diff options
Diffstat (limited to 'tools')
298 files changed, 6173 insertions, 1407 deletions
diff --git a/tools/accounting/.gitignore b/tools/accounting/.gitignore index 86485203c4ae..c45fb4ed4309 100644 --- a/tools/accounting/.gitignore +++ b/tools/accounting/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only getdelays diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index f3327cb56edf..db189945e9b0 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -217,7 +217,7 @@ #define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ #define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ @@ -285,6 +285,7 @@ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -299,6 +300,7 @@ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ #define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ @@ -367,6 +369,7 @@ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ /* diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index d5e517d1c3dd..12c9684d59ba 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -41,6 +41,10 @@ /* Intel MSRs. Some also available on other CPUs */ +#define MSR_TEST_CTRL 0x00000033 +#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29 +#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT) + #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ #define SPEC_CTRL_IBRS BIT(0) /* Indirect Branch Restricted Speculation */ #define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */ @@ -70,6 +74,11 @@ */ #define MSR_IA32_UMWAIT_CONTROL_TIME_MASK (~0x03U) +/* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */ +#define MSR_IA32_CORE_CAPS 0x000000cf +#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT 5 +#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT) + #define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) #define NHM_C1_AUTO_DEMOTE (1UL << 26) diff --git a/tools/bootconfig/.gitignore b/tools/bootconfig/.gitignore index e7644dfaa4a7..b77513cae685 100644 --- a/tools/bootconfig/.gitignore +++ b/tools/bootconfig/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only bootconfig diff --git a/tools/bootconfig/Makefile b/tools/bootconfig/Makefile index a6146ac64458..da5975775337 100644 --- a/tools/bootconfig/Makefile +++ b/tools/bootconfig/Makefile @@ -1,23 +1,30 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for bootconfig command +include ../scripts/Makefile.include bindir ?= /usr/bin -HEADER = include/linux/bootconfig.h -CFLAGS = -Wall -g -I./include +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +endif -PROGS = bootconfig +LIBSRC = $(srctree)/lib/bootconfig.c $(srctree)/include/linux/bootconfig.h +CFLAGS = -Wall -g -I$(CURDIR)/include -all: $(PROGS) +ALL_TARGETS := bootconfig +ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) -bootconfig: ../../lib/bootconfig.c main.c $(HEADER) +all: $(ALL_PROGRAMS) + +$(OUTPUT)bootconfig: main.c $(LIBSRC) $(CC) $(filter %.c,$^) $(CFLAGS) -o $@ -install: $(PROGS) - install bootconfig $(DESTDIR)$(bindir) +test: $(ALL_PROGRAMS) test-bootconfig.sh + ./test-bootconfig.sh $(OUTPUT) -test: bootconfig - ./test-bootconfig.sh +install: $(ALL_PROGRAMS) + install $(OUTPUT)bootconfig $(DESTDIR)$(bindir) clean: - $(RM) -f *.o bootconfig + $(RM) -f $(OUTPUT)*.o $(ALL_PROGRAMS) diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index a9b97814d1a9..16b9a420e6fd 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -130,6 +130,7 @@ int load_xbc_from_initrd(int fd, char **buf) int ret; u32 size = 0, csum = 0, rcsum; char magic[BOOTCONFIG_MAGIC_LEN]; + const char *msg; ret = fstat(fd, &stat); if (ret < 0) @@ -182,10 +183,12 @@ int load_xbc_from_initrd(int fd, char **buf) return -EINVAL; } - ret = xbc_init(*buf); + ret = xbc_init(*buf, &msg, NULL); /* Wrong data */ - if (ret < 0) + if (ret < 0) { + pr_err("parse error: %s.\n", msg); return ret; + } return size; } @@ -244,11 +247,34 @@ int delete_xbc(const char *path) return ret; } +static void show_xbc_error(const char *data, const char *msg, int pos) +{ + int lin = 1, col, i; + + if (pos < 0) { + pr_err("Error: %s.\n", msg); + return; + } + + /* Note that pos starts from 0 but lin and col should start from 1. */ + col = pos + 1; + for (i = 0; i < pos; i++) { + if (data[i] == '\n') { + lin++; + col = pos - i; + } + } + pr_err("Parse Error: %s at %d:%d\n", msg, lin, col); + +} + int apply_xbc(const char *path, const char *xbc_path) { u32 size, csum; char *buf, *data; int ret, fd; + const char *msg; + int pos; ret = load_xbc_file(xbc_path, &buf); if (ret < 0) { @@ -267,11 +293,12 @@ int apply_xbc(const char *path, const char *xbc_path) *(u32 *)(data + size + 4) = csum; /* Check the data format */ - ret = xbc_init(buf); + ret = xbc_init(buf, &msg, &pos); if (ret < 0) { - pr_err("Failed to parse %s: %d\n", xbc_path, ret); + show_xbc_error(data, msg, pos); free(data); free(buf); + return ret; } printf("Apply %s to %s\n", xbc_path, path); diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index 1411f4c3454f..81b350ffd03f 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -3,9 +3,16 @@ echo "Boot config test script" -BOOTCONF=./bootconfig -INITRD=`mktemp initrd-XXXX` -TEMPCONF=`mktemp temp-XXXX.bconf` +if [ -d "$1" ]; then + TESTDIR=$1 +else + TESTDIR=. +fi +BOOTCONF=${TESTDIR}/bootconfig + +INITRD=`mktemp ${TESTDIR}/initrd-XXXX` +TEMPCONF=`mktemp ${TESTDIR}/temp-XXXX.bconf` +OUTFILE=`mktemp ${TESTDIR}/tempout-XXXX` NG=0 cleanup() { @@ -65,7 +72,6 @@ new_size=$(stat -c %s $INITRD) xpass test $new_size -eq $initrd_size echo "No error messge while applying" -OUTFILE=`mktemp tempout-XXXX` dd if=/dev/zero of=$INITRD bs=4096 count=1 printf " \0\0\0 \0\0\0" >> $INITRD $BOOTCONF -a $TEMPCONF $INITRD > $OUTFILE 2>&1 diff --git a/tools/bpf/.gitignore b/tools/bpf/.gitignore index 59024197e71d..cf53342175e7 100644 --- a/tools/bpf/.gitignore +++ b/tools/bpf/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only FEATURE-DUMP.bpf feature bpf_asm diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore index 8d6e8901ed2b..26cde83e1ca3 100644 --- a/tools/bpf/bpftool/.gitignore +++ b/tools/bpf/bpftool/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only *.d /_bpftool /bpftool diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 2a7befbd11ad..0fe0d584c57e 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -591,6 +591,8 @@ int do_struct_ops(int argc, char **argv) err = cmd_select(cmds, argc, argv, do_help); - btf__free(btf_vmlinux); + if (!IS_ERR(btf_vmlinux)) + btf__free(btf_vmlinux); + return err; } diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore index 90a456a2a72f..ffdb70230c8b 100644 --- a/tools/bpf/runqslower/.gitignore +++ b/tools/bpf/runqslower/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only /.output diff --git a/tools/build/.gitignore b/tools/build/.gitignore index a776371a3502..98ae1f509592 100644 --- a/tools/build/.gitignore +++ b/tools/build/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only fixdep diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 574c2e0b9d20..3e0c019ef297 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -72,7 +72,8 @@ FEATURE_TESTS_BASIC := \ setns \ libaio \ libzstd \ - disassembler-four-args + disassembler-four-args \ + file-handle # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list # of all feature tests diff --git a/tools/build/feature/.gitignore b/tools/build/feature/.gitignore index 09b335b98842..15fcd34acdb9 100644 --- a/tools/build/feature/.gitignore +++ b/tools/build/feature/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only *.d *.bin *.output diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index ab8e89a7009c..92012381393a 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -68,7 +68,8 @@ FILES= \ test-llvm-version.bin \ test-libaio.bin \ test-libzstd.bin \ - test-clang-bpf-global-var.bin + test-clang-bpf-global-var.bin \ + test-file-handle.bin FILES := $(addprefix $(OUTPUT),$(FILES)) @@ -327,6 +328,8 @@ $(OUTPUT)test-clang-bpf-global-var.bin: $(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) | \ grep BTF_KIND_VAR +$(OUTPUT)test-file-handle.bin: + $(BUILD) ############################### diff --git a/tools/build/feature/test-file-handle.c b/tools/build/feature/test-file-handle.c new file mode 100644 index 000000000000..4d3b03b27a0b --- /dev/null +++ b/tools/build/feature/test-file-handle.c @@ -0,0 +1,17 @@ +#define _GNU_SOURCE +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <inttypes.h> + +int main(void) +{ + struct { + struct file_handle fh; + uint64_t cgroup_id; + } handle; + int mount_id; + + name_to_handle_at(AT_FDCWD, "/", &handle.fh, &mount_id, 0); + return 0; +} diff --git a/tools/cgroup/.gitignore b/tools/cgroup/.gitignore index 633cd9b874f9..46a82775f2ca 100644 --- a/tools/cgroup/.gitignore +++ b/tools/cgroup/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only cgroup_event_listener diff --git a/tools/gpio/.gitignore b/tools/gpio/.gitignore index a94c0e83b209..a00d604027a2 100644 --- a/tools/gpio/.gitignore +++ b/tools/gpio/.gitignore @@ -1,4 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only gpio-event-mon gpio-hammer +gpio-watch lsgpio include/linux/gpio.h diff --git a/tools/gpio/Build b/tools/gpio/Build index 4141f35837db..67c7b7f6a717 100644 --- a/tools/gpio/Build +++ b/tools/gpio/Build @@ -2,3 +2,4 @@ gpio-utils-y += gpio-utils.o lsgpio-y += lsgpio.o gpio-utils.o gpio-hammer-y += gpio-hammer.o gpio-utils.o gpio-event-mon-y += gpio-event-mon.o gpio-utils.o +gpio-watch-y += gpio-watch.o diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index 6080de58861f..440434027557 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -18,7 +18,7 @@ MAKEFLAGS += -r override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include -ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon +ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon gpio-watch ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) all: $(ALL_PROGRAMS) @@ -35,7 +35,7 @@ $(OUTPUT)include/linux/gpio.h: ../../include/uapi/linux/gpio.h prepare: $(OUTPUT)include/linux/gpio.h -GPIO_UTILS_IN := $(output)gpio-utils-in.o +GPIO_UTILS_IN := $(OUTPUT)gpio-utils-in.o $(GPIO_UTILS_IN): prepare FORCE $(Q)$(MAKE) $(build)=gpio-utils @@ -66,6 +66,15 @@ $(GPIO_EVENT_MON_IN): prepare FORCE $(OUTPUT)gpio-utils-in.o $(OUTPUT)gpio-event-mon: $(GPIO_EVENT_MON_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ +# +# gpio-watch +# +GPIO_WATCH_IN := $(OUTPUT)gpio-watch-in.o +$(GPIO_WATCH_IN): prepare FORCE + $(Q)$(MAKE) $(build)=gpio-watch +$(OUTPUT)gpio-watch: $(GPIO_WATCH_IN) + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ + clean: rm -f $(ALL_PROGRAMS) rm -f $(OUTPUT)include/linux/gpio.h diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c index 0e0060a6eb34..9fd926e8cb52 100644 --- a/tools/gpio/gpio-hammer.c +++ b/tools/gpio/gpio-hammer.c @@ -77,7 +77,7 @@ int hammer_device(const char *device_name, unsigned int *lines, int nlines, fprintf(stdout, "[%c] ", swirr[j]); j++; - if (j == sizeof(swirr)-1) + if (j == sizeof(swirr) - 1) j = 0; fprintf(stdout, "["); @@ -135,7 +135,14 @@ int main(int argc, char **argv) device_name = optarg; break; case 'o': - lines[i] = strtoul(optarg, NULL, 10); + /* + * Avoid overflow. Do not immediately error, we want to + * be able to accurately report on the amount of times + * '-o' was given to give an accurate error message + */ + if (i < GPIOHANDLES_MAX) + lines[i] = strtoul(optarg, NULL, 10); + i++; break; case '?': @@ -143,6 +150,14 @@ int main(int argc, char **argv) return -1; } } + + if (i >= GPIOHANDLES_MAX) { + fprintf(stderr, + "Only %d occurrences of '-o' are allowed, %d were found\n", + GPIOHANDLES_MAX, i + 1); + return -1; + } + nlines = i; if (!device_name || !nlines) { diff --git a/tools/gpio/gpio-utils.c b/tools/gpio/gpio-utils.c index 53470de6a502..06003789e7c7 100644 --- a/tools/gpio/gpio-utils.c +++ b/tools/gpio/gpio-utils.c @@ -17,7 +17,7 @@ #include <linux/gpio.h> #include "gpio-utils.h" -#define COMSUMER "gpio-utils" +#define CONSUMER "gpio-utils" /** * doc: Operation of gpio @@ -209,7 +209,7 @@ int gpiotools_gets(const char *device_name, unsigned int *lines, ret = gpiotools_request_linehandle(device_name, lines, nlines, GPIOHANDLE_REQUEST_INPUT, data, - COMSUMER); + CONSUMER); if (ret < 0) return ret; @@ -259,7 +259,7 @@ int gpiotools_sets(const char *device_name, unsigned int *lines, ret = gpiotools_request_linehandle(device_name, lines, nlines, GPIOHANDLE_REQUEST_OUTPUT, data, - COMSUMER); + CONSUMER); if (ret < 0) return ret; diff --git a/tools/gpio/gpio-watch.c b/tools/gpio/gpio-watch.c new file mode 100644 index 000000000000..5cea24fddfa7 --- /dev/null +++ b/tools/gpio/gpio-watch.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * gpio-watch - monitor unrequested lines for property changes using the + * character device + * + * Copyright (C) 2019 BayLibre SAS + * Author: Bartosz Golaszewski <bgolaszewski@baylibre.com> + */ + +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/gpio.h> +#include <poll.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <unistd.h> + +int main(int argc, char **argv) +{ + struct gpioline_info_changed chg; + struct gpioline_info req; + struct pollfd pfd; + int fd, i, j, ret; + char *event, *end; + ssize_t rd; + + if (argc < 3) + goto err_usage; + + fd = open(argv[1], O_RDWR | O_CLOEXEC); + if (fd < 0) { + perror("unable to open gpiochip"); + return EXIT_FAILURE; + } + + for (i = 0, j = 2; i < argc - 2; i++, j++) { + memset(&req, 0, sizeof(req)); + + req.line_offset = strtoul(argv[j], &end, 0); + if (*end != '\0') + goto err_usage; + + ret = ioctl(fd, GPIO_GET_LINEINFO_WATCH_IOCTL, &req); + if (ret) { + perror("unable to set up line watch"); + return EXIT_FAILURE; + } + } + + pfd.fd = fd; + pfd.events = POLLIN | POLLPRI; + + for (;;) { + ret = poll(&pfd, 1, 5000); + if (ret < 0) { + perror("error polling the linechanged fd"); + return EXIT_FAILURE; + } else if (ret > 0) { + memset(&chg, 0, sizeof(chg)); + rd = read(pfd.fd, &chg, sizeof(chg)); + if (rd < 0 || rd != sizeof(chg)) { + if (rd != sizeof(chg)) + errno = EIO; + + perror("error reading line change event"); + return EXIT_FAILURE; + } + + switch (chg.event_type) { + case GPIOLINE_CHANGED_REQUESTED: + event = "requested"; + break; + case GPIOLINE_CHANGED_RELEASED: + event = "released"; + break; + case GPIOLINE_CHANGED_CONFIG: + event = "config changed"; + break; + default: + fprintf(stderr, + "invalid event type received from the kernel\n"); + return EXIT_FAILURE; + } + + printf("line %u: %s at %llu\n", + chg.info.line_offset, event, chg.timestamp); + } + } + + return 0; + +err_usage: + printf("%s: <gpiochip> <line0> <line1> ...\n", argv[0]); + return EXIT_FAILURE; +} diff --git a/tools/iio/.gitignore b/tools/iio/.gitignore index 3758202618bd..5bd6f4df98b7 100644 --- a/tools/iio/.gitignore +++ b/tools/iio/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only iio_event_monitor iio_generic_buffer lsiio diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 669d69441a62..4671fbf28842 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -3,9 +3,9 @@ #define __LINUX_BITS_H #include <linux/const.h> +#include <vdso/bits.h> #include <asm/bitsperlong.h> -#define BIT(nr) (UL(1) << (nr)) #define BIT_ULL(nr) (ULL(1) << (nr)) #define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / BITS_PER_LONG) @@ -18,12 +18,30 @@ * position @h. For example * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ -#define GENMASK(h, l) \ +#if !defined(__ASSEMBLY__) && \ + (!defined(CONFIG_CC_IS_GCC) || CONFIG_GCC_VERSION >= 49000) +#include <linux/build_bug.h> +#define GENMASK_INPUT_CHECK(h, l) \ + (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ + __builtin_constant_p((l) > (h)), (l) > (h), 0))) +#else +/* + * BUILD_BUG_ON_ZERO is not available in h files included from asm files, + * disable the input check if that is the case. + */ +#define GENMASK_INPUT_CHECK(h, l) 0 +#endif + +#define __GENMASK(h, l) \ (((~UL(0)) - (UL(1) << (l)) + 1) & \ (~UL(0) >> (BITS_PER_LONG - 1 - (h)))) +#define GENMASK(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l)) -#define GENMASK_ULL(h, l) \ +#define __GENMASK_ULL(h, l) \ (((~ULL(0)) - (ULL(1) << (l)) + 1) & \ (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) +#define GENMASK_ULL(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) #endif /* __LINUX_BITS_H */ diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h new file mode 100644 index 000000000000..cc7070c7439b --- /dev/null +++ b/tools/include/linux/build_bug.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#include <linux/compiler.h> + +#ifdef __CHECKER__ +#define BUILD_BUG_ON_ZERO(e) (0) +#else /* __CHECKER__ */ +/* + * Force a compilation error if condition is true, but also produce a + * result (of value 0 and type int), so the expression can be used + * e.g. in a structure initializer (or where-ever else comma expressions + * aren't permitted). + */ +#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); }))) +#endif /* __CHECKER__ */ + +/* Force a compilation error if a constant expression is not a power of 2 */ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON(((n) & ((n) - 1)) != 0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) + +/* + * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the + * expression but avoids the generation of any code, even if that expression + * has side-effects. + */ +#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) + +/** + * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied + * error message. + * @condition: the condition which the compiler should know is false. + * + * See BUILD_BUG_ON for description. + */ +#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) + +/** + * BUILD_BUG_ON - break compile if a condition is true. + * @condition: the condition which the compiler should know is false. + * + * If you have some code which relies on certain constants being equal, or + * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to + * detect if someone changes it. + */ +#define BUILD_BUG_ON(condition) \ + BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) + +/** + * BUILD_BUG - break compile if used. + * + * If you have some code that you expect the compiler to eliminate at + * build time, you should use BUILD_BUG to detect if it is + * unexpectedly used. + */ +#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") + +/** + * static_assert - check integer constant expression at build time + * + * static_assert() is a wrapper for the C11 _Static_assert, with a + * little macro magic to make the message optional (defaulting to the + * stringification of the tested expression). + * + * Contrary to BUILD_BUG_ON(), static_assert() can be used at global + * scope, but requires the expression to be an integer constant + * expression (i.e., it is not enough that __builtin_constant_p() is + * true for expr). + * + * Also note that BUILD_BUG_ON() fails the build if the condition is + * true, while static_assert() fails the build if the expression is + * false. + */ +#ifndef static_assert +#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr) +#define __static_assert(expr, msg, ...) _Static_assert(expr, msg) +#endif // static_assert + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 1827c2f973f9..180f7714a5f1 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -10,6 +10,32 @@ # define __compiletime_error(message) #endif +#ifdef __OPTIMIZE__ +# define __compiletime_assert(condition, msg, prefix, suffix) \ + do { \ + extern void prefix ## suffix(void) __compiletime_error(msg); \ + if (!(condition)) \ + prefix ## suffix(); \ + } while (0) +#else +# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) +#endif + +#define _compiletime_assert(condition, msg, prefix, suffix) \ + __compiletime_assert(condition, msg, prefix, suffix) + +/** + * compiletime_assert - break build and emit msg if condition is false + * @condition: a compile-time constant condition to check + * @msg: a message to emit if condition is false + * + * In tradition of POSIX assert, this macro will break the build if the + * supplied condition is *false*, emitting the supplied error message if the + * compiler has support to do so. + */ +#define compiletime_assert(condition, msg) \ + _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) + /* Optimization barrier */ /* The "volatile" is due to gcc bugs */ #define barrier() __asm__ __volatile__("": : :"memory") diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h index 7b55a55f5911..81b8aae5a855 100644 --- a/tools/include/linux/const.h +++ b/tools/include/linux/const.h @@ -1,9 +1,6 @@ #ifndef _LINUX_CONST_H #define _LINUX_CONST_H -#include <uapi/linux/const.h> - -#define UL(x) (_UL(x)) -#define ULL(x) (_ULL(x)) +#include <vdso/const.h> #endif /* _LINUX_CONST_H */ diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index cba226948a0c..a7e54a08fb54 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -5,6 +5,7 @@ #include <stdarg.h> #include <stddef.h> #include <assert.h> +#include <linux/build_bug.h> #include <linux/compiler.h> #include <endian.h> #include <byteswap.h> @@ -35,9 +36,6 @@ (type *)((char *)__mptr - offsetof(type, member)); }) #endif -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) - #ifndef max #define max(x, y) ({ \ typeof(x) _max1 = (x); \ diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 868bf7996c0f..808b48a93330 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -948,6 +948,8 @@ extern "C" { #define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) + /** * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 829c0a48577f..2813e579b480 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -1619,6 +1619,27 @@ struct drm_i915_gem_context_param { * By default, new contexts allow persistence. */ #define I915_CONTEXT_PARAM_PERSISTENCE 0xb + +/* + * I915_CONTEXT_PARAM_RINGSIZE: + * + * Sets the size of the CS ringbuffer to use for logical ring contexts. This + * applies a limit of how many batches can be queued to HW before the caller + * is blocked due to lack of space for more commands. + * + * Only reliably possible to be set prior to first use, i.e. during + * construction. At any later point, the current execution must be flushed as + * the ring can only be changed while the context is idle. Note, the ringsize + * can be specified as a constructor property, see + * I915_CONTEXT_CREATE_EXT_SETPARAM, but can also be set later if required. + * + * Only applies to the current set of engine and lost when those engines + * are replaced by a new mapping (see I915_CONTEXT_PARAM_ENGINES). + * + * Must be between 4 - 512 KiB, in intervals of page size [4 KiB]. + * Default is 16 KiB. + */ +#define I915_CONTEXT_PARAM_RINGSIZE 0xc /* Must be kept compact -- no holes and well documented */ __u64 value; diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 0d8a6f47711c..a10e3cdc2839 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -163,6 +163,7 @@ struct fscrypt_get_key_status_arg { #define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg) #define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS _IOWR('f', 25, struct fscrypt_remove_key_arg) #define FS_IOC_GET_ENCRYPTION_KEY_STATUS _IOWR('f', 26, struct fscrypt_get_key_status_arg) +#define FS_IOC_GET_ENCRYPTION_NONCE _IOR('f', 27, __u8[16]) /**********************************************************************/ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4b95f9a31a2f..428c7dde6b4b 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -474,12 +474,17 @@ struct kvm_s390_mem_op { __u32 size; /* amount of bytes */ __u32 op; /* type of operation */ __u64 buf; /* buffer in userspace */ - __u8 ar; /* the access register number */ - __u8 reserved[31]; /* should be set to 0 */ + union { + __u8 ar; /* the access register number */ + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* should be set to 0 */ + }; }; /* types for kvm_s390_mem_op->op */ #define KVM_S390_MEMOP_LOGICAL_READ 0 #define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) @@ -1010,6 +1015,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ARM_NISV_TO_USER 177 #define KVM_CAP_ARM_INJECT_EXT_DABT 178 #define KVM_CAP_S390_VCPU_RESETS 179 +#define KVM_CAP_S390_PROTECTED 180 +#define KVM_CAP_PPC_SECURE_GUEST 181 #ifdef KVM_CAP_IRQ_ROUTING @@ -1478,6 +1485,39 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +/* Available with KVM_CAP_S390_PROTECTED */ +#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ @@ -1628,4 +1668,7 @@ struct kvm_hyperv_eventfd { #define KVM_HYPERV_CONN_ID_MASK 0x00ffffff #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) +#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) +#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) + #endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index fc1a64c3447b..923cc162609c 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -5,8 +5,9 @@ #include <asm/mman.h> #include <asm-generic/hugetlb_encode.h> -#define MREMAP_MAYMOVE 1 -#define MREMAP_FIXED 2 +#define MREMAP_MAYMOVE 1 +#define MREMAP_FIXED 2 +#define MREMAP_DONTUNMAP 4 #define OVERCOMMIT_GUESS 0 #define OVERCOMMIT_ALWAYS 1 diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 397cfd65b3fe..7b2d6fc9e6ed 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -142,8 +142,9 @@ enum perf_event_sample_format { PERF_SAMPLE_REGS_INTR = 1U << 18, PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_AUX = 1U << 20, + PERF_SAMPLE_CGROUP = 1U << 21, - PERF_SAMPLE_MAX = 1U << 21, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 22, /* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; @@ -381,7 +382,8 @@ struct perf_event_attr { ksymbol : 1, /* include ksymbol events */ bpf_event : 1, /* include bpf events */ aux_output : 1, /* generate AUX records instead of events */ - __reserved_1 : 32; + cgroup : 1, /* include cgroup events */ + __reserved_1 : 31; union { __u32 wakeup_events; /* wakeup every n events */ @@ -1012,6 +1014,16 @@ enum perf_event_type { */ PERF_RECORD_BPF_EVENT = 18, + /* + * struct { + * struct perf_event_header header; + * u64 id; + * char path[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_CGROUP = 19, + PERF_RECORD_MAX, /* non-ABI */ }; diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 2e3bc22c6f20..3bac0a8ceab2 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -35,6 +35,7 @@ /* Flags for the clone3() syscall. */ #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */ +#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */ /* * cloning flags intersect with CSIGNAL so can be used with unshare and clone3 @@ -81,6 +82,8 @@ * @set_tid_size: This defines the size of the array referenced * in @set_tid. This cannot be larger than the * kernel's limit of nested PID namespaces. + * @cgroup: If CLONE_INTO_CGROUP is specified set this to + * a file descriptor for the cgroup. * * The structure is versioned by size and thus extensible. * New struct members must go at the end of the struct and @@ -97,11 +100,13 @@ struct clone_args { __aligned_u64 tls; __aligned_u64 set_tid; __aligned_u64 set_tid_size; + __aligned_u64 cgroup; }; #endif #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */ #define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */ +#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */ /* * Scheduling policies diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index 40d028eed645..9fe72e4b1373 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -116,4 +116,28 @@ #define VHOST_VSOCK_SET_GUEST_CID _IOW(VHOST_VIRTIO, 0x60, __u64) #define VHOST_VSOCK_SET_RUNNING _IOW(VHOST_VIRTIO, 0x61, int) +/* VHOST_VDPA specific defines */ + +/* Get the device id. The device ids follow the same definition of + * the device id defined in virtio-spec. + */ +#define VHOST_VDPA_GET_DEVICE_ID _IOR(VHOST_VIRTIO, 0x70, __u32) +/* Get and set the status. The status bits follow the same definition + * of the device status defined in virtio-spec. + */ +#define VHOST_VDPA_GET_STATUS _IOR(VHOST_VIRTIO, 0x71, __u8) +#define VHOST_VDPA_SET_STATUS _IOW(VHOST_VIRTIO, 0x72, __u8) +/* Get and set the device config. The device config follows the same + * definition of the device config defined in virtio-spec. + */ +#define VHOST_VDPA_GET_CONFIG _IOR(VHOST_VIRTIO, 0x73, \ + struct vhost_vdpa_config) +#define VHOST_VDPA_SET_CONFIG _IOW(VHOST_VIRTIO, 0x74, \ + struct vhost_vdpa_config) +/* Enable/disable the ring. */ +#define VHOST_VDPA_SET_VRING_ENABLE _IOW(VHOST_VIRTIO, 0x75, \ + struct vhost_vring_state) +/* Get the max ring size. */ +#define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16) + #endif diff --git a/tools/include/vdso/bits.h b/tools/include/vdso/bits.h new file mode 100644 index 000000000000..6d005a1f5d94 --- /dev/null +++ b/tools/include/vdso/bits.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_BITS_H +#define __VDSO_BITS_H + +#include <vdso/const.h> + +#define BIT(nr) (UL(1) << (nr)) + +#endif /* __VDSO_BITS_H */ diff --git a/tools/include/vdso/const.h b/tools/include/vdso/const.h new file mode 100644 index 000000000000..94b385ad438d --- /dev/null +++ b/tools/include/vdso/const.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_CONST_H +#define __VDSO_CONST_H + +#include <uapi/linux/const.h> + +#define UL(x) (_UL(x)) +#define ULL(x) (_ULL(x)) + +#endif /* __VDSO_CONST_H */ diff --git a/tools/laptop/dslm/.gitignore b/tools/laptop/dslm/.gitignore index 9fc984e64386..f7f1296b96ae 100644 --- a/tools/laptop/dslm/.gitignore +++ b/tools/laptop/dslm/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only dslm diff --git a/tools/laptop/freefall/freefall.c b/tools/laptop/freefall/freefall.c index d29a86cda87f..d77d7861787c 100644 --- a/tools/laptop/freefall/freefall.c +++ b/tools/laptop/freefall/freefall.c @@ -4,7 +4,7 @@ * Copyright 2008 Eric Piel * Copyright 2009 Pavel Machek <pavel@ucw.cz> * Copyright 2012 Sonal Santan - * Copyright 2014 Pali Rohár <pali.rohar@gmail.com> + * Copyright 2014 Pali Rohár <pali@kernel.org> */ #include <stdio.h> diff --git a/tools/leds/.gitignore b/tools/leds/.gitignore index ac96d9f53dfc..06bd3ee1b7c9 100644 --- a/tools/leds/.gitignore +++ b/tools/leds/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only uledmon diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index e97c2ebcf447..8a81b3679d2b 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only libbpf_version.h libbpf.pc FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ff9174282a8c..8f480e29a6b0 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -178,6 +178,8 @@ struct bpf_capabilities { __u32 array_mmap:1; /* BTF_FUNC_GLOBAL is supported */ __u32 btf_func_global:1; + /* kernel support for expected_attach_type in BPF_PROG_LOAD */ + __u32 exp_attach_type:1; }; enum reloc_type { @@ -194,6 +196,22 @@ struct reloc_desc { int sym_off; }; +struct bpf_sec_def; + +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, + struct bpf_program *prog); + +struct bpf_sec_def { + const char *sec; + size_t len; + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + bool is_exp_attach_type_optional; + bool is_attachable; + bool is_attach_btf; + attach_fn_t attach_fn; +}; + /* * bpf_prog should be a better name but it has been used in * linux/filter.h. @@ -204,6 +222,7 @@ struct bpf_program { char *name; int prog_ifindex; char *section_name; + const struct bpf_sec_def *sec_def; /* section_name with / replaced by _; makes recursive pinning * in bpf_object__pin_programs easier */ @@ -3316,6 +3335,37 @@ static int bpf_object__probe_array_mmap(struct bpf_object *obj) } static int +bpf_object__probe_exp_attach_type(struct bpf_object *obj) +{ + struct bpf_load_program_attr attr; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int fd; + + memset(&attr, 0, sizeof(attr)); + /* use any valid combination of program type and (optional) + * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) + * to see if kernel supports expected_attach_type field for + * BPF_PROG_LOAD command + */ + attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK; + attr.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; + attr.insns = insns; + attr.insns_cnt = ARRAY_SIZE(insns); + attr.license = "GPL"; + + fd = bpf_load_program_xattr(&attr, NULL, 0); + if (fd >= 0) { + obj->caps.exp_attach_type = 1; + close(fd); + return 1; + } + return 0; +} + +static int bpf_object__probe_caps(struct bpf_object *obj) { int (*probe_fn[])(struct bpf_object *obj) = { @@ -3325,6 +3375,7 @@ bpf_object__probe_caps(struct bpf_object *obj) bpf_object__probe_btf_func_global, bpf_object__probe_btf_datasec, bpf_object__probe_array_mmap, + bpf_object__probe_exp_attach_type, }; int i, ret; @@ -4861,7 +4912,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = prog->type; - load_attr.expected_attach_type = prog->expected_attach_type; + /* old kernels might not support specifying expected_attach_type */ + if (!prog->caps->exp_attach_type && prog->sec_def && + prog->sec_def->is_exp_attach_type_optional) + load_attr.expected_attach_type = 0; + else + load_attr.expected_attach_type = prog->expected_attach_type; if (prog->caps->name) load_attr.name = prog->name; load_attr.insns = insns; @@ -5062,6 +5118,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) return 0; } +static const struct bpf_sec_def *find_sec_def(const char *sec_name); + static struct bpf_object * __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) @@ -5117,24 +5175,17 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, bpf_object__elf_finish(obj); bpf_object__for_each_program(prog, obj) { - enum bpf_prog_type prog_type; - enum bpf_attach_type attach_type; - - if (prog->type != BPF_PROG_TYPE_UNSPEC) - continue; - - err = libbpf_prog_type_by_name(prog->section_name, &prog_type, - &attach_type); - if (err == -ESRCH) + prog->sec_def = find_sec_def(prog->section_name); + if (!prog->sec_def) /* couldn't guess, but user might manually specify */ continue; - if (err) - goto out; - bpf_program__set_type(prog, prog_type); - bpf_program__set_expected_attach_type(prog, attach_type); - if (prog_type == BPF_PROG_TYPE_TRACING || - prog_type == BPF_PROG_TYPE_EXT) + bpf_program__set_type(prog, prog->sec_def->prog_type); + bpf_program__set_expected_attach_type(prog, + prog->sec_def->expected_attach_type); + + if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || + prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); } @@ -6223,23 +6274,32 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, btf, atype) \ - { string, sizeof(string) - 1, ptype, eatype, is_attachable, btf, atype } +#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional, \ + attachable, attach_btf) \ + { \ + .sec = string, \ + .len = sizeof(string) - 1, \ + .prog_type = ptype, \ + .expected_attach_type = eatype, \ + .is_exp_attach_type_optional = eatype_optional, \ + .is_attachable = attachable, \ + .is_attach_btf = attach_btf, \ + } /* Programs that can NOT be attached. */ #define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) /* Programs that can be attached. */ #define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, 0, 1, 0, atype) + BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0) /* Programs that must specify expected attach type at load time. */ #define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, 0, eatype) + BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0) /* Programs that use BTF to identify attach point */ #define BPF_PROG_BTF(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, 0, 1, 0) + BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1) /* Programs that can be attached but attach type can't be identified by section * name. Kept for backward compatibility. @@ -6253,11 +6313,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, __VA_ARGS__ \ } -struct bpf_sec_def; - -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, - struct bpf_program *prog); - static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, struct bpf_program *prog); static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, @@ -6269,17 +6324,6 @@ static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, struct bpf_program *prog); -struct bpf_sec_def { - const char *sec; - size_t len; - enum bpf_prog_type prog_type; - enum bpf_attach_type expected_attach_type; - bool is_attachable; - bool is_attach_btf; - enum bpf_attach_type attach_type; - attach_fn_t attach_fn; -}; - static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), BPF_PROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT), @@ -6713,7 +6757,7 @@ int libbpf_attach_type_by_name(const char *name, continue; if (!section_defs[i].is_attachable) return -EINVAL; - *attach_type = section_defs[i].attach_type; + *attach_type = section_defs[i].expected_attach_type; return 0; } pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); @@ -7542,7 +7586,6 @@ static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, struct bpf_link * bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) { - const struct bpf_sec_def *sec_def; enum bpf_attach_type attach_type; char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -7561,11 +7604,6 @@ bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) link->detach = &bpf_link__detach_fd; attach_type = bpf_program__get_expected_attach_type(prog); - if (!attach_type) { - sec_def = find_sec_def(bpf_program__title(prog, false)); - if (sec_def) - attach_type = sec_def->attach_type; - } link_fd = bpf_link_create(prog_fd, cgroup_fd, attach_type, NULL); if (link_fd < 0) { link_fd = -errno; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 44df1d3e7287..f1dacecb1619 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -458,7 +458,7 @@ struct xdp_link_info { struct bpf_xdp_set_link_opts { size_t sz; - __u32 old_fd; + int old_fd; }; #define bpf_xdp_set_link_opts__last_field old_fd diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 18b5319025e1..0b709fd10bba 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -142,7 +142,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, struct ifinfomsg ifinfo; char attrbuf[64]; } req; - __u32 nl_pid; + __u32 nl_pid = 0; sock = libbpf_netlink_open(&nl_pid); if (sock < 0) @@ -288,7 +288,7 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, { struct xdp_id_md xdp_id = {}; int sock, ret; - __u32 nl_pid; + __u32 nl_pid = 0; __u32 mask; if (flags & ~XDP_FLAGS_MASK || !info_size) @@ -321,7 +321,7 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) { - if (info->attach_mode != XDP_ATTACHED_MULTI) + if (info->attach_mode != XDP_ATTACHED_MULTI && !flags) return info->prog_id; if (flags & XDP_FLAGS_DRV_MODE) return info->drv_prog_id; diff --git a/tools/lib/lockdep/.gitignore b/tools/lib/lockdep/.gitignore index cc0e7a9f99e3..6c308ac4388c 100644 --- a/tools/lib/lockdep/.gitignore +++ b/tools/lib/lockdep/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only liblockdep.so.* diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 18106899cb4e..69b44d2cc0f5 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -105,6 +105,12 @@ struct perf_record_bpf_event { __u8 tag[BPF_TAG_SIZE]; // prog tag }; +struct perf_record_cgroup { + struct perf_event_header header; + __u64 id; + char path[PATH_MAX]; +}; + struct perf_record_sample { struct perf_event_header header; __u64 array[]; @@ -352,6 +358,7 @@ union perf_event { struct perf_record_mmap2 mmap2; struct perf_record_comm comm; struct perf_record_namespaces namespaces; + struct perf_record_cgroup cgroup; struct perf_record_fork fork; struct perf_record_lost lost; struct perf_record_lost_samples lost_samples; diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c index 2548ff8c4d9c..06ac7bd2144b 100644 --- a/tools/lib/rbtree.c +++ b/tools/lib/rbtree.c @@ -497,7 +497,7 @@ struct rb_node *rb_next(const struct rb_node *node) if (node->rb_right) { node = node->rb_right; while (node->rb_left) - node=node->rb_left; + node = node->rb_left; return (struct rb_node *)node; } @@ -528,7 +528,7 @@ struct rb_node *rb_prev(const struct rb_node *node) if (node->rb_left) { node = node->rb_left; while (node->rb_right) - node=node->rb_right; + node = node->rb_right; return (struct rb_node *)node; } diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore index 9e9f25fb1922..7123c70b9ebc 100644 --- a/tools/lib/traceevent/.gitignore +++ b/tools/lib/traceevent/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only TRACEEVENT-CFLAGS libtraceevent-dynamic-list libtraceevent.so.* diff --git a/tools/memory-model/.gitignore b/tools/memory-model/.gitignore index b1d34c52f3c3..cf4cd66d8fbf 100644 --- a/tools/memory-model/.gitignore +++ b/tools/memory-model/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only litmus diff --git a/tools/memory-model/litmus-tests/.gitignore b/tools/memory-model/litmus-tests/.gitignore index 6e2ddc54152f..c492a1ddad91 100644 --- a/tools/memory-model/litmus-tests/.gitignore +++ b/tools/memory-model/litmus-tests/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only *.litmus.out diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore index 914cff12899b..45cefda24c7b 100644 --- a/tools/objtool/.gitignore +++ b/tools/objtool/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only arch/x86/lib/inat-tables.c objtool fixdep diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index ee08aeff30a1..f591c4d1b6fe 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -3,9 +3,15 @@ include ../scripts/Makefile.include include ../scripts/Makefile.arch # always use the host compiler +ifneq ($(LLVM),) +HOSTAR ?= llvm-ar +HOSTCC ?= clang +HOSTLD ?= ld.lld +else HOSTAR ?= ar HOSTCC ?= gcc HOSTLD ?= ld +endif AR = $(HOSTAR) CC = $(HOSTCC) LD = $(HOSTLD) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 8dd01f986fbb..4b170fd08a28 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1050,10 +1050,7 @@ static struct rela *find_jump_table(struct objtool_file *file, * it. */ for (; - &insn->list != &file->insn_list && - insn->sec == func->sec && - insn->offset >= func->offset; - + &insn->list != &file->insn_list && insn->func && insn->func->pfunc == func; insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC) @@ -2008,8 +2005,8 @@ static int validate_return(struct symbol *func, struct instruction *insn, struct } if (state->bp_scratch) { - WARN("%s uses BP as a scratch register", - func->name); + WARN_FUNC("BP used as a scratch register", + insn->sec, insn->offset); return 1; } @@ -2364,14 +2361,27 @@ static bool ignore_unreachable_insn(struct instruction *insn) !strcmp(insn->sec->name, ".altinstr_aux")) return true; + if (!insn->func) + return false; + + /* + * CONFIG_UBSAN_TRAP inserts a UD2 when it sees + * __builtin_unreachable(). The BUG() macro has an unreachable() after + * the UD2, which causes GCC's undefined trap logic to emit another UD2 + * (or occasionally a JMP to UD2). + */ + if (list_prev_entry(insn, list)->dead_end && + (insn->type == INSN_BUG || + (insn->type == INSN_JUMP_UNCONDITIONAL && + insn->jump_dest && insn->jump_dest->type == INSN_BUG))) + return true; + /* * Check if this (or a subsequent) instruction is related to * CONFIG_UBSAN or CONFIG_KASAN. * * End the search at 5 instructions to avoid going into the weeds. */ - if (!insn->func) - return false; for (i = 0; i < 5; i++) { if (is_kasan_insn(insn) || is_ubsan_insn(insn)) diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 13ccf775a83a..ba4cbb1cdd63 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -66,7 +66,7 @@ int orc_dump(const char *_objname) char *name; size_t nr_sections; Elf64_Addr orc_ip_addr = 0; - size_t shstrtab_idx; + size_t shstrtab_idx, strtab_idx = 0; Elf *elf; Elf_Scn *scn; GElf_Shdr sh; @@ -127,6 +127,8 @@ int orc_dump(const char *_objname) if (!strcmp(name, ".symtab")) { symtab = data; + } else if (!strcmp(name, ".strtab")) { + strtab_idx = i; } else if (!strcmp(name, ".orc_unwind")) { orc = data->d_buf; orc_size = sh.sh_size; @@ -138,7 +140,7 @@ int orc_dump(const char *_objname) } } - if (!symtab || !orc || !orc_ip) + if (!symtab || !strtab_idx || !orc || !orc_ip) return 0; if (orc_size % sizeof(*orc) != 0) { @@ -159,21 +161,29 @@ int orc_dump(const char *_objname) return -1; } - scn = elf_getscn(elf, sym.st_shndx); - if (!scn) { - WARN_ELF("elf_getscn"); - return -1; - } - - if (!gelf_getshdr(scn, &sh)) { - WARN_ELF("gelf_getshdr"); - return -1; - } - - name = elf_strptr(elf, shstrtab_idx, sh.sh_name); - if (!name || !*name) { - WARN_ELF("elf_strptr"); - return -1; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) { + scn = elf_getscn(elf, sym.st_shndx); + if (!scn) { + WARN_ELF("elf_getscn"); + return -1; + } + + if (!gelf_getshdr(scn, &sh)) { + WARN_ELF("gelf_getshdr"); + return -1; + } + + name = elf_strptr(elf, shstrtab_idx, sh.sh_name); + if (!name) { + WARN_ELF("elf_strptr"); + return -1; + } + } else { + name = elf_strptr(elf, strtab_idx, sym.st_name); + if (!name) { + WARN_ELF("elf_strptr"); + return -1; + } } printf("%s+%llx:", name, (unsigned long long)rela.r_addend); diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 41e4a2754da4..4c0dabd28000 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -88,11 +88,6 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti struct orc_entry *orc; struct rela *rela; - if (!insn_sec->sym) { - WARN("missing symbol for section %s", insn_sec->name); - return -1; - } - /* populate ORC data */ orc = (struct orc_entry *)u_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc)); @@ -105,8 +100,32 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti } memset(rela, 0, sizeof(*rela)); - rela->sym = insn_sec->sym; - rela->addend = insn_off; + if (insn_sec->sym) { + rela->sym = insn_sec->sym; + rela->addend = insn_off; + } else { + /* + * The Clang assembler doesn't produce section symbols, so we + * have to reference the function symbol instead: + */ + rela->sym = find_symbol_containing(insn_sec, insn_off); + if (!rela->sym) { + /* + * Hack alert. This happens when we need to reference + * the NOP pad insn immediately after the function. + */ + rela->sym = find_symbol_containing(insn_sec, + insn_off - 1); + } + if (!rela->sym) { + WARN("missing symbol for insn at offset 0x%lx\n", + insn_off); + return -1; + } + + rela->addend = insn_off - rela->sym->offset; + } + rela->type = R_X86_64_PC32; rela->offset = idx * sizeof(int); rela->sec = ip_relasec; diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c index 32b7c6f9043d..0a1344c45213 100644 --- a/tools/pci/pcitest.c +++ b/tools/pci/pcitest.c @@ -30,14 +30,17 @@ struct pci_test { int irqtype; bool set_irqtype; bool get_irqtype; + bool clear_irq; bool read; bool write; bool copy; unsigned long size; + bool use_dma; }; static int run_test(struct pci_test *test) { + struct pci_endpoint_test_xfer_param param; int ret = -EINVAL; int fd; @@ -74,6 +77,15 @@ static int run_test(struct pci_test *test) fprintf(stdout, "%s\n", irq[ret]); } + if (test->clear_irq) { + ret = ioctl(fd, PCITEST_CLEAR_IRQ); + fprintf(stdout, "CLEAR IRQ:\t\t"); + if (ret < 0) + fprintf(stdout, "FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + if (test->legacyirq) { ret = ioctl(fd, PCITEST_LEGACY_IRQ, 0); fprintf(stdout, "LEGACY IRQ:\t"); @@ -102,7 +114,10 @@ static int run_test(struct pci_test *test) } if (test->write) { - ret = ioctl(fd, PCITEST_WRITE, test->size); + param.size = test->size; + if (test->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + ret = ioctl(fd, PCITEST_WRITE, ¶m); fprintf(stdout, "WRITE (%7ld bytes):\t\t", test->size); if (ret < 0) fprintf(stdout, "TEST FAILED\n"); @@ -111,7 +126,10 @@ static int run_test(struct pci_test *test) } if (test->read) { - ret = ioctl(fd, PCITEST_READ, test->size); + param.size = test->size; + if (test->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + ret = ioctl(fd, PCITEST_READ, ¶m); fprintf(stdout, "READ (%7ld bytes):\t\t", test->size); if (ret < 0) fprintf(stdout, "TEST FAILED\n"); @@ -120,7 +138,10 @@ static int run_test(struct pci_test *test) } if (test->copy) { - ret = ioctl(fd, PCITEST_COPY, test->size); + param.size = test->size; + if (test->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + ret = ioctl(fd, PCITEST_COPY, ¶m); fprintf(stdout, "COPY (%7ld bytes):\t\t", test->size); if (ret < 0) fprintf(stdout, "TEST FAILED\n"); @@ -153,7 +174,7 @@ int main(int argc, char **argv) /* set default endpoint device */ test->device = "/dev/pci-endpoint-test.0"; - while ((c = getopt(argc, argv, "D:b:m:x:i:Ilhrwcs:")) != EOF) + while ((c = getopt(argc, argv, "D:b:m:x:i:deIlhrwcs:")) != EOF) switch (c) { case 'D': test->device = optarg; @@ -194,9 +215,15 @@ int main(int argc, char **argv) case 'c': test->copy = true; continue; + case 'e': + test->clear_irq = true; + continue; case 's': test->size = strtoul(optarg, NULL, 0); continue; + case 'd': + test->use_dma = true; + continue; case 'h': default: usage: @@ -208,7 +235,9 @@ usage: "\t-m <msi num> MSI test (msi number between 1..32)\n" "\t-x <msix num> \tMSI-X test (msix number between 1..2048)\n" "\t-i <irq type> \tSet IRQ type (0 - Legacy, 1 - MSI, 2 - MSI-X)\n" + "\t-e Clear IRQ\n" "\t-I Get current IRQ type configured\n" + "\t-d Use DMA\n" "\t-l Legacy IRQ test\n" "\t-r Read buffer test\n" "\t-w Write buffer test\n" diff --git a/tools/pcmcia/.gitignore b/tools/pcmcia/.gitignore index 53d081336757..94cb97b77f06 100644 --- a/tools/pcmcia/.gitignore +++ b/tools/pcmcia/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only crc32hash diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index bf1252dc2cb0..f3f84781fd74 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only PERF-CFLAGS PERF-GUI-VARS PERF-VERSION-FILE diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 8ead55593984..f16d8a71d3f5 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -405,14 +405,16 @@ ui.*:: This option is only applied to TUI. call-graph.*:: - When sub-commands 'top' and 'report' work with -g/—-children - there're options in control of call-graph. + The following controls the handling of call-graphs (obtained via the + -g/--call-graph options). call-graph.record-mode:: - The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'. - The value of 'dwarf' is effective only if perf detect needed library - (libunwind or a recent version of libdw). - 'lbr' only work for cpus that support it. + The mode for user space can be 'fp' (frame pointer), 'dwarf' + and 'lbr'. The value 'dwarf' is effective only if libunwind + (or a recent version of libdw) is present on the system; + the value 'lbr' only works for certain cpus. The method for + kernel space is controlled not by this option but by the + kernel config (CONFIG_UNWINDER_*). call-graph.dump-size:: The size of stack to dump in order to do post-unwinding. Default is 8192 (byte). diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 7f4db7592467..b3f3b3f1c161 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -237,16 +237,22 @@ OPTIONS option and remains only for backward compatibility. See --event. -g:: - Enables call-graph (stack chain/backtrace) recording. + Enables call-graph (stack chain/backtrace) recording for both + kernel space and user space. --call-graph:: Setup and enable call-graph (stack chain/backtrace) recording, - implies -g. Default is "fp". + implies -g. Default is "fp" (for user space). - Allows specifying "fp" (frame pointer) or "dwarf" - (DWARF's CFI - Call Frame Information) or "lbr" - (Hardware Last Branch Record facility) as the method to collect - the information used to show the call graphs. + The unwinding method used for kernel space is dependent on the + unwinder used by the active kernel configuration, i.e + CONFIG_UNWINDER_FRAME_POINTER (fp) or CONFIG_UNWINDER_ORC (orc) + + Any option specified here controls the method used for user space. + + Valid options are "fp" (frame pointer), "dwarf" (DWARF's CFI - + Call Frame Information) or "lbr" (Hardware Last Branch Record + facility). In some systems, where binaries are build with gcc --fomit-frame-pointer, using the "fp" method will produce bogus @@ -385,7 +391,10 @@ displayed with the weight and local_weight sort keys. This currently works for abort events and some memory events in precise mode on modern Intel CPUs. --namespaces:: -Record events of type PERF_RECORD_NAMESPACES. +Record events of type PERF_RECORD_NAMESPACES. This enables 'cgroup_id' sort key. + +--all-cgroups:: +Record events of type PERF_RECORD_CGROUP. This enables 'cgroup' sort key. --transaction:: Record transaction flags for transaction related events. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index bd0a029d4c08..f569b9ea4002 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -95,6 +95,7 @@ OPTIONS abort cost. This is the global weight. - local_weight: Local weight version of the weight above. - cgroup_id: ID derived from cgroup namespace device and inode numbers. + - cgroup: cgroup pathname in the cgroupfs. - transaction: Transaction abort flags. - overhead: Overhead percentage of sample - overhead_sys: Overhead percentage of sample running in system mode @@ -377,6 +378,11 @@ OPTIONS Show event group information together. It forces group output also if there are no groups defined in data file. +--group-sort-idx:: + Sort the output by the event at the index n in group. If n is invalid, + sort by the first event. It can support multiple groups with different + amount of events. WARNING: This should be used on grouped events. + --demangle:: Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index db6a36aac47e..963487e82edc 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -319,6 +319,9 @@ OPTIONS --show-bpf-events Display bpf events i.e. events of type PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT. +--show-cgroup-events + Display cgroup events i.e. events of type PERF_RECORD_CGROUP. + --demangle:: Demangle symbol names to human readable form. It's enabled by default, disable with --no-demangle. @@ -390,6 +393,9 @@ include::itrace.txt[] --reltime:: Print time stamps relative to trace start. +--deltatime:: + Print time stamps relative to previous event. + --per-event-dump:: Create per event files with a "perf.data.EVENT.dump" name instead of printing to stdout, useful, for instance, for generating flamegraphs. @@ -406,6 +412,14 @@ include::itrace.txt[] --xed:: Run xed disassembler on output. Requires installing the xed disassembler. +-S:: +--symbols=symbol[,symbol...]:: + Only consider the listed symbols. Symbols are typically a name + but they may also be hexadecimal address. + + For example, to select the symbol noploop or the address 0x4007a0: + perf script --symbols=noploop,0x4007a0 + --call-trace:: Show call stream for intel_pt traces. The CPUs are interleaved, but can be filtered with -C. diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 324b6b53c86b..487737a725e9 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -53,6 +53,11 @@ Default is to monitor all CPUS. --group:: Put the counters into a counter group. +--group-sort-idx:: + Sort the output by the event at the index n in group. If n is invalid, + sort by the first event. It can support multiple groups with different + amount of events. WARNING: This should be used on grouped events. + -F <freq>:: --freq=<freq>:: Profile at this frequency. Use 'max' to use the currently maximum @@ -272,6 +277,10 @@ Default is to monitor all CPUS. Record events of type PERF_RECORD_NAMESPACES and display it with the 'cgroup_id' sort key. +--all-cgroups:: + Record events of type PERF_RECORD_CGROUP and display it with the + 'cgroup' sort key. + --switch-on EVENT_NAME:: Only consider events after this event is found. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 80e55e796be9..12a8204d63c6 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -228,8 +228,17 @@ strip-libs = $(filter-out -l%,$(1)) PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) +# Python 3.8 changed the output of `python-config --ldflags` to not include the +# '-lpythonX.Y' flag unless '--embed' is also passed. The feature check for +# libpython fails if that flag is not included in LDFLAGS +ifeq ($(shell $(PYTHON_CONFIG_SQ) --ldflags --embed 2>&1 1>/dev/null; echo $$?), 0) + PYTHON_CONFIG_LDFLAGS := --ldflags --embed +else + PYTHON_CONFIG_LDFLAGS := --ldflags +endif + ifdef PYTHON_CONFIG - PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) + PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) $(PYTHON_CONFIG_LDFLAGS) 2>/dev/null) PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) @@ -348,6 +357,10 @@ ifeq ($(feature-gettid), 1) CFLAGS += -DHAVE_GETTID endif +ifeq ($(feature-file-handle), 1) + CFLAGS += -DHAVE_FILE_HANDLE +endif + ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 3eda9d4b88e7..d15a311408f1 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -231,6 +231,7 @@ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ BPF_DIR = $(srctree)/tools/lib/bpf/ SUBCMD_DIR = $(srctree)/tools/lib/subcmd/ LIBPERF_DIR = $(srctree)/tools/lib/perf/ +DOC_DIR = $(srctree)/tools/perf/Documentation/ # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed. # Without this setting the output feature dump file misses some features, for @@ -573,7 +574,7 @@ arch_errno_hdr_dir := $(srctree)/tools arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh $(arch_errno_name_array): $(arch_errno_tbl) - $(Q)$(SHELL) '$(arch_errno_tbl)' $(CC) $(arch_errno_hdr_dir) > $@ + $(Q)$(SHELL) '$(arch_errno_tbl)' $(firstword $(CC)) $(arch_errno_hdr_dir) > $@ sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh @@ -792,7 +793,6 @@ $(LIBSUBCMD): FORCE $(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a $(LIBSUBCMD)-clean: - $(call QUIET_CLEAN, libsubcmd) $(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) clean help: @@ -832,7 +832,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html # 'make doc' should call 'make -C Documentation all' $(DOC_TARGETS): - $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all) + $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:doc=all) TAG_FOLDERS= . ../lib ../include TAG_FILES= ../../include/uapi/linux/perf_event.h @@ -959,7 +959,7 @@ install-python_ext: # 'make install-doc' should call 'make -C Documentation install' $(INSTALL_DOC_TARGETS): - $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:-doc=) + $(Q)$(MAKE) -C $(DOC_DIR) O=$(OUTPUT) $(@:-doc=) ### Cleaning rules @@ -1008,7 +1008,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(rename_flags_array) \ $(OUTPUT)$(arch_errno_name_array) \ $(OUTPUT)$(sync_file_range_arrays) - $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean + $(call QUIET_CLEAN, Documentation) \ + $(MAKE) -C $(DOC_DIR) O=$(OUTPUT) clean >/dev/null # # To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY) diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index 0a7782c61209..5c13438c7bd4 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -1,6 +1,6 @@ perf-y += header.o +perf-y += machine.o perf-y += perf_regs.o -perf-y += sym-handling.o perf-$(CONFIG_DWARF) += dwarf-regs.o perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c new file mode 100644 index 000000000000..d41b27e781d3 --- /dev/null +++ b/tools/perf/arch/arm64/util/machine.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <string.h> +#include "debug.h" +#include "symbol.h" + +/* On arm64, kernel text segment start at high memory address, + * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory + * address, like 0xffff 0000 00ax xxxx. When only samll amount of + * memory is used by modules, gap between end of module's text segment + * and start of kernel text segment may be reach 2G. + * Therefore do not fill this gap and do not assign it to the kernel dso map. + */ + +#define SYMBOL_LIMIT (1 << 12) /* 4K */ + +void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) +{ + if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) || + (strchr(p->name, '[') == NULL && strchr(c->name, '['))) + /* Limit range of last symbol in module and kernel */ + p->end += SYMBOL_LIMIT; + else + p->end = c->start; + pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end); +} diff --git a/tools/perf/arch/arm64/util/sym-handling.c b/tools/perf/arch/arm64/util/sym-handling.c deleted file mode 100644 index 8dfa3e5229f1..000000000000 --- a/tools/perf/arch/arm64/util/sym-handling.c +++ /dev/null @@ -1,19 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * - * Copyright (C) 2015 Naveen N. Rao, IBM Corporation - */ - -#include "symbol.h" // for the elf__needs_adjust_symbols() prototype -#include <stdbool.h> - -#ifdef HAVE_LIBELF_SUPPORT -#include <gelf.h> - -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) -{ - return ehdr.e_type == ET_EXEC || - ehdr.e_type == ET_REL || - ehdr.e_type == ET_DYN; -} -#endif diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 7cf0b8803097..e5c9504f8586 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,5 +1,4 @@ perf-y += header.o -perf-y += sym-handling.o perf-y += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index abb7a12d8f93..0856b32f9e08 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -10,16 +10,6 @@ #include "probe-event.h" #include "probe-file.h" -#ifdef HAVE_LIBELF_SUPPORT -bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) -{ - return ehdr.e_type == ET_EXEC || - ehdr.e_type == ET_REL || - ehdr.e_type == ET_DYN; -} - -#endif - int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 44d510bc9b78..37b844f839bc 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -8,357 +8,357 @@ # # The abi is "common", "64" or "x32" for this file. # -0 common read __x64_sys_read -1 common write __x64_sys_write -2 common open __x64_sys_open -3 common close __x64_sys_close -4 common stat __x64_sys_newstat -5 common fstat __x64_sys_newfstat -6 common lstat __x64_sys_newlstat -7 common poll __x64_sys_poll -8 common lseek __x64_sys_lseek -9 common mmap __x64_sys_mmap -10 common mprotect __x64_sys_mprotect -11 common munmap __x64_sys_munmap -12 common brk __x64_sys_brk -13 64 rt_sigaction __x64_sys_rt_sigaction -14 common rt_sigprocmask __x64_sys_rt_sigprocmask -15 64 rt_sigreturn __x64_sys_rt_sigreturn/ptregs -16 64 ioctl __x64_sys_ioctl -17 common pread64 __x64_sys_pread64 -18 common pwrite64 __x64_sys_pwrite64 -19 64 readv __x64_sys_readv -20 64 writev __x64_sys_writev -21 common access __x64_sys_access -22 common pipe __x64_sys_pipe -23 common select __x64_sys_select -24 common sched_yield __x64_sys_sched_yield -25 common mremap __x64_sys_mremap -26 common msync __x64_sys_msync -27 common mincore __x64_sys_mincore -28 common madvise __x64_sys_madvise -29 common shmget __x64_sys_shmget -30 common shmat __x64_sys_shmat -31 common shmctl __x64_sys_shmctl -32 common dup __x64_sys_dup -33 common dup2 __x64_sys_dup2 -34 common pause __x64_sys_pause -35 common nanosleep __x64_sys_nanosleep -36 common getitimer __x64_sys_getitimer -37 common alarm __x64_sys_alarm -38 common setitimer __x64_sys_setitimer -39 common getpid __x64_sys_getpid -40 common sendfile __x64_sys_sendfile64 -41 common socket __x64_sys_socket -42 common connect __x64_sys_connect -43 common accept __x64_sys_accept -44 common sendto __x64_sys_sendto -45 64 recvfrom __x64_sys_recvfrom -46 64 sendmsg __x64_sys_sendmsg -47 64 recvmsg __x64_sys_recvmsg -48 common shutdown __x64_sys_shutdown -49 common bind __x64_sys_bind -50 common listen __x64_sys_listen -51 common getsockname __x64_sys_getsockname -52 common getpeername __x64_sys_getpeername -53 common socketpair __x64_sys_socketpair -54 64 setsockopt __x64_sys_setsockopt -55 64 getsockopt __x64_sys_getsockopt -56 common clone __x64_sys_clone/ptregs -57 common fork __x64_sys_fork/ptregs -58 common vfork __x64_sys_vfork/ptregs -59 64 execve __x64_sys_execve/ptregs -60 common exit __x64_sys_exit -61 common wait4 __x64_sys_wait4 -62 common kill __x64_sys_kill -63 common uname __x64_sys_newuname -64 common semget __x64_sys_semget -65 common semop __x64_sys_semop -66 common semctl __x64_sys_semctl -67 common shmdt __x64_sys_shmdt -68 common msgget __x64_sys_msgget -69 common msgsnd __x64_sys_msgsnd -70 common msgrcv __x64_sys_msgrcv -71 common msgctl __x64_sys_msgctl -72 common fcntl __x64_sys_fcntl -73 common flock __x64_sys_flock -74 common fsync __x64_sys_fsync -75 common fdatasync __x64_sys_fdatasync -76 common truncate __x64_sys_truncate -77 common ftruncate __x64_sys_ftruncate -78 common getdents __x64_sys_getdents -79 common getcwd __x64_sys_getcwd -80 common chdir __x64_sys_chdir -81 common fchdir __x64_sys_fchdir -82 common rename __x64_sys_rename -83 common mkdir __x64_sys_mkdir -84 common rmdir __x64_sys_rmdir -85 common creat __x64_sys_creat -86 common link __x64_sys_link -87 common unlink __x64_sys_unlink -88 common symlink __x64_sys_symlink -89 common readlink __x64_sys_readlink -90 common chmod __x64_sys_chmod -91 common fchmod __x64_sys_fchmod -92 common chown __x64_sys_chown -93 common fchown __x64_sys_fchown -94 common lchown __x64_sys_lchown -95 common umask __x64_sys_umask -96 common gettimeofday __x64_sys_gettimeofday -97 common getrlimit __x64_sys_getrlimit -98 common getrusage __x64_sys_getrusage -99 common sysinfo __x64_sys_sysinfo -100 common times __x64_sys_times -101 64 ptrace __x64_sys_ptrace -102 common getuid __x64_sys_getuid -103 common syslog __x64_sys_syslog -104 common getgid __x64_sys_getgid -105 common setuid __x64_sys_setuid -106 common setgid __x64_sys_setgid -107 common geteuid __x64_sys_geteuid -108 common getegid __x64_sys_getegid -109 common setpgid __x64_sys_setpgid -110 common getppid __x64_sys_getppid -111 common getpgrp __x64_sys_getpgrp -112 common setsid __x64_sys_setsid -113 common setreuid __x64_sys_setreuid -114 common setregid __x64_sys_setregid -115 common getgroups __x64_sys_getgroups -116 common setgroups __x64_sys_setgroups -117 common setresuid __x64_sys_setresuid -118 common getresuid __x64_sys_getresuid -119 common setresgid __x64_sys_setresgid -120 common getresgid __x64_sys_getresgid -121 common getpgid __x64_sys_getpgid -122 common setfsuid __x64_sys_setfsuid -123 common setfsgid __x64_sys_setfsgid -124 common getsid __x64_sys_getsid -125 common capget __x64_sys_capget -126 common capset __x64_sys_capset -127 64 rt_sigpending __x64_sys_rt_sigpending -128 64 rt_sigtimedwait __x64_sys_rt_sigtimedwait -129 64 rt_sigqueueinfo __x64_sys_rt_sigqueueinfo -130 common rt_sigsuspend __x64_sys_rt_sigsuspend -131 64 sigaltstack __x64_sys_sigaltstack -132 common utime __x64_sys_utime -133 common mknod __x64_sys_mknod +0 common read sys_read +1 common write sys_write +2 common open sys_open +3 common close sys_close +4 common stat sys_newstat +5 common fstat sys_newfstat +6 common lstat sys_newlstat +7 common poll sys_poll +8 common lseek sys_lseek +9 common mmap sys_mmap +10 common mprotect sys_mprotect +11 common munmap sys_munmap +12 common brk sys_brk +13 64 rt_sigaction sys_rt_sigaction +14 common rt_sigprocmask sys_rt_sigprocmask +15 64 rt_sigreturn sys_rt_sigreturn +16 64 ioctl sys_ioctl +17 common pread64 sys_pread64 +18 common pwrite64 sys_pwrite64 +19 64 readv sys_readv +20 64 writev sys_writev +21 common access sys_access +22 common pipe sys_pipe +23 common select sys_select +24 common sched_yield sys_sched_yield +25 common mremap sys_mremap +26 common msync sys_msync +27 common mincore sys_mincore +28 common madvise sys_madvise +29 common shmget sys_shmget +30 common shmat sys_shmat +31 common shmctl sys_shmctl +32 common dup sys_dup +33 common dup2 sys_dup2 +34 common pause sys_pause +35 common nanosleep sys_nanosleep +36 common getitimer sys_getitimer +37 common alarm sys_alarm +38 common setitimer sys_setitimer +39 common getpid sys_getpid +40 common sendfile sys_sendfile64 +41 common socket sys_socket +42 common connect sys_connect +43 common accept sys_accept +44 common sendto sys_sendto +45 64 recvfrom sys_recvfrom +46 64 sendmsg sys_sendmsg +47 64 recvmsg sys_recvmsg +48 common shutdown sys_shutdown +49 common bind sys_bind +50 common listen sys_listen +51 common getsockname sys_getsockname +52 common getpeername sys_getpeername +53 common socketpair sys_socketpair +54 64 setsockopt sys_setsockopt +55 64 getsockopt sys_getsockopt +56 common clone sys_clone +57 common fork sys_fork +58 common vfork sys_vfork +59 64 execve sys_execve +60 common exit sys_exit +61 common wait4 sys_wait4 +62 common kill sys_kill +63 common uname sys_newuname +64 common semget sys_semget +65 common semop sys_semop +66 common semctl sys_semctl +67 common shmdt sys_shmdt +68 common msgget sys_msgget +69 common msgsnd sys_msgsnd +70 common msgrcv sys_msgrcv +71 common msgctl sys_msgctl +72 common fcntl sys_fcntl +73 common flock sys_flock +74 common fsync sys_fsync +75 common fdatasync sys_fdatasync +76 common truncate sys_truncate +77 common ftruncate sys_ftruncate +78 common getdents sys_getdents +79 common getcwd sys_getcwd +80 common chdir sys_chdir +81 common fchdir sys_fchdir +82 common rename sys_rename +83 common mkdir sys_mkdir +84 common rmdir sys_rmdir +85 common creat sys_creat +86 common link sys_link +87 common unlink sys_unlink +88 common symlink sys_symlink +89 common readlink sys_readlink +90 common chmod sys_chmod +91 common fchmod sys_fchmod +92 common chown sys_chown +93 common fchown sys_fchown +94 common lchown sys_lchown +95 common umask sys_umask +96 common gettimeofday sys_gettimeofday +97 common getrlimit sys_getrlimit +98 common getrusage sys_getrusage +99 common sysinfo sys_sysinfo +100 common times sys_times +101 64 ptrace sys_ptrace +102 common getuid sys_getuid +103 common syslog sys_syslog +104 common getgid sys_getgid +105 common setuid sys_setuid +106 common setgid sys_setgid +107 common geteuid sys_geteuid +108 common getegid sys_getegid +109 common setpgid sys_setpgid +110 common getppid sys_getppid +111 common getpgrp sys_getpgrp +112 common setsid sys_setsid +113 common setreuid sys_setreuid +114 common setregid sys_setregid +115 common getgroups sys_getgroups +116 common setgroups sys_setgroups +117 common setresuid sys_setresuid +118 common getresuid sys_getresuid +119 common setresgid sys_setresgid +120 common getresgid sys_getresgid +121 common getpgid sys_getpgid +122 common setfsuid sys_setfsuid +123 common setfsgid sys_setfsgid +124 common getsid sys_getsid +125 common capget sys_capget +126 common capset sys_capset +127 64 rt_sigpending sys_rt_sigpending +128 64 rt_sigtimedwait sys_rt_sigtimedwait +129 64 rt_sigqueueinfo sys_rt_sigqueueinfo +130 common rt_sigsuspend sys_rt_sigsuspend +131 64 sigaltstack sys_sigaltstack +132 common utime sys_utime +133 common mknod sys_mknod 134 64 uselib -135 common personality __x64_sys_personality -136 common ustat __x64_sys_ustat -137 common statfs __x64_sys_statfs -138 common fstatfs __x64_sys_fstatfs -139 common sysfs __x64_sys_sysfs -140 common getpriority __x64_sys_getpriority -141 common setpriority __x64_sys_setpriority -142 common sched_setparam __x64_sys_sched_setparam -143 common sched_getparam __x64_sys_sched_getparam -144 common sched_setscheduler __x64_sys_sched_setscheduler -145 common sched_getscheduler __x64_sys_sched_getscheduler -146 common sched_get_priority_max __x64_sys_sched_get_priority_max -147 common sched_get_priority_min __x64_sys_sched_get_priority_min -148 common sched_rr_get_interval __x64_sys_sched_rr_get_interval -149 common mlock __x64_sys_mlock -150 common munlock __x64_sys_munlock -151 common mlockall __x64_sys_mlockall -152 common munlockall __x64_sys_munlockall -153 common vhangup __x64_sys_vhangup -154 common modify_ldt __x64_sys_modify_ldt -155 common pivot_root __x64_sys_pivot_root -156 64 _sysctl __x64_sys_sysctl -157 common prctl __x64_sys_prctl -158 common arch_prctl __x64_sys_arch_prctl -159 common adjtimex __x64_sys_adjtimex -160 common setrlimit __x64_sys_setrlimit -161 common chroot __x64_sys_chroot -162 common sync __x64_sys_sync -163 common acct __x64_sys_acct -164 common settimeofday __x64_sys_settimeofday -165 common mount __x64_sys_mount -166 common umount2 __x64_sys_umount -167 common swapon __x64_sys_swapon -168 common swapoff __x64_sys_swapoff -169 common reboot __x64_sys_reboot -170 common sethostname __x64_sys_sethostname -171 common setdomainname __x64_sys_setdomainname -172 common iopl __x64_sys_iopl/ptregs -173 common ioperm __x64_sys_ioperm +135 common personality sys_personality +136 common ustat sys_ustat +137 common statfs sys_statfs +138 common fstatfs sys_fstatfs +139 common sysfs sys_sysfs +140 common getpriority sys_getpriority +141 common setpriority sys_setpriority +142 common sched_setparam sys_sched_setparam +143 common sched_getparam sys_sched_getparam +144 common sched_setscheduler sys_sched_setscheduler +145 common sched_getscheduler sys_sched_getscheduler +146 common sched_get_priority_max sys_sched_get_priority_max +147 common sched_get_priority_min sys_sched_get_priority_min +148 common sched_rr_get_interval sys_sched_rr_get_interval +149 common mlock sys_mlock +150 common munlock sys_munlock +151 common mlockall sys_mlockall +152 common munlockall sys_munlockall +153 common vhangup sys_vhangup +154 common modify_ldt sys_modify_ldt +155 common pivot_root sys_pivot_root +156 64 _sysctl sys_sysctl +157 common prctl sys_prctl +158 common arch_prctl sys_arch_prctl +159 common adjtimex sys_adjtimex +160 common setrlimit sys_setrlimit +161 common chroot sys_chroot +162 common sync sys_sync +163 common acct sys_acct +164 common settimeofday sys_settimeofday +165 common mount sys_mount +166 common umount2 sys_umount +167 common swapon sys_swapon +168 common swapoff sys_swapoff +169 common reboot sys_reboot +170 common sethostname sys_sethostname +171 common setdomainname sys_setdomainname +172 common iopl sys_iopl +173 common ioperm sys_ioperm 174 64 create_module -175 common init_module __x64_sys_init_module -176 common delete_module __x64_sys_delete_module +175 common init_module sys_init_module +176 common delete_module sys_delete_module 177 64 get_kernel_syms 178 64 query_module -179 common quotactl __x64_sys_quotactl +179 common quotactl sys_quotactl 180 64 nfsservctl 181 common getpmsg 182 common putpmsg 183 common afs_syscall 184 common tuxcall 185 common security -186 common gettid __x64_sys_gettid -187 common readahead __x64_sys_readahead -188 common setxattr __x64_sys_setxattr -189 common lsetxattr __x64_sys_lsetxattr -190 common fsetxattr __x64_sys_fsetxattr -191 common getxattr __x64_sys_getxattr -192 common lgetxattr __x64_sys_lgetxattr -193 common fgetxattr __x64_sys_fgetxattr -194 common listxattr __x64_sys_listxattr -195 common llistxattr __x64_sys_llistxattr -196 common flistxattr __x64_sys_flistxattr -197 common removexattr __x64_sys_removexattr -198 common lremovexattr __x64_sys_lremovexattr -199 common fremovexattr __x64_sys_fremovexattr -200 common tkill __x64_sys_tkill -201 common time __x64_sys_time -202 common futex __x64_sys_futex -203 common sched_setaffinity __x64_sys_sched_setaffinity -204 common sched_getaffinity __x64_sys_sched_getaffinity +186 common gettid sys_gettid +187 common readahead sys_readahead +188 common setxattr sys_setxattr +189 common lsetxattr sys_lsetxattr +190 common fsetxattr sys_fsetxattr +191 common getxattr sys_getxattr +192 common lgetxattr sys_lgetxattr +193 common fgetxattr sys_fgetxattr +194 common listxattr sys_listxattr +195 common llistxattr sys_llistxattr +196 common flistxattr sys_flistxattr +197 common removexattr sys_removexattr +198 common lremovexattr sys_lremovexattr +199 common fremovexattr sys_fremovexattr +200 common tkill sys_tkill +201 common time sys_time +202 common futex sys_futex +203 common sched_setaffinity sys_sched_setaffinity +204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 64 io_setup __x64_sys_io_setup -207 common io_destroy __x64_sys_io_destroy -208 common io_getevents __x64_sys_io_getevents -209 64 io_submit __x64_sys_io_submit -210 common io_cancel __x64_sys_io_cancel +206 64 io_setup sys_io_setup +207 common io_destroy sys_io_destroy +208 common io_getevents sys_io_getevents +209 64 io_submit sys_io_submit +210 common io_cancel sys_io_cancel 211 64 get_thread_area -212 common lookup_dcookie __x64_sys_lookup_dcookie -213 common epoll_create __x64_sys_epoll_create +212 common lookup_dcookie sys_lookup_dcookie +213 common epoll_create sys_epoll_create 214 64 epoll_ctl_old 215 64 epoll_wait_old -216 common remap_file_pages __x64_sys_remap_file_pages -217 common getdents64 __x64_sys_getdents64 -218 common set_tid_address __x64_sys_set_tid_address -219 common restart_syscall __x64_sys_restart_syscall -220 common semtimedop __x64_sys_semtimedop -221 common fadvise64 __x64_sys_fadvise64 -222 64 timer_create __x64_sys_timer_create -223 common timer_settime __x64_sys_timer_settime -224 common timer_gettime __x64_sys_timer_gettime -225 common timer_getoverrun __x64_sys_timer_getoverrun -226 common timer_delete __x64_sys_timer_delete -227 common clock_settime __x64_sys_clock_settime -228 common clock_gettime __x64_sys_clock_gettime -229 common clock_getres __x64_sys_clock_getres -230 common clock_nanosleep __x64_sys_clock_nanosleep -231 common exit_group __x64_sys_exit_group -232 common epoll_wait __x64_sys_epoll_wait -233 common epoll_ctl __x64_sys_epoll_ctl -234 common tgkill __x64_sys_tgkill -235 common utimes __x64_sys_utimes +216 common remap_file_pages sys_remap_file_pages +217 common getdents64 sys_getdents64 +218 common set_tid_address sys_set_tid_address +219 common restart_syscall sys_restart_syscall +220 common semtimedop sys_semtimedop +221 common fadvise64 sys_fadvise64 +222 64 timer_create sys_timer_create +223 common timer_settime sys_timer_settime +224 common timer_gettime sys_timer_gettime +225 common timer_getoverrun sys_timer_getoverrun +226 common timer_delete sys_timer_delete +227 common clock_settime sys_clock_settime +228 common clock_gettime sys_clock_gettime +229 common clock_getres sys_clock_getres +230 common clock_nanosleep sys_clock_nanosleep +231 common exit_group sys_exit_group +232 common epoll_wait sys_epoll_wait +233 common epoll_ctl sys_epoll_ctl +234 common tgkill sys_tgkill +235 common utimes sys_utimes 236 64 vserver -237 common mbind __x64_sys_mbind -238 common set_mempolicy __x64_sys_set_mempolicy -239 common get_mempolicy __x64_sys_get_mempolicy -240 common mq_open __x64_sys_mq_open -241 common mq_unlink __x64_sys_mq_unlink -242 common mq_timedsend __x64_sys_mq_timedsend -243 common mq_timedreceive __x64_sys_mq_timedreceive -244 64 mq_notify __x64_sys_mq_notify -245 common mq_getsetattr __x64_sys_mq_getsetattr -246 64 kexec_load __x64_sys_kexec_load -247 64 waitid __x64_sys_waitid -248 common add_key __x64_sys_add_key -249 common request_key __x64_sys_request_key -250 common keyctl __x64_sys_keyctl -251 common ioprio_set __x64_sys_ioprio_set -252 common ioprio_get __x64_sys_ioprio_get -253 common inotify_init __x64_sys_inotify_init -254 common inotify_add_watch __x64_sys_inotify_add_watch -255 common inotify_rm_watch __x64_sys_inotify_rm_watch -256 common migrate_pages __x64_sys_migrate_pages -257 common openat __x64_sys_openat -258 common mkdirat __x64_sys_mkdirat -259 common mknodat __x64_sys_mknodat -260 common fchownat __x64_sys_fchownat -261 common futimesat __x64_sys_futimesat -262 common newfstatat __x64_sys_newfstatat -263 common unlinkat __x64_sys_unlinkat -264 common renameat __x64_sys_renameat -265 common linkat __x64_sys_linkat -266 common symlinkat __x64_sys_symlinkat -267 common readlinkat __x64_sys_readlinkat -268 common fchmodat __x64_sys_fchmodat -269 common faccessat __x64_sys_faccessat -270 common pselect6 __x64_sys_pselect6 -271 common ppoll __x64_sys_ppoll -272 common unshare __x64_sys_unshare -273 64 set_robust_list __x64_sys_set_robust_list -274 64 get_robust_list __x64_sys_get_robust_list -275 common splice __x64_sys_splice -276 common tee __x64_sys_tee -277 common sync_file_range __x64_sys_sync_file_range -278 64 vmsplice __x64_sys_vmsplice -279 64 move_pages __x64_sys_move_pages -280 common utimensat __x64_sys_utimensat -281 common epoll_pwait __x64_sys_epoll_pwait -282 common signalfd __x64_sys_signalfd -283 common timerfd_create __x64_sys_timerfd_create -284 common eventfd __x64_sys_eventfd -285 common fallocate __x64_sys_fallocate -286 common timerfd_settime __x64_sys_timerfd_settime -287 common timerfd_gettime __x64_sys_timerfd_gettime -288 common accept4 __x64_sys_accept4 -289 common signalfd4 __x64_sys_signalfd4 -290 common eventfd2 __x64_sys_eventfd2 -291 common epoll_create1 __x64_sys_epoll_create1 -292 common dup3 __x64_sys_dup3 -293 common pipe2 __x64_sys_pipe2 -294 common inotify_init1 __x64_sys_inotify_init1 -295 64 preadv __x64_sys_preadv -296 64 pwritev __x64_sys_pwritev -297 64 rt_tgsigqueueinfo __x64_sys_rt_tgsigqueueinfo -298 common perf_event_open __x64_sys_perf_event_open -299 64 recvmmsg __x64_sys_recvmmsg -300 common fanotify_init __x64_sys_fanotify_init -301 common fanotify_mark __x64_sys_fanotify_mark -302 common prlimit64 __x64_sys_prlimit64 -303 common name_to_handle_at __x64_sys_name_to_handle_at -304 common open_by_handle_at __x64_sys_open_by_handle_at -305 common clock_adjtime __x64_sys_clock_adjtime -306 common syncfs __x64_sys_syncfs -307 64 sendmmsg __x64_sys_sendmmsg -308 common setns __x64_sys_setns -309 common getcpu __x64_sys_getcpu -310 64 process_vm_readv __x64_sys_process_vm_readv -311 64 process_vm_writev __x64_sys_process_vm_writev -312 common kcmp __x64_sys_kcmp -313 common finit_module __x64_sys_finit_module -314 common sched_setattr __x64_sys_sched_setattr -315 common sched_getattr __x64_sys_sched_getattr -316 common renameat2 __x64_sys_renameat2 -317 common seccomp __x64_sys_seccomp -318 common getrandom __x64_sys_getrandom -319 common memfd_create __x64_sys_memfd_create -320 common kexec_file_load __x64_sys_kexec_file_load -321 common bpf __x64_sys_bpf -322 64 execveat __x64_sys_execveat/ptregs -323 common userfaultfd __x64_sys_userfaultfd -324 common membarrier __x64_sys_membarrier -325 common mlock2 __x64_sys_mlock2 -326 common copy_file_range __x64_sys_copy_file_range -327 64 preadv2 __x64_sys_preadv2 -328 64 pwritev2 __x64_sys_pwritev2 -329 common pkey_mprotect __x64_sys_pkey_mprotect -330 common pkey_alloc __x64_sys_pkey_alloc -331 common pkey_free __x64_sys_pkey_free -332 common statx __x64_sys_statx -333 common io_pgetevents __x64_sys_io_pgetevents -334 common rseq __x64_sys_rseq +237 common mbind sys_mbind +238 common set_mempolicy sys_set_mempolicy +239 common get_mempolicy sys_get_mempolicy +240 common mq_open sys_mq_open +241 common mq_unlink sys_mq_unlink +242 common mq_timedsend sys_mq_timedsend +243 common mq_timedreceive sys_mq_timedreceive +244 64 mq_notify sys_mq_notify +245 common mq_getsetattr sys_mq_getsetattr +246 64 kexec_load sys_kexec_load +247 64 waitid sys_waitid +248 common add_key sys_add_key +249 common request_key sys_request_key +250 common keyctl sys_keyctl +251 common ioprio_set sys_ioprio_set +252 common ioprio_get sys_ioprio_get +253 common inotify_init sys_inotify_init +254 common inotify_add_watch sys_inotify_add_watch +255 common inotify_rm_watch sys_inotify_rm_watch +256 common migrate_pages sys_migrate_pages +257 common openat sys_openat +258 common mkdirat sys_mkdirat +259 common mknodat sys_mknodat +260 common fchownat sys_fchownat +261 common futimesat sys_futimesat +262 common newfstatat sys_newfstatat +263 common unlinkat sys_unlinkat +264 common renameat sys_renameat +265 common linkat sys_linkat +266 common symlinkat sys_symlinkat +267 common readlinkat sys_readlinkat +268 common fchmodat sys_fchmodat +269 common faccessat sys_faccessat +270 common pselect6 sys_pselect6 +271 common ppoll sys_ppoll +272 common unshare sys_unshare +273 64 set_robust_list sys_set_robust_list +274 64 get_robust_list sys_get_robust_list +275 common splice sys_splice +276 common tee sys_tee +277 common sync_file_range sys_sync_file_range +278 64 vmsplice sys_vmsplice +279 64 move_pages sys_move_pages +280 common utimensat sys_utimensat +281 common epoll_pwait sys_epoll_pwait +282 common signalfd sys_signalfd +283 common timerfd_create sys_timerfd_create +284 common eventfd sys_eventfd +285 common fallocate sys_fallocate +286 common timerfd_settime sys_timerfd_settime +287 common timerfd_gettime sys_timerfd_gettime +288 common accept4 sys_accept4 +289 common signalfd4 sys_signalfd4 +290 common eventfd2 sys_eventfd2 +291 common epoll_create1 sys_epoll_create1 +292 common dup3 sys_dup3 +293 common pipe2 sys_pipe2 +294 common inotify_init1 sys_inotify_init1 +295 64 preadv sys_preadv +296 64 pwritev sys_pwritev +297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo +298 common perf_event_open sys_perf_event_open +299 64 recvmmsg sys_recvmmsg +300 common fanotify_init sys_fanotify_init +301 common fanotify_mark sys_fanotify_mark +302 common prlimit64 sys_prlimit64 +303 common name_to_handle_at sys_name_to_handle_at +304 common open_by_handle_at sys_open_by_handle_at +305 common clock_adjtime sys_clock_adjtime +306 common syncfs sys_syncfs +307 64 sendmmsg sys_sendmmsg +308 common setns sys_setns +309 common getcpu sys_getcpu +310 64 process_vm_readv sys_process_vm_readv +311 64 process_vm_writev sys_process_vm_writev +312 common kcmp sys_kcmp +313 common finit_module sys_finit_module +314 common sched_setattr sys_sched_setattr +315 common sched_getattr sys_sched_getattr +316 common renameat2 sys_renameat2 +317 common seccomp sys_seccomp +318 common getrandom sys_getrandom +319 common memfd_create sys_memfd_create +320 common kexec_file_load sys_kexec_file_load +321 common bpf sys_bpf +322 64 execveat sys_execveat +323 common userfaultfd sys_userfaultfd +324 common membarrier sys_membarrier +325 common mlock2 sys_mlock2 +326 common copy_file_range sys_copy_file_range +327 64 preadv2 sys_preadv2 +328 64 pwritev2 sys_pwritev2 +329 common pkey_mprotect sys_pkey_mprotect +330 common pkey_alloc sys_pkey_alloc +331 common pkey_free sys_pkey_free +332 common statx sys_statx +333 common io_pgetevents sys_io_pgetevents +334 common rseq sys_rseq # don't use numbers 387 through 423, add new calls after the last # 'common' entry -424 common pidfd_send_signal __x64_sys_pidfd_send_signal -425 common io_uring_setup __x64_sys_io_uring_setup -426 common io_uring_enter __x64_sys_io_uring_enter -427 common io_uring_register __x64_sys_io_uring_register -428 common open_tree __x64_sys_open_tree -429 common move_mount __x64_sys_move_mount -430 common fsopen __x64_sys_fsopen -431 common fsconfig __x64_sys_fsconfig -432 common fsmount __x64_sys_fsmount -433 common fspick __x64_sys_fspick -434 common pidfd_open __x64_sys_pidfd_open -435 common clone3 __x64_sys_clone3/ptregs -437 common openat2 __x64_sys_openat2 -438 common pidfd_getfd __x64_sys_pidfd_getfd +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree +429 common move_mount sys_move_mount +430 common fsopen sys_fsopen +431 common fsconfig sys_fsconfig +432 common fsmount sys_fsmount +433 common fspick sys_fspick +434 common pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 +437 common openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd # # x32-specific system call numbers start at 512 to avoid cache impact @@ -366,39 +366,39 @@ # on-the-fly for compat_sys_*() compatibility system calls if X86_X32 # is defined. # -512 x32 rt_sigaction __x32_compat_sys_rt_sigaction -513 x32 rt_sigreturn sys32_x32_rt_sigreturn -514 x32 ioctl __x32_compat_sys_ioctl -515 x32 readv __x32_compat_sys_readv -516 x32 writev __x32_compat_sys_writev -517 x32 recvfrom __x32_compat_sys_recvfrom -518 x32 sendmsg __x32_compat_sys_sendmsg -519 x32 recvmsg __x32_compat_sys_recvmsg -520 x32 execve __x32_compat_sys_execve/ptregs -521 x32 ptrace __x32_compat_sys_ptrace -522 x32 rt_sigpending __x32_compat_sys_rt_sigpending -523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait_time64 -524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo -525 x32 sigaltstack __x32_compat_sys_sigaltstack -526 x32 timer_create __x32_compat_sys_timer_create -527 x32 mq_notify __x32_compat_sys_mq_notify -528 x32 kexec_load __x32_compat_sys_kexec_load -529 x32 waitid __x32_compat_sys_waitid -530 x32 set_robust_list __x32_compat_sys_set_robust_list -531 x32 get_robust_list __x32_compat_sys_get_robust_list -532 x32 vmsplice __x32_compat_sys_vmsplice -533 x32 move_pages __x32_compat_sys_move_pages -534 x32 preadv __x32_compat_sys_preadv64 -535 x32 pwritev __x32_compat_sys_pwritev64 -536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo -537 x32 recvmmsg __x32_compat_sys_recvmmsg_time64 -538 x32 sendmmsg __x32_compat_sys_sendmmsg -539 x32 process_vm_readv __x32_compat_sys_process_vm_readv -540 x32 process_vm_writev __x32_compat_sys_process_vm_writev -541 x32 setsockopt __x32_compat_sys_setsockopt -542 x32 getsockopt __x32_compat_sys_getsockopt -543 x32 io_setup __x32_compat_sys_io_setup -544 x32 io_submit __x32_compat_sys_io_submit -545 x32 execveat __x32_compat_sys_execveat/ptregs -546 x32 preadv2 __x32_compat_sys_preadv64v2 -547 x32 pwritev2 __x32_compat_sys_pwritev64v2 +512 x32 rt_sigaction compat_sys_rt_sigaction +513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn +514 x32 ioctl compat_sys_ioctl +515 x32 readv compat_sys_readv +516 x32 writev compat_sys_writev +517 x32 recvfrom compat_sys_recvfrom +518 x32 sendmsg compat_sys_sendmsg +519 x32 recvmsg compat_sys_recvmsg +520 x32 execve compat_sys_execve +521 x32 ptrace compat_sys_ptrace +522 x32 rt_sigpending compat_sys_rt_sigpending +523 x32 rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 +524 x32 rt_sigqueueinfo compat_sys_rt_sigqueueinfo +525 x32 sigaltstack compat_sys_sigaltstack +526 x32 timer_create compat_sys_timer_create +527 x32 mq_notify compat_sys_mq_notify +528 x32 kexec_load compat_sys_kexec_load +529 x32 waitid compat_sys_waitid +530 x32 set_robust_list compat_sys_set_robust_list +531 x32 get_robust_list compat_sys_get_robust_list +532 x32 vmsplice compat_sys_vmsplice +533 x32 move_pages compat_sys_move_pages +534 x32 preadv compat_sys_preadv64 +535 x32 pwritev compat_sys_pwritev64 +536 x32 rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo +537 x32 recvmmsg compat_sys_recvmmsg_time64 +538 x32 sendmmsg compat_sys_sendmmsg +539 x32 process_vm_readv compat_sys_process_vm_readv +540 x32 process_vm_writev compat_sys_process_vm_writev +541 x32 setsockopt compat_sys_setsockopt +542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit +545 x32 execveat compat_sys_execveat +546 x32 preadv2 compat_sys_preadv64v2 +547 x32 pwritev2 compat_sys_pwritev64v2 diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 5e697cd2224a..c94a002f295e 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -455,6 +455,7 @@ static struct perf_diff pdiff = { .fork = perf_event__process_fork, .lost = perf_event__process_lost, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .ordered_events = true, .ordering_requires_timestamps = true, }, diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 4c301466101b..1ab349abe904 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1397,6 +1397,11 @@ static int record__synthesize(struct record *rec, bool tail) if (err < 0) pr_warning("Couldn't synthesize bpf events.\n"); + err = perf_event__synthesize_cgroups(tool, process_synthesized_event, + machine); + if (err < 0) + pr_warning("Couldn't synthesize cgroup events.\n"); + err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->core.threads, process_synthesized_event, opts->sample_address, 1); @@ -1428,6 +1433,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) if (rec->opts.record_namespaces) tool->namespace_events = true; + if (rec->opts.record_cgroup) { +#ifdef HAVE_FILE_HANDLE + tool->cgroup_events = true; +#else + pr_err("cgroup tracking is not supported\n"); + return -1; +#endif + } + if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) { signal(SIGUSR2, snapshot_sig_handler); if (rec->opts.auxtrace_snapshot_mode) @@ -2358,6 +2372,8 @@ static struct option __record_options[] = { "per thread proc mmap processing timeout in ms"), OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces, "Record namespaces events"), + OPT_BOOLEAN(0, "all-cgroups", &record.opts.record_cgroup, + "Record cgroup events"), OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events, "Record context switch events"), OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 5f4045df76f4..26d8fc27e427 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -635,7 +635,7 @@ static int report__browse_hists(struct report *rep) * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. */ - if (ret != K_SWITCH_INPUT_DATA) + if (ret != K_SWITCH_INPUT_DATA && ret != K_RELOAD) ret = 0; break; case 2: @@ -1105,6 +1105,7 @@ int cmd_report(int argc, const char **argv) .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, @@ -1227,6 +1228,10 @@ int cmd_report(int argc, const char **argv) "Show a column with the sum of periods"), OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set, "Show event group information together"), + OPT_INTEGER(0, "group-sort-idx", &symbol_conf.group_sort_idx, + "Sort the output by the event at the index n in group. " + "If n is invalid, sort by the first event. " + "WARNING: should be used on grouped events."), OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "", "use branch records for per branch histogram filling", parse_branch_mode), @@ -1369,6 +1374,12 @@ repeat: setup_forced_leader(&report, session->evlist); + if (symbol_conf.group_sort_idx && !session->evlist->nr_groups) { + parse_options_usage(NULL, options, "group-sort-idx", 0); + ret = -EINVAL; + goto error; + } + if (itrace_synth_opts.last_branch) has_br_stack = true; @@ -1470,7 +1481,7 @@ repeat: sort_order = sort_tmp; } - if ((last_key != K_SWITCH_INPUT_DATA) && + if ((last_key != K_SWITCH_INPUT_DATA && last_key != K_RELOAD) && (setup_sorting(session->evlist) < 0)) { if (sort_order) parse_options_usage(report_usage, options, "s", 1); @@ -1549,7 +1560,7 @@ repeat: sort__setup_elide(stdout); ret = __cmd_report(&report); - if (ret == K_SWITCH_INPUT_DATA) { + if (ret == K_SWITCH_INPUT_DATA || ret == K_RELOAD) { perf_session__delete(session); last_key = K_SWITCH_INPUT_DATA; goto repeat; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 656b347f6dd8..1f57a7ecdf3d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -63,7 +63,9 @@ static char const *script_name; static char const *generate_script_lang; static bool reltime; +static bool deltatime; static u64 initial_time; +static u64 previous_time; static bool debug_mode; static u64 last_timestamp; static u64 nr_unordered; @@ -704,6 +706,13 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, if (!initial_time) initial_time = sample->time; t = sample->time - initial_time; + } else if (deltatime) { + if (previous_time) + t = sample->time - previous_time; + else { + t = 0; + } + previous_time = sample->time; } nsecs = t; secs = nsecs / NSEC_PER_SEC; @@ -1685,6 +1694,7 @@ struct perf_script { bool show_lost_events; bool show_round_events; bool show_bpf_events; + bool show_cgroup_events; bool allocated; bool per_event_dump; struct evswitch evswitch; @@ -2203,6 +2213,41 @@ out: return ret; } +static int process_cgroup_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct thread *thread; + struct perf_script *script = container_of(tool, struct perf_script, tool); + struct perf_session *session = script->session; + struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + int ret = -1; + + thread = machine__findnew_thread(machine, sample->pid, sample->tid); + if (thread == NULL) { + pr_debug("problem processing CGROUP event, skipping it.\n"); + return -1; + } + + if (perf_event__process_cgroup(tool, event, sample, machine) < 0) + goto out; + + if (!evsel->core.attr.sample_id_all) { + sample->cpu = 0; + sample->time = 0; + } + if (!filter_cpu(sample)) { + perf_sample__fprintf_start(sample, thread, evsel, + PERF_RECORD_CGROUP, stdout); + perf_event__fprintf(event, stdout); + } + ret = 0; +out: + thread__put(thread); + return ret; +} + static int process_fork_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -2542,6 +2587,8 @@ static int __cmd_script(struct perf_script *script) script->tool.context_switch = process_switch_event; if (script->show_namespace_events) script->tool.namespaces = process_namespaces_event; + if (script->show_cgroup_events) + script->tool.cgroup = process_cgroup_event; if (script->show_lost_events) script->tool.lost = process_lost_event; if (script->show_round_events) { @@ -3218,10 +3265,10 @@ static char *get_script_path(const char *script_root, const char *suffix) __script_root = get_script_root(script_dirent, suffix); if (__script_root && !strcmp(script_root, __script_root)) { free(__script_root); - closedir(lang_dir); closedir(scripts_dir); scnprintf(script_path, MAXPATHLEN, "%s/%s", lang_path, script_dirent->d_name); + closedir(lang_dir); return strdup(script_path); } free(__script_root); @@ -3467,6 +3514,7 @@ int cmd_script(int argc, const char **argv) .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, .namespaces = perf_event__process_namespaces, + .cgroup = perf_event__process_cgroup, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = process_attr, @@ -3555,6 +3603,7 @@ int cmd_script(int argc, const char **argv) "anything beyond the specified depth will be ignored. " "Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)), OPT_BOOLEAN(0, "reltime", &reltime, "Show time stamps relative to start"), + OPT_BOOLEAN(0, "deltatime", &deltatime, "Show time stamps relative to previous event"), OPT_BOOLEAN('I', "show-info", &show_full_info, "display extended information from perf.data file"), OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path, @@ -3567,6 +3616,8 @@ int cmd_script(int argc, const char **argv) "Show context switch events (if recorded)"), OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events, "Show namespace events (if recorded)"), + OPT_BOOLEAN('\0', "show-cgroup-events", &script.show_cgroup_events, + "Show cgroup events (if recorded)"), OPT_BOOLEAN('\0', "show-lost-events", &script.show_lost_events, "Show lost events (if recorded)"), OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events, @@ -3651,6 +3702,13 @@ int cmd_script(int argc, const char **argv) } } + if (reltime && deltatime) { + fprintf(stderr, + "reltime and deltatime - the two don't get along well. " + "Please limit to --reltime or --deltatime.\n"); + return -1; + } + if (itrace_synth_opts.callchain && itrace_synth_opts.callchain_sz > scripting_max_stack) scripting_max_stack = itrace_synth_opts.callchain_sz; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index d2539b793f9d..289cf83e658a 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -616,6 +616,7 @@ static void *display_thread_tui(void *arg) .arg = top, .refresh = top->delay_secs, }; + int ret; /* In order to read symbols from other namespaces perf to needs to call * setns(2). This isn't permitted if the struct_fs has multiple users. @@ -626,6 +627,7 @@ static void *display_thread_tui(void *arg) prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0); +repeat: perf_top__sort_new_samples(top); /* @@ -638,13 +640,18 @@ static void *display_thread_tui(void *arg) hists->uid_filter_str = top->record_opts.target.uid_str; } - perf_evlist__tui_browse_hists(top->evlist, help, &hbt, + ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, &top->session->header.env, !top->record_opts.overwrite, &top->annotation_opts); - stop_top(); + if (ret == K_RELOAD) { + top->zero = true; + goto repeat; + } else + stop_top(); + return NULL; } @@ -1246,6 +1253,14 @@ static int __cmd_top(struct perf_top *top) if (opts->record_namespaces) top->tool.namespace_events = true; + if (opts->record_cgroup) { +#ifdef HAVE_FILE_HANDLE + top->tool.cgroup_events = true; +#else + pr_err("cgroup tracking is not supported.\n"); + return -1; +#endif + } ret = perf_event__synthesize_bpf_events(top->session, perf_event__process, &top->session->machines.host, @@ -1253,6 +1268,11 @@ static int __cmd_top(struct perf_top *top) if (ret < 0) pr_debug("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n"); + ret = perf_event__synthesize_cgroups(&top->tool, perf_event__process, + &top->session->machines.host); + if (ret < 0) + pr_debug("Couldn't synthesize cgroup events.\n"); + machine__synthesize_threads(&top->session->machines.host, &opts->target, top->evlist->core.threads, false, top->nr_threads_synthesize); @@ -1545,6 +1565,12 @@ int cmd_top(int argc, const char **argv) "number of thread to run event synthesize"), OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces, "Record namespaces events"), + OPT_BOOLEAN(0, "all-cgroups", &opts->record_cgroup, + "Record cgroup events"), + OPT_INTEGER(0, "group-sort-idx", &symbol_conf.group_sort_idx, + "Sort the output by the event at the index n in group. " + "If n is invalid, sort by the first event. " + "WARNING: should be used on grouped events."), OPTS_EVSWITCH(&top.evswitch), OPT_END() }; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index bfb21d049e6c..cf147db4e5ca 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -22,7 +22,9 @@ include/uapi/linux/usbdevice_fs.h include/uapi/linux/vhost.h include/uapi/sound/asound.h include/linux/bits.h +include/vdso/bits.h include/linux/const.h +include/vdso/const.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h @@ -115,6 +117,7 @@ check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' +check include/linux/build_bug.h '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"' check include/linux/ctype.h '-I "isdigit("' check lib/ctype.c '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B' check arch/x86/include/asm/inat.h '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"' diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json b/tools/perf/pmu-events/arch/test/test_cpu/branch.json index 93ddfd8053ca..93ddfd8053ca 100644 --- a/tools/perf/pmu-events/arch/x86/amdfam17h/branch.json +++ b/tools/perf/pmu-events/arch/test/test_cpu/branch.json diff --git a/tools/perf/pmu-events/arch/test/test_cpu/other.json b/tools/perf/pmu-events/arch/test/test_cpu/other.json new file mode 100644 index 000000000000..7d53d7ecd723 --- /dev/null +++ b/tools/perf/pmu-events/arch/test/test_cpu/other.json @@ -0,0 +1,26 @@ +[ + { + "EventCode": "0x6", + "Counter": "0,1", + "UMask": "0x80", + "EventName": "SEGMENT_REG_LOADS.ANY", + "SampleAfterValue": "200000", + "BriefDescription": "Number of segment register loads." + }, + { + "EventCode": "0x9", + "Counter": "0,1", + "UMask": "0x20", + "EventName": "DISPATCH_BLOCKED.ANY", + "SampleAfterValue": "200000", + "BriefDescription": "Memory cluster signals to block micro-op dispatch for any reason" + }, + { + "EventCode": "0x3A", + "Counter": "0,1", + "UMask": "0x0", + "EventName": "EIST_TRANS", + "SampleAfterValue": "200000", + "BriefDescription": "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/test/test_cpu/uncore.json b/tools/perf/pmu-events/arch/test/test_cpu/uncore.json new file mode 100644 index 000000000000..d0a890cc814d --- /dev/null +++ b/tools/perf/pmu-events/arch/test/test_cpu/uncore.json @@ -0,0 +1,21 @@ +[ + { + "EventCode": "0x02", + "EventName": "uncore_hisi_ddrc.flux_wcmd", + "BriefDescription": "DDRC write commands", + "PublicDescription": "DDRC write commands", + "Unit": "hisi_sccl,ddrc" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x81", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json b/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json deleted file mode 100644 index 6221a840fcea..000000000000 --- a/tools/perf/pmu-events/arch/x86/amdfam17h/cache.json +++ /dev/null @@ -1,329 +0,0 @@ -[ - { - "EventName": "ic_fw32", - "EventCode": "0x80", - "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)." - }, - { - "EventName": "ic_fw32_miss", - "EventCode": "0x81", - "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag." - }, - { - "EventName": "ic_cache_fill_l2", - "EventCode": "0x82", - "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache." - }, - { - "EventName": "ic_cache_fill_sys", - "EventCode": "0x83", - "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache." - }, - { - "EventName": "bp_l1_tlb_miss_l2_hit", - "EventCode": "0x84", - "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB." - }, - { - "EventName": "bp_l1_tlb_miss_l2_miss", - "EventCode": "0x85", - "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs." - }, - { - "EventName": "bp_snp_re_sync", - "EventCode": "0x86", - "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event." - }, - { - "EventName": "ic_fetch_stall.ic_stall_any", - "EventCode": "0x87", - "BriefDescription": "IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).", - "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).", - "UMask": "0x4" - }, - { - "EventName": "ic_fetch_stall.ic_stall_dq_empty", - "EventCode": "0x87", - "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.", - "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.", - "UMask": "0x2" - }, - { - "EventName": "ic_fetch_stall.ic_stall_back_pressure", - "EventCode": "0x87", - "BriefDescription": "IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.", - "PublicDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.", - "UMask": "0x1" - }, - { - "EventName": "ic_cache_inval.l2_invalidating_probe", - "EventCode": "0x8c", - "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS).", - "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to L2 invalidating probe (external or LS).", - "UMask": "0x2" - }, - { - "EventName": "ic_cache_inval.fill_invalidated", - "EventCode": "0x8c", - "BriefDescription": "IC line invalidated due to overwriting fill response.", - "PublicDescription": "The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core. IC line invalidated due to overwriting fill response.", - "UMask": "0x1" - }, - { - "EventName": "bp_tlb_rel", - "EventCode": "0x99", - "BriefDescription": "The number of ITLB reload requests." - }, - { - "EventName": "l2_request_g1.rd_blk_l", - "EventCode": "0x60", - "BriefDescription": "Requests to L2 Group1.", - "PublicDescription": "Requests to L2 Group1.", - "UMask": "0x80" - }, - { - "EventName": "l2_request_g1.rd_blk_x", - "EventCode": "0x60", - "BriefDescription": "Requests to L2 Group1.", - "PublicDescription": "Requests to L2 Group1.", - "UMask": "0x40" - }, - { - "EventName": "l2_request_g1.ls_rd_blk_c_s", - "EventCode": "0x60", - "BriefDescription": "Requests to L2 Group1.", - "PublicDescription": "Requests to L2 Group1.", - "UMask": "0x20" - }, - { - "EventName": "l2_request_g1.cacheable_ic_read", - "EventCode": "0x60", - "BriefDescription": "Requests to L2 Group1.", - "PublicDescription": "Requests to L2 Group1.", - "UMask": "0x10" - }, - { - "EventName": "l2_request_g1.change_to_x", - "EventCode": "0x60", - "BriefDescription": "Requests to L2 Group1.", - "PublicDescription": "Requests to L2 Group1.", - "UMask": "0x8" - }, - { - "EventName": "l2_request_g1.prefetch_l2", - "EventCode": "0x60", - "BriefDescription": "Requests to L2 Group1.", - "PublicDescription": "Requests to L2 Group1.", - "UMask": "0x4" - }, - { - "EventName": "l2_request_g1.l2_hw_pf", - "EventCode": "0x60", - "BriefDescription": "Requests to L2 Group1.", - "PublicDescription": "Requests to L2 Group1.", - "UMask": "0x2" - }, - { - "EventName": "l2_request_g1.other_requests", - "EventCode": "0x60", - "BriefDescription": "Events covered by l2_request_g2.", - "PublicDescription": "Requests to L2 Group1. Events covered by l2_request_g2.", - "UMask": "0x1" - }, - { - "EventName": "l2_request_g2.group1", - "EventCode": "0x61", - "BriefDescription": "All Group 1 commands not in unit0.", - "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. All Group 1 commands not in unit0.", - "UMask": "0x80" - }, - { - "EventName": "l2_request_g2.ls_rd_sized", - "EventCode": "0x61", - "BriefDescription": "RdSized, RdSized32, RdSized64.", - "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSized, RdSized32, RdSized64.", - "UMask": "0x40" - }, - { - "EventName": "l2_request_g2.ls_rd_sized_nc", - "EventCode": "0x61", - "BriefDescription": "RdSizedNC, RdSized32NC, RdSized64NC.", - "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous. RdSizedNC, RdSized32NC, RdSized64NC.", - "UMask": "0x20" - }, - { - "EventName": "l2_request_g2.ic_rd_sized", - "EventCode": "0x61", - "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "UMask": "0x10" - }, - { - "EventName": "l2_request_g2.ic_rd_sized_nc", - "EventCode": "0x61", - "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "UMask": "0x8" - }, - { - "EventName": "l2_request_g2.smc_inval", - "EventCode": "0x61", - "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "UMask": "0x4" - }, - { - "EventName": "l2_request_g2.bus_locks_originator", - "EventCode": "0x61", - "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "UMask": "0x2" - }, - { - "EventName": "l2_request_g2.bus_locks_responses", - "EventCode": "0x61", - "BriefDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "PublicDescription": "Multi-events in that LS and IF requests can be received simultaneous.", - "UMask": "0x1" - }, - { - "EventName": "l2_latency.l2_cycles_waiting_on_fills", - "EventCode": "0x62", - "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.", - "PublicDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.", - "UMask": "0x1" - }, - { - "EventName": "l2_wcb_req.wcb_write", - "EventCode": "0x63", - "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.", - "BriefDescription": "LS to L2 WCB write requests.", - "UMask": "0x40" - }, - { - "EventName": "l2_wcb_req.wcb_close", - "EventCode": "0x63", - "BriefDescription": "LS to L2 WCB close requests.", - "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.", - "UMask": "0x20" - }, - { - "EventName": "l2_wcb_req.zero_byte_store", - "EventCode": "0x63", - "BriefDescription": "LS to L2 WCB zero byte store requests.", - "PublicDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.", - "UMask": "0x4" - }, - { - "EventName": "l2_wcb_req.cl_zero", - "EventCode": "0x63", - "PublicDescription": "LS to L2 WCB cache line zeroing requests.", - "BriefDescription": "LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.", - "UMask": "0x1" - }, - { - "EventName": "l2_cache_req_stat.ls_rd_blk_cs", - "EventCode": "0x64", - "BriefDescription": "LS ReadBlock C/S Hit.", - "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS ReadBlock C/S Hit.", - "UMask": "0x80" - }, - { - "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x", - "EventCode": "0x64", - "BriefDescription": "LS Read Block L Hit X.", - "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block L Hit X.", - "UMask": "0x40" - }, - { - "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s", - "EventCode": "0x64", - "BriefDescription": "LsRdBlkL Hit Shared.", - "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkL Hit Shared.", - "UMask": "0x20" - }, - { - "EventName": "l2_cache_req_stat.ls_rd_blk_x", - "EventCode": "0x64", - "BriefDescription": "LsRdBlkX/ChgToX Hit X. Count RdBlkX finding Shared as a Miss.", - "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LsRdBlkX/ChgToX Hit X. Count RdBlkX finding Shared as a Miss.", - "UMask": "0x10" - }, - { - "EventName": "l2_cache_req_stat.ls_rd_blk_c", - "EventCode": "0x64", - "BriefDescription": "LS Read Block C S L X Change to X Miss.", - "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. LS Read Block C S L X Change to X Miss.", - "UMask": "0x8" - }, - { - "EventName": "l2_cache_req_stat.ic_fill_hit_x", - "EventCode": "0x64", - "BriefDescription": "IC Fill Hit Exclusive Stale.", - "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Exclusive Stale.", - "UMask": "0x4" - }, - { - "EventName": "l2_cache_req_stat.ic_fill_hit_s", - "EventCode": "0x64", - "BriefDescription": "IC Fill Hit Shared.", - "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Hit Shared.", - "UMask": "0x2" - }, - { - "EventName": "l2_cache_req_stat.ic_fill_miss", - "EventCode": "0x64", - "BriefDescription": "IC Fill Miss.", - "PublicDescription": "This event does not count accesses to the L2 cache by the L2 prefetcher, but it does count accesses by the L1 prefetcher. IC Fill Miss.", - "UMask": "0x1" - }, - { - "EventName": "l2_fill_pending.l2_fill_busy", - "EventCode": "0x6d", - "BriefDescription": "Total cycles spent with one or more fill requests in flight from L2.", - "PublicDescription": "Total cycles spent with one or more fill requests in flight from L2.", - "UMask": "0x1" - }, - { - "EventName": "l3_request_g1.caching_l3_cache_accesses", - "EventCode": "0x01", - "BriefDescription": "Caching: L3 cache accesses", - "UMask": "0x80", - "Unit": "L3PMC" - }, - { - "EventName": "l3_lookup_state.all_l3_req_typs", - "EventCode": "0x04", - "BriefDescription": "All L3 Request Types", - "UMask": "0xff", - "Unit": "L3PMC" - }, - { - "EventName": "l3_comb_clstr_state.other_l3_miss_typs", - "EventCode": "0x06", - "BriefDescription": "Other L3 Miss Request Types", - "UMask": "0xfe", - "Unit": "L3PMC" - }, - { - "EventName": "l3_comb_clstr_state.request_miss", - "EventCode": "0x06", - "BriefDescription": "L3 cache misses", - "UMask": "0x01", - "Unit": "L3PMC" - }, - { - "EventName": "xi_sys_fill_latency", - "EventCode": "0x90", - "BriefDescription": "L3 Cache Miss Latency. Total cycles for all transactions divided by 16. Ignores SliceMask and ThreadMask.", - "UMask": "0x00", - "Unit": "L3PMC" - }, - { - "EventName": "xi_ccx_sdp_req1.all_l3_miss_req_typs", - "EventCode": "0x9a", - "BriefDescription": "All L3 Miss Request Types. Ignores SliceMask and ThreadMask.", - "UMask": "0x3f", - "Unit": "L3PMC" - } -] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/other.json b/tools/perf/pmu-events/arch/x86/amdfam17h/other.json deleted file mode 100644 index b26a00d05a2e..000000000000 --- a/tools/perf/pmu-events/arch/x86/amdfam17h/other.json +++ /dev/null @@ -1,65 +0,0 @@ -[ - { - "EventName": "ic_oc_mode_switch.oc_ic_mode_switch", - "EventCode": "0x28a", - "BriefDescription": "OC to IC mode switch.", - "PublicDescription": "OC Mode Switch. OC to IC mode switch.", - "UMask": "0x2" - }, - { - "EventName": "ic_oc_mode_switch.ic_oc_mode_switch", - "EventCode": "0x28a", - "BriefDescription": "IC to OC mode switch.", - "PublicDescription": "OC Mode Switch. IC to OC mode switch.", - "UMask": "0x1" - }, - { - "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall", - "EventCode": "0xaf", - "BriefDescription": "RETIRE Tokens unavailable.", - "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.", - "UMask": "0x40" - }, - { - "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall", - "EventCode": "0xaf", - "BriefDescription": "AGSQ Tokens unavailable.", - "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.", - "UMask": "0x20" - }, - { - "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall", - "EventCode": "0xaf", - "BriefDescription": "ALU tokens total unavailable.", - "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.", - "UMask": "0x10" - }, - { - "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall", - "EventCode": "0xaf", - "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.", - "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall.", - "UMask": "0x8" - }, - { - "EventName": "de_dis_dispatch_token_stalls0.alsq3_token_stall", - "EventCode": "0xaf", - "BriefDescription": "ALSQ 3 Tokens unavailable.", - "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3 Tokens unavailable.", - "UMask": "0x4" - }, - { - "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall", - "EventCode": "0xaf", - "BriefDescription": "ALSQ 2 Tokens unavailable.", - "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.", - "UMask": "0x2" - }, - { - "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall", - "EventCode": "0xaf", - "BriefDescription": "ALSQ 1 Tokens unavailable.", - "PublicDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.", - "UMask": "0x1" - } -] diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/branch.json b/tools/perf/pmu-events/arch/x86/amdzen1/branch.json new file mode 100644 index 000000000000..a9943eeb8d6b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/branch.json @@ -0,0 +1,23 @@ +[ + { + "EventName": "bp_l1_btb_correct", + "EventCode": "0x8a", + "BriefDescription": "L1 BTB Correction." + }, + { + "EventName": "bp_l2_btb_correct", + "EventCode": "0x8b", + "BriefDescription": "L2 BTB Correction." + }, + { + "EventName": "bp_dyn_ind_pred", + "EventCode": "0x8e", + "BriefDescription": "Dynamic Indirect Predictions.", + "PublicDescription": "Indirect Branch Prediction for potential multi-target branch (speculative)." + }, + { + "EventName": "bp_de_redirect", + "EventCode": "0x91", + "BriefDescription": "Decoder Overrides Existing Branch Prediction (speculative)." + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/cache.json b/tools/perf/pmu-events/arch/x86/amdzen1/cache.json new file mode 100644 index 000000000000..404d4c569c01 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/cache.json @@ -0,0 +1,294 @@ +[ + { + "EventName": "ic_fw32", + "EventCode": "0x80", + "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)." + }, + { + "EventName": "ic_fw32_miss", + "EventCode": "0x81", + "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag." + }, + { + "EventName": "ic_cache_fill_l2", + "EventCode": "0x82", + "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache." + }, + { + "EventName": "ic_cache_fill_sys", + "EventCode": "0x83", + "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache." + }, + { + "EventName": "bp_l1_tlb_miss_l2_hit", + "EventCode": "0x84", + "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB." + }, + { + "EventName": "bp_l1_tlb_miss_l2_miss", + "EventCode": "0x85", + "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs." + }, + { + "EventName": "bp_snp_re_sync", + "EventCode": "0x86", + "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event." + }, + { + "EventName": "ic_fetch_stall.ic_stall_any", + "EventCode": "0x87", + "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).", + "UMask": "0x4" + }, + { + "EventName": "ic_fetch_stall.ic_stall_dq_empty", + "EventCode": "0x87", + "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.", + "UMask": "0x2" + }, + { + "EventName": "ic_fetch_stall.ic_stall_back_pressure", + "EventCode": "0x87", + "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.", + "UMask": "0x1" + }, + { + "EventName": "ic_cache_inval.l2_invalidating_probe", + "EventCode": "0x8c", + "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS). The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core.", + "UMask": "0x2" + }, + { + "EventName": "ic_cache_inval.fill_invalidated", + "EventCode": "0x8c", + "BriefDescription": "IC line invalidated due to overwriting fill response. The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core.", + "UMask": "0x1" + }, + { + "EventName": "bp_tlb_rel", + "EventCode": "0x99", + "BriefDescription": "The number of ITLB reload requests." + }, + { + "EventName": "l2_request_g1.rd_blk_l", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache reads (including hardware and software prefetch).", + "UMask": "0x80" + }, + { + "EventName": "l2_request_g1.rd_blk_x", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache stores.", + "UMask": "0x40" + }, + { + "EventName": "l2_request_g1.ls_rd_blk_c_s", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache shared reads.", + "UMask": "0x20" + }, + { + "EventName": "l2_request_g1.cacheable_ic_read", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Instruction cache reads.", + "UMask": "0x10" + }, + { + "EventName": "l2_request_g1.change_to_x", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache state change requests. Request change to writable, check L2 for current state.", + "UMask": "0x8" + }, + { + "EventName": "l2_request_g1.prefetch_l2_cmd", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). PrefetchL2Cmd.", + "UMask": "0x4" + }, + { + "EventName": "l2_request_g1.l2_hw_pf", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). L2 Prefetcher. All prefetches accepted by L2 pipeline, hit or miss. Types of PF and L2 hit/miss broken out in a separate perfmon event.", + "UMask": "0x2" + }, + { + "EventName": "l2_request_g1.group2", + "EventCode": "0x60", + "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g2 (PMCx061).", + "UMask": "0x1" + }, + { + "EventName": "l2_request_g2.group1", + "EventCode": "0x61", + "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).", + "UMask": "0x80" + }, + { + "EventName": "l2_request_g2.ls_rd_sized", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Data cache read sized.", + "UMask": "0x40" + }, + { + "EventName": "l2_request_g2.ls_rd_sized_nc", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Data cache read sized non-cacheable.", + "UMask": "0x20" + }, + { + "EventName": "l2_request_g2.ic_rd_sized", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Instruction cache read sized.", + "UMask": "0x10" + }, + { + "EventName": "l2_request_g2.ic_rd_sized_nc", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Instruction cache read sized non-cacheable.", + "UMask": "0x8" + }, + { + "EventName": "l2_request_g2.smc_inval", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Self-modifying code invalidates.", + "UMask": "0x4" + }, + { + "EventName": "l2_request_g2.bus_locks_originator", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Bus locks.", + "UMask": "0x2" + }, + { + "EventName": "l2_request_g2.bus_locks_responses", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Bus lock response.", + "UMask": "0x1" + }, + { + "EventName": "l2_latency.l2_cycles_waiting_on_fills", + "EventCode": "0x62", + "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.", + "UMask": "0x1" + }, + { + "EventName": "l2_wcb_req.wcb_write", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB write requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.", + "UMask": "0x40" + }, + { + "EventName": "l2_wcb_req.wcb_close", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB close requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.", + "UMask": "0x20" + }, + { + "EventName": "l2_wcb_req.zero_byte_store", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB zero byte store requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.", + "UMask": "0x4" + }, + { + "EventName": "l2_wcb_req.cl_zero", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB cache line zeroing requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.", + "UMask": "0x1" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_cs", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache shared read hit in L2", + "UMask": "0x80" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache read hit in L2.", + "UMask": "0x40" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache read hit on shared line in L2.", + "UMask": "0x20" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_x", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache store or state change hit in L2.", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_c", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache request miss in L2 (all types).", + "UMask": "0x8" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_hit_x", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache hit modifiable line in L2.", + "UMask": "0x4" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_hit_s", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache hit clean line in L2.", + "UMask": "0x2" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_miss", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2.", + "UMask": "0x1" + }, + { + "EventName": "l2_fill_pending.l2_fill_busy", + "EventCode": "0x6d", + "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.", + "UMask": "0x1" + }, + { + "EventName": "l3_request_g1.caching_l3_cache_accesses", + "EventCode": "0x01", + "BriefDescription": "Caching: L3 cache accesses", + "UMask": "0x80", + "Unit": "L3PMC" + }, + { + "EventName": "l3_lookup_state.all_l3_req_typs", + "EventCode": "0x04", + "BriefDescription": "All L3 Request Types", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_comb_clstr_state.other_l3_miss_typs", + "EventCode": "0x06", + "BriefDescription": "Other L3 Miss Request Types", + "UMask": "0xfe", + "Unit": "L3PMC" + }, + { + "EventName": "l3_comb_clstr_state.request_miss", + "EventCode": "0x06", + "BriefDescription": "L3 cache misses", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "EventName": "xi_sys_fill_latency", + "EventCode": "0x90", + "BriefDescription": "L3 Cache Miss Latency. Total cycles for all transactions divided by 16. Ignores SliceMask and ThreadMask.", + "UMask": "0x00", + "Unit": "L3PMC" + }, + { + "EventName": "xi_ccx_sdp_req1.all_l3_miss_req_typs", + "EventCode": "0x9a", + "BriefDescription": "All L3 Miss Request Types. Ignores SliceMask and ThreadMask.", + "UMask": "0x3f", + "Unit": "L3PMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/core.json b/tools/perf/pmu-events/arch/x86/amdzen1/core.json index 1079544eeed5..7e1aa8273935 100644 --- a/tools/perf/pmu-events/arch/x86/amdfam17h/core.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/core.json @@ -62,7 +62,6 @@ "EventName": "ex_ret_brn_ind_misp", "EventCode": "0xca", "BriefDescription": "Retired Indirect Branch Instructions Mispredicted.", - "PublicDescription": "Retired Indirect Branch Instructions Mispredicted." }, { "EventName": "ex_ret_mmx_fp_instr.sse_instr", @@ -91,11 +90,6 @@ "BriefDescription": "Retired Conditional Branch Instructions." }, { - "EventName": "ex_ret_cond_misp", - "EventCode": "0xd2", - "BriefDescription": "Retired Conditional Branch Instructions Mispredicted." - }, - { "EventName": "ex_div_busy", "EventCode": "0xd3", "BriefDescription": "Div Cycles Busy count." @@ -108,22 +102,19 @@ { "EventName": "ex_tagged_ibs_ops.ibs_count_rollover", "EventCode": "0x1cf", - "BriefDescription": "Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.", - "PublicDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.", + "BriefDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.", "UMask": "0x4" }, { "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops_ret", "EventCode": "0x1cf", - "BriefDescription": "Number of Ops tagged by IBS that retired.", - "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.", + "BriefDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.", "UMask": "0x2" }, { "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops", "EventCode": "0x1cf", - "BriefDescription": "Number of Ops tagged by IBS.", - "PublicDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.", + "BriefDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.", "UMask": "0x1" }, { diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json b/tools/perf/pmu-events/arch/x86/amdzen1/floating-point.json index ea4711983d1d..a35542bd3b36 100644 --- a/tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/floating-point.json @@ -2,18 +2,74 @@ { "EventName": "fpu_pipe_assignment.dual", "EventCode": "0x00", - "BriefDescription": "Total number multi-pipe uOps.", - "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to Pipe 3.", + "BriefDescription": "Total number multi-pipe uOps assigned to all pipes.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to all pipes.", "UMask": "0xf0" }, { + "EventName": "fpu_pipe_assignment.dual3", + "EventCode": "0x00", + "BriefDescription": "Total number multi-pipe uOps assigned to pipe 3.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to pipe 3.", + "UMask": "0x80" + }, + { + "EventName": "fpu_pipe_assignment.dual2", + "EventCode": "0x00", + "BriefDescription": "Total number multi-pipe uOps assigned to pipe 2.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to pipe 2.", + "UMask": "0x40" + }, + { + "EventName": "fpu_pipe_assignment.dual1", + "EventCode": "0x00", + "BriefDescription": "Total number multi-pipe uOps assigned to pipe 1.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to pipe 1.", + "UMask": "0x20" + }, + { + "EventName": "fpu_pipe_assignment.dual0", + "EventCode": "0x00", + "BriefDescription": "Total number multi-pipe uOps assigned to pipe 0.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number multi-pipe uOps assigned to pipe 0.", + "UMask": "0x10" + }, + { "EventName": "fpu_pipe_assignment.total", "EventCode": "0x00", - "BriefDescription": "Total number uOps.", - "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to Pipe 3.", + "BriefDescription": "Total number uOps assigned to all fpu pipes.", + "PublicDescription": "The number of operations (uOps) and dual-pipe uOps dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to all pipes.", "UMask": "0xf" }, { + "EventName": "fpu_pipe_assignment.total3", + "EventCode": "0x00", + "BriefDescription": "Total number of fp uOps on pipe 3.", + "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one-cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 3.", + "UMask": "0x8" + }, + { + "EventName": "fpu_pipe_assignment.total2", + "EventCode": "0x00", + "BriefDescription": "Total number of fp uOps on pipe 2.", + "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 2.", + "UMask": "0x4" + }, + { + "EventName": "fpu_pipe_assignment.total1", + "EventCode": "0x00", + "BriefDescription": "Total number of fp uOps on pipe 1.", + "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 1.", + "UMask": "0x2" + }, + { + "EventName": "fpu_pipe_assignment.total0", + "EventCode": "0x00", + "BriefDescription": "Total number of fp uOps on pipe 0.", + "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 0.", + "UMask": "0x1" + }, + { "EventName": "fp_sched_empty", "EventCode": "0x01", "BriefDescription": "This is a speculative event. The number of cycles in which the FPU scheduler is empty. Note that some Ops like FP loads bypass the scheduler." diff --git a/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json b/tools/perf/pmu-events/arch/x86/amdzen1/memory.json index fa2d60d4def0..b33a3c308019 100644 --- a/tools/perf/pmu-events/arch/x86/amdfam17h/memory.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/memory.json @@ -3,28 +3,24 @@ "EventName": "ls_locks.bus_lock", "EventCode": "0x25", "BriefDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.", - "PublicDescription": "Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type.", "UMask": "0x1" }, { "EventName": "ls_dispatch.ld_st_dispatch", "EventCode": "0x29", - "BriefDescription": "Load-op-Stores.", - "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed. Load-op-Stores.", + "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed. Load-op-Stores.", "UMask": "0x4" }, { "EventName": "ls_dispatch.store_dispatch", "EventCode": "0x29", - "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", - "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "BriefDescription": "Counts the number of stores dispatched to the LS unit. Unit Masks ADDed.", "UMask": "0x2" }, { "EventName": "ls_dispatch.ld_dispatch", "EventCode": "0x29", - "BriefDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", - "PublicDescription": "Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "BriefDescription": "Counts the number of loads dispatched to the LS unit. Unit Masks ADDed.", "UMask": "0x1" }, { @@ -38,83 +34,114 @@ "BriefDescription": "The number of accesses to the data cache for load and store references. This may include certain microcode scratchpad accesses, although these are generally rare. Each increment represents an eight-byte access, although the instruction may only be accessing a portion of that. This event is a speculative event." }, { + "EventName": "ls_mab_alloc.dc_prefetcher", + "EventCode": "0x41", + "BriefDescription": "LS MAB allocates by type - DC prefetcher.", + "UMask": "0x8" + }, + { + "EventName": "ls_mab_alloc.stores", + "EventCode": "0x41", + "BriefDescription": "LS MAB allocates by type - stores.", + "UMask": "0x2" + }, + { + "EventName": "ls_mab_alloc.loads", + "EventCode": "0x41", + "BriefDescription": "LS MAB allocates by type - loads.", + "UMask": "0x01" + }, + { "EventName": "ls_l1_d_tlb_miss.all", "EventCode": "0x45", "BriefDescription": "L1 DTLB Miss or Reload off all sizes.", - "PublicDescription": "L1 DTLB Miss or Reload off all sizes.", "UMask": "0xff" }, { "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_miss", "EventCode": "0x45", "BriefDescription": "L1 DTLB Miss of a page of 1G size.", - "PublicDescription": "L1 DTLB Miss of a page of 1G size.", "UMask": "0x80" }, { "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_miss", "EventCode": "0x45", "BriefDescription": "L1 DTLB Miss of a page of 2M size.", - "PublicDescription": "L1 DTLB Miss of a page of 2M size.", "UMask": "0x40" }, { "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_miss", "EventCode": "0x45", "BriefDescription": "L1 DTLB Miss of a page of 32K size.", - "PublicDescription": "L1 DTLB Miss of a page of 32K size.", "UMask": "0x20" }, { "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_miss", "EventCode": "0x45", "BriefDescription": "L1 DTLB Miss of a page of 4K size.", - "PublicDescription": "L1 DTLB Miss of a page of 4K size.", "UMask": "0x10" }, { "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_hit", "EventCode": "0x45", "BriefDescription": "L1 DTLB Reload of a page of 1G size.", - "PublicDescription": "L1 DTLB Reload of a page of 1G size.", "UMask": "0x8" }, { "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_hit", "EventCode": "0x45", "BriefDescription": "L1 DTLB Reload of a page of 2M size.", - "PublicDescription": "L1 DTLB Reload of a page of 2M size.", "UMask": "0x4" }, { "EventName": "ls_l1_d_tlb_miss.tlb_reload_32k_l2_hit", "EventCode": "0x45", "BriefDescription": "L1 DTLB Reload of a page of 32K size.", - "PublicDescription": "L1 DTLB Reload of a page of 32K size.", "UMask": "0x2" }, { "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_hit", "EventCode": "0x45", "BriefDescription": "L1 DTLB Reload of a page of 4K size.", - "PublicDescription": "L1 DTLB Reload of a page of 4K size.", "UMask": "0x1" }, { - "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_iside", + "EventName": "ls_tablewalker.iside", "EventCode": "0x46", - "BriefDescription": "Tablewalker allocation.", - "PublicDescription": "Tablewalker allocation.", + "BriefDescription": "Total Page Table Walks on I-side.", "UMask": "0xc" }, { - "EventName": "ls_tablewalker.perf_mon_tablewalk_alloc_dside", + "EventName": "ls_tablewalker.ic_type1", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks IC Type 1.", + "UMask": "0x8" + }, + { + "EventName": "ls_tablewalker.ic_type0", "EventCode": "0x46", - "BriefDescription": "Tablewalker allocation.", - "PublicDescription": "Tablewalker allocation.", + "BriefDescription": "Total Page Table Walks IC Type 0.", + "UMask": "0x4" + }, + { + "EventName": "ls_tablewalker.dside", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks on D-side.", "UMask": "0x3" }, { + "EventName": "ls_tablewalker.dc_type1", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks DC Type 1.", + "UMask": "0x2" + }, + { + "EventName": "ls_tablewalker.dc_type0", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks DC Type 0.", + "UMask": "0x1" + }, + { "EventName": "ls_misal_accesses", "EventCode": "0x47", "BriefDescription": "Misaligned loads." @@ -123,35 +150,30 @@ "EventName": "ls_pref_instr_disp.prefetch_nta", "EventCode": "0x4b", "BriefDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.", - "PublicDescription": "Software Prefetch Instructions (PREFETCHNTA instruction) Dispatched.", "UMask": "0x4" }, { "EventName": "ls_pref_instr_disp.store_prefetch_w", "EventCode": "0x4b", "BriefDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.", - "PublicDescription": "Software Prefetch Instructions (3DNow PREFETCHW instruction) Dispatched.", "UMask": "0x2" }, { "EventName": "ls_pref_instr_disp.load_prefetch_w", "EventCode": "0x4b", - "BriefDescription": "Prefetch, Prefetch_T0_T1_T2.", - "PublicDescription": "Software Prefetch Instructions Dispatched. Prefetch, Prefetch_T0_T1_T2.", + "BriefDescription": "Software Prefetch Instructions Dispatched. Prefetch, Prefetch_T0_T1_T2.", "UMask": "0x1" }, { "EventName": "ls_inef_sw_pref.mab_mch_cnt", "EventCode": "0x52", - "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.", - "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core. Software PREFETCH instruction saw a match on an already-allocated miss request buffer.", "UMask": "0x2" }, { "EventName": "ls_inef_sw_pref.data_pipe_sw_pf_dc_hit", "EventCode": "0x52", - "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core.", - "PublicDescription": "The number of software prefetches that did not fetch data outside of the processor core.", + "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core. Software PREFETCH instruction saw a DC hit.", "UMask": "0x1" }, { diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/other.json b/tools/perf/pmu-events/arch/x86/amdzen1/other.json new file mode 100644 index 000000000000..ff780098d36e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen1/other.json @@ -0,0 +1,56 @@ +[ + { + "EventName": "ic_oc_mode_switch.oc_ic_mode_switch", + "EventCode": "0x28a", + "BriefDescription": "OC Mode Switch. OC to IC mode switch.", + "UMask": "0x2" + }, + { + "EventName": "ic_oc_mode_switch.ic_oc_mode_switch", + "EventCode": "0x28a", + "BriefDescription": "OC Mode Switch. IC to OC mode switch.", + "UMask": "0x1" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.", + "UMask": "0x40" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.", + "UMask": "0x20" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.", + "UMask": "0x10" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3_0 Tokens unavailable.", + "UMask": "0x8" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq3_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 3 Tokens unavailable.", + "UMask": "0x4" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.", + "UMask": "0x2" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/branch.json b/tools/perf/pmu-events/arch/x86/amdzen2/branch.json new file mode 100644 index 000000000000..ef4166a66288 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/branch.json @@ -0,0 +1,52 @@ +[ + { + "EventName": "bp_l1_btb_correct", + "EventCode": "0x8a", + "BriefDescription": "L1 Branch Prediction Overrides Existing Prediction (speculative)." + }, + { + "EventName": "bp_l2_btb_correct", + "EventCode": "0x8b", + "BriefDescription": "L2 Branch Prediction Overrides Existing Prediction (speculative)." + }, + { + "EventName": "bp_dyn_ind_pred", + "EventCode": "0x8e", + "BriefDescription": "Dynamic Indirect Predictions.", + "PublicDescription": "Indirect Branch Prediction for potential multi-target branch (speculative)." + }, + { + "EventName": "bp_de_redirect", + "EventCode": "0x91", + "BriefDescription": "Decoder Overrides Existing Branch Prediction (speculative)." + }, + { + "EventName": "bp_l1_tlb_fetch_hit", + "EventCode": "0x94", + "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB.", + "UMask": "0xFF" + }, + { + "EventName": "bp_l1_tlb_fetch_hit.if1g", + "EventCode": "0x94", + "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB. Instruction fetches to a 1GB page.", + "UMask": "0x4" + }, + { + "EventName": "bp_l1_tlb_fetch_hit.if2m", + "EventCode": "0x94", + "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB. Instruction fetches to a 2MB page.", + "UMask": "0x2" + }, + { + "EventName": "bp_l1_tlb_fetch_hit.if4k", + "EventCode": "0x94", + "BriefDescription": "The number of instruction fetches that hit in the L1 ITLB. Instruction fetches to a 4KB page.", + "UMask": "0x1" + }, + { + "EventName": "bp_tlb_rel", + "EventCode": "0x99", + "BriefDescription": "The number of ITLB reload requests." + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/cache.json b/tools/perf/pmu-events/arch/x86/amdzen2/cache.json new file mode 100644 index 000000000000..1c60bfa0f00b --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/cache.json @@ -0,0 +1,338 @@ +[ + { + "EventName": "l2_request_g1.rd_blk_l", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache reads (including hardware and software prefetch).", + "UMask": "0x80" + }, + { + "EventName": "l2_request_g1.rd_blk_x", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache stores.", + "UMask": "0x40" + }, + { + "EventName": "l2_request_g1.ls_rd_blk_c_s", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache shared reads.", + "UMask": "0x20" + }, + { + "EventName": "l2_request_g1.cacheable_ic_read", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Instruction cache reads.", + "UMask": "0x10" + }, + { + "EventName": "l2_request_g1.change_to_x", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). Data cache state change requests. Request change to writable, check L2 for current state.", + "UMask": "0x8" + }, + { + "EventName": "l2_request_g1.prefetch_l2_cmd", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). PrefetchL2Cmd.", + "UMask": "0x4" + }, + { + "EventName": "l2_request_g1.l2_hw_pf", + "EventCode": "0x60", + "BriefDescription": "All L2 Cache Requests (Breakdown 1 - Common). L2 Prefetcher. All prefetches accepted by L2 pipeline, hit or miss. Types of PF and L2 hit/miss broken out in a separate perfmon event.", + "UMask": "0x2" + }, + { + "EventName": "l2_request_g1.group2", + "EventCode": "0x60", + "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g2 (PMCx061).", + "UMask": "0x1" + }, + { + "EventName": "l2_request_g2.group1", + "EventCode": "0x61", + "BriefDescription": "Miscellaneous events covered in more detail by l2_request_g1 (PMCx060).", + "UMask": "0x80" + }, + { + "EventName": "l2_request_g2.ls_rd_sized", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Data cache read sized.", + "UMask": "0x40" + }, + { + "EventName": "l2_request_g2.ls_rd_sized_nc", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Data cache read sized non-cacheable.", + "UMask": "0x20" + }, + { + "EventName": "l2_request_g2.ic_rd_sized", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Instruction cache read sized.", + "UMask": "0x10" + }, + { + "EventName": "l2_request_g2.ic_rd_sized_nc", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Instruction cache read sized non-cacheable.", + "UMask": "0x8" + }, + { + "EventName": "l2_request_g2.smc_inval", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Self-modifying code invalidates.", + "UMask": "0x4" + }, + { + "EventName": "l2_request_g2.bus_locks_originator", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Bus locks.", + "UMask": "0x2" + }, + { + "EventName": "l2_request_g2.bus_locks_responses", + "EventCode": "0x61", + "BriefDescription": "All L2 Cache Requests (Breakdown 2 - Rare). Bus lock response.", + "UMask": "0x1" + }, + { + "EventName": "l2_latency.l2_cycles_waiting_on_fills", + "EventCode": "0x62", + "BriefDescription": "Total cycles spent waiting for L2 fills to complete from L3 or memory, divided by four. Event counts are for both threads. To calculate average latency, the number of fills from both threads must be used.", + "UMask": "0x1" + }, + { + "EventName": "l2_wcb_req.wcb_write", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB write requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) write requests.", + "UMask": "0x40" + }, + { + "EventName": "l2_wcb_req.wcb_close", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB close requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) close requests.", + "UMask": "0x20" + }, + { + "EventName": "l2_wcb_req.zero_byte_store", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB zero byte store requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) zero byte store requests.", + "UMask": "0x4" + }, + { + "EventName": "l2_wcb_req.cl_zero", + "EventCode": "0x63", + "BriefDescription": "LS to L2 WCB cache line zeroing requests. LS (Load/Store unit) to L2 WCB (Write Combining Buffer) cache line zeroing requests.", + "UMask": "0x1" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_cs", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache shared read hit in L2", + "UMask": "0x80" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_x", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache read hit in L2.", + "UMask": "0x40" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_l_hit_s", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache read hit on shared line in L2.", + "UMask": "0x20" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_x", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache store or state change hit in L2.", + "UMask": "0x10" + }, + { + "EventName": "l2_cache_req_stat.ls_rd_blk_c", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Data cache request miss in L2 (all types).", + "UMask": "0x8" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_hit_x", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache hit modifiable line in L2.", + "UMask": "0x4" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_hit_s", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache hit clean line in L2.", + "UMask": "0x2" + }, + { + "EventName": "l2_cache_req_stat.ic_fill_miss", + "EventCode": "0x64", + "BriefDescription": "Core to L2 cacheable request access status (not including L2 Prefetch). Instruction cache request miss in L2.", + "UMask": "0x1" + }, + { + "EventName": "l2_fill_pending.l2_fill_busy", + "EventCode": "0x6d", + "BriefDescription": "Cycles with fill pending from L2. Total cycles spent with one or more fill requests in flight from L2.", + "UMask": "0x1" + }, + { + "EventName": "l2_pf_hit_l2", + "EventCode": "0x70", + "BriefDescription": "L2 prefetch hit in L2.", + "UMask": "0xff" + }, + { + "EventName": "l2_pf_miss_l2_hit_l3", + "EventCode": "0x71", + "BriefDescription": "L2 prefetcher hits in L3. Counts all L2 prefetches accepted by the L2 pipeline which miss the L2 cache and hit the L3.", + "UMask": "0xff" + }, + { + "EventName": "l2_pf_miss_l2_l3", + "EventCode": "0x72", + "BriefDescription": "L2 prefetcher misses in L3. All L2 prefetches accepted by the L2 pipeline which miss the L2 and the L3 caches.", + "UMask": "0xff" + }, + { + "EventName": "ic_fw32", + "EventCode": "0x80", + "BriefDescription": "The number of 32B fetch windows transferred from IC pipe to DE instruction decoder (includes non-cacheable and cacheable fill responses)." + }, + { + "EventName": "ic_fw32_miss", + "EventCode": "0x81", + "BriefDescription": "The number of 32B fetch windows tried to read the L1 IC and missed in the full tag." + }, + { + "EventName": "ic_cache_fill_l2", + "EventCode": "0x82", + "BriefDescription": "The number of 64 byte instruction cache line was fulfilled from the L2 cache." + }, + { + "EventName": "ic_cache_fill_sys", + "EventCode": "0x83", + "BriefDescription": "The number of 64 byte instruction cache line fulfilled from system memory or another cache." + }, + { + "EventName": "bp_l1_tlb_miss_l2_hit", + "EventCode": "0x84", + "BriefDescription": "The number of instruction fetches that miss in the L1 ITLB but hit in the L2 ITLB." + }, + { + "EventName": "bp_l1_tlb_miss_l2_tlb_miss", + "EventCode": "0x85", + "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs.", + "UMask": "0xff" + }, + { + "EventName": "bp_l1_tlb_miss_l2_tlb_miss.if1g", + "EventCode": "0x85", + "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs. Instruction fetches to a 1GB page.", + "UMask": "0x4" + }, + { + "EventName": "bp_l1_tlb_miss_l2_tlb_miss.if2m", + "EventCode": "0x85", + "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs. Instruction fetches to a 2MB page.", + "UMask": "0x2" + }, + { + "EventName": "bp_l1_tlb_miss_l2_tlb_miss.if4k", + "EventCode": "0x85", + "BriefDescription": "The number of instruction fetches that miss in both the L1 and L2 TLBs. Instruction fetches to a 4KB page.", + "UMask": "0x1" + }, + { + "EventName": "bp_snp_re_sync", + "EventCode": "0x86", + "BriefDescription": "The number of pipeline restarts caused by invalidating probes that hit on the instruction stream currently being executed. This would happen if the active instruction stream was being modified by another processor in an MP system - typically a highly unlikely event." + }, + { + "EventName": "ic_fetch_stall.ic_stall_any", + "EventCode": "0x87", + "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle for any reason (nothing valid in pipe ICM1).", + "UMask": "0x4" + }, + { + "EventName": "ic_fetch_stall.ic_stall_dq_empty", + "EventCode": "0x87", + "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to DQ empty.", + "UMask": "0x2" + }, + { + "EventName": "ic_fetch_stall.ic_stall_back_pressure", + "EventCode": "0x87", + "BriefDescription": "Instruction Pipe Stall. IC pipe was stalled during this clock cycle (including IC to OC fetches) due to back-pressure.", + "UMask": "0x1" + }, + { + "EventName": "ic_cache_inval.l2_invalidating_probe", + "EventCode": "0x8c", + "BriefDescription": "IC line invalidated due to L2 invalidating probe (external or LS). The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core.", + "UMask": "0x2" + }, + { + "EventName": "ic_cache_inval.fill_invalidated", + "EventCode": "0x8c", + "BriefDescription": "IC line invalidated due to overwriting fill response. The number of instruction cache lines invalidated. A non-SMC event is CMC (cross modifying code), either from the other thread of the core or another core.", + "UMask": "0x1" + }, + { + "EventName": "ic_oc_mode_switch.oc_ic_mode_switch", + "EventCode": "0x28a", + "BriefDescription": "OC Mode Switch. OC to IC mode switch.", + "UMask": "0x2" + }, + { + "EventName": "ic_oc_mode_switch.ic_oc_mode_switch", + "EventCode": "0x28a", + "BriefDescription": "OC Mode Switch. IC to OC mode switch.", + "UMask": "0x1" + }, + { + "EventName": "l3_request_g1.caching_l3_cache_accesses", + "EventCode": "0x01", + "BriefDescription": "Caching: L3 cache accesses", + "UMask": "0x80", + "Unit": "L3PMC" + }, + { + "EventName": "l3_lookup_state.all_l3_req_typs", + "EventCode": "0x04", + "BriefDescription": "All L3 Request Types", + "UMask": "0xff", + "Unit": "L3PMC" + }, + { + "EventName": "l3_comb_clstr_state.other_l3_miss_typs", + "EventCode": "0x06", + "BriefDescription": "Other L3 Miss Request Types", + "UMask": "0xfe", + "Unit": "L3PMC" + }, + { + "EventName": "l3_comb_clstr_state.request_miss", + "EventCode": "0x06", + "BriefDescription": "L3 cache misses", + "UMask": "0x01", + "Unit": "L3PMC" + }, + { + "EventName": "xi_sys_fill_latency", + "EventCode": "0x90", + "BriefDescription": "L3 Cache Miss Latency. Total cycles for all transactions divided by 16. Ignores SliceMask and ThreadMask.", + "UMask": "0x00", + "Unit": "L3PMC" + }, + { + "EventName": "xi_ccx_sdp_req1.all_l3_miss_req_typs", + "EventCode": "0x9A", + "BriefDescription": "All L3 Miss Request Types. Ignores SliceMask and ThreadMask.", + "UMask": "0x3f", + "Unit": "L3PMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/core.json b/tools/perf/pmu-events/arch/x86/amdzen2/core.json new file mode 100644 index 000000000000..de89e5a44ff1 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/core.json @@ -0,0 +1,130 @@ +[ + { + "EventName": "ex_ret_instr", + "EventCode": "0xc0", + "BriefDescription": "Retired Instructions." + }, + { + "EventName": "ex_ret_cops", + "EventCode": "0xc1", + "BriefDescription": "Retired Uops.", + "PublicDescription": "The number of micro-ops retired. This count includes all processor activity (instructions, exceptions, interrupts, microcode assists, etc.). The number of events logged per cycle can vary from 0 to 8." + }, + { + "EventName": "ex_ret_brn", + "EventCode": "0xc2", + "BriefDescription": "Retired Branch Instructions.", + "PublicDescription": "The number of branch instructions retired. This includes all types of architectural control flow changes, including exceptions and interrupts." + }, + { + "EventName": "ex_ret_brn_misp", + "EventCode": "0xc3", + "BriefDescription": "Retired Branch Instructions Mispredicted.", + "PublicDescription": "The number of branch instructions retired, of any type, that were not correctly predicted. This includes those for which prediction is not attempted (far control transfers, exceptions and interrupts)." + }, + { + "EventName": "ex_ret_brn_tkn", + "EventCode": "0xc4", + "BriefDescription": "Retired Taken Branch Instructions.", + "PublicDescription": "The number of taken branches that were retired. This includes all types of architectural control flow changes, including exceptions and interrupts." + }, + { + "EventName": "ex_ret_brn_tkn_misp", + "EventCode": "0xc5", + "BriefDescription": "Retired Taken Branch Instructions Mispredicted.", + "PublicDescription": "The number of retired taken branch instructions that were mispredicted." + }, + { + "EventName": "ex_ret_brn_far", + "EventCode": "0xc6", + "BriefDescription": "Retired Far Control Transfers.", + "PublicDescription": "The number of far control transfers retired including far call/jump/return, IRET, SYSCALL and SYSRET, plus exceptions and interrupts. Far control transfers are not subject to branch prediction." + }, + { + "EventName": "ex_ret_brn_resync", + "EventCode": "0xc7", + "BriefDescription": "Retired Branch Resyncs.", + "PublicDescription": "The number of resync branches. These reflect pipeline restarts due to certain microcode assists and events such as writes to the active instruction stream, among other things. Each occurrence reflects a restart penalty similar to a branch mispredict. This is relatively rare." + }, + { + "EventName": "ex_ret_near_ret", + "EventCode": "0xc8", + "BriefDescription": "Retired Near Returns.", + "PublicDescription": "The number of near return instructions (RET or RET Iw) retired." + }, + { + "EventName": "ex_ret_near_ret_mispred", + "EventCode": "0xc9", + "BriefDescription": "Retired Near Returns Mispredicted.", + "PublicDescription": "The number of near returns retired that were not correctly predicted by the return address predictor. Each such mispredict incurs the same penalty as a mispredicted conditional branch instruction." + }, + { + "EventName": "ex_ret_brn_ind_misp", + "EventCode": "0xca", + "BriefDescription": "Retired Indirect Branch Instructions Mispredicted." + }, + { + "EventName": "ex_ret_mmx_fp_instr.sse_instr", + "EventCode": "0xcb", + "BriefDescription": "SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. SSE instructions (SSE, SSE2, SSE3, SSSE3, SSE4A, SSE41, SSE42, AVX).", + "UMask": "0x4" + }, + { + "EventName": "ex_ret_mmx_fp_instr.mmx_instr", + "EventCode": "0xcb", + "BriefDescription": "MMX instructions.", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. MMX instructions.", + "UMask": "0x2" + }, + { + "EventName": "ex_ret_mmx_fp_instr.x87_instr", + "EventCode": "0xcb", + "BriefDescription": "x87 instructions.", + "PublicDescription": "The number of MMX, SSE or x87 instructions retired. The UnitMask allows the selection of the individual classes of instructions as given in the table. Each increment represents one complete instruction. Since this event includes non-numeric instructions it is not suitable for measuring MFLOPS. x87 instructions.", + "UMask": "0x1" + }, + { + "EventName": "ex_ret_cond", + "EventCode": "0xd1", + "BriefDescription": "Retired Conditional Branch Instructions." + }, + { + "EventName": "ex_ret_cond_misp", + "EventCode": "0xd2", + "BriefDescription": "Retired Conditional Branch Instructions Mispredicted." + }, + { + "EventName": "ex_div_busy", + "EventCode": "0xd3", + "BriefDescription": "Div Cycles Busy count." + }, + { + "EventName": "ex_div_count", + "EventCode": "0xd4", + "BriefDescription": "Div Op Count." + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_count_rollover", + "EventCode": "0x1cf", + "BriefDescription": "Tagged IBS Ops. Number of times an op could not be tagged by IBS because of a previous tagged op that has not retired.", + "UMask": "0x4" + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops_ret", + "EventCode": "0x1cf", + "BriefDescription": "Tagged IBS Ops. Number of Ops tagged by IBS that retired.", + "UMask": "0x2" + }, + { + "EventName": "ex_tagged_ibs_ops.ibs_tagged_ops", + "EventCode": "0x1cf", + "BriefDescription": "Tagged IBS Ops. Number of Ops tagged by IBS.", + "UMask": "0x1" + }, + { + "EventName": "ex_ret_fus_brnch_inst", + "EventCode": "0x1d0", + "BriefDescription": "Retired Fused Instructions. The number of fuse-branch instructions retired per cycle. The number of events logged per cycle can vary from 0-8.", + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/floating-point.json b/tools/perf/pmu-events/arch/x86/amdzen2/floating-point.json new file mode 100644 index 000000000000..622a0c420e46 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/floating-point.json @@ -0,0 +1,140 @@ +[ + { + "EventName": "fpu_pipe_assignment.total", + "EventCode": "0x00", + "BriefDescription": "Total number of fp uOps.", + "PublicDescription": "Total number of fp uOps. The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS.", + "UMask": "0xf" + }, + { + "EventName": "fpu_pipe_assignment.total3", + "EventCode": "0x00", + "BriefDescription": "Total number uOps assigned to pipe 3.", + "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one-cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 3.", + "UMask": "0x8" + }, + { + "EventName": "fpu_pipe_assignment.total2", + "EventCode": "0x00", + "BriefDescription": "Total number uOps assigned to pipe 2.", + "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 2.", + "UMask": "0x4" + }, + { + "EventName": "fpu_pipe_assignment.total1", + "EventCode": "0x00", + "BriefDescription": "Total number uOps assigned to pipe 1.", + "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 1.", + "UMask": "0x2" + }, + { + "EventName": "fpu_pipe_assignment.total0", + "EventCode": "0x00", + "BriefDescription": "Total number of fp uOps on pipe 0.", + "PublicDescription": "The number of operations (uOps) dispatched to each of the 4 FPU execution pipelines. This event reflects how busy the FPU pipelines are and may be used for workload characterization. This includes all operations performed by x87, MMX, and SSE instructions, including moves. Each increment represents a one- cycle dispatch event. This event is a speculative event. Since this event includes non-numeric operations it is not suitable for measuring MFLOPS. Total number uOps assigned to pipe 0.", + "UMask": "0x1" + }, + { + "EventName": "fp_ret_sse_avx_ops.all", + "EventCode": "0x03", + "BriefDescription": "All FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.", + "UMask": "0xff" + }, + { + "EventName": "fp_ret_sse_avx_ops.mac_flops", + "EventCode": "0x03", + "BriefDescription": "Multiply-add FLOPS. Multiply-add counts as 2 FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.", + "PublicDescription": "", + "UMask": "0x8" + }, + { + "EventName": "fp_ret_sse_avx_ops.div_flops", + "EventCode": "0x03", + "BriefDescription": "Divide/square root FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.", + "UMask": "0x4" + }, + { + "EventName": "fp_ret_sse_avx_ops.mult_flops", + "EventCode": "0x03", + "BriefDescription": "Multiply FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.", + "UMask": "0x2" + }, + { + "EventName": "fp_ret_sse_avx_ops.add_sub_flops", + "EventCode": "0x03", + "BriefDescription": "Add/subtract FLOPS. This is a retire-based event. The number of retired SSE/AVX FLOPS. The number of events logged per cycle can vary from 0 to 64. This event can count above 15.", + "UMask": "0x1" + }, + { + "EventName": "fp_num_mov_elim_scal_op.optimized", + "EventCode": "0x04", + "BriefDescription": "Number of Scalar Ops optimized. This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.", + "UMask": "0x8" + }, + { + "EventName": "fp_num_mov_elim_scal_op.opt_potential", + "EventCode": "0x04", + "BriefDescription": "Number of Ops that are candidates for optimization (have Z-bit either set or pass). This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.", + "UMask": "0x4" + }, + { + "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops_elim", + "EventCode": "0x04", + "BriefDescription": "Number of SSE Move Ops eliminated. This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.", + "UMask": "0x2" + }, + { + "EventName": "fp_num_mov_elim_scal_op.sse_mov_ops", + "EventCode": "0x04", + "BriefDescription": "Number of SSE Move Ops. This is a dispatch based speculative event, and is useful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.", + "UMask": "0x1" + }, + { + "EventName": "fp_retired_ser_ops.sse_bot_ret", + "EventCode": "0x05", + "BriefDescription": "SSE bottom-executing uOps retired. The number of serializing Ops retired.", + "UMask": "0x8" + }, + { + "EventName": "fp_retired_ser_ops.sse_ctrl_ret", + "EventCode": "0x05", + "BriefDescription": "The number of serializing Ops retired. SSE control word mispredict traps due to mispredictions in RC, FTZ or DAZ, or changes in mask bits.", + "UMask": "0x4" + }, + { + "EventName": "fp_retired_ser_ops.x87_bot_ret", + "EventCode": "0x05", + "BriefDescription": "x87 bottom-executing uOps retired. The number of serializing Ops retired.", + "UMask": "0x2" + }, + { + "EventName": "fp_retired_ser_ops.x87_ctrl_ret", + "EventCode": "0x05", + "BriefDescription": "x87 control word mispredict traps due to mispredictions in RC or PC, or changes in mask bits. The number of serializing Ops retired.", + "UMask": "0x1" + }, + { + "EventName": "fp_disp_faults.ymm_spill_fault", + "EventCode": "0x0e", + "BriefDescription": "Floating Point Dispatch Faults. YMM spill fault.", + "UMask": "0x8" + }, + { + "EventName": "fp_disp_faults.ymm_fill_fault", + "EventCode": "0x0e", + "BriefDescription": "Floating Point Dispatch Faults. YMM fill fault.", + "UMask": "0x4" + }, + { + "EventName": "fp_disp_faults.xmm_fill_fault", + "EventCode": "0x0e", + "BriefDescription": "Floating Point Dispatch Faults. XMM fill fault.", + "UMask": "0x2" + }, + { + "EventName": "fp_disp_faults.x87_fill_fault", + "EventCode": "0x0e", + "BriefDescription": "Floating Point Dispatch Faults. x87 fill fault.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/memory.json b/tools/perf/pmu-events/arch/x86/amdzen2/memory.json new file mode 100644 index 000000000000..715046b339cb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/memory.json @@ -0,0 +1,341 @@ +[ + { + "EventName": "ls_bad_status2.stli_other", + "EventCode": "0x24", + "BriefDescription": "Non-forwardable conflict; used to reduce STLI's via software. All reasons. Store To Load Interlock (STLI) are loads that were unable to complete because of a possible match with an older store, and the older store could not do STLF for some reason.", + "PublicDescription" : "Store-to-load conflicts: A load was unable to complete due to a non-forwardable conflict with an older store. Most commonly, a load's address range partially but not completely overlaps with an uncompleted older store. Software can avoid this problem by using same-size and same-alignment loads and stores when accessing the same data. Vector/SIMD code is particularly susceptible to this problem; software should construct wide vector stores by manipulating vector elements in registers using shuffle/blend/swap instructions prior to storing to memory, instead of using narrow element-by-element stores.", + "UMask": "0x2" + }, + { + "EventName": "ls_locks.spec_lock_hi_spec", + "EventCode": "0x25", + "BriefDescription": "Retired lock instructions. High speculative cacheable lock speculation succeeded.", + "UMask": "0x8" + }, + { + "EventName": "ls_locks.spec_lock_lo_spec", + "EventCode": "0x25", + "BriefDescription": "Retired lock instructions. Low speculative cacheable lock speculation succeeded.", + "UMask": "0x4" + }, + { + "EventName": "ls_locks.non_spec_lock", + "EventCode": "0x25", + "BriefDescription": "Retired lock instructions. Non-speculative lock succeeded.", + "UMask": "0x2" + }, + { + "EventName": "ls_locks.bus_lock", + "EventCode": "0x25", + "BriefDescription": "Retired lock instructions. Bus lock when a locked operations crosses a cache boundary or is done on an uncacheable memory type. Comparable to legacy bus lock.", + "UMask": "0x1" + }, + { + "EventName": "ls_ret_cl_flush", + "EventCode": "0x26", + "BriefDescription": "Number of retired CLFLUSH instructions." + }, + { + "EventName": "ls_ret_cpuid", + "EventCode": "0x27", + "BriefDescription": "Number of retired CPUID instructions." + }, + { + "EventName": "ls_dispatch.ld_st_dispatch", + "EventCode": "0x29", + "BriefDescription": "Dispatch of a single op that performs a load from and store to the same memory address. Number of single ops that do load/store to an address.", + "UMask": "0x4" + }, + { + "EventName": "ls_dispatch.store_dispatch", + "EventCode": "0x29", + "BriefDescription": "Number of stores dispatched. Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "UMask": "0x2" + }, + { + "EventName": "ls_dispatch.ld_dispatch", + "EventCode": "0x29", + "BriefDescription": "Number of loads dispatched. Counts the number of operations dispatched to the LS unit. Unit Masks ADDed.", + "UMask": "0x1" + }, + { + "EventName": "ls_smi_rx", + "EventCode": "0x2B", + "BriefDescription": "Number of SMIs received." + }, + { + "EventName": "ls_int_taken", + "EventCode": "0x2C", + "BriefDescription": "Number of interrupts taken." + }, + { + "EventName": "ls_rdtsc", + "EventCode": "0x2D", + "BriefDescription": "Number of reads of the TSC (RDTSC instructions). The count is speculative." + }, + { + "EventName": "ls_stlf", + "EventCode": "0x35", + "BriefDescription": "Number of STLF hits." + }, + { + "EventName": "ls_st_commit_cancel2.st_commit_cancel_wcb_full", + "EventCode": "0x37", + "BriefDescription": "A non-cacheable store and the non-cacheable commit buffer is full." + }, + { + "EventName": "ls_dc_accesses", + "EventCode": "0x40", + "BriefDescription": "Number of accesses to the dcache for load/store references.", + "PublicDescription": "The number of accesses to the data cache for load and store references. This may include certain microcode scratchpad accesses, although these are generally rare. Each increment represents an eight-byte access, although the instruction may only be accessing a portion of that. This event is a speculative event." + }, + { + "EventName": "ls_mab_alloc.dc_prefetcher", + "EventCode": "0x41", + "BriefDescription": "LS MAB Allocates by Type. DC prefetcher.", + "UMask": "0x8" + }, + { + "EventName": "ls_mab_alloc.stores", + "EventCode": "0x41", + "BriefDescription": "LS MAB Allocates by Type. Stores.", + "UMask": "0x2" + }, + { + "EventName": "ls_mab_alloc.loads", + "EventCode": "0x41", + "BriefDescription": "LS MAB Allocates by Type. Loads.", + "UMask": "0x1" + }, + { + "EventName": "ls_refills_from_sys.ls_mabresp_rmt_dram", + "EventCode": "0x43", + "BriefDescription": "Demand Data Cache Fills by Data Source. DRAM or IO from different die.", + "UMask": "0x40" + }, + { + "EventName": "ls_refills_from_sys.ls_mabresp_rmt_cache", + "EventCode": "0x43", + "BriefDescription": "Demand Data Cache Fills by Data Source. Hit in cache; Remote CCX and the address's Home Node is on a different die.", + "UMask": "0x10" + }, + { + "EventName": "ls_refills_from_sys.ls_mabresp_lcl_dram", + "EventCode": "0x43", + "BriefDescription": "Demand Data Cache Fills by Data Source. DRAM or IO from this thread's die.", + "UMask": "0x8" + }, + { + "EventName": "ls_refills_from_sys.ls_mabresp_lcl_cache", + "EventCode": "0x43", + "BriefDescription": "Demand Data Cache Fills by Data Source. Hit in cache; local CCX (not Local L2), or Remote CCX and the address's Home Node is on this thread's die.", + "UMask": "0x2" + }, + { + "EventName": "ls_refills_from_sys.ls_mabresp_lcl_l2", + "EventCode": "0x43", + "BriefDescription": "Demand Data Cache Fills by Data Source. Local L2 hit.", + "UMask": "0x1" + }, + { + "EventName": "ls_l1_d_tlb_miss.all", + "EventCode": "0x45", + "BriefDescription": "All L1 DTLB Misses or Reloads.", + "UMask": "0xff" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss. DTLB reload to a 1G page that miss in the L2 TLB.", + "UMask": "0x80" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss. DTLB reload to a 2M page that miss in the L2 TLB.", + "UMask": "0x40" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_coalesced_page_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss. DTLB reload coalesced page miss.", + "UMask": "0x20" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_miss", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss. DTLB reload to a 4K page that miss the L2 TLB.", + "UMask": "0x10" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_1g_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss. DTLB reload to a 1G page that hit in the L2 TLB.", + "UMask": "0x8" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_2m_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss. DTLB reload to a 2M page that hit in the L2 TLB.", + "UMask": "0x4" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_coalesced_page_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss. DTLB reload hit a coalesced page.", + "UMask": "0x2" + }, + { + "EventName": "ls_l1_d_tlb_miss.tlb_reload_4k_l2_hit", + "EventCode": "0x45", + "BriefDescription": "L1 DTLB Miss. DTLB reload to a 4K page that hit in the L2 TLB.", + "UMask": "0x1" + }, + { + "EventName": "ls_tablewalker.iside", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks on I-side.", + "UMask": "0xc" + }, + { + "EventName": "ls_tablewalker.ic_type1", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks IC Type 1.", + "UMask": "0x8" + }, + { + "EventName": "ls_tablewalker.ic_type0", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks IC Type 0.", + "UMask": "0x4" + }, + { + "EventName": "ls_tablewalker.dside", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks on D-side.", + "UMask": "0x3" + }, + { + "EventName": "ls_tablewalker.dc_type1", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks DC Type 1.", + "UMask": "0x2" + }, + { + "EventName": "ls_tablewalker.dc_type0", + "EventCode": "0x46", + "BriefDescription": "Total Page Table Walks DC Type 0.", + "UMask": "0x1" + }, + { + "EventName": "ls_misal_accesses", + "EventCode": "0x47", + "BriefDescription": "Misaligned loads." + }, + { + "EventName": "ls_pref_instr_disp", + "EventCode": "0x4b", + "BriefDescription": "Software Prefetch Instructions Dispatched (Speculative).", + "UMask": "0xff" + }, + { + "EventName": "ls_pref_instr_disp.prefetch_nta", + "EventCode": "0x4b", + "BriefDescription": "Software Prefetch Instructions Dispatched (Speculative). PrefetchNTA instruction. See docAPM3 PREFETCHlevel.", + "UMask": "0x4" + }, + { + "EventName": "ls_pref_instr_disp.prefetch_w", + "EventCode": "0x4b", + "BriefDescription": "Software Prefetch Instructions Dispatched (Speculative). See docAPM3 PREFETCHW.", + "UMask": "0x2" + }, + { + "EventName": "ls_pref_instr_disp.prefetch", + "EventCode": "0x4b", + "BriefDescription": "Software Prefetch Instructions Dispatched (Speculative). Prefetch_T0_T1_T2. PrefetchT0, T1 and T2 instructions. See docAPM3 PREFETCHlevel.", + "UMask": "0x1" + }, + { + "EventName": "ls_inef_sw_pref.mab_mch_cnt", + "EventCode": "0x52", + "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core. Software PREFETCH instruction saw a match on an already-allocated miss request buffer.", + "UMask": "0x2" + }, + { + "EventName": "ls_inef_sw_pref.data_pipe_sw_pf_dc_hit", + "EventCode": "0x52", + "BriefDescription": "The number of software prefetches that did not fetch data outside of the processor core. Software PREFETCH instruction saw a DC hit.", + "UMask": "0x1" + }, + { + "EventName": "ls_sw_pf_dc_fill.ls_mabresp_rmt_dram", + "EventCode": "0x59", + "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. From DRAM (home node remote).", + "UMask": "0x40" + }, + { + "EventName": "ls_sw_pf_dc_fill.ls_mabresp_rmt_cache", + "EventCode": "0x59", + "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. From another cache (home node remote).", + "UMask": "0x10" + }, + { + "EventName": "ls_sw_pf_dc_fill.ls_mabresp_lcl_dram", + "EventCode": "0x59", + "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. DRAM or IO from this thread's die. From DRAM (home node local).", + "UMask": "0x8" + }, + { + "EventName": "ls_sw_pf_dc_fill.ls_mabresp_lcl_cache", + "EventCode": "0x59", + "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. From another cache (home node local).", + "UMask": "0x2" + }, + { + "EventName": "ls_sw_pf_dc_fill.ls_mabresp_lcl_l2", + "EventCode": "0x59", + "BriefDescription": "Software Prefetch Data Cache Fills by Data Source. Local L2 hit.", + "UMask": "0x1" + }, + { + "EventName": "ls_hw_pf_dc_fill.ls_mabresp_rmt_dram", + "EventCode": "0x5A", + "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. From DRAM (home node remote).", + "UMask": "0x40" + }, + { + "EventName": "ls_hw_pf_dc_fill.ls_mabresp_rmt_cache", + "EventCode": "0x5A", + "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. From another cache (home node remote).", + "UMask": "0x10" + }, + { + "EventName": "ls_hw_pf_dc_fill.ls_mabresp_lcl_dram", + "EventCode": "0x5A", + "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. From DRAM (home node local).", + "UMask": "0x8" + }, + { + "EventName": "ls_hw_pf_dc_fill.ls_mabresp_lcl_cache", + "EventCode": "0x5A", + "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. From another cache (home node local).", + "UMask": "0x2" + }, + { + "EventName": "ls_hw_pf_dc_fill.ls_mabresp_lcl_l2", + "EventCode": "0x5A", + "BriefDescription": "Hardware Prefetch Data Cache Fills by Data Source. Local L2 hit.", + "UMask": "0x1" + }, + { + "EventName": "ls_not_halted_cyc", + "EventCode": "0x76", + "BriefDescription": "Cycles not in Halt." + }, + { + "EventName": "ls_tlb_flush", + "EventCode": "0x78", + "BriefDescription": "All TLB Flushes" + } +] diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/other.json b/tools/perf/pmu-events/arch/x86/amdzen2/other.json new file mode 100644 index 000000000000..e94994d4a60e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/amdzen2/other.json @@ -0,0 +1,115 @@ +[ + { + "EventName": "de_dis_uop_queue_empty_di0", + "EventCode": "0xa9", + "BriefDescription": "Cycles where the Micro-Op Queue is empty." + }, + { + "EventName": "de_dis_uops_from_decoder", + "EventCode": "0xaa", + "BriefDescription": "Ops dispatched from either the decoders, OpCache or both.", + "UMask": "0xff" + }, + { + "EventName": "de_dis_uops_from_decoder.opcache_dispatched", + "EventCode": "0xaa", + "BriefDescription": "Count of dispatched Ops from OpCache.", + "UMask": "0x2" + }, + { + "EventName": "de_dis_uops_from_decoder.decoder_dispatched", + "EventCode": "0xaa", + "BriefDescription": "Count of dispatched Ops from Decoder.", + "UMask": "0x1" + }, + { + "EventName": "de_dis_dispatch_token_stalls1.fp_misc_rsrc_stall", + "EventCode": "0xae", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. FP Miscellaneous resource unavailable. Applies to the recovery of mispredicts with FP ops.", + "UMask": "0x80" + }, + { + "EventName": "de_dis_dispatch_token_stalls1.fp_sch_rsrc_stall", + "EventCode": "0xae", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. FP scheduler resource stall. Applies to ops that use the FP scheduler.", + "UMask": "0x40" + }, + { + "EventName": "de_dis_dispatch_token_stalls1.fp_reg_file_rsrc_stall", + "EventCode": "0xae", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Floating point register file resource stall. Applies to all FP ops that have a destination register.", + "UMask": "0x20" + }, + { + "EventName": "de_dis_dispatch_token_stalls1.taken_branch_buffer_rsrc_stall", + "EventCode": "0xae", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Taken branch buffer resource stall.", + "UMask": "0x10" + }, + { + "EventName": "de_dis_dispatch_token_stalls1.int_sched_misc_token_stall", + "EventCode": "0xae", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Integer Scheduler miscellaneous resource stall.", + "UMask": "0x8" + }, + { + "EventName": "de_dis_dispatch_token_stalls1.store_queue_token_stall", + "EventCode": "0xae", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Store queue resource stall. Applies to all ops with store semantics.", + "UMask": "0x4" + }, + { + "EventName": "de_dis_dispatch_token_stalls1.load_queue_token_stall", + "EventCode": "0xae", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Load queue resource stall. Applies to all ops with load semantics.", + "UMask": "0x2" + }, + { + "EventName": "de_dis_dispatch_token_stalls1.int_phy_reg_file_token_stall", + "EventCode": "0xae", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. Integer Physical Register File resource stall. Applies to all ops that have an integer destination register.", + "UMask": "0x1" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.sc_agu_dispatch_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. SC AGU dispatch stall.", + "UMask": "0x40" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.retire_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. RETIRE Tokens unavailable.", + "UMask": "0x20" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.agsq_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. AGSQ Tokens unavailable.", + "UMask": "0x10" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alu_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALU tokens total unavailable.", + "UMask": "0x8" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq3_0_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ3_0_TokenStall.", + "UMask": "0x4" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq2_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 2 Tokens unavailable.", + "UMask": "0x2" + }, + { + "EventName": "de_dis_dispatch_token_stalls0.alsq1_token_stall", + "EventCode": "0xaf", + "BriefDescription": "Cycles where a dispatch group is valid but does not get dispatched due to a token stall. ALSQ 1 Tokens unavailable.", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 45a34ce4fe89..8cdc7c13dc2a 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -297,7 +297,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index 961fe4395758..16fd8a7490fc 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -115,7 +115,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 746734ce09be..1eb0415fa11a 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -297,7 +297,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index a728c6e5119b..7fde0d2943cd 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -316,7 +316,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 5402cd3120f9..f57c5f3506c2 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -267,7 +267,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 832f3cb40b34..311a005dc35b 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -267,7 +267,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index d69b2a8fc0bc..28e25447d3ef 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -285,7 +285,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 5f465fd81315..db23db2e98be 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -285,7 +285,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index 3e909b306003..dbb33e00b72a 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -171,7 +171,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 745ced083844..25b06cf98747 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -36,4 +36,5 @@ GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core GenuineIntel-6-7D,v1,icelake,core GenuineIntel-6-7E,v1,icelake,core GenuineIntel-6-86,v1,tremontx,core -AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core +AuthenticAMD-23-([12][0-9A-F]|[0-9A-F]),v2,amdzen1,core +AuthenticAMD-23-[[:xdigit:]]+,v1,amdzen2,core diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 50c053235752..fb2d7b8875f8 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -171,7 +171,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index f97e8316ad2f..8704efeb8d31 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -304,7 +304,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 35f5db1786f7..b4f91137f40c 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -316,7 +316,7 @@ }, { "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", "MetricGroup": "Summary", "MetricName": "Kernel_Utilization" }, diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 3c4236a5bad8..fa86c5f997cc 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -771,6 +771,19 @@ static void print_mapping_table_suffix(FILE *outfp) fprintf(outfp, "};\n"); } +static void print_mapping_test_table(FILE *outfp) +{ + /* + * Print the terminating, NULL entry. + */ + fprintf(outfp, "{\n"); + fprintf(outfp, "\t.cpuid = \"testcpu\",\n"); + fprintf(outfp, "\t.version = \"v1\",\n"); + fprintf(outfp, "\t.type = \"core\",\n"); + fprintf(outfp, "\t.table = pme_test_cpu,\n"); + fprintf(outfp, "},\n"); +} + static int process_mapfile(FILE *outfp, char *fpath) { int n = 16384; @@ -848,6 +861,7 @@ static int process_mapfile(FILE *outfp, char *fpath) } out: + print_mapping_test_table(outfp); print_mapping_table_suffix(outfp); fclose(mapfp); free(line); @@ -1168,6 +1182,22 @@ int main(int argc, char *argv[]) goto empty_map; } + sprintf(ldirname, "%s/test", start_dirname); + + rc = nftw(ldirname, process_one_file, maxfds, 0); + if (rc && verbose) { + pr_info("%s: Error walking file tree %s rc=%d for test\n", + prog, ldirname, rc); + goto empty_map; + } else if (rc < 0) { + /* Make build fail */ + free_arch_std_events(); + ret = 1; + goto out_free_mapfile; + } else if (rc) { + goto empty_map; + } + if (close_table) print_events_table_suffix(eventsfp); diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore index 8cc30e731c73..d053b325f728 100644 --- a/tools/perf/tests/.gitignore +++ b/tools/perf/tests/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only llvm-src-base.c llvm-src-kbuild.c llvm-src-prologue.c diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 1692529639b0..b3d1bf13ca07 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -14,6 +14,7 @@ perf-y += evsel-roundtrip-name.o perf-y += evsel-tp-sched.o perf-y += fdarray.o perf-y += pmu.o +perf-y += pmu-events.o perf-y += hists_common.o perf-y += hists_link.o perf-y += hists_filter.o diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 54d9516c9839..b6322eb0f423 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -73,6 +73,10 @@ static struct test generic_tests[] = { .func = test__pmu, }, { + .desc = "PMU events", + .func = test__pmu_events, + }, + { .desc = "DSO data read", .func = test__dso_data, }, diff --git a/tools/perf/tests/make b/tools/perf/tests/make index c850d1664c56..5d0c3a9c47a1 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -28,9 +28,13 @@ endif PARALLEL_OPT= ifeq ($(SET_PARALLEL),1) - cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null) - ifeq ($(cores),0) - cores := 1 + ifeq ($(JOBS),) + cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null) + ifeq ($(cores),0) + cores := 1 + endif + else + cores=$(JOBS) endif PARALLEL_OPT="-j$(cores)" endif diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c new file mode 100644 index 000000000000..d64261da8bf7 --- /dev/null +++ b/tools/perf/tests/pmu-events.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "parse-events.h" +#include "pmu.h" +#include "tests.h" +#include <errno.h> +#include <stdio.h> +#include <linux/kernel.h> +#include <linux/zalloc.h> +#include "debug.h" +#include "../pmu-events/pmu-events.h" + +struct perf_pmu_test_event { + struct pmu_event event; + + /* extra events for aliases */ + const char *alias_str; + + /* + * Note: For when PublicDescription does not exist in the JSON, we + * will have no long_desc in pmu_event.long_desc, but long_desc may + * be set in the alias. + */ + const char *alias_long_desc; +}; + +static struct perf_pmu_test_event test_cpu_events[] = { + { + .event = { + .name = "bp_l1_btb_correct", + .event = "event=0x8a", + .desc = "L1 BTB Correction", + .topic = "branch", + }, + .alias_str = "event=0x8a", + .alias_long_desc = "L1 BTB Correction", + }, + { + .event = { + .name = "bp_l2_btb_correct", + .event = "event=0x8b", + .desc = "L2 BTB Correction", + .topic = "branch", + }, + .alias_str = "event=0x8b", + .alias_long_desc = "L2 BTB Correction", + }, + { + .event = { + .name = "segment_reg_loads.any", + .event = "umask=0x80,period=200000,event=0x6", + .desc = "Number of segment register loads", + .topic = "other", + }, + .alias_str = "umask=0x80,(null)=0x30d40,event=0x6", + .alias_long_desc = "Number of segment register loads", + }, + { + .event = { + .name = "dispatch_blocked.any", + .event = "umask=0x20,period=200000,event=0x9", + .desc = "Memory cluster signals to block micro-op dispatch for any reason", + .topic = "other", + }, + .alias_str = "umask=0x20,(null)=0x30d40,event=0x9", + .alias_long_desc = "Memory cluster signals to block micro-op dispatch for any reason", + }, + { + .event = { + .name = "eist_trans", + .event = "umask=0x0,period=200000,event=0x3a", + .desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", + .topic = "other", + }, + .alias_str = "umask=0,(null)=0x30d40,event=0x3a", + .alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", + }, + { /* sentinel */ + .event = { + .name = NULL, + }, + }, +}; + +static struct perf_pmu_test_event test_uncore_events[] = { + { + .event = { + .name = "uncore_hisi_ddrc.flux_wcmd", + .event = "event=0x2", + .desc = "DDRC write commands. Unit: hisi_sccl,ddrc ", + .topic = "uncore", + .long_desc = "DDRC write commands", + .pmu = "hisi_sccl,ddrc", + }, + .alias_str = "event=0x2", + .alias_long_desc = "DDRC write commands", + }, + { + .event = { + .name = "unc_cbo_xsnp_response.miss_eviction", + .event = "umask=0x81,event=0x22", + .desc = "Unit: uncore_cbox A cross-core snoop resulted from L3 Eviction which misses in some processor core", + .topic = "uncore", + .long_desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core", + .pmu = "uncore_cbox", + }, + .alias_str = "umask=0x81,event=0x22", + .alias_long_desc = "A cross-core snoop resulted from L3 Eviction which misses in some processor core", + }, + { /* sentinel */ + .event = { + .name = NULL, + }, + } +}; + +const int total_test_events_size = ARRAY_SIZE(test_uncore_events); + +static bool is_same(const char *reference, const char *test) +{ + if (!reference && !test) + return true; + + if (reference && !test) + return false; + + if (!reference && test) + return false; + + return !strcmp(reference, test); +} + +static struct pmu_events_map *__test_pmu_get_events_map(void) +{ + struct pmu_events_map *map; + + for (map = &pmu_events_map[0]; map->cpuid; map++) { + if (!strcmp(map->cpuid, "testcpu")) + return map; + } + + pr_err("could not find test events map\n"); + + return NULL; +} + +/* Verify generated events from pmu-events.c is as expected */ +static int __test_pmu_event_table(void) +{ + struct pmu_events_map *map = __test_pmu_get_events_map(); + struct pmu_event *table; + int map_events = 0, expected_events; + + /* ignore 2x sentinels */ + expected_events = ARRAY_SIZE(test_cpu_events) + + ARRAY_SIZE(test_uncore_events) - 2; + + if (!map) + return -1; + + for (table = map->table; table->name; table++) { + struct perf_pmu_test_event *test; + struct pmu_event *te; + bool found = false; + + if (table->pmu) + test = &test_uncore_events[0]; + else + test = &test_cpu_events[0]; + + te = &test->event; + + for (; te->name; test++, te = &test->event) { + if (strcmp(table->name, te->name)) + continue; + found = true; + map_events++; + + if (!is_same(table->desc, te->desc)) { + pr_debug2("testing event table %s: mismatched desc, %s vs %s\n", + table->name, table->desc, te->desc); + return -1; + } + + if (!is_same(table->topic, te->topic)) { + pr_debug2("testing event table %s: mismatched topic, %s vs %s\n", + table->name, table->topic, + te->topic); + return -1; + } + + if (!is_same(table->long_desc, te->long_desc)) { + pr_debug2("testing event table %s: mismatched long_desc, %s vs %s\n", + table->name, table->long_desc, + te->long_desc); + return -1; + } + + if (!is_same(table->unit, te->unit)) { + pr_debug2("testing event table %s: mismatched unit, %s vs %s\n", + table->name, table->unit, + te->unit); + return -1; + } + + if (!is_same(table->perpkg, te->perpkg)) { + pr_debug2("testing event table %s: mismatched perpkg, %s vs %s\n", + table->name, table->perpkg, + te->perpkg); + return -1; + } + + if (!is_same(table->metric_expr, te->metric_expr)) { + pr_debug2("testing event table %s: mismatched metric_expr, %s vs %s\n", + table->name, table->metric_expr, + te->metric_expr); + return -1; + } + + if (!is_same(table->metric_name, te->metric_name)) { + pr_debug2("testing event table %s: mismatched metric_name, %s vs %s\n", + table->name, table->metric_name, + te->metric_name); + return -1; + } + + if (!is_same(table->deprecated, te->deprecated)) { + pr_debug2("testing event table %s: mismatched deprecated, %s vs %s\n", + table->name, table->deprecated, + te->deprecated); + return -1; + } + + pr_debug("testing event table %s: pass\n", table->name); + } + + if (!found) { + pr_err("testing event table: could not find event %s\n", + table->name); + return -1; + } + } + + if (map_events != expected_events) { + pr_err("testing event table: found %d, but expected %d\n", + map_events, expected_events); + return -1; + } + + return 0; +} + +static struct perf_pmu_alias *find_alias(const char *test_event, struct list_head *aliases) +{ + struct perf_pmu_alias *alias; + + list_for_each_entry(alias, aliases, list) + if (!strcmp(test_event, alias->name)) + return alias; + + return NULL; +} + +/* Verify aliases are as expected */ +static int __test__pmu_event_aliases(char *pmu_name, int *count) +{ + struct perf_pmu_test_event *test; + struct pmu_event *te; + struct perf_pmu *pmu; + LIST_HEAD(aliases); + int res = 0; + bool use_uncore_table; + struct pmu_events_map *map = __test_pmu_get_events_map(); + + if (!map) + return -1; + + if (is_pmu_core(pmu_name)) { + test = &test_cpu_events[0]; + use_uncore_table = false; + } else { + test = &test_uncore_events[0]; + use_uncore_table = true; + } + + pmu = zalloc(sizeof(*pmu)); + if (!pmu) + return -1; + + pmu->name = pmu_name; + + pmu_add_cpu_aliases_map(&aliases, pmu, map); + + for (te = &test->event; te->name; test++, te = &test->event) { + struct perf_pmu_alias *alias = find_alias(te->name, &aliases); + + if (!alias) { + bool uncore_match = pmu_uncore_alias_match(pmu_name, + te->pmu); + + if (use_uncore_table && !uncore_match) { + pr_debug3("testing aliases PMU %s: skip matching alias %s\n", + pmu_name, te->name); + continue; + } + + pr_debug2("testing aliases PMU %s: no alias, alias_table->name=%s\n", + pmu_name, te->name); + res = -1; + break; + } + + if (!is_same(alias->desc, te->desc)) { + pr_debug2("testing aliases PMU %s: mismatched desc, %s vs %s\n", + pmu_name, alias->desc, te->desc); + res = -1; + break; + } + + if (!is_same(alias->long_desc, test->alias_long_desc)) { + pr_debug2("testing aliases PMU %s: mismatched long_desc, %s vs %s\n", + pmu_name, alias->long_desc, + test->alias_long_desc); + res = -1; + break; + } + + if (!is_same(alias->str, test->alias_str)) { + pr_debug2("testing aliases PMU %s: mismatched str, %s vs %s\n", + pmu_name, alias->str, test->alias_str); + res = -1; + break; + } + + if (!is_same(alias->topic, te->topic)) { + pr_debug2("testing aliases PMU %s: mismatched topic, %s vs %s\n", + pmu_name, alias->topic, te->topic); + res = -1; + break; + } + + (*count)++; + pr_debug2("testing aliases PMU %s: matched event %s\n", + pmu_name, alias->name); + } + + free(pmu); + return res; +} + +int test__pmu_events(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + struct perf_pmu *pmu = NULL; + + if (__test_pmu_event_table()) + return -1; + + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + int count = 0; + + if (list_empty(&pmu->format)) { + pr_debug2("skipping testing PMU %s\n", pmu->name); + continue; + } + + if (__test__pmu_event_aliases(pmu->name, &count)) { + pr_debug("testing PMU %s aliases: failed\n", pmu->name); + return -1; + } + + if (count == 0) + pr_debug3("testing PMU %s aliases: no events to match\n", + pmu->name); + else + pr_debug("testing PMU %s aliases: pass\n", pmu->name); + } + + return 0; +} diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 14239e472187..61865699c3f4 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -151,6 +151,9 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_PHYS_ADDR) COMP(phys_addr); + if (type & PERF_SAMPLE_CGROUP) + COMP(cgroup); + if (type & PERF_SAMPLE_AUX) { COMP(aux_sample.size); if (memcmp(s1->aux_sample.data, s2->aux_sample.data, @@ -230,6 +233,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) .regs = regs, }, .phys_addr = 113, + .cgroup = 114, .aux_sample = { .size = sizeof(aux_data), .data = (void *)aux_data, @@ -336,7 +340,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u * were added. Please actually update the test rather than just change * the condition below. */ - if (PERF_SAMPLE_MAX > PERF_SAMPLE_AUX << 1) { + if (PERF_SAMPLE_MAX > PERF_SAMPLE_CGROUP << 1) { pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n"); return -1; } diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 9a160fef47c9..61a1ab032080 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -49,6 +49,7 @@ int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest); int test__perf_evsel__tp_sched_test(struct test *test, int subtest); int test__syscall_openat_tp_fields(struct test *test, int subtest); int test__pmu(struct test *test, int subtest); +int test__pmu_events(struct test *test, int subtest); int test__attr(struct test *test, int subtest); int test__dso_data(struct test *test, int subtest); int test__dso_data_cache(struct test *test, int subtest); diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c index 062ca849c8fd..f4db894e0af6 100644 --- a/tools/perf/trace/beauty/clone.c +++ b/tools/perf/trace/beauty/clone.c @@ -46,6 +46,7 @@ static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size, P_FLAG(NEWNET); P_FLAG(IO); P_FLAG(CLEAR_SIGHAND); + P_FLAG(INTO_CGROUP); #undef P_FLAG if (flags) diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c index 9fa771a90d79..862c8331dded 100644 --- a/tools/perf/trace/beauty/mmap.c +++ b/tools/perf/trace/beauty/mmap.c @@ -69,6 +69,7 @@ static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size, P_MREMAP_FLAG(MAYMOVE); P_MREMAP_FLAG(FIXED); + P_MREMAP_FLAG(DONTUNMAP); #undef P_MREMAP_FLAG if (flags) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index f36dee499320..487e54ef56a9 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -677,7 +677,7 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si return browser->title ? browser->title(browser, bf, size) : 0; } -static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_lost_event, char *title, int key) +static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_lost_event, char *title, size_t size, int key) { switch (key) { case K_TIMER: { @@ -703,7 +703,7 @@ static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_l ui_browser__warn_lost_events(&browser->b); } - hist_browser__title(browser, title, sizeof(title)); + hist_browser__title(browser, title, size); ui_browser__show_title(&browser->b, title); break; } @@ -764,13 +764,13 @@ int hist_browser__run(struct hist_browser *browser, const char *help, if (ui_browser__show(&browser->b, title, "%s", help) < 0) return -1; - if (key && hist_browser__handle_hotkey(browser, warn_lost_event, title, key)) + if (key && hist_browser__handle_hotkey(browser, warn_lost_event, title, sizeof(title), key)) goto out; while (1) { key = ui_browser__run(&browser->b, delay_secs); - if (hist_browser__handle_hotkey(browser, warn_lost_event, title, key)) + if (hist_browser__handle_hotkey(browser, warn_lost_event, title, sizeof(title), key)) break; } out: @@ -2465,13 +2465,41 @@ do_annotate(struct hist_browser *browser, struct popup_action *act) return 0; } +static struct symbol *symbol__new_unresolved(u64 addr, struct map *map) +{ + struct annotated_source *src; + struct symbol *sym; + char name[64]; + + snprintf(name, sizeof(name), "%.*" PRIx64, BITS_PER_LONG / 4, addr); + + sym = symbol__new(addr, ANNOTATION_DUMMY_LEN, 0, 0, name); + if (sym) { + src = symbol__hists(sym, 1); + if (!src) { + symbol__delete(sym); + return NULL; + } + + dso__insert_symbol(map->dso, sym); + } + + return sym; +} + static int add_annotate_opt(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, - struct map_symbol *ms) + struct map_symbol *ms, + u64 addr) { - if (ms->sym == NULL || ms->map->dso->annotate_warned || - symbol__annotation(ms->sym)->src == NULL) + if (!ms->map || !ms->map->dso || ms->map->dso->annotate_warned) + return 0; + + if (!ms->sym) + ms->sym = symbol__new_unresolved(addr, ms->map); + + if (ms->sym == NULL || symbol__annotation(ms->sym)->src == NULL) return 0; if (asprintf(optstr, "Annotate %s", ms->sym->name) < 0) @@ -2964,7 +2992,8 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, "s Switch to another data file in PWD\n" "t Zoom into current Thread\n" "V Verbose (DSO names in callchains, etc)\n" - "/ Filter symbol by name"; + "/ Filter symbol by name\n" + "0-9 Sort by event n in group"; static const char top_help[] = HIST_BROWSER_HELP_COMMON "P Print histograms to perf.hist.N\n" "t Zoom into current Thread\n" @@ -3025,6 +3054,31 @@ do_hotkey: // key came straight from options ui__popup_menu() * go to the next or previous */ goto out_free_stack; + case '0' ... '9': + if (!symbol_conf.event_group || + evsel->core.nr_members < 2) { + snprintf(buf, sizeof(buf), + "Sort by index only available with group events!"); + helpline = buf; + continue; + } + + if (key - '0' == symbol_conf.group_sort_idx) + continue; + + symbol_conf.group_sort_idx = key - '0'; + + if (symbol_conf.group_sort_idx >= evsel->core.nr_members) { + snprintf(buf, sizeof(buf), + "Max event group index to sort is %d (index from 0 to %d)", + evsel->core.nr_members - 1, + evsel->core.nr_members - 1); + helpline = buf; + continue; + } + + key = K_RELOAD; + goto out_free_stack; case 'a': if (!hists__has(hists, sym)) { ui_browser__warning(&browser->b, delay_secs * 2, @@ -3033,21 +3087,45 @@ do_hotkey: // key came straight from options ui__popup_menu() continue; } - if (browser->selection == NULL || - browser->selection->sym == NULL || - browser->selection->map->dso->annotate_warned) + if (!browser->selection || + !browser->selection->map || + !browser->selection->map->dso || + browser->selection->map->dso->annotate_warned) { continue; + } - if (symbol__annotation(browser->selection->sym)->src == NULL) { - ui_browser__warning(&browser->b, delay_secs * 2, - "No samples for the \"%s\" symbol.\n\n" - "Probably appeared just in a callchain", - browser->selection->sym->name); - continue; + if (!browser->selection->sym) { + if (!browser->he_selection) + continue; + + if (sort__mode == SORT_MODE__BRANCH) { + bi = browser->he_selection->branch_info; + if (!bi || !bi->to.ms.map) + continue; + + actions->ms.sym = symbol__new_unresolved(bi->to.al_addr, bi->to.ms.map); + actions->ms.map = bi->to.ms.map; + } else { + actions->ms.sym = symbol__new_unresolved(browser->he_selection->ip, + browser->selection->map); + actions->ms.map = browser->selection->map; + } + + if (!actions->ms.sym) + continue; + } else { + if (symbol__annotation(browser->selection->sym)->src == NULL) { + ui_browser__warning(&browser->b, delay_secs * 2, + "No samples for the \"%s\" symbol.\n\n" + "Probably appeared just in a callchain", + browser->selection->sym->name); + continue; + } + + actions->ms.map = browser->selection->map; + actions->ms.sym = browser->selection->sym; } - actions->ms.map = browser->selection->map; - actions->ms.sym = browser->selection->sym; do_annotate(browser, actions); continue; case 'P': @@ -3219,17 +3297,20 @@ do_hotkey: // key came straight from options ui__popup_menu() nr_options += add_annotate_opt(browser, &actions[nr_options], &options[nr_options], - &bi->from.ms); + &bi->from.ms, + bi->from.al_addr); if (bi->to.ms.sym != bi->from.ms.sym) nr_options += add_annotate_opt(browser, &actions[nr_options], &options[nr_options], - &bi->to.ms); + &bi->to.ms, + bi->to.al_addr); } else { nr_options += add_annotate_opt(browser, &actions[nr_options], &options[nr_options], - browser->selection); + browser->selection, + browser->he_selection->ip); } skip_annotation: nr_options += add_thread_opt(browser, &actions[nr_options], @@ -3440,6 +3521,7 @@ browse_hists: pos = perf_evsel__prev(pos); goto browse_hists; case K_SWITCH_INPUT_DATA: + case K_RELOAD: case 'q': case CTRL('c'): goto out; diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index f73675500061..025f4c7f96bf 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -151,15 +151,90 @@ static int field_cmp(u64 field_a, u64 field_b) return 0; } +static int hist_entry__new_pair(struct hist_entry *a, struct hist_entry *b, + hpp_field_fn get_field, int nr_members, + u64 **fields_a, u64 **fields_b) +{ + u64 *fa = calloc(nr_members, sizeof(*fa)), + *fb = calloc(nr_members, sizeof(*fb)); + struct hist_entry *pair; + + if (!fa || !fb) + goto out_free; + + list_for_each_entry(pair, &a->pairs.head, pairs.node) { + struct evsel *evsel = hists_to_evsel(pair->hists); + fa[perf_evsel__group_idx(evsel)] = get_field(pair); + } + + list_for_each_entry(pair, &b->pairs.head, pairs.node) { + struct evsel *evsel = hists_to_evsel(pair->hists); + fb[perf_evsel__group_idx(evsel)] = get_field(pair); + } + + *fields_a = fa; + *fields_b = fb; + return 0; +out_free: + free(fa); + free(fb); + *fields_a = *fields_b = NULL; + return -1; +} + +static int __hpp__group_sort_idx(struct hist_entry *a, struct hist_entry *b, + hpp_field_fn get_field, int idx) +{ + struct evsel *evsel = hists_to_evsel(a->hists); + u64 *fields_a, *fields_b; + int cmp, nr_members, ret, i; + + cmp = field_cmp(get_field(a), get_field(b)); + if (!perf_evsel__is_group_event(evsel)) + return cmp; + + nr_members = evsel->core.nr_members; + if (idx < 1 || idx >= nr_members) + return cmp; + + ret = hist_entry__new_pair(a, b, get_field, nr_members, &fields_a, &fields_b); + if (ret) { + ret = cmp; + goto out; + } + + ret = field_cmp(fields_a[idx], fields_b[idx]); + if (ret) + goto out; + + for (i = 1; i < nr_members; i++) { + if (i != idx) { + ret = field_cmp(fields_a[i], fields_b[i]); + if (ret) + goto out; + } + } + +out: + free(fields_a); + free(fields_b); + + return ret; +} + static int __hpp__sort(struct hist_entry *a, struct hist_entry *b, hpp_field_fn get_field) { s64 ret; int i, nr_members; struct evsel *evsel; - struct hist_entry *pair; u64 *fields_a, *fields_b; + if (symbol_conf.group_sort_idx && symbol_conf.event_group) { + return __hpp__group_sort_idx(a, b, get_field, + symbol_conf.group_sort_idx); + } + ret = field_cmp(get_field(a), get_field(b)); if (ret || !symbol_conf.event_group) return ret; @@ -169,22 +244,10 @@ static int __hpp__sort(struct hist_entry *a, struct hist_entry *b, return ret; nr_members = evsel->core.nr_members; - fields_a = calloc(nr_members, sizeof(*fields_a)); - fields_b = calloc(nr_members, sizeof(*fields_b)); - - if (!fields_a || !fields_b) + i = hist_entry__new_pair(a, b, get_field, nr_members, &fields_a, &fields_b); + if (i) goto out; - list_for_each_entry(pair, &a->pairs.head, pairs.node) { - evsel = hists_to_evsel(pair->hists); - fields_a[perf_evsel__group_idx(evsel)] = get_field(pair); - } - - list_for_each_entry(pair, &b->pairs.head, pairs.node) { - evsel = hists_to_evsel(pair->hists); - fields_b[perf_evsel__group_idx(evsel)] = get_field(pair); - } - for (i = 1; i < nr_members; i++) { ret = field_cmp(fields_a[i], fields_b[i]); if (ret) diff --git a/tools/perf/ui/keysyms.h b/tools/perf/ui/keysyms.h index fbfac29077f2..04cc4e5c031f 100644 --- a/tools/perf/ui/keysyms.h +++ b/tools/perf/ui/keysyms.h @@ -25,5 +25,6 @@ #define K_ERROR -2 #define K_RESIZE -3 #define K_SWITCH_INPUT_DATA -4 +#define K_RELOAD -5 #endif /* _PERF_KEYSYMS_H_ */ diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 07c775938d46..2d88069d6428 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -74,6 +74,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2); #define ANNOTATION__CYCLES_WIDTH 6 #define ANNOTATION__MINMAX_CYCLES_WIDTH 19 #define ANNOTATION__AVG_IPC_WIDTH 36 +#define ANNOTATION_DUMMY_LEN 256 struct annotation_options { bool hide_src_code, diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 5bc9d3b01bd9..b73fb7823048 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -191,3 +191,83 @@ int parse_cgroups(const struct option *opt, const char *str, } return 0; } + +static struct cgroup *__cgroup__findnew(struct rb_root *root, uint64_t id, + bool create, const char *path) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct cgroup *cgrp; + + while (*p != NULL) { + parent = *p; + cgrp = rb_entry(parent, struct cgroup, node); + + if (cgrp->id == id) + return cgrp; + + if (cgrp->id < id) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + if (!create) + return NULL; + + cgrp = malloc(sizeof(*cgrp)); + if (cgrp == NULL) + return NULL; + + cgrp->name = strdup(path); + if (cgrp->name == NULL) { + free(cgrp); + return NULL; + } + + cgrp->fd = -1; + cgrp->id = id; + refcount_set(&cgrp->refcnt, 1); + + rb_link_node(&cgrp->node, parent, p); + rb_insert_color(&cgrp->node, root); + + return cgrp; +} + +struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id, + const char *path) +{ + struct cgroup *cgrp; + + down_write(&env->cgroups.lock); + cgrp = __cgroup__findnew(&env->cgroups.tree, id, true, path); + up_write(&env->cgroups.lock); + return cgrp; +} + +struct cgroup *cgroup__find(struct perf_env *env, uint64_t id) +{ + struct cgroup *cgrp; + + down_read(&env->cgroups.lock); + cgrp = __cgroup__findnew(&env->cgroups.tree, id, false, NULL); + up_read(&env->cgroups.lock); + return cgrp; +} + +void perf_env__purge_cgroups(struct perf_env *env) +{ + struct rb_node *node; + struct cgroup *cgrp; + + down_write(&env->cgroups.lock); + while (!RB_EMPTY_ROOT(&env->cgroups.tree)) { + node = rb_first(&env->cgroups.tree); + cgrp = rb_entry(node, struct cgroup, node); + + rb_erase(node, &env->cgroups.tree); + cgroup__put(cgrp); + } + up_write(&env->cgroups.lock); +} diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index 2ec11f01090d..e98d5975fe55 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -3,16 +3,19 @@ #define __CGROUP_H__ #include <linux/refcount.h> +#include <linux/rbtree.h> +#include "util/env.h" struct option; struct cgroup { - char *name; - int fd; - refcount_t refcnt; + struct rb_node node; + u64 id; + char *name; + int fd; + refcount_t refcnt; }; - extern int nr_cgroups; /* number of explicit cgroups defined */ struct cgroup *cgroup__get(struct cgroup *cgroup); @@ -26,4 +29,10 @@ void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup); int parse_cgroups(const struct option *opt, const char *str, int unset); +struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id, + const char *path); +struct cgroup *cgroup__find(struct perf_env *env, uint64_t id); + +void perf_env__purge_cgroups(struct perf_env *env); + #endif /* __CGROUP_H__ */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 983b7388f22b..dc5c5e6fc502 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -317,7 +317,7 @@ static void set_max_cpu_num(void) /* get the highest possible cpu number for a sparse allocation */ ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt); - if (ret == PATH_MAX) { + if (ret >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); goto out; } @@ -328,7 +328,7 @@ static void set_max_cpu_num(void) /* get the highest present cpu number for a sparse allocation */ ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt); - if (ret == PATH_MAX) { + if (ret >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); goto out; } @@ -356,7 +356,7 @@ static void set_max_node_num(void) /* get the highest possible cpu number for a sparse allocation */ ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt); - if (ret == PATH_MAX) { + if (ret >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); goto out; } @@ -441,7 +441,7 @@ int cpu__setup_cpunode_map(void) return 0; n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt); - if (n == PATH_MAX) { + if (n >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); return -1; } @@ -456,7 +456,7 @@ int cpu__setup_cpunode_map(void) continue; n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name); - if (n == PATH_MAX) { + if (n >= PATH_MAX) { pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); continue; } diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c index 591707c69c39..939471731ea6 100644 --- a/tools/perf/util/dsos.c +++ b/tools/perf/util/dsos.c @@ -26,13 +26,29 @@ static int __dso_id__cmp(struct dso_id *a, struct dso_id *b) return 0; } +static bool dso_id__empty(struct dso_id *id) +{ + if (!id) + return true; + + return !id->maj && !id->min && !id->ino && !id->ino_generation; +} + +static void dso__inject_id(struct dso *dso, struct dso_id *id) +{ + dso->id.maj = id->maj; + dso->id.min = id->min; + dso->id.ino = id->ino; + dso->id.ino_generation = id->ino_generation; +} + static int dso_id__cmp(struct dso_id *a, struct dso_id *b) { /* * The second is always dso->id, so zeroes if not set, assume passing * NULL for a means a zeroed id */ - if (a == NULL) + if (dso_id__empty(a) || dso_id__empty(b)) return 0; return __dso_id__cmp(a, b); @@ -249,6 +265,10 @@ struct dso *__dsos__addnew(struct dsos *dsos, const char *name) static struct dso *__dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id) { struct dso *dso = __dsos__find_id(dsos, name, id, false); + + if (dso && dso_id__empty(&dso->id) && !dso_id__empty(id)) + dso__inject_id(dso, id); + return dso ? dso : __dsos__addnew_id(dsos, name, id); } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 4154f944f474..fadc59708ece 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -6,6 +6,7 @@ #include <linux/ctype.h> #include <linux/zalloc.h> #include "bpf-event.h" +#include "cgroup.h" #include <errno.h> #include <sys/utsname.h> #include <bpf/libbpf.h> @@ -168,6 +169,7 @@ void perf_env__exit(struct perf_env *env) int i; perf_env__purge_bpf(env); + perf_env__purge_cgroups(env); zfree(&env->hostname); zfree(&env->os_release); zfree(&env->version); diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 11d05ae3606a..7632075a8792 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -88,6 +88,12 @@ struct perf_env { u32 btfs_cnt; } bpf_progs; + /* same reason as above (for perf-top) */ + struct { + struct rw_semaphore lock; + struct rb_root tree; + } cgroups; + /* For fast cpu to numa node lookup via perf_env__numa_node */ int *numa_map; int nr_numa_map; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index c5447ff516a2..dc0e11214ae1 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -54,6 +54,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_NAMESPACES] = "NAMESPACES", [PERF_RECORD_KSYMBOL] = "KSYMBOL", [PERF_RECORD_BPF_EVENT] = "BPF_EVENT", + [PERF_RECORD_CGROUP] = "CGROUP", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -180,6 +181,12 @@ size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp) return ret; } +size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp) +{ + return fprintf(fp, " cgroup: %" PRI_lu64 " %s\n", + event->cgroup.id, event->cgroup.path); +} + int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -196,6 +203,14 @@ int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused, return machine__process_namespaces_event(machine, event, sample); } +int perf_event__process_cgroup(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_cgroup_event(machine, event, sample); +} + int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -417,6 +432,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_NAMESPACES: ret += perf_event__fprintf_namespaces(event, fp); break; + case PERF_RECORD_CGROUP: + ret += perf_event__fprintf_cgroup(event, fp); + break; case PERF_RECORD_MMAP2: ret += perf_event__fprintf_mmap2(event, fp); break; @@ -599,10 +617,23 @@ int machine__resolve(struct machine *machine, struct addr_location *al, al->sym = map__find_symbol(al->map, al->addr); } - if (symbol_conf.sym_list && - (!al->sym || !strlist__has_entry(symbol_conf.sym_list, - al->sym->name))) { - al->filtered |= (1 << HIST_FILTER__SYMBOL); + if (symbol_conf.sym_list) { + int ret = 0; + char al_addr_str[32]; + size_t sz = sizeof(al_addr_str); + + if (al->sym) { + ret = strlist__has_entry(symbol_conf.sym_list, + al->sym->name); + } + if (!(ret && al->sym)) { + snprintf(al_addr_str, sz, "0x%"PRIx64, + al->map->unmap_ip(al->map, al->sym->start)); + ret = strlist__has_entry(symbol_conf.sym_list, + al_addr_str); + } + if (!ret) + al->filtered |= (1 << HIST_FILTER__SYMBOL); } return 0; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 3cda40a2fafc..b8289f160f07 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -135,6 +135,7 @@ struct perf_sample { u32 raw_size; u64 data_src; u64 phys_addr; + u64 cgroup; u32 flags; u16 insn_len; u8 cpumode; @@ -322,6 +323,10 @@ int perf_event__process_namespaces(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_cgroup(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -377,6 +382,7 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp); size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp); size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 816d930d774e..eb880efbce16 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1104,6 +1104,11 @@ void perf_evsel__config(struct evsel *evsel, struct record_opts *opts, if (opts->record_namespaces) attr->namespaces = track; + if (opts->record_cgroup) { + attr->cgroup = track && !perf_missing_features.cgroup; + perf_evsel__set_sample_bit(evsel, CGROUP); + } + if (opts->record_switch_events) attr->context_switch = track; @@ -1287,6 +1292,7 @@ void perf_evsel__exit(struct evsel *evsel) perf_thread_map__put(evsel->core.threads); zfree(&evsel->group_name); zfree(&evsel->name); + zfree(&evsel->pmu_name); perf_evsel__object.fini(evsel); } @@ -1788,7 +1794,11 @@ try_fallback: * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.branch_hw_idx && + if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { + perf_missing_features.cgroup = true; + pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n"); + goto out_close; + } else if (!perf_missing_features.branch_hw_idx && (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) { perf_missing_features.branch_hw_idx = true; pr_debug2("switching off branch HW index support\n"); @@ -2266,6 +2276,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } + data->cgroup = 0; + if (type & PERF_SAMPLE_CGROUP) { + data->cgroup = *array; + array++; + } + if (type & PERF_SAMPLE_AUX) { OVERFLOW_CHECK_u64(array); sz = *array++; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 33804740e2ca..53187c501ee8 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -120,6 +120,7 @@ struct perf_missing_features { bool bpf; bool aux_output; bool branch_hw_idx; + bool cgroup; }; extern struct perf_missing_features perf_missing_features; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index e74a5acf66d9..283a69ff6a3d 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -10,6 +10,7 @@ #include "mem-events.h" #include "session.h" #include "namespaces.h" +#include "cgroup.h" #include "sort.h" #include "units.h" #include "evlist.h" @@ -194,6 +195,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); } + hists__new_col_len(hists, HISTC_CGROUP, 6); hists__new_col_len(hists, HISTC_CGROUP_ID, 20); hists__new_col_len(hists, HISTC_CPU, 3); hists__new_col_len(hists, HISTC_SOCKET, 6); @@ -222,6 +224,16 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->trace_output) hists__new_col_len(hists, HISTC_TRACE, strlen(h->trace_output)); + + if (h->cgroup) { + const char *cgrp_name = "unknown"; + struct cgroup *cgrp = cgroup__find(h->ms.maps->machine->env, + h->cgroup); + if (cgrp != NULL) + cgrp_name = cgrp->name; + + hists__new_col_len(hists, HISTC_CGROUP, strlen(cgrp_name)); + } } void hists__output_recalc_col_len(struct hists *hists, int max_rows) @@ -691,6 +703,7 @@ __hists__add_entry(struct hists *hists, .dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0, .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, }, + .cgroup = sample->cgroup, .ms = { .maps = al->maps, .map = al->map, diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 0aa63aeb58ec..4141295a66fa 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -38,6 +38,7 @@ enum hist_column { HISTC_THREAD, HISTC_COMM, HISTC_CGROUP_ID, + HISTC_CGROUP, HISTC_PARENT, HISTC_CPU, HISTC_SOCKET, @@ -536,6 +537,7 @@ static inline int block_hists_tui_browse(struct block_hist *bh __maybe_unused, #define K_LEFT -1000 #define K_RIGHT -2000 #define K_SWITCH_INPUT_DATA -3000 +#define K_RELOAD -4000 #endif unsigned int hists__sort_list_width(struct hists *hists); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index fd14f1489802..97142e9671be 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -33,6 +33,7 @@ #include "asm/bug.h" #include "bpf-event.h" #include <internal/lib.h> // page_size +#include "cgroup.h" #include <linux/ctype.h> #include <symbol/kallsyms.h> @@ -654,6 +655,22 @@ int machine__process_namespaces_event(struct machine *machine __maybe_unused, return err; } +int machine__process_cgroup_event(struct machine *machine, + union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + struct cgroup *cgrp; + + if (dump_trace) + perf_event__fprintf_cgroup(event, stdout); + + cgrp = cgroup__findnew(machine->env, event->cgroup.id, event->cgroup.path); + if (cgrp == NULL) + return -ENOMEM; + + return 0; +} + int machine__process_lost_event(struct machine *machine __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused) { @@ -1878,6 +1895,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret = machine__process_mmap_event(machine, event, sample); break; case PERF_RECORD_NAMESPACES: ret = machine__process_namespaces_event(machine, event, sample); break; + case PERF_RECORD_CGROUP: + ret = machine__process_cgroup_event(machine, event, sample); break; case PERF_RECORD_MMAP2: ret = machine__process_mmap2_event(machine, event, sample); break; case PERF_RECORD_FORK: diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index be0a930eca89..fa1be9ea00fa 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -128,6 +128,9 @@ int machine__process_switch_event(struct machine *machine, int machine__process_namespaces_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); +int machine__process_cgroup_event(struct machine *machine, + union perf_event *event, + struct perf_sample *sample); int machine__process_mmap_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); int machine__process_mmap2_event(struct machine *machine, union perf_event *event, diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index c3a8c701609a..926449a7cdbf 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -95,13 +95,16 @@ struct egroup { static struct evsel *find_evsel_group(struct evlist *perf_evlist, const char **ids, int idnum, - struct evsel **metric_events) + struct evsel **metric_events, + bool *evlist_used) { struct evsel *ev; - int i = 0; + int i = 0, j = 0; bool leader_found; evlist__for_each_entry (perf_evlist, ev) { + if (evlist_used[j++]) + continue; if (!strcmp(ev->name, ids[i])) { if (!metric_events[i]) metric_events[i] = ev; @@ -109,22 +112,17 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, if (i == idnum) break; } else { - if (i + 1 == idnum) { - /* Discard the whole match and start again */ - i = 0; - memset(metric_events, 0, - sizeof(struct evsel *) * idnum); - continue; - } - - if (!strcmp(ev->name, ids[i])) - metric_events[i] = ev; - else { - /* Discard the whole match and start again */ - i = 0; - memset(metric_events, 0, - sizeof(struct evsel *) * idnum); - continue; + /* Discard the whole match and start again */ + i = 0; + memset(metric_events, 0, + sizeof(struct evsel *) * idnum); + + if (!strcmp(ev->name, ids[i])) { + if (!metric_events[i]) + metric_events[i] = ev; + i++; + if (i == idnum) + break; } } } @@ -146,7 +144,10 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, !strcmp(ev->name, metric_events[i]->name)) { ev->metric_leader = metric_events[i]; } + j++; } + ev = metric_events[i]; + evlist_used[ev->idx] = true; } return metric_events[0]; @@ -162,6 +163,13 @@ static int metricgroup__setup_events(struct list_head *groups, int ret = 0; struct egroup *eg; struct evsel *evsel; + bool *evlist_used; + + evlist_used = calloc(perf_evlist->core.nr_entries, sizeof(bool)); + if (!evlist_used) { + ret = -ENOMEM; + return ret; + } list_for_each_entry (eg, groups, nd) { struct evsel **metric_events; @@ -172,7 +180,7 @@ static int metricgroup__setup_events(struct list_head *groups, break; } evsel = find_evsel_group(perf_evlist, eg->ids, eg->idnum, - metric_events); + metric_events, evlist_used); if (!evsel) { pr_debug("Cannot resolve %s: %s\n", eg->metric_name, eg->metric_expr); @@ -196,6 +204,9 @@ static int metricgroup__setup_events(struct list_head *groups, expr->metric_events = metric_events; list_add(&expr->nd, &me->head); } + + free(evlist_used); + return ret; } diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index a7dc0b096974..10107747b361 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1449,7 +1449,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats, NULL); if (evsel) { - evsel->pmu_name = name; + evsel->pmu_name = name ? strdup(name) : NULL; evsel->use_uncore_alias = use_uncore_alias; return 0; } else { @@ -1497,7 +1497,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->snapshot = info.snapshot; evsel->metric_expr = info.metric_expr; evsel->metric_name = info.metric_name; - evsel->pmu_name = name; + evsel->pmu_name = name ? strdup(name) : NULL; evsel->use_uncore_alias = use_uncore_alias; evsel->percore = config_term_percore(&evsel->config_terms); } @@ -1547,7 +1547,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, if (!parse_events_add_pmu(parse_state, list, pmu->name, head, true, true)) { - pr_debug("%s -> %s/%s/\n", config, + pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; } diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 7b1c8ee537cf..baa48f28d57d 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -342,11 +342,13 @@ bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUT * Because the prefix cycles is mixed up with cpu-cycles. * loads and stores are mixed up with cache event */ -cycles-ct { return str(yyscanner, PE_KERNEL_PMU_EVENT); } -cycles-t { return str(yyscanner, PE_KERNEL_PMU_EVENT); } -mem-loads { return str(yyscanner, PE_KERNEL_PMU_EVENT); } -mem-stores { return str(yyscanner, PE_KERNEL_PMU_EVENT); } -topdown-[a-z-]+ { return str(yyscanner, PE_KERNEL_PMU_EVENT); } +cycles-ct | +cycles-t | +mem-loads | +mem-stores | +topdown-[a-z-]+ | +tx-capacity-[a-z-]+ | +el-capacity-[a-z-]+ { return str(yyscanner, PE_KERNEL_PMU_EVENT); } L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index 355d3458d4e6..b94fa07f5d32 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -35,6 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value) bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX), + bit_name(CGROUP), { .name = NULL, } }; #undef bit_name @@ -132,6 +133,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr, PRINT_ATTRf(ksymbol, p_unsigned); PRINT_ATTRf(bpf_event, p_unsigned); PRINT_ATTRf(aux_output, p_unsigned); + PRINT_ATTRf(cgroup, p_unsigned); PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned); PRINT_ATTRf(bp_type, p_unsigned); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 8b99fd312aae..ef6a63f3d386 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -21,7 +21,6 @@ #include "pmu.h" #include "parse-events.h" #include "header.h" -#include "pmu-events/pmu-events.h" #include "string2.h" #include "strbuf.h" #include "fncache.h" @@ -699,7 +698,7 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu) return map; } -static bool pmu_uncore_alias_match(const char *pmu_name, const char *name) +bool pmu_uncore_alias_match(const char *pmu_name, const char *name) { char *tmp = NULL, *tok, *str; bool res; @@ -744,16 +743,11 @@ out: * to the current running CPU. Then, add all PMU events from that table * as aliases. */ -static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) +void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, + struct pmu_events_map *map) { int i; - struct pmu_events_map *map; const char *name = pmu->name; - - map = perf_pmu__find_map(pmu); - if (!map) - return; - /* * Found a matching PMU events table. Create aliases */ @@ -788,6 +782,17 @@ new_alias: } } +static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) +{ + struct pmu_events_map *map; + + map = perf_pmu__find_map(pmu); + if (!map) + return; + + pmu_add_cpu_aliases_map(head, pmu, map); +} + struct perf_event_attr * __weak perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { @@ -979,12 +984,11 @@ static int pmu_resolve_param_term(struct parse_events_term *term, struct parse_events_term *t; list_for_each_entry(t, head_terms, list) { - if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { - if (!strcmp(t->config, term->config)) { - t->used = true; - *value = t->val.num; - return 0; - } + if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM && + t->config && !strcmp(t->config, term->config)) { + t->used = true; + *value = t->val.num; + return 0; } } @@ -1395,6 +1399,11 @@ static void wordwrap(char *s, int start, int max, int corr) } } +bool is_pmu_core(const char *name) +{ + return !strcmp(name, "cpu") || is_arm_pmu_core(name); +} + void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, bool long_desc, bool details_flag, bool deprecated) { diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 6737e3d5d568..5fb3f16828df 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -7,6 +7,7 @@ #include <linux/perf_event.h> #include <stdbool.h> #include "parse-events.h" +#include "pmu-events/pmu-events.h" struct perf_evsel_config_term; @@ -87,6 +88,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); +bool is_pmu_core(const char *name); void print_pmu_events(const char *event_glob, bool name_only, bool quiet, bool long_desc, bool details_flag, bool deprecated); @@ -97,8 +99,11 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, int perf_pmu__test(void); struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); +void pmu_add_cpu_aliases_map(struct list_head *head, struct perf_pmu *pmu, + struct pmu_events_map *map); struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu); +bool pmu_uncore_alias_match(const char *pmu_name, const char *name); int perf_pmu__convert_scale(const char *scale, char **end, double *sval); diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index e7279ea6043a..a9d9c142eb7c 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -34,3 +34,4 @@ util/string.c util/symbol_fprintf.c util/units.c util/affinity.c +util/rwsem.c diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 5421fd2ad383..24316458be20 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -34,6 +34,7 @@ struct record_opts { bool auxtrace_snapshot_on_exit; bool auxtrace_sample_mode; bool record_namespaces; + bool record_cgroup; bool record_switch_events; bool all_kernel; bool all_user; diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 8c1b27cd8b99..2c372cf5495e 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -694,6 +694,9 @@ static int regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size) bf[0] = 0; + if (!regs || !regs->regs) + return 0; + for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) { u64 val = regs->regs[i++]; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 055b00abd56d..0b0bfe5bef17 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -471,6 +471,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->comm = process_event_stub; if (tool->namespaces == NULL) tool->namespaces = process_event_stub; + if (tool->cgroup == NULL) + tool->cgroup = process_event_stub; if (tool->fork == NULL) tool->fork = process_event_stub; if (tool->exit == NULL) @@ -1436,6 +1438,8 @@ static int machines__deliver_event(struct machines *machines, return tool->comm(tool, event, sample, machine); case PERF_RECORD_NAMESPACES: return tool->namespaces(tool, event, sample, machine); + case PERF_RECORD_CGROUP: + return tool->cgroup(tool, event, sample, machine); case PERF_RECORD_FORK: return tool->fork(tool, event, sample, machine); case PERF_RECORD_EXIT: diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 8a065a6f9713..c5e3e9a68162 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -3,7 +3,7 @@ from subprocess import Popen, PIPE from re import sub cc = getenv("CC") -cc_is_clang = b"clang version" in Popen([cc, "-v"], stderr=PIPE).stderr.readline() +cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline() def clang_has_option(option): return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] @@ -21,6 +21,8 @@ if cc_is_clang: vars[var] = sub("-fstack-clash-protection", "", vars[var]) if not clang_has_option("-fstack-protector-strong"): vars[var] = sub("-fstack-protector-strong", "", vars[var]) + if not clang_has_option("-fno-semantic-interposition"): + vars[var] = sub("-fno-semantic-interposition", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index ab0cfd790ad0..f14cc728c358 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -12,6 +12,7 @@ #include "cacheline.h" #include "comm.h" #include "map.h" +#include "maps.h" #include "symbol.h" #include "map_symbol.h" #include "branch.h" @@ -25,6 +26,8 @@ #include "mem-events.h" #include "annotate.h" #include "time-utils.h" +#include "cgroup.h" +#include "machine.h" #include <linux/kernel.h> #include <linux/string.h> @@ -634,6 +637,39 @@ struct sort_entry sort_cgroup_id = { .se_width_idx = HISTC_CGROUP_ID, }; +/* --sort cgroup */ + +static int64_t +sort__cgroup_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return right->cgroup - left->cgroup; +} + +static int hist_entry__cgroup_snprintf(struct hist_entry *he, + char *bf, size_t size, + unsigned int width __maybe_unused) +{ + const char *cgrp_name = "N/A"; + + if (he->cgroup) { + struct cgroup *cgrp = cgroup__find(he->ms.maps->machine->env, + he->cgroup); + if (cgrp != NULL) + cgrp_name = cgrp->name; + else + cgrp_name = "unknown"; + } + + return repsep_snprintf(bf, size, "%s", cgrp_name); +} + +struct sort_entry sort_cgroup = { + .se_header = "Cgroup", + .se_cmp = sort__cgroup_cmp, + .se_snprintf = hist_entry__cgroup_snprintf, + .se_width_idx = HISTC_CGROUP, +}; + /* --sort socket */ static int64_t @@ -869,7 +905,8 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, if (he->branch_info) { struct addr_map_symbol *from = &he->branch_info->from; - return _hist_entry__sym_snprintf(&from->ms, from->addr, he->level, bf, size, width); + return _hist_entry__sym_snprintf(&from->ms, from->al_addr, + he->level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -881,7 +918,8 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, if (he->branch_info) { struct addr_map_symbol *to = &he->branch_info->to; - return _hist_entry__sym_snprintf(&to->ms, to->addr, he->level, bf, size, width); + return _hist_entry__sym_snprintf(&to->ms, to->al_addr, + he->level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -1658,6 +1696,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_TRACE, "trace", sort_trace), DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size), DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size), + DIM(SORT_CGROUP, "cgroup", sort_cgroup), DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null), DIM(SORT_TIME, "time", sort_time), diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 6c862d62d052..cfa6ac6f7d06 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -101,6 +101,7 @@ struct hist_entry { struct thread *thread; struct comm *comm; struct namespace_id cgroup_id; + u64 cgroup; u64 ip; u64 transaction; s32 socket; @@ -224,6 +225,7 @@ enum sort_type { SORT_TRACE, SORT_SYM_SIZE, SORT_DSO_SIZE, + SORT_CGROUP, SORT_CGROUP_ID, SORT_SYM_IPC_NULL, SORT_TIME, diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 76c6052b12e2..9e757d18d713 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -115,11 +115,11 @@ static void aggr_printout(struct perf_stat_config *config, fprintf(config->output, "S%d-D%d-C%*d%s", cpu_map__id_to_socket(id), cpu_map__id_to_die(id), - config->csv_output ? 0 : -5, + config->csv_output ? 0 : -3, cpu_map__id_to_cpu(id), config->csv_sep); } else { - fprintf(config->output, "CPU%*d%s ", - config->csv_output ? 0 : -5, + fprintf(config->output, "CPU%*d%s", + config->csv_output ? 0 : -7, evsel__cpus(evsel)->map[id], config->csv_sep); } diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 0fd713d3674f..03ecb8cd0eec 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -803,8 +803,11 @@ static void generic_metric(struct perf_stat_config *config, out->force_header ? (metric_name ? metric_name : name) : "", 0); } - } else - print_metric(config, ctxp, NULL, NULL, "", 0); + } else { + print_metric(config, ctxp, NULL, NULL, + out->force_header ? + (metric_name ? metric_name : name) : "", 0); + } for (i = 1; i < pctx.num_ids; i++) zfree(&pctx.ids[i].name); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 1965aefccb02..be5b493f8284 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -704,9 +704,15 @@ void symsrc__destroy(struct symsrc *ss) close(ss->fd); } -bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr) +bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) { - return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL; + /* + * Usually vmlinux is an ELF file with type ET_EXEC for most + * architectures; except Arm64 kernel is linked with option + * '-share', so need to check type ET_DYN. + */ + return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL || + ehdr.e_type == ET_DYN; } int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name, diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index 10f1ec3e0349..b916afb95ec5 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -73,6 +73,7 @@ struct symbol_conf { const char *symfs; int res_sample; int pad_output_len_dso; + int group_sort_idx; }; extern struct symbol_conf symbol_conf; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 3f28af39f9c6..a661b122d9d8 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -16,6 +16,7 @@ #include "util/synthetic-events.h" #include "util/target.h" #include "util/time-utils.h" +#include "util/cgroup.h" #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/string.h> @@ -414,6 +415,127 @@ out: return rc; } +#ifdef HAVE_FILE_HANDLE +static int perf_event__synthesize_cgroup(struct perf_tool *tool, + union perf_event *event, + char *path, size_t mount_len, + perf_event__handler_t process, + struct machine *machine) +{ + size_t event_size = sizeof(event->cgroup) - sizeof(event->cgroup.path); + size_t path_len = strlen(path) - mount_len + 1; + struct { + struct file_handle fh; + uint64_t cgroup_id; + } handle; + int mount_id; + + while (path_len % sizeof(u64)) + path[mount_len + path_len++] = '\0'; + + memset(&event->cgroup, 0, event_size); + + event->cgroup.header.type = PERF_RECORD_CGROUP; + event->cgroup.header.size = event_size + path_len + machine->id_hdr_size; + + handle.fh.handle_bytes = sizeof(handle.cgroup_id); + if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) { + pr_debug("stat failed: %s\n", path); + return -1; + } + + event->cgroup.id = handle.cgroup_id; + strncpy(event->cgroup.path, path + mount_len, path_len); + memset(event->cgroup.path + path_len, 0, machine->id_hdr_size); + + if (perf_tool__process_synth_event(tool, event, machine, process) < 0) { + pr_debug("process synth event failed\n"); + return -1; + } + + return 0; +} + +static int perf_event__walk_cgroup_tree(struct perf_tool *tool, + union perf_event *event, + char *path, size_t mount_len, + perf_event__handler_t process, + struct machine *machine) +{ + size_t pos = strlen(path); + DIR *d; + struct dirent *dent; + int ret = 0; + + if (perf_event__synthesize_cgroup(tool, event, path, mount_len, + process, machine) < 0) + return -1; + + d = opendir(path); + if (d == NULL) { + pr_debug("failed to open directory: %s\n", path); + return -1; + } + + while ((dent = readdir(d)) != NULL) { + if (dent->d_type != DT_DIR) + continue; + if (!strcmp(dent->d_name, ".") || + !strcmp(dent->d_name, "..")) + continue; + + /* any sane path should be less than PATH_MAX */ + if (strlen(path) + strlen(dent->d_name) + 1 >= PATH_MAX) + continue; + + if (path[pos - 1] != '/') + strcat(path, "/"); + strcat(path, dent->d_name); + + ret = perf_event__walk_cgroup_tree(tool, event, path, + mount_len, process, machine); + if (ret < 0) + break; + + path[pos] = '\0'; + } + + closedir(d); + return ret; +} + +int perf_event__synthesize_cgroups(struct perf_tool *tool, + perf_event__handler_t process, + struct machine *machine) +{ + union perf_event event; + char cgrp_root[PATH_MAX]; + size_t mount_len; /* length of mount point in the path */ + + if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) { + pr_debug("cannot find cgroup mount point\n"); + return -1; + } + + mount_len = strlen(cgrp_root); + /* make sure the path starts with a slash (after mount point) */ + strcat(cgrp_root, "/"); + + if (perf_event__walk_cgroup_tree(tool, &event, cgrp_root, mount_len, + process, machine) < 0) + return -1; + + return 0; +} +#else +int perf_event__synthesize_cgroups(struct perf_tool *tool __maybe_unused, + perf_event__handler_t process __maybe_unused, + struct machine *machine __maybe_unused) +{ + return -1; +} +#endif + int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine) { @@ -1230,6 +1352,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_PHYS_ADDR) result += sizeof(u64); + if (type & PERF_SAMPLE_CGROUP) + result += sizeof(u64); + if (type & PERF_SAMPLE_AUX) { result += sizeof(u64); result += sample->aux_sample.size; @@ -1404,6 +1529,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo array++; } + if (type & PERF_SAMPLE_CGROUP) { + *array = sample->cgroup; + array++; + } + if (type & PERF_SAMPLE_AUX) { sz = sample->aux_sample.size; *array++ = sz; diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h index baead0cdc381..e7a3e9589738 100644 --- a/tools/perf/util/synthetic-events.h +++ b/tools/perf/util/synthetic-events.h @@ -45,6 +45,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handl int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data); int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_namespaces(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_cgroups(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_format, const struct perf_sample *sample); int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine); int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs); diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 2abbf668b8de..3fb67bd31e4a 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -46,6 +46,7 @@ struct perf_tool { mmap2, comm, namespaces, + cgroup, fork, exit, lost, @@ -78,6 +79,7 @@ struct perf_tool { bool ordered_events; bool ordering_requires_timestamps; bool namespace_events; + bool cgroup_events; bool no_warn; enum show_feature_header show_feat_hdr; }; diff --git a/tools/power/acpi/.gitignore b/tools/power/acpi/.gitignore index f698a0e5bfa6..0b319fc8bb17 100644 --- a/tools/power/acpi/.gitignore +++ b/tools/power/acpi/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only /acpidbg /acpidump /ec diff --git a/tools/power/cpupower/.gitignore b/tools/power/cpupower/.gitignore index 1f9977cc609c..7677329c42a6 100644 --- a/tools/power/cpupower/.gitignore +++ b/tools/power/cpupower/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only .libs libcpupower.so libcpupower.so.* diff --git a/tools/power/x86/intel-speed-select/.gitignore b/tools/power/x86/intel-speed-select/.gitignore index f61145925ce9..a814f89fe75f 100644 --- a/tools/power/x86/intel-speed-select/.gitignore +++ b/tools/power/x86/intel-speed-select/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only include/ intel-speed-select diff --git a/tools/power/x86/turbostat/.gitignore b/tools/power/x86/turbostat/.gitignore index 7521370d3568..e13109b43cd1 100644 --- a/tools/power/x86/turbostat/.gitignore +++ b/tools/power/x86/turbostat/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only turbostat diff --git a/tools/spi/.gitignore b/tools/spi/.gitignore index 4280576397e8..14ddba3d2195 100644 --- a/tools/spi/.gitignore +++ b/tools/spi/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only spidev_fdx spidev_test diff --git a/tools/testing/kunit/.gitignore b/tools/testing/kunit/.gitignore index c791ff59a37a..1c63e31f7edf 100644 --- a/tools/testing/kunit/.gitignore +++ b/tools/testing/kunit/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # Byte-compiled / optimized / DLL files __pycache__/ *.py[cod]
\ No newline at end of file diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index dbebf05f5931..47f9cc9dcd94 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -21,8 +21,8 @@ DRIVERS := ../../../drivers NVDIMM_SRC := $(DRIVERS)/nvdimm ACPI_SRC := $(DRIVERS)/acpi/nfit DAX_SRC := $(DRIVERS)/dax -ccflags-y := -I$(src)/$(NVDIMM_SRC)/ -ccflags-y += -I$(src)/$(ACPI_SRC)/ +ccflags-y := -I$(srctree)/drivers/nvdimm/ +ccflags-y += -I$(srctree)/drivers/acpi/nfit/ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o diff --git a/tools/testing/nvdimm/test/Kbuild b/tools/testing/nvdimm/test/Kbuild index fb3c3d7cdb9b..75baebf8f4ba 100644 --- a/tools/testing/nvdimm/test/Kbuild +++ b/tools/testing/nvdimm/test/Kbuild @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y := -I$(src)/../../../../drivers/nvdimm/ -ccflags-y += -I$(src)/../../../../drivers/acpi/nfit/ +ccflags-y := -I$(srctree)/drivers/nvdimm/ +ccflags-y += -I$(srctree)/drivers/acpi/nfit/ obj-m += nfit_test.o obj-m += nfit_test_iomap.o diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index bf6422a6af7f..a8ee5c4d41eb 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -3164,7 +3164,9 @@ static __init int nfit_test_init(void) mcsafe_test(); dax_pmem_test(); dax_pmem_core_test(); +#ifdef CONFIG_DEV_DAX_PMEM_COMPAT dax_pmem_compat_test(); +#endif nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm); diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore index 3834899b6693..d971516401e6 100644 --- a/tools/testing/radix-tree/.gitignore +++ b/tools/testing/radix-tree/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only generated/map-shift.h idr.c idr-test diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore index 304fdf1a21dc..055a5019b13c 100644 --- a/tools/testing/selftests/.gitignore +++ b/tools/testing/selftests/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only gpiogpio-event-mon gpiogpio-hammer gpioinclude/ diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 0635684cbf07..2ff68702fd41 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -38,6 +38,7 @@ TARGETS += net/mptcp TARGETS += netfilter TARGETS += nsfs TARGETS += pidfd +TARGETS += pid_namespace TARGETS += powerpc TARGETS += proc TARGETS += pstore diff --git a/tools/testing/selftests/android/ion/.gitignore b/tools/testing/selftests/android/ion/.gitignore index 95e8f4561474..78eae9972bb1 100644 --- a/tools/testing/selftests/android/ion/.gitignore +++ b/tools/testing/selftests/android/ion/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only ionapp_export ionapp_import ionmap_test diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index 3c5b4e8ff894..78c902045ca7 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only mangle_* fake_sigreturn_* !*.[ch] diff --git a/tools/testing/selftests/arm64/tags/.gitignore b/tools/testing/selftests/arm64/tags/.gitignore index e8fae8d61ed6..f4f6c5112463 100644 --- a/tools/testing/selftests/arm64/tags/.gitignore +++ b/tools/testing/selftests/arm64/tags/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only tags_test diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 2198cd876675..c30079c86998 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only test_verifier test_maps test_lru_map diff --git a/tools/testing/selftests/bpf/map_tests/.gitignore b/tools/testing/selftests/bpf/map_tests/.gitignore index 45984a364647..89c4a3d37544 100644 --- a/tools/testing/selftests/bpf/map_tests/.gitignore +++ b/tools/testing/selftests/bpf/map_tests/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only tests.h diff --git a/tools/testing/selftests/bpf/prog_tests/.gitignore b/tools/testing/selftests/bpf/prog_tests/.gitignore index 45984a364647..89c4a3d37544 100644 --- a/tools/testing/selftests/bpf/prog_tests/.gitignore +++ b/tools/testing/selftests/bpf/prog_tests/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only tests.h diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 16a814eb4d64..56d80adcf4bd 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -19,15 +19,16 @@ void test_mmap(void) const size_t map_sz = roundup_page(sizeof(struct map_data)); const int zero = 0, one = 1, two = 2, far = 1500; const long page_size = sysconf(_SC_PAGE_SIZE); - int err, duration = 0, i, data_map_fd; + int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd; struct bpf_map *data_map, *bss_map; void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; struct test_mmap__bss *bss_data; + struct bpf_map_info map_info; + __u32 map_info_sz = sizeof(map_info); struct map_data *map_data; struct test_mmap *skel; __u64 val = 0; - skel = test_mmap__open_and_load(); if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) return; @@ -36,6 +37,14 @@ void test_mmap(void) data_map = skel->maps.data_map; data_map_fd = bpf_map__fd(data_map); + /* get map's ID */ + memset(&map_info, 0, map_info_sz); + err = bpf_obj_get_info_by_fd(data_map_fd, &map_info, &map_info_sz); + if (CHECK(err, "map_get_info", "failed %d\n", errno)) + goto cleanup; + data_map_id = map_info.id; + + /* mmap BSS map */ bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED, bpf_map__fd(bss_map), 0); if (CHECK(bss_mmaped == MAP_FAILED, "bss_mmap", @@ -98,6 +107,10 @@ void test_mmap(void) "data_map freeze succeeded: err=%d, errno=%d\n", err, errno)) goto cleanup; + err = mprotect(map_mmaped, map_sz, PROT_READ); + if (CHECK(err, "mprotect_ro", "mprotect to r/o failed %d\n", errno)) + goto cleanup; + /* unmap R/W mapping */ err = munmap(map_mmaped, map_sz); map_mmaped = NULL; @@ -111,6 +124,12 @@ void test_mmap(void) map_mmaped = NULL; goto cleanup; } + err = mprotect(map_mmaped, map_sz, PROT_WRITE); + if (CHECK(!err, "mprotect_wr", "mprotect() succeeded unexpectedly!\n")) + goto cleanup; + err = mprotect(map_mmaped, map_sz, PROT_EXEC); + if (CHECK(!err, "mprotect_ex", "mprotect() succeeded unexpectedly!\n")) + goto cleanup; map_data = map_mmaped; /* map/unmap in a loop to test ref counting */ @@ -197,6 +216,45 @@ void test_mmap(void) CHECK_FAIL(map_data->val[far] != 3 * 321); munmap(tmp2, 4 * page_size); + + tmp1 = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0); + if (CHECK(tmp1 == MAP_FAILED, "last_mmap", "failed %d\n", errno)) + goto cleanup; + + test_mmap__destroy(skel); + skel = NULL; + CHECK_FAIL(munmap(bss_mmaped, bss_sz)); + bss_mmaped = NULL; + CHECK_FAIL(munmap(map_mmaped, map_sz)); + map_mmaped = NULL; + + /* map should be still held by active mmap */ + tmp_fd = bpf_map_get_fd_by_id(data_map_id); + if (CHECK(tmp_fd < 0, "get_map_by_id", "failed %d\n", errno)) { + munmap(tmp1, map_sz); + goto cleanup; + } + close(tmp_fd); + + /* this should release data map finally */ + munmap(tmp1, map_sz); + + /* we need to wait for RCU grace period */ + for (i = 0; i < 10000; i++) { + __u32 id = data_map_id - 1; + if (bpf_map_get_next_id(id, &id) || id > data_map_id) + break; + usleep(1); + } + + /* should fail to get map FD by non-existing ID */ + tmp_fd = bpf_map_get_fd_by_id(data_map_id); + if (CHECK(tmp_fd >= 0, "get_map_by_id_after", + "unexpectedly succeeded %d\n", tmp_fd)) { + close(tmp_fd); + goto cleanup; + } + cleanup: if (bss_mmaped) CHECK_FAIL(munmap(bss_mmaped, bss_sz)); diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c index 9d9351dc2ded..713167449c98 100644 --- a/tools/testing/selftests/bpf/prog_tests/section_names.c +++ b/tools/testing/selftests/bpf/prog_tests/section_names.c @@ -43,18 +43,18 @@ static struct sec_name_test tests[] = { {"lwt_seg6local", {0, BPF_PROG_TYPE_LWT_SEG6LOCAL, 0}, {-EINVAL, 0} }, { "cgroup_skb/ingress", - {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, + {0, BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_INGRESS}, {0, BPF_CGROUP_INET_INGRESS}, }, { "cgroup_skb/egress", - {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, + {0, BPF_PROG_TYPE_CGROUP_SKB, BPF_CGROUP_INET_EGRESS}, {0, BPF_CGROUP_INET_EGRESS}, }, {"cgroup/skb", {0, BPF_PROG_TYPE_CGROUP_SKB, 0}, {-EINVAL, 0} }, { "cgroup/sock", - {0, BPF_PROG_TYPE_CGROUP_SOCK, 0}, + {0, BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE}, {0, BPF_CGROUP_INET_SOCK_CREATE}, }, { @@ -69,26 +69,38 @@ static struct sec_name_test tests[] = { }, { "cgroup/dev", - {0, BPF_PROG_TYPE_CGROUP_DEVICE, 0}, + {0, BPF_PROG_TYPE_CGROUP_DEVICE, BPF_CGROUP_DEVICE}, {0, BPF_CGROUP_DEVICE}, }, - {"sockops", {0, BPF_PROG_TYPE_SOCK_OPS, 0}, {0, BPF_CGROUP_SOCK_OPS} }, + { + "sockops", + {0, BPF_PROG_TYPE_SOCK_OPS, BPF_CGROUP_SOCK_OPS}, + {0, BPF_CGROUP_SOCK_OPS}, + }, { "sk_skb/stream_parser", - {0, BPF_PROG_TYPE_SK_SKB, 0}, + {0, BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_PARSER}, {0, BPF_SK_SKB_STREAM_PARSER}, }, { "sk_skb/stream_verdict", - {0, BPF_PROG_TYPE_SK_SKB, 0}, + {0, BPF_PROG_TYPE_SK_SKB, BPF_SK_SKB_STREAM_VERDICT}, {0, BPF_SK_SKB_STREAM_VERDICT}, }, {"sk_skb", {0, BPF_PROG_TYPE_SK_SKB, 0}, {-EINVAL, 0} }, - {"sk_msg", {0, BPF_PROG_TYPE_SK_MSG, 0}, {0, BPF_SK_MSG_VERDICT} }, - {"lirc_mode2", {0, BPF_PROG_TYPE_LIRC_MODE2, 0}, {0, BPF_LIRC_MODE2} }, + { + "sk_msg", + {0, BPF_PROG_TYPE_SK_MSG, BPF_SK_MSG_VERDICT}, + {0, BPF_SK_MSG_VERDICT}, + }, + { + "lirc_mode2", + {0, BPF_PROG_TYPE_LIRC_MODE2, BPF_LIRC_MODE2}, + {0, BPF_LIRC_MODE2}, + }, { "flow_dissector", - {0, BPF_PROG_TYPE_FLOW_DISSECTOR, 0}, + {0, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_FLOW_DISSECTOR}, {0, BPF_FLOW_DISSECTOR}, }, { @@ -158,17 +170,17 @@ static void test_prog_type_by_name(const struct sec_name_test *test) &expected_attach_type); CHECK(rc != test->expected_load.rc, "check_code", - "prog: unexpected rc=%d for %s", rc, test->sec_name); + "prog: unexpected rc=%d for %s\n", rc, test->sec_name); if (rc) return; CHECK(prog_type != test->expected_load.prog_type, "check_prog_type", - "prog: unexpected prog_type=%d for %s", + "prog: unexpected prog_type=%d for %s\n", prog_type, test->sec_name); CHECK(expected_attach_type != test->expected_load.expected_attach_type, - "check_attach_type", "prog: unexpected expected_attach_type=%d for %s", + "check_attach_type", "prog: unexpected expected_attach_type=%d for %s\n", expected_attach_type, test->sec_name); } @@ -180,13 +192,13 @@ static void test_attach_type_by_name(const struct sec_name_test *test) rc = libbpf_attach_type_by_name(test->sec_name, &attach_type); CHECK(rc != test->expected_attach.rc, "check_ret", - "attach: unexpected rc=%d for %s", rc, test->sec_name); + "attach: unexpected rc=%d for %s\n", rc, test->sec_name); if (rc) return; CHECK(attach_type != test->expected_attach.attach_type, - "check_attach_type", "attach: unexpected attach_type=%d for %s", + "check_attach_type", "attach: unexpected attach_type=%d for %s\n", attach_type, test->sec_name); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c index 1e4c258de09d..b17eb2045c1d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c +++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c @@ -15,7 +15,10 @@ char *CMD_ARGS[] = {"true", NULL}; -int heap_mprotect(void) +#define GET_PAGE_ADDR(ADDR, PAGE_SIZE) \ + (char *)(((unsigned long) (ADDR + PAGE_SIZE)) & ~(PAGE_SIZE-1)) + +int stack_mprotect(void) { void *buf; long sz; @@ -25,12 +28,9 @@ int heap_mprotect(void) if (sz < 0) return sz; - buf = memalign(sz, 2 * sz); - if (buf == NULL) - return -ENOMEM; - - ret = mprotect(buf, sz, PROT_READ | PROT_WRITE | PROT_EXEC); - free(buf); + buf = alloca(sz * 3); + ret = mprotect(GET_PAGE_ADDR(buf, sz), sz, + PROT_READ | PROT_WRITE | PROT_EXEC); return ret; } @@ -73,8 +73,8 @@ void test_test_lsm(void) skel->bss->monitored_pid = getpid(); - err = heap_mprotect(); - if (CHECK(errno != EPERM, "heap_mprotect", "want errno=EPERM, got %d\n", + err = stack_mprotect(); + if (CHECK(errno != EPERM, "stack_mprotect", "want err=EPERM, got %d\n", errno)) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c index 05b294d6b923..15ef3531483e 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -6,19 +6,34 @@ void test_xdp_attach(void) { + __u32 duration = 0, id1, id2, id0 = 0, len; struct bpf_object *obj1, *obj2, *obj3; const char *file = "./test_xdp.o"; + struct bpf_prog_info info = {}; int err, fd1, fd2, fd3; - __u32 duration = 0; DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1); + len = sizeof(info); + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1); if (CHECK_FAIL(err)) return; + err = bpf_obj_get_info_by_fd(fd1, &info, &len); + if (CHECK_FAIL(err)) + goto out_1; + id1 = info.id; + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj2, &fd2); if (CHECK_FAIL(err)) goto out_1; + + memset(&info, 0, sizeof(info)); + err = bpf_obj_get_info_by_fd(fd2, &info, &len); + if (CHECK_FAIL(err)) + goto out_2; + id2 = info.id; + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj3, &fd3); if (CHECK_FAIL(err)) goto out_2; @@ -28,6 +43,11 @@ void test_xdp_attach(void) if (CHECK(err, "load_ok", "initial load failed")) goto out_close; + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != id1, "id1_check", + "loaded prog id %u != id1 %u, err %d", id0, id1, err)) + goto out_close; + err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, &opts); if (CHECK(!err, "load_fail", "load with expected id didn't fail")) @@ -37,6 +57,10 @@ void test_xdp_attach(void) err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts); if (CHECK(err, "replace_ok", "replace valid old_fd failed")) goto out; + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != id2, "id2_check", + "loaded prog id %u != id2 %u, err %d", id0, id2, err)) + goto out_close; err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts); if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail")) @@ -51,6 +75,10 @@ void test_xdp_attach(void) if (CHECK(err, "remove_ok", "remove valid old_fd failed")) goto out; + err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + if (CHECK(err || id0 != 0, "unload_check", + "loaded prog id %u != 0, err %d", id0, err)) + goto out_close; out: bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); out_close: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c new file mode 100644 index 000000000000..d2d7a283d72f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/if_link.h> +#include <test_progs.h> + +#define IFINDEX_LO 1 + +void test_xdp_info(void) +{ + __u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id; + const char *file = "./xdp_dummy.o"; + struct bpf_prog_info info = {}; + struct bpf_object *obj; + int err, prog_fd; + + /* Get prog_id for XDP_ATTACHED_NONE mode */ + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + if (CHECK(err, "get_xdp_none", "errno=%d\n", errno)) + return; + if (CHECK(prog_id, "prog_id_none", "unexpected prog_id=%u\n", prog_id)) + return; + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + if (CHECK(err, "get_xdp_none_skb", "errno=%d\n", errno)) + return; + if (CHECK(prog_id, "prog_id_none_skb", "unexpected prog_id=%u\n", + prog_id)) + return; + + /* Setup prog */ + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (CHECK_FAIL(err)) + return; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &len); + if (CHECK(err, "get_prog_info", "errno=%d\n", errno)) + goto out_close; + + err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + if (CHECK(err, "set_xdp_skb", "errno=%d\n", errno)) + goto out_close; + + /* Get prog_id for single prog mode */ + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + if (CHECK(err, "get_xdp", "errno=%d\n", errno)) + goto out; + if (CHECK(prog_id != info.id, "prog_id", "prog_id not available\n")) + goto out; + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + if (CHECK(err, "get_xdp_skb", "errno=%d\n", errno)) + goto out; + if (CHECK(prog_id != info.id, "prog_id_skb", "prog_id not available\n")) + goto out; + + err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_DRV_MODE); + if (CHECK(err, "get_xdp_drv", "errno=%d\n", errno)) + goto out; + if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id)) + goto out; + +out: + bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); +out_close: + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c index a4e3c223028d..b4598d4bc4f7 100644 --- a/tools/testing/selftests/bpf/progs/lsm.c +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -23,12 +23,12 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma, return ret; __u32 pid = bpf_get_current_pid_tgid() >> 32; - int is_heap = 0; + int is_stack = 0; - is_heap = (vma->vm_start >= vma->vm_mm->start_brk && - vma->vm_end <= vma->vm_mm->brk); + is_stack = (vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack); - if (is_heap && monitored_pid == pid) { + if (is_stack && monitored_pid == pid) { mprotect_count++; ret = -EPERM; } diff --git a/tools/testing/selftests/bpf/verifier/.gitignore b/tools/testing/selftests/bpf/verifier/.gitignore index 45984a364647..89c4a3d37544 100644 --- a/tools/testing/selftests/bpf/verifier/.gitignore +++ b/tools/testing/selftests/bpf/verifier/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only tests.h diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 4d0d09574bf4..a253a064e6e0 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -501,7 +501,7 @@ .result = REJECT }, { - "bounds check mixed 32bit and 64bit arithmatic. test1", + "bounds check mixed 32bit and 64bit arithmetic. test1", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_MOV64_IMM(BPF_REG_1, -1), @@ -520,7 +520,7 @@ .result = ACCEPT }, { - "bounds check mixed 32bit and 64bit arithmatic. test2", + "bounds check mixed 32bit and 64bit arithmetic. test2", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_MOV64_IMM(BPF_REG_1, -1), diff --git a/tools/testing/selftests/breakpoints/.gitignore b/tools/testing/selftests/breakpoints/.gitignore index a23bb4a6f06c..def2e97dab9a 100644 --- a/tools/testing/selftests/breakpoints/.gitignore +++ b/tools/testing/selftests/breakpoints/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only breakpoint_test step_after_suspend_test diff --git a/tools/testing/selftests/capabilities/.gitignore b/tools/testing/selftests/capabilities/.gitignore index b732dd0d4738..426d9adca67c 100644 --- a/tools/testing/selftests/capabilities/.gitignore +++ b/tools/testing/selftests/capabilities/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only test_execve validate_cap diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore index 7f9835624793..aa6de65b0838 100644 --- a/tools/testing/selftests/cgroup/.gitignore +++ b/tools/testing/selftests/cgroup/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only test_memcontrol test_core test_freezer diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile index 66aafe1f5746..967f268fde74 100644 --- a/tools/testing/selftests/cgroup/Makefile +++ b/tools/testing/selftests/cgroup/Makefile @@ -11,6 +11,6 @@ TEST_GEN_PROGS += test_freezer include ../lib.mk -$(OUTPUT)/test_memcontrol: cgroup_util.c -$(OUTPUT)/test_core: cgroup_util.c -$(OUTPUT)/test_freezer: cgroup_util.c +$(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h +$(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h +$(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 8f7131dcf1ff..8a637ca7d73a 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -15,6 +15,7 @@ #include <unistd.h> #include "cgroup_util.h" +#include "../clone3/clone3_selftests.h" static ssize_t read_text(const char *path, char *buf, size_t max_len) { @@ -331,12 +332,112 @@ int cg_run(const char *cgroup, } } +pid_t clone_into_cgroup(int cgroup_fd) +{ +#ifdef CLONE_ARGS_SIZE_VER2 + pid_t pid; + + struct clone_args args = { + .flags = CLONE_INTO_CGROUP, + .exit_signal = SIGCHLD, + .cgroup = cgroup_fd, + }; + + pid = sys_clone3(&args, sizeof(struct clone_args)); + /* + * Verify that this is a genuine test failure: + * ENOSYS -> clone3() not available + * E2BIG -> CLONE_INTO_CGROUP not available + */ + if (pid < 0 && (errno == ENOSYS || errno == E2BIG)) + goto pretend_enosys; + + return pid; + +pretend_enosys: +#endif + errno = ENOSYS; + return -ENOSYS; +} + +int clone_reap(pid_t pid, int options) +{ + int ret; + siginfo_t info = { + .si_signo = 0, + }; + +again: + ret = waitid(P_PID, pid, &info, options | __WALL | __WNOTHREAD); + if (ret < 0) { + if (errno == EINTR) + goto again; + return -1; + } + + if (options & WEXITED) { + if (WIFEXITED(info.si_status)) + return WEXITSTATUS(info.si_status); + } + + if (options & WSTOPPED) { + if (WIFSTOPPED(info.si_status)) + return WSTOPSIG(info.si_status); + } + + if (options & WCONTINUED) { + if (WIFCONTINUED(info.si_status)) + return 0; + } + + return -1; +} + +int dirfd_open_opath(const char *dir) +{ + return open(dir, O_DIRECTORY | O_CLOEXEC | O_NOFOLLOW | O_PATH); +} + +#define close_prot_errno(fd) \ + if (fd >= 0) { \ + int _e_ = errno; \ + close(fd); \ + errno = _e_; \ + } + +static int clone_into_cgroup_run_nowait(const char *cgroup, + int (*fn)(const char *cgroup, void *arg), + void *arg) +{ + int cgroup_fd; + pid_t pid; + + cgroup_fd = dirfd_open_opath(cgroup); + if (cgroup_fd < 0) + return -1; + + pid = clone_into_cgroup(cgroup_fd); + close_prot_errno(cgroup_fd); + if (pid == 0) + exit(fn(cgroup, arg)); + + return pid; +} + int cg_run_nowait(const char *cgroup, int (*fn)(const char *cgroup, void *arg), void *arg) { int pid; + pid = clone_into_cgroup_run_nowait(cgroup, fn, arg); + if (pid > 0) + return pid; + + /* Genuine test failure. */ + if (pid < 0 && errno != ENOSYS) + return -1; + pid = fork(); if (pid == 0) { char buf[64]; @@ -450,3 +551,28 @@ int proc_read_strstr(int pid, bool thread, const char *item, const char *needle) return strstr(buf, needle) ? 0 : -1; } + +int clone_into_cgroup_run_wait(const char *cgroup) +{ + int cgroup_fd; + pid_t pid; + + cgroup_fd = dirfd_open_opath(cgroup); + if (cgroup_fd < 0) + return -1; + + pid = clone_into_cgroup(cgroup_fd); + close_prot_errno(cgroup_fd); + if (pid < 0) + return -1; + + if (pid == 0) + exit(EXIT_SUCCESS); + + /* + * We don't care whether this fails. We only care whether the initial + * clone succeeded. + */ + (void)clone_reap(pid, WEXITED); + return 0; +} diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 49c54fbdb229..5a1305dd1f0b 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -50,3 +50,7 @@ extern int cg_wait_for_proc_count(const char *cgroup, int count); extern int cg_killall(const char *cgroup); extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size); extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle); +extern pid_t clone_into_cgroup(int cgroup_fd); +extern int clone_reap(pid_t pid, int options); +extern int clone_into_cgroup_run_wait(const char *cgroup); +extern int dirfd_open_opath(const char *dir); diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index e19ce940cd6a..3df648c37876 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -2,7 +2,10 @@ #include <linux/limits.h> #include <sys/types.h> +#include <sys/mman.h> +#include <sys/wait.h> #include <unistd.h> +#include <fcntl.h> #include <stdio.h> #include <errno.h> #include <signal.h> @@ -12,6 +15,115 @@ #include "../kselftest.h" #include "cgroup_util.h" +static int touch_anon(char *buf, size_t size) +{ + int fd; + char *pos = buf; + + fd = open("/dev/urandom", O_RDONLY); + if (fd < 0) + return -1; + + while (size > 0) { + ssize_t ret = read(fd, pos, size); + + if (ret < 0) { + if (errno != EINTR) { + close(fd); + return -1; + } + } else { + pos += ret; + size -= ret; + } + } + close(fd); + + return 0; +} + +static int alloc_and_touch_anon_noexit(const char *cgroup, void *arg) +{ + int ppid = getppid(); + size_t size = (size_t)arg; + void *buf; + + buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, + 0, 0); + if (buf == MAP_FAILED) + return -1; + + if (touch_anon((char *)buf, size)) { + munmap(buf, size); + return -1; + } + + while (getppid() == ppid) + sleep(1); + + munmap(buf, size); + return 0; +} + +/* + * Create a child process that allocates and touches 100MB, then waits to be + * killed. Wait until the child is attached to the cgroup, kill all processes + * in that cgroup and wait until "cgroup.procs" is empty. At this point try to + * destroy the empty cgroup. The test helps detect race conditions between + * dying processes leaving the cgroup and cgroup destruction path. + */ +static int test_cgcore_destroy(const char *root) +{ + int ret = KSFT_FAIL; + char *cg_test = NULL; + int child_pid; + char buf[PAGE_SIZE]; + + cg_test = cg_name(root, "cg_test"); + + if (!cg_test) + goto cleanup; + + for (int i = 0; i < 10; i++) { + if (cg_create(cg_test)) + goto cleanup; + + child_pid = cg_run_nowait(cg_test, alloc_and_touch_anon_noexit, + (void *) MB(100)); + + if (child_pid < 0) + goto cleanup; + + /* wait for the child to enter cgroup */ + if (cg_wait_for_proc_count(cg_test, 1)) + goto cleanup; + + if (cg_killall(cg_test)) + goto cleanup; + + /* wait for cgroup to be empty */ + while (1) { + if (cg_read(cg_test, "cgroup.procs", buf, sizeof(buf))) + goto cleanup; + if (buf[0] == '\0') + break; + usleep(1000); + } + + if (rmdir(cg_test)) + goto cleanup; + + if (waitpid(child_pid, NULL, 0) < 0) + goto cleanup; + } + ret = KSFT_PASS; +cleanup: + if (cg_test) + cg_destroy(cg_test); + free(cg_test); + return ret; +} + /* * A(0) - B(0) - C(1) * \ D(0) @@ -25,8 +137,11 @@ static int test_cgcore_populated(const char *root) { int ret = KSFT_FAIL; + int err; char *cg_test_a = NULL, *cg_test_b = NULL; char *cg_test_c = NULL, *cg_test_d = NULL; + int cgroup_fd = -EBADF; + pid_t pid; cg_test_a = cg_name(root, "cg_test_a"); cg_test_b = cg_name(root, "cg_test_a/cg_test_b"); @@ -78,6 +193,52 @@ static int test_cgcore_populated(const char *root) if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n")) goto cleanup; + /* Test that we can directly clone into a new cgroup. */ + cgroup_fd = dirfd_open_opath(cg_test_d); + if (cgroup_fd < 0) + goto cleanup; + + pid = clone_into_cgroup(cgroup_fd); + if (pid < 0) { + if (errno == ENOSYS) + goto cleanup_pass; + goto cleanup; + } + + if (pid == 0) { + if (raise(SIGSTOP)) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + err = cg_read_strcmp(cg_test_d, "cgroup.events", "populated 1\n"); + + (void)clone_reap(pid, WSTOPPED); + (void)kill(pid, SIGCONT); + (void)clone_reap(pid, WEXITED); + + if (err) + goto cleanup; + + if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n")) + goto cleanup; + + /* Remove cgroup. */ + if (cg_test_d) { + cg_destroy(cg_test_d); + free(cg_test_d); + cg_test_d = NULL; + } + + pid = clone_into_cgroup(cgroup_fd); + if (pid < 0) + goto cleanup_pass; + if (pid == 0) + exit(EXIT_SUCCESS); + (void)clone_reap(pid, WEXITED); + goto cleanup; + +cleanup_pass: ret = KSFT_PASS; cleanup: @@ -93,6 +254,8 @@ cleanup: free(cg_test_c); free(cg_test_b); free(cg_test_a); + if (cgroup_fd >= 0) + close(cgroup_fd); return ret; } @@ -136,6 +299,16 @@ static int test_cgcore_invalid_domain(const char *root) if (errno != EOPNOTSUPP) goto cleanup; + if (!clone_into_cgroup_run_wait(child)) + goto cleanup; + + if (errno == ENOSYS) + goto cleanup_pass; + + if (errno != EOPNOTSUPP) + goto cleanup; + +cleanup_pass: ret = KSFT_PASS; cleanup: @@ -345,6 +518,9 @@ static int test_cgcore_internal_process_constraint(const char *root) if (!cg_enter_current(parent)) goto cleanup; + if (!clone_into_cgroup_run_wait(parent)) + goto cleanup; + ret = KSFT_PASS; cleanup: @@ -512,6 +688,7 @@ struct corecg_test { T(test_cgcore_populated), T(test_cgcore_proc_migration), T(test_cgcore_thread_migration), + T(test_cgcore_destroy), }; #undef T diff --git a/tools/testing/selftests/clone3/.gitignore b/tools/testing/selftests/clone3/.gitignore index 0dc4f32c6cb8..a81085742d40 100644 --- a/tools/testing/selftests/clone3/.gitignore +++ b/tools/testing/selftests/clone3/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only clone3 clone3_clear_sighand clone3_set_tid diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h index a3f2c8ad8bcc..91c1a78ddb39 100644 --- a/tools/testing/selftests/clone3/clone3_selftests.h +++ b/tools/testing/selftests/clone3/clone3_selftests.h @@ -5,12 +5,24 @@ #define _GNU_SOURCE #include <sched.h> +#include <linux/sched.h> +#include <linux/types.h> #include <stdint.h> #include <syscall.h> -#include <linux/types.h> +#include <sys/wait.h> + +#include "../kselftest.h" #define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr))) +#ifndef CLONE_INTO_CGROUP +#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */ +#endif + +#ifndef CLONE_ARGS_SIZE_VER0 +#define CLONE_ARGS_SIZE_VER0 64 +#endif + #ifndef __NR_clone3 #define __NR_clone3 -1 struct clone_args { @@ -22,10 +34,13 @@ struct clone_args { __aligned_u64 stack; __aligned_u64 stack_size; __aligned_u64 tls; +#define CLONE_ARGS_SIZE_VER1 80 __aligned_u64 set_tid; __aligned_u64 set_tid_size; +#define CLONE_ARGS_SIZE_VER2 88 + __aligned_u64 cgroup; }; -#endif +#endif /* __NR_clone3 */ static pid_t sys_clone3(struct clone_args *args, size_t size) { diff --git a/tools/testing/selftests/drivers/.gitignore b/tools/testing/selftests/drivers/.gitignore index f6aebcc27b76..ca74f2e1c719 100644 --- a/tools/testing/selftests/drivers/.gitignore +++ b/tools/testing/selftests/drivers/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only /dma-buf/udmabuf diff --git a/tools/testing/selftests/efivarfs/.gitignore b/tools/testing/selftests/efivarfs/.gitignore index 33618493562b..807407f7f58b 100644 --- a/tools/testing/selftests/efivarfs/.gitignore +++ b/tools/testing/selftests/efivarfs/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only create-read open-unlink diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore index b02279da6fa1..c078ece12ff0 100644 --- a/tools/testing/selftests/exec/.gitignore +++ b/tools/testing/selftests/exec/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only subdir* script* execveat diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore index 8449cf6716ce..f0c0ff20d6cf 100644 --- a/tools/testing/selftests/filesystems/.gitignore +++ b/tools/testing/selftests/filesystems/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only dnotify_test devpts_pts diff --git a/tools/testing/selftests/filesystems/binderfs/.gitignore b/tools/testing/selftests/filesystems/binderfs/.gitignore index 8a5d9bf63dd4..8e5cf9084894 100644 --- a/tools/testing/selftests/filesystems/binderfs/.gitignore +++ b/tools/testing/selftests/filesystems/binderfs/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only binderfs_test diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile index 58cb659b56b4..8af25ae96049 100644 --- a/tools/testing/selftests/filesystems/binderfs/Makefile +++ b/tools/testing/selftests/filesystems/binderfs/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I../../../../../usr/include/ +CFLAGS += -I../../../../../usr/include/ -pthread TEST_GEN_PROGS := binderfs_test +binderfs_test: binderfs_test.c ../../kselftest.h ../../kselftest_harness.h + include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 8c2ed962e1c7..8a6b507e34a8 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -3,114 +3,47 @@ #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> +#include <pthread.h> #include <sched.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/fsuid.h> #include <sys/ioctl.h> #include <sys/mount.h> +#include <sys/socket.h> #include <sys/stat.h> +#include <sys/sysinfo.h> #include <sys/types.h> +#include <sys/wait.h> #include <unistd.h> #include <linux/android/binder.h> #include <linux/android/binderfs.h> -#include "../../kselftest.h" - -static ssize_t write_nointr(int fd, const void *buf, size_t count) -{ - ssize_t ret; -again: - ret = write(fd, buf, count); - if (ret < 0 && errno == EINTR) - goto again; - - return ret; -} -static void write_to_file(const char *filename, const void *buf, size_t count, - int allowed_errno) -{ - int fd, saved_errno; - ssize_t ret; +#include "../../kselftest.h" +#include "../../kselftest_harness.h" - fd = open(filename, O_WRONLY | O_CLOEXEC); - if (fd < 0) - ksft_exit_fail_msg("%s - Failed to open file %s\n", - strerror(errno), filename); +#define DEFAULT_THREADS 4 - ret = write_nointr(fd, buf, count); - if (ret < 0) { - if (allowed_errno && (errno == allowed_errno)) { - close(fd); - return; - } +#define PTR_TO_INT(p) ((int)((intptr_t)(p))) +#define INT_TO_PTR(u) ((void *)((intptr_t)(u))) - goto on_error; +#define close_prot_errno_disarm(fd) \ + if (fd >= 0) { \ + int _e_ = errno; \ + close(fd); \ + errno = _e_; \ + fd = -EBADF; \ } - if ((size_t)ret != count) - goto on_error; - - close(fd); - return; - -on_error: - saved_errno = errno; - close(fd); - errno = saved_errno; - - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to write to file %s\n", - strerror(errno), filename); - - ksft_exit_fail_msg("Failed to write to file %s\n", filename); -} - -static void change_to_userns(void) -{ - int ret; - uid_t uid; - gid_t gid; - /* {g,u}id_map files only allow a max of 4096 bytes written to them */ - char idmap[4096]; - - uid = getuid(); - gid = getgid(); - - ret = unshare(CLONE_NEWUSER); - if (ret < 0) - ksft_exit_fail_msg("%s - Failed to unshare user namespace\n", - strerror(errno)); - - write_to_file("/proc/self/setgroups", "deny", strlen("deny"), ENOENT); - - ret = snprintf(idmap, sizeof(idmap), "0 %d 1", uid); - if (ret < 0 || (size_t)ret >= sizeof(idmap)) - ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n", - strerror(errno)); - - write_to_file("/proc/self/uid_map", idmap, strlen(idmap), 0); - - ret = snprintf(idmap, sizeof(idmap), "0 %d 1", gid); - if (ret < 0 || (size_t)ret >= sizeof(idmap)) - ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n", - strerror(errno)); - - write_to_file("/proc/self/gid_map", idmap, strlen(idmap), 0); - - ret = setgid(0); - if (ret) - ksft_exit_fail_msg("%s - Failed to setgid(0)\n", - strerror(errno)); +#define log_exit(format, ...) \ + ({ \ + fprintf(stderr, format "\n", ##__VA_ARGS__); \ + exit(EXIT_FAILURE); \ + }) - ret = setuid(0); - if (ret) - ksft_exit_fail_msg("%s - Failed to setgid(0)\n", - strerror(errno)); -} - -static void change_to_mountns(void) +static void change_mountns(void) { int ret; @@ -132,36 +65,31 @@ static void rmdir_protect_errno(const char *dir) errno = saved_errno; } -static void __do_binderfs_test(void) +static int __do_binderfs_test(void) { int fd, ret, saved_errno; size_t len; ssize_t wret; - bool keep = false; struct binderfs_device device = { 0 }; struct binder_version version = { 0 }; + char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX", + device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME]; - change_to_mountns(); - - ret = mkdir("/dev/binderfs", 0755); - if (ret < 0) { - if (errno != EEXIST) - ksft_exit_fail_msg( - "%s - Failed to create binderfs mountpoint\n", - strerror(errno)); + change_mountns(); - keep = true; - } + if (!mkdtemp(binderfs_mntpt)) + ksft_exit_fail_msg( + "%s - Failed to create binderfs mountpoint\n", + strerror(errno)); - ret = mount(NULL, "/dev/binderfs", "binder", 0, 0); + ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); if (ret < 0) { if (errno != ENODEV) ksft_exit_fail_msg("%s - Failed to mount binderfs\n", strerror(errno)); - keep ? : rmdir_protect_errno("/dev/binderfs"); - ksft_exit_skip( - "The Android binderfs filesystem is not available\n"); + rmdir_protect_errno(binderfs_mntpt); + return 1; } /* binderfs mount test passed */ @@ -169,7 +97,8 @@ static void __do_binderfs_test(void) memcpy(device.name, "my-binder", strlen("my-binder")); - fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); + snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); + fd = open(device_path, O_RDONLY | O_CLOEXEC); if (fd < 0) ksft_exit_fail_msg( "%s - Failed to open binder-control device\n", @@ -180,7 +109,7 @@ static void __do_binderfs_test(void) close(fd); errno = saved_errno; if (ret < 0) { - keep ? : rmdir_protect_errno("/dev/binderfs"); + rmdir_protect_errno(binderfs_mntpt); ksft_exit_fail_msg( "%s - Failed to allocate new binder device\n", strerror(errno)); @@ -193,9 +122,10 @@ static void __do_binderfs_test(void) /* binder device allocation test passed */ ksft_inc_pass_cnt(); - fd = open("/dev/binderfs/my-binder", O_CLOEXEC | O_RDONLY); + snprintf(device_path, sizeof(device_path), "%s/my-binder", binderfs_mntpt); + fd = open(device_path, O_CLOEXEC | O_RDONLY); if (fd < 0) { - keep ? : rmdir_protect_errno("/dev/binderfs"); + rmdir_protect_errno(binderfs_mntpt); ksft_exit_fail_msg("%s - Failed to open my-binder device\n", strerror(errno)); } @@ -205,7 +135,7 @@ static void __do_binderfs_test(void) close(fd); errno = saved_errno; if (ret < 0) { - keep ? : rmdir_protect_errno("/dev/binderfs"); + rmdir_protect_errno(binderfs_mntpt); ksft_exit_fail_msg( "%s - Failed to open perform BINDER_VERSION request\n", strerror(errno)); @@ -217,9 +147,9 @@ static void __do_binderfs_test(void) /* binder transaction with binderfs binder device passed */ ksft_inc_pass_cnt(); - ret = unlink("/dev/binderfs/my-binder"); + ret = unlink(device_path); if (ret < 0) { - keep ? : rmdir_protect_errno("/dev/binderfs"); + rmdir_protect_errno(binderfs_mntpt); ksft_exit_fail_msg("%s - Failed to delete binder device\n", strerror(errno)); } @@ -227,12 +157,13 @@ static void __do_binderfs_test(void) /* binder device removal passed */ ksft_inc_pass_cnt(); - ret = unlink("/dev/binderfs/binder-control"); + snprintf(device_path, sizeof(device_path), "%s/binder-control", binderfs_mntpt); + ret = unlink(device_path); if (!ret) { - keep ? : rmdir_protect_errno("/dev/binderfs"); + rmdir_protect_errno(binderfs_mntpt); ksft_exit_fail_msg("Managed to delete binder-control device\n"); } else if (errno != EPERM) { - keep ? : rmdir_protect_errno("/dev/binderfs"); + rmdir_protect_errno(binderfs_mntpt); ksft_exit_fail_msg( "%s - Failed to delete binder-control device but exited with unexpected error code\n", strerror(errno)); @@ -242,34 +173,341 @@ static void __do_binderfs_test(void) ksft_inc_xfail_cnt(); on_error: - ret = umount2("/dev/binderfs", MNT_DETACH); - keep ?: rmdir_protect_errno("/dev/binderfs"); + ret = umount2(binderfs_mntpt, MNT_DETACH); + rmdir_protect_errno(binderfs_mntpt); if (ret < 0) ksft_exit_fail_msg("%s - Failed to unmount binderfs\n", strerror(errno)); /* binderfs unmount test passed */ ksft_inc_pass_cnt(); + return 0; } -static void binderfs_test_privileged() +static int wait_for_pid(pid_t pid) { - if (geteuid() != 0) - ksft_print_msg( - "Tests are not run as root. Skipping privileged tests\n"); - else - __do_binderfs_test(); + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static int setid_userns_root(void) +{ + if (setuid(0)) + return -1; + if (setgid(0)) + return -1; + + setfsuid(0); + setfsgid(0); + + return 0; +} + +enum idmap_type { + UID_MAP, + GID_MAP, +}; + +static ssize_t read_nointr(int fd, void *buf, size_t count) +{ + ssize_t ret; +again: + ret = read(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; +again: + ret = write(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +static int write_id_mapping(enum idmap_type type, pid_t pid, const char *buf, + size_t buf_size) +{ + int fd; + int ret; + char path[4096]; + + if (type == GID_MAP) { + int setgroups_fd; + + snprintf(path, sizeof(path), "/proc/%d/setgroups", pid); + setgroups_fd = open(path, O_WRONLY | O_CLOEXEC | O_NOFOLLOW); + if (setgroups_fd < 0 && errno != ENOENT) + return -1; + + if (setgroups_fd >= 0) { + ret = write_nointr(setgroups_fd, "deny", sizeof("deny") - 1); + close_prot_errno_disarm(setgroups_fd); + if (ret != sizeof("deny") - 1) + return -1; + } + } + + switch (type) { + case UID_MAP: + ret = snprintf(path, sizeof(path), "/proc/%d/uid_map", pid); + break; + case GID_MAP: + ret = snprintf(path, sizeof(path), "/proc/%d/gid_map", pid); + break; + default: + return -1; + } + if (ret < 0 || ret >= sizeof(path)) + return -E2BIG; + + fd = open(path, O_WRONLY | O_CLOEXEC | O_NOFOLLOW); + if (fd < 0) + return -1; + + ret = write_nointr(fd, buf, buf_size); + close_prot_errno_disarm(fd); + if (ret != buf_size) + return -1; + + return 0; +} + +static void change_userns(int syncfds[2]) +{ + int ret; + char buf; + + close_prot_errno_disarm(syncfds[1]); + + ret = unshare(CLONE_NEWUSER); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unshare user namespace\n", + strerror(errno)); + + ret = write_nointr(syncfds[0], "1", 1); + if (ret != 1) + ksft_exit_fail_msg("write_nointr() failed\n"); + + ret = read_nointr(syncfds[0], &buf, 1); + if (ret != 1) + ksft_exit_fail_msg("read_nointr() failed\n"); + + close_prot_errno_disarm(syncfds[0]); + + if (setid_userns_root()) + ksft_exit_fail_msg("setid_userns_root() failed"); +} + +static void change_idmaps(int syncfds[2], pid_t pid) +{ + int ret; + char buf; + char id_map[4096]; + + close_prot_errno_disarm(syncfds[0]); + + ret = read_nointr(syncfds[1], &buf, 1); + if (ret != 1) + ksft_exit_fail_msg("read_nointr() failed\n"); + + snprintf(id_map, sizeof(id_map), "0 %d 1\n", getuid()); + ret = write_id_mapping(UID_MAP, pid, id_map, strlen(id_map)); + if (ret) + ksft_exit_fail_msg("write_id_mapping(UID_MAP) failed"); + + snprintf(id_map, sizeof(id_map), "0 %d 1\n", getgid()); + ret = write_id_mapping(GID_MAP, pid, id_map, strlen(id_map)); + if (ret) + ksft_exit_fail_msg("write_id_mapping(GID_MAP) failed"); + + ret = write_nointr(syncfds[1], "1", 1); + if (ret != 1) + ksft_exit_fail_msg("write_nointr() failed"); + + close_prot_errno_disarm(syncfds[1]); } -static void binderfs_test_unprivileged() +static void *binder_version_thread(void *data) { - change_to_userns(); - __do_binderfs_test(); + int fd = PTR_TO_INT(data); + struct binder_version version = { 0 }; + int ret; + + ret = ioctl(fd, BINDER_VERSION, &version); + if (ret < 0) + ksft_print_msg("%s - Failed to open perform BINDER_VERSION request\n", strerror(errno)); + + pthread_exit(data); } -int main(int argc, char *argv[]) +/* + * Regression test: + * 2669b8b0c798 ("binder: prevent UAF for binderfs devices") + * f0fe2c0f050d ("binder: prevent UAF for binderfs devices II") + * 211b64e4b5b6 ("binderfs: use refcount for binder control devices too") + */ +TEST(binderfs_stress) { - binderfs_test_privileged(); - binderfs_test_unprivileged(); - ksft_exit_pass(); + int fds[1000]; + int syncfds[2]; + pid_t pid; + int fd, ret; + size_t len; + struct binderfs_device device = { 0 }; + char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX", + device_path[sizeof(P_tmpdir "/binderfs_XXXXXX/") + BINDERFS_MAX_NAME]; + + ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno)); + + pid = fork(); + if (pid < 0) { + close_prot_errno_disarm(syncfds[0]); + close_prot_errno_disarm(syncfds[1]); + ksft_exit_fail_msg("%s - Failed to fork", strerror(errno)); + } + + if (pid == 0) { + int i, j, k, nthreads; + pthread_attr_t attr; + pthread_t threads[DEFAULT_THREADS]; + change_userns(syncfds); + change_mountns(); + + if (!mkdtemp(binderfs_mntpt)) + log_exit("%s - Failed to create binderfs mountpoint\n", + strerror(errno)); + + ret = mount(NULL, binderfs_mntpt, "binder", 0, 0); + if (ret < 0) + log_exit("%s - Failed to mount binderfs\n", strerror(errno)); + + for (int i = 0; i < ARRAY_SIZE(fds); i++) { + + snprintf(device_path, sizeof(device_path), + "%s/binder-control", binderfs_mntpt); + fd = open(device_path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + log_exit("%s - Failed to open binder-control device\n", strerror(errno)); + + memset(&device, 0, sizeof(device)); + snprintf(device.name, sizeof(device.name), "%d", i); + ret = ioctl(fd, BINDER_CTL_ADD, &device); + close_prot_errno_disarm(fd); + if (ret < 0) + log_exit("%s - Failed to allocate new binder device\n", strerror(errno)); + + snprintf(device_path, sizeof(device_path), "%s/%d", + binderfs_mntpt, i); + fds[i] = open(device_path, O_RDONLY | O_CLOEXEC); + if (fds[i] < 0) + log_exit("%s - Failed to open binder device\n", strerror(errno)); + } + + ret = umount2(binderfs_mntpt, MNT_DETACH); + rmdir_protect_errno(binderfs_mntpt); + if (ret < 0) + log_exit("%s - Failed to unmount binderfs\n", strerror(errno)); + + nthreads = get_nprocs_conf(); + if (nthreads > DEFAULT_THREADS) + nthreads = DEFAULT_THREADS; + + pthread_attr_init(&attr); + for (k = 0; k < ARRAY_SIZE(fds); k++) { + for (i = 0; i < nthreads; i++) { + ret = pthread_create(&threads[i], &attr, binder_version_thread, INT_TO_PTR(fds[k])); + if (ret) { + ksft_print_msg("%s - Failed to create thread %d\n", strerror(errno), i); + break; + } + } + + for (j = 0; j < i; j++) { + void *fdptr = NULL; + + ret = pthread_join(threads[j], &fdptr); + if (ret) + ksft_print_msg("%s - Failed to join thread %d for fd %d\n", strerror(errno), j, PTR_TO_INT(fdptr)); + } + } + pthread_attr_destroy(&attr); + + for (k = 0; k < ARRAY_SIZE(fds); k++) + close(fds[k]); + + exit(EXIT_SUCCESS); + } + + change_idmaps(syncfds, pid); + + ret = wait_for_pid(pid); + if (ret) + ksft_exit_fail_msg("wait_for_pid() failed"); } + +TEST(binderfs_test_privileged) +{ + if (geteuid() != 0) + XFAIL(return, "Tests are not run as root. Skipping privileged tests"); + + if (__do_binderfs_test() == 1) + XFAIL(return, "The Android binderfs filesystem is not available"); +} + +TEST(binderfs_test_unprivileged) +{ + int ret; + int syncfds[2]; + pid_t pid; + + ret = socketpair(PF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, syncfds); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to create socket pair", strerror(errno)); + + pid = fork(); + if (pid < 0) { + close_prot_errno_disarm(syncfds[0]); + close_prot_errno_disarm(syncfds[1]); + ksft_exit_fail_msg("%s - Failed to fork", strerror(errno)); + } + + if (pid == 0) { + change_userns(syncfds); + if (__do_binderfs_test() == 1) + exit(2); + exit(EXIT_SUCCESS); + } + + change_idmaps(syncfds, pid); + + ret = wait_for_pid(pid); + if (ret) { + if (ret == 2) + XFAIL(return, "The Android binderfs filesystem is not available"); + else + ksft_exit_fail_msg("wait_for_pid() failed"); + } +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/epoll/.gitignore b/tools/testing/selftests/filesystems/epoll/.gitignore index 9ae8db44ec14..9090157258b1 100644 --- a/tools/testing/selftests/filesystems/epoll/.gitignore +++ b/tools/testing/selftests/filesystems/epoll/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only epoll_wakeup_test diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 37a04dab56f0..11eee0b60040 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -7,13 +7,14 @@ #include <pthread.h> #include <sys/epoll.h> #include <sys/socket.h> +#include <sys/eventfd.h> #include "../../kselftest_harness.h" struct epoll_mtcontext { int efd[3]; int sfd[4]; - int count; + volatile int count; pthread_t main; pthread_t waiter; @@ -3071,4 +3072,68 @@ TEST(epoll58) close(ctx.sfd[3]); } +static void *epoll59_thread(void *ctx_) +{ + struct epoll_mtcontext *ctx = ctx_; + struct epoll_event e; + int i; + + for (i = 0; i < 100000; i++) { + while (ctx->count == 0) + ; + + e.events = EPOLLIN | EPOLLERR | EPOLLET; + epoll_ctl(ctx->efd[0], EPOLL_CTL_MOD, ctx->sfd[0], &e); + ctx->count = 0; + } + + return NULL; +} + +/* + * t0 + * (p) \ + * e0 + * (et) / + * e0 + * + * Based on https://bugzilla.kernel.org/show_bug.cgi?id=205933 + */ +TEST(epoll59) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + int i, ret; + + signal(SIGUSR1, signal_handler); + + ctx.efd[0] = epoll_create1(0); + ASSERT_GE(ctx.efd[0], 0); + + ctx.sfd[0] = eventfd(1, 0); + ASSERT_GE(ctx.sfd[0], 0); + + e.events = EPOLLIN | EPOLLERR | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ASSERT_EQ(pthread_create(&emitter, NULL, epoll59_thread, &ctx), 0); + + for (i = 0; i < 100000; i++) { + ret = epoll_wait(ctx.efd[0], &e, 1, 1000); + ASSERT_GT(ret, 0); + + while (ctx.count != 0) + ; + ctx.count = 1; + } + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + close(ctx.efd[0]); + close(ctx.sfd[0]); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ftrace/.gitignore b/tools/testing/selftests/ftrace/.gitignore index 98d8a5a63049..2659417cb2c7 100644 --- a/tools/testing/selftests/ftrace/.gitignore +++ b/tools/testing/selftests/ftrace/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only logs diff --git a/tools/testing/selftests/ftrace/test.d/event/event-no-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-no-pid.tc new file mode 100644 index 000000000000..f0f366f18d0c --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/event-no-pid.tc @@ -0,0 +1,125 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event tracing - restricts events based on pid notrace filtering +# flags: instance + +do_reset() { + echo > set_event + echo > set_event_pid + echo > set_event_notrace_pid + echo 0 > options/event-fork + echo 0 > events/enable + clear_trace + echo 1 > tracing_on +} + +fail() { #msg + cat trace + do_reset + echo $1 + exit_fail +} + +count_pid() { + pid=$@ + cat trace | grep -v '^#' | sed -e 's/[^-]*-\([0-9]*\).*/\1/' | grep $pid | wc -l +} + +count_no_pid() { + pid=$1 + cat trace | grep -v '^#' | sed -e 's/[^-]*-\([0-9]*\).*/\1/' | grep -v $pid | wc -l +} + +enable_system() { + system=$1 + + if [ -d events/$system ]; then + echo 1 > events/$system/enable + fi +} + +enable_events() { + echo 0 > tracing_on + # Enable common groups of events, as all events can allow for + # events to be traced via scheduling that we don't care to test. + enable_system syscalls + enable_system rcu + enable_system block + enable_system exceptions + enable_system irq + enable_system net + enable_system power + enable_system signal + enable_system sock + enable_system timer + enable_system thermal + echo 1 > tracing_on +} + +if [ ! -f set_event -o ! -d events/sched ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +if [ ! -f set_event_pid -o ! -f set_event_notrace_pid ]; then + echo "event pid notrace filtering is not supported" + exit_unsupported +fi + +echo 0 > options/event-fork + +do_reset + +read mypid rest < /proc/self/stat + +echo $mypid > set_event_notrace_pid +grep -q $mypid set_event_notrace_pid + +enable_events + +yield + +echo 0 > tracing_on + +cnt=`count_pid $mypid` +if [ $cnt -ne 0 ]; then + fail "Filtered out task has events" +fi + +cnt=`count_no_pid $mypid` +if [ $cnt -eq 0 ]; then + fail "No other events were recorded" +fi + +do_reset + +echo $mypid > set_event_notrace_pid +echo 1 > options/event-fork + +enable_events + +yield & +child=$! +echo "child = $child" +wait $child + +echo 0 > tracing_on + +cnt=`count_pid $mypid` +if [ $cnt -ne 0 ]; then + fail "Filtered out task has events" +fi + +cnt=`count_pid $child` +if [ $cnt -ne 0 ]; then + fail "Child of filtered out taskhas events" +fi + +cnt=`count_no_pid $mypid` +if [ $cnt -eq 0 ]; then + fail "No other events were recorded" +fi + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc new file mode 100644 index 000000000000..8aa46a2ea133 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-notrace-pid.tc @@ -0,0 +1,108 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: ftrace - function pid notrace filters +# flags: instance + +# Make sure that function pid matching filter with notrace works. + +if ! grep -q function available_tracers; then + echo "no function tracer configured" + exit_unsupported +fi + +if [ ! -f set_ftrace_notrace_pid ]; then + echo "set_ftrace_notrace_pid not found? Is function tracer not set?" + exit_unsupported +fi + +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is function tracer not set?" + exit_unsupported +fi + +do_function_fork=1 + +if [ ! -f options/function-fork ]; then + do_function_fork=0 + echo "no option for function-fork found. Option will not be tested." +fi + +read PID _ < /proc/self/stat + +if [ $do_function_fork -eq 1 ]; then + # default value of function-fork option + orig_value=`grep function-fork trace_options` +fi + +do_reset() { + if [ $do_function_fork -eq 0 ]; then + return + fi + + echo > set_ftrace_notrace_pid + echo $orig_value > trace_options +} + +fail() { # msg + do_reset + echo $1 + exit_fail +} + +do_test() { + disable_tracing + + echo do_execve* > set_ftrace_filter + echo *do_fork >> set_ftrace_filter + + echo $PID > set_ftrace_notrace_pid + echo function > current_tracer + + if [ $do_function_fork -eq 1 ]; then + # don't allow children to be traced + echo nofunction-fork > trace_options + fi + + enable_tracing + yield + + count_pid=`cat trace | grep -v ^# | grep $PID | wc -l` + count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l` + + # count_pid should be 0 + if [ $count_pid -ne 0 -o $count_other -eq 0 ]; then + fail "PID filtering not working? traced task = $count_pid; other tasks = $count_other " + fi + + disable_tracing + clear_trace + + if [ $do_function_fork -eq 0 ]; then + return + fi + + # allow children to be traced + echo function-fork > trace_options + + # With pid in both set_ftrace_pid and set_ftrace_notrace_pid + # there should not be any tasks traced. + + echo $PID > set_ftrace_pid + + enable_tracing + yield + + count_pid=`cat trace | grep -v ^# | grep $PID | wc -l` + count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l` + + # both should be zero + if [ $count_pid -ne 0 -o $count_other -ne 0 ]; then + fail "PID filtering not following fork? traced task = $count_pid; other tasks = $count_other " + fi +} + +do_test + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc index 0c04282d33dd..1947387fe976 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc @@ -41,7 +41,7 @@ fi echo '** ENABLE EVENTS' -echo 1 > events/enable +echo 1 > events/sched/enable echo '** ENABLE TRACING' enable_tracing diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index a09f57061902..0efcd494daab 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only futex_requeue_pi futex_requeue_pi_mismatched_ops futex_requeue_pi_signal_restart diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore index 7d14f743d1a4..4c69408f3e84 100644 --- a/tools/testing/selftests/gpio/.gitignore +++ b/tools/testing/selftests/gpio/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only gpio-mockup-chardev diff --git a/tools/testing/selftests/ia64/.gitignore b/tools/testing/selftests/ia64/.gitignore index ab806edc8732..e962fb2a08d5 100644 --- a/tools/testing/selftests/ia64/.gitignore +++ b/tools/testing/selftests/ia64/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only aliasing-test diff --git a/tools/testing/selftests/intel_pstate/.gitignore b/tools/testing/selftests/intel_pstate/.gitignore index 3bfcbae5fa13..862de222a3f3 100644 --- a/tools/testing/selftests/intel_pstate/.gitignore +++ b/tools/testing/selftests/intel_pstate/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only aperf msr diff --git a/tools/testing/selftests/ipc/.gitignore b/tools/testing/selftests/ipc/.gitignore index 9af04c9353c0..9ed280e4c704 100644 --- a/tools/testing/selftests/ipc/.gitignore +++ b/tools/testing/selftests/ipc/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only msgque_test msgque diff --git a/tools/testing/selftests/ir/.gitignore b/tools/testing/selftests/ir/.gitignore index 070ea0c75fb8..0bbada8c1811 100644 --- a/tools/testing/selftests/ir/.gitignore +++ b/tools/testing/selftests/ir/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only ir_loopback diff --git a/tools/testing/selftests/kcmp/.gitignore b/tools/testing/selftests/kcmp/.gitignore index 5a9b3732b2de..38ccdfe80ef7 100644 --- a/tools/testing/selftests/kcmp/.gitignore +++ b/tools/testing/selftests/kcmp/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only kcmp_test kcmp-test-file diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index 8b944cf042f6..3702dbcc90a7 100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -61,6 +61,8 @@ ALL_TESTS="$ALL_TESTS 0006:10:1" ALL_TESTS="$ALL_TESTS 0007:5:1" ALL_TESTS="$ALL_TESTS 0008:150:1" ALL_TESTS="$ALL_TESTS 0009:150:1" +ALL_TESTS="$ALL_TESTS 0010:1:1" +ALL_TESTS="$ALL_TESTS 0011:1:1" # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -149,6 +151,7 @@ function load_req_mod() test_finish() { + echo "$MODPROBE" > /proc/sys/kernel/modprobe echo "Test completed" } @@ -443,6 +446,30 @@ kmod_test_0009() config_expect_result ${FUNCNAME[0]} SUCCESS } +kmod_test_0010() +{ + kmod_defaults_driver + config_num_threads 1 + echo "/KMOD_TEST_NONEXISTENT" > /proc/sys/kernel/modprobe + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} -ENOENT + echo "$MODPROBE" > /proc/sys/kernel/modprobe +} + +kmod_test_0011() +{ + kmod_defaults_driver + config_num_threads 1 + # This causes the kernel to not even try executing modprobe. The error + # code is still -ENOENT like when modprobe doesn't exist, so we can't + # easily test for the exact difference. But this still is a useful test + # since there was a bug where request_module() returned 0 in this case. + echo > /proc/sys/kernel/modprobe + config_trigger ${FUNCNAME[0]} + config_expect_result ${FUNCNAME[0]} -ENOENT + echo "$MODPROBE" > /proc/sys/kernel/modprobe +} + list_tests() { echo "Test ID list:" @@ -460,6 +487,8 @@ list_tests() echo "0007 x $(get_test_count 0007) - multithreaded tests with default setup test request_module() and get_fs_type()" echo "0008 x $(get_test_count 0008) - multithreaded - push kmod_concurrent over max_modprobes for request_module()" echo "0009 x $(get_test_count 0009) - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type()" + echo "0010 x $(get_test_count 0010) - test nonexistent modprobe path" + echo "0011 x $(get_test_count 0011) - test completely disabling module autoloading" } usage() @@ -505,18 +534,23 @@ function test_num() fi } -function get_test_count() +function get_test_data() { test_num $1 - TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + local field_num=$(echo $1 | sed 's/^0*//') + echo $ALL_TESTS | awk '{print $'$field_num'}' +} + +function get_test_count() +{ + TEST_DATA=$(get_test_data $1) LAST_TWO=${TEST_DATA#*:*} echo ${LAST_TWO%:*} } function get_test_enabled() { - test_num $1 - TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}') + TEST_DATA=$(get_test_data $1) echo ${TEST_DATA#*:*:} } @@ -611,6 +645,7 @@ test_reqs allow_user_defaults load_req_mod +MODPROBE=$(</proc/sys/kernel/modprobe) trap "test_finish" EXIT parse_args $@ diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 16877c3daabf..a9b2b48947ff 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only /s390x/memop /s390x/resets /s390x/sync_regs_test diff --git a/tools/testing/selftests/media_tests/.gitignore b/tools/testing/selftests/media_tests/.gitignore index 8745eba39012..da438e780ffe 100644 --- a/tools/testing/selftests/media_tests/.gitignore +++ b/tools/testing/selftests/media_tests/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only media_device_test media_device_open video_device_test diff --git a/tools/testing/selftests/membarrier/.gitignore b/tools/testing/selftests/membarrier/.gitignore index f2f7ec0a99b4..f2fbba178601 100644 --- a/tools/testing/selftests/membarrier/.gitignore +++ b/tools/testing/selftests/membarrier/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only membarrier_test_multi_thread membarrier_test_single_thread diff --git a/tools/testing/selftests/memfd/.gitignore b/tools/testing/selftests/memfd/.gitignore index afe87c40ac80..dd9a051f608e 100644 --- a/tools/testing/selftests/memfd/.gitignore +++ b/tools/testing/selftests/memfd/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only fuse_mnt fuse_test memfd_test diff --git a/tools/testing/selftests/mount/.gitignore b/tools/testing/selftests/mount/.gitignore index 856ad4107eb3..0bc64a6d4c18 100644 --- a/tools/testing/selftests/mount/.gitignore +++ b/tools/testing/selftests/mount/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only unprivileged-remount-test diff --git a/tools/testing/selftests/mqueue/.gitignore b/tools/testing/selftests/mqueue/.gitignore index d8d42377205a..72ad8ca691c9 100644 --- a/tools/testing/selftests/mqueue/.gitignore +++ b/tools/testing/selftests/mqueue/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only mq_open_tests mq_perf_tests diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 997c65dcad68..742c499328b2 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only msg_zerocopy socket psock_fanout diff --git a/tools/testing/selftests/net/forwarding/.gitignore b/tools/testing/selftests/net/forwarding/.gitignore index a793eef5b876..2dea317f12e7 100644 --- a/tools/testing/selftests/net/forwarding/.gitignore +++ b/tools/testing/selftests/net/forwarding/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only forwarding.config diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore index ea13b255a99d..260336d5f0b1 100644 --- a/tools/testing/selftests/net/mptcp/.gitignore +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only mptcp_connect pm_nl_ctl *.pcap diff --git a/tools/testing/selftests/nsfs/.gitignore b/tools/testing/selftests/nsfs/.gitignore index 2ab2c824ce86..ed79ebdf286e 100644 --- a/tools/testing/selftests/nsfs/.gitignore +++ b/tools/testing/selftests/nsfs/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only owner pidns diff --git a/tools/testing/selftests/openat2/.gitignore b/tools/testing/selftests/openat2/.gitignore index bd68f6c3fd07..82a4846cbc4b 100644 --- a/tools/testing/selftests/openat2/.gitignore +++ b/tools/testing/selftests/openat2/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only /*_test diff --git a/tools/testing/selftests/pid_namespace/.gitignore b/tools/testing/selftests/pid_namespace/.gitignore new file mode 100644 index 000000000000..93ab9d7e5b7e --- /dev/null +++ b/tools/testing/selftests/pid_namespace/.gitignore @@ -0,0 +1 @@ +regression_enomem diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile new file mode 100644 index 000000000000..dcaefa224ca0 --- /dev/null +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -g -I../../../../usr/include/ + +TEST_GEN_PROGS := regression_enomem + +include ../lib.mk + +$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h diff --git a/tools/testing/selftests/pid_namespace/config b/tools/testing/selftests/pid_namespace/config new file mode 100644 index 000000000000..26cdb27e7dbb --- /dev/null +++ b/tools/testing/selftests/pid_namespace/config @@ -0,0 +1,2 @@ +CONFIG_PID_NS=y +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/pid_namespace/regression_enomem.c b/tools/testing/selftests/pid_namespace/regression_enomem.c new file mode 100644 index 000000000000..73d532556d17 --- /dev/null +++ b/tools/testing/selftests/pid_namespace/regression_enomem.c @@ -0,0 +1,45 @@ +#define _GNU_SOURCE +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/types.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/wait.h> + +#include "../kselftest.h" +#include "../kselftest_harness.h" +#include "../pidfd/pidfd.h" + +/* + * Regression test for: + * 35f71bc0a09a ("fork: report pid reservation failure properly") + * b26ebfe12f34 ("pid: Fix error return value in some cases") + */ +TEST(regression_enomem) +{ + pid_t pid; + + if (geteuid()) + EXPECT_EQ(0, unshare(CLONE_NEWUSER)); + + EXPECT_EQ(0, unshare(CLONE_NEWPID)); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) + exit(EXIT_SUCCESS); + + EXPECT_EQ(0, wait_for_pid(pid)); + + pid = fork(); + ASSERT_LT(pid, 0); + ASSERT_EQ(errno, ENOMEM); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 39559d723c41..2d4db5afb142 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only pidfd_open_test pidfd_poll_test pidfd_test diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index d482515604db..c1921a53dbed 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -13,6 +13,8 @@ #include <string.h> #include <syscall.h> #include <sys/mount.h> +#include <sys/types.h> +#include <sys/wait.h> #include "../kselftest.h" diff --git a/tools/testing/selftests/powerpc/alignment/.gitignore b/tools/testing/selftests/powerpc/alignment/.gitignore index 6d4fd014511c..28bc6ca13cc6 100644 --- a/tools/testing/selftests/powerpc/alignment/.gitignore +++ b/tools/testing/selftests/powerpc/alignment/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only copy_first_unaligned alignment_handler diff --git a/tools/testing/selftests/powerpc/benchmarks/.gitignore b/tools/testing/selftests/powerpc/benchmarks/.gitignore index 9161679b1e1a..c9ce13983c99 100644 --- a/tools/testing/selftests/powerpc/benchmarks/.gitignore +++ b/tools/testing/selftests/powerpc/benchmarks/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only gettimeofday context_switch fork diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index d40300a65b42..a32a6ab89914 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -2,6 +2,8 @@ TEST_GEN_PROGS := gettimeofday context_switch fork mmap_bench futex_bench null_syscall TEST_GEN_FILES := exec_target +TEST_FILES := settings + CFLAGS += -O2 top_srcdir = ../../../../.. diff --git a/tools/testing/selftests/powerpc/benchmarks/settings b/tools/testing/selftests/powerpc/benchmarks/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/powerpc/benchmarks/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/powerpc/cache_shape/.gitignore b/tools/testing/selftests/powerpc/cache_shape/.gitignore index ec1848434be5..b385eee3012c 100644 --- a/tools/testing/selftests/powerpc/cache_shape/.gitignore +++ b/tools/testing/selftests/powerpc/cache_shape/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only cache_shape diff --git a/tools/testing/selftests/powerpc/copyloops/.gitignore b/tools/testing/selftests/powerpc/copyloops/.gitignore index 12ef5b031974..ddaf140b8255 100644 --- a/tools/testing/selftests/powerpc/copyloops/.gitignore +++ b/tools/testing/selftests/powerpc/copyloops/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only copyuser_64_t0 copyuser_64_t1 copyuser_64_t2 diff --git a/tools/testing/selftests/powerpc/dscr/.gitignore b/tools/testing/selftests/powerpc/dscr/.gitignore index b585c6c1564a..1d08b15af697 100644 --- a/tools/testing/selftests/powerpc/dscr/.gitignore +++ b/tools/testing/selftests/powerpc/dscr/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only dscr_default_test dscr_explicit_test dscr_inherit_exec_test diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile index 5df476364b4d..cfa6eedcb66c 100644 --- a/tools/testing/selftests/powerpc/dscr/Makefile +++ b/tools/testing/selftests/powerpc/dscr/Makefile @@ -3,6 +3,8 @@ TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test \ dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test \ dscr_sysfs_thread_test +TEST_FILES := settings + top_srcdir = ../../../../.. include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/dscr/settings b/tools/testing/selftests/powerpc/dscr/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/powerpc/dscr/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh index f988d2f42e8f..8a8d0f456946 100755 --- a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh +++ b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh @@ -41,6 +41,11 @@ for dev in `ls -1 /sys/bus/pci/devices/ | grep '\.0$'` ; do continue; fi + if [ "ahci" = "$(basename $(realpath /sys/bus/pci/devices/$dev/driver))" ] ; then + echo "$dev, Skipped: ahci doesn't support recovery" + continue + fi + # Don't inject errosr into an already-frozen PE. This happens with # PEs that contain multiple PCI devices (e.g. multi-function cards) # and injecting new errors during the recovery process will probably diff --git a/tools/testing/selftests/powerpc/math/.gitignore b/tools/testing/selftests/powerpc/math/.gitignore index 50ded63e25b7..e31ca6f453ed 100644 --- a/tools/testing/selftests/powerpc/math/.gitignore +++ b/tools/testing/selftests/powerpc/math/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only fpu_syscall vmx_syscall fpu_preempt diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore index 0ebeaea22641..2ca523255b1b 100644 --- a/tools/testing/selftests/powerpc/mm/.gitignore +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only hugetlb_vs_thp_test subpage_prot tempfile @@ -6,3 +7,4 @@ segv_errors wild_bctr large_vm_fork_separation bad_accesses +tlbie_test diff --git a/tools/testing/selftests/powerpc/pmu/.gitignore b/tools/testing/selftests/powerpc/pmu/.gitignore index e748f336eed3..ff7896903d7b 100644 --- a/tools/testing/selftests/powerpc/pmu/.gitignore +++ b/tools/testing/selftests/powerpc/pmu/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only count_instructions l3_bank_test per_event_excludes diff --git a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore index 42bddbed8b64..2920fb39439b 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/.gitignore +++ b/tools/testing/selftests/powerpc/pmu/ebb/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only reg_access_test event_attributes_test cycles_test diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index 417306353e07..ca35dd8848b0 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -7,6 +7,7 @@ noarg: # The EBB handler is 64-bit code and everything links against it CFLAGS += -m64 +TMPOUT = $(OUTPUT)/ # Toolchains may build PIE by default which breaks the assembly no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/powerpc/primitives/.gitignore b/tools/testing/selftests/powerpc/primitives/.gitignore index 4cc4e31bed1d..1e5c04e24254 100644 --- a/tools/testing/selftests/powerpc/primitives/.gitignore +++ b/tools/testing/selftests/powerpc/primitives/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only load_unaligned_zeropad diff --git a/tools/testing/selftests/powerpc/ptrace/.gitignore b/tools/testing/selftests/powerpc/ptrace/.gitignore index dce19f221c46..0e96150b7c7e 100644 --- a/tools/testing/selftests/powerpc/ptrace/.gitignore +++ b/tools/testing/selftests/powerpc/ptrace/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr diff --git a/tools/testing/selftests/powerpc/security/.gitignore b/tools/testing/selftests/powerpc/security/.gitignore index 0b969fba3beb..f795e06f5ae3 100644 --- a/tools/testing/selftests/powerpc/security/.gitignore +++ b/tools/testing/selftests/powerpc/security/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only rfi_flush diff --git a/tools/testing/selftests/powerpc/signal/.gitignore b/tools/testing/selftests/powerpc/signal/.gitignore index dca5852a1546..405b5364044c 100644 --- a/tools/testing/selftests/powerpc/signal/.gitignore +++ b/tools/testing/selftests/powerpc/signal/.gitignore @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only signal signal_tm sigfuz +sigreturn_vdso diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile index 113838fbbe7f..932a032bf036 100644 --- a/tools/testing/selftests/powerpc/signal/Makefile +++ b/tools/testing/selftests/powerpc/signal/Makefile @@ -1,10 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_GEN_PROGS := signal signal_tm sigfuz +TEST_GEN_PROGS := signal signal_tm sigfuz sigreturn_vdso CFLAGS += -maltivec $(OUTPUT)/signal_tm: CFLAGS += -mhtm $(OUTPUT)/sigfuz: CFLAGS += -pthread -m64 +TEST_FILES := settings + top_srcdir = ../../../../.. include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/signal/settings b/tools/testing/selftests/powerpc/signal/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/powerpc/signal/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/powerpc/signal/sigreturn_vdso.c b/tools/testing/selftests/powerpc/signal/sigreturn_vdso.c new file mode 100644 index 000000000000..e282fff0fe25 --- /dev/null +++ b/tools/testing/selftests/powerpc/signal/sigreturn_vdso.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test that we can take signals with and without the VDSO mapped, which trigger + * different paths in the signal handling code. + * + * See handle_rt_signal64() and setup_trampoline() in signal_64.c + */ + +#define _GNU_SOURCE + +#include <errno.h> +#include <stdio.h> +#include <signal.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <unistd.h> + +// Ensure assert() is not compiled out +#undef NDEBUG +#include <assert.h> + +#include "utils.h" + +static int search_proc_maps(char *needle, unsigned long *low, unsigned long *high) +{ + unsigned long start, end; + static char buf[4096]; + char name[128]; + FILE *f; + int rc = -1; + + f = fopen("/proc/self/maps", "r"); + if (!f) { + perror("fopen"); + return -1; + } + + while (fgets(buf, sizeof(buf), f)) { + rc = sscanf(buf, "%lx-%lx %*c%*c%*c%*c %*x %*d:%*d %*d %127s\n", + &start, &end, name); + if (rc == 2) + continue; + + if (rc != 3) { + printf("sscanf errored\n"); + rc = -1; + break; + } + + if (strstr(name, needle)) { + *low = start; + *high = end - 1; + rc = 0; + break; + } + } + + fclose(f); + + return rc; +} + +static volatile sig_atomic_t took_signal = 0; + +static void sigusr1_handler(int sig) +{ + took_signal++; +} + +int test_sigreturn_vdso(void) +{ + unsigned long low, high, size; + struct sigaction act; + char *p; + + act.sa_handler = sigusr1_handler; + act.sa_flags = 0; + sigemptyset(&act.sa_mask); + + assert(sigaction(SIGUSR1, &act, NULL) == 0); + + // Confirm the VDSO is mapped, and work out where it is + assert(search_proc_maps("[vdso]", &low, &high) == 0); + size = high - low + 1; + printf("VDSO is at 0x%lx-0x%lx (%lu bytes)\n", low, high, size); + + kill(getpid(), SIGUSR1); + assert(took_signal == 1); + printf("Signal delivered OK with VDSO mapped\n"); + + // Remap the VDSO somewhere else + p = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + assert(p != MAP_FAILED); + assert(mremap((void *)low, size, size, MREMAP_MAYMOVE|MREMAP_FIXED, p) != MAP_FAILED); + assert(search_proc_maps("[vdso]", &low, &high) == 0); + size = high - low + 1; + printf("VDSO moved to 0x%lx-0x%lx (%lu bytes)\n", low, high, size); + + kill(getpid(), SIGUSR1); + assert(took_signal == 2); + printf("Signal delivered OK with VDSO moved\n"); + + assert(munmap((void *)low, size) == 0); + printf("Unmapped VDSO\n"); + + // Confirm the VDSO is not mapped anymore + assert(search_proc_maps("[vdso]", &low, &high) != 0); + + // Make the stack executable + assert(search_proc_maps("[stack]", &low, &high) == 0); + size = high - low + 1; + mprotect((void *)low, size, PROT_READ|PROT_WRITE|PROT_EXEC); + printf("Remapped the stack executable\n"); + + kill(getpid(), SIGUSR1); + assert(took_signal == 3); + printf("Signal delivered OK with VDSO unmapped\n"); + + return 0; +} + +int main(void) +{ + return test_harness(test_sigreturn_vdso, "sigreturn_vdso"); +} diff --git a/tools/testing/selftests/powerpc/stringloops/.gitignore b/tools/testing/selftests/powerpc/stringloops/.gitignore index 31a17e0ba884..b0dfc74aa57e 100644 --- a/tools/testing/selftests/powerpc/stringloops/.gitignore +++ b/tools/testing/selftests/powerpc/stringloops/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only memcmp_64 memcmp_32 strlen diff --git a/tools/testing/selftests/powerpc/switch_endian/.gitignore b/tools/testing/selftests/powerpc/switch_endian/.gitignore index 89e762eab676..30e962cf84d1 100644 --- a/tools/testing/selftests/powerpc/switch_endian/.gitignore +++ b/tools/testing/selftests/powerpc/switch_endian/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only switch_endian_test check-reversed.S diff --git a/tools/testing/selftests/powerpc/syscalls/.gitignore b/tools/testing/selftests/powerpc/syscalls/.gitignore index f0f3fcc9d802..b00cab225476 100644 --- a/tools/testing/selftests/powerpc/syscalls/.gitignore +++ b/tools/testing/selftests/powerpc/syscalls/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only ipc_unmuxed diff --git a/tools/testing/selftests/powerpc/tm/.gitignore b/tools/testing/selftests/powerpc/tm/.gitignore index 98f2708d86cc..d8900a0c47a1 100644 --- a/tools/testing/selftests/powerpc/tm/.gitignore +++ b/tools/testing/selftests/powerpc/tm/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only tm-resched-dscr tm-syscall tm-signal-msr-resv @@ -13,6 +14,7 @@ tm-signal-context-chk-vmx tm-signal-context-chk-vsx tm-signal-context-force-tm tm-signal-sigreturn-nt +tm-signal-pagefault tm-vmx-unavail tm-unavailable tm-trap diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index b15a1a325bd0..5881e97c73c1 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -5,7 +5,9 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \ tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable tm-trap \ $(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt \ - tm-signal-context-force-tm tm-poison + tm-signal-context-force-tm tm-poison tm-signal-pagefault + +TEST_FILES := settings top_srcdir = ../../../../.. include ../../lib.mk @@ -22,6 +24,8 @@ $(OUTPUT)/tm-resched-dscr: ../pmu/lib.c $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64 $(OUTPUT)/tm-signal-context-force-tm: CFLAGS += -pthread -m64 +$(OUTPUT)/tm-signal-pagefault: CFLAGS += -pthread -m64 +$(OUTPUT)/tm-poison: CFLAGS += -m64 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS)) $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S diff --git a/tools/testing/selftests/powerpc/tm/settings b/tools/testing/selftests/powerpc/tm/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c b/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c index 31717625f318..421cb082f6be 100644 --- a/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c +++ b/tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c @@ -42,9 +42,10 @@ #endif /* Setting contexts because the test will crash and we want to recover */ -ucontext_t init_context, main_context; +ucontext_t init_context; -static int count, first_time; +/* count is changed in the signal handler, so it must be volatile */ +static volatile int count; void usr_signal_handler(int signo, siginfo_t *si, void *uc) { @@ -98,11 +99,6 @@ void usr_signal_handler(int signo, siginfo_t *si, void *uc) void seg_signal_handler(int signo, siginfo_t *si, void *uc) { - if (count == COUNT_MAX) { - /* Return to tm_signal_force_msr() and exit */ - setcontext(&main_context); - } - count++; /* Reexecute the test */ @@ -126,37 +122,41 @@ void tm_trap_test(void) */ getcontext(&init_context); - /* Allocated an alternative signal stack area */ - ss.ss_sp = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); - ss.ss_size = SIGSTKSZ; - ss.ss_flags = 0; + while (count < COUNT_MAX) { + /* Allocated an alternative signal stack area */ + ss.ss_sp = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); + ss.ss_size = SIGSTKSZ; + ss.ss_flags = 0; - if (ss.ss_sp == (void *)-1) { - perror("mmap error\n"); - exit(-1); - } + if (ss.ss_sp == (void *)-1) { + perror("mmap error\n"); + exit(-1); + } - /* Force the allocation through a page fault */ - if (madvise(ss.ss_sp, SIGSTKSZ, MADV_DONTNEED)) { - perror("madvise\n"); - exit(-1); - } + /* Force the allocation through a page fault */ + if (madvise(ss.ss_sp, SIGSTKSZ, MADV_DONTNEED)) { + perror("madvise\n"); + exit(-1); + } - /* Setting an alternative stack to generate a page fault when - * the signal is raised. - */ - if (sigaltstack(&ss, NULL)) { - perror("sigaltstack\n"); - exit(-1); + /* + * Setting an alternative stack to generate a page fault when + * the signal is raised. + */ + if (sigaltstack(&ss, NULL)) { + perror("sigaltstack\n"); + exit(-1); + } + + /* The signal handler will enable MSR_TS */ + sigaction(SIGUSR1, &usr_sa, NULL); + /* If it does not crash, it might segfault, avoid it to retest */ + sigaction(SIGSEGV, &seg_sa, NULL); + + raise(SIGUSR1); + count++; } - - /* The signal handler will enable MSR_TS */ - sigaction(SIGUSR1, &usr_sa, NULL); - /* If it does not crash, it will segfault, avoid it to retest */ - sigaction(SIGSEGV, &seg_sa, NULL); - - raise(SIGUSR1); } int tm_signal_context_force_tm(void) @@ -169,11 +169,7 @@ int tm_signal_context_force_tm(void) */ SKIP_IF(!is_ppc64le()); - /* Will get back here after COUNT_MAX interactions */ - getcontext(&main_context); - - if (!first_time++) - tm_trap_test(); + tm_trap_test(); return EXIT_SUCCESS; } diff --git a/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c b/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c new file mode 100644 index 000000000000..5908bc6abe60 --- /dev/null +++ b/tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c @@ -0,0 +1,284 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2020, Gustavo Luiz Duarte, IBM Corp. + * + * This test starts a transaction and triggers a signal, forcing a pagefault to + * happen when the kernel signal handling code touches the user signal stack. + * + * In order to avoid pre-faulting the signal stack memory and to force the + * pagefault to happen precisely in the kernel signal handling code, the + * pagefault handling is done in userspace using the userfaultfd facility. + * + * Further pagefaults are triggered by crafting the signal handler's ucontext + * to point to additional memory regions managed by the userfaultfd, so using + * the same mechanism used to avoid pre-faulting the signal stack memory. + * + * On failure (bug is present) kernel crashes or never returns control back to + * userspace. If bug is not present, tests completes almost immediately. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <linux/userfaultfd.h> +#include <poll.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> +#include <fcntl.h> +#include <sys/mman.h> +#include <pthread.h> +#include <signal.h> +#include <errno.h> + +#include "tm.h" + + +#define UF_MEM_SIZE 655360 /* 10 x 64k pages */ + +/* Memory handled by userfaultfd */ +static char *uf_mem; +static size_t uf_mem_offset = 0; + +/* + * Data that will be copied into the faulting pages (instead of zero-filled + * pages). This is used to make the test more reliable and avoid segfaulting + * when we return from the signal handler. Since we are making the signal + * handler's ucontext point to newly allocated memory, when that memory is + * paged-in it will contain the expected content. + */ +static char backing_mem[UF_MEM_SIZE]; + +static size_t pagesize; + +/* + * Return a chunk of at least 'size' bytes of memory that will be handled by + * userfaultfd. If 'backing_data' is not NULL, its content will be save to + * 'backing_mem' and then copied into the faulting pages when the page fault + * is handled. + */ +void *get_uf_mem(size_t size, void *backing_data) +{ + void *ret; + + if (uf_mem_offset + size > UF_MEM_SIZE) { + fprintf(stderr, "Requesting more uf_mem than expected!\n"); + exit(EXIT_FAILURE); + } + + ret = &uf_mem[uf_mem_offset]; + + /* Save the data that will be copied into the faulting page */ + if (backing_data != NULL) + memcpy(&backing_mem[uf_mem_offset], backing_data, size); + + /* Reserve the requested amount of uf_mem */ + uf_mem_offset += size; + /* Keep uf_mem_offset aligned to the page size (round up) */ + uf_mem_offset = (uf_mem_offset + pagesize - 1) & ~(pagesize - 1); + + return ret; +} + +void *fault_handler_thread(void *arg) +{ + struct uffd_msg msg; /* Data read from userfaultfd */ + long uffd; /* userfaultfd file descriptor */ + struct uffdio_copy uffdio_copy; + struct pollfd pollfd; + ssize_t nread, offset; + + uffd = (long) arg; + + for (;;) { + pollfd.fd = uffd; + pollfd.events = POLLIN; + if (poll(&pollfd, 1, -1) == -1) { + perror("poll() failed"); + exit(EXIT_FAILURE); + } + + nread = read(uffd, &msg, sizeof(msg)); + if (nread == 0) { + fprintf(stderr, "read(): EOF on userfaultfd\n"); + exit(EXIT_FAILURE); + } + + if (nread == -1) { + perror("read() failed"); + exit(EXIT_FAILURE); + } + + /* We expect only one kind of event */ + if (msg.event != UFFD_EVENT_PAGEFAULT) { + fprintf(stderr, "Unexpected event on userfaultfd\n"); + exit(EXIT_FAILURE); + } + + /* + * We need to handle page faults in units of pages(!). + * So, round faulting address down to page boundary. + */ + uffdio_copy.dst = msg.arg.pagefault.address & ~(pagesize-1); + + offset = (char *) uffdio_copy.dst - uf_mem; + uffdio_copy.src = (unsigned long) &backing_mem[offset]; + + uffdio_copy.len = pagesize; + uffdio_copy.mode = 0; + uffdio_copy.copy = 0; + if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy) == -1) { + perror("ioctl-UFFDIO_COPY failed"); + exit(EXIT_FAILURE); + } + } +} + +void setup_uf_mem(void) +{ + long uffd; /* userfaultfd file descriptor */ + pthread_t thr; + struct uffdio_api uffdio_api; + struct uffdio_register uffdio_register; + int ret; + + pagesize = sysconf(_SC_PAGE_SIZE); + + /* Create and enable userfaultfd object */ + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd == -1) { + perror("userfaultfd() failed"); + exit(EXIT_FAILURE); + } + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) { + perror("ioctl-UFFDIO_API failed"); + exit(EXIT_FAILURE); + } + + /* + * Create a private anonymous mapping. The memory will be demand-zero + * paged, that is, not yet allocated. When we actually touch the memory + * the related page will be allocated via the userfaultfd mechanism. + */ + uf_mem = mmap(NULL, UF_MEM_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (uf_mem == MAP_FAILED) { + perror("mmap() failed"); + exit(EXIT_FAILURE); + } + + /* + * Register the memory range of the mapping we've just mapped to be + * handled by the userfaultfd object. In 'mode' we request to track + * missing pages (i.e. pages that have not yet been faulted-in). + */ + uffdio_register.range.start = (unsigned long) uf_mem; + uffdio_register.range.len = UF_MEM_SIZE; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { + perror("ioctl-UFFDIO_REGISTER"); + exit(EXIT_FAILURE); + } + + /* Create a thread that will process the userfaultfd events */ + ret = pthread_create(&thr, NULL, fault_handler_thread, (void *) uffd); + if (ret != 0) { + fprintf(stderr, "pthread_create(): Error. Returned %d\n", ret); + exit(EXIT_FAILURE); + } +} + +/* + * Assumption: the signal was delivered while userspace was in transactional or + * suspended state, i.e. uc->uc_link != NULL. + */ +void signal_handler(int signo, siginfo_t *si, void *uc) +{ + ucontext_t *ucp = uc; + + /* Skip 'trap' after returning, otherwise we get a SIGTRAP again */ + ucp->uc_link->uc_mcontext.regs->nip += 4; + + ucp->uc_mcontext.v_regs = + get_uf_mem(sizeof(elf_vrreg_t), ucp->uc_mcontext.v_regs); + + ucp->uc_link->uc_mcontext.v_regs = + get_uf_mem(sizeof(elf_vrreg_t), ucp->uc_link->uc_mcontext.v_regs); + + ucp->uc_link = get_uf_mem(sizeof(ucontext_t), ucp->uc_link); +} + +bool have_userfaultfd(void) +{ + long rc; + + errno = 0; + rc = syscall(__NR_userfaultfd, -1); + + return rc == 0 || errno != ENOSYS; +} + +int tm_signal_pagefault(void) +{ + struct sigaction sa; + stack_t ss; + + SKIP_IF(!have_htm()); + SKIP_IF(!have_userfaultfd()); + + setup_uf_mem(); + + /* + * Set an alternative stack that will generate a page fault when the + * signal is raised. The page fault will be treated via userfaultfd, + * i.e. via fault_handler_thread. + */ + ss.ss_sp = get_uf_mem(SIGSTKSZ, NULL); + ss.ss_size = SIGSTKSZ; + ss.ss_flags = 0; + if (sigaltstack(&ss, NULL) == -1) { + perror("sigaltstack() failed"); + exit(EXIT_FAILURE); + } + + sa.sa_flags = SA_SIGINFO | SA_ONSTACK; + sa.sa_sigaction = signal_handler; + if (sigaction(SIGTRAP, &sa, NULL) == -1) { + perror("sigaction() failed"); + exit(EXIT_FAILURE); + } + + /* Trigger a SIGTRAP in transactional state */ + asm __volatile__( + "tbegin.;" + "beq 1f;" + "trap;" + "1: ;" + : : : "memory"); + + /* Trigger a SIGTRAP in suspended state */ + asm __volatile__( + "tbegin.;" + "beq 1f;" + "tsuspend.;" + "trap;" + "tresume.;" + "1: ;" + : : : "memory"); + + return EXIT_SUCCESS; +} + +int main(int argc, char **argv) +{ + /* + * Depending on kernel config, the TM Bad Thing might not result in a + * crash, instead the kernel never returns control back to userspace, so + * set a tight timeout. If the test passes it completes almost + * immediately. + */ + test_harness_set_timeout(2); + return test_harness(tm_signal_pagefault, "tm_signal_pagefault"); +} diff --git a/tools/testing/selftests/powerpc/vphn/.gitignore b/tools/testing/selftests/powerpc/vphn/.gitignore index 7c04395010cb..b744aedfd1f2 100644 --- a/tools/testing/selftests/powerpc/vphn/.gitignore +++ b/tools/testing/selftests/powerpc/vphn/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only test-vphn diff --git a/tools/testing/selftests/prctl/.gitignore b/tools/testing/selftests/prctl/.gitignore index 0b5c27447bf6..91af2b631bc9 100644 --- a/tools/testing/selftests/prctl/.gitignore +++ b/tools/testing/selftests/prctl/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only disable-tsc-ctxt-sw-stress-test disable-tsc-on-off-stress-test disable-tsc-test diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index 66fab4c58ed4..4bca5a9327a4 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only /fd-001-lookup /fd-002-posix-eq /fd-003-kthread diff --git a/tools/testing/selftests/pstore/.gitignore b/tools/testing/selftests/pstore/.gitignore index 5a4a26e5464b..9938fb406389 100644 --- a/tools/testing/selftests/pstore/.gitignore +++ b/tools/testing/selftests/pstore/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only logs *uuid diff --git a/tools/testing/selftests/ptp/.gitignore b/tools/testing/selftests/ptp/.gitignore index f562e49d6917..534ca26eee48 100644 --- a/tools/testing/selftests/ptp/.gitignore +++ b/tools/testing/selftests/ptp/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only testptp diff --git a/tools/testing/selftests/ptrace/.gitignore b/tools/testing/selftests/ptrace/.gitignore index cfcc49a7def7..7bebf9534a86 100644 --- a/tools/testing/selftests/ptrace/.gitignore +++ b/tools/testing/selftests/ptrace/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only get_syscall_info peeksiginfo diff --git a/tools/testing/selftests/rcutorture/.gitignore b/tools/testing/selftests/rcutorture/.gitignore index ccc240275d1c..f6cbce77460b 100644 --- a/tools/testing/selftests/rcutorture/.gitignore +++ b/tools/testing/selftests/rcutorture/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only initrd b[0-9]* res diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore index 712a3d41a325..24e27957efcc 100644 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only srcu.c diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore index 1d016e66980a..57d296341304 100644 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only srcu.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore index f47cb2045f13..d65462d64816 100644 --- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only *.out diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index cc610da7e369..5910888ebfe1 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only basic_percpu_ops_test basic_test basic_rseq_op_test diff --git a/tools/testing/selftests/rtc/.gitignore b/tools/testing/selftests/rtc/.gitignore index d0ad44f6294a..fb2d533aa575 100644 --- a/tools/testing/selftests/rtc/.gitignore +++ b/tools/testing/selftests/rtc/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only rtctest setdate diff --git a/tools/testing/selftests/safesetid/.gitignore b/tools/testing/selftests/safesetid/.gitignore index 9c1a629bca01..25d3db172907 100644 --- a/tools/testing/selftests/safesetid/.gitignore +++ b/tools/testing/selftests/safesetid/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only safesetid-test diff --git a/tools/testing/selftests/seccomp/.gitignore b/tools/testing/selftests/seccomp/.gitignore index 5af29d3a1b0a..dec678577f9c 100644 --- a/tools/testing/selftests/seccomp/.gitignore +++ b/tools/testing/selftests/seccomp/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only seccomp_bpf seccomp_benchmark diff --git a/tools/testing/selftests/sigaltstack/.gitignore b/tools/testing/selftests/sigaltstack/.gitignore index 35897b0a3f44..50a19a8888ce 100644 --- a/tools/testing/selftests/sigaltstack/.gitignore +++ b/tools/testing/selftests/sigaltstack/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only sas diff --git a/tools/testing/selftests/size/.gitignore b/tools/testing/selftests/size/.gitignore index 189b7818de34..923e18eed1a0 100644 --- a/tools/testing/selftests/size/.gitignore +++ b/tools/testing/selftests/size/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only get_size diff --git a/tools/testing/selftests/sparc64/drivers/.gitignore b/tools/testing/selftests/sparc64/drivers/.gitignore index 90e835ed74e6..0331f77373b5 100644 --- a/tools/testing/selftests/sparc64/drivers/.gitignore +++ b/tools/testing/selftests/sparc64/drivers/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only adi-test diff --git a/tools/testing/selftests/splice/.gitignore b/tools/testing/selftests/splice/.gitignore index 1e23fefd68e8..d5a2da428752 100644 --- a/tools/testing/selftests/splice/.gitignore +++ b/tools/testing/selftests/splice/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only default_file_splice_read diff --git a/tools/testing/selftests/sync/.gitignore b/tools/testing/selftests/sync/.gitignore index f5091e7792f2..f1152357712f 100644 --- a/tools/testing/selftests/sync/.gitignore +++ b/tools/testing/selftests/sync/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only sync_test diff --git a/tools/testing/selftests/tc-testing/.gitignore b/tools/testing/selftests/tc-testing/.gitignore index c26d72e0166f..d52f65de23b4 100644 --- a/tools/testing/selftests/tc-testing/.gitignore +++ b/tools/testing/selftests/tc-testing/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only __pycache__/ *.pyc plugins/ diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index e566c70e64a1..a3e43189d940 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -713,9 +713,8 @@ def set_operation_mode(pm, parser, args, remaining): exit(0) if args.list: - if args.list: - list_test_cases(alltests) - exit(0) + list_test_cases(alltests) + exit(0) if len(alltests): req_plugins = pm.get_required_plugins(alltests) diff --git a/tools/testing/selftests/timens/.gitignore b/tools/testing/selftests/timens/.gitignore index 789f21e81028..2e43851b47c1 100644 --- a/tools/testing/selftests/timens/.gitignore +++ b/tools/testing/selftests/timens/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only clock_nanosleep exec gettime_perf diff --git a/tools/testing/selftests/timers/.gitignore b/tools/testing/selftests/timers/.gitignore index 32a9eadb2d4e..bb5326ff900b 100644 --- a/tools/testing/selftests/timers/.gitignore +++ b/tools/testing/selftests/timers/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only alarmtimer-suspend change_skew clocksource-switch diff --git a/tools/testing/selftests/tmpfs/.gitignore b/tools/testing/selftests/tmpfs/.gitignore index a96838fad74d..b1afaa925905 100644 --- a/tools/testing/selftests/tmpfs/.gitignore +++ b/tools/testing/selftests/tmpfs/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only /bug-link-o-tmpfile diff --git a/tools/testing/selftests/vDSO/.gitignore b/tools/testing/selftests/vDSO/.gitignore index 133bf9ee986c..382cfb39a1a3 100644 --- a/tools/testing/selftests/vDSO/.gitignore +++ b/tools/testing/selftests/vDSO/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only vdso_test vdso_standalone_test_x86 diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index d3bed9407773..0edb6d900e8d 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only hugepage-mmap hugepage-shm map_hugetlb diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index d3362777a425..61e5cfeb1350 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -54,6 +54,7 @@ #include <linux/userfaultfd.h> #include <setjmp.h> #include <stdbool.h> +#include <assert.h> #include "../kselftest.h" @@ -76,6 +77,8 @@ static int test_type; #define ALARM_INTERVAL_SECS 10 static volatile bool test_uffdio_copy_eexist = true; static volatile bool test_uffdio_zeropage_eexist = true; +/* Whether to test uffd write-protection */ +static bool test_uffdio_wp = false; static bool map_shared; static int huge_fd; @@ -86,6 +89,13 @@ static char *area_src, *area_src_alias, *area_dst, *area_dst_alias; static char *zeropage; pthread_attr_t attr; +/* Userfaultfd test statistics */ +struct uffd_stats { + int cpu; + unsigned long missing_faults; + unsigned long wp_faults; +}; + /* pthread_mutex_t starts at page offset 0 */ #define area_mutex(___area, ___nr) \ ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) @@ -125,6 +135,37 @@ static void usage(void) exit(1); } +static void uffd_stats_reset(struct uffd_stats *uffd_stats, + unsigned long n_cpus) +{ + int i; + + for (i = 0; i < n_cpus; i++) { + uffd_stats[i].cpu = i; + uffd_stats[i].missing_faults = 0; + uffd_stats[i].wp_faults = 0; + } +} + +static void uffd_stats_report(struct uffd_stats *stats, int n_cpus) +{ + int i; + unsigned long long miss_total = 0, wp_total = 0; + + for (i = 0; i < n_cpus; i++) { + miss_total += stats[i].missing_faults; + wp_total += stats[i].wp_faults; + } + + printf("userfaults: %llu missing (", miss_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", stats[i].missing_faults); + printf("\b), %llu wp (", wp_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", stats[i].wp_faults); + printf("\b)\n"); +} + static int anon_release_pages(char *rel_area) { int ret = 0; @@ -245,10 +286,15 @@ struct uffd_test_ops { void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); }; -#define ANON_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \ +#define SHMEM_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \ (1 << _UFFDIO_COPY) | \ (1 << _UFFDIO_ZEROPAGE)) +#define ANON_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \ + (1 << _UFFDIO_COPY) | \ + (1 << _UFFDIO_ZEROPAGE) | \ + (1 << _UFFDIO_WRITEPROTECT)) + static struct uffd_test_ops anon_uffd_test_ops = { .expected_ioctls = ANON_EXPECTED_IOCTLS, .allocate_area = anon_allocate_area, @@ -257,7 +303,7 @@ static struct uffd_test_ops anon_uffd_test_ops = { }; static struct uffd_test_ops shmem_uffd_test_ops = { - .expected_ioctls = ANON_EXPECTED_IOCTLS, + .expected_ioctls = SHMEM_EXPECTED_IOCTLS, .allocate_area = shmem_allocate_area, .release_pages = shmem_release_pages, .alias_mapping = noop_alias_mapping, @@ -281,6 +327,21 @@ static int my_bcmp(char *str1, char *str2, size_t n) return 0; } +static void wp_range(int ufd, __u64 start, __u64 len, bool wp) +{ + struct uffdio_writeprotect prms = { 0 }; + + /* Write protection page faults */ + prms.range.start = start; + prms.range.len = len; + /* Undo write-protect, do wakeup after that */ + prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0; + + if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) + fprintf(stderr, "clear WP failed for address 0x%Lx\n", + start), exit(1); +} + static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; @@ -419,7 +480,10 @@ static int __copy_page(int ufd, unsigned long offset, bool retry) uffdio_copy.dst = (unsigned long) area_dst + offset; uffdio_copy.src = (unsigned long) area_src + offset; uffdio_copy.len = page_size; - uffdio_copy.mode = 0; + if (test_uffdio_wp) + uffdio_copy.mode = UFFDIO_COPY_MODE_WP; + else + uffdio_copy.mode = 0; uffdio_copy.copy = 0; if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { /* real retval in ufdio_copy.copy */ @@ -467,8 +531,8 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg) return 0; } -/* Return 1 if page fault handled by us; otherwise 0 */ -static int uffd_handle_page_fault(struct uffd_msg *msg) +static void uffd_handle_page_fault(struct uffd_msg *msg, + struct uffd_stats *stats) { unsigned long offset; @@ -476,25 +540,32 @@ static int uffd_handle_page_fault(struct uffd_msg *msg) fprintf(stderr, "unexpected msg event %u\n", msg->event), exit(1); - if (bounces & BOUNCE_VERIFY && - msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) - fprintf(stderr, "unexpected write fault\n"), exit(1); + if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { + wp_range(uffd, msg->arg.pagefault.address, page_size, false); + stats->wp_faults++; + } else { + /* Missing page faults */ + if (bounces & BOUNCE_VERIFY && + msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + fprintf(stderr, "unexpected write fault\n"), exit(1); - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; - offset &= ~(page_size-1); + offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; + offset &= ~(page_size-1); - return copy_page(uffd, offset); + if (copy_page(uffd, offset)) + stats->missing_faults++; + } } static void *uffd_poll_thread(void *arg) { - unsigned long cpu = (unsigned long) arg; + struct uffd_stats *stats = (struct uffd_stats *)arg; + unsigned long cpu = stats->cpu; struct pollfd pollfd[2]; struct uffd_msg msg; struct uffdio_register uffd_reg; int ret; char tmp_chr; - unsigned long userfaults = 0; pollfd[0].fd = uffd; pollfd[0].events = POLLIN; @@ -524,7 +595,7 @@ static void *uffd_poll_thread(void *arg) msg.event), exit(1); break; case UFFD_EVENT_PAGEFAULT: - userfaults += uffd_handle_page_fault(&msg); + uffd_handle_page_fault(&msg, stats); break; case UFFD_EVENT_FORK: close(uffd); @@ -543,50 +614,67 @@ static void *uffd_poll_thread(void *arg) break; } } - return (void *)userfaults; + + return NULL; } pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; static void *uffd_read_thread(void *arg) { - unsigned long *this_cpu_userfaults; + struct uffd_stats *stats = (struct uffd_stats *)arg; struct uffd_msg msg; - this_cpu_userfaults = (unsigned long *) arg; - *this_cpu_userfaults = 0; - pthread_mutex_unlock(&uffd_read_mutex); /* from here cancellation is ok */ for (;;) { if (uffd_read_msg(uffd, &msg)) continue; - (*this_cpu_userfaults) += uffd_handle_page_fault(&msg); + uffd_handle_page_fault(&msg, stats); } - return (void *)NULL; + + return NULL; } static void *background_thread(void *arg) { unsigned long cpu = (unsigned long) arg; - unsigned long page_nr; + unsigned long page_nr, start_nr, mid_nr, end_nr; + + start_nr = cpu * nr_pages_per_cpu; + end_nr = (cpu+1) * nr_pages_per_cpu; + mid_nr = (start_nr + end_nr) / 2; - for (page_nr = cpu * nr_pages_per_cpu; - page_nr < (cpu+1) * nr_pages_per_cpu; - page_nr++) + /* Copy the first half of the pages */ + for (page_nr = start_nr; page_nr < mid_nr; page_nr++) + copy_page_retry(uffd, page_nr * page_size); + + /* + * If we need to test uffd-wp, set it up now. Then we'll have + * at least the first half of the pages mapped already which + * can be write-protected for testing + */ + if (test_uffdio_wp) + wp_range(uffd, (unsigned long)area_dst + start_nr * page_size, + nr_pages_per_cpu * page_size, true); + + /* + * Continue the 2nd half of the page copying, handling write + * protection faults if any + */ + for (page_nr = mid_nr; page_nr < end_nr; page_nr++) copy_page_retry(uffd, page_nr * page_size); return NULL; } -static int stress(unsigned long *userfaults) +static int stress(struct uffd_stats *uffd_stats) { unsigned long cpu; pthread_t locking_threads[nr_cpus]; pthread_t uffd_threads[nr_cpus]; pthread_t background_threads[nr_cpus]; - void **_userfaults = (void **) userfaults; finished = 0; for (cpu = 0; cpu < nr_cpus; cpu++) { @@ -595,12 +683,13 @@ static int stress(unsigned long *userfaults) return 1; if (bounces & BOUNCE_POLL) { if (pthread_create(&uffd_threads[cpu], &attr, - uffd_poll_thread, (void *)cpu)) + uffd_poll_thread, + (void *)&uffd_stats[cpu])) return 1; } else { if (pthread_create(&uffd_threads[cpu], &attr, uffd_read_thread, - &_userfaults[cpu])) + (void *)&uffd_stats[cpu])) return 1; pthread_mutex_lock(&uffd_read_mutex); } @@ -637,7 +726,8 @@ static int stress(unsigned long *userfaults) fprintf(stderr, "pipefd write error\n"); return 1; } - if (pthread_join(uffd_threads[cpu], &_userfaults[cpu])) + if (pthread_join(uffd_threads[cpu], + (void *)&uffd_stats[cpu])) return 1; } else { if (pthread_cancel(uffd_threads[cpu])) @@ -735,17 +825,31 @@ static int faulting_process(int signal_test) } for (nr = 0; nr < split_nr_pages; nr++) { + int steps = 1; + unsigned long offset = nr * page_size; + if (signal_test) { if (sigsetjmp(*sigbuf, 1) != 0) { - if (nr == lastnr) { + if (steps == 1 && nr == lastnr) { fprintf(stderr, "Signal repeated\n"); return 1; } lastnr = nr; if (signal_test == 1) { - if (copy_page(uffd, nr * page_size)) - signalled++; + if (steps == 1) { + /* This is a MISSING request */ + steps++; + if (copy_page(uffd, offset)) + signalled++; + } else { + /* This is a WP request */ + assert(steps == 2); + wp_range(uffd, + (__u64)area_dst + + offset, + page_size, false); + } } else { signalled++; continue; @@ -758,8 +862,13 @@ static int faulting_process(int signal_test) fprintf(stderr, "nr %lu memory corruption %Lu %Lu\n", nr, count, - count_verify[nr]), exit(1); - } + count_verify[nr]); + } + /* + * Trigger write protection if there is by writting + * the same value back. + */ + *area_count(area_dst, nr) = count; } if (signal_test) @@ -781,6 +890,11 @@ static int faulting_process(int signal_test) nr, count, count_verify[nr]), exit(1); } + /* + * Trigger write protection if there is by writting + * the same value back. + */ + *area_count(area_dst, nr) = count; } if (uffd_test_ops->release_pages(area_dst)) @@ -884,6 +998,8 @@ static int userfaultfd_zeropage_test(void) uffdio_register.range.start = (unsigned long) area_dst; uffdio_register.range.len = nr_pages * page_size; uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (test_uffdio_wp) + uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) fprintf(stderr, "register failure\n"), exit(1); @@ -908,11 +1024,11 @@ static int userfaultfd_events_test(void) { struct uffdio_register uffdio_register; unsigned long expected_ioctls; - unsigned long userfaults; pthread_t uffd_mon; int err, features; pid_t pid; char c; + struct uffd_stats stats = { 0 }; printf("testing events (fork, remap, remove): "); fflush(stdout); @@ -929,6 +1045,8 @@ static int userfaultfd_events_test(void) uffdio_register.range.start = (unsigned long) area_dst; uffdio_register.range.len = nr_pages * page_size; uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (test_uffdio_wp) + uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) fprintf(stderr, "register failure\n"), exit(1); @@ -939,7 +1057,7 @@ static int userfaultfd_events_test(void) "unexpected missing ioctl for anon memory\n"), exit(1); - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL)) + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) perror("uffd_poll_thread create"), exit(1); pid = fork(); @@ -955,13 +1073,14 @@ static int userfaultfd_events_test(void) if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) perror("pipe write"), exit(1); - if (pthread_join(uffd_mon, (void **)&userfaults)) + if (pthread_join(uffd_mon, NULL)) return 1; close(uffd); - printf("userfaults: %ld\n", userfaults); - return userfaults != nr_pages; + uffd_stats_report(&stats, 1); + + return stats.missing_faults != nr_pages; } static int userfaultfd_sig_test(void) @@ -973,6 +1092,7 @@ static int userfaultfd_sig_test(void) int err, features; pid_t pid; char c; + struct uffd_stats stats = { 0 }; printf("testing signal delivery: "); fflush(stdout); @@ -988,6 +1108,8 @@ static int userfaultfd_sig_test(void) uffdio_register.range.start = (unsigned long) area_dst; uffdio_register.range.len = nr_pages * page_size; uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (test_uffdio_wp) + uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) fprintf(stderr, "register failure\n"), exit(1); @@ -1004,7 +1126,7 @@ static int userfaultfd_sig_test(void) if (uffd_test_ops->release_pages(area_dst)) return 1; - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL)) + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) perror("uffd_poll_thread create"), exit(1); pid = fork(); @@ -1030,6 +1152,7 @@ static int userfaultfd_sig_test(void) close(uffd); return userfaults != 0; } + static int userfaultfd_stress(void) { void *area; @@ -1038,7 +1161,7 @@ static int userfaultfd_stress(void) struct uffdio_register uffdio_register; unsigned long cpu; int err; - unsigned long userfaults[nr_cpus]; + struct uffd_stats uffd_stats[nr_cpus]; uffd_test_ops->allocate_area((void **)&area_src); if (!area_src) @@ -1119,6 +1242,8 @@ static int userfaultfd_stress(void) uffdio_register.range.start = (unsigned long) area_dst; uffdio_register.range.len = nr_pages * page_size; uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (test_uffdio_wp) + uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { fprintf(stderr, "register failure\n"); return 1; @@ -1167,10 +1292,17 @@ static int userfaultfd_stress(void) if (uffd_test_ops->release_pages(area_dst)) return 1; + uffd_stats_reset(uffd_stats, nr_cpus); + /* bounce pass */ - if (stress(userfaults)) + if (stress(uffd_stats)) return 1; + /* Clear all the write protections if there is any */ + if (test_uffdio_wp) + wp_range(uffd, (unsigned long)area_dst, + nr_pages * page_size, false); + /* unregister */ if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) { fprintf(stderr, "unregister failure\n"); @@ -1209,10 +1341,7 @@ static int userfaultfd_stress(void) area_src_alias = area_dst_alias; area_dst_alias = tmp_area; - printf("userfaults:"); - for (cpu = 0; cpu < nr_cpus; cpu++) - printf(" %lu", userfaults[cpu]); - printf("\n"); + uffd_stats_report(uffd_stats, nr_cpus); } if (err) @@ -1252,6 +1381,8 @@ static void set_test_type(const char *type) if (!strcmp(type, "anon")) { test_type = TEST_ANON; uffd_test_ops = &anon_uffd_test_ops; + /* Only enable write-protect test for anonymous test */ + test_uffdio_wp = true; } else if (!strcmp(type, "hugetlb")) { test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; diff --git a/tools/testing/selftests/watchdog/.gitignore b/tools/testing/selftests/watchdog/.gitignore index 5aac51575c7e..61d7b89cdbca 100644 --- a/tools/testing/selftests/watchdog/.gitignore +++ b/tools/testing/selftests/watchdog/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only watchdog-test diff --git a/tools/testing/selftests/wireguard/qemu/.gitignore b/tools/testing/selftests/wireguard/qemu/.gitignore index 415b542a9d59..bfa15e6feb2f 100644 --- a/tools/testing/selftests/wireguard/qemu/.gitignore +++ b/tools/testing/selftests/wireguard/qemu/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only build/ distfiles/ diff --git a/tools/testing/selftests/x86/.gitignore b/tools/testing/selftests/x86/.gitignore index 7757f73ff9a3..022a1f3b64ef 100644 --- a/tools/testing/selftests/x86/.gitignore +++ b/tools/testing/selftests/x86/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only *_32 *_64 single_step_syscall diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore index 7f7a2ccc30c4..87ca2731cff9 100644 --- a/tools/testing/vsock/.gitignore +++ b/tools/testing/vsock/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only *.d vsock_test vsock_diag_test diff --git a/tools/thermal/tmon/.gitignore b/tools/thermal/tmon/.gitignore index 06e96be65276..d9e97a0308f5 100644 --- a/tools/thermal/tmon/.gitignore +++ b/tools/thermal/tmon/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only /tmon diff --git a/tools/thermal/tmon/tmon.c b/tools/thermal/tmon/tmon.c index 83ec6e482f12..7eb3216a27f4 100644 --- a/tools/thermal/tmon/tmon.c +++ b/tools/thermal/tmon/tmon.c @@ -46,7 +46,7 @@ static void start_daemon_mode(void); pthread_t event_tid; pthread_mutex_t input_lock; -void usage() +void usage(void) { printf("Usage: tmon [OPTION...]\n"); printf(" -c, --control cooling device in control\n"); @@ -62,7 +62,7 @@ void usage() exit(0); } -void version() +void version(void) { printf("TMON version %s\n", VERSION); exit(EXIT_SUCCESS); @@ -70,7 +70,6 @@ void version() static void tmon_cleanup(void) { - syslog(LOG_INFO, "TMON exit cleanup\n"); fflush(stdout); refresh(); @@ -96,7 +95,6 @@ static void tmon_cleanup(void) exit(1); } - static void tmon_sig_handler(int sig) { syslog(LOG_INFO, "TMON caught signal %d\n", sig); @@ -120,7 +118,6 @@ static void tmon_sig_handler(int sig) tmon_exit = true; } - static void start_syslog(void) { if (debug_on) @@ -167,7 +164,6 @@ static void prepare_logging(void) return; } - fprintf(tmon_log, "#----------- THERMAL SYSTEM CONFIG -------------\n"); for (i = 0; i < ptdata.nr_tz_sensor; i++) { char binding_str[33]; /* size of long + 1 */ @@ -175,7 +171,7 @@ static void prepare_logging(void) memset(binding_str, 0, sizeof(binding_str)); for (j = 0; j < 32; j++) - binding_str[j] = (ptdata.tzi[i].cdev_binding & 1<<j) ? + binding_str[j] = (ptdata.tzi[i].cdev_binding & (1 << j)) ? '1' : '0'; fprintf(tmon_log, "#thermal zone %s%02d cdevs binding: %32s\n", @@ -187,7 +183,6 @@ static void prepare_logging(void) trip_type_name[ptdata.tzi[i].tp[j].type], ptdata.tzi[i].tp[j].temp); } - } for (i = 0; i < ptdata.nr_cooling_dev; i++) @@ -219,7 +214,6 @@ static struct option opts[] = { { 0, 0, NULL, 0 } }; - int main(int argc, char **argv) { int err = 0; @@ -283,7 +277,7 @@ int main(int argc, char **argv) if (signal(SIGINT, tmon_sig_handler) == SIG_ERR) syslog(LOG_DEBUG, "Cannot handle SIGINT\n"); if (signal(SIGTERM, tmon_sig_handler) == SIG_ERR) - syslog(LOG_DEBUG, "Cannot handle SIGINT\n"); + syslog(LOG_DEBUG, "Cannot handle SIGTERM\n"); if (probe_thermal_sysfs()) { pthread_mutex_destroy(&input_lock); @@ -328,8 +322,7 @@ int main(int argc, char **argv) show_cooling_device(); } time_elapsed += ticktime; - controller_handler(trec[0].temp[target_tz_index] / 1000, - &yk); + controller_handler(trec[0].temp[target_tz_index] / 1000, &yk); trec[0].pid_out_pct = yk; if (!dialogue_on) show_control_w(); @@ -340,14 +333,15 @@ int main(int argc, char **argv) return 0; } -static void start_daemon_mode() +static void start_daemon_mode(void) { daemon_mode = 1; /* fork */ pid_t sid, pid = fork(); - if (pid < 0) { + + if (pid < 0) exit(EXIT_FAILURE); - } else if (pid > 0) + else if (pid > 0) /* kill parent */ exit(EXIT_SUCCESS); @@ -366,11 +360,9 @@ static void start_daemon_mode() if ((chdir("/")) < 0) exit(EXIT_FAILURE); - sleep(10); close(STDIN_FILENO); close(STDOUT_FILENO); close(STDERR_FILENO); - } diff --git a/tools/usb/.gitignore b/tools/usb/.gitignore index 1b7448981435..fce1ef5a9267 100644 --- a/tools/usb/.gitignore +++ b/tools/usb/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only ffs-test testusb diff --git a/tools/usb/usbip/.gitignore b/tools/usb/usbip/.gitignore index 03b892c8bd8c..597361a96dbb 100644 --- a/tools/usb/usbip/.gitignore +++ b/tools/usb/usbip/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only Makefile Makefile.in aclocal.m4 diff --git a/tools/virtio/.gitignore b/tools/virtio/.gitignore index 1cfbb0157a46..075588c4da08 100644 --- a/tools/virtio/.gitignore +++ b/tools/virtio/.gitignore @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only *.d virtio_test vringh_test diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index 8e2a908115c2..f33f32f1d208 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -8,7 +8,32 @@ CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-poin vpath %.c ../../drivers/virtio ../../drivers/vhost mod: ${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test V=${V} -.PHONY: all test mod clean + +#oot: build vhost as an out of tree module for a distro kernel +#no effort is taken to make it actually build or work, but tends to mostly work +#if the distro kernel is very close to upstream +#unsupported! this is a development tool only, don't use the +#resulting modules in production! +OOT_KSRC=/lib/modules/$$(uname -r)/build +OOT_VHOST=`pwd`/../../drivers/vhost +#Everyone depends on vhost +#Tweak the below to enable more modules +OOT_CONFIGS=\ + CONFIG_VHOST=m \ + CONFIG_VHOST_NET=n \ + CONFIG_VHOST_SCSI=n \ + CONFIG_VHOST_VSOCK=n +OOT_BUILD=KCFLAGS="-I "${OOT_VHOST} ${MAKE} -C ${OOT_KSRC} V=${V} +oot-build: + echo "UNSUPPORTED! Don't use the resulting modules in production!" + ${OOT_BUILD} M=`pwd`/vhost_test + ${OOT_BUILD} M=${OOT_VHOST} ${OOT_CONFIGS} + +oot-clean: oot-build +oot: oot-build +oot-clean: OOT_BUILD+=clean + +.PHONY: all test mod clean vhost oot oot-clean oot-build clean: ${RM} *.o vringh_test virtio_test vhost_test/*.o vhost_test/.*.cmd \ vhost_test/Module.symvers vhost_test/modules.order *.d diff --git a/tools/vm/.gitignore b/tools/vm/.gitignore index 44f095fa2604..79bb92ae1bb3 100644 --- a/tools/vm/.gitignore +++ b/tools/vm/.gitignore @@ -1,2 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only slabinfo page-types |