1 files changed, 70 insertions, 35 deletions

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index bda3c27f0da0..e4815e15dc9a 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_MWAIT_H
 #define _ASM_X86_MWAIT_H
 
@@ -5,43 +6,46 @@
 #include <linux/sched/idle.h>
 
 #include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
 
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
 #define MWAIT_SUBSTATE_SIZE		4
 #define MWAIT_HINT2CSTATE(hint)		(((hint) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK)
 #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
 
 #define MWAIT_ECX_INTERRUPT_BREAK	0x1
 #define MWAITX_ECX_TIMER_ENABLE		BIT(1)
-#define MWAITX_MAX_LOOPS		((u32)-1)
-#define MWAITX_DISABLE_CSTATES		0xf
+#define MWAITX_MAX_WAIT_CYCLES		UINT_MAX
+#define MWAITX_DISABLE_CSTATES		0xf0
+#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)
 {
-	/* "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));
 }
 
 /*
@@ -70,20 +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)
 {
-	/* "mwaitx %eax, %ebx, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xfb;"
-		     :: "a" (eax), "b" (ebx), "c" (ecx));
+	/* No need for TSA buffer clearing on AMD */
+
+	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)
 {
-	trace_hardirqs_on();
-	/* "mwait %eax, %ecx;" */
-	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
+
+	asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
 }
 
 /*
@@ -96,20 +106,45 @@ 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();
 }
 
+/*
+ * Caller can specify whether to enter C0.1 (low latency, less
+ * power saving) or C0.2 state (saves more power, but longer wakeup
+ * latency). This may be overridden by the IA32_UMWAIT_CONTROL MSR
+ * which can force requests for C0.2 to be downgraded to C0.1.
+ */
+static inline void __tpause(u32 ecx, u32 edx, u32 eax)
+{
+	/* "tpause %ecx" */
+	asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1"
+		     :: "c" (ecx), "d" (edx), "a" (eax));
+}
+
 #endif /* _ASM_X86_MWAIT_H */