x86/asm/entry/64: Update comments about stack frames
Tweak a few outdated comments that were obsoleted by recent changes
to syscall entry code:
- we no longer have a "partial stack frame" on
entry, ever.
- explain the syscall entry usage of old_rsp.
Partially based on a (split out of) patch from Denys Vlasenko.
Originally-from: Denys Vlasenko <dvlasenk@redhat.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Will Drewry <wad@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index aed3f11..d287f78 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -15,10 +15,8 @@
* after an interrupt and after each system call.
*
* A note on terminology:
- * - top of stack: Architecture defined interrupt frame from SS to RIP
+ * - iret frame: Architecture defined interrupt frame from SS to RIP
* at the top of the kernel process stack.
- * - partial stack frame: partially saved registers up to R11.
- * - full stack frame: Like partial stack frame, but all register saved.
*
* Some macro usage:
* - CFI macros are used to generate dwarf2 unwind information for better
@@ -219,7 +217,7 @@
* Interrupts are off on entry.
* Only called from user space.
*
- * When user can change the frames always force IRET. That is because
+ * When user can change pt_regs->foo always force IRET. That is because
* it deals with uncanonical addresses better. SYSRET has trouble
* with them due to bugs in both AMD and Intel CPUs.
*/
@@ -238,6 +236,11 @@
*/
GLOBAL(system_call_after_swapgs)
+ /*
+ * We use 'old_rsp' as a scratch register, hence this block must execute
+ * atomically in the face of possible interrupt-driven task preemption,
+ * so we can enable interrupts only after we're done with using old_rsp:
+ */
movq %rsp,PER_CPU_VAR(old_rsp)
/* kernel_stack is set so that 5 slots (iret frame) are preallocated */
movq PER_CPU_VAR(kernel_stack),%rsp
@@ -303,7 +306,7 @@
FIXUP_TOP_OF_STACK %r11
jmp int_ret_from_sys_call
- /* Do syscall tracing */
+ /* Do syscall entry tracing */
tracesys:
movq %rsp, %rdi
movq $AUDIT_ARCH_X86_64, %rsi
@@ -339,11 +342,11 @@
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
movq %rax,RAX(%rsp)
- /* Use IRET because user could have changed frame */
+ /* Use IRET because user could have changed pt_regs->foo */
/*
* Syscall return path ending with IRET.
- * Has correct top of stack, but partial stack frame.
+ * Has correct iret frame.
*/
GLOBAL(int_ret_from_sys_call)
DISABLE_INTERRUPTS(CLBR_NONE)
@@ -374,7 +377,7 @@
TRACE_IRQS_OFF
jmp int_with_check
- /* handle signals and tracing -- both require a full stack frame */
+ /* handle signals and tracing -- both require a full pt_regs */
int_very_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
