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

[RFC PATCH 5/5] selftests/rseq: Implement NUMA node id vs mm_cid invariant test

by Mathieu Desnoyers

This test validates that the mapping between a mm_cid and a NUMA node id remains invariant for the process lifetime for a process with a number of threads >= number of allowed CPUs. In other words, it validates that if any thread within the process running on behalf of a mm_cid N observes a NUMA node id M, all threads within this process will always observe the same NUMA node id value when running on behalf of that same mm_cid. This characteristic is important for NUMA locality. On all architectures except Power, the NUMA topology is never reconfigured after a CPU has been associated with a NUMA node in the system lifetime. Even on Power, we can assume that NUMA topology reconfiguration happens rarely, and therefore we do not expect it to happen while the NUMA test is running. As a result the NUMA node id associated with a mm_cid should be invariant as long as: - A process has a number of threads >= number of allowed CPUs, - The allowed CPUs mask is unchanged, and - The NUMA configuration is unchanged. This test is skipped on architectures that do not implement rseq_load_u32_u32. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../testing/selftests/rseq/basic_numa_test.c | 144 ++++++++++++++++++ 3 files changed, 146 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/basic_numa_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce..8a8d163cbb9f 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +basic_numa_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb58..9ef1c949114a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -14,7 +14,7 @@ LDLIBS += -lpthread -ldl # still track changes to header files and depend on shared object. OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ +TEST_GEN_PROGS = basic_test basic_numa_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ param_test_mm_cid_benchmark param_test_mm_cid_compare_twice diff --git a/tools/testing/selftests/rseq/basic_numa_test.c b/tools/testing/selftests/rseq/basic_numa_test.c new file mode 100644 index 000000000000..8e51c662057d --- /dev/null +++ b/tools/testing/selftests/rseq/basic_numa_test.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Basic rseq NUMA test. Validate that (mm_cid, numa_node_id) pairs are + * invariant when the number of threads >= number of allowed CPUs, as + * long as those preconditions are respected: + * + * - A process has a number of threads >= number of allowed CPUs, + * - The allowed CPUs mask is unchanged, and + * - The NUMA configuration is unchanged. + */ +#define _GNU_SOURCE +#include <assert.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <string.h> +#include <poll.h> +#include <sys/time.h> + +#include "rseq.h" + +#define NR_LOOPS 100 + +static int nr_threads, nr_active_threads, test_go, test_stop; + +#ifdef RSEQ_ARCH_HAS_LOAD_U32_U32 + +static int cpu_numa_id[CPU_SETSIZE]; + +static int get_affinity_weight(void) +{ + cpu_set_t allowed_cpus; + + if (sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus)) { + perror("sched_getaffinity"); + abort(); + } + return CPU_COUNT(&allowed_cpus); +} + +static void numa_id_init(void) +{ + int i; + + for (i = 0; i < CPU_SETSIZE; i++) + cpu_numa_id[i] = -1; +} + +static void *test_thread(void *arg) +{ + int i; + + if (rseq_register_current_thread()) { + fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + /* + * Rendez-vous across all threads to make sure the number of + * threads >= number of possible CPUs for the entire test duration. + */ + if (__atomic_add_fetch(&nr_active_threads, 1, __ATOMIC_RELAXED) == nr_threads) + __atomic_store_n(&test_go, 1, __ATOMIC_RELAXED); + while (!__atomic_load_n(&test_go, __ATOMIC_RELAXED)) + rseq_barrier(); + + for (i = 0; i < NR_LOOPS; i++) { + uint32_t mm_cid, node; + int cached_node_id; + + while (rseq_load_u32_u32(RSEQ_MO_RELAXED, &mm_cid, + &rseq_get_abi()->mm_cid, + &node, &rseq_get_abi()->node_id) != 0) { + /* Retry. */ + } + cached_node_id = RSEQ_READ_ONCE(cpu_numa_id[mm_cid]); + if (cached_node_id == -1) { + RSEQ_WRITE_ONCE(cpu_numa_id[mm_cid], node); + } else { + if (node != cached_node_id) { + fprintf(stderr, "Error: NUMA node id discrepancy: mm_cid %u cached node id %d node id %u.\n", + mm_cid, cached_node_id, node); + fprintf(stderr, "This is likely a kernel bug, or caused by a concurrent NUMA topology reconfiguration.\n"); + abort(); + } + } + (void) poll(NULL, 0, 10); /* wait 10ms */ + } + /* + * Rendez-vous before exiting all threads to make sure the + * number of threads >= number of possible CPUs for the entire + * test duration. + */ + if (__atomic_sub_fetch(&nr_active_threads, 1, __ATOMIC_RELAXED) == 0) + __atomic_store_n(&test_stop, 1, __ATOMIC_RELAXED); + while (!__atomic_load_n(&test_stop, __ATOMIC_RELAXED)) + rseq_barrier(); + + if (rseq_unregister_current_thread()) { + fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + return NULL; +} + +static int test_numa(void) +{ + pthread_t tid[nr_threads]; + int err, i; + void *tret; + + numa_id_init(); + + printf("testing rseq (mm_cid, numa_node_id) invariant, multi-threaded (%d threads)\n", + nr_threads); + + for (i = 0; i < nr_threads; i++) { + err = pthread_create(&tid[i], NULL, test_thread, NULL); + if (err != 0) + abort(); + } + + for (i = 0; i < nr_threads; i++) { + err = pthread_join(tid[i], &tret); + if (err != 0) + abort(); + } + + return 0; +} +#else +static int test_numa(void) +{ + fprintf(stderr, "rseq_load_u32_u32 is not implemented on this architecture. Skipping numa test.\n"); + return 0; +} +#endif + +int main(int argc, char **argv) +{ + nr_threads = get_affinity_weight(); + return test_numa(); +} -- 2.39.2

