January 2023 - Linux-kselftest-mirror

[RFC PATCH 19/19] selftests/vm: Add pins-cgroup selftest for mlock/mmap

by Alistair Popple

Add some basic tests of mlock/mmap cgroup accounting for pinned memory. Signed-off-by: Alistair Popple <apopple(a)nvidia.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-kernel(a)vger.kernel.org Cc: linux-mm(a)kvack.org Cc: linux-kselftest(a)vger.kernel.org Cc: cgroups(a)vger.kernel.org --- MAINTAINERS | 1 +- tools/testing/selftests/vm/Makefile | 1 +- tools/testing/selftests/vm/pins-cgroup.c | 271 ++++++++++++++++++++++++- 3 files changed, 273 insertions(+) create mode 100644 tools/testing/selftests/vm/pins-cgroup.c diff --git a/MAINTAINERS b/MAINTAINERS index f8526e2..4c4eed9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5387,6 +5387,7 @@ L: cgroups(a)vger.kernel.org L: linux-mm(a)kvack.org S: Maintained F: mm/pins_cgroup.c +F: tools/testing/selftests/vm/pins-cgroup.c CORETEMP HARDWARE MONITORING DRIVER M: Fenghua Yu <fenghua.yu(a)intel.com> diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 89c14e4..0653720 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -56,6 +56,7 @@ TEST_GEN_PROGS += soft-dirty TEST_GEN_PROGS += split_huge_page_test TEST_GEN_FILES += ksm_tests TEST_GEN_PROGS += ksm_functional_tests +TEST_GEN_FILES += pins-cgroup ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) diff --git a/tools/testing/selftests/vm/pins-cgroup.c b/tools/testing/selftests/vm/pins-cgroup.c new file mode 100644 index 0000000..c2eabc2 --- /dev/null +++ b/tools/testing/selftests/vm/pins-cgroup.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "../kselftest_harness.h" + +#define _GNU_SOURCE +#include <fcntl.h> +#include <assert.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/ioctl.h> +#include <sys/prctl.h> +#include <sys/resource.h> +#include <sys/capability.h> +#include <unistd.h> + +#define CGROUP_TEMP "/sys/fs/cgroup/pins_XXXXXX" +#define PINS_MAX (-1UL) + +FIXTURE(pins_cg) +{ + char *cg_path; + long page_size; +}; + +static char *cgroup_new(void) +{ + char *cg; + + cg = malloc(sizeof(CGROUP_TEMP)); + strcpy(cg, CGROUP_TEMP); + if (!mkdtemp(cg)) { + perror("Failed to create cgroup"); + return NULL; + } + + return cg; +} + +static int cgroup_add_proc(char *cg, pid_t pid) +{ + char *cg_proc; + FILE *f; + int ret = 0; + + if (asprintf(&cg_proc, "%s/cgroup.procs", cg) < 0) + return -1; + + f = fopen(cg_proc, "w"); + free(cg_proc); + if (!f) + return -1; + + if (fprintf(f, "%ld\n", (long) pid) < 0) + ret = -1; + + fclose(f); + return ret; +} + +static int cgroup_set_limit(char *cg, unsigned long limit) +{ + char *cg_pins_max; + FILE *f; + int ret = 0; + + if (asprintf(&cg_pins_max, "%s/pins.max", cg) < 0) + return -1; + + f = fopen(cg_pins_max, "w"); + free(cg_pins_max); + if (!f) + return -1; + + if (limit != PINS_MAX) { + if (fprintf(f, "%ld\n", limit) < 0) + ret = -1; + } else { + if (fprintf(f, "max\n") < 0) + ret = -1; + } + + fclose(f); + return ret; +} + +FIXTURE_SETUP(pins_cg) +{ + char *cg_subtree_control; + FILE *f; + + if (asprintf(&cg_subtree_control, + "/sys/fs/cgroup/cgroup.subtree_control") < 0) + return; + + f = fopen(cg_subtree_control, "w"); + free(cg_subtree_control); + if (!f) + return; + + fprintf(f, "+pins\n"); + fclose(f); + + self->cg_path = cgroup_new(); + self->page_size = sysconf(_SC_PAGE_SIZE); +} + +FIXTURE_TEARDOWN(pins_cg) +{ + cgroup_add_proc("/sys/fs/cgroup", getpid()); + + rmdir(self->cg_path); + free(self->cg_path); +} + +static long cgroup_pins(char *cg) +{ + long pin_count; + char *cg_pins_current; + FILE *f; + int ret; + + if (asprintf(&cg_pins_current, "%s/pins.current", cg) < 0) + return -1; + + f = fopen(cg_pins_current, "r"); + if (!f) { + printf("Can't open %s\n", cg_pins_current); + getchar(); + free(cg_pins_current); + return -2; + } + + free(cg_pins_current); + + if (fscanf(f, "%ld", &pin_count) == EOF) + ret = -3; + else + ret = pin_count; + + fclose(f); + return ret; +} + +static int set_rlim_memlock(unsigned long size) +{ + struct rlimit rlim_memlock = { + .rlim_cur = size, + .rlim_max = size, + }; + cap_t cap; + cap_value_t capability[1] = { CAP_IPC_LOCK }; + + /* + * Many of the rlimit checks are skipped if a process has + * CAP_IP_LOCK. As this test should be run as root we need to + * explicitly drop it. + */ + cap = cap_get_proc(); + if (!cap) + return -1; + if (cap_set_flag(cap, CAP_EFFECTIVE, 1, capability, CAP_CLEAR)) + return -1; + if (cap_set_proc(cap)) + return -1; + return setrlimit(RLIMIT_MEMLOCK, &rlim_memlock); +} + +TEST_F(pins_cg, basic) +{ + pid_t child_pid; + long page_size = self->page_size; + char *p; + + ASSERT_EQ(cgroup_add_proc(self->cg_path, getpid()), 0); + p = mmap(NULL, 32*page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + ASSERT_NE(p, MAP_FAILED); + + ASSERT_EQ(cgroup_pins(self->cg_path), 0); + memset(p, 0, 16*page_size); + ASSERT_EQ(mlock(p, page_size), 0); + ASSERT_EQ(cgroup_pins(self->cg_path), 1); + ASSERT_EQ(mlock(p + page_size, page_size), 0); + ASSERT_EQ(cgroup_pins(self->cg_path), 2); + ASSERT_EQ(mlock(p, page_size), 0); + ASSERT_EQ(cgroup_pins(self->cg_path), 2); + ASSERT_EQ(mlock(p, 4*page_size), 0); + ASSERT_EQ(cgroup_pins(self->cg_path), 4); + ASSERT_EQ(munlock(p + 2*page_size, 2*page_size), 0); + ASSERT_EQ(cgroup_pins(self->cg_path), 2); + ASSERT_EQ(cgroup_set_limit(self->cg_path, 8), 0); + ASSERT_EQ(mlock(p, 16*page_size), -1); + ASSERT_EQ(errno, ENOMEM); + ASSERT_EQ(cgroup_pins(self->cg_path), 2); + ASSERT_EQ(cgroup_set_limit(self->cg_path, PINS_MAX), 0); + + /* check mremap() a locked region correctly accounts locked pages */ + ASSERT_EQ(mlock(p, 32*page_size), 0); + ASSERT_EQ(cgroup_pins(self->cg_path), 32); + p = mremap(p, 32*page_size, 64*page_size, MREMAP_MAYMOVE); + ASSERT_NE(p, MAP_FAILED); + ASSERT_EQ(cgroup_pins(self->cg_path), 64); + ASSERT_EQ(munmap(p + 32*page_size, 32*page_size), 0) + ASSERT_EQ(cgroup_pins(self->cg_path), 32); + p = mremap(p, 32*page_size, 32*page_size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP); + ASSERT_NE(p, MAP_FAILED); + ASSERT_EQ(cgroup_pins(self->cg_path), 32); + ASSERT_EQ(munlock(p, 32*page_size), 0); + + /* mremap() a locked region should fail if limit exceeded */ + ASSERT_EQ(set_rlim_memlock(32*page_size), 0); + ASSERT_EQ(mlock(p, 32*page_size), 0); + ASSERT_EQ(mremap(p, 32*page_size, 64*page_size, 0), MAP_FAILED); + ASSERT_EQ(munlock(p, 32*page_size), 0); + + /* Exceeds rlimit, expected to fail */ + ASSERT_EQ(set_rlim_memlock(16*page_size), 0); + ASSERT_EQ(mlock(p, 32*page_size), -1); + ASSERT_EQ(errno, ENOMEM); + + /* memory in the child isn't locked so shouldn't increase pin_cg count */ + ASSERT_EQ(mlock(p, 16*page_size), 0); + child_pid = fork(); + if (!child_pid) { + ASSERT_EQ(cgroup_pins(self->cg_path), 16); + ASSERT_EQ(mlock(p, 16*page_size), 0); + ASSERT_EQ(cgroup_pins(self->cg_path), 32); + return; + + } + waitpid(child_pid, NULL, 0); + + /* check that child exit uncharged the pins */ + ASSERT_EQ(cgroup_pins(self->cg_path), 16); +} + +TEST_F(pins_cg, mmap) +{ + char *p; + + ASSERT_EQ(cgroup_add_proc(self->cg_path, getpid()), 0); + p = mmap(NULL, 4*self->page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_LOCKED, -1, 0); + ASSERT_NE(p, MAP_FAILED); + ASSERT_EQ(cgroup_pins(self->cg_path), 4); +} + +/* + * Test moving to a different cgroup. + */ +TEST_F(pins_cg, move_cg) +{ + char *p, *new_cg; + + ASSERT_EQ(cgroup_add_proc(self->cg_path, getpid()), 0); + p = mmap(NULL, 16*self->page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + ASSERT_NE(p, MAP_FAILED); + memset(p, 0, 16*self->page_size); + ASSERT_EQ(mlock(p, 16*self->page_size), 0); + ASSERT_EQ(cgroup_pins(self->cg_path), 16); + ASSERT_NE(new_cg = cgroup_new(), NULL); + ASSERT_EQ(cgroup_add_proc(new_cg, getpid()), 0); + ASSERT_EQ(cgroup_pins(new_cg), 16); + ASSERT_EQ(cgroup_add_proc(self->cg_path, getpid()), 0); + rmdir(new_cg); +} +TEST_HARNESS_MAIN -- git-series 0.9.1

2 years, 9 months

1
0
0 0

[PATCH 0/2] selftests/nolibc: small simplification of test development phase

by Willy Tarreau

Hello Paul, while developing and testing the recent changes for errno/environ/auxv, I found that I wasn't relying on the kernel that much and that I was mostly using qemu in userland only with my local kernel. I figured that it was more convenient for this purpose than rebuilding an initramfs and kernel for a quick test, and decided to make this approach easier to use for everyone by adding a "run-user" target to the Makefile to do exactly this. E.g: Native build: $ time make -C tools/testing/selftests/nolibc run-user ... make: Entering directory '/g/public/linux/master/tools/testing/selftests/nolibc' MKDIR sysroot/x86/include make[1]: Entering directory '/g/public/linux/master/tools/include/nolibc' make[2]: Entering directory '/g/public/linux/master' make[2]: Leaving directory '/g/public/linux/master' make[2]: Entering directory '/g/public/linux/master' INSTALL /g/public/linux/master/tools/testing/selftests/nolibc/sysroot/sysroot/include make[2]: Leaving directory '/g/public/linux/master' make[1]: Leaving directory '/g/public/linux/master/tools/include/nolibc' CC nolibc-test 18 chroot_root = -1 EPERM [FAIL] 43 link_dir = -1 EACCES != (-1 EPERM) [FAIL] See all results in /g/public/linux/master/tools/testing/selftests/nolibc/run.out make: Leaving directory '/g/public/linux/master/tools/testing/selftests/nolibc' real 0m0.966s user 0m0.731s sys 0m0.164s Cross build: $ time make -C tools/testing/selftests/nolibc run-user ARCH=s390 CROSS_COMPILE=/f/tc/nolibc/gcc-11.3.0-nolibc/s390-linux/bin/s390-linux- make: Entering directory '/g/public/linux/master/tools/testing/selftests/nolibc' MKDIR sysroot/s390/include make[1]: Entering directory '/g/public/linux/master/tools/include/nolibc' make[2]: Entering directory '/g/public/linux/master' make[2]: Leaving directory '/g/public/linux/master' make[2]: Entering directory '/g/public/linux/master' INSTALL /g/public/linux/master/tools/testing/selftests/nolibc/sysroot/sysroot/include make[2]: Leaving directory '/g/public/linux/master' make[1]: Leaving directory '/g/public/linux/master/tools/include/nolibc' CC nolibc-test 18 chroot_root = -1 EPERM [FAIL] 43 link_dir = -1 EACCES != (-1 EPERM) [FAIL] See all results in /g/public/linux/master/tools/testing/selftests/nolibc/run.out make: Leaving directory '/g/public/linux/master/tools/testing/selftests/nolibc' real 0m1.014s user 0m0.732s sys 0m0.183s In addition, the "x86_64" value for ARCH= is now supported as I got caught too many times with it not working in this subdir while it's used for the rest of the kernel ("x86" is used instead as coming from subarch.include). Generally you don't type it as x86_64 probably is the native build for most users, but when you start to test toolchains it's a different thing. There's no matter of urgency for these patches, they're just a bit of user-friendly stuff. As such, if you're fine with stacking them on top of what you already have for 6.3, that will be great, otherwise they can easily wait. Thank you! Willy [CCing Ammar who could benefit from this] --- Willy Tarreau (2): selftests/nolibc: support "x86_64" for arch name selftests/nolibc: add a "run-user" target to test the program in user land tools/testing/selftests/nolibc/Makefile | 10 ++++++++++ 1 file changed, 10 insertions(+) -- 2.17.5

2 years, 9 months

3
20
0 0

[PATCH] selftests: iommu: Fix test_cmd_destroy_access() call in user_copy

by Nicolin Chen

The test_cmd_destroy_access() should end with a semicolon, so add one. There is a test_ioctl_destroy(ioas_id) following already, so drop one. Fixes: 57f0988706fe ("iommufd: Add a selftest") Signed-off-by: Nicolin Chen <nicolinc(a)nvidia.com> --- tools/testing/selftests/iommu/iommufd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 8aa8a346cf22..fa08209268c4 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1259,7 +1259,7 @@ TEST_F(iommufd_mock_domain, user_copy) test_cmd_destroy_access_pages( access_cmd.id, access_cmd.access_pages.out_access_pages_id); - test_cmd_destroy_access(access_cmd.id) test_ioctl_destroy(ioas_id); + test_cmd_destroy_access(access_cmd.id); test_ioctl_destroy(ioas_id); } -- 2.39.0

2 years, 9 months

3
2
0 0

Re: [RESEND RFC PATCH v1 07/20] mm: add tracepoints to ksm

by Steven Rostedt

On Sun, 22 Jan 2023 21:00:29 -0800 Stefan Roesch <shr(a)devkernel.io> wrote: > This adds the following tracepoints to ksm: > - start / stop scan > - ksm enter / exit > - merge a page > - merge a page with ksm > - remove a page > - remove a rmap item > > Signed-off-by: Stefan Roesch <shr(a)devkernel.io> > --- > MAINTAINERS | 1 + > include/trace/events/ksm.h | 257 +++++++++++++++++++++++++++++++++++++ > mm/ksm.c | 20 ++- > 3 files changed, 276 insertions(+), 2 deletions(-) > create mode 100644 include/trace/events/ksm.h From the tracing pov: Reviewed-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> -- Steve

2 years, 9 months

1
0
0 0

Prezentacja

by Karol Michun

Dzień dobry! Czy mógłbym przedstawić rozwiązanie, które umożliwia monitoring każdego auta w czasie rzeczywistym w tym jego pozycję, zużycie paliwa i przebieg? Dodatkowo nasze narzędzie minimalizuje koszty utrzymania samochodów, skraca czas przejazdów, a także tworzenie planu tras czy dostaw. Z naszej wiedzy i doświadczenia korzysta już ponad 49 tys. Klientów. Monitorujemy 809 000 pojazdów na całym świecie, co jest naszą najlepszą wizytówką. Bardzo proszę o e-maila zwrotnego, jeśli moglibyśmy wspólnie omówić potencjał wykorzystania takiego rozwiązania w Państwa firmie. Pozdrawiam Karol Michun

2 years, 9 months

1
0
0 0

Re: [PATCH v13 3/3] tools/testing - seccomp test fixes for m68k

by Geert Uytterhoeven

CC linux-kselftest On Thu, Jan 12, 2023 at 4:55 AM Michael Schmitz <schmitzmic(a)gmail.com> wrote: > Add m68k seccomp definitions to seccomp_bpf self test code. > > Tested on ARAnyM. > > Signed-off-by: Michael Schmitz <schmitzmic(a)gmail.com> > > -- > Changes from v12: > > Michael Karcher: > - use correct definition of ARCH_REGS (use of struct pt_regs > cause stack overflow on passing register set to user space > due to size mismatch, and has some register offsets wrong) Thanks for the update! Reviewed-by: Geert Uytterhoeven <geert(a)linux-m68k.org> i.e. will queue in the m68k for-v6.3 branch. > --- a/tools/testing/selftests/seccomp/seccomp_bpf.c > +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c > @@ -138,6 +138,8 @@ struct seccomp_data { > # define __NR_seccomp 337 > # elif defined(__sh__) > # define __NR_seccomp 372 > +# elif defined(__mc68000__) > +# define __NR_seccomp 380 > # else > # warning "seccomp syscall number unknown for this architecture" > # define __NR_seccomp 0xffff > @@ -1838,6 +1840,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) > # define ARCH_REGS struct pt_regs > # define SYSCALL_NUM(_regs) (_regs).regs[3] > # define SYSCALL_RET(_regs) (_regs).regs[0] > +#elif defined(__mc68000__) > +# define ARCH_REGS struct user_regs_struct > +# define SYSCALL_NUM(_regs) (_regs).orig_d0 > +# define SYSCALL_RET(_regs) (_regs).d0 > #else > # error "Do not know how to find your architecture's registers and syscalls" > #endif > @@ -1902,7 +1908,7 @@ const bool ptrace_entry_set_syscall_ret = > * Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for > * architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux). > */ > -#if defined(__x86_64__) || defined(__i386__) || defined(__mips__) > +#if defined(__x86_64__) || defined(__i386__) || defined(__mips__) || defined(__mc68000__) > # define ARCH_GETREGS(_regs) ptrace(PTRACE_GETREGS, tracee, 0, &(_regs)) > # define ARCH_SETREGS(_regs) ptrace(PTRACE_SETREGS, tracee, 0, &(_regs)) > #else Gr{oetje,eeting}s, Geert -- Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert(a)linux-m68k.org In personal conversations with technical people, I call myself a hacker. But when I'm talking to journalists I just say "programmer" or something like that. -- Linus Torvalds

2 years, 9 months

1
0
0 0

[PATCH RFC 0/3] vsock: add support for sockmap

by Bobby Eshleman

Add support for sockmap to vsock. We're testing usage of vsock as a way to redirect guest-local UDS requests to the host and this patch series greatly improves the performance of such a setup. Compared to copying packets via userspace, this improves throughput by 221% in basic testing. Tested as follows. Setup: guest unix dgram sender -> guest vsock redirector -> host vsock server Threads: 1 Payload: 64k No sockmap: - 76.3 MB/s - The guest vsock redirector was "socat VSOCK-CONNECT:2:1234 UNIX-RECV:/path/to/sock" Using sockmap (this patch): - 168.8 MB/s (+221%) - The guest redirector was a simple sockmap echo server, redirecting unix ingress to vsock 2:1234 egress. - Same sender and server programs Only the virtio transport has been tested. The loopback transport was used in writing bpf/selftests, but not thoroughly tested otherwise. This series requires the skb patch. To: Stefan Hajnoczi <stefanha(a)redhat.com> To: Stefano Garzarella <sgarzare(a)redhat.com> To: "Michael S. Tsirkin" <mst(a)redhat.com> To: Jason Wang <jasowang(a)redhat.com> To: "David S. Miller" <davem(a)davemloft.net> To: Eric Dumazet <edumazet(a)google.com> To: Jakub Kicinski <kuba(a)kernel.org> To: Paolo Abeni <pabeni(a)redhat.com> To: Andrii Nakryiko <andrii(a)kernel.org> To: Mykola Lysenko <mykolal(a)fb.com> To: Alexei Starovoitov <ast(a)kernel.org> To: Daniel Borkmann <daniel(a)iogearbox.net> To: Martin KaFai Lau <martin.lau(a)linux.dev> To: Song Liu <song(a)kernel.org> To: Yonghong Song <yhs(a)fb.com> To: John Fastabend <john.fastabend(a)gmail.com> To: KP Singh <kpsingh(a)kernel.org> To: Stanislav Fomichev <sdf(a)google.com> To: Hao Luo <haoluo(a)google.com> To: Jiri Olsa <jolsa(a)kernel.org> To: Shuah Khan <shuah(a)kernel.org> Cc: linux-kernel(a)vger.kernel.org Cc: kvm(a)vger.kernel.org Cc: virtualization(a)lists.linux-foundation.org Cc: netdev(a)vger.kernel.org Cc: bpf(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Bobby Eshleman <bobby.eshleman(a)bytedance.com> --- Bobby Eshleman (3): vsock: support sockmap selftests/bpf: add vsock to vmtest.sh selftests/bpf: Add a test case for vsock sockmap drivers/vhost/vsock.c | 1 + include/linux/virtio_vsock.h | 1 + include/net/af_vsock.h | 17 ++ net/vmw_vsock/Makefile | 1 + net/vmw_vsock/af_vsock.c | 59 ++++++- net/vmw_vsock/virtio_transport.c | 2 + net/vmw_vsock/virtio_transport_common.c | 22 +++ net/vmw_vsock/vsock_bpf.c | 180 +++++++++++++++++++++ net/vmw_vsock/vsock_loopback.c | 2 + tools/testing/selftests/bpf/config.x86_64 | 4 + .../selftests/bpf/prog_tests/sockmap_listen.c | 163 +++++++++++++++++++ tools/testing/selftests/bpf/vmtest.sh | 1 + 12 files changed, 447 insertions(+), 6 deletions(-) --- base-commit: f12f4326c6a75a74e908714be6d2f0e2f0fd0d76 change-id: 20230118-support-vsock-sockmap-connectible-2e1297d2111a Best regards, -- Bobby Eshleman <bobby.eshleman(a)bytedance.com>

2 years, 9 months

4
13
0 0

[PATCH v4 0/3] Checkpoint Support for Syscall User Dispatch

by Gregory Price

v4: Whitespace s/CHECKPOINT_RESTART/CHECKPOINT_RESUME check test_syscall_work(SYSCALL_USER_DISPATCH) to determine if it's turned on or not in fs/proc/array and getter interface v3: Kernel test robot static function fix Whitespace nitpicks v2: Implements the getter/setter interface in ptrace rather than prctl Syscall user dispatch makes it possible to cleanly intercept system calls from user-land. However, most transparent checkpoint software presently leverages some combination of ptrace and system call injection to place software in a ready-to-checkpoint state. If Syscall User Dispatch is enabled at the time of being quiesced, injected system calls will subsequently be interposed upon and dispatched to the task's signal handler. This patch set implements 3 features to enable software such as CRIU to cleanly interpose upon software leveraging syscall user dispatch. - Implement PTRACE_O_SUSPEND_SYSCALL_USER_DISPATCH, akin to a similar feature for SECCOMP. This allows a ptracer to temporarily disable syscall user dispatch, making syscall injection possible. - Implement an fs/proc extension that reports whether Syscall User Dispatch is being used in proc/status. A similar value is present for SECCOMP, and is used to determine whether special logic is needed during checkpoint/resume. - Implement a getter interface for Syscall User Dispatch config info. To resume successfully, the checkpoint/resume software has to save and restore this information. Presently this configuration is write-only, with no way for C/R software to save it. This was done in ptrace because syscall user dispatch is not part of uapi. The syscall_user_dispatch_config structure was added to the ptrace exports. Gregory Price (3): ptrace,syscall_user_dispatch: Implement Syscall User Dispatch Suspension fs/proc/array: Add Syscall User Dispatch to proc status ptrace,syscall_user_dispatch: add a getter/setter for sud configuration .../admin-guide/syscall-user-dispatch.rst | 5 +- fs/proc/array.c | 8 +++ include/linux/ptrace.h | 2 + include/linux/syscall_user_dispatch.h | 19 +++++++ include/uapi/linux/ptrace.h | 16 +++++- kernel/entry/syscall_user_dispatch.c | 51 +++++++++++++++++++ kernel/ptrace.c | 13 +++++ 7 files changed, 112 insertions(+), 2 deletions(-) -- 2.39.0

2 years, 9 months

2
6
0 0

[PATCH v3 0/3] Checkpoint Support for Syscall User Dispatch

by Gregory Price

v3: Kernel test robot static function fix Whitespace nitpicks v2: Implements the getter/setter interface in ptrace rather than prctl Syscall user dispatch makes it possible to cleanly intercept system calls from user-land. However, most transparent checkpoint software presently leverages some combination of ptrace and system call injection to place software in a ready-to-checkpoint state. If Syscall User Dispatch is enabled at the time of being quiesced, injected system calls will subsequently be interposed upon and dispatched to the task's signal handler. This patch set implements 3 features to enable software such as CRIU to cleanly interpose upon software leveraging syscall user dispatch. - Implement PTRACE_O_SUSPEND_SYSCALL_USER_DISPATCH, akin to a similar feature for SECCOMP. This allows a ptracer to temporarily disable syscall user dispatch, making syscall injection possible. - Implement an fs/proc extension that reports whether Syscall User Dispatch is being used in proc/status. A similar value is present for SECCOMP, and is used to determine whether special logic is needed during checkpoint/resume. - Implement a getter interface for Syscall User Dispatch config info. To resume successfully, the checkpoint/resume software has to save and restore this information. Presently this configuration is write-only, with no way for C/R software to save it. This was done in ptrace because syscall user dispatch is not part of uapi. The syscall_user_dispatch_config structure was added to the ptrace exports. Gregory Price (3): ptrace,syscall_user_dispatch: Implement Syscall User Dispatch Suspension fs/proc/array: Add Syscall User Dispatch to proc status ptrace,syscall_user_dispatch: add a getter/setter for sud configuration .../admin-guide/syscall-user-dispatch.rst | 5 +- fs/proc/array.c | 8 +++ include/linux/ptrace.h | 2 + include/linux/syscall_user_dispatch.h | 19 +++++++ include/uapi/linux/ptrace.h | 16 +++++- kernel/entry/syscall_user_dispatch.c | 54 +++++++++++++++++++ kernel/ptrace.c | 13 +++++ 7 files changed, 115 insertions(+), 2 deletions(-) -- 2.39.0

2 years, 9 months

4
7
0 0

[GIT PULL] Kselftest fixes update for Linux 6.2-rc5

by Shuah Khan

Hi Linus, Please pull the following Kselftest fixes update for Linux 6.2-rc5. This Kselftest fixes update for Linux 6.2-rc5 consists of a single fix to address error seen during unconfigured LLVM builds. diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 1b929c02afd37871d5afb9d498426f83432e71c2: Linux 6.2-rc1 (2022-12-25 13:41:39 -0800) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux-kselftest-fixes-6.2-rc5 for you to fetch changes up to 9fdaca2c1e157dc0a3c0faecf3a6a68e7d8d0c7b: kselftest: Fix error message for unconfigured LLVM builds (2023-01-12 13:38:04 -0700) ---------------------------------------------------------------- linux-kselftest-fixes-6.2-rc5 This Kselftest fixes update for Linux 6.2-rc5 consists of a single fix address error seen during unconfigured LLVM builds. ---------------------------------------------------------------- Mark Brown (1): kselftest: Fix error message for unconfigured LLVM builds tools/testing/selftests/lib.mk | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) ----------------------------------------------------------------

2 years, 9 months

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror January 2023