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

[PATCH v2 1/2] mm: Add an F_SEAL_FS_WRITE seal to memfd

by Joel Fernandes (Google)

Android uses ashmem for sharing memory regions. We are looking forward to migrating all usecases of ashmem to memfd so that we can possibly remove the ashmem driver in the future from staging while also benefiting from using memfd and contributing to it. Note staging drivers are also not ABI and generally can be removed at anytime. One of the main usecases Android has is the ability to create a region and mmap it as writeable, then drop its protection for "future" writes while keeping the existing already mmap'ed writeable-region active. This allows us to implement a usecase where receivers of the shared memory buffer can get a read-only view, while the sender continues to write to the buffer. See CursorWindow in Android for more details: https://developer.android.com/reference/android/database/CursorWindow This usecase cannot be implemented with the existing F_SEAL_WRITE seal. To support the usecase, this patch adds a new F_SEAL_FS_WRITE seal which prevents any future mmap and write syscalls from succeeding while keeping the existing mmap active. The following program shows the seal working in action: int main() { int ret, fd; void *addr, *addr2, *addr3, *addr1; ret = memfd_create_region("test_region", REGION_SIZE); printf("ret=%d\n", ret); fd = ret; // Create map addr = mmap(0, REGION_SIZE, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); if (addr == MAP_FAILED) printf("map 0 failed\n"); else printf("map 0 passed\n"); if ((ret = write(fd, "test", 4)) != 4) printf("write failed even though no fs-write seal " "(ret=%d errno =%d)\n", ret, errno); else printf("write passed\n"); addr1 = mmap(0, REGION_SIZE, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); if (addr1 == MAP_FAILED) perror("map 1 prot-write failed even though no seal\n"); else printf("map 1 prot-write passed as expected\n"); ret = fcntl(fd, F_ADD_SEALS, F_SEAL_FS_WRITE); if (ret == -1) printf("fcntl failed, errno: %d\n", errno); else printf("fs-write seal now active\n"); if ((ret = write(fd, "test", 4)) != 4) printf("write failed as expected due to fs-write seal\n"); else printf("write passed (unexpected)\n"); addr2 = mmap(0, REGION_SIZE, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); if (addr2 == MAP_FAILED) perror("map 2 prot-write failed as expected due to seal\n"); else printf("map 2 passed\n"); addr3 = mmap(0, REGION_SIZE, PROT_READ, MAP_SHARED, fd, 0); if (addr3 == MAP_FAILED) perror("map 3 failed\n"); else printf("map 3 prot-read passed as expected\n"); } The output of running this program is as follows: ret=3 map 0 passed write passed map 1 prot-write passed as expected fs-write seal now active write failed as expected due to fs-write seal map 2 prot-write failed as expected due to seal : Permission denied map 3 prot-read passed as expected Note: This seal will also prevent growing and shrinking of the memfd. This is not something we do in Android so it does not affect us, however I have mentioned this behavior of the seal in the manpage. Cc: jreck(a)google.com Cc: john.stultz(a)linaro.org Cc: tkjos(a)google.com Cc: gregkh(a)linuxfoundation.org Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org> --- v1->v2: No change, just added selftests to the series. manpages are ready and I'll submit them once the patches are accepted. include/uapi/linux/fcntl.h | 1 + mm/memfd.c | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index c98312fa78a5..fe44a2035edf 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -41,6 +41,7 @@ #define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ +#define F_SEAL_FS_WRITE 0x0010 /* prevent all write-related syscalls */ /* (1U << 31) is reserved for signed error codes */ /* diff --git a/mm/memfd.c b/mm/memfd.c index 27069518e3c5..9b8855b80de9 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -150,7 +150,8 @@ static unsigned int *memfd_file_seals_ptr(struct file *file) #define F_ALL_SEALS (F_SEAL_SEAL | \ F_SEAL_SHRINK | \ F_SEAL_GROW | \ - F_SEAL_WRITE) + F_SEAL_WRITE | \ + F_SEAL_FS_WRITE) static int memfd_add_seals(struct file *file, unsigned int seals) { @@ -219,6 +220,9 @@ static int memfd_add_seals(struct file *file, unsigned int seals) } } + if ((seals & F_SEAL_FS_WRITE) && !(*file_seals & F_SEAL_FS_WRITE)) + file->f_mode &= ~(FMODE_WRITE | FMODE_PWRITE); + *file_seals |= seals; error = 0; -- 2.19.0.605.g01d371f741-goog

7 years, 2 months

5
9
0 0

[PATCH] selftests: fix warning: "_GNU_SOURCE" redefined

by Peng Hao

Makefile contains -D_GNU_SOURCE. remove define "_GNU_SOURCE" in c files. Signed-off-by: Peng Hao <peng.hao2(a)zte.com.cn> --- tools/testing/selftests/proc/fd-001-lookup.c | 2 +- tools/testing/selftests/proc/fd-003-kthread.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/proc/fd-001-lookup.c b/tools/testing/selftests/proc/fd-001-lookup.c index a2010df..60d7948 100644 --- a/tools/testing/selftests/proc/fd-001-lookup.c +++ b/tools/testing/selftests/proc/fd-001-lookup.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ // Test /proc/*/fd lookup. -#define _GNU_SOURCE + #undef NDEBUG #include <assert.h> #include <dirent.h> diff --git a/tools/testing/selftests/proc/fd-003-kthread.c b/tools/testing/selftests/proc/fd-003-kthread.c index 1d659d5..dc591f9 100644 --- a/tools/testing/selftests/proc/fd-003-kthread.c +++ b/tools/testing/selftests/proc/fd-003-kthread.c @@ -14,7 +14,7 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ // Test that /proc/$KERNEL_THREAD/fd/ is empty. -#define _GNU_SOURCE + #undef NDEBUG #include <sys/syscall.h> #include <assert.h> -- 1.8.3.1

7 years, 2 months

2
1
0 0

[PATCH] selftests: kvm: Fix -Wformat warnings

by Andrea Parri

Fixes the following warnings: dirty_log_test.c: In function ‘help’: dirty_log_test.c:216:9: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘int’ [-Wformat=] printf(" -i: specify iteration counts (default: %"PRIu64")\n", ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from include/test_util.h:18:0, from dirty_log_test.c:16: /usr/include/inttypes.h:105:34: note: format string is defined here # define PRIu64 __PRI64_PREFIX "u" dirty_log_test.c:218:9: warning: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘int’ [-Wformat=] printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n", ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from include/test_util.h:18:0, from dirty_log_test.c:16: /usr/include/inttypes.h:105:34: note: format string is defined here # define PRIu64 __PRI64_PREFIX "u" Signed-off-by: Andrea Parri <andrea.parri(a)amarulasolutions.com> --- tools/testing/selftests/kvm/dirty_log_test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 0c2cdc105f968..a9c4b5e21d7e7 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -31,9 +31,9 @@ /* How many pages to dirty for each guest loop */ #define TEST_PAGES_PER_LOOP 1024 /* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */ -#define TEST_HOST_LOOP_N 32 +#define TEST_HOST_LOOP_N 32UL /* Interval for each host loop (ms) */ -#define TEST_HOST_LOOP_INTERVAL 10 +#define TEST_HOST_LOOP_INTERVAL 10UL /* * Guest variables. We use these variables to share data between host -- 2.17.1

7 years, 2 months

2
1
0 0

[PATCH] kvm: selftests: fix spelling mistake "Insufficent" -> "Insufficient"

by Colin King

From: Colin Ian King <colin.king(a)canonical.com> Trivial fix to spelling mistake in TEST_ASSERT message text Signed-off-by: Colin Ian King <colin.king(a)canonical.com> --- tools/testing/selftests/kvm/lib/kvm_util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 6fd8c089cafc..a56ef6b187bb 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -123,7 +123,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) /* Allocate memory. */ vm = calloc(1, sizeof(*vm)); - TEST_ASSERT(vm != NULL, "Insufficent Memory"); + TEST_ASSERT(vm != NULL, "Insufficient Memory"); vm->mode = mode; vm_open(vm, perm); -- 2.17.1

7 years, 2 months

2
1
0 0

[bug report] Fix cg_read_strcmp()

by Dan Carpenter

Hello Jay Kamat, This is a semi-automatic email about new static checker warnings. The patch 48c2bb0b9cf8: "Fix cg_read_strcmp()" from Sep 7, 2018, leads to the following Smatch complaint: ./tools/testing/selftests/cgroup/cgroup_util.c:111 cg_read_strcmp() error: we previously assumed 'expected' could be null (see line 97) ./tools/testing/selftests/cgroup/cgroup_util.c 96 /* Handle the case of comparing against empty string */ 97 if (!expected) ^^^^^^^^ Originally, we assumed that expected was non-NULL but we added a check here. I feel like maybe the intention was to check was supposed to be: if (expected[0] == '\0') but that's just a random guess. 98 size = 32; 99 else 100 size = strlen(expected) + 1; 101 102 buf = malloc(size); 103 if (!buf) 104 return -1; 105 106 if (cg_read(cgroup, control, buf, size)) { 107 free(buf); 108 return -1; 109 } 110 111 ret = strcmp(expected, buf); ^^^^^^^^ Unchecked dereference. 112 free(buf); 113 return ret; regards, dan carpenter

7 years, 2 months

1
0
0 0

[PATCH] selftests: bpf: install script with_addr.sh

by Anders Roxell

When test_flow_dissector.sh runs it complains that it can't find script with_addr.sh: ./test_flow_dissector.sh: line 81: ./with_addr.sh: No such file or directory Rework so that with_addr.sh gets installed, add it to TEST_PROGS_EXTENDED variable. Fixes: 50b3ed57dee9 ("selftests/bpf: test bpf flow dissection") Signed-off-by: Anders Roxell <anders.roxell(a)linaro.org> --- tools/testing/selftests/bpf/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 1381ab81099c..efd108ff737d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -51,6 +51,8 @@ TEST_PROGS := test_kmod.sh \ test_skb_cgroup_id.sh \ test_flow_dissector.sh +TEST_PROGS_EXTENDED := with_addr.sh + # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector -- 2.19.1

7 years, 2 months

3
2
0 0

[PATCH] selftests: bpf: add config fragment LWTUNNEL

by Anders Roxell

When test_lwt_seg6local.sh was added commit c99a84eac026 ("selftests/bpf: test for seg6local End.BPF action") config fragment wasn't added, and without CONFIG_LWTUNNEL enabled we see this: Error: CONFIG_LWTUNNEL is not enabled in this kernel. selftests: test_lwt_seg6local [FAILED] Signed-off-by: Anders Roxell <anders.roxell(a)linaro.org> --- tools/testing/selftests/bpf/config | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 3655508f95fd..dd49df5e2df4 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -19,3 +19,4 @@ CONFIG_CRYPTO_SHA256=m CONFIG_VXLAN=y CONFIG_GENEVE=y CONFIG_NET_CLS_FLOWER=m +CONFIG_LWTUNNEL=y -- 2.19.1

7 years, 2 months

3
2
0 0

[PATCH] selftests/gpio: fix compiling errors

by Li Zhijian

lizhijian@haswell-OptiPlex-9020:/home/lizj/linux/tools/testing/selftests$ make [...snip...] make ARCH=x86 CROSS_COMPILE= -C ../../../gpio make[2]: Entering directory '/home/lizj/linux/tools/gpio' [...snip...] make[3]: Leaving directory '/home/lizj/linux/tools/gpio' LINK /home/lizj/linux/tools/testing/selftests/gpiogpio-event-mon make[2]: Leaving directory '/home/lizj/linux/tools/gpio' gcc -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ gpio-mockup-chardev.c ../../../gpio/gpio-utils.o -lmount -I/usr/include/libmount -o gpio-mockup-chardev gcc: error: ../../../gpio/gpio-utils.o: No such file or directory <builtin>: recipe for target 'gpio-mockup-chardev' failed make[1]: *** [gpio-mockup-chardev] Error 1 make[1]: Leaving directory '/home/lizj/linux/tools/testing/selftests/gpio' Makefile:85: recipe for target 'all' failed make: *** [all] Error 2 in this patch - correct target name to $OUTPUTgpio-utils.o - pass OUTPUT to tools/gpio/Makefile - support cleanup ../gpiogpio-hammer.o CC: Bamvor Jian Zhang <bamv2005(a)gmail.com> CC: Bartosz Golaszewski <brgl(a)bgdev.pl> CC: Shuah Khan <shuah(a)kernel.org> CC: linux-gpio(a)vger.kernel.org Signed-off-by: Li Zhijian <lizhijian(a)cn.fujitsu.com> --- tools/testing/selftests/gpio/Makefile | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 4665cdb..7f9354a 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -7,7 +7,7 @@ EXTRA_PROGS := ../gpiogpio-event-mon ../gpiogpio-hammer ../gpiolsgpio EXTRA_DIRS := ../gpioinclude/ EXTRA_OBJS := ../gpiogpio-event-mon-in.o ../gpiogpio-event-mon.o EXTRA_OBJS += ../gpiogpio-hammer-in.o ../gpiogpio-utils.o ../gpiolsgpio-in.o -EXTRA_OBJS += ../gpiolsgpio.o +EXTRA_OBJS += ../gpiolsgpio.o ../gpiogpio-hammer.o include ../lib.mk @@ -22,7 +22,7 @@ CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ LDLIBS += -lmount -I/usr/include/libmount $(BINARIES):| khdr -$(BINARIES): ../../../gpio/gpio-utils.o +$(BINARIES): ../gpiogpio-utils.o -../../../gpio/gpio-utils.o: - make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio +../gpiogpio-utils.o: + make OUTPUT=$(OUTPUT) ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio -- 2.7.4

7 years, 2 months

2
3
0 0

[RFC PATCH for 4.21 16/16] cpu-opv/selftests: Provide Makefile, scripts, gitignore

by Mathieu Desnoyers

A run_param_test.sh script runs many variants of the parametrizable tests. Wire up the cpu-opv Makefile, add directory entry into MAINTAINERS file. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Joel Fernandes <joelaf(a)google.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Watson <davejwatson(a)fb.com> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Andi Kleen <andi(a)firstfloor.org> Cc: linux-kselftest(a)vger.kernel.org Cc: "H . Peter Anvin" <hpa(a)zytor.com> Cc: Chris Lameter <cl(a)linux.com> Cc: Russell King <linux(a)arm.linux.org.uk> Cc: Michael Kerrisk <mtk.manpages(a)gmail.com> Cc: "Paul E . McKenney" <paulmck(a)linux.vnet.ibm.com> Cc: Paul Turner <pjt(a)google.com> Cc: Boqun Feng <boqun.feng(a)gmail.com> Cc: Josh Triplett <josh(a)joshtriplett.org> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Ben Maurer <bmaurer(a)fb.com> Cc: linux-api(a)vger.kernel.org Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> --- MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/cpu-opv/.gitignore | 6 + tools/testing/selftests/cpu-opv/Makefile | 39 +++++++ tools/testing/selftests/cpu-opv/run_param_test.sh | 134 ++++++++++++++++++++++ 5 files changed, 181 insertions(+) create mode 100644 tools/testing/selftests/cpu-opv/.gitignore create mode 100644 tools/testing/selftests/cpu-opv/Makefile create mode 100755 tools/testing/selftests/cpu-opv/run_param_test.sh diff --git a/MAINTAINERS b/MAINTAINERS index 3b50578fc5d9..206fe4597697 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3864,6 +3864,7 @@ L: linux-kernel(a)vger.kernel.org S: Supported F: kernel/cpu_opv.c F: include/uapi/linux/cpu_opv.h +F: tools/testing/selftests/cpu-opv/ CRAMFS FILESYSTEM M: Nicolas Pitre <nico(a)linaro.org> diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index f1fe492c8e17..42bcc6e5fc5d 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -6,6 +6,7 @@ TARGETS += capabilities TARGETS += cgroup TARGETS += cpufreq TARGETS += cpu-hotplug +TARGETS += cpu-opv TARGETS += efivarfs TARGETS += exec TARGETS += filesystems diff --git a/tools/testing/selftests/cpu-opv/.gitignore b/tools/testing/selftests/cpu-opv/.gitignore new file mode 100644 index 000000000000..8c7bb1f8be79 --- /dev/null +++ b/tools/testing/selftests/cpu-opv/.gitignore @@ -0,0 +1,6 @@ +basic_cpu_opv_test +basic_percpu_ops_test +param_test +param_test_benchmark +param_test_compare_twice +param_test_skip_fastpath diff --git a/tools/testing/selftests/cpu-opv/Makefile b/tools/testing/selftests/cpu-opv/Makefile new file mode 100644 index 000000000000..46f49bf30bae --- /dev/null +++ b/tools/testing/selftests/cpu-opv/Makefile @@ -0,0 +1,39 @@ +# SPDX-License-Identifier: GPL-2.0+ OR MIT +CFLAGS += -O2 -Wall -g -I./ -I../rseq/ -I../../../../usr/include/ -L./ -Wl,-rpath=./ +LDLIBS += -lpthread + +# Own dependencies because we only want to build against 1st prerequisite, but +# still track changes to header files and depend on shared object. +OVERRIDE_TARGETS = 1 + +TEST_GEN_PROGS = basic_cpu_opv_test basic_percpu_ops_test \ + param_test param_test_skip_fastpath \ + param_test_benchmark param_test_compare_twice + +TEST_GEN_PROGS_EXTENDED = librseq.so libcpu-op.so + +TEST_PROGS = run_param_test.sh + +include ../lib.mk + +$(OUTPUT)/libcpu-op.so: cpu-op.c cpu-op.h + $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ + +$(OUTPUT)/librseq.so: ../rseq/rseq.c ../rseq/rseq.h ../rseq/rseq-*.h + $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ + +$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h + $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -lcpu-op -o $@ + +$(OUTPUT)/param_test_skip_fastpath: param_test.c $(TEST_GEN_PROGS_EXTENDED) \ + ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h + $(CC) $(CFLAGS) -DRSEQ_SKIP_FASTPATH $< $(LDLIBS) -lrseq -lcpu-op -o $@ + +$(OUTPUT)/param_test_benchmark: param_test.c $(TEST_GEN_PROGS_EXTENDED) \ + ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h + $(CC) $(CFLAGS) -DBENCHMARK $< $(LDLIBS) -lrseq -lcpu-op -o $@ + +$(OUTPUT)/param_test_compare_twice: param_test.c $(TEST_GEN_PROGS_EXTENDED) \ + ../rseq/rseq.h ../rseq/rseq-*.h cpu-op.h percpu-op.h + $(CC) $(CFLAGS) -DRSEQ_COMPARE_TWICE $< $(LDLIBS) -lrseq -lcpu-op -o $@ + diff --git a/tools/testing/selftests/cpu-opv/run_param_test.sh b/tools/testing/selftests/cpu-opv/run_param_test.sh new file mode 100755 index 000000000000..066d2479893c --- /dev/null +++ b/tools/testing/selftests/cpu-opv/run_param_test.sh @@ -0,0 +1,134 @@ +#!/bin/bash + +NR_CPUS=`grep '^processor' /proc/cpuinfo | wc -l` + +EXTRA_ARGS=${@} + +OLDIFS="$IFS" +IFS=$'\n' +TEST_LIST=( + "-T s" + "-T l" + "-T b" + "-T b -M" + "-T m" + "-T m -M" + "-T i" +) + +TEST_NAME=( + "spinlock" + "list" + "buffer" + "buffer with barrier" + "memcpy" + "memcpy with barrier" + "increment" +) +IFS="$OLDIFS" + +REPS=1000 +SLOW_REPS=100 +NR_THREADS=$((6*${NR_CPUS})) + +function do_tests() +{ + local i=0 + while [ "$i" -lt "${#TEST_LIST[@]}" ]; do + echo "Running test ${TEST_NAME[$i]}" + ./param_test ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1 + echo "Running skip fast-path test ${TEST_NAME[$i]}" + ./param_test_skip_fastpath ${TEST_LIST[$i]} -r ${SLOW_REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1 + echo "Running compare-twice test ${TEST_NAME[$i]}" + ./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1 + let "i++" + done +} + +echo "Default parameters" +do_tests + +echo "Loop injection: 10000 loops" + +OLDIFS="$IFS" +IFS=$'\n' +INJECT_LIST=( + "1" + "2" + "3" + "4" + "5" + "6" + "7" + "8" + "9" +) +IFS="$OLDIFS" + +NR_LOOPS=10000 + +i=0 +while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do + echo "Injecting at <${INJECT_LIST[$i]}>" + do_tests -${INJECT_LIST[i]} ${NR_LOOPS} + let "i++" +done +NR_LOOPS= + +function inject_blocking() +{ + OLDIFS="$IFS" + IFS=$'\n' + INJECT_LIST=( + "7" + "8" + "9" + ) + IFS="$OLDIFS" + + NR_LOOPS=-1 + + i=0 + while [ "$i" -lt "${#INJECT_LIST[@]}" ]; do + echo "Injecting at <${INJECT_LIST[$i]}>" + do_tests -${INJECT_LIST[i]} -1 ${@} + let "i++" + done + NR_LOOPS= +} + +echo "Yield injection (25%)" +inject_blocking -m 4 -y + +echo "Yield injection (50%)" +inject_blocking -m 2 -y + +echo "Yield injection (100%)" +inject_blocking -m 1 -y + +echo "Kill injection (25%)" +inject_blocking -m 4 -k + +echo "Kill injection (50%)" +inject_blocking -m 2 -k + +echo "Kill injection (100%)" +inject_blocking -m 1 -k + +echo "Sleep injection (1ms, 25%)" +inject_blocking -m 4 -s 1 + +echo "Sleep injection (1ms, 50%)" +inject_blocking -m 2 -s 1 + +echo "Sleep injection (1ms, 100%)" +inject_blocking -m 1 -s 1 + +echo "Disable rseq for 25% threads" +do_tests -D 4 + +echo "Disable rseq for 50% threads" +do_tests -D 2 + +echo "Disable rseq" +do_tests -d -- 2.11.0

7 years, 2 months

1
0
0 0

[RFC PATCH for 4.21 15/16] cpu-opv/selftests: Provide parametrized tests

by Mathieu Desnoyers

"param_test" is a parametrizable percpu operations test using both restartable sequences and cpu_opv. See the "--help" output for usage. "param_test_benchmark" is the same as "param_test", but it removes testing book-keeping code to allow accurate benchmarks. "param_test_compare_twice" is the same as "param_test", but it performs each comparison within rseq critical section twice, thus validating invariants. If any of the second comparisons fails, an error message is printed and the test aborts. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Joel Fernandes <joelaf(a)google.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Dave Watson <davejwatson(a)fb.com> Cc: Will Deacon <will.deacon(a)arm.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Andi Kleen <andi(a)firstfloor.org> Cc: linux-kselftest(a)vger.kernel.org Cc: "H . Peter Anvin" <hpa(a)zytor.com> Cc: Chris Lameter <cl(a)linux.com> Cc: Russell King <linux(a)arm.linux.org.uk> Cc: Michael Kerrisk <mtk.manpages(a)gmail.com> Cc: "Paul E . McKenney" <paulmck(a)linux.vnet.ibm.com> Cc: Paul Turner <pjt(a)google.com> Cc: Boqun Feng <boqun.feng(a)gmail.com> Cc: Josh Triplett <josh(a)joshtriplett.org> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Ben Maurer <bmaurer(a)fb.com> Cc: linux-api(a)vger.kernel.org Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> --- tools/testing/selftests/cpu-opv/param_test.c | 1187 ++++++++++++++++++++++++++ 1 file changed, 1187 insertions(+) create mode 100644 tools/testing/selftests/cpu-opv/param_test.c diff --git a/tools/testing/selftests/cpu-opv/param_test.c b/tools/testing/selftests/cpu-opv/param_test.c new file mode 100644 index 000000000000..c62e75f07385 --- /dev/null +++ b/tools/testing/selftests/cpu-opv/param_test.c @@ -0,0 +1,1187 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <unistd.h> +#include <poll.h> +#include <sys/types.h> +#include <signal.h> +#include <errno.h> +#include <stddef.h> + +static inline pid_t gettid(void) +{ + return syscall(__NR_gettid); +} + +#define NR_INJECT 9 +static int loop_cnt[NR_INJECT + 1]; + +static int loop_cnt_1 asm("asm_loop_cnt_1") __attribute__((used)); +static int loop_cnt_2 asm("asm_loop_cnt_2") __attribute__((used)); +static int loop_cnt_3 asm("asm_loop_cnt_3") __attribute__((used)); +static int loop_cnt_4 asm("asm_loop_cnt_4") __attribute__((used)); +static int loop_cnt_5 asm("asm_loop_cnt_5") __attribute__((used)); +static int loop_cnt_6 asm("asm_loop_cnt_6") __attribute__((used)); + +static int opt_modulo, verbose; + +static int opt_yield, opt_signal, opt_sleep, + opt_disable_rseq, opt_threads = 200, + opt_disable_mod = 0, opt_test = 's', opt_mb = 0; + +#ifndef RSEQ_SKIP_FASTPATH +static long long opt_reps = 5000; +#else +static long long opt_reps = 100; +#endif + +static __thread __attribute__((tls_model("initial-exec"))) +unsigned int signals_delivered; + +#ifndef BENCHMARK + +static __thread __attribute__((tls_model("initial-exec"), unused)) +unsigned int yield_mod_cnt, nr_abort; + +#define printf_verbose(fmt, ...) \ + do { \ + if (verbose) \ + printf(fmt, ## __VA_ARGS__); \ + } while (0) + +#ifdef __i386__ + +#define INJECT_ASM_REG "eax" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \ + "test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \ + "jz 333f\n\t" \ + "222:\n\t" \ + "dec %%" INJECT_ASM_REG "\n\t" \ + "jnz 222b\n\t" \ + "333:\n\t" + +#elif defined(__x86_64__) + +#define INJECT_ASM_REG_P "rax" +#define INJECT_ASM_REG "eax" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG_P \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \ + "mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \ + "test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \ + "jz 333f\n\t" \ + "222:\n\t" \ + "dec %%" INJECT_ASM_REG "\n\t" \ + "jnz 222b\n\t" \ + "333:\n\t" + +#elif defined(__ARMEL__) + +#define RSEQ_INJECT_INPUT \ + , [loop_cnt_1]"m"(loop_cnt[1]) \ + , [loop_cnt_2]"m"(loop_cnt[2]) \ + , [loop_cnt_3]"m"(loop_cnt[3]) \ + , [loop_cnt_4]"m"(loop_cnt[4]) \ + , [loop_cnt_5]"m"(loop_cnt[5]) \ + , [loop_cnt_6]"m"(loop_cnt[6]) + +#define INJECT_ASM_REG "r4" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "ldr " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \ + "cmp " INJECT_ASM_REG ", #0\n\t" \ + "beq 333f\n\t" \ + "222:\n\t" \ + "subs " INJECT_ASM_REG ", #1\n\t" \ + "bne 222b\n\t" \ + "333:\n\t" + +#elif __PPC__ + +#define RSEQ_INJECT_INPUT \ + , [loop_cnt_1]"m"(loop_cnt[1]) \ + , [loop_cnt_2]"m"(loop_cnt[2]) \ + , [loop_cnt_3]"m"(loop_cnt[3]) \ + , [loop_cnt_4]"m"(loop_cnt[4]) \ + , [loop_cnt_5]"m"(loop_cnt[5]) \ + , [loop_cnt_6]"m"(loop_cnt[6]) + +#define INJECT_ASM_REG "r18" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "lwz %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \ + "cmpwi %%" INJECT_ASM_REG ", 0\n\t" \ + "beq 333f\n\t" \ + "222:\n\t" \ + "subic. %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG ", 1\n\t" \ + "bne 222b\n\t" \ + "333:\n\t" +#else +#error unsupported target +#endif + +#define RSEQ_INJECT_FAILED \ + nr_abort++; + +#define RSEQ_INJECT_C(n) \ +{ \ + int loc_i, loc_nr_loops = loop_cnt[n]; \ + \ + for (loc_i = 0; loc_i < loc_nr_loops; loc_i++) { \ + rseq_barrier(); \ + } \ + if (loc_nr_loops == -1 && opt_modulo) { \ + if (yield_mod_cnt == opt_modulo - 1) { \ + if (opt_sleep > 0) \ + poll(NULL, 0, opt_sleep); \ + if (opt_yield) \ + sched_yield(); \ + if (opt_signal) \ + raise(SIGUSR1); \ + yield_mod_cnt = 0; \ + } else { \ + yield_mod_cnt++; \ + } \ + } \ +} + +#else + +#define printf_verbose(fmt, ...) + +#endif /* BENCHMARK */ + +#include "percpu-op.h" + +struct percpu_lock_entry { + intptr_t v; +} __attribute__((aligned(128))); + +struct percpu_lock { + struct percpu_lock_entry c[CPU_SETSIZE]; +}; + +struct test_data_entry { + intptr_t count; +} __attribute__((aligned(128))); + +struct spinlock_test_data { + struct percpu_lock lock; + struct test_data_entry c[CPU_SETSIZE]; +}; + +struct spinlock_thread_test_data { + struct spinlock_test_data *data; + long long reps; + int reg; +}; + +struct inc_test_data { + struct test_data_entry c[CPU_SETSIZE]; +}; + +struct inc_thread_test_data { + struct inc_test_data *data; + long long reps; + int reg; +}; + +struct percpu_list_node { + intptr_t data; + struct percpu_list_node *next; +}; + +struct percpu_list_entry { + struct percpu_list_node *head; +} __attribute__((aligned(128))); + +struct percpu_list { + struct percpu_list_entry c[CPU_SETSIZE]; +}; + +#define BUFFER_ITEM_PER_CPU 100 + +struct percpu_buffer_node { + intptr_t data; +}; + +struct percpu_buffer_entry { + intptr_t offset; + intptr_t buflen; + struct percpu_buffer_node **array; +} __attribute__((aligned(128))); + +struct percpu_buffer { + struct percpu_buffer_entry c[CPU_SETSIZE]; +}; + +#define MEMCPY_BUFFER_ITEM_PER_CPU 100 + +struct percpu_memcpy_buffer_node { + intptr_t data1; + uint64_t data2; +}; + +struct percpu_memcpy_buffer_entry { + intptr_t offset; + intptr_t buflen; + struct percpu_memcpy_buffer_node *array; +} __attribute__((aligned(128))); + +struct percpu_memcpy_buffer { + struct percpu_memcpy_buffer_entry c[CPU_SETSIZE]; +}; + +/* A simple percpu spinlock. */ +static void rseq_percpu_lock(struct percpu_lock *lock, int cpu) +{ + for (;;) { + int ret; + + ret = percpu_cmpeqv_storev(&lock->c[cpu].v, + 0, 1, cpu); + if (rseq_likely(!ret)) + break; + if (rseq_unlikely(ret < 0)) { + perror("cpu_opv"); + abort(); + } + /* Retry if comparison fails. */ + } + /* + * Acquire semantic when taking lock after control dependency. + * Matches rseq_smp_store_release(). + */ + rseq_smp_acquire__after_ctrl_dep(); +} + +static void rseq_percpu_unlock(struct percpu_lock *lock, int cpu) +{ + assert(lock->c[cpu].v == 1); + /* + * Release lock, with release semantic. Matches + * rseq_smp_acquire__after_ctrl_dep(). + */ + rseq_smp_store_release(&lock->c[cpu].v, 0); +} + +void *test_percpu_spinlock_thread(void *arg) +{ + struct spinlock_thread_test_data *thread_data = arg; + struct spinlock_test_data *data = thread_data->data; + long long i, reps; + + if (!opt_disable_rseq && thread_data->reg && + rseq_register_current_thread()) + abort(); + reps = thread_data->reps; + for (i = 0; i < reps; i++) { + int cpu = rseq_cpu_start(); + + rseq_percpu_lock(&data->lock, cpu); + data->c[cpu].count++; + rseq_percpu_unlock(&data->lock, cpu); +#ifndef BENCHMARK + if (i != 0 && !(i % (reps / 10))) + printf_verbose("tid %d: count %lld\n", (int) gettid(), i); +#endif + } + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && thread_data->reg && + rseq_unregister_current_thread()) + abort(); + return NULL; +} + +/* + * A simple test which implements a sharded counter using a per-cpu + * lock. Obviously real applications might prefer to simply use a + * per-cpu increment; however, this is reasonable for a test and the + * lock can be extended to synchronize more complicated operations. + */ +void test_percpu_spinlock(void) +{ + const int num_threads = opt_threads; + int i, ret; + uint64_t sum; + pthread_t test_threads[num_threads]; + struct spinlock_test_data data; + struct spinlock_thread_test_data thread_data[num_threads]; + + memset(&data, 0, sizeof(data)); + for (i = 0; i < num_threads; i++) { + thread_data[i].reps = opt_reps; + if (opt_disable_mod <= 0 || (i % opt_disable_mod)) + thread_data[i].reg = 1; + else + thread_data[i].reg = 0; + thread_data[i].data = &data; + ret = pthread_create(&test_threads[i], NULL, + test_percpu_spinlock_thread, + &thread_data[i]); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + sum = 0; + for (i = 0; i < CPU_SETSIZE; i++) + sum += data.c[i].count; + + assert(sum == (uint64_t)opt_reps * num_threads); +} + +void *test_percpu_inc_thread(void *arg) +{ + struct inc_thread_test_data *thread_data = arg; + struct inc_test_data *data = thread_data->data; + long long i, reps; + + if (!opt_disable_rseq && thread_data->reg && + rseq_register_current_thread()) + abort(); + reps = thread_data->reps; + for (i = 0; i < reps; i++) { + int cpu, ret; + + cpu = rseq_cpu_start(); + ret = percpu_addv(&data->c[cpu].count, 1, cpu); + if (rseq_unlikely(ret)) { + perror("cpu_opv"); + abort(); + } +#ifndef BENCHMARK + if (i != 0 && !(i % (reps / 10))) + printf_verbose("tid %d: count %lld\n", (int) gettid(), i); +#endif + } + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && thread_data->reg && + rseq_unregister_current_thread()) + abort(); + return NULL; +} + +void test_percpu_inc(void) +{ + const int num_threads = opt_threads; + int i, ret; + uint64_t sum; + pthread_t test_threads[num_threads]; + struct inc_test_data data; + struct inc_thread_test_data thread_data[num_threads]; + + memset(&data, 0, sizeof(data)); + for (i = 0; i < num_threads; i++) { + thread_data[i].reps = opt_reps; + if (opt_disable_mod <= 0 || (i % opt_disable_mod)) + thread_data[i].reg = 1; + else + thread_data[i].reg = 0; + thread_data[i].data = &data; + ret = pthread_create(&test_threads[i], NULL, + test_percpu_inc_thread, + &thread_data[i]); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + sum = 0; + for (i = 0; i < CPU_SETSIZE; i++) + sum += data.c[i].count; + + assert(sum == (uint64_t)opt_reps * num_threads); +} + +void percpu_list_push(struct percpu_list *list, + struct percpu_list_node *node, + int cpu) +{ + for (;;) { + intptr_t *targetptr, newval, expect; + int ret; + + /* Load list->c[cpu].head with single-copy atomicity. */ + expect = (intptr_t)RSEQ_READ_ONCE(list->c[cpu].head); + newval = (intptr_t)node; + targetptr = (intptr_t *)&list->c[cpu].head; + node->next = (struct percpu_list_node *)expect; + ret = percpu_cmpeqv_storev(targetptr, expect, newval, cpu); + if (rseq_likely(!ret)) + break; + if (rseq_unlikely(ret < 0)) { + perror("cpu_opv"); + abort(); + } + /* Retry if comparison fails. */ + } +} + +/* + * Unlike a traditional lock-less linked list; the availability of a + * rseq primitive allows us to implement pop without concerns over + * ABA-type races. + */ +struct percpu_list_node *percpu_list_pop(struct percpu_list *list, + int cpu) +{ + struct percpu_list_node *head; + intptr_t *targetptr, expectnot, *load; + off_t offset; + int ret; + + targetptr = (intptr_t *)&list->c[cpu].head; + expectnot = (intptr_t)NULL; + offset = offsetof(struct percpu_list_node, next); + load = (intptr_t *)&head; + ret = percpu_cmpnev_storeoffp_load(targetptr, expectnot, + offset, load, cpu); + if (rseq_unlikely(ret < 0)) { + perror("cpu_opv"); + abort(); + } + if (ret > 0) + return NULL; + return head; +} + +void *test_percpu_list_thread(void *arg) +{ + long long i, reps; + struct percpu_list *list = (struct percpu_list *)arg; + + if (!opt_disable_rseq && rseq_register_current_thread()) + abort(); + + reps = opt_reps; + for (i = 0; i < reps; i++) { + struct percpu_list_node *node; + + node = percpu_list_pop(list, rseq_cpu_start()); + if (opt_yield) + sched_yield(); /* encourage shuffling */ + if (node) + percpu_list_push(list, node, rseq_cpu_start()); + } + + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && rseq_unregister_current_thread()) + abort(); + + return NULL; +} + +/* Simultaneous modification to a per-cpu linked list from many threads. */ +void test_percpu_list(void) +{ + const int num_threads = opt_threads; + int i, j, ret; + uint64_t sum = 0, expected_sum = 0; + struct percpu_list list; + pthread_t test_threads[num_threads]; + cpu_set_t allowed_cpus; + + memset(&list, 0, sizeof(list)); + + /* Generate list entries for every usable cpu. */ + sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); + for (i = 0; i < CPU_SETSIZE; i++) { + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + for (j = 1; j <= 100; j++) { + struct percpu_list_node *node; + + expected_sum += j; + + node = malloc(sizeof(*node)); + assert(node); + node->data = j; + node->next = list.c[i].head; + list.c[i].head = node; + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_create(&test_threads[i], NULL, + test_percpu_list_thread, &list); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + for (i = 0; i < CPU_SETSIZE; i++) { + struct percpu_list_node *node; + + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + + while ((node = percpu_list_pop(&list, i))) { + sum += node->data; + free(node); + } + } + + /* + * All entries should now be accounted for (unless some external + * actor is interfering with our allowed affinity while this + * test is running). + */ + assert(sum == expected_sum); +} + +bool percpu_buffer_push(struct percpu_buffer *buffer, + struct percpu_buffer_node *node, + int cpu) +{ + for (;;) { + intptr_t *targetptr_spec, newval_spec; + intptr_t *targetptr_final, newval_final; + intptr_t offset; + int ret; + + offset = RSEQ_READ_ONCE(buffer->c[cpu].offset); + if (offset == buffer->c[cpu].buflen) + return false; + newval_spec = (intptr_t)node; + targetptr_spec = (intptr_t *)&buffer->c[cpu].array[offset]; + newval_final = offset + 1; + targetptr_final = &buffer->c[cpu].offset; + if (opt_mb) + ret = percpu_cmpeqv_storev_storev_release( + targetptr_final, offset, targetptr_spec, + newval_spec, newval_final, cpu); + else + ret = percpu_cmpeqv_storev_storev(targetptr_final, + offset, targetptr_spec, newval_spec, + newval_final, cpu); + if (rseq_likely(!ret)) + break; + if (rseq_unlikely(ret < 0)) { + perror("cpu_opv"); + abort(); + } + /* Retry if comparison fails. */ + } + return true; +} + +struct percpu_buffer_node *percpu_buffer_pop(struct percpu_buffer *buffer, + int cpu) +{ + struct percpu_buffer_node *head; + + for (;;) { + intptr_t *targetptr, newval; + intptr_t offset; + int ret; + + /* Load offset with single-copy atomicity. */ + offset = RSEQ_READ_ONCE(buffer->c[cpu].offset); + if (offset == 0) + return NULL; + head = RSEQ_READ_ONCE(buffer->c[cpu].array[offset - 1]); + newval = offset - 1; + targetptr = (intptr_t *)&buffer->c[cpu].offset; + ret = percpu_cmpeqv_cmpeqv_storev(targetptr, offset, + (intptr_t *)&buffer->c[cpu].array[offset - 1], + (intptr_t)head, newval, cpu); + if (rseq_likely(!ret)) + break; + if (rseq_unlikely(ret < 0)) { + perror("cpu_opv"); + abort(); + } + /* Retry if comparison fails. */ + } + return head; +} + +void *test_percpu_buffer_thread(void *arg) +{ + long long i, reps; + struct percpu_buffer *buffer = (struct percpu_buffer *)arg; + + if (!opt_disable_rseq && rseq_register_current_thread()) + abort(); + + reps = opt_reps; + for (i = 0; i < reps; i++) { + struct percpu_buffer_node *node; + + node = percpu_buffer_pop(buffer, rseq_cpu_start()); + if (opt_yield) + sched_yield(); /* encourage shuffling */ + if (node) { + if (!percpu_buffer_push(buffer, node, + rseq_cpu_start())) { + /* Should increase buffer size. */ + abort(); + } + } + } + + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && rseq_unregister_current_thread()) + abort(); + + return NULL; +} + +/* Simultaneous modification to a per-cpu buffer from many threads. */ +void test_percpu_buffer(void) +{ + const int num_threads = opt_threads; + int i, j, ret; + uint64_t sum = 0, expected_sum = 0; + struct percpu_buffer buffer; + pthread_t test_threads[num_threads]; + cpu_set_t allowed_cpus; + + memset(&buffer, 0, sizeof(buffer)); + + /* Generate list entries for every usable cpu. */ + sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); + for (i = 0; i < CPU_SETSIZE; i++) { + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + /* Worse-case is every item in same CPU. */ + buffer.c[i].array = + malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE * + BUFFER_ITEM_PER_CPU); + assert(buffer.c[i].array); + buffer.c[i].buflen = CPU_SETSIZE * BUFFER_ITEM_PER_CPU; + for (j = 1; j <= BUFFER_ITEM_PER_CPU; j++) { + struct percpu_buffer_node *node; + + expected_sum += j; + + /* + * We could theoretically put the word-sized + * "data" directly in the buffer. However, we + * want to model objects that would not fit + * within a single word, so allocate an object + * for each node. + */ + node = malloc(sizeof(*node)); + assert(node); + node->data = j; + buffer.c[i].array[j - 1] = node; + buffer.c[i].offset++; + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_create(&test_threads[i], NULL, + test_percpu_buffer_thread, &buffer); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + for (i = 0; i < CPU_SETSIZE; i++) { + struct percpu_buffer_node *node; + + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + + while ((node = percpu_buffer_pop(&buffer, i))) { + sum += node->data; + free(node); + } + free(buffer.c[i].array); + } + + /* + * All entries should now be accounted for (unless some external + * actor is interfering with our allowed affinity while this + * test is running). + */ + assert(sum == expected_sum); +} + +bool percpu_memcpy_buffer_push(struct percpu_memcpy_buffer *buffer, + struct percpu_memcpy_buffer_node item, int cpu) +{ + for (;;) { + intptr_t *targetptr_final, newval_final, offset; + char *destptr, *srcptr; + size_t copylen; + int ret; + + /* Load offset with single-copy atomicity. */ + offset = RSEQ_READ_ONCE(buffer->c[cpu].offset); + if (offset == buffer->c[cpu].buflen) + return false; + destptr = (char *)&buffer->c[cpu].array[offset]; + srcptr = (char *)&item; + /* copylen must be <= 4kB. */ + copylen = sizeof(item); + newval_final = offset + 1; + targetptr_final = &buffer->c[cpu].offset; + if (opt_mb) + ret = percpu_cmpeqv_memcpy_storev_release( + targetptr_final, offset, + destptr, srcptr, copylen, + newval_final, cpu); + else + ret = percpu_cmpeqv_memcpy_storev(targetptr_final, + offset, destptr, srcptr, copylen, + newval_final, cpu); + if (rseq_likely(!ret)) + break; + if (rseq_unlikely(ret < 0)) { + perror("cpu_opv"); + abort(); + } + /* Retry if comparison fails. */ + } + return true; +} + +bool percpu_memcpy_buffer_pop(struct percpu_memcpy_buffer *buffer, + struct percpu_memcpy_buffer_node *item, int cpu) +{ + for (;;) { + intptr_t *targetptr_final, newval_final, offset; + char *destptr, *srcptr; + size_t copylen; + int ret; + + /* Load offset with single-copy atomicity. */ + offset = RSEQ_READ_ONCE(buffer->c[cpu].offset); + if (offset == 0) + return false; + destptr = (char *)item; + srcptr = (char *)&buffer->c[cpu].array[offset - 1]; + /* copylen must be <= 4kB. */ + copylen = sizeof(*item); + newval_final = offset - 1; + targetptr_final = &buffer->c[cpu].offset; + ret = percpu_cmpeqv_memcpy_storev(targetptr_final, + offset, destptr, srcptr, copylen, + newval_final, cpu); + if (rseq_likely(!ret)) + break; + if (rseq_unlikely(ret < 0)) { + perror("cpu_opv"); + abort(); + } + /* Retry if comparison fails. */ + } + return true; +} + +void *test_percpu_memcpy_buffer_thread(void *arg) +{ + long long i, reps; + struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg; + + if (!opt_disable_rseq && rseq_register_current_thread()) + abort(); + + reps = opt_reps; + for (i = 0; i < reps; i++) { + struct percpu_memcpy_buffer_node item; + bool result; + + result = percpu_memcpy_buffer_pop(buffer, &item, + rseq_cpu_start()); + if (opt_yield) + sched_yield(); /* encourage shuffling */ + if (result) { + if (!percpu_memcpy_buffer_push(buffer, item, + rseq_cpu_start())) { + /* Should increase buffer size. */ + abort(); + } + } + } + + printf_verbose("tid %d: number of rseq abort: %d, signals delivered: %u\n", + (int) gettid(), nr_abort, signals_delivered); + if (!opt_disable_rseq && rseq_unregister_current_thread()) + abort(); + + return NULL; +} + +/* Simultaneous modification to a per-cpu buffer from many threads. */ +void test_percpu_memcpy_buffer(void) +{ + const int num_threads = opt_threads; + int i, j, ret; + uint64_t sum = 0, expected_sum = 0; + struct percpu_memcpy_buffer buffer; + pthread_t test_threads[num_threads]; + cpu_set_t allowed_cpus; + + memset(&buffer, 0, sizeof(buffer)); + + /* Generate list entries for every usable cpu. */ + sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); + for (i = 0; i < CPU_SETSIZE; i++) { + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + /* Worse-case is every item in same CPU. */ + buffer.c[i].array = + malloc(sizeof(*buffer.c[i].array) * CPU_SETSIZE * + MEMCPY_BUFFER_ITEM_PER_CPU); + assert(buffer.c[i].array); + buffer.c[i].buflen = CPU_SETSIZE * MEMCPY_BUFFER_ITEM_PER_CPU; + for (j = 1; j <= MEMCPY_BUFFER_ITEM_PER_CPU; j++) { + expected_sum += 2 * j + 1; + + /* + * We could theoretically put the word-sized + * "data" directly in the buffer. However, we + * want to model objects that would not fit + * within a single word, so allocate an object + * for each node. + */ + buffer.c[i].array[j - 1].data1 = j; + buffer.c[i].array[j - 1].data2 = j + 1; + buffer.c[i].offset++; + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_create(&test_threads[i], NULL, + test_percpu_memcpy_buffer_thread, + &buffer); + if (ret) { + errno = ret; + perror("pthread_create"); + abort(); + } + } + + for (i = 0; i < num_threads; i++) { + ret = pthread_join(test_threads[i], NULL); + if (ret) { + errno = ret; + perror("pthread_join"); + abort(); + } + } + + for (i = 0; i < CPU_SETSIZE; i++) { + struct percpu_memcpy_buffer_node item; + + if (!CPU_ISSET(i, &allowed_cpus)) + continue; + + while (percpu_memcpy_buffer_pop(&buffer, &item, i)) { + sum += item.data1; + sum += item.data2; + } + free(buffer.c[i].array); + } + + /* + * All entries should now be accounted for (unless some external + * actor is interfering with our allowed affinity while this + * test is running). + */ + assert(sum == expected_sum); +} + +static void test_signal_interrupt_handler(int signo) +{ + signals_delivered++; +} + +static int set_signal_handler(void) +{ + int ret = 0; + struct sigaction sa; + sigset_t sigset; + + ret = sigemptyset(&sigset); + if (ret < 0) { + perror("sigemptyset"); + return ret; + } + + sa.sa_handler = test_signal_interrupt_handler; + sa.sa_mask = sigset; + sa.sa_flags = 0; + ret = sigaction(SIGUSR1, &sa, NULL); + if (ret < 0) { + perror("sigaction"); + return ret; + } + + printf_verbose("Signal handler set for SIGUSR1\n"); + + return ret; +} + +static void show_usage(int argc, char **argv) +{ + printf("Usage : %s <OPTIONS>\n", + argv[0]); + printf("OPTIONS:\n"); + printf(" [-1 loops] Number of loops for delay injection 1\n"); + printf(" [-2 loops] Number of loops for delay injection 2\n"); + printf(" [-3 loops] Number of loops for delay injection 3\n"); + printf(" [-4 loops] Number of loops for delay injection 4\n"); + printf(" [-5 loops] Number of loops for delay injection 5\n"); + printf(" [-6 loops] Number of loops for delay injection 6\n"); + printf(" [-7 loops] Number of loops for delay injection 7 (-1 to enable -m)\n"); + printf(" [-8 loops] Number of loops for delay injection 8 (-1 to enable -m)\n"); + printf(" [-9 loops] Number of loops for delay injection 9 (-1 to enable -m)\n"); + printf(" [-m N] Yield/sleep/kill every modulo N (default 0: disabled) (>= 0)\n"); + printf(" [-y] Yield\n"); + printf(" [-k] Kill thread with signal\n"); + printf(" [-s S] S: =0: disabled (default), >0: sleep time (ms)\n"); + printf(" [-t N] Number of threads (default 200)\n"); + printf(" [-r N] Number of repetitions per thread (default 5000)\n"); + printf(" [-d] Disable rseq system call (no initialization)\n"); + printf(" [-D M] Disable rseq for each M threads\n"); + printf(" [-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement\n"); + printf(" [-M] Push into buffer and memcpy buffer with memory barriers.\n"); + printf(" [-v] Verbose output.\n"); + printf(" [-h] Show this help.\n"); + printf("\n"); +} + +int main(int argc, char **argv) +{ + int i; + + for (i = 1; i < argc; i++) { + if (argv[i][0] != '-') + continue; + switch (argv[i][1]) { + case '1': + case '2': + case '3': + case '4': + case '5': + case '6': + case '7': + case '8': + case '9': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + loop_cnt[argv[i][1] - '0'] = atol(argv[i + 1]); + i++; + break; + case 'm': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_modulo = atol(argv[i + 1]); + if (opt_modulo < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 's': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_sleep = atol(argv[i + 1]); + if (opt_sleep < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 'y': + opt_yield = 1; + break; + case 'k': + opt_signal = 1; + break; + case 'd': + opt_disable_rseq = 1; + break; + case 'D': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_disable_mod = atol(argv[i + 1]); + if (opt_disable_mod < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 't': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_threads = atol(argv[i + 1]); + if (opt_threads < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 'r': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_reps = atoll(argv[i + 1]); + if (opt_reps < 0) { + show_usage(argc, argv); + goto error; + } + i++; + break; + case 'h': + show_usage(argc, argv); + goto end; + case 'T': + if (argc < i + 2) { + show_usage(argc, argv); + goto error; + } + opt_test = *argv[i + 1]; + switch (opt_test) { + case 's': + case 'l': + case 'i': + case 'b': + case 'm': + break; + default: + show_usage(argc, argv); + goto error; + } + i++; + break; + case 'v': + verbose = 1; + break; + case 'M': + opt_mb = 1; + break; + default: + show_usage(argc, argv); + goto error; + } + } + + loop_cnt_1 = loop_cnt[1]; + loop_cnt_2 = loop_cnt[2]; + loop_cnt_3 = loop_cnt[3]; + loop_cnt_4 = loop_cnt[4]; + loop_cnt_5 = loop_cnt[5]; + loop_cnt_6 = loop_cnt[6]; + + if (set_signal_handler()) + goto error; + + if (!opt_disable_rseq && rseq_register_current_thread()) + goto error; + switch (opt_test) { + case 's': + printf_verbose("spinlock\n"); + test_percpu_spinlock(); + break; + case 'l': + printf_verbose("linked list\n"); + test_percpu_list(); + break; + case 'b': + printf_verbose("buffer\n"); + test_percpu_buffer(); + break; + case 'm': + printf_verbose("memcpy buffer\n"); + test_percpu_memcpy_buffer(); + break; + case 'i': + printf_verbose("counter increment\n"); + test_percpu_inc(); + break; + } + if (!opt_disable_rseq && rseq_unregister_current_thread()) + abort(); +end: + return 0; + +error: + return -1; +} -- 2.11.0

7 years, 2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror