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, 21 insertions, 177 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8d778e46725d..fcac875c3d79 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -74,186 +74,30 @@ do {									\
 	}								\
 } while (0)
 
-/*
- * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
- * that correspond to that nop. Getting from one nop to the next, we
- * add to the array the offset that is equal to the sum of all sizes of
- * nops preceding the one we are after.
- *
- * Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the
- * nice symmetry of sizes of the previous nops.
- */
-#if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64)
-static const unsigned char intelnops[] =
+const unsigned char x86nops[] =
 {
-	GENERIC_NOP1,
-	GENERIC_NOP2,
-	GENERIC_NOP3,
-	GENERIC_NOP4,
-	GENERIC_NOP5,
-	GENERIC_NOP6,
-	GENERIC_NOP7,
-	GENERIC_NOP8,
-	GENERIC_NOP5_ATOMIC
-};
-static const unsigned char * const intel_nops[ASM_NOP_MAX+2] =
-{
-	NULL,
-	intelnops,
-	intelnops + 1,
-	intelnops + 1 + 2,
-	intelnops + 1 + 2 + 3,
-	intelnops + 1 + 2 + 3 + 4,
-	intelnops + 1 + 2 + 3 + 4 + 5,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
+	BYTES_NOP1,
+	BYTES_NOP2,
+	BYTES_NOP3,
+	BYTES_NOP4,
+	BYTES_NOP5,
+	BYTES_NOP6,
+	BYTES_NOP7,
+	BYTES_NOP8,
 };
-#endif
 
-#ifdef K8_NOP1
-static const unsigned char k8nops[] =
-{
-	K8_NOP1,
-	K8_NOP2,
-	K8_NOP3,
-	K8_NOP4,
-	K8_NOP5,
-	K8_NOP6,
-	K8_NOP7,
-	K8_NOP8,
-	K8_NOP5_ATOMIC
-};
-static const unsigned char * const k8_nops[ASM_NOP_MAX+2] =
-{
-	NULL,
-	k8nops,
-	k8nops + 1,
-	k8nops + 1 + 2,
-	k8nops + 1 + 2 + 3,
-	k8nops + 1 + 2 + 3 + 4,
-	k8nops + 1 + 2 + 3 + 4 + 5,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
-};
-#endif
-
-#if defined(K7_NOP1) && !defined(CONFIG_X86_64)
-static const unsigned char k7nops[] =
-{
-	K7_NOP1,
-	K7_NOP2,
-	K7_NOP3,
-	K7_NOP4,
-	K7_NOP5,
-	K7_NOP6,
-	K7_NOP7,
-	K7_NOP8,
-	K7_NOP5_ATOMIC
-};
-static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
-{
-	NULL,
-	k7nops,
-	k7nops + 1,
-	k7nops + 1 + 2,
-	k7nops + 1 + 2 + 3,
-	k7nops + 1 + 2 + 3 + 4,
-	k7nops + 1 + 2 + 3 + 4 + 5,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
-};
-#endif
-
-#ifdef P6_NOP1
-static const unsigned char p6nops[] =
-{
-	P6_NOP1,
-	P6_NOP2,
-	P6_NOP3,
-	P6_NOP4,
-	P6_NOP5,
-	P6_NOP6,
-	P6_NOP7,
-	P6_NOP8,
-	P6_NOP5_ATOMIC
-};
-static const unsigned char * const p6_nops[ASM_NOP_MAX+2] =
+const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
 {
 	NULL,
-	p6nops,
-	p6nops + 1,
-	p6nops + 1 + 2,
-	p6nops + 1 + 2 + 3,
-	p6nops + 1 + 2 + 3 + 4,
-	p6nops + 1 + 2 + 3 + 4 + 5,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
+	x86nops,
+	x86nops + 1,
+	x86nops + 1 + 2,
+	x86nops + 1 + 2 + 3,
+	x86nops + 1 + 2 + 3 + 4,
+	x86nops + 1 + 2 + 3 + 4 + 5,
+	x86nops + 1 + 2 + 3 + 4 + 5 + 6,
+	x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
 };
-#endif
-
-/* Initialize these to a safe default */
-#ifdef CONFIG_X86_64
-const unsigned char * const *ideal_nops = p6_nops;
-#else
-const unsigned char * const *ideal_nops = intel_nops;
-#endif
-
-void __init arch_init_ideal_nops(void)
-{
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_INTEL:
-		/*
-		 * Due to a decoder implementation quirk, some
-		 * specific Intel CPUs actually perform better with
-		 * the "k8_nops" than with the SDM-recommended NOPs.
-		 */
-		if (boot_cpu_data.x86 == 6 &&
-		    boot_cpu_data.x86_model >= 0x0f &&
-		    boot_cpu_data.x86_model != 0x1c &&
-		    boot_cpu_data.x86_model != 0x26 &&
-		    boot_cpu_data.x86_model != 0x27 &&
-		    boot_cpu_data.x86_model < 0x30) {
-			ideal_nops = k8_nops;
-		} else if (boot_cpu_has(X86_FEATURE_NOPL)) {
-			   ideal_nops = p6_nops;
-		} else {
-#ifdef CONFIG_X86_64
-			ideal_nops = k8_nops;
-#else
-			ideal_nops = intel_nops;
-#endif
-		}
-		break;
-
-	case X86_VENDOR_HYGON:
-		ideal_nops = p6_nops;
-		return;
-
-	case X86_VENDOR_AMD:
-		if (boot_cpu_data.x86 > 0xf) {
-			ideal_nops = p6_nops;
-			return;
-		}
-
-		fallthrough;
-
-	default:
-#ifdef CONFIG_X86_64
-		ideal_nops = k8_nops;
-#else
-		if (boot_cpu_has(X86_FEATURE_K8))
-			ideal_nops = k8_nops;
-		else if (boot_cpu_has(X86_FEATURE_K7))
-			ideal_nops = k7_nops;
-		else
-			ideal_nops = intel_nops;
-#endif
-	}
-}
 
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
 static void __init_or_module add_nops(void *insns, unsigned int len)
@@ -262,7 +106,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 		unsigned int noplen = len;
 		if (noplen > ASM_NOP_MAX)
 			noplen = ASM_NOP_MAX;
-		memcpy(insns, ideal_nops[noplen], noplen);
+		memcpy(insns, x86_nops[noplen], noplen);
 		insns += noplen;
 		len -= noplen;
 	}
@@ -1302,13 +1146,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	default: /* assume NOP */
 		switch (len) {
 		case 2: /* NOP2 -- emulate as JMP8+0 */
-			BUG_ON(memcmp(emulate, ideal_nops[len], len));
+			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP8_INSN_OPCODE;
 			tp->rel32 = 0;
 			break;
 
 		case 5: /* NOP5 -- emulate as JMP32+0 */
-			BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], len));
+			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP32_INSN_OPCODE;
 			tp->rel32 = 0;
 			break;