Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "Another round of CR3/PCID related fixes (I think this addresses all
  but one of the known problems with PCID support), an objtool fix plus
  a Clang fix that (finally) solves all Clang quirks to build a bootable
  x86 kernel as-is"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/asm: Fix inline asm call constraints for Clang
  objtool: Handle another GCC stack pointer adjustment bug
  x86/mm/32: Load a sane CR3 before cpu_init() on secondary CPUs
  x86/mm/32: Move setup_clear_cpu_cap(X86_FEATURE_PCID) earlier
  x86/mm/64: Stop using CR3.PCID == 0 in ASID-aware code
  x86/mm: Factor out CR3-building code

3 files changed, 35 insertions, 20 deletions

diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt
index 6a1af43..3995735 100644
--- a/tools/objtool/Documentation/stack-validation.txt
+++ b/tools/objtool/Documentation/stack-validation.txt
@@ -194,10 +194,10 @@ they mean, and suggestions for how to fix them.
    If it's a GCC-compiled .c file, the error may be because the function
    uses an inline asm() statement which has a "call" instruction.  An
    asm() statement with a call instruction must declare the use of the
-   stack pointer in its output operand.  For example, on x86_64:
+   stack pointer in its output operand.  On x86_64, this means adding
+   the ASM_CALL_CONSTRAINT as an output constraint:
 
-     register void *__sp asm("rsp");
-     asm volatile("call func" : "+r" (__sp));
+     asm volatile("call func" : ASM_CALL_CONSTRAINT);
 
    Otherwise the stack frame may not get created before the call.
 
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 0e8c8ec..0f22768 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -208,14 +208,14 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		break;
 
 	case 0x89:
-		if (rex == 0x48 && modrm == 0xe5) {
+		if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) {
 
-			/* mov %rsp, %rbp */
+			/* mov %rsp, reg */
 			*type = INSN_STACK;
 			op->src.type = OP_SRC_REG;
 			op->src.reg = CFI_SP;
 			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_BP;
+			op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b];
 			break;
 		}
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f744617..a0c518e 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1203,24 +1203,39 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 		switch (op->src.type) {
 
 		case OP_SRC_REG:
-			if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP) {
+			if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP &&
+			    cfa->base == CFI_SP &&
+			    regs[CFI_BP].base == CFI_CFA &&
+			    regs[CFI_BP].offset == -cfa->offset) {
+
+				/* mov %rsp, %rbp */
+				cfa->base = op->dest.reg;
+				state->bp_scratch = false;
+			}
 
-				if (cfa->base == CFI_SP &&
-				    regs[CFI_BP].base == CFI_CFA &&
-				    regs[CFI_BP].offset == -cfa->offset) {
+			else if (op->src.reg == CFI_SP &&
+				 op->dest.reg == CFI_BP && state->drap) {
 
-					/* mov %rsp, %rbp */
-					cfa->base = op->dest.reg;
-					state->bp_scratch = false;
-				}
+				/* drap: mov %rsp, %rbp */
+				regs[CFI_BP].base = CFI_BP;
+				regs[CFI_BP].offset = -state->stack_size;
+				state->bp_scratch = false;
+			}
 
-				else if (state->drap) {
+			else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) {
 
-					/* drap: mov %rsp, %rbp */
-					regs[CFI_BP].base = CFI_BP;
-					regs[CFI_BP].offset = -state->stack_size;
-					state->bp_scratch = false;
-				}
+				/*
+				 * mov %rsp, %reg
+				 *
+				 * This is needed for the rare case where GCC
+				 * does:
+				 *
+				 *   mov    %rsp, %rax
+				 *   ...
+				 *   mov    %rax, %rsp
+				 */
+				state->vals[op->dest.reg].base = CFI_CFA;
+				state->vals[op->dest.reg].offset = -state->stack_size;
 			}
 
 			else if (op->dest.reg == cfa->base) {