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

[PATCH AUTOSEL 6.8 02/30] selftests/bpf: Prevent client connect before server bind in test_tc_tunnel.sh

by Sasha Levin

From: "Alessandro Carminati (Red Hat)" <alessandro.carminati(a)gmail.com> [ Upstream commit f803bcf9208a2540acb4c32bdc3616673169f490 ] In some systems, the netcat server can incur in delay to start listening. When this happens, the test can randomly fail in various points. This is an example error message: # ip gre none gso # encap 192.168.1.1 to 192.168.1.2, type gre, mac none len 2000 # test basic connectivity # Ncat: Connection refused. The issue stems from a race condition between the netcat client and server. The test author had addressed this problem by implementing a sleep, which I have removed in this patch. This patch introduces a function capable of sleeping for up to two seconds. However, it can terminate the waiting period early if the port is reported to be listening. Signed-off-by: Alessandro Carminati (Red Hat) <alessandro.carminati(a)gmail.com> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/bpf/20240314105911.213411-1-alessandro.carminati@gm… Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/test_tc_tunnel.sh | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index 910044f08908a..7989ec6084545 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -72,7 +72,6 @@ cleanup() { server_listen() { ip netns exec "${ns2}" nc "${netcat_opt}" -l "${port}" > "${outfile}" & server_pid=$! - sleep 0.2 } client_connect() { @@ -93,6 +92,16 @@ verify_data() { fi } +wait_for_port() { + for i in $(seq 20); do + if ip netns exec "${ns2}" ss ${2:--4}OHntl | grep -q "$1"; then + return 0 + fi + sleep 0.1 + done + return 1 +} + set -e # no arguments: automated test, run all @@ -193,6 +202,7 @@ setup # basic communication works echo "test basic connectivity" server_listen +wait_for_port ${port} ${netcat_opt} client_connect verify_data @@ -204,6 +214,7 @@ ip netns exec "${ns1}" tc filter add dev veth1 egress \ section "encap_${tuntype}_${mac}" echo "test bpf encap without decap (expect failure)" server_listen +wait_for_port ${port} ${netcat_opt} ! client_connect if [[ "$tuntype" =~ "udp" ]]; then -- 2.43.0

5 days, 6 hours

1
0
0 0

[PATCH AUTOSEL 6.9 33/35] selftests: net: fix timestamp not arriving in cmsg_time.sh

by Sasha Levin

From: Jakub Kicinski <kuba(a)kernel.org> [ Upstream commit 2d3b8dfd82d76b1295167c6453d683ab99e50794 ] On slow machines the SND timestamp sometimes doesn't arrive before we quit. The test only waits as long as the packet delay, so it's easy for a race condition to happen. Double the wait but do a bit of polling, once the SND timestamp arrives there's no point to wait any longer. This fixes the "TXTIME abs" failures on debug kernels, like: Case ICMPv4 - TXTIME abs returned '', expected 'OK' Reviewed-by: Willem de Bruijn <willemb(a)google.com> Link: https://lore.kernel.org/r/20240510005705.43069-1-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/net/cmsg_sender.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index c79e65581dc37..161db24e3c409 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -333,16 +333,17 @@ static const char *cs_ts_info2str(unsigned int info) return "unknown"; } -static void +static unsigned long cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) { struct sock_extended_err *see; struct scm_timestamping *ts; + unsigned long ts_seen = 0; struct cmsghdr *cmsg; int i, err; if (!opt.ts.ena) - return; + return 0; msg->msg_control = cbuf; msg->msg_controllen = cbuf_sz; @@ -396,8 +397,11 @@ cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) printf(" %5s ts%d %lluus\n", cs_ts_info2str(see->ee_info), i, rel_time); + ts_seen |= 1 << see->ee_info; } } + + return ts_seen; } static void ca_set_sockopts(int fd) @@ -509,10 +513,16 @@ int main(int argc, char *argv[]) err = ERN_SUCCESS; if (opt.ts.ena) { - /* Make sure all timestamps have time to loop back */ - usleep(opt.txtime.delay); + unsigned long seen; + int i; - cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + /* Make sure all timestamps have time to loop back */ + for (i = 0; i < 40; i++) { + seen = cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + if (seen & (1 << SCM_TSTAMP_SND)) + break; + usleep(opt.txtime.delay / 20); + } } err_out: -- 2.43.0

5 days, 6 hours

1
0
0 0

[PATCH AUTOSEL 6.9 32/35] bpf: avoid uninitialized warnings in verifier_global_subprogs.c

by Sasha Levin

From: "Jose E. Marchesi" <jose.marchesi(a)oracle.com> [ Upstream commit cd3fc3b9782130a5bc1dc3dfccffbc1657637a93 ] [Changes from V1: - The warning to disable is -Wmaybe-uninitialized, not -Wuninitialized. - This warning is only supported in GCC.] The BPF selftest verifier_global_subprogs.c contains code that purposedly performs out of bounds access to memory, to check whether the kernel verifier is able to catch them. For example: __noinline int global_unsupp(const int *mem) { if (!mem) return 0; return mem[100]; /* BOOM */ } With -O1 and higher and no inlining, GCC notices this fact and emits a "maybe uninitialized" warning. This is by design. Note that the emission of these warnings is highly dependent on the precise optimizations that are performed. This patch adds a compiler pragma to verifier_global_subprogs.c to ignore these warnings. Tested in bpf-next master. No regressions. Signed-off-by: Jose E. Marchesi <jose.marchesi(a)oracle.com> Cc: david.faust(a)oracle.com Cc: cupertino.miranda(a)oracle.com Cc: Yonghong Song <yonghong.song(a)linux.dev> Cc: Eduard Zingerman <eddyz87(a)gmail.com> Acked-by: Yonghong Song <yonghong.song(a)linux.dev> Link: https://lore.kernel.org/r/20240507184756.1772-1-jose.marchesi@oracle.com Signed-off-by: Alexei Starovoitov <ast(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../testing/selftests/bpf/progs/verifier_global_subprogs.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index baff5ffe94051..a9fc30ed4d732 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -8,6 +8,13 @@ #include "xdp_metadata.h" #include "bpf_kfuncs.h" +/* The compiler may be able to detect the access to uninitialized + memory in the routines performing out of bound memory accesses and + emit warnings about it. This is the case of GCC. */ +#if !defined(__clang__) +#pragma GCC diagnostic ignored "-Wmaybe-uninitialized" +#endif + int arr[1]; int unkn_idx; const volatile bool call_dead_subprog = false; -- 2.43.0

5 days, 6 hours

1
0
0 0

[PATCH AUTOSEL 6.9 21/35] kselftest: arm64: Add a null pointer check

by Sasha Levin

From: Kunwu Chan <chentao(a)kylinos.cn> [ Upstream commit 80164282b3620a3cb73de6ffda5592743e448d0e ] There is a 'malloc' call, which can be unsuccessful. This patch will add the malloc failure checking to avoid possible null dereference and give more information about test fail reasons. Signed-off-by: Kunwu Chan <chentao(a)kylinos.cn> Reviewed-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Link: https://lore.kernel.org/r/20240423082102.2018886-1-chentao@kylinos.cn Signed-off-by: Will Deacon <will(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/arm64/tags/tags_test.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/arm64/tags/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c index 5701163460ef7..955f87c1170d7 100644 --- a/tools/testing/selftests/arm64/tags/tags_test.c +++ b/tools/testing/selftests/arm64/tags/tags_test.c @@ -6,6 +6,7 @@ #include <stdint.h> #include <sys/prctl.h> #include <sys/utsname.h> +#include "../../kselftest.h" #define SHIFT_TAG(tag) ((uint64_t)(tag) << 56) #define SET_TAG(ptr, tag) (((uint64_t)(ptr) & ~SHIFT_TAG(0xff)) | \ @@ -21,6 +22,9 @@ int main(void) if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, 0, 0, 0) == 0) tbi_enabled = 1; ptr = (struct utsname *)malloc(sizeof(*ptr)); + if (!ptr) + ksft_exit_fail_msg("Failed to allocate utsname buffer\n"); + if (tbi_enabled) tag = 0x42; ptr = (struct utsname *)SET_TAG(ptr, tag); -- 2.43.0

5 days, 6 hours

1
0
0 0

[PATCH AUTOSEL 6.9 03/35] selftests/bpf: Fix flaky test btf_map_in_map/lookup_update

by Sasha Levin

From: Yonghong Song <yonghong.song(a)linux.dev> [ Upstream commit 14bb1e8c8d4ad5d9d2febb7d19c70a3cf536e1e5 ] Recently, I frequently hit the following test failure: [root@arch-fb-vm1 bpf]# ./test_progs -n 33/1 test_lookup_update:PASS:skel_open 0 nsec [...] test_lookup_update:PASS:sync_rcu 0 nsec test_lookup_update:FAIL:map1_leak inner_map1 leaked! #33/1 btf_map_in_map/lookup_update:FAIL #33 btf_map_in_map:FAIL In the test, after map is closed and then after two rcu grace periods, it is assumed that map_id is not available to user space. But the above assumption cannot be guaranteed. After zero or one or two rcu grace periods in different siturations, the actual freeing-map-work is put into a workqueue. Later on, when the work is dequeued, the map will be actually freed. See bpf_map_put() in kernel/bpf/syscall.c. By using workqueue, there is no ganrantee that map will be actually freed after a couple of rcu grace periods. This patch removed such map leak detection and then the test can pass consistently. Signed-off-by: Yonghong Song <yonghong.song(a)linux.dev> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20240322061353.632136-1-yonghong.song@linux.dev Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../selftests/bpf/prog_tests/btf_map_in_map.c | 26 +------------------ 1 file changed, 1 insertion(+), 25 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c index a8b53b8736f01..f66ceccd7029c 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c @@ -25,7 +25,7 @@ static void test_lookup_update(void) int map1_fd, map2_fd, map3_fd, map4_fd, map5_fd, map1_id, map2_id; int outer_arr_fd, outer_hash_fd, outer_arr_dyn_fd; struct test_btf_map_in_map *skel; - int err, key = 0, val, i, fd; + int err, key = 0, val, i; skel = test_btf_map_in_map__open_and_load(); if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n")) @@ -102,30 +102,6 @@ static void test_lookup_update(void) CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n"); CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n"); - test_btf_map_in_map__destroy(skel); - skel = NULL; - - /* we need to either wait for or force synchronize_rcu(), before - * checking for "still exists" condition, otherwise map could still be - * resolvable by ID, causing false positives. - * - * Older kernels (5.8 and earlier) freed map only after two - * synchronize_rcu()s, so trigger two, to be entirely sure. - */ - CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); - CHECK(kern_sync_rcu(), "sync_rcu", "failed\n"); - - fd = bpf_map_get_fd_by_id(map1_id); - if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) { - close(fd); - goto cleanup; - } - fd = bpf_map_get_fd_by_id(map2_id); - if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) { - close(fd); - goto cleanup; - } - cleanup: test_btf_map_in_map__destroy(skel); } -- 2.43.0

5 days, 6 hours

1
0
0 0

[PATCH AUTOSEL 6.9 02/35] selftests/bpf: Prevent client connect before server bind in test_tc_tunnel.sh

by Sasha Levin

From: "Alessandro Carminati (Red Hat)" <alessandro.carminati(a)gmail.com> [ Upstream commit f803bcf9208a2540acb4c32bdc3616673169f490 ] In some systems, the netcat server can incur in delay to start listening. When this happens, the test can randomly fail in various points. This is an example error message: # ip gre none gso # encap 192.168.1.1 to 192.168.1.2, type gre, mac none len 2000 # test basic connectivity # Ncat: Connection refused. The issue stems from a race condition between the netcat client and server. The test author had addressed this problem by implementing a sleep, which I have removed in this patch. This patch introduces a function capable of sleeping for up to two seconds. However, it can terminate the waiting period early if the port is reported to be listening. Signed-off-by: Alessandro Carminati (Red Hat) <alessandro.carminati(a)gmail.com> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/bpf/20240314105911.213411-1-alessandro.carminati@gm… Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/test_tc_tunnel.sh | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index 910044f08908a..7989ec6084545 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -72,7 +72,6 @@ cleanup() { server_listen() { ip netns exec "${ns2}" nc "${netcat_opt}" -l "${port}" > "${outfile}" & server_pid=$! - sleep 0.2 } client_connect() { @@ -93,6 +92,16 @@ verify_data() { fi } +wait_for_port() { + for i in $(seq 20); do + if ip netns exec "${ns2}" ss ${2:--4}OHntl | grep -q "$1"; then + return 0 + fi + sleep 0.1 + done + return 1 +} + set -e # no arguments: automated test, run all @@ -193,6 +202,7 @@ setup # basic communication works echo "test basic connectivity" server_listen +wait_for_port ${port} ${netcat_opt} client_connect verify_data @@ -204,6 +214,7 @@ ip netns exec "${ns1}" tc filter add dev veth1 egress \ section "encap_${tuntype}_${mac}" echo "test bpf encap without decap (expect failure)" server_listen +wait_for_port ${port} ${netcat_opt} ! client_connect if [[ "$tuntype" =~ "udp" ]]; then -- 2.43.0

5 days, 6 hours

1
0
0 0

[PATCH] selftests/mm: hugetlb_madv_vs_map: Avoid test skipping by querying hugepage size at runtime

by Dev Jain

Currently, the size used in mmap() is statically defined, leading to skipping of the test on a hugepage size other than 2 MB, since munmap() won't free the hugepage for a size greater than 2 MB. Hence, query the size at runtime. Also, there is no reason why a hugepage allocation should fail, since we are using a simple mmap() using MAP_HUGETLB; hence, instead of skipping the test, make it fail. Signed-off-by: Dev Jain <dev.jain(a)arm.com> --- tools/testing/selftests/mm/hugetlb_madv_vs_map.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/mm/hugetlb_madv_vs_map.c b/tools/testing/selftests/mm/hugetlb_madv_vs_map.c index d01e8d4901d0..8f122a0f0828 100644 --- a/tools/testing/selftests/mm/hugetlb_madv_vs_map.c +++ b/tools/testing/selftests/mm/hugetlb_madv_vs_map.c @@ -27,9 +27,9 @@ #include "vm_util.h" #include "../kselftest.h" -#define MMAP_SIZE (1 << 21) #define INLOOP_ITER 100 +size_t mmap_size; char *huge_ptr; /* Touch the memory while it is being madvised() */ @@ -44,7 +44,7 @@ void *touch(void *unused) void *madv(void *unused) { for (int i = 0; i < INLOOP_ITER; i++) - madvise(huge_ptr, MMAP_SIZE, MADV_DONTNEED); + madvise(huge_ptr, mmap_size, MADV_DONTNEED); return NULL; } @@ -59,7 +59,7 @@ void *map_extra(void *unused) void *ptr; for (int i = 0; i < INLOOP_ITER; i++) { - ptr = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE, + ptr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); @@ -93,14 +93,16 @@ int main(void) free_hugepages); } + mmap_size = default_huge_page_size(); + while (max--) { - huge_ptr = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE, + huge_ptr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); if ((unsigned long)huge_ptr == -1) { - ksft_exit_skip("Failed to allocated huge page\n"); - return KSFT_SKIP; + ksft_test_result_fail("Failed to allocate huge page\n"); + return KSFT_FAIL; } pthread_create(&thread1, NULL, madv, NULL); @@ -117,7 +119,7 @@ int main(void) } /* Unmap and restart */ - munmap(huge_ptr, MMAP_SIZE); + munmap(huge_ptr, mmap_size); } return KSFT_PASS; -- 2.39.2

5 days, 7 hours

3
2
0 0

[RESEDN PATCH v2] selftests: introduce additional eventfd test coverage

by Wen Yang

Add several new test cases which assert corner cases on the eventfd mechanism, for example, the supplied buffer is less than 8 bytes, attempting to write a value that is too large, etc. ./eventfd_test # Starting 9 tests from 1 test cases. # RUN global.eventfd_check_flag_rdwr ... # OK global.eventfd_check_flag_rdwr ok 1 global.eventfd_check_flag_rdwr # RUN global.eventfd_check_flag_cloexec ... # OK global.eventfd_check_flag_cloexec ok 2 global.eventfd_check_flag_cloexec # RUN global.eventfd_check_flag_nonblock ... # OK global.eventfd_check_flag_nonblock ok 3 global.eventfd_check_flag_nonblock # RUN global.eventfd_chek_flag_cloexec_and_nonblock ... # OK global.eventfd_chek_flag_cloexec_and_nonblock ok 4 global.eventfd_chek_flag_cloexec_and_nonblock # RUN global.eventfd_check_flag_semaphore ... # OK global.eventfd_check_flag_semaphore ok 5 global.eventfd_check_flag_semaphore # RUN global.eventfd_check_write ... # OK global.eventfd_check_write ok 6 global.eventfd_check_write # RUN global.eventfd_check_read ... # OK global.eventfd_check_read ok 7 global.eventfd_check_read # RUN global.eventfd_check_read_with_nonsemaphore ... # OK global.eventfd_check_read_with_nonsemaphore ok 8 global.eventfd_check_read_with_nonsemaphore # RUN global.eventfd_check_read_with_semaphore ... # OK global.eventfd_check_read_with_semaphore ok 9 global.eventfd_check_read_with_semaphore # PASSED: 9 / 9 tests passed. # Totals: pass:9 fail:0 xfail:0 xpass:0 skip:0 error:0 Signed-off-by: Wen Yang <wen.yang(a)linux.dev> Cc: SShuah Khan <shuah(a)kernel.org> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Andrei Vagin <avagin(a)google.com> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Dave Young <dyoung(a)redhat.com> Cc: Tim Bird <tim.bird(a)sony.com> Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org --- v2: use strings which indicate what is being tested, that are useful to a human .../filesystems/eventfd/eventfd_test.c | 136 +++++++++++++++++- 1 file changed, 131 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/filesystems/eventfd/eventfd_test.c b/tools/testing/selftests/filesystems/eventfd/eventfd_test.c index f142a137526c..85acb4e3ef00 100644 --- a/tools/testing/selftests/filesystems/eventfd/eventfd_test.c +++ b/tools/testing/selftests/filesystems/eventfd/eventfd_test.c @@ -13,6 +13,8 @@ #include <sys/eventfd.h> #include "../../kselftest_harness.h" +#define EVENTFD_TEST_ITERATIONS 100000UL + struct error { int code; char msg[512]; @@ -40,7 +42,7 @@ static inline int sys_eventfd2(unsigned int count, int flags) return syscall(__NR_eventfd2, count, flags); } -TEST(eventfd01) +TEST(eventfd_check_flag_rdwr) { int fd, flags; @@ -54,7 +56,7 @@ TEST(eventfd01) close(fd); } -TEST(eventfd02) +TEST(eventfd_check_flag_cloexec) { int fd, flags; @@ -68,7 +70,7 @@ TEST(eventfd02) close(fd); } -TEST(eventfd03) +TEST(eventfd_check_flag_nonblock) { int fd, flags; @@ -83,7 +85,7 @@ TEST(eventfd03) close(fd); } -TEST(eventfd04) +TEST(eventfd_chek_flag_cloexec_and_nonblock) { int fd, flags; @@ -161,7 +163,7 @@ static int verify_fdinfo(int fd, struct error *err, const char *prefix, return 0; } -TEST(eventfd05) +TEST(eventfd_check_flag_semaphore) { struct error err = {0}; int fd, ret; @@ -183,4 +185,128 @@ TEST(eventfd05) close(fd); } +/* + * A write(2) fails with the error EINVAL if the size of the supplied buffer + * is less than 8 bytes, or if an attempt is made to write the value + * 0xffffffffffffffff. + */ +TEST(eventfd_check_write) +{ + uint64_t value = 1; + ssize_t size; + int fd; + + fd = sys_eventfd2(0, 0); + ASSERT_GE(fd, 0); + + size = write(fd, &value, sizeof(int)); + EXPECT_EQ(size, -1); + EXPECT_EQ(errno, EINVAL); + + size = write(fd, &value, sizeof(value)); + EXPECT_EQ(size, sizeof(value)); + + value = (uint64_t)-1; + size = write(fd, &value, sizeof(value)); + EXPECT_EQ(size, -1); + EXPECT_EQ(errno, EINVAL); + + close(fd); +} + +/* + * A read(2) fails with the error EINVAL if the size of the supplied buffer is + * less than 8 bytes. + */ +TEST(eventfd_check_read) +{ + uint64_t value; + ssize_t size; + int fd; + + fd = sys_eventfd2(1, 0); + ASSERT_GE(fd, 0); + + size = read(fd, &value, sizeof(int)); + EXPECT_EQ(size, -1); + EXPECT_EQ(errno, EINVAL); + + size = read(fd, &value, sizeof(value)); + EXPECT_EQ(size, sizeof(value)); + EXPECT_EQ(value, 1); + + close(fd); +} + + +/* + * If EFD_SEMAPHORE was not specified and the eventfd counter has a nonzero + * value, then a read(2) returns 8 bytes containing that value, and the + * counter's value is reset to zero. + * If the eventfd counter is zero at the time of the call to read(2), then the + * call fails with the error EAGAIN if the file descriptor has been made nonblocking. + */ +TEST(eventfd_check_read_with_nonsemaphore) +{ + uint64_t value; + ssize_t size; + int fd; + int i; + + fd = sys_eventfd2(0, EFD_NONBLOCK); + ASSERT_GE(fd, 0); + + value = 1; + for (i = 0; i < EVENTFD_TEST_ITERATIONS; i++) { + size = write(fd, &value, sizeof(value)); + EXPECT_EQ(size, sizeof(value)); + } + + size = read(fd, &value, sizeof(value)); + EXPECT_EQ(size, sizeof(uint64_t)); + EXPECT_EQ(value, EVENTFD_TEST_ITERATIONS); + + size = read(fd, &value, sizeof(value)); + EXPECT_EQ(size, -1); + EXPECT_EQ(errno, EAGAIN); + + close(fd); +} + +/* + * If EFD_SEMAPHORE was specified and the eventfd counter has a nonzero value, + * then a read(2) returns 8 bytes containing the value 1, and the counter's + * value is decremented by 1. + * If the eventfd counter is zero at the time of the call to read(2), then the + * call fails with the error EAGAIN if the file descriptor has been made nonblocking. + */ +TEST(eventfd_check_read_with_semaphore) +{ + uint64_t value; + ssize_t size; + int fd; + int i; + + fd = sys_eventfd2(0, EFD_SEMAPHORE|EFD_NONBLOCK); + ASSERT_GE(fd, 0); + + value = 1; + for (i = 0; i < EVENTFD_TEST_ITERATIONS; i++) { + size = write(fd, &value, sizeof(value)); + EXPECT_EQ(size, sizeof(value)); + } + + for (i = 0; i < EVENTFD_TEST_ITERATIONS; i++) { + size = read(fd, &value, sizeof(value)); + EXPECT_EQ(size, sizeof(value)); + EXPECT_EQ(value, 1); + } + + size = read(fd, &value, sizeof(value)); + EXPECT_EQ(size, -1); + EXPECT_EQ(errno, EAGAIN); + + close(fd); +} + TEST_HARNESS_MAIN -- 2.25.1

5 days, 20 hours

1
0
0 0

[PATCH v5 0/5] pids controller events rework

by Michal Koutný

This makes pids.events:max affine to pids.max limit. How are the new events supposed to be useful? - pids.events.local:max - tells that cgroup's limit is hit (too tight?) - pids.events:* - "only" directs top-down search to cgroups of interest Changes from v4 (https://lore.kernel.org/r/20240416142014.27630-1-mkoutny@suse.com) - rebased on cgroup/for-6.10 (rather cgroup/for-next, there's no rush) - introduce pids_files_legacy at one place (Tejun) - more descriptive Documentation/ (Tejun) Changes from v3 (https://lore.kernel.org/r/20240405170548.15234-1-mkoutny@suse.com) - use existing functions for TAP output in selftest (Muhammad) - formatting in selftest (Muhammad) - remove pids.events:max.imposed event, keep it internal (Johannes) - allow legacy behavior with a mount option - detach migration charging patches - drop RFC prefix Changes from v2 (https://lore.kernel.org/r/20200205134426.10570-1-mkoutny@suse.com) - implemented pids.events.local (Tejun) - added migration charging [1] https://lore.kernel.org/r/20230202155626.1829121-1-hannes@cmpxchg.org/ Michal Koutný (5): cgroup/pids: Separate semantics of pids.events related to pids.max cgroup/pids: Make event counters hierarchical cgroup/pids: Add pids.events.local selftests: cgroup: Lexicographic order in Makefile selftests: cgroup: Add basic tests for pids controller Documentation/admin-guide/cgroup-v1/pids.rst | 3 +- Documentation/admin-guide/cgroup-v2.rst | 21 ++- include/linux/cgroup-defs.h | 7 +- kernel/cgroup/cgroup.c | 15 +- kernel/cgroup/pids.c | 129 +++++++++++--- tools/testing/selftests/cgroup/.gitignore | 11 +- tools/testing/selftests/cgroup/Makefile | 25 +-- tools/testing/selftests/cgroup/test_pids.c | 178 +++++++++++++++++++ 8 files changed, 346 insertions(+), 43 deletions(-) create mode 100644 tools/testing/selftests/cgroup/test_pids.c base-commit: 21c38a3bd4ee3fb7337d013a638302fb5e5f9dc2 -- 2.44.0

6 days, 1 hour

2
6
0 0

[PATCH] selftest: mm: Test if hugepage does not get leaked during __bio_release_pages()

by Donet Tom

Commit 1b151e2435fc ("block: Remove special-casing of compound pages") caused a change in behaviour when releasing the pages if the buffer does not start at the beginning of the page. This was because the calculation of the number of pages to release was incorrect. This was fixed by commit 38b43539d64b ("block: Fix page refcounts for unaligned buffers in __bio_release_pages()"). We pin the user buffer during direct I/O writes. If this buffer is a hugepage, bio_release_page() will unpin it and decrement all references and pin counts at ->bi_end_io. However, if any references to the hugepage remain post-I/O, the hugepage will not be freed upon unmap, leading to a memory leak. This patch verifies that a hugepage, used as a user buffer for DIO operations, is correctly freed upon unmapping, regardless of whether the offsets are aligned or unaligned w.r.t page boundary. Test Result Fail Scenario (Without the fix) -------------------------------------------------------- []# ./hugetlb_dio TAP version 13 1..4 No. Free pages before allocation : 7 No. Free pages after munmap : 7 ok 1 : Huge pages freed successfully ! No. Free pages before allocation : 7 No. Free pages after munmap : 7 ok 2 : Huge pages freed successfully ! No. Free pages before allocation : 7 No. Free pages after munmap : 7 ok 3 : Huge pages freed successfully ! No. Free pages before allocation : 7 No. Free pages after munmap : 6 not ok 4 : Huge pages not freed! Totals: pass:3 fail:1 xfail:0 xpass:0 skip:0 error:0 Test Result PASS Scenario (With the fix) --------------------------------------------------------- []#./hugetlb_dio TAP version 13 1..4 No. Free pages before allocation : 7 No. Free pages after munmap : 7 ok 1 : Huge pages freed successfully ! No. Free pages before allocation : 7 No. Free pages after munmap : 7 ok 2 : Huge pages freed successfully ! No. Free pages before allocation : 7 No. Free pages after munmap : 7 ok 3 : Huge pages freed successfully ! No. Free pages before allocation : 7 No. Free pages after munmap : 7 ok 4 : Huge pages freed successfully ! Totals: pass:4 fail:0 xfail:0 xpass:0 skip:0 error:0 Signed-off-by: Donet Tom <donettom(a)linux.ibm.com> Signed-off-by: Ritesh Harjani (IBM) <ritesh.list(a)gmail.com> --- tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/hugetlb_dio.c | 118 +++++++++++++++++++++++ 2 files changed, 119 insertions(+) create mode 100644 tools/testing/selftests/mm/hugetlb_dio.c diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index eb5f39a2668b..87d8130b3376 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -71,6 +71,7 @@ TEST_GEN_FILES += ksm_functional_tests TEST_GEN_FILES += mdwe_test TEST_GEN_FILES += hugetlb_fault_after_madv TEST_GEN_FILES += hugetlb_madv_vs_map +TEST_GEN_FILES += hugetlb_dio ifneq ($(ARCH),arm64) TEST_GEN_FILES += soft-dirty diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c new file mode 100644 index 000000000000..6f6587c7913c --- /dev/null +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program tests for hugepage leaks after DIO writes to a file using a + * hugepage as the user buffer. During DIO, the user buffer is pinned and + * should be properly unpinned upon completion. This patch verifies that the + * kernel correctly unpins the buffer at DIO completion for both aligned and + * unaligned user buffer offsets (w.r.t page boundary), ensuring the hugepage + * is freed upon unmapping. + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <sys/stat.h> +#include <stdlib.h> +#include <fcntl.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <sys/mman.h> +#include "vm_util.h" +#include "../kselftest.h" + +void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) +{ + int fd; + char *buffer = NULL; + char *orig_buffer = NULL; + size_t h_pagesize = 0; + size_t writesize; + int free_hpage_b = 0; + int free_hpage_a = 0; + + writesize = end_off - start_off; + + /* Get the default huge page size */ + h_pagesize = default_huge_page_size(); + if (!h_pagesize) + ksft_exit_fail_msg("Unable to determine huge page size\n"); + + /* Open the file to DIO */ + fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT); + if (fd < 0) + ksft_exit_fail_msg("Error opening file"); + + /* Get the free huge pages before allocation */ + free_hpage_b = get_free_hugepages(); + if (free_hpage_b == 0) { + close(fd); + ksft_exit_skip("No free hugepage, exiting!\n"); + } + + /* Allocate a hugetlb page */ + orig_buffer = mmap(NULL, h_pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE + | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + if (orig_buffer == MAP_FAILED) { + close(fd); + ksft_exit_fail_msg("Error mapping memory"); + } + buffer = orig_buffer; + buffer += start_off; + + memset(buffer, 'A', writesize); + + /* Write the buffer to the file */ + if (write(fd, buffer, writesize) != (writesize)) { + munmap(orig_buffer, h_pagesize); + close(fd); + ksft_exit_fail_msg("Error writing to file"); + } + + /* unmap the huge page */ + munmap(orig_buffer, h_pagesize); + close(fd); + + /* Get the free huge pages after unmap*/ + free_hpage_a = get_free_hugepages(); + + /* + * If the no. of free hugepages before allocation and after unmap does + * not match - that means there could still be a page which is pinned. + */ + if (free_hpage_a != free_hpage_b) { + printf("No. Free pages before allocation : %d\n", free_hpage_b); + printf("No. Free pages after munmap : %d\n", free_hpage_a); + ksft_test_result_fail(": Huge pages not freed!\n"); + } else { + printf("No. Free pages before allocation : %d\n", free_hpage_b); + printf("No. Free pages after munmap : %d\n", free_hpage_a); + ksft_test_result_pass(": Huge pages freed successfully !\n"); + } +} + +int main(void) +{ + size_t pagesize = 0; + + ksft_print_header(); + ksft_set_plan(4); + + /* Get base page size */ + pagesize = psize(); + + /* start and end is aligned to pagesize */ + run_dio_using_hugetlb(0, (pagesize * 3)); + + /* start is aligned but end is not aligned */ + run_dio_using_hugetlb(0, (pagesize * 3) - (pagesize / 2)); + + /* start is unaligned and end is aligned */ + run_dio_using_hugetlb(pagesize / 2, (pagesize * 3)); + + /* both start and end are unaligned */ + run_dio_using_hugetlb(pagesize / 2, (pagesize * 3) + (pagesize / 2)); + + ksft_finished(); + return 0; +} + -- 2.39.3

1 week

5
12
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror