x86: re-work memset()

Move the function to its own assembly file. Having it in C just for the
entire body to be an asm() isn't really helpful. Then have two flavors:
A "basic" version using qword steps for the bulk of the operation, and an
ERMS version for modern hardware, to be substituted in via alternatives
patching.

For RET to be usable in an alternative's replacement code, extend the
CALL/JMP patching to cover the case of "JMP __x86_return_thunk" coming
last in replacement code.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Jason Andryuk <jason.andryuk@amd.com>

xen/arch/x86/Makefile

@@ -47,6 +47,7 @@ obj-$(CONFIG_RETURN_THUNK) += indirect-thunk.o
 obj-$(CONFIG_PV) += ioport_emulate.o
 obj-y += irq.o
 obj-$(CONFIG_KEXEC) += machine_kexec.o
+obj-y += memset.o
 obj-y += mm.o x86_64/mm.o
 obj-$(CONFIG_VM_EVENT) += monitor.o
 obj-y += mpparse.o

xen/arch/x86/alternative.c

@@ -351,6 +351,12 @@ static int init_or_livepatch _apply_alternatives(struct alt_instr *start,
         /* 0xe8/0xe9 are relative branches; fix the offset. */
         if ( a->repl_len >= 5 && (*buf & 0xfe) == 0xe8 )
             *(int32_t *)(buf + 1) += repl - orig;
+        else if ( IS_ENABLED(CONFIG_RETURN_THUNK) &&
+                  a->repl_len > 5 && buf[a->repl_len - 5] == 0xe9 &&
+                  ((long)repl + a->repl_len +
+                   *(int32_t *)(buf + a->repl_len - 4) ==
+                   (long)__x86_return_thunk) )
+            *(int32_t *)(buf + a->repl_len - 4) += repl - orig;
 
         a->priv = 1;
 

xen/arch/x86/memset.S

@@ -0,0 +1,30 @@
+#include <asm/asm_defns.h>
+
+.macro memset
+        and     $7, %edx
+        shr     $3, %rcx
+        movzbl  %sil, %esi
+        mov     $0x0101010101010101, %rax
+        imul    %rsi, %rax
+        mov     %rdi, %r8
+        rep stosq
+        or      %edx, %ecx
+        jz      0f
+        rep stosb
+0:
+        mov     %r8, %rax
+        RET
+.endm
+
+.macro memset_erms
+        mov     %esi, %eax
+        mov     %rdi, %r8
+        rep stosb
+        mov     %r8, %rax
+        RET
+.endm
+
+FUNC(memset)
+        mov     %rdx, %rcx
+        ALTERNATIVE memset, memset_erms, X86_FEATURE_ERMS
+END(memset)

xen/arch/x86/string.c

@@ -22,19 +22,6 @@ void *(memcpy)(void *dest, const void *src, size_t n)
     return dest;
 }
 
-void *(memset)(void *s, int c, size_t n)
-{
-    long d0, d1;
-
-    asm volatile (
-        "rep stosb"
-        : "=&c" (d0), "=&D" (d1)
-        : "a" (c), "1" (s), "0" (n)
-        : "memory");
-
-    return s;
-}
-
 void *(memmove)(void *dest, const void *src, size_t n)
 {
     long d0, d1, d2;