10 months, 3 weeks

1
0
0 0

[RFC PATCH 4/5] selftests/rseq: x86: Implement rseq_load_u32_u32

by Mathieu Desnoyers

Allow loading a pair of u32 within a rseq critical section. It can be used in situations where both rseq_abi()->mm_cid and rseq_abi()->node_id need to be sampled atomically with respect to preemption, signal delivery and migration. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/rseq/rseq-x86-bits.h | 43 ++++++++++++++++++++ tools/testing/selftests/rseq/rseq.h | 14 +++++++ 2 files changed, 57 insertions(+) diff --git a/tools/testing/selftests/rseq/rseq-x86-bits.h b/tools/testing/selftests/rseq/rseq-x86-bits.h index 8a9431eec467..fdf5ef398393 100644 --- a/tools/testing/selftests/rseq/rseq-x86-bits.h +++ b/tools/testing/selftests/rseq/rseq-x86-bits.h @@ -990,4 +990,47 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_trymemcpy_storev)(intptr_t *v, intptr_t #endif +#if defined(RSEQ_TEMPLATE_CPU_ID_NONE) && defined(RSEQ_TEMPLATE_MO_RELAXED) + +#define RSEQ_ARCH_HAS_LOAD_U32_U32 + +static inline __attribute__((always_inline)) +int RSEQ_TEMPLATE_IDENTIFIER(rseq_load_u32_u32)(uint32_t *dst1, uint32_t *src1, + uint32_t *dst2, uint32_t *src2) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_INJECT_ASM(3) + "movl %[src1], %%eax\n\t" + "movl %%eax, %[dst1]\n\t" + "movl %[src2], %%eax\n\t" + "movl %%eax, %[dst2]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [rseq_offset] "r" (rseq_offset), + /* final store input */ + [dst1] "m" (*dst1), + [src1] "m" (*src1), + [dst2] "m" (*dst2), + [src2] "m" (*src2) + : "memory", "cc", "rax" + RSEQ_INJECT_CLOBBER + : abort + ); + rseq_after_asm_goto(); + return 0; +abort: + rseq_after_asm_goto(); + RSEQ_INJECT_FAILED + return -1; +} + +#endif /* defined(RSEQ_TEMPLATE_CPU_ID_NONE) && defined(RSEQ_TEMPLATE_MO_RELAXED) */ + #include "rseq-bits-reset.h" diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index d7364ea4d201..b6095c2a5da6 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -381,4 +381,18 @@ int rseq_cmpeqv_trymemcpy_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode per } } +#ifdef RSEQ_ARCH_HAS_LOAD_U32_U32 + +static inline __attribute__((always_inline)) +int rseq_load_u32_u32(enum rseq_mo rseq_mo, + uint32_t *dst1, uint32_t *src1, + uint32_t *dst2, uint32_t *src2) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + return rseq_load_u32_u32_relaxed(dst1, src1, dst2, src2); +} + +#endif + #endif /* RSEQ_H_ */ -- 2.39.2

