February 2025 - Linux-kselftest-mirror

[PATCH net-next v3] selftests: net: add support for testing SO_RCVMARK and SO_RCVPRIORITY

by Anna Emese Nyiri

Introduce tests to verify the correct functionality of the SO_RCVMARK and SO_RCVPRIORITY socket options. Key changes include: - so_rcv_listener.c: Implements a receiver application to test the correct behavior of the SO_RCVMARK and SO_RCVPRIORITY options. - test_so_rcv.sh: Provides a shell script to automate testing for these options. - Makefile: Integrates test_so_rcv.sh into the kernel selftests. v3: - Add the C part to TEST_GEN_FILES. - Ensure the test fails if no cmsg of type opt.name is received in so_rcv_listener.c - Rebased on net-next. v2: https://lore.kernel.org/netdev/20250210192216.37756-1-annaemesenyiri@gmail.… - Add the C part to TEST_GEN_PROGS and .gitignore. - Modify buffer space and add IPv6 testing option in so_rcv_listener.c. - Add IPv6 testing, remove unnecessary comment, add kselftest exit codes, run both binaries in a namespace, and add sleep in test_so_rcv.sh. The sleep was added to ensure that the listener process has enough time to start before the sender attempts to connect. - Rebased on net-next. v1: https://lore.kernel.org/netdev/20250129143601.16035-2-annaemesenyiri@gmail.… Suggested-by: Jakub Kicinski <kuba(a)kernel.org> Suggested-by: Ferenc Fejes <fejes(a)inf.elte.hu> Signed-off-by: Anna Emese Nyiri <annaemesenyiri(a)gmail.com> --- tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 2 + tools/testing/selftests/net/so_rcv_listener.c | 168 ++++++++++++++++++ tools/testing/selftests/net/test_so_rcv.sh | 73 ++++++++ 4 files changed, 244 insertions(+) create mode 100644 tools/testing/selftests/net/so_rcv_listener.c create mode 100755 tools/testing/selftests/net/test_so_rcv.sh diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 28a715a8ef2b..80dcae53ef55 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -42,6 +42,7 @@ socket so_incoming_cpu so_netns_cookie so_txtime +so_rcv_listener stress_reuseport_listen tap tcp_fastopen_backup_key diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b6271714504d..8d6116b80cf1 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -33,6 +33,7 @@ TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh TEST_PROGS += cmsg_so_priority.sh +TEST_PROGS += test_so_rcv.sh TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh TEST_PROGS += netns-name.sh TEST_PROGS += nl_netdev.py @@ -76,6 +77,7 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap epoll_busy_ TEST_GEN_FILES += toeplitz TEST_GEN_FILES += cmsg_sender TEST_GEN_FILES += stress_reuseport_listen +TEST_GEN_FILES += so_rcv_listener TEST_PROGS += test_vxlan_vnifiltering.sh TEST_GEN_FILES += io_uring_zerocopy_tx TEST_PROGS += io_uring_zerocopy_tx.sh diff --git a/tools/testing/selftests/net/so_rcv_listener.c b/tools/testing/selftests/net/so_rcv_listener.c new file mode 100644 index 000000000000..4b0b14edce61 --- /dev/null +++ b/tools/testing/selftests/net/so_rcv_listener.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <errno.h> +#include <netdb.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <linux/types.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <arpa/inet.h> + +#ifndef SO_RCVPRIORITY +#define SO_RCVPRIORITY 82 +#endif + +struct options { + __u32 val; + int name; + int rcvname; + const char *host; + const char *service; +} opt; + +static void __attribute__((noreturn)) usage(const char *bin) +{ + printf("Usage: %s [opts] <dst host> <dst port / service>\n", bin); + printf("Options:\n" + "\t\t-M val Test SO_RCVMARK\n" + "\t\t-P val Test SO_RCVPRIORITY\n" + ""); + exit(EXIT_FAILURE); +} + +static void parse_args(int argc, char *argv[]) +{ + int o; + + while ((o = getopt(argc, argv, "M:P:")) != -1) { + switch (o) { + case 'M': + opt.val = atoi(optarg); + opt.name = SO_MARK; + opt.rcvname = SO_RCVMARK; + break; + case 'P': + opt.val = atoi(optarg); + opt.name = SO_PRIORITY; + opt.rcvname = SO_RCVPRIORITY; + break; + default: + usage(argv[0]); + break; + } + } + + if (optind != argc - 2) + usage(argv[0]); + + opt.host = argv[optind]; + opt.service = argv[optind + 1]; +} + +int main(int argc, char *argv[]) +{ + int err = 0; + int recv_fd = -1; + int ret_value = 0; + __u32 recv_val; + struct cmsghdr *cmsg; + char cbuf[CMSG_SPACE(sizeof(__u32))]; + char recv_buf[CMSG_SPACE(sizeof(__u32))]; + struct iovec iov[1]; + struct msghdr msg; + struct sockaddr_in recv_addr4; + struct sockaddr_in6 recv_addr6; + + parse_args(argc, argv); + + int family = strchr(opt.host, ':') ? AF_INET6 : AF_INET; + + recv_fd = socket(family, SOCK_DGRAM, IPPROTO_UDP); + if (recv_fd < 0) { + perror("Can't open recv socket"); + ret_value = -errno; + goto cleanup; + } + + err = setsockopt(recv_fd, SOL_SOCKET, opt.rcvname, &opt.val, sizeof(opt.val)); + if (err < 0) { + perror("Recv setsockopt error"); + ret_value = -errno; + goto cleanup; + } + + if (family == AF_INET) { + memset(&recv_addr4, 0, sizeof(recv_addr4)); + recv_addr4.sin_family = family; + recv_addr4.sin_port = htons(atoi(opt.service)); + + if (inet_pton(family, opt.host, &recv_addr4.sin_addr) <= 0) { + perror("Invalid IPV4 address"); + ret_value = -errno; + goto cleanup; + } + + err = bind(recv_fd, (struct sockaddr *)&recv_addr4, sizeof(recv_addr4)); + } else { + memset(&recv_addr6, 0, sizeof(recv_addr6)); + recv_addr6.sin6_family = family; + recv_addr6.sin6_port = htons(atoi(opt.service)); + + if (inet_pton(family, opt.host, &recv_addr6.sin6_addr) <= 0) { + perror("Invalid IPV6 address"); + ret_value = -errno; + goto cleanup; + } + + err = bind(recv_fd, (struct sockaddr *)&recv_addr6, sizeof(recv_addr6)); + } + + if (err < 0) { + perror("Recv bind error"); + ret_value = -errno; + goto cleanup; + } + + iov[0].iov_base = recv_buf; + iov[0].iov_len = sizeof(recv_buf); + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = iov; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + + err = recvmsg(recv_fd, &msg, 0); + if (err < 0) { + perror("Message receive error"); + ret_value = -errno; + goto cleanup; + } + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == opt.name) { + recv_val = *(__u32 *)CMSG_DATA(cmsg); + printf("Received value: %u\n", recv_val); + + if (recv_val != opt.val) { + fprintf(stderr, "Error: expected value: %u, got: %u\n", + opt.val, recv_val); + ret_value = -EINVAL; + } + goto cleanup; + } + } + + fprintf(stderr, "Error: No matching cmsg received\n"); + ret_value = -ENOMSG; + +cleanup: + if (recv_fd >= 0) + close(recv_fd); + + return ret_value; +} diff --git a/tools/testing/selftests/net/test_so_rcv.sh b/tools/testing/selftests/net/test_so_rcv.sh new file mode 100755 index 000000000000..d8aa4362879d --- /dev/null +++ b/tools/testing/selftests/net/test_so_rcv.sh @@ -0,0 +1,73 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +HOSTS=("127.0.0.1" "::1") +PORT=1234 +TOTAL_TESTS=0 +FAILED_TESTS=0 + +declare -A TESTS=( + ["SO_RCVPRIORITY"]="-P 2" + ["SO_RCVMARK"]="-M 3" +) + +check_result() { + ((TOTAL_TESTS++)) + if [ "$1" -ne 0 ]; then + ((FAILED_TESTS++)) + fi +} + +cleanup() +{ + cleanup_ns $NS +} + +trap cleanup EXIT + +setup_ns NS + +for HOST in "${HOSTS[@]}"; do + PROTOCOL="IPv4" + if [[ "$HOST" == "::1" ]]; then + PROTOCOL="IPv6" + fi + for test_name in "${!TESTS[@]}"; do + echo "Running $test_name test, $PROTOCOL" + arg=${TESTS[$test_name]} + + ip netns exec $NS ./so_rcv_listener $arg $HOST $PORT & + LISTENER_PID=$! + + sleep 0.5 + + if ! ip netns exec $NS ./cmsg_sender $arg $HOST $PORT; then + echo "Sender failed for $test_name, $PROTOCOL" + kill "$LISTENER_PID" 2>/dev/null + wait "$LISTENER_PID" + check_result 1 + continue + fi + + wait "$LISTENER_PID" + LISTENER_EXIT_CODE=$? + + if [ "$LISTENER_EXIT_CODE" -eq 0 ]; then + echo "Rcv test OK for $test_name, $PROTOCOL" + check_result 0 + else + echo "Rcv test FAILED for $test_name, $PROTOCOL" + check_result 1 + fi + done +done + +if [ "$FAILED_TESTS" -ne 0 ]; then + echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed" + exit ${KSFT_FAIL} +else + echo "OK - All $TOTAL_TESTS tests passed" + exit ${KSFT_PASS} +fi -- 2.43.0

9 months

4
3
0 0

[PATCH net-next v8 0/3] netdev-genl: Add an xsk attribute to queues

by Joe Damato

Greetings: Welcome to v8. Minor change, see changelog below. Re-tested on my mlx5 system both with and without CONFIG_XDP_SOCKETS enabled and both with and without NETIF set. This is an attempt to followup on something Jakub asked me about [1], adding an xsk attribute to queues and more clearly documenting which queues are linked to NAPIs... After the RFC [2], Jakub suggested creating an empty nest for queues which have a pool, so I've adjusted this version to work that way. The nest can be extended in the future to express attributes about XSK as needed. Queues which are not used for AF_XDP do not have the xsk attribute present. I've run the included test on: - my mlx5 machine (via NETIF=) - without setting NETIF And the test seems to pass in both cases. Thanks, Joe [1]: https://lore.kernel.org/netdev/20250113143109.60afa59a@kernel.org/ [2]: https://lore.kernel.org/netdev/20250129172431.65773-1-jdamato@fastly.com/ v8: - Update the Makefile in patch 3 to use TEST_GEN_FILES instead of TEST_GET_PROGS. - Fix a codespell complaint in xdp_helper.c. v7: https://lore.kernel.org/netdev/20250213192336.42156-1-jdamato@fastly.com/ - Added CONFIG_XDP_SOCKETS to selftests/driver/net/config as suggested by Stanislav. - Updated xdp_helper.c to return -1 for AF_XDP non-existence, but 1 for other failures. - Updated queues.py to mark test as skipped if AF_XDP does not exist. v6: https://lore.kernel.org/bpf/20250210193903.16235-1-jdamato@fastly.com/ - Added ifdefs for CONFIG_XDP_SOCKETS in patch 2 as Stanislav suggested. v5: https://lore.kernel.org/bpf/20250208041248.111118-1-jdamato@fastly.com/ - Removed unused ret variable from patch 2 as Simon suggested. v4: https://lore.kernel.org/lkml/20250207030916.32751-1-jdamato@fastly.com/ - Add patch 1, as suggested by Jakub, which adds an empty nest helper. - Use the helper in patch 2, which makes the code cleaner and prevents a possible bug. v3: https://lore.kernel.org/netdev/20250204191108.161046-1-jdamato@fastly.com/ - Change comment format in patch 2 to avoid kdoc warnings. No other changes. v2: https://lore.kernel.org/all/20250203185828.19334-1-jdamato@fastly.com/ - Switched from RFC to actual submission now that net-next is open - Adjusted patch 1 to include an empty nest as suggested by Jakub - Adjusted patch 2 to update the test based on changes to patch 1, and to incorporate some Python feedback from Jakub :) rfc: https://lore.kernel.org/netdev/20250129172431.65773-1-jdamato@fastly.com/ Joe Damato (3): netlink: Add nla_put_empty_nest helper netdev-genl: Add an XSK attribute to queues selftests: drv-net: Test queue xsk attribute Documentation/netlink/specs/netdev.yaml | 13 ++- include/net/netlink.h | 15 +++ include/uapi/linux/netdev.h | 6 ++ net/core/netdev-genl.c | 12 +++ tools/include/uapi/linux/netdev.h | 6 ++ .../testing/selftests/drivers/net/.gitignore | 2 + tools/testing/selftests/drivers/net/Makefile | 3 + tools/testing/selftests/drivers/net/config | 1 + tools/testing/selftests/drivers/net/queues.py | 42 +++++++- .../selftests/drivers/net/xdp_helper.c | 98 +++++++++++++++++++ 10 files changed, 194 insertions(+), 4 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/.gitignore create mode 100644 tools/testing/selftests/drivers/net/xdp_helper.c base-commit: 7a7e0197133d18cfd9931e7d3a842d0f5730223f -- 2.43.0

9 months

2
2
0 0

[PATCH 0/2] selftests/mm: Allow execution on systems without huge pages

by Mark Brown

Currently the mm selftests refuse to run if we don't have huge page support but there are plenty of tests that don't depend on this feature, relax this requirement to allow coverage on relevant systems (eg, most 32 bit arm ones). While doing this I noticed a bug with an existing check if we're running THP tests, the fix overlaps with the above change so is sent as part of a series. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Mark Brown (2): selftests/mm: Fix check for running THP tests selftests/mm: Allow tests to run with no huge pages support tools/testing/selftests/mm/run_vmtests.sh | 68 +++++++++++++++++++------------ 1 file changed, 43 insertions(+), 25 deletions(-) --- base-commit: a64dcfb451e254085a7daee5fe51bf22959d52d3 change-id: 20250211-kselftest-mm-no-hugepages-ee5917a170eb Best regards, -- Mark Brown <broonie(a)kernel.org>

9 months

2
4
0 0

[PATCH 2/2] rseq/selftests: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. Since mm_cid compaction is less likely for tasks running in short bursts, we increase the likelihood by just running a busy loop at every iteration. This compaction is a best effort work and this behaviour is currently acceptable. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 208 ++++++++++++++++++ 3 files changed, 210 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce4..2c89f97e4f737 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb586..ce1b38f46a355 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice + param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..8808500466d02 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,208 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 0.5 s */ +#define RUNNER_PERIOD 500000 +/* Number of runs before we terminate or get the token */ +#define THREAD_RUNS 5 + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + /* + * Currently mm_cid compaction is less likely for tasks + * running in short bursts: increase likelihood by just + * running for some time doing nothing. + */ + for (int j = 0; j < 0xffff; j++) + for (int k = 0; k < 0xffff; k++) + asm(""); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.48.1

9 months

2
1
0 0

[RFC v2 0/5] mm: introduce THP deferred setting

by Nico Pache

This series is a follow-up to [1], which adds mTHP support to khugepaged. mTHP khugepaged support was necessary for the global="defer" and mTHP="inherit" case (and others) to make sense. We've seen cases were customers switching from RHEL7 to RHEL8 see a significant increase in the memory footprint for the same workloads. Through our investigations we found that a large contributing factor to the increase in RSS was an increase in THP usage. For workloads like MySQL, or when using allocators like jemalloc, it is often recommended to set /transparent_hugepages/enabled=never. This is in part due to performance degradations and increased memory waste. This series introduces enabled=defer, this setting acts as a middle ground between always and madvise. If the mapping is MADV_HUGEPAGE, the page fault handler will act normally, making a hugepage if possible. If the allocation is not MADV_HUGEPAGE, then the page fault handler will default to the base size allocation. The caveat is that khugepaged can still operate on pages thats not MADV_HUGEPAGE. This allows for two things... one, applications specifically designed to use hugepages will get them, and two, applications that don't use hugepages can still benefit from them without aggressively inserting THPs at every possible chance. This curbs the memory waste, and defers the use of hugepages to khugepaged. Khugepaged can then scan the memory for eligible collapsing. Admins may want to lower max_ptes_none, if not, khugepaged may aggressively collapse single allocations into hugepages. TESTING: - Built for x86_64, aarch64, ppc64le, and s390x - selftests mm - In [1] I provided a script [2] that has multiple access patterns - lots of general use. These changes have been running in my VM for some time - redis testing. This test was my original case for the defer mode. What I was able to prove was that THP=always leads to increased max_latency cases; hence why it is recommended to disable THPs for redis servers. However with 'defer' we dont have the max_latency spikes and can still get the system to utilize THPs. I further tested this with the mTHP defer setting and found that redis (and probably other jmalloc users) can utilize THPs via defer (+mTHP defer) without a large latency penalty and some potential gains. I uploaded some mmtest results here [3] which compares: stock+thp=never stock+(m)thp=always khugepaged-mthp + defer (max_ptes_none=64) The results show that (m)THPs can cause some throughput regression in some cases, but also has gains in other cases. The mTHP+defer results have more gains and less losses over the (m)THP=always case. V2 Changes: - base changes on mTHP khugepaged support - Fix selftests parsing issue - add mTHP defer option - add mTHP defer Documentation [1] - https://lkml.org/lkml/2025/2/10/1982 [2] - https://gitlab.com/npache/khugepaged_mthp_test [3] - https://people.redhat.com/npache/mthp_khugepaged_defer/testoutput2/output.h… Nico Pache (5): mm: defer THP insertion to khugepaged mm: document transparent_hugepage=defer usage selftests: mm: add defer to thp setting parser khugepaged: add defer option to mTHP options mm: document mTHP defer setting Documentation/admin-guide/mm/transhuge.rst | 40 ++++++++++--- include/linux/huge_mm.h | 18 +++++- mm/huge_memory.c | 69 +++++++++++++++++++--- mm/khugepaged.c | 10 ++-- tools/testing/selftests/mm/thp_settings.c | 1 + tools/testing/selftests/mm/thp_settings.h | 1 + 6 files changed, 115 insertions(+), 24 deletions(-) -- 2.48.1

9 months

2
13
0 0

[PATCH] selftests/damon/damos_quota_goal: handle minimum quota that cannot be further reduced

by SeongJae Park

damos_quota_goal.py selftest see if DAMOS quota goals tuning feature increases or reduces the effective size quota for given score as expected. The tuning feature sets the minimum quota size as one byte, so if the effective size quota is already one, we cannot expect it further be reduced. However the test is not aware of the edge case, and fails since it shown no expected change of the effective quota. Handle the case by updating the failure logic for no change to see if it was the case, and simply skips to next test input. Fixes: f1c07c0a1662b ("selftests/damon: add a test for DAMOS quota goal") Cc: <stable(a)vger.kernel.org> # 6.10.x Reported-by: kernel test robot <oliver.sang(a)intel.com> Closes: https://lore.kernel.org/oe-lkp/202502171423.b28a918d-lkp@intel.com Signed-off-by: SeongJae Park <sj(a)kernel.org> --- tools/testing/selftests/damon/damos_quota_goal.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/damon/damos_quota_goal.py b/tools/testing/selftests/damon/damos_quota_goal.py index 18246f3b62f7..f76e0412b564 100755 --- a/tools/testing/selftests/damon/damos_quota_goal.py +++ b/tools/testing/selftests/damon/damos_quota_goal.py @@ -63,6 +63,9 @@ def main(): if last_effective_bytes != 0 else -1.0)) if last_effective_bytes == goal.effective_bytes: + # effective quota was already minimum that cannot be more reduced + if expect_increase is False and last_effective_bytes == 1: + continue print('efective bytes not changed: %d' % goal.effective_bytes) exit(1) base-commit: 20017459916819f8ae15ca3840e71fbf0ea8354e -- 2.39.5

9 months

1
0
0 0

[PATCH 0/2] selftests/ftrace: Fix ftracetest test cases

by Masami Hiramatsu (Google)

Here is a couple of patches to fix issues. I think mount_options.tc's one is a real bug(I'm not sure how it worked), but another one is an enhancement for (my) execution environment. Anyway, those should go through kselftests tree. Thank you, --- Masami Hiramatsu (Google) (2): selftests/ftrace: Fix to use remount when testing mount GID option selftests/ftrace: Make uprobe test more robust against binary name .../ftrace/test.d/00basic/mount_options.tc | 8 ++++---- .../ftrace/test.d/dynevent/add_remove_uprobe.tc | 4 +++- 2 files changed, 7 insertions(+), 5 deletions(-) -- Masami Hiramatsu (Google) <mhiramat(a)kernel.org>

9 months

4
5
0 0

Re: [PATCH v8 3/4] scanf: convert self-test to KUnit

by Andy Shevchenko

On Sat, Feb 15, 2025 at 02:52:22PM -0500, Tamir Duberstein wrote: > On Sat, Feb 15, 2025 at 1:51 PM kernel test robot <lkp(a)intel.com> wrote: > I am not able to reproduce these warnings with clang 19.1.7. They also > don't obviously make sense to me. Please, when reply, remove boielrplate stuff! I have just wasted a couple of minutes to understand what's going on in the message that is 2700 lines of text as the reply to the bot message which was ~700 lines. -- With Best Regards, Andy Shevchenko

9 months

2
1
0 0

[PATCH v6 0/6] ptrace: introduce PTRACE_SET_SYSCALL_INFO API

by Dmitry V. Levin

PTRACE_SET_SYSCALL_INFO is a generic ptrace API that complements PTRACE_GET_SYSCALL_INFO by letting the ptracer modify details of system calls the tracee is blocked in. This API allows ptracers to obtain and modify system call details in a straightforward and architecture-agnostic way, providing a consistent way of manipulating the system call number and arguments across architectures. As in case of PTRACE_GET_SYSCALL_INFO, PTRACE_SET_SYSCALL_INFO also does not aim to address numerous architecture-specific system call ABI peculiarities, like differences in the number of system call arguments for such system calls as pread64 and preadv. The current implementation supports changing only those bits of system call information that are used by strace system call tampering, namely, syscall number, syscall arguments, and syscall return value. Support of changing additional details returned by PTRACE_GET_SYSCALL_INFO, such as instruction pointer and stack pointer, could be added later if needed, by using struct ptrace_syscall_info.flags to specify the additional details that should be set. Currently, "flags" and "reserved" fields of struct ptrace_syscall_info must be initialized with zeroes; "arch", "instruction_pointer", and "stack_pointer" fields are currently ignored. PTRACE_SET_SYSCALL_INFO currently supports only PTRACE_SYSCALL_INFO_ENTRY, PTRACE_SYSCALL_INFO_EXIT, and PTRACE_SYSCALL_INFO_SECCOMP operations. Other operations could be added later if needed. Ideally, PTRACE_SET_SYSCALL_INFO should have been introduced along with PTRACE_GET_SYSCALL_INFO, but it didn't happen. The last straw that convinced me to implement PTRACE_SET_SYSCALL_INFO was apparent failure to provide an API of changing the first system call argument on riscv architecture [1]. ptrace(2) man page: long ptrace(enum __ptrace_request request, pid_t pid, void *addr, void *data); ... PTRACE_SET_SYSCALL_INFO Modify information about the system call that caused the stop. The "data" argument is a pointer to struct ptrace_syscall_info that specifies the system call information to be set. The "addr" argument should be set to sizeof(struct ptrace_syscall_info)). [1] https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Notes: v6: * mips: Submit mips_get_syscall_arg() o32 fix via mips tree to get it merged into v6.14-rc3 * Rebase to v6.14-rc3 * v5: https://lore.kernel.org/all/20250210113336.GA887@strace.io/ v5: * ptrace: Extend the commit message to say that the new API does not aim to address numerous architecture-specific syscall ABI peculiarities * selftests: Add a workaround for s390 16-bit syscall numbers * Add more Acked-by * v4: https://lore.kernel.org/all/20250203065849.GA14120@strace.io/ v4: * Split out syscall_set_return_value() for hexagon into a separate patch * s390: Change the style of syscall_set_arguments() implementation as requested * Add more Reviewed-by * v3: https://lore.kernel.org/all/20250128091445.GA8257@strace.io/ v3: * powerpc: Submit syscall_set_return_value() fix for "sc" case separately * mips: Do not introduce erroneous argument truncation on mips n32, add a detailed description to the commit message of the mips_get_syscall_arg() change * ptrace: Add explicit padding to the end of struct ptrace_syscall_info, simplify obtaining of user ptrace_syscall_info, do not introduce PTRACE_SYSCALL_INFO_SIZE_VER0 * ptrace: Change the return type of ptrace_set_syscall_info_* functions from "unsigned long" to "int" * ptrace: Add -ERANGE check to ptrace_set_syscall_info_exit(), add comments to -ERANGE checks * ptrace: Update comments about supported syscall stops * selftests: Extend set_syscall_info test, fix for mips n32 * Add Tested-by and Reviewed-by v2: * Add patch to fix syscall_set_return_value() on powerpc * Add patch to fix mips_get_syscall_arg() on mips * Add syscall_set_return_value() implementation on hexagon * Add syscall_set_return_value() invocation to syscall_set_nr() on arm and arm64. * Fix syscall_set_nr() and mips_set_syscall_arg() on mips * Add a comment to syscall_set_nr() on arc, powerpc, s390, sh, and sparc * Remove redundant ptrace_syscall_info.op assignments in ptrace_get_syscall_info_* * Minor style tweaks in ptrace_get_syscall_info_op() * Remove syscall_set_return_value() invocation from ptrace_set_syscall_info_entry() * Skip syscall_set_arguments() invocation in case of syscall number -1 in ptrace_set_syscall_info_entry() * Split ptrace_syscall_info.reserved into ptrace_syscall_info.reserved and ptrace_syscall_info.flags * Use __kernel_ulong_t instead of unsigned long in set_syscall_info test Dmitry V. Levin (6): hexagon: add syscall_set_return_value() syscall.h: add syscall_set_arguments() syscall.h: introduce syscall_set_nr() ptrace_get_syscall_info: factor out ptrace_get_syscall_info_op ptrace: introduce PTRACE_SET_SYSCALL_INFO request selftests/ptrace: add a test case for PTRACE_SET_SYSCALL_INFO arch/arc/include/asm/syscall.h | 25 + arch/arm/include/asm/syscall.h | 37 ++ arch/arm64/include/asm/syscall.h | 29 + arch/csky/include/asm/syscall.h | 13 + arch/hexagon/include/asm/syscall.h | 21 + arch/loongarch/include/asm/syscall.h | 15 + arch/m68k/include/asm/syscall.h | 7 + arch/microblaze/include/asm/syscall.h | 7 + arch/mips/include/asm/syscall.h | 46 ++ arch/nios2/include/asm/syscall.h | 16 + arch/openrisc/include/asm/syscall.h | 13 + arch/parisc/include/asm/syscall.h | 19 + arch/powerpc/include/asm/syscall.h | 20 + arch/riscv/include/asm/syscall.h | 16 + arch/s390/include/asm/syscall.h | 21 + arch/sh/include/asm/syscall_32.h | 24 + arch/sparc/include/asm/syscall.h | 22 + arch/um/include/asm/syscall-generic.h | 19 + arch/x86/include/asm/syscall.h | 43 ++ arch/xtensa/include/asm/syscall.h | 18 + include/asm-generic/syscall.h | 30 + include/uapi/linux/ptrace.h | 7 +- kernel/ptrace.c | 179 +++++- tools/testing/selftests/ptrace/Makefile | 2 +- .../selftests/ptrace/set_syscall_info.c | 519 ++++++++++++++++++ 25 files changed, 1141 insertions(+), 27 deletions(-) create mode 100644 tools/testing/selftests/ptrace/set_syscall_info.c base-commit: 0ad2507d5d93f39619fc42372c347d6006b64319 -- ldv

9 months

1
0
0 0

[PATCH v7 0/6] introduce PIDFD_SELF* sentinels

by Lorenzo Stoakes

If you wish to utilise a pidfd interface to refer to the current process or thread it is rather cumbersome, requiring something like: int pidfd = pidfd_open(getpid(), 0 or PIDFD_THREAD); ... close(pidfd); Or the equivalent call opening /proc/self. It is more convenient to use a sentinel value to indicate to an interface that accepts a pidfd that we simply wish to refer to the current process thread. This series introduces sentinels for this purposes which can be passed as the pidfd in this instance rather than having to establish a dummy fd for this purpose. It is useful to refer to both the current thread from the userland's perspective for which we use PIDFD_SELF, and the current process from the userland's perspective, for which we use PIDFD_SELF_PROCESS. There is unfortunately some confusion between the kernel and userland as to what constitutes a process - a thread from the userland perspective is a process in userland, and a userland process is a thread group (more specifically the thread group leader from the kernel perspective). We therefore alias things thusly: * PIDFD_SELF_THREAD aliased by PIDFD_SELF - use PIDTYPE_PID. * PIDFD_SELF_THREAD_GROUP alised by PIDFD_SELF_PROCESS - use PIDTYPE_TGID. In all of the kernel code we refer to PIDFD_SELF_THREAD and PIDFD_SELF_THREAD_GROUP. However we expect users to use PIDFD_SELF and PIDFD_SELF_PROCESS. This matters for cases where, for instance, a user unshare()'s FDs or does thread-specific signal handling and where the user would be hugely confused if the FDs referenced or signal processed referred to the thread group leader rather than the individual thread. For now we only adjust pidfd_get_task() and the pidfd_send_signal() system call with specific handling for this, implementing this functionality for process_madvise(), process_mrelease() (albeit, using it here wouldn't really make sense) and pidfd_send_signal(). We defer making further changes, as this would require a significant rework of the pidfd mechanism. The motivating case here is to support PIDFD_SELF in process_madvise(), so this suffices for immediate uses. Moving forward, this can be further expanded to other uses. v7: * Reworked implementation according to Christian's requirements. We now only support process_madvise() and pidfd_send_signal() system calls with PIDFD_SELF as specified. * Updated tests to account for broken pidfd_open_test.c implementation. * Fixed missing includes in pidfd self tests. * Removed tests relating to functionality no longer supported. * Update guard pages test to use PIDFD_SELF. v6: * Avoid static inline in UAPI header as suggested by Pedro. * Place PIDFD_SELF values out of range of errors and any other sentinel as suggested by Pedro. https://lore.kernel.org/linux-mm/cover.1729926229.git.lorenzo.stoakes@oracl… v5: * Fixup self test dependencies on pidfd/pidfd.h. https://lore.kernel.org/linux-mm/cover.1729848252.git.lorenzo.stoakes@oracl… v4: * Avoid returning an fd in the __pidfd_get_pid() function as pointed out by Christian, instead simply always pin the pid and maintain fd scope in the helper alone. * Add wrapper header file in tools/include/linux to allow for import of UAPI pidfd.h header without encountering the collision between system fcntl.h and linux/fcntl.h as discussed with Shuah and John. * Fixup tests to import the UAPI pidfd.h header working around conflicts between system fcntl.h and linux/fcntl.h which the UAPI pidfd.h imports, as reported by Shuah. * Use an int for pidfd_is_self_sentinel() to avoid any dependency on stdbool.h in userland. https://lore.kernel.org/linux-mm/cover.1729198898.git.lorenzo.stoakes@oracl… v3: * Do not fput() an invalid fd as reported by kernel test bot. * Fix unintended churn from moving variable declaration. https://lore.kernel.org/linux-mm/cover.1729073310.git.lorenzo.stoakes@oracl… v2: * Fix tests as reported by Shuah. * Correct RFC version lore link. https://lore.kernel.org/linux-mm/cover.1728643714.git.lorenzo.stoakes@oracl… Non-RFC v1: * Removed RFC tag - there seems to be general consensus that this change is a good idea, but perhaps some debate to be had on implementation. It seems sensible then to move forward with the RFC flag removed. * Introduced PIDFD_SELF_THREAD, PIDFD_SELF_THREAD_GROUP and their aliases PIDFD_SELF and PIDFD_SELF_PROCESS respectively. * Updated testing accordingly. https://lore.kernel.org/linux-mm/cover.1728578231.git.lorenzo.stoakes@oracl… RFC version: https://lore.kernel.org/linux-mm/cover.1727644404.git.lorenzo.stoakes@oracl… Lorenzo Stoakes (6): pidfd: add PIDFD_SELF* sentinels to refer to own thread/process selftests/pidfd: add missing system header imcludes to pidfd tests tools: testing: separate out wait_for_pid() into helper header selftests: pidfd: add pidfd.h UAPI wrapper selftests: pidfd: add tests for PIDFD_SELF_* selftests/mm: use PIDFD_SELF in guard pages test include/uapi/linux/pidfd.h | 24 ++++ kernel/pid.c | 24 +++- kernel/signal.c | 106 +++++++++++------- tools/include/linux/pidfd.h | 14 +++ tools/testing/selftests/cgroup/test_kill.c | 2 +- tools/testing/selftests/mm/Makefile | 4 + tools/testing/selftests/mm/guard-pages.c | 15 +-- .../pid_namespace/regression_enomem.c | 2 +- tools/testing/selftests/pidfd/Makefile | 3 +- tools/testing/selftests/pidfd/pidfd.h | 28 +---- .../selftests/pidfd/pidfd_fdinfo_test.c | 1 + tools/testing/selftests/pidfd/pidfd_helpers.h | 39 +++++++ .../testing/selftests/pidfd/pidfd_open_test.c | 6 +- .../selftests/pidfd/pidfd_setns_test.c | 1 + tools/testing/selftests/pidfd/pidfd_test.c | 76 +++++++++++-- 15 files changed, 242 insertions(+), 103 deletions(-) create mode 100644 tools/include/linux/pidfd.h create mode 100644 tools/testing/selftests/pidfd/pidfd_helpers.h -- 2.48.1

9 months

8
26
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror February 2025