x86: Remove dynamic NOP selection

This ensures that a NOP is a NOP and not a random other instruction that
is also a NOP. It allows simplification of dynamic code patching that
wants to verify existing code before writing new instructions (ftrace,
jump_label, static_call, etc..).

Differentiating on NOPs is not a feature.

This pessimises 32bit (DONTCARE) and 32bit on 64bit CPUs (CARELESS).
32bit is not a performance target.

Everything x86_64 since AMD K10 (2007) and Intel IvyBridge (2012) is
fine with using NOPL (as opposed to prefix NOP). And per FEATURE_NOPL
being required for x86_64, all x86_64 CPUs can use NOPL. So stop
caring about NOPs, simplify things and get on with life.

[ The problem seems to be that some uarchs can only decode NOPL on a
single front-end port while others have severe decode penalties for
excessive prefixes. All modern uarchs can handle both, except Atom,
which has prefix penalties. ]

[ Also, much doubt you can actually measure any of this on normal
workloads. ]

After this, FEATURE_NOPL is unused except for required-features for
x86_64. FEATURE_K8 is only used for PTI.

 [ bp: Kernel build measurements showed ~0.3s slowdown on Sandybridge
   which is hardly a slowdown. Get rid of X86_FEATURE_K7, while at it. ]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> # bpf
Acked-by: Linus Torvalds <torvalds@linuxfoundation.org>
Link: https://lkml.kernel.org/r/20210312115749.065275711@infradead.org

1 files changed, 55 insertions, 121 deletions

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 */