February 2024 - Linux-kselftest-mirror

[PATCH v15 6/6] ring-buffer/selftest: Add ring-buffer mapping test

by Vincent Donnefort

This test maps a ring-buffer and validate the meta-page after reset and after emitting few events. Cc: Shuah Khan <shuah(a)kernel.org> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Vincent Donnefort <vdonnefort(a)google.com> diff --git a/tools/testing/selftests/ring-buffer/Makefile b/tools/testing/selftests/ring-buffer/Makefile new file mode 100644 index 000000000000..627c5fa6d1ab --- /dev/null +++ b/tools/testing/selftests/ring-buffer/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wl,-no-as-needed -Wall +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -D_GNU_SOURCE + +TEST_GEN_PROGS = map_test + +include ../lib.mk diff --git a/tools/testing/selftests/ring-buffer/config b/tools/testing/selftests/ring-buffer/config new file mode 100644 index 000000000000..d936f8f00e78 --- /dev/null +++ b/tools/testing/selftests/ring-buffer/config @@ -0,0 +1,2 @@ +CONFIG_FTRACE=y +CONFIG_TRACER_SNAPSHOT=y diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c new file mode 100644 index 000000000000..56c44b29d998 --- /dev/null +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Ring-buffer memory mapping tests + * + * Copyright (c) 2024 Vincent Donnefort <vdonnefort(a)google.com> + */ +#include <fcntl.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <linux/trace_mmap.h> + +#include <sys/mman.h> +#include <sys/ioctl.h> + +#include "../user_events/user_events_selftests.h" /* share tracefs setup */ +#include "../kselftest_harness.h" + +#define TRACEFS_ROOT "/sys/kernel/tracing" + +static int __tracefs_write(const char *path, const char *value) +{ + int fd, ret; + + fd = open(path, O_WRONLY | O_TRUNC); + if (fd < 0) + return fd; + + ret = write(fd, value, strlen(value)); + + close(fd); + + return ret == -1 ? -errno : 0; +} + +static int __tracefs_write_int(const char *path, int value) +{ + char *str; + int ret; + + if (asprintf(&str, "%d", value) < 0) + return -1; + + ret = __tracefs_write(path, str); + + free(str); + + return ret; +} + +#define tracefs_write_int(path, value) \ + ASSERT_EQ(__tracefs_write_int((path), (value)), 0) + +#define tracefs_write(path, value) \ + ASSERT_EQ(__tracefs_write((path), (value)), 0) + +static int tracefs_reset(void) +{ + if (__tracefs_write_int(TRACEFS_ROOT"/tracing_on", 0)) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/trace", "")) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/set_event", "")) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/current_tracer", "nop")) + return -1; + + return 0; +} + +struct tracefs_cpu_map_desc { + struct trace_buffer_meta *meta; + void *data; + int cpu_fd; +}; + +int tracefs_cpu_map(struct tracefs_cpu_map_desc *desc, int cpu) +{ + unsigned long meta_len, data_len; + int page_size = getpagesize(); + char *cpu_path; + void *map; + + if (asprintf(&cpu_path, + TRACEFS_ROOT"/per_cpu/cpu%d/trace_pipe_raw", + cpu) < 0) + return -ENOMEM; + + desc->cpu_fd = open(cpu_path, O_RDONLY | O_NONBLOCK); + free(cpu_path); + if (desc->cpu_fd < 0) + return -ENODEV; + + map = mmap(NULL, page_size, PROT_READ, MAP_SHARED, desc->cpu_fd, 0); + if (map == MAP_FAILED) + return -errno; + + desc->meta = (struct trace_buffer_meta *)map; + + meta_len = desc->meta->meta_page_size; + data_len = desc->meta->subbuf_size * desc->meta->nr_subbufs; + + map = mmap(NULL, data_len, PROT_READ, MAP_SHARED, desc->cpu_fd, meta_len); + if (map == MAP_FAILED) { + munmap(desc->meta, desc->meta->meta_page_size); + return -EINVAL; + } + + desc->data = map; + + return 0; +} + +void tracefs_cpu_unmap(struct tracefs_cpu_map_desc *desc) +{ + munmap(desc->data, desc->meta->subbuf_size * desc->meta->nr_subbufs); + munmap(desc->meta, desc->meta->meta_page_size); + close(desc->cpu_fd); +} + +FIXTURE(map) { + struct tracefs_cpu_map_desc map_desc; + bool umount; +}; + +FIXTURE_VARIANT(map) { + int subbuf_size; +}; + +FIXTURE_VARIANT_ADD(map, subbuf_size_4k) { + .subbuf_size = 4, +}; + +FIXTURE_VARIANT_ADD(map, subbuf_size_8k) { + .subbuf_size = 8, +}; + +FIXTURE_SETUP(map) +{ + int cpu = sched_getcpu(); + cpu_set_t cpu_mask; + bool fail, umount; + char *message; + + if (!tracefs_enabled(&message, &fail, &umount)) { + if (fail) { + TH_LOG("Tracefs setup failed: %s", message); + ASSERT_FALSE(fail); + } + SKIP(return, "Skipping: %s", message); + } + + self->umount = umount; + + ASSERT_GE(cpu, 0); + + ASSERT_EQ(tracefs_reset(), 0); + + tracefs_write_int(TRACEFS_ROOT"/buffer_subbuf_size_kb", variant->subbuf_size); + + ASSERT_EQ(tracefs_cpu_map(&self->map_desc, cpu), 0); + + /* + * Ensure generated events will be found on this very same ring-buffer. + */ + CPU_ZERO(&cpu_mask); + CPU_SET(cpu, &cpu_mask); + ASSERT_EQ(sched_setaffinity(0, sizeof(cpu_mask), &cpu_mask), 0); +} + +FIXTURE_TEARDOWN(map) +{ + tracefs_reset(); + + if (self->umount) + tracefs_unmount(); + + tracefs_cpu_unmap(&self->map_desc); +} + +TEST_F(map, meta_page_check) +{ + struct tracefs_cpu_map_desc *desc = &self->map_desc; + int cnt = 0; + + ASSERT_EQ(desc->meta->entries, 0); + ASSERT_EQ(desc->meta->overrun, 0); + ASSERT_EQ(desc->meta->read, 0); + + ASSERT_EQ(desc->meta->reader.id, 0); + ASSERT_EQ(desc->meta->reader.read, 0); + + ASSERT_EQ(ioctl(desc->cpu_fd, TRACE_MMAP_IOCTL_GET_READER), 0); + ASSERT_EQ(desc->meta->reader.id, 0); + + tracefs_write_int(TRACEFS_ROOT"/tracing_on", 1); + for (int i = 0; i < 16; i++) + tracefs_write_int(TRACEFS_ROOT"/trace_marker", i); +again: + ASSERT_EQ(ioctl(desc->cpu_fd, TRACE_MMAP_IOCTL_GET_READER), 0); + + ASSERT_EQ(desc->meta->entries, 16); + ASSERT_EQ(desc->meta->overrun, 0); + ASSERT_EQ(desc->meta->read, 16); + + ASSERT_EQ(desc->meta->reader.id, 1); + + if (!(cnt++)) + goto again; +} + +FIXTURE(snapshot) { + bool umount; +}; + +FIXTURE_SETUP(snapshot) +{ + bool fail, umount; + struct stat sb; + char *message; + + if (stat(TRACEFS_ROOT"/snapshot", &sb)) + SKIP(return, "Skipping: %s", "snapshot not available"); + + if (!tracefs_enabled(&message, &fail, &umount)) { + if (fail) { + TH_LOG("Tracefs setup failed: %s", message); + ASSERT_FALSE(fail); + } + SKIP(return, "Skipping: %s", message); + } + + self->umount = umount; +} + +FIXTURE_TEARDOWN(snapshot) +{ + __tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "!snapshot"); + tracefs_reset(); + + if (self->umount) + tracefs_unmount(); +} + +TEST_F(snapshot, excludes_map) +{ + struct tracefs_cpu_map_desc map_desc; + int cpu = sched_getcpu(); + + ASSERT_GE(cpu, 0); + tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "snapshot"); + ASSERT_EQ(tracefs_cpu_map(&map_desc, cpu), -EBUSY); +} + +TEST_F(snapshot, excluded_by_map) +{ + struct tracefs_cpu_map_desc map_desc; + int cpu = sched_getcpu(); + + ASSERT_EQ(tracefs_cpu_map(&map_desc, cpu), 0); + + ASSERT_EQ(__tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "snapshot"), -EBUSY); + ASSERT_EQ(__tracefs_write(TRACEFS_ROOT"/snapshot", + "1"), -EBUSY); +} + +TEST_HARNESS_MAIN -- 2.43.0.687.g38aa6559b0-goog

1 year, 4 months

1
0
0 0

[PATCH net 6/7] selftests: tls: use exact comparison in recv_partial

by Jakub Kicinski

This exact case was fail for async crypto and we weren't catching it. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/tls.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 7799e042a971..bc36c91c4480 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1002,12 +1002,12 @@ TEST_F(tls, recv_partial) memset(recv_mem, 0, sizeof(recv_mem)); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_first), + MSG_WAITALL), strlen(test_str_first)); EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0); memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), - MSG_WAITALL), -1); + EXPECT_EQ(recv(self->cfd, recv_mem, strlen(test_str_second), + MSG_WAITALL), strlen(test_str_second)); EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)), 0); } -- 2.43.0

1 year, 4 months

2
1
0 0

[RFC PATCH v2 0/6] RISC-V: Add dynamic TSO support

by Christoph Müllner

The upcoming RISC-V Ssdtso specification introduces a bit in the senvcfg CSR to switch the memory consistency model of user mode at run-time from RVWMO to TSO. The active consistency model can therefore be switched on a per-hart base and managed by the kernel on a per-process base. This patchset implements basic Ssdtso support and adds a prctl API on top so that user-space processes can switch to a stronger memory consistency model (than the kernel was written for) at run-time. The patchset also comes with a short documentation of the prctl API. This series is based on the third draft of the Ssdtso specification which can be found here: https://github.com/riscv/riscv-ssdtso/releases/tag/v1.0-draft3 Note, that the Ssdtso specification is in development state (i.e., not frozen or even ratified) which is also the reason why this series is marked as RFC. This series saw the following changes since v1: * Reordered/restructured patches * Fixed build issues * Addressed typos * Removed ability to switch TSO->WMO * Moved the state from per-thread to per-process * Reschedule all CPUs after switching * Some cleanups in the documentation * Adding compatibility with Ztso (spec change in draft 3) This patchset can also be found in this GitHub branch: https://github.com/cmuellner/linux/tree/ssdtso-v2 A QEMU implementation of DTSO can be found in this GitHub branch: https://github.com/cmuellner/qemu/tree/ssdtso-v2 Christoph Müllner (6): mm: Add dynamic memory consistency model switching uapi: prctl: Add new prctl call to set/get the memory consistency model RISC-V: Enable dynamic memory consistency model support with Ssdtso RISC-V: Implement prctl call to set/get the memory consistency model RISC-V: Expose Ssdtso via hwprobe API RISC-V: selftests: Add DTSO tests Documentation/arch/riscv/hwprobe.rst | 3 + .../mm/dynamic-memory-consistency-model.rst | 86 ++++++++++++++++ Documentation/mm/index.rst | 1 + arch/Kconfig | 14 +++ arch/riscv/Kconfig | 11 +++ arch/riscv/include/asm/csr.h | 1 + arch/riscv/include/asm/dtso.h | 97 +++++++++++++++++++ arch/riscv/include/asm/hwcap.h | 1 + arch/riscv/include/asm/processor.h | 7 ++ arch/riscv/include/asm/switch_to.h | 3 + arch/riscv/include/uapi/asm/hwprobe.h | 1 + arch/riscv/kernel/Makefile | 1 + arch/riscv/kernel/asm-offsets.c | 3 + arch/riscv/kernel/cpufeature.c | 1 + arch/riscv/kernel/dtso.c | 67 +++++++++++++ arch/riscv/kernel/sys_hwprobe.c | 2 + include/linux/sched.h | 5 + include/uapi/linux/prctl.h | 5 + kernel/sys.c | 12 +++ tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/dtso/.gitignore | 1 + tools/testing/selftests/riscv/dtso/Makefile | 11 +++ tools/testing/selftests/riscv/dtso/dtso.c | 82 ++++++++++++++++ 23 files changed, 416 insertions(+), 1 deletion(-) create mode 100644 Documentation/mm/dynamic-memory-consistency-model.rst create mode 100644 arch/riscv/include/asm/dtso.h create mode 100644 arch/riscv/kernel/dtso.c create mode 100644 tools/testing/selftests/riscv/dtso/.gitignore create mode 100644 tools/testing/selftests/riscv/dtso/Makefile create mode 100644 tools/testing/selftests/riscv/dtso/dtso.c -- 2.43.0

1 year, 4 months

1
6
0 0

[PATCH net] selftests: net: add more missing kernel config

by Paolo Abeni

The reuseport_addr_any.sh is currently skipping DCCP tests and pmtu.sh is skipping all the FOU/GUE related cases: add the missing options. Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> --- Note that this does not include the - still missing - OVS-related option and pmtu.sh is will keep skipping such cases. Such tests will still fail in the virtme environment even with the relevant kernel options enabled, as they have an hard to solve dependency on systemd/dbus. The longer term plan is to move such test cases in the openvswitch directory. One short term option to avoid skips in selftests results while retaining the potential code coverage would be making the ovs tests disabled by default but reachable via pmtu.sh command line arguments. --- tools/testing/selftests/net/config | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 3b749addd364..54d21e2911a9 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -13,6 +13,10 @@ CONFIG_IPV6=y CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_VETH=y CONFIG_NET_IPVTI=y +CONFIG_NET_FOU=y +CONFIG_NET_FOU_IP_TUNNELS=y +CONFIG_NET_IPIP=y +CONFIG_IPV6_SIT=y CONFIG_IPV6_VTI=y CONFIG_DUMMY=y CONFIG_BRIDGE_VLAN_FILTERING=y @@ -24,6 +28,7 @@ CONFIG_IFB=y CONFIG_INET_DIAG=y CONFIG_INET_ESP=y CONFIG_INET_ESP_OFFLOAD=y +CONFIG_IP_DCCP=m CONFIG_IP_GRE=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y -- 2.43.0

1 year, 4 months

3
2
0 0

[PATCH v2 0/7] Use TAP in some more x86 KVM selftests

by Thomas Huth

Here's a follow-up from my RFC series last year: https://lore.kernel.org/lkml/20221004093131.40392-1-thuth@redhat.com/T/ and from v1 earlier this year: https://lore.kernel.org/kvm/20230712075910.22480-1-thuth@redhat.com/ Basic idea of this series is now to use the kselftest_harness.h framework to get TAP output in the tests, so that it is easier for the user to see what is going on, and e.g. to be able to detect whether a certain test is part of the test binary or not (which is useful when tests get extended in the course of time). v2: - Dropped the "Rename the ASSERT_EQ macro" patch (already merged) - Split the fixes in the sync_regs_test into separate patches (see the first two patches) - Introduce the KVM_ONE_VCPU_TEST_SUITE() macro as suggested by Sean (see third patch) and use it in the following patches - Add a new patch to convert vmx_pmu_caps_test.c, too Thomas Huth (7): KVM: selftests: x86: sync_regs_test: Use vcpu_run() where appropriate KVM: selftests: x86: sync_regs_test: Get regs structure before modifying it KVM: selftests: Add a macro to define a test with one vcpu KVM: selftests: x86: Use TAP interface in the sync_regs test KVM: selftests: x86: Use TAP interface in the fix_hypercall test KVM: selftests: x86: Use TAP interface in the vmx_pmu_caps test KVM: selftests: x86: Use TAP interface in the userspace_msr_exit test .../selftests/kvm/include/kvm_test_harness.h | 35 +++++ .../selftests/kvm/x86_64/fix_hypercall_test.c | 27 ++-- .../selftests/kvm/x86_64/sync_regs_test.c | 121 +++++++++++++----- .../kvm/x86_64/userspace_msr_exit_test.c | 19 +-- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 50 ++------ 5 files changed, 160 insertions(+), 92 deletions(-) create mode 100644 tools/testing/selftests/kvm/include/kvm_test_harness.h -- 2.41.0

1 year, 4 months

2
9
0 0

Re: [RFC PATCH 0/5] RISC-V: Add dynamic TSO support

by Andrea Parri

On Fri, Nov 24, 2023 at 12:04:09PM +0100, Jonas Oberhauser wrote: > Unfortunately, at least last time I checked RISC-V still hadn't gotten such > instructions. > What they have is the *semantics* of the instructions, but no actual opcodes > to encode them. > I argued for them in the RISC-V memory group, but it was considered to be > outside the scope of that group. (Sorry for the late, late reply; just recalled this thread...) That's right. AFAICT, the discussion about the native load-acquire and store-release instructions was revived somewhere last year within the RVI community, culminating in the so called Zalasr-proposal [1]; Brendan, Hans and Andrew (+ Cc) might be able to provide more up-to- date information about the status/plans for that proposal. (Remark that RISC-V did introduce LR/SCs and AMOs instructions with acquire/release semantics separately, cf. the so called A-extension.) Andrea [1] https://github.com/mehnadnerd/riscv-zalasr

1 year, 4 months

1
0
0 0

[PATCH] selftests: Add missing gitignore entries

by Bernd Edlinger

Prevent them from polluting git status after building selftests. Signed-off-by: Bernd Edlinger <bernd.edlinger(a)hotmail.de> --- tools/testing/selftests/damon/.gitignore | 1 + tools/testing/selftests/thermal/intel/power_floor/.gitignore | 2 ++ tools/testing/selftests/thermal/intel/workload_hint/.gitignore | 2 ++ tools/testing/selftests/uevent/.gitignore | 2 ++ 4 files changed, 7 insertions(+) create mode 100644 tools/testing/selftests/thermal/intel/power_floor/.gitignore create mode 100644 tools/testing/selftests/thermal/intel/workload_hint/.gitignore create mode 100644 tools/testing/selftests/uevent/.gitignore diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore index c6c2965a6607..79b32e30fce3 100644 --- a/tools/testing/selftests/damon/.gitignore +++ b/tools/testing/selftests/damon/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only huge_count_read_write +access_memory diff --git a/tools/testing/selftests/thermal/intel/power_floor/.gitignore b/tools/testing/selftests/thermal/intel/power_floor/.gitignore new file mode 100644 index 000000000000..754810406b33 --- /dev/null +++ b/tools/testing/selftests/thermal/intel/power_floor/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +power_floor_test diff --git a/tools/testing/selftests/thermal/intel/workload_hint/.gitignore b/tools/testing/selftests/thermal/intel/workload_hint/.gitignore new file mode 100644 index 000000000000..b5448c0576c9 --- /dev/null +++ b/tools/testing/selftests/thermal/intel/workload_hint/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +workload_hint_test diff --git a/tools/testing/selftests/uevent/.gitignore b/tools/testing/selftests/uevent/.gitignore new file mode 100644 index 000000000000..15127939d872 --- /dev/null +++ b/tools/testing/selftests/uevent/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +uevent_filtering -- 2.39.2

1 year, 4 months

3
2
0 0

[PATCH net] selftests: net: cope with slow env in gro.sh test

by Paolo Abeni

The gro self-tests sends the packets to be aggregated with multiple write operations. When running is slow environment, it's hard to guarantee that the GRO engine will wait for the last packet in an intended train. The above causes almost deterministic failures in our CI for the 'large' test-case. Address the issue explicitly ignoring failures for such case in slow environments (KSFT_MACHINE_SLOW==true). Fixes: 7d1575014a63 ("selftests/net: GRO coalesce test") Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> --- Note that the fixes tag is there mainly to justify targeting the net tree, and this is aiming at net to hopefully make the test more stable ASAP for both trees. I experimented with a largish refactory replacing the multiple writes with a single GSO packet, but exhausted by time budget before reaching any good result. --- tools/testing/selftests/net/gro.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh index 19352f106c1d..114b5281a3f5 100755 --- a/tools/testing/selftests/net/gro.sh +++ b/tools/testing/selftests/net/gro.sh @@ -31,6 +31,10 @@ run_test() { 1>>log.txt wait "${server_pid}" exit_code=$? + if [ ${test} == "large" -a -n "${KSFT_MACHINE_SLOW}" ]; then + echo "Ignoring errors due to slow environment" 1>&2 + exit_code=0 + fi if [[ "${exit_code}" -eq 0 ]]; then break; fi -- 2.43.0

1 year, 4 months

4
6
0 0

[PATCH] kunit: device: Unregister the kunit_bus on shutdown

by David Gow

If KUnit is built as a module, and it's unloaded, the kunit_bus is not unregistered. This causes an error if it's then re-loaded later, as we try to re-register the bus. Unregister the bus and root_device on shutdown, if it looks valid. In addition, be more specific about the value of kunit_bus_device. It is: - a valid struct device* if the kunit_bus initialised correctly. - an ERR_PTR if it failed to initialise. - NULL before initialisation and after shutdown. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Signed-off-by: David Gow <davidgow(a)google.com> --- This will hopefully resolve some of the issues linked to from: https://lore.kernel.org/intel-gfx/DM4PR11MB614179CB9C387842D8E8BB40B97C2@DM… --- lib/kunit/device-impl.h | 2 ++ lib/kunit/device.c | 14 ++++++++++++++ lib/kunit/test.c | 3 +++ 3 files changed, 19 insertions(+) diff --git a/lib/kunit/device-impl.h b/lib/kunit/device-impl.h index 54bd55836405..5fcd48ff0f36 100644 --- a/lib/kunit/device-impl.h +++ b/lib/kunit/device-impl.h @@ -13,5 +13,7 @@ // For internal use only -- registers the kunit_bus. int kunit_bus_init(void); +// For internal use only -- unregisters the kunit_bus. +void kunit_bus_shutdown(void); #endif //_KUNIT_DEVICE_IMPL_H diff --git a/lib/kunit/device.c b/lib/kunit/device.c index 074c6dd2e36a..644a38a1f5b1 100644 --- a/lib/kunit/device.c +++ b/lib/kunit/device.c @@ -54,6 +54,20 @@ int kunit_bus_init(void) return error; } +/* Unregister the 'kunit_bus' in case the KUnit module is unloaded. */ +void kunit_bus_shutdown(void) +{ + /* Make sure the bus exists before we unregister it. */ + if (IS_ERR_OR_NULL(kunit_bus_device)) + return; + + bus_unregister(&kunit_bus_type); + + root_device_unregister(kunit_bus_device); + + kunit_bus_device = NULL; +} + /* Release a 'fake' KUnit device. */ static void kunit_device_release(struct device *d) { diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 31a5a992e646..1d1475578515 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -928,6 +928,9 @@ static void __exit kunit_exit(void) #ifdef CONFIG_MODULES unregister_module_notifier(&kunit_mod_nb); #endif + + kunit_bus_shutdown(); + kunit_debugfs_cleanup(); } module_exit(kunit_exit); -- 2.43.0.429.g432eaa2c6b-goog

1 year, 4 months

3
3
0 0

[PATCH] mm, memcg: cg2 memory{.swap,}.peak write handlers

by David Finkel

Other mechanisms for querying the peak memory usage of either a process or v1 memory cgroup allow for resetting the high watermark. Restore parity with those mechanisms. For example: - Any write to memory.max_usage_in_bytes in a cgroup v1 mount resets the high watermark. - writing "5" to the clear_refs pseudo-file in a processes's proc directory resets the peak RSS. This change copies the cgroup v1 behavior so any write to the memory.peak and memory.swap.peak pseudo-files reset the high watermark to the current usage. This behavior is particularly useful for work scheduling systems that need to track memory usage of worker processes/cgroups per-work-item. Since memory can't be squeezed like CPU can (the OOM-killer has opinions), these systems need to track the peak memory usage to compute system/container fullness when binpacking workitems. Signed-off-by: David Finkel <davidf(a)vimeo.com> --- Documentation/admin-guide/cgroup-v2.rst | 20 +++--- mm/memcontrol.c | 23 ++++++ .../selftests/cgroup/test_memcontrol.c | 72 ++++++++++++++++--- 3 files changed, 99 insertions(+), 16 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 3f85254f3cef..95af0628dc44 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1305,11 +1305,13 @@ PAGE_SIZE multiple when read back. reclaim induced by memory.reclaim. memory.peak - A read-only single value file which exists on non-root - cgroups. + A read-write single value file which exists on non-root cgroups. + + The max memory usage recorded for the cgroup and its descendants since + either the creation of the cgroup or the most recent reset. - The max memory usage recorded for the cgroup and its - descendants since the creation of the cgroup. + Any non-empty write to this file resets it to the current memory usage. + All content written is completely ignored. memory.oom.group A read-write single value file which exists on non-root @@ -1626,11 +1628,13 @@ PAGE_SIZE multiple when read back. Healthy workloads are not expected to reach this limit. memory.swap.peak - A read-only single value file which exists on non-root - cgroups. + A read-write single value file which exists on non-root cgroups. + + The max swap usage recorded for the cgroup and its descendants since + the creation of the cgroup or the most recent reset. - The max swap usage recorded for the cgroup and its - descendants since the creation of the cgroup. + Any non-empty write to this file resets it to the current swap usage. + All content written is completely ignored. memory.swap.max A read-write single value file which exists on non-root diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1c1061df9cd1..b04af158922d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -25,6 +25,7 @@ * Copyright (C) 2020 Alibaba, Inc, Alex Shi */ +#include <linux/cgroup-defs.h> #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/cgroup.h> @@ -6635,6 +6636,16 @@ static u64 memory_peak_read(struct cgroup_subsys_state *css, return (u64)memcg->memory.watermark * PAGE_SIZE; } +static ssize_t memory_peak_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + + page_counter_reset_watermark(&memcg->memory); + + return nbytes; +} + static int memory_min_show(struct seq_file *m, void *v) { return seq_puts_memcg_tunable(m, @@ -6947,6 +6958,7 @@ static struct cftype memory_files[] = { .name = "peak", .flags = CFTYPE_NOT_ON_ROOT, .read_u64 = memory_peak_read, + .write = memory_peak_write, }, { .name = "min", @@ -7917,6 +7929,16 @@ static u64 swap_peak_read(struct cgroup_subsys_state *css, return (u64)memcg->swap.watermark * PAGE_SIZE; } +static ssize_t swap_peak_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + + page_counter_reset_watermark(&memcg->swap); + + return nbytes; +} + static int swap_high_show(struct seq_file *m, void *v) { return seq_puts_memcg_tunable(m, @@ -7999,6 +8021,7 @@ static struct cftype swap_files[] = { .name = "swap.peak", .flags = CFTYPE_NOT_ON_ROOT, .read_u64 = swap_peak_read, + .write = swap_peak_write, }, { .name = "swap.events", diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index c7c9572003a8..0326c317f1f2 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -161,12 +161,12 @@ static int alloc_pagecache_50M_check(const char *cgroup, void *arg) /* * This test create a memory cgroup, allocates * some anonymous memory and some pagecache - * and check memory.current and some memory.stat values. + * and checks memory.current, memory.peak, and some memory.stat values. */ -static int test_memcg_current(const char *root) +static int test_memcg_current_peak(const char *root) { int ret = KSFT_FAIL; - long current; + long current, peak, peak_reset; char *memcg; memcg = cg_name(root, "memcg_test"); @@ -180,12 +180,32 @@ static int test_memcg_current(const char *root) if (current != 0) goto cleanup; + peak = cg_read_long(memcg, "memory.peak"); + if (peak != 0) + goto cleanup; + if (cg_run(memcg, alloc_anon_50M_check, NULL)) goto cleanup; + peak = cg_read_long(memcg, "memory.peak"); + if (peak < MB(50)) + goto cleanup; + + peak_reset = cg_write(memcg, "memory.peak", "\n"); + if (peak_reset != 0) + goto cleanup; + + peak = cg_read_long(memcg, "memory.peak"); + if (peak > MB(30)) + goto cleanup; + if (cg_run(memcg, alloc_pagecache_50M_check, NULL)) goto cleanup; + peak = cg_read_long(memcg, "memory.peak"); + if (peak < MB(50)) + goto cleanup; + ret = KSFT_PASS; cleanup: @@ -815,13 +835,14 @@ static int alloc_anon_50M_check_swap(const char *cgroup, void *arg) /* * This test checks that memory.swap.max limits the amount of - * anonymous memory which can be swapped out. + * anonymous memory which can be swapped out. Additionally, it verifies that + * memory.swap.peak reflects the high watermark and can be reset. */ -static int test_memcg_swap_max(const char *root) +static int test_memcg_swap_max_peak(const char *root) { int ret = KSFT_FAIL; char *memcg; - long max; + long max, peak; if (!is_swap_enabled()) return KSFT_SKIP; @@ -838,6 +859,12 @@ static int test_memcg_swap_max(const char *root) goto cleanup; } + if (cg_read_long(memcg, "memory.swap.peak")) + goto cleanup; + + if (cg_read_long(memcg, "memory.peak")) + goto cleanup; + if (cg_read_strcmp(memcg, "memory.max", "max\n")) goto cleanup; @@ -860,6 +887,27 @@ static int test_memcg_swap_max(const char *root) if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1) goto cleanup; + peak = cg_read_long(memcg, "memory.peak"); + if (peak < MB(29)) + goto cleanup; + + peak = cg_read_long(memcg, "memory.swap.peak"); + if (peak < MB(29)) + goto cleanup; + + if (cg_write(memcg, "memory.swap.peak", "\n")) + goto cleanup; + + if (cg_read_long(memcg, "memory.swap.peak") > MB(10)) + goto cleanup; + + + if (cg_write(memcg, "memory.peak", "\n")) + goto cleanup; + + if (cg_read_long(memcg, "memory.peak")) + goto cleanup; + if (cg_run(memcg, alloc_anon_50M_check_swap, (void *)MB(30))) goto cleanup; @@ -867,6 +915,14 @@ static int test_memcg_swap_max(const char *root) if (max <= 0) goto cleanup; + peak = cg_read_long(memcg, "memory.peak"); + if (peak < MB(29)) + goto cleanup; + + peak = cg_read_long(memcg, "memory.swap.peak"); + if (peak < MB(19)) + goto cleanup; + ret = KSFT_PASS; cleanup: @@ -1293,7 +1349,7 @@ struct memcg_test { const char *name; } tests[] = { T(test_memcg_subtree_control), - T(test_memcg_current), + T(test_memcg_current_peak), T(test_memcg_min), T(test_memcg_low), T(test_memcg_high), @@ -1301,7 +1357,7 @@ struct memcg_test { T(test_memcg_max), T(test_memcg_reclaim), T(test_memcg_oom_events), - T(test_memcg_swap_max), + T(test_memcg_swap_max_peak), T(test_memcg_sock), T(test_memcg_oom_group_leaf_events), T(test_memcg_oom_group_parent_events), -- 2.39.2

1 year, 4 months

3
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror February 2024