x86/paravirt: Use relative reference for the original instruction offset

Similar to the alternative patching, use a relative reference for original
instruction offset rather than absolute one, which saves 8 bytes for one
PARA_SITE entry on x86_64.  As a result, a R_X86_64_PC32 relocation is
generated instead of an R_X86_64_64 one, which also reduces relocation
metadata on relocatable builds. Hardcode the alignment to 4 now.

  [ bp: Massage commit message. ]
Signed-off-by: Hou Wenlong <houwenlong.hwl@antgroup.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/9e6053107fbaabc0d33e5d2865c5af2c67ec9925.1686301237.git.houwenlong.hwl@antgroup.com

arch/x86/include/asm/paravirt.h

@@ -743,16 +743,16 @@ void native_pv_lock_init(void) __init;
 
 #else  /* __ASSEMBLY__ */
 
-#define _PVSITE(ptype, ops, word, algn)		\
+#define _PVSITE(ptype, ops)			\
 771:;						\
 	ops;					\
 772:;						\
 	.pushsection .parainstructions,"a";	\
-	 .align	algn;				\
-	 word 771b;				\
+	 .align	4;				\
+	 .long 771b-.;				\
 	 .byte ptype;				\
 	 .byte 772b-771b;			\
-	 _ASM_ALIGN;				\
+	 .align 4;				\
 	.popsection
 
 
@@ -760,7 +760,7 @@ void native_pv_lock_init(void) __init;
 #ifdef CONFIG_PARAVIRT_XXL
 
 #define PARA_PATCH(off)		((off) / 8)
-#define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops, .quad, 8)
+#define PARA_SITE(ptype, ops)	_PVSITE(ptype, ops)
 #define PARA_INDIRECT(addr)	*addr(%rip)
 
 #ifdef CONFIG_DEBUG_ENTRY

arch/x86/include/asm/paravirt_types.h

@@ -5,7 +5,7 @@
 #ifndef __ASSEMBLY__
 /* These all sit in the .parainstructions section to tell us what to patch. */
 struct paravirt_patch_site {
-	u8 *instr;		/* original instructions */
+	s32 instr_offset;	/* original instructions */
 	u8 type;		/* type of this instruction */
 	u8 len;			/* length of original instruction */
 };
@@ -263,11 +263,11 @@ extern struct paravirt_patch_template pv_ops;
 #define _paravirt_alt(insn_string, type)		\
 	"771:\n\t" insn_string "\n" "772:\n"		\
 	".pushsection .parainstructions,\"a\"\n"	\
-	_ASM_ALIGN "\n"					\
-	_ASM_PTR " 771b\n"				\
+	"  .align 4\n"					\
+	"  .long 771b-.\n"				\
 	"  .byte " type "\n"				\
 	"  .byte 772b-771b\n"				\
-	_ASM_ALIGN "\n"					\
+	"  .align 4\n"					\
 	".popsection\n"
 
 /* Generate patchable code, with the default asm parameters. */

arch/x86/kernel/alternative.c

@@ -1431,20 +1431,22 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
 {
 	struct paravirt_patch_site *p;
 	char insn_buff[MAX_PATCH_LEN];
+	u8 *instr;
 
 	for (p = start; p < end; p++) {
 		unsigned int used;
 
+		instr = (u8 *)&p->instr_offset + p->instr_offset;
 		BUG_ON(p->len > MAX_PATCH_LEN);
 		/* prep the buffer with the original instructions */
-		memcpy(insn_buff, p->instr, p->len);
-		used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
+		memcpy(insn_buff, instr, p->len);
+		used = paravirt_patch(p->type, insn_buff, (unsigned long)instr, p->len);
 
 		BUG_ON(used > p->len);
 
 		/* Pad the rest with nops */
 		add_nops(insn_buff + used, p->len - used);
-		text_poke_early(p->instr, insn_buff, p->len);
+		text_poke_early(instr, insn_buff, p->len);
 	}
 }
 extern struct paravirt_patch_site __start_parainstructions[],

arch/x86/kernel/callthunks.c

@@ -240,7 +240,7 @@ patch_paravirt_call_sites(struct paravirt_patch_site *start,
 	struct paravirt_patch_site *p;
 
 	for (p = start; p < end; p++)
-		patch_call(p->instr, ct);
+		patch_call((void *)&p->instr_offset + p->instr_offset, ct);
 }
 
 static __init_or_module void