x86: Return to kernel without IRET
On my box, this saves about 100ns on each interrupt and trap that
happens while running in kernel space. This speeds up my kernel_pf
microbenchmark by about 17%.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1e96c36..504cec5 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1033,9 +1033,56 @@
retint_restore_args: /* return to kernel space */
DISABLE_INTERRUPTS(CLBR_ANY)
/*
- * The iretq could re-enable interrupts:
+ * The sti could re-enable interrupts:
*/
TRACE_IRQS_IRETQ
+
+ /*
+ * Fast return to kernel. The stack looks like:
+ *
+ * previous frame
+ * possible 8 byte gap for alignment
+ * SS RSP EFLAGS CS RIP
+ * ORIG_RAX RDI ... R11
+ *
+ * We rewrite it to:
+ *
+ * previous frame
+ * RIP (EFLAGS & ~IF) ...
+ * pointer to the EFLAGS slot
+ * RDI ... R11
+ */
+ movq RSP-ARGOFFSET(%rsp), %rsi
+ subq $16, %rsi
+ movq EFLAGS-ARGOFFSET(%rsp), %rdi
+ movq RIP-ARGOFFSET(%rsp), %rcx
+ btr $9, %rdi
+ movq %rdi, (%rsi)
+ movq %rcx, 8(%rsi)
+ movq %rsi, ORIG_RAX-ARGOFFSET(%rsp)
+ popq_cfi %r11
+ popq_cfi %r10
+ popq_cfi %r9
+ popq_cfi %r8
+ popq_cfi %rax
+ popq_cfi %rcx
+ popq_cfi %rdx
+ popq_cfi %rsi
+ popq_cfi %rdi
+
+ popq %rsp
+ jc 1f
+ /* Interrupts were not enabled */
+ popfq_cfi
+ retq
+1:
+ CFI_ADJUST_CFA_OFFSET 8
+ /* Interrupts were enabled */
+ popfq_cfi
+ sti
+ /* Interrupts are still off because of the one-insn grace period. */
+ retq
+
restore_args:
RESTORE_ARGS 1,8,1
