| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20170926060629.GB8868@intel.com>
Date: Tue, 26 Sep 2017 14:06:30 +0800
From: "Du, Changbin" <changbin.du@...el.com>
To: "Du, Changbin" <changbin.du@...el.com>
Cc: Arnaldo Carvalho de Melo <acme@...nel.org>, peterz@...radead.org,
mingo@...hat.com, alexander.shishkin@...ux.intel.com,
linux-kernel@...r.kernel.org
Subject: Re: Does perf-annotate work correctly?
Hi Arnaldo and all,
Is there someone looking at this issue? I can provide more info if you need.
This issue makes it so inconvenient to use perf. Thanks.
On Wed, Sep 13, 2017 at 09:54:25AM +0800, Du, Changbin wrote:
> On Tue, Sep 12, 2017 at 11:33:50AM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Tue, Sep 12, 2017 at 06:10:35PM +0800, Du, Changbin escreveu:
> > > 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.
> >
> > Ok, was this using the module .ko file or /proc/kcore? You forgot to
> > cut'n'paste the first line on the screen.
> >
> It is arch/x86/kvm/kvm.ko.
>
> > Also, how did you use gdb?
> >
> $ gdb arch/x86/kvm/kvm.ko
> $ (gdb) disassemble /s apic_has_interrupt_for_ppr
>
> > perf uses objdump to do the disassembly, and depending on how it is used
> > (live system, post processing on a different machine, permissions) it
> > may use different files to do the disassembly.
> >
> But objdump has same out as gdb. (Always on same machine, and no binary changed.)
>
> $ objdump -d -S arch/x86/kvm/kvm.o
> ...
> static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
> {
> 3b4a0: e8 00 00 00 00 callq 3b4a5 <apic_has_interrupt_for_ppr+0x5>
> 3b4a5: 55 push %rbp
> 3b4a6: 48 89 e5 mov %rsp,%rbp
> 3b4a9: 48 83 ec 08 sub $0x8,%rsp
> int highest_irr;
> if (kvm_x86_ops->sync_pir_to_irr && apic->vcpu->arch.apicv_active)
> 3b4ad: 48 8b 05 00 00 00 00 mov 0x0(%rip),%rax # 3b4b4 <apic_has_interrupt_for_ppr+0x14>
> 3b4b4: 48 8b 80 38 02 00 00 mov 0x238(%rax),%rax
> 3b4bb: 48 85 c0 test %rax,%rax
> 3b4be: 74 10 je 3b4d0 <apic_has_interrupt_for_ppr+0x30>
> 3b4c0: 48 8b 97 88 00 00 00 mov 0x88(%rdi),%rdx
> 3b4c7: 80 ba 28 03 00 00 00 cmpb $0x0,0x328(%rdx)
> 3b4ce: 75 3a jne 3b50a <apic_has_interrupt_for_ppr+0x6a>
>
> /*
> * Note that irr_pending is just a hint. It will be always
> * true with virtual interrupt delivery enabled.
> */
> if (!apic->irr_pending)
> 3b4d0: 80 bf 91 00 00 00 00 cmpb $0x0,0x91(%rdi)
> 3b4d7: 74 2a je 3b503 <apic_has_interrupt_for_ppr+0x63>
> 3b4d9: 48 8b 8f a0 00 00 00 mov 0xa0(%rdi),%rcx
> static int find_highest_vector(void *bitmap)
> {
> int vec;
> u32 *reg;
>
> for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG;
> 3b4e0: b8 e0 00 00 00 mov $0xe0,%eax
> vec >= 0; vec -= APIC_VECTORS_PER_REG) {
> reg = bitmap + REG_POS(vec);
> if (*reg)
> 3b4e5: 89 c2 mov %eax,%edx
> 3b4e7: c1 fa 05 sar $0x5,%edx
> 3b4ea: c1 e2 04 shl $0x4,%edx
> 3b4ed: 48 63 d2 movslq %edx,%rdx
> 3b4f0: 8b 94 11 00 02 00 00 mov 0x200(%rcx,%rdx,1),%edx
> 3b4f7: 85 d2 test %edx,%edx
> 3b4f9: 75 2d jne 3b528 <apic_has_interrupt_for_ppr+0x88>
>
>
>
> > Please provide more detailed information on the exact command line
> > arguments and usage scenario.
> >
> > - Arnaldo
>
> >
> > > │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
> >
> >
>
> --
> Thanks,
> Changbin Du
--
Thanks,
Changbin Du
Download attachment "signature.asc" of type "application/pgp-signature" (474 bytes)
Powered by blists - more mailing lists