x86/callthunks: Handle %rip-relative relocations in call thunk template

Contrary to alternatives, relocations are currently not supported in
call thunk templates.  Re-use the existing infrastructure from
alternative.c to allow %rip-relative relocations when copying call
thunk template from its storage location.

The patch allows unification of ASM_INCREMENT_CALL_DEPTH, which already
uses PER_CPU_VAR macro, with INCREMENT_CALL_DEPTH, used in call thunk
template, which is currently limited to use absolute address.

Reuse existing relocation infrastructure from alternative.c.,
as suggested by Peter Zijlstra.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20231105213731.1878100-3-ubizjak@gmail.com

arch/x86/include/asm/text-patching.h

@@ -18,6 +18,8 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
+void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len);
+
 /*
  * Currently, the max observed size in the kernel code is
  * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.

arch/x86/kernel/alternative.c

@@ -325,8 +325,7 @@ bool need_reloc(unsigned long offset, u8 *src, size_t src_len)
 	return (target < src || target > src + src_len);
 }
 
-static void __init_or_module noinline
-apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
+void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len)
 {
 	int prev, target = 0;
 

arch/x86/kernel/callthunks.c

@@ -24,6 +24,8 @@
 
 static int __initdata_or_module debug_callthunks;
 
+#define MAX_PATCH_LEN (255-1)
+
 #define prdbg(fmt, args...)					\
 do {								\
 	if (debug_callthunks)					\
@@ -184,10 +186,15 @@ static const u8 nops[] = {
 static void *patch_dest(void *dest, bool direct)
 {
 	unsigned int tsize = SKL_TMPL_SIZE;
+	u8 insn_buff[MAX_PATCH_LEN];
 	u8 *pad = dest - tsize;
 
+	memcpy(insn_buff, skl_call_thunk_template, tsize);
+	apply_relocation(insn_buff, tsize, pad,
+			 skl_call_thunk_template, tsize);
+
 	/* Already patched? */
-	if (!bcmp(pad, skl_call_thunk_template, tsize))
+	if (!bcmp(pad, insn_buff, tsize))
 		return pad;
 
 	/* Ensure there are nops */
@@ -197,9 +204,9 @@ static void *patch_dest(void *dest, bool direct)
 	}
 
 	if (direct)
-		memcpy(pad, skl_call_thunk_template, tsize);
+		memcpy(pad, insn_buff, tsize);
 	else
-		text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true);
+		text_poke_copy_locked(pad, insn_buff, tsize, true);
 	return pad;
 }
 
@@ -297,20 +304,27 @@ void *callthunks_translate_call_dest(void *dest)
 static bool is_callthunk(void *addr)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
-	void *tmpl = skl_call_thunk_template;
+	u8 insn_buff[MAX_PATCH_LEN];
 	unsigned long dest;
+	u8 *pad;
 
 	dest = roundup((unsigned long)addr, CONFIG_FUNCTION_ALIGNMENT);
 	if (!thunks_initialized || skip_addr((void *)dest))
 		return false;
 
-	return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size);
+	*pad = dest - tmpl_size;
+
+	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
+	apply_relocation(insn_buff, tmpl_size, pad,
+			 skl_call_thunk_template, tmpl_size);
+
+	return !bcmp(pad, insn_buff, tmpl_size);
 }
 
 int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
-	void *tmpl = skl_call_thunk_template;
+	u8 insn_buff[MAX_PATCH_LEN];
 
 	if (!thunks_initialized)
 		return 0;
@@ -319,7 +333,11 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 	if (func && is_callthunk(func))
 		return 0;
 
-	memcpy(*pprog, tmpl, tmpl_size);
+	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
+	apply_relocation(insn_buff, tmpl_size, *pprog,
+			 skl_call_thunk_template, tmpl_size);
+
+	memcpy(*pprog, insn_buff, tmpl_size);
 	*pprog += tmpl_size;
 	return tmpl_size;
 }