objtool,x86: Replace alternatives with .retpoline_sites

Instead of writing complete alternatives, simply provide a list of all
the retpoline thunk calls. Then the kernel is free to do with them as
it pleases. Simpler code all-round.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Borislav Petkov <[email protected]>
Acked-by: Josh Poimboeuf <[email protected]>
Tested-by: Alexei Starovoitov <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: Peter Zijlstra

arch/x86/kernel/vmlinux.lds.S

@@ -272,6 +272,20 @@ SECTIONS
 		__parainstructions_end = .;
 	}
 
+#ifdef CONFIG_RETPOLINE
+	/*
+	 * List of instructions that call/jmp/jcc to retpoline thunks
+	 * __x86_indirect_thunk_*(). These instructions can be patched along
+	 * with alternatives, after which the section can be freed.
+	 */
+	. = ALIGN(8);
+	.retpoline_sites : AT(ADDR(.retpoline_sites) - LOAD_OFFSET) {
+		__retpoline_sites = .;
+		*(.retpoline_sites)
+		__retpoline_sites_end = .;
+	}
+#endif
+
 	/*
 	 * struct alt_inst entries. From the header (alternative.h):
 	 * "Alternative instructions for different CPU types or capabilities"

tools/objtool/arch/x86/decode.c

@@ -711,126 +711,6 @@ const char *arch_ret_insn(int len)
 	return ret[len-1];
 }
 
-/* asm/alternative.h ? */
-
-#define ALTINSTR_FLAG_INV	(1 << 15)
-#define ALT_NOT(feat)		((feat) | ALTINSTR_FLAG_INV)
-
-struct alt_instr {
-	s32 instr_offset;	/* original instruction */
-	s32 repl_offset;	/* offset to replacement instruction */
-	u16 cpuid;		/* cpuid bit set for replacement */
-	u8  instrlen;		/* length of original instruction */
-	u8  replacementlen;	/* length of new instruction */
-} __packed;
-
-static int elf_add_alternative(struct elf *elf,
-			       struct instruction *orig, struct symbol *sym,
-			       int cpuid, u8 orig_len, u8 repl_len)
-{
-	const int size = sizeof(struct alt_instr);
-	struct alt_instr *alt;
-	struct section *sec;
-	Elf_Scn *s;
-
-	sec = find_section_by_name(elf, ".altinstructions");
-	if (!sec) {
-		sec = elf_create_section(elf, ".altinstructions",
-					 SHF_ALLOC, 0, 0);
-
-		if (!sec) {
-			WARN_ELF("elf_create_section");
-			return -1;
-		}
-	}
-
-	s = elf_getscn(elf->elf, sec->idx);
-	if (!s) {
-		WARN_ELF("elf_getscn");
-		return -1;
-	}
-
-	sec->data = elf_newdata(s);
-	if (!sec->data) {
-		WARN_ELF("elf_newdata");
-		return -1;
-	}
-
-	sec->data->d_size = size;
-	sec->data->d_align = 1;
-
-	alt = sec->data->d_buf = malloc(size);
-	if (!sec->data->d_buf) {
-		perror("malloc");
-		return -1;
-	}
-	memset(sec->data->d_buf, 0, size);
-
-	if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size,
-				  R_X86_64_PC32, orig->sec, orig->offset)) {
-		WARN("elf_create_reloc: alt_instr::instr_offset");
-		return -1;
-	}
-
-	if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4,
-			  R_X86_64_PC32, sym, 0)) {
-		WARN("elf_create_reloc: alt_instr::repl_offset");
-		return -1;
-	}
-
-	alt->cpuid = bswap_if_needed(cpuid);
-	alt->instrlen = orig_len;
-	alt->replacementlen = repl_len;
-
-	sec->sh.sh_size += size;
-	sec->changed = true;
-
-	return 0;
-}
-
-#define X86_FEATURE_RETPOLINE                ( 7*32+12)
-
-int arch_rewrite_retpolines(struct objtool_file *file)
-{
-	struct instruction *insn;
-	struct reloc *reloc;
-	struct symbol *sym;
-	char name[32] = "";
-
-	list_for_each_entry(insn, &file->retpoline_call_list, call_node) {
-
-		if (insn->type != INSN_JUMP_DYNAMIC &&
-		    insn->type != INSN_CALL_DYNAMIC)
-			continue;
-
-		if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk"))
-			continue;
-
-		reloc = insn->reloc;
-
-		sprintf(name, "__x86_indirect_alt_%s_%s",
-			insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call",
-			reloc->sym->name + 21);
-
-		sym = find_symbol_by_name(file->elf, name);
-		if (!sym) {
-			sym = elf_create_undef_symbol(file->elf, name);
-			if (!sym) {
-				WARN("elf_create_undef_symbol");
-				return -1;
-			}
-		}
-
-		if (elf_add_alternative(file->elf, insn, sym,
-					ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) {
-			WARN("elf_add_alternative");
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
 int arch_decode_hint_reg(u8 sp_reg, int *base)
 {
 	switch (sp_reg) {

tools/objtool/check.c

@@ -683,6 +683,52 @@ static int create_static_call_sections(struct objtool_file *file)
 	return 0;
 }
 
