Merge tag 'x86_alternatives_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 instruction alternatives updates from Borislav Petkov:

 - Up until now the Fast Short Rep Mov optimizations implied the
   presence of the ERMS CPUID flag. AMD decoupled them with a BIOS
   setting so decouple that dependency in the kernel code too

 - Teach the alternatives machinery to handle relocations

 - Make debug_alternative accept flags in order to see only that set of
   patching done one is interested in

 - Other fixes, cleanups and optimizations to the patching code

* tag 'x86_alternatives_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/alternative: PAUSE is not a NOP
  x86/alternatives: Add cond_resched() to text_poke_bp_batch()
  x86/nospec: Shorten RESET_CALL_DEPTH
  x86/alternatives: Add longer 64-bit NOPs
  x86/alternatives: Fix section mismatch warnings
  x86/alternative: Optimize returns patching
  x86/alternative: Complicate optimize_nops() some more
  x86/alternative: Rewrite optimize_nops() some
  x86/lib/memmove: Decouple ERMS from FSRM
  x86/alternative: Support relocations in alternatives
  x86/alternative: Make debug-alternative selective

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 +49,9 @@
  * 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)
+ * 11: osp osp cs nopl 0x00000000(%eax,%eax,1)
  */
 #define BYTES_NOP1	0x90
 #define BYTES_NOP2	0x66,BYTES_NOP1
@@ -56,6 +61,15 @@
 #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 BYTES_NOP11	0x66,BYTES_NOP10
+
+#define ASM_NOP9  _ASM_BYTES(BYTES_NOP9)
+#define ASM_NOP10 _ASM_BYTES(BYTES_NOP10)
+#define ASM_NOP11 _ASM_BYTES(BYTES_NOP11)
+
+#define ASM_NOP_MAX 11
 
 #endif /* CONFIG_64BIT */
 
@@ -68,8 +82,6 @@
 #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

arch/x86/include/asm/nospec-branch.h

@@ -84,12 +84,12 @@
 	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
 
 #define RESET_CALL_DEPTH					\
-	mov	$0x80, %rax;					\
-	shl	$56, %rax;					\
+	xor	%eax, %eax;					\
+	bts	$63, %rax;					\
 	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);
 
 #define RESET_CALL_DEPTH_FROM_CALL				\
-	mov	$0xfc, %rax;					\
+	movb	$0xfc, %al;					\
 	shl	$56, %rax;					\
 	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
 	CALL_THUNKS_DEBUG_INC_CALLS

arch/x86/lib/memmove_64.S

@@ -38,10 +38,12 @@ SYM_FUNC_START(__memmove)
 	cmp %rdi, %r8
 	jg 2f
 
-	/* FSRM implies ERMS => no length checks, do the copy directly */
+#define CHECK_LEN	cmp $0x20, %rdx; jb 1f
+#define MEMMOVE_BYTES	movq %rdx, %rcx; rep movsb; RET
 .Lmemmove_begin_forward:
-	ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM
-	ALTERNATIVE "", "jmp .Lmemmove_erms", X86_FEATURE_ERMS
+	ALTERNATIVE_2 __stringify(CHECK_LEN), \
+		      __stringify(CHECK_LEN; MEMMOVE_BYTES), X86_FEATURE_ERMS, \
+		      __stringify(MEMMOVE_BYTES), X86_FEATURE_FSRM
 
 	/*
 	 * movsq instruction have many startup latency
@@ -207,11 +209,6 @@ SYM_FUNC_START(__memmove)
 	movb %r11b, (%rdi)
 13:
 	RET
-
-.Lmemmove_erms:
-	movq %rdx, %rcx
-	rep movsb
-	RET
 SYM_FUNC_END(__memmove)
 EXPORT_SYMBOL(__memmove)
 

tools/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 +49,9 @@
  * 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)
+ * 11: osp osp cs nopl 0x00000000(%eax,%eax,1)
  */
 #define BYTES_NOP1	0x90
 #define BYTES_NOP2	0x66,BYTES_NOP1
@@ -56,6 +61,15 @@
 #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 BYTES_NOP11	0x66,BYTES_NOP10
+
+#define ASM_NOP9  _ASM_BYTES(BYTES_NOP9)
+#define ASM_NOP10 _ASM_BYTES(BYTES_NOP10)
+#define ASM_NOP11 _ASM_BYTES(BYTES_NOP11)
+
+#define ASM_NOP_MAX 11
 
 #endif /* CONFIG_64BIT */
 
@@ -68,8 +82,6 @@
 #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

tools/objtool/arch/x86/special.c

@@ -42,13 +42,7 @@ bool arch_support_alt_relocation(struct special_alt *special_alt,
 				 struct instruction *insn,
 				 struct reloc *reloc)
 {
-	/*
-	 * The x86 alternatives code adjusts the offsets only when it
-	 * encounters a branch instruction at the very beginning of the
-	 * replacement group.
-	 */
-	return insn->offset == special_alt->new_off &&
-	       (insn->type == INSN_CALL || is_jump(insn));
+	return true;
 }
 
 /*