objtool/x86: Rewrite retpoline thunk calls

commit 9bc0bb50727c8ac69fbb33fb937431cf3518ff37 upstream.

When the compiler emits: "CALL __x86_indirect_thunk_\reg" for an
indirect call, have objtool rewrite it to:

	ALTERNATIVE "call __x86_indirect_thunk_\reg",
		    "call *%reg", ALT_NOT(X86_FEATURE_RETPOLINE)

Additionally, in order to not emit endless identical
.altinst_replacement chunks, use a global symbol for them, see
__x86_indirect_alt_*.

This also avoids objtool from having to do code generation.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Link: https://lkml.kernel.org/r/20210326151300.320177914@infradead.org
[bwh: Backported to 5.10: include "arch_elf.h" instead of "arch/elf.h"]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

tools/objtool/arch/x86/decode.c

@@ -16,6 +16,7 @@
 #include "../../arch.h"
 #include "../../warn.h"
 #include <asm/orc_types.h>
+#include "arch_elf.h"
 
 static unsigned char op_to_cfi_reg[][2] = {
 	{CFI_AX, CFI_R8},
@@ -585,6 +586,122 @@ const char *arch_nop_insn(int len)
 	return nops[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_WRITE, size, 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 = 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 (!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(struct instruction *insn, u8 sp_reg)
 {
 	struct cfi_reg *cfa = &insn->cfi.cfa;