_OP(add, add, ldadd)
 #define this_cpu_cmpxchg_8(pcp, o, n)	\
 	_pcp_protect_return(cmpxchg_relaxed, pcp, o, n)
 
+#define this_cpu_cmpxchg64(pcp, o, n)	this_cpu_cmpxchg_8(pcp, o, n)
+
+#define this_cpu_cmpxchg128(pcp, o, n)					\
+({									\
+	typedef typeof(pcp) pcp_op_T__;					\
+	u128 old__, new__, ret__;					\
+	pcp_op_T__ *ptr__;						\
+	old__ = o;							\
+	new__ = n;							\
+	preempt_disable_notrace();					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
+	ret__ = cmpxchg128_local((void *)ptr__, old__, new__);		\
+	preempt_enable_notrace();					\
+	ret__;								\
+})
+
 #ifdef __KVM_NVHE_HYPERVISOR__
 extern unsigned long __hyp_per_cpu_offset(unsigned int cpu);
 #define __per_cpu_offset
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -148,6 +148,22 @@
 #define this_cpu_cmpxchg_4(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval) arch_this_cpu_cmpxchg(pcp, oval, nval)
 
+#define this_cpu_cmpxchg64(pcp, o, n)	this_cpu_cmpxchg_8(pcp, o, n)
+
+#define this_cpu_cmpxchg128(pcp, oval, nval)				\
+({									\
+	typedef typeof(pcp) pcp_op_T__;					\
+	u128 old__, new__, ret__;					\
+	pcp_op_T__ *ptr__;						\
+	old__ = oval;							\
+	new__ = nval;							\
+	preempt_disable_notrace();					\
+	ptr__ = raw_cpu_ptr(&(pcp));					\
+	ret__ = cmpxchg128((void *)ptr__, old__, new__);		\
+	preempt_enable_notrace();					\
+	ret__;								\
+})
+
 #define arch_this_cpu_xchg(pcp, nval)					\
 ({									\
 	typeof(pcp) *ptr__;						\
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -210,6 +210,65 @@ do {									\
 	(typeof(_var))(unsigned long) pco_old__;			\
 })
 
+#if defined(CONFIG_X86_32) && defined(CONFIG_X86_CMPXCHG64)
+#define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval)		\
+({									\
+	union {								\
+		u64 var;						\
+		struct {						\
+			u32 low, high;					\
+		};							\
+	} old__, new__;							\
+									\
+	old__.var = _oval;						\
+	new__.var = _nval;						\
+									\
+	asm qual ("cmpxchg8b " __percpu_arg([var])			\
+		  : [var] "+m" (_var),					\
+		    "+a" (old__.low),					\
+		    "+d" (old__.high)					\
+		  : "b" (new__.low),					\
+		    "c" (new__.high)					\
+		  : "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)
+#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 percpu_cmpxchg128_op(size, qual, _var, _oval, _nval)		\
+({									\
+	union {								\
+		u128 var;						\
+		struct {						\
+			u64 low, high;					\
+		};							\
+	} old__, new__;							\
+									\
+	old__.var = _oval;						\
+	new__.var = _nval;						\
+									\
+	asm qual ("cmpxchg16b " __percpu_arg([var])			\
+		  : [var] "+m" (_var),					\
+		    "+a" (old__.low),					\
+		    "+d" (old__.high)					\
+		  : "b" (new__.low),					\
+		    "c" (new__.high)					\
+		  : "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)
+#endif
+
 /*
  * this_cpu_read() makes gcc load the percpu variable every time it is
  * accessed while this_cpu_read_stable() allows the value to be cached.
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -298,6 +298,14 @@ do {									\
 #define raw_cpu_cmpxchg_8(pcp, oval, nval) \
 	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
+#ifndef raw_cpu_cmpxchg64
+#define raw_cpu_cmpxchg64(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg128
+#define raw_cpu_cmpxchg128(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
 
 #ifndef raw_cpu_cmpxchg_double_1
 #define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \
@@ -423,6 +431,14 @@ do {									\
 #define this_cpu_cmpxchg_8(pcp, oval, nval) \
 	this_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
+#ifndef this_cpu_cmpxchg64
+#define this_cpu_cmpxchg64(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg128
+#define this_cpu_cmpxchg128(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
 
 #ifndef this_cpu_cmpxchg_double_1
 #define this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \