Re: [PATCH v3 3/4] x86/alternative: Rewrite optimize_nops() some

[Peter Zijlstra]

On Wed, Feb 08, 2023 at 09:29:23PM +0100, Peter Zijlstra wrote:

> As is, there were only a hand full of NOPs that turned into this jmp.d8
> thing on the defconfig+kvm_guest.config I build to test this -- it is by
> no means a common thing. And about half of them would be gone by
> extending the max nop length to at least 10 or so.
> 
> In fact, I did that patch once, lemme see if I still have it...

Even still applies too, lemme go test that.

Also, there's a bunch of alternatives() where we explicitly put in that
short jmp instead of taking the nops, see for example:

  $ git grep -i "alternative.*jmp" arch/x86/

---
Subject: x86_64: Longer NOPs
From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>


Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 arch/x86/include/asm/nops.h   |   13 +++++++++++--
 arch/x86/kernel/alternative.c |    8 ++++++++
 2 files changed, 19 insertions(+), 2 deletions(-)

--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -34,6 +34,8 @@
 #define BYTES_NOP7	0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
 #define BYTES_NOP8	0x3e,BYTES_NOP7
 
+#define ASM_NOP_MAX 8
+
 #else
 
 /*
@@ -47,6 +49,8 @@
  * 6: osp nopl 0x00(%eax,%eax,1)
  * 7: nopl 0x00000000(%eax)
  * 8: nopl 0x00000000(%eax,%eax,1)
+ * 9: cs nopl 0x00000000(%eax,%eax,1)
+ * 10: osp cs nopl 0x00000000(%eax,%eax,1)
  */
 #define BYTES_NOP1	0x90
 #define BYTES_NOP2	0x66,BYTES_NOP1
@@ -56,6 +60,13 @@
 #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
+#define BYTES_NOP9	0x2e,BYTES_NOP8
+#define BYTES_NOP10	0x66,BYTES_NOP9
+
+#define ASM_NOP9  _ASM_BYTES(BYTES_NOP9)
+#define ASM_NOP10 _ASM_BYTES(BYTES_NOP10)
+
+#define ASM_NOP_MAX 10
 
 #endif /* CONFIG_64BIT */
 
@@ -68,8 +79,6 @@
 #define ASM_NOP7 _ASM_BYTES(BYTES_NOP7)
 #define ASM_NOP8 _ASM_BYTES(BYTES_NOP8)
 
-#define ASM_NOP_MAX 8
-
 #ifndef __ASSEMBLY__
 extern const unsigned char * const x86_nops[];
 #endif
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -86,6 +86,10 @@ static const unsigned char x86nops[] =
 	BYTES_NOP6,
 	BYTES_NOP7,
 	BYTES_NOP8,
+#ifdef CONFIG_64BIT
+	BYTES_NOP9,
+	BYTES_NOP10,
+#endif
 };
 
 const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
@@ -99,6 +103,10 @@ const unsigned char * const x86_nops[ASM
 	x86nops + 1 + 2 + 3 + 4 + 5,
 	x86nops + 1 + 2 + 3 + 4 + 5 + 6,
 	x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+#ifdef CONFIG_64BIT
+	x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
+	x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8 + 9,
+#endif
 };
 
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */