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

[PATCH bpf-next v2 0/3] Add overwrite mode for bpf ring buffer

by Xu Kuohai

When the bpf ring buffer is full, new events can not be recorded util the consumer consumes some events to free space. This may cause critical events to be discarded, such as in fault diagnostic, where recent events are more critical than older ones. So add ovewrite mode for bpf ring buffer. In this mode, the new event overwrites the oldest event when the buffer is full. v2: - remove libbpf changes (Andrii) - update overwrite benchmark v1: https://lore.kernel.org/bpf/20250804022101.2171981-1-xukuohai@huaweicloud.c… Xu Kuohai (3): bpf: Add overwrite mode for bpf ring buffer selftests/bpf: Add test for overwrite ring buffer selftests/bpf/benchs: Add producer and overwrite bench for ring buffer include/uapi/linux/bpf.h | 4 + kernel/bpf/ringbuf.c | 159 +++++++++++++++--- tools/include/uapi/linux/bpf.h | 4 + tools/testing/selftests/bpf/Makefile | 3 +- tools/testing/selftests/bpf/bench.c | 2 + .../selftests/bpf/benchs/bench_ringbufs.c | 95 ++++++++++- .../bpf/benchs/run_bench_ringbufs.sh | 4 + .../selftests/bpf/prog_tests/ringbuf.c | 74 ++++++++ .../selftests/bpf/progs/ringbuf_bench.c | 10 ++ .../bpf/progs/test_ringbuf_overwrite.c | 98 +++++++++++ 10 files changed, 418 insertions(+), 35 deletions(-) create mode 100644 tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c -- 2.43.0

1 week, 3 days

1
3
0 0

[PATCH] selftests/mm: refactore split_huge_page_test with kselftest_harness

by Wei Yang

Refactor split_huge_page_test with kselftest_harness, since there is a magic counting about valid tests. The idea is simple: For standalone test, put it into TEST(). For tests iterating order/offset, define fixture and variant with order and offset. And skip it if order/offset is not valid. No functional change is expected. Signed-off-by: Wei Yang <richard.weiyang(a)gmail.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Zi Yan <ziy(a)nvidia.com> Cc: Donet Tom <donettom(a)linux.ibm.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> --- .../selftests/mm/split_huge_page_test.c | 308 ++++++++++++++---- 1 file changed, 238 insertions(+), 70 deletions(-) diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 7731191cc8e9..2376c3530b26 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -20,14 +20,16 @@ #include <stdbool.h> #include <time.h> #include "vm_util.h" -#include "../kselftest.h" +#include "../kselftest_harness.h" uint64_t pagesize; -unsigned int pageshift; uint64_t pmd_pagesize; unsigned int pmd_order; int *expected_orders; +char *optional_xfs_path; +char fs_loc_template[] = "/tmp/thp_fs_XXXXXX"; + #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages" #define SMAP_PATH "/proc/self/smaps" #define INPUT_MAX 80 @@ -41,6 +43,20 @@ const char *kpageflags_proc = "/proc/kpageflags"; int pagemap_fd; int kpageflags_fd; +#define ADD_VARIANT_ORDER(fixture_name, ord) \ + FIXTURE_VARIANT_ADD(fixture_name, order_##ord) \ + { \ + .order = ord, \ + } + +#define ADD_VARIANT_ORDER_OFFSET(fixture_name, ord, stp) \ + FIXTURE_VARIANT_ADD(fixture_name, order_##ord##_stp_##stp) \ + { \ + .order = ord, \ + .step = stp, \ + } + + static bool is_backed_by_folio(char *vaddr, int order, int pagemap_fd, int kpageflags_fd) { @@ -255,6 +271,26 @@ static int check_after_split_folio_orders(char *vaddr_start, size_t len, return status; } +void prepare_proc_fd(void) +{ + pagemap_fd = open(pagemap_proc, O_RDONLY); + if (pagemap_fd == -1) + ksft_exit_fail_msg("read pagemap: %s\n", strerror(errno)); + + kpageflags_fd = open(kpageflags_proc, O_RDONLY); + if (kpageflags_fd == -1) + ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno)); +} + +void cleanup_proc_fd(void) +{ + if (pagemap_fd != -1) + close(pagemap_fd); + + if (kpageflags_fd != -1) + close(kpageflags_fd); +} + static void write_file(const char *path, const char *buf, size_t buflen) { int fd; @@ -292,10 +328,8 @@ static char *allocate_zero_filled_hugepage(size_t len) size_t i; result = memalign(pmd_pagesize, len); - if (!result) { - printf("Fail to allocate memory\n"); - exit(EXIT_FAILURE); - } + if (!result) + ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); madvise(result, len, MADV_HUGEPAGE); @@ -334,16 +368,19 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp rss_anon_before, rss_anon_after); } -static void split_pmd_zero_pages(void) +TEST(split_pmd_zero_pages) { char *one_page; int nr_hpages = 4; size_t len = nr_hpages * pmd_pagesize; + prepare_proc_fd(); + one_page = allocate_zero_filled_hugepage(len); verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len); - ksft_test_result_pass("Split zero filled huge pages successful\n"); free(one_page); + + cleanup_proc_fd(); } static void split_pmd_thp_to_order(int order) @@ -383,11 +420,10 @@ static void split_pmd_thp_to_order(int order) if (!check_huge_anon(one_page, 0, pmd_pagesize)) ksft_exit_fail_msg("Still AnonHugePages not split\n"); - ksft_test_result_pass("Split huge pages to order %d successful\n", order); free(one_page); } -static void split_pte_mapped_thp(void) +TEST(split_pte_mapped_thp) { const size_t nr_thps = 4; const size_t thp_area_size = nr_thps * pmd_pagesize; @@ -395,6 +431,8 @@ static void split_pte_mapped_thp(void) char *thp_area, *tmp, *page_area = MAP_FAILED; size_t i; + prepare_proc_fd(); + thp_area = mmap((void *)(1UL << 30), thp_area_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (thp_area == MAP_FAILED) { @@ -470,14 +508,43 @@ static void split_pte_mapped_thp(void) ksft_test_result_fail("THP %zu not split\n", i); } - ksft_test_result_pass("Split PTE-mapped huge pages successful\n"); out: munmap(thp_area, thp_area_size); if (page_area != MAP_FAILED) munmap(page_area, page_area_size); + cleanup_proc_fd(); +} + +FIXTURE(split_file_backed_thp) { +}; + +FIXTURE_VARIANT(split_file_backed_thp) { + int order; +}; + +FIXTURE_SETUP(split_file_backed_thp) +{ + if (variant->order >= pmd_order) + SKIP(return, "order %d is not supported", variant->order); + prepare_proc_fd(); +} + +FIXTURE_TEARDOWN(split_file_backed_thp) +{ + cleanup_proc_fd(); } -static void split_file_backed_thp(int order) +ADD_VARIANT_ORDER(split_file_backed_thp, 0); +ADD_VARIANT_ORDER(split_file_backed_thp, 1); +ADD_VARIANT_ORDER(split_file_backed_thp, 2); +ADD_VARIANT_ORDER(split_file_backed_thp, 3); +ADD_VARIANT_ORDER(split_file_backed_thp, 4); +ADD_VARIANT_ORDER(split_file_backed_thp, 5); +ADD_VARIANT_ORDER(split_file_backed_thp, 6); +ADD_VARIANT_ORDER(split_file_backed_thp, 7); +ADD_VARIANT_ORDER(split_file_backed_thp, 8); + +TEST_F(split_file_backed_thp, orders) { int status; int fd; @@ -487,7 +554,7 @@ static void split_file_backed_thp(int order) ssize_t num_written, num_read; char *file_buf1, *file_buf2; uint64_t pgoff_start = 0, pgoff_end = 1024; - int i; + int i, order = variant->order; ksft_print_msg("Please enable pr_debug in split_huge_pages_in_file() for more info.\n"); @@ -567,7 +634,6 @@ static void split_file_backed_thp(int order) ksft_exit_fail_msg("cannot remove tmp dir: %s\n", strerror(errno)); ksft_print_msg("Please check dmesg for more information\n"); - ksft_test_result_pass("File-backed THP split to order %d test done\n", order); return; close_file: @@ -579,6 +645,45 @@ static void split_file_backed_thp(int order) ksft_exit_fail_msg("Error occurred\n"); } +FIXTURE(split_pmd_thp_to_order) { +}; + +FIXTURE_VARIANT(split_pmd_thp_to_order) { + int order; +}; + +FIXTURE_SETUP(split_pmd_thp_to_order) +{ + if (variant->order >= pmd_order) + SKIP(return, "order %d is not supported", variant->order); + + expected_orders = (int *)malloc(sizeof(int) * (pmd_order + 1)); + if (!expected_orders) + ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); + + prepare_proc_fd(); +} + +FIXTURE_TEARDOWN(split_pmd_thp_to_order) +{ + free(expected_orders); + cleanup_proc_fd(); +} + +ADD_VARIANT_ORDER(split_pmd_thp_to_order, 0); +ADD_VARIANT_ORDER(split_pmd_thp_to_order, 2); +ADD_VARIANT_ORDER(split_pmd_thp_to_order, 3); +ADD_VARIANT_ORDER(split_pmd_thp_to_order, 4); +ADD_VARIANT_ORDER(split_pmd_thp_to_order, 5); +ADD_VARIANT_ORDER(split_pmd_thp_to_order, 6); +ADD_VARIANT_ORDER(split_pmd_thp_to_order, 7); +ADD_VARIANT_ORDER(split_pmd_thp_to_order, 8); + +TEST_F(split_pmd_thp_to_order, order) +{ + split_pmd_thp_to_order(variant->order); +} + static bool prepare_thp_fs(const char *xfs_path, char *thp_fs_template, const char **thp_fs_loc) { @@ -757,81 +862,144 @@ static void split_thp_in_pagecache_to_order_at(size_t fd_size, } } -int main(int argc, char **argv) -{ - int i; - size_t fd_size; - char *optional_xfs_path = NULL; - char fs_loc_template[] = "/tmp/thp_fs_XXXXXX"; +FIXTURE(split_thp_in_pagecache_to_order) { + bool created_tmp; const char *fs_loc; +}; + +FIXTURE_VARIANT(split_thp_in_pagecache_to_order) { + int order; +}; + +FIXTURE_SETUP(split_thp_in_pagecache_to_order) +{ + /* limit order to less than pmd_order */ + if (variant->order >= pmd_order) + SKIP(return, "order %d is not supported", variant->order); + expected_orders = (int *)malloc(sizeof(int) * (pmd_order + 1)); + if (!expected_orders) + ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); + + self->created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template, + &self->fs_loc); + prepare_proc_fd(); +} + +FIXTURE_TEARDOWN(split_thp_in_pagecache_to_order) +{ + cleanup_proc_fd(); + cleanup_thp_fs(self->fs_loc, self->created_tmp); + free(expected_orders); +} + +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 8); +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 7); +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 6); +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 5); +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 4); +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 3); +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 2); +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 1); +ADD_VARIANT_ORDER(split_thp_in_pagecache_to_order, 0); + +TEST_F(split_thp_in_pagecache_to_order, order) +{ + size_t fd_size = 2 * pmd_pagesize; + + split_thp_in_pagecache_to_order_at(fd_size, self->fs_loc, variant->order, -1); +} + +FIXTURE(split_thp_in_pagecache_to_order_offset) { bool created_tmp; + const char *fs_loc; int offset; - unsigned int nr_pages; - unsigned int tests; +}; - ksft_print_header(); +FIXTURE_VARIANT(split_thp_in_pagecache_to_order_offset) { + int order; + int step; +}; - if (geteuid() != 0) { - ksft_print_msg("Please run the benchmark as root\n"); - ksft_finished(); - } - - if (argc > 1) - optional_xfs_path = argv[1]; +FIXTURE_SETUP(split_thp_in_pagecache_to_order_offset) +{ + int nr_pages = pmd_pagesize / pagesize; + int offset = variant->step * MAX(nr_pages / 4, 1 << variant->order); - pagesize = getpagesize(); - pageshift = ffs(pagesize) - 1; - pmd_pagesize = read_pmd_pagesize(); - if (!pmd_pagesize) - ksft_exit_fail_msg("Reading PMD pagesize failed\n"); + /* limit order to less than pmd_order */ + if (variant->order >= pmd_order) + SKIP(return, "order %d is not supported", variant->order); - nr_pages = pmd_pagesize / pagesize; - pmd_order = sz2ord(pmd_pagesize, pagesize); + if (offset < nr_pages) + self->offset = offset; + else + SKIP(return, "offset out of thp range"); expected_orders = (int *)malloc(sizeof(int) * (pmd_order + 1)); if (!expected_orders) ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno)); - tests = 2 + (pmd_order - 1) + (2 * pmd_order) + (pmd_order - 1) * 4 + 2; - ksft_set_plan(tests); - - pagemap_fd = open(pagemap_proc, O_RDONLY); - if (pagemap_fd == -1) - ksft_exit_fail_msg("read pagemap: %s\n", strerror(errno)); - - kpageflags_fd = open(kpageflags_proc, O_RDONLY); - if (kpageflags_fd == -1) - ksft_exit_fail_msg("read kpageflags: %s\n", strerror(errno)); + self->created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template, + &self->fs_loc); + prepare_proc_fd(); +} - fd_size = 2 * pmd_pagesize; +FIXTURE_TEARDOWN(split_thp_in_pagecache_to_order_offset) +{ + cleanup_proc_fd(); + cleanup_thp_fs(self->fs_loc, self->created_tmp); + free(expected_orders); +} - split_pmd_zero_pages(); +#define SPLIT_IN_PAGECACHE_ORDER_OFFSETS(ord) \ + ADD_VARIANT_ORDER_OFFSET(split_thp_in_pagecache_to_order_offset, ord, 0);\ + ADD_VARIANT_ORDER_OFFSET(split_thp_in_pagecache_to_order_offset, ord, 1);\ + ADD_VARIANT_ORDER_OFFSET(split_thp_in_pagecache_to_order_offset, ord, 2);\ + ADD_VARIANT_ORDER_OFFSET(split_thp_in_pagecache_to_order_offset, ord, 3)\ + +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(0); +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(1); +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(2); +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(3); +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(4); +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(5); +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(6); +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(7); +SPLIT_IN_PAGECACHE_ORDER_OFFSETS(8); + +TEST_F(split_thp_in_pagecache_to_order_offset, order_offset) +{ + size_t fd_size = 2 * pmd_pagesize; - for (i = 0; i < pmd_order; i++) - if (i != 1) - split_pmd_thp_to_order(i); + split_thp_in_pagecache_to_order_at(fd_size, self->fs_loc, + variant->order, self->offset); +} - split_pte_mapped_thp(); - for (i = 0; i < pmd_order; i++) - split_file_backed_thp(i); +int main(int argc, char **argv) +{ + int i; - created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template, - &fs_loc); - for (i = pmd_order - 1; i >= 0; i--) - split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, -1); + if (geteuid() != 0) { + ksft_print_msg("Please run the benchmark as root\n"); + ksft_finished(); + } - for (i = 0; i < pmd_order; i++) - for (offset = 0; - offset < nr_pages; - offset += MAX(nr_pages / 4, 1 << i)) - split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, offset); - cleanup_thp_fs(fs_loc, created_tmp); + for (i = 1; i < argc; i++) { + /* only one parameter supported */ + if (*argv[i] != '-') { + optional_xfs_path = argv[i]; + break; + } - close(pagemap_fd); - close(kpageflags_fd); - free(expected_orders); + /* option -l/-h has no parameter */ + if (*(argv[i] + 1) != 'l' && *(argv[i] + 1) != 'h') + i++; + } - ksft_finished(); + pagesize = getpagesize(); + pmd_pagesize = read_pmd_pagesize(); + if (!pmd_pagesize) + ksft_exit_fail_msg("Reading PMD pagesize failed\n"); + pmd_order = sz2ord(pmd_pagesize, pagesize); - return 0; + return test_harness_run(argc, argv); } -- 2.34.1

1 week, 4 days

3
4
0 0

next-20250905: x86_64: udpgso_bench.sh triggers NULL deref in zerocopy_fill_skb_from_iter

by Naresh Kamboju

The following kernel crash was noticed on x86_64 running selftests net udpgso_bench.sh on Linux next-20250905 tag. Regression Analysis: - New regression? yes - Reproducibility? Re-validation is in progress First seen on next-20250905 Bad: next-20250905 Good: next-20250904 Test regression: next-20250905 x86_64 selftests net BUG kernel NULL pointer dereference zerocopy_fill_skb_from_iter Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> x86_64: Test: * selftests: net: udpgso_bench.sh Test error: selftests: net: udpgso_bench.sh ipv4 tcp <trim> # tcp zerocopy [ 991.110488] SELinux: unrecognized netlink message: protocol=4 nlmsg_type=19 sclass=netlink_tcpdiag_socket pid=64835 comm=ss # RTNETLINK answers: Invalid argument [ 991.129878] BUG: kernel NULL pointer dereference, address: 0000000000000008 [ 991.136850] #PF: supervisor read access in kernel mode [ 991.141986] #PF: error_code(0x0000) - not-present page [ 991.147118] PGD 0 P4D 0 [ 991.149657] Oops: Oops: 0000 [#1] SMP PTI [ 991.153661] CPU: 0 UID: 0 PID: 64842 Comm: udpgso_bench_tx Tainted: G S 6.17.0-rc4-next-20250905 #1 PREEMPT(voluntary) [ 991.165907] Tainted: [S]=CPU_OUT_OF_SPEC [ 991.169825] Hardware name: Supermicro SYS-5019S-ML/X11SSH-F, BIOS 2.7 12/07/2021 [ 991.177209] RIP: 0010:zerocopy_fill_skb_from_iter (include/linux/page-flags.h:284) [ 991.182954] Code: 4d 85 c0 0f 84 04 01 00 00 44 39 c7 41 0f 4d f8 4c 63 de 4a 8b 54 dc 30 49 89 d6 4d 29 ce 49 c1 fe 06 49 d3 ee 4d 85 f6 74 24 <48> 8b 4a 08 f6 c1 01 0f 85 cb 00 00 00 0f 1f 44 00 00 31 c9 48 f7 All code ======== 0: 4d 85 c0 test %r8,%r8 3: 0f 84 04 01 00 00 je 0x10d 9: 44 39 c7 cmp %r8d,%edi c: 41 0f 4d f8 cmovge %r8d,%edi 10: 4c 63 de movslq %esi,%r11 13: 4a 8b 54 dc 30 mov 0x30(%rsp,%r11,8),%rdx 18: 49 89 d6 mov %rdx,%r14 1b: 4d 29 ce sub %r9,%r14 1e: 49 c1 fe 06 sar $0x6,%r14 22: 49 d3 ee shr %cl,%r14 25: 4d 85 f6 test %r14,%r14 28: 74 24 je 0x4e 2a:* 48 8b 4a 08 mov 0x8(%rdx),%rcx <-- trapping instruction 2e: f6 c1 01 test $0x1,%cl 31: 0f 85 cb 00 00 00 jne 0x102 37: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 3c: 31 c9 xor %ecx,%ecx 3e: 48 rex.W 3f: f7 .byte 0xf7 Code starting with the faulting instruction =========================================== 0: 48 8b 4a 08 mov 0x8(%rdx),%rcx 4: f6 c1 01 test $0x1,%cl 7: 0f 85 cb 00 00 00 jne 0xd8 d: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 12: 31 c9 xor %ecx,%ecx 14: 48 rex.W 15: f7 .byte 0xf7 [ 991.201691] RSP: 0018:ffffb11281d0ba90 EFLAGS: 00010202 [ 991.206910] RAX: ffffe14ec4208000 RBX: 0000000000005000 RCX: 0000000000000009 [ 991.214033] RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000001000 [ 991.221156] RBP: ffffb11281d0bb88 R08: 00000000000020ff R09: ffffe14ec4208000 [ 991.228280] R10: 0000000000000005 R11: 0000000000000006 R12: ffff96b4825f4200 [ 991.235406] R13: 0000000000000001 R14: 000000003d6277bf R15: 0000000000000000 [ 991.242529] FS: 00007f41e80b9740(0000) GS:ffff96b83bc1b000(0000) knlGS:0000000000000000 [ 991.250608] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 991.256378] CR2: 0000000000000008 CR3: 0000000106c42003 CR4: 00000000003706f0 [ 991.263513] Call Trace: [ 991.265956] <TASK> [ 991.268055] __zerocopy_sg_from_iter (net/core/datagram.c:?) [ 991.272674] ? kmalloc_reserve (net/core/skbuff.c:581) [ 991.276599] skb_zerocopy_iter_stream (net/core/skbuff.c:1867) [ 991.281219] tcp_sendmsg_locked (net/ipv4/tcp.c:1283) [ 991.285493] tcp_sendmsg (net/ipv4/tcp.c:1393) [ 991.288896] inet6_sendmsg (net/ipv6/af_inet6.c:661) [ 991.292466] __sock_sendmsg (net/socket.c:717) [ 991.296126] __sys_sendto (net/socket.c:?) [ 991.299785] __x64_sys_sendto (net/socket.c:2235 net/socket.c:2231 net/socket.c:2231) [ 991.303622] x64_sys_call (arch/x86/entry/syscall_64.c:41) [ 991.307462] do_syscall_64 (arch/x86/entry/syscall_64.c:?) [ 991.311128] ? irqentry_exit (kernel/entry/common.c:210) [ 991.314881] ? exc_page_fault (arch/x86/mm/fault.c:1536) [ 991.318720] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) [ 991.323762] RIP: 0033:0x7f41e814b687 [ 991.327352] Code: 48 89 fa 4c 89 df e8 58 b3 00 00 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 1a 5b c3 0f 1f 84 00 00 00 00 00 48 8b 44 24 10 0f 05 <5b> c3 0f 1f 80 00 00 00 00 83 e2 39 83 fa 08 75 de e8 23 ff ff ff All code ======== 0: 48 89 fa mov %rdi,%rdx 3: 4c 89 df mov %r11,%rdi 6: e8 58 b3 00 00 call 0xb363 b: 8b 93 08 03 00 00 mov 0x308(%rbx),%edx 11: 59 pop %rcx 12: 5e pop %rsi 13: 48 83 f8 fc cmp $0xfffffffffffffffc,%rax 17: 74 1a je 0x33 19: 5b pop %rbx 1a: c3 ret 1b: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1) 22: 00 23: 48 8b 44 24 10 mov 0x10(%rsp),%rax 28: 0f 05 syscall 2a:* 5b pop %rbx <-- trapping instruction 2b: c3 ret 2c: 0f 1f 80 00 00 00 00 nopl 0x0(%rax) 33: 83 e2 39 and $0x39,%edx 36: 83 fa 08 cmp $0x8,%edx 39: 75 de jne 0x19 3b: e8 23 ff ff ff call 0xffffffffffffff63 Code starting with the faulting instruction =========================================== 0: 5b pop %rbx 1: c3 ret 2: 0f 1f 80 00 00 00 00 nopl 0x0(%rax) 9: 83 e2 39 and $0x39,%edx c: 83 fa 08 cmp $0x8,%edx f: 75 de jne 0xffffffffffffffef 11: e8 23 ff ff ff call 0xffffffffffffff39 [ 991.346124] RSP: 002b:00007ffdd843ba50 EFLAGS: 00000202 ORIG_RAX: 000000000000002c [ 991.353680] RAX: ffffffffffffffda RBX: 00007f41e80b9740 RCX: 00007f41e814b687 [ 991.360806] RDX: 000000000000f180 RSI: 000056251f1fd100 RDI: 0000000000000005 [ 991.367931] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 [ 991.375063] R10: 0000000004000000 R11: 0000000000000202 R12: 0000000000000000 [ 991.382193] R13: 000056251f1fb080 R14: 000001a670e438d8 R15: 0000000000000005 [ 991.389357] </TASK> [ 991.391571] Modules linked in: mptcp_diag tcp_diag inet_diag xt_conntrack xfrm_user ipip bridge stp llc geneve vxlan act_csum act_pedit openvswitch nsh nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 psample cls_flower sch_prio xt_mark nft_compat nf_tables sch_ingress act_mirred cls_basic sch_fq_codel vrf pktgen macvtap macvlan tap x86_pkg_temp_thermal ip_tables x_tables [last unloaded: test_bpf] [ 991.426812] CR2: 0000000000000008 [ 991.430121] ---[ end trace 0000000000000000 ]--- [ 991.434733] RIP: 0010:zerocopy_fill_skb_from_iter (include/linux/page-flags.h:284) [ 991.440477] Code: 4d 85 c0 0f 84 04 01 00 00 44 39 c7 41 0f 4d f8 4c 63 de 4a 8b 54 dc 30 49 89 d6 4d 29 ce 49 c1 fe 06 49 d3 ee 4d 85 f6 74 24 <48> 8b 4a 08 f6 c1 01 0f 85 cb 00 00 00 0f 1f 44 00 00 31 c9 48 f7 All code ======== 0: 4d 85 c0 test %r8,%r8 3: 0f 84 04 01 00 00 je 0x10d 9: 44 39 c7 cmp %r8d,%edi c: 41 0f 4d f8 cmovge %r8d,%edi 10: 4c 63 de movslq %esi,%r11 13: 4a 8b 54 dc 30 mov 0x30(%rsp,%r11,8),%rdx 18: 49 89 d6 mov %rdx,%r14 1b: 4d 29 ce sub %r9,%r14 1e: 49 c1 fe 06 sar $0x6,%r14 22: 49 d3 ee shr %cl,%r14 25: 4d 85 f6 test %r14,%r14 28: 74 24 je 0x4e 2a:* 48 8b 4a 08 mov 0x8(%rdx),%rcx <-- trapping instruction 2e: f6 c1 01 test $0x1,%cl 31: 0f 85 cb 00 00 00 jne 0x102 37: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 3c: 31 c9 xor %ecx,%ecx 3e: 48 rex.W 3f: f7 .byte 0xf7 Code starting with the faulting instruction =========================================== 0: 48 8b 4a 08 mov 0x8(%rdx),%rcx 4: f6 c1 01 test $0x1,%cl 7: 0f 85 cb 00 00 00 jne 0xd8 d: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 12: 31 c9 xor %ecx,%ecx 14: 48 rex.W 15: f7 .byte 0xf7 [ 991.459215] RSP: 0018:ffffb11281d0ba90 EFLAGS: 00010202 [ 991.464434] RAX: ffffe14ec4208000 RBX: 0000000000005000 RCX: 0000000000000009 [ 991.471557] RDX: 0000000000000000 RSI: 0000000000000006 RDI: 0000000000001000 [ 991.478681] RBP: ffffb11281d0bb88 R08: 00000000000020ff R09: ffffe14ec4208000 [ 991.485807] R10: 0000000000000005 R11: 0000000000000006 R12: ffff96b4825f4200 [ 991.492930] R13: 0000000000000001 R14: 000000003d6277bf R15: 0000000000000000 [ 991.500054] FS: 00007f41e80b9740(0000) GS:ffff96b83bc1b000(0000) knlGS:0000000000000000 [ 991.508132] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 991.513870] CR2: 0000000000000008 CR3: 0000000106c42003 CR4: 00000000003706f0 [ 991.520994] note: udpgso_bench_tx[64842] exited with irqs disabled ## Source * Kernel version: 6.17.0-rc4 * Git tree: https://kernel.googlesource.com/pub/scm/linux/kernel/git/next/linux-next.git * Git describe: next-20250905 * Git commit: be5d4872e528796df9d7425f2bd9b3893eb3a42c * Architectures: x86_64 * Toolchains: clang-nightly * Kconfigs: defconfig+selftests/*/config ## Build * Test log: https://qa-reports.linaro.org/api/testruns/29777495/log_file/ * LAVA test log: https://lkft.validation.linaro.org/scheduler/job/8434053#L16943 * Test details: https://regressions.linaro.org/lkft/linux-next-master/next-20250905/log-par… * Test plan: https://tuxapi.tuxsuite.com/v1/groups/linaro/projects/lkft/tests/32GkXBGNRN… * Build link: https://storage.tuxsuite.com/public/linaro/lkft/builds/32GkU7mdlpISpPeeeEwI… * Kernel config: https://storage.tuxsuite.com/public/linaro/lkft/builds/32GkU7mdlpISpPeeeEwI… -- Linaro LKFT https://lkft.linaro.org

1 week, 4 days

3
4
0 0

[PATCH] kunit: print a message before triggering a NULL dereference

by Dan Carpenter

Print a message so that people reading dmesg know that these NULL dereferences are not a bug, but instead a deliberate part of the testing. Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> --- lib/kunit/kunit-test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 8c01eabd4eaf..a8b6e16f4465 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -119,6 +119,8 @@ static void kunit_test_null_dereference(void *data) struct kunit *test = data; int *null = NULL; + pr_info("Triggering deliberate NULL derefence.\n"); + *null = 0; KUNIT_FAIL(test, "This line should never be reached\n"); -- 2.47.2

1 week, 4 days

1
0
0 0

[PATCH] selftests: pid_namespace: add the missing close()

by zhouyuhang

From: Zhou Yuhang <zhouyuhang(a)kylinos.cn> Add the missing close() in the pid_max_cb() function. Signed-off-by: Zhou Yuhang <zhouyuhang(a)kylinos.cn> --- tools/testing/selftests/pid_namespace/pid_max.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/pid_namespace/pid_max.c b/tools/testing/selftests/pid_namespace/pid_max.c index 96f274f0582b..41f8b943bc96 100644 --- a/tools/testing/selftests/pid_namespace/pid_max.c +++ b/tools/testing/selftests/pid_namespace/pid_max.c @@ -61,6 +61,7 @@ static int pid_max_cb(void *data) } ret = write(fd, "500", sizeof("500") - 1); + close(fd); if (ret < 0) { fprintf(stderr, "%m - Failed to write pid_max\n"); return -1; -- 2.33.0

1 week, 4 days

1
0
0 0

[bug report] selftest/bpf/benchs: Add benchmark for sockmap usage

by Dan Carpenter

Hello Jiayuan Chen, Commit 7b2fa44de5e7 ("selftest/bpf/benchs: Add benchmark for sockmap usage") from Apr 7, 2025 (linux-next), leads to the following Smatch static checker warning: tools/testing/selftests/bpf/benchs/bench_sockmap.c:129 bench_sockmap_prog_destroy() error: buffer overflow 'ctx.fds' 5 <= 19 tools/testing/selftests/bpf/benchs/bench_sockmap.c 123 static void bench_sockmap_prog_destroy(void) 124 { 125 int i; 126 127 for (i = 0; i < sizeof(ctx.fds); i++) { ^^^^^^^^^^^^^^^ This should be ARRAY_SIZE(ctx.fds) otherwise it's a buffer overflow. 128 if (ctx.fds[0] > 0) ^^^^^^^^^^ Instead of .fds[0] it should be .fds[i], right? --> 129 close(ctx.fds[i]); 130 } 131 132 bench_sockmap_prog__destroy(ctx.skel); 133 } regards, dan carpenter

1 week, 4 days

1
0
0 0

[PATCH v2 bpf-next] selftests/bpf: Fix the invalid operand for instruction issue

by Feng Yang

From: Feng Yang <yangfeng(a)kylinos.cn> The following issue occurs when compiling with clang version 17.0.6: progs/compute_live_registers.c:251:3: error: invalid operand for instruction 251 | "r0 = 1;" | ^ <inline asm>:1:22: note: instantiated into assembly here 1 | r0 = 1;r2 = 2;if r1 & 0x7 goto +1;exit;r0 = r2;exit; | ^ 1 error generated. Use __imm_insn to fix this issue. Fixes: 4a4b84ba9e453 ("selftests/bpf: verify jset handling in CFG computation") Signed-off-by: Feng Yang <yangfeng(a)kylinos.cn> --- Changes in v2: - Use __imm_insn, thanks: Eduard Zingerman. - Link to v1: https://lore.kernel.org/all/20250827031540.461017-1-yangfeng59949@163.com/ --- tools/testing/selftests/bpf/progs/compute_live_registers.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/compute_live_registers.c b/tools/testing/selftests/bpf/progs/compute_live_registers.c index 6884ab99a421..01d73ad76faf 100644 --- a/tools/testing/selftests/bpf/progs/compute_live_registers.c +++ b/tools/testing/selftests/bpf/progs/compute_live_registers.c @@ -249,11 +249,13 @@ __naked void if3_jset_bug(void) asm volatile ( "r0 = 1;" "r2 = 2;" - "if r1 & 0x7 goto +1;" + ".8byte %[jset];" /* same as 'if r1 & 0x7 goto +1;' */ "exit;" "r0 = r2;" "exit;" - ::: __clobber_all); + : + : __imm_insn(jset, BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0x7, 1)) + : __clobber_all); } SEC("socket") -- 2.43.0

1 week, 4 days

2
2
0 0

[PATCH v1] libbpf: remove unused args in parse_usdt_note

by Jiawei Zhao

Remove unused 'elf' and 'path' parameters from parse_usdt_note function signature. These parameters are not referenced within the function body and only add unnecessary complexity. The function only requires the note header, data buffer, offsets, and output structure to perform USDT note parsing. Update function declaration, definition, and the single call site in collect_usdt_targets() to match the simplified signature. This is a safe internal cleanup as parse_usdt_note is a static function. Signed-off-by: Jiawei Zhao <phoenix500526(a)163.com> --- tools/lib/bpf/usdt.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index e5eeac0b0fa4..deaea4bd13a6 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -581,9 +581,8 @@ static struct elf_seg *find_vma_seg(struct elf_seg *segs, size_t seg_cnt, long o return NULL; } -static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, - const char *data, size_t name_off, size_t desc_off, - struct usdt_note *usdt_note); +static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off, + size_t desc_off, struct usdt_note *usdt_note); static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie); @@ -637,7 +636,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * struct elf_seg *seg = NULL; void *tmp; - err = parse_usdt_note(elf, path, &nhdr, data->d_buf, name_off, desc_off, &note); + err = parse_usdt_note(&nhdr, data->d_buf, name_off, desc_off, &note); if (err) goto err_out; @@ -1143,8 +1142,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct /* Parse out USDT ELF note from '.note.stapsdt' section. * Logic inspired by perf's code. */ -static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, - const char *data, size_t name_off, size_t desc_off, +static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off, struct usdt_note *note) { const char *provider, *name, *args; -- 2.43.0

1 week, 4 days

3
2
0 0

[PATCH net-next v2] selftests: net: Add tests to verify team driver option set and get.

by Marc Harvey

There are currently no kernel tests that verify setting and getting options of the team driver. In the future, options may be added that implicitly change other options, which will make it useful to have tests like these that show nothing breaks. There will be a follow up patch to this that adds new "rx_enabled" and "tx_enabled" options, which will implicitly affect the "enabled" option value and vice versa. The tests use teamnl to first set options to specific values and then gets them to compare to the set values. Signed-off-by: Marc Harvey <marcharvey(a)google.com> --- Changes in v2: - Fixed shellcheck failures. - Fixed test failing in vng by adding a config option to enable the team driver's active backup mode. - Link to v1: https://lore.kernel.org/netdev/20250902235504.4190036-1-marcharvey@google.c… .../selftests/drivers/net/team/Makefile | 6 +- .../testing/selftests/drivers/net/team/config | 1 + .../selftests/drivers/net/team/options.sh | 192 ++++++++++++++++++ 3 files changed, 197 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/team/options.sh diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile index eaf6938f100e..8b00b70ce67f 100644 --- a/tools/testing/selftests/drivers/net/team/Makefile +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -1,11 +1,13 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for net selftests -TEST_PROGS := dev_addr_lists.sh propagation.sh +TEST_PROGS := dev_addr_lists.sh propagation.sh options.sh TEST_INCLUDES := \ ../bonding/lag_lib.sh \ ../../../net/forwarding/lib.sh \ - ../../../net/lib.sh + ../../../net/lib.sh \ + ../../../net/in_netns.sh \ + ../../../net/lib/sh/defer.sh \ include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config index 636b3525b679..558e1d0cf565 100644 --- a/tools/testing/selftests/drivers/net/team/config +++ b/tools/testing/selftests/drivers/net/team/config @@ -3,4 +3,5 @@ CONFIG_IPV6=y CONFIG_MACVLAN=y CONFIG_NETDEVSIM=m CONFIG_NET_TEAM=y +CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y diff --git a/tools/testing/selftests/drivers/net/team/options.sh b/tools/testing/selftests/drivers/net/team/options.sh new file mode 100755 index 000000000000..82bf22aa3480 --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/options.sh @@ -0,0 +1,192 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# These tests verify basic set and get functionality of the team +# driver options over netlink. + +# Run in private netns. +test_dir="$(dirname "$0")" +if [[ $# -eq 0 ]]; then + "${test_dir}"/../../../net/in_netns.sh "$0" __subprocess + exit $? +fi + +ALL_TESTS=" + team_test_options +" + +source "${test_dir}/../../../net/lib.sh" + +TEAM_PORT="team0" +MEMBER_PORT="dummy0" + +setup() +{ + ip link add name "${MEMBER_PORT}" type dummy + ip link add name "${TEAM_PORT}" type team +} + +get_and_check_value() +{ + local option_name="$1" + local expected_value="$2" + local port_flag="$3" + + local value_from_get + + if ! value_from_get=$(teamnl "${TEAM_PORT}" getoption "${option_name}" \ + "${port_flag}"); then + echo "Could not get option '${option_name}'" >&2 + return 1 + fi + + if [[ "${value_from_get}" != "${expected_value}" ]]; then + echo "Incorrect value for option '${option_name}'" >&2 + echo "get (${value_from_get}) != set (${expected_value})" >&2 + return 1 + fi +} + +set_and_check_get() +{ + local option_name="$1" + local option_value="$2" + local port_flag="$3" + + local value_from_get + + if ! teamnl "${TEAM_PORT}" setoption "${option_name}" "${option_value}" \ + "${port_flag}"; then + echo "'setoption ${option_name} ${option_value}' failed" >&2 + return 1 + fi + + get_and_check_value "${option_name}" "${option_value}" "${port_flag}" + return $? +} + +# Get a "port flag" to pass to the `teamnl` command. +# E.g. $1="dummy0" -> "port=dummy0", +# $1="" -> "" +get_port_flag() +{ + local port_name="$1" + + if [[ -n "${port_name}" ]]; then + echo "--port=${port_name}" + fi +} + +attach_port_if_specified() +{ + local port_name="${1}" + + if [[ -n "${port_name}" ]]; then + ip link set dev "${port_name}" master "${TEAM_PORT}" + return $? + fi +} + +detach_port_if_specified() +{ + local port_name="${1}" + + if [[ -n "${port_name}" ]]; then + ip link set dev "${port_name}" nomaster + return $? + fi +} + +####################################### +# Test that an option's get value matches its set value. +# Globals: +# RET - Used by testing infra like `check_err`. +# EXIT_STATUS - Used by `log_test` to whole script exit value. +# Arguments: +# option_name - The name of the option. +# value_1 - The first value to try setting. +# value_2 - The second value to try setting. +# port_name - The (optional) name of the attached port. +####################################### +team_test_option() +{ + local option_name="$1" + local value_1="$2" + local value_2="$3" + local possible_values="$2 $3 $2" + local port_name="$4" + local port_flag + + RET=0 + + echo "Setting '${option_name}' to '${value_1}' and '${value_2}'" + + attach_port_if_specified "${port_name}" + check_err $? "Couldn't attach ${port_name} to master" + port_flag=$(get_port_flag "${port_name}") + + # Set and get both possible values. + for value in ${possible_values}; do + set_and_check_get "${option_name}" "${value}" "${port_flag}" + check_err $? "Failed to set '${option_name}' to '${value}'" + done + + detach_port_if_specified "${port_name}" + check_err $? "Couldn't detach ${port_name} from its master" + + log_test "Set + Get '${option_name}' test" +} + +####################################### +# Test that getting a non-existant option fails. +# Globals: +# RET - Used by testing infra like `check_err`. +# EXIT_STATUS - Used by `log_test` to whole script exit value. +# Arguments: +# option_name - The name of the option. +# port_name - The (optional) name of the attached port. +####################################### +team_test_get_option_fails() +{ + local option_name="$1" + local port_name="$2" + local port_flag + + RET=0 + + attach_port_if_specified "${port_name}" + check_err $? "Couldn't attach ${port_name} to master" + port_flag=$(get_port_flag "${port_name}") + + # Just confirm that getting the value fails. + teamnl "${TEAM_PORT}" getoption "${option_name}" "${port_flag}" + check_fail $? "Shouldn't be able to get option '${option_name}'" + + detach_port_if_specified "${port_name}" + + log_test "Get '${option_name}' fails" +} + +team_test_options() +{ + # Wrong option name behavior. + team_test_get_option_fails fake_option1 + team_test_get_option_fails fake_option2 "${MEMBER_PORT}" + + # Correct set and get behavior. + team_test_option mode activebackup loadbalance + team_test_option notify_peers_count 0 5 + team_test_option notify_peers_interval 0 5 + team_test_option mcast_rejoin_count 0 5 + team_test_option mcast_rejoin_interval 0 5 + team_test_option enabled true false "${MEMBER_PORT}" + team_test_option user_linkup true false "${MEMBER_PORT}" + team_test_option user_linkup_enabled true false "${MEMBER_PORT}" + team_test_option priority 10 20 "${MEMBER_PORT}" + team_test_option queue_id 0 1 "${MEMBER_PORT}" +} + +require_command teamnl +setup +tests_run +exit "${EXIT_STATUS}" -- 2.51.0.338.gd7d06c2dae-goog

1 week, 4 days

2
2
0 0

[PATCH net-next 10/10] selftests: forwarding: Add test for BR_BOOLOPT_FDB_LOCAL_VLAN_0

by Petr Machata

Add a selftest to check the operation of this newly-introduced bridge option. Signed-off-by: Petr Machata <petrm(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: linux-kselftest(a)vger.kernel.org .../testing/selftests/net/forwarding/Makefile | 1 + .../net/forwarding/bridge_fdb_local_vlan_0.sh | 374 ++++++++++++++++++ 2 files changed, 375 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/bridge_fdb_local_vlan_0.sh diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 0a0d4c2a85f7..e6f482a600da 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -5,6 +5,7 @@ TEST_PROGS = \ bridge_fdb_learning_limit.sh \ bridge_igmp.sh \ bridge_locked_port.sh \ + bridge_fdb_local_vlan_0.sh \ bridge_mdb.sh \ bridge_mdb_host.sh \ bridge_mdb_max.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_fdb_local_vlan_0.sh b/tools/testing/selftests/net/forwarding/bridge_fdb_local_vlan_0.sh new file mode 100755 index 000000000000..5a0b43aff5aa --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_fdb_local_vlan_0.sh @@ -0,0 +1,374 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +-----------------------+ +-----------------------+ +# | H1 (vrf) | | H2 (vrf) | | H3 (vrf) | +# | + $h1 | | + $h2 | | + $h3 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | | | 192.0.2.18/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:1::2/64 | | | 2001:db8:2::2/64 | +# | | | | | | | | | +# +----|------------------+ +----|------------------+ +----|------------------+ +# | | | +# +----|-------------------------|-------------------------|------------------+ +# | +--|-------------------------|------------------+ | | +# | | + $swp1 + $swp2 | + $swp3 | +# | | | 192.0.2.17/28 | +# | | BR1 (802.1q) | 2001:db8:2::1/64 | +# | | 192.0.2.3/28 | | +# | | 2001:db8:1::3/64 | | +# | +-----------------------------------------------+ SW | +# +---------------------------------------------------------------------------+ +# +#shellcheck disable=SC2317 # SC doesn't see our uses of functions. +#shellcheck disable=SC2034 # ... and global variables + +ALL_TESTS=" + test_d_no_sharing + test_d_sharing + test_q_no_sharing + test_q_sharing +" + +NUM_NETIFS=6 +source lib.sh + +pMAC=00:11:22:33:44:55 +bMAC=00:11:22:33:44:66 +mMAC=00:11:22:33:44:77 +xMAC=00:11:22:33:44:88 + +host_create() +{ + local h=$1; shift + local ipv4=$1; shift + local ipv6=$1; shift + + simple_if_init "$h" "$ipv4" "$ipv6" + defer simple_if_fini "$h" "$ipv4" "$ipv6" + + ip_route_add vrf "v$h" 192.0.2.16/28 nexthop via 192.0.2.3 + ip_route_add vrf "v$h" 2001:db8:2::/64 nexthop via 2001:db8:1::3 +} + +h3_create() +{ + simple_if_init "$h3" 192.0.2.18/28 2001:db8:2::2/64 + defer simple_if_fini "$h3" 192.0.2.18/28 2001:db8:2::2/64 + + ip_route_add vrf "v$h3" 192.0.2.0/28 nexthop via 192.0.2.17 + ip_route_add vrf "v$h3" 2001:db8:1::/64 nexthop via 2001:db8:2::1 + + tc qdisc add dev "$h3" clsact + defer tc qdisc del dev "$h3" clsact + + tc filter add dev "$h3" ingress proto ip pref 104 \ + flower skip_hw ip_proto udp dst_port 4096 \ + action pass + defer tc filter del dev "$h3" ingress proto ip pref 104 + + tc qdisc add dev "$h2" clsact + defer tc qdisc del dev "$h2" clsact + + tc filter add dev "$h2" ingress proto ip pref 104 \ + flower skip_hw ip_proto udp dst_port 4096 \ + action pass + defer tc filter del dev "$h2" ingress proto ip pref 104 +} + +switch_create() +{ + ip_link_set_up "$swp1" + + ip_link_set_up "$swp2" + + ip_addr_add "$swp3" 192.0.2.17/28 + ip_addr_add "$swp3" 2001:db8:2::1/64 + ip_link_set_up "$swp3" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + host_create "$h1" 192.0.2.1/28 2001:db8:1::1/64 + host_create "$h2" 192.0.2.2/28 2001:db8:1::2/64 + h3_create + + switch_create +} + +adf_bridge_create() +{ + local dev + local mac + + ip_link_add br up type bridge vlan_default_pvid 0 "$@" + mac=$(mac_get br) + ip_addr_add br 192.0.2.3/28 + ip_addr_add br 2001:db8:1::3/64 + + bridge_vlan_add dev br vid 1 pvid untagged self + bridge_vlan_add dev br vid 2 self + bridge_vlan_add dev br vid 3 self + + for dev in "$swp1" "$swp2"; do + ip_link_set_master "$dev" br + bridge_vlan_add dev "$dev" vid 1 pvid untagged + bridge_vlan_add dev "$dev" vid 2 + bridge_vlan_add dev "$dev" vid 3 + done + + ip_link_set_addr br "$mac" +} + +check_fdb_local_vlan_0_support() +{ + if ip_link_add XXbr up type bridge vlan_filtering 1 fdb_local_vlan_0 1 \ + &>/dev/null; then + return 0 + fi + + log_test_skip "FDB sharing" \ + "iproute 2 or the kernel do not support fdb_local_vlan_0" +} + +check_mac_presence() +{ + local should_fail=$1; shift + local dev=$1; shift + local vlan=$1; shift + local mac + + mac=$(mac_get "$dev") + + if ((vlan == 0)); then + vlan=null + fi + + bridge -j fdb show dev "$dev" | + jq -e --arg mac "$mac" --argjson vlan "$vlan" \ + '.[] | select(.mac == $mac) | select(.vlan == $vlan)' > /dev/null + check_err_fail "$should_fail" $? "FDB dev $dev vid $vlan addr $mac exists" +} + +do_sharing_test() +{ + local should_fail=$1; shift + local what=$1; shift + local dev + + RET=0 + + for dev in "$swp1" "$swp2" br; do + check_mac_presence 0 "$dev" 0 + check_mac_presence "$should_fail" "$dev" 1 + check_mac_presence "$should_fail" "$dev" 2 + check_mac_presence "$should_fail" "$dev" 3 + done + + log_test "$what" +} + +do_end_to_end_test() +{ + local mac=$1; shift + local what=$1; shift + local probe_dev=${1-$h3}; shift + local expect=${1-10}; shift + + local t0 + local t1 + local dd + + RET=0 + + # In mausezahn, use $dev MAC as the destination MAC. In the MAC sharing + # context, that will cause an FDB miss on VLAN 1 and prompt a second + # lookup in VLAN 0. + + t0=$(tc_rule_stats_get "$probe_dev" 104 ingress) + + $MZ "$h1" -c 10 -p 64 -a own -b "$mac" \ + -A 192.0.2.1 -B 192.0.2.18 -t udp "dp=4096,sp=2048" -q + sleep 1 + + t1=$(tc_rule_stats_get "$probe_dev" 104 ingress) + dd=$((t1 - t0)) + + ((dd == expect)) + check_err $? "Expected $expect packets on $probe_dev got $dd" + + log_test "$what" +} + +do_tests() +{ + local should_fail=$1; shift + local what=$1; shift + local swp1_mac + local br_mac + + swp1_mac=$(mac_get "$swp1") + br_mac=$(mac_get br) + + do_sharing_test "$should_fail" "$what" + do_end_to_end_test "$swp1_mac" "$what: end to end, $swp1 MAC" + do_end_to_end_test "$br_mac" "$what: end to end, br MAC" +} + +bridge_standard() +{ + local vlan_filtering=$1; shift + + if ((vlan_filtering)); then + echo 802.1q + else + echo 802.1d + fi +} + +nonexistent_fdb_test() +{ + local vlan_filtering=$1; shift + local standard + + standard=$(bridge_standard "$vlan_filtering") + + # We expect flooding, so $h2 should get the traffic. + do_end_to_end_test "$xMAC" "$standard: Nonexistent FDB" "$h2" +} + +misleading_fdb_test() +{ + local vlan_filtering=$1; shift + local standard + + standard=$(bridge_standard "$vlan_filtering") + + defer_scope_push + # Add an FDB entry on VLAN 0. The lookup on VLAN-aware bridge + # shouldn't pick this up even with fdb_local_vlan_0 enabled, so + # the traffic should be flooded. This all holds on + # vlan_filtering bridge, on non-vlan_filtering one the FDB entry + # is expected to be found as usual, no flooding takes place. + # + # Adding only on VLAN 0 is a bit tricky, because bridge is + # trying to be nice and interprets the request as if the FDB + # should be added on each VLAN. + + bridge fdb add "$mMAC" dev "$swp1" master + bridge fdb del "$mMAC" dev "$swp1" vlan 1 master + bridge fdb del "$mMAC" dev "$swp1" vlan 2 master + bridge fdb del "$mMAC" dev "$swp1" vlan 3 master + + local expect=$((vlan_filtering ? 10 : 0)) + do_end_to_end_test "$mMAC" \ + "$standard: Lookup of non-local MAC on VLAN 0" \ + "$h2" "$expect" + defer_scope_pop +} + +change_mac() +{ + local dev=$1; shift + local mac=$1; shift + local cur_mac + + cur_mac=$(mac_get "$dev") + + log_info "Change $dev MAC $cur_mac -> $mac" + ip_link_set_addr "$dev" "$mac" + defer log_info "Change $dev MAC back" +} + +do_test_no_sharing() +{ + local vlan_filtering=$1; shift + local standard + + standard=$(bridge_standard "$vlan_filtering") + + adf_bridge_create vlan_filtering "$vlan_filtering" + setup_wait + + do_tests 0 "$standard, no FDB sharing" + + change_mac "$swp1" "$pMAC" + change_mac br "$bMAC" + + do_tests 0 "$standard, no FDB sharing after MAC change" + + in_defer_scope check_fdb_local_vlan_0_support || return + + log_info "Set fdb_local_vlan_0=1" + ip link set dev br type bridge fdb_local_vlan_0 1 + + do_tests 1 "$standard, fdb sharing after toggle" +} + +do_test_sharing() +{ + local vlan_filtering=$1; shift + local standard + + standard=$(bridge_standard "$vlan_filtering") + + in_defer_scope check_fdb_local_vlan_0_support || return + + adf_bridge_create vlan_filtering "$vlan_filtering" fdb_local_vlan_0 1 + setup_wait + + do_tests 1 "$standard, FDB sharing" + + nonexistent_fdb_test "$vlan_filtering" + misleading_fdb_test "$vlan_filtering" + + change_mac "$swp1" "$pMAC" + change_mac br "$bMAC" + + do_tests 1 "$standard, FDB sharing after MAC change" + + log_info "Set fdb_local_vlan_0=0" + ip link set dev br type bridge fdb_local_vlan_0 0 + + do_tests 0 "$standard, No FDB sharing after toggle" +} + +test_d_no_sharing() +{ + do_test_no_sharing 0 +} + +test_d_sharing() +{ + do_test_sharing 0 +} + +test_q_no_sharing() +{ + do_test_no_sharing 1 +} + +test_q_sharing() +{ + do_test_sharing 1 +} + + +trap cleanup EXIT + +setup_prepare +tests_run -- 2.49.0

1 week, 4 days

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror