- Linux-kselftest-mirror - lists.linaro.org

[PATCH AUTOSEL 5.15 2/6] selftests/bpf: Fix send_signal test with nested CONFIG_PARAVIRT

by Sasha Levin

From: Yonghong Song <yonghong.song(a)linux.dev> [ Upstream commit 7015843afcaf68c132784c89528dfddc0005e483 ] Alexei reported that send_signal test may fail with nested CONFIG_PARAVIRT configs. In this particular case, the base VM is AMD with 166 cpus, and I run selftests with regular qemu on top of that and indeed send_signal test failed. I also tried with an Intel box with 80 cpus and there is no issue. The main qemu command line includes: -enable-kvm -smp 16 -cpu host The failure log looks like: $ ./test_progs -t send_signal [ 48.501588] watchdog: BUG: soft lockup - CPU#9 stuck for 26s! [test_progs:2225] [ 48.503622] Modules linked in: bpf_testmod(O) [ 48.503622] CPU: 9 PID: 2225 Comm: test_progs Tainted: G O 6.9.0-08561-g2c1713a8f1c9-dirty #69 [ 48.507629] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 [ 48.511635] RIP: 0010:handle_softirqs+0x71/0x290 [ 48.511635] Code: [...] 10 0a 00 00 00 31 c0 65 66 89 05 d5 f4 fa 7e fb bb ff ff ff ff <49> c7 c2 cb [ 48.518527] RSP: 0018:ffffc90000310fa0 EFLAGS: 00000246 [ 48.519579] RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 00000000000006e0 [ 48.522526] RDX: 0000000000000006 RSI: ffff88810791ae80 RDI: 0000000000000000 [ 48.523587] RBP: ffffc90000fabc88 R08: 00000005a0af4f7f R09: 0000000000000000 [ 48.525525] R10: 0000000561d2f29c R11: 0000000000006534 R12: 0000000000000280 [ 48.528525] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 48.528525] FS: 00007f2f2885cd00(0000) GS:ffff888237c40000(0000) knlGS:0000000000000000 [ 48.531600] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 48.535520] CR2: 00007f2f287059f0 CR3: 0000000106a28002 CR4: 00000000003706f0 [ 48.537538] Call Trace: [ 48.537538] <IRQ> [ 48.537538] ? watchdog_timer_fn+0x1cd/0x250 [ 48.539590] ? lockup_detector_update_enable+0x50/0x50 [ 48.539590] ? __hrtimer_run_queues+0xff/0x280 [ 48.542520] ? hrtimer_interrupt+0x103/0x230 [ 48.544524] ? __sysvec_apic_timer_interrupt+0x4f/0x140 [ 48.545522] ? sysvec_apic_timer_interrupt+0x3a/0x90 [ 48.547612] ? asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.547612] ? handle_softirqs+0x71/0x290 [ 48.547612] irq_exit_rcu+0x63/0x80 [ 48.551585] sysvec_apic_timer_interrupt+0x75/0x90 [ 48.552521] </IRQ> [ 48.553529] <TASK> [ 48.553529] asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.555609] RIP: 0010:finish_task_switch.isra.0+0x90/0x260 [ 48.556526] Code: [...] 9f 58 0a 00 00 48 85 db 0f 85 89 01 00 00 4c 89 ff e8 53 d9 bd 00 fb 66 90 <4d> 85 ed 74 [ 48.562524] RSP: 0018:ffffc90000fabd38 EFLAGS: 00000282 [ 48.563589] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff83385620 [ 48.563589] RDX: ffff888237c73ae4 RSI: 0000000000000000 RDI: ffff888237c6fd00 [ 48.568521] RBP: ffffc90000fabd68 R08: 0000000000000000 R09: 0000000000000000 [ 48.569528] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8881009d0000 [ 48.573525] R13: ffff8881024e5400 R14: ffff88810791ae80 R15: ffff888237c6fd00 [ 48.575614] ? finish_task_switch.isra.0+0x8d/0x260 [ 48.576523] __schedule+0x364/0xac0 [ 48.577535] schedule+0x2e/0x110 [ 48.578555] pipe_read+0x301/0x400 [ 48.579589] ? destroy_sched_domains_rcu+0x30/0x30 [ 48.579589] vfs_read+0x2b3/0x2f0 [ 48.579589] ksys_read+0x8b/0xc0 [ 48.583590] do_syscall_64+0x3d/0xc0 [ 48.583590] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 48.586525] RIP: 0033:0x7f2f28703fa1 [ 48.587592] Code: [...] 00 00 00 0f 1f 44 00 00 f3 0f 1e fa 80 3d c5 23 14 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 [ 48.593534] RSP: 002b:00007ffd90f8cf88 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 48.595589] RAX: ffffffffffffffda RBX: 00007ffd90f8d5e8 RCX: 00007f2f28703fa1 [ 48.595589] RDX: 0000000000000001 RSI: 00007ffd90f8cfb0 RDI: 0000000000000006 [ 48.599592] RBP: 00007ffd90f8d2f0 R08: 0000000000000064 R09: 0000000000000000 [ 48.602527] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [ 48.603589] R13: 00007ffd90f8d608 R14: 00007f2f288d8000 R15: 0000000000f6bdb0 [ 48.605527] </TASK> In the test, two processes are communicating through pipe. Further debugging with strace found that the above splat is triggered as read() syscall could not receive the data even if the corresponding write() syscall in another process successfully wrote data into the pipe. The failed subtest is "send_signal_perf". The corresponding perf event has sample_period 1 and config PERF_COUNT_SW_CPU_CLOCK. sample_period 1 means every overflow event will trigger a call to the BPF program. So I suspect this may overwhelm the system. So I increased the sample_period to 100,000 and the test passed. The sample_period 10,000 still has the test failed. In other parts of selftest, e.g., [1], sample_freq is used instead. So I decided to use sample_freq = 1,000 since the test can pass as well. [1] https://lore.kernel.org/bpf/20240604070700.3032142-1-song@kernel.org/ Reported-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Yonghong Song <yonghong.song(a)linux.dev> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20240605201203.2603846-1-yonghong.song@linux.dev Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/prog_tests/send_signal.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 776916b61c406..7b1343f70e65a 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -149,7 +149,8 @@ static void test_send_signal_tracepoint(bool signal_thread) static void test_send_signal_perf(bool signal_thread) { struct perf_event_attr attr = { - .sample_period = 1, + .freq = 1, + .sample_freq = 1000, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, }; -- 2.43.0

11 months, 1 week

1
0
0 0

[PATCH AUTOSEL 6.1 04/11] selftests/bpf: Fix send_signal test with nested CONFIG_PARAVIRT

by Sasha Levin

From: Yonghong Song <yonghong.song(a)linux.dev> [ Upstream commit 7015843afcaf68c132784c89528dfddc0005e483 ] Alexei reported that send_signal test may fail with nested CONFIG_PARAVIRT configs. In this particular case, the base VM is AMD with 166 cpus, and I run selftests with regular qemu on top of that and indeed send_signal test failed. I also tried with an Intel box with 80 cpus and there is no issue. The main qemu command line includes: -enable-kvm -smp 16 -cpu host The failure log looks like: $ ./test_progs -t send_signal [ 48.501588] watchdog: BUG: soft lockup - CPU#9 stuck for 26s! [test_progs:2225] [ 48.503622] Modules linked in: bpf_testmod(O) [ 48.503622] CPU: 9 PID: 2225 Comm: test_progs Tainted: G O 6.9.0-08561-g2c1713a8f1c9-dirty #69 [ 48.507629] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 [ 48.511635] RIP: 0010:handle_softirqs+0x71/0x290 [ 48.511635] Code: [...] 10 0a 00 00 00 31 c0 65 66 89 05 d5 f4 fa 7e fb bb ff ff ff ff <49> c7 c2 cb [ 48.518527] RSP: 0018:ffffc90000310fa0 EFLAGS: 00000246 [ 48.519579] RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 00000000000006e0 [ 48.522526] RDX: 0000000000000006 RSI: ffff88810791ae80 RDI: 0000000000000000 [ 48.523587] RBP: ffffc90000fabc88 R08: 00000005a0af4f7f R09: 0000000000000000 [ 48.525525] R10: 0000000561d2f29c R11: 0000000000006534 R12: 0000000000000280 [ 48.528525] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 48.528525] FS: 00007f2f2885cd00(0000) GS:ffff888237c40000(0000) knlGS:0000000000000000 [ 48.531600] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 48.535520] CR2: 00007f2f287059f0 CR3: 0000000106a28002 CR4: 00000000003706f0 [ 48.537538] Call Trace: [ 48.537538] <IRQ> [ 48.537538] ? watchdog_timer_fn+0x1cd/0x250 [ 48.539590] ? lockup_detector_update_enable+0x50/0x50 [ 48.539590] ? __hrtimer_run_queues+0xff/0x280 [ 48.542520] ? hrtimer_interrupt+0x103/0x230 [ 48.544524] ? __sysvec_apic_timer_interrupt+0x4f/0x140 [ 48.545522] ? sysvec_apic_timer_interrupt+0x3a/0x90 [ 48.547612] ? asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.547612] ? handle_softirqs+0x71/0x290 [ 48.547612] irq_exit_rcu+0x63/0x80 [ 48.551585] sysvec_apic_timer_interrupt+0x75/0x90 [ 48.552521] </IRQ> [ 48.553529] <TASK> [ 48.553529] asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.555609] RIP: 0010:finish_task_switch.isra.0+0x90/0x260 [ 48.556526] Code: [...] 9f 58 0a 00 00 48 85 db 0f 85 89 01 00 00 4c 89 ff e8 53 d9 bd 00 fb 66 90 <4d> 85 ed 74 [ 48.562524] RSP: 0018:ffffc90000fabd38 EFLAGS: 00000282 [ 48.563589] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff83385620 [ 48.563589] RDX: ffff888237c73ae4 RSI: 0000000000000000 RDI: ffff888237c6fd00 [ 48.568521] RBP: ffffc90000fabd68 R08: 0000000000000000 R09: 0000000000000000 [ 48.569528] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8881009d0000 [ 48.573525] R13: ffff8881024e5400 R14: ffff88810791ae80 R15: ffff888237c6fd00 [ 48.575614] ? finish_task_switch.isra.0+0x8d/0x260 [ 48.576523] __schedule+0x364/0xac0 [ 48.577535] schedule+0x2e/0x110 [ 48.578555] pipe_read+0x301/0x400 [ 48.579589] ? destroy_sched_domains_rcu+0x30/0x30 [ 48.579589] vfs_read+0x2b3/0x2f0 [ 48.579589] ksys_read+0x8b/0xc0 [ 48.583590] do_syscall_64+0x3d/0xc0 [ 48.583590] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 48.586525] RIP: 0033:0x7f2f28703fa1 [ 48.587592] Code: [...] 00 00 00 0f 1f 44 00 00 f3 0f 1e fa 80 3d c5 23 14 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 [ 48.593534] RSP: 002b:00007ffd90f8cf88 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 48.595589] RAX: ffffffffffffffda RBX: 00007ffd90f8d5e8 RCX: 00007f2f28703fa1 [ 48.595589] RDX: 0000000000000001 RSI: 00007ffd90f8cfb0 RDI: 0000000000000006 [ 48.599592] RBP: 00007ffd90f8d2f0 R08: 0000000000000064 R09: 0000000000000000 [ 48.602527] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [ 48.603589] R13: 00007ffd90f8d608 R14: 00007f2f288d8000 R15: 0000000000f6bdb0 [ 48.605527] </TASK> In the test, two processes are communicating through pipe. Further debugging with strace found that the above splat is triggered as read() syscall could not receive the data even if the corresponding write() syscall in another process successfully wrote data into the pipe. The failed subtest is "send_signal_perf". The corresponding perf event has sample_period 1 and config PERF_COUNT_SW_CPU_CLOCK. sample_period 1 means every overflow event will trigger a call to the BPF program. So I suspect this may overwhelm the system. So I increased the sample_period to 100,000 and the test passed. The sample_period 10,000 still has the test failed. In other parts of selftest, e.g., [1], sample_freq is used instead. So I decided to use sample_freq = 1,000 since the test can pass as well. [1] https://lore.kernel.org/bpf/20240604070700.3032142-1-song@kernel.org/ Reported-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Yonghong Song <yonghong.song(a)linux.dev> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20240605201203.2603846-1-yonghong.song@linux.dev Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/prog_tests/send_signal.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index d63a20fbed339..210b806351bcf 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -152,7 +152,8 @@ static void test_send_signal_tracepoint(bool signal_thread) static void test_send_signal_perf(bool signal_thread) { struct perf_event_attr attr = { - .sample_period = 1, + .freq = 1, + .sample_freq = 1000, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, }; -- 2.43.0

