1 files changed, 52 insertions, 46 deletions

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 3a8fdf881313..e4815e15dc9a 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -15,7 +15,6 @@
 #define MWAIT_HINT2SUBSTATE(hint)	((hint) & MWAIT_CSTATE_MASK)
 #define MWAIT_C1_SUBSTATE_MASK  0xf0
 
-#define CPUID_MWAIT_LEAF		5
 #define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1
 #define CPUID5_ECX_INTERRUPT_BREAK	0x2
 
@@ -26,29 +25,27 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-static inline void __monitor(const void *eax, unsigned long ecx,
-			     unsigned long edx)
+static __always_inline void __monitor(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitor %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc8;"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
+	/*
+	 * Use the instruction mnemonic with implicit operands, as the LLVM
+	 * assembler fails to assemble the mnemonic with explicit operands:
+	 */
+	asm volatile("monitor" :: "a" (eax), "c" (ecx), "d" (edx));
 }
 
-static inline void __monitorx(const void *eax, unsigned long ecx,
-			      unsigned long edx)
+static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
 {
-	/* "monitorx %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfa;"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
+	asm volatile("monitorx" :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
-static inline void __mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __mwait(u32 eax, u32 ecx)
 {
-	mds_idle_clear_cpu_buffers();
-
-	/* "mwait %eax, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+	/*
+	 * Use the instruction mnemonic with implicit operands, as the LLVM
+	 * assembler fails to assemble the mnemonic with explicit operands:
+	 */
+	asm volatile("mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -77,22 +74,26 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
  * EAX                     (logical) address to monitor
  * ECX                     #GP if not zero
  */
-static inline void __mwaitx(unsigned long eax, unsigned long ebx,
-			    unsigned long ecx)
+static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
 {
-	/* No MDS buffer clear as this is AMD/HYGON only */
+	/* No need for TSA buffer clearing on AMD */
 
-	/* "mwaitx %eax, %ebx, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfb;"
-		     :: "a" (eax), "b" (ebx), "c" (ecx));
+	asm volatile("mwaitx" :: "a" (eax), "b" (ebx), "c" (ecx));
 }
 
-static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+/*
+ * Re-enable interrupts right upon calling mwait in such a way that
+ * no interrupt can fire _before_ the execution of mwait, ie: no
+ * instruction must be placed between "sti" and "mwait".
+ *
+ * This is necessary because if an interrupt queues a timer before
+ * executing mwait, it would otherwise go unnoticed and the next tick
+ * would not be reprogrammed accordingly before mwait ever wakes up.
+ */
+static __always_inline void __sti_mwait(u32 eax, u32 ecx)
 {
-	mds_idle_clear_cpu_buffers();
-	/* "mwait %eax, %ecx;" */
-	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+
+	asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -105,19 +106,31 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
  * New with Core Duo processors, MWAIT can take some hints based on CPU
  * capability.
  */
-static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
+static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
 {
+	if (need_resched())
+		return;
+
+	x86_idle_clear_cpu_buffers();
+
 	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
-		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
-			mb();
-			clflush((void *)&current_thread_info()->flags);
-			mb();
-		}
+		const void *addr = &current_thread_info()->flags;
+
+		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+		__monitor(addr, 0, 0);
 
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		if (!need_resched())
+		if (need_resched())
+			goto out;
+
+		if (ecx & 1) {
 			__mwait(eax, ecx);
+		} else {
+			__sti_mwait(eax, ecx);
+			raw_local_irq_disable();
+		}
 	}
+
+out:
 	current_clr_polling();
 }
 
@@ -129,16 +142,9 @@ static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
  */
 static inline void __tpause(u32 ecx, u32 edx, u32 eax)
 {
-	/* "tpause %ecx, %edx, %eax;" */
-	#ifdef CONFIG_AS_TPAUSE
-	asm volatile("tpause %%ecx\n"
-		     :
-		     : "c"(ecx), "d"(edx), "a"(eax));
-	#else
-	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1\t\n"
-		     :
-		     : "c"(ecx), "d"(edx), "a"(eax));
-	#endif
+	/* "tpause %ecx" */
+	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1"
+		     :: "c" (ecx), "d" (edx), "a" (eax));
 }
 
 #endif /* _ASM_X86_MWAIT_H */