Re: bpf_get_branch_snapshot on qemu-kvm

From: Song Liu <songliubraving@fb.com>
To: Like Xu <like.xu.linux@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>, bpf <bpf@vger.kernel.org>,
	Networking <netdev@vger.kernel.org>,
	Kernel Team <Kernel-team@fb.com>,
	"Andrii Nakryiko" <andrii@kernel.org>,
	Alexei Starovoitov <ast@kernel.org>,
	"like.xu@linux.intel.com" <like.xu@linux.intel.com>
Subject: Re: bpf_get_branch_snapshot on qemu-kvm
Date: Wed, 29 Sep 2021 14:39:44 +0000	[thread overview]
Message-ID: <04BD2D70-62C1-4ADF-B437-E0D720E04B6B@fb.com> (raw)
In-Reply-To: <d75f6a9a-dbb3-c725-c001-ec9bdd55173f@gmail.com>

Hi Like,

> On Sep 29, 2021, at 5:05 AM, Like Xu <like.xu.linux@gmail.com> wrote:
> 
> On 29/9/2021 3:35 pm, Peter Zijlstra wrote:
>> On Wed, Sep 29, 2021 at 12:04:21AM +0000, Song Liu wrote:
>>> Hi Peter,
>>> 
>>> We have see the warning below while testing the new bpf_get_branch_snapshot
>>> helper, on a QEMU vm (/usr/bin/qemu-system-x86_64 -enable-kvm -cpu host ...).
>>> This issue doesn't happen on bare metal systems (no QEMU).
>>> 
>>> We didn't cover this case, as LBR didn't really work in QEMU. But it seems to
>>> work after I upgrade the host kernel to 5.12.
> 
> The guest LBR is enabled since the v5.12.
> 
>>> 
>>> At the moment, we don't have much idea on how to debug and fix the issue. Could
>>> you please share your thoughts on this?
>> Well, that's virt, afaik stuff not working is like a feature there or
>> something, who knows. I've Cc'ed Like Xu who might have clue since he
>> did the patches.
>> Virt just ain't worth the pain if you ask me.
> 
> Just cc me for any vPMU/x86 stuff.
> 
>>> 
>>> Thanks in advance!
>>> 
>>> Song
>>> 
>>> 
>>> 
>>> 
>>> ============================== 8< ============================
>>> 
>>> [  139.494159] unchecked MSR access error: WRMSR to 0x3f1 (tried to write 0x0000000000000000) at rIP: 0xffffffff81011a8b (intel_pmu_snapshot_branch_stack+0x3b/0xd0)
> 
> Uh, it uses a PEBS counter to sample or count, which is not yet upstream but should be soon.
> 
> Song, can you try to fix bpf_get_branch_snapshot on a normal PMC counter,
> or where is the src for bpf_get_branch_snapshot? I am more than happy to help.

bpf_get_branch_snapshot is available in the bpf-next tree:

https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/

To repro the issue:

1. build the kernel and boot qemu with it;
2. build tools/testing/selftests/bpf
     cd tools/testing/selftests/bpf ; make -j
3. copy test_progs and bpf_testmod.ko from tools/testing/selftests/bpf
   to the qemu vm;
4. run the test as 
     ./test_progs -t snapshot -v

This should trigger "unchecked MSR access error" in dmesg. Please 
let me know if this doesn't work. 

Thanks,
Song

> 
>>> [  139.495587] Call Trace:
>>> [  139.495845]  bpf_get_branch_snapshot+0x17/0x40
>>> [  139.496285]  bpf_prog_35810402cd1d294c_test1+0x33/0xe6c
>>> [  139.496791]  bpf_trampoline_10737534536_0+0x4c/0x1000
>>> [  139.497274]  bpf_testmod_loop_test+0x5/0x20 [bpf_testmod]
>>> [  139.497799]  bpf_testmod_test_read+0x71/0x1f0 [bpf_testmod]
>>> [  139.498332]  ? bpf_testmod_loop_test+0x20/0x20 [bpf_testmod]
>>> [  139.498878]  ? sysfs_kf_bin_read+0xbe/0x110
>>> [  139.499284]  ? bpf_testmod_loop_test+0x20/0x20 [bpf_testmod]
>>> [  139.499829]  kernfs_fop_read_iter+0x1ac/0x2c0
>>> [  139.500245]  ? kernfs_create_link+0x110/0x110
>>> [  139.500667]  new_sync_read+0x24b/0x360
>>> [  139.501037]  ? __x64_sys_llseek+0x1e0/0x1e0
>>> [  139.501444]  ? rcu_read_lock_held_common+0x1a/0x50
>>> [  139.501942]  ? rcu_read_lock_held_common+0x1a/0x50
>>> [  139.502404]  ? rcu_read_lock_sched_held+0x5f/0xd0
>>> [  139.502865]  ? rcu_read_lock_bh_held+0xb0/0xb0
>>> [  139.503294]  ? security_file_permission+0xe7/0x2c0
>>> [  139.503758]  vfs_read+0x1a4/0x2a0
>>> [  139.504091]  ksys_read+0xc0/0x160
>>> [  139.504413]  ? vfs_write+0x510/0x510
>>> [  139.504756]  ? ktime_get_coarse_real_ts64+0xe4/0xf0
>>> [  139.505234]  do_syscall_64+0x3a/0x80
>>> [  139.505581]  entry_SYSCALL_64_after_hwframe+0x44/0xae
>>> [  139.506066] RIP: 0033:0x7fb8a05728b2
>>> [  139.506413] Code: 97 20 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b6 0f 1f 80 00 00 00 00 f3 0f 1e fa 8b 05 96 db 20 00 85 c0 75 12 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 56 c3 0f 1f 44 00 00 41 54 49 89 d4 55 48 89
>>> [  139.508164] RSP: 002b:00007ffe66315a28 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
>>> [  139.508870] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fb8a05728b2
>>> [  139.509545] RDX: 0000000000000064 RSI: 0000000000000000 RDI: 0000000000000010
>>> [  139.510225] RBP: 00007ffe66315a60 R08: 0000000000000000 R09: 00007ffe66315907
>>> [  139.510897] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000040c8b0
>>> [  139.511570] R13: 00007ffe66315cc0 R14: 0000000000000000 R15: 0000000000000000