+static int create_retpoline_sites_sections(struct objtool_file *file)
+{
+	struct instruction *insn;
+	struct section *sec;
+	int idx;
+
+	sec = find_section_by_name(file->elf, ".retpoline_sites");
+	if (sec) {
+		WARN("file already has .retpoline_sites, skipping");
+		return 0;
+	}
+
+	idx = 0;
+	list_for_each_entry(insn, &file->retpoline_call_list, call_node)
+		idx++;
+
+	if (!idx)
+		return 0;
+
+	sec = elf_create_section(file->elf, ".retpoline_sites", 0,
+				 sizeof(int), idx);
+	if (!sec) {
+		WARN("elf_create_section: .retpoline_sites");
+		return -1;
+	}
+
+	idx = 0;
+	list_for_each_entry(insn, &file->retpoline_call_list, call_node) {
+
+		int *site = (int *)sec->data->d_buf + idx;
+		*site = 0;
+
+		if (elf_add_reloc_to_insn(file->elf, sec,
+					  idx * sizeof(int),
+					  R_X86_64_PC32,
+					  insn->sec, insn->offset)) {
+			WARN("elf_add_reloc_to_insn: .retpoline_sites");
+			return -1;
+		}
+
+		idx++;
+	}
+
+	return 0;
+}
+
 static int create_mcount_loc_sections(struct objtool_file *file)
 {
 	struct section *sec;
@@ -1016,6 +1062,11 @@ static void annotate_call_site(struct objtool_file *file,
 		return;
 	}
 
+	if (sym->retpoline_thunk) {
+		list_add_tail(&insn->call_node, &file->retpoline_call_list);
+		return;
+	}
+
 	/*
 	 * Many compilers cannot disable KCOV with a function attribute
 	 * so they need a little help, NOP out any KCOV calls from noinstr
@@ -1075,6 +1126,39 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn,
 	annotate_call_site(file, insn, sibling);
 }
 
+static void add_retpoline_call(struct objtool_file *file, struct instruction *insn)
+{
+	/*
+	 * Retpoline calls/jumps are really dynamic calls/jumps in disguise,
+	 * so convert them accordingly.
+	 */
+	switch (insn->type) {
+	case INSN_CALL:
+		insn->type = INSN_CALL_DYNAMIC;
+		break;
+	case INSN_JUMP_UNCONDITIONAL:
+		insn->type = INSN_JUMP_DYNAMIC;
+		break;
+	case INSN_JUMP_CONDITIONAL:
+		insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL;
+		break;
+	default:
+		return;
+	}
+
+	insn->retpoline_safe = true;
+
+	/*
+	 * Whatever stack impact regular CALLs have, should be undone
+	 * by the RETURN of the called function.
+	 *
+	 * Annotated intra-function calls retain the stack_ops but
+	 * are converted to JUMP, see read_intra_function_calls().
+	 */
+	remove_insn_ops(insn);
+
+	annotate_call_site(file, insn, false);
+}
 /*
  * Find the destination instructions for all jumps.
  */
@@ -1097,19 +1181,7 @@ static int add_jump_destinations(struct objtool_file *file)
 			dest_sec = reloc->sym->sec;
 			dest_off = arch_dest_reloc_offset(reloc->addend);
 		} else if (reloc->sym->retpoline_thunk) {
-			/*
-			 * Retpoline jumps are really dynamic jumps in
-			 * disguise, so convert them accordingly.
-			 */
-			if (insn->type == INSN_JUMP_UNCONDITIONAL)
-				insn->type = INSN_JUMP_DYNAMIC;
-			else
-				insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL;
-
-			list_add_tail(&insn->call_node,
-				      &file->retpoline_call_list);
-
-			insn->retpoline_safe = true;
+			add_retpoline_call(file, insn);
 			continue;
 		} else if (insn->func) {
 			/* internal or external sibling call (with reloc) */
@@ -1238,18 +1310,7 @@ static int add_call_destinations(struct objtool_file *file)
 			add_call_dest(file, insn, dest, false);
 
 		} else if (reloc->sym->retpoline_thunk) {
-			/*
-			 * Retpoline calls are really dynamic calls in
-			 * disguise, so convert them accordingly.
-			 */
-			insn->type = INSN_CALL_DYNAMIC;
-			insn->retpoline_safe = true;
-
-			list_add_tail(&insn->call_node,
-				      &file->retpoline_call_list);
-
-			remove_insn_ops(insn);
-			continue;
+			add_retpoline_call(file, insn);
 
 		} else
 			add_call_dest(file, insn, reloc->sym, false);
@@ -1980,11 +2041,6 @@ static void mark_rodata(struct objtool_file *file)
 	file->rodata = found;
 }
 
-__weak int arch_rewrite_retpolines(struct objtool_file *file)
-{
-	return 0;
-}
-
 static int decode_sections(struct objtool_file *file)
 {
 	int ret;
@@ -2057,15 +2113,6 @@ static int decode_sections(struct objtool_file *file)
 	if (ret)
 		return ret;
 
-	/*
-	 * Must be after add_special_section_alts(), since this will emit
-	 * alternatives. Must be after add_{jump,call}_destination(), since
-	 * those create the call insn lists.
-	 */
-	ret = arch_rewrite_retpolines(file);
-	if (ret)
-		return ret;
-
 	return 0;
 }
 
@@ -3468,6 +3515,13 @@ int check(struct objtool_file *file)
 		goto out;
 	warnings += ret;
 
+	if (retpoline) {
+		ret = create_retpoline_sites_sections(file);
+		if (ret < 0)
+			goto out;
+		warnings += ret;
+	}
+
 	if (mcount) {
 		ret = create_mcount_loc_sections(file);
 		if (ret < 0)