June 2025 - Linux-kselftest-mirror

[PATCH bpf-next v1 0/2] bpf,ktls: Fix data corruption caused by using bpf_msg_pop_data() in ktls

by Jiayuan Chen

Cong reported an issue where running 'test_sockmap' in the current bpf-next tree results in an error [1]. The specific test case that triggered the error is a combined test involving ktls and bpf_msg_pop_data(). Root Cause: When sending plaintext data, we initially calculated the corresponding ciphertext length. However, if we later reduced the plaintext data length via socket policy, we failed to recalculate the ciphertext length. This results in transmitting buffers containing uninitialized data during ciphertext transmission. This causes uninitialized bytes to be appended after a complete "Application Data" packet, leading to errors on the receiving end when parsing TLS record. This issue has existed for a long time but was only exposed after the following test code was merged. commit 47eae080410b ("selftests/bpf: Add more tests for test_txmsg_push_pop in test_sockmap") Although we already had tests for pop data before this commit, the pop data length was insufficient (less than 5 bytes). This meant that the corrupted TLS records with data length <5 bytes were cached without being parsed, resulting in no error being triggered. After this fix, all tests pass. 1/ 6 sockmap::txmsg test passthrough:OK 2/ 6 sockmap::txmsg test redirect:OK 3/ 2 sockmap::txmsg test redirect wait send mem:OK 4/ 6 sockmap::txmsg test drop:OK 5/ 6 sockmap::txmsg test ingress redirect:OK 6/ 7 sockmap::txmsg test skb:OK 7/12 sockmap::txmsg test apply:OK 8/12 sockmap::txmsg test cork:OK 9/ 3 sockmap::txmsg test hanging corks:OK 10/11 sockmap::txmsg test push_data:OK 11/17 sockmap::txmsg test pull-data:OK 12/ 9 sockmap::txmsg test pop-data:OK 13/ 6 sockmap::txmsg test push/pop data:OK 14/ 1 sockmap::txmsg test ingress parser:OK 15/ 1 sockmap::txmsg test ingress parser2:OK 16/ 6 sockhash::txmsg test passthrough:OK 17/ 6 sockhash::txmsg test redirect:OK 18/ 2 sockhash::txmsg test redirect wait send mem:OK 19/ 6 sockhash::txmsg test drop:OK 20/ 6 sockhash::txmsg test ingress redirect:OK 21/ 7 sockhash::txmsg test skb:OK 22/12 sockhash::txmsg test apply:OK 23/12 sockhash::txmsg test cork:OK 24/ 3 sockhash::txmsg test hanging corks:OK 25/11 sockhash::txmsg test push_data:OK 26/17 sockhash::txmsg test pull-data:OK 27/ 9 sockhash::txmsg test pop-data:OK 28/ 6 sockhash::txmsg test push/pop data:OK 29/ 1 sockhash::txmsg test ingress parser:OK 30/ 1 sockhash::txmsg test ingress parser2:OK 31/ 6 sockhash:ktls:txmsg test passthrough:OK 32/ 6 sockhash:ktls:txmsg test redirect:OK 33/ 2 sockhash:ktls:txmsg test redirect wait send mem:OK 34/ 6 sockhash:ktls:txmsg test drop:OK 35/ 6 sockhash:ktls:txmsg test ingress redirect:OK 36/ 7 sockhash:ktls:txmsg test skb:OK 37/12 sockhash:ktls:txmsg test apply:OK 38/12 sockhash:ktls:txmsg test cork:OK 39/ 3 sockhash:ktls:txmsg test hanging corks:OK 40/11 sockhash:ktls:txmsg test push_data:OK 41/17 sockhash:ktls:txmsg test pull-data:OK 42/ 9 sockhash:ktls:txmsg test pop-data:OK 43/ 6 sockhash:ktls:txmsg test push/pop data:OK 44/ 1 sockhash:ktls:txmsg test ingress parser:OK 45/ 0 sockhash:ktls:txmsg test ingress parser2:OK Pass: 45 Fail: 0 [1]: https://lore.kernel.org/bpf/CAM_iQpU7=4xjbefZoxndKoX9gFFMOe7FcWMq5tHBsymbrn… Jiayuan Chen (2): bpf,ktls: Fix data corruption when using bpf_msg_pop_data() in ktls selftests/bpf: Add test to cover ktls with bpf_msg_pop_data net/tls/tls_sw.c | 15 +++ .../selftests/bpf/prog_tests/sockmap_ktls.c | 91 +++++++++++++++++++ .../selftests/bpf/progs/test_sockmap_ktls.c | 4 + 3 files changed, 110 insertions(+) -- 2.47.1

6 months, 1 week

3
7
0 0

[PATCH v2 0/3] KVM: arm64: selftests: arch_timer_edge_cases fixes

by Sebastian Ott

Some small fixes for arch_timer_edge_cases that I stumbled upon while debugging failures for this selftest on ampere-one. Changes since v1: modified patch 3 based on suggestions from Marc. I've done some tests with this on various machines - seems to be all good, however on ampere-one I now hit this in 10% of the runs: ==== Test Assertion Failure ==== arm64/arch_timer_edge_cases.c:481: timer_get_cntct(timer) >= DEF_CNT + (timer_get_cntfrq() * (uint64_t)(delta_2_ms) / 1000) pid=166657 tid=166657 errno=4 - Interrupted system call 1 0x0000000000404db3: test_run at arch_timer_edge_cases.c:933 2 0x0000000000401f9f: main at arch_timer_edge_cases.c:1062 3 0x0000ffffaedd625b: ?? ??:0 4 0x0000ffffaedd633b: ?? ??:0 5 0x00000000004020af: _start at ??:? timer_get_cntct(timer) >= DEF_CNT + msec_to_cycles(delta_2_ms) This is not new, it was just hidden behind the other failure. I'll try to figure out what this is about (seems to be independent of the wait time).. Sebastian Ott (3): KVM: arm64: selftests: fix help text for arch_timer_edge_cases KVM: arm64: selftests: fix thread migration in arch_timer_edge_cases KVM: arm64: selftests: arch_timer_edge_cases - determine effective counter width .../kvm/arm64/arch_timer_edge_cases.c | 37 ++++++++++++------- 1 file changed, 24 insertions(+), 13 deletions(-) base-commit: 0ff41df1cb268fc69e703a08a57ee14ae967d0ca -- 2.49.0

6 months, 1 week

3
7
0 0

[RFC] selftests/mm: Skip tests dependent on a binary not built

by Khaled Elnaggar

Hello. Running the mm selftests from the kernel's root directory on an x86_64 debian machine using: make defconfig sudo make kselftest TARGETS=mm the tests run normally till we reach one which stalls for 180 seconds and times out according to the following logs: ``` ----------------------------------------------- running ./charge_reserved_hugetlb.sh -cgroup-v2 ----------------------------------------------- CLEANUP DONE CLEANUP DONE Test normal case. private=, populate=, method=0, reserve= nr hugepages = 10 writing cgroup limit: 20971520 writing reseravation limit: 20971520 Starting: hugetlb_usage=0 reserved_usage=0 expect_failure is 0 Putting task in cgroup 'hugetlb_cgroup_test' Method is 0 >>> write_hugetlb_memory.sh: line 22: ./write_to_hugetlbfs: No such file or directory <<< Waiting for hugetlb memory reservation to reach size 10485760. 0 Waiting for hugetlb memory reservation to reach size 10485760. 0 ... Waiting for hugetlb memory reservation to reach size 10485760. 0 Waiting for hugetlb memory reservation to reach size 10485760. 0 not ok 1 selftests: mm: run_vmtests.sh # TIMEOUT 180 seconds make[3]: Leaving directory '/linux/tools/testing/selftests/mm' ``` Logs show that the executable "write_to_hugetlbfs" is missing, causing the test to hang waiting for hugepage reservations. The executable not found means it was not built by the Make system. It is mentioned in Makefile:136-142, and only built if ARCH is 64-bit ``` ifneq (,$(filter $(ARCH),arm64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390)) TEST_GEN_FILES += va_high_addr_switch ifneq ($(ARCH),riscv64) TEST_GEN_FILES += virtual_address_range endif TEST_GEN_FILES += write_to_hugetlbfs endif ``` So, for some reason, the top-level Makefile provides ARCH as x86. My proposed solution is similar to existing virtual_address_range check that is to check for the binary, and if it is not found, skip these 2 test cases: charge_reserved_hugetlb.sh and hugetlb_reparenting_test.sh since they directly and indirectly depend on write_to_hugetlbfs binary. This is just a workaround, the root issue of different ARCH detection when running tests from the kernel root directory should still be addressed. I am not sure how to approach it and open for your suggestions. Note that this issue does not happen when ran from selftests/mm using something like sudo make -C tools/testing/selftests/mm because then mm/Makefile's ARCH detection runs correctly (x86_64) Kindly review and share your thoughts. Signed-off-by: Khaled Elnaggar <khaledelnaggarlinux(a)gmail.com> --- tools/testing/selftests/mm/run_vmtests.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index dddd1dd8af14..cdbcfdb62f8a 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -375,8 +375,13 @@ CATEGORY="process_mrelease" run_test ./mrelease_test CATEGORY="mremap" run_test ./mremap_test CATEGORY="hugetlb" run_test ./thuge-gen + +# the following depend on write_to_hugetlbfs binary +if [ -x ./write_to_hugetlbfs ]; then CATEGORY="hugetlb" run_test ./charge_reserved_hugetlb.sh -cgroup-v2 CATEGORY="hugetlb" run_test ./hugetlb_reparenting_test.sh -cgroup-v2 +fi + if $RUN_DESTRUCTIVE; then nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages) enable_soft_offline=$(cat /proc/sys/vm/enable_soft_offline) -- 2.47.2

6 months, 1 week

3
5
0 0

[PATCH 00/17] ARM64 PMU Partitioning

by Colton Lewis

Overview: This series implements a new PMU scheme on ARM, a partitioned PMU that exists alongside the existing emulated PMU and may be enabled by the kernel command line kvm.reserved_host_counters or by the vcpu ioctl KVM_ARM_PARTITION_PMU. This is a continuation of the RFC posted earlier this year. [1] The high level overview and reason for the name is that this implementation takes advantage of recent CPU features to partition the PMU counters into a host-reserved set and a guest-reserved set. Guests are allowed untrapped hardware access to the most frequently used PMU registers and features for the guest-reserved counters only. This untrapped hardware access significantly reduces the overhead of using performance monitoring capabilities such as the `perf` tool inside a guest VM. Register accesses that aren't trapping to KVM mean less time spent in the host kernel and more time on the workloads guests care about. This optimization especially shines during high `perf` sample rates or large numbers of events that require multiplexing hardware counters. Performance: For example, the following tests were carried out on identical ARM machines with 10 general purpose counters with identical guest images run on QEMU, the only difference being my PMU implementation or the existing one. Some arguments have been simplified here to clarify the purpose of the test: 1) time perf record -e ${FIFTEEN_HW_EVENTS} -F 1000 -- \ gzip -c tmpfs/random.64M.img >/dev/null On emulated PMU this command took 4.143s real time with 0.159s system time. On partitioned PMU this command took 3.139s real time with 0.110s system time, runtime reductions of 24.23% and 30.82%. 2) time perf stat -dd -- \ automated_specint2017.sh On emulated PMU this benchmark completed in 3789.16s real time with 224.45s system time and a final benchmark score of 4.28. On partitioned PMU this benchmark completed in 3525.67s real time with 15.98s system time and a final benchmark score of 4.56. That is a 6.95% reduction in runtime, 92.88% reduction in system time, and 6.54% improvement in overall benchmark score. Seeing these improvements on something as lightweight as perf stat is remarkable and implies there would have been a much greater improvement with perf record. I did not test that because I was not confident it would even finish in a reasonable time on the emulated PMU Test 3 was slightly different, I ran the workload in a VM with a single VCPU pinned to a physical CPU and analyzed from the host where the physical CPU spent its time using mpstat. 3) perf record -e ${FIFTEEN_HW_EVENTS} -F 4000 -- \ stress-ng --cpu 0 --timeout 30 Over a period of 30s the cpu running with the emulated PMU spent 34.96% of the time in the host kernel and 55.85% of the time in the guest. The cpu running the partitioned PMU spent 0.97% of its time in the host kernel and 91.06% of its time in the guest. Taken together, these tests represent a remarkable performance improvement for anything perf related using this new PMU implementation. Caveats: Because the most consistent and performant thing to do was untrap PMCR_EL0, the number of counters visible to the guest via PMCR_EL0.N is always equal to the value KVM sets for MDCR_EL2.HPMN. Previously allowed writes to PMCR_EL0.N via {GET,SET}_ONE_REG no longer affect the guest. These improvements come at a cost to 7-35 new registers that must be swapped at every vcpu_load and vcpu_put if the feature is enabled. I have been informed KVM would like to avoid paying this cost when possible. One solution is to make the trapping changes and context swapping lazy such that the trapping changes and context swapping only take place after the guest has actually accessed the PMU so guests that never access the PMU never pay the cost. This is not done here because it is not crucial to the primary functionality and I thought review would be more productive as soon as I had something complete enough for reviewers to easily play with. However, this or any better ideas are on the table for inclusion in future re-rolls. [1] https://lore.kernel.org/kvmarm/20250213180317.3205285-1-coltonlewis@google.… Colton Lewis (16): arm64: cpufeature: Add cpucap for HPMN0 arm64: Generate sign macro for sysreg Enums arm64: cpufeature: Add cpucap for PMICNTR KVM: arm64: Reorganize PMU functions KVM: arm64: Introduce method to partition the PMU perf: arm_pmuv3: Generalize counter bitmasks perf: arm_pmuv3: Keep out of guest counter partition KVM: arm64: Set up FGT for Partitioned PMU KVM: arm64: Writethrough trapped PMEVTYPER register KVM: arm64: Use physical PMSELR for PMXEVTYPER if partitioned KVM: arm64: Writethrough trapped PMOVS register KVM: arm64: Context switch Partitioned PMU guest registers perf: pmuv3: Handle IRQs for Partitioned PMU guest counters KVM: arm64: Inject recorded guest interrupts KVM: arm64: Add ioctl to partition the PMU when supported KVM: arm64: selftests: Add test case for partitioned PMU Marc Zyngier (1): KVM: arm64: Cleanup PMU includes Documentation/virt/kvm/api.rst | 16 + arch/arm/include/asm/arm_pmuv3.h | 24 + arch/arm64/include/asm/arm_pmuv3.h | 36 +- arch/arm64/include/asm/kvm_host.h | 208 +++++- arch/arm64/include/asm/kvm_pmu.h | 82 +++ arch/arm64/kernel/cpufeature.c | 15 + arch/arm64/kvm/Makefile | 2 +- arch/arm64/kvm/arm.c | 24 +- arch/arm64/kvm/debug.c | 13 +- arch/arm64/kvm/hyp/include/hyp/switch.h | 65 +- arch/arm64/kvm/pmu-emul.c | 629 +---------------- arch/arm64/kvm/pmu-part.c | 358 ++++++++++ arch/arm64/kvm/pmu.c | 630 ++++++++++++++++++ arch/arm64/kvm/sys_regs.c | 54 +- arch/arm64/tools/cpucaps | 2 + arch/arm64/tools/gen-sysreg.awk | 1 + arch/arm64/tools/sysreg | 6 +- drivers/perf/arm_pmuv3.c | 55 +- include/kvm/arm_pmu.h | 199 ------ include/linux/perf/arm_pmu.h | 15 +- include/linux/perf/arm_pmuv3.h | 14 +- include/uapi/linux/kvm.h | 4 + tools/include/uapi/linux/kvm.h | 2 + .../selftests/kvm/arm64/vpmu_counter_access.c | 40 +- virt/kvm/kvm_main.c | 1 + 25 files changed, 1616 insertions(+), 879 deletions(-) create mode 100644 arch/arm64/include/asm/kvm_pmu.h create mode 100644 arch/arm64/kvm/pmu-part.c delete mode 100644 include/kvm/arm_pmu.h base-commit: 1b85d923ba8c9e6afaf19e26708411adde94fba8 -- 2.49.0.1204.g71687c7c1d-goog

6 months, 1 week

3
33
0 0

[PATCH] selftests: cachestat: add tests for mmap and /proc/cpuinfo

by Suresh K C

From: Suresh K C <suresh.k.chandrappa(a)gmail.com> Add a test case to verify cachestat behavior with memory-mapped files using mmap(). This ensures that pages accessed via mmap are correctly accounted for in the page cache. Also add a test for /proc/cpuinfo to validate cachestat's handling of virtual files in pseudo-filesystems. This improves test coverage for edge cases involving non-regular files. Tested on x86_64 with default kernel config. Signed-off-by: Suresh K C <suresh.k.chandrappa(a)gmail.com> --- .../selftests/cachestat/test_cachestat.c | 69 ++++++++++++++++++- 1 file changed, 67 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c index 632ab44737ec..81e7f6dd2279 100644 --- a/tools/testing/selftests/cachestat/test_cachestat.c +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -22,7 +22,7 @@ static const char * const dev_files[] = { "/dev/zero", "/dev/null", "/dev/urandom", - "/proc/version", "/proc" + "/proc/version","/proc/cpuinfo","/proc" }; void print_cachestat(struct cachestat *cs) @@ -202,6 +202,65 @@ static int test_cachestat(const char *filename, bool write_random, bool create, return ret; } +bool test_cachestat_mmap(void){ + + size_t PS = sysconf(_SC_PAGESIZE); + size_t filesize = PS * 512 * 2;; + int syscall_ret; + size_t compute_len = PS * 512; + struct cachestat_range cs_range = { PS, compute_len }; + char *filename = "tmpshmcstat"; + unsigned long num_pages = compute_len / PS; + struct cachestat cs; + bool ret = true; + int fd = open(filename, O_RDWR | O_CREAT | O_TRUNC, 0666); + if (fd < 0) { + ksft_print_msg("Unable to create mmap file.\n"); + ret = false; + goto out; + } + if (ftruncate(fd, filesize)) { + ksft_print_msg("Unable to truncate mmap file.\n"); + ret = false; + goto close_fd; + } + if (!write_exactly(fd, filesize)) { + ksft_print_msg("Unable to write to mmap file.\n"); + ret = false; + goto close_fd; + } + char *map = mmap(NULL, filesize, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (map == MAP_FAILED) { + ksft_print_msg("mmap failed.\n"); + ret = false; + goto close_fd; + } + + for (int i = 0; i < filesize; i++) { + map[i] = 'A'; + } + map[filesize - 1] = 'X'; + + syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0); + + if (syscall_ret) { + ksft_print_msg("Cachestat returned non-zero.\n"); + ret = false; + } else { + print_cachestat(&cs); + if (cs.nr_cache + cs.nr_evicted != num_pages) { + ksft_print_msg("Total number of cached and evicted pages is off.\n"); + ret = false; + } + } + +close_fd: + close(fd); + unlink(filename); +out: + return ret; +} + bool test_cachestat_shmem(void) { size_t PS = sysconf(_SC_PAGESIZE); @@ -274,7 +333,7 @@ int main(void) ret = 1; } - for (int i = 0; i < 5; i++) { + for (int i = 0; i < 6; i++) { const char *dev_filename = dev_files[i]; if (test_cachestat(dev_filename, false, false, false, @@ -315,5 +374,11 @@ int main(void) ret = 1; } + if (test_cachestat_mmap()) + ksft_test_result_pass("cachestat works with a mmap file\n"); + else { + ksft_test_result_fail("cachestat fails with a mmap file\n"); + ret = 1; + } return ret; } -- 2.43.0

6 months, 1 week

2
1
0 0

[PATCH v2] riscv: sbi: Add SBI Debug Triggers Extension tests

by Jesse Taube

Add tests for the DBTR SBI extension. Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> --- V1 -> V2: - Call report_prefix_pop before returning - Disable compressed instructions in exec_call, update related comment - Remove extra "| 1" in dbtr_test_load - Remove extra newlines - Remove extra tabs in check_exec - Remove typedefs from enums - Return when dbtr_install_trigger fails - s/avalible/available/g - s/unistall/uninstall/g --- lib/riscv/asm/sbi.h | 28 ++ lib/riscv/sbi.c | 58 ++++ riscv/Makefile | 1 + riscv/sbi-dbtr.c | 751 ++++++++++++++++++++++++++++++++++++++++++++ riscv/sbi-tests.h | 1 + riscv/sbi.c | 1 + 6 files changed, 840 insertions(+) create mode 100644 riscv/sbi-dbtr.c diff --git a/lib/riscv/asm/sbi.h b/lib/riscv/asm/sbi.h index a5738a5c..ce19ab89 100644 --- a/lib/riscv/asm/sbi.h +++ b/lib/riscv/asm/sbi.h @@ -51,6 +51,7 @@ enum sbi_ext_id { SBI_EXT_SUSP = 0x53555350, SBI_EXT_FWFT = 0x46574654, SBI_EXT_SSE = 0x535345, + SBI_EXT_DBTR = 0x44425452, }; enum sbi_ext_base_fid { @@ -125,6 +126,17 @@ enum sbi_ext_fwft_fid { #define SBI_FWFT_SET_FLAG_LOCK BIT(0) +enum sbi_ext_dbtr_fid { + SBI_EXT_DBTR_NUM_TRIGGERS = 0, + SBI_EXT_DBTR_SETUP_SHMEM, + SBI_EXT_DBTR_TRIGGER_READ, + SBI_EXT_DBTR_TRIGGER_INSTALL, + SBI_EXT_DBTR_TRIGGER_UPDATE, + SBI_EXT_DBTR_TRIGGER_UNINSTALL, + SBI_EXT_DBTR_TRIGGER_ENABLE, + SBI_EXT_DBTR_TRIGGER_DISABLE, +}; + enum sbi_ext_sse_fid { SBI_EXT_SSE_READ_ATTRS = 0, SBI_EXT_SSE_WRITE_ATTRS, @@ -282,6 +294,22 @@ static inline bool sbi_sse_event_is_global(uint32_t event_id) return !!(event_id & SBI_SSE_EVENT_GLOBAL_BIT); } +struct sbiret sbi_debug_num_triggers(unsigned long trig_tdata1); +struct sbiret sbi_debug_set_shmem(void *shmem); +struct sbiret sbi_debug_set_shmem_raw(unsigned long shmem_phys_lo, + unsigned long shmem_phys_hi, + unsigned long flags); +struct sbiret sbi_debug_read_triggers(unsigned long trig_idx_base, + unsigned long trig_count); +struct sbiret sbi_debug_install_triggers(unsigned long trig_count); +struct sbiret sbi_debug_update_triggers(unsigned long trig_count); +struct sbiret sbi_debug_uninstall_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask); +struct sbiret sbi_debug_enable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask); +struct sbiret sbi_debug_disable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask); + struct sbiret sbi_sse_read_attrs_raw(unsigned long event_id, unsigned long base_attr_id, unsigned long attr_count, unsigned long phys_lo, unsigned long phys_hi); diff --git a/lib/riscv/sbi.c b/lib/riscv/sbi.c index 2959378f..39c0d3bd 100644 --- a/lib/riscv/sbi.c +++ b/lib/riscv/sbi.c @@ -32,6 +32,64 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, return ret; } +struct sbiret sbi_debug_num_triggers(unsigned long trig_tdata1) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_NUM_TRIGGERS, trig_tdata1, 0, 0, 0, 0, 0); +} + +struct sbiret sbi_debug_set_shmem(void *shmem) +{ + phys_addr_t p = virt_to_phys(shmem); + + return sbi_debug_set_shmem_raw(lower_32_bits(p), upper_32_bits(p), 0); +} + +struct sbiret sbi_debug_set_shmem_raw(unsigned long shmem_phys_lo, + unsigned long shmem_phys_hi, + unsigned long flags) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_SETUP_SHMEM, shmem_phys_lo, + shmem_phys_hi, flags, 0, 0, 0); +} + +struct sbiret sbi_debug_read_triggers(unsigned long trig_idx_base, + unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_READ, trig_idx_base, + trig_count, 0, 0, 0, 0); +} + +struct sbiret sbi_debug_install_triggers(unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_INSTALL, trig_count, 0, 0, 0, 0, 0); +} + +struct sbiret sbi_debug_update_triggers(unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_UPDATE, trig_count, 0, 0, 0, 0, 0); +} + +struct sbiret sbi_debug_uninstall_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_UNINSTALL, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +struct sbiret sbi_debug_enable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_ENABLE, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +struct sbiret sbi_debug_disable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_DISABLE, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + struct sbiret sbi_sse_read_attrs_raw(unsigned long event_id, unsigned long base_attr_id, unsigned long attr_count, unsigned long phys_lo, unsigned long phys_hi) diff --git a/riscv/Makefile b/riscv/Makefile index 11e68eae..55c7ac93 100644 --- a/riscv/Makefile +++ b/riscv/Makefile @@ -20,6 +20,7 @@ all: $(tests) $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-asm.o $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-fwft.o $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-sse.o +$(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-dbtr.o all_deps += $($(TEST_DIR)/sbi-deps) diff --git a/riscv/sbi-dbtr.c b/riscv/sbi-dbtr.c new file mode 100644 index 00000000..fe323f0f --- /dev/null +++ b/riscv/sbi-dbtr.c @@ -0,0 +1,751 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SBI DBTR testsuite + * + * Copyright (C) 2025, Rivos Inc., Jesse Taube <jesse(a)rivosinc.com> + */ + +#include <asm/io.h> + +#include "sbi-tests.h" + +#define INSN_LEN(insn) ((((insn) & 0x3) < 0x3) ? 2 : 4) + +#if __riscv_xlen == 64 +#define SBI_DBTR_SHMEM_INVALID_ADDR 0xFFFFFFFFFFFFFFFFUL +#elif __riscv_xlen == 32 +#define SBI_DBTR_SHMEM_INVALID_ADDR 0xFFFFFFFFUL +#else +#error "Unexpected __riscv_xlen" +#endif + +#define RV_MAX_TRIGGERS 32 + +#define SBI_DBTR_TRIG_STATE_MAPPED BIT(0) +#define SBI_DBTR_TRIG_STATE_U BIT(1) +#define SBI_DBTR_TRIG_STATE_S BIT(2) +#define SBI_DBTR_TRIG_STATE_VU BIT(3) +#define SBI_DBTR_TRIG_STATE_VS BIT(4) +#define SBI_DBTR_TRIG_STATE_HAVE_HW_TRIG BIT(5) + +#define SBI_DBTR_TRIG_STATE_HW_TRIG_IDX_SHIFT 8 +#define SBI_DBTR_TRIG_STATE_HW_TRIG_IDX(trig_state) (trig_state >> SBI_DBTR_TRIG_STATE_HW_TRIG_IDX_SHIFT) + +#define SBI_DBTR_TDATA1_TYPE_SHIFT (__riscv_xlen - 4) + +#define SBI_DBTR_TDATA1_MCONTROL6_LOAD_BIT BIT(0) +#define SBI_DBTR_TDATA1_MCONTROL6_STORE_BIT BIT(1) +#define SBI_DBTR_TDATA1_MCONTROL6_EXECUTE_BIT BIT(2) +#define SBI_DBTR_TDATA1_MCONTROL6_U_BIT BIT(3) +#define SBI_DBTR_TDATA1_MCONTROL6_S_BIT BIT(4) +#define SBI_DBTR_TDATA1_MCONTROL6_SELECT_BIT BIT(21) +#define SBI_DBTR_TDATA1_MCONTROL6_VS_BIT BIT(23) +#define SBI_DBTR_TDATA1_MCONTROL6_VU_BIT BIT(24) + +#define SBI_DBTR_TDATA1_MCONTROL_LOAD_BIT BIT(0) +#define SBI_DBTR_TDATA1_MCONTROL_STORE_BIT BIT(1) +#define SBI_DBTR_TDATA1_MCONTROL_EXECUTE_BIT BIT(2) +#define SBI_DBTR_TDATA1_MCONTROL_U_BIT BIT(3) +#define SBI_DBTR_TDATA1_MCONTROL_S_BIT BIT(4) +#define SBI_DBTR_TDATA1_MCONTROL_SELECT_BIT BIT(19) + +enum McontrolType { + SBI_DBTR_TDATA1_TYPE_NONE = (0UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_LEGACY = (1UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_MCONTROL = (2UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ICOUNT = (3UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ITRIGGER = (4UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ETRIGGER = (5UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_MCONTROL6 = (6UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_TMEXTTRIGGER = (7UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED0 = (8UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED1 = (9UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED2 = (10UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED3 = (11UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM0 = (12UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM1 = (13UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM2 = (14UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_DISABLED = (15UL << SBI_DBTR_TDATA1_TYPE_SHIFT), +}; + +enum Tdata1Value { + VALUE_NONE = 0, + VALUE_LOAD = BIT(0), + VALUE_STORE = BIT(1), + VALUE_EXECUTE = BIT(2), +}; + +enum Tdata1Mode { + MODE_NONE = 0, + MODE_M = BIT(0), + MODE_U = BIT(1), + MODE_S = BIT(2), + MODE_VU = BIT(3), + MODE_VS = BIT(4), +}; + +struct sbi_dbtr_data_msg { + unsigned long tstate; + unsigned long tdata1; + unsigned long tdata2; + unsigned long tdata3; +}; + +struct sbi_dbtr_id_msg { + unsigned long idx; +}; + +/* SBI shared mem messages layout */ +struct sbi_dbtr_shmem_entry { + union { + struct sbi_dbtr_data_msg data; + struct sbi_dbtr_id_msg id; + }; +}; + +static bool dbtr_handled; + +// Expected to be leaf function as not to disrupt frame-pointer +static __attribute__((naked)) void exec_call(void) +{ + // skip over nop when triggered instead of ret. + asm volatile (".option push\n" + ".option arch, -c\n" + "nop\n" + "ret\n" + ".option pop\n"); +} + +static void dbtr_exception_handler(struct pt_regs *regs) +{ + dbtr_handled = true; + + /* Reading *epc may cause a fault, skip over nop */ + if ((void *)regs->epc == exec_call) { + regs->epc += 4; + return; + } + + /* WARNING: Skips over the trapped intruction */ + regs->epc += INSN_LEN(readw((void *)regs->epc)); +} + +static bool do_save(void *tdata2) +{ + bool ret; + + writel(0, tdata2); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static bool do_load(void *tdata2) +{ + bool ret; + + readl(tdata2); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static bool do_exec(void) +{ + bool ret; + + exec_call(); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static unsigned long gen_tdata1_mcontrol(enum Tdata1Mode mode, enum Tdata1Value value) +{ + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL; + + if (value & VALUE_LOAD) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_LOAD_BIT; + + if (value & VALUE_STORE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_STORE_BIT; + + if (value & VALUE_EXECUTE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_EXECUTE_BIT; + + if (mode & MODE_M) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_U_BIT; + + if (mode & MODE_U) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_U_BIT; + + if (mode & MODE_S) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_S_BIT; + + return tdata1; +} + +static unsigned long gen_tdata1_mcontrol6(enum Tdata1Mode mode, enum Tdata1Value value) +{ + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL6; + + if (value & VALUE_LOAD) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_LOAD_BIT; + + if (value & VALUE_STORE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_STORE_BIT; + + if (value & VALUE_EXECUTE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_EXECUTE_BIT; + + if (mode & MODE_M) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_U_BIT; + + if (mode & MODE_U) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_U_BIT; + + if (mode & MODE_S) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_S_BIT; + + if (mode & MODE_VU) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_VU_BIT; + + if (mode & MODE_VS) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_VS_BIT; + + return tdata1; +} + +static unsigned long gen_tdata1(enum McontrolType type, enum Tdata1Value value, enum Tdata1Mode mode) +{ + switch (type) { + case SBI_DBTR_TDATA1_TYPE_MCONTROL: + return gen_tdata1_mcontrol(mode, value); + case SBI_DBTR_TDATA1_TYPE_MCONTROL6: + return gen_tdata1_mcontrol6(mode, value); + default: + return 0; + } +} + +static bool dbtr_install_trigger(struct sbi_dbtr_shmem_entry *shmem, void *tdata2, + unsigned long tdata1) +{ + struct sbiret sbi_ret; + bool ret; + + shmem->data.tdata1 = tdata1; + shmem->data.tdata2 = (unsigned long)tdata2; + + sbi_ret = sbi_debug_install_triggers(1); + ret = sbiret_report_error(&sbi_ret, SBI_SUCCESS, "sbi_debug_install_triggers"); + if (ret) + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + return ret; +} + +static bool dbtr_uninstall_trigger(void) +{ + struct sbiret ret; + + install_exception_handler(EXC_BREAKPOINT, NULL); + + ret = sbi_debug_uninstall_triggers(0, 1); + return sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); +} + +static unsigned long dbtr_test_num_triggers(void) +{ + struct sbiret ret; + //sbi_debug_num_triggers will return trig_max in sbiret.value when trig_tdata1 == 0 + unsigned long tdata1 = 0; + + // should be atleast one trigger. + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_num_triggers"); + + if (ret.value == 0) + report_fail("sbi_debug_num_triggers: Returned 0 triggers available"); + else + report_pass("sbi_debug_num_triggers: Returned %lu triggers available", ret.value); + + return ret.value; +} + +static enum McontrolType dbtr_test_type(unsigned long *num_trig) +{ + struct sbiret ret; + + //sbi_debug_num_triggers will return trig_max in sbiret.value when trig_tdata1 == 0 + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL6; + + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_num_triggers"); + if (ret.value > 0) { + report_pass("sbi_debug_num_triggers: Returned %lu mcontrol6 triggers available", + ret.value); + *num_trig = ret.value; + return tdata1; + } + + tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL; + + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_num_triggers"); + *num_trig = ret.value; + if (ret.value > 0) { + report_pass("sbi_debug_num_triggers: Returned %lu mcontrol triggers available", + ret.value); + return tdata1; + } + + report_fail("sbi_debug_num_triggers: Returned 0 mcontrol(6) triggers available"); + + return SBI_DBTR_TDATA1_TYPE_NONE; +} + +static struct sbiret dbtr_test_save_install_uninstall(struct sbi_dbtr_shmem_entry *shmem, + enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("save_trigger"); + + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S | MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_install_triggers(1); + if (!sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_install_triggers")) { + report_prefix_pop(); + return ret; + } + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(do_save(&test), "triggered"); + + if (do_load(&test)) + report_fail("triggered by load"); + + ret = sbi_debug_uninstall_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + if (do_save(&test)) + report_fail("triggered after uninstall"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); + + return ret; +} + +static void dbtr_test_update(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("update_trigger"); + + if (!dbtr_install_trigger(shmem, NULL, gen_tdata1(type, VALUE_NONE, MODE_NONE))) { + report_prefix_pop(); + return; + } + + shmem->id.idx = 0; + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_update_triggers(1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_update_triggers"); + + report(do_save(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_load(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + + report_prefix_push("load_trigger"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_LOAD, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_load(&test), "triggered"); + + if (do_save(&test)) + report_fail("triggered by save"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_disable_enable(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("sbi_debug_disable_triggers"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + if (do_save(&test)) { + report_fail("should not trigger"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); + report_skip("sbi_debug_enable_triggers: no disable"); + + return; + } + + report_pass("should not trigger"); + + report_prefix_pop(); + report_prefix_push("sbi_debug_enable_triggers"); + + ret = sbi_debug_enable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_enable_triggers"); + + report(do_save(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_exec(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + + report_prefix_push("exec_trigger"); + /* check if loads and saves trigger exec */ + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + report_prefix_pop(); + return; + } + + if (do_load(&test)) + report_fail("triggered by load"); + + if (do_save(&test)) + report_fail("triggered by save"); + + dbtr_uninstall_trigger(); + + /* Check if exec works */ + if (!dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + report_prefix_pop(); + return; + } + report(do_exec(), "exec trigger"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_read(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + const unsigned long tstatus_expected = SBI_DBTR_TRIG_STATE_S | SBI_DBTR_TRIG_STATE_MAPPED; + const unsigned long tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + static unsigned long test; + struct sbiret ret; + + report_prefix_push("sbi_debug_read_triggers"); + if (!dbtr_install_trigger(shmem, &test, tdata1)) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_read_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_read_triggers"); + + report(shmem->data.tdata1 == tdata1, "tdata1 expected: 0x%016lx, found: 0x%016lx", + tdata1, shmem->data.tdata1); + report(shmem->data.tdata2 == ((unsigned long)&test), + "tdata2 expected: 0x%016lx, found: 0x%016lx", ((unsigned long)&test), + shmem->data.tdata2); + report(shmem->data.tstate == tstatus_expected, "tstate expected: 0x%016lx, found: 0x%016lx", + tstatus_expected, shmem->data.tstate); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void check_exec(unsigned long base) +{ + struct sbiret ret; + + report(do_exec(), "exec triggered"); + + ret = sbi_debug_uninstall_triggers(base, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); +} + +static void dbtr_test_multiple(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type, + unsigned long num_trigs) +{ + static unsigned long test[2]; + struct sbiret ret; + bool have_three = num_trigs > 2; + + if (num_trigs < 2) + return; + + report_prefix_push("test_multiple"); + + if (!dbtr_install_trigger(shmem, &test[0], gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + if (!dbtr_install_trigger(shmem, &test[1], gen_tdata1(type, VALUE_LOAD, MODE_S))) + goto error; + if (have_three && + !dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + ret = sbi_debug_uninstall_triggers(1, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + goto error; + } + + report(do_save(&test[0]), "save triggered"); + + if (do_load(&test[0])) + report_fail("save triggered by load"); + + report(do_load(&test[1]), "load triggered"); + + if (do_save(&test[1])) + report_fail("load triggered by save"); + + if (have_three) + check_exec(2); + + ret = sbi_debug_uninstall_triggers(1, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + if (do_load(&test[1])) + report_fail("load triggered after uninstall"); + + report(do_save(&test[0]), "save triggered"); + + if (!have_three && + dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) + check_exec(1); + +error: + ret = sbi_debug_uninstall_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_multiple_types(struct sbi_dbtr_shmem_entry *shmem, unsigned long type) +{ + static unsigned long test; + + report_prefix_push("dbtr_test_multiple_types"); + + /* check if loads and saves trigger exec */ + if (!dbtr_install_trigger(shmem, &test, + gen_tdata1(type, VALUE_EXECUTE | VALUE_LOAD | VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_load(&test), "load trigger"); + + report(do_save(&test), "save trigger"); + + dbtr_uninstall_trigger(); + + /* Check if exec works */ + if (!dbtr_install_trigger(shmem, exec_call, + gen_tdata1(type, VALUE_EXECUTE | VALUE_LOAD | VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_exec(), "exec trigger"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_disable_uninstall(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable uninstall"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + dbtr_uninstall_trigger(); + + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_save(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_uninstall_enable(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("uninstall enable"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + dbtr_uninstall_trigger(); + + ret = sbi_debug_enable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_enable_triggers"); + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(!do_save(&test), "should not trigger"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_uninstall_update(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("uninstall update"); + if (!dbtr_install_trigger(shmem, NULL, gen_tdata1(type, VALUE_NONE, MODE_NONE))) { + report_prefix_pop(); + return; + } + + dbtr_uninstall_trigger(); + + shmem->id.idx = 0; + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_update_triggers(1); + sbiret_report_error(&ret, SBI_ERR_FAILURE, "sbi_debug_update_triggers"); + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(!do_save(&test), "should not trigger"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_disable_read(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + const unsigned long tstatus_expected = SBI_DBTR_TRIG_STATE_S | SBI_DBTR_TRIG_STATE_MAPPED; + const unsigned long tdata1 = gen_tdata1(type, VALUE_STORE, MODE_NONE); + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable_read"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + ret = sbi_debug_read_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_read_triggers"); + + report(shmem->data.tdata1 == tdata1, "tdata1 expected: 0x%016lx, found: 0x%016lx", + tdata1, shmem->data.tdata1); + report(shmem->data.tdata2 == ((unsigned long)&test), + "tdata2 expected: 0x%016lx, found: 0x%016lx", + ((unsigned long)&test), shmem->data.tdata2); + report(shmem->data.tstate == tstatus_expected, "tstate expected: 0x%016lx, found: 0x%016lx", + tstatus_expected, shmem->data.tstate); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +void check_dbtr(void) +{ + static struct sbi_dbtr_shmem_entry shmem[RV_MAX_TRIGGERS] = {}; + unsigned long num_trigs; + enum McontrolType trig_type; + struct sbiret ret; + + report_prefix_push("dbtr"); + + if (!sbi_probe(SBI_EXT_DBTR)) { + report_skip("extension not available"); + report_prefix_pop(); + return; + } + + if (__sbi_get_imp_id() == SBI_IMPL_OPENSBI && + __sbi_get_imp_version() < sbi_impl_opensbi_mk_version(1, 6)) { + report_skip("OpenSBI < v1.7 detected, skipping tests"); + report_prefix_pop(); + return; + } + + num_trigs = dbtr_test_num_triggers(); + if (!num_trigs) + goto error; + + trig_type = dbtr_test_type(&num_trigs); + if (trig_type == SBI_DBTR_TDATA1_TYPE_NONE) + goto error; + + ret = sbi_debug_set_shmem(shmem); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_set_shmem"); + + ret = dbtr_test_save_install_uninstall(&shmem[0], trig_type); + /* install or uninstall failed */ + if (ret.error != SBI_SUCCESS) + goto error; + + dbtr_test_load(&shmem[0], trig_type); + dbtr_test_exec(&shmem[0], trig_type); + dbtr_test_read(&shmem[0], trig_type); + dbtr_test_disable_enable(&shmem[0], trig_type); + dbtr_test_update(&shmem[0], trig_type); + dbtr_test_multiple_types(&shmem[0], trig_type); + dbtr_test_multiple(shmem, trig_type, num_trigs); + dbtr_test_disable_uninstall(&shmem[0], trig_type); + dbtr_test_uninstall_enable(&shmem[0], trig_type); + dbtr_test_uninstall_update(&shmem[0], trig_type); + dbtr_test_disable_read(&shmem[0], trig_type); + +error: + report_prefix_pop(); +} diff --git a/riscv/sbi-tests.h b/riscv/sbi-tests.h index d5c4ae70..6a227745 100644 --- a/riscv/sbi-tests.h +++ b/riscv/sbi-tests.h @@ -99,6 +99,7 @@ static inline bool env_enabled(const char *env) void sbi_bad_fid(int ext); void check_sse(void); +void check_dbtr(void); #endif /* __ASSEMBLER__ */ #endif /* _RISCV_SBI_TESTS_H_ */ diff --git a/riscv/sbi.c b/riscv/sbi.c index edb1a6be..5bd496d0 100644 --- a/riscv/sbi.c +++ b/riscv/sbi.c @@ -1561,6 +1561,7 @@ int main(int argc, char **argv) check_susp(); check_sse(); check_fwft(); + check_dbtr(); return report_summary(); } -- 2.43.0

6 months, 1 week

2
1
0 0

[PATCH] selftests/timers: Fix integer overlow errors on 32 bit systems

by Terry Tritton

The use of NSEC_PER_SEC (1000000000L) as defined in include/vdso/time64.h causes several integer overflow warnings and test errors on 32 bit architectures. Use a long long instead of long to prevent integer overflow when converting seconds to nanoseconds. Signed-off-by: Terry Tritton <terry.tritton(a)linaro.org> --- tools/testing/selftests/timers/adjtick.c | 5 ++++- tools/testing/selftests/timers/alarmtimer-suspend.c | 4 +++- tools/testing/selftests/timers/inconsistency-check.c | 4 +++- tools/testing/selftests/timers/leap-a-day.c | 4 +++- tools/testing/selftests/timers/mqueue-lat.c | 3 ++- tools/testing/selftests/timers/nanosleep.c | 4 +++- tools/testing/selftests/timers/nsleep-lat.c | 4 +++- tools/testing/selftests/timers/posix_timers.c | 5 ++++- tools/testing/selftests/timers/raw_skew.c | 4 +++- tools/testing/selftests/timers/set-2038.c | 4 +++- tools/testing/selftests/timers/set-timer-lat.c | 4 +++- tools/testing/selftests/timers/valid-adjtimex.c | 5 ++++- 12 files changed, 38 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/timers/adjtick.c b/tools/testing/selftests/timers/adjtick.c index 777d9494b683..b5929c33b632 100644 --- a/tools/testing/selftests/timers/adjtick.c +++ b/tools/testing/selftests/timers/adjtick.c @@ -22,10 +22,13 @@ #include <sys/time.h> #include <sys/timex.h> #include <time.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL +#define USEC_PER_SEC 1000000LL + #define MILLION 1000000 long systick; diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c index a9ef76ea6051..b5799df271ae 100644 --- a/tools/testing/selftests/timers/alarmtimer-suspend.c +++ b/tools/testing/selftests/timers/alarmtimer-suspend.c @@ -28,10 +28,12 @@ #include <signal.h> #include <stdlib.h> #include <pthread.h> -#include <include/vdso/time64.h> #include <errno.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define UNREASONABLE_LAT (NSEC_PER_SEC * 5) /* hopefully we resume in 5 secs */ #define SUSPEND_SECS 15 diff --git a/tools/testing/selftests/timers/inconsistency-check.c b/tools/testing/selftests/timers/inconsistency-check.c index 9d1573769d55..2b2d7293b313 100644 --- a/tools/testing/selftests/timers/inconsistency-check.c +++ b/tools/testing/selftests/timers/inconsistency-check.c @@ -28,9 +28,11 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/leap-a-day.c b/tools/testing/selftests/timers/leap-a-day.c index 04004a7c0934..008c38ce4b2f 100644 --- a/tools/testing/selftests/timers/leap-a-day.c +++ b/tools/testing/selftests/timers/leap-a-day.c @@ -48,9 +48,11 @@ #include <string.h> #include <signal.h> #include <unistd.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define CLOCK_TAI 11 time_t next_leap; diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c index 63de2334a291..1a6d26f86137 100644 --- a/tools/testing/selftests/timers/mqueue-lat.c +++ b/tools/testing/selftests/timers/mqueue-lat.c @@ -29,9 +29,10 @@ #include <signal.h> #include <errno.h> #include <mqueue.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL #define TARGET_TIMEOUT 100000000 /* 100ms in nanoseconds */ #define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c index 252c6308c569..55ea67478fdd 100644 --- a/tools/testing/selftests/timers/nanosleep.c +++ b/tools/testing/selftests/timers/nanosleep.c @@ -27,9 +27,11 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c index de23dc0c9f97..347d622987c8 100644 --- a/tools/testing/selftests/timers/nsleep-lat.c +++ b/tools/testing/selftests/timers/nsleep-lat.c @@ -24,9 +24,11 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index f0eceb0faf34..555bf161f420 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -16,11 +16,14 @@ #include <string.h> #include <unistd.h> #include <time.h> -#include <include/vdso/time64.h> #include <pthread.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL +#define USEC_PER_SEC 1000000LL + #define DELAY 2 static void __fatal_error(const char *test, const char *name, const char *what) diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c index 957f7cd29cb1..ff7675d98560 100644 --- a/tools/testing/selftests/timers/raw_skew.c +++ b/tools/testing/selftests/timers/raw_skew.c @@ -25,9 +25,11 @@ #include <sys/time.h> #include <sys/timex.h> #include <time.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ __typeof__(s) __s = (s); \ diff --git a/tools/testing/selftests/timers/set-2038.c b/tools/testing/selftests/timers/set-2038.c index ed244315e11c..8130d551a11c 100644 --- a/tools/testing/selftests/timers/set-2038.c +++ b/tools/testing/selftests/timers/set-2038.c @@ -27,9 +27,11 @@ #include <unistd.h> #include <time.h> #include <sys/time.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define KTIME_MAX ((long long)~((unsigned long long)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index 9d8437c13929..79a6a6cba186 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -28,9 +28,11 @@ #include <signal.h> #include <stdlib.h> #include <pthread.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 6b7801055ad1..e4f31e678630 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -29,9 +29,12 @@ #include <string.h> #include <signal.h> #include <unistd.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL +#define USEC_PER_SEC 1000000LL + #define ADJ_SETOFFSET 0x0100 #include <sys/syscall.h> -- 2.39.5

6 months, 1 week

2
2
0 0

[PATCH] selftests: ublk: kublk: improve behavior on init failure

by Uday Shankar

Some failure modes are handled poorly by kublk. For example, if ublk_drv is built as a module but not currently loaded into the kernel, ./kublk add ... just hangs forever. This happens because in this case (and a few others), the worker process does not notify its parent (via a write to the shared eventfd) that it has tried and failed to initialize, so the parent hangs forever. Fix this by ensuring that we always notify the parent process of any initialization failure, and have the parent print a (not very descriptive) log line when this happens. Signed-off-by: Uday Shankar <ushankar(a)purestorage.com> --- tools/testing/selftests/ublk/kublk.c | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index a98e14e4c245965d817b93843ff9a4011291223b..e2d2042810d4bb472e48a0ed91317d2bdf6e2f2a 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -1112,7 +1112,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) __u64 features; const struct ublk_tgt_ops *ops; struct ublksrv_ctrl_dev_info *info; - struct ublk_dev *dev; + struct ublk_dev *dev = NULL; int dev_id = ctx->dev_id; int ret, i; @@ -1120,13 +1120,15 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) if (!ops) { ublk_err("%s: no such tgt type, type %s\n", __func__, tgt_type); - return -ENODEV; + ret = -ENODEV; + goto fail; } if (nr_queues > UBLK_MAX_QUEUES || depth > UBLK_QUEUE_DEPTH) { ublk_err("%s: invalid nr_queues or depth queues %u depth %u\n", __func__, nr_queues, depth); - return -EINVAL; + ret = -EINVAL; + goto fail; } /* default to 1:1 threads:queues if nthreads is unspecified */ @@ -1136,30 +1138,37 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) if (nthreads > UBLK_MAX_THREADS) { ublk_err("%s: %u is too many threads (max %u)\n", __func__, nthreads, UBLK_MAX_THREADS); - return -EINVAL; + ret = -EINVAL; + goto fail; } if (nthreads != nr_queues && !ctx->per_io_tasks) { ublk_err("%s: threads %u must be same as queues %u if " "not using per_io_tasks\n", __func__, nthreads, nr_queues); - return -EINVAL; + ret = -EINVAL; + goto fail; } dev = ublk_ctrl_init(); if (!dev) { ublk_err("%s: can't alloc dev id %d, type %s\n", __func__, dev_id, tgt_type); - return -ENOMEM; + ret = -ENOMEM; + goto fail; } /* kernel doesn't support get_features */ ret = ublk_ctrl_get_features(dev, &features); - if (ret < 0) - return -EINVAL; + if (ret < 0) { + ret = -EINVAL; + goto fail; + } - if (!(features & UBLK_F_CMD_IOCTL_ENCODE)) - return -ENOTSUP; + if (!(features & UBLK_F_CMD_IOCTL_ENCODE)) { + ret = -ENOTSUP; + goto fail; + } info = &dev->dev_info; info->dev_id = ctx->dev_id; @@ -1200,7 +1209,8 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) fail: if (ret < 0) ublk_send_dev_event(ctx, dev, -1); - ublk_ctrl_deinit(dev); + if (dev) + ublk_ctrl_deinit(dev); return ret; } @@ -1262,6 +1272,8 @@ static int cmd_dev_add(struct dev_ctx *ctx) shmctl(ctx->_shmid, IPC_RMID, NULL); /* wait for child and detach from it */ wait(NULL); + if (exit_code == EXIT_FAILURE) + ublk_err("%s: command failed\n", __func__); exit(exit_code); } else { exit(EXIT_FAILURE); --- base-commit: c09a8b00f850d3ca0af998bff1fac4a3f6d11768 change-id: 20250603-ublk_init_fail-b498905159eb Best regards, -- Uday Shankar <ushankar(a)purestorage.com>

6 months, 1 week

3
2
0 0

[PATCH v2] selftests: ir_decoder: Convert header comment to proper multi-line block

by Abdelrahman Fekry

well, i checked the script using checkpatch.pl and it shows that the patch has no warnings or errors and its ready to be sent v2: - fixed multiple trailing whitespace errors and - the Signed-off-by mismatch The test file for the IR decoder used single-line comments at the top to document its purpose and licensing, which is inconsistent with the style used throughout the Linux kernel. In this patch i converted the file header to a proper multi-line comment block (/*) that aligns with standard kernel practices. This improves readability, consistency across selftests, and ensures the license and documentation are clearly visible in a familiar format. No functional changes have been made. Signed-off-by: Abdelrahman Fekry <abdelrahmanfekry375(a)gmail.com> --- tools/testing/selftests/ir/ir_loopback.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index f4a15cbdd5ea..c94faa975630 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -1,14 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 -// test ir decoder -// -// Copyright (C) 2018 Sean Young <sean(a)mess.org> - -// When sending LIRC_MODE_SCANCODE, the IR will be encoded. rc-loopback -// will send this IR to the receiver side, where we try to read the decoded -// IR. Decoding happens in a separate kernel thread, so we will need to -// wait until that is scheduled, hence we use poll to check for read -// readiness. - +/* Copyright (C) 2018 Sean Young <sean(a)mess.org> + * + * Selftest for IR decoder + * + * + * When sending LIRC_MODE_SCANCODE, the IR will be encoded. + * rc-loopback will send this IR to the receiver side, + * where we try to read the decoded IR. + * Decoding happens in a separate kernel thread, + * so we will need to wait until that is scheduled, + * hence we use poll to check for read + * readiness. + */ #include <linux/lirc.h> #include <errno.h> #include <stdio.h> -- 2.25.1

6 months, 1 week

1
0
0 0

[PATCH bpf-next v3 00/11] bpf: Mitigate Spectre v1 using barriers

by Luis Gerhorst

This improves the expressiveness of unprivileged BPF by inserting speculation barriers instead of rejecting the programs. The approach was previously presented at LPC'24 [1] and RAID'24 [2]. To mitigate the Spectre v1 (PHT) vulnerability, the kernel rejects potentially-dangerous unprivileged BPF programs as of commit 9183671af6db ("bpf: Fix leakage under speculation on mispredicted branches"). In [2], we have analyzed 364 object files from open source projects (Linux Samples and Selftests, BCC, Loxilb, Cilium, libbpf Examples, Parca, and Prevail) and found that this affects 31% to 54% of programs. To resolve this in the majority of cases this patchset adds a fall-back for mitigating Spectre v1 using speculation barriers. The kernel still optimistically attempts to verify all speculative paths but uses speculation barriers against v1 when unsafe behavior is detected. This allows for more programs to be accepted without disabling the BPF Spectre mitigations (e.g., by setting cpu_mitigations_off()). For this, it relies on the fact that speculation barriers prevent all later instructions if the speculation was not correct: * On x86_64, lfence acts as full speculation barrier, not only as a load fence [3]: An LFENCE instruction or a serializing instruction will ensure that no later instructions execute, even speculatively, until all prior instructions complete locally. [...] Inserting an LFENCE instruction after a bounds check prevents later operations from executing before the bound check completes. This was experimentally confirmed in [4]. * ARM's SB speculation barrier instruction also affects "any instruction that appears later in the program order than the barrier" [5]. In [1] we have measured the overhead of this approach relative to having mitigations off and including the upstream Spectre v4 mitigations. For event tracing and stack-sampling profilers, we found that mitigations increase BPF program execution time by 0% to 62%. For the Loxilb network load balancer, we have measured a 14% slowdown in SCTP performance but no significant slowdown for TCP. This overhead only applies to programs that were previously rejected. I reran the expressiveness-evaluation with v6.14 and made sure the main results still match those from [1] and [2] (which used v6.5). Main design decisions are: * Do not use separate bytecode insns for v1 and v4 barriers (inspired by Daniel Borkmann's question at LPC). This simplifies the verifier significantly and has the only downside that performance on PowerPC is not as high as it could be. * Allow archs to still disable v1/v4 mitigations separately by setting bpf_jit_bypass_spec_v1/v4(). This has the benefit that archs can benefit from improved BPF expressiveness / performance if they are not vulnerable (e.g., ARM64 for v4 in the kernel). * Do not remove the empty BPF_NOSPEC implementation for backends for which it is unknown whether they are vulnerable to Spectre v1. [1] https://lpc.events/event/18/contributions/1954/ ("Mitigating Spectre-PHT using Speculation Barriers in Linux eBPF") [2] https://arxiv.org/pdf/2405.00078 ("VeriFence: Lightweight and Precise Spectre Defenses for Untrusted Linux Kernel Extensions") [3] https://www.intel.com/content/www/us/en/developer/articles/technical/softwa… ("Managed Runtime Speculative Execution Side Channel Mitigations") [4] https://dl.acm.org/doi/pdf/10.1145/3359789.3359837 ("Speculator: a tool to analyze speculative execution attacks and mitigations" - Section 4.6 "Stopping Speculative Execution") [5] https://developer.arm.com/documentation/ddi0597/2020-12/Base-Instructions/S… ("SB - Speculation Barrier - Arm Armv8-A A32/T32 Instruction Set Architecture (2020-12)") Changes: * v2 -> v3: - Fix https://lore.kernel.org/oe-kbuild-all/202504212030.IF1SLhz6-lkp@intel.com/ and similar by moving the bpf_jit_bypass_spec_v1/v4() prototypes out of the #ifdef CONFIG_BPF_SYSCALL. Decided not to move them to filter.h (where similar bpf_jit_*() prototypes live) as they would still have to be duplicated in bpf.h to be usable to bpf_bypass_spec_v1/v4() (unless including filter.h in bpf.h is an option). - Fix https://lore.kernel.org/oe-kbuild-all/202504220035.SoGveGpj-lkp@intel.com/ by moving the variable declarations out of the switch-case. - Build touched C files with W=2 and bpf config on x86 to check that there are no other warnings introduced. - Found 3 more checkpatch warnings that can be fixed without degrading readability. - Rebase to bpf-next 2025-05-01 - Link to v2: https://lore.kernel.org/bpf/20250421091802.3234859-1-luis.gerhorst@fau.de/ * v1 -> v2: - Drop former commits 9 ("bpf: Return PTR_ERR from push_stack()") and 11 ("bpf: Fall back to nospec for spec path verification") as suggested by Alexei. This series therefore no longer changes push_stack() to return PTR_ERR. - Add detailed explanation of how lfence works internally and how it affects the algorithm. - Add tests checking that nospec instructions are inserted in expected locations using __xlated_unpriv as suggested by Eduard (also, include a fix for __xlated_unpriv) - Add a test for the mitigations from the description of commit 9183671af6db ("bpf: Fix leakage under speculation on mispredicted branches") - Remove unused variables from do_check[_insn]() as suggested by Eduard. - Remove INSN_IDX_MODIFIED to improve readability as suggested by Eduard. This also causes the nospec_result-check to run (and fail) for jumping-ops. Add a warning to assert that this check must never succeed in that case. - Add details on the safety of patch 10 ("bpf: Allow nospec-protected var-offset stack access") based on the feedback on v1. - Rebase to bpf-next-250420 - Link to v1: https://lore.kernel.org/all/20250313172127.1098195-1-luis.gerhorst@fau.de/ * RFC -> v1: - rebase to bpf-next-250313 - tests: mark expected successes/new errors - add bpt_jit_bypass_spec_v1/v4() to avoid #ifdef in bpf_bypass_spec_v1/v4() - ensure that nospec with v1-support is implemented for archs for which GCC supports speculation barriers, except for MIPS - arm64: emit speculation barrier - powerpc: change nospec to include v1 barrier - discuss potential security (archs that do not impl. BPF nospec) and performance (only PowerPC) regressions - Link to RFC: https://lore.kernel.org/bpf/20250224203619.594724-1-luis.gerhorst@fau.de/ Luis Gerhorst (11): selftests/bpf: Fix caps for __xlated/jited_unpriv bpf: Move insn if/else into do_check_insn() bpf: Return -EFAULT on misconfigurations bpf: Return -EFAULT on internal errors bpf, arm64, powerpc: Add bpf_jit_bypass_spec_v1/v4() bpf, arm64, powerpc: Change nospec to include v1 barrier bpf: Rename sanitize_stack_spill to nospec_result bpf: Fall back to nospec for Spectre v1 selftests/bpf: Add test for Spectre v1 mitigation bpf: Allow nospec-protected var-offset stack access bpf: Fall back to nospec for sanitization-failures arch/arm64/net/bpf_jit.h | 5 + arch/arm64/net/bpf_jit_comp.c | 28 +- arch/powerpc/net/bpf_jit_comp64.c | 80 ++- include/linux/bpf.h | 11 +- include/linux/bpf_verifier.h | 3 +- include/linux/filter.h | 2 +- kernel/bpf/core.c | 32 +- kernel/bpf/verifier.c | 653 ++++++++++-------- tools/testing/selftests/bpf/progs/bpf_misc.h | 4 + .../selftests/bpf/progs/verifier_and.c | 8 +- .../selftests/bpf/progs/verifier_bounds.c | 66 +- .../bpf/progs/verifier_bounds_deduction.c | 45 +- .../selftests/bpf/progs/verifier_map_ptr.c | 20 +- .../selftests/bpf/progs/verifier_movsx.c | 16 +- .../selftests/bpf/progs/verifier_unpriv.c | 65 +- .../bpf/progs/verifier_value_ptr_arith.c | 101 ++- tools/testing/selftests/bpf/test_loader.c | 14 +- .../selftests/bpf/verifier/dead_code.c | 3 +- tools/testing/selftests/bpf/verifier/jmp32.c | 33 +- tools/testing/selftests/bpf/verifier/jset.c | 10 +- 20 files changed, 771 insertions(+), 428 deletions(-) base-commit: 358b1c0f56ebb6996fcec7dcdcf6bae5dcbc8b6c -- 2.49.0

6 months, 1 week

6
34
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror June 2025