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

[PATCH] selftests: bpf: Replace sizeof(arr)/sizeof(arr[0]) with ARRAY_SIZE

by yangfeng

From: Feng Yang <yangfeng(a)kylinos.cn> The ARRAY_SIZE macro is more compact and more formal in linux source. Signed-off-by: Feng Yang <yangfeng(a)kylinos.cn> --- tools/testing/selftests/bpf/prog_tests/fexit_stress.c | 3 ++- tools/testing/selftests/bpf/prog_tests/log_buf.c | 5 +++-- .../testing/selftests/bpf/prog_tests/module_fentry_shadow.c | 3 ++- .../bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c | 3 ++- .../selftests/bpf/prog_tests/raw_tp_writable_test_run.c | 5 +++-- tools/testing/selftests/bpf/prog_tests/tc_opts.c | 2 +- tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c | 3 ++- tools/testing/selftests/bpf/progs/syscall.c | 3 ++- tools/testing/selftests/bpf/progs/test_rdonly_maps.c | 3 ++- tools/testing/selftests/bpf/progs/verifier_bits_iter.c | 2 +- 10 files changed, 20 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index 49b1ffc9af1f..14c91b6f1e83 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "bpf_util.h" void serial_test_fexit_stress(void) { @@ -36,7 +37,7 @@ void serial_test_fexit_stress(void) for (i = 0; i < bpf_max_tramp_links; i++) { fexit_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL", trace_program, - sizeof(trace_program) / sizeof(struct bpf_insn), + ARRAY_SIZE(trace_program), &trace_opts); if (!ASSERT_GE(fexit_fd[i], 0, "fexit load")) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index 0f7ea4d7d9f6..46611040dec3 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -5,6 +5,7 @@ #include <bpf/btf.h> #include "test_log_buf.skel.h" +#include "bpf_util.h" static size_t libbpf_log_pos; static char libbpf_log_buf[1024 * 1024]; @@ -143,11 +144,11 @@ static void bpf_prog_load_log_buf(void) BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - const size_t good_prog_insn_cnt = sizeof(good_prog_insns) / sizeof(struct bpf_insn); + const size_t good_prog_insn_cnt = ARRAY_SIZE(good_prog_insns); const struct bpf_insn bad_prog_insns[] = { BPF_EXIT_INSN(), }; - size_t bad_prog_insn_cnt = sizeof(bad_prog_insns) / sizeof(struct bpf_insn); + size_t bad_prog_insn_cnt = ARRAY_SIZE(bad_prog_insns); LIBBPF_OPTS(bpf_prog_load_opts, opts); const size_t log_buf_sz = 1024 * 1024; char *log_buf; diff --git a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c index aa9f67eb1c95..bea05f78de5f 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c +++ b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c @@ -4,6 +4,7 @@ #include <bpf/btf.h> #include "bpf/libbpf_internal.h" #include "cgroup_helpers.h" +#include "bpf_util.h" static const char *module_name = "bpf_testmod"; static const char *symbol_name = "bpf_fentry_shadow_test"; @@ -100,7 +101,7 @@ void test_module_fentry_shadow(void) load_opts.attach_btf_obj_fd = btf_fd[i]; prog_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL", trace_program, - sizeof(trace_program) / sizeof(struct bpf_insn), + ARRAY_SIZE(trace_program), &load_opts); if (!ASSERT_GE(prog_fd[i], 0, "bpf_prog_load")) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c index e2f1445b0e10..216b0dfac0fe 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c @@ -2,6 +2,7 @@ #include <test_progs.h> #include <linux/nbd.h> +#include "bpf_util.h" void test_raw_tp_writable_reject_nbd_invalid(void) { @@ -25,7 +26,7 @@ void test_raw_tp_writable_reject_nbd_invalid(void) ); bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", - program, sizeof(program) / sizeof(struct bpf_insn), + program, ARRAY_SIZE(program), &opts); if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load", "failed: %d errno %d\n", bpf_fd, errno)) diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c index f4aa7dab4766..e3668058b7bb 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -2,6 +2,7 @@ #include <test_progs.h> #include <linux/nbd.h> +#include "bpf_util.h" /* NOTE: conflict with other tests. */ void serial_test_raw_tp_writable_test_run(void) @@ -24,7 +25,7 @@ void serial_test_raw_tp_writable_test_run(void) ); int bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", - trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), + trace_program, ARRAY_SIZE(trace_program), &trace_opts); if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded", "failed: %d errno %d\n", bpf_fd, errno)) @@ -41,7 +42,7 @@ void serial_test_raw_tp_writable_test_run(void) ); int filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL v2", - skb_program, sizeof(skb_program) / sizeof(struct bpf_insn), + skb_program, ARRAY_SIZE(skb_program), &skb_opts); if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", filter_fd, errno)) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index 196abf223465..f77f604389aa 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -2384,7 +2384,7 @@ static int generate_dummy_prog(void) BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn); + const size_t prog_insn_cnt = ARRAY_SIZE(prog_insns); LIBBPF_OPTS(bpf_prog_load_opts, opts); const size_t log_buf_sz = 256; char log_buf[log_buf_sz]; diff --git a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c index 0adf8d9475cb..472f4f9fa95f 100644 --- a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c +++ b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c @@ -7,6 +7,7 @@ #include "test_unpriv_bpf_disabled.skel.h" #include "cap_helpers.h" +#include "bpf_util.h" /* Using CAP_LAST_CAP is risky here, since it can get pulled in from * an old /usr/include/linux/capability.h and be < CAP_BPF; as a result @@ -146,7 +147,7 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn); + const size_t prog_insn_cnt = ARRAY_SIZE(prog_insns); LIBBPF_OPTS(bpf_prog_load_opts, load_opts); struct bpf_map_info map_info = {}; __u32 map_info_len = sizeof(map_info); diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c index 3d3cafdebe72..0f4dfb770c32 100644 --- a/tools/testing/selftests/bpf/progs/syscall.c +++ b/tools/testing/selftests/bpf/progs/syscall.c @@ -8,6 +8,7 @@ #include <linux/btf.h> #include <string.h> #include <errno.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -119,7 +120,7 @@ int load_prog(struct args *ctx) static __u64 value = 34; static union bpf_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, - .insn_cnt = sizeof(insns) / sizeof(insns[0]), + .insn_cnt = ARRAY_SIZE(insns), }; int ret; diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c index fc8e8a34a3db..7035fb4d4165 100644 --- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c +++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c @@ -4,6 +4,7 @@ #include <linux/ptrace.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" const struct { unsigned a[4]; @@ -64,7 +65,7 @@ int full_loop(struct pt_regs *ctx) { /* prevent compiler to optimize everything out */ unsigned * volatile p = (void *)&rdonly_values.a; - int i = sizeof(rdonly_values.a) / sizeof(rdonly_values.a[0]); + int i = ARRAY_SIZE(rdonly_values.a); unsigned iters = 0, sum = 0; /* validate verifier can allow full loop as well */ diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index 716113c2bce2..f4da4d508ddb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -87,7 +87,7 @@ int bits_memalloc(void) int *bit; __builtin_memset(&data, 0xf0, sizeof(data)); /* 4 * 16 */ - bpf_for_each(bits, bit, &data[0], sizeof(data) / sizeof(u64)) + bpf_for_each(bits, bit, &data[0], ARRAY_SIZE(data)) nr++; return nr; } -- 2.27.0

10 months

2
1
0 0

[PATCH v2] mm/damon/tests/vaddr-kunit: init maple tree without MT_FLAGS_LOCK_EXTERN

by SeongJae Park

damon_test_three_regions_in_vmas() initializes a maple tree with MM_MT_FLAGS. The flags contains MT_FLAGS_LOCK_EXTERN, which means mt_lock of the maple tree will not be used. And therefore the maple tree initialization code skips initialization of the mt_lock. However, __link_vmas(), which adds vmas for test to the maple tree, uses the mt_lock. In other words, the uninitialized spinlock is used. The problem becomes clear when spinlock debugging is turned on, since it reports spinlock bad magic bug. Fix the issue by excluding MT_FLAGS_LOCK_EXTERN from the maple tree initialization flags. Note that we don't use empty flags to make it further similar to the usage of mm maple tree, and to be prepared for possible future changes, as suggested by Liam. Reported-by: Guenter Roeck <linux(a)roeck-us.net> Closes: https://lore.kernel.org/1453b2b2-6119-4082-ad9e-f3c5239bf87e@roeck-us.net Fixes: d0cf3dd47f0d ("damon: convert __damon_va_three_regions to use the VMA iterator") Suggested-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Signed-off-by: SeongJae Park <sj(a)kernel.org> --- Changes from v1 (https://lore.kernel.org/20240904004534.1189-1-sj@kernel.org) - Keep lock usage and update the initialization flags (Liam) - Fix a typo: s/celar/clear/ (Guenter) mm/damon/tests/vaddr-kunit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h index 83626483f82b..a339d117150f 100644 --- a/mm/damon/tests/vaddr-kunit.h +++ b/mm/damon/tests/vaddr-kunit.h @@ -77,7 +77,7 @@ static void damon_test_three_regions_in_vmas(struct kunit *test) (struct vm_area_struct) {.vm_start = 307, .vm_end = 330}, }; - mt_init_flags(&mm.mm_mt, MM_MT_FLAGS); + mt_init_flags(&mm.mm_mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_USE_RCU); if (__link_vmas(&mm.mm_mt, vmas, ARRAY_SIZE(vmas))) kunit_skip(test, "Failed to create VMA tree"); -- 2.39.2

10 months

3
4
0 0

[PATCH bpf,v2,0/2] bpf: fix incorrect name check pass logic in btf_name_valid_section

by Jeongjun Park

This patch was written to fix an issue where btf_name_valid_section() would not properly check names with certain conditions and would throw an OOB vuln. And selftest was added to verify this patch. Jeongjun Park (2): bpf: add check for invalid name in btf_name_valid_section() selftest/bpf : Add a selftest test case to check for incorrect names kernel/bpf/btf.c | 4 ++- tools/testing/selftests/bpf/prog_tests/btf.c | 34 ++++++++++++++++++++ 2 files changed, 37 insertions(+), 1 deletion(-)

10 months

3
4
0 0

[PATCH v2 1/1] selftests/bpf: Fix procmap_query()'s params mismatch and compilation warning

by Yuan Chen

From: Yuan Chen <chenyuan(a)kylinos.cn> When the PROCMAP_QUERY is not defined, a compilation error occurs due to the mismatch of the procmap_query()'s params, procmap_query() only be called in the file where the function is defined, modify the params so they can match. We get a warning when build samples/bpf: trace_helpers.c:252:5: warning: no previous prototype for ‘procmap_query’ [-Wmissing-prototypes] 252 | int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) | ^~~~~~~~~~~~~ As this function is only used in the file, mark it as 'static'. Fixes: 4e9e07603ecd ("selftests/bpf: make use of PROCMAP_QUERY ioctl if available") Signed-off-by: Yuan Chen <chenyuan(a)kylinos.cn> --- tools/testing/selftests/bpf/trace_helpers.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 1bfd881c0e07..2d742fdac6b9 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -249,7 +249,7 @@ int kallsyms_find(const char *sym, unsigned long long *addr) #ifdef PROCMAP_QUERY int env_verbosity __weak = 0; -int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) +static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { char path_buf[PATH_MAX], build_id_buf[20]; struct procmap_query q; @@ -293,7 +293,7 @@ int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, si return 0; } #else -int procmap_query(int fd, const void *addr, size_t *start, size_t *offset, int *flags) +static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { return -EOPNOTSUPP; } -- 2.46.0

10 months

2
1
0 0

[PATCH] selftests: futex: Fix missing free in main

by zhangjiao2

From: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> Free string allocated by asprintf(). Signed-off-by: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> --- tools/testing/selftests/futex/functional/futex_requeue_pi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c index 215c6cb539b4..fb2dab46087f 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c @@ -416,5 +416,8 @@ int main(int argc, char *argv[]) ret = unit_test(broadcast, locked, owner, timeout_ns); print_result(test_name, ret); + if (strlen(test_name) > strlen(TEST_NAME)) + free(test_name); + return ret; } -- 2.33.0

10 months

2
1
0 0

[PATCH] iommufd/selftest:fix a resource leak

by Liu Jing

If the file fails to open, not only return return1 but also close the file descriptor,otherwise resource leak will occur Signed-off-by: Liu Jing <liujing(a)cmss.chinamobile.com> --- .../selftests/iommu/iommufd_fail_nth.c | 143 ++++++++++-------- 1 file changed, 83 insertions(+), 60 deletions(-) diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index c5d5e69452b0..ff4e5d8aad57 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -237,10 +237,10 @@ TEST_FAIL_NTH(basic_fail_nth, basic) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; { struct iommu_ioas_iova_ranges ranges_cmd = { @@ -250,7 +250,7 @@ TEST_FAIL_NTH(basic_fail_nth, basic) .allowed_iovas = (uintptr_t)ranges, }; if (ioctl(self->fd, IOMMU_IOAS_IOVA_RANGES, &ranges_cmd)) - return -1; + goto close; } { @@ -264,13 +264,13 @@ TEST_FAIL_NTH(basic_fail_nth, basic) ranges[0].start = 16*1024; ranges[0].last = BUFFER_SIZE + 16 * 1024 * 600 - 1; if (ioctl(self->fd, IOMMU_IOAS_ALLOW_IOVAS, &allow_cmd)) - return -1; + goto close; } if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, BUFFER_SIZE, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; { struct iommu_ioas_copy copy_cmd = { @@ -284,15 +284,19 @@ TEST_FAIL_NTH(basic_fail_nth, basic) }; if (ioctl(self->fd, IOMMU_IOAS_COPY, &copy_cmd)) - return -1; + goto close; } if (_test_ioctl_ioas_unmap(self->fd, ioas_id, iova, BUFFER_SIZE, NULL)) - return -1; + goto close; /* Failure path of no IOVA to unmap */ _test_ioctl_ioas_unmap(self->fd, ioas_id, iova, BUFFER_SIZE, NULL); return 0; + +close: + close(self->fd); + return -1; } /* iopt_area_fill_domains() and iopt_area_fill_domain() */ @@ -305,30 +309,33 @@ TEST_FAIL_NTH(basic_fail_nth, map_domain) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; fail_nth_enable(); if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, 262144, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_ioctl_destroy(self->fd, stdev_id)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; return 0; +close: + close(self->fd); + return -1; } TEST_FAIL_NTH(basic_fail_nth, map_two_domains) @@ -342,40 +349,43 @@ TEST_FAIL_NTH(basic_fail_nth, map_two_domains) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; fail_nth_enable(); if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id2, &hwpt_id2, NULL)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, 262144, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_ioctl_destroy(self->fd, stdev_id)) - return -1; + goto close; if (_test_ioctl_destroy(self->fd, stdev_id2)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id2, &hwpt_id2, NULL)) - return -1; + goto close; return 0; +close: + close(self->fd); + return -1; } TEST_FAIL_NTH(basic_fail_nth, access_rw) @@ -387,23 +397,23 @@ TEST_FAIL_NTH(basic_fail_nth, access_rw) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, 262144, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; fail_nth_enable(); if (_test_cmd_create_access(self->fd, ioas_id, &self->access_id, 0)) - return -1; + goto close; { struct iommu_test_cmd access_cmd = { @@ -418,22 +428,22 @@ TEST_FAIL_NTH(basic_fail_nth, access_rw) // READ if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_cmd.access_rw.flags = MOCK_ACCESS_RW_WRITE; if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_cmd.access_rw.flags = MOCK_ACCESS_RW_SLOW_PATH; if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_cmd.access_rw.flags = MOCK_ACCESS_RW_SLOW_PATH | MOCK_ACCESS_RW_WRITE; if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; } { @@ -449,12 +459,15 @@ TEST_FAIL_NTH(basic_fail_nth, access_rw) if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; } if (_test_cmd_destroy_access(self->access_id)) return -1; self->access_id = 0; return 0; +close: + close(self->fd); + return -1; } /* pages.c access functions */ @@ -466,22 +479,22 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, BUFFER_SIZE, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_cmd_create_access(self->fd, ioas_id, &self->access_id, MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES)) - return -1; + goto close; fail_nth_enable(); @@ -497,18 +510,21 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin) if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_pages_id = access_cmd.access_pages.out_access_pages_id; } if (_test_cmd_destroy_access_pages(self->fd, self->access_id, access_pages_id)) - return -1; + goto close; if (_test_cmd_destroy_access(self->access_id)) return -1; self->access_id = 0; return 0; +close: + close(self->fd); + return -1; } /* iopt_pages_fill_xarray() */ @@ -522,25 +538,25 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) - return -1; + goto close; if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, BUFFER_SIZE, &iova, IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_cmd_create_access(self->fd, ioas_id, &self->access_id, MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES)) - return -1; + goto close; fail_nth_enable(); @@ -556,21 +572,24 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain) if (ioctl(self->fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_ACCESS_RW), &access_cmd)) - return -1; + goto close; access_pages_id = access_cmd.access_pages.out_access_pages_id; } if (_test_cmd_destroy_access_pages(self->fd, self->access_id, access_pages_id)) - return -1; + goto close; if (_test_cmd_destroy_access(self->access_id)) return -1; self->access_id = 0; if (_test_ioctl_destroy(self->fd, stdev_id)) - return -1; + goto close; return 0; +close: + close(self->fd); + return -1; } /* device.c */ @@ -586,45 +605,49 @@ TEST_FAIL_NTH(basic_fail_nth, device) self->fd = open("/dev/iommu", O_RDWR); if (self->fd == -1) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) - return -1; + goto close; if (_test_ioctl_ioas_alloc(self->fd, &ioas_id2)) - return -1; + goto close; iova = MOCK_APERTURE_START; if (_test_ioctl_ioas_map(self->fd, ioas_id, buffer, PAGE_SIZE, &iova, IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; if (_test_ioctl_ioas_map(self->fd, ioas_id2, buffer, PAGE_SIZE, &iova, IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) - return -1; + goto close; fail_nth_enable(); if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, NULL, &idev_id)) - return -1; + goto close; if (_test_cmd_get_hw_info(self->fd, idev_id, &info, sizeof(info), NULL)) - return -1; + goto close; if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0, 0, &hwpt_id, IOMMU_HWPT_DATA_NONE, 0, 0)) - return -1; + goto close; if (_test_cmd_mock_domain_replace(self->fd, stdev_id, ioas_id2, NULL)) - return -1; + goto close; if (_test_cmd_mock_domain_replace(self->fd, stdev_id, hwpt_id, NULL)) - return -1; + goto close; return 0; +close: + close(self->fd); + return -1; + } TEST_HARNESS_MAIN -- 2.33.0

10 months

2
1
0 0

[PATCH] um: kunit: resolve missing prototypes warning

by Gabriele Monaco

While building for KUnit with default settings, the build is generating the following compilation warnings. ``` $ make ARCH=um O=.kunit --jobs=16 ../lib/iomap.c:156:5: warning: no previous prototype for ‘ioread64_lo_hi’ [-Wmissing-prototypes] 156 | u64 ioread64_lo_hi(const void __iomem *addr) | ^~~~~~~~~~~~~~ [...] ``` The warning happens because the prototypes are defined in `asm-generic/iomap.h` only when `readq` and `writeq` are defined. For UM, those function get some default definitions but are currently defined _after_ the prototypes for `ioread64*`/`iowrite64*` functions. Moving the inclusion of `asm-generic/iomap.h` fixes it. Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- include/asm-generic/io.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 80de699bf6af..0b02c8e38f20 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -13,10 +13,6 @@ #include <linux/types.h> #include <linux/instruction_pointer.h> -#ifdef CONFIG_GENERIC_IOMAP -#include <asm-generic/iomap.h> -#endif - #include <asm/mmiowb.h> #include <asm-generic/pci_iomap.h> @@ -295,6 +291,10 @@ static inline void writeq(u64 value, volatile void __iomem *addr) #endif #endif /* CONFIG_64BIT */ +#ifdef CONFIG_GENERIC_IOMAP +#include <asm-generic/iomap.h> +#endif + /* * {read,write}{b,w,l,q}_relaxed() are like the regular version, but * are not guaranteed to provide ordering against spinlocks or memory base-commit: 67784a74e258a467225f0e68335df77acd67b7ab -- 2.46.0

10 months

2
2
0 0

[PATCH net-next v17 02/14] mm: move the page fragment allocator from page_alloc into its own file

by Yunsheng Lin

Inspired by [1], move the page fragment allocator from page_alloc into its own c file and header file, as we are about to make more change for it to replace another page_frag implementation in sock.c As this patchset is going to replace 'struct page_frag' with 'struct page_frag_cache' in sched.h, including page_frag_cache.h in sched.h has a compiler error caused by interdependence between mm_types.h and mm.h for asm-offsets.c, see [2]. So avoid the compiler error by moving 'struct page_frag_cache' to mm_types_task.h as suggested by Alexander, see [3]. 1. https://lore.kernel.org/all/20230411160902.4134381-3-dhowells@redhat.com/ 2. https://lore.kernel.org/all/15623dac-9358-4597-b3ee-3694a5956920@gmail.com/ 3. https://lore.kernel.org/all/CAKgT0UdH1yD=LSCXFJ=YM_aiA4OomD-2wXykO42bizaWMt… CC: David Howells <dhowells(a)redhat.com> CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Acked-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/gfp.h | 22 --- include/linux/mm_types.h | 18 --- include/linux/mm_types_task.h | 18 +++ include/linux/page_frag_cache.h | 31 ++++ include/linux/skbuff.h | 1 + mm/Makefile | 1 + mm/page_alloc.c | 136 ---------------- mm/page_frag_cache.c | 145 ++++++++++++++++++ .../selftests/mm/page_frag/page_frag_test.c | 2 +- 9 files changed, 197 insertions(+), 177 deletions(-) create mode 100644 include/linux/page_frag_cache.h create mode 100644 mm/page_frag_cache.c diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f53f76e0b17e..01a49be7c98d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -371,28 +371,6 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -struct page_frag_cache; -void page_frag_cache_drain(struct page_frag_cache *nc); -extern void __page_frag_cache_drain(struct page *page, unsigned int count); -void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, - gfp_t gfp_mask, unsigned int align_mask); - -static inline void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align) -{ - WARN_ON_ONCE(!is_power_of_2(align)); - return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); -} - -static inline void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) -{ - return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); -} - -extern void page_frag_free(void *addr); - #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 485424979254..843d75412105 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -521,9 +521,6 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) -#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) -#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) - /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages @@ -542,21 +539,6 @@ static inline void *folio_get_private(struct folio *folio) return folio->private; } -struct page_frag_cache { - void * va; -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - __u16 offset; - __u16 size; -#else - __u32 offset; -#endif - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_refcount every time we allocate a fragment. - */ - unsigned int pagecnt_bias; - bool pfmemalloc; -}; - typedef unsigned long vm_flags_t; /* diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index a2f6179b672b..cdc1e3696439 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -8,6 +8,7 @@ * (These are defined separately to decouple sched.h from mm_types.h as much as possible.) */ +#include <linux/align.h> #include <linux/types.h> #include <asm/page.h> @@ -46,6 +47,23 @@ struct page_frag { #endif }; +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +struct page_frag_cache { + void *va; +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + __u16 offset; + __u16 size; +#else + __u32 offset; +#endif + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_refcount every time we allocate a fragment. + */ + unsigned int pagecnt_bias; + bool pfmemalloc; +}; + /* Track pages that require TLB flushes */ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h new file mode 100644 index 000000000000..67ac8626ed9b --- /dev/null +++ b/include/linux/page_frag_cache.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PAGE_FRAG_CACHE_H +#define _LINUX_PAGE_FRAG_CACHE_H + +#include <linux/log2.h> +#include <linux/mm_types_task.h> +#include <linux/types.h> + +void page_frag_cache_drain(struct page_frag_cache *nc); +void __page_frag_cache_drain(struct page *page, unsigned int count); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + +void page_frag_free(void *addr); + +#endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cf8f6ce06742..7482997c719f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -31,6 +31,7 @@ #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> +#include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> diff --git a/mm/Makefile b/mm/Makefile index d2915f8c9dc0..e9d342fa8058 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -65,6 +65,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-y += page-alloc.o +obj-y += page_frag_cache.o obj-y += init-mm.o obj-y += memblock.o obj-y += $(memory-hotplug-y) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c565de8f48e9..d0e88aa6eb0d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4798,142 +4798,6 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); -/* - * Page Fragment: - * An arbitrary-length arbitrary-offset area of memory which resides - * within a 0 or higher order page. Multiple fragments within that page - * are individually refcounted, in the page's reference counter. - * - * The page_frag functions below provide a simple allocation framework for - * page fragments. This is used by the network stack and network device - * drivers to provide a backing region of memory for use as either an - * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. - */ -static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, - gfp_t gfp_mask) -{ - struct page *page = NULL; - gfp_t gfp = gfp_mask; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; - page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, - PAGE_FRAG_CACHE_MAX_ORDER); - nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; -#endif - if (unlikely(!page)) - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - - nc->va = page ? page_address(page) : NULL; - - return page; -} - -void page_frag_cache_drain(struct page_frag_cache *nc) -{ - if (!nc->va) - return; - - __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); - nc->va = NULL; -} -EXPORT_SYMBOL(page_frag_cache_drain); - -void __page_frag_cache_drain(struct page *page, unsigned int count) -{ - VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); - - if (page_ref_sub_and_test(page, count)) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(__page_frag_cache_drain); - -void *__page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) -{ - unsigned int size = PAGE_SIZE; - struct page *page; - int offset; - - if (unlikely(!nc->va)) { -refill: - page = __page_frag_cache_refill(nc, gfp_mask); - if (!page) - return NULL; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); - - /* reset page count bias and offset to start of new frag */ - nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - nc->offset = size; - } - - offset = nc->offset - fragsz; - if (unlikely(offset < 0)) { - page = virt_to_page(nc->va); - - if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) - goto refill; - - if (unlikely(nc->pfmemalloc)) { - free_unref_page(page, compound_order(page)); - goto refill; - } - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* OK, page count is 0, we can safely set it */ - set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - offset = size - fragsz; - if (unlikely(offset < 0)) { - /* - * The caller is trying to allocate a fragment - * with fragsz > PAGE_SIZE but the cache isn't big - * enough to satisfy the request, this may - * happen in low memory conditions. - * We don't release the cache page because - * it could make memory pressure worse - * so we simply return NULL here. - */ - return NULL; - } - } - - nc->pagecnt_bias--; - offset &= align_mask; - nc->offset = offset; - - return nc->va + offset; -} -EXPORT_SYMBOL(__page_frag_alloc_align); - -/* - * Frees a page fragment allocated out of either a compound or order 0 page. - */ -void page_frag_free(void *addr) -{ - struct page *page = virt_to_head_page(addr); - - if (unlikely(put_page_testzero(page))) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(page_frag_free); - static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) { diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c new file mode 100644 index 000000000000..609a485cd02a --- /dev/null +++ b/mm/page_frag_cache.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Page fragment allocator + * + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides within a + * 0 or higher order page. Multiple fragments within that page are + * individually refcounted, in the page's reference counter. + * + * The page_frag functions provide a simple allocation framework for page + * fragments. This is used by the network stack and network device drivers to + * provide a backing region of memory for use as either an sk_buff->head, or to + * be used in the "frags" portion of skb_shared_info. + */ + +#include <linux/export.h> +#include <linux/gfp_types.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/page_frag_cache.h> +#include "internal.h" + +static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + struct page *page = NULL; + gfp_t gfp = gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; + page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, + PAGE_FRAG_CACHE_MAX_ORDER); + nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; +#endif + if (unlikely(!page)) + page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); + + nc->va = page ? page_address(page) : NULL; + + return page; +} + +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->va) + return; + + __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); + nc->va = NULL; +} +EXPORT_SYMBOL(page_frag_cache_drain); + +void __page_frag_cache_drain(struct page *page, unsigned int count) +{ + VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); + + if (page_ref_sub_and_test(page, count)) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(__page_frag_cache_drain); + +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) +{ + unsigned int size = PAGE_SIZE; + struct page *page; + int offset; + + if (unlikely(!nc->va)) { +refill: + page = __page_frag_cache_refill(nc, gfp_mask); + if (!page) + return NULL; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); + + /* reset page count bias and offset to start of new frag */ + nc->pfmemalloc = page_is_pfmemalloc(page); + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + nc->offset = size; + } + + offset = nc->offset - fragsz; + if (unlikely(offset < 0)) { + page = virt_to_page(nc->va); + + if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) + goto refill; + + if (unlikely(nc->pfmemalloc)) { + free_unref_page(page, compound_order(page)); + goto refill; + } + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size = nc->size; +#endif + /* OK, page count is 0, we can safely set it */ + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + offset = size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } + } + + nc->pagecnt_bias--; + offset &= align_mask; + nc->offset = offset; + + return nc->va + offset; +} +EXPORT_SYMBOL(__page_frag_alloc_align); + +/* + * Frees a page fragment allocated out of either a compound or order 0 page. + */ +void page_frag_free(void *addr) +{ + struct page *page = virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(page_frag_free); diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index 6d6f31936b10..5395a36e4030 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -6,12 +6,12 @@ * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> */ -#include <linux/mm.h> #include <linux/module.h> #include <linux/cpumask.h> #include <linux/completion.h> #include <linux/ptr_ring.h> #include <linux/kthread.h> +#include <linux/page_frag_cache.h> static struct ptr_ring ptr_ring; static int nr_objs = 512; -- 2.33.0

10 months

2
1
0 0

[PATCH net-next v17 01/14] mm: page_frag: add a test module for page_frag

by Yunsheng Lin

The testing is done by ensuring that the fragment allocated from a frag_frag_cache instance is pushed into a ptr_ring instance in a kthread binded to a specified cpu, and a kthread binded to a specified cpu will pop the fragment from the ptr_ring and free the fragment. CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> --- tools/testing/selftests/mm/Makefile | 3 + tools/testing/selftests/mm/page_frag/Makefile | 18 ++ .../selftests/mm/page_frag/page_frag_test.c | 170 +++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 8 + tools/testing/selftests/mm/test_page_frag.sh | 171 ++++++++++++++++++ 5 files changed, 370 insertions(+) create mode 100644 tools/testing/selftests/mm/page_frag/Makefile create mode 100644 tools/testing/selftests/mm/page_frag/page_frag_test.c create mode 100755 tools/testing/selftests/mm/test_page_frag.sh diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index cfad627e8d94..e98ec779b2aa 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,6 +36,8 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +TEST_GEN_MODS_DIR := page_frag + TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test TEST_GEN_FILES += gup_longterm @@ -125,6 +127,7 @@ TEST_FILES += test_hmm.sh TEST_FILES += va_high_addr_switch.sh TEST_FILES += charge_reserved_hugetlb.sh TEST_FILES += hugetlb_reparenting_test.sh +TEST_FILES += test_page_frag.sh # required by charge_reserved_hugetlb.sh TEST_FILES += write_hugetlb_memory.sh diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile new file mode 100644 index 000000000000..58dda74d50a3 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -0,0 +1,18 @@ +PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = page_frag_test.ko + +obj-m += page_frag_test.o + +all: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c new file mode 100644 index 000000000000..6d6f31936b10 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for page_frag cache + * + * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/completion.h> +#include <linux/ptr_ring.h> +#include <linux/kthread.h> + +static struct ptr_ring ptr_ring; +static int nr_objs = 512; +static atomic_t nthreads; +static struct completion wait; +static struct page_frag_cache test_nc; + +static int nr_test = 2000000; +module_param(nr_test, int, 0); +MODULE_PARM_DESC(nr_test, "number of iterations to test"); + +static bool test_align; +module_param(test_align, bool, 0); +MODULE_PARM_DESC(test_align, "use align API for testing"); + +static int test_alloc_len = 2048; +module_param(test_alloc_len, int, 0); +MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); + +static int test_push_cpu; +module_param(test_push_cpu, int, 0); +MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment"); + +static int test_pop_cpu; +module_param(test_pop_cpu, int, 0); +MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment"); + +static int page_frag_pop_thread(void *arg) +{ + struct ptr_ring *ring = arg; + int nr = nr_test; + + pr_info("page_frag pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (nr > 0) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + nr--; + page_frag_free(obj); + } else { + cond_resched(); + } + } + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + pr_info("page_frag pop test thread exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_frag_push_thread(void *arg) +{ + struct ptr_ring *ring = arg; + int nr = nr_test; + + pr_info("page_frag push test thread begins on cpu %d\n", + smp_processor_id()); + + while (nr > 0) { + void *va; + int ret; + + if (test_align) { + va = page_frag_alloc_align(&test_nc, test_alloc_len, + GFP_KERNEL, SMP_CACHE_BYTES); + + WARN_ONCE((unsigned long)va & (SMP_CACHE_BYTES - 1), + "unaligned va returned\n"); + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } + + if (!va) + continue; + + ret = __ptr_ring_produce(ring, va); + if (ret) { + page_frag_free(va); + cond_resched(); + } else { + nr--; + } + } + + pr_info("page_frag push test thread exits on cpu %d\n", + smp_processor_id()); + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int __init page_frag_test_init(void) +{ + struct task_struct *tsk_push, *tsk_pop; + ktime_t start; + u64 duration; + int ret; + + test_nc.va = NULL; + atomic_set(&nthreads, 2); + init_completion(&wait); + + if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 || + !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu)) + return -EINVAL; + + ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL); + if (ret) + return ret; + + tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring, + test_push_cpu, "page_frag_push"); + if (IS_ERR(tsk_push)) + return PTR_ERR(tsk_push); + + tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring, + test_pop_cpu, "page_frag_pop"); + if (IS_ERR(tsk_pop)) { + kthread_stop(tsk_push); + return PTR_ERR(tsk_pop); + } + + start = ktime_get(); + wake_up_process(tsk_push); + wake_up_process(tsk_pop); + + pr_info("waiting for test to complete\n"); + wait_for_completion(&wait); + + duration = (u64)ktime_us_delta(ktime_get(), start); + pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", duration); + + ptr_ring_cleanup(&ptr_ring, NULL); + page_frag_cache_drain(&test_nc); + + return -EAGAIN; +} + +static void __exit page_frag_test_exit(void) +{ +} + +module_init(page_frag_test_init); +module_exit(page_frag_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yunsheng Lin <linyunsheng(a)huawei.com>"); +MODULE_DESCRIPTION("Test module for page_frag"); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 36045edb10de..96fd470b9f51 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -75,6 +75,8 @@ separated by spaces: read-only VMAs - mdwe test prctl(PR_SET_MDWE, ...) +- page_frag + test handling of page fragment allocation and freeing example: ./run_vmtests.sh -t "hmm mmap ksm" EOF @@ -456,6 +458,12 @@ CATEGORY="mkdirty" run_test ./mkdirty CATEGORY="mdwe" run_test ./mdwe_test +CATEGORY="page_frag" run_test ./test_page_frag.sh smoke + +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh new file mode 100755 index 000000000000..d2b0734a90b5 --- /dev/null +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -0,0 +1,171 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> +# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki(a)gmail.com> +# +# This is a test script for the kernel test driver to test the +# correctness and performance of page_frag's implementation. +# Therefore it is just a kernel module loader. You can specify +# and pass different parameters in order to: +# a) analyse performance of page fragment allocations; +# b) stressing and stability check of page_frag subsystem. + +DRIVER="./page_frag/page_frag_test.ko" +CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) +TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}') + +if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then + TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}') + NR_TEST=100000000 +else + TEST_CPU_1=$TEST_CPU_0 + NR_TEST=1000000 +fi + +# 1 if fails +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# +# Static templates for testing of page_frag APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" +NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" +ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" + +check_test_requirements() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile page_frag_test module" + exit $ksft_skip + fi +} + +run_nonaligned_check() +{ + echo "Run performance tests to evaluate how fast nonaligned alloc API is." + + insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1 + echo "Done." + echo "Ccheck the kernel ring buffer to see the summary." +} + +run_aligned_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_smoke_check() +{ + echo "Run smoke test." + + insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +usage() +{ + echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "manual parameters" + echo + echo "Valid tests and parameters:" + echo + modinfo $DRIVER + echo + echo "Example usage:" + echo + echo "# Shows help message" + echo "$0" + echo + echo "# Smoke testing" + echo "$0 smoke" + echo + echo "# Performance testing for nonaligned alloc API" + echo "$0 nonaligned" + echo + echo "# Performance testing for aligned alloc API" + echo "$0 aligned" + echo + exit 0 +} + +function validate_passed_args() +{ + VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'` + + # + # Something has been passed, check it. + # + for passed_arg in $@; do + key=${passed_arg//=*/} + valid=0 + + for valid_arg in $VALID_ARGS; do + if [[ $key = $valid_arg ]]; then + valid=1 + break + fi + done + + if [[ $valid -ne 1 ]]; then + echo "Error: key is not correct: ${key}" + exit $exitcode + fi + done +} + +function run_manual_check() +{ + # + # Validate passed parameters. If there is wrong one, + # the script exists and does not execute further. + # + validate_passed_args $@ + + echo "Run the test with following parameters: $@" + insmod $DRIVER $@ > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +function run_test() +{ + if [ $# -eq 0 ]; then + usage + else + if [[ "$1" = "smoke" ]]; then + run_smoke_check + elif [[ "$1" = "nonaligned" ]]; then + run_nonaligned_check + elif [[ "$1" = "aligned" ]]; then + run_aligned_check + else + run_manual_check $@ + fi + fi +} + +check_test_requirements +run_test $@ + +exit 0 -- 2.33.0

10 months

2
1
0 0

next: rcu_preempt self-detected stall on CPU - queued_spin_lock_slowpath

by Naresh Kamboju

The following kernel rcu info generated while running the test case selftests: memfd: run_fuse_test.sh on qemu-arm64 running Linux next-20240902. The qemu-arm64 did not recover. This build was created with kselftest merge configs. Anders bisected this to, # first bad commit: [5fb9c98e9d8ddf2abc645e2dcd9eb6703f77fdab] fuse: add support for no forget requests Crash log: ---------- [ 0.000000] Booting Linux on physical CPU 0x0000000000 [0x000f0510] [ 0.000000] Linux version 6.11.0-rc6-next-20240902 (tuxmake@tuxmake) (aarch64-linux-gnu-gcc (Debian 13.3.0-5) 13.3.0, GNU ld (GNU Binutils for Debian) 2.43) #1 SMP PREEMPT @1725295942 [ 0.000000] KASLR enabled [ 0.000000] random: crng init done [ 0.000000] Machine model: linux,dummy-virt .. # selftests: memfd: run_fuse_test.sh <3>[ 107.408167] rcu: INFO: rcu_preempt self-detected stall on CPU <3>[ 107.409195] rcu: 1-....: (5249 ticks this GP) idle=4d34/1/0x4000000000000000 softirq=10271/10271 fqs=2623 <3>[ 107.410438] rcu: (t=5250 jiffies g=20109 q=58 ncpus=2) <4>[ 107.411776] CPU: 1 UID: 0 PID: 386 Comm: fuse_mnt Not tainted 6.11.0-rc6-next-20240902 #1 <4>[ 107.412663] Hardware name: linux,dummy-virt (DT) <4>[ 107.413680] pstate: 03400009 (nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) <4>[ 107.414341] pc : queued_spin_lock_slowpath+0x5c/0x440 <4>[ 107.415481] lr : _raw_spin_lock+0x74/0x90 <4>[ 107.415974] sp : ffff800080993ad0 <4>[ 107.419229] x29: ffff800080993ad0 x28: 0000000000000008 x27: fff000000635b800 <4>[ 107.421148] x26: 0000000000000000 x25: 0000000000000000 x24: ffff800080993ba0 <4>[ 107.422099] x23: ffffa8c953aa02c8 x22: ffffa8c953aa02a0 x21: 0000000000000000 <4>[ 107.423060] x20: fff0000005088330 x19: fff0000005088330 x18: 0000000000000000 <4>[ 107.424145] x17: fff057375aeca000 x16: ffffa8c9a382f930 x15: 0000000000000000 <4>[ 107.425097] x14: 0000000000000000 x13: 00000000000000d0 x12: 0000000000000000 <4>[ 107.425990] x11: 0000000000000000 x10: fff00000ff7fb7b0 x9 : ffffa8c9a382f9a4 <4>[ 107.426955] x8 : ffff800080993a38 x7 : 0000000000000000 x6 : 0000000000000001 <4>[ 107.427836] x5 : ffffa8c9a490a000 x4 : ffffa8c9a490a5c0 x3 : 0000000000000000 <4>[ 107.428777] x2 : 0000000000000002 x1 : 0000000000000000 x0 : 0000000000000001 <4>[ 107.430091] Call trace: <4>[ 107.430421] queued_spin_lock_slowpath+0x5c/0x440 <4>[ 107.431226] _raw_spin_lock+0x74/0x90 <4>[ 107.431841] fuse_iget+0x1a0/0x2b8 [fuse] <4>[ 107.433439] fuse_fill_super_common+0x344/0x468 [fuse] <4>[ 107.434320] fuse_fill_super+0x6c/0xc8 [fuse] <4>[ 107.435044] get_tree_nodev+0x78/0xc8 <4>[ 107.435656] fuse_get_tree+0xc8/0x1a0 [fuse] <4>[ 107.436133] vfs_get_tree+0x30/0x100 <4>[ 107.436927] path_mount+0x3f4/0xa70 <4>[ 107.437515] __arm64_sys_mount+0x1e0/0x2a8 <4>[ 107.438148] invoke_syscall+0x50/0x120 <4>[ 107.438760] el0_svc_common.constprop.0+0x48/0xf0 <4>[ 107.439484] do_el0_svc+0x24/0x38 <4>[ 107.440251] el0_svc+0x3c/0x108 <4>[ 107.440574] el0t_64_sync_handler+0x120/0x130 <4>[ 107.440978] el0t_64_sync+0x190/0x198 <3>[ 170.451886] rcu: INFO: rcu_preempt self-detected stall on CPU <3>[ 170.452546] rcu: 1-....: (21001 ticks this GP) idle=4d34/1/0x4000000000000000 softirq=10271/10271 fqs=10494 <3>[ 170.453323] rcu: (t=21011 jiffies g=20109 q=83 ncpus=2) <4>[ 170.454283] CPU: 1 UID: 0 PID: 386 Comm: fuse_mnt Not tainted 6.11.0-rc6-next-20240902 #1 <4>[ 170.454966] Hardware name: linux,dummy-virt (DT) <4>[ 170.455736] pstate: 03400009 (nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) <4>[ 170.456697] pc : queued_spin_lock_slowpath+0x5c/0x440 <4>[ 170.457179] lr : _raw_spin_lock+0x74/0x90 boot Log links, -------- - https://storage.tuxsuite.com/public/linaro/lkft/tests/2lWV52ERJsLvYqFnGkWoP… - https://storage.tuxsuite.com/public/linaro/lkft/tests/2lWV52ERJsLvYqFnGkWoP… metadata: ---- git describe: next-20240902 git repo: https://gitlab.com/Linaro/lkft/mirrors/next/linux-next git sha: ecc768a84f0b8e631986f9ade3118fa37852fef0 kernel config: https://storage.tuxsuite.com/public/linaro/lkft/builds/2lWV3S20oiROqoJeQxul… build url: https://storage.tuxsuite.com/public/linaro/lkft/builds/2lWV3S20oiROqoJeQxul… toolchain: gcc-13 Steps to reproduce: --------- - https://storage.tuxsuite.com/public/linaro/lkft/tests/2lWV52ERJsLvYqFnGkWoP… - https://storage.tuxsuite.com/public/linaro/lkft/tests/2lWV52ERJsLvYqFnGkWoP… -- Linaro LKFT https://lkft.linaro.org

10 months

3
2
0 0

[PATCH RESEND] selftests/futex: Order calls in futex_requeue

by Edward Liaw

Similar to fbf4dec70277 ("selftests/futex: Order calls to futex_lock_pi"), which fixed a flake in futex_lock_pi due to racing between the parent and child threads. The same issue can occur in the futex_requeue test, because it expects waiterfn to make progress to futex_wait before the parent starts to requeue. This is mitigated by the parent sleeping for WAKE_WAIT_US, but it still fails occasionally. This can be reproduced by adding a sleep in the waiterfn before futex_wait: TAP version 13 1..2 not ok 1 futex_requeue simple returned: 0 not ok 2 futex_requeue simple returned: 0 not ok 3 futex_requeue many returned: 0 not ok 4 futex_requeue many returned: 0 Instead, replace the sleep with barriers to make the sequencing explicit. Fixes: 7cb5dd8e2c8c ("selftests: futex: Add futex compare requeue test") Reviewed-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Signed-off-by: Edward Liaw <edliaw(a)google.com> --- .../selftests/futex/functional/futex_requeue.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/futex/functional/futex_requeue.c b/tools/testing/selftests/futex/functional/futex_requeue.c index 51485be6eb2f..8f7d3e8bf32a 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue.c +++ b/tools/testing/selftests/futex/functional/futex_requeue.c @@ -12,9 +12,9 @@ #define TEST_NAME "futex-requeue" #define timeout_ns 30000000 -#define WAKE_WAIT_US 10000 volatile futex_t *f1; +static pthread_barrier_t barrier; void usage(char *prog) { @@ -32,6 +32,8 @@ void *waiterfn(void *arg) to.tv_sec = 0; to.tv_nsec = timeout_ns; + pthread_barrier_wait(&barrier); + if (futex_wait(f1, *f1, &to, 0)) printf("waiter failed errno %d\n", errno); @@ -70,13 +72,15 @@ int main(int argc, char *argv[]) ksft_print_msg("%s: Test futex_requeue\n", basename(argv[0])); + pthread_barrier_init(&barrier, NULL, 2); /* * Requeue a waiter from f1 to f2, and wake f2. */ if (pthread_create(&waiter[0], NULL, waiterfn, NULL)) error("pthread_create failed\n", errno); - usleep(WAKE_WAIT_US); + pthread_barrier_wait(&barrier); + pthread_barrier_destroy(&barrier); info("Requeuing 1 futex from f1 to f2\n"); res = futex_cmp_requeue(f1, 0, &f2, 0, 1, 0); @@ -99,6 +103,7 @@ int main(int argc, char *argv[]) ksft_test_result_pass("futex_requeue simple succeeds\n"); } + pthread_barrier_init(&barrier, NULL, 11); /* * Create 10 waiters at f1. At futex_requeue, wake 3 and requeue 7. @@ -109,7 +114,8 @@ int main(int argc, char *argv[]) error("pthread_create failed\n", errno); } - usleep(WAKE_WAIT_US); + pthread_barrier_wait(&barrier); + pthread_barrier_destroy(&barrier); info("Waking 3 futexes at f1 and requeuing 7 futexes from f1 to f2\n"); res = futex_cmp_requeue(f1, 0, &f2, 3, 7, 0); -- 2.46.0.469.g59c65b2a67-goog

