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

[PATCH] Add Selftest to test fork() syscall

by Shivam Chaudhary

This test verifies the correct behavior of the fork() system call, which creates a child process by duplicating the parent process. The test checks the following: - The child PID returned by fork() is present in /proc. - The child PID is different from the parent PID. - The memory allocated to a variable in the child process is independent of the parent process. Test logs : - Run without root TAP version 13 1..1 ok 1 # SKIP This test needs root to run! - Run with root TAP version 13 1..1 # Inside the parent process. # Child PID got from fork() return : 56038 # Parent PID from getpid(): 56037 # Inside the child process. 1..2 ok 1 Child Pid from /proc and fork() matching ok 2 Child Pid != Parent pid 1..3 ok 3 After modification in child No effect on the value of 'var' in parent # Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0 Signed-off-by: Shivam Chaudhary <cvam0000(a)gmail.com> --- Here is my proposal for a new directory, /syscalls, to add syscall selftests, as there is currently no dedicated space for these tests. I encountered this issue while writing the test case for the delete_module syscall and was unsure where to place it. As a heads-up, the delete_module test is currently under review, and I would like to add it to this directory. tools/testing/selftests/Makefile | 1 + tools/testing/selftests/syscalls/.gitignore | 1 + .../syscalls/fork_syscall/.gitignore | 1 + .../selftests/syscalls/fork_syscall/Makefile | 5 + .../syscalls/fork_syscall/fork_syscall.c | 151 ++++++++++++++++++ 5 files changed, 159 insertions(+) create mode 100644 tools/testing/selftests/syscalls/.gitignore create mode 100644 tools/testing/selftests/syscalls/fork_syscall/.gitignore create mode 100644 tools/testing/selftests/syscalls/fork_syscall/Makefile create mode 100644 tools/testing/selftests/syscalls/fork_syscall/fork_syscall.c diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 363d031a16f7..9265c17c5de3 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -97,6 +97,7 @@ TARGETS += sparc64 TARGETS += splice TARGETS += static_keys TARGETS += sync +TARGETS += syscalls/fork_syscall TARGETS += syscall_user_dispatch TARGETS += sysctl TARGETS += tc-testing diff --git a/tools/testing/selftests/syscalls/.gitignore b/tools/testing/selftests/syscalls/.gitignore new file mode 100644 index 000000000000..c7ae138d3f0c --- /dev/null +++ b/tools/testing/selftests/syscalls/.gitignore @@ -0,0 +1 @@ +// SPDX-License-Identifier: GPL-2.0 \ No newline at end of file diff --git a/tools/testing/selftests/syscalls/fork_syscall/.gitignore b/tools/testing/selftests/syscalls/fork_syscall/.gitignore new file mode 100644 index 000000000000..788cc1ff70bd --- /dev/null +++ b/tools/testing/selftests/syscalls/fork_syscall/.gitignore @@ -0,0 +1 @@ +# SPDX-License-Identifier: GPL-2.0-only \ No newline at end of file diff --git a/tools/testing/selftests/syscalls/fork_syscall/Makefile b/tools/testing/selftests/syscalls/fork_syscall/Makefile new file mode 100644 index 000000000000..56033a3d5a87 --- /dev/null +++ b/tools/testing/selftests/syscalls/fork_syscall/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := fork_syscall +CFLAGS += -Wall + +include ../lib.mk \ No newline at end of file diff --git a/tools/testing/selftests/syscalls/fork_syscall/fork_syscall.c b/tools/testing/selftests/syscalls/fork_syscall/fork_syscall.c new file mode 100644 index 000000000000..eab22831f7e1 --- /dev/null +++ b/tools/testing/selftests/syscalls/fork_syscall/fork_syscall.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* kselftest for fork() system call + * + * Summery : fork() system call is used to create a new process + * by duplicating an existing one. The new process, known as the + * child process, is a copy of the parent process. + * + * Child process is dublicate process but has different PID and + * memory allocation. + * + * About the test : With this test we are testing the following: + * - Child PID which fork() returns to Parent is present in /proc + * - Child PID is not same as Parent PID. + * - Memory allocation to a variable in child and parent process + * is different. +*/ + + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <dirent.h> +#include <ctype.h> + +#include "../../kselftest.h" + +// Function to check if a string is numeric (PID check) +int is_numeric(const char *str) { + while (*str) { + if (!isdigit(*str)) return 0; + str++; + } + return 1; +} + +// Function to find the child PID in /proc +pid_t find_child_pid(pid_t parent_pid) { + DIR *proc_dir = opendir("/proc"); + struct dirent *entry; + + if (proc_dir == NULL) { + perror("Failed to open /proc directory"); + ksft_exit_fail(); + return 1; + } + + // Iterate through the /proc directory to find PIDs + while ((entry = readdir(proc_dir)) != NULL) { + // Check if the entry is a PID + if (is_numeric(entry->d_name)) { + pid_t pid = atoi(entry->d_name); + + // Construct the path to /proc/<pid>/ + //stat to check the parent PID + + char path[40], buffer[100]; + snprintf(path, 40, "/proc/%d/stat", pid); + + FILE *stat_file = fopen(path, "r"); + if (stat_file != NULL) { + fgets(buffer, 100, stat_file); + fclose(stat_file); + + // The fourth field in /proc/<pid>/stat is the parent PID + pid_t ppid; + sscanf(buffer, "%*d %*s %*c %d", &ppid); + + if (ppid == parent_pid) { + closedir(proc_dir); + // Return the child PID if the parent PID matches + return pid; + } + } + } + } + + closedir(proc_dir); + + // Return -1 if no child PID was found + return -1; +} + +int main(void) { + + // Setting up kselftest framework + ksft_print_header(); + ksft_set_plan(1); + + // Check if test is run a root + if (geteuid()) { + ksft_test_result_skip("This test needs root to run!\n"); + return 1; + } + + // forking + pid_t pid = fork(); + + // Declare a variable in both parent and child processes + int var = 17; + + if (pid == -1) { + ksft_test_result_error("%s.\n", strerror(errno)); + ksft_finished(); + return 1; + + } else if (pid == 0) { + // This is the child process + ksft_print_msg("Inside the child process.\n"); + var = 1998; + + } else { + // This is the parent process + pid_t ppid=getpid(); + ksft_print_msg("Inside the parent process.\n"); + ksft_print_msg("Child PID got from fork() return : %d\n", pid); + ksft_print_msg("Parent PID from getpid(): %d\n",ppid); + + // Find the child PID in /proc + pid_t child_pid = find_child_pid(getpid()); + if (child_pid != -1) { + ksft_set_plan(2); + if(child_pid == pid && pid != ppid && var != 1998) { + ksft_test_result_pass("Child Pid from /proc and fork() matching\n"); + ksft_test_result_pass("Child Pid != Parent pid\n"); + ksft_set_plan(3); + ksft_test_result_pass( + "After modification in child No effect on the value of 'var' in parent\n"); + ksft_exit_pass(); + return 0; + } + else { + ksft_exit_fail(); + return 1; + } + } + else { + ksft_test_result_fail("Child Pid from /proc and fork() does not match"); + ksft_exit_fail(); + return 1; + } + + // Wait for the child process to finish + wait(NULL); + } + + return 0; +} + -- 2.34.1

6 months

2
3
0 0

selftests/sched_ext: enq_last_no_enq_fails testcase fails

by Vishal Chourasia

Hi, ===== START ===== TEST: enq_last_no_enq_fails DESCRIPTION: Verify we fail to load a scheduler if we specify the SCX_OPS_ENQ_LAST flag without defining ops.enqueue() OUTPUT: ERR: enq_last_no_enq_fails.c:35 Incorrectly succeeded in to attaching scheduler not ok 2 enq_last_no_enq_fails # ===== END ===== Above selftest fails even when BPF scheduler is not loaded into the kernel. Below is snippet from the dmesg verifing bpf program was not loaded: sched_ext: enq_last_no_enq_fails: SCX_OPS_ENQ_LAST requires ops.enqueue() to be implemented scx_ops_enable.isra.0+0xde8/0xe30 bpf_struct_ops_link_create+0x1ac/0x240 link_create+0x178/0x400 __sys_bpf+0x7ac/0xd50 sys_bpf+0x2c/0x70 system_call_exception+0x148/0x310 system_call_vectored_common+0x15c/0x2ec sched_ext: "enq_select_cpu_fails" does not implement cgroup cpu.weight sched_ext: BPF scheduler "enq_select_cpu_fails" enabled sched_ext: BPF scheduler "enq_select_cpu_fails" disabled (runtime error) static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) { ... ret = validate_ops(ops); if (ret) goto err_disable; ... err_disable: mutex_unlock(&scx_ops_enable_mutex); /* * Returning an error code here would not pass all the error information * to userspace. Record errno using scx_ops_error() for cases * scx_ops_error() wasn't already invoked and exit indicating success so * that the error is notified through ops.exit() with all the details. * * Flush scx_ops_disable_work to ensure that error is reported before * init completion. */ scx_ops_error("scx_ops_enable() failed (%d)", ret); kthread_flush_work(&scx_ops_disable_work); return 0; } validate_ops() correctly reports the error, but err_disable path ultimately returns with a value of zero from: enq_last_no_enq_fails.c static enum scx_test_status run(void *ctx) { struct enq_last_no_enq_fails *skel = ctx; struct bpf_link *link; link = bpf_map__attach_struct_ops(skel->maps.enq_last_no_enq_fails_ops); if (link) { SCX_ERR("Incorrectly succeeded in to attaching scheduler"); return SCX_TEST_FAIL; } bpf_link__destroy(link); return SCX_TEST_PASS; }

6 months

2
1
0 0

[PATCH v2 1/2] selftest: rtc: Add to check rtc alarm status for alarm related test

by Joseph Jang

In alarm_wkalm_set and alarm_wkalm_set_minute test, they use different ioctl (RTC_ALM_SET/RTC_WKALM_SET) for alarm feature detection. They will skip testing if RTC_ALM_SET/RTC_WKALM_SET ioctl returns an EINVAL error code. This design may miss detecting real problems when the efi.set_wakeup_time() return errors and then RTC_ALM_SET/RTC_WKALM_SET ioctl returns an EINVAL error code with RTC_FEATURE_ALARM enabled. In order to make rtctest more explicit and robust, we propose to use RTC_PARAM_GET ioctl interface to check rtc alarm feature state before running alarm related tests. If the kernel does not support RTC_PARAM_GET ioctl interface, we will fallback to check the error number of (RTC_ALM_SET/RTC_WKALM_SET) ioctl call for alarm feature detection. Requires commit 101ca8d05913b ("rtc: efi: Enable SET/GET WAKEUP services as optional") Reviewed-by: Koba Ko <kobak(a)nvidia.com> Reviewed-by: Matthew R. Ochs <mochs(a)nvidia.com> Signed-off-by: Joseph Jang <jjang(a)nvidia.com> --- Changes in v2: - Changed to use $(top_srcdir) instead of hardcoding the path. tools/testing/selftests/rtc/Makefile | 2 +- tools/testing/selftests/rtc/rtctest.c | 64 +++++++++++++++++++++++++++ 2 files changed, 65 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile index 55198ecc04db..6e3a98fb24ba 100644 --- a/tools/testing/selftests/rtc/Makefile +++ b/tools/testing/selftests/rtc/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -O3 -Wl,-no-as-needed -Wall +CFLAGS += -O3 -Wl,-no-as-needed -Wall -I$(top_srcdir)/usr/include LDLIBS += -lrt -lpthread -lm TEST_GEN_PROGS = rtctest diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c index 63ce02d1d5cc..2b12497eb30d 100644 --- a/tools/testing/selftests/rtc/rtctest.c +++ b/tools/testing/selftests/rtc/rtctest.c @@ -25,6 +25,12 @@ static char *rtc_file = "/dev/rtc0"; +enum rtc_alarm_state { + RTC_ALARM_UNKNOWN, + RTC_ALARM_ENABLED, + RTC_ALARM_DISABLED, +}; + FIXTURE(rtc) { int fd; }; @@ -82,6 +88,24 @@ static void nanosleep_with_retries(long ns) } } +static enum rtc_alarm_state get_rtc_alarm_state(int fd) +{ + struct rtc_param param = { 0 }; + int rc; + + /* Validate kernel reflects unsupported RTC alarm state */ + param.param = RTC_PARAM_FEATURES; + param.index = 0; + rc = ioctl(fd, RTC_PARAM_GET, &param); + if (rc < 0) + return RTC_ALARM_UNKNOWN; + + if ((param.uvalue & _BITUL(RTC_FEATURE_ALARM)) == 0) + return RTC_ALARM_DISABLED; + + return RTC_ALARM_ENABLED; +} + TEST_F_TIMEOUT(rtc, date_read_loop, READ_LOOP_DURATION_SEC + 2) { int rc; long iter_count = 0; @@ -197,11 +221,16 @@ TEST_F(rtc, alarm_alm_set) { fd_set readfds; time_t secs, new; int rc; + enum rtc_alarm_state alarm_state = RTC_ALARM_UNKNOWN; if (self->fd == -1 && errno == ENOENT) SKIP(return, "Skipping test since %s does not exist", rtc_file); ASSERT_NE(-1, self->fd); + alarm_state = get_rtc_alarm_state(self->fd); + if (alarm_state == RTC_ALARM_DISABLED) + SKIP(return, "Skipping test since alarms are not supported."); + rc = ioctl(self->fd, RTC_RD_TIME, &tm); ASSERT_NE(-1, rc); @@ -210,6 +239,11 @@ TEST_F(rtc, alarm_alm_set) { rc = ioctl(self->fd, RTC_ALM_SET, &tm); if (rc == -1) { + /* + * Report error if rtc alarm was enabled. Fallback to check ioctl + * error number if rtc alarm state is unknown. + */ + ASSERT_EQ(RTC_ALARM_UNKNOWN, alarm_state); ASSERT_EQ(EINVAL, errno); TH_LOG("skip alarms are not supported."); return; @@ -255,11 +289,16 @@ TEST_F(rtc, alarm_wkalm_set) { fd_set readfds; time_t secs, new; int rc; + enum rtc_alarm_state alarm_state = RTC_ALARM_UNKNOWN; if (self->fd == -1 && errno == ENOENT) SKIP(return, "Skipping test since %s does not exist", rtc_file); ASSERT_NE(-1, self->fd); + alarm_state = get_rtc_alarm_state(self->fd); + if (alarm_state == RTC_ALARM_DISABLED) + SKIP(return, "Skipping test since alarms are not supported."); + rc = ioctl(self->fd, RTC_RD_TIME, &alarm.time); ASSERT_NE(-1, rc); @@ -270,6 +309,11 @@ TEST_F(rtc, alarm_wkalm_set) { rc = ioctl(self->fd, RTC_WKALM_SET, &alarm); if (rc == -1) { + /* + * Report error if rtc alarm was enabled. Fallback to check ioctl + * error number if rtc alarm state is unknown. + */ + ASSERT_EQ(RTC_ALARM_UNKNOWN, alarm_state); ASSERT_EQ(EINVAL, errno); TH_LOG("skip alarms are not supported."); return; @@ -307,11 +351,16 @@ TEST_F_TIMEOUT(rtc, alarm_alm_set_minute, 65) { fd_set readfds; time_t secs, new; int rc; + enum rtc_alarm_state alarm_state = RTC_ALARM_UNKNOWN; if (self->fd == -1 && errno == ENOENT) SKIP(return, "Skipping test since %s does not exist", rtc_file); ASSERT_NE(-1, self->fd); + alarm_state = get_rtc_alarm_state(self->fd); + if (alarm_state == RTC_ALARM_DISABLED) + SKIP(return, "Skipping test since alarms are not supported."); + rc = ioctl(self->fd, RTC_RD_TIME, &tm); ASSERT_NE(-1, rc); @@ -320,6 +369,11 @@ TEST_F_TIMEOUT(rtc, alarm_alm_set_minute, 65) { rc = ioctl(self->fd, RTC_ALM_SET, &tm); if (rc == -1) { + /* + * Report error if rtc alarm was enabled. Fallback to check ioctl + * error number if rtc alarm state is unknown. + */ + ASSERT_EQ(RTC_ALARM_UNKNOWN, alarm_state); ASSERT_EQ(EINVAL, errno); TH_LOG("skip alarms are not supported."); return; @@ -365,11 +419,16 @@ TEST_F_TIMEOUT(rtc, alarm_wkalm_set_minute, 65) { fd_set readfds; time_t secs, new; int rc; + enum rtc_alarm_state alarm_state = RTC_ALARM_UNKNOWN; if (self->fd == -1 && errno == ENOENT) SKIP(return, "Skipping test since %s does not exist", rtc_file); ASSERT_NE(-1, self->fd); + alarm_state = get_rtc_alarm_state(self->fd); + if (alarm_state == RTC_ALARM_DISABLED) + SKIP(return, "Skipping test since alarms are not supported."); + rc = ioctl(self->fd, RTC_RD_TIME, &alarm.time); ASSERT_NE(-1, rc); @@ -380,6 +439,11 @@ TEST_F_TIMEOUT(rtc, alarm_wkalm_set_minute, 65) { rc = ioctl(self->fd, RTC_WKALM_SET, &alarm); if (rc == -1) { + /* + * Report error if rtc alarm was enabled. Fallback to check ioctl + * error number if rtc alarm state is unknown. + */ + ASSERT_EQ(RTC_ALARM_UNKNOWN, alarm_state); ASSERT_EQ(EINVAL, errno); TH_LOG("skip alarms are not supported."); return; -- 2.34.1

6 months

3
2
0 0

[PATCH] sched_ext: Fix function pointer type mismatches in BPF selftests

by Vishal Chourasia

Fix incompatible function pointer type warnings in sched_ext BPF selftests by explicitly casting the function pointers when initializing struct_ops. This addresses multiple -Wincompatible-function-pointer-types warnings from the clang compiler where function signatures didn't match exactly. The void * cast ensures the compiler accepts the function pointer assignment despite minor type differences in the parameters. --- .../selftests/sched_ext/create_dsq.bpf.c | 6 +- .../sched_ext/ddsp_bogus_dsq_fail.bpf.c | 4 +- .../sched_ext/ddsp_vtimelocal_fail.bpf.c | 4 +- .../selftests/sched_ext/dsp_local_on.bpf.c | 8 +-- .../sched_ext/enq_select_cpu_fails.bpf.c | 4 +- tools/testing/selftests/sched_ext/exit.bpf.c | 14 ++--- .../testing/selftests/sched_ext/hotplug.bpf.c | 8 +-- .../sched_ext/init_enable_count.bpf.c | 8 +-- .../testing/selftests/sched_ext/maximal.bpf.c | 58 +++++++++---------- .../selftests/sched_ext/maybe_null.bpf.c | 6 +- .../sched_ext/maybe_null_fail_dsp.bpf.c | 4 +- .../sched_ext/maybe_null_fail_yld.bpf.c | 4 +- .../selftests/sched_ext/prog_run.bpf.c | 2 +- .../selftests/sched_ext/select_cpu_dfl.bpf.c | 2 +- .../sched_ext/select_cpu_dfl_nodispatch.bpf.c | 6 +- .../sched_ext/select_cpu_dispatch.bpf.c | 2 +- .../select_cpu_dispatch_bad_dsq.bpf.c | 4 +- .../select_cpu_dispatch_dbl_dsp.bpf.c | 4 +- .../sched_ext/select_cpu_vtime.bpf.c | 12 ++-- 19 files changed, 80 insertions(+), 80 deletions(-) diff --git a/tools/testing/selftests/sched_ext/create_dsq.bpf.c b/tools/testing/selftests/sched_ext/create_dsq.bpf.c index 23f79ed343f02..2cfc4ffd60e28 100644 --- a/tools/testing/selftests/sched_ext/create_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/create_dsq.bpf.c @@ -51,8 +51,8 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init) SEC(".struct_ops.link") struct sched_ext_ops create_dsq_ops = { - .init_task = create_dsq_init_task, - .exit_task = create_dsq_exit_task, - .init = create_dsq_init, + .init_task = (void *) create_dsq_init_task, + .exit_task = (void *) create_dsq_exit_task, + .init = (void *) create_dsq_init, .name = "create_dsq", }; diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index e97ad41d354ad..37d9bf6fb7458 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -35,8 +35,8 @@ void BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops ddsp_bogus_dsq_fail_ops = { - .select_cpu = ddsp_bogus_dsq_fail_select_cpu, - .exit = ddsp_bogus_dsq_fail_exit, + .select_cpu = (void *) ddsp_bogus_dsq_fail_select_cpu, + .exit = (void *) ddsp_bogus_dsq_fail_exit, .name = "ddsp_bogus_dsq_fail", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dde7e7dafbfbc..dffc97d9cdf14 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -32,8 +32,8 @@ void BPF_STRUCT_OPS(ddsp_vtimelocal_fail_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops ddsp_vtimelocal_fail_ops = { - .select_cpu = ddsp_vtimelocal_fail_select_cpu, - .exit = ddsp_vtimelocal_fail_exit, + .select_cpu = (void *) ddsp_vtimelocal_fail_select_cpu, + .exit = (void *) ddsp_vtimelocal_fail_exit, .name = "ddsp_vtimelocal_fail", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index efb4672decb41..6a7db1502c29e 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -56,10 +56,10 @@ void BPF_STRUCT_OPS(dsp_local_on_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops dsp_local_on_ops = { - .select_cpu = dsp_local_on_select_cpu, - .enqueue = dsp_local_on_enqueue, - .dispatch = dsp_local_on_dispatch, - .exit = dsp_local_on_exit, + .select_cpu = (void *) dsp_local_on_select_cpu, + .enqueue = (void *) dsp_local_on_enqueue, + .dispatch = (void *) dsp_local_on_dispatch, + .exit = (void *) dsp_local_on_exit, .name = "dsp_local_on", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index b3dfc1033cd6a..1efb50d61040a 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -36,8 +36,8 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, SEC(".struct_ops.link") struct sched_ext_ops enq_select_cpu_fails_ops = { - .select_cpu = enq_select_cpu_fails_select_cpu, - .enqueue = enq_select_cpu_fails_enqueue, + .select_cpu = (void *) enq_select_cpu_fails_select_cpu, + .enqueue = (void *) enq_select_cpu_fails_enqueue, .name = "enq_select_cpu_fails", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index ae12ddaac921b..bf79ccd55f8f0 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -72,13 +72,13 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(exit_init) SEC(".struct_ops.link") struct sched_ext_ops exit_ops = { - .select_cpu = exit_select_cpu, - .enqueue = exit_enqueue, - .dispatch = exit_dispatch, - .init_task = exit_init_task, - .enable = exit_enable, - .exit = exit_exit, - .init = exit_init, + .select_cpu = (void *) exit_select_cpu, + .enqueue = (void *) exit_enqueue, + .dispatch = (void *) exit_dispatch, + .init_task = (void *) exit_init_task, + .enable = (void *) exit_enable, + .exit = (void *) exit_exit, + .init = (void *) exit_init, .name = "exit", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/hotplug.bpf.c b/tools/testing/selftests/sched_ext/hotplug.bpf.c index 8f2601db39f37..6c9f25c9bf53e 100644 --- a/tools/testing/selftests/sched_ext/hotplug.bpf.c +++ b/tools/testing/selftests/sched_ext/hotplug.bpf.c @@ -46,16 +46,16 @@ void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_offline, s32 cpu) SEC(".struct_ops.link") struct sched_ext_ops hotplug_cb_ops = { - .cpu_online = hotplug_cpu_online, - .cpu_offline = hotplug_cpu_offline, - .exit = hotplug_exit, + .cpu_online = (void *) hotplug_cpu_online, + .cpu_offline = (void *) hotplug_cpu_offline, + .exit = (void *) hotplug_exit, .name = "hotplug_cbs", .timeout_ms = 1000U, }; SEC(".struct_ops.link") struct sched_ext_ops hotplug_nocb_ops = { - .exit = hotplug_exit, + .exit = (void *) hotplug_exit, .name = "hotplug_nocbs", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c index 47ea89a626c37..5eb9edb1837dc 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c @@ -45,9 +45,9 @@ void BPF_STRUCT_OPS(cnt_disable, struct task_struct *p) SEC(".struct_ops.link") struct sched_ext_ops init_enable_count_ops = { - .init_task = cnt_init_task, - .exit_task = cnt_exit_task, - .enable = cnt_enable, - .disable = cnt_disable, + .init_task = (void *) cnt_init_task, + .exit_task = (void *) cnt_exit_task, + .enable = (void *) cnt_enable, + .disable = (void *) cnt_disable, .name = "init_enable_count", }; diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 00bfa9cb95d38..4d4cd8d966dba 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -131,34 +131,34 @@ void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) SEC(".struct_ops.link") struct sched_ext_ops maximal_ops = { - .select_cpu = maximal_select_cpu, - .enqueue = maximal_enqueue, - .dequeue = maximal_dequeue, - .dispatch = maximal_dispatch, - .runnable = maximal_runnable, - .running = maximal_running, - .stopping = maximal_stopping, - .quiescent = maximal_quiescent, - .yield = maximal_yield, - .core_sched_before = maximal_core_sched_before, - .set_weight = maximal_set_weight, - .set_cpumask = maximal_set_cpumask, - .update_idle = maximal_update_idle, - .cpu_acquire = maximal_cpu_acquire, - .cpu_release = maximal_cpu_release, - .cpu_online = maximal_cpu_online, - .cpu_offline = maximal_cpu_offline, - .init_task = maximal_init_task, - .enable = maximal_enable, - .exit_task = maximal_exit_task, - .disable = maximal_disable, - .cgroup_init = maximal_cgroup_init, - .cgroup_exit = maximal_cgroup_exit, - .cgroup_prep_move = maximal_cgroup_prep_move, - .cgroup_move = maximal_cgroup_move, - .cgroup_cancel_move = maximal_cgroup_cancel_move, - .cgroup_set_weight = maximal_cgroup_set_weight, - .init = maximal_init, - .exit = maximal_exit, + .select_cpu = (void *) maximal_select_cpu, + .enqueue = (void *) maximal_enqueue, + .dequeue = (void *) maximal_dequeue, + .dispatch = (void *) maximal_dispatch, + .runnable = (void *) maximal_runnable, + .running = (void *) maximal_running, + .stopping = (void *) maximal_stopping, + .quiescent = (void *) maximal_quiescent, + .yield = (void *) maximal_yield, + .core_sched_before = (void *) maximal_core_sched_before, + .set_weight = (void *) maximal_set_weight, + .set_cpumask = (void *) maximal_set_cpumask, + .update_idle = (void *) maximal_update_idle, + .cpu_acquire = (void *) maximal_cpu_acquire, + .cpu_release = (void *) maximal_cpu_release, + .cpu_online = (void *) maximal_cpu_online, + .cpu_offline = (void *) maximal_cpu_offline, + .init_task = (void *) maximal_init_task, + .enable = (void *) maximal_enable, + .exit_task = (void *) maximal_exit_task, + .disable = (void *) maximal_disable, + .cgroup_init = (void *) maximal_cgroup_init, + .cgroup_exit = (void *) maximal_cgroup_exit, + .cgroup_prep_move = (void *) maximal_cgroup_prep_move, + .cgroup_move = (void *) maximal_cgroup_move, + .cgroup_cancel_move = (void *) maximal_cgroup_cancel_move, + .cgroup_set_weight = (void *) maximal_cgroup_set_weight, + .init = (void *) maximal_init, + .exit = (void *) maximal_exit, .name = "maximal", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null.bpf.c b/tools/testing/selftests/sched_ext/maybe_null.bpf.c index 27d0f386acfb1..cf4ae870cd4e5 100644 --- a/tools/testing/selftests/sched_ext/maybe_null.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null.bpf.c @@ -29,8 +29,8 @@ bool BPF_STRUCT_OPS(maybe_null_success_yield, struct task_struct *from, SEC(".struct_ops.link") struct sched_ext_ops maybe_null_success = { - .dispatch = maybe_null_success_dispatch, - .yield = maybe_null_success_yield, - .enable = maybe_null_running, + .dispatch = (void *) maybe_null_success_dispatch, + .yield = (void *) maybe_null_success_yield, + .enable = (void *) maybe_null_running, .name = "minimal", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c index c0641050271d3..ec724d7b33d18 100644 --- a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c @@ -19,7 +19,7 @@ void BPF_STRUCT_OPS(maybe_null_fail_dispatch, s32 cpu, struct task_struct *p) SEC(".struct_ops.link") struct sched_ext_ops maybe_null_fail = { - .dispatch = maybe_null_fail_dispatch, - .enable = maybe_null_running, + .dispatch = (void *) maybe_null_fail_dispatch, + .enable = (void *) maybe_null_running, .name = "maybe_null_fail_dispatch", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c index 3c1740028e3b9..e6552cace020e 100644 --- a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c @@ -22,7 +22,7 @@ bool BPF_STRUCT_OPS(maybe_null_fail_yield, struct task_struct *from, SEC(".struct_ops.link") struct sched_ext_ops maybe_null_fail = { - .yield = maybe_null_fail_yield, - .enable = maybe_null_running, + .yield = (void *) maybe_null_fail_yield, + .enable = (void *) maybe_null_running, .name = "maybe_null_fail_yield", }; diff --git a/tools/testing/selftests/sched_ext/prog_run.bpf.c b/tools/testing/selftests/sched_ext/prog_run.bpf.c index 6a4d7c48e3f22..00c267626a68f 100644 --- a/tools/testing/selftests/sched_ext/prog_run.bpf.c +++ b/tools/testing/selftests/sched_ext/prog_run.bpf.c @@ -28,6 +28,6 @@ void BPF_STRUCT_OPS(prog_run_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops prog_run_ops = { - .exit = prog_run_exit, + .exit = (void *) prog_run_exit, .name = "prog_run", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index 2ed2991afafe3..f171ac4709706 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -35,6 +35,6 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dfl_ops = { - .enqueue = select_cpu_dfl_enqueue, + .enqueue = (void *) select_cpu_dfl_enqueue, .name = "select_cpu_dfl", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 4bb5abb2d3690..9efdbb7da9288 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -82,8 +82,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dfl_nodispatch_ops = { - .select_cpu = select_cpu_dfl_nodispatch_select_cpu, - .enqueue = select_cpu_dfl_nodispatch_enqueue, - .init_task = select_cpu_dfl_nodispatch_init_task, + .select_cpu = (void *) select_cpu_dfl_nodispatch_select_cpu, + .enqueue = (void *) select_cpu_dfl_nodispatch_enqueue, + .init_task = (void *) select_cpu_dfl_nodispatch_init_task, .name = "select_cpu_dfl_nodispatch", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index f0b96a4a04b2c..59bfc4f36167a 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -35,7 +35,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_ops = { - .select_cpu = select_cpu_dispatch_select_cpu, + .select_cpu = (void *) select_cpu_dispatch_select_cpu, .name = "select_cpu_dispatch", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 7b42ddce0f56c..3bbd5fcdfb18e 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -30,8 +30,8 @@ void BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_bad_dsq_ops = { - .select_cpu = select_cpu_dispatch_bad_dsq_select_cpu, - .exit = select_cpu_dispatch_bad_dsq_exit, + .select_cpu = (void *) select_cpu_dispatch_bad_dsq_select_cpu, + .exit = (void *) select_cpu_dispatch_bad_dsq_exit, .name = "select_cpu_dispatch_bad_dsq", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 653e3dc0b4dc8..0fda57fe0ecfa 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -31,8 +31,8 @@ void BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_dbl_dsp_ops = { - .select_cpu = select_cpu_dispatch_dbl_dsp_select_cpu, - .exit = select_cpu_dispatch_dbl_dsp_exit, + .select_cpu = (void *) select_cpu_dispatch_dbl_dsp_select_cpu, + .exit = (void *) select_cpu_dispatch_dbl_dsp_exit, .name = "select_cpu_dispatch_dbl_dsp", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index 7f3ebf4fc2ead..e6c67bcf5e6e3 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -81,12 +81,12 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(select_cpu_vtime_init) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_vtime_ops = { - .select_cpu = select_cpu_vtime_select_cpu, - .dispatch = select_cpu_vtime_dispatch, - .running = select_cpu_vtime_running, - .stopping = select_cpu_vtime_stopping, - .enable = select_cpu_vtime_enable, - .init = select_cpu_vtime_init, + .select_cpu = (void *) select_cpu_vtime_select_cpu, + .dispatch = (void *) select_cpu_vtime_dispatch, + .running = (void *) select_cpu_vtime_running, + .stopping = (void *) select_cpu_vtime_stopping, + .enable = (void *) select_cpu_vtime_enable, + .init = (void *) select_cpu_vtime_init, .name = "select_cpu_vtime", .timeout_ms = 1000U, }; -- 2.47.0

6 months

2
1
0 0

[PATCH v1 0/2] mseal: fixing madvise for file-backed mapping and PROT_NONE

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)google.com> Two fixes for madvise(MADV_DONTNEED) when sealed. For PROT_NONE mappings, the previous blocking of madvise(MADV_DONTNEED) is unnecessary. As PROT_NONE already prohibits memory access, madvise(MADV_DONTNEED) should be allowed to proceed in order to free the page. For file-backed, private, read-only memory mappings, we previously did not block the madvise(MADV_DONTNEED). This was based on the assumption that the memory's content, being file-backed, could be retrieved from the file if accessed again. However, this assumption failed to consider scenarios where a mapping is initially created as read-write, modified, and subsequently changed to read-only. The newly introduced VM_WASWRITE flag addresses this oversight. Jeff Xu (2): mseal: Two fixes for madvise(MADV_DONTNEED) when sealed selftest/mseal: Add tests for madvise include/linux/mm.h | 2 + mm/mprotect.c | 3 + mm/mseal.c | 42 +++++++-- tools/testing/selftests/mm/mseal_test.c | 118 +++++++++++++++++++++++- 4 files changed, 157 insertions(+), 8 deletions(-) -- 2.47.0.rc1.288.g06298d1525-goog

6 months

7
14
0 0

[PATCH V13 00/14] perf/core: Add ability for an event to "pause" or "resume" AUX area tracing

by Adrian Hunter

Hi Note for V12: There was a small conflict between the Intel PT changes in "KVM: x86: Fix Intel PT Host/Guest mode when host tracing" and the changes in this patch set, so I have put the patch sets together, along with outstanding fix "perf/x86/intel/pt: Fix buffer full but size is 0 case" Cover letter for KVM changes (patches 2 to 4): There is a long-standing problem whereby running Intel PT on host and guest in Host/Guest mode, causes VM-Entry failure. The motivation for this patch set is to provide a fix for stable kernels prior to the advent of the "Mediated Passthrough vPMU" patch set: https://lore.kernel.org/kvm/20240801045907.4010984-1-mizhang@google.com/ which would render a large part of the fix unnecessary but likely not be suitable for backport to stable due to its size and complexity. Ideally, this patch set would be applied before "Mediated Passthrough vPMU" Note that the fix does not conflict with "Mediated Passthrough vPMU", it is just that "Mediated Passthrough vPMU" will make the code to stop and restart Intel PT unnecessary. Note for V11: Moving aux_paused into a union within struct hw_perf_event caused a regression because aux_paused was being written unconditionally even though it is valid only for AUX (e.g. Intel PT) PMUs. That is fixed in V11. Hardware traces, such as instruction traces, can produce a vast amount of trace data, so being able to reduce tracing to more specific circumstances can be useful. The ability to pause or resume tracing when another event happens, can do that. These patches add such a facilty and show how it would work for Intel Processor Trace. Maintainers of other AUX area tracing implementations are requested to consider if this is something they might employ and then whether or not the ABI would work for them. Note, thank you to James Clark (ARM) for evaluating the API for Coresight. Suzuki K Poulose (ARM) also responded positively to the RFC. Changes to perf tools are now (since V4) fleshed out. Please note, Intel® Architecture Instruction Set Extensions and Future Features Programming Reference March 2024 319433-052, currently: https://cdrdv2.intel.com/v1/dl/getContent/671368 introduces hardware pause / resume for Intel PT in a feature named Intel PT Trigger Tracing. For that more fields in perf_event_attr will be necessary. The main differences are: - it can be applied not just to overflows, but optionally to every event - a packet is emitted into the trace, optionally with IP information - no PMI - works with PMC and DR (breakpoint) events only Here are the proposed additions to perf_event_attr, please comment: diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 0c557f0a17b3..05dcc43f11bb 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -369,6 +369,22 @@ enum perf_event_read_format { PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ }; +enum { + PERF_AUX_ACTION_START_PAUSED = 1U << 0, + PERF_AUX_ACTION_PAUSE = 1U << 1, + PERF_AUX_ACTION_RESUME = 1U << 2, + PERF_AUX_ACTION_EMIT = 1U << 3, + PERF_AUX_ACTION_NR = 0x1f << 4, + PERF_AUX_ACTION_NO_IP = 1U << 9, + PERF_AUX_ACTION_PAUSE_ON_EVT = 1U << 10, + PERF_AUX_ACTION_RESUME_ON_EVT = 1U << 11, + PERF_AUX_ACTION_EMIT_ON_EVT = 1U << 12, + PERF_AUX_ACTION_NR_ON_EVT = 0x1f << 13, + PERF_AUX_ACTION_NO_IP_ON_EVT = 1U << 18, + PERF_AUX_ACTION_MASK = ~PERF_AUX_ACTION_START_PAUSED, + PERF_AUX_PAUSE_RESUME_MASK = PERF_AUX_ACTION_PAUSE | PERF_AUX_ACTION_RESUME, +}; + #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ #define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ #define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ @@ -515,10 +531,19 @@ struct perf_event_attr { union { __u32 aux_action; struct { - __u32 aux_start_paused : 1, /* start AUX area tracing paused */ - aux_pause : 1, /* on overflow, pause AUX area tracing */ - aux_resume : 1, /* on overflow, resume AUX area tracing */ - __reserved_3 : 29; + __u32 aux_start_paused : 1, /* start AUX area tracing paused */ + aux_pause : 1, /* on overflow, pause AUX area tracing */ + aux_resume : 1, /* on overflow, resume AUX area tracing */ + aux_emit : 1, /* generate AUX records instead of events */ + aux_nr : 5, /* AUX area tracing reference number */ + aux_no_ip : 1, /* suppress IP in AUX records */ + /* Following apply to event occurrence not overflows */ + aux_pause_on_evt : 1, /* on event, pause AUX area tracing */ + aux_resume_on_evt : 1, /* on event, resume AUX area tracing */ + aux_emit_on_evt : 1, /* generate AUX records instead of events */ + aux_nr_on_evt : 5, /* AUX area tracing reference number */ + aux_no_ip_on_evt : 1, /* suppress IP in AUX records */ + __reserved_3 : 13; }; }; Changes in V13: perf/core: Add aux_pause, aux_resume, aux_start_paused Do aux_resume at the end of __perf_event_overflow() so as to trace less of perf itself perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume Add error message also in EOPNOTSUPP case (Leo) Changes in V12: Add previously sent patch "perf/x86/intel/pt: Fix buffer full but size is 0 case" Add previously sent patch set "KVM: x86: Fix Intel PT Host/Guest mode when host tracing" Rebase on current tip plus patch set "KVM: x86: Fix Intel PT Host/Guest mode when host tracing" Changes in V11: perf/core: Add aux_pause, aux_resume, aux_start_paused Make assignment to event->hw.aux_paused conditional on (pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE). perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling Remove definition of has_aux_action() because it has already been added as an inline function. perf/x86/intel/pt: Fix sampling synchronization perf tools: Enable evsel__is_aux_event() to work for ARM/ARM64 perf tools: Enable evsel__is_aux_event() to work for S390_CPUMSF Dropped because they have already been applied Changes in V10: perf/core: Add aux_pause, aux_resume, aux_start_paused Move aux_paused into a union within struct hw_perf_event. Additional comment wrt PERF_EF_PAUSE/PERF_EF_RESUME. Factor out has_aux_action() as an inline function. Use scoped_guard for irqsave. Move calls of perf_event_aux_pause() from __perf_event_output() to __perf_event_overflow(). Changes in V9: perf/x86/intel/pt: Fix sampling synchronization New patch perf/core: Add aux_pause, aux_resume, aux_start_paused Move aux_paused to struct hw_perf_event perf/x86/intel/pt: Add support for pause / resume Add more comments and barriers for resume_allowed and pause_allowed Always use WRITE_ONCE with resume_allowed Changes in V8: perf tools: Parse aux-action Fix clang warning: util/auxtrace.c:821:7: error: missing field 'aux_action' initializer [-Werror,-Wmissing-field-initializers] 821 | {NULL}, | ^ Changes in V7: Add Andi's Reviewed-by for patches 2-12 Re-base Changes in V6: perf/core: Add aux_pause, aux_resume, aux_start_paused Removed READ/WRITE_ONCE from __perf_event_aux_pause() Expanded comment about guarding against NMI Changes in V5: perf/core: Add aux_pause, aux_resume, aux_start_paused Added James' Ack perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling New patch perf tools Added Ian's Ack Changes in V4: perf/core: Add aux_pause, aux_resume, aux_start_paused Rename aux_output_cfg -> aux_action Reorder aux_action bits from: aux_pause, aux_resume, aux_start_paused to: aux_start_paused, aux_pause, aux_resume Fix aux_action bits __u64 -> __u32 coresight: Have a stab at support for pause / resume Dropped perf tools All new patches Changes in RFC V3: coresight: Have a stab at support for pause / resume 'mode' -> 'flags' so it at least compiles Changes in RFC V2: Use ->stop() / ->start() instead of ->pause_resume() Move aux_start_paused bit into aux_output_cfg Tighten up when Intel PT pause / resume is allowed Add an example of how it might work for CoreSight Adrian Hunter (14): perf/x86/intel/pt: Fix buffer full but size is 0 case KVM: x86: Fix Intel PT IA32_RTIT_CTL MSR validation KVM: x86: Fix Intel PT Host/Guest mode when host tracing also KVM: selftests: Add guest Intel PT test perf/core: Add aux_pause, aux_resume, aux_start_paused perf/x86/intel/pt: Add support for pause / resume perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling perf tools: Add aux_start_paused, aux_pause and aux_resume perf tools: Add aux-action config term perf tools: Parse aux-action perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume perf intel-pt: Improve man page format perf intel-pt: Add documentation for pause / resume perf intel-pt: Add a test for pause / resume arch/x86/events/intel/core.c | 4 +- arch/x86/events/intel/pt.c | 209 +++++++- arch/x86/events/intel/pt.h | 16 + arch/x86/include/asm/intel_pt.h | 4 + arch/x86/kvm/vmx/vmx.c | 26 +- arch/x86/kvm/vmx/vmx.h | 1 - include/linux/perf_event.h | 28 + include/uapi/linux/perf_event.h | 11 +- kernel/events/core.c | 75 ++- kernel/events/internal.h | 1 + tools/include/uapi/linux/perf_event.h | 11 +- tools/perf/Documentation/perf-intel-pt.txt | 596 +++++++++++++-------- tools/perf/Documentation/perf-record.txt | 4 + tools/perf/builtin-record.c | 4 +- tools/perf/tests/shell/test_intel_pt.sh | 28 + tools/perf/util/auxtrace.c | 67 ++- tools/perf/util/auxtrace.h | 6 +- tools/perf/util/evsel.c | 15 + tools/perf/util/evsel.h | 1 + tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 10 + tools/perf/util/parse-events.h | 1 + tools/perf/util/parse-events.l | 1 + tools/perf/util/perf_event_attr_fprintf.c | 3 + tools/perf/util/pmu.c | 1 + tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/x86_64/processor.h | 1 + tools/testing/selftests/kvm/x86_64/intel_pt.c | 381 +++++++++++++ 28 files changed, 1243 insertions(+), 264 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/intel_pt.c Regards Adrian

6 months

4
23
0 0

[PATCH net-next v5 0/3] Threads support in proc connector

by Anjali Kulkarni

Recently we committed a fix to allow processes to receive notifications for non-zero exits via the process connector module. Commit is a4c9a56e6a2c. However, for threads, when it does a pthread_exit(&exit_status) call, the kernel is not aware of the exit status with which pthread_exit is called. It is sent by child thread to the parent process, if it is waiting in pthread_join(). Hence, for a thread exiting abnormally, kernel cannot send notifications to any listening processes. The exception to this is if the thread is sent a signal which it has not handled, and dies along with it's process as a result; for eg. SIGSEGV or SIGKILL. In this case, kernel is aware of the non-zero exit and sends a notification for it. For our use case, we cannot have parent wait in pthread_join, one of the main reasons for this being that we do not want to track normal pthread_exit(), which could be a very large number. We only want to be notified of any abnormal exits. Hence, threads are created with pthread_attr_t set to PTHREAD_CREATE_DETACHED. To fix this problem, we add a new type PROC_CN_MCAST_NOTIFY to proc connector API, which allows a thread to send it's exit status to kernel either when it needs to call pthread_exit() with non-zero value to indicate some error or from signal handler before pthread_exit(). We also need to filter packets with non-zero exit notifications futher based on instances, which can be identified by task names. Hence, added a comm field to the packet's struct proc_event, in which task->comm is stored. v4->v5 changes: - Handled comment by Stanislav Fomichev to fix a print format error. - Made thread.c completely automated by starting proc_filter program from within threads.c. - Changed name CONFIG_CN_HASH_KUNIT_TEST to CN_HASH_KUNIT_TEST in Kconfig.debug and changed display text. v3->v4 changes: - Reduce size of exit.log by removing unnecessary text. v2->v3 changes: - Handled comment by Liam Howlett to set hdev to NULL and add comment on it. - Handled comment by Liam Howlett to combine functions for deleting+get and deleting into one in cn_hash.c - Handled comment by Liam Howlett to remove extern in the functions defined in cn_hash_test.h - Some nits by Liam Howlett fixed. - Handled comment by Liam Howlett to make threads test automated. proc_filter.c creates exit.log, which is read by thread.c and checks the values reported. - Added "comm" field to struct proc_event, to copy the task's name to the packet to allow further filtering by packets. v1->v2 changes: - Handled comment by Peter Zijlstra to remove locking for PF_EXIT_NOTIFY task->flags. - Added error handling in thread.c v->v1 changes: - Handled comment by Simon Horman to remove unused err in cn_proc.c - Handled comment by Simon Horman to make adata and key_display static in cn_hash_test.c Anjali Kulkarni (3): connector/cn_proc: Add hash table for threads connector/cn_proc: Kunit tests for threads hash table connector/cn_proc: Selftest for threads drivers/connector/Makefile | 2 +- drivers/connector/cn_hash.c | 221 +++++++++++++++++ drivers/connector/cn_proc.c | 62 ++++- drivers/connector/connector.c | 75 +++++- include/linux/connector.h | 35 +++ include/linux/sched.h | 2 +- include/uapi/linux/cn_proc.h | 5 +- lib/Kconfig.debug | 17 ++ lib/Makefile | 1 + lib/cn_hash_test.c | 167 +++++++++++++ lib/cn_hash_test.h | 10 + tools/testing/selftests/connector/Makefile | 23 +- .../testing/selftests/connector/proc_filter.c | 34 ++- tools/testing/selftests/connector/thread.c | 232 ++++++++++++++++++ .../selftests/connector/thread_filter.c | 96 ++++++++ 15 files changed, 967 insertions(+), 15 deletions(-) create mode 100644 drivers/connector/cn_hash.c create mode 100644 lib/cn_hash_test.c create mode 100644 lib/cn_hash_test.h create mode 100644 tools/testing/selftests/connector/thread.c create mode 100644 tools/testing/selftests/connector/thread_filter.c -- 2.46.0

6 months

4
20
0 0

[PATCH AUTOSEL 6.6 03/23] selftests/bpf: Verify that sync_linked_regs preserves subreg_def

by Sasha Levin

From: Eduard Zingerman <eddyz87(a)gmail.com> [ Upstream commit a41b3828ec056a631ad22413d4560017fed5c3bd ] This test was added because of a bug in verifier.c:sync_linked_regs(), upon range propagation it destroyed subreg_def marks for registers. The test is written in a way to return an upper half of a register that is affected by range propagation and must have it's subreg_def preserved. This gives a return value of 0 and leads to undefined return value if subreg_def mark is not preserved. Signed-off-by: Eduard Zingerman <eddyz87(a)gmail.com> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Acked-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20240924210844.1758441-2-eddyz87@gmail.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../selftests/bpf/progs/verifier_scalar_ids.c | 67 +++++++++++++++++++ 1 file changed, 67 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 13b29a7faa71a..d24d3a36ec144 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -656,4 +656,71 @@ __naked void two_old_ids_one_cur_id(void) : __clobber_all); } +SEC("socket") +/* Note the flag, see verifier.c:opt_subreg_zext_lo32_rnd_hi32() */ +__flag(BPF_F_TEST_RND_HI32) +__success +/* This test was added because of a bug in verifier.c:sync_linked_regs(), + * upon range propagation it destroyed subreg_def marks for registers. + * The subreg_def mark is used to decide whether zero extension instructions + * are needed when register is read. When BPF_F_TEST_RND_HI32 is set it + * also causes generation of statements to randomize upper halves of + * read registers. + * + * The test is written in a way to return an upper half of a register + * that is affected by range propagation and must have it's subreg_def + * preserved. This gives a return value of 0 and leads to undefined + * return value if subreg_def mark is not preserved. + */ +__retval(0) +/* Check that verifier believes r1/r0 are zero at exit */ +__log_level(2) +__msg("4: (77) r1 >>= 32 ; R1_w=0") +__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("6: (95) exit") +__msg("from 3 to 4") +__msg("4: (77) r1 >>= 32 ; R1_w=0") +__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("6: (95) exit") +/* Verify that statements to randomize upper half of r1 had not been + * generated. + */ +__xlated("call unknown") +__xlated("r0 &= 2147483647") +__xlated("w1 = w0") +/* This is how disasm.c prints BPF_ZEXT_REG at the moment, x86 and arm + * are the only CI archs that do not need zero extension for subregs. + */ +#if !defined(__TARGET_ARCH_x86) && !defined(__TARGET_ARCH_arm64) +__xlated("w1 = w1") +#endif +__xlated("if w0 < 0xa goto pc+0") +__xlated("r1 >>= 32") +__xlated("r0 = r1") +__xlated("exit") +__naked void linked_regs_and_subreg_def(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* make sure r0 is in 32-bit range, otherwise w1 = w0 won't + * assign same IDs to registers. + */ + "r0 &= 0x7fffffff;" + /* link w1 and w0 via ID */ + "w1 = w0;" + /* 'if' statement propagates range info from w0 to w1, + * but should not affect w1->subreg_def property. + */ + "if w0 < 10 goto +0;" + /* r1 is read here, on archs that require subreg zero + * extension this would cause zext patch generation. + */ + "r1 >>= 32;" + "r0 = r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; -- 2.43.0

6 months

1
0
0 0

[PATCH AUTOSEL 6.11 20/30] selftests/bpf: Assert link info uprobe_multi count & path_size if unset

by Sasha Levin

From: Tyrone Wu <wudevelops(a)gmail.com> [ Upstream commit b836cbdf3b81a4a22b3452186efa2e5105a77e10 ] Add assertions in `bpf_link_info.uprobe_multi` test to verify that `count` and `path_size` fields are correctly populated when the fields are unset. This tests a previous bug where the `path_size` field was not populated when `path` and `path_size` were unset. Signed-off-by: Tyrone Wu <wudevelops(a)gmail.com> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Link: https://lore.kernel.org/bpf/20241011000803.681190-2-wudevelops@gmail.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/bpf/prog_tests/fill_link_info.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index f3932941bbaaf..59ef57145b63c 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -417,6 +417,15 @@ verify_umulti_link_info(int fd, bool retprobe, __u64 *offsets, if (!ASSERT_NEQ(err, -1, "readlink")) return -1; + memset(&info, 0, sizeof(info)); + err = bpf_link_get_info_by_fd(fd, &info, &len); + if (!ASSERT_OK(err, "bpf_link_get_info_by_fd")) + return -1; + + ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count"); + ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1, + "info.uprobe_multi.path_size"); + for (bit = 0; bit < 8; bit++) { memset(&info, 0, sizeof(info)); info.uprobe_multi.path = ptr_to_u64(path_buf); -- 2.43.0

6 months

1
0
0 0

[PATCH AUTOSEL 6.11 03/30] selftests/bpf: Verify that sync_linked_regs preserves subreg_def

by Sasha Levin

From: Eduard Zingerman <eddyz87(a)gmail.com> [ Upstream commit a41b3828ec056a631ad22413d4560017fed5c3bd ] This test was added because of a bug in verifier.c:sync_linked_regs(), upon range propagation it destroyed subreg_def marks for registers. The test is written in a way to return an upper half of a register that is affected by range propagation and must have it's subreg_def preserved. This gives a return value of 0 and leads to undefined return value if subreg_def mark is not preserved. Signed-off-by: Eduard Zingerman <eddyz87(a)gmail.com> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Acked-by: Daniel Borkmann <daniel(a)iogearbox.net> Link: https://lore.kernel.org/bpf/20240924210844.1758441-2-eddyz87@gmail.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- .../selftests/bpf/progs/verifier_scalar_ids.c | 67 +++++++++++++++++++ 1 file changed, 67 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 13b29a7faa71a..d24d3a36ec144 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -656,4 +656,71 @@ __naked void two_old_ids_one_cur_id(void) : __clobber_all); } +SEC("socket") +/* Note the flag, see verifier.c:opt_subreg_zext_lo32_rnd_hi32() */ +__flag(BPF_F_TEST_RND_HI32) +__success +/* This test was added because of a bug in verifier.c:sync_linked_regs(), + * upon range propagation it destroyed subreg_def marks for registers. + * The subreg_def mark is used to decide whether zero extension instructions + * are needed when register is read. When BPF_F_TEST_RND_HI32 is set it + * also causes generation of statements to randomize upper halves of + * read registers. + * + * The test is written in a way to return an upper half of a register + * that is affected by range propagation and must have it's subreg_def + * preserved. This gives a return value of 0 and leads to undefined + * return value if subreg_def mark is not preserved. + */ +__retval(0) +/* Check that verifier believes r1/r0 are zero at exit */ +__log_level(2) +__msg("4: (77) r1 >>= 32 ; R1_w=0") +__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("6: (95) exit") +__msg("from 3 to 4") +__msg("4: (77) r1 >>= 32 ; R1_w=0") +__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("6: (95) exit") +/* Verify that statements to randomize upper half of r1 had not been + * generated. + */ +__xlated("call unknown") +__xlated("r0 &= 2147483647") +__xlated("w1 = w0") +/* This is how disasm.c prints BPF_ZEXT_REG at the moment, x86 and arm + * are the only CI archs that do not need zero extension for subregs. + */ +#if !defined(__TARGET_ARCH_x86) && !defined(__TARGET_ARCH_arm64) +__xlated("w1 = w1") +#endif +__xlated("if w0 < 0xa goto pc+0") +__xlated("r1 >>= 32") +__xlated("r0 = r1") +__xlated("exit") +__naked void linked_regs_and_subreg_def(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* make sure r0 is in 32-bit range, otherwise w1 = w0 won't + * assign same IDs to registers. + */ + "r0 &= 0x7fffffff;" + /* link w1 and w0 via ID */ + "w1 = w0;" + /* 'if' statement propagates range info from w0 to w1, + * but should not affect w1->subreg_def property. + */ + "if w0 < 10 goto +0;" + /* r1 is read here, on archs that require subreg zero + * extension this would cause zext patch generation. + */ + "r1 >>= 32;" + "r0 = r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; -- 2.43.0

6 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror