x86: Save rbp in pt_regs on irq entry
From the x86_64 low level interrupt handlers, the frame pointer is
saved right after the partial pt_regs frame.
rbp is not supposed to be part of the irq partial saved registers,
but it only requires to extend the pt_regs frame by 8 bytes to
do so, plus a tiny stack offset fixup on irq exit.
This changes a bit the semantics or get_irq_entry() that is supposed
to provide only the value of caller saved registers and the cpu
saved frame. However it's a win for unwinders that can walk through
stack frames on top of get_irq_regs() snapshots.
A noticeable impact is that it makes perf events cpu-clock and
task-clock events based callchains working on x86_64.
Let's then save rbp into the irq pt_regs.
As a result with:
perf record -e cpu-clock perf bench sched messaging
perf report --stdio
Before:
20.94% perf [kernel.kallsyms] [k] lock_acquire
|
--- lock_acquire
|
|--44.01%-- __write_nocancel
|
|--43.18%-- __read
|
|--6.08%-- fork
| create_worker
|
|--0.88%-- _dl_fixup
|
|--0.65%-- do_lookup_x
|
|--0.53%-- __GI___libc_read
--4.67%-- [...]
After:
19.23% perf [kernel.kallsyms] [k] __lock_acquire
|
--- __lock_acquire
|
|--97.74%-- lock_acquire
| |
| |--21.82%-- _raw_spin_lock
| | |
| | |--37.26%-- unix_stream_recvmsg
| | | sock_aio_read
| | | do_sync_read
| | | vfs_read
| | | sys_read
| | | system_call
| | | __read
| | |
| | |--24.09%-- unix_stream_sendmsg
| | | sock_aio_write
| | | do_sync_write
| | | vfs_write
| | | sys_write
| | | system_call
| | | __write_nocancel
v2: Fix cfi annotations.
Reported-by: Soeren Sandmann Pedersen <sandmann@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Jan Beulich <JBeulich@novell.com>
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e3ba417..d3b895f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -299,17 +299,21 @@
ENTRY(save_args)
XCPT_FRAME
cld
- movq_cfi rdi, RDI+16-ARGOFFSET
- movq_cfi rsi, RSI+16-ARGOFFSET
- movq_cfi rdx, RDX+16-ARGOFFSET
- movq_cfi rcx, RCX+16-ARGOFFSET
- movq_cfi rax, RAX+16-ARGOFFSET
- movq_cfi r8, R8+16-ARGOFFSET
- movq_cfi r9, R9+16-ARGOFFSET
- movq_cfi r10, R10+16-ARGOFFSET
- movq_cfi r11, R11+16-ARGOFFSET
+ /*
+ * start from rbp in pt_regs and jump over
+ * return address.
+ */
+ movq_cfi rdi, RDI+8-RBP
+ movq_cfi rsi, RSI+8-RBP
+ movq_cfi rdx, RDX+8-RBP
+ movq_cfi rcx, RCX+8-RBP
+ movq_cfi rax, RAX+8-RBP
+ movq_cfi r8, R8+8-RBP
+ movq_cfi r9, R9+8-RBP
+ movq_cfi r10, R10+8-RBP
+ movq_cfi r11, R11+8-RBP
- leaq -ARGOFFSET+16(%rsp),%rdi /* arg1 for handler */
+ leaq -RBP+8(%rsp),%rdi /* arg1 for handler */
movq_cfi rbp, 8 /* push %rbp */
leaq 8(%rsp), %rbp /* mov %rsp, %ebp */
testl $3, CS(%rdi)
@@ -782,8 +786,9 @@
/* 0(%rsp): ~(interrupt number) */
.macro interrupt func
- subq $ORIG_RAX-ARGOFFSET+8, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8
+ /* reserve pt_regs for scratch regs and rbp */
+ subq $ORIG_RAX-RBP, %rsp
+ CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
call save_args
PARTIAL_FRAME 0
call \func
@@ -808,9 +813,14 @@
TRACE_IRQS_OFF
decl PER_CPU_VAR(irq_count)
leaveq
+
CFI_RESTORE rbp
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
+
+ /* we did not save rbx, restore only from ARGOFFSET */
+ addq $8, %rsp
+ CFI_ADJUST_CFA_OFFSET -8
exit_intr:
GET_THREAD_INFO(%rcx)
testl $3,CS-ARGOFFSET(%rsp)