x86/module: Use text_poke() for late relocations

Because of late module patching, a livepatch module needs to be able to
apply some of its relocations well after it has been loaded.  Instead of
playing games with module_{dis,en}able_ro(), use existing text poking
mechanisms to apply relocations after module loading.

So far only x86, s390 and Power have HAVE_LIVEPATCH but only the first
two also have STRICT_MODULE_RWX.

This will allow removal of the last module_disable_ro() usage in
livepatch.  The ultimate goal is to completely disallow making
executable mappings writable.

[ jpoimboe: Split up patches.  Use mod state to determine whether
	    memcpy() can be used.  Implement text_poke() for UML. ]

Cc: x86@kernel.org
Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Joe Lawrence <joe.lawrence@redhat.com>
Acked-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>

arch/um/kernel/um_arch.c

@@ -362,3 +362,19 @@ void __init check_bugs(void)
 void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
+
+void *text_poke(void *addr, const void *opcode, size_t len)
+{
+	/*
+	 * In UML, the only reference to this function is in
+	 * apply_relocate_add(), which shouldn't ever actually call this
+	 * because UML doesn't have live patching.
+	 */
+	WARN_ON(1);
+
+	return memcpy(addr, opcode, len);
+}
+
+void text_poke_sync(void)
+{
+}

arch/x86/kernel/module.c

@@ -126,11 +126,12 @@ int apply_relocate(Elf32_Shdr *sechdrs,
 	return 0;
 }
 #else /*X86_64*/
-int apply_relocate_add(Elf64_Shdr *sechdrs,
+static int __apply_relocate_add(Elf64_Shdr *sechdrs,
 		   const char *strtab,
 		   unsigned int symindex,
 		   unsigned int relsec,
-		   struct module *me)
+		   struct module *me,
+		   void *(*write)(void *dest, const void *src, size_t len))
 {
 	unsigned int i;
 	Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
@@ -162,19 +163,19 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		case R_X86_64_64:
 			if (*(u64 *)loc != 0)
 				goto invalid_relocation;
-			*(u64 *)loc = val;
+			write(loc, &val, 8);
 			break;
 		case R_X86_64_32:
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
-			*(u32 *)loc = val;
+			write(loc, &val, 4);
 			if (val != *(u32 *)loc)
 				goto overflow;
 			break;
 		case R_X86_64_32S:
 			if (*(s32 *)loc != 0)
 				goto invalid_relocation;
-			*(s32 *)loc = val;
+			write(loc, &val, 4);
 			if ((s64)val != *(s32 *)loc)
 				goto overflow;
 			break;
@@ -183,7 +184,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;
-			*(u32 *)loc = val;
+			write(loc, &val, 4);
 #if 0
 			if ((s64)val != *(s32 *)loc)
 				goto overflow;
@@ -193,7 +194,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			if (*(u64 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;
-			*(u64 *)loc = val;
+			write(loc, &val, 8);
 			break;
 		default:
 			pr_err("%s: Unknown rela relocation: %llu\n",
@@ -215,6 +216,29 @@ overflow:
 	       me->name);
 	return -ENOEXEC;
 }
+
+int apply_relocate_add(Elf64_Shdr *sechdrs,
+		   const char *strtab,
+		   unsigned int symindex,
+		   unsigned int relsec,
+		   struct module *me)
+{
+	int ret;
+	bool early = me->state == MODULE_STATE_UNFORMED;
+	void *(*write)(void *, const void *, size_t) = memcpy;
+
+	if (!early)
+		write = text_poke;
+
+	ret = __apply_relocate_add(sechdrs, strtab, symindex, relsec, me,
+				   write);
+
+	if (!early)
+		text_poke_sync();
+
+	return ret;
+}
+
 #endif
 
 int module_finalize(const Elf_Ehdr *hdr,