x86/alternative: Simplify callthunk patching

Now that paravirt call patching is implemented using alternatives, it
is possible to avoid having to patch the alternative sites by
including the altinstr_replacement calls in the call_sites list.

This means we're now stacking relative adjustments like so:

  callthunks_patch_builtin_calls():
    patches all function calls to target: func() -> func()-10
    since the CALL accounting lives in the CALL_PADDING.

    This explicitly includes .altinstr_replacement

  alt_replace_call():
    patches: x86_BUG() -> target()

    this patching is done in a relative manner, and will preserve
    the above adjustment, meaning that with calldepth patching it
    will do: x86_BUG()-10 -> target()-10

  apply_relocation():
    does code relocation, and adjusts all RIP-relative instructions
    to the new location, also in a relative manner.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250207122546.617187089@infradead.org

6 files changed, 13 insertions, 39 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index a2141665239b..853fbcf68719 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -100,7 +100,6 @@ struct module;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;
-	struct alt_instr		*alt_start, *alt_end;
 };
 
 #ifdef CONFIG_CALL_THUNKS
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index e914a65ff154..fda11df1e650 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1705,14 +1705,14 @@ void __init alternative_instructions(void)
 	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
 	apply_returns(__return_sites, __return_sites_end);
 
-	apply_alternatives(__alt_instructions, __alt_instructions_end);
-
 	/*
-	 * Now all calls are established. Apply the call thunks if
-	 * required.
+	 * Adjust all CALL instructions to point to func()-10, including
+	 * those in .altinstr_replacement.
 	 */
 	callthunks_patch_builtin_calls();
 
+	apply_alternatives(__alt_instructions, __alt_instructions_end);
+
 	/*
 	 * Seal all functions that do not have their address taken.
 	 */
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 8418a892d195..25ae54250112 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -240,21 +240,10 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct)
 }
 
 static __init_or_module void
-patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end,
-		     const struct core_text *ct)
-{
-	struct alt_instr *a;
-
-	for (a = start; a < end; a++)
-		patch_call((void *)&a->instr_offset + a->instr_offset, ct);
-}
-
-static __init_or_module void
 callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct)
 {
 	prdbg("Patching call sites %s\n", ct->name);
 	patch_call_sites(cs->call_start, cs->call_end, ct);
-	patch_alt_call_sites(cs->alt_start, cs->alt_end, ct);
 	prdbg("Patching call sites done%s\n", ct->name);
 }
 
@@ -263,8 +252,6 @@ void __init callthunks_patch_builtin_calls(void)
 	struct callthunk_sites cs = {
 		.call_start	= __call_sites,
 		.call_end	= __call_sites_end,
-		.alt_start	= __alt_instructions,
-		.alt_end	= __alt_instructions_end
 	};
 
 	if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 837450b6e882..cb9d295e67cb 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -275,12 +275,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *rseg = (void *)returns->sh_addr;
 		apply_returns(rseg, rseg + returns->sh_size);
 	}
-	if (alt) {
-		/* patch .altinstructions */
-		void *aseg = (void *)alt->sh_addr;
-		apply_alternatives(aseg, aseg + alt->sh_size);
-	}
-	if (calls || alt) {
+	if (calls) {
 		struct callthunk_sites cs = {};
 
 		if (calls) {
@@ -288,13 +283,13 @@ int module_finalize(const Elf_Ehdr *hdr,
 			cs.call_end = (void *)calls->sh_addr + calls->sh_size;
 		}
 
-		if (alt) {
-			cs.alt_start = (void *)alt->sh_addr;
-			cs.alt_end = (void *)alt->sh_addr + alt->sh_size;
-		}
-
 		callthunks_patch_module_calls(&cs, me);
 	}
+	if (alt) {
+		/* patch .altinstructions */
+		void *aseg = (void *)alt->sh_addr;
+		apply_alternatives(aseg, aseg + alt->sh_size);
+	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
 		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index fe1362c34564..181aa604f8cd 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -850,5 +850,6 @@ bool arch_is_rethunk(struct symbol *sym)
 bool arch_is_embedded_insn(struct symbol *sym)
 {
 	return !strcmp(sym->name, "retbleed_return_thunk") ||
+	       !strcmp(sym->name, "srso_alias_safe_ret") ||
 	       !strcmp(sym->name, "srso_safe_ret");
 }
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 753dbc4f8198..26f2c1b8e099 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1283,15 +1283,6 @@ static void annotate_call_site(struct objtool_file *file,
 	if (!sym)
 		sym = reloc->sym;
 
-	/*
-	 * Alternative replacement code is just template code which is
-	 * sometimes copied to the original instruction. For now, don't
-	 * annotate it. (In the future we might consider annotating the
-	 * original instruction if/when it ever makes sense to do so.)
-	 */
-	if (!strcmp(insn->sec->name, ".altinstr_replacement"))
-		return;
-
 	if (sym->static_call_tramp) {
 		list_add_tail(&insn->call_node, &file->static_call_list);
 		return;
@@ -1349,7 +1340,8 @@ static void annotate_call_site(struct objtool_file *file,
 		return;
 	}
 
-	if (insn->type == INSN_CALL && !insn->sec->init)
+	if (insn->type == INSN_CALL && !insn->sec->init &&
+	    !insn->_call_dest->embedded_insn)
 		list_add_tail(&insn->call_node, &file->call_list);
 
 	if (!sibling && dead_end_function(file, sym))