selftests/bpf: Add stress test for rqspinlock in NMI
Subsystems (3)
Kumar Kartikeya Dwivedi
maintainerPATCH 1/1 selftests/bpf: Add stress test for rqspinlock in NMI
Introduce a kernel module that will exercise lock acquisition in the NMI path, and bias toward creating contention such that NMI waiters end up being non-head waiters. Prior to the rqspinlock fix made in the commit 0d80e7f951be ("rqspinlock: Choose trylock fallback for NMI waiters"), it was possible for the queueing path of non-head waiters to get stuck in NMI, which this stress test reproduces fairly easily with just 3 CPUs.
Both AA and ABBA flavors are supported, and it will serve as a test case for future fixes that address this corner case. More information about the problem in question is available in the commit cited above. When the fix is reverted, this stress test will lock up the system.
To enable this test automatically through the test_progs infrastructure, add a load_module_params API to exercise both AA and ABBA cases when running the test.
Note that the test runs for at most 5 seconds, and becomes a noop after that, in order to allow the system to make forward progress. In addition, CPU 0 is always kept untouched by the created threads and NMIs. The test will automatically scale to the number of available online CPUs.
Note that at least 3 CPUs are necessary to run this test, hence skip the selftest in case the environment has less than 3 CPUs available.
--- tools/testing/selftests/bpf/Makefile | 2 +- .../selftests/bpf/prog_tests/res_spin_lock.c | 16 ++ .../testing/selftests/bpf/test_kmods/Makefile | 2 +- .../bpf/test_kmods/bpf_test_rqspinlock.c | 208 ++++++++++++++++++ tools/testing/selftests/bpf/testing_helpers.c | 14 +- tools/testing/selftests/bpf/testing_helpers.h | 1 + 6 files changed, 239 insertions(+), 4 deletions(-) create mode 100644 tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c
tools/testing/selftests/bpf/Makefile +1 -1
@@ -120,7 +120,7 @@ TEST_PROGS_EXTENDED := \ test_bpftool.py TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko + bpf_test_modorder_y.ko bpf_test_rqspinlock.ko TEST_KMOD_TARGETS = $(addprefix $(OUTPUT)/,$(TEST_KMODS)) # Compile but not part of 'make run_tests'
tools/testing/selftests/bpf/prog_tests/res_spin_lock.c +16 -0
@@ -99,3 +99,19 @@ void test_res_spin_lock_success(void)res_spin_lock__destroy (skel);return ; } + +void serial_test_res_spin_lock_stress (void ) +{ +if (libbpf_num_possible_cpus () <3 ) { +test__skip (); +return ; + } + +ASSERT_OK (load_module ("bpf_test_rqspinlock.ko" , false),"load module AA" ); +sleep (5 ); +unload_module ("bpf_test_rqspinlock" , false); + +ASSERT_OK (load_module_params ("bpf_test_rqspinlock.ko" ,"test_ab=1" , false),"load module ABBA" ); +sleep (5 ); +unload_module ("bpf_test_rqspinlock" , false); +}
tools/testing/selftests/bpf/test_kmods/Makefile +1 -1
@@ -8,7 +8,7 @@ Q = @ endif MODULES = bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko + bpf_test_modorder_y.ko bpf_test_rqspinlock.ko $(foreach m,$(MODULES),$(eval obj-m += $(m:.ko=.o)))
tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c new file +208 -0
208 lines not on this page · raw message
tools/testing/selftests/bpf/testing_helpers.c +12 -2
@@ -399,7 +399,7 @@ int unload_module(const char *name, bool verbose)return 0 ; } -int load_module (const char *path,bool verbose) +static int __load_module (const char *path,const char *param_values,bool verbose) {int fd;
@@ -411,7 +411,7 @@ int load_module(const char *path, bool verbose)fprintf (stdout,"Can't find %s kernel module: %d\n" , path, -errno);return -ENOENT ; } -if (finit_module (fd,"" ,0 )) { +if (finit_module (fd, param_values,0 )) {fprintf (stdout,"Failed to load %s into the kernel: %d\n" , path, -errno);close (fd);return -EINVAL ;
@@ -423,6 +423,16 @@ int load_module(const char *path, bool verbose)return 0 ; } +int load_module_params (const char *path,const char *param_values,bool verbose) +{ +return __load_module (path, param_values, verbose); +} + +int load_module (const char *path,bool verbose) +{ +return __load_module (path,"" , verbose); +} +int unload_bpf_testmod (bool verbose) {return unload_module ("bpf_testmod" , verbose);
tools/testing/selftests/bpf/testing_helpers.h +1 -0
@@ -39,6 +39,7 @@ int kern_sync_rcu(void);int finit_module (int fd,const char *param_values,int flags);int delete_module (const char *name,int flags);int load_module (const char *path,bool verbose); +int load_module_params (const char *path,const char *param_values,bool verbose);int unload_module (const char *name,bool verbose);static inline __u64 get_time_ns (void )
--
2.51.0
Kumar Kartikeya Dwivedi
maintainerQuoted 23 lines · Kumar Kartikeya Dwivedi
Introduce a kernel module that will exercise lock acquisition in the NMI path, and bias toward creating contention such that NMI waiters end up being non-head waiters. Prior to the rqspinlock fix made in the commit
0d80e7f951be("rqspinlock: Choose trylock fallback for NMI waiters"), it was possible for the queueing path of non-head waiters to get stuck in NMI, which this stress test reproduces fairly easily with just 3 CPUs.Both AA and ABBA flavors are supported, and it will serve as a test case for future fixes that address this corner case. More information about the problem in question is available in the commit cited above. When the fix is reverted, this stress test will lock up the system.
To enable this test automatically through the
test_progsinfrastructure, add aload_module_paramsAPI to exercise both AA and ABBA cases when running the test.Note that the test runs for at most 5 seconds, and becomes a noop after that, in order to allow the system to make forward progress. In addition, CPU 0 is always kept untouched by the created threads and NMIs. The test will automatically scale to the number of available online CPUs.
Quoted 5 lines
Note that at least 3 CPUs are necessary to run this test, hence skip the selftest in case the environment has less than 3 CPUs available.
Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>---
This currently won't trigger in BPF CI, as the VMs have two CPUs allocated to them.
I was wondering if this is a simple change, otherwise I can rework the module to work with less than 3 CPUs.
Quoted 28 lines · Kumar Kartikeya Dwivedi
Quoted 26 lines · Kumar Kartikeya Dwivedi
Introduce a kernel module that will exercise lock acquisition in the NMI path, and bias toward creating contention such that NMI waiters end up being non-head waiters. Prior to the rqspinlock fix made in the commit
0d80e7f951be("rqspinlock: Choose trylock fallback for NMI waiters"), it was possible for the queueing path of non-head waiters to get stuck in NMI, which this stress test reproduces fairly easily with just 3 CPUs.Both AA and ABBA flavors are supported, and it will serve as a test case for future fixes that address this corner case. More information about the problem in question is available in the commit cited above. When the fix is reverted, this stress test will lock up the system.
To enable this test automatically through the
test_progsinfrastructure, add aload_module_paramsAPI to exercise both AA and ABBA cases when running the test.Note that the test runs for at most 5 seconds, and becomes a noop after that, in order to allow the system to make forward progress. In addition, CPU 0 is always kept untouched by the created threads and NMIs. The test will automatically scale to the number of available online CPUs.
Note that at least 3 CPUs are necessary to run this test, hence skip the selftest in case the environment has less than 3 CPUs available.
Quoted 7 lines
Quoted 2 lines
Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>---
This currently won't trigger in BPF CI, as the VMs have two CPUs allocated to them.
I was wondering if this is a simple change, otherwise I can rework the module to work with less than 3 CPUs.
It's fine. We can bump CI's cpu count.
But please see the bug spotted by our brand new AI review. Despite false positives it's amazing what it catches.
Don't click on "Logs for ai-review" pw entry.
It's hard to navigate from there.
Click on "PR summary" and scroll down.
Kumar Kartikeya Dwivedi
maintainerQuoted 39 lines · Alexei Starovoitov
Quoted 28 lines · Kumar Kartikeya Dwivedi
Quoted 26 lines · Kumar Kartikeya Dwivedi
Introduce a kernel module that will exercise lock acquisition in the NMI path, and bias toward creating contention such that NMI waiters end up being non-head waiters. Prior to the rqspinlock fix made in the commit
0d80e7f951be("rqspinlock: Choose trylock fallback for NMI waiters"), it was possible for the queueing path of non-head waiters to get stuck in NMI, which this stress test reproduces fairly easily with just 3 CPUs.Both AA and ABBA flavors are supported, and it will serve as a test case for future fixes that address this corner case. More information about the problem in question is available in the commit cited above. When the fix is reverted, this stress test will lock up the system.
To enable this test automatically through the
test_progsinfrastructure, add aload_module_paramsAPI to exercise both AA and ABBA cases when running the test.Note that the test runs for at most 5 seconds, and becomes a noop after that, in order to allow the system to make forward progress. In addition, CPU 0 is always kept untouched by the created threads and NMIs. The test will automatically scale to the number of available online CPUs.
Note that at least 3 CPUs are necessary to run this test, hence skip the selftest in case the environment has less than 3 CPUs available.
Quoted 7 lines
Quoted 2 lines
Signed-off-by Kumar Kartikeya Dwivedi <[email protected]>---
This currently won't trigger in BPF CI, as the VMs have two CPUs allocated to them.
I was wondering if this is a simple change, otherwise I can rework the module to work with less than 3 CPUs.
Quoted 8 lines
It's fine. We can bump CI's cpu count.
But please see the bug spotted by our brand new AI review. Despite false positives it's amazing what it catches.
Don't click on "Logs for ai-review" pw entry.
It's hard to navigate from there.
Click on "PR summary" and scroll down.
Honored to be the first recipient (thanks for working on this Ihor and Chris). Should we use a Reported-by: to credit such bugs?
I can also respin as is for now and we can decide later, but we probably should keep track just for statistics.