10 months, 3 weeks

1
0
0 0

[PATCH v2] lib/math: Add int_pow test suite

by Luis Felipe Hernandez

Adds test suite for integer based power function. Signed-off-by: Luis Felipe Hernandez <luis.hernandez093(a)gmail.com> --- lib/Kconfig.debug | 9 ++++++ lib/math/Makefile | 1 + lib/math/tests/Makefile | 3 ++ lib/math/tests/int_pow_kunit.c | 52 ++++++++++++++++++++++++++++++++++ 4 files changed, 65 insertions(+) create mode 100644 lib/math/tests/Makefile create mode 100644 lib/math/tests/int_pow_kunit.c diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a30c03a66172..b0bbd30d4cba 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -3051,3 +3051,12 @@ config RUST_KERNEL_DOCTESTS endmenu # "Rust" endmenu # Kernel hacking + +config INT_POW_TEST + tristate "Integer exponentiation (int_pow) test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Enable this to test the int_pow maths function KUnit test. + + If unsure, say N diff --git a/lib/math/Makefile b/lib/math/Makefile index 91fcdb0c9efe..3c1f92a7459d 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -5,5 +5,6 @@ obj-$(CONFIG_CORDIC) += cordic.o obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o obj-$(CONFIG_RATIONAL) += rational.o +obj-$(CONFIG_INT_POW_TEST) += tests/int_pow_kunit.o obj-$(CONFIG_TEST_DIV64) += test_div64.o obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile new file mode 100644 index 000000000000..6a169123320a --- /dev/null +++ b/lib/math/tests/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_INT_POW_TEST) += int_pow_kunit.o diff --git a/lib/math/tests/int_pow_kunit.c b/lib/math/tests/int_pow_kunit.c new file mode 100644 index 000000000000..e04dd73dabd1 --- /dev/null +++ b/lib/math/tests/int_pow_kunit.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <kunit/test.h> +#include <linux/math.h> + +struct test_case_params { + u64 base; + unsigned int exponent; + u64 expected_result; + const char *name; +}; + +static const struct test_case_params params[] = { + { 64, 0, 1, "Power of zero" }, + { 64, 1, 64, "Power of one"}, + { 0, 5, 0, "Base zero" }, + { 1, 64, 1, "Base one" }, + { 2, 2, 4, "Two squared"}, + { 2, 3, 8, "Two cubed"}, + { 5, 5, 3125, "Five raised to the fith power" }, + { U64_MAX, 1, U64_MAX, "Max base" }, + { 2, 63, 9223372036854775808, "Large result"}, +}; + +static void get_desc(const struct test_case_params *tc, char *desc) +{ + strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(int_pow, params, get_desc); + +static void int_pow_test(struct kunit *test) +{ + const struct test_case_params *tc = (const struct test_case_params *)test->param_value; + + KUNIT_EXPECT_EQ(test, tc->expected_result, int_pow(tc->base, tc->exponent)); +} + +static struct kunit_case math_int_pow_test_cases[] = { + KUNIT_CASE_PARAM(int_pow_test, int_pow_gen_params), + {} +}; + +static struct kunit_suite int_pow_test_suite = { + .name = "math-int_pow", + .test_cases = math_int_pow_test_cases, +}; + +kunit_test_suites(&int_pow_test_suite); + +MODULE_DESCRIPTION("math.int_pow KUnit test suite"); +MODULE_LICENSE("GPL"); -- 2.46.0

10 months, 3 weeks

2
2
0 0

[PATCHv2 net 0/2] selftests: Fix udpgro failures

by Hangbin Liu

There are 2 issues for the current udpgro test. The first one is the testing doesn't record all the failures, which may report pass but the test actually failed. e.g. https://netdev-3.bots.linux.dev/vmksft-net/results/725661/45-udpgro-sh/stdo… The other one is after commit d7db7775ea2e ("net: veth: do not manipulate GRO when using XDP"), there is no need to load xdp program to enable GRO on veth device. Hangbin Liu (2): selftests: udpgro: report error when receive failed selftests: udpgro: no need to load xdp for gro tools/testing/selftests/net/udpgro.sh | 53 ++++++++++++++------------- 1 file changed, 28 insertions(+), 25 deletions(-) -- 2.45.0

10 months, 3 weeks

2
3
0 0

[PATCH v4 0/3] tracing: Support poll on event hist file

by Masami Hiramatsu (Google)

Hi, Here is the v4 patch to support polling on event 'hist' file. The previous version is here; https://lore.kernel.org/all/172359427367.323666.6446548762874507863.stgit@d… This version uses getopt() in poll test command in [3/3] according to Shuah's comment in the previous thread. Background ---------- There has been interest in allowing user programs to monitor kernel events in real time. Ftrace provides `trace_pipe` interface to wait on events in the ring buffer, but it is needed to wait until filling up a page with events in the ring buffer. We can also peek the `trace` file periodically, but that is inefficient way to monitor a randomely happening event. Overview -------- This patch set allows user to `poll`(or `select`, `epoll`) on event histogram interface. As you know each event has its own `hist` file which shows histograms generated by trigger action. So user can set a new hist trigger on any event you want to monitor, and poll on the `hist` file until it is updated. There are 2 poll events are supported, POLLIN and POLLPRI. POLLIN means that there are any readable update on `hist` file and this event will be flashed only when you call read(). So, this is useful if you want to read the histogram periodically. The other POLLPRI event is for monitoring trace event. Like the POLLIN, this will be returned when the histogram is updated, but you don't need to read() the file and use poll() again. Note that this waits for histogram update (not event arrival), thus you must set a histogram on the event at first. Usage ----- Here is an example usage: ---- TRACEFS=/sys/kernel/tracing EVENT=$TRACEFS/events/sched/sched_process_free # setup histogram trigger and enable event echo "hist:key=comm" >> $EVENT/trigger echo 1 > $EVENT/enable # Wait for update poll pri $EVENT/hist # Event arrived. echo "process free event is comming" tail $TRACEFS/trace ---- The 'poll' command is in the selftest patch. You can take this series also from here; https://git.kernel.org/pub/scm/linux/kernel/git/mhiramat/linux.git/log/?h=t… Thank you, --- Masami Hiramatsu (Google) (3): tracing/hist: Add poll(POLLIN) support on hist file tracing/hist: Support POLLPRI event for poll on histogram selftests/tracing: Add hist poll() support test include/linux/trace_events.h | 5 + kernel/trace/trace_events.c | 18 ++++ kernel/trace/trace_events_hist.c | 101 +++++++++++++++++++- tools/testing/selftests/ftrace/Makefile | 2 tools/testing/selftests/ftrace/poll.c | 74 +++++++++++++++ .../ftrace/test.d/trigger/trigger-hist-poll.tc | 74 +++++++++++++++ 6 files changed, 271 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/ftrace/poll.c create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc -- Masami Hiramatsu (Google) <mhiramat(a)kernel.org>

10 months, 3 weeks

3
6
0 0

[PATCH v5 0/4] Introduce userspace-driven ALSA timers

by Ivan Orlov

There are multiple possible timer sources which could be useful for the sound stream synchronization: hrtimers, hardware clocks (e.g. PTP), timer wheels (jiffies). Currently, using one of them to synchronize the audio stream of snd-aloop module would require writing a kernel-space driver which exports an ALSA timer through the snd_timer interface. However, it is not really convenient for application developers, who may want to define their custom timer sources for audio synchronization. For instance, we could have a network application which receives frames and sends them to snd-aloop pcm device, and another application listening on the other end of snd-aloop. It makes sense to transfer a new period of data only when certain amount of frames is received through the network, but definitely not when a certain amount of jiffies on a local system elapses. Since all of the devices are purely virtual it won't introduce any glitches and will help the application developers to avoid using sample-rate conversion. This patch series introduces userspace-driven ALSA timers: virtual timers which are created and controlled from userspace. The timer can be created from the userspace using the new ioctl SNDRV_TIMER_IOCTL_CREATE. After creating a timer, it becomes available for use system-wide, so it can be passed to snd-aloop as a timer source (timer_source parameter would be "-1.SNDRV_TIMER_GLOBAL_UDRIVEN.{timer_id}"). When the userspace app decides to trigger a timer, it calls another ioctl SNDRV_TIMER_IOCTL_TRIGGER on the file descriptor of a timer. It initiates a transfer of a new period of data. Userspace-driven timers are associated with file descriptors. If the application wishes to destroy the timer, it can simply release the file descriptor of a virtual timer. I believe introducing new ioctl calls is quite inconvenient (as we have a limited amount of them), but other possible ways of app <-> kernel communication (like virtual FS) seem completely inappropriate for this task (but I'd love to discuss alternative solutions). This patch series also updates the snd-aloop module so the global timers can be used as a timer_source for it (it allows using userspace-driven timers as timer source). V1 -> V2: - Fix some problems found by Christophe Jaillet <christophe.jaillet(a)wanadoo.fr> V2 -> V3: - Add improvements suggested by Takashi Iwai <tiwai(a)suse.de> V3 -> V4: - Address comments from Jaroslav Kysela <perex(a)perex.cz> and Mark Brown <broonie(a)kernel.org> V4 -> V5: - Add missing error processing noticed by Takashi Iwai <tiwai(a)suse.de> - Return timer file descriptor as part of the snd_timer_uinfo structure. This is a more standard way of using ioctl interface, where the return value of the ioctl is either 0 or an error code. Please, find the patch-specific changelog in the following patches. Ivan Orlov (4): ALSA: aloop: Allow using global timers Docs/sound: Add documentation for userspace-driven ALSA timers ALSA: timer: Introduce virtual userspace-driven timers selftests: ALSA: Cover userspace-driven timers with test Documentation/sound/index.rst | 1 + Documentation/sound/utimers.rst | 126 +++++++++++ include/uapi/sound/asound.h | 17 +- sound/core/Kconfig | 10 + sound/core/timer.c | 225 ++++++++++++++++++++ sound/drivers/aloop.c | 2 + tools/testing/selftests/alsa/Makefile | 4 +- tools/testing/selftests/alsa/global-timer.c | 87 ++++++++ tools/testing/selftests/alsa/utimer-test.c | 164 ++++++++++++++ 9 files changed, 633 insertions(+), 3 deletions(-) create mode 100644 Documentation/sound/utimers.rst create mode 100644 tools/testing/selftests/alsa/global-timer.c create mode 100644 tools/testing/selftests/alsa/utimer-test.c -- 2.34.1

10 months, 3 weeks

2
5
0 0

[PATCH net-next v19 09/13] tcp: RX path for devmem TCP

by Mina Almasry

In tcp_recvmsg_locked(), detect if the skb being received by the user is a devmem skb. In this case - if the user provided the MSG_SOCK_DEVMEM flag - pass it to tcp_recvmsg_devmem() for custom handling. tcp_recvmsg_devmem() copies any data in the skb header to the linear buffer, and returns a cmsg to the user indicating the number of bytes returned in the linear buffer. tcp_recvmsg_devmem() then loops over the unaccessible devmem skb frags, and returns to the user a cmsg_devmem indicating the location of the data in the dmabuf device memory. cmsg_devmem contains this information: 1. the offset into the dmabuf where the payload starts. 'frag_offset'. 2. the size of the frag. 'frag_size'. 3. an opaque token 'frag_token' to return to the kernel when the buffer is to be released. The pages awaiting freeing are stored in the newly added sk->sk_user_frags, and each page passed to userspace is get_page()'d. This reference is dropped once the userspace indicates that it is done reading this page. All pages are released when the socket is destroyed. Signed-off-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Kaiyuan Zhang <kaiyuanz(a)google.com> Signed-off-by: Mina Almasry <almasrymina(a)google.com> Reviewed-by: Pavel Begunkov <asml.silence(a)gmail.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> --- v16: - Fix number assignement (Arnd). v13: - Refactored user frags cleanup into a common function to avoid __maybe_unused. (Pavel) - change to offset = 0 for some improved clarity. v11: - Refactor to common function te remove conditional lock sparse warning (Paolo) v7: - Updated the SO_DEVMEM_* uapi to use the next available entries (Arnd). - Updated dmabuf_cmsg struct to be __u64 padded (Arnd). - Squashed fix from Eric to initialize sk_user_frags for passive sockets (Eric). v6 - skb->dmabuf -> skb->readable (Pavel) - Fixed asm definitions of SO_DEVMEM_LINEAR/SO_DEVMEM_DMABUF not found on some archs. - Squashed in locking optimizations from edumazet(a)google.com. With this change we lock the xarray once per per tcp_recvmsg_dmabuf() rather than once per frag in xa_alloc(). Changes in v1: - Added dmabuf_id to dmabuf_cmsg (David/Stan). - Devmem -> dmabuf (David). - Change tcp_recvmsg_dmabuf() check to skb->dmabuf (Paolo). - Use __skb_frag_ref() & napi_pp_put_page() for refcounting (Yunsheng). RFC v3: - Fixed issue with put_cmsg() failing silently. --- arch/alpha/include/uapi/asm/socket.h | 5 + arch/mips/include/uapi/asm/socket.h | 5 + arch/parisc/include/uapi/asm/socket.h | 5 + arch/sparc/include/uapi/asm/socket.h | 5 + include/linux/socket.h | 1 + include/net/netmem.h | 13 ++ include/net/sock.h | 2 + include/uapi/asm-generic/socket.h | 5 + include/uapi/linux/uio.h | 13 ++ net/ipv4/tcp.c | 255 +++++++++++++++++++++++++- net/ipv4/tcp_ipv4.c | 16 ++ net/ipv4/tcp_minisocks.c | 2 + 12 files changed, 322 insertions(+), 5 deletions(-) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index e94f621903fe..ef4656a41058 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -140,6 +140,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 60ebaed28a4c..414807d55e33 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -151,6 +151,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index be264c2b1a11..2b817efd4544 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -132,6 +132,11 @@ #define SO_PASSPIDFD 0x404A #define SO_PEERPIDFD 0x404B +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 682da3714686..00248fc68977 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -133,6 +133,11 @@ #define SO_PASSPIDFD 0x0055 #define SO_PEERPIDFD 0x0056 +#define SO_DEVMEM_LINEAR 0x0057 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 0x0058 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) diff --git a/include/linux/socket.h b/include/linux/socket.h index df9cdb8bbfb8..d18cc47e89bd 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -327,6 +327,7 @@ struct ucred { * plain text and require encryption */ +#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/include/net/netmem.h b/include/net/netmem.h index 284f84a312c2..84043fbdd797 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -65,6 +65,19 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov) return niov - net_iov_owner(niov)->niovs; } +static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_virtual + + ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT); +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding->id; +} + static inline struct net_devmem_dmabuf_binding * net_iov_binding(const struct net_iov *niov) { diff --git a/include/net/sock.h b/include/net/sock.h index cce23ac4d514..f8ec869be238 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -337,6 +337,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_user_frags: xarray of pages the user is holding a reference on. */ struct sock { /* @@ -542,6 +543,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct xarray sk_user_frags; }; struct sock_bh_locked { diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8ce8a39a1e5f..e993edc9c0ee 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 059b1a9147f4..3a22ddae376a 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -20,6 +20,19 @@ struct iovec __kernel_size_t iov_len; /* Must be size_t (1003.1g) */ }; +struct dmabuf_cmsg { + __u64 frag_offset; /* offset into the dmabuf where the frag starts. + */ + __u32 frag_size; /* size of the frag. */ + __u32 frag_token; /* token representing this frag for + * DEVMEM_DONTNEED. + */ + __u32 dmabuf_id; /* dmabuf id this frag belongs to. */ + __u32 flags; /* Currently unused. Reserved for future + * uses. + */ +}; + /* * UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1) */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 30e0aa38ba9b..40e7335dae6e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -471,6 +471,7 @@ void tcp_init_sock(struct sock *sk) set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); + xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock); @@ -2323,6 +2324,220 @@ static int tcp_inq_hint(struct sock *sk) return inq; } +/* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ +struct tcp_xa_pool { + u8 max; /* max <= MAX_SKB_FRAGS */ + u8 idx; /* idx <= max */ + __u32 tokens[MAX_SKB_FRAGS]; + netmem_ref netmems[MAX_SKB_FRAGS]; +}; + +static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) +{ + int i; + + /* Commit part that has been copied to user space. */ + for (i = 0; i < p->idx; i++) + __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, + (__force void *)p->netmems[i], GFP_KERNEL); + /* Rollback what has been pre-allocated and is no longer needed. */ + for (; i < p->max; i++) + __xa_erase(&sk->sk_user_frags, p->tokens[i]); + + p->max = 0; + p->idx = 0; +} + +static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) +{ + if (!p->max) + return; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + xa_unlock_bh(&sk->sk_user_frags); +} + +static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, + unsigned int max_frags) +{ + int err, k; + + if (p->idx < p->max) + return 0; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + for (k = 0; k < max_frags; k++) { + err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], + XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); + if (err) + break; + } + + xa_unlock_bh(&sk->sk_user_frags); + + p->max = k; + p->idx = 0; + return k ? 0 : err; +} + +/* On error, returns the -errno. On success, returns number of bytes sent to the + * user. May not consume all of @remaining_len. + */ +static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, + unsigned int offset, struct msghdr *msg, + int remaining_len) +{ + struct dmabuf_cmsg dmabuf_cmsg = { 0 }; + struct tcp_xa_pool tcp_xa_pool; + unsigned int start; + int i, copy, n; + int sent = 0; + int err = 0; + + tcp_xa_pool.max = 0; + tcp_xa_pool.idx = 0; + do { + start = skb_headlen(skb); + + if (skb_frags_readable(skb)) { + err = -ENODEV; + goto out; + } + + /* Copy header. */ + copy = start - offset; + if (copy > 0) { + copy = min(copy, remaining_len); + + n = copy_to_iter(skb->data + offset, copy, + &msg->msg_iter); + if (n != copy) { + err = -EFAULT; + goto out; + } + + offset += copy; + remaining_len -= copy; + + /* First a dmabuf_cmsg for # bytes copied to user + * buffer. + */ + memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); + dmabuf_cmsg.frag_size = copy; + err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + sent += copy; + + if (remaining_len == 0) + goto out; + } + + /* after that, send information of dmabuf pages through a + * sequence of cmsg + */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct net_iov *niov; + u64 frag_offset; + int end; + + /* !skb_frags_readable() should indicate that ALL the + * frags in this skb are dmabuf net_iovs. We're checking + * for that flag above, but also check individual frags + * here. If the tcp stack is not setting + * skb_frags_readable() correctly, we still don't want + * to crash here. + */ + if (!skb_frag_net_iov(frag)) { + net_err_ratelimited("Found non-dmabuf skb with net_iov"); + err = -ENODEV; + goto out; + } + + niov = skb_frag_net_iov(frag); + end = start + skb_frag_size(frag); + copy = end - offset; + + if (copy > 0) { + copy = min(copy, remaining_len); + + frag_offset = net_iov_virtual_addr(niov) + + skb_frag_off(frag) + offset - + start; + dmabuf_cmsg.frag_offset = frag_offset; + dmabuf_cmsg.frag_size = copy; + err = tcp_xa_pool_refill(sk, &tcp_xa_pool, + skb_shinfo(skb)->nr_frags - i); + if (err) + goto out; + + /* Will perform the exchange later */ + dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; + dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); + + offset += copy; + remaining_len -= copy; + + err = put_cmsg(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + atomic_long_inc(&niov->pp_ref_count); + tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); + + sent += copy; + + if (remaining_len == 0) + goto out; + } + start = end; + } + + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!remaining_len) + goto out; + + /* if remaining_len is not satisfied yet, we need to go to the + * next frag in the frag_list to satisfy remaining_len. + */ + skb = skb_shinfo(skb)->frag_list ?: skb->next; + + offset = 0; + } while (skb); + + if (remaining_len) { + err = -EFAULT; + goto out; + } + +out: + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!sent) + sent = err; + + return sent; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -2336,6 +2551,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); + int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; @@ -2515,15 +2731,44 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, } if (!(flags & MSG_TRUNC)) { - err = skb_copy_datagram_msg(skb, offset, msg, used); - if (err) { - /* Exception. Bailout! */ - if (!copied) - copied = -EFAULT; + if (last_copied_dmabuf != -1 && + last_copied_dmabuf != !skb_frags_readable(skb)) break; + + if (skb_frags_readable(skb)) { + err = skb_copy_datagram_msg(skb, offset, msg, + used); + if (err) { + /* Exception. Bailout! */ + if (!copied) + copied = -EFAULT; + break; + } + } else { + if (!(flags & MSG_SOCK_DEVMEM)) { + /* dmabuf skbs can only be received + * with the MSG_SOCK_DEVMEM flag. + */ + if (!copied) + copied = -EFAULT; + + break; + } + + err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, + used); + if (err <= 0) { + if (!copied) + copied = -EFAULT; + + break; + } + used = err; } } + last_copied_dmabuf = !skb_frags_readable(skb); + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd17f25ff288..f3b2ae0823c4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -79,6 +79,7 @@ #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <linux/btf_ids.h> +#include <linux/skbuff_ref.h> #include <crypto/hash.h> #include <linux/scatterlist.h> @@ -2507,10 +2508,25 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head) } #endif +static void tcp_release_user_frags(struct sock *sk) +{ +#ifdef CONFIG_PAGE_POOL + unsigned long index; + void *netmem; + + xa_for_each(&sk->sk_user_frags, index, netmem) + WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); +#endif +} + void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + tcp_release_user_frags(sk); + + xa_destroy(&sk->sk_user_frags); + trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a19a9dbd3409..9ab87a41255d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -625,6 +625,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); + xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1); + return newsk; } EXPORT_SYMBOL(tcp_create_openreq_child); -- 2.46.0.76.ge559c4bf1a-goog

10 months, 3 weeks

2
3
0 0

[PATCH net] tc-testing: don't access non-existent variable on exception

by Simon Horman

Since commit 255c1c7279ab ("tc-testing: Allow test cases to be skipped") the variable test_ordinal doesn't exist in call_pre_case(). So it should not be accessed when an exception occurs. This resolves the following splat: ... During handling of the above exception, another exception occurred: Traceback (most recent call last): File ".../tdc.py", line 1028, in <module> main() File ".../tdc.py", line 1022, in main set_operation_mode(pm, parser, args, remaining) File ".../tdc.py", line 966, in set_operation_mode catresults = test_runner_serial(pm, args, alltests) File ".../tdc.py", line 642, in test_runner_serial (index, tsr) = test_runner(pm, args, alltests) File ".../tdc.py", line 536, in test_runner res = run_one_test(pm, args, index, tidx) File ".../tdc.py", line 419, in run_one_test pm.call_pre_case(tidx) File ".../tdc.py", line 146, in call_pre_case print('test_ordinal is {}'.format(test_ordinal)) NameError: name 'test_ordinal' is not defined Fixes: 255c1c7279ab ("tc-testing: Allow test cases to be skipped") Signed-off-by: Simon Horman <horms(a)kernel.org> --- tools/testing/selftests/tc-testing/tdc.py | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index ee349187636f..4f255cec0c22 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -143,7 +143,6 @@ class PluginMgr: except Exception as ee: print('exception {} in call to pre_case for {} plugin'. format(ee, pgn_inst.__class__)) - print('test_ordinal is {}'.format(test_ordinal)) print('testid is {}'.format(caseinfo['id'])) raise

10 months, 3 weeks

3
2
0 0

[RFC PATCH] selftests/mm: compaction_test: Move often used filepaths to strings

by Aryabhatta Dey

Add defines for the file path names to avoid duplicate strings in print messages and make it easier to maintain. Signed-off-by: Aryabhatta Dey <aryabhattadey35(a)gmail.com> --- tools/testing/selftests/mm/compaction_test.c | 46 ++++++++++---------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index e140558e6f53..8f46431a9182 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -21,6 +21,9 @@ #define MAP_SIZE_MB 100 #define MAP_SIZE (MAP_SIZE_MB * 1024 * 1024) +#define COMPACT_UNEVICTABLE_ALLOWED_FILE_PATH "/proc/sys/vm/compact_unevictable_allowed" +#define NR_HUGEPAGES_FILE_NAME_PATH "/proc/sys/vm/nr_hugepages" + struct map_list { void *map; struct map_list *next; @@ -59,17 +62,16 @@ int prereq(void) char allowed; int fd; - fd = open("/proc/sys/vm/compact_unevictable_allowed", - O_RDONLY | O_NONBLOCK); + fd = open(COMPACT_UNEVICTABLE_ALLOWED_FILE_PATH, O_RDONLY | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/compact_unevictable_allowed: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + COMPACT_UNEVICTABLE_ALLOWED_FILE_PATH, strerror(errno)); return -1; } if (read(fd, &allowed, sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to read from /proc/sys/vm/compact_unevictable_allowed: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from %s: %s\n", + COMPACT_UNEVICTABLE_ALLOWED_FILE_PATH, strerror(errno)); close(fd); return -1; } @@ -97,10 +99,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, in to play */ mem_free = mem_free * 0.8; - fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + fd = open(NR_HUGEPAGES_FILE_NAME_PATH, O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); ret = -1; goto out; } @@ -108,16 +110,16 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 100000 to %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } lseek(fd, 0, SEEK_SET); if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_print_msg("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to re-read from %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } @@ -134,8 +136,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) != strlen(init_nr_hugepages)) { - ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write value to %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } @@ -162,15 +164,15 @@ int set_zero_hugepages(unsigned long *initial_nr_hugepages) int fd, ret = -1; char nr_hugepages[20] = {0}; - fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + fd = open(NR_HUGEPAGES_FILE_NAME_PATH, O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto out; } if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } @@ -178,8 +180,8 @@ int set_zero_hugepages(unsigned long *initial_nr_hugepages) /* Start with the initial condition of 0 huge pages */ if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 0 to %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } -- 2.46.0

10 months, 3 weeks

1
0
0 0

[RFC PATCH] selftests/mm: compaction_test: Move often used filepaths to strings

by Aryabhatta Dey

Add defines for file path names to avoid duplicate strings in print messages and make it easier to maintain. Signed-off-by: Aryabhatta Dey <aryabhattadey35(a)gmail.com> --- tools/testing/selftests/mm/compaction_test.c | 46 ++++++++++---------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index e140558e6f53..541ac0373258 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -21,6 +21,9 @@ #define MAP_SIZE_MB 100 #define MAP_SIZE (MAP_SIZE_MB * 1024 * 1024) +#define COMPACT_UNEVICTABLE_ALLOWED "/proc/sys/vm/compact_unevictable_allowed" +#define NR_HUGEPAGES "/proc/sys/vm/nr_hugepages" + struct map_list { void *map; struct map_list *next; @@ -59,17 +62,16 @@ int prereq(void) char allowed; int fd; - fd = open("/proc/sys/vm/compact_unevictable_allowed", - O_RDONLY | O_NONBLOCK); + fd = open(COMPACT_UNEVICTABLE_ALLOWED, O_RDONLY | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/compact_unevictable_allowed: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + COMPACT_UNEVICTABLE_ALLOWED, strerror(errno)); return -1; } if (read(fd, &allowed, sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to read from /proc/sys/vm/compact_unevictable_allowed: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from %s: %s\n", + COMPACT_UNEVICTABLE_ALLOWED, strerror(errno)); close(fd); return -1; } @@ -97,10 +99,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, in to play */ mem_free = mem_free * 0.8; - fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + fd = open(NR_HUGEPAGES, O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + NR_HUGEPAGES, strerror(errno)); ret = -1; goto out; } @@ -108,16 +110,16 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 100000 to %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } lseek(fd, 0, SEEK_SET); if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_print_msg("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to re-read from %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } @@ -134,8 +136,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) != strlen(init_nr_hugepages)) { - ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write value to %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } @@ -162,15 +164,15 @@ int set_zero_hugepages(unsigned long *initial_nr_hugepages) int fd, ret = -1; char nr_hugepages[20] = {0}; - fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + fd = open(NR_HUGEPAGES, O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto out; } if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } @@ -178,8 +180,8 @@ int set_zero_hugepages(unsigned long *initial_nr_hugepages) /* Start with the initial condition of 0 huge pages */ if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 0 to %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } -- 2.46.0

10 months, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror