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

[PATCH v3 4/4] selftests/rseq: 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. 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. Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> 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 | 204 ++++++++++++++++++ 3 files changed, 206 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 0fda241fa62b..b3920c59bf40 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 0d0a5fae5954..bc4d940f66d4 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -17,7 +17,7 @@ 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 \ - syscall_errors_test + syscall_errors_test 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 000000000000..d13623625f5a --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,204 @@ +// 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) + +/* 50 ms */ +#define RUNNER_PERIOD 50000 +/* + * Number of runs before we terminate or get the token. + * The number is slowly increasing with the number of CPUs as the compaction + * process can take longer on larger systems. This is an arbitrary value. + */ +#define THREAD_RUNS (3 + args->num_cpus/8) + +/* + * 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); + 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; +} -- 2.51.0

2 months, 2 weeks

1
0
0 0

next-20250924: Internal error: Oops: mnt_ns_release (fs/namespace.c:148) __arm64_sys_listmount (fs/namespace.c:5936)

by Naresh Kamboju

While running LTP syscalls tests on Linux next-20250924 tag build the following kernel oops noticed on arm64 and x86_64 devices. First seen on next-20250924 Good: next-20250923 Bad: next-2025094 Regression Analysis: - New regression? yes - Reproducibility? yes Test regression: next-20250924: Internal error: Oops: mnt_ns_release (fs/namespace.c:148) __arm64_sys_listmount (fs/namespace.c:5936) Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> $ git log --oneline next-20250923..next-20250924 -- fs/namespace.c c54644c3221b6 (next/fs-next) Merge branch 'for-next' of https://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs.git 1f28cc19559a8 Merge branch 'namespace-6.18' into vfs.all e2c277f720291 Merge branch 'kernel-6.18.clone3' into vfs.all b2af83d5b8223 Merge branch 'vfs-6.18.mount' into vfs.all 29ecd1ca48ec2 Merge branch 'vfs-6.18.misc' into vfs.all d7610cb7454bb ns: simplify ns_common_init() further 59bfb66816809 listmount: don't call path_put() under namespace semaphore 2bc5bfbfd3f27 statmount: don't call path_put() under namespace semaphore ## Test log [ 41.821877] Internal error: Oops: 0000000096000005 [#1] SMP [ 41.919038] Modules linked in: cdc_ether usbnet sm3_ce sha3_ce nvme xhci_pci_renesas nvme_core arm_cspmu_module arm_spe_pmu ipmi_devintf ipmi_msghandler arm_cmn cppc_cpufreq drm fuse backlight [ 41.944048] CPU: 14 UID: 0 PID: 6416 Comm: listmount04 Not tainted 6.17.0-rc7-next-20250924 #1 PREEMPT [ 41.958197] Hardware name: Inspur NF5280R7/Mitchell MB, BIOS 04.04.00004001 2025-02-04 22:23:30 02/04/2025 [ 41.967837] pstate: 63400009 (nZCv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) [ 41.974958] pc : mnt_ns_release (arch/arm64/include/asm/atomic_lse.h:62 (discriminator 1) arch/arm64/include/asm/atomic_lse.h:76 (discriminator 1) arch/arm64/include/asm/atomic.h:51 (discriminator 1) include/linux/atomic/atomic-arch-fallback.h:944 (discriminator 1) include/linux/atomic/atomic-instrumented.h:401 (discriminator 1) include/linux/refcount.h:389 (discriminator 1) include/linux/refcount.h:432 (discriminator 1) include/linux/refcount.h:450 (discriminator 1) fs/namespace.c:148 (discriminator 1)) [ 41.981910] lr : __arm64_sys_listmount (fs/namespace.c:5936) [ 41.993467] sp : ffff8000ff5afd50 [ 42.000329] x29: ffff8000ff5afd50 x28: fff00001bd947380 x27: 0000000000000000 [ 42.007454] x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000100 [ 42.030726] x23: 0000000000000000 x22: 0000000000000020 x21: ffff8000ff5afdc8 [ 42.038281] x20: 0000aaaabd6a1110 x19: 0000000000000000 x18: 0000000000000000 [ 42.045405] x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 [ 42.052528] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [ 42.075541] x11: 0000000000000000 x10: 0000000000000000 x9 : ffffda68dcdbbe30 [ 42.082835] x8 : ffff8000ff5afda0 x7 : fefefefefefefefe x6 : ffffda68df5e9000 [ 42.096212] x5 : fff00001bd947380 [ 42.108978] x4 : fff00001bd947380 x3 : 0000000000000000 [ 42.114449] x2 : 0000000000000000 x1 : 00000000ffffffff x0 : 00000000000000b8 [ 42.134515] Call trace: [ 42.139725] mnt_ns_release (arch/arm64/include/asm/atomic_lse.h:62 (discriminator 1) arch/arm64/include/asm/atomic_lse.h:76 (discriminator 1) arch/arm64/include/asm/atomic.h:51 (discriminator 1) include/linux/atomic/atomic-arch-fallback.h:944 (discriminator 1) include/linux/atomic/atomic-instrumented.h:401 (discriminator 1) include/linux/refcount.h:389 (discriminator 1) include/linux/refcount.h:432 (discriminator 1) include/linux/refcount.h:450 (discriminator 1) fs/namespace.c:148 (discriminator 1)) (P) [ 42.143811] __arm64_sys_listmount (fs/namespace.c:5936) [ 42.148327] invoke_syscall.constprop.0 (arch/arm64/include/asm/syscall.h:61 arch/arm64/kernel/syscall.c:54) [ 42.159193] do_el0_svc (include/linux/thread_info.h:135 (discriminator 2) arch/arm64/kernel/syscall.c:140 (discriminator 2) arch/arm64/kernel/syscall.c:151 (discriminator 2)) [ 42.163970] el0_svc (arch/arm64/include/asm/irqflags.h:82 (discriminator 1) arch/arm64/include/asm/irqflags.h:123 (discriminator 1) arch/arm64/include/asm/irqflags.h:136 (discriminator 1) arch/arm64/kernel/entry-common.c:102 (discriminator 1) arch/arm64/kernel/entry-common.c:745 (discriminator 1)) [ 42.173791] el0t_64_sync_handler (arch/arm64/kernel/entry-common.c:764) [ 42.185342] el0t_64_sync (arch/arm64/kernel/entry.S:596) [ 42.189165] Code: aa0003f3 9102e000 d503201f 12800001 (b8610001) All code ======== 0: aa0003f3 mov x19, x0 4: 9102e000 add x0, x0, #0xb8 8: d503201f nop c: 12800001 mov w1, #0xffffffff // #-1 10:* b8610001 ldaddl w1, w1, [x0] <-- trapping instruction Code starting with the faulting instruction =========================================== 0: b8610001 ldaddl w1, w1, [x0] [ 42.211485] ---[ end trace 0000000000000000 ]--- ## Source * Kernel version: 6.17.0-rc7 * Git tree: https://kernel.googlesource.com/pub/scm/linux/kernel/git/next/linux-next.git * Git describe: 6.17.0-rc7-next-20250924 * Git commit: b5a4da2c459f79a2c87c867398f1c0c315779781 * Architectures: arm64, x86_64 * Toolchains: gcc-13 * Kconfigs: defconfig+lkftconfig ## Build * Test log arm64: https://qa-reports.linaro.org/api/testruns/30007634/log_file/ * Test log x86_64: https://qa-reports.linaro.org/api/testruns/30000230/log_file/ * Test details: https://regressions.linaro.org/lkft/linux-next-master-ampere/next-20250924/… * Build plan: https://tuxapi.tuxsuite.com/v1/groups/ampere/projects/ci/tests/339teV8pAwrs… * Build link: https://storage.tuxsuite.com/public/ampere/ci/builds/339teBhKZ4DENKbJJNnbWK… * Kernel config: https://storage.tuxsuite.com/public/ampere/ci/builds/339teBhKZ4DENKbJJNnbWK… -- Linaro LKFT

2 months, 2 weeks

3
2
0 0

[PATCH RESEND v4] selftests/tty: add TIOCSTI test suite

by Abhinav Saxena

TIOCSTI is a TTY ioctl command that allows inserting characters into the terminal input queue, making it appear as if the user typed those characters. This functionality has behavior that varies based on system configuration and process credentials. The dev.tty.legacy_tiocsti sysctl introduced in commit 83efeeeb3d04 ("tty: Allow TIOCSTI to be disabled") controls TIOCSTI usage. When disabled, TIOCSTI requires CAP_SYS_ADMIN capability. The current implementation checks the current process's credentials via capable(CAP_SYS_ADMIN), but does not validate against the file opener's credentials stored in file->f_cred. This creates different behavior when file descriptors are passed between processes via SCM_RIGHTS. Add a test suite with 16 test variants using fixture variants to verify TIOCSTI behavior when dev.tty.legacy_tiocsti is enabled/disabled: - Basic TIOCSTI tests (8 variants): Direct testing with different capability and controlling terminal combinations - FD passing tests (8 variants): Test behavior when file descriptors are passed between processes with different capabilities The FD passing tests document this behavior - some tests show different results than expected based on file opener credentials, demonstrating that TIOCSTI uses current process credentials rather than file opener credentials. The tests validate proper enforcement of the legacy_tiocsti sysctl. Test implementation uses openpty(3) with TIOCSCTTY for isolated PTY environments. See tty_ioctl(4) for details on TIOCSTI behavior and security requirements. Signed-off-by: Abhinav Saxena <xandfury(a)gmail.com> --- RESEND: add TTY/serial maintainers and linux-serial CCs. No code changes. - Link to orignal v4: https://lore.kernel.org/r/20250902-toicsti-bug-v4-1-e5c960e0b3d6@gmail.com Changes in v4: - Moved skip conditions and sysctl setup from TEST_F to FIXTURE_SETUP (Kees Cook) - Fixed fclose() error handling in set_legacy_tiocsti_setting (Kees Cook) - Extracted run_basic_tiocsti_test() and run_fdpass_tiocsti_test functions (Kees Cook) - Removed redundant sysctl restore logic from TEST_F (Kees Cook) - Simplified FIXTURE_TEARDOWN (Kees Cook) - Replace drop_to_nobody() to drop_all_privs() which should be more portable (Justin Stitt) - Link to v3: https://lore.kernel.org/r/20250730-toicsti-bug-v3-1-dd2dac97f27a@gmail.com Add selftests for TIOCSTI ioctl To run all tests: $ sudo ./tools/testing/selftests/tty/tty_tiocsti_test Test Results: - PASSED: 13/16 tests - Different behavior: 3/16 tests (documenting credential checking behavior) All tests validated using: - scripts/checkpatch.pl --strict (clean output) - Functional testing on kernel v6.16-rc2 Changes in v3: - Replaced all printf() calls with TH_LOG() for proper test logging (Kees Cook) - Added struct __test_metadata parameter to helper functions - Moved common legacy_tiocsti availability check to FIXTURE_SETUP() - Implemented sysctl modification/restoration in FIXTURE_SETUP/TEARDOWN - Used openpty() with TIOCSCTTY for reliable PTY testing environment - Fixed child/parent synchronization in FD passing tests - Replaced manual _exit(1) handling with proper ASSERT statements - Switched // comments to /* */ format throughout - Expanded to 16 test variants using fixture variants - Enhanced error handling and test reliability - Link to v2: https://lore.kernel.org/r/20250713-toicsti-bug-v2-1-b183787eea29@gmail.com - Link to v1: https://lore.kernel.org/r/20250622-toicsti-bug-v1-0-f374373b04b2@gmail.com References: - tty_ioctl(4) - documents TIOCSTI ioctl and capability requirements - openpty(3) - pseudo-terminal creation and management - commit 83efeeeb3d04 ("tty: Allow TIOCSTI to be disabled") - Documentation/security/credentials.rst - https://github.com/KSPP/linux/issues/156 - https://lore.kernel.org/linux-hardening/Y0m9l52AKmw6Yxi1@hostpad/ - drivers/tty/Kconfig - Documentation/driver-api/tty/ --- tools/testing/selftests/tty/Makefile | 6 +- tools/testing/selftests/tty/config | 1 + tools/testing/selftests/tty/tty_tiocsti_test.c | 650 +++++++++++++++++++++++++ 3 files changed, 656 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/tty/Makefile b/tools/testing/selftests/tty/Makefile index 50d7027b2ae3fb495dd1c0684363fa8f426be42c..7f6fbe5a0cd5663310e334d9d068b21dab9136ec 100644 --- a/tools/testing/selftests/tty/Makefile +++ b/tools/testing/selftests/tty/Makefile @@ -1,5 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS = -O2 -Wall -TEST_GEN_PROGS := tty_tstamp_update +TEST_GEN_PROGS := tty_tstamp_update tty_tiocsti_test +LDLIBS += -lcap include ../lib.mk + +# Add libcap for TIOCSTI test +$(OUTPUT)/tty_tiocsti_test: LDLIBS += -lcap diff --git a/tools/testing/selftests/tty/config b/tools/testing/selftests/tty/config new file mode 100644 index 0000000000000000000000000000000000000000..c6373aba66366c82435bb26c019eb360eb6310eb --- /dev/null +++ b/tools/testing/selftests/tty/config @@ -0,0 +1 @@ +CONFIG_LEGACY_TIOCSTI=y diff --git a/tools/testing/selftests/tty/tty_tiocsti_test.c b/tools/testing/selftests/tty/tty_tiocsti_test.c new file mode 100644 index 0000000000000000000000000000000000000000..5e767e6cb3ef8f05c5430eb0fcc792064c446c03 --- /dev/null +++ b/tools/testing/selftests/tty/tty_tiocsti_test.c @@ -0,0 +1,650 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * TTY Tests - TIOCSTI + * + * Copyright © 2025 Abhinav Saxena <xandfury(a)gmail.com> + */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <errno.h> +#include <stdbool.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/wait.h> +#include <pwd.h> +#include <termios.h> +#include <grp.h> +#include <sys/capability.h> +#include <sys/prctl.h> +#include <pty.h> +#include <utmp.h> + +#include "../kselftest_harness.h" + +enum test_type { + TEST_PTY_TIOCSTI_BASIC, + TEST_PTY_TIOCSTI_FD_PASSING, + /* other tests cases such as serial may be added. */ +}; + +/* + * Test Strategy: + * - Basic tests: Use PTY with/without TIOCSCTTY (controlling terminal for + * current process) + * - FD passing tests: Child creates PTY, parent receives FD (demonstrates + * security issue) + * + * SECURITY VULNERABILITY DEMONSTRATION: + * FD passing tests show that TIOCSTI uses CURRENT process credentials, not + * opener credentials. This means privileged processes can be given FDs from + * unprivileged processes and successfully perform TIOCSTI operations that the + * unprivileged process couldn't do directly. + * + * Attack scenario: + * 1. Unprivileged process opens TTY (direct TIOCSTI fails due to lack of + * privileges) + * 2. Unprivileged process passes FD to privileged process via SCM_RIGHTS + * 3. Privileged process can use TIOCSTI on the FD (succeeds due to its + * privileges) + * 4. Result: Effective privilege escalation via file descriptor passing + * + * This matches the kernel logic in tiocsti(): + * 1. if (!tty_legacy_tiocsti && !capable(CAP_SYS_ADMIN)) return -EIO; + * 2. if ((current->signal->tty != tty) && !capable(CAP_SYS_ADMIN)) + * return -EPERM; + * Note: Both checks use capable() on CURRENT process, not FD opener! + * + * If the file credentials were also checked along with the capable() checks + * then the results for FD pass tests would be consistent with the basic tests. + */ + +FIXTURE(tiocsti) +{ + int pty_master_fd; /* PTY - for basic tests */ + int pty_slave_fd; + bool has_pty; + bool initial_cap_sys_admin; + int original_legacy_tiocsti_setting; + bool can_modify_sysctl; +}; + +FIXTURE_VARIANT(tiocsti) +{ + const enum test_type test_type; + const bool controlling_tty; /* true=current->signal->tty == tty */ + const int legacy_tiocsti; /* 0=restricted, 1=permissive */ + const bool requires_cap; /* true=with CAP_SYS_ADMIN, false=without */ + const int expected_success; /* 0=success, -EIO/-EPERM=specific error */ +}; + +/* + * Tests Controlling Terminal Variants (current->signal->tty == tty) + * + * TIOCSTI Test Matrix: + * + * | legacy_tiocsti | CAP_SYS_ADMIN | Expected Result | Error | + * |----------------|---------------|-----------------|-------| + * | 1 (permissive) | true | SUCCESS | - | + * | 1 (permissive) | false | SUCCESS | - | + * | 0 (restricted) | true | SUCCESS | - | + * | 0 (restricted) | false | FAILURE | -EIO | + */ + +/* clang-format off */ +FIXTURE_VARIANT_ADD(tiocsti, basic_pty_permissive_withcap) { + .test_type = TEST_PTY_TIOCSTI_BASIC, + .controlling_tty = true, + .legacy_tiocsti = 1, + .requires_cap = true, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, basic_pty_permissive_nocap) { + .test_type = TEST_PTY_TIOCSTI_BASIC, + .controlling_tty = true, + .legacy_tiocsti = 1, + .requires_cap = false, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, basic_pty_restricted_withcap) { + .test_type = TEST_PTY_TIOCSTI_BASIC, + .controlling_tty = true, + .legacy_tiocsti = 0, + .requires_cap = true, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, basic_pty_restricted_nocap) { + .test_type = TEST_PTY_TIOCSTI_BASIC, + .controlling_tty = true, + .legacy_tiocsti = 0, + .requires_cap = false, + .expected_success = -EIO, /* FAILURE: legacy restriction */ +}; /* clang-format on */ + +/* + * Note for FD Passing Test Variants + * Since we're testing the scenario where an unprivileged process pass an FD + * to a privileged one, .requires_cap here means the caps of the child process. + * Not the parent; parent would always be privileged. + */ + +/* clang-format off */ +FIXTURE_VARIANT_ADD(tiocsti, fdpass_pty_permissive_withcap) { + .test_type = TEST_PTY_TIOCSTI_FD_PASSING, + .controlling_tty = true, + .legacy_tiocsti = 1, + .requires_cap = true, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, fdpass_pty_permissive_nocap) { + .test_type = TEST_PTY_TIOCSTI_FD_PASSING, + .controlling_tty = true, + .legacy_tiocsti = 1, + .requires_cap = false, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, fdpass_pty_restricted_withcap) { + .test_type = TEST_PTY_TIOCSTI_FD_PASSING, + .controlling_tty = true, + .legacy_tiocsti = 0, + .requires_cap = true, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, fdpass_pty_restricted_nocap) { + .test_type = TEST_PTY_TIOCSTI_FD_PASSING, + .controlling_tty = true, + .legacy_tiocsti = 0, + .requires_cap = false, + .expected_success = -EIO, +}; /* clang-format on */ + +/* + * Non-Controlling Terminal Variants (current->signal->tty != tty) + * + * TIOCSTI Test Matrix: + * + * | legacy_tiocsti | CAP_SYS_ADMIN | Expected Result | Error | + * |----------------|---------------|-----------------|-------| + * | 1 (permissive) | true | SUCCESS | - | + * | 1 (permissive) | false | FAILURE | -EPERM| + * | 0 (restricted) | true | SUCCESS | - | + * | 0 (restricted) | false | FAILURE | -EIO | + */ + +/* clang-format off */ +FIXTURE_VARIANT_ADD(tiocsti, basic_nopty_permissive_withcap) { + .test_type = TEST_PTY_TIOCSTI_BASIC, + .controlling_tty = false, + .legacy_tiocsti = 1, + .requires_cap = true, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, basic_nopty_permissive_nocap) { + .test_type = TEST_PTY_TIOCSTI_BASIC, + .controlling_tty = false, + .legacy_tiocsti = 1, + .requires_cap = false, + .expected_success = -EPERM, +}; + +FIXTURE_VARIANT_ADD(tiocsti, basic_nopty_restricted_withcap) { + .test_type = TEST_PTY_TIOCSTI_BASIC, + .controlling_tty = false, + .legacy_tiocsti = 0, + .requires_cap = true, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, basic_nopty_restricted_nocap) { + .test_type = TEST_PTY_TIOCSTI_BASIC, + .controlling_tty = false, + .legacy_tiocsti = 0, + .requires_cap = false, + .expected_success = -EIO, +}; + +FIXTURE_VARIANT_ADD(tiocsti, fdpass_nopty_permissive_withcap) { + .test_type = TEST_PTY_TIOCSTI_FD_PASSING, + .controlling_tty = false, + .legacy_tiocsti = 1, + .requires_cap = true, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, fdpass_nopty_permissive_nocap) { + .test_type = TEST_PTY_TIOCSTI_FD_PASSING, + .controlling_tty = false, + .legacy_tiocsti = 1, + .requires_cap = false, + .expected_success = -EPERM, +}; + +FIXTURE_VARIANT_ADD(tiocsti, fdpass_nopty_restricted_withcap) { + .test_type = TEST_PTY_TIOCSTI_FD_PASSING, + .controlling_tty = false, + .legacy_tiocsti = 0, + .requires_cap = true, + .expected_success = 0, +}; + +FIXTURE_VARIANT_ADD(tiocsti, fdpass_nopty_restricted_nocap) { + .test_type = TEST_PTY_TIOCSTI_FD_PASSING, + .controlling_tty = false, + .legacy_tiocsti = 0, + .requires_cap = false, + .expected_success = -EIO, +}; /* clang-format on */ + +/* Helper function to send FD via SCM_RIGHTS */ +static int send_fd_via_socket(int socket_fd, int fd_to_send) +{ + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + char cmsg_buf[CMSG_SPACE(sizeof(int))]; + char dummy_data = 'F'; + struct iovec iov = { .iov_base = &dummy_data, .iov_len = 1 }; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = cmsg_buf; + msg.msg_controllen = sizeof(cmsg_buf); + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + + memcpy(CMSG_DATA(cmsg), &fd_to_send, sizeof(int)); + + return sendmsg(socket_fd, &msg, 0) < 0 ? -1 : 0; +} + +/* Helper function to receive FD via SCM_RIGHTS */ +static int recv_fd_via_socket(int socket_fd) +{ + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + char cmsg_buf[CMSG_SPACE(sizeof(int))]; + char dummy_data; + struct iovec iov = { .iov_base = &dummy_data, .iov_len = 1 }; + int received_fd = -1; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = cmsg_buf; + msg.msg_controllen = sizeof(cmsg_buf); + + if (recvmsg(socket_fd, &msg, 0) < 0) + return -1; + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_RIGHTS) { + memcpy(&received_fd, CMSG_DATA(cmsg), sizeof(int)); + break; + } + } + + return received_fd; +} + +static inline bool has_cap_sys_admin(void) +{ + cap_t caps = cap_get_proc(); + + if (!caps) + return false; + + cap_flag_value_t cap_val; + bool has_cap = (cap_get_flag(caps, CAP_SYS_ADMIN, CAP_EFFECTIVE, + &cap_val) == 0) && + (cap_val == CAP_SET); + + cap_free(caps); + return has_cap; +} + +/* + * Switch to non-root user and clear all capabilities + */ +static inline bool drop_all_privs(struct __test_metadata *_metadata) +{ + /* Drop supplementary groups */ + ASSERT_EQ(setgroups(0, NULL), 0); + + /* Switch to non-root user */ + ASSERT_EQ(setgid(1000), 0); + ASSERT_EQ(setuid(1000), 0); + + /* Clear all capabilities */ + cap_t empty = cap_init(); + + ASSERT_NE(empty, NULL); + ASSERT_EQ(cap_set_proc(empty), 0); + cap_free(empty); + + /* Prevent privilege regain */ + ASSERT_EQ(prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0), 0); + + /* Verify privilege drop */ + ASSERT_FALSE(has_cap_sys_admin()); + return true; +} + +static inline int get_legacy_tiocsti_setting(struct __test_metadata *_metadata) +{ + FILE *fp; + int value = -1; + + fp = fopen("/proc/sys/dev/tty/legacy_tiocsti", "r"); + if (!fp) { + /* legacy_tiocsti sysctl not available (kernel < 6.2) */ + return -1; + } + + if (fscanf(fp, "%d", &value) == 1 && fclose(fp) == 0) { + if (value < 0 || value > 1) + value = -1; /* Invalid value */ + } else { + value = -1; /* Failed to parse */ + } + + return value; +} + +static inline bool set_legacy_tiocsti_setting(struct __test_metadata *_metadata, + int value) +{ + FILE *fp; + bool success = false; + + /* Sanity-check the value */ + ASSERT_GE(value, 0); + ASSERT_LE(value, 1); + + /* + * Try to open for writing; if we lack permission, return false so + * the test harness will skip variants that need to change it + */ + fp = fopen("/proc/sys/dev/tty/legacy_tiocsti", "w"); + if (!fp) + return false; + + /* Write the new setting */ + if (fprintf(fp, "%d\n", value) > 0 && fclose(fp) == 0) + success = true; + else + TH_LOG("Failed to write legacy_tiocsti: %s", strerror(errno)); + + return success; +} + +/* + * TIOCSTI injection test function + * @tty_fd: TTY slave file descriptor to test TIOCSTI on + * Returns: 0 on success, -errno on failure + */ +static inline int test_tiocsti_injection(struct __test_metadata *_metadata, + int tty_fd) +{ + int ret; + char inject_char = 'V'; + + errno = 0; + ret = ioctl(tty_fd, TIOCSTI, &inject_char); + return ret == 0 ? 0 : -errno; +} + +/* + * Child process: test TIOCSTI directly with capability/controlling + * terminal setup + */ +static void run_basic_tiocsti_test(struct __test_metadata *_metadata, + FIXTURE_DATA(tiocsti) * self, + const FIXTURE_VARIANT(tiocsti) * variant) +{ + /* Handle capability requirements */ + if (self->initial_cap_sys_admin && !variant->requires_cap) + ASSERT_TRUE(drop_all_privs(_metadata)); + + if (variant->controlling_tty) { + /* + * Create new session and set PTY as + * controlling terminal + */ + pid_t sid = setsid(); + + ASSERT_GE(sid, 0); + ASSERT_EQ(ioctl(self->pty_slave_fd, TIOCSCTTY, 0), 0); + } + + /* + * Validate test environment setup and verify final + * capability state matches expectation + * after potential drop. + */ + ASSERT_TRUE(self->has_pty); + ASSERT_EQ(has_cap_sys_admin(), variant->requires_cap); + + /* Test TIOCSTI and validate result */ + int result = test_tiocsti_injection(_metadata, self->pty_slave_fd); + + /* Check against expected result from variant */ + EXPECT_EQ(result, variant->expected_success); + _exit(0); +} + +/* + * Child process: create PTY and then pass FD to parent via SCM_RIGHTS + */ +static void run_fdpass_tiocsti_test(struct __test_metadata *_metadata, + const FIXTURE_VARIANT(tiocsti) * variant, + int sockfd) +{ + signal(SIGHUP, SIG_IGN); + + /* Handle privilege dropping */ + if (!variant->requires_cap && has_cap_sys_admin()) + ASSERT_TRUE(drop_all_privs(_metadata)); + + /* Create child's PTY */ + int child_master_fd, child_slave_fd; + + ASSERT_EQ(openpty(&child_master_fd, &child_slave_fd, NULL, NULL, NULL), + 0); + + if (variant->controlling_tty) { + pid_t sid = setsid(); + + ASSERT_GE(sid, 0); + ASSERT_EQ(ioctl(child_slave_fd, TIOCSCTTY, 0), 0); + } + + /* Test child's direct TIOCSTI for reference */ + int direct_result = test_tiocsti_injection(_metadata, child_slave_fd); + + EXPECT_EQ(direct_result, variant->expected_success); + + /* Send FD to parent */ + ASSERT_EQ(send_fd_via_socket(sockfd, child_slave_fd), 0); + + /* Wait for parent completion signal */ + char sync_byte; + ssize_t bytes_read = read(sockfd, &sync_byte, 1); + + ASSERT_EQ(bytes_read, 1); + + close(child_master_fd); + close(child_slave_fd); + close(sockfd); + _exit(0); +} + +FIXTURE_SETUP(tiocsti) +{ + /* Create PTY pair for basic tests */ + self->has_pty = (openpty(&self->pty_master_fd, &self->pty_slave_fd, + NULL, NULL, NULL) == 0); + if (!self->has_pty) { + self->pty_master_fd = -1; + self->pty_slave_fd = -1; + } + + self->initial_cap_sys_admin = has_cap_sys_admin(); + self->original_legacy_tiocsti_setting = + get_legacy_tiocsti_setting(_metadata); + + if (self->original_legacy_tiocsti_setting < 0) + SKIP(return, + "legacy_tiocsti sysctl not available (kernel < 6.2)"); + + /* Common skip conditions */ + if (variant->test_type == TEST_PTY_TIOCSTI_BASIC && !self->has_pty) + SKIP(return, "PTY not available for controlling terminal test"); + + if (variant->test_type == TEST_PTY_TIOCSTI_FD_PASSING && + !self->initial_cap_sys_admin) + SKIP(return, "FD Pass tests require CAP_SYS_ADMIN"); + + if (variant->requires_cap && !self->initial_cap_sys_admin) + SKIP(return, "Test requires initial CAP_SYS_ADMIN"); + + /* Test if we can modify the sysctl (requires appropriate privileges) */ + self->can_modify_sysctl = set_legacy_tiocsti_setting( + _metadata, self->original_legacy_tiocsti_setting); + + /* Sysctl setup based on variant */ + if (self->can_modify_sysctl && + self->original_legacy_tiocsti_setting != variant->legacy_tiocsti) { + if (!set_legacy_tiocsti_setting(_metadata, + variant->legacy_tiocsti)) + SKIP(return, "Failed to set legacy_tiocsti sysctl"); + + } else if (!self->can_modify_sysctl && + self->original_legacy_tiocsti_setting != + variant->legacy_tiocsti) + SKIP(return, "legacy_tiocsti setting mismatch"); +} + +FIXTURE_TEARDOWN(tiocsti) +{ + /* + * Backup restoration - + * each test should restore its own sysctl changes + */ + if (self->can_modify_sysctl) { + int current_value = get_legacy_tiocsti_setting(_metadata); + + if (current_value != self->original_legacy_tiocsti_setting) { + TH_LOG("Backup: Restoring legacy_tiocsti from %d to %d", + current_value, + self->original_legacy_tiocsti_setting); + set_legacy_tiocsti_setting( + _metadata, + self->original_legacy_tiocsti_setting); + } + } + + if (self->has_pty) { + if (self->pty_master_fd >= 0) + close(self->pty_master_fd); + if (self->pty_slave_fd >= 0) + close(self->pty_slave_fd); + } +} + +TEST_F(tiocsti, test) +{ + int status; + pid_t child_pid; + + if (variant->test_type == TEST_PTY_TIOCSTI_BASIC) { + /* ===== BASIC TIOCSTI TEST ===== */ + child_pid = fork(); + ASSERT_GE(child_pid, 0); + + /* Perform the actual test in the child process */ + if (child_pid == 0) + run_basic_tiocsti_test(_metadata, self, variant); + + } else { + /* ===== FD PASSING SECURITY TEST ===== */ + int sockpair[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sockpair), 0); + + child_pid = fork(); + ASSERT_GE(child_pid, 0); + + if (child_pid == 0) { + /* Child process - create PTY and send FD */ + close(sockpair[0]); + run_fdpass_tiocsti_test(_metadata, variant, + sockpair[1]); + } + + /* Parent process - receive FD and test TIOCSTI */ + close(sockpair[1]); + + int received_fd = recv_fd_via_socket(sockpair[0]); + + ASSERT_GE(received_fd, 0); + + bool parent_has_cap = self->initial_cap_sys_admin; + + TH_LOG("=== TIOCSTI FD Passing Test Context ==="); + TH_LOG("legacy_tiocsti: %d, Parent CAP_SYS_ADMIN: %s, Child: %s", + variant->legacy_tiocsti, parent_has_cap ? "yes" : "no", + variant->requires_cap ? "kept" : "dropped"); + + /* SECURITY TEST: Try TIOCSTI with FD opened by child */ + int result = test_tiocsti_injection(_metadata, received_fd); + + /* Log security concern if demonstrated */ + if (result == 0 && !variant->requires_cap) { + TH_LOG("*** SECURITY CONCERN DEMONSTRATED ***"); + TH_LOG("Privileged parent can use TIOCSTI on FD from unprivileged child"); + TH_LOG("This shows current process credentials are used, not opener credentials"); + } + + EXPECT_EQ(result, variant->expected_success) + { + TH_LOG("FD passing: expected error %d, got %d", + variant->expected_success, result); + } + + /* Signal child completion */ + char sync_byte = 'D'; + ssize_t bytes_written = write(sockpair[0], &sync_byte, 1); + + ASSERT_EQ(bytes_written, 1); + + close(received_fd); + close(sockpair[0]); + } + + /* Common child process cleanup for both test types */ + ASSERT_EQ(waitpid(child_pid, &status, 0), child_pid); + + if (WIFSIGNALED(status)) { + TH_LOG("Child terminated by signal %d", WTERMSIG(status)); + ASSERT_FALSE(WIFSIGNALED(status)) + { + TH_LOG("Child process failed assertion"); + } + } else { + EXPECT_EQ(WEXITSTATUS(status), 0); + } +} + +TEST_HARNESS_MAIN --- base-commit: e6b9dce0aeeb91dfc0974ab87f02454e24566182 change-id: 20250618-toicsti-bug-7822b8e94a32 Best regards, -- Abhinav Saxena <xandfury(a)gmail.com>

2 months, 2 weeks

1
1
0 0

[PATCH v4 1/2] net/tls: support maximum record size limit

by Wilfred Mallawa

From: Wilfred Mallawa <wilfred.mallawa(a)wdc.com> During a handshake, an endpoint may specify a maximum record size limit. Currently, the kernel defaults to TLS_MAX_PAYLOAD_SIZE (16KB) for the maximum record size. Meaning that, the outgoing records from the kernel can exceed a lower size negotiated during the handshake. In such a case, the TLS endpoint must send a fatal "record_overflow" alert [1], and thus the record is discarded. Upcoming Western Digital NVMe-TCP hardware controllers implement TLS support. For these devices, supporting TLS record size negotiation is necessary because the maximum TLS record size supported by the controller is less than the default 16KB currently used by the kernel. This patch adds support for retrieving the negotiated record size limit during a handshake, and enforcing it at the TLS layer such that outgoing records are no larger than the size negotiated. This patch depends on the respective userspace support in tlshd and GnuTLS [2]. [1] https://www.rfc-editor.org/rfc/rfc8449 [2] https://gitlab.com/gnutls/gnutls/-/merge_requests/2005 Signed-off-by: Wilfred Mallawa <wilfred.mallawa(a)wdc.com> --- Changes V3 -> V4: * Added record_size_limit RFC reference to documentation * Always export the record size limit in tls_get_info() * Disallow user space to change the record_size_limit from under us if an open record is pending. * Added record_size_limit minimum size check as per RFC * Allow space for the ContentType byte for TLS 1.3. The expected behaviour is that userspace directly uses the negotiated record_size_limit, kernel will limit the plaintext buffer size appropirately. * New patch to add self-tests. --- Documentation/networking/tls.rst | 12 +++++ include/net/tls.h | 5 +++ include/uapi/linux/tls.h | 2 + net/tls/tls_device.c | 2 +- net/tls/tls_main.c | 75 ++++++++++++++++++++++++++++++++ net/tls/tls_sw.c | 2 +- 6 files changed, 96 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/tls.rst b/Documentation/networking/tls.rst index 36cc7afc2527..d24bf8911bb8 100644 --- a/Documentation/networking/tls.rst +++ b/Documentation/networking/tls.rst @@ -280,6 +280,18 @@ If the record decrypted turns out to had been padded or is not a data record it will be decrypted again into a kernel buffer without zero copy. Such events are counted in the ``TlsDecryptRetry`` statistic. +TLS_TX_RECORD_SIZE_LIM +~~~~~~~~~~~~~~~~~~~~~~ + +Sets the maximum size for the plaintext of a protected record. + +The provided value should correspond to the limit negotiated during the TLS +handshake via the `record_size_limit` extension (RFC 8449)[1]. When this +option is set, the kernel enforces this limit on all transmitted TLS records, +ensuring no plaintext fragment exceeds the specified size. + +[1] https://datatracker.ietf.org/doc/html/rfc8449 + Statistics ========== diff --git a/include/net/tls.h b/include/net/tls.h index 857340338b69..32f053770ec4 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -53,6 +53,8 @@ struct tls_rec; /* Maximum data size carried in a TLS record */ #define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14) +/* Minimum record size limit as per RFC8449 */ +#define TLS_MIN_RECORD_SIZE_LIM ((size_t)1 << 6) #define TLS_HEADER_SIZE 5 #define TLS_NONCE_OFFSET TLS_HEADER_SIZE @@ -226,6 +228,9 @@ struct tls_context { u8 rx_conf:3; u8 zerocopy_sendfile:1; u8 rx_no_pad:1; + u16 tx_record_size_limit; /* Max plaintext fragment size. For TLS 1.3, + * this excludes the ContentType. + */ int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index b66a800389cc..3add266d5916 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -41,6 +41,7 @@ #define TLS_RX 2 /* Set receive parameters */ #define TLS_TX_ZEROCOPY_RO 3 /* TX zerocopy (only sendfile now) */ #define TLS_RX_EXPECT_NO_PAD 4 /* Attempt opportunistic zero-copy */ +#define TLS_TX_RECORD_SIZE_LIM 5 /* Maximum record size */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -194,6 +195,7 @@ enum { TLS_INFO_RXCONF, TLS_INFO_ZC_RO_TX, TLS_INFO_RX_NO_PAD, + TLS_INFO_TX_RECORD_SIZE_LIM, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index f672a62a9a52..bf16ceb41dde 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -459,7 +459,7 @@ static int tls_push_data(struct sock *sk, /* TLS_HEADER_SIZE is not counted as part of the TLS record, and * we need to leave room for an authentication tag. */ - max_open_record_len = TLS_MAX_PAYLOAD_SIZE + + max_open_record_len = tls_ctx->tx_record_size_limit + prot->prepend_size; do { rc = tls_do_allocation(sk, ctx, pfrag, prot->prepend_size); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index a3ccb3135e51..09883d9c6c96 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -544,6 +544,31 @@ static int do_tls_getsockopt_no_pad(struct sock *sk, char __user *optval, return 0; } +static int do_tls_getsockopt_tx_record_size(struct sock *sk, char __user *optval, + int __user *optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + int len; + /* TLS 1.3: Record length contains ContentType */ + u16 record_size_limit = ctx->prot_info.version == TLS_1_3_VERSION ? + ctx->tx_record_size_limit + 1 : + ctx->tx_record_size_limit; + + if (get_user(len, optlen)) + return -EFAULT; + + if (len < sizeof(record_size_limit)) + return -EINVAL; + + if (put_user(sizeof(record_size_limit), optlen)) + return -EFAULT; + + if (copy_to_user(optval, &record_size_limit, sizeof(record_size_limit))) + return -EFAULT; + + return 0; +} + static int do_tls_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) { @@ -563,6 +588,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, case TLS_RX_EXPECT_NO_PAD: rc = do_tls_getsockopt_no_pad(sk, optval, optlen); break; + case TLS_TX_RECORD_SIZE_LIM: + rc = do_tls_getsockopt_tx_record_size(sk, optval, optlen); + break; default: rc = -ENOPROTOOPT; break; @@ -812,6 +840,43 @@ static int do_tls_setsockopt_no_pad(struct sock *sk, sockptr_t optval, return rc; } +static int do_tls_setsockopt_tx_record_size(struct sock *sk, sockptr_t optval, + unsigned int optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *sw_ctx = tls_sw_ctx_tx(ctx); + u16 value; + + if (sw_ctx->open_rec) + return -EBUSY; + + if (sockptr_is_null(optval) || optlen != sizeof(value)) + return -EINVAL; + + if (copy_from_sockptr(&value, optval, sizeof(value))) + return -EFAULT; + + if (value < TLS_MIN_RECORD_SIZE_LIM) + return -EINVAL; + + if (ctx->prot_info.version == TLS_1_2_VERSION && + value > TLS_MAX_PAYLOAD_SIZE) + return -EINVAL; + + if (ctx->prot_info.version == TLS_1_3_VERSION && + value - 1 > TLS_MAX_PAYLOAD_SIZE) + return -EINVAL; + + /* + * For TLS 1.3: 'value' includes one byte for the appended ContentType. + * Adjust the kernel's internal plaintext limit accordingly. + */ + ctx->tx_record_size_limit = ctx->prot_info.version == TLS_1_3_VERSION ? + value - 1 : value; + + return 0; +} + static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { @@ -833,6 +898,9 @@ static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval, case TLS_RX_EXPECT_NO_PAD: rc = do_tls_setsockopt_no_pad(sk, optval, optlen); break; + case TLS_TX_RECORD_SIZE_LIM: + rc = do_tls_setsockopt_tx_record_size(sk, optval, optlen); + break; default: rc = -ENOPROTOOPT; break; @@ -1022,6 +1090,7 @@ static int tls_init(struct sock *sk) ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; + ctx->tx_record_size_limit = TLS_MAX_PAYLOAD_SIZE; update_sk_prot(sk, ctx); out: write_unlock_bh(&sk->sk_callback_lock); @@ -1111,6 +1180,11 @@ static int tls_get_info(struct sock *sk, struct sk_buff *skb, bool net_admin) goto nla_failure; } + err = nla_put_u16(skb, TLS_INFO_TX_RECORD_SIZE_LIM, + ctx->tx_record_size_limit); + if (err) + goto nla_failure; + rcu_read_unlock(); nla_nest_end(skb, start); return 0; @@ -1132,6 +1206,7 @@ static size_t tls_get_info_size(const struct sock *sk, bool net_admin) nla_total_size(sizeof(u16)) + /* TLS_INFO_TXCONF */ nla_total_size(0) + /* TLS_INFO_ZC_RO_TX */ nla_total_size(0) + /* TLS_INFO_RX_NO_PAD */ + nla_total_size(sizeof(u16)) + /* TLS_INFO_TX_RECORD_SIZE_LIM */ 0; return size; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bac65d0d4e3e..28fb796573d1 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1079,7 +1079,7 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, orig_size = msg_pl->sg.size; full_record = false; try_to_copy = msg_data_left(msg); - record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size; + record_room = tls_ctx->tx_record_size_limit - msg_pl->sg.size; if (try_to_copy >= record_room) { try_to_copy = record_room; full_record = true; -- 2.51.0

2 months, 2 weeks

4
10
0 0

[PATCH v2 2/2] ipv6: Check AF_UNSPEC in ip6_route_multipath_add()

by Maksimilijan Marosevic

This check was removed in commit e6f497955fb6 ("ipv6: Check GATEWAY in rtm_to_fib6_multipath_config().") as part of rt6_qualify_for ecmp(). The author correctly recognises that rt6_qualify_for_ecmp() returns false if fb_nh_gw_family is set to AF_UNSPEC, but then mistakes AF_UNSPEC for AF_INET6 when reasoning that the check is unnecessary. This means certain malformed entries don't get caught in ip6_route_multipath_add(). This patch reintroduces the AF_UNSPEC check while respecting changes of the initial patch. Reported-by: syzbot+a259a17220263c2d73fc(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=a259a17220263c2d73fc Fixes: e6f497955fb6 ("ipv6: Check GATEWAY in rtm_to_fib6_multipath_config().") Signed-off-by: Maksimilijan Marosevic <maksimilijan.marosevic(a)proton.me> --- net/ipv6/route.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index aee6a10b112a..884bae3fb1b1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5454,6 +5454,14 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, goto cleanup; } + if (rt->fib6_nh->fib_nh_gw_family == AF_UNSPEC) { + err = -EINVAL; + NL_SET_ERR_MSG(extack, + "Device only routes can not be added for IPv6 using the multipath API."); + fib6_info_release(rt); + goto cleanup; + } + rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1; err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); -- 2.43.0

2 months, 2 weeks

1
0
0 0

Hello from France.

by David Santamaria

The Alphabetical layout was... auto-correct. Friendly: Neo (Jesus-Christ a.k.a. King David again). - Miracles proving that I was Jesus, and King David, are in my Facebook. I proposed to explain the Holy-Trinity live on TV. It is since year 2000 that I must be in the news. I do not declare be Jew, but get persecuted anyway by antisemites (antichristians?). Writing still does not pay my bills at all, keeps me almost homeless. While my intellectual property is stolen, my names removed from many Masterpieces. Facebook https://www.facebook.com/profile.php?id=100057121342964 Paypal https://www.paypal.com/paypalme/meDavidSantamaria Email/Teams DavidSantamaria(a)hotmail.fr<mailto:DavidSantamaria@hotmail.fr> RCS/WhatsApp +33 7 67 99 32 37 $ADA addr1qx8chpwdeqv77duf2eutrtgvd5967l4w87fy54fx0022gr8p80z2mq7cmunmrdvy8yn3pzfzpm46zyfjp8usl36vpw2q509hrd $BTC 3FdwVoDzJoUzceogUwEmVu9YxoFvX6c2Rk $WAVES 3PEAeFkwqVsgAiyad8uVQzQxiGDyJNnCCn5 Sent from my Public Address.

2 months, 2 weeks

1
0
0 0

[PATCH 1/2] selftests/acct: add cleanup for leftover process_log binary

by Madhur Kumar

Some kselftests generate temporary binaries that are not tracked by TEST_GEN_PROGS. Add EXTRA_CLEAN entry to remove process_log during `make kselftest-clean`. Signed-off-by: Madhur Kumar <madhurkumar004(a)gmail.com> --- tools/testing/selftests/acct/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/acct/Makefile b/tools/testing/selftests/acct/Makefile index 7e025099cf65..16eb97079e63 100644 --- a/tools/testing/selftests/acct/Makefile +++ b/tools/testing/selftests/acct/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 TEST_GEN_PROGS := acct_syscall CFLAGS += -Wall +EXTRA_CLEAN := process_log -include ../lib.mk \ No newline at end of file +include ../lib.mk -- 2.51.0

2 months, 2 weeks

2
8
0 0

[PATCH net-next 00/13] selftests: Mark auto-deferring functions clearly

by Petr Machata

selftests/net/lib.sh contains a suite of iproute2 wrappers that automatically schedule the corresponding cleanup through defer. The fact they do so is however not immediately obvious, one needs to know which functions are handling the deferral behind the scenes, and which expect the caller to handle cleanups themselves. A convention for these auto-deferring functions would help both writing and patch review. This patchset does so by marking these functions with an adf_ prefix. We already have a few such functions: forwarding/lib.sh has adf_mcd_start() and a few selftests add private helpers that conform to this convention. Patches #1 to #8 gradually convert individual functions, one per patch. Patch #9 renames an auto-deferring private helpers named dfr_* to adf_*. The plan is not to retro-rename all private helpers, but I happened to know about this one. Patches #10 to #12 introduce several autodefer helpers for commonly used forwarding/lib.sh functions, and opportunistically convert straightforward instances of 'action; defer counteraction' to the new helpers. Patch #13 adds some README verbiage to pitch defer and the adf_* convention. Petr Machata (13): selftests: net: lib: Rename ip_link_add() to adf_* selftests: net: lib: Rename ip_link_set_master() to adf_* selftests: net: lib: Rename ip_link_set_addr() to adf_* selftests: net: lib: Rename ip_link_set_up() to adf_* selftests: net: lib: Rename ip_link_set_down() to adf_* selftests: net: lib: Rename ip_addr_add() to adf_* selftests: net: lib: Rename ip_route_add() to adf_* selftests: net: lib: Rename bridge_vlan_add() to adf_* selftests: net: vlan_bridge_binding: Rename dfr_set_binding_*() to adf_* selftests: forwarding: lib: Add an autodefer variant of vrf_prepare() selftests: forwarding: lib: Add an autodefer variant of simple_if_init() selftests: forwarding: lib: Add an autodefer variant of forwarding_enable() selftests: forwarding: README: Mention defer, adf_ .../drivers/net/mlxsw/devlink_trap_policer.sh | 9 +- .../drivers/net/mlxsw/qos_ets_strict.sh | 12 +- .../drivers/net/mlxsw/qos_max_descriptors.sh | 9 +- .../drivers/net/mlxsw/qos_mc_aware.sh | 12 +- .../drivers/net/mlxsw/sch_red_core.sh | 6 +- tools/testing/selftests/net/fdb_notify.sh | 26 ++-- tools/testing/selftests/net/forwarding/README | 15 ++ .../net/forwarding/bridge_activity_notify.sh | 21 ++- .../net/forwarding/bridge_fdb_local_vlan_0.sh | 65 ++++---- tools/testing/selftests/net/forwarding/lib.sh | 18 +++ .../selftests/net/forwarding/sch_ets_core.sh | 9 +- .../selftests/net/forwarding/sch_red.sh | 12 +- .../selftests/net/forwarding/sch_tbf_core.sh | 6 +- .../net/forwarding/vxlan_bridge_1q_mc_ul.sh | 141 +++++++++--------- .../net/forwarding/vxlan_reserved.sh | 33 ++-- tools/testing/selftests/net/lib.sh | 16 +- .../net/test_vxlan_fdb_changelink.sh | 8 +- .../selftests/net/vlan_bridge_binding.sh | 44 +++--- 18 files changed, 225 insertions(+), 237 deletions(-) -- 2.49.0

2 months, 2 weeks

3
27
0 0

[PATCH net-next 00/15] mptcp: pm: special case for c-flag + luminar endp

by Matthieu Baerts (NGI0)

Here are some patches for the MPTCP PM, including some refactoring that I thought it would be best to send at the end of a cycle to avoid conflicts between net and net-next that could last a few weeks. The most interesting changes are in the first and last patch, the rest are patches refactoring the code & tests to validate the modifications. - Patches 1 & 2: When servers set the C-flag in their MP_CAPABLE to tell clients not to create subflows to the initial address and port -- e.g. a deployment behind a L4 load balancer like a typical CDN deployment -- clients will not use their other endpoints when default settings are used. That's because the in-kernel path-manager uses the 'subflow' endpoints to create subflows only to the initial address and port. The first patch fixes that (for >=v5.14), and the second one validates it. - Patches 3-14: various patches refactoring the code around the in-kernel PM (mainly): split too long functions, rename variables and functions to avoid confusions, reduce structure size, and compare IDs instead of IP addresses. Note that one patch modifies one internal variable used in one BPF selftest. - Patch 15: ability to control endpoints that are used in reaction to a new address announced by the other peer. With that, endpoints can be used only once. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Notes: - Patches 1 & 2 are sent to net-next on purpose: to delay a bit the backports, just in case. Plus we are at the end of a cycle, and not to delay the other refactoring patches. - Sorry, I wanted to send this series earlier on, but due to some unrelated issues (and holiday), it got delayed. Most patches are pure refactoring ones. --- Matthieu Baerts (NGI0) (15): mptcp: pm: in-kernel: usable client side with C-flag selftests: mptcp: join: validate C-flag + def limit mptcp: pm: in-kernel: refactor fill_local_addresses_vec mptcp: pm: in-kernel: refactor fill_remote_addresses_vec mptcp: pm: rename 'subflows' to 'extra_subflows' mptcp: pm: in-kernel: rename 'subflows_max' to 'limit_extra_subflows' mptcp: pm: in-kernel: rename 'add_addr_signal_max' to 'endp_signal_max' mptcp: pm: in-kernel: rename 'add_addr_accept_max' to 'limit_add_addr_accepted' mptcp: pm: in-kernel: rename 'local_addr_max' to 'endp_subflow_max' mptcp: pm: in-kernel: rename 'local_addr_list' to 'endp_list' mptcp: pm: in-kernel: rename 'addrs' to 'endpoints' mptcp: pm: in-kernel: remove stale_loss_cnt mptcp: pm: in-kernel: reduce pernet struct size mptcp: pm: in-kernel: compare IDs instead of addresses mptcp: pm: in-kernel: add laminar endpoints include/uapi/linux/mptcp.h | 11 +- net/mptcp/pm.c | 32 +- net/mptcp/pm_kernel.c | 569 ++++++++++++++-------- net/mptcp/pm_userspace.c | 2 +- net/mptcp/protocol.h | 21 +- net/mptcp/sockopt.c | 22 +- tools/testing/selftests/bpf/progs/mptcp_subflow.c | 2 +- tools/testing/selftests/net/mptcp/mptcp_join.sh | 11 + 8 files changed, 441 insertions(+), 229 deletions(-) --- base-commit: a1f1f2422e098485b09e55a492de05cf97f9954d change-id: 20250925-net-next-mptcp-c-flag-laminar-f8442e4d4bd9 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

2 months, 2 weeks

2
16
0 0

[PATCH RFC bpf-next v2 0/5] Add the the capability to load HW RX checsum in eBPF programs

by Lorenzo Bianconi

Introduce bpf_xdp_metadata_rx_checksum() kfunc in order to load the HW RX cheksum results in the eBPF program binded to the NIC. Implement xmo_rx_checksum callback for veth and ice drivers. Please note ice support changes are just compile-tested at the moment. --- Changes in RFC v2: - Squash patch 1/6 and 2/6 - Introduce enum xdp_checksum definitions - Rework ice support to reuse ice_rx_csum codebase --- Lorenzo Bianconi (5): netlink: specs: Add XDP RX checksum capability to XDP metadata specs net: veth: Add xmo_rx_checksum callback to veth driver net: ice: Add xmo_rx_checksum callback selftests/bpf: Add selftest support for bpf_xdp_metadata_rx_checksum selftests/bpf: Add bpf_xdp_metadata_rx_checksum support to xdp_hw_metadat prog Documentation/netlink/specs/netdev.yaml | 5 + drivers/net/ethernet/intel/ice/ice_base.c | 1 + drivers/net/ethernet/intel/ice/ice_txrx.h | 1 + drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 125 +++++++++++++-------- drivers/net/veth.c | 20 ++++ include/net/xdp.h | 14 +++ net/core/xdp.c | 29 +++++ .../selftests/bpf/prog_tests/xdp_metadata.c | 7 ++ .../testing/selftests/bpf/progs/xdp_hw_metadata.c | 7 ++ tools/testing/selftests/bpf/progs/xdp_metadata.c | 1 + tools/testing/selftests/bpf/xdp_hw_metadata.c | 27 +++++ tools/testing/selftests/bpf/xdp_metadata.h | 13 +++ 12 files changed, 206 insertions(+), 44 deletions(-) --- base-commit: 5e3fee34f626a8cb8715f5b5409416c481714ebf change-id: 20250925-bpf-xdp-meta-rxcksum-900685e2909d Best regards, -- Lorenzo Bianconi <lorenzo(a)kernel.org>

2 months, 2 weeks

5
17
0 0

[PATCH v2] selftest: net: Fix error message if empty variable

by Alessandro Zanni

Fix to avoid cases where the `res` shell variable is empty in script comparisons. The comparison has been modified into string comparison to handle other possible values the variable could assume. The issue can be reproduced with the command: make kselftest TARGETS=net It solves the error: ./tfo_passive.sh: line 98: [: -eq: unary operator expected Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- Notes: v2: edit condition to handle strings tools/testing/selftests/net/tfo_passive.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/tfo_passive.sh b/tools/testing/selftests/net/tfo_passive.sh index 80bf11fdc046..a4550511830a 100755 --- a/tools/testing/selftests/net/tfo_passive.sh +++ b/tools/testing/selftests/net/tfo_passive.sh @@ -95,7 +95,7 @@ wait res=$(cat $out_file) rm $out_file -if [ $res -eq 0 ]; then +if [ "$res" = "0" ]; then echo "got invalid NAPI ID from passive TFO socket" cleanup_ns exit 1 -- 2.43.0

2 months, 2 weeks

3
2
0 0

[PATCH net-next] selftests: drv-net: Enable BTF

by Stanislav Fomichev

Commit fec2e55bdef ("selftests: drv-net: Pull data before parsing headers") added __ksym external symbol to xdp_native.bpf.c which now requires a kernel with BTF. Enable BTF for driver selftests. Before: # TAP version 13 # 1..10 # # Exception| Traceback (most recent call last): # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/net/lib/py/ksft.py", line 244, in ksft_run # # Exception| case(*args) # # Exception| ~~~~^^^^^^^ # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/drivers/net/./xdp.py", line 231, in test_xdp_native_pass_sb # # Exception| _test_pass(cfg, bpf_info, 256) # # Exception| ~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^ # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/drivers/net/./xdp.py", line 209, in _test_pass # # Exception| prog_info = _load_xdp_prog(cfg, bpf_info) # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/drivers/net/./xdp.py", line 114, in _load_xdp_prog # # Exception| cmd( # # Exception| ~~~^ # # Exception| f"ip link set dev {cfg.ifname} mtu {bpf_info.mtu} xdpdrv obj {abs_path} sec {bpf_info.xdp_sec}", # # Exception| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # # Exception| shell=True # # Exception| ^^^^^^^^^^ # # Exception| ) # # Exception| ^ # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/net/lib/py/utils.py", line 75, in __init__ # # Exception| self.process(terminate=False, fail=fail, timeout=timeout) # # Exception| ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/net/lib/py/utils.py", line 95, in process # # Exception| raise CmdExitFailure("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" % # # Exception| (self.proc.args, stdout, stderr), self) # # Exception| net.lib.py.utils.CmdExitFailure: Command failed: ip link set dev eni30773np1 mtu 1500 xdpdrv obj /home/sdf/src/linux/tools/testing/selftests/net/lib/xdp_native.bpf.o sec xdp # # Exception| STDOUT: b'' # # Exception| STDERR: b"libbpf: kernel BTF is missing at '/sys/kernel/btf/vmlinux', was CONFIG_DEBUG_INFO_BTF enabled?\nlibbpf: failed to find '.BTF' ELF section in /lib/modules/6.17.0-rc6-virtme/build/vmlinux\nlibbpf: failed to find valid kernel BTF\nlib bpf: Error loading vmlinux BTF: -3\nlibbpf: failed to load object '/home/sdf/src/linux/tools/testing/selftests/net/lib/xdp_native.bpf.o'\n" # not ok 1 xdp.test_xdp_native_pass_sb ... After: # TAP version 13 # 1..10 # ok 1 xdp.test_xdp_native_pass_sb # ok 2 xdp.test_xdp_native_pass_mb # ok 3 xdp.test_xdp_native_drop_sb # ok 4 xdp.test_xdp_native_drop_mb # ok 5 xdp.test_xdp_native_tx_sb # ok 6 xdp.test_xdp_native_tx_mb # # Ignoring SIGTERM (cnt: 2), already exiting... # # Ignoring SIGTERM (cnt: 3), already exiting... # # Exception| Traceback (most recent call last): # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/net/lib/py/ksft.py", line 244, in ksft_run # # Exception| case(*args) # # Exception| ~~~~^^^^^^^ # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/drivers/net/./xdp.py", line 506, in test_xdp_native_adjst_taa # # Exception| res = _test_xdp_native_tail_adjst( # # Exception| cfg, # # Exception| pkt_sz_lst, # # Exception| offset_lst, # # Exception| ) # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/drivers/net/./xdp.py", line 467, in _test_xdp_native_tail_adt # # Exception| recvd_str = _exchg_udp(cfg, port, test_str) # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/drivers/net/./xdp.py", line 72, in _exchg_udp # # Exception| with bkg(rx_udp_cmd, exit_wait=True) as nc: # # Exception| ~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/net/lib/py/utils.py", line 137, in __exit__ # # Exception| return self.process(terminate=terminate, fail=self.check_fail) # # Exception| ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/net/lib/py/utils.py", line 85, in process # # Exception| stdout, stderr = self.proc.communicate(timeout) # # Exception| ~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^ # # Exception| File "/usr/lib/python3.13/subprocess.py", line 1222, in communicate # # Exception| stdout, stderr = self._communicate(input, endtime, timeout) # # Exception| ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^ # # Exception| File "/usr/lib/python3.13/subprocess.py", line 2128, in _communicate # # Exception| ready = selector.select(timeout) # # Exception| File "/usr/lib/python3.13/selectors.py", line 398, in select # # Exception| fd_event_list = self._selector.poll(timeout) # # Exception| File "/home/sdf/src/linux/tools/testing/selftests/net/lib/py/ksft.py", line 208, in _ksft_intr # # Exception| raise KsftTerminate() # # Exception| net.lib.py.ksft.KsftTerminate # # Stopping tests due to KsftTerminate. # not ok 7 xdp.test_xdp_native_adjst_tail_grow_data # # Totals: pass:6 fail:1 xfail:0 xpass:0 skip:0 error:0 Signed-off-by: Stanislav Fomichev <sdf(a)fomichev.me> --- tools/testing/selftests/drivers/net/config | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index f27172ddee0a..da5a5a94fa6a 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -5,3 +5,5 @@ CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_NETCONSOLE_EXTENDED_LOG=y CONFIG_XDP_SOCKETS=y +CONFIG_DEBUG_INFO_BTF=y +CONFIG_DEBUG_INFO_BTF_MODULES=n -- 2.51.0

2 months, 2 weeks

2
1
0 0

[PATCH v3 00/36] sparc64: vdso: Switch to the generic vDSO library

by Thomas Weißschuh

The generic vDSO provides a lot common functionality shared between different architectures. SPARC is the last architecture not using it, preventing some necessary code cleanup. Make use of the generic infrastructure. Follow-up to and replacement for Arnd's SPARC vDSO removal patches: https://lore.kernel.org/lkml/20250707144726.4008707-1-arnd@kernel.org/ Tested on a Niagara T4 and QEMU. This has a semantic conflict with my series "vdso: Reject absolute relocations during build". The last patch of this series expects all users of the generic vDSO library to use the vdsocheck tool. This is not the case (yet) for SPARC64. I do have the patches for the integration, the specifics will depend on which series is applied first. Based on tip/timers/vdso. [0] https://lore.kernel.org/lkml/20250812-vdso-absolute-reloc-v4-0-61a8b615e5ec… Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Changes in v3: - Allocate vDSO data pages dynamically (and lots of preparations for that) - Drop clock_getres() - Fix 32bit clock_gettime() syscall fallback - Link to v2: https://lore.kernel.org/r/20250815-vdso-sparc64-generic-2-v2-0-b5ff80672347… Changes in v2: - Rebase on v6.17-rc1 - Drop RFC state - Fix typo in commit message - Drop duplicate 'select GENERIC_TIME_VSYSCALL' - Merge "sparc64: time: Remove architecture-specific clocksource data" into the main conversion patch. It violated the check in __clocksource_register_scale() - Link to v1: https://lore.kernel.org/r/20250724-vdso-sparc64-generic-2-v1-0-e376a3bd24d1… --- Arnd Bergmann (1): clocksource: remove ARCH_CLOCKSOURCE_DATA Thomas Weißschuh (35): selftests: vDSO: vdso_test_correctness: Handle different tv_usec types arm64: vDSO: getrandom: Explicitly include asm/alternative.h arm64: vDSO: gettimeofday: Explicitly include vdso/clocksource.h arm64: vDSO: compat_gettimeofday: Add explicit includes ARM: vdso: gettimeofday: Add explicit includes powerpc/vdso/gettimeofday: Explicitly include vdso/time32.h powerpc/vdso: Explicitly include asm/cputable.h and asm/feature-fixups.h LoongArch: vDSO: Explicitly include asm/vdso/vdso.h MIPS: vdso: Add include guard to asm/vdso/vdso.h MIPS: vdso: Explicitly include asm/vdso/vdso.h random: vDSO: Add explicit includes vdso/gettimeofday: Add explicit includes vdso/helpers: Explicitly include vdso/processor.h vdso/datapage: Remove inclusion of gettimeofday.h vdso/datapage: Trim down unnecessary includes random: vDSO: trim vDSO includes random: vDSO: remove ifdeffery random: vDSO: split out datapage update into helper functions random: vDSO: only access vDSO datapage after random_init() s390/time: Set up vDSO datapage later vdso/datastore: Reduce scope of some variables in vvar_fault() vdso/datastore: Drop inclusion of linux/mmap_lock.h vdso/datastore: Map pages through struct page vdso/datastore: Allocate data pages dynamically sparc64: vdso: Link with -z noexecstack sparc64: vdso: Remove obsolete "fake section table" reservation sparc64: vdso: Replace code patching with runtime conditional sparc64: vdso: Move hardware counter read into header sparc64: vdso: Move syscall fallbacks into header sparc64: vdso: Introduce vdso/processor.h sparc64: vdso: Switch to the generic vDSO library sparc64: vdso2c: Drop sym_vvar_start handling sparc64: vdso2c: Remove symbol handling sparc64: vdso: Implement clock_gettime64() clocksource: drop include of asm/clocksource.h from linux/clocksource.h arch/arm/include/asm/vdso/gettimeofday.h | 2 + arch/arm64/include/asm/vdso/compat_gettimeofday.h | 3 + arch/arm64/include/asm/vdso/gettimeofday.h | 2 + arch/arm64/kernel/vdso/vgetrandom.c | 2 + arch/loongarch/kernel/process.c | 1 + arch/loongarch/kernel/vdso.c | 1 + arch/mips/include/asm/vdso/vdso.h | 5 + arch/mips/kernel/vdso.c | 1 + arch/powerpc/include/asm/vdso/gettimeofday.h | 1 + arch/powerpc/include/asm/vdso/processor.h | 3 + arch/s390/kernel/time.c | 4 +- arch/sparc/Kconfig | 3 +- arch/sparc/include/asm/clocksource.h | 9 - arch/sparc/include/asm/processor.h | 3 + arch/sparc/include/asm/processor_32.h | 2 - arch/sparc/include/asm/processor_64.h | 25 -- arch/sparc/include/asm/vdso.h | 2 - arch/sparc/include/asm/vdso/clocksource.h | 10 + arch/sparc/include/asm/vdso/gettimeofday.h | 184 ++++++++++ arch/sparc/include/asm/vdso/processor.h | 41 +++ arch/sparc/include/asm/vdso/vsyscall.h | 10 + arch/sparc/include/asm/vvar.h | 75 ---- arch/sparc/kernel/Makefile | 1 - arch/sparc/kernel/time_64.c | 6 +- arch/sparc/kernel/vdso.c | 69 ---- arch/sparc/vdso/Makefile | 8 +- arch/sparc/vdso/vclock_gettime.c | 380 ++------------------- arch/sparc/vdso/vdso-layout.lds.S | 26 +- arch/sparc/vdso/vdso.lds.S | 2 - arch/sparc/vdso/vdso2c.c | 24 -- arch/sparc/vdso/vdso2c.h | 45 +-- arch/sparc/vdso/vdso32/vdso32.lds.S | 4 +- arch/sparc/vdso/vma.c | 274 +-------------- drivers/char/random.c | 75 ++-- include/linux/clocksource.h | 8 - include/linux/vdso_datastore.h | 6 + include/vdso/datapage.h | 23 +- include/vdso/helpers.h | 1 + init/main.c | 2 + kernel/time/Kconfig | 4 - lib/vdso/datastore.c | 73 ++-- lib/vdso/getrandom.c | 3 + lib/vdso/gettimeofday.c | 17 + .../testing/selftests/vDSO/vdso_test_correctness.c | 8 +- 44 files changed, 451 insertions(+), 997 deletions(-) --- base-commit: 5f84f6004e298bd41c9e4ed45c18447954b1dce6 change-id: 20250722-vdso-sparc64-generic-2-25f2e058e92c Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

2 months, 2 weeks

6
49
0 0

[PATCH v2] selftests/iommu: prevent use of uninitialized variable

by Alessandro Zanni

Fix to avoid the usage of the `res` variable uninitialized in the following macro expansions. It solves the following warning: In function ‘iommufd_viommu_vdevice_alloc’, inlined from ‘wrapper_iommufd_viommu_vdevice_alloc’ at iommufd.c:2889:1: ../kselftest_harness.h:760:12: warning: ‘ret’ may be used uninitialized [-Wmaybe-uninitialized] 760 | if (!(__exp _t __seen)) { \ | ^ ../kselftest_harness.h:513:9: note: in expansion of macro ‘__EXPECT’ 513 | __EXPECT(expected, #expected, seen, #seen, ==, 1) | ^~~~~~~~ iommufd_utils.h:1057:9: note: in expansion of macro ‘ASSERT_EQ’ 1057 | ASSERT_EQ(0, _test_cmd_trigger_vevents(self->fd, dev_id, nvevents)) | ^~~~~~~~~ iommufd.c:2924:17: note: in expansion of macro ‘test_cmd_trigger_vevents’ 2924 | test_cmd_trigger_vevents(dev_id, 3); | ^~~~~~~~~~~~~~~~~~~~~~~~ The issue can be reproduced, building the tests, with the command: make -C tools/testing/selftests TARGETS=iommu Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- tools/testing/selftests/iommu/iommufd_utils.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 3c3e08b8c90e..772ca1db6e59 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -1042,15 +1042,13 @@ static int _test_cmd_trigger_vevents(int fd, __u32 dev_id, __u32 nvevents) .dev_id = dev_id, }, }; - int ret; while (nvevents--) { - ret = ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_VEVENT), - &trigger_vevent_cmd); - if (ret < 0) + if (!ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_VEVENT), + &trigger_vevent_cmd)) return -1; } - return ret; + return 0; } #define test_cmd_trigger_vevents(dev_id, nvevents) \ -- 2.43.0

2 months, 2 weeks

2
1
0 0

[PATCH v3 0/3] selftests/bpf: Prepare to add -Wsign-compare for bpf selftests

by Mehdi Ben Hadj Khelifa

This series is preparing to add the -Wsign-compare C compilation flag to the Makefile for bpf selftests as requested by a TODO to help avoid implicit type conversions and have predictable behavior. Changelog: Changes from v2: -Split up the patch into a patch series as suggested by vivek -Include only changes to variable types with no casting by my mentor david -Removed the -Wsign-compare in Makefile to avoid compilation errors until adding casting for rest of comparisons. Link:https://lore.kernel.org/bpf/20250924195731.6374-1-mehdi.benhadjkhelifa… Changes from v1: - Fix CI failed builds where it failed due to do missing .c and .h files in my patch for working in mainline. Link:https://lore.kernel.org/bpf/20250924162408.815137-1-mehdi.benhadjkheli… Mehdi Ben Hadj Khelifa (3): selftests/bpf: Prepare to add -Wsign-compare for bpf tests selftests/bpf: Prepare to add -Wsign-compare for bpf tests selftests/bpf: Prepare to add -Wsign-compare for bpf tests tools/testing/selftests/bpf/progs/test_global_func11.c | 2 +- tools/testing/selftests/bpf/progs/test_global_func12.c | 2 +- tools/testing/selftests/bpf/progs/test_global_func13.c | 2 +- tools/testing/selftests/bpf/progs/test_global_func9.c | 2 +- tools/testing/selftests/bpf/progs/test_map_init.c | 2 +- tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c | 2 +- .../selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c | 2 +- tools/testing/selftests/bpf/progs/test_skb_ctx.c | 2 +- tools/testing/selftests/bpf/progs/test_snprintf.c | 2 +- tools/testing/selftests/bpf/progs/test_sockmap_strp.c | 2 +- tools/testing/selftests/bpf/progs/test_tc_tunnel.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp_dynptr.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp_loop.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp_noinline.c | 4 ++-- tools/testing/selftests/bpf/progs/uprobe_multi.c | 4 ++-- .../selftests/bpf/progs/uprobe_multi_session_recursive.c | 5 +++-- .../selftests/bpf/progs/verifier_iterating_callbacks.c | 2 +- 18 files changed, 22 insertions(+), 21 deletions(-) -- 2.51.0

2 months, 3 weeks

4
8
0 0

[PATCH net-next v2 0/8] psp: add a kselftest suite and netdevsim implementation

by Daniel Zahka

Add a basic test suite for drivers that support PSP. Also, add a PSP implementation in the netdevsim driver. The netdevsim implementation does encapsulation and decapsulation of PSP packets, but no crypto. The tests cover the basic usage of the uapi, and demonstrate key exchange and connection setup. The tests and netdevsim support IPv4 and IPv6. Here is an example run on a system with a CX7 NIC. TAP version 13 1..28 ok 1 psp.data_basic_send_v0_ip4 ok 2 psp.data_basic_send_v0_ip6 ok 3 psp.data_basic_send_v1_ip4 ok 4 psp.data_basic_send_v1_ip6 ok 5 psp.data_basic_send_v2_ip4 # SKIP ('PSP version not supported', 'hdr0-aes-gmac-128') ok 6 psp.data_basic_send_v2_ip6 # SKIP ('PSP version not supported', 'hdr0-aes-gmac-128') ok 7 psp.data_basic_send_v3_ip4 # SKIP ('PSP version not supported', 'hdr0-aes-gmac-256') ok 8 psp.data_basic_send_v3_ip6 # SKIP ('PSP version not supported', 'hdr0-aes-gmac-256') ok 9 psp.data_mss_adjust_ip4 ok 10 psp.data_mss_adjust_ip6 ok 11 psp.dev_list_devices ok 12 psp.dev_get_device ok 13 psp.dev_get_device_bad ok 14 psp.dev_rotate ok 15 psp.dev_rotate_spi ok 16 psp.assoc_basic ok 17 psp.assoc_bad_dev ok 18 psp.assoc_sk_only_conn ok 19 psp.assoc_sk_only_mismatch ok 20 psp.assoc_sk_only_mismatch_tx ok 21 psp.assoc_sk_only_unconn ok 22 psp.assoc_version_mismatch ok 23 psp.assoc_twice ok 24 psp.data_send_bad_key ok 25 psp.data_send_disconnect ok 26 psp.data_stale_key ok 27 psp.removal_device_rx # XFAIL Test only works on netdevsim ok 28 psp.removal_device_bi # XFAIL Test only works on netdevsim # Totals: pass:22 fail:0 xfail:2 xpass:0 skip:4 error:0 # # Responder logs (0): # STDERR: # Set PSP enable on device 1 to 0x3 # Set PSP enable on device 1 to 0x0 CHANGES: v2: - fix pylint warnings - insert CONFIG_INET_PSP in alphebetical order - use branch to skip all tests - fix compilation error when CONFIG_INET_PSP is not set v1: https://lore.kernel.org/netdev/20250924194959.2845473-1-daniel.zahka@gmail.… Jakub Kicinski (8): netdevsim: a basic test PSP implementation selftests: drv-net: base device access API test selftests: drv-net: add PSP responder selftests: drv-net: psp: add basic data transfer and key rotation tests selftests: drv-net: psp: add association tests selftests: drv-net: psp: add connection breaking tests selftests: drv-net: psp: add test for auto-adjusting TCP MSS selftests: drv-net: psp: add tests for destroying devices drivers/net/netdevsim/Makefile | 4 + drivers/net/netdevsim/netdev.c | 55 +- drivers/net/netdevsim/netdevsim.h | 33 + drivers/net/netdevsim/psp.c | 234 +++++++ net/core/skbuff.c | 1 + .../testing/selftests/drivers/net/.gitignore | 1 + tools/testing/selftests/drivers/net/Makefile | 10 + tools/testing/selftests/drivers/net/config | 1 + .../drivers/net/hw/lib/py/__init__.py | 4 +- .../selftests/drivers/net/lib/py/__init__.py | 4 +- .../selftests/drivers/net/lib/py/env.py | 5 + tools/testing/selftests/drivers/net/psp.py | 593 ++++++++++++++++++ .../selftests/drivers/net/psp_responder.c | 483 ++++++++++++++ .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/ksft.py | 10 + tools/testing/selftests/net/lib/py/ynl.py | 5 + 16 files changed, 1432 insertions(+), 13 deletions(-) create mode 100644 drivers/net/netdevsim/psp.c create mode 100755 tools/testing/selftests/drivers/net/psp.py create mode 100644 tools/testing/selftests/drivers/net/psp_responder.c -- 2.47.3

2 months, 3 weeks

1
8
0 0

[PATCH v2] selftests/kexec: Ignore selftest binary

by Sohil Mehta

From: Dylan Yudaken <dyudaken(a)gmail.com> Add a .gitignore for the test case build object. Signed-off-by: Dylan Yudaken <dyudaken(a)gmail.com> Signed-off-by: Sohil Mehta <sohil.mehta(a)intel.com> Reviewed-by: Simon Horman <horms(a)kernel.org> --- The binary creates some noise. The patch to fix that seems to have fallen through the cracks. Sending another revision with an expanded Cc list. v2: - Pick up the review tag v1: https://lore.kernel.org/all/20250623232549.3263273-1-dyudaken@gmail.com/ --- tools/testing/selftests/kexec/.gitignore | 2 ++ 1 file changed, 2 insertions(+) create mode 100644 tools/testing/selftests/kexec/.gitignore diff --git a/tools/testing/selftests/kexec/.gitignore b/tools/testing/selftests/kexec/.gitignore new file mode 100644 index 000000000000..5f3d9e089ae8 --- /dev/null +++ b/tools/testing/selftests/kexec/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +test_kexec_jump -- 2.43.0

2 months, 3 weeks

2
1
0 0

[PATCH v10 00/21] TDX KVM selftests

by Sagi Shahar

This is v10 of the TDX selftests. This series is based on v6.17-rc4 and has a dependency on "KVM: TDX: Force split irqchip for TDX at irqchip creation time" [1] Changes from v9 [2]: - Rebased on top of v6.17-rc4. - Addressed the comments from v9. - Removed special handling for split irqchip in the test code in favor for the kvm fix in [1]. - Removed outdated support for VM memory not backed by guest_memfd. - Split "KVM: selftests: Hook TDX support to vm and vcpu creation" into 4 separate patches. [1] https://lore.kernel.org/lkml/20250904062007.622530-1-sagis@google.com/ [2] https://lore.kernel.org/lkml/20250821042915.3712925-1-sagis@google.com/ Ackerley Tng (2): KVM: selftests: Add helpers to init TDX memory and finalize VM KVM: selftests: Add ucall support for TDX Erdem Aktas (2): KVM: selftests: Add TDX boot code KVM: selftests: Add support for TDX TDCALL from guest Isaku Yamahata (2): KVM: selftests: Update kvm_init_vm_address_properties() for TDX KVM: selftests: TDX: Use KVM_TDX_CAPABILITIES to validate TDs' attribute configuration Sagi Shahar (15): KVM: selftests: Allocate pgd in virt_map() as necessary KVM: selftests: Expose functions to get default sregs values KVM: selftests: Expose function to allocate guest vCPU stack KVM: selftests: Expose segment definitons to assembly files KVM: selftests: Add kbuild definitons KVM: selftests: Define structs to pass parameters to TDX boot code KVM: selftests: Set up TDX boot code region KVM: selftests: Set up TDX boot parameters region KVM: selftests: Add helper to initialize TDX VM KVM: selftests: Call TDX init when creating a new TDX vm KVM: selftests: Setup memory regions for TDX on vm creation KVM: selftests: Call KVM_TDX_INIT_VCPU when creating a new TDX vcpu KVM: selftests: Set entry point for TDX guest code KVM: selftests: Add wrapper for TDX MMIO from guest KVM: selftests: Add TDX lifecycle test tools/include/linux/kbuild.h | 18 + tools/testing/selftests/kvm/Makefile.kvm | 32 ++ .../selftests/kvm/include/x86/processor.h | 35 ++ .../selftests/kvm/include/x86/processor_asm.h | 12 + .../selftests/kvm/include/x86/tdx/td_boot.h | 74 ++++ .../kvm/include/x86/tdx/td_boot_asm.h | 16 + .../selftests/kvm/include/x86/tdx/tdcall.h | 34 ++ .../selftests/kvm/include/x86/tdx/tdx.h | 14 + .../selftests/kvm/include/x86/tdx/tdx_util.h | 86 +++++ .../testing/selftests/kvm/include/x86/ucall.h | 4 +- tools/testing/selftests/kvm/lib/kvm_util.c | 10 +- .../testing/selftests/kvm/lib/x86/processor.c | 91 +++-- .../selftests/kvm/lib/x86/tdx/td_boot.S | 60 +++ .../kvm/lib/x86/tdx/td_boot_offsets.c | 21 ++ .../selftests/kvm/lib/x86/tdx/tdcall.S | 93 +++++ .../kvm/lib/x86/tdx/tdcall_offsets.c | 16 + tools/testing/selftests/kvm/lib/x86/tdx/tdx.c | 23 ++ .../selftests/kvm/lib/x86/tdx/tdx_util.c | 354 ++++++++++++++++++ tools/testing/selftests/kvm/lib/x86/ucall.c | 45 ++- tools/testing/selftests/kvm/x86/tdx_vm_test.c | 31 ++ 20 files changed, 1032 insertions(+), 37 deletions(-) create mode 100644 tools/include/linux/kbuild.h create mode 100644 tools/testing/selftests/kvm/include/x86/processor_asm.h create mode 100644 tools/testing/selftests/kvm/include/x86/tdx/td_boot.h create mode 100644 tools/testing/selftests/kvm/include/x86/tdx/td_boot_asm.h create mode 100644 tools/testing/selftests/kvm/include/x86/tdx/tdcall.h create mode 100644 tools/testing/selftests/kvm/include/x86/tdx/tdx.h create mode 100644 tools/testing/selftests/kvm/include/x86/tdx/tdx_util.h create mode 100644 tools/testing/selftests/kvm/lib/x86/tdx/td_boot.S create mode 100644 tools/testing/selftests/kvm/lib/x86/tdx/td_boot_offsets.c create mode 100644 tools/testing/selftests/kvm/lib/x86/tdx/tdcall.S create mode 100644 tools/testing/selftests/kvm/lib/x86/tdx/tdcall_offsets.c create mode 100644 tools/testing/selftests/kvm/lib/x86/tdx/tdx.c create mode 100644 tools/testing/selftests/kvm/lib/x86/tdx/tdx_util.c create mode 100644 tools/testing/selftests/kvm/x86/tdx_vm_test.c -- 2.51.0.338.gd7d06c2dae-goog

2 months, 3 weeks

2
33
0 0

[PATCH v2 net-next 00/14] AccECN protocol case handling series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Plesae find the v2 AccECN case handling patch series, which covers several excpetional case handling of Accurate ECN spec (RFC9768), adds new identifiers to be used by CC modules, adds ecn_delta into rate_sample, and keeps the ACE counter for computation, etc. This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best regards, Chia-Yu --- Chia-Yu Chang (11): tcp: L4S ECT(1) identifier and NEEDS_ACCECN for CC modules tcp: disable RFC3168 fallback identifier for CC modules tcp: accecn: handle unexpected AccECN negotiation feedback tcp: accecn: retransmit downgraded SYN in AccECN negotiation tcp: move increment of num_retrans tcp: accecn: retransmit SYN/ACK without AccECN option or non-AccECN SYN/ACK tcp: accecn: unset ECT if receive or send ACE=0 in AccECN negotiaion tcp: accecn: fallback outgoing half link to non-AccECN tcp: accecn: verify ACE counter in 1st ACK after AccECN negotiation tcp: accecn: stop sending AccECN opt when loss ACK w/ option tcp: accecn: enable AccECN Ilpo Järvinen (3): tcp: try to avoid safer when ACKs are thinned gro: flushing when CWR is set negatively affects AccECN tcp: accecn: Add ece_delta to rate_sample .../networking/net_cachelines/tcp_sock.rst | 1 + include/linux/tcp.h | 4 +- include/net/inet_ecn.h | 20 +++- include/net/tcp.h | 30 +++++- include/net/tcp_ecn.h | 85 ++++++++++++----- net/ipv4/sysctl_net_ipv4.c | 2 +- net/ipv4/tcp.c | 2 + net/ipv4/tcp_cong.c | 9 +- net/ipv4/tcp_input.c | 91 +++++++++++++------ net/ipv4/tcp_minisocks.c | 40 +++++--- net/ipv4/tcp_offload.c | 3 +- net/ipv4/tcp_output.c | 38 +++++--- 12 files changed, 239 insertions(+), 86 deletions(-) -- 2.34.1

2 months, 3 weeks

3
25
0 0

[PATCH] selftest: net: Fix error message if empty variable

by Alessandro Zanni

Fix to avoid cases where the `res` shell variable is empty in script comparisons. The issue can be reproduced with the command: make kselftest TARGETS=net It solves the error: ./tfo_passive.sh: line 98: [: -eq: unary operator expected Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- tools/testing/selftests/net/tfo_passive.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/tfo_passive.sh b/tools/testing/selftests/net/tfo_passive.sh index 80bf11fdc046..2655931b2396 100755 --- a/tools/testing/selftests/net/tfo_passive.sh +++ b/tools/testing/selftests/net/tfo_passive.sh @@ -95,7 +95,7 @@ wait res=$(cat $out_file) rm $out_file -if [ $res -eq 0 ]; then +if [ -n "$res" ] && [ $res -eq 0 ]; then echo "got invalid NAPI ID from passive TFO socket" cleanup_ns exit 1 -- 2.43.0

2 months, 3 weeks

3
2
0 0

[PATCH bpf-next v2] selftests/bpf: Add -Wsign-compare C compilation flag

by Mehdi Ben Hadj Khelifa

-Change all the source files and the corresponding headers to having matching sign comparisons. Signed-off-by: Mehdi Ben Hadj Khelifa <mehdi.benhadjkhelifa(a)gmail.com> --- Changelog: Changes since v1: - Fix CI failed builds where it failed due to do missing .c and .h files in my patch for working in mainline. https://lore.kernel.org/bpf/20250924162408.815137-1-mehdi.benhadjkhelifa@gm… --- tools/lib/bpf/usdt.bpf.h | 4 ++-- tools/testing/selftests/bpf/Makefile | 4 ++-- tools/testing/selftests/bpf/bpf_arena_htab.h | 2 +- tools/testing/selftests/bpf/progs/arena_list.c | 2 +- .../bpf/progs/bench_local_storage_create.c | 2 +- tools/testing/selftests/bpf/progs/bind_perm.c | 2 +- tools/testing/selftests/bpf/progs/bpf_cc_cubic.c | 2 +- tools/testing/selftests/bpf/progs/bpf_cubic.c | 8 ++++---- .../bpf/progs/bpf_iter_bpf_percpu_array_map.c | 2 +- .../selftests/bpf/progs/bpf_iter_task_stack.c | 2 +- .../testing/selftests/bpf/progs/bpf_iter_tasks.c | 3 ++- .../selftests/bpf/progs/bpf_iter_vma_offset.c | 4 ++-- .../testing/selftests/bpf/progs/bpf_qdisc_fifo.c | 2 +- tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c | 4 ++-- .../bpf/progs/cgroup_getset_retval_getsockopt.c | 6 +++--- .../selftests/bpf/progs/connect4_dropper.c | 2 +- .../selftests/bpf/progs/cpumask_success.c | 4 ++-- .../testing/selftests/bpf/progs/dynptr_success.c | 8 ++++---- tools/testing/selftests/bpf/progs/iters.c | 16 ++++++++-------- .../selftests/bpf/progs/kfunc_call_test.c | 2 +- tools/testing/selftests/bpf/progs/linked_list.c | 10 +++++----- tools/testing/selftests/bpf/progs/lsm.c | 2 +- .../testing/selftests/bpf/progs/map_in_map_btf.c | 2 +- tools/testing/selftests/bpf/progs/map_ptr_kern.c | 2 +- .../selftests/bpf/progs/mmap_inner_array.c | 2 +- .../testing/selftests/bpf/progs/mptcp_subflow.c | 2 +- .../selftests/bpf/progs/netif_receive_skb.c | 4 ++-- tools/testing/selftests/bpf/progs/profiler.inc.h | 6 +++--- .../testing/selftests/bpf/progs/rcu_read_lock.c | 4 ++-- .../bpf/progs/sk_storage_omem_uncharge.c | 6 +++--- .../selftests/bpf/progs/sockopt_inherit.c | 4 ++-- tools/testing/selftests/bpf/progs/sockopt_sk.c | 4 ++-- tools/testing/selftests/bpf/progs/strobemeta.h | 2 +- .../selftests/bpf/progs/task_local_data.bpf.h | 6 +++--- .../selftests/bpf/progs/test_bpf_cookie.c | 2 +- .../testing/selftests/bpf/progs/test_check_mtu.c | 4 ++-- .../selftests/bpf/progs/test_core_extern.c | 2 +- .../testing/selftests/bpf/progs/test_get_xattr.c | 4 ++-- .../selftests/bpf/progs/test_global_func11.c | 2 +- .../selftests/bpf/progs/test_global_func12.c | 2 +- .../selftests/bpf/progs/test_global_func13.c | 2 +- .../selftests/bpf/progs/test_global_func14.c | 2 +- .../selftests/bpf/progs/test_global_func9.c | 2 +- .../selftests/bpf/progs/test_lwt_seg6local.c | 4 ++-- .../testing/selftests/bpf/progs/test_map_init.c | 2 +- .../selftests/bpf/progs/test_parse_tcp_hdr_opt.c | 2 +- .../bpf/progs/test_parse_tcp_hdr_opt_dynptr.c | 2 +- .../selftests/bpf/progs/test_pkt_access.c | 6 +++--- .../testing/selftests/bpf/progs/test_seg6_loop.c | 4 ++-- tools/testing/selftests/bpf/progs/test_skb_ctx.c | 2 +- .../testing/selftests/bpf/progs/test_snprintf.c | 2 +- .../selftests/bpf/progs/test_sockmap_kern.h | 2 +- .../selftests/bpf/progs/test_sockmap_strp.c | 2 +- .../testing/selftests/bpf/progs/test_tc_tunnel.c | 2 +- tools/testing/selftests/bpf/progs/test_xdp.c | 2 +- .../selftests/bpf/progs/test_xdp_dynptr.c | 2 +- .../testing/selftests/bpf/progs/test_xdp_loop.c | 2 +- .../selftests/bpf/progs/test_xdp_noinline.c | 4 ++-- tools/testing/selftests/bpf/progs/udp_limit.c | 2 +- tools/testing/selftests/bpf/progs/uprobe_multi.c | 4 ++-- .../bpf/progs/uprobe_multi_session_recursive.c | 5 +++-- .../selftests/bpf/progs/verifier_arena_large.c | 4 ++-- .../bpf/progs/verifier_iterating_callbacks.c | 2 +- 63 files changed, 109 insertions(+), 107 deletions(-) diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index 43deb05a5197..59095c7f5b65 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -148,7 +148,7 @@ int bpf_usdt_arg_size(struct pt_regs *ctx, __u64 arg_num) if (arg_num >= BPF_USDT_MAX_ARG_CNT) return -ENOENT; barrier_var(arg_num); - if (arg_num >= spec->arg_cnt) + if (arg_num >= (__u64)spec->arg_cnt) return -ENOENT; arg_spec = &spec->args[arg_num]; @@ -184,7 +184,7 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) if (arg_num >= BPF_USDT_MAX_ARG_CNT) return -ENOENT; barrier_var(arg_num); - if (arg_num >= spec->arg_cnt) + if (arg_num >= (__u64)spec->arg_cnt) return -ENOENT; arg_spec = &spec->args[arg_num]; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 0b6ee902bce5..1b3c0c9388cc 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -453,8 +453,8 @@ BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(abspath $(OUTPUT)/../usr/include) \ -std=gnu11 \ -fno-strict-aliasing \ - -Wno-compare-distinct-pointer-types -# TODO: enable me -Wsign-compare + -Wno-compare-distinct-pointer-types \ + -Wsign-compare CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) diff --git a/tools/testing/selftests/bpf/bpf_arena_htab.h b/tools/testing/selftests/bpf/bpf_arena_htab.h index acc01a876668..ad77514c3cb1 100644 --- a/tools/testing/selftests/bpf/bpf_arena_htab.h +++ b/tools/testing/selftests/bpf/bpf_arena_htab.h @@ -42,7 +42,7 @@ static hashtab_elem_t *lookup_elem_raw(arena_list_head_t *head, __u32 hash, int hashtab_elem_t *l; list_for_each_entry(l, head, hash_node) - if (l->hash == hash && l->key == key) + if ((__u32)l->hash == hash && l->key == key) return l; return NULL; diff --git a/tools/testing/selftests/bpf/progs/arena_list.c b/tools/testing/selftests/bpf/progs/arena_list.c index 3a2ddcacbea6..02676f77a4cf 100644 --- a/tools/testing/selftests/bpf/progs/arena_list.c +++ b/tools/testing/selftests/bpf/progs/arena_list.c @@ -50,7 +50,7 @@ int arena_list_add(void *ctx) list_head = &global_head; - for (i = zero; i < cnt && can_loop; i++) { + for (i = zero; i < (__u64)cnt && can_loop; i++) { struct elem __arena *n = bpf_alloc(sizeof(*n)); test_val++; diff --git a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c index c8ec0d0368e4..2b23e59bc04a 100644 --- a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c +++ b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c @@ -44,7 +44,7 @@ int BPF_PROG(sched_process_fork, struct task_struct *parent, struct task_struct { struct storage *stg; - if (parent->tgid != bench_pid) + if ((__u32)parent->tgid != bench_pid) return 0; stg = bpf_task_storage_get(&task_storage_map, child, NULL, diff --git a/tools/testing/selftests/bpf/progs/bind_perm.c b/tools/testing/selftests/bpf/progs/bind_perm.c index 7bd2a027025d..e629909c97b6 100644 --- a/tools/testing/selftests/bpf/progs/bind_perm.c +++ b/tools/testing/selftests/bpf/progs/bind_perm.c @@ -7,7 +7,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -static __always_inline int bind_prog(struct bpf_sock_addr *ctx, int family) +static __always_inline int bind_prog(struct bpf_sock_addr *ctx, __u32 family) { struct bpf_sock *sk; diff --git a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c index 4e51785e7606..76b4184713e2 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c @@ -91,7 +91,7 @@ static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, (__u64)tp->snd_ssthresh * prr_delivered + tp->prior_cwnd - 1; sndcnt = (__u32)div64_u64(dividend, (__u64)tp->prior_cwnd) - tp->prr_out; } else { - sndcnt = max(prr_delivered - tp->prr_out, newly_acked_sacked); + sndcnt = max(prr_delivered - tp->prr_out, (__u32)newly_acked_sacked); if (flag & FLAG_SND_UNA_ADVANCED && !newly_lost) sndcnt++; sndcnt = min(delta, sndcnt); diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index f089faa97ae6..100937488d2d 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -277,7 +277,7 @@ static void bictcp_update(struct bpf_bictcp *ca, __u32 cwnd, __u32 acked) ca->ack_cnt += acked; /* count the number of ACKed packets */ if (ca->last_cwnd == cwnd && - (__s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) + (__s32)(tcp_jiffies32 - ca->last_time) <= (__s32)HZ / 32) return; /* The CUBIC function can update ca->cnt at most once per jiffy. @@ -474,7 +474,7 @@ static void hystart_update(struct sock *sk, __u32 delay) if (sk->sk_pacing_status == SK_PACING_NONE) threshold >>= 1; - if ((__s32)(now - ca->round_start) > threshold) { + if ((__s32)(now - ca->round_start) > (__s32)threshold) { ca->found = 1; tp->snd_ssthresh = tp->snd_cwnd; } @@ -512,7 +512,7 @@ void BPF_PROG(bpf_cubic_acked, struct sock *sk, const struct ack_sample *sample) return; /* Discard delay samples right after fast recovery */ - if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < HZ) + if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < (__s32)HZ) return; delay = sample->rtt_us; @@ -525,7 +525,7 @@ void BPF_PROG(bpf_cubic_acked, struct sock *sk, const struct ack_sample *sample) /* hystart triggers when cwnd is larger than some threshold */ if (!ca->found && tcp_in_slow_start(tp) && hystart && - tp->snd_cwnd >= hystart_low_window) + tp->snd_cwnd >= (__u32)hystart_low_window) hystart_update(sk, delay); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c index 9fdea8cd4c6f..0baf00463f35 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c @@ -24,7 +24,7 @@ int dump_bpf_percpu_array_map(struct bpf_iter__bpf_map_elem *ctx) __u32 *key = ctx->key; void *pptr = ctx->value; __u32 step; - int i; + __u32 i; if (key == (void *)0 || pptr == (void *)0) return 0; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c index f5a309455490..647ec1aa0326 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -27,7 +27,7 @@ int dump_task_stack(struct bpf_iter__task *ctx) BPF_SEQ_PRINTF(seq, "pid: %8u num_entries: %8u\n", task->pid, retlen / SIZE_OF_ULONG); for (i = 0; i < MAX_STACK_TRACE_DEPTH; i++) { - if (retlen > i * SIZE_OF_ULONG) + if ((__u32)retlen > i * SIZE_OF_ULONG) BPF_SEQ_PRINTF(seq, "[<0>] %pB\n", (void *)entries[i]); } BPF_SEQ_PRINTF(seq, "\n"); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c index 966ee5a7b066..704db7589565 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c @@ -115,7 +115,8 @@ int dump_task_sleepable(struct bpf_iter__task *ctx) /* Same length as the string */ ret = bpf_copy_from_user_task_str((char *)task_str2, 10, user_ptr, task, 0); /* only need to do the task pid check once */ - if (bpf_strncmp(task_str2, 10, "test_data\0") != 0 || ret != 10 || task->tgid != pid) { + if (bpf_strncmp(task_str2, 10, "test_data\0") != 0 || ret != 10 || + (__u32)task->tgid != pid) { BPF_SEQ_PRINTF(seq, "%s\n", info); return 0; } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c b/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c index 174298e122d3..d9088851babf 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c @@ -22,11 +22,11 @@ int get_vma_offset(struct bpf_iter__task_vma *ctx) if (task == NULL || vma == NULL) return 0; - if (last_tgid != task->tgid) + if (last_tgid != (__u32)task->tgid) unique_tgid_cnt++; last_tgid = task->tgid; - if (task->tgid != pid) + if ((__u32)task->tgid != pid) return 0; if (vma->vm_start <= address && vma->vm_end > address) { diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c index 1de2be3e370b..7a639dcb23a9 100644 --- a/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c +++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c @@ -88,7 +88,7 @@ void BPF_PROG(bpf_fifo_reset, struct Qdisc *sch) { struct bpf_list_node *node; struct skb_node *skbn; - int i; + __u32 i; bpf_for(i, 0, sch->q.qlen) { struct sk_buff *skb = NULL; diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c index 1a3233a275c7..4f80164b5491 100644 --- a/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c +++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c @@ -351,7 +351,7 @@ int BPF_PROG(bpf_fq_enqueue, struct sk_buff *skb, struct Qdisc *sch, jiffies = bpf_jiffies64(); if ((s64)(jiffies - (flow_copy->age + q.flow_refill_delay)) > 0) { - if (flow_copy->credit < q.quantum) + if ((__u32)flow_copy->credit < q.quantum) flow_copy->credit = q.quantum; } flow_copy->age = 0; @@ -590,7 +590,7 @@ struct sk_buff *BPF_PROG(bpf_fq_dequeue, struct Qdisc *sch) { struct dequeue_nonprio_ctx cb_ctx = {}; struct sk_buff *skb = NULL; - int i; + __u32 i; if (!sch->q.qlen) goto out; diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c index 932b8ecd4ae3..854dae839f7f 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -22,7 +22,7 @@ int get_retval(struct bpf_sockopt *ctx) __sync_fetch_and_add(&invocations, 1); /* optval larger than PAGE_SIZE use kernel's buffer. */ - if (ctx->optlen > page_size) + if ((__u32)ctx->optlen > page_size) ctx->optlen = 0; return 1; @@ -37,7 +37,7 @@ int set_eisconn(struct bpf_sockopt *ctx) assertion_error = 1; /* optval larger than PAGE_SIZE use kernel's buffer. */ - if (ctx->optlen > page_size) + if ((__u32)ctx->optlen > page_size) ctx->optlen = 0; return 1; @@ -51,7 +51,7 @@ int clear_retval(struct bpf_sockopt *ctx) ctx->retval = 0; /* optval larger than PAGE_SIZE use kernel's buffer. */ - if (ctx->optlen > page_size) + if ((__u32)ctx->optlen > page_size) ctx->optlen = 0; return 1; diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c index a3819a5d09c8..0014f8de9d1c 100644 --- a/tools/testing/selftests/bpf/progs/connect4_dropper.c +++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c @@ -20,7 +20,7 @@ int connect_v4_dropper(struct bpf_sock_addr *ctx) { if (ctx->type != SOCK_STREAM) return VERDICT_PROCEED; - if (ctx->user_port == bpf_htons(port)) + if (ctx->user_port == (__u32)bpf_htons(port)) return VERDICT_REJECT; return VERDICT_PROCEED; } diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c index 0e04c31b91c0..c09e290fbdac 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_success.c +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -221,7 +221,7 @@ int BPF_PROG(test_first_firstzero_cpu, struct task_struct *task, u64 clone_flags if (!cpumask) return 0; - if (bpf_cpumask_first(cast(cpumask)) < nr_cpus) { + if (bpf_cpumask_first(cast(cpumask)) < (__u32)nr_cpus) { err = 3; goto release_exit; } @@ -866,7 +866,7 @@ int BPF_PROG(test_populate, struct task_struct *task, u64 clone_flags) * access NR_CPUS, the upper bound for nr_cpus, so we infer * it from the size of cpumask_t. */ - if (nr_cpus < 0 || nr_cpus >= CPUMASK_TEST_MASKLEN * 8) { + if (nr_cpus < 0 || (__u32)nr_cpus >= CPUMASK_TEST_MASKLEN * 8) { err = 3; goto out; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index 127dea342e5a..149b9308105e 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -40,7 +40,7 @@ int test_read_write(void *ctx) char write_data[64] = "hello there, world!!"; char read_data[64] = {}; struct bpf_dynptr ptr; - int i; + __u32 i; if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; @@ -114,7 +114,7 @@ int test_dynptr_data(void *ctx) if (err) return 0; - if (val != *(int *)data) + if ((int)val != *(int *)data) err = 5; return 0; @@ -626,7 +626,7 @@ int BPF_PROG(test_dynptr_skb_tp_btf, void *skb, void *location) static inline int bpf_memcmp(const char *a, const char *b, u32 size) { - int i; + __u32 i; bpf_for(i, 0, size) { if (a[i] != b[i]) @@ -937,7 +937,7 @@ static __always_inline void test_dynptr_probe(void *ptr, bpf_read_dynptr_fn_t bp { char buf[sizeof(expected_str)]; struct bpf_dynptr ptr_buf; - int i; + __u32 i; if (bpf_get_current_pid_tgid() >> 32 != pid) return; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 7dd92a303bf6..bb896fd7b364 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -369,7 +369,7 @@ SEC("raw_tp") __success int iter_array_fill(const void *ctx) { - int sum, i; + __u32 sum, i; MY_PID_GUARD(); @@ -395,7 +395,7 @@ SEC("raw_tp") __success int iter_nested_iters(const void *ctx) { - int sum, row, col; + __u64 sum, row, col; MY_PID_GUARD(); @@ -463,7 +463,7 @@ int iter_nested_deeply_iters(const void *ctx) static __noinline void fill_inner_dimension(int row) { - int col; + __u64 col; bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { arr2d[row][col] = row * col; @@ -472,7 +472,7 @@ static __noinline void fill_inner_dimension(int row) static __noinline int sum_inner_dimension(int row) { - int sum = 0, col; + __u64 sum = 0, col; bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) { sum += arr2d[row][col]; @@ -487,7 +487,7 @@ SEC("raw_tp") __success int iter_subprog_iters(const void *ctx) { - int sum, row, col; + __u64 sum, row, col; MY_PID_GUARD(); @@ -626,7 +626,7 @@ __success int iter_stack_array_loop(const void *ctx) { long arr1[16], arr2[16], sum = 0; - int i; + __u32 i; MY_PID_GUARD(); @@ -663,7 +663,7 @@ static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul) while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= n) + if ((__u32)i >= n) break; arr[i] = i * mul; } @@ -1537,7 +1537,7 @@ int iter_arr_with_actual_elem_count(const void *ctx) { int i, n = loop_data.n, sum = 0; - if (n > ARRAY_SIZE(loop_data.data)) + if ((__u64)n > ARRAY_SIZE(loop_data.data)) return 0; bpf_for(i, 0, n) { diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 8b86113a0126..c4e570662b54 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -108,7 +108,7 @@ int kfunc_syscall_test(struct syscall_test_args *args) { const long size = args->size; - if (size > sizeof(args->data)) + if ((__u64)size > sizeof(args->data)) return -7; /* -E2BIG */ bpf_kfunc_call_test_mem_len_pass1(&args->data, sizeof(args->data)); diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c index 421f40835acd..d817c8a483f3 100644 --- a/tools/testing/selftests/bpf/progs/linked_list.c +++ b/tools/testing/selftests/bpf/progs/linked_list.c @@ -110,7 +110,7 @@ int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *hea { struct bpf_list_node *n; struct foo *f[200], *pf; - int i; + __u64 i; /* Loop following this check adds nodes 2-at-a-time in order to * validate multiple release_on_unlock release logic @@ -144,7 +144,7 @@ int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *hea if (!n) return 3; pf = container_of(n, struct foo, node2); - if (pf->data != (ARRAY_SIZE(f) - i - 1)) { + if ((__u64)pf->data != (ARRAY_SIZE(f) - i - 1)) { bpf_obj_drop(pf); return 4; } @@ -163,7 +163,7 @@ int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *hea if (!n) return 5; pf = container_of(n, struct foo, node2); - if (pf->data != i) { + if ((__u64)pf->data != i) { bpf_obj_drop(pf); return 6; } @@ -193,7 +193,7 @@ int list_in_list(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool le struct bpf_list_node *n; struct bar *ba[8], *b; struct foo *f; - int i; + __u64 i; f = bpf_obj_new(typeof(*f)); if (!f) @@ -238,7 +238,7 @@ int list_in_list(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool le return 6; } b = container_of(n, struct bar, node); - if (b->data != i) { + if ((__u64)b->data != i) { bpf_obj_drop(f); bpf_obj_drop(b); return 7; diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c index 0c13b7409947..bb6a4bb6e364 100644 --- a/tools/testing/selftests/bpf/progs/lsm.c +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -115,7 +115,7 @@ int BPF_PROG(test_void_hook, struct linux_binprm *bprm) __u32 key = 0; __u64 *value; - if (monitored_pid == pid) + if ((__u32)monitored_pid == pid) bprm_count++; bpf_copy_from_user(args, sizeof(args), (void *)bprm->vma->vm_mm->arg_start); diff --git a/tools/testing/selftests/bpf/progs/map_in_map_btf.c b/tools/testing/selftests/bpf/progs/map_in_map_btf.c index 7a1336d7b16a..719368217fe8 100644 --- a/tools/testing/selftests/bpf/progs/map_in_map_btf.c +++ b/tools/testing/selftests/bpf/progs/map_in_map_btf.c @@ -49,7 +49,7 @@ int add_to_list_in_inner_array(void *ctx) struct bpf_map *map; int zero = 0; - if (done || (u32)bpf_get_current_pid_tgid() != pid) + if (done || (__u32)bpf_get_current_pid_tgid() != (__u32)pid) return 0; map = bpf_map_lookup_elem(&outer_array, &zero); diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index efaf622c28dd..310526d06233 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -148,7 +148,7 @@ static inline int check_array(void) { struct bpf_array *array = (struct bpf_array *)&m_array; struct bpf_map *map = (struct bpf_map *)&m_array; - int i, n_lookups = 0, n_keys = 0; + __u32 i, n_lookups = 0, n_keys = 0; VERIFY(check_default(&array->map, map)); diff --git a/tools/testing/selftests/bpf/progs/mmap_inner_array.c b/tools/testing/selftests/bpf/progs/mmap_inner_array.c index 90aacbc2938a..90e31cf3a4d3 100644 --- a/tools/testing/selftests/bpf/progs/mmap_inner_array.c +++ b/tools/testing/selftests/bpf/progs/mmap_inner_array.c @@ -38,7 +38,7 @@ int add_to_list_in_inner_array(void *ctx) __u64 *value; curr_pid = (u32)bpf_get_current_pid_tgid(); - if (done || curr_pid != pid) + if (done || curr_pid != (__u32)pid) return 0; pid_match = true; diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c index 70302477e326..8af5c2dfc08c 100644 --- a/tools/testing/selftests/bpf/progs/mptcp_subflow.c +++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c @@ -63,7 +63,7 @@ int mptcp_subflow(struct bpf_sock_ops *skops) static int _check_getsockopt_subflow_mark(struct mptcp_sock *msk, struct bpf_sockopt *ctx) { struct mptcp_subflow_context *subflow; - int i = 0; + __u32 i = 0; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk; diff --git a/tools/testing/selftests/bpf/progs/netif_receive_skb.c b/tools/testing/selftests/bpf/progs/netif_receive_skb.c index 9e067dcbf607..920b884eef01 100644 --- a/tools/testing/selftests/bpf/progs/netif_receive_skb.c +++ b/tools/testing/selftests/bpf/progs/netif_receive_skb.c @@ -35,7 +35,7 @@ static int __strncmp(const void *m1, const void *m2, size_t len) { const unsigned char *s1 = m1; const unsigned char *s2 = m2; - int i, delta = 0; + size_t i, delta = 0; for (i = 0; i < len; i++) { delta = s1[i] - s2[i]; @@ -107,7 +107,7 @@ int BPF_PROG(trace_netif_receive_skb, struct sk_buff *skb) /* Ensure we can write skb string representation */ p.type_id = bpf_core_type_id_kernel(struct sk_buff); p.ptr = skb; - for (i = 0; i < ARRAY_SIZE(flags); i++) { + for (i = 0; (size_t)i < ARRAY_SIZE(flags); i++) { ++num_subtests; ret = bpf_snprintf_btf(str, STRSIZE, &p, sizeof(p), 0); if (ret < 0) diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 813143b4985d..f664f5915169 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -169,7 +169,7 @@ static INLINE int get_var_spid_index(struct var_kill_data_arr_t* arr_struct, #ifdef UNROLL __pragma_loop_unroll #endif - for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) + for (size_t i = 0; i < ARRAY_SIZE(arr_struct->array); i++) if (arr_struct->array[i].meta.pid == spid) return i; return -1; @@ -402,7 +402,7 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) #ifdef UNROLL __pragma_loop_unroll #endif - for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) + for (size_t i = 0; i < ARRAY_SIZE(arr_struct->array); i++) if (arr_struct->array[i].meta.pid == 0) { bpf_probe_read_kernel(&arr_struct->array[i], sizeof(arr_struct->array[i]), @@ -629,7 +629,7 @@ int raw_tracepoint__sched_process_exit(void* ctx) #ifdef UNROLL __pragma_loop_unroll #endif - for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) { + for (size_t i = 0; i < ARRAY_SIZE(arr_struct->array); i++) { struct var_kill_data_t* past_kill_data = &arr_struct->array[i]; if (past_kill_data != NULL && past_kill_data->kill_target_pid == (pid_t)tpid) { diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c index 3a868a199349..38fa039f586b 100644 --- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c @@ -34,7 +34,7 @@ int get_cgroup_id(void *ctx) struct css_set *cgroups; task = bpf_get_current_task_btf(); - if (task->pid != target_pid) + if ((__u32)task->pid != target_pid) return 0; /* simulate bpf_get_current_cgroup_id() helper */ @@ -56,7 +56,7 @@ int task_succ(void *ctx) long *ptr; task = bpf_get_current_task_btf(); - if (task->pid != target_pid) + if ((__u32)task->pid != target_pid) return 0; bpf_rcu_read_lock(); diff --git a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c index 46d6eb2a3b17..2df842c7e9ed 100644 --- a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c +++ b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c @@ -28,7 +28,7 @@ int BPF_PROG(bpf_local_storage_destroy, struct bpf_local_storage *local_storage) return 0; sk = bpf_core_cast(sk_ptr, struct sock); - if (sk->sk_cookie.counter != cookie) + if ((__u64)sk->sk_cookie.counter != cookie) return 0; cookie_found++; @@ -43,11 +43,11 @@ int BPF_PROG(inet6_sock_destruct, struct sock *sk) { int *value; - if (!cookie || sk->sk_cookie.counter != cookie) + if (!cookie || (__u64)sk->sk_cookie.counter != cookie) return 0; value = bpf_sk_storage_get(&sk_storage, sk, 0, 0); - if (value && *value == 0xdeadbeef) { + if (value && (__u32)*value == 0xdeadbeef) { cookie_found++; sk_ptr = sk; local_storage_ptr = sk->sk_bpf_storage; diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c index a3434b840928..9f15752af34b 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -56,7 +56,7 @@ int _getsockopt(struct bpf_sockopt *ctx) struct sockopt_inherit *storage; __u8 *optval = ctx->optval; - if (ctx->level != SOL_CUSTOM) + if (ctx->level != (__s32)SOL_CUSTOM) goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) @@ -87,7 +87,7 @@ int _setsockopt(struct bpf_sockopt *ctx) struct sockopt_inherit *storage; __u8 *optval = ctx->optval; - if (ctx->level != SOL_CUSTOM) + if (ctx->level != (__s32)SOL_CUSTOM) goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index cb990a7d3d45..f08529dfb2cb 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -107,7 +107,7 @@ int _getsockopt(struct bpf_sockopt *ctx) return 1; } - if (ctx->level != SOL_CUSTOM) + if (ctx->level != (__s32)SOL_CUSTOM) return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) @@ -212,7 +212,7 @@ int _setsockopt(struct bpf_sockopt *ctx) return 1; } - if (ctx->level != SOL_CUSTOM) + if (ctx->level != (__s32)SOL_CUSTOM) return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index a5c74d31a244..36b4e82abae2 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -409,7 +409,7 @@ static __always_inline uint64_t read_map_var(struct strobemeta_cfg *cfg, descr->id = map.id; descr->cnt = map.cnt; - if (cfg->req_meta_idx == idx) { + if (cfg->req_meta_idx == (__s64)idx) { data->req_id = map.id; data->req_meta_valid = 1; } diff --git a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h index 432fff2af844..51a958d04aa7 100644 --- a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h +++ b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h @@ -181,7 +181,7 @@ static int __tld_fetch_key(struct tld_object *tld_obj, const char *name, int i_s metadata = tld_obj->data_map->meta->metadata; bpf_for(i, 0, cnt) { - if (i >= TLD_MAX_DATA_CNT) + if ((__u32)i >= TLD_MAX_DATA_CNT) break; if (i >= i_start && !bpf_strncmp(metadata[i].name, TLD_NAME_LEN, name)) @@ -214,7 +214,7 @@ static int __tld_fetch_key(struct tld_object *tld_obj, const char *name, int i_s if (likely(_data)) { \ if (likely(off > 0)) { \ barrier_var(off); \ - if (likely(off < __PAGE_SIZE - size)) \ + if (likely((size_t)off < __PAGE_SIZE - size)) \ data = _data + off; \ } else { \ cnt = -(off); \ @@ -223,7 +223,7 @@ static int __tld_fetch_key(struct tld_object *tld_obj, const char *name, int i_s off = __tld_fetch_key(tld_obj, name, cnt); \ (tld_obj)->key_map->key.off = off; \ \ - if (likely(off < __PAGE_SIZE - size)) { \ + if (likely((size_t)off < __PAGE_SIZE - size)) { \ barrier_var(off); \ if (off > 0) \ data = _data + off; \ diff --git a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c index c83142b55f47..47e80864b6b8 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c @@ -6,7 +6,7 @@ #include <bpf/bpf_tracing.h> #include <errno.h> -int my_tid; +__u32 my_tid; __u64 kprobe_res; __u64 kprobe_multi_res; diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index 2ec1de11a3ae..246caea8124f 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -47,7 +47,7 @@ int xdp_use_helper(struct xdp_md *ctx) goto out; } - if (mtu_len != GLOBAL_USER_MTU) + if (mtu_len != (__u32)GLOBAL_USER_MTU) retval = XDP_DROP; out: @@ -165,7 +165,7 @@ int tc_use_helper(struct __sk_buff *ctx) goto out; } - if (mtu_len != GLOBAL_USER_MTU) + if (mtu_len != (__u32)GLOBAL_USER_MTU) retval = BPF_REDIRECT; out: global_bpf_mtu_tc = mtu_len; diff --git a/tools/testing/selftests/bpf/progs/test_core_extern.c b/tools/testing/selftests/bpf/progs/test_core_extern.c index a3c7c1042f35..4eae1eb885f1 100644 --- a/tools/testing/selftests/bpf/progs/test_core_extern.c +++ b/tools/testing/selftests/bpf/progs/test_core_extern.c @@ -37,7 +37,7 @@ uint64_t missing_val = -1; SEC("raw_tp/sys_enter") int handle_sys_enter(struct pt_regs *ctx) { - int i; + __u32 i; kern_ver = LINUX_KERNEL_VERSION; unkn_virt_val = LINUX_UNKNOWN_VIRTUAL_EXTERN; diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c index 54305f4c9f2d..3cda9379a62a 100644 --- a/tools/testing/selftests/bpf/progs/test_get_xattr.c +++ b/tools/testing/selftests/bpf/progs/test_get_xattr.c @@ -42,7 +42,7 @@ int BPF_PROG(test_file_open, struct file *f) bpf_dynptr_from_mem(value1, sizeof(value1), 0, &value_ptr); - for (i = 0; i < ARRAY_SIZE(xattr_names); i++) { + for (i = 0; (__u32)i < ARRAY_SIZE(xattr_names); i++) { ret = bpf_get_file_xattr(f, xattr_names[i], &value_ptr); if (ret == sizeof(expected_value)) break; @@ -68,7 +68,7 @@ int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name) bpf_dynptr_from_mem(value2, sizeof(value2), 0, &value_ptr); - for (i = 0; i < ARRAY_SIZE(xattr_names); i++) { + for (i = 0; (__u32)i < ARRAY_SIZE(xattr_names); i++) { ret = bpf_get_dentry_xattr(dentry, xattr_names[i], &value_ptr); if (ret == sizeof(expected_value)) break; diff --git a/tools/testing/selftests/bpf/progs/test_global_func11.c b/tools/testing/selftests/bpf/progs/test_global_func11.c index 283e036dc401..2ad72bf0e07b 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func11.c +++ b/tools/testing/selftests/bpf/progs/test_global_func11.c @@ -5,7 +5,7 @@ #include "bpf_misc.h" struct S { - int x; + __u32 x; }; __noinline int foo(const struct S *s) diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c index 6e03d42519a6..53eab8ec6772 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func12.c +++ b/tools/testing/selftests/bpf/progs/test_global_func12.c @@ -5,7 +5,7 @@ #include "bpf_misc.h" struct S { - int x; + __u32 x; }; __noinline int foo(const struct S *s) diff --git a/tools/testing/selftests/bpf/progs/test_global_func13.c b/tools/testing/selftests/bpf/progs/test_global_func13.c index 02ea80da75b5..c4afdfc9d92e 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func13.c +++ b/tools/testing/selftests/bpf/progs/test_global_func13.c @@ -5,7 +5,7 @@ #include "bpf_misc.h" struct S { - int x; + __u32 x; }; __noinline int foo(const struct S *s) diff --git a/tools/testing/selftests/bpf/progs/test_global_func14.c b/tools/testing/selftests/bpf/progs/test_global_func14.c index 33b7d5efd7b2..9c494fb39e2f 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func14.c +++ b/tools/testing/selftests/bpf/progs/test_global_func14.c @@ -9,7 +9,7 @@ struct S; __noinline int foo(const struct S *s) { if (s) - return bpf_get_prandom_u32() < *(const int *) s; + return bpf_get_prandom_u32() < *(const __u32 *) s; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_global_func9.c b/tools/testing/selftests/bpf/progs/test_global_func9.c index 1f2cb0159b8d..9138d9bd08fc 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func9.c +++ b/tools/testing/selftests/bpf/progs/test_global_func9.c @@ -5,7 +5,7 @@ #include "bpf_misc.h" struct S { - int x; + __u32 x; }; struct C { diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c index fed66f36adb6..976af2d3cdda 100644 --- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c @@ -167,7 +167,7 @@ int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, if (*pad_off == 0) *pad_off = cur_off; - if (*tlv_off == -1) + if (*tlv_off == (__u32)-1) *tlv_off = cur_off; else if (!offset_valid) return -EINVAL; @@ -186,7 +186,7 @@ int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, uint32_t partial_srh_len; int err; - if (tlv_off != -1) + if (tlv_off != (__u32)-1) tlv_off += srh_off; if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c index c89d28ead673..311e6ac64588 100644 --- a/tools/testing/selftests/bpf/progs/test_map_init.c +++ b/tools/testing/selftests/bpf/progs/test_map_init.c @@ -22,7 +22,7 @@ int sysenter_getpgid(const void *ctx) /* Just do it for once, when called from our own test prog. This * ensures the map value is only updated for a single CPU. */ - int cur_pid = bpf_get_current_pid_tgid() >> 32; + __u32 cur_pid = bpf_get_current_pid_tgid() >> 32; if (cur_pid == inPid) bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST); diff --git a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c index d9b2ba7ac340..4b8ab8716246 100644 --- a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c +++ b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c @@ -102,7 +102,7 @@ int xdp_ingress_v6(struct xdp_md *xdp) opt_state.byte_offset = sizeof(struct tcphdr) + tcp_offset; /* max number of bytes of options in tcp header is 40 bytes */ - for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) { + for (__u32 i = 0; i < tcp_hdr_opt_max_opt_checks; i++) { err = parse_hdr_opt(xdp, &opt_state); if (err || !opt_state.hdr_bytes_remaining) diff --git a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c index dc6e43bc6a62..bf3ac5c2938c 100644 --- a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c @@ -100,7 +100,7 @@ int xdp_ingress_v6(struct xdp_md *xdp) off += sizeof(struct tcphdr); /* max number of bytes of options in tcp header is 40 bytes */ - for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) { + for (__u32 i = 0; i < tcp_hdr_opt_max_opt_checks; i++) { err = parse_hdr_opt(&ptr, &off, &hdr_bytes_remaining, &server_id); if (err || !hdr_bytes_remaining) diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index bce7173152c6..39b5a5ba9033 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -130,11 +130,11 @@ int test_pkt_access(struct __sk_buff *skb) tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len); } - if (test_pkt_access_subprog1(skb) != skb->len * 2) + if ((__u32)test_pkt_access_subprog1(skb) != skb->len * 2) return TC_ACT_SHOT; - if (test_pkt_access_subprog2(2, skb) != skb->len * 2) + if ((__u32)test_pkt_access_subprog2(2, skb) != skb->len * 2) return TC_ACT_SHOT; - if (test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex) + if ((__u32)test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex) return TC_ACT_SHOT; if (tcp) { if (test_pkt_write_access_subprog(skb, (void *)tcp - data)) diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c index 5059050f74f6..fccb21d23fe2 100644 --- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -170,7 +170,7 @@ static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb, if (*pad_off == 0) *pad_off = cur_off; - if (*tlv_off == -1) + if (*tlv_off == (__u32)-1) *tlv_off = cur_off; else if (!offset_valid) return -EINVAL; @@ -189,7 +189,7 @@ static __always_inline int add_tlv(struct __sk_buff *skb, uint32_t partial_srh_len; int err; - if (tlv_off != -1) + if (tlv_off != (__u32)-1) tlv_off += srh_off; if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC) diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c index a724a70c6700..7939a2edc414 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -11,7 +11,7 @@ SEC("tc") int process(struct __sk_buff *skb) { __pragma_loop_unroll_full - for (int i = 0; i < 5; i++) { + for (__u32 i = 0; i < 5; i++) { if (skb->cb[i] != i + 1) return 1; skb->cb[i]++; diff --git a/tools/testing/selftests/bpf/progs/test_snprintf.c b/tools/testing/selftests/bpf/progs/test_snprintf.c index 8fda07544023..1aa4835da71a 100644 --- a/tools/testing/selftests/bpf/progs/test_snprintf.c +++ b/tools/testing/selftests/bpf/progs/test_snprintf.c @@ -4,7 +4,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -__u32 pid = 0; +int pid = 0; char num_out[64] = {}; long num_ret = 0; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index f48f85f1bd70..2297c83433b7 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -336,7 +336,7 @@ int bpf_prog9(struct sk_msg_md *msg) bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); if (bytes) { - if (((__u64)data_end - (__u64)data) >= *bytes) + if (((__u64)data_end - (__u64)data) >= (__u64)*bytes) return SK_PASS; ret = bpf_msg_cork_bytes(msg, *bytes); if (ret) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_strp.c b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c index dde3d5bec515..e9675c45d8ef 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_strp.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c @@ -2,7 +2,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -int verdict_max_size = 10000; +__u32 verdict_max_size = 10000; struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index 404124a93892..c7e2d4571a2b 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -80,7 +80,7 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph) { __u16 *iph16 = (__u16 *)iph; __u32 csum; - int i; + size_t i; iph->check = 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 8caf58be5818..ce2a9ae26088 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -89,7 +89,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp) struct vip vip = {}; int dport; __u32 csum = 0; - int i; + size_t i; if (iph + 1 > data_end) return XDP_DROP; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c index 67a77944ef29..12ad0ec91021 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c @@ -89,7 +89,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp, struct bpf_dynptr *xd struct vip vip = {}; int dport; __u32 csum = 0; - int i; + size_t i; __builtin_memset(eth_buffer, 0, sizeof(eth_buffer)); __builtin_memset(iph_buffer_tcp, 0, sizeof(iph_buffer_tcp)); diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c index 93267a68825b..e9b7bbff5c23 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -85,7 +85,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp) struct vip vip = {}; int dport; __u32 csum = 0; - int i; + size_t i; if (iph + 1 > data_end) return XDP_DROP; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index fad94e41cef9..85ef3c0a3e20 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -372,7 +372,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, next_iph_u16 = (__u16 *) iph; __pragma_loop_unroll_full - for (int i = 0; i < sizeof(struct iphdr) >> 1; i++) + for (size_t i = 0; i < sizeof(struct iphdr) >> 1; i++) csum += *next_iph_u16++; iph->check = ~((csum & 0xffff) + (csum >> 16)); if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr))) @@ -423,7 +423,7 @@ int send_icmp_reply(void *data, void *data_end) iph->check = 0; next_iph_u16 = (__u16 *) iph; __pragma_loop_unroll_full - for (int i = 0; i < sizeof(struct iphdr) >> 1; i++) + for (size_t i = 0; i < sizeof(struct iphdr) >> 1; i++) csum += *next_iph_u16++; iph->check = ~((csum & 0xffff) + (csum >> 16)); return swap_mac_and_send(data, data_end); diff --git a/tools/testing/selftests/bpf/progs/udp_limit.c b/tools/testing/selftests/bpf/progs/udp_limit.c index 4767451b59ac..af1b3195ea8a 100644 --- a/tools/testing/selftests/bpf/progs/udp_limit.c +++ b/tools/testing/selftests/bpf/progs/udp_limit.c @@ -50,7 +50,7 @@ int sock_release(struct bpf_sock *ctx) return 1; sk_storage = bpf_sk_storage_get(&sk_map, ctx, 0, 0); - if (!sk_storage || *sk_storage != 0xdeadbeef) + if (!sk_storage || *sk_storage != (int)0xdeadbeef) return 0; __sync_fetch_and_add(&invocations, 1); diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c index 44190efcdba2..f99957773c3a 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_multi.c +++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c @@ -20,13 +20,13 @@ __u64 uretprobe_multi_func_3_result = 0; __u64 uprobe_multi_sleep_result = 0; -int pid = 0; +__u32 pid = 0; int child_pid = 0; int child_tid = 0; int child_pid_usdt = 0; int child_tid_usdt = 0; -int expect_pid = 0; +__u32 expect_pid = 0; bool bad_pid_seen = false; bool bad_pid_seen_usdt = false; diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c b/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c index 8fbcd69fae22..017f1859ebe8 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c +++ b/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c @@ -3,6 +3,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include <stdbool.h> +#include <stddef.h> #include "bpf_kfuncs.h" #include "bpf_misc.h" @@ -10,8 +11,8 @@ char _license[] SEC("license") = "GPL"; int pid = 0; -int idx_entry = 0; -int idx_return = 0; +size_t idx_entry = 0; +size_t idx_return = 0; __u64 test_uprobe_cookie_entry[6]; __u64 test_uprobe_cookie_return[3]; diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_large.c b/tools/testing/selftests/bpf/progs/verifier_arena_large.c index f19e15400b3e..cb6cc9c4643a 100644 --- a/tools/testing/selftests/bpf/progs/verifier_arena_large.c +++ b/tools/testing/selftests/bpf/progs/verifier_arena_large.c @@ -86,10 +86,10 @@ int access_reserved(void *ctx) return 1; /* Try to dirty reserved memory. */ - for (i = 0; i < len && can_loop; i++) + for (i = 0; (size_t)i < len && can_loop; i++) *page = 0x5a; - for (i = 0; i < len && can_loop; i++) { + for (i = 0; (size_t)i < len && can_loop; i++) { page = (volatile char __arena *)(base + i * PAGE_SIZE); /* diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c index 75dd922e4e9f..72f9f8c23c93 100644 --- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -593,7 +593,7 @@ int loop_inside_iter_volatile_limit(const void *ctx) { struct bpf_iter_num it; int *v, sum = 0; - __u64 i = 0; + __s32 i = 0; bpf_iter_num_new(&it, 0, ARR2_SZ); while ((v = bpf_iter_num_next(&it))) { -- 2.51.0

2 months, 3 weeks

2
1
0 0

[PATCH] kvm, selftests: ioctl to handle MSIs injected from userspace as software-bypassing vLPIs

by Maximilian Dittgen

From: Maximilian Dittgen <mdittgen(a)amazon.de> At the moment, all MSIs injected from userspace using KVM_SIGNAL_MSI are processed as LPIs in software with a hypervisor trap and exit. To properly test GICv4 direct vLPI injection from KVM selftests, we write a KVM_DEBUG_GIC_MSI_SETUP ioctl that manually creates an IRQ routing table entry for the specified MSI, and populates ITS structures (device, collection, and interrupt translation table entries) to map the MSI to a vLPI. We then call GICv4 kvm_vgic_v4_set_forwarding to let the vLPI bypass hypervisor traps and inject directly to the vCPU. To demonstrate the use of this ioctl, we implement a -D flag to the vgic_lpi_stress.c selftest that runs the stress test using direct vLPI injection rather than software-emulated LPI handling. Signed-off-by: Maximilian Dittgen <mdittgen(a)amazon.de> --- arch/arm64/kvm/arm.c | 37 +++++ arch/arm64/kvm/vgic/vgic-its.c | 133 ++++++++++++++++++ arch/arm64/kvm/vgic/vgic.h | 2 + include/linux/irqchip/arm-gic-v3.h | 1 + include/uapi/linux/kvm.h | 15 ++ .../selftests/kvm/arm64/vgic_lpi_stress.c | 52 ++++++- 6 files changed, 238 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 5bf101c869c9..e18f5ff68274 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -46,6 +46,8 @@ #include <kvm/arm_pmu.h> #include <kvm/arm_psci.h> +#include <vgic/vgic.h> + #include "sys_regs.h" static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT; @@ -1927,6 +1929,41 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) return -EFAULT; return kvm_vm_ioctl_get_reg_writable_masks(kvm, &range); } + case KVM_DEBUG_GIC_MSI_SETUP: { + /* Define interrupt ID boundaries for input validation */ + #define GIC_LPI_OFFSET 8192 + #define GIC_LPI_MAX 65535 + #define SPI_INTID_MIN 32 + #define SPI_INTID_MAX 1019 + + struct kvm_debug_gic_msi_setup params; + struct kvm_vcpu *vcpu; + + if (copy_from_user(&params, argp, sizeof(params))) + return -EFAULT; + + /* validate vcpu_id is in range and exists */ + if (params.vcpu_id >= atomic_read(&kvm->online_vcpus)) + return -EINVAL; + + vcpu = kvm_get_vcpu(kvm, params.vcpu_id); + if (!vcpu) + return -EINVAL; + + /* validate vintid is in LPI range */ + if (params.vintid < GIC_LPI_OFFSET || params.vintid > GIC_LPI_MAX) + return -EINVAL; + + /* + * Validate host_irq is in safe range -- we use SPI range since + * selftests guests will have no shared peripheral devices + */ + if (params.host_irq < SPI_INTID_MIN || params.host_irq > SPI_INTID_MAX) + return -EINVAL; + + /* Mock single MSI for testing */ + return debug_gic_msi_setup_mock_msi(kvm, &params); + } default: return -EINVAL; } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 7368c13f16b7..46153ef5efcb 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2816,3 +2816,136 @@ int kvm_vgic_register_its_device(void) return kvm_register_device_ops(&kvm_arm_vgic_its_ops, KVM_DEV_TYPE_ARM_VGIC_ITS); } + +static struct vgic_its *vgic_get_its(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *irq_entry) +{ + struct kvm_msi msi = (struct kvm_msi) { + .address_lo = irq_entry->msi.address_lo, + .address_hi = irq_entry->msi.address_hi, + .data = irq_entry->msi.data, + .flags = irq_entry->msi.flags, + .devid = irq_entry->msi.devid, + }; + + return vgic_msi_to_its(kvm, &msi); +} + +/* + * debug_gic_msi_setup_mock_msi - manually set up vLPI direct injection infrastructure + * for an MSI upon userspace request. Used for testing vLPIs from selftests. + * + * Creates an IRQ routing entry mapping the specified MSI signature to a mock + * host IRQ, then populates ITS structures (device, collection, ITE) to establish + * the DevID/EventID to LPI translation. Finally enables GICv4 vLPI forwarding + * to bypass software emulation and inject interrupts directly to the vCPU. + * + * This function is intended solely for KVM selftests via KVM_DEBUG_GIC_MSI_SETUP. + * It uses mock host IRQs in the SPI range assuming no real hardware devices are + * present on a selftest guest. Using this interface in production will corrupt the + * IRQ routing table. + */ +int debug_gic_msi_setup_mock_msi(struct kvm *kvm, struct kvm_debug_gic_msi_setup *params) +{ + struct kvm_irq_routing_entry user_entry; + struct kvm_kernel_irq_routing_entry entry; + struct vgic_its *its; + struct its_device *device; + struct its_collection *collection; + struct its_ite *ite; + struct vgic_irq *irq; + struct kvm_vcpu *vcpu; + u64 doorbell_addr = GITS_BASE_GPA + GITS_TRANSLATER; + u32 device_id = params->device_id; + u32 event_id = params->event_id; + u32 coll_id = params->vcpu_id; + u32 lpi_nr = params->vintid; + gpa_t itt_addr = params->itt_addr; + int ret; + int host_irq = params->host_irq; + + // Unmap any existing vLPI on the mock host IRQ (remnants from prior mocks) + kvm_vgic_v4_unset_forwarding(kvm, host_irq); + + /* Create mock user IRQ routing entry using kvm_set_routing_entry function */ + memset(&user_entry, 0, sizeof(user_entry)); + user_entry.gsi = host_irq; + user_entry.type = KVM_IRQ_ROUTING_MSI; + user_entry.u.msi.address_lo = doorbell_addr & 0xFFFFFFFF; + user_entry.u.msi.address_hi = doorbell_addr >> 32; + user_entry.u.msi.data = event_id; + user_entry.u.msi.devid = device_id; + user_entry.flags = KVM_MSI_VALID_DEVID; + + /* Initialize kernel routing entry */ + memset(&entry, 0, sizeof(entry)); + + /* Use vgic-irqfd.c function to create entry */ + ret = kvm_set_routing_entry(kvm, &entry, &user_entry); + if (ret) + return ret; + + /* Now that we created an MSI -> ITS mapping, we can populate the ITS for this MSI */ + + /* Get ITS instance */ + its = vgic_get_its(kvm, &entry); + if (IS_ERR(its)) + return PTR_ERR(its); + + /* Enable ITS manually for testing, normally done by guest writing to GITS_CTLR register */ + its->enabled = true; + + /* Get target vCPU */ + vcpu = kvm_get_vcpu(kvm, params->vcpu_id); + if (!vcpu) + return -EINVAL; + + /* + * Enable this vLPIs for this vCPU manually for testing, normally + * done by guest writing GICR_CTLR + */ + atomic_set(&vcpu->arch.vgic_cpu.ctlr, GICR_CTLR_ENABLE_LPIS); + + mutex_lock(&its->its_lock); + + /* Create ITS device */ + device = vgic_its_alloc_device(its, device_id, itt_addr, 8); + if (IS_ERR(device)) { + ret = PTR_ERR(device); + goto unlock; + } + + /* Create collection mapped to inputted vcpu */ + ret = vgic_its_alloc_collection(its, &collection, coll_id); + if (ret) + goto unlock; + + collection->target_addr = params->vcpu_id; // Map to specified vcpu + + /* Create ITE */ + ite = vgic_its_alloc_ite(device, collection, event_id); + if (IS_ERR(ite)) { + ret = PTR_ERR(ite); + vgic_its_free_collection(its, coll_id); + goto unlock; + } + + /* Create LPI */ + irq = vgic_add_lpi(kvm, lpi_nr, vcpu); + if (IS_ERR(irq)) { + ret = PTR_ERR(irq); + its_free_ite(kvm, ite); + vgic_its_free_collection(its, coll_id); + goto unlock; + } + + ite->irq = irq; + mutex_unlock(&its->its_lock); + + /* Now that routing entry is initialized, call v4 forwarding setup */ + return kvm_vgic_v4_set_forwarding(kvm, host_irq, &entry); + +unlock: + mutex_unlock(&its->its_lock); + return ret; +} diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index de1c1d3261c3..8c8f1e963884 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -432,4 +432,6 @@ static inline bool vgic_is_v3(struct kvm *kvm) int vgic_its_debug_init(struct kvm_device *dev); void vgic_its_debug_destroy(struct kvm_device *dev); +int debug_gic_msi_setup_mock_msi(struct kvm *kvm, struct kvm_debug_gic_msi_setup *params); + #endif diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 70c0948f978e..76beac55cb69 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -378,6 +378,7 @@ #define GITS_CIDR3 0xfffc #define GITS_TRANSLATER 0x10040 +#define GITS_BASE_GPA 0x8000000ULL #define GITS_SGIR 0x20020 diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index f0f0d49d2544..a655bbb70e99 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1440,6 +1440,21 @@ struct kvm_enc_region { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) +/* + * Generate an IRQ routing entry and vLPI tables for userspace-sourced + * MSI, enabling direct vLPI injection testing from selftests + */ +#define KVM_DEBUG_GIC_MSI_SETUP _IOW(KVMIO, 0xf0, struct kvm_debug_gic_msi_setup) + +struct kvm_debug_gic_msi_setup { + __u32 device_id; + __u32 event_id; + __u32 vcpu_id; + __u32 vintid; + __u32 host_irq; + __u64 itt_addr; +}; + #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) diff --git a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c index fc4fe52fb6f8..8350665d9bdc 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c +++ b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c @@ -18,10 +18,14 @@ #include "ucall.h" #include "vgic.h" +#define KVM_DEBUG_GIC_MSI_SETUP _IOW(KVMIO, 0xf0, struct kvm_debug_gic_msi_setup) + #define TEST_MEMSLOT_INDEX 1 #define GIC_LPI_OFFSET 8192 +static bool vlpi_enabled; + static size_t nr_iterations = 1000; static vm_paddr_t gpa_base; @@ -220,6 +224,21 @@ static void setup_gic(void) its_fd = vgic_its_setup(vm); } +static int enable_msi_vlpi_injection(u32 device_id, u32 event_id, + u32 vcpu_id, u32 vintid, u32 host_irq) +{ + struct kvm_debug_gic_msi_setup params = { + .device_id = device_id, + .event_id = event_id, + .vcpu_id = vcpu_id, + .vintid = vintid, + .host_irq = host_irq, + .itt_addr = test_data.itt_tables + (device_id * SZ_64K) + }; + + return __vm_ioctl(vm, KVM_DEBUG_GIC_MSI_SETUP, &params); +} + static void signal_lpi(u32 device_id, u32 event_id) { vm_paddr_t db_addr = GITS_BASE_GPA + GITS_TRANSLATER; @@ -267,6 +286,30 @@ static void *vcpu_worker_thread(void *data) switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: + /* if flag is set, set direct injection mappings for MSIs */ + if (vlpi_enabled) { + u32 intid = GIC_LPI_OFFSET; + + for (u32 device_id = 0; device_id < test_data.nr_devices; + device_id++) { + for (u32 event_id = 0; event_id < test_data.nr_event_ids; + event_id++) { + + /* we mock host_irqs in the SPI interrupt range of + * 100-1020 since selftest guests have no hardware + * devices + */ + int ret = enable_msi_vlpi_injection(device_id, + event_id, vcpu->id, intid, + intid - GIC_LPI_OFFSET + 100); + TEST_ASSERT(ret == 0, "KVM_DEBUG_GIC_MSI_SETUP failed: %d", + ret); + + intid++; + } + } + } + pthread_barrier_wait(&test_setup_barrier); continue; case UCALL_DONE: @@ -362,7 +405,9 @@ static void destroy_vm(void) static void pr_usage(const char *name) { - pr_info("%s [-v NR_VCPUS] [-d NR_DEVICES] [-e NR_EVENTS] [-i ITERS] -h\n", name); + pr_info("%s -D [-v NR_VCPUS] [-d NR_DEVICES] [-e NR_EVENTS] [-i ITERS] -h\n", name); + pr_info(" -D:\tenable direct vLPI injection (default: %s)\n", + vlpi_enabled ? "true" : "false"); pr_info(" -v:\tnumber of vCPUs (default: %u)\n", test_data.nr_cpus); pr_info(" -d:\tnumber of devices (default: %u)\n", test_data.nr_devices); pr_info(" -e:\tnumber of event IDs per device (default: %u)\n", test_data.nr_event_ids); @@ -374,8 +419,11 @@ int main(int argc, char **argv) u32 nr_threads; int c; - while ((c = getopt(argc, argv, "hv:d:e:i:")) != -1) { + while ((c = getopt(argc, argv, "hDv:d:e:i:")) != -1) { switch (c) { + case 'D': + vlpi_enabled = true; + break; case 'v': test_data.nr_cpus = atoi(optarg); break; -- 2.50.1 (Apple Git-155) Amazon Web Services Development Center Germany GmbH Tamara-Danz-Str. 13 10243 Berlin Geschaeftsfuehrung: Christian Schlaeger Eingetragen am Amtsgericht Charlottenburg unter HRB 257764 B Sitz: Berlin Ust-ID: DE 365 538 597

2 months, 3 weeks

2
1
0 0

[PATCH net-next v2 0/6] netconsole: support automatic target recovery

by Andre Carvalho

This patchset introduces target resume capability to netconsole allowing it to recover targets when underlying low-level interface comes back online. The patchset starts by refactoring netconsole state representation in order to allow representing deactivated targets (targets that are disabled due to interfaces going down). It then modifies netconsole to handle NETDEV_UP events for such targets and setups netpoll. The patchset includes a selftest that validates netconsole target state transitions and that target is functional after resumed. Signed-off-by: Andre Carvalho <asantostc(a)gmail.com> --- Changes in v2: - Attempt to resume target in the same thread, instead of using workqueue . - Add wrapper around __netpoll_setup (patch 4). - Renamed resume_target to maybe_resume_target and moved conditionals to inside its implementation, keeping code more clear. - Verify that device addr matches target mac address when target was setup using mac. - Update selftest to cover targets bound by mac and interface name. - Fix typo in selftest comment and sort tests alphabetically in Makefile. - Link to v1: https://lore.kernel.org/r/20250909-netcons-retrigger-v1-0-3aea904926cf@gmai… --- Andre Carvalho (4): netconsole: convert 'enabled' flag to enum for clearer state management netpoll: add wrapper around __netpoll_setup with dev reference netconsole: resume previously deactivated target selftests: netconsole: validate target reactivation Breno Leitao (2): netconsole: add target_state enum netconsole: add STATE_DEACTIVATED to track targets disabled by low level drivers/net/netconsole.c | 102 +++++++++++++++------ include/linux/netpoll.h | 1 + net/core/netpoll.c | 20 ++++ tools/testing/selftests/drivers/net/Makefile | 1 + .../selftests/drivers/net/lib/sh/lib_netcons.sh | 30 +++++- .../selftests/drivers/net/netcons_resume.sh | 92 +++++++++++++++++++ 6 files changed, 216 insertions(+), 30 deletions(-) --- base-commit: 312e6f7676e63bbb9b81e5c68e580a9f776cc6f0 change-id: 20250816-netcons-retrigger-a4f547bfc867 Best regards, -- Andre Carvalho <asantostc(a)gmail.com>

2 months, 3 weeks

3
13
0 0

[PATCH v2 00/11] Start porting UML to nolibc

by Benjamin Berg

From: Benjamin Berg <benjamin.berg(a)intel.com> This patchset is an attempt to start a nolibc port of UML. The goal is to port UML to use nolibc in smaller chunks to make the switch more manageable. There are three parts to this patchset: * Two patches to use tools/include headers instead of kernel headers for userspace files. * A few nolibc fixes and a new NOLIBC_NO_STARTCODE compile flag for it * Finally nolibc build support for UML and switching two files while adding the appropriate support in nolibc itself. v1 of this patchset was https://lore.kernel.org/all/20250915071115.1429196-1-benjamin@sipsolutions.… Changes in v2: - add sys/uio.h and sys/ptrace.h to nolibc - Use NOLIBC_NO_RUNTIME to disable nolibc startup code - Fix out-of-tree build - various small improvements and cleanups Should the nolibc changes be merged separately or could everything go through the same branch? Also, what about tools/include/linux/compiler.h? It seems that was added for the tracing code, but it is not clear to me who might ACK that fix. Benjamin Benjamin Berg (11): tools compiler.h: fix __used definition um: use tools/include for user files tools/nolibc/stdio: remove perror if NOLIBC_IGNORE_ERRNO is set tools/nolibc/dirent: avoid errno in readdir_r tools/nolibc: use __fallthrough__ rather than fallthrough tools/nolibc: add option to disable runtime um: add infrastructure to build files using nolibc um: use nolibc for the --showconfig implementation tools/nolibc: add uio.h with readv and writev tools/nolibc: add ptrace support um: switch ptrace FP register access to nolibc arch/um/Makefile | 38 +++++++++++--- arch/um/include/shared/init.h | 2 +- arch/um/include/shared/os.h | 2 + arch/um/include/shared/user.h | 6 --- arch/um/kernel/Makefile | 2 +- arch/um/kernel/skas/stub.c | 1 + arch/um/kernel/skas/stub_exe.c | 4 +- arch/um/os-Linux/skas/process.c | 6 +-- arch/um/os-Linux/start_up.c | 4 +- arch/um/scripts/Makefile.rules | 10 +++- arch/x86/um/Makefile | 6 ++- arch/x86/um/os-Linux/Makefile | 5 +- arch/x86/um/os-Linux/registers.c | 16 ++---- arch/x86/um/user-offsets.c | 1 - tools/include/linux/compiler.h | 2 +- tools/include/nolibc/Makefile | 2 + tools/include/nolibc/arch-arm.h | 2 + tools/include/nolibc/arch-arm64.h | 2 + tools/include/nolibc/arch-loongarch.h | 2 + tools/include/nolibc/arch-m68k.h | 2 + tools/include/nolibc/arch-mips.h | 2 + tools/include/nolibc/arch-powerpc.h | 2 + tools/include/nolibc/arch-riscv.h | 2 + tools/include/nolibc/arch-s390.h | 2 + tools/include/nolibc/arch-sh.h | 2 + tools/include/nolibc/arch-sparc.h | 2 + tools/include/nolibc/arch-x86.h | 4 ++ tools/include/nolibc/compiler.h | 4 +- tools/include/nolibc/crt.h | 3 ++ tools/include/nolibc/dirent.h | 6 +-- tools/include/nolibc/nolibc.h | 2 + tools/include/nolibc/stackprotector.h | 2 + tools/include/nolibc/stdio.h | 2 + tools/include/nolibc/stdlib.h | 2 + tools/include/nolibc/sys.h | 3 +- tools/include/nolibc/sys/auxv.h | 3 ++ tools/include/nolibc/sys/ptrace.h | 52 ++++++++++++++++++++ tools/include/nolibc/sys/uio.h | 49 ++++++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 11 +++++ 39 files changed, 222 insertions(+), 48 deletions(-) create mode 100644 tools/include/nolibc/sys/ptrace.h create mode 100644 tools/include/nolibc/sys/uio.h -- 2.51.0

2 months, 3 weeks

8
34
0 0

[PATCH] Net: psock_tpacket: Fix null argument warning in walk_tx

by Wake Liu

The sendto() call in walk_tx() was passing NULL as the buffer argument, which can trigger a -Wnonnull warning with some compilers. Although the size is 0 and no data is actually sent, passing a null pointer is technically incorrect. This commit changes NULL to an empty string literal ("") to satisfy the non-null argument requirement and fix the compiler warning. Signed-off-by: Wake Liu <wakel(a)google.com> --- tools/testing/selftests/net/psock_tpacket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c index 221270cee3ea..0c24adbb292e 100644 --- a/tools/testing/selftests/net/psock_tpacket.c +++ b/tools/testing/selftests/net/psock_tpacket.c @@ -470,7 +470,7 @@ static void walk_tx(int sock, struct ring *ring) bug_on(total_packets != 0); - ret = sendto(sock, NULL, 0, 0, NULL, 0); + ret = sendto(sock, "", 0, 0, NULL, 0); if (ret == -1) { perror("sendto"); exit(1); -- 2.51.0.534.gc79095c0ca-goog

2 months, 3 weeks

2
1
0 0

[PATCH] selftests/kvm: remove stale TODO in xapic_state_test

by Sukrut Heroorkar

The TODO about using the number of vCPUs instead of vcpu.id + 1 was already addressed by commit 376bc1b458c9 ("KVM: selftests: Don't assume vcpu->id is '0' in xAPIC state test"). The comment is now stale and can be removed. Signed-off-by: Sukrut Heroorkar <hsukrut3(a)gmail.com> --- tools/testing/selftests/kvm/x86/xapic_state_test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/x86/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c index fdebff1165c7..3b4814c55722 100644 --- a/tools/testing/selftests/kvm/x86/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_state_test.c @@ -120,8 +120,8 @@ static void test_icr(struct xapic_vcpu *x) __test_icr(x, icr | i); /* - * Send all flavors of IPIs to non-existent vCPUs. TODO: use number of - * vCPUs, not vcpu.id + 1. Arbitrarily use vector 0xff. + * Send all flavors of IPIs to non-existent vCPUs. Arbitrarily use + * vector 0xff. */ icr = APIC_INT_ASSERT | 0xff; for (i = 0; i < 0xff; i++) { -- 2.43.0

2 months, 3 weeks

2
1
0 0

[PATCH] selftests/iommu: prevent use of uninitialized variable

by Alessandro Zanni

Fix to avoid the usage of the `res` variable uninitialized in the following macro expansions. It solves the following warning: In function ‘iommufd_viommu_vdevice_alloc’, inlined from ‘wrapper_iommufd_viommu_vdevice_alloc’ at iommufd.c:2889:1: ../kselftest_harness.h:760:12: warning: ‘ret’ may be used uninitialized [-Wmaybe-uninitialized] 760 | if (!(__exp _t __seen)) { \ | ^ ../kselftest_harness.h:513:9: note: in expansion of macro ‘__EXPECT’ 513 | __EXPECT(expected, #expected, seen, #seen, ==, 1) | ^~~~~~~~ iommufd_utils.h:1057:9: note: in expansion of macro ‘ASSERT_EQ’ 1057 | ASSERT_EQ(0, _test_cmd_trigger_vevents(self->fd, dev_id, nvevents)) | ^~~~~~~~~ iommufd.c:2924:17: note: in expansion of macro ‘test_cmd_trigger_vevents’ 2924 | test_cmd_trigger_vevents(dev_id, 3); | ^~~~~~~~~~~~~~~~~~~~~~~~ The issue can be reproduced, building the tests, with the command: make -C tools/testing/selftests TARGETS=iommu Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- tools/testing/selftests/iommu/iommufd_utils.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 3c3e08b8c90e..4ae0fcc4f871 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -1042,7 +1042,7 @@ static int _test_cmd_trigger_vevents(int fd, __u32 dev_id, __u32 nvevents) .dev_id = dev_id, }, }; - int ret; + int ret = 0; while (nvevents--) { ret = ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_VEVENT), -- 2.43.0

2 months, 3 weeks

3
3
0 0

[PATCH v3 0/9] rust: use `kernel::{fmt,prelude::fmt!}`

by Tamir Duberstein

This is series 2a/5 of the migration to `core::ffi::CStr`[0]. 20250704-core-cstr-prepare-v1-0-a91524037783(a)gmail.com. This series depends on the prior series[0] and is intended to go through the rust tree to reduce the number of release cycles required to complete the work. Subsystem maintainers: I would appreciate your `Acked-by`s so that this can be taken through Miguel's tree (where the other series must go). [0] https://lore.kernel.org/all/20250704-core-cstr-prepare-v1-0-a91524037783@gm… Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v3: - Add a patch to address new code in device.rs. - Drop incorrectly applied Acked-by tags from Danilo. - Link to v2: https://lore.kernel.org/r/20250719-core-cstr-fanout-1-v2-0-1ab5ba189c6e@gma… Changes in v2: - Rebase on rust-next. - Drop pin-init patch, which is no longer needed. - Link to v1: https://lore.kernel.org/r/20250709-core-cstr-fanout-1-v1-0-64308e7203fc@gma… --- Tamir Duberstein (9): gpu: nova-core: use `kernel::{fmt,prelude::fmt!}` rust: alloc: use `kernel::{fmt,prelude::fmt!}` rust: block: use `kernel::{fmt,prelude::fmt!}` rust: device: use `kernel::{fmt,prelude::fmt!}` rust: file: use `kernel::{fmt,prelude::fmt!}` rust: kunit: use `kernel::{fmt,prelude::fmt!}` rust: seq_file: use `kernel::{fmt,prelude::fmt!}` rust: sync: use `kernel::{fmt,prelude::fmt!}` rust: device: use `kernel::{fmt,prelude::fmt!}` drivers/block/rnull.rs | 2 +- drivers/gpu/nova-core/gpu.rs | 3 +-- drivers/gpu/nova-core/regs/macros.rs | 6 +++--- rust/kernel/alloc/kbox.rs | 2 +- rust/kernel/alloc/kvec.rs | 2 +- rust/kernel/alloc/kvec/errors.rs | 2 +- rust/kernel/block/mq.rs | 2 +- rust/kernel/block/mq/gen_disk.rs | 2 +- rust/kernel/block/mq/raw_writer.rs | 3 +-- rust/kernel/device.rs | 6 +++--- rust/kernel/device/property.rs | 23 ++++++++++++----------- rust/kernel/fs/file.rs | 5 +++-- rust/kernel/kunit.rs | 8 ++++---- rust/kernel/seq_file.rs | 6 +++--- rust/kernel/sync/arc.rs | 2 +- scripts/rustdoc_test_gen.rs | 2 +- 16 files changed, 38 insertions(+), 38 deletions(-) --- base-commit: 8f5ae30d69d7543eee0d70083daf4de8fe15d585 change-id: 20250709-core-cstr-fanout-1-f20611832272 Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

2 months, 3 weeks

3
12
0 0

[PATCH net-next] selftests: rtnetlink: correct error message in rtnetlink.sh fou test

by Alok Tiwari

The rtnetlink FOU selftest prints an incorrect string: "FAIL: fou"s. Change it to the intended "FAIL: fou" by removing a stray character in the end_test string of the test. Signed-off-by: Alok Tiwari <alok.a.tiwari(a)oracle.com> --- tools/testing/selftests/net/rtnetlink.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index d6c00efeb664..24bba74c77ee 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -519,7 +519,7 @@ kci_test_encap_fou() run_cmd_fail ip -netns "$testns" fou del port 9999 run_cmd ip -netns "$testns" fou del port 7777 if [ $ret -ne 0 ]; then - end_test "FAIL: fou"s + end_test "FAIL: fou" return 1 fi -- 2.50.1

2 months, 3 weeks

3
2
0 0

Thematic Funds Letter Of Intent

by Al Sayyid Sultan

To: linux-kselftest(a)vger.kernel.org Date: 24-09-2025 Thematic Funds Letter Of Intent It's a pleasure to connect with you Having been referred to your investment by my team, we would be honored to review your available investment projects for onward referral to my principal investors who can allocate capital for the financing of it. kindly advise at your convenience Best Regards, Respectfully, Al Sayyid Sultan Yarub Al Busaidi Director

2 months, 3 weeks

1
0
0 0

[PATCH] selftest:sud_test: Fix "usigned" -> "unsigned"

by Sidharth Seela

Trivial fix to a spelling mistake in comments. Signed-off-by: Sidharth Seela <sidharthseela(a)gmail.com> -- diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index 2eb2c06303f2..6b846f5c1fa6 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -140,7 +140,7 @@ TEST(bad_prctl_param) prctl_invalid(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, 1, -1L, &sel, EINVAL); /* - * Allowed range overflows usigned long + * Allowed range overflows unsigned long */ prctl_invalid(_metadata, PR_SYS_DISPATCH_EXCLUSIVE_ON, -1L, 0x1, &sel, EINVAL); -- 2.39.5 (Apple Git-154)

2 months, 3 weeks

1
0
0 0

[PATCHv2 net 1/2] bonding: fix xfrm offload feature setup on active-backup mode

by Hangbin Liu

The active-backup bonding mode supports XFRM ESP offload. However, when a bond is added using command like `ip link add bond0 type bond mode 1 miimon 100`, the `ethtool -k` command shows that the XFRM ESP offload is disabled. This occurs because, in bond_newlink(), we change bond link first and register bond device later. So the XFRM feature update in bond_option_mode_set() is not called as the bond device is not yet registered, leading to the offload feature not being set successfully. To resolve this issue, we can modify the code order in bond_newlink() to ensure that the bond device is registered first before changing the bond link parameters. This change will allow the XFRM ESP offload feature to be correctly enabled. Fixes: 007ab5345545 ("bonding: fix feature flag setting at init time") Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- v2: rebase to latest net, no code update --- drivers/net/bonding/bond_main.c | 2 +- drivers/net/bonding/bond_netlink.c | 16 +++++++++------- include/net/bonding.h | 1 + 3 files changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 57be04f6cb11..f4f0feddd9fa 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4411,7 +4411,7 @@ void bond_work_init_all(struct bonding *bond) INIT_DELAYED_WORK(&bond->slave_arr_work, bond_slave_arr_handler); } -static void bond_work_cancel_all(struct bonding *bond) +void bond_work_cancel_all(struct bonding *bond) { cancel_delayed_work_sync(&bond->mii_work); cancel_delayed_work_sync(&bond->arp_work); diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 57fff2421f1b..7a9d73ec8e91 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -579,20 +579,22 @@ static int bond_newlink(struct net_device *bond_dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct bonding *bond = netdev_priv(bond_dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; int err; - err = bond_changelink(bond_dev, tb, data, extack); - if (err < 0) + err = register_netdevice(bond_dev); + if (err) return err; - err = register_netdevice(bond_dev); - if (!err) { - struct bonding *bond = netdev_priv(bond_dev); + netif_carrier_off(bond_dev); + bond_work_init_all(bond); - netif_carrier_off(bond_dev); - bond_work_init_all(bond); + err = bond_changelink(bond_dev, tb, data, extack); + if (err) { + bond_work_cancel_all(bond); + unregister_netdevice(bond_dev); } return err; diff --git a/include/net/bonding.h b/include/net/bonding.h index e06f0d63b2c1..bd56ad976cfb 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -711,6 +711,7 @@ struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); void bond_work_init_all(struct bonding *bond); +void bond_work_cancel_all(struct bonding *bond); #ifdef CONFIG_PROC_FS void bond_create_proc_entry(struct bonding *bond); -- 2.50.1

2 months, 3 weeks

2
3
0 0

[PATCH v3 0/5] platform/chrome: Fix a possible UAF via revocable

by Tzung-Bi Shih

This is a follow-up series of [1]. It tries to fix a possible UAF in the fops of cros_ec_chardev after the underlying protocol device has gone by using revocable. The 1st patch introduces the revocable which is an implementation of ideas from the talk [2]. The 2nd and 3rd patches add test cases for revocable in Kunit and selftest. The 4th patch converts existing protocol devices to resource providers of cros_ec_device. The 5th patch converts cros_ec_chardev to a resource consumer of cros_ec_device to fix the UAF. [1] https://lore.kernel.org/chrome-platform/20250721044456.2736300-6-tzungbi@ke… [2] https://lpc.events/event/17/contributions/1627/ Cc: Laurent Pinchart <laurent.pinchart(a)ideasonboard.com> Cc: Bartosz Golaszewski <bartosz.golaszewski(a)linaro.org> Cc: Wolfram Sang <wsa+renesas(a)sang-engineering.com> v3: - Rebase onto https://lore.kernel.org/chrome-platform/20250828083601.856083-1-tzungbi@ker… and next-20250912. - Change the 4th patch accordingly. v2: https://lore.kernel.org/chrome-platform/20250820081645.847919-1-tzungbi@ker… - Rename "ref_proxy" -> "revocable". - Add test cases in Kunit and selftest. v1: https://lore.kernel.org/chrome-platform/20250814091020.1302888-1-tzungbi@ke… Tzung-Bi Shih (5): revocable: Revocable resource management revocable: Add Kunit test cases selftests: revocable: Add kselftest cases platform/chrome: Protect cros_ec_device lifecycle with revocable platform/chrome: cros_ec_chardev: Consume cros_ec_device via revocable .../driver-api/driver-model/index.rst | 1 + .../driver-api/driver-model/revocable.rst | 151 ++++++++++++ MAINTAINERS | 9 + drivers/base/Kconfig | 8 + drivers/base/Makefile | 5 +- drivers/base/revocable.c | 229 ++++++++++++++++++ drivers/base/revocable_test.c | 110 +++++++++ drivers/platform/chrome/cros_ec.c | 5 + drivers/platform/chrome/cros_ec_chardev.c | 124 +++++++--- include/linux/platform_data/cros_ec_proto.h | 4 + include/linux/revocable.h | 37 +++ tools/testing/selftests/Makefile | 1 + .../selftests/drivers/base/revocable/Makefile | 7 + .../drivers/base/revocable/revocable_test.c | 116 +++++++++ .../drivers/base/revocable/test-revocable.sh | 39 +++ .../base/revocable/test_modules/Makefile | 10 + .../revocable/test_modules/revocable_test.c | 188 ++++++++++++++ 17 files changed, 1003 insertions(+), 41 deletions(-) create mode 100644 Documentation/driver-api/driver-model/revocable.rst create mode 100644 drivers/base/revocable.c create mode 100644 drivers/base/revocable_test.c create mode 100644 include/linux/revocable.h create mode 100644 tools/testing/selftests/drivers/base/revocable/Makefile create mode 100644 tools/testing/selftests/drivers/base/revocable/revocable_test.c create mode 100755 tools/testing/selftests/drivers/base/revocable/test-revocable.sh create mode 100644 tools/testing/selftests/drivers/base/revocable/test_modules/Makefile create mode 100644 tools/testing/selftests/drivers/base/revocable/test_modules/revocable_test.c -- 2.51.0.384.g4c02a37b29-goog

2 months, 3 weeks

11
39
0 0

[PATCH v2] mm/memory-failure: Support disabling soft offline for HugeTLB pages

by Kyle Meyer

Soft offlining a HugeTLB page reduces the HugeTLB page pool. Commit 56374430c5dfc ("mm/memory-failure: userspace controls soft-offlining pages") introduced the following sysctl interface to control soft offline: /proc/sys/vm/enable_soft_offline The interface does not distinguish between page types: 0 - Soft offline is disabled 1 - Soft offline is enabled Convert enable_soft_offline to a bitmask and support disabling soft offline for HugeTLB pages: Bits: 0 - Enable soft offline 1 - Disable soft offline for HugeTLB pages Supported values: 0 - Soft offline is disabled 1 - Soft offline is enabled 3 - Soft offline is enabled (disabled for HugeTLB pages) Existing behavior is preserved. Update documentation and HugeTLB soft offline self tests. Reported-by: Shawn Fan <shawn.fan(a)intel.com> Suggested-by: Tony Luck <tony.luck(a)intel.com> Signed-off-by: Kyle Meyer <kyle.meyer(a)hpe.com> --- Tony's patch: * https://lore.kernel.org/all/20250904155720.22149-1-tony.luck@intel.com v1: * https://lore.kernel.org/all/aMGkAI3zKlVsO0S2@hpe.com v1 -> v2: * Make the interface extensible, as suggested by David. * Preserve existing behavior, as suggested by Jiaqi and David. Why clear errno in self tests? madvise() does not set errno when it's successful and errno is set by madvise() during test_soft_offline_common(3) causing test_soft_offline_common(1) to fail: # Test soft-offline when enabled_soft_offline=1 # Hugepagesize is 1048576kB # enable_soft_offline => 1 # Before MADV_SOFT_OFFLINE nr_hugepages=7 # Allocated 0x80000000 bytes of hugetlb pages # MADV_SOFT_OFFLINE 0x7fd600000000 ret=0, errno=95 # MADV_SOFT_OFFLINE should ret 0 # After MADV_SOFT_OFFLINE nr_hugepages=6 not ok 2 Test soft-offline when enabled_soft_offline=1 --- .../ABI/testing/sysfs-memory-page-offline | 3 ++ Documentation/admin-guide/sysctl/vm.rst | 28 ++++++++++++++++--- mm/memory-failure.c | 17 +++++++++-- .../selftests/mm/hugetlb-soft-offline.c | 19 ++++++++++--- 4 files changed, 56 insertions(+), 11 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-memory-page-offline b/Documentation/ABI/testing/sysfs-memory-page-offline index 00f4e35f916f..d3f05ed6605e 100644 --- a/Documentation/ABI/testing/sysfs-memory-page-offline +++ b/Documentation/ABI/testing/sysfs-memory-page-offline @@ -20,6 +20,9 @@ Description: number, or a error when the offlining failed. Reading the file is not allowed. + Soft-offline can be controlled via sysctl, see: + Documentation/admin-guide/sysctl/vm.rst + What: /sys/devices/system/memory/hard_offline_page Date: Sep 2009 KernelVersion: 2.6.33 diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 4d71211fdad8..ace73480eb9d 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -309,19 +309,39 @@ physical memory) vs performance / capacity implications in transparent and HugeTLB cases. For all architectures, enable_soft_offline controls whether to soft offline -memory pages. When set to 1, kernel attempts to soft offline the pages -whenever it thinks needed. When set to 0, kernel returns EOPNOTSUPP to -the request to soft offline the pages. Its default value is 1. +memory pages. + +enable_soft_offline is a bitmask: + +Bits:: + + 0 - Enable soft offline + 1 - Disable soft offline for HugeTLB pages + +Supported values:: + + 0 - Soft offline is disabled + 1 - Soft offline is enabled + 3 - Soft offline is enabled (disabled for HugeTLB pages) + +The default value is 1. + +If soft offline is disabled for the requested page type, EOPNOTSUPP is returned. It is worth mentioning that after setting enable_soft_offline to 0, the following requests to soft offline pages will not be performed: +- Request to soft offline from sysfs (soft_offline_page). + - Request to soft offline pages from RAS Correctable Errors Collector. -- On ARM, the request to soft offline pages from GHES driver. +- On ARM and X86, the request to soft offline pages from GHES driver. - On PARISC, the request to soft offline pages from Page Deallocation Table. +Note: + Soft offlining a HugeTLB page reduces the HugeTLB page pool. + extfrag_threshold ================= diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fc30ca4804bf..0ad9ae11d9e8 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -64,11 +64,14 @@ #include "internal.h" #include "ras/ras_event.h" +#define SOFT_OFFLINE_ENABLED BIT(0) +#define SOFT_OFFLINE_SKIP_HUGETLB BIT(1) + static int sysctl_memory_failure_early_kill __read_mostly; static int sysctl_memory_failure_recovery __read_mostly = 1; -static int sysctl_enable_soft_offline __read_mostly = 1; +static int sysctl_enable_soft_offline __read_mostly = SOFT_OFFLINE_ENABLED; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); @@ -150,7 +153,7 @@ static const struct ctl_table memory_failure_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = SYSCTL_THREE, } }; @@ -2799,12 +2802,20 @@ int soft_offline_page(unsigned long pfn, int flags) return -EIO; } - if (!sysctl_enable_soft_offline) { + if (!(sysctl_enable_soft_offline & SOFT_OFFLINE_ENABLED)) { pr_info_once("disabled by /proc/sys/vm/enable_soft_offline\n"); put_ref_page(pfn, flags); return -EOPNOTSUPP; } + if (sysctl_enable_soft_offline & SOFT_OFFLINE_SKIP_HUGETLB) { + if (folio_test_hugetlb(pfn_folio(pfn))) { + pr_info_once("disabled for HugeTLB pages by /proc/sys/vm/enable_soft_offline\n"); + put_ref_page(pfn, flags); + return -EOPNOTSUPP; + } + } + mutex_lock(&mf_mutex); if (PageHWPoison(page)) { diff --git a/tools/testing/selftests/mm/hugetlb-soft-offline.c b/tools/testing/selftests/mm/hugetlb-soft-offline.c index f086f0e04756..b87c8778cadf 100644 --- a/tools/testing/selftests/mm/hugetlb-soft-offline.c +++ b/tools/testing/selftests/mm/hugetlb-soft-offline.c @@ -5,6 +5,8 @@ * offlining failed with EOPNOTSUPP. * - if enable_soft_offline = 1, a hugepage should be dissolved and * nr_hugepages/free_hugepages should be reduced by 1. + * - if enable_soft_offline = 3, hugepages should stay intact and soft + * offlining failed with EOPNOTSUPP. * * Before running, make sure more than 2 hugepages of default_hugepagesz * are allocated. For example, if /proc/meminfo/Hugepagesize is 2048kB: @@ -32,6 +34,9 @@ #define EPREFIX " !!! " +#define SOFT_OFFLINE_ENABLED (1 << 0) +#define SOFT_OFFLINE_SKIP_HUGETLB (1 << 1) + static int do_soft_offline(int fd, size_t len, int expect_errno) { char *filemap = NULL; @@ -56,6 +61,7 @@ static int do_soft_offline(int fd, size_t len, int expect_errno) ksft_print_msg("Allocated %#lx bytes of hugetlb pages\n", len); hwp_addr = filemap + len / 2; + errno = 0; ret = madvise(hwp_addr, pagesize, MADV_SOFT_OFFLINE); ksft_print_msg("MADV_SOFT_OFFLINE %p ret=%d, errno=%d\n", hwp_addr, ret, errno); @@ -83,7 +89,7 @@ static int set_enable_soft_offline(int value) char cmd[256] = {0}; FILE *cmdfile = NULL; - if (value != 0 && value != 1) + if (value < 0 || value > 3) return -EINVAL; sprintf(cmd, "echo %d > /proc/sys/vm/enable_soft_offline", value); @@ -155,13 +161,17 @@ static int create_hugetlbfs_file(struct statfs *file_stat) static void test_soft_offline_common(int enable_soft_offline) { int fd; - int expect_errno = enable_soft_offline ? 0 : EOPNOTSUPP; + int expect_errno = 0; struct statfs file_stat; unsigned long hugepagesize_kb = 0; unsigned long nr_hugepages_before = 0; unsigned long nr_hugepages_after = 0; int ret; + if (!(enable_soft_offline & SOFT_OFFLINE_ENABLED) || + (enable_soft_offline & SOFT_OFFLINE_SKIP_HUGETLB)) + expect_errno = EOPNOTSUPP; + ksft_print_msg("Test soft-offline when enabled_soft_offline=%d\n", enable_soft_offline); @@ -198,7 +208,7 @@ static void test_soft_offline_common(int enable_soft_offline) // No need for the hugetlbfs file from now on. close(fd); - if (enable_soft_offline) { + if (expect_errno == 0) { if (nr_hugepages_before != nr_hugepages_after + 1) { ksft_test_result_fail("MADV_SOFT_OFFLINE should reduced 1 hugepage\n"); return; @@ -219,8 +229,9 @@ static void test_soft_offline_common(int enable_soft_offline) int main(int argc, char **argv) { ksft_print_header(); - ksft_set_plan(2); + ksft_set_plan(3); + test_soft_offline_common(3); test_soft_offline_common(1); test_soft_offline_common(0); -- 2.51.0

2 months, 3 weeks

8
20
0 0

[RFC PATCH v2 00/35] AMD: Add Secure AVIC KVM selftests

by Neeraj Upadhyay

This series adds KVM selftests for Secure AVIC. The Secure AVIC KVM support patch series is at: https://lore.kernel.org/kvm/20250923050317.205482-1-Neeraj.Upadhyay@amd.com/ Git tree is available at: https://github.com/AMDESE/linux-kvm/tree/savic-host-latest Changes since v1: v1: https://lore.kernel.org/lkml/20250228093024.114983-1-Neeraj.Upadhyay@amd.co… - Drop Secure AVIC APIC regs test as it relied on KVM_GET_LAPIC, KVM_SET_LAPIC IOCTLS. Since commit f65916a ("KVM: TDX: Force APICv active for TDX guest"), these IOCTLs do not work for protected APIC guests. - Rebase on top of latest kvm next tree. - Add detailed commit logs. - Clean up the instruction decoder. Neeraj Upadhyay (29): KVM: selftests: Return an unused GHCB from the pool KVM: selftests: Align GHCB entry struct to page size KVM: selftests: Add #VC exception handler with error code support KVM: selftests: Add MSR access support for SEV-ES guests KVM: selftests: Skip guest memory checks for APIC MMIO mapping KVM: selftests: Add x86 instruction decoding library KVM: selftests: Adapt instruction decoder library for userspace KVM: selftests: Restrict instruction decoder to x86_64 only KVM: selftests: Remove unneeded functions from instruction decoder KVM: selftests: Fix missing definitions in x86 instruction decoder KVM: selftests: Change pt_regs to ex_regs for selftest use KVM: selftests: Add compilation for instruction decoder library KVM: selftests: Add MMIO #VC exception handling for SEV-ES guests KVM: selftests: Add instruction decoding for movabs instructions KVM: selftests: Add SEV guest support in xapic_state_test KVM: selftests: Add x2apic mode testing in xapic_ipi_test KVM: selftests: Add SEV VM support in xapic_ipi_test KVM: selftests: Add Secure AVIC library KVM: selftests: Add #VC handler for unaccelerated Secure AVIC MSRs KVM: selftests: Add IPI handling support for Secure AVIC KVM: selftests: Add args parameter to kvm_arch_vm_post_create() KVM: selftests: Add GHCB call for SAVIC backing page notification KVM: selftests: Add Secure AVIC mode to xapic_ipi_test KVM: selftests: Add test to verify APIC MSR accesses for SAVIC guest KVM: selftests: Extend savic_test with idle halt testing KVM: selftests: Add IOAPIC tests for Secure AVIC KVM: selftests: Add cross-vCPU IPI testing for SAVIC guests KVM: selftests: Add NMI test for SAVIC guests KVM: selftests: Add MSI injection test for SAVIC Peter Gonda (6): Add GHCB with setters and getters Add arch specific additional guest pages Add vm_vaddr_alloc_pages_shared() Add GHCB allocations and helpers Add is_sev_enabled() helpers Add ability for SEV-ES guests to use ucalls via GHCB tools/arch/x86/include/asm/msr-index.h | 4 +- tools/testing/selftests/kvm/.gitignore | 3 +- tools/testing/selftests/kvm/Makefile.kvm | 14 +- .../testing/selftests/kvm/arm64/set_id_regs.c | 2 +- .../testing/selftests/kvm/include/kvm_util.h | 14 +- .../testing/selftests/kvm/include/x86/apic.h | 57 + .../selftests/kvm/include/x86/insn-eval.h | 48 + .../selftests/kvm/include/x86/processor.h | 8 + .../testing/selftests/kvm/include/x86/savic.h | 25 + tools/testing/selftests/kvm/include/x86/sev.h | 29 + tools/testing/selftests/kvm/include/x86/svm.h | 109 ++ tools/testing/selftests/kvm/lib/kvm_util.c | 109 +- .../testing/selftests/kvm/lib/x86/handlers.S | 4 +- .../testing/selftests/kvm/lib/x86/insn-eval.c | 1238 +++++++++++++++++ .../testing/selftests/kvm/lib/x86/processor.c | 24 +- tools/testing/selftests/kvm/lib/x86/savic.c | 488 +++++++ tools/testing/selftests/kvm/lib/x86/sev.c | 581 +++++++- tools/testing/selftests/kvm/lib/x86/ucall.c | 18 + tools/testing/selftests/kvm/s390/cmma_test.c | 2 +- tools/testing/selftests/kvm/x86/savic_test.c | 1171 ++++++++++++++++ .../selftests/kvm/x86/sev_smoke_test.c | 40 +- .../selftests/kvm/x86/xapic_ipi_test.c | 183 ++- .../selftests/kvm/x86/xapic_state_test.c | 117 +- 23 files changed, 4192 insertions(+), 96 deletions(-) create mode 100644 tools/testing/selftests/kvm/include/x86/insn-eval.h create mode 100644 tools/testing/selftests/kvm/include/x86/savic.h create mode 100644 tools/testing/selftests/kvm/lib/x86/insn-eval.c create mode 100644 tools/testing/selftests/kvm/lib/x86/savic.c create mode 100644 tools/testing/selftests/kvm/x86/savic_test.c base-commit: a6ad54137af92535cfe32e19e5f3bc1bb7dbd383 -- 2.34.1

2 months, 3 weeks

1
35
0 0

[PATCH] selftests: Fix Makefile to run targets even the ones in SKIP_TARGETS

by I Viswanath

With the current Makefile, if the user tries something like make TARGETS="bpf mm" only mm is run and bpf is skipped, which is not intentional. `bpf` and `sched_ext` are always filtered out even when TARGETS is set explicitly due to how SKIP_TARGETS is implemented. This default skip exists because these tests require newer LLVM/Clang versions that may not be available on all systems. Fix the SKIP_TARGETS logic so that bpf and sched_ext remain skipped when TARGETS is taken from the Makefile but are included when the user specifies them explicitly. Signed-off-by: I Viswanath <viswanathiyyappan(a)gmail.com> --- make --silent summary=1 TARGETS="bpf size" kselftest make[3]: Entering directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/bpf' Auto-detecting system features: ... llvm: [ OFF ] Makefile:127: tools/build/Makefile.feature: No such file or directory make[4]: *** No rule to make target 'tools/build/Makefile.feature'. Stop. make[3]: *** [Makefile:344: /home/user/kernel-dev/linux-next/tools/testing/selftests/bpf/tools/sbin/bpftool] Error 2 make[3]: Leaving directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/bpf' make[3]: Nothing to be done for 'all'. make[3]: Entering directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/bpf' Auto-detecting system features: ... llvm: [ OFF ] Makefile:127: tools/build/Makefile.feature: No such file or directory make[4]: *** No rule to make target 'tools/build/Makefile.feature'. Stop. make[3]: *** [Makefile:344: /home/user/kernel-dev/linux-next/tools/testing/selftests/bpf/tools/sbin/bpftool] Error 2 make[3]: Leaving directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/bpf' TAP version 13 1..1 # selftests: size: get_size ok 1 selftests: size: get_size make --silent summary=1 kselftest (bpf is between arm64 and breakpoints in TARGETS) make[3]: Nothing to be done for 'all'. make[3]: Entering directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/alsa' make[3]: Nothing to be done for 'all'. make[3]: Leaving directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/alsa' make[3]: Entering directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/amd-pstate' make[3]: Nothing to be done for 'all'. make[3]: Leaving directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/amd-pstate' make[3]: Entering directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/arm64' make[3]: Leaving directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/arm64' make[3]: Entering directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/breakpoints' make[3]: Nothing to be done for 'all'. make[3]: Leaving directory '/home/user/kernel-dev/linux-next/tools/testing/selftests/breakpoints' make[3]: Nothing to be done for 'all'. tools/testing/selftests/Makefile | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index babed7b1c2d1..c6cedb09c372 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -145,7 +145,10 @@ endif # User can optionally provide a TARGETS skiplist. By default we skip # targets using BPF since it has cutting edge build time dependencies # which require more effort to install. -SKIP_TARGETS ?= bpf sched_ext +ifeq ($(origin TARGETS), file) + SKIP_TARGETS ?= bpf sched_ext +endif + ifneq ($(SKIP_TARGETS),) TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS)) override TARGETS := $(TMP) -- 2.47.3

2 months, 3 weeks

2
1
0 0

[PATCH net-next 0/6] mptcp: pm: netlink: announce server-side flag

by Matthieu Baerts (NGI0)

Now that the 'flags' attribute is used, it seems interesting to add one flag for 'server-side', a boolean value. Here are a few patches related to the 'server-side' attribute: - Patch 1: only announce this attribute on the server side. - Patch 2: announce the 'server-side' flag when this is the case. - Patch 3: deprecate the 'server-side' attribute. - Patch 4: use the 'server-side' flag in the selftests. - Patches 5, 6: small cleanups when working on code around. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Matthieu Baerts (NGI0) (6): mptcp: pm: netlink: only add server-side attr when true mptcp: pm: netlink: announce server-side flag mptcp: pm: netlink: deprecate server-side attribute selftests: mptcp: pm: get server-side flag mptcp: use _BITUL() instead of (1 << x) mptcp: remove unused returned value of check_data_fin Documentation/netlink/specs/mptcp_pm.yaml | 5 +++-- include/uapi/linux/mptcp.h | 11 ++++++----- include/uapi/linux/mptcp_pm.h | 4 ++-- net/mptcp/pm_netlink.c | 9 +++++++-- net/mptcp/protocol.c | 5 +---- tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 9 ++++++++- tools/testing/selftests/net/mptcp/userspace_pm.sh | 2 +- 7 files changed, 28 insertions(+), 17 deletions(-) --- base-commit: 315f423be0d1ebe720d8fd4fa6bed68586b13d34 change-id: 20250916-net-next-mptcp-server-side-flag-0f002418946d Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

2 months, 3 weeks

3
8
0 0

[PATCH net-next v3] selftests: forwarding: Reorder (ar)ping arguments to obey POSIX getopt

by David Yang

Quoted from musl wiki: GNU getopt permutes argv to pull options to the front, ahead of non-option arguments. musl and the POSIX standard getopt stop processing options at the first non-option argument with no permutation. Thus these scripts stop working on musl since non-option arguments for tools using getopt() (in this case, (ar)ping) do not always come last. Fix it by reordering arguments. Signed-off-by: David Yang <mmyangfl(a)gmail.com> --- v2: https://lore.kernel.org/r/20250906170440.3513399-1-mmyangfl@gmail.com - fix (ar)ping only v1: https://lore.kernel.org/r/20250905173947.3164807-1-mmyangfl@gmail.com - fix CI errors .../selftests/net/forwarding/custom_multipath_hash.sh | 2 +- .../selftests/net/forwarding/gre_custom_multipath_hash.sh | 2 +- .../selftests/net/forwarding/ip6_forward_instats_vrf.sh | 6 +++--- .../net/forwarding/ip6gre_custom_multipath_hash.sh | 2 +- tools/testing/selftests/net/forwarding/lib.sh | 8 ++++---- .../selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh | 2 +- .../selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh | 4 ++-- 7 files changed, 13 insertions(+), 13 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh index 7d531f7091e6..5dbfab0e23e3 100755 --- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh @@ -226,7 +226,7 @@ send_flowlabel() # Generate 16384 echo requests, each with a random flow label. ip vrf exec v$h1 sh -c \ "for _ in {1..16384}; do \ - $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + $PING6 -F 0 -c 1 -q 2001:db8:4::2 >/dev/null 2>&1; \ done" } diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh index dda11a4a9450..b4f17a5bbc61 100755 --- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh @@ -321,7 +321,7 @@ send_flowlabel() # Generate 16384 echo requests, each with a random flow label. ip vrf exec v$h1 sh -c \ "for _ in {1..16384}; do \ - $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + $PING6 -F 0 -c 1 -q 2001:db8:2::2 >/dev/null 2>&1; \ done" } diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh index 49fa94b53a1c..25036e38043c 100755 --- a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -95,7 +95,7 @@ ipv6_in_too_big_err() # Send too big packets ip vrf exec $vrf_name \ - $PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + $PING6 -s 1300 -c 1 -w $PING_TIMEOUT 2001:1:2::2 &> /dev/null local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) test "$((t1 - t0))" -ne 0 @@ -131,7 +131,7 @@ ipv6_in_addr_err() # Disable forwarding temporary while sending the packet sysctl -qw net.ipv6.conf.all.forwarding=0 ip vrf exec $vrf_name \ - $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + $PING6 -c 1 -w $PING_TIMEOUT 2001:1:2::2 &> /dev/null sysctl -qw net.ipv6.conf.all.forwarding=1 local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) @@ -150,7 +150,7 @@ ipv6_in_discard() # Add a policy to discard ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block ip vrf exec $vrf_name \ - $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + $PING6 -c 1 -w $PING_TIMEOUT 2001:1:2::2 &> /dev/null ip xfrm policy del dst 2001:1:2::2/128 dir fwd local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards) diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh index e28b4a079e52..b24acfa52a3a 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh @@ -323,7 +323,7 @@ send_flowlabel() # Generate 16384 echo requests, each with a random flow label. ip vrf exec v$h1 sh -c \ "for _ in {1..16384}; do \ - $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + $PING6 -F 0 -c 1 -q 2001:db8:2::2 >/dev/null 2>&1; \ done" } diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 08121cb9dc26..2c252423b326 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1267,8 +1267,8 @@ ping_do() vrf_name=$(master_name_get $if_name) ip vrf exec $vrf_name \ - $PING $args $dip -c $PING_COUNT -i 0.1 \ - -w $PING_TIMEOUT &> /dev/null + $PING $args -c $PING_COUNT -i 0.1 \ + -w $PING_TIMEOUT $dip &> /dev/null } ping_test() @@ -1298,8 +1298,8 @@ ping6_do() vrf_name=$(master_name_get $if_name) ip vrf exec $vrf_name \ - $PING6 $args $dip -c $PING_COUNT -i 0.1 \ - -w $PING_TIMEOUT &> /dev/null + $PING6 $args -c $PING_COUNT -i 0.1 \ + -w $PING_TIMEOUT $dip &> /dev/null } ping6_test() diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh index a20d22d1df36..8d4ae6c952a1 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -238,7 +238,7 @@ test_lag_slave() ip neigh flush dev br1 setup_wait_dev $up_dev setup_wait_dev $host_dev - $ARPING -I br1 192.0.2.130 -qfc 1 + $ARPING -I br1 -qfc 1 192.0.2.130 sleep 2 mirror_test vrf-h1 192.0.2.1 192.0.2.18 $host_dev 1 ">= 10" diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh index 1b902cc579f6..a21c771908b3 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -196,7 +196,7 @@ test_span_gre_forbidden_egress() bridge vlan add dev $swp3 vid 555 # Re-prime FDB - $ARPING -I br1.555 192.0.2.130 -fqc 1 + $ARPING -I br1.555 -fqc 1 192.0.2.130 sleep 1 quick_test_span_gre_dir $tundev @@ -290,7 +290,7 @@ test_span_gre_fdb_roaming() bridge fdb del dev $swp2 $h3mac vlan 555 master 2>/dev/null # Re-prime FDB - $ARPING -I br1.555 192.0.2.130 -fqc 1 + $ARPING -I br1.555 -fqc 1 192.0.2.130 sleep 1 quick_test_span_gre_dir $tundev -- 2.51.0

2 months, 3 weeks

4
3
0 0

[PATCH RFC bpf-next 0/6] Add the the capability to load HW RX checsum in eBPF programs

by Lorenzo Bianconi

Introduce bpf_xdp_metadata_rx_checksum() kfunc in order to load the HW RX cheksum results in the eBPF program binded to the NIC. Implement xmo_rx_checksum callback for veth and ice drivers. --- Lorenzo Bianconi (6): netlink: specs: Add XDP RX checksum capability to XDP metadata specs net: xdp: Add xmo_rx_checksum callback veth: Add xmo_rx_checksum callback to veth driver net: ice: Add xmo_rx_checksum callback selftests/bpf: Add selftest support for bpf_xdp_metadata_rx_checksum selftests/bpf: Add bpf_xdp_metadata_rx_checksum support to xdp_hw_metadat prog Documentation/netlink/specs/netdev.yaml | 5 ++ drivers/net/ethernet/intel/ice/ice_base.c | 1 + drivers/net/ethernet/intel/ice/ice_txrx.h | 1 + drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 82 ++++++++++++++++++++++ drivers/net/veth.c | 19 +++++ include/net/xdp.h | 6 ++ net/core/xdp.c | 29 ++++++++ .../selftests/bpf/prog_tests/xdp_metadata.c | 7 ++ .../testing/selftests/bpf/progs/xdp_hw_metadata.c | 7 ++ tools/testing/selftests/bpf/progs/xdp_metadata.c | 1 + tools/testing/selftests/bpf/xdp_hw_metadata.c | 27 +++++++ tools/testing/selftests/bpf/xdp_metadata.h | 13 ++++ 12 files changed, 198 insertions(+) --- base-commit: 315f423be0d1ebe720d8fd4fa6bed68586b13d34 change-id: 20250915-xdp-meta-rxcksum-963cb3a793e7 Best regards, -- Lorenzo Bianconi <lorenzo(a)kernel.org>

2 months, 3 weeks

3
12
0 0

[PATCH][next] selftests/clone3: Fix spelling mistake "supportd" -> "supported"

by Colin Ian King

There is a spelling mistake in a ksft_print_msg message. Fix it. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/clone3/clone3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 05c3d2dcbf2a..385cf08f8cf8 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -71,7 +71,7 @@ static void test_shadow_stack_supported(void) } else if ((void *)ret == MAP_FAILED) { ksft_print_msg("Failed to map shadow stack\n"); } else { - ksft_print_msg("Shadow stack supportd\n"); + ksft_print_msg("Shadow stack supported\n"); shadow_stack_supported = true; if (!shadow_stack_enabled) -- 2.51.0

2 months, 3 weeks

1
0
0 0

[PATCH 00/15 v6.6.y] Backport minmax.h updates from v6.17-rc7

by Eliav Farber

This series backports 15 patches to update minmax.h in the 6.6.y branch, aligning it with v6.17-rc7. The ultimate goal is to synchronize all longterm branches so that they include the full set of minmax.h changes. The key motivation is to bring in commit d03eba99f5bf ("minmax: allow min()/max()/clamp() if the arguments have the same signedness"), which is missing in older kernels. In mainline, this change enables min()/max()/clamp() to accept mixed argument types, provided both have the same signedness. Without it, backported patches that use these forms may trigger compiler warnings, which escalate to build failures when -Werror is enabled. David Laight (7): minmax.h: add whitespace around operators and after commas minmax.h: update some comments minmax.h: reduce the #define expansion of min(), max() and clamp() minmax.h: use BUILD_BUG_ON_MSG() for the lo < hi test in clamp() minmax.h: move all the clamp() definitions after the min/max() ones minmax.h: simplify the variants of clamp() minmax.h: remove some #defines that are only expanded once Linus Torvalds (8): minmax: avoid overly complicated constant expressions in VM code minmax: simplify and clarify min_t()/max_t() implementation minmax: add a few more MIN_T/MAX_T users minmax: make generic MIN() and MAX() macros available everywhere minmax: simplify min()/max()/clamp() implementation minmax: don't use max() in situations that want a C constant expression minmax: improve macro expansion and type checking minmax: fix up min3() and max3() too arch/um/drivers/mconsole_user.c | 2 + arch/x86/mm/pgtable.c | 2 +- drivers/edac/sb_edac.c | 4 +- drivers/edac/skx_common.h | 1 - .../drm/amd/display/modules/hdcp/hdcp_ddc.c | 2 + .../drm/amd/pm/powerplay/hwmgr/ppevvmath.h | 14 +- drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c | 2 +- drivers/gpu/drm/drm_color_mgmt.c | 2 +- drivers/gpu/drm/radeon/evergreen_cs.c | 2 + drivers/hwmon/adt7475.c | 24 +- drivers/input/touchscreen/cyttsp4_core.c | 2 +- drivers/irqchip/irq-sun6i-r.c | 2 +- drivers/md/dm-integrity.c | 6 +- drivers/media/dvb-frontends/stv0367_priv.h | 3 + .../net/can/usb/etas_es58x/es58x_devlink.c | 2 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- drivers/net/fjes/fjes_main.c | 4 +- drivers/nfc/pn544/i2c.c | 2 - drivers/platform/x86/sony-laptop.c | 1 - drivers/scsi/isci/init.c | 6 +- .../pci/hive_isp_css_include/math_support.h | 5 - fs/btrfs/tree-checker.c | 2 +- include/linux/compiler.h | 9 + include/linux/minmax.h | 228 +++++++++++------- include/linux/pageblock-flags.h | 2 +- kernel/trace/preemptirq_delay_test.c | 2 - lib/btree.c | 1 - lib/decompress_unlzma.c | 2 + lib/vsprintf.c | 2 +- mm/zsmalloc.c | 2 - net/ipv4/proc.c | 2 +- net/ipv6/proc.c | 2 +- tools/testing/selftests/mm/mremap_test.c | 2 + tools/testing/selftests/seccomp/seccomp_bpf.c | 2 + 34 files changed, 202 insertions(+), 146 deletions(-) -- 2.47.3

2 months, 3 weeks

1
15
0 0

[PATCH 0/2] eventpoll: Fix epoll_wait() report false negative

by Nam Cao

Hi, While staring at epoll, I noticed ep_events_available() looks wrong. I wrote a small program to confirm, and yes it is definitely wrong. This series adds a reproducer to kselftest, and fix the bug. Nam Cao (2): selftests/eventpoll: Add test for multiple waiters eventpoll: Fix epoll_wait() report false negative fs/eventpoll.c | 16 +------ .../filesystems/epoll/epoll_wakeup_test.c | 45 +++++++++++++++++++ 2 files changed, 47 insertions(+), 14 deletions(-) -- 2.39.5

2 months, 3 weeks

5
15
0 0

[RFC PATCH bpf-next v1 0/3] bpf: Add BPF program type for overriding tracepoint probes

by Fuyu Zhao

Hi everyone, This patchset introduces a new BPF program type that allows overriding a tracepoint probe function registered via register_trace_*. Motivation ---------- Tracepoint probe functions registered via register_trace_* in the kernel cannot be dynamically modified, changing a probe function requires recompiling the kernel and rebooting. Nor can BPF programs change an existing probe function. Overiding tracepoint supports a way to apply patches into kernel quickly (such as applying security ones), through predefined static tracepoints, without waiting for upstream integration. This patchset demonstrates the way to override probe functions by BPF program. Overview -------- This patchset adds BPF_PROG_TYPE_RAW_TRACEPOINT_OVERRIDE program type. When this type of BPF program attaches, it overrides the target tracepoint probe function. And it also extends a new struct type "tracepoint_func_snapshot", which extends the tracepoint structure. It is used to record the original probe function registered by kernel after BPF program being attached and restore from it after detachment. Critical steps -------------- 1. Attach: Attach programs via the raw_tracepoint_open syscall. 2. Override: (a) Locate the target probe by `probe_name`. (b) Override target probe with the BPF program. (c) Save the BPF program and target probe function into "tracepoint_func_snapshot". 3. Restore: When the BPF program is detached, automatically restore the original probe function from earlier saved snapshot. Future work ----------- This patchset is intended as a first step toward supporting BPF programs that can override tracepoint probes. The current implementation may not yet cover all use cases or handle every corner case. I welcome feedback and suggestions from the community, and will continue to refine and improve the design based on comments and real-world requirements. Thanks! Fuyu Fuyu Zhao (3): bpf: Introduce BPF_PROG_TYPE_RAW_TRACEPOINT_OVERRIDE libbpf: Add support for BPF_PROG_TYPE_RAW_TRACEPOINT_OVERRIDE selftests/bpf: Add selftest for "raw_tp.o" include/linux/bpf_types.h | 2 + include/linux/trace_events.h | 9 + include/linux/tracepoint-defs.h | 6 + include/linux/tracepoint.h | 3 + include/uapi/linux/bpf.h | 2 + kernel/bpf/syscall.c | 35 +++- kernel/trace/bpf_trace.c | 31 +++ kernel/tracepoint.c | 190 +++++++++++++++++- tools/include/uapi/linux/bpf.h | 2 + tools/lib/bpf/bpf.c | 1 + tools/lib/bpf/bpf.h | 3 +- tools/lib/bpf/libbpf.c | 27 ++- tools/lib/bpf/libbpf.h | 3 +- .../bpf/prog_tests/raw_tp_override_test_run.c | 23 +++ .../bpf/progs/test_raw_tp_override_test_run.c | 20 ++ .../selftests/bpf/test_kmods/bpf_testmod.c | 7 + 16 files changed, 352 insertions(+), 12 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/raw_tp_override_test_run.c create mode 100644 tools/testing/selftests/bpf/progs/test_raw_tp_override_test_run.c -- 2.43.0

2 months, 3 weeks

5
14
0 0

[PATCH] selftests/kexec: Add .gitignore for generated binary

by Madhur Kumar

The test_kexec_jump binary is generated during 'make kselftest' but was not ignored, leading to it appearing as untracked in `git status`. Create a .gitignore file for selftests/kexec and add this generated file to it. Signed-off-by: Madhur Kumar <madhurkumar004(a)gmail.com> --- tools/testing/selftests/kexec/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/kexec/.gitignore diff --git a/tools/testing/selftests/kexec/.gitignore b/tools/testing/selftests/kexec/.gitignore new file mode 100644 index 000000000000..6cbe9a1049f3 --- /dev/null +++ b/tools/testing/selftests/kexec/.gitignore @@ -0,0 +1 @@ +test_kexec_jump -- 2.51.0

2 months, 3 weeks

1
0
0 0

[PATCH] selftests/cachestat: Add file tmpshmcstat to .gitignore

by Madhur Kumar

The tmpshmcstat file is generated with kselftest run but was not ignored, leading to it appearing as untracked in git status. Add it to .gitignore to silence the warning. Signed-off-by: Madhur Kumar <madhurkumar004(a)gmail.com> --- tools/testing/selftests/cachestat/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/cachestat/.gitignore b/tools/testing/selftests/cachestat/.gitignore index d6c30b43a4bb..abbb13b6e96b 100644 --- a/tools/testing/selftests/cachestat/.gitignore +++ b/tools/testing/selftests/cachestat/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only test_cachestat +tmpshmcstat -- 2.51.0

2 months, 3 weeks

1
0
0 0

[PATCH v2] selftests/timers: Consolidate and fix 32-bit overflow in timespec_sub

by Wake Liu

The timespec_sub function, as implemented in several timer selftests, is prone to integer overflow on 32-bit systems. The calculation `NSEC_PER_SEC * b.tv_sec` is performed using 32-bit arithmetic, and the result overflows before being stored in the 64-bit `ret` variable. This leads to incorrect time delta calculations and test failures. As suggested by tglx, this patch fixes the issue by: 1. Creating a new `static inline` helper function, `timespec_to_ns`, which safely converts a `timespec` to nanoseconds by casting `tv_sec` to `long long` before multiplying with `NSEC_PER_SEC`. 2. Placing the new helper and a rewritten `timespec_sub` into a common header: tools/testing/selftests/timers/helpers.h. 3. Removing the duplicated, buggy implementations from all timer selftests and replacing them with an #include of the new header. This consolidates the code and ensures the calculation is correctly performed using 64-bit arithmetic across all tests. Changes in v2: - Per tglx's feedback, instead of changing NSEC_PER_SEC globally, this version consolidates the buggy timespec_sub() implementations into a new 32-bit safe inline function in a shared header. - Amended the commit message to be more descriptive. --- .../selftests/timers/alarmtimer-suspend.c | 15 +++------ tools/testing/selftests/timers/helpers.h | 31 +++++++++++++++++++ tools/testing/selftests/timers/nanosleep.c | 2 +- tools/testing/selftests/timers/nsleep-lat.c | 12 ++----- .../testing/selftests/timers/valid-adjtimex.c | 8 ++--- 5 files changed, 43 insertions(+), 25 deletions(-) create mode 100644 tools/testing/selftests/timers/helpers.h diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c index a9ef76ea6051..e85ab182abe5 100644 --- a/tools/testing/selftests/timers/alarmtimer-suspend.c +++ b/tools/testing/selftests/timers/alarmtimer-suspend.c @@ -31,8 +31,9 @@ #include <include/vdso/time64.h> #include <errno.h> #include "../kselftest.h" +#include "helpers.h" -#define UNREASONABLE_LAT (NSEC_PER_SEC * 5) /* hopefully we resume in 5 secs */ +#define UNREASONABLE_LAT (NSEC_PER_SEC * 5LL) /* hopefully we resume in 5 secs */ #define SUSPEND_SECS 15 int alarmcount; @@ -70,14 +71,6 @@ char *clockstring(int clockid) } -long long timespec_sub(struct timespec a, struct timespec b) -{ - long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; - - ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; - return ret; -} - int final_ret; void sigalarm(int signo) @@ -88,8 +81,8 @@ void sigalarm(int signo) clock_gettime(alarm_clock_id, &ts); alarmcount++; - delta_ns = timespec_sub(start_time, ts); - delta_ns -= NSEC_PER_SEC * SUSPEND_SECS * alarmcount; + delta_ns = timespec_sub(ts, start_time); + delta_ns -= (long long)NSEC_PER_SEC * SUSPEND_SECS * alarmcount; printf("ALARM(%i): %ld:%ld latency: %lld ns ", alarmcount, ts.tv_sec, ts.tv_nsec, delta_ns); diff --git a/tools/testing/selftests/timers/helpers.h b/tools/testing/selftests/timers/helpers.h new file mode 100644 index 000000000000..652f20247091 --- /dev/null +++ b/tools/testing/selftests/timers/helpers.h @@ -0,0 +1,31 @@ +#ifndef SELFTESTS_TIMERS_HELPERS_H +#define SELFTESTS_TIMERS_HELPERS_H + +#include <time.h> + +#ifndef NSEC_PER_SEC +#define NSEC_PER_SEC 1000000000L +#endif + +/* + * timespec_to_ns - Convert timespec to nanoseconds + */ +static inline long long timespec_to_ns(const struct timespec *ts) +{ + return ((long long) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; +} + +/* + * timespec_sub - Subtract two timespec values + * + * @a: first timespec + * @b: second timespec + * + * Returns a - b in nanoseconds. + */ +static inline long long timespec_sub(struct timespec a, struct timespec b) +{ + return timespec_to_ns(&a) - timespec_to_ns(&b); +} + +#endif /* SELFTESTS_TIMERS_HELPERS_H */ diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c index 252c6308c569..41c33629d5f0 100644 --- a/tools/testing/selftests/timers/nanosleep.c +++ b/tools/testing/selftests/timers/nanosleep.c @@ -138,7 +138,7 @@ int main(int argc, char **argv) fflush(stdout); length = 10; - while (length <= (NSEC_PER_SEC * 10)) { + while (length <= (NSEC_PER_SEC * 10LL)) { ret = nanosleep_test(clockid, length); if (ret == UNSUPPORTED) { ksft_test_result_skip("%-31s\n", clockstring(clockid)); diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c index de23dc0c9f97..c888a77aab7a 100644 --- a/tools/testing/selftests/timers/nsleep-lat.c +++ b/tools/testing/selftests/timers/nsleep-lat.c @@ -26,6 +26,7 @@ #include <signal.h> #include <include/vdso/time64.h> #include "../kselftest.h" +#include "helpers.h" #define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ @@ -74,14 +75,6 @@ struct timespec timespec_add(struct timespec ts, unsigned long long ns) } -long long timespec_sub(struct timespec a, struct timespec b) -{ - long long ret = NSEC_PER_SEC * b.tv_sec + b.tv_nsec; - - ret -= NSEC_PER_SEC * a.tv_sec + a.tv_nsec; - return ret; -} - int nanosleep_lat_test(int clockid, long long ns) { struct timespec start, end, target; @@ -146,7 +139,7 @@ int main(int argc, char **argv) continue; length = 10; - while (length <= (NSEC_PER_SEC * 10)) { + while (length <= (NSEC_PER_SEC * 10LL)) { ret = nanosleep_lat_test(clockid, length); if (ret) break; @@ -164,3 +157,4 @@ int main(int argc, char **argv) ksft_finished(); } + diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 6b7801055ad1..a61d4b4739a2 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -260,16 +260,16 @@ int validate_set_offset(void) if (set_offset(-NSEC_PER_SEC - 1, 1)) return -1; - if (set_offset(5 * NSEC_PER_SEC, 1)) + if (set_offset(5LL * NSEC_PER_SEC, 1)) return -1; - if (set_offset(-5 * NSEC_PER_SEC, 1)) + if (set_offset(-5LL * NSEC_PER_SEC, 1)) return -1; - if (set_offset(5 * NSEC_PER_SEC + NSEC_PER_SEC / 2, 1)) + if (set_offset(5LL * NSEC_PER_SEC + NSEC_PER_SEC / 2, 1)) return -1; - if (set_offset(-5 * NSEC_PER_SEC - NSEC_PER_SEC / 2, 1)) + if (set_offset(-5LL * NSEC_PER_SEC - NSEC_PER_SEC / 2, 1)) return -1; if (set_offset(USEC_PER_SEC - 1, 0)) -- 2.51.0.384.g4c02a37b29-goog

2 months, 3 weeks

2
1
0 0

[PATCH v2] selftests: ublk: fix behavior when fio is not installed

by Uday Shankar

Some ublk selftests have strange behavior when fio is not installed. While most tests behave correctly (run if they don't need fio, or skip if they need fio), the following tests have different behavior: - test_null_01, test_null_02, test_generic_01, test_generic_02, and test_generic_12 try to run fio without checking if it exists first, and fail on any failure of the fio command (including "fio command not found"). So these tests fail when they should skip. - test_stress_05 runs fio without checking if it exists first, but doesn't fail on fio command failure. This test passes, but that pass is misleading as the test doesn't do anything useful without fio installed. So this test passes when it should skip. Fix these issues by adding _have_program fio checks to the top of all of these tests. Signed-off-by: Uday Shankar <ushankar(a)purestorage.com> --- Changes in v2: - Also fix test_generic_01, test_generic_02, test_generic_12, which fail on systems where bpftrace is installed but fio is not (Mohit Gupta) - Link to v1: https://lore.kernel.org/r/20250916-ublk_fio-v1-1-8d522539eed7@purestorage.c… --- tools/testing/selftests/ublk/test_generic_01.sh | 4 ++++ tools/testing/selftests/ublk/test_generic_02.sh | 4 ++++ tools/testing/selftests/ublk/test_generic_12.sh | 4 ++++ tools/testing/selftests/ublk/test_null_01.sh | 4 ++++ tools/testing/selftests/ublk/test_null_02.sh | 4 ++++ tools/testing/selftests/ublk/test_stress_05.sh | 4 ++++ 6 files changed, 24 insertions(+) diff --git a/tools/testing/selftests/ublk/test_generic_01.sh b/tools/testing/selftests/ublk/test_generic_01.sh index 9227a208ba53128e4a202298316ff77e05607595..21a31cd5491aa79ffe3ad458a0055e832c619325 100755 --- a/tools/testing/selftests/ublk/test_generic_01.sh +++ b/tools/testing/selftests/ublk/test_generic_01.sh @@ -10,6 +10,10 @@ if ! _have_program bpftrace; then exit "$UBLK_SKIP_CODE" fi +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + _prep_test "null" "sequential io order" dev_id=$(_add_ublk_dev -t null) diff --git a/tools/testing/selftests/ublk/test_generic_02.sh b/tools/testing/selftests/ublk/test_generic_02.sh index 3e80121e3bf5e191aa9ffe1f85e1693be4fdc2d2..12920768b1a080d37fcdff93de7a0439101de09e 100755 --- a/tools/testing/selftests/ublk/test_generic_02.sh +++ b/tools/testing/selftests/ublk/test_generic_02.sh @@ -10,6 +10,10 @@ if ! _have_program bpftrace; then exit "$UBLK_SKIP_CODE" fi +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + _prep_test "null" "sequential io order for MQ" dev_id=$(_add_ublk_dev -t null -q 2) diff --git a/tools/testing/selftests/ublk/test_generic_12.sh b/tools/testing/selftests/ublk/test_generic_12.sh index 7abbb00d251df9403857b1c6f53aec8bf8eab176..b4046201b4d99ef5355b845ebea2c9a3924276a5 100755 --- a/tools/testing/selftests/ublk/test_generic_12.sh +++ b/tools/testing/selftests/ublk/test_generic_12.sh @@ -10,6 +10,10 @@ if ! _have_program bpftrace; then exit "$UBLK_SKIP_CODE" fi +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + _prep_test "null" "do imbalanced load, it should be balanced over I/O threads" NTHREADS=6 diff --git a/tools/testing/selftests/ublk/test_null_01.sh b/tools/testing/selftests/ublk/test_null_01.sh index a34203f726685787da80b0e32da95e0fcb90d0b1..c2cb8f7a09fe37a9956d067fd56b28dc7ca6bd68 100755 --- a/tools/testing/selftests/ublk/test_null_01.sh +++ b/tools/testing/selftests/ublk/test_null_01.sh @@ -6,6 +6,10 @@ TID="null_01" ERR_CODE=0 +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + _prep_test "null" "basic IO test" dev_id=$(_add_ublk_dev -t null) diff --git a/tools/testing/selftests/ublk/test_null_02.sh b/tools/testing/selftests/ublk/test_null_02.sh index 5633ca8766554b22be252c7cb2d13de1bf923b90..8accd35beb55c149f74b23f0fb562e12cbf3e362 100755 --- a/tools/testing/selftests/ublk/test_null_02.sh +++ b/tools/testing/selftests/ublk/test_null_02.sh @@ -6,6 +6,10 @@ TID="null_02" ERR_CODE=0 +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + _prep_test "null" "basic IO test with zero copy" dev_id=$(_add_ublk_dev -t null -z) diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh index 566cfd90d192ce8c1f98ca2539792d54a787b3d1..274295061042e5db3f4f0846ae63ea9b787fb2ee 100755 --- a/tools/testing/selftests/ublk/test_stress_05.sh +++ b/tools/testing/selftests/ublk/test_stress_05.sh @@ -5,6 +5,10 @@ TID="stress_05" ERR_CODE=0 +if ! _have_program fio; then + exit "$UBLK_SKIP_CODE" +fi + run_io_and_remove() { local size=$1 --- base-commit: da7b97ba0d219a14a83e9cc93f98b53939f12944 change-id: 20250916-ublk_fio-1910998b00b3 Best regards, -- Uday Shankar <ushankar(a)purestorage.com>

2 months, 3 weeks

3
2
0 0

[PATCH v7 0/6] mm/memfd: introduce MFD_NOEXEC_SEAL and MFD_EXEC

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)google.com> Since Linux introduced the memfd feature, memfd have always had their execute bit set, and the memfd_create() syscall doesn't allow setting it differently. However, in a secure by default system, such as ChromeOS, (where all executables should come from the rootfs, which is protected by Verified boot), this executable nature of memfd opens a door for NoExec bypass and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm process created a memfd to share the content with an external process, however the memfd is overwritten and used for executing arbitrary code and root escalation. [2] lists more VRP in this kind. On the other hand, executable memfd has its legit use, runc uses memfd’s seal and executable feature to copy the contents of the binary then execute them, for such system, we need a solution to differentiate runc's use of executable memfds and an attacker's [3]. To address those above, this set of patches add following: 1> Let memfd_create() set X bit at creation time. 2> Let memfd to be sealed for modifying X bit. 3> A new pid namespace sysctl: vm.memfd_noexec to control the behavior of X bit.For example, if a container has vm.memfd_noexec=2, then memfd_create() without MFD_NOEXEC_SEAL will be rejected. 4> A new security hook in memfd_create(). This make it possible to a new LSM, which rejects or allows executable memfd based on its security policy. Change history: v7: - patch 2/6: remove #ifdef and MAX_PATH (memfd_test.c). - patch 3/6: check capability (CAP_SYS_ADMIN) from userns instead of global ns (pid_sysctl.h). Add a tab (pid_namespace.h). - patch 5/6: remove #ifdef (memfd_test.c) - patch 6/6: remove unneeded security_move_mount(security.c). v6:https://lore.kernel.org/lkml/20221206150233.1963717-1-jeffxu@google.com/ - Address comment and move "#ifdef CONFIG_" from .c file to pid_sysctl.h v5:https://lore.kernel.org/lkml/20221206152358.1966099-1-jeffxu@google.com/ - Pass vm.memfd_noexec from current ns to child ns. - Fix build issue detected by kernel test robot. - Add missing security.c v3:https://lore.kernel.org/lkml/20221202013404.163143-1-jeffxu@google.com/ - Address API design comments in v2. - Let memfd_create() to set X bit at creation time. - A new pid namespace sysctl: vm.memfd_noexec to control behavior of X bit. - A new security hook in memfd_create(). v2:https://lore.kernel.org/lkml/20220805222126.142525-1-jeffxu@google.com/ - address comments in V1. - add sysctl (vm.mfd_noexec) to set the default file permissions of memfd_create to be non-executable. v1:https://lwn.net/Articles/890096/ [1] https://crbug.com/1305411 [2] https://bugs.chromium.org/p/chromium/issues/list?q=type%3Dbug-security%20me… [3] https://lwn.net/Articles/781013/ Daniel Verkamp (2): mm/memfd: add F_SEAL_EXEC selftests/memfd: add tests for F_SEAL_EXEC Jeff Xu (4): mm/memfd: add MFD_NOEXEC_SEAL and MFD_EXEC mm/memfd: Add write seals when apply SEAL_EXEC to executable memfd selftests/memfd: add tests for MFD_NOEXEC_SEAL MFD_EXEC mm/memfd: security hook for memfd_create include/linux/lsm_hook_defs.h | 1 + include/linux/lsm_hooks.h | 4 + include/linux/pid_namespace.h | 19 ++ include/linux/security.h | 6 + include/uapi/linux/fcntl.h | 1 + include/uapi/linux/memfd.h | 4 + kernel/pid_namespace.c | 5 + kernel/pid_sysctl.h | 59 ++++ mm/memfd.c | 61 +++- mm/shmem.c | 6 + security/security.c | 5 + tools/testing/selftests/memfd/fuse_test.c | 1 + tools/testing/selftests/memfd/memfd_test.c | 341 ++++++++++++++++++++- 13 files changed, 510 insertions(+), 3 deletions(-) create mode 100644 kernel/pid_sysctl.h base-commit: eb7081409f94a9a8608593d0fb63a1aa3d6f95d8 -- 2.39.0.rc1.256.g54fd8350bd-goog

2 months, 3 weeks

9
25
0 0

[PATCH v3 0/8] riscv: Add Zalasr ISA extension support

by Xu Lu

This patch adds support for the Zalasr ISA extension, which supplies the real load acquire/store release instructions. The specification can be found here: https://github.com/riscv/riscv-zalasr/blob/main/chapter2.adoc This patch seires has been tested with ltp on Qemu with Brensan's zalasr support patch[1]. Some false positive spacing error happens during patch checking. Thus I CCed maintainers of checkpatch.pl as well. [1] https://lore.kernel.org/all/CAGPSXwJEdtqW=nx71oufZp64nK6tK=0rytVEcz4F-gfvCO… v3: - Apply acquire/release semantics to arch_xchg/arch_cmpxchg operations so as to ensure FENCE.TSO ordering between operations which precede the UNLOCK+LOCK sequence and operations which follow the sequence. Thanks to Andrea. - Support hwprobe of Zalasr. - Allow Zalasr extensions for Guest/VM. v2: - Adjust the order of Zalasr and Zalrsc in dt-bindings. Thanks to Conor. Xu Lu (8): riscv: add ISA extension parsing for Zalasr dt-bindings: riscv: Add Zalasr ISA extension description riscv: hwprobe: Export Zalasr extension riscv: Introduce Zalasr instructions riscv: Use Zalasr for smp_load_acquire/smp_store_release riscv: Apply acquire/release semantics to arch_xchg/arch_cmpxchg operations RISC-V: KVM: Allow Zalasr extensions for Guest/VM KVM: riscv: selftests: Add Zalasr extensions to get-reg-list test Documentation/arch/riscv/hwprobe.rst | 5 +- .../devicetree/bindings/riscv/extensions.yaml | 5 + arch/riscv/include/asm/atomic.h | 6 - arch/riscv/include/asm/barrier.h | 91 ++++++++++-- arch/riscv/include/asm/cmpxchg.h | 136 ++++++++---------- arch/riscv/include/asm/hwcap.h | 1 + arch/riscv/include/asm/insn-def.h | 79 ++++++++++ arch/riscv/include/uapi/asm/hwprobe.h | 1 + arch/riscv/include/uapi/asm/kvm.h | 1 + arch/riscv/kernel/cpufeature.c | 1 + arch/riscv/kernel/sys_hwprobe.c | 1 + arch/riscv/kvm/vcpu_onereg.c | 2 + .../selftests/kvm/riscv/get-reg-list.c | 4 + 13 files changed, 242 insertions(+), 91 deletions(-) -- 2.20.1

2 months, 3 weeks

3
14
0 0

[PATCH v4 0/2] arm64: Support FEAT_LSFE (Large System Float Extension)

by Mark Brown

FEAT_LSFE is optional from v9.5, it adds new instructions for atomic memory operations with floating point values. We have no immediate use for it in kernel, provide a hwcap so userspace can discover it and allow the ID register field to be exposed to KVM guests. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v4: - Rebase onto arm64/for-next/cpufeature, note that both patches have build dependencies on this. - Drop unneeded cc clobber in hwcap. - Use STRFADD as the instruction probed in hwcap. - Link to v3: https://lore.kernel.org/r/20250818-arm64-lsfe-v3-0-af6f4d66eb39@kernel.org Changes in v3: - Rebase onto v6.17-rc1. - Link to v2: https://lore.kernel.org/r/20250703-arm64-lsfe-v2-0-eced80999cb4@kernel.org Changes in v2: - Fix result of vi dropping in hwcap test. - Link to v1: https://lore.kernel.org/r/20250627-arm64-lsfe-v1-0-68351c4bf741@kernel.org --- Mark Brown (2): KVM: arm64: Expose FEAT_LSFE to guests kselftest/arm64: Add lsfe to the hwcaps test arch/arm64/kvm/sys_regs.c | 4 +++- tools/testing/selftests/arm64/abi/hwcap.c | 21 +++++++++++++++++++++ 2 files changed, 24 insertions(+), 1 deletion(-) --- base-commit: 220928e52cb03d223b3acad3888baf0687486d21 change-id: 20250625-arm64-lsfe-0810cf98adc2 Best regards, -- Mark Brown <broonie(a)kernel.org>

2 months, 3 weeks

4
6
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror