Merge branch 'x86/cpu' into WIP.x86/core, to merge the NOP changes & resolve a semantic conflict

Conflict-merge this main commit in essence:

  a89dfde3dc3c: ("x86: Remove dynamic NOP selection")

With this upstream commit:

  b90829704780: ("bpf: Use NOP_ATOMIC5 instead of emit_nops(&prog, 5) for BPF_TRAMP_F_CALL_ORIG")

Semantic merge conflict:

  arch/x86/net/bpf_jit_comp.c

  - memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
  + memcpy(prog, x86_nops[5], X86_PATCH_SIZE);

Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 61 insertions, 133 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index b440c950246d..a0431935850f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -84,7 +84,7 @@
 
 /* CPU types for specific tunings: */
 #define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7			( 3*32+ 5) /* "" Athlon */
+/* FREE, was #define X86_FEATURE_K7			( 3*32+ 5) "" Athlon */
 #define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
 #define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 06c3cc22a058..5ce342b91ff3 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -6,12 +6,6 @@
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-#ifdef CONFIG_X86_64
-# define STATIC_KEY_INIT_NOP P6_NOP5_ATOMIC
-#else
-# define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC
-#endif
-
 #include <asm/asm.h>
 #include <asm/nops.h>
 
@@ -23,7 +17,7 @@
 static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:"
-		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
+		".byte " __stringify(BYTES_NOP5) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
 		".long 1b - ., %l[l_yes] - . \n\t"
@@ -63,7 +57,7 @@ l_yes:
 	.long		\target - .Lstatic_jump_after_\@
 .Lstatic_jump_after_\@:
 	.else
-	.byte		STATIC_KEY_INIT_NOP
+	.byte		BYTES_NOP5
 	.endif
 	.pushsection __jump_table, "aw"
 	_ASM_ALIGN
@@ -75,7 +69,7 @@ l_yes:
 .macro STATIC_JUMP_IF_FALSE target, key, def
 .Lstatic_jump_\@:
 	.if \def
-	.byte		STATIC_KEY_INIT_NOP
+	.byte		BYTES_NOP5
 	.else
 	/* Equivalent to "jmp.d32 \target" */
 	.byte		0xe9
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
index 12f12b5cf2ca..c1e5e818ba16 100644
--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -4,89 +4,58 @@
 
 /*
  * Define nops for use with alternative() and for tracing.
- *
- * *_NOP5_ATOMIC must be a single instruction.
  */
 
-#define NOP_DS_PREFIX 0x3e
+#ifndef CONFIG_64BIT
 
-/* generic versions from gas
-   1: nop
-   the following instructions are NOT nops in 64-bit mode,
-   for 64-bit mode use K8 or P6 nops instead
-   2: movl %esi,%esi
-   3: leal 0x00(%esi),%esi
-   4: leal 0x00(,%esi,1),%esi
-   6: leal 0x00000000(%esi),%esi
-   7: leal 0x00000000(,%esi,1),%esi
-*/
-#define GENERIC_NOP1 0x90
-#define GENERIC_NOP2 0x89,0xf6
-#define GENERIC_NOP3 0x8d,0x76,0x00
-#define GENERIC_NOP4 0x8d,0x74,0x26,0x00
-#define GENERIC_NOP5 GENERIC_NOP1,GENERIC_NOP4
-#define GENERIC_NOP6 0x8d,0xb6,0x00,0x00,0x00,0x00
-#define GENERIC_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
-#define GENERIC_NOP8 GENERIC_NOP1,GENERIC_NOP7
-#define GENERIC_NOP5_ATOMIC NOP_DS_PREFIX,GENERIC_NOP4
+/*
+ * Generic 32bit nops from GAS:
+ *
+ * 1: nop
+ * 2: movl %esi,%esi
+ * 3: leal 0x0(%esi),%esi
+ * 4: leal 0x0(%esi,%eiz,1),%esi
+ * 5: leal %ds:0x0(%esi,%eiz,1),%esi
+ * 6: leal 0x0(%esi),%esi
+ * 7: leal 0x0(%esi,%eiz,1),%esi
+ * 8: leal %ds:0x0(%esi,%eiz,1),%esi
+ *
+ * Except 5 and 8, which are DS prefixed 4 and 7 resp, where GAS would emit 2
+ * nop instructions.
+ */
+#define BYTES_NOP1	0x90
+#define BYTES_NOP2	0x89,0xf6
+#define BYTES_NOP3	0x8d,0x76,0x00
+#define BYTES_NOP4	0x8d,0x74,0x26,0x00
+#define BYTES_NOP5	0x3e,BYTES_NOP4
+#define BYTES_NOP6	0x8d,0xb6,0x00,0x00,0x00,0x00
+#define BYTES_NOP7	0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
+#define BYTES_NOP8	0x3e,BYTES_NOP7
 
-/* Opteron 64bit nops
-   1: nop
-   2: osp nop
-   3: osp osp nop
-   4: osp osp osp nop
-*/
-#define K8_NOP1 GENERIC_NOP1
-#define K8_NOP2	0x66,K8_NOP1
-#define K8_NOP3	0x66,K8_NOP2
-#define K8_NOP4	0x66,K8_NOP3
-#define K8_NOP5	K8_NOP3,K8_NOP2
-#define K8_NOP6	K8_NOP3,K8_NOP3
-#define K8_NOP7	K8_NOP4,K8_NOP3
-#define K8_NOP8	K8_NOP4,K8_NOP4
-#define K8_NOP5_ATOMIC 0x66,K8_NOP4
+#else
 
-/* K7 nops
-   uses eax dependencies (arbitrary choice)
-   1: nop
-   2: movl %eax,%eax
-   3: leal (,%eax,1),%eax
-   4: leal 0x00(,%eax,1),%eax
-   6: leal 0x00000000(%eax),%eax
-   7: leal 0x00000000(,%eax,1),%eax
-*/
-#define K7_NOP1	GENERIC_NOP1
-#define K7_NOP2	0x8b,0xc0
-#define K7_NOP3	0x8d,0x04,0x20
-#define K7_NOP4	0x8d,0x44,0x20,0x00
-#define K7_NOP5	K7_NOP4,K7_NOP1
-#define K7_NOP6	0x8d,0x80,0,0,0,0
-#define K7_NOP7	0x8D,0x04,0x05,0,0,0,0
-#define K7_NOP8	K7_NOP7,K7_NOP1
-#define K7_NOP5_ATOMIC NOP_DS_PREFIX,K7_NOP4
+/*
+ * Generic 64bit nops from GAS:
+ *
+ * 1: nop
+ * 2: osp nop
+ * 3: nopl (%eax)
+ * 4: nopl 0x00(%eax)
+ * 5: nopl 0x00(%eax,%eax,1)
+ * 6: osp nopl 0x00(%eax,%eax,1)
+ * 7: nopl 0x00000000(%eax)
+ * 8: nopl 0x00000000(%eax,%eax,1)
+ */
+#define BYTES_NOP1	0x90
+#define BYTES_NOP2	0x66,BYTES_NOP1
+#define BYTES_NOP3	0x0f,0x1f,0x00
+#define BYTES_NOP4	0x0f,0x1f,0x40,0x00
+#define BYTES_NOP5	0x0f,0x1f,0x44,0x00,0x00
+#define BYTES_NOP6	0x66,BYTES_NOP5
+#define BYTES_NOP7	0x0f,0x1f,0x80,0x00,0x00,0x00,0x00
+#define BYTES_NOP8	0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00
 
-/* P6 nops
-   uses eax dependencies (Intel-recommended choice)
-   1: nop
-   2: osp nop
-   3: nopl (%eax)
-   4: nopl 0x00(%eax)
-   5: nopl 0x00(%eax,%eax,1)
-   6: osp nopl 0x00(%eax,%eax,1)
-   7: nopl 0x00000000(%eax)
-   8: nopl 0x00000000(%eax,%eax,1)
-   Note: All the above are assumed to be a single instruction.
-	There is kernel code that depends on this.
-*/
-#define P6_NOP1	GENERIC_NOP1
-#define P6_NOP2	0x66,0x90
-#define P6_NOP3	0x0f,0x1f,0x00
-#define P6_NOP4	0x0f,0x1f,0x40,0
-#define P6_NOP5	0x0f,0x1f,0x44,0x00,0
-#define P6_NOP6	0x66,0x0f,0x1f,0x44,0x00,0
-#define P6_NOP7	0x0f,0x1f,0x80,0,0,0,0
-#define P6_NOP8	0x0f,0x1f,0x84,0x00,0,0,0,0
-#define P6_NOP5_ATOMIC P6_NOP5
+#endif /* CONFIG_64BIT */
 
 #ifdef __ASSEMBLY__
 #define _ASM_MK_NOP(x) .byte x
@@ -94,54 +63,19 @@
 #define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
 #endif
 
-#if defined(CONFIG_MK7)
-#define ASM_NOP1 _ASM_MK_NOP(K7_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(K7_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(K7_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(K7_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(K7_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(K7_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(K7_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(K7_NOP8)
-#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K7_NOP5_ATOMIC)
-#elif defined(CONFIG_X86_P6_NOP)
-#define ASM_NOP1 _ASM_MK_NOP(P6_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(P6_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(P6_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(P6_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(P6_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(P6_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(P6_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(P6_NOP8)
-#define ASM_NOP5_ATOMIC _ASM_MK_NOP(P6_NOP5_ATOMIC)
-#elif defined(CONFIG_X86_64)
-#define ASM_NOP1 _ASM_MK_NOP(K8_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(K8_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(K8_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(K8_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(K8_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(K8_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(K8_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(K8_NOP8)
-#define ASM_NOP5_ATOMIC _ASM_MK_NOP(K8_NOP5_ATOMIC)
-#else
-#define ASM_NOP1 _ASM_MK_NOP(GENERIC_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(GENERIC_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(GENERIC_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(GENERIC_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(GENERIC_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(GENERIC_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(GENERIC_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(GENERIC_NOP8)
-#define ASM_NOP5_ATOMIC _ASM_MK_NOP(GENERIC_NOP5_ATOMIC)
-#endif
+#define ASM_NOP1 _ASM_MK_NOP(BYTES_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(BYTES_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(BYTES_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(BYTES_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(BYTES_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(BYTES_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(BYTES_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(BYTES_NOP8)
 
 #define ASM_NOP_MAX 8
-#define NOP_ATOMIC5 (ASM_NOP_MAX+1)	/* Entry for the 5-byte atomic NOP */
 
 #ifndef __ASSEMBLY__
-extern const unsigned char * const *ideal_nops;
-extern void arch_init_ideal_nops(void);
+extern const unsigned char * const x86_nops[];
 #endif
 
 #endif /* _ASM_X86_NOPS_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 1d3cbaef4bb7..2acd6cb62328 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -214,7 +214,7 @@ static inline void clflush(volatile void *__p)
 
 static inline void clflushopt(volatile void *__p)
 {
-	alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0",
+	alternative_io(".byte 0x3e; clflush %P0",
 		       ".byte 0x66; clflush %P0",
 		       X86_FEATURE_CLFLUSHOPT,
 		       "+m" (*(volatile char __force *)__p));
@@ -225,7 +225,7 @@ static inline void clwb(volatile void *__p)
 	volatile struct { char x[64]; } *p = __p;
 
 	asm volatile(ALTERNATIVE_2(
-		".byte " __stringify(NOP_DS_PREFIX) "; clflush (%[pax])",
+		".byte 0x3e; clflush (%[pax])",
 		".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */
 		X86_FEATURE_CLFLUSHOPT,
 		".byte 0x66, 0x0f, 0xae, 0x30",  /* clwb (%%rax) */