x86/asm: Add MONITORX/MWAITX instruction support

AMD Carrizo processors (Family 15h, Models 60h-6fh) added a new
feature called MWAITX (MWAIT with extensions) as an extension to
MONITOR/MWAIT.

This new instruction controls a configurable timer which causes
the core to exit wait state on timer expiration, in addition to
"normal" MWAIT condition of reading from a monitored VA.

Compared to MONITOR/MWAIT, there are minor differences in opcode
and input parameters:

MWAITX ECX[1]: enable timer if set
MWAITX EBX[31:0]: max wait time expressed in SW P0 clocks ==
TSC. The software P0 frequency is the same as the TSC frequency.

                MWAIT                           MWAITX
opcode          0f 01 c9           |            0f 01 fb
ECX[0]                  value of RFLAGS.IF seen by instruction
ECX[1]          unused/#GP if set  |            enable timer if set
ECX[31:2]                     unused/#GP if set
EAX                           unused (reserve for hint)
EBX[31:0]       unused             |            max wait time (SW P0 == TSC)

                MONITOR                         MONITORX
opcode          0f 01 c8           |            0f 01 fa
EAX                     (logical) address to monitor
ECX                     #GP if not zero

Max timeout = EBX/(TSC frequency)

Signed-off-by: Huang Rui <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Cc: Aaron Lu <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andreas Herrmann <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Dirk Brandewie <[email protected]>
Cc: Fengguang Wu <[email protected]>
Cc: Frédéric Weisbecker <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: John Stultz <[email protected]>
Cc: Josh Triplett <[email protected]>
Cc: Len Brown <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Mike Galbraith <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Rafael J. Wysocki <[email protected]>
Cc: Ross Zwisler <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Tony Li <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

2 files changed, 46 insertions, 0 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3d6606fb97d0..a39e5708209b 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -176,6 +176,7 @@
 #define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
 #define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
 #define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 653dfa7662e1..c70689b5e5aa 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -14,6 +14,9 @@
 #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
 
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
@@ -23,6 +26,14 @@ static inline void __monitor(const void *eax, unsigned long ecx,
 		     :: "a" (eax), "c" (ecx), "d"(edx));
 }
 
+static inline void __monitorx(const void *eax, unsigned long ecx,
+			      unsigned long edx)
+{
+	/* "monitorx %eax, %ecx, %edx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xfa;"
+		     :: "a" (eax), "c" (ecx), "d"(edx));
+}
+
 static inline void __mwait(unsigned long eax, unsigned long ecx)
 {
 	/* "mwait %eax, %ecx;" */
@@ -30,6 +41,40 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 		     :: "a" (eax), "c" (ecx));
 }
 
+/*
+ * MWAITX allows for a timer expiration to get the core out a wait state in
+ * addition to the default MWAIT exit condition of a store appearing at a
+ * monitored virtual address.
+ *
+ * Registers:
+ *
+ * MWAITX ECX[1]: enable timer if set
+ * MWAITX EBX[31:0]: max wait time expressed in SW P0 clocks. The software P0
+ * frequency is the same as the TSC frequency.
+ *
+ * Below is a comparison between MWAIT and MWAITX on AMD processors:
+ *
+ *                 MWAIT                           MWAITX
+ * opcode          0f 01 c9           |            0f 01 fb
+ * ECX[0]                  value of RFLAGS.IF seen by instruction
+ * ECX[1]          unused/#GP if set  |            enable timer if set
+ * ECX[31:2]                     unused/#GP if set
+ * EAX                           unused (reserve for hint)
+ * EBX[31:0]       unused             |            max wait time (P0 clocks)
+ *
+ *                 MONITOR                         MONITORX
+ * opcode          0f 01 c8           |            0f 01 fa
+ * EAX                     (logical) address to monitor
+ * ECX                     #GP if not zero
+ */
+static inline void __mwaitx(unsigned long eax, unsigned long ebx,
+			    unsigned long ecx)
+{
+	/* "mwaitx %eax, %ebx, %ecx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xfb;"
+		     :: "a" (eax), "b" (ebx), "c" (ecx));
+}
+
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
 	trace_hardirqs_on();