objtool: Handle GCC stack pointer adjustment bug

Arnd Bergmann reported the following warning with GCC 7.1.1:

  fs/fs_pin.o: warning: objtool: pin_kill()+0x139: stack state mismatch: cfa1=7+88 cfa2=7+96

And the kbuild robot reported the following warnings with GCC 5.4.1:

  fs/fs_pin.o: warning: objtool: pin_kill()+0x182: return with modified stack frame
  fs/quota/dquot.o: warning: objtool: dquot_alloc_inode()+0x140: stack state mismatch: cfa1=7+120 cfa2=7+128
  fs/quota/dquot.o: warning: objtool: dquot_free_inode()+0x11a: stack state mismatch: cfa1=7+112 cfa2=7+120

Those warnings are caused by an unusual GCC non-optimization where it
uses an intermediate register to adjust the stack pointer.  It does:

  lea    0x8(%rsp), %rcx
  ...
  mov    %rcx, %rsp

Instead of the obvious:

  add    $0x8, %rsp

It makes no sense to use an intermediate register, so I opened a GCC bug
to track it:

  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81813

But it's not exactly a high-priority bug and it looks like we'll be
stuck with this issue for a while.  So for now we have to track register
values when they're loaded with stack pointer offsets.

This is kind of a big workaround for a tiny problem, but c'est la vie.
I hope to eventually create a GCC plugin to implement a big chunk of
objtool's functionality.  Hopefully at that point we'll be able to
remove of a lot of these GCC-isms from the objtool code.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/6a41a96884c725e7f05413bb7df40cfe824b2444.1504028945.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 26 insertions, 68 deletions

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 7841e5d31973..0e8c8ec4fd4e 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -86,8 +86,8 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 	struct insn insn;
 	int x86_64, sign;
 	unsigned char op1, op2, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0,
-		      modrm = 0, modrm_mod = 0, modrm_rm = 0, modrm_reg = 0,
-		      sib = 0;
+		      rex_x = 0, modrm = 0, modrm_mod = 0, modrm_rm = 0,
+		      modrm_reg = 0, sib = 0;
 
 	x86_64 = is_x86_64(elf);
 	if (x86_64 == -1)
@@ -114,6 +114,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		rex = insn.rex_prefix.bytes[0];
 		rex_w = X86_REX_W(rex) >> 3;
 		rex_r = X86_REX_R(rex) >> 2;
+		rex_x = X86_REX_X(rex) >> 1;
 		rex_b = X86_REX_B(rex);
 	}
 
@@ -217,6 +218,18 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 			op->dest.reg = CFI_BP;
 			break;
 		}
+
+		if (rex_w && !rex_b && modrm_mod == 3 && modrm_rm == 4) {
+
+			/* mov reg, %rsp */
+			*type = INSN_STACK;
+			op->src.type = OP_SRC_REG;
+			op->src.reg = op_to_cfi_reg[modrm_reg][rex_r];
+			op->dest.type = OP_DEST_REG;
+			op->dest.reg = CFI_SP;
+			break;
+		}
+
 		/* fallthrough */
 	case 0x88:
 		if (!rex_b &&
@@ -269,80 +282,28 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		break;
 
 	case 0x8d:
-		if (rex == 0x48 && modrm == 0x65) {
+		if (sib == 0x24 && rex_w && !rex_b && !rex_x) {
 
-			/* lea disp(%rbp), %rsp */
+			/* lea disp(%rsp), reg */
 			*type = INSN_STACK;
 			op->src.type = OP_SRC_ADD;
-			op->src.reg = CFI_BP;
+			op->src.reg = CFI_SP;
 			op->src.offset = insn.displacement.value;
 			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_SP;
-			break;
-		}
+			op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
 
-		if (rex == 0x48 && (modrm == 0xa4 || modrm == 0x64) &&
-		    sib == 0x24) {
+		} else if (rex == 0x48 && modrm == 0x65) {
 
-			/* lea disp(%rsp), %rsp */
+			/* lea disp(%rbp), %rsp */
 			*type = INSN_STACK;
 			op->src.type = OP_SRC_ADD;
-			op->src.reg = CFI_SP;
+			op->src.reg = CFI_BP;
 			op->src.offset = insn.displacement.value;
 			op->dest.type = OP_DEST_REG;
 			op->dest.reg = CFI_SP;
-			break;
-		}
 
-		if (rex == 0x48 && modrm == 0x2c && sib == 0x24) {
-
-			/* lea (%rsp), %rbp */
-			*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;
-			break;
-		}
-
-		if (rex == 0x4c && modrm == 0x54 && sib == 0x24 &&
-		    insn.displacement.value == 8) {
-
-			/*
-			 * lea 0x8(%rsp), %r10
-			 *
-			 * Here r10 is the "drap" pointer, used as a stack
-			 * pointer helper when the stack gets realigned.
-			 */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_ADD;
-			op->src.reg = CFI_SP;
-			op->src.offset = 8;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_R10;
-			break;
-		}
-
-		if (rex == 0x4c && modrm == 0x6c && sib == 0x24 &&
-		    insn.displacement.value == 16) {
-
-			/*
-			 * lea 0x10(%rsp), %r13
-			 *
-			 * Here r13 is the "drap" pointer, used as a stack
-			 * pointer helper when the stack gets realigned.
-			 */
-			*type = INSN_STACK;
-			op->src.type = OP_SRC_ADD;
-			op->src.reg = CFI_SP;
-			op->src.offset = 16;
-			op->dest.type = OP_DEST_REG;
-			op->dest.reg = CFI_R13;
-			break;
-		}
-
-		if (rex == 0x49 && modrm == 0x62 &&
-		    insn.displacement.value == -8) {
+		} else if (rex == 0x49 && modrm == 0x62 &&
+			   insn.displacement.value == -8) {
 
 			/*
 			 * lea -0x8(%r10), %rsp
@@ -356,11 +317,9 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 			op->src.offset = -8;
 			op->dest.type = OP_DEST_REG;
 			op->dest.reg = CFI_SP;
-			break;
-		}
 
-		if (rex == 0x49 && modrm == 0x65 &&
-		    insn.displacement.value == -16) {
+		} else if (rex == 0x49 && modrm == 0x65 &&
+			   insn.displacement.value == -16) {
 
 			/*
 			 * lea -0x10(%r13), %rsp
@@ -374,7 +333,6 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 			op->src.offset = -16;
 			op->dest.type = OP_DEST_REG;
 			op->dest.reg = CFI_SP;
-			break;
 		}
 
 		break;