10 months

2
1
0 0

[PATCH net-next v2] selftests: add selftest for UDP SO_PEEK_OFF support

by Jason Xing

From: Jason Xing <kernelxing(a)tencent.com> Add the SO_PEEK_OFF selftest for UDP. In this patch, I mainly do three things: 1. rename tcp_so_peek_off.c 2. adjust for UDP protocol 3. add selftests into it Suggested-by: Jon Maloy <jmaloy(a)redhat.com> Reviewed-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Jason Xing <kernelxing(a)tencent.com> --- v2 Link: https://lore.kernel.org/all/20240901051821.94956-1-kerneljasonxing@gmail.co… 1. update .gitignore (Stanislav) 2. use connect() < 0 as the test statement (Willem) v1 Link: https://lore.kernel.org/all/9f4dd14d-fbe3-4c61-b04c-f0e6b8096d7b@redhat.com/ --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 2 +- .../{tcp_so_peek_off.c => sk_so_peek_off.c} | 91 +++++++++++-------- 3 files changed, 57 insertions(+), 37 deletions(-) rename tools/testing/selftests/net/{tcp_so_peek_off.c => sk_so_peek_off.c} (58%) diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 666ab7d9390b..923bf098e2eb 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -34,6 +34,7 @@ scm_pidfd scm_rights sk_bind_sendto_listen sk_connect_zero_addr +sk_so_peek_off socket so_incoming_cpu so_netns_cookie diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 1179e3261bef..d5029f978aa9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -80,7 +80,7 @@ TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr -TEST_GEN_PROGS += tcp_so_peek_off +TEST_GEN_PROGS += sk_so_peek_off TEST_PROGS += test_ingress_egress_chaining.sh TEST_GEN_PROGS += so_incoming_cpu TEST_PROGS += sctp_vrf.sh diff --git a/tools/testing/selftests/net/tcp_so_peek_off.c b/tools/testing/selftests/net/sk_so_peek_off.c similarity index 58% rename from tools/testing/selftests/net/tcp_so_peek_off.c rename to tools/testing/selftests/net/sk_so_peek_off.c index df8a39d9d3c3..d87dd8d8d491 100644 --- a/tools/testing/selftests/net/tcp_so_peek_off.c +++ b/tools/testing/selftests/net/sk_so_peek_off.c @@ -10,37 +10,41 @@ #include <arpa/inet.h> #include "../kselftest.h" -static char *afstr(int af) +static char *afstr(int af, int proto) { - return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6"; + if (proto == IPPROTO_TCP) + return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6"; + else + return af == AF_INET ? "UDP/IPv4" : "UDP/IPv6"; } -int tcp_peek_offset_probe(sa_family_t af) +int sk_peek_offset_probe(sa_family_t af, int proto) { + int type = (proto == IPPROTO_TCP ? SOCK_STREAM : SOCK_DGRAM); int optv = 0; int ret = 0; int s; - s = socket(af, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP); + s = socket(af, type, proto); if (s < 0) { ksft_perror("Temporary TCP socket creation failed"); } else { if (!setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &optv, sizeof(int))) ret = 1; else - printf("%s does not support SO_PEEK_OFF\n", afstr(af)); + printf("%s does not support SO_PEEK_OFF\n", afstr(af, proto)); close(s); } return ret; } -static void tcp_peek_offset_set(int s, int offset) +static void sk_peek_offset_set(int s, int offset) { if (setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, sizeof(offset))) ksft_perror("Failed to set SO_PEEK_OFF value\n"); } -static int tcp_peek_offset_get(int s) +static int sk_peek_offset_get(int s) { int offset; socklen_t len = sizeof(offset); @@ -50,8 +54,9 @@ static int tcp_peek_offset_get(int s) return offset; } -static int tcp_peek_offset_test(sa_family_t af) +static int sk_peek_offset_test(sa_family_t af, int proto) { + int type = (proto == IPPROTO_TCP ? SOCK_STREAM : SOCK_DGRAM); union { struct sockaddr sa; struct sockaddr_in a4; @@ -62,13 +67,13 @@ static int tcp_peek_offset_test(sa_family_t af) int recv_sock = 0; int offset = 0; ssize_t len; - char buf; + char buf[2]; memset(&a, 0, sizeof(a)); a.sa.sa_family = af; - s[0] = socket(af, SOCK_STREAM, IPPROTO_TCP); - s[1] = socket(af, SOCK_STREAM | SOCK_NONBLOCK, IPPROTO_TCP); + s[0] = recv_sock = socket(af, type, proto); + s[1] = socket(af, type, proto); if (s[0] < 0 || s[1] < 0) { ksft_perror("Temporary socket creation failed\n"); @@ -82,76 +87,78 @@ static int tcp_peek_offset_test(sa_family_t af) ksft_perror("Temporary socket getsockname() failed\n"); goto out; } - if (listen(s[0], 0) < 0) { + if (proto == IPPROTO_TCP && listen(s[0], 0) < 0) { ksft_perror("Temporary socket listen() failed\n"); goto out; } - if (connect(s[1], &a.sa, sizeof(a)) >= 0 || errno != EINPROGRESS) { + if (connect(s[1], &a.sa, sizeof(a)) < 0) { ksft_perror("Temporary socket connect() failed\n"); goto out; } - recv_sock = accept(s[0], NULL, NULL); - if (recv_sock <= 0) { - ksft_perror("Temporary socket accept() failed\n"); - goto out; + if (proto == IPPROTO_TCP) { + recv_sock = accept(s[0], NULL, NULL); + if (recv_sock <= 0) { + ksft_perror("Temporary socket accept() failed\n"); + goto out; + } } /* Some basic tests of getting/setting offset */ - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != -1) { ksft_perror("Initial value of socket offset not -1\n"); goto out; } - tcp_peek_offset_set(recv_sock, 0); - offset = tcp_peek_offset_get(recv_sock); + sk_peek_offset_set(recv_sock, 0); + offset = sk_peek_offset_get(recv_sock); if (offset != 0) { ksft_perror("Failed to set socket offset to 0\n"); goto out; } /* Transfer a message */ - if (send(s[1], (char *)("ab"), 2, 0) <= 0 || errno != EINPROGRESS) { + if (send(s[1], (char *)("ab"), 2, 0) != 2) { ksft_perror("Temporary probe socket send() failed\n"); goto out; } /* Read first byte */ - len = recv(recv_sock, &buf, 1, MSG_PEEK); - if (len != 1 || buf != 'a') { + len = recv(recv_sock, buf, 1, MSG_PEEK); + if (len != 1 || buf[0] != 'a') { ksft_perror("Failed to read first byte of message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 1) { ksft_perror("Offset not forwarded correctly at first byte\n"); goto out; } /* Try to read beyond last byte */ - len = recv(recv_sock, &buf, 2, MSG_PEEK); - if (len != 1 || buf != 'b') { + len = recv(recv_sock, buf, 2, MSG_PEEK); + if (len != 1 || buf[0] != 'b') { ksft_perror("Failed to read last byte of message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 2) { ksft_perror("Offset not forwarded correctly at last byte\n"); goto out; } /* Flush message */ - len = recv(recv_sock, NULL, 2, MSG_TRUNC); + len = recv(recv_sock, buf, 2, MSG_TRUNC); if (len != 2) { ksft_perror("Failed to flush message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 0) { ksft_perror("Offset not reverted correctly after flush\n"); goto out; } - printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af)); + printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af, proto)); res = 1; out: - if (recv_sock >= 0) + if (proto == IPPROTO_TCP && recv_sock >= 0) close(recv_sock); if (s[1] >= 0) close(s[1]); @@ -160,24 +167,36 @@ static int tcp_peek_offset_test(sa_family_t af) return res; } -int main(void) +static int do_test(int proto) { int res4, res6; - res4 = tcp_peek_offset_probe(AF_INET); - res6 = tcp_peek_offset_probe(AF_INET6); + res4 = sk_peek_offset_probe(AF_INET, proto); + res6 = sk_peek_offset_probe(AF_INET6, proto); if (!res4 && !res6) return KSFT_SKIP; if (res4) - res4 = tcp_peek_offset_test(AF_INET); + res4 = sk_peek_offset_test(AF_INET, proto); if (res6) - res6 = tcp_peek_offset_test(AF_INET6); + res6 = sk_peek_offset_test(AF_INET6, proto); if (!res4 || !res6) return KSFT_FAIL; return KSFT_PASS; } + +int main(void) +{ + int restcp, resudp; + + restcp = do_test(IPPROTO_TCP); + resudp = do_test(IPPROTO_UDP); + if (restcp == KSFT_FAIL || resudp == KSFT_FAIL) + return KSFT_FAIL; + + return KSFT_PASS; +} -- 2.37.3

10 months

2
1
0 0

[PATCH] selftests: vDSO: enable partial vdso_test_getrandom bench

by Christophe Leroy

In order to use vdso_test_getrandom with analysis tools like 'perf' it can be useful to perform only one kind of test, for instead only vdso. Add an optional argument that allows telling which of the three API you want to benchmark. Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> --- .../selftests/vDSO/vdso_test_getrandom.c | 122 +++++++++++------- 1 file changed, 73 insertions(+), 49 deletions(-) diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index 8866b65a4605..c38210ac8dc5 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -46,6 +46,10 @@ static struct { .lock = PTHREAD_MUTEX_INITIALIZER }; +#define VDSO_TEST_VDSO 0x1 +#define VDSO_TEST_LIBC 0x2 +#define VDSO_TEST_SYSCALL 0x4 + static void *vgetrandom_get_state(void) { void *state = NULL; @@ -173,60 +177,72 @@ static void *test_syscall_getrandom(void *ctx) return NULL; } -static void bench_single(void) +static void bench_single(int tests) { struct timespec start, end, diff; - clock_gettime(CLOCK_MONOTONIC, &start); - test_vdso_getrandom(NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" vdso: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); - - clock_gettime(CLOCK_MONOTONIC, &start); - test_libc_getrandom(NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" libc: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); - - clock_gettime(CLOCK_MONOTONIC, &start); - test_syscall_getrandom(NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf("syscall: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + if (tests & VDSO_TEST_VDSO) { + clock_gettime(CLOCK_MONOTONIC, &start); + test_vdso_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" vdso: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + } + + if (tests & VDSO_TEST_LIBC) { + clock_gettime(CLOCK_MONOTONIC, &start); + test_libc_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" libc: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + } + + if (tests & VDSO_TEST_SYSCALL) { + clock_gettime(CLOCK_MONOTONIC, &start); + test_syscall_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf("syscall: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + } } -static void bench_multi(void) +static void bench_multi(int tests) { struct timespec start, end, diff; pthread_t threads[THREADS]; - clock_gettime(CLOCK_MONOTONIC, &start); - for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) == 0); - for (size_t i = 0; i < THREADS; ++i) - pthread_join(threads[i], NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" vdso: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); - - clock_gettime(CLOCK_MONOTONIC, &start); - for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) == 0); - for (size_t i = 0; i < THREADS; ++i) - pthread_join(threads[i], NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" libc: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); - - clock_gettime(CLOCK_MONOTONIC, &start); - for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) == 0); - for (size_t i = 0; i < THREADS; ++i) - pthread_join(threads[i], NULL); - clock_gettime(CLOCK_MONOTONIC, &end); - timespecsub(&end, &start, &diff); - printf(" syscall: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + if (tests & VDSO_TEST_VDSO) { + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" vdso: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + } + + if (tests & VDSO_TEST_LIBC) { + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" libc: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + } + + if (tests & VDSO_TEST_SYSCALL) { + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" syscall: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + } } static void fill(void) @@ -255,11 +271,13 @@ static void kselftest(void) static void usage(const char *argv0) { - fprintf(stderr, "Usage: %s [bench-single|bench-multi|fill]\n", argv0); + fprintf(stderr, "Usage: %s [bench-single|bench-multi|fill [vdso|libc|syscall]]\n", argv0); } int main(int argc, char *argv[]) { + int tests = VDSO_TEST_VDSO | VDSO_TEST_LIBC | VDSO_TEST_SYSCALL; + vgetrandom_init(); if (argc == 1) { @@ -267,14 +285,20 @@ int main(int argc, char *argv[]) return 0; } - if (argc != 2) { + if (argc == 3 && !strcmp(argv[2], "vdso")) { + tests = VDSO_TEST_VDSO; + } else if (argc == 3 && !strcmp(argv[2], "libc")) { + tests = VDSO_TEST_LIBC; + } else if (argc == 3 && !strcmp(argv[2], "syscall")) { + tests = VDSO_TEST_SYSCALL; + } else if (argc != 2) { usage(argv[0]); return 1; } if (!strcmp(argv[1], "bench-single")) - bench_single(); + bench_single(tests); else if (!strcmp(argv[1], "bench-multi")) - bench_multi(); + bench_multi(tests); else if (!strcmp(argv[1], "fill")) fill(); else { -- 2.44.0

10 months

1
0
0 0

[PATCH HID 0/7] HID: bpf: add a new hook to control hid-generic

by Benjamin Tissoires

This is a slight change from the fundamentals of HID-BPF. In theory, HID-BPF is abstract to the kernel itself, and makes only changes at the HID level (through report descriptors or events emitted to/from the device). However, we have seen a few use cases where HID-BPF might interact with the running kernel when the target device is already handled by a specific device. For example, the XP-Pen/Huion/UC-Logic tablets are handled by hid-uclogic but this driver is also doing a report descriptor fixup without checking if the device has already been fixed by HID-BPF. In the same way, another recent example[0] was when a cheap foot pedal is used and tricks iPhones and Windows machines by presenting itself as a known Apple wireless keyboard. The problem is that this fake keyboard is not presenting a compatible report descriptor and hid-core merges all device nodes together making libinput ignore the keyboard part for historical reasons. Last, there has been a long standing request to allow to disable the input part of a given gamepad while SDL or Steam opens the device through hidraw. This series aims at tackling both of these problems: - first we had a new hook `hid_bpf_driver_probe` which allows the BPF program to decide if the curently probed driver should be used or not - then this same hook can also change the ->driver_data of the struct hid_device_id argument, and we teach hid-generic to use that field as the connect mask. Basically, it means that when we insert a BPF program to fix a device, we can force hid-generic to handle the device, and thus preventing any other kernel driver to tamper with our device. We can also selectively decide to export the hidraw or input nodes when using hid-generic. In the SDL/Steam use case, this would means that the gaming application will load one BPF program per input device it wants to open through hidraw, that BPF program reassigns the input device to hid-generic and disables hid-input, then it can open the new hidraw node. Once that program terminates, the BPF program is removed (either automatically because no-one has the fd of the links open, or manually by SDL/Steam), and the normal driver rebinds to the HID device, restoring full input functionality. This branch is on top of the for-6.12/hidraw branch of hid.git, mainly because that branch saw some selftests/hid changes. [0] https://gitlab.freedesktop.org/libinput/libinput/-/issues/1014 Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org> --- Benjamin Tissoires (7): selftests/hid: add dependency on hid_common.h selftests/hid: cleanup C tests by adding a common struct uhid_device selftests/hid: allow to parametrize bus/vid/pid/rdesc on the test device HID: bpf: allow BPF programs to force using hid-generic selftests/hid: add test for assigning a given device to hid-generic HID: bpf: Allow to control the connect mask of hid-generic from BPF selftests/hid: add test to disable hid-input Documentation/hid/hid-bpf.rst | 2 +- drivers/hid/bpf/hid_bpf_dispatch.c | 31 ++++ drivers/hid/bpf/hid_bpf_struct_ops.c | 4 + drivers/hid/hid-core.c | 18 +- drivers/hid/hid-generic.c | 5 +- include/linux/hid_bpf.h | 40 ++++ tools/testing/selftests/hid/Makefile | 2 +- tools/testing/selftests/hid/hid_bpf.c | 205 ++++++++++++++++----- tools/testing/selftests/hid/hid_common.h | 112 +++++++---- tools/testing/selftests/hid/hidraw.c | 36 +--- tools/testing/selftests/hid/progs/hid.c | 31 ++++ .../testing/selftests/hid/progs/hid_bpf_helpers.h | 4 + 12 files changed, 372 insertions(+), 118 deletions(-) --- base-commit: 321f7798cfb8d834ae0ed0d467c8bf46804243f9 change-id: 20240829-hid-bpf-hid-generic-61579f5b5945 Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

10 months

2
12
0 0

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.11-rc1-17-gb4bcdff7e839)

by kernelci.org bot

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.11-rc1-17-gb4bcdff7e839) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-17-gb4… Test: kselftest-seccomp Tree: kselftest Branch: next Describe: v6.11-rc1-17-gb4bcdff7e839 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: b4bcdff7e839237d89a2aa15b6042b96b0240ac4 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66d7b13e6922285319c8685f Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-17-gb4bcdff7e839/arm… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-17-gb4bcdff7e839/arm… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-seccomp.login: https://kernelci.org/test/case/id/66d7b13e6922285319c86860 failing since 35 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

10 months

1
0
0 0

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.11-rc1-17-gb4bcdff7e839)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.11-rc1-17-gb4bcdff7e839) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-17-gb4… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v6.11-rc1-17-gb4bcdff7e839 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: b4bcdff7e839237d89a2aa15b6042b96b0240ac4 Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66d7b2a624bc264505c8685f Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-17-gb4bcdff7e839/arm… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-17-gb4bcdff7e839/arm… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/66d7b2a624bc264505c86860 failing since 35 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

10 months

1
0
0 0

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-17-gb4bcdff7e839)

by kernelci.org bot

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-17-gb4bcdff7e839) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.11-rc1-17-gb4bcd… Tree: kselftest Branch: next Git Describe: v6.11-rc1-17-gb4bcdff7e839 Git Commit: b4bcdff7e839237d89a2aa15b6042b96b0240ac4 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-12) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-12) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 --- For more info write to <info(a)kernelci.org>

10 months

1
0
0 0

[PATCH net-next 00/11] mptcp: MIB counters for MPJ TX + misc improvements

by Matthieu Baerts (NGI0)

Recently, a few issues have been discovered around the creation of additional subflows. Without these counters, it was difficult to point out the reason why some subflows were not created as expected. In patch 3, all error paths from __mptcp_subflow_connect() are covered, except the one related to the 'fully established mode', because it can only happen with the userspace PM, which will propagate the error to the userspace in this case (ENOTCONN). These new counters are also verified in the MPTCP Join selftest in patch 6. While at it, a few other patches are improving the MPTCP path-manager code ... - Patch 1: 'flush' related helpers are renamed to avoid confusions - Patch 2: directly pass known ID and flags to create a new subflow, i/o getting them later by iterating over all endpoints again ... and the MPJoin selftests: - Patch 4: reduce the number of positional parameters - Patch 5: only one line for the 'join' checks, instead of 3 - Patch 7: more explicit check names, instead of sometimes too cryptic ones: rtx, ptx, ftx, ctx, fclzrx, sum - Patch 8: specify client/server instead of 'invert' for some checks not suggesting one specific direction - Patch 9: mute errors of mptcp_connect when ran in the background - Patch 10: simplify checksum_tests by using a for-loop - Patch 11: remove 'define' re-definitions Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Geliang Tang (1): selftests: mptcp: join: simplify checksum_tests Matthieu Baerts (NGI0) (10): mptcp: pm: rename helpers linked to 'flush' mptcp: pm: reduce entries iterations on connect mptcp: MIB counters for sent MP_JOIN selftests: mptcp: join: reduce join_nr params selftests: mptcp: join: one line for join check selftests: mptcp: join: validate MPJ SYN TX MIB counters selftests: mptcp: join: more explicit check name selftests: mptcp: join: specify host being checked selftests: mptcp: join: mute errors when ran in the background selftests: mptcp: pm_nl_ctl: remove re-definition net/mptcp/mib.c | 4 + net/mptcp/mib.h | 4 + net/mptcp/pm.c | 11 - net/mptcp/pm_netlink.c | 78 ++---- net/mptcp/pm_userspace.c | 40 +-- net/mptcp/protocol.h | 16 +- net/mptcp/subflow.c | 50 +++- tools/testing/selftests/net/mptcp/mptcp_join.sh | 350 ++++++++++++++---------- tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 10 +- 9 files changed, 309 insertions(+), 254 deletions(-) --- base-commit: 221f9cce949ac8042f65b71ed1fde13b99073256 change-id: 20240902-net-next-mptcp-mib-mpjtx-misc-d80298438016 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

10 months

2
12
0 0

[PATCH v2] selftests: splice: Add usage() to splice_read.c

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Give the programmer more help information to inform the program on how to use it. Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- tools/testing/selftests/splice/splice_read.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/splice/splice_read.c b/tools/testing/selftests/splice/splice_read.c index 46dae6a25cfb..73a8bc146f97 100644 --- a/tools/testing/selftests/splice/splice_read.c +++ b/tools/testing/selftests/splice/splice_read.c @@ -9,6 +9,12 @@ #include <sys/types.h> #include <sys/stat.h> +void usage(const char *prog) +{ + fprintf(stderr, "Usage: %s INPUT [BYTES]\n", prog); + fprintf(stderr, " %s /etc/os-release | cat\n", prog); +} + int main(int argc, char *argv[]) { int fd; @@ -16,7 +22,7 @@ int main(int argc, char *argv[]) ssize_t spliced; if (argc < 2) { - fprintf(stderr, "Usage: %s INPUT [BYTES]\n", argv[0]); + usage(argv[0]); return EXIT_FAILURE; } @@ -49,6 +55,7 @@ int main(int argc, char *argv[]) size, SPLICE_F_MOVE); if (spliced < 0) { perror("splice"); + usage(argv[0]); return EXIT_FAILURE; } -- 2.46.0

10 months

2
1
0 0

[PATCH] selftests/vDSO: support DT_GNU_HASH

by Fangrui Song

glibc added support for DT_GNU_HASH in 2006 and DT_HASH has been obsoleted for more than one decade in many Linux distributions. Many vDSOs support DT_GNU_HASH. This patch adds selftests support. Signed-off-by: Fangrui Song <maskray(a)google.com> --- tools/testing/selftests/vDSO/parse_vdso.c | 105 ++++++++++++++++------ 1 file changed, 79 insertions(+), 26 deletions(-) diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index 4ae417372e9e..35cb545da13e 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -47,6 +47,7 @@ static struct vdso_info /* Symbol table */ ELF(Sym) *symtab; const char *symstrings; + ELF(Word) *gnu_hash; ELF(Word) *bucket, *chain; ELF(Word) nbucket, nchain; @@ -75,6 +76,16 @@ static unsigned long elf_hash(const char *name) return h; } +static uint32_t gnu_hash(const char *name) +{ + const unsigned char *s = (void *)name; + uint32_t h = 5381; + + for (; *s; s++) + h += h * 32 + *s; + return h; +} + void vdso_init_from_sysinfo_ehdr(uintptr_t base) { size_t i; @@ -117,6 +128,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) */ ELF(Word) *hash = 0; vdso_info.symstrings = 0; + vdso_info.gnu_hash = 0; vdso_info.symtab = 0; vdso_info.versym = 0; vdso_info.verdef = 0; @@ -137,6 +149,11 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; + case DT_GNU_HASH: + vdso_info.gnu_hash = + (ELF(Word) *)((uintptr_t)dyn[i].d_un.d_ptr + + vdso_info.load_offset); + break; case DT_VERSYM: vdso_info.versym = (ELF(Versym) *) ((uintptr_t)dyn[i].d_un.d_ptr @@ -149,17 +166,26 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) break; } } - if (!vdso_info.symstrings || !vdso_info.symtab || !hash) + if (!vdso_info.symstrings || !vdso_info.symtab || + (!hash && !vdso_info.gnu_hash)) return; /* Failed */ if (!vdso_info.verdef) vdso_info.versym = 0; /* Parse the hash table header. */ - vdso_info.nbucket = hash[0]; - vdso_info.nchain = hash[1]; - vdso_info.bucket = &hash[2]; - vdso_info.chain = &hash[vdso_info.nbucket + 2]; + if (vdso_info.gnu_hash) { + vdso_info.nbucket = vdso_info.gnu_hash[0]; + /* The bucket array is located after the header (4 uint32) and the bloom + filter (size_t array of gnu_hash[2] elements). */ + vdso_info.bucket = vdso_info.gnu_hash + 4 + + sizeof(size_t) / 4 * vdso_info.gnu_hash[2]; + } else { + vdso_info.nbucket = hash[0]; + vdso_info.nchain = hash[1]; + vdso_info.bucket = &hash[2]; + vdso_info.chain = &hash[vdso_info.nbucket + 2]; + } /* That's all we need. */ vdso_info.valid = true; @@ -203,6 +229,26 @@ static bool vdso_match_version(ELF(Versym) ver, && !strcmp(name, vdso_info.symstrings + aux->vda_name); } +static bool check_sym(ELF(Sym) *sym, ELF(Word) i, const char *name, + const char *version, unsigned long ver_hash) +{ + /* Check for a defined global or weak function w/ right name. */ + if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) + return false; + if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && + ELF64_ST_BIND(sym->st_info) != STB_WEAK) + return false; + if (strcmp(name, vdso_info.symstrings + sym->st_name)) + return false; + + /* Check symbol version. */ + if (vdso_info.versym && + !vdso_match_version(vdso_info.versym[i], version, ver_hash)) + return false; + + return true; +} + void *vdso_sym(const char *version, const char *name) { unsigned long ver_hash; @@ -210,29 +256,36 @@ void *vdso_sym(const char *version, const char *name) return 0; ver_hash = elf_hash(version); - ELF(Word) chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; + ELF(Word) i; - for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) { - ELF(Sym) *sym = &vdso_info.symtab[chain]; + if (vdso_info.gnu_hash) { + uint32_t h1 = gnu_hash(name), h2, *hashval; - /* Check for a defined global or weak function w/ right name. */ - if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) - continue; - if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && - ELF64_ST_BIND(sym->st_info) != STB_WEAK) - continue; - if (sym->st_shndx == SHN_UNDEF) - continue; - if (strcmp(name, vdso_info.symstrings + sym->st_name)) - continue; - - /* Check symbol version. */ - if (vdso_info.versym - && !vdso_match_version(vdso_info.versym[chain], - version, ver_hash)) - continue; - - return (void *)(vdso_info.load_offset + sym->st_value); + i = vdso_info.bucket[h1 % vdso_info.nbucket]; + if (i == 0) + return 0; + h1 |= 1; + hashval = vdso_info.bucket + vdso_info.nbucket + + (i - vdso_info.gnu_hash[1]); + for (;; i++) { + ELF(Sym) *sym = &vdso_info.symtab[i]; + h2 = *hashval++; + if (h1 == (h2 | 1) && + check_sym(sym, i, name, version, ver_hash)) + return (void *)(vdso_info.load_offset + + sym->st_value); + if (h2 & 1) + break; + } + } else { + i = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; + for (; i; i = vdso_info.chain[i]) { + ELF(Sym) *sym = &vdso_info.symtab[i]; + if (sym->st_shndx != SHN_UNDEF && + check_sym(sym, i, name, version, ver_hash)) + return (void *)(vdso_info.load_offset + + sym->st_value); + } } return 0; -- 2.46.0.76.ge559c4bf1a-goog

10 months

3
5
0 0

[PATCH] selftests: filesystems: fix warn_unused_result build warnings

by Abhinav Jain

Add return value checks for read & write calls in test_listmount_ns function. This patch resolves below compilation warnings: ``` statmount_test_ns.c: In function ‘test_listmount_ns’: statmount_test_ns.c:322:17: warning: ignoring return value of ‘write’ declared with attribute ‘warn_unused_result’ [-Wunused-result] statmount_test_ns.c:323:17: warning: ignoring return value of ‘read’ declared with attribute ‘warn_unused_result’ [-Wunused-result] ``` Signed-off-by: Abhinav Jain <jain.abhinav177(a)gmail.com> --- .../selftests/filesystems/statmount/statmount_test_ns.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c index e044f5fc57fd..70cb0c8b21cf 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c @@ -319,8 +319,11 @@ static void test_listmount_ns(void) * Tell our parent how many mounts we have, and then wait for it * to tell us we're done. */ - write(child_ready_pipe[1], &nr_mounts, sizeof(nr_mounts)); - read(parent_ready_pipe[0], &cval, sizeof(cval)); + if (write(child_ready_pipe[1], &nr_mounts, sizeof(nr_mounts)) != + sizeof(nr_mounts)) + ret = NSID_ERROR; + if (read(parent_ready_pipe[0], &cval, sizeof(cval)) != sizeof(cval)) + ret = NSID_ERROR; exit(NSID_PASS); } -- 2.34.1

10 months

2
2
0 0

[PATCH] selftests: net: convert comma to semicolon

by Chen Ni

Replace a comma between expression statements by a semicolon. Signed-off-by: Chen Ni <nichen(a)iscas.ac.cn> --- tools/testing/selftests/net/psock_fanout.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 1a736f700be4..4f31e92ebd96 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -165,9 +165,9 @@ static void sock_fanout_set_ebpf(int fd) attr.insns = (unsigned long) prog; attr.insn_cnt = ARRAY_SIZE(prog); attr.license = (unsigned long) "GPL"; - attr.log_buf = (unsigned long) log_buf, - attr.log_size = sizeof(log_buf), - attr.log_level = 1, + attr.log_buf = (unsigned long) log_buf; + attr.log_size = sizeof(log_buf); + attr.log_level = 1; pfd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); if (pfd < 0) { -- 2.25.1

10 months

2
1
0 0

[PATCH v3 0/3] RISC-V: mm: do not treat hint addr on mmap as the upper bound to search

by Yangyu Chen

Previous patch series[1][2] changes a mmap behavior that treats the hint address as the upper bound of the mmap address range. The motivation of the previous patch series is that some user space software may assume 48-bit address space and use higher bits to encode some information, which may collide with large virtual address space mmap may return. However, to make sv48 by default, we don't need to change the meaning of the hint address on mmap as the upper bound of the mmap address range. This behavior breaks some user space software like Chromium that gets ENOMEM error when the hint address + size is not big enough, as specified in [3]. Other ISAs with larger than 48-bit virtual address space like x86, arm64, and powerpc do not have this special mmap behavior on hint address. They all just make 48-bit / 47-bit virtual address space by default, and if a user space software wants to large virtual address space, it only need to specify a hint address larger than 48-bit / 47-bit. Thus, this patch series change mmap to use sv48 by default but does not treat the hint address as the upper bound of the mmap address range. After this patch, the behavior of mmap will align with existing behavior on other ISAs with larger than 48-bit virtual address space like x86, arm64, and powerpc. The user space software will no longer need to rewrite their code to fit with this special mmap behavior only on RISC-V. Note: Charlie also created another series [4] to completely remove the arch_get_mmap_end and arch_get_mmap_base behavior based on the hint address and size. However, this will cause programs like Go and Java, which need to store information in the higher bits of the pointer, to fail on Sv57 machines. Changes in v3: - Rebase to newest master - Changes some information in cover letter after patchset [2] - Use patch [5] to patch selftests - Link to v2: https://lore.kernel.org/linux-riscv/tencent_B2D0435BC011135736262764B511994… Changes in v2: - correct arch_get_mmap_end and arch_get_mmap_base - Add description in documentation about mmap behavior on kernel v6.6-6.7. - Improve commit message and cover letter - Rebase to newest riscv/for-next branch - Link to v1: https://lore.kernel.org/linux-riscv/tencent_F3B3B5AB1C9D704763CA423E1A41F8B… [1] https://lore.kernel.org/linux-riscv/20230809232218.849726-1-charlie@rivosin… [2] https://lore.kernel.org/linux-riscv/20240130-use_mmap_hint_address-v3-0-8a6… [3] https://lore.kernel.org/linux-riscv/MEYP282MB2312A08FF95D44014AB78411C68D2@… [4] https://lore.kernel.org/linux-riscv/20240826-riscv_mmap-v1-0-cd8962afe47f@r… [5] https://lore.kernel.org/linux-riscv/20240826-riscv_mmap-v1-2-cd8962afe47f@r… Charlie Jenkins (1): riscv: selftests: Remove mmap hint address checks Yangyu Chen (2): RISC-V: mm: not use hint addr as upper bound Documentation: riscv: correct sv57 kernel behavior Documentation/arch/riscv/vm-layout.rst | 43 ++++++++---- arch/riscv/include/asm/processor.h | 20 ++---- .../selftests/riscv/mm/mmap_bottomup.c | 2 - .../testing/selftests/riscv/mm/mmap_default.c | 2 - tools/testing/selftests/riscv/mm/mmap_test.h | 67 ------------------- 5 files changed, 36 insertions(+), 98 deletions(-) -- 2.45.2

10 months

4
9
0 0

[PATCH v3 0/3] selftests: Fix cpuid / vendor checking build issues

by Ilpo Järvinen

This series first generalizes resctrl selftest non-contiguous CAT check to not assume non-AMD vendor implies Intel. Second, it improves kselftest common parts and resctrl selftest such that the use of __cpuid_count() does not lead into a build failure (happens at least on ARM). While ARM does not currently support resctrl features, there's an ongoing work to enable resctrl support also for it on the kernel side. In any case, a common header such as kselftest.h should have a proper fallback in place for what it provides, thus it seems justified to fix this common level problem on the common level rather than e.g. disabling build for resctrl selftest for archs lacking resctrl support. I've dropped reviewed and tested by tags from the last patch due to major changes into the makefile logic. So it would be helpful if Muhammad could retest with this version. v3: - Remove "empty" wording - Also cast input parameters to void - Initialize ARCH from uname -m if not set (this might allow cleaning up some other makefiles but that is left as future work) v2: - Removed RFC from the last patch & added Fixes and tags - Fixed the error message's line splits - Noted down the reason for void casts in the stub Ilpo Järvinen (3): selftests/resctrl: Generalize non-contiguous CAT check selftests/resctrl: Always initialize ecx to avoid build warnings kselftest: Provide __cpuid_count() stub on non-x86 archs tools/testing/selftests/kselftest.h | 6 +++++ tools/testing/selftests/lib.mk | 6 +++++ tools/testing/selftests/resctrl/cat_test.c | 28 +++++++++++++--------- 3 files changed, 29 insertions(+), 11 deletions(-) -- 2.39.2

10 months

1
4
0 0

[PATCH] utimer-test: remove unused variables

by bajing

The variable i is never referenced in the code, just remove it. Signed-off-by: bajing <bajing(a)cmss.chinamobile.com> --- tools/testing/selftests/alsa/utimer-test.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/alsa/utimer-test.c b/tools/testing/selftests/alsa/utimer-test.c index 32ee3ce57721..9d2683c83ef3 100644 --- a/tools/testing/selftests/alsa/utimer-test.c +++ b/tools/testing/selftests/alsa/utimer-test.c @@ -140,7 +140,6 @@ TEST_F(timer_f, utimer) { TEST(wrong_timers_test) { int timer_dev_fd; int utimer_fd; - size_t i; struct snd_timer_uinfo wrong_timer = { .resolution = 0, .id = UTIMER_DEFAULT_ID, -- 2.33.0

10 months

1
0
0 0

[PATCH RFC 0/8] extensible syscalls: CHECK_FIELDS to allow for easier feature detection

by Aleksa Sarai

This is something that I've been thinking about for a while. We had a discussion at LPC 2020 about this[1] but the proposals suggested there never materialised. In short, it is quite difficult for userspace to detect the feature capability of syscalls at runtime. This is something a lot of programs want to do, but they are forced to create elaborate scenarios to try to figure out if a feature is supported without causing damage to the system. For the vast majority of cases, each individual feature also needs to be tested individually (because syscall results are all-or-nothing), so testing even a single syscall's feature set can easily inflate the startup time of programs. This patchset implements the fairly minimal design I proposed in this talk[2] and in some old LKML threads (though I can't find the exact references ATM). The general flow looks like: 1. Userspace will indicate to the kernel that a syscall should a be no-op by setting the top bit of the extensible struct size argument. We will almost certainly never support exabyte sized structs, so the top bits are free for us to use as makeshift flag bits. This is preferable to using the per-syscall flag field inside the structure because seccomp can easily detect the bit in the flag and allow the probe or forcefully return -EEXTSYS_NOOP. 2. The kernel will then fill the provided structure with every valid bit pattern that the current kernel understands. For flags or other bitflag-like fields, this is the set of valid flags or bits. For pointer fields or fields that take an arbitrary value, the field has every bit set (0xFF... to fill the field) to indicate that any value is valid in the field. 3. The syscall then returns -EEXTSYS_NOOP which is an errno that will only ever be used for this purpose (so userspace can be sure that the request succeeded). On older kernels, the syscall will return a different error (usually -E2BIG or -EFAULT) and userspace can do their old-fashioned checks. 4. Userspace can then check which flags and fields are supported by looking at the fields in the returned structure. Flags are checked by doing an AND with the flags field, and field support can checked by comparing to 0. In principle you could just AND the entire structure if you wanted to do this check generically without caring about the structure contents (this is what libraries might consider doing). Userspace can even find out the internal kernel structure size by passing a PAGE_SIZE buffer and seeing how many bytes are non-zero. As with copy_struct_from_user(), this is designed to be forward- and backwards- compatible. This allows programas to get a one-shot understanding of what features a syscall supports without having to do any elaborate setups or tricks to detect support for destructive features. Flags can simply be ANDed to check if they are in the supported set, and fields can just be checked to see if they are non-zero. This patchset is IMHO the simplest way we can add the ability to introspect the feature set of extensible struct (copy_struct_from_user) syscalls. It doesn't preclude the chance of a more generic mechanism being added later. The intended way of using this interface to get feature information looks something like the following (imagine that openat2 has gained a new field and a new flag in the future): static bool openat2_no_automount_supported; static bool openat2_cwd_fd_supported; int check_openat2_support(void) { int err; struct open_how how = {}; err = openat2(AT_FDCWD, ".", &how, CHECK_FIELDS | sizeof(how)); assert(err < 0); switch (errno) { case EFAULT: case E2BIG: /* Old kernel... */ check_support_the_old_way(); break; case EEXTSYS_NOOP: openat2_no_automount_supported = (how.flags & RESOLVE_NO_AUTOMOUNT); openat2_cwd_fd_supported = (how.cwd_fd != 0); break; } } [1]: https://lwn.net/Articles/830666/ [2]: https://youtu.be/ggD-eb3yPVs Signed-off-by: Aleksa Sarai <cyphar(a)cyphar.com> --- Aleksa Sarai (8): uaccess: add copy_struct_to_user helper sched_getattr: port to copy_struct_to_user openat2: explicitly return -E2BIG for (usize > PAGE_SIZE) openat2: add CHECK_FIELDS flag to usize argument clone3: add CHECK_FIELDS flag to usize argument selftests: openat2: add 0xFF poisoned data after misaligned struct selftests: openat2: add CHECK_FIELDS selftests selftests: clone3: add CHECK_FIELDS selftests fs/open.c | 17 ++ include/linux/uaccess.h | 98 +++++++++ include/uapi/asm-generic/errno.h | 3 + include/uapi/linux/openat2.h | 2 + kernel/fork.c | 33 ++- kernel/sched/syscalls.c | 42 +--- tools/testing/selftests/clone3/.gitignore | 1 + tools/testing/selftests/clone3/Makefile | 2 +- .../testing/selftests/clone3/clone3_check_fields.c | 229 +++++++++++++++++++++ tools/testing/selftests/openat2/openat2_test.c | 126 +++++++++++- 10 files changed, 504 insertions(+), 49 deletions(-) --- base-commit: 431c1646e1f86b949fa3685efc50b660a364c2b6 change-id: 20240803-extensible-structs-check_fields-a47e94cef691 Best regards, -- Aleksa Sarai <cyphar(a)cyphar.com>

10 months

2
13
0 0

[PATCH] selftests/bpf: Fix procmap_query()'s params mismatch and compilation warning

by Yuan Chen

From: Yuan Chen <chenyuan(a)kylinos.cn> When the PROCMAP_QUERY is not defined, a compilation error occurs due to the mismatch of the procmap_query()'s params, procmap_query() only be called in the file where the function is defined, modify the params so they can match. We get a warning when build samples/bpf: trace_helpers.c:252:5: warning: no previous prototype for ‘procmap_query’ [-Wmissing-prototypes] 252 | int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) | ^~~~~~~~~~~~~ As this function is only used in the file, mark it as 'static'. Signed-off-by: Yuan Chen <chenyuan(a)kylinos.cn> --- tools/testing/selftests/bpf/trace_helpers.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 1bfd881c0e07..2d742fdac6b9 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -249,7 +249,7 @@ int kallsyms_find(const char *sym, unsigned long long *addr) #ifdef PROCMAP_QUERY int env_verbosity __weak = 0; -int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) +static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { char path_buf[PATH_MAX], build_id_buf[20]; struct procmap_query q; @@ -293,7 +293,7 @@ int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, si return 0; } #else -int procmap_query(int fd, const void *addr, size_t *start, size_t *offset, int *flags) +static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { return -EOPNOTSUPP; } -- 2.46.0

10 months

2
1
0 0

[PATCH 0/6] Extend pmu_counters_test to AMD CPUs

by Colton Lewis

(I was positive I had sent this already, but I couldn't find it on the mailing list to reply to and ask for reviews.) Extend pmu_counters_test to AMD CPUs. As the AMD PMU is quite different from Intel with different events and feature sets, this series introduces a new code path to test it, specifically focusing on the core counters including the PerfCtrExtCore and PerfMonV2 features. Northbridge counters and cache counters exist, but are not as important and can be deferred to a later series. The first patch is a bug fix that could be submitted separately. The series has been tested on both Intel and AMD machines, but I have not found an AMD machine old enough to lack PerfCtrExtCore. I have made efforts that no part of the code has any dependency on its presence. I am aware of similar work in this direction done by Jinrong Liang [1]. He told me he is not working on it currently and I am not intruding by making my own submission. [1] https://lore.kernel.org/kvm/20231121115457.76269-1-cloudliang@tencent.com/ Colton Lewis (6): KVM: x86: selftests: Fix typos in macro variable use KVM: x86: selftests: Define AMD PMU CPUID leaves KVM: x86: selftests: Set up AMD VM in pmu_counters_test KVM: x86: selftests: Test read/write core counters KVM: x86: selftests: Test core events KVM: x86: selftests: Test PerfMonV2 .../selftests/kvm/include/x86_64/processor.h | 7 + .../selftests/kvm/x86_64/pmu_counters_test.c | 267 ++++++++++++++++-- 2 files changed, 249 insertions(+), 25 deletions(-) -- 2.46.0.76.ge559c4bf1a-goog

10 months

3
20
0 0

[PATCH net-next] selftests: add selftest for UDP SO_PEEK_OFF support

by Jason Xing

From: Jason Xing <kernelxing(a)tencent.com> Add the SO_PEEK_OFF selftest for UDP. In this patch, I mainly do three things: 1. rename tcp_so_peek_off.c 2. adjust for UDP protocol 3. add selftests into it Suggested-by: Jon Maloy <jmaloy(a)redhat.com> Signed-off-by: Jason Xing <kernelxing(a)tencent.com> --- Link: https://lore.kernel.org/all/9f4dd14d-fbe3-4c61-b04c-f0e6b8096d7b@redhat.com/ --- tools/testing/selftests/net/Makefile | 2 +- .../{tcp_so_peek_off.c => sk_so_peek_off.c} | 91 +++++++++++-------- 2 files changed, 56 insertions(+), 37 deletions(-) rename tools/testing/selftests/net/{tcp_so_peek_off.c => sk_so_peek_off.c} (58%) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 1179e3261bef..d5029f978aa9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -80,7 +80,7 @@ TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr -TEST_GEN_PROGS += tcp_so_peek_off +TEST_GEN_PROGS += sk_so_peek_off TEST_PROGS += test_ingress_egress_chaining.sh TEST_GEN_PROGS += so_incoming_cpu TEST_PROGS += sctp_vrf.sh diff --git a/tools/testing/selftests/net/tcp_so_peek_off.c b/tools/testing/selftests/net/sk_so_peek_off.c similarity index 58% rename from tools/testing/selftests/net/tcp_so_peek_off.c rename to tools/testing/selftests/net/sk_so_peek_off.c index df8a39d9d3c3..870a890138c4 100644 --- a/tools/testing/selftests/net/tcp_so_peek_off.c +++ b/tools/testing/selftests/net/sk_so_peek_off.c @@ -10,37 +10,41 @@ #include <arpa/inet.h> #include "../kselftest.h" -static char *afstr(int af) +static char *afstr(int af, int proto) { - return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6"; + if (proto == IPPROTO_TCP) + return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6"; + else + return af == AF_INET ? "UDP/IPv4" : "UDP/IPv6"; } -int tcp_peek_offset_probe(sa_family_t af) +int sk_peek_offset_probe(sa_family_t af, int proto) { + int type = (proto == IPPROTO_TCP ? SOCK_STREAM : SOCK_DGRAM); int optv = 0; int ret = 0; int s; - s = socket(af, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP); + s = socket(af, type, proto); if (s < 0) { ksft_perror("Temporary TCP socket creation failed"); } else { if (!setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &optv, sizeof(int))) ret = 1; else - printf("%s does not support SO_PEEK_OFF\n", afstr(af)); + printf("%s does not support SO_PEEK_OFF\n", afstr(af, proto)); close(s); } return ret; } -static void tcp_peek_offset_set(int s, int offset) +static void sk_peek_offset_set(int s, int offset) { if (setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, sizeof(offset))) ksft_perror("Failed to set SO_PEEK_OFF value\n"); } -static int tcp_peek_offset_get(int s) +static int sk_peek_offset_get(int s) { int offset; socklen_t len = sizeof(offset); @@ -50,8 +54,9 @@ static int tcp_peek_offset_get(int s) return offset; } -static int tcp_peek_offset_test(sa_family_t af) +static int sk_peek_offset_test(sa_family_t af, int proto) { + int type = (proto == IPPROTO_TCP ? SOCK_STREAM : SOCK_DGRAM); union { struct sockaddr sa; struct sockaddr_in a4; @@ -62,13 +67,13 @@ static int tcp_peek_offset_test(sa_family_t af) int recv_sock = 0; int offset = 0; ssize_t len; - char buf; + char buf[2]; memset(&a, 0, sizeof(a)); a.sa.sa_family = af; - s[0] = socket(af, SOCK_STREAM, IPPROTO_TCP); - s[1] = socket(af, SOCK_STREAM | SOCK_NONBLOCK, IPPROTO_TCP); + s[0] = recv_sock = socket(af, type, proto); + s[1] = socket(af, type, proto); if (s[0] < 0 || s[1] < 0) { ksft_perror("Temporary socket creation failed\n"); @@ -82,76 +87,78 @@ static int tcp_peek_offset_test(sa_family_t af) ksft_perror("Temporary socket getsockname() failed\n"); goto out; } - if (listen(s[0], 0) < 0) { + if (proto == IPPROTO_TCP && listen(s[0], 0) < 0) { ksft_perror("Temporary socket listen() failed\n"); goto out; } - if (connect(s[1], &a.sa, sizeof(a)) >= 0 || errno != EINPROGRESS) { + if (connect(s[1], &a.sa, sizeof(a))) { ksft_perror("Temporary socket connect() failed\n"); goto out; } - recv_sock = accept(s[0], NULL, NULL); - if (recv_sock <= 0) { - ksft_perror("Temporary socket accept() failed\n"); - goto out; + if (proto == IPPROTO_TCP) { + recv_sock = accept(s[0], NULL, NULL); + if (recv_sock <= 0) { + ksft_perror("Temporary socket accept() failed\n"); + goto out; + } } /* Some basic tests of getting/setting offset */ - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != -1) { ksft_perror("Initial value of socket offset not -1\n"); goto out; } - tcp_peek_offset_set(recv_sock, 0); - offset = tcp_peek_offset_get(recv_sock); + sk_peek_offset_set(recv_sock, 0); + offset = sk_peek_offset_get(recv_sock); if (offset != 0) { ksft_perror("Failed to set socket offset to 0\n"); goto out; } /* Transfer a message */ - if (send(s[1], (char *)("ab"), 2, 0) <= 0 || errno != EINPROGRESS) { + if (send(s[1], (char *)("ab"), 2, 0) != 2) { ksft_perror("Temporary probe socket send() failed\n"); goto out; } /* Read first byte */ - len = recv(recv_sock, &buf, 1, MSG_PEEK); - if (len != 1 || buf != 'a') { + len = recv(recv_sock, buf, 1, MSG_PEEK); + if (len != 1 || buf[0] != 'a') { ksft_perror("Failed to read first byte of message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 1) { ksft_perror("Offset not forwarded correctly at first byte\n"); goto out; } /* Try to read beyond last byte */ - len = recv(recv_sock, &buf, 2, MSG_PEEK); - if (len != 1 || buf != 'b') { + len = recv(recv_sock, buf, 2, MSG_PEEK); + if (len != 1 || buf[0] != 'b') { ksft_perror("Failed to read last byte of message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 2) { ksft_perror("Offset not forwarded correctly at last byte\n"); goto out; } /* Flush message */ - len = recv(recv_sock, NULL, 2, MSG_TRUNC); + len = recv(recv_sock, buf, 2, MSG_TRUNC); if (len != 2) { ksft_perror("Failed to flush message\n"); goto out; } - offset = tcp_peek_offset_get(recv_sock); + offset = sk_peek_offset_get(recv_sock); if (offset != 0) { ksft_perror("Offset not reverted correctly after flush\n"); goto out; } - printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af)); + printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af, proto)); res = 1; out: - if (recv_sock >= 0) + if (proto == IPPROTO_TCP && recv_sock >= 0) close(recv_sock); if (s[1] >= 0) close(s[1]); @@ -160,24 +167,36 @@ static int tcp_peek_offset_test(sa_family_t af) return res; } -int main(void) +static int do_test(int proto) { int res4, res6; - res4 = tcp_peek_offset_probe(AF_INET); - res6 = tcp_peek_offset_probe(AF_INET6); + res4 = sk_peek_offset_probe(AF_INET, proto); + res6 = sk_peek_offset_probe(AF_INET6, proto); if (!res4 && !res6) return KSFT_SKIP; if (res4) - res4 = tcp_peek_offset_test(AF_INET); + res4 = sk_peek_offset_test(AF_INET, proto); if (res6) - res6 = tcp_peek_offset_test(AF_INET6); + res6 = sk_peek_offset_test(AF_INET6, proto); if (!res4 || !res6) return KSFT_FAIL; return KSFT_PASS; } + +int main(void) +{ + int restcp, resudp; + + restcp = do_test(IPPROTO_TCP); + resudp = do_test(IPPROTO_UDP); + if (restcp == KSFT_FAIL || resudp == KSFT_FAIL) + return KSFT_FAIL; + + return KSFT_PASS; +} -- 2.37.3

10 months

3
5
0 0

[PATCH v4 0/5] Wire up getrandom() vDSO implementation on powerpc

by Christophe Leroy

This series wires up getrandom() vDSO implementation on powerpc. Tested on PPC32 on real hardware. Tested on PPC64 (both BE and LE) on QEMU: Performance on powerpc 885: ~# ./vdso_test_getrandom bench-single vdso: 25000000 times in 62.938002291 seconds libc: 25000000 times in 535.581916866 seconds syscall: 25000000 times in 531.525042806 seconds Performance on powerpc 8321: ~# ./vdso_test_getrandom bench-single vdso: 25000000 times in 16.899318858 seconds libc: 25000000 times in 131.050596522 seconds syscall: 25000000 times in 129.794790389 seconds Performance on QEMU pseries: ~ # ./vdso_test_getrandom bench-single vdso: 25000000 times in 4.977777162 seconds libc: 25000000 times in 75.516749981 seconds syscall: 25000000 times in 86.842242014 seconds Changes in v4: - Rebased on recent random git tree (963233ff0133) (The new tree includes selftests fixes) - Read/write counter in native byte order - Don't use anymore compat macros to write output - Fixed selftests build failure with patch 4 (without patch 5) on little endian on PPC64 - Implement a __kernel_getrandom() stub returning ENOSYS on ppc64 in patch 4 (without patch 5) to make selftests happy. Changes in v3: - Rebased on recent random git tree (0c7e00e22c21) - Fixed build failures reported by robots around VM_DROPPABLE - Fixed crash on PPC64 due to clobbered r13 by not using r13 anymore (saving it was not enough for signals). - Split final patch in two, first for PPC32, second for PPC64 - Moved selftest fixes out of this series Changes in v2: - Define VM_DROPPABLE for powerpc/32 - Fixes generic vDSO getrandom headers to enable CONFIG_COMPAT build. - Fixed size of generation counter - Fixed selftests to work on non x86 architectures Christophe Leroy (5): mm: Define VM_DROPPABLE for powerpc/32 powerpc/vdso32: Add crtsavres powerpc/vdso: Refactor CFLAGS for CVDSO build powerpc/vdso: Wire up getrandom() vDSO implementation on PPC32 powerpc/vdso: Wire up getrandom() vDSO implementation on PPC64 arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/mman.h | 2 +- arch/powerpc/include/asm/vdso/getrandom.h | 54 ++++ arch/powerpc/include/asm/vdso/vsyscall.h | 6 + arch/powerpc/include/asm/vdso_datapage.h | 2 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/vdso/Makefile | 57 ++-- arch/powerpc/kernel/vdso/getrandom.S | 58 ++++ arch/powerpc/kernel/vdso/gettimeofday.S | 13 - arch/powerpc/kernel/vdso/vdso32.lds.S | 1 + arch/powerpc/kernel/vdso/vdso64.lds.S | 1 + arch/powerpc/kernel/vdso/vgetrandom-chacha.S | 320 +++++++++++++++++++ arch/powerpc/kernel/vdso/vgetrandom.c | 14 + fs/proc/task_mmu.c | 4 +- include/linux/mm.h | 4 +- include/trace/events/mmflags.h | 4 +- tools/testing/selftests/vDSO/Makefile | 2 +- 17 files changed, 501 insertions(+), 43 deletions(-) create mode 100644 arch/powerpc/include/asm/vdso/getrandom.h create mode 100644 arch/powerpc/kernel/vdso/getrandom.S create mode 100644 arch/powerpc/kernel/vdso/vgetrandom-chacha.S create mode 100644 arch/powerpc/kernel/vdso/vgetrandom.c -- 2.44.0

10 months

2
14
0 0

[PATCH net-next v17 11/14] mm: page_frag: add testing for the newly added prepare API

by Yunsheng Lin

Add testing for the newly added prepare API, for both aligned and non-aligned API, also probe API is also tested along with prepare API. CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> --- .../selftests/mm/page_frag/page_frag_test.c | 66 +++++++++++++++++-- tools/testing/selftests/mm/run_vmtests.sh | 4 ++ tools/testing/selftests/mm/test_page_frag.sh | 31 +++++++++ 3 files changed, 96 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index a4bd543d6950..7cfa896f69cb 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -27,6 +27,10 @@ static bool test_align; module_param(test_align, bool, 0); MODULE_PARM_DESC(test_align, "use align API for testing"); +static bool test_prepare; +module_param(test_prepare, bool, 0); +MODULE_PARM_DESC(test_prepare, "use prepare API for testing"); + static int test_alloc_len = 2048; module_param(test_alloc_len, int, 0); MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); @@ -67,6 +71,18 @@ static int page_frag_pop_thread(void *arg) return 0; } +static void frag_frag_test_commit(struct page_frag_cache *nc, + struct page_frag *prepare_pfrag, + struct page_frag *probe_pfrag, + unsigned int used_sz) +{ + WARN_ON_ONCE(prepare_pfrag->page != probe_pfrag->page || + prepare_pfrag->offset != probe_pfrag->offset || + prepare_pfrag->size != probe_pfrag->size); + + page_frag_commit(nc, prepare_pfrag, used_sz); +} + static int page_frag_push_thread(void *arg) { struct ptr_ring *ring = arg; @@ -80,13 +96,52 @@ static int page_frag_push_thread(void *arg) int ret; if (test_align) { - va = page_frag_alloc_align(&test_nc, test_alloc_len, - GFP_KERNEL, SMP_CACHE_BYTES); + if (test_prepare) { + struct page_frag prepare_frag, probe_frag; + void *probe_va; + + va = page_frag_alloc_refill_prepare_align(&test_nc, + test_alloc_len, + &prepare_frag, + GFP_KERNEL, + SMP_CACHE_BYTES); + + probe_va = __page_frag_alloc_refill_probe_align(&test_nc, + test_alloc_len, + &probe_frag, + -SMP_CACHE_BYTES); + WARN_ON_ONCE(va != probe_va); + + if (likely(va)) + frag_frag_test_commit(&test_nc, &prepare_frag, + &probe_frag, test_alloc_len); + } else { + va = page_frag_alloc_align(&test_nc, + test_alloc_len, + GFP_KERNEL, + SMP_CACHE_BYTES); + } WARN_ONCE((unsigned long)va & (SMP_CACHE_BYTES - 1), "unaligned va returned\n"); } else { - va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + if (test_prepare) { + struct page_frag prepare_frag, probe_frag; + void *probe_va; + + va = page_frag_alloc_refill_prepare(&test_nc, test_alloc_len, + &prepare_frag, GFP_KERNEL); + + probe_va = page_frag_alloc_refill_probe(&test_nc, test_alloc_len, + &probe_frag); + + WARN_ON_ONCE(va != probe_va); + if (likely(va)) + frag_frag_test_commit(&test_nc, &prepare_frag, + &probe_frag, test_alloc_len); + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } } if (!va) @@ -149,8 +204,9 @@ static int __init page_frag_test_init(void) wait_for_completion(&wait); duration = (u64)ktime_us_delta(ktime_get(), start); - pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, - test_align ? "aligned" : "non-aligned", duration); + pr_info("%d of iterations for %s %s API testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", + test_prepare ? "prepare" : "alloc", duration); ptr_ring_cleanup(&ptr_ring, NULL); page_frag_cache_drain(&test_nc); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 96fd470b9f51..e4a36231bbea 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -464,6 +464,10 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh aligned CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned_prepare + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned_prepare + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh index d2b0734a90b5..3bc40a895d0d 100755 --- a/tools/testing/selftests/mm/test_page_frag.sh +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -36,6 +36,8 @@ ksft_skip=4 SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" +NONALIGNED_PREPARE_PARAM="$NONALIGNED_PARAM test_prepare=1" +ALIGNED_PREPARE_PARAM="$ALIGNED_PARAM test_prepare=1" check_test_requirements() { @@ -74,6 +76,24 @@ run_aligned_check() echo "Check the kernel ring buffer to see the summary." } +run_nonaligned_prepare_check() +{ + echo "Run performance tests to evaluate how fast nonaligned prepare API is." + + insmod $DRIVER $NONALIGNED_PREPARE_PARAM > /dev/null 2>&1 + echo "Done." + echo "Ccheck the kernel ring buffer to see the summary." +} + +run_aligned_prepare_check() +{ + echo "Run performance tests to evaluate how fast aligned prepare API is." + + insmod $DRIVER $ALIGNED_PREPARE_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + run_smoke_check() { echo "Run smoke test." @@ -86,6 +106,7 @@ run_smoke_check() usage() { echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "[ aligned_prepare ] | [ nonaligned_prepare ] | " echo "manual parameters" echo echo "Valid tests and parameters:" @@ -106,6 +127,12 @@ usage() echo "# Performance testing for aligned alloc API" echo "$0 aligned" echo + echo "# Performance testing for nonaligned prepare API" + echo "$0 nonaligned_prepare" + echo + echo "# Performance testing for aligned prepare API" + echo "$0 aligned_prepare" + echo exit 0 } @@ -159,6 +186,10 @@ function run_test() run_nonaligned_check elif [[ "$1" = "aligned" ]]; then run_aligned_check + elif [[ "$1" = "nonaligned_prepare" ]]; then + run_nonaligned_prepare_check + elif [[ "$1" = "aligned_prepare" ]]; then + run_aligned_prepare_check else run_manual_check $@ fi -- 2.33.0

10 months

1
0
0 0

[PATCH net-next v17 04/14] mm: page_frag: avoid caller accessing 'page_frag_cache' directly

by Yunsheng Lin

Use appropriate frag_page API instead of caller accessing 'page_frag_cache' directly. CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Reviewed-by: Alexander Duyck <alexanderduyck(a)fb.com> Acked-by: Chuck Lever <chuck.lever(a)oracle.com> --- drivers/vhost/net.c | 2 +- include/linux/page_frag_cache.h | 10 ++++++++++ net/core/skbuff.c | 6 +++--- net/rxrpc/conn_object.c | 4 +--- net/rxrpc/local_object.c | 4 +--- net/sunrpc/svcsock.c | 6 ++---- tools/testing/selftests/mm/page_frag/page_frag_test.c | 2 +- 7 files changed, 19 insertions(+), 15 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f16279351db5..9ad37c012189 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1325,7 +1325,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) vqs[VHOST_NET_VQ_RX]); f->private_data = n; - n->pf_cache.va = NULL; + page_frag_cache_init(&n->pf_cache); return 0; } diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h index 67ac8626ed9b..0a52f7a179c8 100644 --- a/include/linux/page_frag_cache.h +++ b/include/linux/page_frag_cache.h @@ -7,6 +7,16 @@ #include <linux/mm_types_task.h> #include <linux/types.h> +static inline void page_frag_cache_init(struct page_frag_cache *nc) +{ + nc->va = NULL; +} + +static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc) +{ + return !!nc->pfmemalloc; +} + void page_frag_cache_drain(struct page_frag_cache *nc); void __page_frag_cache_drain(struct page *page, unsigned int count); void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a52638363ea5..a5f8e4e0c649 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -752,14 +752,14 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); - pfmemalloc = nc->pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(nc); } else { local_bh_disable(); local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); - pfmemalloc = nc->pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(nc); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); local_bh_enable(); @@ -849,7 +849,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) len = SKB_HEAD_ALIGN(len); data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = nc->page.pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); } local_unlock_nested_bh(&napi_alloc_cache.bh_lock); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 1539d315afe7..694c4df7a1a3 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -337,9 +337,7 @@ static void rxrpc_clean_up_connection(struct work_struct *work) */ rxrpc_purge_queue(&conn->rx_queue); - if (conn->tx_data_alloc.va) - __page_frag_cache_drain(virt_to_page(conn->tx_data_alloc.va), - conn->tx_data_alloc.pagecnt_bias); + page_frag_cache_drain(&conn->tx_data_alloc); call_rcu(&conn->rcu, rxrpc_rcu_free_connection); } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 504453c688d7..a8cffe47cf01 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -452,9 +452,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local) #endif rxrpc_purge_queue(&local->rx_queue); rxrpc_purge_client_connections(local); - if (local->tx_alloc.va) - __page_frag_cache_drain(virt_to_page(local->tx_alloc.va), - local->tx_alloc.pagecnt_bias); + page_frag_cache_drain(&local->tx_alloc); } /* diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 6b3f01beb294..dcfd84cf0694 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1609,7 +1609,6 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt) static void svc_sock_free(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - struct page_frag_cache *pfc = &svsk->sk_frag_cache; struct socket *sock = svsk->sk_sock; trace_svcsock_free(svsk, sock); @@ -1619,8 +1618,7 @@ static void svc_sock_free(struct svc_xprt *xprt) sockfd_put(sock); else sock_release(sock); - if (pfc->va) - __page_frag_cache_drain(virt_to_head_page(pfc->va), - pfc->pagecnt_bias); + + page_frag_cache_drain(&svsk->sk_frag_cache); kfree(svsk); } diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index 5395a36e4030..a4bd543d6950 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -117,7 +117,7 @@ static int __init page_frag_test_init(void) u64 duration; int ret; - test_nc.va = NULL; + page_frag_cache_init(&test_nc); atomic_set(&nthreads, 2); init_completion(&wait); -- 2.33.0

10 months

1
0
0 0

[PATCH 0/2] Improve migration by backing off earlier

by Dev Jain

It was recently observed at [1] that during the folio unmapping stage of migration, when the PTEs are cleared, a racing thread faulting on that folio may increase the refcount of the folio, sleep on the folio lock (the migration path has the lock), and migration ultimately fails when asserting the actual refcount against the expected. Migration is a best effort service; the unmapping and the moving phase are wrapped around loops for retrying. The refcount of the folio is currently being asserted during the move stage; if it fails, we retry. But, if a racing thread changes the refcount, and ends up sleeping on the folio lock (which is mostly the case), there is no way the refcount would be decremented; as a result, this renders the retrying useless. In the first patch, we make the refcount check also during the unmap stage; if it fails, we restore the original state of the PTE, drop the folio lock, let the system make progress, and retry unmapping again. This improves the probability of migration winning the race. Given that migration is a best-effort service, it is wrong to fail the test for just a single failure; hence, fail the test after 100 consecutive failures (where 100 is still a subjective choice). [1] https://lore.kernel.org/all/20240801081657.1386743-1-dev.jain@arm.com/ Dev Jain (2): mm: Retry migration earlier upon refcount mismatch selftests/mm: Do not fail test for a single migration failure mm/migrate.c | 9 +++++++++ tools/testing/selftests/mm/migration.c | 17 +++++++++++------ 2 files changed, 20 insertions(+), 6 deletions(-) -- 2.30.2

10 months

6
29
0 0

[PATCH] selftests/futex: Create test for robust list

by André Almeida

Create a test for the robust list mechanism. Signed-off-by: André Almeida <andrealmeid(a)igalia.com> --- .../selftests/futex/functional/.gitignore | 1 + .../selftests/futex/functional/Makefile | 3 +- .../selftests/futex/functional/robust_list.c | 450 ++++++++++++++++++ 3 files changed, 453 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/futex/functional/robust_list.c diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index fbcbdb6963b3..4726e1be7497 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -9,3 +9,4 @@ futex_wait_wouldblock futex_wait futex_requeue futex_waitv +robust_list diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index f79f9bac7918..b8635a1ac7f6 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -17,7 +17,8 @@ TEST_GEN_PROGS := \ futex_wait_private_mapped_file \ futex_wait \ futex_requeue \ - futex_waitv + futex_waitv \ + robust_list TEST_PROGS := run.sh diff --git a/tools/testing/selftests/futex/functional/robust_list.c b/tools/testing/selftests/futex/functional/robust_list.c new file mode 100644 index 000000000000..5cc0edaaf028 --- /dev/null +++ b/tools/testing/selftests/futex/functional/robust_list.c @@ -0,0 +1,450 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright Igalia, 2024 + * + * Robust list test by André Almeida <andrealmeid(a)igalia.com> + * + * The robust list uAPI allows userspace to create "robust" locks, in the sense + * that if the lock holder thread dies, the remaining threads that are waiting + * for the lock won't block forever, waiting for a lock that will never be + * released. + * + * This is achieve by userspace setting a list where a thread can enter all the + * locks (futexes) that it is holding. The robust list is a linked list, and + * userspace register the start of the list with the syscall set_robust_list(). + * If such thread eventually dies, the kernel will walk this list, waking up one + * thread waiting for each futex and marking the futex word with the flag + * FUTEX_OWNER_DIED. + * + * See also + * man set_robust_list + * Documententation/locking/robust-futex-ABI.rst + * Documententation/locking/robust-futexes.rst + */ + +#define _GNU_SOURCE + +#include "../../kselftest_harness.h" + +#include "futextest.h" + +#include <pthread.h> +#include <stdatomic.h> +#include <stddef.h> + +#define STACK_SIZE (1024 * 1024) + +#define FUTEX_TIMEOUT 3 + +static pthread_barrier_t barrier, barrier2; + +int set_robust_list(struct robust_list_head *head, size_t len) +{ + return syscall(SYS_set_robust_list, head, len); +} + +int get_robust_list(int pid, struct robust_list_head **head, size_t *len_ptr) +{ + return syscall(SYS_get_robust_list, pid, head, len_ptr); +} + +int futex2_wait(void *futex, int val, struct timespec *timo) +{ + return syscall(SYS_futex_wait, futex, val, ~0U, FUTEX2_SIZE_U32, timo, CLOCK_MONOTONIC); +} + +/* + * Basic lock struct, contains just the futex word and the robust list element + * Real implementations have also a *prev to easily walk in the list + */ +struct lock_struct { + int futex; + struct robust_list list; +}; + +/* + * Helper function to spawn a child thread. Returns -1 on error, pid on success + */ +static int create_child(int (*fn)(void *arg), void *arg) +{ + char *stack; + pid_t pid; + + stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (stack == MAP_FAILED) + return -1; + + stack += STACK_SIZE; + + pid = clone(fn, stack, CLONE_VM | SIGCHLD, arg); + + if (pid == -1) + return -1; + + return pid; +} + +/* + * Helper function to prepare and register a robust list + */ +static int set_list(struct robust_list_head *head) +{ + int ret; + + ret = set_robust_list(head, sizeof(struct robust_list_head)); + if (ret) + return ret; + + head->futex_offset = (size_t) offsetof(struct lock_struct, futex) - + (size_t) offsetof(struct lock_struct, list); + head->list.next = &head->list; + head->list_op_pending = NULL; + + return 0; +} + +/* + * A basic (and incomplete) mutex lock function with robustness + */ +static int mutex_lock(struct lock_struct *lock, struct robust_list_head *head, bool error_inject) +{ + int *futex = &lock->futex, zero = 0, ret = -1; + pid_t tid = gettid(); + + /* + * Set list_op_pending before starting the lock, so the kernel can catch + * the case where the thread died during the lock operation + */ + head->list_op_pending = &lock->list; + + if (atomic_compare_exchange_strong(futex, &zero, tid)) { + /* + * We took the lock, insert it in the robust list + */ + struct robust_list *list = &head->list; + + /* Error injection to test list_op_pending */ + if (error_inject) + return 0; + + while (list->next != &head->list) + list = list->next; + + list->next = &lock->list; + lock->list.next = &head->list; + + ret = 0; + } else { + /* + * We didn't take the lock, wait until the owner wakes (or dies) + */ + struct timespec to; + + clock_gettime(CLOCK_MONOTONIC, &to); + to.tv_sec = to.tv_sec + FUTEX_TIMEOUT; + + tid = atomic_load(futex); + /* Kernel ignores futexes without the waiters flag */ + tid |= FUTEX_WAITERS; + atomic_store(futex, tid); + + ret = futex2_wait(futex, tid, &to); + + /* + * A real mutex_lock() implementation would loop here to finally + * take the lock. We don't care about that, so we stop here. + */ + } + + head->list_op_pending = NULL; + + return ret; +} + +/* + * This child thread will succeed taking the lock, and then will exit holding it + */ +static int child_fn_lock(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + ret = set_list(&head); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + ret = mutex_lock(lock, &head, false); + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + pthread_barrier_wait(&barrier); + + /* + * There's a race here: the parent thread needs to be inside + * futex_wait() before the child thread dies, otherwise it will miss the + * wakeup from handle_futex_death() that this child will emit. We wait a + * little bit just to make sure that this happens. + */ + sleep(1); + + return 0; +} + +/* + * Spawns a child thread that will set a robust list, take the lock, register it + * in the robust list and die. The parent thread will wait on this futex, and + * should be waken up when the child exits. + */ +TEST(robustness) +{ + struct lock_struct lock = { .futex = 0 }; + struct robust_list_head head; + int ret, *futex = &lock.futex; + + ret = set_list(&head); + ASSERT_EQ(ret, 0); + + /* + * Lets use a barrier to ensure that the child thread takes the lock + * before the parent + */ + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + + ret = create_child(&child_fn_lock, &lock); + ASSERT_NE(ret, -1); + + pthread_barrier_wait(&barrier); + ret = mutex_lock(&lock, &head, false); + + /* + * futex_wait() should return 0 and the futex word should be marked with + * FUTEX_OWNER_DIED + */ + ASSERT_EQ(ret, 0) TH_LOG("futex wait returned %d", errno); + ASSERT_TRUE(*futex | FUTEX_OWNER_DIED); + + pthread_barrier_destroy(&barrier); +} + +/* + * The only valid value for len is sizeof(*head) + */ +TEST(set_robust_list_invalid_size) +{ + struct robust_list_head head; + size_t head_size = sizeof(struct robust_list_head); + int ret; + + ret = set_robust_list(&head, head_size); + ASSERT_EQ(ret, 0); + + ret = set_robust_list(&head, head_size * 2); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + ret = set_robust_list(&head, head_size - 1); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + ret = set_robust_list(&head, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); +} + +/* + * Test get_robust_list with pid = 0, getting the list of the running thread + */ +TEST(get_robust_list_self) +{ + struct robust_list_head head, head2, *get_head; + size_t head_size = sizeof(struct robust_list_head), len_ptr; + int ret; + + ret = set_robust_list(&head, head_size); + ASSERT_EQ(ret, 0); + + ret = get_robust_list(0, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(get_head, &head); + ASSERT_EQ(head_size, len_ptr); + + ret = set_robust_list(&head2, head_size); + ASSERT_EQ(ret, 0); + + ret = get_robust_list(0, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(get_head, &head2); + ASSERT_EQ(head_size, len_ptr); +} + +static int child_list(void *arg) +{ + struct robust_list_head *head = (struct robust_list_head *) arg; + int ret; + + ret = set_robust_list(head, sizeof(struct robust_list_head)); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + pthread_barrier_wait(&barrier); + pthread_barrier_wait(&barrier2); + + return 0; +} + +/* + * Test get_robust_list from another thread. We use two barriers here to ensure + * that: + * 1) the child thread set the list before we try to get it from the + * parent + * 2) the child thread still alive when we try to get the list from it + */ +TEST(get_robust_list_child) +{ + pid_t tid; + int ret; + struct robust_list_head head, *get_head; + size_t len_ptr; + + ret = pthread_barrier_init(&barrier, NULL, 2); + ret = pthread_barrier_init(&barrier2, NULL, 2); + ASSERT_EQ(ret, 0); + + tid = create_child(&child_list, &head); + ASSERT_NE(tid, -1); + + pthread_barrier_wait(&barrier); + + ret = get_robust_list(tid, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(&head, get_head); + + pthread_barrier_wait(&barrier2); + + pthread_barrier_destroy(&barrier); + pthread_barrier_destroy(&barrier2); +} + +static int child_fn_lock_with_error(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + ret = set_list(&head); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + ret = mutex_lock(lock, &head, true); + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + pthread_barrier_wait(&barrier); + + sleep(1); + + return 0; +} + +/* + * Same as robustness test, but inject an error where the mutex_lock() exits + * earlier, just after setting list_op_pending and taking the lock, to test the + * list_op_pending mechanism + */ +TEST(set_list_op_pending) +{ + struct lock_struct lock = { .futex = 0 }; + struct robust_list_head head; + int ret, *futex = &lock.futex; + + ret = set_list(&head); + ASSERT_EQ(ret, 0); + + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + + ret = create_child(&child_fn_lock_with_error, &lock); + ASSERT_NE(ret, -1); + + pthread_barrier_wait(&barrier); + ret = mutex_lock(&lock, &head, false); + + ASSERT_EQ(ret, 0) TH_LOG("futex wait returned %d", errno); + ASSERT_TRUE(*futex | FUTEX_OWNER_DIED); + + pthread_barrier_destroy(&barrier); +} + +#define CHILD_NR 10 + +static int child_lock_holder(void *arg) +{ + struct lock_struct *locks = (struct lock_struct *) arg; + struct robust_list_head head; + int i; + + set_list(&head); + + for (i = 0; i < CHILD_NR; i++) { + locks[i].futex = 0; + mutex_lock(&locks[i], &head, false); + } + + pthread_barrier_wait(&barrier); + pthread_barrier_wait(&barrier2); + + sleep(1); + return 0; +} + +static int child_wait_lock(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + pthread_barrier_wait(&barrier2); + ret = mutex_lock(lock, &head, false); + + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + if (!(lock->futex | FUTEX_OWNER_DIED)) + ksft_test_result_fail("futex not marked with FUTEX_OWNER_DIED\n"); + + return 0; +} + +/* + * Test a robust list of more than one element. All the waiters should wake when + * the holder dies + */ +TEST(robust_list_multiple_elements) +{ + struct lock_struct locks[CHILD_NR]; + int i, ret; + + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + ret = pthread_barrier_init(&barrier2, NULL, CHILD_NR + 1); + ASSERT_EQ(ret, 0); + + create_child(&child_lock_holder, &locks); + + /* Wait until the locker thread takes the look */ + pthread_barrier_wait(&barrier); + + for (i = 0; i < CHILD_NR; i++) + create_child(&child_wait_lock, &locks[i]); + + /* Wait for all children to return */ + while (wait(NULL) > 0); + + pthread_barrier_destroy(&barrier); + pthread_barrier_destroy(&barrier2); +} + +TEST_HARNESS_MAIN -- 2.46.0

10 months

2
2
0 0

[PATCH] selftests: vDSO: Also test counter in vdso_test_chacha

by Christophe Leroy

The chacha vDSO selftest doesn't check the way the counter is handled by __arch_chacha20_blocks_nostack(). It indirectly checks that the counter is writen on exit and read back on new entry, but it doesn't check that the format is correct. It has led to an invisible erroneous implementation on powerpc where the counter was writen and read in wrong byte order. Also, the counter uses two words, but the tests with a zero counter and uses a small amount of blocks so at the end the upper part of the counter is always 0 so it is not checked. Add a verification of counter's content in addition to the verification of the output. Also add two tests where the counter crosses the u32 upper limit. The first test verifies that the function properly writes back the upper word, the second test verifies that the function properly reads back the upper word. While at it, remove 'nonce' which is not unused anymore after the replacement of libsodium by open coded chacha implementation. Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> --- .../testing/selftests/vDSO/vdso_test_chacha.c | 39 ++++++++++++++----- 1 file changed, 30 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c index 9d18d49a82f8..ed6cf372d9ee 100644 --- a/tools/testing/selftests/vDSO/vdso_test_chacha.c +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -17,11 +17,12 @@ static uint32_t rol32(uint32_t word, unsigned int shift) return (word << (shift & 31)) | (word >> ((-shift) & 31)); } -static void reference_chacha20_blocks(uint8_t *dst_bytes, const uint32_t *key, size_t nblocks) +static void reference_chacha20_blocks(uint8_t *dst_bytes, const uint32_t *key, uint32_t *counter, size_t nblocks) { uint32_t s[16] = { 0x61707865U, 0x3320646eU, 0x79622d32U, 0x6b206574U, - key[0], key[1], key[2], key[3], key[4], key[5], key[6], key[7] + key[0], key[1], key[2], key[3], key[4], key[5], key[6], key[7], + counter[0], counter[1], }; while (nblocks--) { @@ -52,6 +53,8 @@ static void reference_chacha20_blocks(uint8_t *dst_bytes, const uint32_t *key, s if (!++s[12]) ++s[13]; } + counter[0] = s[12]; + counter[1] = s[13]; } typedef uint8_t u8; @@ -66,8 +69,7 @@ typedef uint64_t u64; int main(int argc, char *argv[]) { enum { TRIALS = 1000, BLOCKS = 128, BLOCK_SIZE = 64 }; - static const uint8_t nonce[8] = { 0 }; - uint32_t counter[2]; + uint32_t counter1[2], counter2[2]; uint32_t key[8]; uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS]; @@ -84,17 +86,36 @@ int main(int argc, char *argv[]) printf("getrandom() failed!\n"); return KSFT_SKIP; } - reference_chacha20_blocks(output1, key, BLOCKS); + memset(counter1, 0, sizeof(counter1)); + reference_chacha20_blocks(output1, key, counter1, BLOCKS); for (unsigned int split = 0; split < BLOCKS; ++split) { memset(output2, 'X', sizeof(output2)); - memset(counter, 0, sizeof(counter)); + memset(counter2, 0, sizeof(counter2)); if (split) - __arch_chacha20_blocks_nostack(output2, key, counter, split); - __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter, BLOCKS - split); - if (memcmp(output1, output2, sizeof(output1))) + __arch_chacha20_blocks_nostack(output2, key, counter2, split); + __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter2, BLOCKS - split); + if (memcmp(output1, output2, sizeof(output1)) || + memcmp(counter2, counter2, sizeof(counter1))) return KSFT_FAIL; } } + memset(counter1, 0, sizeof(counter1)); + counter1[0] = (uint32_t)-BLOCKS + 2; + memset(counter2, 0, sizeof(counter2)); + counter2[0] = (uint32_t)-BLOCKS + 2; + + reference_chacha20_blocks(output1, key, counter1, BLOCKS); + __arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS); + if (memcmp(output1, output2, sizeof(output1)) || + memcmp(counter2, counter2, sizeof(counter1))) + return KSFT_FAIL; + + reference_chacha20_blocks(output1, key, counter1, BLOCKS); + __arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS); + if (memcmp(output1, output2, sizeof(output1)) || + memcmp(counter2, counter2, sizeof(counter1))) + return KSFT_FAIL; + ksft_test_result_pass("chacha: PASS\n"); return KSFT_PASS; } -- 2.44.0

10 months

2
3
0 0

[PATCH] selftests: vDSO: Build vDSO tests with O2 optimisation

by Christophe Leroy

Without -O2, the generated code for testing chacha function is awful. GCC even implements rol32() as a function instead of just using the rotlwi instruction, that function is 20 instructions long. ~# time ./vdso_test_chacha TAP version 13 1..1 ok 1 chacha: PASS real 0m 37.16s user 0m 36.89s sys 0m 0.26s Several other selftests directory add -O2, and the kernel is also always built with optimisation active. Do the same for vDSO selftests. With this patch the time is reduced by approx 15%. ~# time ./vdso_test_chacha TAP version 13 1..1 ok 1 chacha: PASS real 0m 32.09s user 0m 31.86s sys 0m 0.22s Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> --- tools/testing/selftests/vDSO/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index cfb7c281b22c..96f25aa2f84e 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -13,7 +13,7 @@ TEST_GEN_PROGS += vdso_test_correctness TEST_GEN_PROGS += vdso_test_getrandom TEST_GEN_PROGS += vdso_test_chacha -CFLAGS := -std=gnu99 +CFLAGS := -std=gnu99 -O2 ifeq ($(CONFIG_X86_32),y) LDLIBS += -lgcc_s -- 2.44.0

10 months

2
1
0 0

I am facing Issue with Running Kselftest on ARM64 Architecture

by iamolivasmith＠gmail.com

Hello everyone, I am working on running Kselftest on an ARM64 platform and have facing a few issues that I am hoping someone here might have experience with. I have successfully compiled the tests and am able to run most of them but I am facing a specific problem with the memory management tests. They seem to fail consistently; even though I have confirmed that the kernel configuration should support them. The errors I am seeing are related to page allocation failures & Also i have double checked that there ample memory available on the system. I have also tried running these tests on a different ARM64 platform with similar kernel configurations and encountered the same issue. Is this a known problem with ARM64 Kselftest, or is there something unique to my configuration that I am not seeing? if you have any advice; any suggestions or pointers to relevant documentation would be greatly appreciated. Thank you <a href="https://www.igmguru.com/blog/what-is-ampscript-in-salesforce-marketing-cloud">https://www.igmguru.com/blog/what-is-ampscript-in-salesforce-marketing-cloud</a>

10 months

1
0
0 0

[PATCH v3 0/5] Wire up getrandom() vDSO implementation on powerpc

by Christophe Leroy

This series wires up getrandom() vDSO implementation on powerpc. Tested on PPC32 on real hardware. Tested on PPC64 (both BE and LE) on QEMU: Performance on powerpc 885: ~# ./vdso_test_getrandom bench-single vdso: 25000000 times in 62.938002291 seconds libc: 25000000 times in 535.581916866 seconds syscall: 25000000 times in 531.525042806 seconds Performance on powerpc 8321: ~# ./vdso_test_getrandom bench-single vdso: 25000000 times in 16.899318858 seconds libc: 25000000 times in 131.050596522 seconds syscall: 25000000 times in 129.794790389 seconds Performance on QEMU pseries: ~ # ./vdso_test_getrandom bench-single vdso: 25000000 times in 4.977777162 seconds libc: 25000000 times in 75.516749981 seconds syscall: 25000000 times in 86.842242014 seconds In order to run selftests, some fixes are needed, see https://lore.kernel.org/linuxppc-dev/6c5da802e72befecfa09046c489aa45d934d61… Those selftest fixes are independant and are not required to apply and use this series. Changes in v3: - Rebased on recent random git tree (0c7e00e22c21) - Fixed build failures reported by robots around VM_DROPPABLE - Fixed crash on PPC64 due to clobbered r13 by not using r13 anymore (saving it was not enough for signals). - Split final patch in two, first for PPC32, second for PPC64 - Moved selftest fixes out of this series Changes in v2: - Define VM_DROPPABLE for powerpc/32 - Fixes generic vDSO getrandom headers to enable CONFIG_COMPAT build. - Fixed size of generation counter - Fixed selftests to work on non x86 architectures Christophe Leroy (5): mm: Define VM_DROPPABLE for powerpc/32 powerpc/vdso32: Add crtsavres powerpc/vdso: Refactor CFLAGS for CVDSO build powerpc/vdso: Wire up getrandom() vDSO implementation on PPC32 powerpc/vdso: Wire up getrandom() vDSO implementation on PPC64 arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/asm-compat.h | 8 + arch/powerpc/include/asm/mman.h | 2 +- arch/powerpc/include/asm/vdso/getrandom.h | 54 ++++ arch/powerpc/include/asm/vdso/vsyscall.h | 6 + arch/powerpc/include/asm/vdso_datapage.h | 2 + arch/powerpc/kernel/asm-offsets.c | 1 + arch/powerpc/kernel/vdso/Makefile | 57 ++-- arch/powerpc/kernel/vdso/getrandom.S | 58 ++++ arch/powerpc/kernel/vdso/gettimeofday.S | 13 - arch/powerpc/kernel/vdso/vdso32.lds.S | 1 + arch/powerpc/kernel/vdso/vdso64.lds.S | 1 + arch/powerpc/kernel/vdso/vgetrandom-chacha.S | 299 +++++++++++++++++++ arch/powerpc/kernel/vdso/vgetrandom.c | 14 + fs/proc/task_mmu.c | 4 +- include/linux/mm.h | 4 +- include/trace/events/mmflags.h | 4 +- tools/arch/powerpc/vdso | 1 + tools/testing/selftests/vDSO/Makefile | 4 + 19 files changed, 492 insertions(+), 42 deletions(-) create mode 100644 arch/powerpc/include/asm/vdso/getrandom.h create mode 100644 arch/powerpc/kernel/vdso/getrandom.S create mode 100644 arch/powerpc/kernel/vdso/vgetrandom-chacha.S create mode 100644 arch/powerpc/kernel/vdso/vgetrandom.c create mode 120000 tools/arch/powerpc/vdso -- 2.44.0

10 months

3
11
0 0

[PATCH net-next] wireguard: allowedips: Add WGALLOWEDIP_F_REMOVE_ME flag

by Jordan Rife

With the current API the only way to remove an allowed IP is to completely rebuild the allowed IPs set for a peer using WGPEER_F_REPLACE_ALLOWEDIPS. In other words, if my current configuration is such that a peer has allowed IP IPs 192.168.0.2 and 192.168.0.3 and I want to remove 192.168.0.2 the actual transition looks like this. [192.168.0.2, 192.168.0.3] <-- Initial state [] <-- Step 1: Allowed IPs removed for peer [192.168.0.3] <-- Step 2: Allowed IPs added back for peer This is true even if the allowed IP list is small and the update does not need to be batched into multiple WG_CMD_SET_DEVICE requests, as the removal and subsequent addition of IPs is non-atomic within a single request. Consequently, wg_allowedips_lookup_dst and wg_allowedips_lookup_src may return NULL while reconfiguring a peer even for packets bound for IPs a user did not intend to remove leading to unintended interruptions in connectivity. This presents in userspace as failed calls to sendto and sendmsg. In my case, I ran netperf while repeatedly reconfiguring the allowed IPs for a peer with wg. /usr/local/bin/netperf -H 10.102.73.72 -l 10m -t UDP_STREAM -- -R 1 -m 1024 send_data: data send error: No route to host (errno 113) netperf: send_omni: send_data failed: No route to host While this may not be of particular concern for environments where peers and allowed IPs are mostly static, Cilium manages peers and allowed IPs in a dynamic environment where peers (i.e. Kubernetes nodes) and allowed IPs (i.e. Pods running on those nodes) can frequently change. Cilium must continually keep its WireGuard device's configuration in sync with its cluster state leading to unnecessary churn and packet drops. This patch introduces a new flag called WGALLOWEDIP_F_REMOVE_ME which in the same way that WGPEER_F_REMOVE_ME allows a user to remove a single peer from a WireGuard device's configuration allows a user to remove an IP from a peer's set of allowed IPs. This has two benefits. First, it allows systems such as Cilium to avoid introducing connectivity blips while reconfiguring a WireGuard device. Second, it allows us to more efficiently keep the device's configuration in sync with the cluster state, as we no longer need to do frequent rebuilds of the allowed IPs list for each peer. Instead, the device's configuration can be incrementally updated. This patch also bumps WG_GENL_VERSION which can be used by clients to detect whether or not their system supports the WGALLOWEDIP_F_REMOVE_ME flag. Signed-off-by: Jordan Rife <jrife(a)google.com> Link: https://github.com/cilium/cilium/issues/33159 --- drivers/net/wireguard/allowedips.c | 103 ++++++++++---- drivers/net/wireguard/allowedips.h | 4 + drivers/net/wireguard/netlink.c | 45 +++++-- drivers/net/wireguard/selftest/allowedips.c | 30 +++++ include/uapi/linux/wireguard.h | 11 +- tools/testing/selftests/wireguard/Makefile | 18 +++ tools/testing/selftests/wireguard/netns.sh | 38 ++++++ tools/testing/selftests/wireguard/remove-ip.c | 126 ++++++++++++++++++ 8 files changed, 333 insertions(+), 42 deletions(-) create mode 100644 tools/testing/selftests/wireguard/Makefile create mode 100644 tools/testing/selftests/wireguard/remove-ip.c diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 4b8528206cc8a..47a96a1b8f0ea 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -249,6 +249,56 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, return 0; } +static void _remove(struct allowedips_node __rcu *node, struct mutex *lock) +{ + struct allowedips_node *child, **parent_bit, *parent; + bool free_parent; + + list_del_init(&node->peer_list); + RCU_INIT_POINTER(node->peer, NULL); + if (node->bit[0] && node->bit[1]) + return; + child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])], + lockdep_is_held(lock)); + if (child) + child->parent_bit_packed = node->parent_bit_packed; + parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL); + *parent_bit = child; + parent = (void *)parent_bit - + offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]); + free_parent = !rcu_access_pointer(node->bit[0]) && + !rcu_access_pointer(node->bit[1]) && + (node->parent_bit_packed & 3) <= 1 && + !rcu_access_pointer(parent->peer); + if (free_parent) + child = rcu_dereference_protected(parent->bit[!(node->parent_bit_packed & 1)], + lockdep_is_held(lock)); + call_rcu(&node->rcu, node_free_rcu); + if (!free_parent) + return; + if (child) + child->parent_bit_packed = parent->parent_bit_packed; + *(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child; + call_rcu(&parent->rcu, node_free_rcu); +} + +static int remove(struct allowedips_node __rcu **trie, u8 bits, const u8 *key, + u8 cidr, struct wg_peer *peer, struct mutex *lock) +{ + struct allowedips_node *node; + + if (unlikely(cidr > bits || !peer)) + return -EINVAL; + if (!rcu_access_pointer(*trie) || + !node_placement(*trie, key, cidr, bits, &node, lock) || + peer != node->peer) + return 0; + + _remove(node, lock); + + return 0; +} + void wg_allowedips_init(struct allowedips *table) { table->root4 = table->root6 = NULL; @@ -300,43 +350,38 @@ int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip, return add(&table->root6, 128, key, cidr, peer, lock); } +int wg_allowedips_remove_v4(struct allowedips *table, const struct in_addr *ip, + u8 cidr, struct wg_peer *peer, struct mutex *lock) +{ + /* Aligned so it can be passed to fls */ + u8 key[4] __aligned(__alignof(u32)); + + ++table->seq; + swap_endian(key, (const u8 *)ip, 32); + return remove(&table->root4, 32, key, cidr, peer, lock); +} + +int wg_allowedips_remove_v6(struct allowedips *table, const struct in6_addr *ip, + u8 cidr, struct wg_peer *peer, struct mutex *lock) +{ + /* Aligned so it can be passed to fls64 */ + u8 key[16] __aligned(__alignof(u64)); + + ++table->seq; + swap_endian(key, (const u8 *)ip, 128); + return remove(&table->root6, 128, key, cidr, peer, lock); +} + void wg_allowedips_remove_by_peer(struct allowedips *table, struct wg_peer *peer, struct mutex *lock) { - struct allowedips_node *node, *child, **parent_bit, *parent, *tmp; - bool free_parent; + struct allowedips_node *node, *tmp; if (list_empty(&peer->allowedips_list)) return; ++table->seq; list_for_each_entry_safe(node, tmp, &peer->allowedips_list, peer_list) { - list_del_init(&node->peer_list); - RCU_INIT_POINTER(node->peer, NULL); - if (node->bit[0] && node->bit[1]) - continue; - child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])], - lockdep_is_held(lock)); - if (child) - child->parent_bit_packed = node->parent_bit_packed; - parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL); - *parent_bit = child; - parent = (void *)parent_bit - - offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]); - free_parent = !rcu_access_pointer(node->bit[0]) && - !rcu_access_pointer(node->bit[1]) && - (node->parent_bit_packed & 3) <= 1 && - !rcu_access_pointer(parent->peer); - if (free_parent) - child = rcu_dereference_protected( - parent->bit[!(node->parent_bit_packed & 1)], - lockdep_is_held(lock)); - call_rcu(&node->rcu, node_free_rcu); - if (!free_parent) - continue; - if (child) - child->parent_bit_packed = parent->parent_bit_packed; - *(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child; - call_rcu(&parent->rcu, node_free_rcu); + _remove(node, lock); } } diff --git a/drivers/net/wireguard/allowedips.h b/drivers/net/wireguard/allowedips.h index 2346c797eb4d8..931958cb6e100 100644 --- a/drivers/net/wireguard/allowedips.h +++ b/drivers/net/wireguard/allowedips.h @@ -38,6 +38,10 @@ int wg_allowedips_insert_v4(struct allowedips *table, const struct in_addr *ip, u8 cidr, struct wg_peer *peer, struct mutex *lock); int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip, u8 cidr, struct wg_peer *peer, struct mutex *lock); +int wg_allowedips_remove_v4(struct allowedips *table, const struct in_addr *ip, + u8 cidr, struct wg_peer *peer, struct mutex *lock); +int wg_allowedips_remove_v6(struct allowedips *table, const struct in6_addr *ip, + u8 cidr, struct wg_peer *peer, struct mutex *lock); void wg_allowedips_remove_by_peer(struct allowedips *table, struct wg_peer *peer, struct mutex *lock); /* The ip input pointer should be __aligned(__alignof(u64))) */ diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index f7055180ba4aa..5f2a8553ab43d 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -46,7 +46,8 @@ static const struct nla_policy peer_policy[WGPEER_A_MAX + 1] = { static const struct nla_policy allowedip_policy[WGALLOWEDIP_A_MAX + 1] = { [WGALLOWEDIP_A_FAMILY] = { .type = NLA_U16 }, [WGALLOWEDIP_A_IPADDR] = NLA_POLICY_MIN_LEN(sizeof(struct in_addr)), - [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 } + [WGALLOWEDIP_A_CIDR_MASK] = { .type = NLA_U8 }, + [WGALLOWEDIP_A_FLAGS] = { .type = NLA_U32 } }; static struct wg_device *lookup_interface(struct nlattr **attrs, @@ -329,6 +330,7 @@ static int set_port(struct wg_device *wg, u16 port) static int set_allowedip(struct wg_peer *peer, struct nlattr **attrs) { int ret = -EINVAL; + u32 flags = 0; u16 family; u8 cidr; @@ -337,19 +339,38 @@ static int set_allowedip(struct wg_peer *peer, struct nlattr **attrs) return ret; family = nla_get_u16(attrs[WGALLOWEDIP_A_FAMILY]); cidr = nla_get_u8(attrs[WGALLOWEDIP_A_CIDR_MASK]); + if (attrs[WGALLOWEDIP_A_FLAGS]) + flags = nla_get_u32(attrs[WGALLOWEDIP_A_FLAGS]); if (family == AF_INET && cidr <= 32 && - nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in_addr)) - ret = wg_allowedips_insert_v4( - &peer->device->peer_allowedips, - nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer, - &peer->device->device_update_lock); - else if (family == AF_INET6 && cidr <= 128 && - nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in6_addr)) - ret = wg_allowedips_insert_v6( - &peer->device->peer_allowedips, - nla_data(attrs[WGALLOWEDIP_A_IPADDR]), cidr, peer, - &peer->device->device_update_lock); + nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in_addr)) { + if (flags & WGALLOWEDIP_F_REMOVE_ME) + ret = wg_allowedips_remove_v4(&peer->device->peer_allowedips, + nla_data(attrs[WGALLOWEDIP_A_IPADDR]), + cidr, + peer, + &peer->device->device_update_lock); + else + ret = wg_allowedips_insert_v4(&peer->device->peer_allowedips, + nla_data(attrs[WGALLOWEDIP_A_IPADDR]), + cidr, + peer, + &peer->device->device_update_lock); + } else if (family == AF_INET6 && cidr <= 128 && + nla_len(attrs[WGALLOWEDIP_A_IPADDR]) == sizeof(struct in6_addr)) { + if (flags & WGALLOWEDIP_F_REMOVE_ME) + ret = wg_allowedips_remove_v6(&peer->device->peer_allowedips, + nla_data(attrs[WGALLOWEDIP_A_IPADDR]), + cidr, + peer, + &peer->device->device_update_lock); + else + ret = wg_allowedips_insert_v6(&peer->device->peer_allowedips, + nla_data(attrs[WGALLOWEDIP_A_IPADDR]), + cidr, + peer, + &peer->device->device_update_lock); + } return ret; } diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 3d1f64ff2e122..9f6458a889e96 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -461,6 +461,10 @@ static __init struct wg_peer *init_peer(void) wg_allowedips_insert_v##version(&t, ip##version(ipa, ipb, ipc, ipd), \ cidr, mem, &mutex) +#define remove(version, mem, ipa, ipb, ipc, ipd, cidr) \ + wg_allowedips_remove_v##version(&t, ip##version(ipa, ipb, ipc, ipd), \ + cidr, mem, &mutex) + #define maybe_fail() do { \ ++i; \ if (!_s) { \ @@ -586,6 +590,32 @@ bool __init wg_allowedips_selftest(void) test_negative(4, a, 192, 0, 0, 0); test_negative(4, a, 255, 0, 0, 0); + insert(4, a, 1, 0, 0, 0, 32); + insert(4, a, 192, 0, 0, 0, 24); + insert(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128); + insert(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98); + test(4, a, 1, 0, 0, 0); + test(4, a, 192, 0, 0, 1); + test(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + test(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0x10101010); + /* Must be an exact match to remove */ + remove(4, a, 192, 0, 0, 0, 32); + test(4, a, 192, 0, 0, 1); + remove(4, a, 192, 0, 0, 0, 24); + test_negative(4, a, 192, 0, 0, 1); + remove(4, a, 1, 0, 0, 0, 32); + test_negative(4, a, 1, 0, 0, 0); + /* Must be an exact match to remove */ + remove(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 96); + test(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + remove(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef, 128); + test_negative(6, a, 0x24446801, 0x40e40800, 0xdeaebeef, 0xdefbeef); + /* Must match the peer to remove */ + remove(6, b, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98); + test(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0x10101010); + remove(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0, 98); + test_negative(6, a, 0x24446800, 0xf0e40800, 0xeeaebeef, 0x10101010); + wg_allowedips_free(&t, &mutex); wg_allowedips_init(&t); insert(4, a, 192, 168, 0, 0, 16); diff --git a/include/uapi/linux/wireguard.h b/include/uapi/linux/wireguard.h index ae88be14c9478..e219194cb9f5a 100644 --- a/include/uapi/linux/wireguard.h +++ b/include/uapi/linux/wireguard.h @@ -101,6 +101,10 @@ * WGALLOWEDIP_A_FAMILY: NLA_U16 * WGALLOWEDIP_A_IPADDR: struct in_addr or struct in6_addr * WGALLOWEDIP_A_CIDR_MASK: NLA_U8 + * WGALLOWEDIP_A_FLAGS: NLA_U32, WGALLOWEDIP_F_REMOVE_ME if + * the specified IP should be removed, + * otherwise this IP will be added if + * it is not already present. * 0: NLA_NESTED * ... * 0: NLA_NESTED @@ -132,7 +136,7 @@ #define _WG_UAPI_WIREGUARD_H #define WG_GENL_NAME "wireguard" -#define WG_GENL_VERSION 1 +#define WG_GENL_VERSION 2 #define WG_KEY_LEN 32 @@ -184,11 +188,16 @@ enum wgpeer_attribute { }; #define WGPEER_A_MAX (__WGPEER_A_LAST - 1) +enum wgallowedip_flag { + WGALLOWEDIP_F_REMOVE_ME = 1U << 0, + __WGALLOWEDIP_F_ALL = WGALLOWEDIP_F_REMOVE_ME +}; enum wgallowedip_attribute { WGALLOWEDIP_A_UNSPEC, WGALLOWEDIP_A_FAMILY, WGALLOWEDIP_A_IPADDR, WGALLOWEDIP_A_CIDR_MASK, + WGALLOWEDIP_A_FLAGS, __WGALLOWEDIP_A_LAST }; #define WGALLOWEDIP_A_MAX (__WGALLOWEDIP_A_LAST - 1) diff --git a/tools/testing/selftests/wireguard/Makefile b/tools/testing/selftests/wireguard/Makefile new file mode 100644 index 0000000000000..4f4db54f89cb3 --- /dev/null +++ b/tools/testing/selftests/wireguard/Makefile @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Note: To build this you must install libnl-3 and libnl-genl-3 development +# packages. +remove-ip: + gcc -I/usr/include/libnl3 \ + -I../../../../usr/include \ + remove-ip.c \ + -o remove-ip \ + -lnl-genl-3 \ + -lnl-3 + +.PHONY: all +all: remove-ip + +.PHONY: clean +clean: + rm remove-ip diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 405ff262ca93d..70058d6ebbe85 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -28,6 +28,7 @@ exec 3>&1 export LANG=C export WG_HIDE_KEYS=never NPROC=( /sys/devices/system/cpu/cpu+([0-9]) ); NPROC=${#NPROC[@]} +SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd ) netns0="wg-test-$$-0" netns1="wg-test-$$-1" netns2="wg-test-$$-2" @@ -610,6 +611,43 @@ n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips" } < <(n0 wg show wg0 allowed-ips) ip0 link del wg0 +# Test IP removal +allowedips=( ) +for i in {1..197}; do + allowedips+=( 192.168.0.$i ) + allowedips+=( abcd::$i ) +done +saved_ifs="$IFS" +IFS=, +allowedips="${allowedips[*]}" +IFS="$saved_ifs" +ip0 link add wg0 type wireguard +n0 wg set wg0 peer "$pub1" allowed-ips "$allowedips" +pub1_hex=$(echo "$pub1" | base64 -d | xxd -p -c 50) +n0 $SCRIPT_DIR/remove-ip wg0 "$pub1_hex" 4 192.168.0.1 +n0 $SCRIPT_DIR/remove-ip wg0 "$pub1_hex" 4 192.168.0.20 +n0 $SCRIPT_DIR/remove-ip wg0 "$pub1_hex" 4 192.168.0.100 +n0 $SCRIPT_DIR/remove-ip wg0 "$pub1_hex" 6 abcd::1 +n0 $SCRIPT_DIR/remove-ip wg0 "$pub1_hex" 6 abcd::20 +n0 $SCRIPT_DIR/remove-ip wg0 "$pub1_hex" 6 abcd::100 +n0 wg show wg0 allowed-ips +{ + read -r pub allowedips + [[ $pub == "$pub1" ]] + i=0 + for ip in $allowedips; do + [[ "$ip" != "192.168.0.1" ]] + [[ "$ip" != "192.168.0.20" ]] + [[ "$ip" != "192.168.0.100" ]] + [[ "$ip" != "abcd::1" ]] + [[ "$ip" != "abcd::20" ]] + [[ "$ip" != "abcd::100" ]] + ((++i)) + done + ((i == 388)) +} < <(n0 wg show wg0 allowed-ips) +ip0 link del wg0 + ! n0 wg show doesnotexist || false ip0 link add wg0 type wireguard diff --git a/tools/testing/selftests/wireguard/remove-ip.c b/tools/testing/selftests/wireguard/remove-ip.c new file mode 100644 index 0000000000000..242f922d99b56 --- /dev/null +++ b/tools/testing/selftests/wireguard/remove-ip.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/wireguard.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <netlink/socket.h> +#include <netlink/netlink.h> +#include <netlink/genl/ctrl.h> +#include <netlink/genl/genl.h> +#include <netlink/genl/family.h> + +#define CURVE25519_KEY_SIZE 32 + +const char *usage = "Usage: remove-ip INTERFACE_NAME PEER_PUBLIC_KEY_HEX IP_VERSION IP"; + +char h2b(char c) +{ + if ('0' <= c && c <= '9') + return c - '0'; + else if ('a' <= c && c <= 'f') + return 10 + (c - 'a'); + + return -1; +} + +int parse_key(const char *raw, unsigned char key[CURVE25519_KEY_SIZE]) +{ + int ret = 0; + int i; + + for (i = 0; i < CURVE25519_KEY_SIZE; i++) { + char h, l; + + h = h2b(raw[0]); + if (h < 0) + return -1; + + l = h2b(raw[1]); + if (l < 0) + return -1; + + key[i] = (h << 4) | l; + raw += 2; + } + + return 0; +} + +int main(int argc, char **argv) +{ + unsigned char addr[sizeof(struct in6_addr)]; + unsigned char pub_key[CURVE25519_KEY_SIZE]; + struct nl_sock *sock; + struct nl_msg *msg; + int addr_len; + int family; + int cidr; + int af; + + if (argc < 5) { + printf("Not enough arguments.\n\n%s\n", usage); + return -1; + } + + if (parse_key(argv[2], pub_key)) { + printf("Could not parse public key\n"); + return -1; + } + + switch (argv[3][0]) { + case '4': + af = AF_INET; + addr_len = sizeof(struct in_addr); + cidr = 32; + break; + case '6': + af = AF_INET6; + addr_len = sizeof(struct in6_addr); + cidr = 128; + break; + default: + printf("Invalid IP version\n"); + return -1; + } + + if (inet_pton(af, argv[4], &addr) <= 0) { + printf("Could not parse IP address\n"); + return -1; + } + + sock = nl_socket_alloc(); + genl_connect(sock); + family = genl_ctrl_resolve(sock, WG_GENL_NAME); + msg = nlmsg_alloc(); + genlmsg_put(msg, NL_AUTO_PID, NL_AUTO_SEQ, family, 0, NLM_F_ECHO, + WG_CMD_SET_DEVICE, WG_GENL_VERSION); + nla_put_string(msg, WGDEVICE_A_IFNAME, argv[1]); + + struct nlattr *peers = nla_nest_start(msg, WGDEVICE_A_PEERS); + struct nlattr *peer0 = nla_nest_start(msg, 0); + + nla_put(msg, WGPEER_A_PUBLIC_KEY, CURVE25519_KEY_SIZE, pub_key); + + struct nlattr *allowed_ips = nla_nest_start(msg, WGPEER_A_ALLOWEDIPS); + struct nlattr *allowed_ip0 = nla_nest_start(msg, 0); + + nla_put_u16(msg, WGALLOWEDIP_A_FAMILY, af); + nla_put(msg, WGALLOWEDIP_A_IPADDR, addr_len, &addr); + nla_put_u8(msg, WGALLOWEDIP_A_CIDR_MASK, cidr); + nla_put_u32(msg, WGALLOWEDIP_A_FLAGS, WGALLOWEDIP_F_REMOVE_ME); + nla_nest_end(msg, allowed_ip0); + nla_nest_end(msg, allowed_ips); + nla_nest_end(msg, peer0); + nla_nest_end(msg, peers); + + int err = nl_send_sync(sock, msg); + + if (err < 0) { + char message[256]; + + nl_perror(err, message); + printf("An error occurred: %d - %s\n", err, message); + } + + return err; +} -- 2.46.0.469.g59c65b2a67-goog

10 months

2
1
0 0

[PATCH 0/2] Adding SO_PEEK_OFF for TCPv6

by jmaloy＠redhat.com

From: Jon Maloy <jmaloy(a)redhat.com> Adding SO_PEEK_OFF for TCPv6 and selftest for both TCPv4 and TCPv6. Jon Maloy (2): tcp: add SO_PEEK_OFF socket option tor TCPv6 selftests: add selftest for tcp SO_PEEK_OFF support net/ipv6/af_inet6.c | 1 + tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/tcp_so_peek_off.c | 181 ++++++++++++++++++ 3 files changed, 183 insertions(+) create mode 100644 tools/testing/selftests/net/tcp_so_peek_off.c -- 2.45.2

10 months

4
8
0 0

[PATCH 00/16] mm: Introduce MAP_BELOW_HINT

by Charlie Jenkins

Some applications rely on placing data in free bits addresses allocated by mmap. Various architectures (eg. x86, arm64, powerpc) restrict the address returned by mmap to be less than the maximum address space, unless the hint address is greater than this value. On arm64 this barrier is at 52 bits and on x86 it is at 56 bits. This flag allows applications a way to specify exactly how many bits they want to be left unused by mmap. This eliminates the need for applications to know the page table hierarchy of the system to be able to reason which addresses mmap will be allowed to return. --- riscv made this feature of mmap returning addresses less than the hint address the default behavior. This was in contrast to the implementation of x86/arm64 that have a single boundary at the 5-level page table region. However this restriction proved too great -- the reduced address space when using a hint address was too small. A patch for riscv [1] reverts the behavior that broke userspace. This series serves to make this feature available to all architectures. I have only tested on riscv and x86. There is a tremendous amount of duplicated code in mmap so the implementations across architectures I believe should be mostly consistent. I added this feature to all architectures that implement either arch_get_mmap_end()/arch_get_mmap_base() or arch_get_unmapped_area_topdown()/arch_get_unmapped_area(). I also added it to the default behavior for arch_get_mmap_end()/arch_get_mmap_base(). Link: https://lore.kernel.org/lkml/20240826-riscv_mmap-v1-2-cd8962afe47f@rivosinc… [1] To: Arnd Bergmann <arnd(a)arndb.de> To: Paul Walmsley <paul.walmsley(a)sifive.com> To: Palmer Dabbelt <palmer(a)dabbelt.com> To: Albert Ou <aou(a)eecs.berkeley.edu> To: Catalin Marinas <catalin.marinas(a)arm.com> To: Will Deacon <will(a)kernel.org> To: Michael Ellerman <mpe(a)ellerman.id.au> To: Nicholas Piggin <npiggin(a)gmail.com> To: Christophe Leroy <christophe.leroy(a)csgroup.eu> To: Naveen N Rao <naveen(a)kernel.org> To: Muchun Song <muchun.song(a)linux.dev> To: Andrew Morton <akpm(a)linux-foundation.org> To: Liam R. Howlett <Liam.Howlett(a)oracle.com> To: Vlastimil Babka <vbabka(a)suse.cz> To: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> To: Thomas Gleixner <tglx(a)linutronix.de> To: Ingo Molnar <mingo(a)redhat.com> To: Borislav Petkov <bp(a)alien8.de> To: Dave Hansen <dave.hansen(a)linux.intel.com> To: x86(a)kernel.org To: H. Peter Anvin <hpa(a)zytor.com> To: Huacai Chen <chenhuacai(a)kernel.org> To: WANG Xuerui <kernel(a)xen0n.name> To: Russell King <linux(a)armlinux.org.uk> To: Thomas Bogendoerfer <tsbogend(a)alpha.franken.de> To: James E.J. Bottomley <James.Bottomley(a)HansenPartnership.com> To: Helge Deller <deller(a)gmx.de> To: Alexander Gordeev <agordeev(a)linux.ibm.com> To: Gerald Schaefer <gerald.schaefer(a)linux.ibm.com> To: Heiko Carstens <hca(a)linux.ibm.com> To: Vasily Gorbik <gor(a)linux.ibm.com> To: Christian Borntraeger <borntraeger(a)linux.ibm.com> To: Sven Schnelle <svens(a)linux.ibm.com> To: Yoshinori Sato <ysato(a)users.sourceforge.jp> To: Rich Felker <dalias(a)libc.org> To: John Paul Adrian Glaubitz <glaubitz(a)physik.fu-berlin.de> To: David S. Miller <davem(a)davemloft.net> To: Andreas Larsson <andreas(a)gaisler.com> To: Shuah Khan <shuah(a)kernel.org> To: Alexandre Ghiti <alexghiti(a)rivosinc.com> Cc: linux-arch(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: Palmer Dabbelt <palmer(a)rivosinc.com> Cc: linux-riscv(a)lists.infradead.org Cc: linux-arm-kernel(a)lists.infradead.org Cc: linuxppc-dev(a)lists.ozlabs.org Cc: linux-mm(a)kvack.org Cc: loongarch(a)lists.linux.dev Cc: linux-mips(a)vger.kernel.org Cc: linux-parisc(a)vger.kernel.org Cc: linux-s390(a)vger.kernel.org Cc: linux-sh(a)vger.kernel.org Cc: sparclinux(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Charlie Jenkins <charlie(a)rivosinc.com> --- Charlie Jenkins (16): mm: Add MAP_BELOW_HINT riscv: mm: Do not restrict mmap address based on hint mm: Add flag and len param to arch_get_mmap_base() mm: Add generic MAP_BELOW_HINT riscv: mm: Support MAP_BELOW_HINT arm64: mm: Support MAP_BELOW_HINT powerpc: mm: Support MAP_BELOW_HINT x86: mm: Support MAP_BELOW_HINT loongarch: mm: Support MAP_BELOW_HINT arm: mm: Support MAP_BELOW_HINT mips: mm: Support MAP_BELOW_HINT parisc: mm: Support MAP_BELOW_HINT s390: mm: Support MAP_BELOW_HINT sh: mm: Support MAP_BELOW_HINT sparc: mm: Support MAP_BELOW_HINT selftests/mm: Create MAP_BELOW_HINT test arch/arm/mm/mmap.c | 10 ++++++++ arch/arm64/include/asm/processor.h | 34 ++++++++++++++++++++++---- arch/loongarch/mm/mmap.c | 11 +++++++++ arch/mips/mm/mmap.c | 9 +++++++ arch/parisc/include/uapi/asm/mman.h | 1 + arch/parisc/kernel/sys_parisc.c | 9 +++++++ arch/powerpc/include/asm/task_size_64.h | 36 +++++++++++++++++++++++----- arch/riscv/include/asm/processor.h | 32 ------------------------- arch/s390/mm/mmap.c | 10 ++++++++ arch/sh/mm/mmap.c | 10 ++++++++ arch/sparc/kernel/sys_sparc_64.c | 8 +++++++ arch/x86/kernel/sys_x86_64.c | 25 ++++++++++++++++--- fs/hugetlbfs/inode.c | 2 +- include/linux/sched/mm.h | 34 ++++++++++++++++++++++++-- include/uapi/asm-generic/mman-common.h | 1 + mm/mmap.c | 2 +- tools/arch/parisc/include/uapi/asm/mman.h | 1 + tools/include/uapi/asm-generic/mman-common.h | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/map_below_hint.c | 29 ++++++++++++++++++++++ 20 files changed, 216 insertions(+), 50 deletions(-) --- base-commit: 5be63fc19fcaa4c236b307420483578a56986a37 change-id: 20240827-patches-below_hint_mmap-b13d79ae1c55 -- - Charlie

10 months

6
32
0 0

[PATCH v1 1/2] mseal: fix mmap(FIXED) error code.

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> mmap(MAP_FIXED) should return EPERM when memory is sealed. Fixes: 4205a39e06da ("mm/munmap: replace can_modify_mm with can_modify_vma") Signed-off-by: Jeff Xu <jeffxu(a)chromium.org> --- mm/mmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/mmap.c b/mm/mmap.c index 80d70ed099cf..0cd0c0ef03c7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1386,7 +1386,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr, mt_on_stack(mt_detach); mas_init(&mas_detach, &mt_detach, /* addr = */ 0); /* Prepare to unmap any existing mapping in the area */ - if (vms_gather_munmap_vmas(&vms, &mas_detach)) + error = vms_gather_munmap_vmas(&vms, &mas_detach); + if (error == -EPERM) + return -EPERM; + if (error) return -ENOMEM; vmg.next = vms.next; -- 2.46.0.295.g3b9ea8a38a-goog

10 months

8
19
0 0

[PATCH] selftests: splice: Add splice_read.sh and hint

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> Add test scripts and prompts. Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- tools/testing/selftests/splice/splice_read.c | 1 + tools/testing/selftests/splice/splice_read.sh | 9 +++++++++ 2 files changed, 10 insertions(+) create mode 100755 tools/testing/selftests/splice/splice_read.sh diff --git a/tools/testing/selftests/splice/splice_read.c b/tools/testing/selftests/splice/splice_read.c index 46dae6a25cfb..194b075f6bc0 100644 --- a/tools/testing/selftests/splice/splice_read.c +++ b/tools/testing/selftests/splice/splice_read.c @@ -49,6 +49,7 @@ int main(int argc, char *argv[]) size, SPLICE_F_MOVE); if (spliced < 0) { perror("splice"); + fprintf(stderr, "May try: %s /etc/os-release | cat\n", argv[0]); return EXIT_FAILURE; } diff --git a/tools/testing/selftests/splice/splice_read.sh b/tools/testing/selftests/splice/splice_read.sh new file mode 100755 index 000000000000..10fd5d738a2d --- /dev/null +++ b/tools/testing/selftests/splice/splice_read.sh @@ -0,0 +1,9 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +set -e +nl=$(./splice_read /etc/os-release | wc -l) + +test "$nl" != 0 && exit 0 + +echo "splice_read broken" +exit 1 -- 2.46.0

10 months

2
2
0 0

[PATCH] KVM: selftests: Add SEV-ES shutdown test

by Peter Gonda

Regression test for ae20eef5 ("KVM: SVM: Update SEV-ES shutdown intercepts with more metadata"). Test confirms userspace is correctly indicated of a guest shutdown not previous behavior of an EINVAL from KVM_RUN. Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <seanjc(a)google.com> Cc: Alper Gun <alpergun(a)google.com> Cc: Tom Lendacky <thomas.lendacky(a)amd.com> Cc: Michael Roth <michael.roth(a)amd.com> Cc: kvm(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Peter Gonda <pgonda(a)google.com> --- .../selftests/kvm/x86_64/sev_smoke_test.c | 26 +++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c index 7c70c0da4fb74..04f24d5f09877 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c @@ -160,6 +160,30 @@ static void test_sev(void *guest_code, uint64_t policy) kvm_vm_free(vm); } +static void guest_shutdown_code(void) +{ + __asm__ __volatile__("ud2"); +} + +static void test_sev_es_shutdown(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + uint32_t type = KVM_X86_SEV_ES_VM; + + vm = vm_sev_create_with_one_vcpu(type, guest_shutdown_code, &vcpu); + + vm_sev_launch(vm, SEV_POLICY_ES, NULL); + + vcpu_run(vcpu); + TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SHUTDOWN, + "Wanted SHUTDOWN, got %s", + exit_reason_str(vcpu->run->exit_reason)); + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); @@ -171,6 +195,8 @@ int main(int argc, char *argv[]) test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG); test_sev(guest_sev_es_code, SEV_POLICY_ES); + test_sev_es_shutdown(); + if (kvm_has_cap(KVM_CAP_XCRS) && (xgetbv(0) & XFEATURE_MASK_X87_AVX) == XFEATURE_MASK_X87_AVX) { test_sync_vmsa(0); -- 2.45.2.803.g4e1b14247a-goog

10 months

3
4
0 0

[PATCH-cgroup 0/2] cgroup/cpuset: Account for boot time isolated CPUs

by Waiman Long

The current cpuset code and test_cpuset_prs.sh test have not fully account for the possibility of pre-isolated CPUs added by the "isolcpus" boot command line parameter. This patch series modifies them to do the right thing whether or not "isolcpus" is present or not. The updated test_cpuset_prs.sh was run successfully with or without the "isolcpus" option. Waiman Long (2): cgroup/cpuset: Account for boot time isolated CPUs selftest/cgroup: Make test_cpuset_prs.sh deal with pre-isolated CPUs kernel/cgroup/cpuset.c | 23 +++++++--- .../selftests/cgroup/test_cpuset_prs.sh | 44 ++++++++++++++----- 2 files changed, 51 insertions(+), 16 deletions(-) -- 2.43.5

10 months

3
9
0 0

[PATCH net-next v23 00/13] Device Memory TCP

by Mina Almasry

v23: https://patchwork.kernel.org/project/netdevbpf/list/?series=882978&state=* ==== Fixing relatively minor issues called out in v22. (thanks again!) Mostly code cleanups, extack error messages, and minor reworks. Nothing major really changed, so the exact changes per commit is called in the commit messages. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v23/ v22: https://patchwork.kernel.org/project/netdevbpf/list/?series=881158&state=* ==== v22 aims to resolve the pending issue pointed to in v21, which is the interaction with xdp. In this series I rebase on top of the minor refactor which refactors propagating xdp configuration to slave devices: https://patchwork.kernel.org/project/netdevbpf/list/?series=881994&state=* I then disable setting xdp on devices using memory providers, and propagating xdp configuration to devices using memory providers. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v22/ v21: https://patchwork.kernel.org/project/netdevbpf/list/?series=880735&state=* ==== v20 addressed some comments and resolved a test failure, but introduced an unfortunate build error with a config edge case I wasn't testing. v21 simply resolves that error. Major Changes: - Resolve build error with CONFIG_PAGE_POOL=n && CONFIG_NET=y Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v21/ v20: https://patchwork.kernel.org/project/netdevbpf/list/?series=879373&state=* ==== v20 aims to resolve a couple of bug reports against v19, and addresses some review comments around the page_pool_check_memory_provider mechanism. Major changes: - Test edge cases such as header split disabled in selftest. - Change `offset = 0` back to `offset = offset - start` to resolve issue found in RX path by Taehee (thanks!) - Address a few comments around page_pool_check_memory_provider() from Pavel & Jakub. - Removed some unnecessary includes across various patches in the series. - Removed unnecessary EXPORT_SYMBOL(page_pool_mem_providers) (Jakub). - Fix regression caused by incorrect dev_get_max_mp_channel check, along with rename (Jakub). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v20/ v19: https://patchwork.kernel.org/project/netdevbpf/list/?series=876852&state=* ==== v18 got a thorough review (thanks!), and this iteration addresses the feedback. Major changes: - Prevent deactivating mp bound queues. - Prevent installing xdp on mp bound netdevs, or installing mps on xdp installed netdevs. - Fix corner cases in netlink API vis-a-vis missing attributes. - Iron out the unreadable netmem driver support story. To be honest, the conversation with Jakub & Pavel got a bit confusing for me. I've implemented an approach in this set that makes sense to me, and AFAICT, addresses the requirements. It may be good as-is, or it may be a conversation starter/continuer. To be honest IMO there are many ways to skin this cat and I don't see an extremely strong reason to go for one approach over another. Here is one approach you may like. - Don't reset niov dma_addr on allocation & free. - Add some tests to the selftest that catches some of the issues around missing netlink attributes or deactivating mp-bound queues. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v19/ v18: https://patchwork.kernel.org/project/netdevbpf/list/?series=874848&state=* ==== v17 got minor feedback: (a) to beef up the description on patch 1 and (b) to remove the leading underscores in the header definition. I applied (a). (b) seems to be against current conventions so I did not apply before further discussion. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v17: https://patchwork.kernel.org/project/netdevbpf/list/?series=869900&state=* ==== v16 also got a very thorough review and some testing (thanks again!). Thes version addresses all the concerns reported on v15, in terms of feedback and issues reported. Major changes: - Use ASSERT_RTNL. - Moved around some of the page_pool helpers definitions so I can hide some netmem helpers in private files as Jakub suggested. - Don't make every net_iov hold a ref on the binding as Jakub suggested. - Fix issue reported by Taehee where we access queues after they have been freed. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v16: https://patchwork.kernel.org/project/netdevbpf/list/?series=866353&state=* ==== v15 got a thorough review and some testing, and this version addresses almost all the feedback. Some more minor comments where the authors said it could be done later, I left out. Major changes: - Addition of dma-buf introspection to page-pool-get and queue-get. - Fixes to selftests suggested by Taehee. - Fixes to documentation suggested by Donald. - A couple of suggestions and fixes to TCP patches by Eric and David. - Fixes to number assignements suggested by Arnd. - Use rtnl_lock()ing to guard against queue reconfiguration while the page_pool initialization is happening. (Jakub). - Fixes to a few warnings reproduced by Taehee. - Fixes to dma-buf binding suggested by Taehee and Jakub. - Fixes to netlink UAPI suggested by Jakub - Applied a number of Reviewed-bys and Acked-bys (including ones I lost from v13+). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v16/ One caveat: Taehee reproduced a KASAN warning and reported it here: https://lore.kernel.org/netdev/CAMArcTUdCxOBYGF3vpbq=eBvqZfnc44KBaQTN7H-wqd… I estimate the issue to be minor and easily fixable: https://lore.kernel.org/netdev/CAHS8izNgaqC--GGE2xd85QB=utUnOHmioCsDd1TNxJW… I hope to be able to follow up with a fix to net tree as net-next closes imminently, but if this iteration doesn't make it in, I will repost with a fix squashed after net-next reopens, no problem. v15: https://patchwork.kernel.org/project/netdevbpf/list/?series=865481&state=* ==== No material changes in this version, only a fix to linking against libynl.a from the last version. Per Jakub's instructions I've pulled one of his patches into this series, and now use the new libynl.a correctly, I hope. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v15/ v14: https://patchwork.kernel.org/project/netdevbpf/list/?series=865135&archive=… ==== No material changes in this version. Only rebase and re-verification on top of net-next. v13, I think, raced with commit ebad6d0334793 ("net/ipv4: Use nested-BH locking for ipv4_tcp_sk.") being merged to net-next that caused a patchwork failure to apply. This series should apply cleanly on commit c4532232fa2a4 ("selftests: net: remove unneeded IP_GRE config"). I did not wait the customary 24hr as Jakub said it's OK to repost as soon as I build test the rebased version: https://lore.kernel.org/netdev/20240625075926.146d769d@kernel.org/ v13: https://patchwork.kernel.org/project/netdevbpf/list/?series=861406&archive=… ==== Major changes: -------------- This iteration addresses Pavel's review comments, applies his reviewed-by's, and seeks to fix the patchwork build error (sorry!). As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v13/ v12: https://patchwork.kernel.org/project/netdevbpf/list/?series=859747&state=* ==== Major changes: -------------- This iteration only addresses one minor comment from Pavel with regards to the trace printing of netmem, and the patchwork build error introduced in v11 because I missed doing an allmodconfig build, sorry. Other than that v11, AFAICT, received no feedback. There is one discussion about how the specifics of plugging io uring memory through the page pool, but not relevant to content in this particular patchset, AFAICT. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v12/ v11: https://patchwork.kernel.org/project/netdevbpf/list/?series=857457&state=* ==== Major Changes: -------------- v11 addresses feedback received in v10. The major change is the removal of the memory provider ops as requested by Christoph. We still accomplish the same thing, but utilizing direct function calls with if statements rather than generic ops. Additionally address sparse warnings, bugs and review comments from folks that reviewed. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v11/ Detailed changelog: ------------------- - Fixes in netdev_rx_queue_restart() from Pavel & David. - Remove commit e650e8c3a36f5 ("net: page_pool: create hooks for custom page providers") from the series to address Christoph's feedback and rebased other patches on the series on this change. - Fixed build errors with CONFIG_DMA_SHARED_BUFFER && !CONFIG_GENERIC_ALLOCATOR build. - Fixed sparse warnings pointed out by Paolo. - Drop unnecessary gro_pull_from_frag0 checks. - Added Bagas reviewed-by to docs. v10: https://patchwork.kernel.org/project/netdevbpf/list/?series=852422&state=* ==== Major Changes: -------------- v9 was sent right before the merge window closed (sorry!). v10 is almost a re-send of the series now that the merge window re-opened. Only rebased to latest net-next and addressed some minor iterative comments received on v9. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v10/ Detailed changelog: ------------------- - Fixed tokens leaking in DONTNEED setsockopt (Nikolay). - Moved net_iov_dma_addr() to devmem.c and made it a devmem specific helpers (David). - Rename hook alloc_pages to alloc_netmems as alloc_pages is now preprocessor macro defined and causes a build error. v9: === Major Changes: -------------- GVE queue API has been merged. Submitting this version as non-RFC after rebasing on top of the merged API, and dropped the out of tree queue API I was carrying on github. Addressed the little feedback v8 has received. Detailed changelog: ------------------ - Added new patch from David Wei to this series for netdev_rx_queue_restart() - Fixed sparse error. - Removed CONFIG_ checks in netmem_is_net_iov() - Flipped skb->readable to skb->unreadable - Minor fixes to selftests & docs. RFC v8: ======= Major Changes: -------------- - Fixed build error generated by patch-by-patch build. - Applied docs suggestions from Randy. RFC v7: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the feedback RFCv6 received from folks, namely Jakub, Yunsheng, Arnd, David, & Pavel. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v7/ Detailed changelog: - Use admin-perm in netlink API. - Addressed feedback from Jakub with regards to netlink API implementation. - Renamed devmem.c functions to something more appropriate for that file. - Improve the performance seen through the page_pool benchmark. - Fix the value definition of all the SO_DEVMEM_* uapi. - Various fixes to documentation. Perf - page-pool benchmark: --------------------------- Improved performance of bench_page_pool_simple.ko tests compared to v6: https://pastebin.com/raw/v5dYRg8L net-next base: 8 cycle fast path. RFC v6: 10 cycle fast path. RFC v7: 9 cycle fast path. RFC v7 with CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path, same as baseline. Perf - Devmem TCP benchmark: --------------------- Perf is about the same regardless of the changes in v7, namely the removal of the static_branch_unlikely to improve the page_pool benchmark performance: 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. RFC v6: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the little feedback RFCv5 received. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v6/ This version also comes with some performance data recorded in the cover letter (see below changelog). Detailed changelog: - Rebased on top of the merged netmem_ref changes. - Converted skb->dmabuf to skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag to tell whether an skb is readable or not. This can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring 0-copy RX. - Squashed a few locking optimizations from Eric Dumazet in the RX path and the DEVMEM_DONTNEED setsockopt. - Expanded the tests a bit. Added validation for invalid scenarios and added some more coverage. Perf - page-pool benchmark: --------------------------- bench_page_pool_simple.ko tests with and without these changes: https://pastebin.com/raw/ncHDwAbn AFAIK the number that really matters in the perf tests is the 'tasklet_page_pool01_fast_path Per elem'. This one measures at about 8 cycles without the changes but there is some 1 cycle noise in some results. With the patches this regresses to 9 cycles with the changes but there is 1 cycle noise occasionally running this test repeatedly. Lastly I tried disable the static_branch_unlikely() in netmem_is_net_iov() check. To my surprise disabling the static_branch_unlikely() check reduces the fast path back to 8 cycles, but the 1 cycle noise remains. Perf - Devmem TCP benchmark: --------------------- 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. Major changes in RFC v5: ======================== 1. Rebased on top of 'Abstract page from net stack' series and used the new netmem type to refer to LSB set pointers instead of re-using struct page. 2. Downgraded this series back to RFC and called it RFC v5. This is because this series is now dependent on 'Abstract page from net stack'[1] and the queue API. Both are removed from the series to reduce the patch # and those bits are fairly independent or pre-requisite work. 3. Reworked the page_pool devmem support to use netmem and for some more unified handling. 4. Reworked the reference counting of net_iov (renamed from page_pool_iov) to use pp_ref_count for refcounting. The full changes including the dependent series and GVE page pool support is here: https://github.com/mina/linux/commits/tcpdevmem-rfcv5/ [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=810774 Major changes in v1: ==================== 1. Implemented MVP queue API ndos to remove the userspace-visible driver reset. 2. Fixed issues in the napi_pp_put_page() devmem frag unref path. 3. Removed RFC tag. Many smaller addressed comments across all the patches (patches have individual change log). Full tree including the rest of the GVE driver changes: https://github.com/mina/linux/commits/tcpdevmem-v1 Changes in RFC v3: ================== 1. Pulled in the memory-provider dependency from Jakub's RFC[1] to make the series reviewable and mergeable. 2. Implemented multi-rx-queue binding which was a todo in v2. 3. Fix to cmsg handling. The sticking point in RFC v2[2] was the device reset required to refill the device rx-queues after the dmabuf bind/unbind. The solution suggested as I understand is a subset of the per-queue management ops Jakub suggested or similar: https://lore.kernel.org/netdev/20230815171638.4c057dcd@kernel.org/ This is not addressed in this revision, because: 1. This point was discussed at netconf & netdev and there is openness to using the current approach of requiring a device reset. 2. Implementing individual queue resetting seems to be difficult for my test bed with GVE. My prototype to test this ran into issues with the rx-queues not coming back up properly if reset individually. At the moment I'm unsure if it's a mistake in the POC or a genuine issue in the virtualization stack behind GVE, which currently doesn't test individual rx-queue restart. 3. Our usecases are not bothered by requiring a device reset to refill the buffer queues, and we'd like to support NICs that run into this limitation with resetting individual queues. My thought is that drivers that have trouble with per-queue configs can use the support in this series, while drivers that support new netdev ops to reset individual queues can automatically reset the queue as part of the dma-buf bind/unbind. The same approach with device resets is presented again for consideration with other sticking points addressed. This proposal includes the rx devmem path only proposed for merge. For a snapshot of my entire tree which includes the GVE POC page pool support & device memory support: https://github.com/torvalds/linux/compare/master...mina:linux:tcpdevmem-v3 [1] https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.… [2] https://lore.kernel.org/netdev/CAHS8izOVJGJH5WF68OsRWFKJid1_huzzUK+hpKbLcL4… Changes in RFC v2: ================== The sticking point in RFC v1[1] was the dma-buf pages approach we used to deliver the device memory to the TCP stack. RFC v2 is a proof-of-concept that attempts to resolve this by implementing scatterlist support in the networking stack, such that we can import the dma-buf scatterlist directly. This is the approach proposed at a high level here[2]. Detailed changes: 1. Replaced dma-buf pages approach with importing scatterlist into the page pool. 2. Replace the dma-buf pages centric API with a netlink API. 3. Removed the TX path implementation - there is no issue with implementing the TX path with scatterlist approach, but leaving out the TX path makes it easier to review. 4. Functionality is tested with this proposal, but I have not conducted perf testing yet. I'm not sure there are regressions, but I removed perf claims from the cover letter until they can be re-confirmed. 5. Added Signed-off-by: contributors to the implementation. 6. Fixed some bugs with the RX path since RFC v1. Any feedback welcome, but specifically the biggest pending questions needing feedback IMO are: 1. Feedback on the scatterlist-based approach in general. 2. Netlink API (Patch 1 & 2). 3. Approach to handle all the drivers that expect to receive pages from the page pool (Patch 6). [1] https://lore.kernel.org/netdev/dfe4bae7-13a0-3c5d-d671-f61b375cb0b4@gmail.c… [2] https://lore.kernel.org/netdev/CAHS8izPm6XRS54LdCDZVd0C75tA1zHSu6jLVO8nzTLX… ================== * TL;DR: Device memory TCP (devmem TCP) is a proposal for transferring data to and/or from device memory efficiently, without bouncing the data to a host memory buffer. * Problem: A large amount of data transfers have device memory as the source and/or destination. Accelerators drastically increased the volume of such transfers. Some examples include: - ML accelerators transferring large amounts of training data from storage into GPU/TPU memory. In some cases ML training setup time can be as long as 50% of TPU compute time, improving data transfer throughput & efficiency can help improving GPU/TPU utilization. - Distributed training, where ML accelerators, such as GPUs on different hosts, exchange data among them. - Distributed raw block storage applications transfer large amounts of data with remote SSDs, much of this data does not require host processing. Today, the majority of the Device-to-Device data transfers the network are implemented as the following low level operations: Device-to-Host copy, Host-to-Host network transfer, and Host-to-Device copy. The implementation is suboptimal, especially for bulk data transfers, and can put significant strains on system resources, such as host memory bandwidth, PCIe bandwidth, etc. One important reason behind the current state is the kernel’s lack of semantics to express device to network transfers. * Proposal: In this patch series we attempt to optimize this use case by implementing socket APIs that enable the user to: 1. send device memory across the network directly, and 2. receive incoming network packets directly into device memory. Packet _payloads_ go directly from the NIC to device memory for receive and from device memory to NIC for transmit. Packet _headers_ go to/from host memory and are processed by the TCP/IP stack normally. The NIC _must_ support header split to achieve this. Advantages: - Alleviate host memory bandwidth pressure, compared to existing network-transfer + device-copy semantics. - Alleviate PCIe BW pressure, by limiting data transfer to the lowest level of the PCIe tree, compared to traditional path which sends data through the root complex. * Patch overview: ** Part 1: netlink API Gives user ability to bind dma-buf to an RX queue. ** Part 2: scatterlist support Currently the standard for device memory sharing is DMABUF, which doesn't generate struct pages. On the other hand, networking stack (skbs, drivers, and page pool) operate on pages. We have 2 options: 1. Generate struct pages for dmabuf device memory, or, 2. Modify the networking stack to process scatterlist. Approach #1 was attempted in RFC v1. RFC v2 implements approach #2. ** part 3: page pool support We piggy back on page pool memory providers proposal: https://github.com/kuba-moo/linux/tree/pp-providers It allows the page pool to define a memory provider that provides the page allocation and freeing. It helps abstract most of the device memory TCP changes from the driver. ** part 4: support for unreadable skb frags Page pool iovs are not accessible by the host; we implement changes throughput the networking stack to correctly handle skbs with unreadable frags. ** Part 5: recvmsg() APIs We define user APIs for the user to send and receive device memory. Not included with this series is the GVE devmem TCP support, just to simplify the review. Code available here if desired: https://github.com/mina/linux/tree/tcpdevmem This series is built on top of net-next with Jakub's pp-providers changes cherry-picked. * NIC dependencies: 1. (strict) Devmem TCP require the NIC to support header split, i.e. the capability to split incoming packets into a header + payload and to put each into a separate buffer. Devmem TCP works by using device memory for the packet payload, and host memory for the packet headers. 2. (optional) Devmem TCP works better with flow steering support & RSS support, i.e. the NIC's ability to steer flows into certain rx queues. This allows the sysadmin to enable devmem TCP on a subset of the rx queues, and steer devmem TCP traffic onto these queues and non devmem TCP elsewhere. The NIC I have access to with these properties is the GVE with DQO support running in Google Cloud, but any NIC that supports these features would suffice. I may be able to help reviewers bring up devmem TCP on their NICs. * Testing: The series includes a udmabuf kselftest that show a simple use case of devmem TCP and validates the entire data path end to end without a dependency on a specific dmabuf provider. ** Test Setup Kernel: net-next with this series and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Cc: Pavel Begunkov <asml.silence(a)gmail.com> Cc: David Wei <dw(a)davidwei.uk> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Yunsheng Lin <linyunsheng(a)huawei.com> Cc: Shailend Chand <shailend(a)google.com> Cc: Harshitha Ramamurthy <hramamurthy(a)google.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Jeroen de Borst <jeroendb(a)google.com> Cc: Praveen Kaligineedi <pkaligineedi(a)google.com> Cc: Bagas Sanjaya <bagasdotme(a)gmail.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Nikolay Aleksandrov <razor(a)blackwall.org> Cc: Taehee Yoo <ap420073(a)gmail.com> Cc: Donald Hunter <donald.hunter(a)gmail.com> Mina Almasry (13): netdev: add netdev_rx_queue_restart() net: netdev netlink api to bind dma-buf to a net device netdev: support binding dma-buf to netdevice netdev: netdevice devmem allocator page_pool: devmem support memory-provider: dmabuf devmem memory provider net: support non paged skb frags net: add support for skbs with unreadable frags tcp: RX path for devmem TCP net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags net: add devmem TCP documentation selftests: add ncdevmem, netcat for devmem TCP netdev: add dmabuf introspection Documentation/netlink/specs/netdev.yaml | 61 +++ Documentation/networking/devmem.rst | 269 +++++++++++ Documentation/networking/index.rst | 1 + arch/alpha/include/uapi/asm/socket.h | 6 + arch/mips/include/uapi/asm/socket.h | 6 + arch/parisc/include/uapi/asm/socket.h | 6 + arch/sparc/include/uapi/asm/socket.h | 6 + include/linux/netdevice.h | 2 + include/linux/skbuff.h | 61 ++- include/linux/skbuff_ref.h | 9 +- include/linux/socket.h | 1 + include/net/devmem.h | 136 ++++++ include/net/mp_dmabuf_devmem.h | 44 ++ include/net/netdev_rx_queue.h | 5 + include/net/netmem.h | 163 ++++++- include/net/page_pool/helpers.h | 39 +- include/net/page_pool/types.h | 22 +- include/net/sock.h | 2 + include/net/tcp.h | 5 +- include/trace/events/page_pool.h | 12 +- include/uapi/asm-generic/socket.h | 6 + include/uapi/linux/netdev.h | 13 + include/uapi/linux/uio.h | 17 + net/Kconfig | 5 + net/core/Makefile | 2 + net/core/datagram.c | 6 + net/core/dev.c | 24 +- net/core/devmem.c | 388 ++++++++++++++++ net/core/gro.c | 3 +- net/core/netdev-genl-gen.c | 23 + net/core/netdev-genl-gen.h | 6 + net/core/netdev-genl.c | 134 +++++- net/core/netdev_rx_queue.c | 81 ++++ net/core/netmem_priv.h | 31 ++ net/core/page_pool.c | 117 +++-- net/core/page_pool_priv.h | 46 ++ net/core/page_pool_user.c | 31 +- net/core/skbuff.c | 77 +++- net/core/sock.c | 68 +++ net/ethtool/common.c | 8 + net/ipv4/esp4.c | 3 +- net/ipv4/tcp.c | 261 ++++++++++- net/ipv4/tcp_input.c | 13 +- net/ipv4/tcp_ipv4.c | 16 + net/ipv4/tcp_minisocks.c | 2 + net/ipv4/tcp_output.c | 5 +- net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 4 +- net/xdp/xsk_buff_pool.c | 5 + tools/include/uapi/linux/netdev.h | 13 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 9 + tools/testing/selftests/net/ncdevmem.c | 570 ++++++++++++++++++++++++ 53 files changed, 2723 insertions(+), 124 deletions(-) create mode 100644 Documentation/networking/devmem.rst create mode 100644 include/net/devmem.h create mode 100644 include/net/mp_dmabuf_devmem.h create mode 100644 net/core/devmem.c create mode 100644 net/core/netdev_rx_queue.c create mode 100644 net/core/netmem_priv.h create mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.46.0.469.g59c65b2a67-goog

10 months

4
25
0 0

[PATCH] kselftest/arm64: Fix build warnings for ptrace

by Dev Jain

A "%s" is missing in ksft_exit_fail_msg(); instead, use the newly introduced ksft_exit_fail_perror(). Signed-off-by: Dev Jain <dev.jain(a)arm.com> --- tools/testing/selftests/arm64/abi/ptrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c index e4fa507cbdd0..b51d21f78cf9 100644 --- a/tools/testing/selftests/arm64/abi/ptrace.c +++ b/tools/testing/selftests/arm64/abi/ptrace.c @@ -163,10 +163,10 @@ static void test_hw_debug(pid_t child, int type, const char *type_name) static int do_child(void) { if (ptrace(PTRACE_TRACEME, -1, NULL, NULL)) - ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno)); + ksft_exit_fail_perror("PTRACE_TRACEME"); if (raise(SIGSTOP)) - ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno)); + ksft_exit_fail_perror("raise(SIGSTOP)"); return EXIT_SUCCESS; } -- 2.30.2

10 months

4
3
0 0

[PATCH] kselftest/arm64: Actually test SME vector length changes via sigreturn

by Mark Brown

The test case for SME vector length changes via sigreturn use a bit too much cut'n'paste and only actually changed the SVE vector length in the test itself. Andre's recent factoring out of the initialisation code caused this to be exposed and the test to start failing. Fix the test to actually cover the thing it's supposed to test. Fixes: 4963aeb35a9e ("kselftest/arm64: signal: Add SME signal handling tests") Signed-off-by: Mark Brown <broonie(a)kernel.org> --- .../arm64/signal/testcases/fake_sigreturn_sme_change_vl.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c index cb8c051b5c8f..dfd6a2badf9f 100644 --- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c @@ -35,30 +35,30 @@ static int fake_sigreturn_ssve_change_vl(struct tdescr *td, { size_t resv_sz, offset; struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf); - struct sve_context *sve; + struct za_context *za; /* Get a signal context with a SME ZA frame in it */ if (!get_current_context(td, &sf.uc, sizeof(sf.uc))) return 1; resv_sz = GET_SF_RESV_SIZE(sf); - head = get_header(head, SVE_MAGIC, resv_sz, &offset); + head = get_header(head, ZA_MAGIC, resv_sz, &offset); if (!head) { - fprintf(stderr, "No SVE context\n"); + fprintf(stderr, "No ZA context\n"); return 1; } - if (head->size != sizeof(struct sve_context)) { + if (head->size != sizeof(struct za_context)) { fprintf(stderr, "Register data present, aborting\n"); return 1; } - sve = (struct sve_context *)head; + za = (struct za_context *)head; /* No changes are supported; init left us at minimum VL so go to max */ fprintf(stderr, "Attempting to change VL from %d to %d\n", - sve->vl, vls[0]); - sve->vl = vls[0]; + za->vl, vls[0]); + za->vl = vls[0]; fake_sigreturn(&sf, sizeof(sf), 0); --- base-commit: b18bbfc14a38b5234e09c2adcf713e38063a7e6e change-id: 20240829-arm64-sme-signal-vl-change-test-cebe4035856a Best regards, -- Mark Brown <broonie(a)kernel.org>

10 months

3
2
0 0

[PATCH] selftest/vDSO: Fix cross build for the random tests

by Mark Brown

Unlike the check for the standalone x86 test the check for building the vDSO getrandom and chacaha tests looks at the architecture for the host rather than the architecture for the target when deciding if they should be built. Since the chacha test includes some assembler code this means that cross building with x86 as either the target or host is broken. Use a check for ARCH instead. Fixes: 4920a2590e91 ("selftests/vDSO: add tests for vgetrandom") Signed-off-by: Mark Brown <broonie(a)kernel.org> --- The x86_64 build is still broken for me because nothing installs tools/arch/x86_64/vdso/vgetrandom-chacha.S (I beleive it's supposed to be copied from ./arch/x86/entry/vdso/vgetrandom-chacha.S but I don't see how?) but this at least fixes all the other architectures. --- tools/testing/selftests/vDSO/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index e21e78aae24d..7fb59310718c 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -10,7 +10,7 @@ ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64)) TEST_GEN_PROGS += vdso_standalone_test_x86 endif TEST_GEN_PROGS += vdso_test_correctness -ifeq ($(uname_M),x86_64) +ifeq ($(ARCH),$(filter $(ARCH),x86_64)) TEST_GEN_PROGS += vdso_test_getrandom TEST_GEN_PROGS += vdso_test_chacha endif --- base-commit: 985bf40edf4343dcb04c33f58b40b4a85c1776d4 change-id: 20240830-vdso-chacha-build-8d3789bf695c Best regards, -- Mark Brown <broonie(a)kernel.org>

10 months

2
7
0 0

[PATCH v2 0/4] Increase mseal test coverage

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> This series increase the test coverage of mseal_test by: Add check for vma_size, prot, and error code for existing tests. Add more testcases for madvise, munmap, mmap and mremap to cover sealing in different scenarios. The increase test coverage hopefully help to prevent future regression. It doesn't change any existing mm api's semantics, i.e. it will pass on linux main and 6.10 branch. Note: in order to pass this test in mm-unstable, mm-unstable must have Liam's fix on mmap [1] [1] https://lore.kernel.org/linux-kselftest/vyllxuh5xbqmaoyl2mselebij5ox7cseekj… History: V2: - remove the mmap fix (Liam R. Howlett will fix it separately) - Add cover letter (Lorenzo Stoakes) - split the testcase for ease of review (Mark Brown) V1: - https://lore.kernel.org/linux-kselftest/20240828225522.684774-1-jeffxu@chro… Jeff Xu (4): selftests/mm: mseal_test, add vma size check selftests/mm: mseal_test add sealed madvise type selftests/mm: mseal_test add more tests for mmap selftests/mm: mseal_test add more tests for mremap tools/testing/selftests/mm/mseal_test.c | 829 ++++++++++++++++++++++-- 1 file changed, 762 insertions(+), 67 deletions(-) -- 2.46.0.469.g59c65b2a67-goog

10 months

3
12
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror