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

[PATCH bpf-next v2 16/18] selftests/bpf: move get_ksyms and get_addrs to trace_helpers.c

by Menglong Dong

We need to get all the kernel function that can be traced sometimes, so we move the get_syms() and get_addrs() in kprobe_multi_test.c to trace_helpers.c and rename it to bpf_get_ksyms() and bpf_get_addrs(). Signed-off-by: Menglong Dong <dongml2(a)chinatelecom.cn> --- .../bpf/prog_tests/kprobe_multi_test.c | 220 +----------------- tools/testing/selftests/bpf/trace_helpers.c | 214 +++++++++++++++++ tools/testing/selftests/bpf/trace_helpers.h | 3 + 3 files changed, 220 insertions(+), 217 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index e19ef509ebf8..171706e78da8 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -422,220 +422,6 @@ static void test_unique_match(void) kprobe_multi__destroy(skel); } -static size_t symbol_hash(long key, void *ctx __maybe_unused) -{ - return str_hash((const char *) key); -} - -static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) -{ - return strcmp((const char *) key1, (const char *) key2) == 0; -} - -static bool is_invalid_entry(char *buf, bool kernel) -{ - if (kernel && strchr(buf, '[')) - return true; - if (!kernel && !strchr(buf, '[')) - return true; - return false; -} - -static bool skip_entry(char *name) -{ - /* - * We attach to almost all kernel functions and some of them - * will cause 'suspicious RCU usage' when fprobe is attached - * to them. Filter out the current culprits - arch_cpu_idle - * default_idle and rcu_* functions. - */ - if (!strcmp(name, "arch_cpu_idle")) - return true; - if (!strcmp(name, "default_idle")) - return true; - if (!strncmp(name, "rcu_", 4)) - return true; - if (!strcmp(name, "bpf_dispatcher_xdp_func")) - return true; - if (!strncmp(name, "__ftrace_invalid_address__", - sizeof("__ftrace_invalid_address__") - 1)) - return true; - return false; -} - -/* Do comparision by ignoring '.llvm.<hash>' suffixes. */ -static int compare_name(const char *name1, const char *name2) -{ - const char *res1, *res2; - int len1, len2; - - res1 = strstr(name1, ".llvm."); - res2 = strstr(name2, ".llvm."); - len1 = res1 ? res1 - name1 : strlen(name1); - len2 = res2 ? res2 - name2 : strlen(name2); - - if (len1 == len2) - return strncmp(name1, name2, len1); - if (len1 < len2) - return strncmp(name1, name2, len1) <= 0 ? -1 : 1; - return strncmp(name1, name2, len2) >= 0 ? 1 : -1; -} - -static int load_kallsyms_compare(const void *p1, const void *p2) -{ - return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name); -} - -static int search_kallsyms_compare(const void *p1, const struct ksym *p2) -{ - return compare_name(p1, p2->name); -} - -static int get_syms(char ***symsp, size_t *cntp, bool kernel) -{ - size_t cap = 0, cnt = 0; - char *name = NULL, *ksym_name, **syms = NULL; - struct hashmap *map; - struct ksyms *ksyms; - struct ksym *ks; - char buf[256]; - FILE *f; - int err = 0; - - ksyms = load_kallsyms_custom_local(load_kallsyms_compare); - if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_custom_local")) - return -EINVAL; - - /* - * The available_filter_functions contains many duplicates, - * but other than that all symbols are usable in kprobe multi - * interface. - * Filtering out duplicates by using hashmap__add, which won't - * add existing entry. - */ - - if (access("/sys/kernel/tracing/trace", F_OK) == 0) - f = fopen("/sys/kernel/tracing/available_filter_functions", "r"); - else - f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); - - if (!f) - return -EINVAL; - - map = hashmap__new(symbol_hash, symbol_equal, NULL); - if (IS_ERR(map)) { - err = libbpf_get_error(map); - goto error; - } - - while (fgets(buf, sizeof(buf), f)) { - if (is_invalid_entry(buf, kernel)) - continue; - - free(name); - if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1) - continue; - if (skip_entry(name)) - continue; - - ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare); - if (!ks) { - err = -EINVAL; - goto error; - } - - ksym_name = ks->name; - err = hashmap__add(map, ksym_name, 0); - if (err == -EEXIST) { - err = 0; - continue; - } - if (err) - goto error; - - err = libbpf_ensure_mem((void **) &syms, &cap, - sizeof(*syms), cnt + 1); - if (err) - goto error; - - syms[cnt++] = ksym_name; - } - - *symsp = syms; - *cntp = cnt; - -error: - free(name); - fclose(f); - hashmap__free(map); - if (err) - free(syms); - return err; -} - -static int get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel) -{ - unsigned long *addr, *addrs, *tmp_addrs; - int err = 0, max_cnt, inc_cnt; - char *name = NULL; - size_t cnt = 0; - char buf[256]; - FILE *f; - - if (access("/sys/kernel/tracing/trace", F_OK) == 0) - f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r"); - else - f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r"); - - if (!f) - return -ENOENT; - - /* In my local setup, the number of entries is 50k+ so Let us initially - * allocate space to hold 64k entries. If 64k is not enough, incrementally - * increase 1k each time. - */ - max_cnt = 65536; - inc_cnt = 1024; - addrs = malloc(max_cnt * sizeof(long)); - if (addrs == NULL) { - err = -ENOMEM; - goto error; - } - - while (fgets(buf, sizeof(buf), f)) { - if (is_invalid_entry(buf, kernel)) - continue; - - free(name); - if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2) - continue; - if (skip_entry(name)) - continue; - - if (cnt == max_cnt) { - max_cnt += inc_cnt; - tmp_addrs = realloc(addrs, max_cnt); - if (!tmp_addrs) { - err = -ENOMEM; - goto error; - } - addrs = tmp_addrs; - } - - addrs[cnt++] = (unsigned long)addr; - } - - *addrsp = addrs; - *cntp = cnt; - -error: - free(name); - fclose(f); - if (err) - free(addrs); - return err; -} - static void do_bench_test(struct kprobe_multi_empty *skel, struct bpf_kprobe_multi_opts *opts) { long attach_start_ns, attach_end_ns; @@ -670,7 +456,7 @@ static void test_kprobe_multi_bench_attach(bool kernel) char **syms = NULL; size_t cnt = 0; - if (!ASSERT_OK(get_syms(&syms, &cnt, kernel), "get_syms")) + if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms")) return; skel = kprobe_multi_empty__open_and_load(); @@ -696,13 +482,13 @@ static void test_kprobe_multi_bench_attach_addr(bool kernel) size_t cnt = 0; int err; - err = get_addrs(&addrs, &cnt, kernel); + err = bpf_get_addrs(&addrs, &cnt, kernel); if (err == -ENOENT) { test__skip(); return; } - if (!ASSERT_OK(err, "get_addrs")) + if (!ASSERT_OK(err, "bpf_get_addrs")) return; skel = kprobe_multi_empty__open_and_load(); diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 81943c6254e6..d24baf244d1f 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -17,6 +17,7 @@ #include <linux/limits.h> #include <libelf.h> #include <gelf.h> +#include "bpf/hashmap.h" #include "bpf/libbpf_internal.h" #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" @@ -519,3 +520,216 @@ void read_trace_pipe(void) { read_trace_pipe_iter(trace_pipe_cb, NULL, 0); } + +static size_t symbol_hash(long key, void *ctx __maybe_unused) +{ + return str_hash((const char *) key); +} + +static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return strcmp((const char *) key1, (const char *) key2) == 0; +} + +static bool is_invalid_entry(char *buf, bool kernel) +{ + if (kernel && strchr(buf, '[')) + return true; + if (!kernel && !strchr(buf, '[')) + return true; + return false; +} + +static bool skip_entry(char *name) +{ + /* + * We attach to almost all kernel functions and some of them + * will cause 'suspicious RCU usage' when fprobe is attached + * to them. Filter out the current culprits - arch_cpu_idle + * default_idle and rcu_* functions. + */ + if (!strcmp(name, "arch_cpu_idle")) + return true; + if (!strcmp(name, "default_idle")) + return true; + if (!strncmp(name, "rcu_", 4)) + return true; + if (!strcmp(name, "bpf_dispatcher_xdp_func")) + return true; + if (!strncmp(name, "__ftrace_invalid_address__", + sizeof("__ftrace_invalid_address__") - 1)) + return true; + return false; +} + +/* Do comparison by ignoring '.llvm.<hash>' suffixes. */ +static int compare_name(const char *name1, const char *name2) +{ + const char *res1, *res2; + int len1, len2; + + res1 = strstr(name1, ".llvm."); + res2 = strstr(name2, ".llvm."); + len1 = res1 ? res1 - name1 : strlen(name1); + len2 = res2 ? res2 - name2 : strlen(name2); + + if (len1 == len2) + return strncmp(name1, name2, len1); + if (len1 < len2) + return strncmp(name1, name2, len1) <= 0 ? -1 : 1; + return strncmp(name1, name2, len2) >= 0 ? 1 : -1; +} + +static int load_kallsyms_compare(const void *p1, const void *p2) +{ + return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name); +} + +static int search_kallsyms_compare(const void *p1, const struct ksym *p2) +{ + return compare_name(p1, p2->name); +} + +int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) +{ + size_t cap = 0, cnt = 0; + char *name = NULL, *ksym_name, **syms = NULL; + struct hashmap *map; + struct ksyms *ksyms; + struct ksym *ks; + char buf[256]; + FILE *f; + int err = 0; + + ksyms = load_kallsyms_custom_local(load_kallsyms_compare); + if (!ksyms) + return -EINVAL; + + /* + * The available_filter_functions contains many duplicates, + * but other than that all symbols are usable to trace. + * Filtering out duplicates by using hashmap__add, which won't + * add existing entry. + */ + + if (access("/sys/kernel/tracing/trace", F_OK) == 0) + f = fopen("/sys/kernel/tracing/available_filter_functions", "r"); + else + f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); + + if (!f) + return -EINVAL; + + map = hashmap__new(symbol_hash, symbol_equal, NULL); + if (IS_ERR(map)) { + err = libbpf_get_error(map); + goto error; + } + + while (fgets(buf, sizeof(buf), f)) { + if (is_invalid_entry(buf, kernel)) + continue; + + free(name); + if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1) + continue; + if (skip_entry(name)) + continue; + + ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare); + if (!ks) { + err = -EINVAL; + goto error; + } + + ksym_name = ks->name; + err = hashmap__add(map, ksym_name, 0); + if (err == -EEXIST) { + err = 0; + continue; + } + if (err) + goto error; + + err = libbpf_ensure_mem((void **) &syms, &cap, + sizeof(*syms), cnt + 1); + if (err) + goto error; + + syms[cnt++] = ksym_name; + } + + *symsp = syms; + *cntp = cnt; + +error: + free(name); + fclose(f); + hashmap__free(map); + if (err) + free(syms); + return err; +} + +int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel) +{ + unsigned long *addr, *addrs, *tmp_addrs; + int err = 0, max_cnt, inc_cnt; + char *name = NULL; + size_t cnt = 0; + char buf[256]; + FILE *f; + + if (access("/sys/kernel/tracing/trace", F_OK) == 0) + f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r"); + else + f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r"); + + if (!f) + return -ENOENT; + + /* In my local setup, the number of entries is 50k+ so Let us initially + * allocate space to hold 64k entries. If 64k is not enough, incrementally + * increase 1k each time. + */ + max_cnt = 65536; + inc_cnt = 1024; + addrs = malloc(max_cnt * sizeof(long)); + if (addrs == NULL) { + err = -ENOMEM; + goto error; + } + + while (fgets(buf, sizeof(buf), f)) { + if (is_invalid_entry(buf, kernel)) + continue; + + free(name); + if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2) + continue; + if (skip_entry(name)) + continue; + + if (cnt == max_cnt) { + max_cnt += inc_cnt; + tmp_addrs = realloc(addrs, max_cnt); + if (!tmp_addrs) { + err = -ENOMEM; + goto error; + } + addrs = tmp_addrs; + } + + addrs[cnt++] = (unsigned long)addr; + } + + *addrsp = addrs; + *cntp = cnt; + +error: + free(name); + fclose(f); + if (err) + free(addrs); + return err; +} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 2ce873c9f9aa..9437bdd4afa5 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -41,4 +41,7 @@ ssize_t get_rel_offset(uintptr_t addr); int read_build_id(const char *path, char *build_id, size_t size); +int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel); +int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel); + #endif -- 2.39.5

4 months, 3 weeks

1
0
0 0

[PATCH v2 0/4] kselftest/arm64: Add coverage for the interaction of vfork() and GCS

by Mark Brown

I had cause to look at the vfork() support for GCS and realised that we don't have any direct test coverage, this series does so by adding vfork() to nolibc and then using that in basic-gcs to provide some simple vfork() coverage. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Add replacement of ifdef with if defined() in nolibc since the code doesn't reflect the coding style. - Remove check for arch specific vfork(). - Link to v1: https://lore.kernel.org/r/20250609-arm64-gcs-vfork-exit-v1-0-baad0f085747@k… --- Mark Brown (4): tools/nolibc: Replace ifdef with if defined() in sys.h tools/nolibc: Provide vfork() kselftest/arm64: Add a test for vfork() with GCS selftests/nolibc: Add coverage of vfork() tools/include/nolibc/sys.h | 57 +++++++++++++++++------- tools/testing/selftests/arm64/gcs/basic-gcs.c | 63 +++++++++++++++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 23 ++++++++-- 3 files changed, 124 insertions(+), 19 deletions(-) --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250528-arm64-gcs-vfork-exit-4a7daf7652ee Best regards, -- Mark Brown <broonie(a)kernel.org>

4 months, 3 weeks

3
7
0 0

[PATCH] selftests: net: fix resource leak in napi_id_helper.c

by Malaya Kumar Rout

Resolve minor resource leaks reported by cppcheck in napi_id_helper.c cppcheck output before this patch: tools/testing/selftests/drivers/net/napi_id_helper.c:37:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:46:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:51:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:59:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:67:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:76:3: error: Resource leak: server [resourceLeak] cppcheck output after this patch: No resource leaks found Signed-off-by: Malaya Kumar Rout <malayarout91(a)gmail.com> --- tools/testing/selftests/drivers/net/napi_id_helper.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c index eecd610c2109..1441b8d49b91 100644 --- a/tools/testing/selftests/drivers/net/napi_id_helper.c +++ b/tools/testing/selftests/drivers/net/napi_id_helper.c @@ -34,6 +34,7 @@ int main(int argc, char *argv[]) if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) { perror("setsockopt"); + close(server); return 1; } @@ -43,11 +44,13 @@ int main(int argc, char *argv[]) if (bind(server, (struct sockaddr *)&address, sizeof(address)) < 0) { perror("bind failed"); + close(server); return 1; } if (listen(server, 1) < 0) { perror("listen"); + close(server); return 1; } @@ -56,6 +59,7 @@ int main(int argc, char *argv[]) client = accept(server, NULL, 0); if (client < 0) { perror("accept"); + close(server); return 1; } @@ -64,6 +68,7 @@ int main(int argc, char *argv[]) &optlen); if (ret != 0) { perror("getsockopt"); + close(server); return 1; } @@ -73,6 +78,7 @@ int main(int argc, char *argv[]) if (napi_id == 0) { fprintf(stderr, "napi ID is 0\n"); + close(server); return 1; } -- 2.43.0

4 months, 3 weeks

5
6
0 0

[PATCH] global: fix misapplications of "awhile"

by Ahelenia Ziemiańska

Of these: 7 "for a while" typos 5 "take a while" typos 1 misreading of "once in a while"? 3 awhiles used correctly remain in the tree Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli(a)nabijaczleweli.xyz> --- Documentation/trace/histogram.rst | 2 +- arch/sh/drivers/pci/common.c | 2 +- arch/sh/drivers/pci/pci-sh7780.c | 2 +- drivers/atm/lanai.c | 2 +- drivers/md/bcache/bcache.h | 2 +- drivers/md/bcache/request.c | 2 +- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 2 +- drivers/scsi/hpsa.c | 2 +- drivers/tty/serial/jsm/jsm_neo.c | 2 +- fs/ocfs2/dlm/dlmrecovery.c | 2 +- sound/pci/emu10k1/emu10k1_main.c | 2 +- sound/pci/emu10k1/emupcm.c | 2 +- tools/testing/selftests/powerpc/tm/tm-tmspr.c | 2 +- 13 files changed, 13 insertions(+), 13 deletions(-) diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 0aada18c38c6..2b98c1720a54 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -249,7 +249,7 @@ Extended error information table, it should keep a running total of the number of bytes requested by that call_site. - We'll let it run for awhile and then dump the contents of the 'hist' + We'll let it run for a while and then dump the contents of the 'hist' file in the kmalloc event's subdirectory (for readability, a number of entries have been omitted):: diff --git a/arch/sh/drivers/pci/common.c b/arch/sh/drivers/pci/common.c index 9633b6147a05..f95004c67e6c 100644 --- a/arch/sh/drivers/pci/common.c +++ b/arch/sh/drivers/pci/common.c @@ -148,7 +148,7 @@ unsigned int pcibios_handle_status_errors(unsigned long addr, cmd |= PCI_STATUS_PARITY | PCI_STATUS_DETECTED_PARITY; - /* Now back off of the IRQ for awhile */ + /* Now back off of the IRQ for a while */ if (hose->err_irq) { disable_irq_nosync(hose->err_irq); hose->err_timer.expires = jiffies + HZ; diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c index 9a624a6ee354..f41d6939a3d9 100644 --- a/arch/sh/drivers/pci/pci-sh7780.c +++ b/arch/sh/drivers/pci/pci-sh7780.c @@ -153,7 +153,7 @@ static irqreturn_t sh7780_pci_serr_irq(int irq, void *dev_id) /* Deassert SERR */ __raw_writel(SH4_PCIINTM_SDIM, hose->reg_base + SH4_PCIINTM); - /* Back off the IRQ for awhile */ + /* Back off the IRQ for a while */ disable_irq_nosync(irq); hose->serr_timer.expires = jiffies + HZ; add_timer(&hose->serr_timer); diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c index 2a1fe3080712..0dfa2cdc897c 100644 --- a/drivers/atm/lanai.c +++ b/drivers/atm/lanai.c @@ -755,7 +755,7 @@ static void lanai_shutdown_rx_vci(const struct lanai_vcc *lvcc) /* Shutdown transmitting on card. * Unfortunately the lanai needs us to wait until all the data * drains out of the buffer before we can dealloc it, so this - * can take awhile -- up to 370ms for a full 128KB buffer + * can take a while -- up to 370ms for a full 128KB buffer * assuming everone else is quiet. In theory the time is * boundless if there's a CBR VCC holding things up. */ diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 1d33e40d26ea..7318d9800370 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -499,7 +499,7 @@ struct gc_stat { * won't automatically reattach). * * CACHE_SET_STOPPING always gets set first when we're closing down a cache set; - * we'll continue to run normally for awhile with CACHE_SET_STOPPING set (i.e. + * we'll continue to run normally for a while with CACHE_SET_STOPPING set (i.e. * flushing dirty data). * * CACHE_SET_RUNNING means all cache devices have been registered and journal diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index af345dc6fde1..87b4341cb42c 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -257,7 +257,7 @@ static CLOSURE_CALLBACK(bch_data_insert_start) /* * But if it's not a writeback write we'd rather just bail out if - * there aren't any buckets ready to write to - it might take awhile and + * there aren't any buckets ready to write to - it might take a while and * we might be starving btree writes for gc or something. */ diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index dcb0545baa50..6a0be54f1c81 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -608,7 +608,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, buf_len = compl_desc->packet_len; hdr_len = compl_desc->header_len; - /* Page might have not been used for awhile and was likely last written + /* Page might have not been used for a while and was likely last written * by a different thread. */ if (rx->dqo.page_pool) { diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index c73a71ac3c29..0066f15153a7 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -7795,7 +7795,7 @@ static int hpsa_wait_for_mode_change_ack(struct ctlr_info *h) u32 doorbell_value; unsigned long flags; - /* under certain very rare conditions, this can take awhile. + /* under certain very rare conditions, this can take a while. * (e.g.: hot replace a failed 144GB drive in a RAID 5 set right * as we enter this code.) */ diff --git a/drivers/tty/serial/jsm/jsm_neo.c b/drivers/tty/serial/jsm/jsm_neo.c index e8e13bf056e2..2eb9ff26d6e8 100644 --- a/drivers/tty/serial/jsm/jsm_neo.c +++ b/drivers/tty/serial/jsm/jsm_neo.c @@ -1189,7 +1189,7 @@ static irqreturn_t neo_intr(int irq, void *voidbrd) /* * The UART triggered us with a bogus interrupt type. * It appears the Exar chip, when REALLY bogged down, will throw - * these once and awhile. + * these periodically. * Its harmless, just ignore it and move on. */ jsm_dbg(INTR, &brd->pci_dev, diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 67fc62a49a76..00f52812dbb0 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2632,7 +2632,7 @@ static int dlm_pick_recovery_master(struct dlm_ctxt *dlm) dlm_reco_master_ready(dlm), msecs_to_jiffies(1000)); if (!dlm_reco_master_ready(dlm)) { - mlog(0, "%s: reco master taking awhile\n", + mlog(0, "%s: reco master taking a while\n", dlm->name); goto again; } diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index bbe252b8916c..6050201851b1 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -606,7 +606,7 @@ static int snd_emu10k1_ecard_init(struct snd_emu10k1 *emu) /* Step 2: Calibrate the ADC and DAC */ snd_emu10k1_ecard_write(emu, EC_DACCAL | EC_LEDN | EC_TRIM_CSN); - /* Step 3: Wait for awhile; XXX We can't get away with this + /* Step 3: Wait for a while; XXX We can't get away with this * under a real operating system; we'll need to block and wait that * way. */ snd_emu10k1_wait(emu, 48000); diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 1bf6e3d652f8..ca4b03317539 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -991,7 +991,7 @@ static snd_pcm_uframes_t snd_emu10k1_capture_pointer(struct snd_pcm_substream *s if (!epcm->running) return 0; if (epcm->first_ptr) { - udelay(50); /* hack, it takes awhile until capture is started */ + udelay(50); /* hack, it takes a while until capture is started */ epcm->first_ptr = 0; } ptr = snd_emu10k1_ptr_read(emu, epcm->capture_idx_reg, 0) & 0x0000ffff; diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c index dd5ddffa28b7..0d64988ffb40 100644 --- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c +++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c @@ -14,7 +14,7 @@ * (1) create more threads than cpus * (2) in each thread: * (a) set TFIAR and TFHAR a unique value - * (b) loop for awhile, continually checking to see if + * (b) loop for a while, continually checking to see if * either register has been corrupted. * * (3) Loop: -- 2.39.5

4 months, 3 weeks

2
1
0 0

[PATCH v11 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v10 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best Regards, Chia-Yu --- v11 (04-Jul-2025) - Fix compilation issue of some intermediate patches in v10 v10 (03-Jul-2025) - Add new patch of separated header file include/net/tcp_ecn.h to include ECN and AccECN functions (Eric Dumazet <edumazet(a)google.com>) - Add comments on the AccECN helper functions in tcp_ecn.h (Eric Dumazet <edumazet(a)google.com>) - Add documentation of tcp_ecn, tcp_ecn_option, tcp_ecn_beacon in ip-sysctl.rst to the corresponding patch (Eric Dumazet <edumazet(a)google.com>) - Split wait third ACK functionality into a separated patch from AccECN negotiation patch (Eric Dumazet <edumazet(a)google.com>) - Add READ_ONCE() over every reads of sysctl for all patches in the series (Eric Dumazet <edumazet(a)google.com>) - Merge heuristics of AccECN option ceb/cep and ACE field multi-wrap into a single patch - Add a table of SACK block reduction and required AccECN field in patch #15 commit message (Eric Dumazet <edumazet(a)google.com>) v9 (21-Jun-2025) - Use tcp_data_ecn_check() to set TCP_ECN_SEE flag only for RFC3168 ECN (Paolo Abeni <pabeni(a)redhat.com>) - Add comments about setting TCP_ECN_SEEN flag for RFC3168 and Accruate ECN (Paolo Abeni <pabeni(a)redhat.com>) - Restruct the code in the for loop of tcp_accecn_process_option() (Paolo Abeni <pabeni(a)redhat.com>) - Remove ecn_bytes and add use_synack_ecn_bytes flag to identify whether syn_ack_bytes or received_ecn_bytes is used (Paolo Abeni <pabeni(a)redhat.com>) - Replace leftover_bytes and leftover_size with leftover_highbyte and leftover_lowbyte and add comments in tcp_options_write() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments and commit message about the 1st retx SYN still attempt AccECN negotiation (Paolo Abeni <pabeni(a)redhat.com>) v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. --- Chia-Yu Chang (6): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: ecn functions in separated include file tcp: Add wait_third_ack flag for ECN negotiation in simultaneous connect tcp: accecn: AccECN option send control tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (9): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option ceb/cep and ACE field multi-wrap heuristics Documentation/networking/ip-sysctl.rst | 55 +- .../networking/net_cachelines/tcp_sock.rst | 13 + include/linux/tcp.h | 33 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 87 ++- include/net/tcp_ecn.h | 648 ++++++++++++++++++ include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 4 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 29 +- net/ipv4/tcp_input.c | 371 ++++++++-- net/ipv4/tcp_ipv4.c | 8 +- net/ipv4/tcp_minisocks.c | 40 +- net/ipv4/tcp_output.c | 297 ++++++-- net/ipv6/syncookies.c | 2 + net/ipv6/tcp_ipv6.c | 1 + 16 files changed, 1429 insertions(+), 187 deletions(-) create mode 100644 include/net/tcp_ecn.h -- 2.34.1

4 months, 3 weeks

1
15
0 0

[PATCH v6 14/14] selftests/sched_ext: Add test for DL server total_bw consistency

by Joel Fernandes

Add a new kselftest to verify that the total_bw value in /sys/kernel/debug/sched/debug remains consistent across all CPUs under different sched_ext BPF program states: 1. Before a BPF scheduler is loaded 2. While a BPF scheduler is loaded and active 3. After a BPF scheduler is unloaded The test runs CPU stress threads to ensure DL server bandwidth values stabilize before checking consistency. This helps catch potential issues with DL server bandwidth accounting during sched_ext transitions. Signed-off-by: Joel Fernandes <joelagnelf(a)nvidia.com> --- tools/testing/selftests/sched_ext/Makefile | 1 + tools/testing/selftests/sched_ext/total_bw.c | 286 +++++++++++++++++++ 2 files changed, 287 insertions(+) create mode 100644 tools/testing/selftests/sched_ext/total_bw.c diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index f0a8cba3a99f..d48be158b0a1 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -184,6 +184,7 @@ auto-test-targets := \ select_cpu_vtime \ rt_stall \ test_example \ + total_bw \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) diff --git a/tools/testing/selftests/sched_ext/total_bw.c b/tools/testing/selftests/sched_ext/total_bw.c new file mode 100644 index 000000000000..6b81d6c51054 --- /dev/null +++ b/tools/testing/selftests/sched_ext/total_bw.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test to verify that total_bw value remains consistent across all CPUs + * in different BPF program states. + * + * Copyright (C) 2025 Nvidia Corporation. + */ +#include <bpf/bpf.h> +#include <errno.h> +#include <pthread.h> +#include <scx/common.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/wait.h> +#include <unistd.h> +#include "minimal.bpf.skel.h" +#include "scx_test.h" + +#define MAX_CPUS 512 +#define STABILIZATION_TIME_SEC 5 +#define STRESS_DURATION_SEC 5 + +struct total_bw_ctx { + struct minimal *skel; + long baseline_bw[MAX_CPUS]; + int nr_cpus; +}; + +static void *cpu_stress_thread(void *arg) +{ + volatile int i; + time_t end_time = time(NULL) + STRESS_DURATION_SEC; + + while (time(NULL) < end_time) { + for (i = 0; i < 1000000; i++); + } + + return NULL; +} + +/* + * The first enqueue on a CPU causes the DL server to start, for that + * reason run stressor threads in the hopes it schedules on all CPUs. + */ +static int run_cpu_stress(int nr_cpus) +{ + pthread_t *threads; + int i, ret = 0; + + threads = calloc(nr_cpus, sizeof(pthread_t)); + if (!threads) + return -ENOMEM; + + /* Create threads to run on each CPU */ + for (i = 0; i < nr_cpus; i++) { + if (pthread_create(&threads[i], NULL, cpu_stress_thread, NULL)) { + ret = -errno; + fprintf(stderr, "Failed to create thread %d: %s\n", i, strerror(-ret)); + break; + } + } + + /* Wait for all threads to complete */ + for (i = 0; i < nr_cpus; i++) { + if (threads[i]) + pthread_join(threads[i], NULL); + } + + free(threads); + return ret; +} + +static int read_total_bw_values(long *bw_values, int max_cpus) +{ + FILE *fp; + char line[256]; + int cpu_count = 0; + + fp = fopen("/sys/kernel/debug/sched/debug", "r"); + if (!fp) { + SCX_ERR("Failed to open debug file"); + return -1; + } + + while (fgets(line, sizeof(line), fp)) { + char *bw_str = strstr(line, "total_bw"); + if (bw_str) { + bw_str = strchr(bw_str, ':'); + if (bw_str) { + /* Only store up to max_cpus values */ + if (cpu_count < max_cpus) { + bw_values[cpu_count] = atol(bw_str + 1); + } + cpu_count++; + } + } + } + + fclose(fp); + return cpu_count; +} + +static bool verify_total_bw_consistency(long *bw_values, int count) +{ + int i; + long first_value; + + if (count <= 0) + return false; + + first_value = bw_values[0]; + + for (i = 1; i < count; i++) { + if (bw_values[i] != first_value) { + SCX_ERR("Inconsistent total_bw: CPU0=%ld, CPU%d=%ld", + first_value, i, bw_values[i]); + return false; + } + } + + return true; +} + +static int fetch_verify_total_bw(long *bw_values, int nr_cpus) +{ + int attempts = 0; + int max_attempts = 10; + int count; + + /* + * The first enqueue on a CPU causes the DL server to start, for that + * reason run stressor threads in the hopes it schedules on all CPUs. + */ + if (run_cpu_stress(nr_cpus) < 0) { + SCX_ERR("Failed to run CPU stress"); + return -1; + } + + /* Let things settle down */ + sleep(STABILIZATION_TIME_SEC); + + /* Try multiple times to get stable values */ + while (attempts < max_attempts) { + count = read_total_bw_values(bw_values, nr_cpus); + fprintf(stderr, "Read %d total_bw values (testing %d CPUs)\n", count, nr_cpus); + /* If system has more CPUs than we're testing, that's OK */ + if (count < nr_cpus) { + SCX_ERR("Expected at least %d CPUs, got %d", nr_cpus, count); + attempts++; + sleep(1); + continue; + } + + /* Only verify the CPUs we're testing */ + if (verify_total_bw_consistency(bw_values, nr_cpus)) { + fprintf(stderr, "Values are consistent: %ld\n", bw_values[0]); + return 0; + } + + attempts++; + sleep(1); + } + + return -1; +} + +static enum scx_test_status setup(void **ctx) +{ + struct total_bw_ctx *test_ctx; + + if (access("/sys/kernel/debug/sched/debug", R_OK) != 0) { + fprintf(stderr, "Skipping test: debugfs sched/debug not accessible\n"); + return SCX_TEST_SKIP; + } + + test_ctx = calloc(1, sizeof(*test_ctx)); + if (!test_ctx) + return SCX_TEST_FAIL; + + test_ctx->nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + if (test_ctx->nr_cpus <= 0) { + free(test_ctx); + return SCX_TEST_FAIL; + } + + /* If system has more CPUs than MAX_CPUS, just test the first MAX_CPUS */ + if (test_ctx->nr_cpus > MAX_CPUS) { + test_ctx->nr_cpus = MAX_CPUS; + } + + /* Test scenario 1: BPF program not loaded */ + /* Read and verify baseline total_bw before loading BPF program */ + fprintf(stderr, "BPF prog initially not loaded, reading total_bw values\n"); + if (fetch_verify_total_bw(test_ctx->baseline_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable baseline values"); + free(test_ctx); + return SCX_TEST_FAIL; + } + + /* Load the BPF skeleton */ + test_ctx->skel = minimal__open(); + if (!test_ctx->skel) { + free(test_ctx); + return SCX_TEST_FAIL; + } + + SCX_ENUM_INIT(test_ctx->skel); + if (minimal__load(test_ctx->skel)) { + minimal__destroy(test_ctx->skel); + free(test_ctx); + return SCX_TEST_FAIL; + } + + *ctx = test_ctx; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct total_bw_ctx *test_ctx = ctx; + struct bpf_link *link; + long loaded_bw[MAX_CPUS]; + long unloaded_bw[MAX_CPUS]; + int i; + + /* Test scenario 2: BPF program loaded */ + link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + fprintf(stderr, "BPF program loaded, reading total_bw values\n"); + if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values with BPF loaded"); + bpf_link__destroy(link); + return SCX_TEST_FAIL; + } + bpf_link__destroy(link); + + /* Test scenario 3: BPF program unloaded */ + fprintf(stderr, "BPF program unloaded, reading total_bw values\n"); + if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values after BPF unload"); + return SCX_TEST_FAIL; + } + + /* Verify all three scenarios have the same total_bw values */ + for (i = 0; i < test_ctx->nr_cpus; i++) { + if (test_ctx->baseline_bw[i] != loaded_bw[i]) { + SCX_ERR("CPU%d: baseline_bw=%ld != loaded_bw=%ld", + i, test_ctx->baseline_bw[i], loaded_bw[i]); + return SCX_TEST_FAIL; + } + + if (test_ctx->baseline_bw[i] != unloaded_bw[i]) { + SCX_ERR("CPU%d: baseline_bw=%ld != unloaded_bw=%ld", + i, test_ctx->baseline_bw[i], unloaded_bw[i]); + return SCX_TEST_FAIL; + } + } + + fprintf(stderr, "All total_bw values are consistent across all scenarios\n"); + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct total_bw_ctx *test_ctx = ctx; + + if (test_ctx) { + if (test_ctx->skel) + minimal__destroy(test_ctx->skel); + free(test_ctx); + } +} + +struct scx_test total_bw = { + .name = "total_bw", + .description = "Verify total_bw consistency across BPF program states", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&total_bw) -- 2.34.1

4 months, 3 weeks

1
0
0 0

[PATCH v6 12/14] selftests/sched_ext: Add test for sched_ext dl_server

by Joel Fernandes

From: Andrea Righi <arighi(a)nvidia.com> Add a selftest to validate the correct behavior of the deadline server for the ext_sched_class. [ Joel: Replaced occurences of CFS in the test with EXT. ] Signed-off-by: Joel Fernandes <joelagnelf(a)nvidia.com> Signed-off-by: Andrea Righi <arighi(a)nvidia.com> --- tools/testing/selftests/sched_ext/Makefile | 1 + .../selftests/sched_ext/rt_stall.bpf.c | 23 ++ tools/testing/selftests/sched_ext/rt_stall.c | 213 ++++++++++++++++++ 3 files changed, 237 insertions(+) create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 9d9d6b4c38b0..f0a8cba3a99f 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -182,6 +182,7 @@ auto-test-targets := \ select_cpu_dispatch_bad_dsq \ select_cpu_dispatch_dbl_dsp \ select_cpu_vtime \ + rt_stall \ test_example \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) diff --git a/tools/testing/selftests/sched_ext/rt_stall.bpf.c b/tools/testing/selftests/sched_ext/rt_stall.bpf.c new file mode 100644 index 000000000000..80086779dd1e --- /dev/null +++ b/tools/testing/selftests/sched_ext/rt_stall.bpf.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A scheduler that verified if RT tasks can stall SCHED_EXT tasks. + * + * Copyright (c) 2025 NVIDIA Corporation. + */ + +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +void BPF_STRUCT_OPS(rt_stall_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops rt_stall_ops = { + .exit = (void *)rt_stall_exit, + .name = "rt_stall", +}; diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c new file mode 100644 index 000000000000..d4cb545ebfd8 --- /dev/null +++ b/tools/testing/selftests/sched_ext/rt_stall.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 NVIDIA Corporation. + */ +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sched.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <linux/sched.h> +#include <signal.h> +#include <bpf/bpf.h> +#include <scx/common.h> +#include <sys/wait.h> +#include <unistd.h> +#include "rt_stall.bpf.skel.h" +#include "scx_test.h" +#include "../kselftest.h" + +#define CORE_ID 0 /* CPU to pin tasks to */ +#define RUN_TIME 5 /* How long to run the test in seconds */ + +/* Simple busy-wait function for test tasks */ +static void process_func(void) +{ + while (1) { + /* Busy wait */ + for (volatile unsigned long i = 0; i < 10000000UL; i++); + } +} + +/* Set CPU affinity to a specific core */ +static void set_affinity(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask) != 0) { + perror("sched_setaffinity"); + exit(EXIT_FAILURE); + } +} + +/* Set task scheduling policy and priority */ +static void set_sched(int policy, int priority) +{ + struct sched_param param; + + param.sched_priority = priority; + if (sched_setscheduler(0, policy, &param) != 0) { + perror("sched_setscheduler"); + exit(EXIT_FAILURE); + } +} + +/* Get process runtime from /proc/<pid>/stat */ +static float get_process_runtime(int pid) +{ + char path[256]; + FILE *file; + long utime, stime; + int fields; + + snprintf(path, sizeof(path), "/proc/%d/stat", pid); + file = fopen(path, "r"); + if (file == NULL) { + perror("Failed to open stat file"); + return -1; + } + + /* Skip the first 13 fields and read the 14th and 15th */ + fields = fscanf(file, + "%*d %*s %*c %*d %*d %*d %*d %*d %*u %*u %*u %*u %*u %lu %lu", + &utime, &stime); + fclose(file); + + if (fields != 2) { + fprintf(stderr, "Failed to read stat file\n"); + return -1; + } + + /* Calculate the total time spent in the process */ + long total_time = utime + stime; + long ticks_per_second = sysconf(_SC_CLK_TCK); + float runtime_seconds = total_time * 1.0 / ticks_per_second; + + return runtime_seconds; +} + +static enum scx_test_status setup(void **ctx) +{ + struct rt_stall *skel; + + skel = rt_stall__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(rt_stall__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static bool sched_stress_test(void) +{ + float cfs_runtime, rt_runtime; + int cfs_pid, rt_pid; + float expected_min_ratio = 0.04; /* 4% */ + + ksft_print_header(); + ksft_set_plan(1); + + /* Create and set up a EXT task */ + cfs_pid = fork(); + if (cfs_pid == 0) { + set_affinity(CORE_ID); + process_func(); + exit(0); + } else if (cfs_pid < 0) { + perror("fork for EXT task"); + ksft_exit_fail(); + } + + /* Create an RT task */ + rt_pid = fork(); + if (rt_pid == 0) { + set_affinity(CORE_ID); + set_sched(SCHED_FIFO, 50); + process_func(); + exit(0); + } else if (rt_pid < 0) { + perror("fork for RT task"); + ksft_exit_fail(); + } + + /* Let the processes run for the specified time */ + sleep(RUN_TIME); + + /* Get runtime for the EXT task */ + cfs_runtime = get_process_runtime(cfs_pid); + if (cfs_runtime != -1) + ksft_print_msg("Runtime of EXT task (PID %d) is %f seconds\n", cfs_pid, cfs_runtime); + else + ksft_exit_fail_msg("Error getting runtime for EXT task (PID %d)\n", cfs_pid); + + /* Get runtime for the RT task */ + rt_runtime = get_process_runtime(rt_pid); + if (rt_runtime != -1) + ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime); + else + ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid); + + /* Kill the processes */ + kill(cfs_pid, SIGKILL); + kill(rt_pid, SIGKILL); + waitpid(cfs_pid, NULL, 0); + waitpid(rt_pid, NULL, 0); + + /* Verify that the scx task got enough runtime */ + float actual_ratio = cfs_runtime / (cfs_runtime + rt_runtime); + ksft_print_msg("EXT task got %.2f%% of total runtime\n", actual_ratio * 100); + + if (actual_ratio >= expected_min_ratio) { + ksft_test_result_pass("PASS: EXT task got more than %.2f%% of runtime\n", + expected_min_ratio * 100); + return true; + } else { + ksft_test_result_fail("FAIL: EXT task got less than %.2f%% of runtime\n", + expected_min_ratio * 100); + return false; + } +} + +static enum scx_test_status run(void *ctx) +{ + struct rt_stall *skel = ctx; + struct bpf_link *link; + bool res; + + link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + res = sched_stress_test(); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE)); + bpf_link__destroy(link); + + if (!res) + ksft_exit_fail(); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct rt_stall *skel = ctx; + + rt_stall__destroy(skel); +} + +struct scx_test rt_stall = { + .name = "rt_stall", + .description = "Verify that RT tasks cannot stall SCHED_EXT tasks", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&rt_stall) -- 2.34.1

4 months, 3 weeks

1
0
0 0

[PATCH net-next v12 0/8] Support rate management on traffic classes in devlink and mlx5

by Mark Bloch

V12: - Fixed YAML indentation in devlink.yaml. - Removed unused total variable from devlink_nl_rate_tc_bw_set(). - Quoted shell variables in devlink.sh and split declarations to fix shellcheck warnings. - Added missing DevlinkFamily imports in selftests to fix pylint warnings. - Pulled changes from net-next to enable these adjustments: Inclusion of DevlinkFamily in YNL test libs. Introduction of nlmsg_for_each_attr_type() macro and its use in nfsd. V11: - Refactored the devlink code to accept relative TC bandwidth share values instead of percentages. - Updated documentation to clarify that values are interpreted as relative shares. - Refactored the logic in mlx5 to support proportional scaling for tc-bw values. - Switched to `nlmsg_for_each_attr_type()` for cleaner attribute parsing. - Added a hardware selftest to validate TC bandwidth behavior. - Refactored esw_qos_is_node_empty for readability. V10: - Added netdevsim selftest for tc-bw ops. - Dropped header: field as it’s unnecessary for local constants in devlink.yaml. V9: - Defined DEVLINK_RATE_TCS_MAX as 8 in uapi/linux/devlink.h. - Replaced IEEE_8021QAZ_MAX_TCS with DEVLINK_RATE_TCS_MAX throughout the code. - Updated devlink-rate-tc-index-max spec to reference the correct UAPI header. V8: - Limit line width to 80 characters in mlx5 changes instead of 100. - Increase the scheduling node levels to support TC arbitration. - Ensure parent nodes are set correctly in all code paths that extend the hierarchy depth for TC arbitration. - Extended the cover letter with the ongoing discussion on devlink-rate and net-shapers. - Extended the cover letter with the Netdev talk link on this series. V7: - Fixed disabling tc-bw on leaf nodes that did not have tc-bw configured. - Fixed an issue where tc-bw was disabled on a node with assigned vports, ensuring that vport->qos.sched_node->parent is correctly updated with the cloned node. - Declared a constant for the maximum allowed Traffic Class index in devlink rate. - Added a range check to validate rate-tc-index. - Added documentation for the tc-bw argument. - Add a validation check to ensure that the total bandwidth assigned to all traffic classes sums to 100. V6: - Addressed comments on devlink patch #3. - Removed first 4 IFC patches, to be pulled from mlx5-next. V5: - Fix warning in devlink_nl_rate_tc_bw_set(). - Fix target branch of patch #4. V4: - Renamed the nested attribute for traffic class bandwidth to DEVLINK_ATTR_RATE_TC_BWS. - Changed the order of the attributes in `devlink.h`. - Refactored the initialization tc-bw array in devlink_nl_rate_tc_bw_set(). - Added extack messages to provide clear feedback on issues with tc-bw arguments. - Updated `rate-tc-bws` to support a multi-attr set, where each attribute includes an index and the corresponding bandwidth for that traffic class. - Handled the issue where the user could provide DEVLINK_ATTR_RATE_TC_BWS with duplicate indices. - Provided ynl exmaples in patch [1/5] commit message. - Take IFC patches to beginning of the series, targeted for mlx5-next. V3: - Dropped rate-tc-index, using tc-bw array index instead. - Renamed rate-bw to rate-tc-bw. - Documneted what the rate-tc-bw represents and added a range check for validation. - Intorduced devlink_nl_rate_tc_bw_set() to parse and set the TC bandwidth values. - Updated the user API in the commit message of patch 1/6 to ensure bandwidths sum equals 100. - Fixed missing filling of rate-parent in devlink_nl_rate_fill(). V2: - Included <linux/dcbnl.h> in devlink.h to resolve missing IEEE_8021QAZ_MAX_TCS definition. - Refactored the rate-tc-bw attribute structure to use a separate rate-tc-index. - Updated patch 2/6 title. This patch series extends the devlink-rate API to support traffic class (TC) bandwidth management, enabling more granular control over traffic shaping and rate limiting across multiple TCs. The API now allows users to specify bandwidth proportions for different traffic classes in a single command. This is particularly useful for managing Enhanced Transmission Selection (ETS) for groups of Virtual Functions (VFs), allowing precise bandwidth allocation across traffic classes. Additionally the series refines the QoS handling in net/mlx5 to support TC arbitration and bandwidth management on vports and rate nodes. Discussions on traffic class shaping in net-shapers began in V5 [1], where we discussed with maintainers whether net-shapers should support traffic classes and how this could be implemented. Later, after further conversations with Paolo Abeni and Simon Horman, Cosmin provided an update [2], confirming that net-shapers' tree-based hierarchy aligns well with traffic classes when treated as distinct subsets of netdev queues. Since mlx5 enforces a 1:1 mapping between TX queues and traffic classes, this approach seems feasible, though some open questions remain regarding queue reconfiguration and certain mlx5 scheduling behaviors. Building on that discussion, Cosmin has now shared a concrete implementation plan on the netdev mailing list [3]. The plan, developed in collaboration with Paolo and Simon, outlines how net-shapers can be extended to support the same use cases currently covered by devlink-rate, with the eventual goal of aligning both and simplifying the shaping infrastructure in the kernel. This work was presented at Netdev 0x19 in Zagreb [4]. There we presented how TC scheduling is enforced in mlx5 hardware, which led to discussions on the mailing list. A summary of how things work: Classification means labeling a packet with a traffic class based on the packet's DSCP or VLAN PCP field, then treating packets with different traffic classes differently during transmit processing. In a virtualized setup, VFs are untrusted and do not control classification or shaping. Classification is done by the hardware using a prio-to-TC mapping set by the hypervisor. VFs only select which send queue to use and are expected to respect the classification logic by sending each traffic class on its dedicated queue. As stated in the net-shapers plan [3], each transmit queue should carry only a single traffic class. Mixing classes in a single queue can lead to HOL blocking. In the mlx5 implementation, if the queue used does not match the classified traffic class, the hardware moves the queue to the correct TC scheduler. This movement is not a reclassification; it’s a necessary enforcement step to ensure traffic class isolation is maintained. Extend devlink-rate API to support rate management on TCs: - devlink: Extend the devlink rate API to support traffic class bandwidth management Introduce a no-op implementation: - net/mlx5: Add no-op implementation for setting tc-bw on rate objects Add support for enabling and disabling TC QoS on vports and nodes: - net/mlx5: Add support for setting tc-bw on nodes - net/mlx5: Add traffic class scheduling support for vport QoS Support for setting tc-bw on rate objects: - net/mlx5: Manage TC arbiter nodes and implement full support for tc-bw [1] https://lore.kernel.org/netdev/20241204220931.254964-1-tariqt@nvidia.com/ [2] https://lore.kernel.org/netdev/67df1a562614b553dcab043f347a0d7c5393ff83.cam… [3] https://lore.kernel.org/netdev/d9831d0c940a7b77419abe7c7330e822bbfd1cfb.cam… [4] https://netdevconf.info/0x19/sessions/talk/optimizing-bandwidth-allocation-… Carolina Jubran (8): netlink: introduce type-checking attribute iteration for nlmsg devlink: Extend devlink rate API with traffic classes bandwidth management selftest: netdevsim: Add devlink rate tc-bw test net/mlx5: Add no-op implementation for setting tc-bw on rate objects net/mlx5: Add support for setting tc-bw on nodes net/mlx5: Add traffic class scheduling support for vport QoS net/mlx5: Manage TC arbiter nodes and implement full support for tc-bw selftests: drv-net: Add test for devlink-rate traffic class bandwidth distribution Documentation/netlink/specs/devlink.yaml | 32 +- .../networking/devlink/devlink-port.rst | 8 + .../net/ethernet/mellanox/mlx5/core/devlink.c | 2 + .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 1037 ++++++++++++++++- .../net/ethernet/mellanox/mlx5/core/esw/qos.h | 8 + .../net/ethernet/mellanox/mlx5/core/eswitch.h | 14 +- drivers/net/netdevsim/dev.c | 43 + drivers/net/netdevsim/netdevsim.h | 1 + drivers/net/vxlan/vxlan_vnifilter.c | 13 +- fs/nfsd/nfsctl.c | 36 +- include/net/devlink.h | 8 + include/net/netlink.h | 14 + include/uapi/linux/devlink.h | 9 + net/devlink/netlink_gen.c | 15 +- net/devlink/netlink_gen.h | 1 + net/devlink/rate.c | 127 ++ .../drivers/net/hw/devlink_rate_tc_bw.py | 466 ++++++++ .../drivers/net/hw/lib/py/__init__.py | 2 +- .../selftests/drivers/net/lib/py/__init__.py | 2 +- .../drivers/net/netdevsim/devlink.sh | 53 + .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/ynl.py | 5 + 22 files changed, 1825 insertions(+), 73 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py base-commit: 20a0c20f82acf46d5731a11743e7c7ac4de25db8 -- 2.34.1

4 months, 3 weeks

2
9
0 0

[PATCH] selftests/futex: Add futex_numa to .gitignore

by Terry Tritton

futex_numa was never added to the .gitignore file. Add it. Signed-off-by: Terry Tritton <terry.tritton(a)linaro.org> --- tools/testing/selftests/futex/functional/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 7b24ae89594a..776ad658f75e 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -11,3 +11,4 @@ futex_wait_timeout futex_wait_uninitialized_heap futex_wait_wouldblock futex_waitv +futex_numa -- 2.39.5

4 months, 3 weeks

2
1
0 0

[PATCH] selftests/kexec: fix test_kexec_jump build and ignore generated binary

by Moon Hee Lee

The test_kexec_jump program builds correctly when invoked from the top-level selftests/Makefile, which explicitly sets the OUTPUT variable. However, building directly in tools/testing/selftests/kexec fails with: make: *** No rule to make target '/test_kexec_jump', needed by 'test_kexec_jump.sh'. Stop. This failure occurs because the Makefile rule relies on $(OUTPUT), which is undefined in direct builds. Fix this by listing test_kexec_jump in TEST_GEN_PROGS, the standard way to declare generated test binaries in the kselftest framework. This ensures the binary is built regardless of invocation context and properly removed by make clean. Also add the binary to .gitignore to avoid tracking it in version control. Signed-off-by: Moon Hee Lee <moonhee.lee.ca(a)gmail.com> --- tools/testing/selftests/kexec/.gitignore | 2 ++ tools/testing/selftests/kexec/Makefile | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/kexec/.gitignore diff --git a/tools/testing/selftests/kexec/.gitignore b/tools/testing/selftests/kexec/.gitignore new file mode 100644 index 000000000000..5f3d9e089ae8 --- /dev/null +++ b/tools/testing/selftests/kexec/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +test_kexec_jump diff --git a/tools/testing/selftests/kexec/Makefile b/tools/testing/selftests/kexec/Makefile index e3000ccb9a5d..874cfdd3b75b 100644 --- a/tools/testing/selftests/kexec/Makefile +++ b/tools/testing/selftests/kexec/Makefile @@ -12,7 +12,7 @@ include ../../../scripts/Makefile.arch ifeq ($(IS_64_BIT)$(ARCH_PROCESSED),1x86) TEST_PROGS += test_kexec_jump.sh -test_kexec_jump.sh: $(OUTPUT)/test_kexec_jump +TEST_GEN_PROGS := test_kexec_jump endif include ../lib.mk -- 2.43.0

4 months, 3 weeks

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror