Merge tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Thomas Gleixner:

 - Improve retpoline code patching by separating it from alternatives
   which reduces memory footprint and allows to do better optimizations
   in the actual runtime patching.

 - Add proper retpoline support for x86/BPF

 - Address noinstr warnings in x86/kvm, lockdep and paravirtualization
   code

 - Add support to handle pv_opsindirect calls in the noinstr analysis

 - Classify symbols upfront and cache the result to avoid redundant
   str*cmp() invocations.

 - Add a CFI hash to reduce memory consumption which also reduces
   runtime on a allyesconfig by ~50%

 - Adjust XEN code to make objtool handling more robust and as a side
   effect to prevent text fragmentation due to placement of the
   hypercall page.

* tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  bpf,x86: Respect X86_FEATURE_RETPOLINE*
  bpf,x86: Simplify computing label offsets
  x86,bugs: Unconditionally allow spectre_v2=retpoline,amd
  x86/alternative: Add debug prints to apply_retpolines()
  x86/alternative: Try inline spectre_v2=retpoline,amd
  x86/alternative: Handle Jcc __x86_indirect_thunk_\reg
  x86/alternative: Implement .retpoline_sites support
  x86/retpoline: Create a retpoline thunk array
  x86/retpoline: Move the retpoline thunk declarations to nospec-branch.h
  x86/asm: Fixup odd GEN-for-each-reg.h usage
  x86/asm: Fix register order
  x86/retpoline: Remove unused replacement symbols
  objtool,x86: Replace alternatives with .retpoline_sites
  objtool: Shrink struct instruction
  objtool: Explicitly avoid self modifying code in .altinstr_replacement
  objtool: Classify symbols
  objtool: Support pv_opsindirect calls for noinstr
  x86/xen: Rework the xen_{cpu,irq,mmu}_opsarrays
  x86/xen: Mark xen_force_evtchn_callback() noinstr
  x86/xen: Make irq_disable() noinstr
  ...

1 files changed, 55 insertions, 125 deletions

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 0893436cc09f..4d6d7fc13255 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -20,6 +20,7 @@
 #include <objtool/arch.h>
 #include <objtool/warn.h>
 #include <objtool/endianness.h>
+#include <objtool/builtin.h>
 #include <arch/elf.h>
 
 static int is_x86_64(const struct elf *elf)
@@ -102,12 +103,13 @@ unsigned long arch_jump_destination(struct instruction *insn)
 #define rm_is_mem(reg)	(mod_is_mem() && !is_RIP() && rm_is(reg))
 #define rm_is_reg(reg)	(mod_is_reg() && modrm_rm == (reg))
 
-int arch_decode_instruction(const struct elf *elf, const struct section *sec,
+int arch_decode_instruction(struct objtool_file *file, const struct section *sec,
 			    unsigned long offset, unsigned int maxlen,
 			    unsigned int *len, enum insn_type *type,
 			    unsigned long *immediate,
 			    struct list_head *ops_list)
 {
+	const struct elf *elf = file->elf;
 	struct insn insn;
 	int x86_64, ret;
 	unsigned char op1, op2,
@@ -544,6 +546,36 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec,
 		*type = INSN_RETURN;
 		break;
 
+	case 0xc7: /* mov imm, r/m */
+		if (!noinstr)
+			break;
+
+		if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) {
+			struct reloc *immr, *disp;
+			struct symbol *func;
+			int idx;
+
+			immr = find_reloc_by_dest(elf, (void *)sec, offset+3);
+			disp = find_reloc_by_dest(elf, (void *)sec, offset+7);
+
+			if (!immr || strcmp(immr->sym->name, "pv_ops"))
+				break;
+
+			idx = (immr->addend + 8) / sizeof(void *);
+
+			func = disp->sym;
+			if (disp->sym->type == STT_SECTION)
+				func = find_symbol_by_offset(disp->sym->sec, disp->addend);
+			if (!func) {
+				WARN("no func for pv_ops[]");
+				return -1;
+			}
+
+			objtool_pv_add(file, idx, func);
+		}
+
+		break;
+
 	case 0xcf: /* iret */
 		/*
 		 * Handle sync_core(), which has an IRET to self.
@@ -659,154 +691,52 @@ 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_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)
+#define BYTE_RET	0xC3
 
-int arch_rewrite_retpolines(struct objtool_file *file)
+const char *arch_ret_insn(int len)
 {
-	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;
-			}
-		}
+	static const char ret[5][5] = {
+		{ BYTE_RET },
+		{ BYTE_RET, BYTES_NOP1 },
+		{ BYTE_RET, BYTES_NOP2 },
+		{ BYTE_RET, BYTES_NOP3 },
+		{ BYTE_RET, BYTES_NOP4 },
+	};
 
-		if (elf_add_alternative(file->elf, insn, sym,
-					ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) {
-			WARN("elf_add_alternative");
-			return -1;
-		}
+	if (len < 1 || len > 5) {
+		WARN("invalid RET size: %d\n", len);
+		return NULL;
 	}
 
-	return 0;
+	return ret[len-1];
 }
 
-int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg)
+int arch_decode_hint_reg(u8 sp_reg, int *base)
 {
-	struct cfi_reg *cfa = &insn->cfi.cfa;
-
 	switch (sp_reg) {
 	case ORC_REG_UNDEFINED:
-		cfa->base = CFI_UNDEFINED;
+		*base = CFI_UNDEFINED;
 		break;
 	case ORC_REG_SP:
-		cfa->base = CFI_SP;
+		*base = CFI_SP;
 		break;
 	case ORC_REG_BP:
-		cfa->base = CFI_BP;
+		*base = CFI_BP;
 		break;
 	case ORC_REG_SP_INDIRECT:
-		cfa->base = CFI_SP_INDIRECT;
+		*base = CFI_SP_INDIRECT;
 		break;
 	case ORC_REG_R10:
-		cfa->base = CFI_R10;
+		*base = CFI_R10;
 		break;
 	case ORC_REG_R13:
-		cfa->base = CFI_R13;
+		*base = CFI_R13;
 		break;
 	case ORC_REG_DI:
-		cfa->base = CFI_DI;
+		*base = CFI_DI;
 		break;
 	case ORC_REG_DX:
-		cfa->base = CFI_DX;
+		*base = CFI_DX;
 		break;
 	default:
 		return -1;