11 months, 1 week

1
0
0 0

[PATCH AUTOSEL 6.6 05/15] selftests/bpf: Fix send_signal test with nested CONFIG_PARAVIRT

by Sasha Levin

From: Yonghong Song <yonghong.song(a)linux.dev> [ Upstream commit 7015843afcaf68c132784c89528dfddc0005e483 ] Alexei reported that send_signal test may fail with nested CONFIG_PARAVIRT configs. In this particular case, the base VM is AMD with 166 cpus, and I run selftests with regular qemu on top of that and indeed send_signal test failed. I also tried with an Intel box with 80 cpus and there is no issue. The main qemu command line includes: -enable-kvm -smp 16 -cpu host The failure log looks like: $ ./test_progs -t send_signal [ 48.501588] watchdog: BUG: soft lockup - CPU#9 stuck for 26s! [test_progs:2225] [ 48.503622] Modules linked in: bpf_testmod(O) [ 48.503622] CPU: 9 PID: 2225 Comm: test_progs Tainted: G O 6.9.0-08561-g2c1713a8f1c9-dirty #69 [ 48.507629] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 [ 48.511635] RIP: 0010:handle_softirqs+0x71/0x290 [ 48.511635] Code: [...] 10 0a 00 00 00 31 c0 65 66 89 05 d5 f4 fa 7e fb bb ff ff ff ff <49> c7 c2 cb [ 48.518527] RSP: 0018:ffffc90000310fa0 EFLAGS: 00000246 [ 48.519579] RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 00000000000006e0 [ 48.522526] RDX: 0000000000000006 RSI: ffff88810791ae80 RDI: 0000000000000000 [ 48.523587] RBP: ffffc90000fabc88 R08: 00000005a0af4f7f R09: 0000000000000000 [ 48.525525] R10: 0000000561d2f29c R11: 0000000000006534 R12: 0000000000000280 [ 48.528525] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 48.528525] FS: 00007f2f2885cd00(0000) GS:ffff888237c40000(0000) knlGS:0000000000000000 [ 48.531600] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 48.535520] CR2: 00007f2f287059f0 CR3: 0000000106a28002 CR4: 00000000003706f0 [ 48.537538] Call Trace: [ 48.537538] <IRQ> [ 48.537538] ? watchdog_timer_fn+0x1cd/0x250 [ 48.539590] ? lockup_detector_update_enable+0x50/0x50 [ 48.539590] ? __hrtimer_run_queues+0xff/0x280 [ 48.542520] ? hrtimer_interrupt+0x103/0x230 [ 48.544524] ? __sysvec_apic_timer_interrupt+0x4f/0x140 [ 48.545522] ? sysvec_apic_timer_interrupt+0x3a/0x90 [ 48.547612] ? asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.547612] ? handle_softirqs+0x71/0x290 [ 48.547612] irq_exit_rcu+0x63/0x80 [ 48.551585] sysvec_apic_timer_interrupt+0x75/0x90 [ 48.552521] </IRQ> [ 48.553529] <TASK> [ 48.553529] asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.555609] RIP: 0010:finish_task_switch.isra.0+0x90/0x260 [ 48.556526] Code: [...] 9f 58 0a 00 00 48 85 db 0f 85 89 01 00 00 4c 89 ff e8 53 d9 bd 00 fb 66 90 <4d> 85 ed 74 [ 48.562524] RSP: 0018:ffffc90000fabd38 EFLAGS: 00000282 [ 48.563589] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff83385620 [ 48.563589] RDX: ffff888237c73ae4 RSI: 0000000000000000 RDI: ffff888237c6fd00 [ 48.568521] RBP: ffffc90000fabd68 R08: 0000000000000000 R09: 0000000000000000 [ 48.569528] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8881009d0000 [ 48.573525] R13: ffff8881024e5400 R14: ffff88810791ae80 R15: ffff888237c6fd00 [ 48.575614] ? finish_task_switch.isra.0+0x8d/0x260 [ 48.576523] __schedule+0x364/0xac0 [ 48.577535] schedule+0x2e/0x110 [ 48.578555] pipe_read+0x301/0x400 [ 48.579589] ? destroy_sched_domains_rcu+0x30/0x30 [ 48.579589] vfs_read+0x2b3/0x2f0 [ 48.579589] ksys_read+0x8b/0xc0 [ 48.583590] do_syscall_64+0x3d/0xc0 [ 48.583590] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 48.586525] RIP: 0033:0x7f2f28703fa1 [ 48.587592] Code: [...] 00 00 00 0f 1f 44 00 00 f3 0f 1e fa 80 3d c5 23 14 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 [ 48.593534] RSP: 002b:00007ffd90f8cf88 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 48.595589] RAX: ffffffffffffffda RBX: 00007ffd90f8d5e8 RCX: 00007f2f28703fa1 [ 48.595589] RDX: 0000000000000001 RSI: 00007ffd90f8cfb0 RDI: 0000000000000006 [ 48.599592] RBP: 00007ffd90f8d2f0 R08: 0000000000000064 R09: 0000000000000000 [ 48.602527] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [ 48.603589] R13: 00007ffd90f8d608 R14: 00007f2f288d8000 R15: 0000000000f6bdb0 [ 48.605527] </TASK> In the test, two processes are communicating through pipe. Further debugging with strace found that the above splat is triggered as read() syscall could not receive the data even if the corresponding write() syscall in another process successfully wrote data into the pipe. The failed subtest is "send_signal_perf". The corresponding perf event has sample_period 1 and config PERF_COUNT_SW_CPU_CLOCK. sample_period 1 means every overflow event will trigger a call to the BPF program. So I suspect this may overwhelm the system. So I increased the sample_period to 100,000 and the test passed. The sample_period 10,000 still has the test failed. In other parts of selftest, e.g., [1], sample_freq is used instead. So I decided to use sample_freq = 1,000 since the test can pass as well. [1] https://lore.kernel.org/bpf/20240604070700.3032142-1-song@kernel.org/ Reported-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Yonghong Song <yonghong.song(a)linux.dev> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20240605201203.2603846-1-yonghong.song@linux.dev Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/prog_tests/send_signal.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index b15b343ebb6b1..9adcda7f1fedc 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -156,7 +156,8 @@ static void test_send_signal_tracepoint(bool signal_thread) static void test_send_signal_perf(bool signal_thread) { struct perf_event_attr attr = { - .sample_period = 1, + .freq = 1, + .sample_freq = 1000, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, }; -- 2.43.0

11 months, 1 week

1
0
0 0

[PATCH AUTOSEL 6.10 07/27] selftests/bpf: Fix send_signal test with nested CONFIG_PARAVIRT

by Sasha Levin

From: Yonghong Song <yonghong.song(a)linux.dev> [ Upstream commit 7015843afcaf68c132784c89528dfddc0005e483 ] Alexei reported that send_signal test may fail with nested CONFIG_PARAVIRT configs. In this particular case, the base VM is AMD with 166 cpus, and I run selftests with regular qemu on top of that and indeed send_signal test failed. I also tried with an Intel box with 80 cpus and there is no issue. The main qemu command line includes: -enable-kvm -smp 16 -cpu host The failure log looks like: $ ./test_progs -t send_signal [ 48.501588] watchdog: BUG: soft lockup - CPU#9 stuck for 26s! [test_progs:2225] [ 48.503622] Modules linked in: bpf_testmod(O) [ 48.503622] CPU: 9 PID: 2225 Comm: test_progs Tainted: G O 6.9.0-08561-g2c1713a8f1c9-dirty #69 [ 48.507629] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 [ 48.511635] RIP: 0010:handle_softirqs+0x71/0x290 [ 48.511635] Code: [...] 10 0a 00 00 00 31 c0 65 66 89 05 d5 f4 fa 7e fb bb ff ff ff ff <49> c7 c2 cb [ 48.518527] RSP: 0018:ffffc90000310fa0 EFLAGS: 00000246 [ 48.519579] RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 00000000000006e0 [ 48.522526] RDX: 0000000000000006 RSI: ffff88810791ae80 RDI: 0000000000000000 [ 48.523587] RBP: ffffc90000fabc88 R08: 00000005a0af4f7f R09: 0000000000000000 [ 48.525525] R10: 0000000561d2f29c R11: 0000000000006534 R12: 0000000000000280 [ 48.528525] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 48.528525] FS: 00007f2f2885cd00(0000) GS:ffff888237c40000(0000) knlGS:0000000000000000 [ 48.531600] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 48.535520] CR2: 00007f2f287059f0 CR3: 0000000106a28002 CR4: 00000000003706f0 [ 48.537538] Call Trace: [ 48.537538] <IRQ> [ 48.537538] ? watchdog_timer_fn+0x1cd/0x250 [ 48.539590] ? lockup_detector_update_enable+0x50/0x50 [ 48.539590] ? __hrtimer_run_queues+0xff/0x280 [ 48.542520] ? hrtimer_interrupt+0x103/0x230 [ 48.544524] ? __sysvec_apic_timer_interrupt+0x4f/0x140 [ 48.545522] ? sysvec_apic_timer_interrupt+0x3a/0x90 [ 48.547612] ? asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.547612] ? handle_softirqs+0x71/0x290 [ 48.547612] irq_exit_rcu+0x63/0x80 [ 48.551585] sysvec_apic_timer_interrupt+0x75/0x90 [ 48.552521] </IRQ> [ 48.553529] <TASK> [ 48.553529] asm_sysvec_apic_timer_interrupt+0x1a/0x20 [ 48.555609] RIP: 0010:finish_task_switch.isra.0+0x90/0x260 [ 48.556526] Code: [...] 9f 58 0a 00 00 48 85 db 0f 85 89 01 00 00 4c 89 ff e8 53 d9 bd 00 fb 66 90 <4d> 85 ed 74 [ 48.562524] RSP: 0018:ffffc90000fabd38 EFLAGS: 00000282 [ 48.563589] RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff83385620 [ 48.563589] RDX: ffff888237c73ae4 RSI: 0000000000000000 RDI: ffff888237c6fd00 [ 48.568521] RBP: ffffc90000fabd68 R08: 0000000000000000 R09: 0000000000000000 [ 48.569528] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8881009d0000 [ 48.573525] R13: ffff8881024e5400 R14: ffff88810791ae80 R15: ffff888237c6fd00 [ 48.575614] ? finish_task_switch.isra.0+0x8d/0x260 [ 48.576523] __schedule+0x364/0xac0 [ 48.577535] schedule+0x2e/0x110 [ 48.578555] pipe_read+0x301/0x400 [ 48.579589] ? destroy_sched_domains_rcu+0x30/0x30 [ 48.579589] vfs_read+0x2b3/0x2f0 [ 48.579589] ksys_read+0x8b/0xc0 [ 48.583590] do_syscall_64+0x3d/0xc0 [ 48.583590] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 48.586525] RIP: 0033:0x7f2f28703fa1 [ 48.587592] Code: [...] 00 00 00 0f 1f 44 00 00 f3 0f 1e fa 80 3d c5 23 14 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 [ 48.593534] RSP: 002b:00007ffd90f8cf88 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 48.595589] RAX: ffffffffffffffda RBX: 00007ffd90f8d5e8 RCX: 00007f2f28703fa1 [ 48.595589] RDX: 0000000000000001 RSI: 00007ffd90f8cfb0 RDI: 0000000000000006 [ 48.599592] RBP: 00007ffd90f8d2f0 R08: 0000000000000064 R09: 0000000000000000 [ 48.602527] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 [ 48.603589] R13: 00007ffd90f8d608 R14: 00007f2f288d8000 R15: 0000000000f6bdb0 [ 48.605527] </TASK> In the test, two processes are communicating through pipe. Further debugging with strace found that the above splat is triggered as read() syscall could not receive the data even if the corresponding write() syscall in another process successfully wrote data into the pipe. The failed subtest is "send_signal_perf". The corresponding perf event has sample_period 1 and config PERF_COUNT_SW_CPU_CLOCK. sample_period 1 means every overflow event will trigger a call to the BPF program. So I suspect this may overwhelm the system. So I increased the sample_period to 100,000 and the test passed. The sample_period 10,000 still has the test failed. In other parts of selftest, e.g., [1], sample_freq is used instead. So I decided to use sample_freq = 1,000 since the test can pass as well. [1] https://lore.kernel.org/bpf/20240604070700.3032142-1-song@kernel.org/ Reported-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Yonghong Song <yonghong.song(a)linux.dev> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20240605201203.2603846-1-yonghong.song@linux.dev Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/prog_tests/send_signal.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 920aee41bd58c..6cc69900b3106 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -156,7 +156,8 @@ static void test_send_signal_tracepoint(bool signal_thread) static void test_send_signal_perf(bool signal_thread) { struct perf_event_attr attr = { - .sample_period = 1, + .freq = 1, + .sample_freq = 1000, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_CLOCK, }; -- 2.43.0

11 months, 1 week

1
0
0 0

Re: [syzbot] [net?] INFO: rcu detected stall in ipv6_rcv (4)

by syzbot

syzbot suspects this issue was fixed by commit: commit fb66df20a7201e60f2b13d7f95d031b31a8831d3 Author: Vladimir Oltean <vladimir.oltean(a)nxp.com> Date: Mon May 27 15:39:55 2024 +0000 net/sched: taprio: extend minimum interval restriction to entire cycle too bisection log: https://syzkaller.appspot.com/x/bisect.txt?x=179b2623980000 start commit: 2cf4f94d8e86 Merge tag 'scsi-fixes' of git://git.kernel.or.. git tree: upstream kernel config: https://syzkaller.appspot.com/x/.config?x=314e9ad033a7d3a7 dashboard link: https://syzkaller.appspot.com/bug?extid=d9b3e95a78490389cfb7 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=1487fc06e80000 C reproducer: https://syzkaller.appspot.com/x/repro.c?x=11e5b4d6e80000 If the result looks correct, please mark the issue as fixed by replying with: #syz fix: net/sched: taprio: extend minimum interval restriction to entire cycle too For information about bisection process see: https://goo.gl/tpsmEJ#bisection

11 months, 1 week

1
0
0 0

[PATCH 0/3] selftests/bpf: convert test_dev_cgroup to test_progs

by Alexis Lothoré (eBPF Foundation)

Hello, this small series aims to integrate test_dev_cgroup in test_progs so it could be run automatically in CI. The new version brings a few differences with the current one: - test now uses directly syscalls instead of wrapping commandline tools into system() calls - test_progs manipulates /dev/null (eg: redirecting test logs into it), so disabling access to it in the bpf program confuses the tests. To fix this, the first commit modifies the bpf program to allow access to char devices 1:3 (/dev/null), and disable access to char devices 1:5 (/dev/zero) - once test is converted, add a small subtest to also check for device type interpretation (char or block) - paths used in mknod tests are now in /dev instead of /tmp: due to the CI runner organisation and mountpoints manipulations, trying to create nodes in /tmp leads to errors unrelated to the test (ie, mknod calls refused by kernel, not the bpf program). I don't understand exactly the root cause at the deepest point (all I see in CI is an -ENXIO error on mknod when trying to create the node in tmp, and I can not make sense out of it neither replicate it locally), so I would gladly take inputs from anyone more educated than me about this. The new test_progs part has been tested in a local qemu environment as well as in upstream CI: ./test_progs -a cgroup_dev 47/1 cgroup_dev/deny-mknod:OK 47/2 cgroup_dev/allow-mknod:OK 47/3 cgroup_dev/deny-mknod-wrong-type:OK 47/4 cgroup_dev/allow-read:OK 47/5 cgroup_dev/allow-write:OK 47/6 cgroup_dev/deny-read:OK 47/7 cgroup_dev/deny-write:OK 47 cgroup_dev:OK Summary: 1/7 PASSED, 0 SKIPPED, 0 FAILED --- Alexis Lothoré (eBPF Foundation) (3): selftests/bpf: do not disable /dev/null device access in cgroup dev test selftests/bpf: convert test_dev_cgroup to test_progs selftests/bpf: add wrong type test to cgroup dev tools/testing/selftests/bpf/.gitignore | 1 - tools/testing/selftests/bpf/Makefile | 2 - .../testing/selftests/bpf/prog_tests/cgroup_dev.c | 123 +++++++++++++++++++++ tools/testing/selftests/bpf/progs/dev_cgroup.c | 4 +- tools/testing/selftests/bpf/test_dev_cgroup.c | 85 -------------- 5 files changed, 125 insertions(+), 90 deletions(-) --- base-commit: c90e2d4a7738a24fbb3657092dbd1ca20c040ed1 change-id: 20240723-convert_dev_cgroup-6464b0d37f1a Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

11 months, 1 week

3
7
0 0

[PATCH v5] tools/testing:Fix the wrong format specifier

by Zhu Jun

The format specifier in fprintf is "%u", that "%u" should use unsigned int type instead.the problem is discovered by reading code. Signed-off-by: Zhu Jun <zhujun2(a)cmss.chinamobile.com> --- v1->v2: modify commit info add how to find the problem in the log v2->v3: Seems this can use macro WTERMSIG like those above usage, rather than changing the print format. v3->v4: Now the commit summary doesn't match the change you are making. Also WTERMSIG() is incorrect for this conditional code path. See comments below in the code path. I would leave the v2 code intact. How are you testing this change? Please include the details in the change log. v4->v5: Compile the kernel for testing using make tools/testing/selftests/kselftest_harness.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index e05ac8261046..675b8f43e148 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -910,7 +910,7 @@ void __wait_for_test(struct __test_metadata *t) .sa_flags = SA_SIGINFO, }; struct sigaction saved_action; - int status; + unsigned int status; if (sigaction(SIGALRM, &action, &saved_action)) { t->passed = 0; -- 2.17.1

11 months, 1 week

3
2
0 0

Testing Quality Call notes - 2024-07-25

by Laura Nao

Hello, KernelCI is hosting a bi-weekly call on Thursday to discuss improvements to existing upstream tests, the development of new tests to increase kernel testing coverage, and the enablement of these tests in KernelCI. In recent months, we at Collabora have focused on various kernel areas, assessing the tests already available upstream and contributing patches to make them easily runnable in CIs. Below is a list of the tests we've been working on and their latest status updates, as discussed in the last meeting held on 2024-07-25: *USB/PCI devices kselftest* - Upstream test to detect unprobed devices on discoverable buses: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… - Test location changed (https://lore.kernel.org/all/20240705-dev-err-log-selftest-v2-1-163b9cd7b3c1…), updated KernelCI PRs accordingly: https://github.com/kernelci/kernelci-core/pull/2577 and https://github.com/kernelci/kernelci-pipeline/pull/642 - Will need to figure out how to structure the files to ensure scalability. A YAML schema would be useful too. *Error log test* - Proposing new kselftest to report device log errors: https://lore.kernel.org/all/20240423-dev-err-log-selftest-v1-0-690c1741d68b… - Now merged upstream *Missing devices kselftest* - Proposing new kselftest to report devices that go missing in the system: https://lore.kernel.org/all/20240724-kselftest-dev-exist-v1-1-9bc21aa761b5@… - The test checks the number of devices present against a reference file, generated by the program at a previous point on a known-good kernel, and reports any missing device. - Helps identifying missing kernel configs or broken driver features *Suspend/resume in cpufreq kselftest* - Enabling suspend/resume test within the cpufreq kselftest in KernelCI - Sent v2 for patch adding RTC wakeup alarm in the cpufreq kselftest: https://lore.kernel.org/lkml/20240715192634.19272-1-shreeya.patel@collabora… - The test now uses rtcwake, as suggested by Rafael J. Wysocki in the first review. There's no easy way to declare the dependency in the kselftest itself. - Patch got acked by the cpufreq kselftest author Viresh Kumar *Boot time test* - Sent first RFC: https://lore.kernel.org/all/20240725110622.96301-1-laura.nao@collabora.com/… *TAP conformance in kselftests* - Ongoing discussion upstream on TAP headers: https://lore.kernel.org/all/87fbfba4-8d4d-44ff-9fe5-e101cce3d6cb@collabora.… - Working to convert test modules used by kselftests into kunit. Cleanup patches sent: https://lore.kernel.org/all/20240725110817.659099-1-usama.anjum@collabora.c… and https://lore.kernel.org/all/20240725121212.808206-1-usama.anjum@collabora.c… Please reply to this thread if you'd like to join the call or discuss any of the topics further. We look forward to collaborating with the community to improve upstream tests and expand coverage to more areas of interest within the kernel. Best regards, Laura Nao

11 months, 1 week

1
0
0 0

[PATCH v8 5/5] KVM: riscv: selftests: Add Svade and Svadu Extension to get-reg-list test

by Yong-Xuan Wang

Update the get-reg-list test to test the Svade and Svadu Extensions are available for guest OS. Signed-off-by: Yong-Xuan Wang <yongxuan.wang(a)sifive.com> Reviewed-by: Andrew Jones <ajones(a)ventanamicro.com> --- tools/testing/selftests/kvm/riscv/get-reg-list.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 8e34f7fa44e9..aac40652e181 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -45,6 +45,8 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSCOFPMF: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVADE: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVADU: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT: @@ -418,6 +420,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(SSAIA), KVM_ISA_EXT_ARR(SSCOFPMF), KVM_ISA_EXT_ARR(SSTC), + KVM_ISA_EXT_ARR(SVADE), + KVM_ISA_EXT_ARR(SVADU), KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), KVM_ISA_EXT_ARR(SVPBMT), @@ -949,6 +953,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(h, H); KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN); KVM_ISA_EXT_SIMPLE_CONFIG(sscofpmf, SSCOFPMF); KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC); +KVM_ISA_EXT_SIMPLE_CONFIG(svade, SVADE); +KVM_ISA_EXT_SIMPLE_CONFIG(svadu, SVADU); KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL); KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT); @@ -1012,6 +1018,8 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_smstateen, &config_sscofpmf, &config_sstc, + &config_svade, + &config_svadu, &config_svinval, &config_svnapot, &config_svpbmt, -- 2.17.1

11 months, 1 week

1
0
0 0

[PATCH net] virtio: fix GSO with frames unaligned to size

by Jakub Kicinski

The commit under fixes added a questionable check to virtio_net_hdr_to_skb(). I'm guessing the check was supposed to protect from csum offset being outside of a segment (especially if len is not multiple of segment size). The condition can't be right, tho, as it breaks previously working sending of GSO frames with only one segment (i.e. when gso_size <= len we silently ignore the GSO request and send a single non-GSO frame). Fix the logic and move it to the GSO part. This has been caught by net/tap and net/psock_send.sh tests. Fixes: e269d79c7d35 ("net: missing check virtio") Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: willemdebruijn.kernel(a)gmail.com CC: mst(a)redhat.com CC: jasowang(a)redhat.com CC: xuanzhuo(a)linux.alibaba.com CC: eperezma(a)redhat.com CC: shuah(a)kernel.org CC: arefev(a)swemel.ru CC: virtualization(a)lists.linux.dev CC: linux-kselftest(a)vger.kernel.org --- include/linux/virtio_net.h | 27 ++++++++++++++++----------- tools/testing/selftests/net/tap.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+), 11 deletions(-) diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index d1d7825318c3..c54b7aa42921 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -52,11 +52,11 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, bool little_endian) { unsigned int nh_min_len = sizeof(struct iphdr); + unsigned int csum_needed = 0; unsigned int gso_type = 0; unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; - u64 ret, remainder, gso_size; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -99,16 +99,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); - if (hdr->gso_size) { - gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); - ret = div64_u64_rem(skb->len, gso_size, &remainder); - if (!(ret && (hdr->gso_size > needed) && - ((remainder > needed) || (remainder == 0)))) { - return -EINVAL; - } - skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG; - } - if (!pskb_may_pull(skb, needed)) return -EINVAL; @@ -119,6 +109,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, p_off = nh_min_len + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; + + csum_needed = needed; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. @@ -188,6 +180,19 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (gso_size == GSO_BY_FRAGS) return -EINVAL; + if (csum_needed) { + unsigned int p_rem, p_size; + + p_size = gso_size; + p_rem = (skb->len - nh_off) % gso_size; + if (p_rem) + p_size = p_rem; + + /* Make sure csum still within packet after GSO */ + if (p_size + nh_off < csum_needed) + return -EINVAL; + } + /* Too small packets are not really GSO ones. */ if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; diff --git a/tools/testing/selftests/net/tap.c b/tools/testing/selftests/net/tap.c index 247c3b3ac1c9..8527d51449cf 100644 --- a/tools/testing/selftests/net/tap.c +++ b/tools/testing/selftests/net/tap.c @@ -418,6 +418,36 @@ TEST_F(tap, test_packet_valid_udp_csum) ASSERT_EQ(ret, off); } +TEST_F(tap, test_packet_invalid_udp_gso_csum) +{ + uint8_t pkt[TEST_PACKET_SZ]; + uint16_t payload; + size_t off; + int ret; + int i; + + payload = ETH_DATA_LEN - sizeof(struct iphdr) - sizeof(struct udphdr); + + memset(pkt, 0, sizeof(pkt)); + off = build_test_packet_valid_udp_gso(pkt, payload); + + for (i = -16; i < 16; i++) { + ret = write(self->fd, pkt, off + i); + + if (i <= 0 || + i > __builtin_offsetof(struct udphdr, check) + 1) { + EXPECT_EQ(ret, off + i) + TH_LOG("mismatch with offset: %d (%zd)", + i, off + i); + } else { + EXPECT_EQ(ret, -1) + TH_LOG("mismatch with offset: %d (%zd)", + i, off + i); + EXPECT_EQ(errno, 22); + } + } +} + TEST_F(tap, test_packet_crash_tap_invalid_eth_proto) { uint8_t pkt[TEST_PACKET_SZ]; -- 2.45.2

11 months, 1 week

3
7
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror