When a annotate a symbol, I find the annotated C source code doesn't match assembly code. So I cannot determine which line of C code has much overhead withou gdb's help.
Here is a example result of function apic_has_interrupt_for_ppr() in kvm module.
│580 __clear_bit(KVM_APIC_PV_EOI_PENDING,
&vcpu->arch.apic_attention); ▒
│581 }
▒
│
▒
│583 static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32
ppr) ▒
│584 {
▒
0.88 │30: cmpb $0x0,0x91(%rdi)
▒
2.54 │ ↓ je 63
▒
0.20 │ mov 0xa0(%rdi),%rcx
▒
│581 int highest_irr;
▒
│582 if (kvm_x86_ops->sync_pir_to_irr &&
apic->vcpu->arch.apicv_active) ▒
4.91 │ mov $0xe0,%eax x
▒
1.46 │45: mov %eax,%edx x
▒
0.02 │ sar $0x5,%edx x
▒
3.57 │ shl $0x4,%edx x
▒
3.34 │ movslq %edx,%rdx x
▒
1.25 │ mov 0x200(%rcx,%rdx,1),%edx x
▒
42.44 │ test %edx,%edx x
▒
0.01 │ ┌──jne 88 x
▒
3.48 │ │ sub $0x20,%eax x
▒
2.24 │ │ cmp $0xffffffe0,%eax x
▒
│586│apic_find_highest_irr():
▒
│ │
▒
│407│ /*
▒
│408│ * Note that irr_pending is just a hint. It will be always
▒
│409│ * true with virtual interrupt delivery enabled.
▒
│410│ */
▒
│411│ if (!apic->irr_pending)
▒
│ │↑ jne 45
▒
0.62 │63:│ mov $0xffffffff,%eax
◆
0.83 │ │ leaveq
▒
13.52 │ │← retq
▒
│6a:│ mov %esi,-0x4(%rbp)
▒
│ │ mov %rdx,%rdi
▒
│418│find_highest_vector():
▒
│340│static int find_highest_vector(void *bitmap)
▒
│341│{
▒
│342│ int vec;
▒
│343│ u32 *reg;
▒
│ │
▒
│345│ for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG;
▒
│ │→ callq *%rax
▒
│ │ mov -0x4(%rbp),%esi
▒
│343│ vec >= 0; vec -= APIC_VECTORS_PER_REG) {
▒
│344│ reg = bitmap + REG_POS(vec);
▒
│345│ if (*reg)
▒
0.05 │75:│ cmp $0xffffffff,%eax
▒
│ │↑ je 63
▒
1.95 │ │ mov %eax,%edx
▒
1.45 │ │ and $0xf0,%edx
Look at the assembly code block where I have put a 'x' on the right. Apparently
the
assembly code doesn't match the C source code arrounded. Let's look the correct
disassemble
result from gdb:
340 for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG;
0x000000000003b4e0 <+64>: mov $0xe0,%eax
342 reg = bitmap + REG_POS(vec);
343 if (*reg)
0x000000000003b4e5 <+69>: mov %eax,%edx
0x000000000003b4e7 <+71>: sar $0x5,%edx
0x000000000003b4ea <+74>: shl $0x4,%edx
0x000000000003b4ed <+77>: movslq %edx,%rdx
0x000000000003b4f0 <+80>: mov 0x200(%rcx,%rdx,1),%edx
0x000000000003b4f7 <+87>: test %edx,%edx
0x000000000003b4f9 <+89>: jne 0x3b528 <apic_has_interrupt_for_ppr+136>
341 vec >= 0; vec -= APIC_VECTORS_PER_REG) {
0x000000000003b4fb <+91>: sub $0x20,%eax
340 for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG;
0x000000000003b4fe <+94>: cmp $0xffffffe0,%eax
0x000000000003b501 <+97>: jne 0x3b4e5 <apic_has_interrupt_for_ppr+69>
Compared to gdb, perf-annoate has messed up. is it a bug or just perf is not as
perfect as gdb?
--
Thanks,
Changbin Du
signature.asc
Description: PGP signature
