3 files changed, 84 insertions, 27 deletions
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fc9fb5d06174..b8f74d80f35c 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -74,6 +74,24 @@ SYM_FUNC_START(rep_movs_alternative)
 	_ASM_EXTABLE_UA( 0b, 1b)
 
 .Llarge_movsq:
+	/* Do the first possibly unaligned word */
+0:	movq (%rsi),%rax
+1:	movq %rax,(%rdi)
+
+	_ASM_EXTABLE_UA( 0b, .Lcopy_user_tail)
+	_ASM_EXTABLE_UA( 1b, .Lcopy_user_tail)
+
+	/* What would be the offset to the aligned destination? */
+	leaq 8(%rdi),%rax
+	andq $-8,%rax
+	subq %rdi,%rax
+
+	/* .. and update pointers and count to match */
+	addq %rax,%rdi
+	addq %rax,%rsi
+	subq %rax,%rcx
+
+	/* make %rcx contain the number of words, %rax the remainder */
 	movq %rcx,%rax
 	shrq $3,%rcx
 	andl $7,%eax
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 391059b2c6fb..614fb9aee2ff 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -366,6 +366,45 @@ SYM_FUNC_END(call_depth_return_thunk)
 
 #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
 
+#ifdef CONFIG_MITIGATION_ITS
+
+.macro ITS_THUNK reg
+
+SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_UNDEFINED
+	ANNOTATE_NOENDBR
+	ANNOTATE_RETPOLINE_SAFE
+	jmp *%\reg
+	int3
+	.align 32, 0xcc		/* fill to the end of the line */
+	.skip  32, 0xcc		/* skip to the next upper half */
+.endm
+
+/* ITS mitigation requires thunks be aligned to upper half of cacheline */
+.align 64, 0xcc
+.skip 32, 0xcc
+SYM_CODE_START(__x86_indirect_its_thunk_array)
+
+#define GEN(reg) ITS_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+	.align 64, 0xcc
+SYM_CODE_END(__x86_indirect_its_thunk_array)
+
+.align 64, 0xcc
+.skip 32, 0xcc
+SYM_CODE_START(its_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_CODE_END(its_return_thunk)
+EXPORT_SYMBOL(its_return_thunk)
+
+#endif /* CONFIG_MITIGATION_ITS */
+
 /*
  * This function name is magical and is used by -mfunction-return=thunk-extern
  * for the compiler to generate JMPs to it.
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index caedb3ef6688..cd3fd5155f6e 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -35,7 +35,7 @@
 #  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
 #  - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
 #
-# REX2 Prefix
+# REX2 Prefix Superscripts
 #  - (!REX2): REX2 is not allowed
 #  - (REX2): REX2 variant e.g. JMPABS
 
@@ -286,10 +286,10 @@ df: ESC
 # Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
 # in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
 # to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64) (!REX2)
-e1: LOOPE/LOOPZ Jb (f64) (!REX2)
-e2: LOOP Jb (f64) (!REX2)
-e3: JrCXZ Jb (f64) (!REX2)
+e0: LOOPNE/LOOPNZ Jb (f64),(!REX2)
+e1: LOOPE/LOOPZ Jb (f64),(!REX2)
+e2: LOOP Jb (f64),(!REX2)
+e3: JrCXZ Jb (f64),(!REX2)
 e4: IN AL,Ib (!REX2)
 e5: IN eAX,Ib (!REX2)
 e6: OUT Ib,AL (!REX2)
@@ -298,10 +298,10 @@ e7: OUT Ib,eAX (!REX2)
 # in "near" jumps and calls is 16-bit. For CALL,
 # push of return address is 16-bit wide, RSP is decremented by 2
 # but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64) (!REX2)
-e9: JMP-near Jz (f64) (!REX2)
-ea: JMP-far Ap (i64) (!REX2)
-eb: JMP-short Jb (f64) (!REX2)
+e8: CALL Jz (f64),(!REX2)
+e9: JMP-near Jz (f64),(!REX2)
+ea: JMP-far Ap (i64),(!REX2)
+eb: JMP-short Jb (f64),(!REX2)
 ec: IN AL,DX (!REX2)
 ed: IN eAX,DX (!REX2)
 ee: OUT DX,AL (!REX2)
@@ -478,22 +478,22 @@ AVXcode: 1
 7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
 # 0x0f 0x80-0x8f
 # Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64) (!REX2)
-81: JNO Jz (f64) (!REX2)
-82: JB/JC/JNAE Jz (f64) (!REX2)
-83: JAE/JNB/JNC Jz (f64) (!REX2)
-84: JE/JZ Jz (f64) (!REX2)
-85: JNE/JNZ Jz (f64) (!REX2)
-86: JBE/JNA Jz (f64) (!REX2)
-87: JA/JNBE Jz (f64) (!REX2)
-88: JS Jz (f64) (!REX2)
-89: JNS Jz (f64) (!REX2)
-8a: JP/JPE Jz (f64) (!REX2)
-8b: JNP/JPO Jz (f64) (!REX2)
-8c: JL/JNGE Jz (f64) (!REX2)
-8d: JNL/JGE Jz (f64) (!REX2)
-8e: JLE/JNG Jz (f64) (!REX2)
-8f: JNLE/JG Jz (f64) (!REX2)
+80: JO Jz (f64),(!REX2)
+81: JNO Jz (f64),(!REX2)
+82: JB/JC/JNAE Jz (f64),(!REX2)
+83: JAE/JNB/JNC Jz (f64),(!REX2)
+84: JE/JZ Jz (f64),(!REX2)
+85: JNE/JNZ Jz (f64),(!REX2)
+86: JBE/JNA Jz (f64),(!REX2)
+87: JA/JNBE Jz (f64),(!REX2)
+88: JS Jz (f64),(!REX2)
+89: JNS Jz (f64),(!REX2)
+8a: JP/JPE Jz (f64),(!REX2)
+8b: JNP/JPO Jz (f64),(!REX2)
+8c: JL/JNGE Jz (f64),(!REX2)
+8d: JNL/JGE Jz (f64),(!REX2)
+8e: JLE/JNG Jz (f64),(!REX2)
+8f: JNLE/JG Jz (f64),(!REX2)
 # 0x0f 0x90-0x9f
 90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
 91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
@@ -996,8 +996,8 @@ AVXcode: 4
 83: Grp1 Ev,Ib (1A),(es)
 # CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
 #			     CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
 88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
 8f: POP2 Bq,Rq (000),(11B),(ev)
 a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)