Merge branch 'x86-alternatives-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 alternative instruction updates from Ingo Molnar:
 "Small RDTSCP opimization, enabled by the newly added ALTERNATIVE_3(),
  and other small improvements"

* 'x86-alternatives-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/TSC: Use RDTSCP
  x86/alternatives: Add an ALTERNATIVE_3() macro
  x86/alternatives: Print containing function
  x86/alternatives: Add macro comments

arch/x86/include/asm/alternative.h

@@ -94,13 +94,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
 #define alt_total_slen		alt_end_marker"b-661b"
 #define alt_rlen(num)		e_replacement(num)"f-"b_replacement(num)"f"
 
-#define __OLDINSTR(oldinstr, num)					\
+#define OLDINSTR(oldinstr, num)						\
+	"# ALT: oldnstr\n"						\
 	"661:\n\t" oldinstr "\n662:\n"					\
+	"# ALT: padding\n"						\
 	".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * "		\
-		"((" alt_rlen(num) ")-(" alt_slen ")),0x90\n"
-
-#define OLDINSTR(oldinstr, num)						\
-	__OLDINSTR(oldinstr, num)					\
+		"((" alt_rlen(num) ")-(" alt_slen ")),0x90\n"		\
 	alt_end_marker ":\n"
 
 /*
@@ -116,11 +115,23 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * additionally longer than the first replacement alternative.
  */
 #define OLDINSTR_2(oldinstr, num1, num2) \
+	"# ALT: oldinstr2\n"									\
 	"661:\n\t" oldinstr "\n662:\n"								\
+	"# ALT: padding2\n"									\
 	".skip -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * "	\
 		"(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n"	\
 	alt_end_marker ":\n"
 
+#define OLDINSTR_3(oldinsn, n1, n2, n3)								\
+	"# ALT: oldinstr3\n"									\
+	"661:\n\t" oldinsn "\n662:\n"								\
+	"# ALT: padding3\n"									\
+	".skip -((" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3))	\
+		" - (" alt_slen ")) > 0) * "							\
+		"(" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3))	\
+		" - (" alt_slen ")), 0x90\n"							\
+	alt_end_marker ":\n"
+
 #define ALTINSTR_ENTRY(feature, num)					      \
 	" .long 661b - .\n"				/* label           */ \
 	" .long " b_replacement(num)"f - .\n"		/* new instruction */ \
@@ -129,8 +140,9 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	" .byte " alt_rlen(num) "\n"			/* replacement len */ \
 	" .byte " alt_pad_len "\n"			/* pad len */
 
-#define ALTINSTR_REPLACEMENT(newinstr, feature, num)	/* replacement */     \
-	b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t"
+#define ALTINSTR_REPLACEMENT(newinstr, feature, num)	/* replacement */	\
+	"# ALT: replacement " #num "\n"						\
+	b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n"
 
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, newinstr, feature)			\
@@ -153,6 +165,19 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
 	".popsection\n"
 
+#define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \
+	OLDINSTR_3(oldinsn, 1, 2, 3)						\
+	".pushsection .altinstructions,\"a\"\n"					\
+	ALTINSTR_ENTRY(feat1, 1)						\
+	ALTINSTR_ENTRY(feat2, 2)						\
+	ALTINSTR_ENTRY(feat3, 3)						\
+	".popsection\n"								\
+	".pushsection .altinstr_replacement, \"ax\"\n"				\
+	ALTINSTR_REPLACEMENT(newinsn1, feat1, 1)				\
+	ALTINSTR_REPLACEMENT(newinsn2, feat2, 2)				\
+	ALTINSTR_REPLACEMENT(newinsn3, feat3, 3)				\
+	".popsection\n"
+
 /*
  * Alternative instructions for different CPU types or capabilities.
  *

arch/x86/include/asm/msr.h

@@ -217,6 +217,8 @@ static __always_inline unsigned long long rdtsc(void)
  */
 static __always_inline unsigned long long rdtsc_ordered(void)
 {
+	DECLARE_ARGS(val, low, high);
+
 	/*
 	 * The RDTSC instruction is not ordered relative to memory
 	 * access.  The Intel SDM and the AMD APM are both vague on this
@@ -227,9 +229,19 @@ static __always_inline unsigned long long rdtsc_ordered(void)
 	 * ordering guarantees as reading from a global memory location
 	 * that some other imaginary CPU is updating continuously with a
 	 * time stamp.
+	 *
+	 * Thus, use the preferred barrier on the respective CPU, aiming for
+	 * RDTSCP as the default.
 	 */
-	barrier_nospec();
-	return rdtsc();
+	asm volatile(ALTERNATIVE_3("rdtsc",
+				   "mfence; rdtsc", X86_FEATURE_MFENCE_RDTSC,
+				   "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC,
+				   "rdtscp", X86_FEATURE_RDTSCP)
+			: EAX_EDX_RET(val, low, high)
+			/* RDTSCP clobbers ECX with MSR_TSC_AUX. */
+			:: "ecx");
+
+	return EAX_EDX_VAL(val, low, high);
 }
 
 static inline unsigned long long native_read_pmc(int counter)

arch/x86/kernel/alternative.c

@@ -394,10 +394,10 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 			continue;
 		}
 
-		DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d",
+		DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
 			a->cpuid >> 5,
 			a->cpuid & 0x1f,
-			instr, a->instrlen,
+			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->padlen);
 
 		DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);