x86/modules: Add call patching

As for the builtins create call thunks and patch the call sites to call the
thunk on Intel SKL CPUs for retbleed mitigation.

Note, that module init functions are ignored for sake of simplicity because
loading modules is not something which is done in high frequent loops and
the attacker has not really a handle on when this happens in order to
launch a matching attack. The depth tracking will still work for calls into
the builtins and because the call is not accounted it will underflow faster
and overstuff, but that's mitigated by the saturating counter and the side
effect is only temporary.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220915111147.575673066@infradead.org

arch/x86/include/asm/alternative.h

@@ -89,8 +89,13 @@ struct callthunk_sites {
 
 #ifdef CONFIG_CALL_THUNKS
 extern void callthunks_patch_builtin_calls(void);
+extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
+					  struct module *mod);
 #else
 static __always_inline void callthunks_patch_builtin_calls(void) {}
+static __always_inline void
+callthunks_patch_module_calls(struct callthunk_sites *sites,
+			      struct module *mod) {}
 #endif
 
 #ifdef CONFIG_SMP

arch/x86/kernel/callthunks.c

@@ -249,3 +249,22 @@ void __init callthunks_patch_builtin_calls(void)
 	thunks_initialized = true;
 	mutex_unlock(&text_mutex);
 }
+
+#ifdef CONFIG_MODULES
+void noinline callthunks_patch_module_calls(struct callthunk_sites *cs,
+					    struct module *mod)
+{
+	struct core_text ct = {
+		.base = (unsigned long)mod->core_layout.base,
+		.end  = (unsigned long)mod->core_layout.base + mod->core_layout.size,
+		.name = mod->name,
+	};
+
+	if (!thunks_initialized)
+		return;
+
+	mutex_lock(&text_mutex);
+	callthunks_setup(cs, &ct);
+	mutex_unlock(&text_mutex);
+}
+#endif /* CONFIG_MODULES */

arch/x86/kernel/module.c

@@ -254,7 +254,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 {
 	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
 		*para = NULL, *orc = NULL, *orc_ip = NULL,
-		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL;
+		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
+		*calls = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
@@ -274,6 +275,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 			retpolines = s;
 		if (!strcmp(".return_sites", secstrings + s->sh_name))
 			returns = s;
+		if (!strcmp(".call_sites", secstrings + s->sh_name))
+			calls = s;
 		if (!strcmp(".ibt_endbr_seal", secstrings + s->sh_name))
 			ibt_endbr = s;
 	}
@@ -299,6 +302,21 @@ int module_finalize(const Elf_Ehdr *hdr,
 		void *aseg = (void *)alt->sh_addr;
 		apply_alternatives(aseg, aseg + alt->sh_size);
 	}
+	if (calls || para) {
+		struct callthunk_sites cs = {};
+
+		if (calls) {
+			cs.call_start = (void *)calls->sh_addr;
+			cs.call_end = (void *)calls->sh_addr + calls->sh_size;
+		}
+
+		if (para) {
+			cs.pv_start = (void *)para->sh_addr;
+			cs.pv_end = (void *)para->sh_addr + para->sh_size;
+		}
+
+		callthunks_patch_module_calls(&cs, me);
+	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
 		apply_ibt_endbr(iseg, iseg + ibt_endbr->sh_size);