[PATCH 1/2] x86/entry: reduce static footprint of idtentry
From: Dominik Brodowski
Date: Wed Feb 14 2018 - 13:00:41 EST
Play a little trick in the generic PUSH_AND_CLEAR_REGS macro
to insert the GP registers "above" the original return address.
This allows us to (re-)insert the macro in error_entry() and
paranoid_entry() and to remove it from the idtentry macro. This
reduces the static footprint significantly:
text data bss dec hex filename
24307 0 0 24307 5ef3 entry_64.o-orig
20987 0 0 20987 51fb entry_64.o
Co-developed-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Dominik Brodowski <linux@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/entry/calling.h | 11 ++++++++++-
arch/x86/entry/entry_64.S | 18 ++++++++----------
2 files changed, 18 insertions(+), 11 deletions(-)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index dce7092ab24a..79ead48e6fe1 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -97,7 +97,7 @@ For 32-bit we have the following conventions - kernel is built with
#define SIZEOF_PTREGS 21*8
-.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
/*
* Push registers and sanitize registers of values that a
* speculation attack might otherwise want to exploit. The
@@ -105,8 +105,14 @@ For 32-bit we have the following conventions - kernel is built with
* could be put to use in a speculative execution gadget.
* Interleave XOR with PUSH for better uop scheduling:
*/
+ .if \save_ret
+ pushq %rsi /* pt_regs->si */
+ movq 8(%rsp), %rsi /* temporarily store ret address in %rsi */
+ movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original ret) */
+ .else
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
+ .endif
pushq \rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq \rax /* pt_regs->ax */
@@ -131,6 +137,9 @@ For 32-bit we have the following conventions - kernel is built with
pushq %r15 /* pt_regs->r15 */
xorq %r15, %r15 /* nospec r15*/
UNWIND_HINT_REGS
+ .if \save_ret
+ pushq %rsi /* return address on top of stack */
+ .endif
.endm
.macro POP_REGS pop_rdi=1 skip_r11rcx=0
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 1c54204207d8..5d9cb0f037e4 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -871,12 +871,8 @@ ENTRY(\sym)
pushq $-1 /* ORIG_RAX: no syscall to restart */
.endif
- /* Save all registers in pt_regs */
- PUSH_AND_CLEAR_REGS
- ENCODE_FRAME_POINTER
-
.if \paranoid < 2
- testb $3, CS(%rsp) /* If coming from userspace, switch stacks */
+ testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */
jnz .Lfrom_usermode_switch_stack_\@
.endif
@@ -1123,13 +1119,15 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1
#endif
/*
- * Switch gs if needed.
+ * Save all registers in pt_regs, and switch gs if needed.
* Use slow, but surefire "are we in kernel?" check.
* Return: ebx=0: need swapgs on exit, ebx=1: otherwise
*/
ENTRY(paranoid_entry)
UNWIND_HINT_FUNC
cld
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
movl $1, %ebx
movl $MSR_GS_BASE, %ecx
rdmsr
@@ -1173,12 +1171,14 @@ ENTRY(paranoid_exit)
END(paranoid_exit)
/*
- * Switch gs if needed.
+ * Save all registers in pt_regs, and switch gs if needed.
* Return: EBX=0: came from user mode; EBX=1: otherwise
*/
ENTRY(error_entry)
- UNWIND_HINT_REGS offset=8
+ UNWIND_HINT_FUNC
cld
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
testb $3, CS+8(%rsp)
jz .Lerror_kernelspace
@@ -1569,8 +1569,6 @@ end_repeat_nmi:
* frame to point back to repeat_nmi.
*/
pushq $-1 /* ORIG_RAX: no syscall to restart */
- PUSH_AND_CLEAR_REGS
- ENCODE_FRAME_POINTER
/*
* Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
--
2.16.1