diff options
author | Ingo Molnar <mingo@kernel.org> | 2020-03-21 11:23:40 +0300 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2020-03-21 11:24:41 +0300 |
commit | a4654e9bde4ecedb4921e6c8fe2088114bdff1b3 (patch) | |
tree | 1b9970b520d7bc7176cc9460fe67f210be5ea181 /tools | |
parent | 7add7875a8eb4ffe5eddaf8a11e409c9e1b6e3f3 (diff) | |
parent | e4160b2e4b02377c67f8ecd05786811598f39acd (diff) | |
download | linux-a4654e9bde4ecedb4921e6c8fe2088114bdff1b3.tar.xz |
Merge branch 'x86/kdump' into locking/kcsan, to resolve conflicts
Conflicts:
arch/x86/purgatory/Makefile
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'tools')
563 files changed, 28114 insertions, 4378 deletions
diff --git a/tools/Makefile b/tools/Makefile index 7e42f7b8bfa7..bd778812e915 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -28,6 +28,7 @@ help: @echo ' pci - PCI tools' @echo ' perf - Linux performance measurement and analysis tool' @echo ' selftests - various kernel selftests' + @echo ' bootconfig - boot config tool' @echo ' spi - spi tools' @echo ' tmon - thermal monitoring and tuning tool' @echo ' turbostat - Intel CPU idle stats and freq reporting tool' @@ -63,7 +64,7 @@ acpi: FORCE cpupower: FORCE $(call descend,power/$@) -cgroup firewire hv guest spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging: FORCE +cgroup firewire hv guest bootconfig spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging: FORCE $(call descend,$@) liblockdep: FORCE @@ -96,7 +97,7 @@ kvm_stat: FORCE $(call descend,kvm/$@) all: acpi cgroup cpupower gpio hv firewire liblockdep \ - perf selftests spi turbostat usb \ + perf selftests bootconfig spi turbostat usb \ virtio vm bpf x86_energy_perf_policy \ tmon freefall iio objtool kvm_stat wmi \ pci debugging @@ -107,7 +108,7 @@ acpi_install: cpupower_install: $(call descend,power/$(@:_install=),install) -cgroup_install firewire_install gpio_install hv_install iio_install perf_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install: +cgroup_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install: $(call descend,$(@:_install=),install) liblockdep_install: @@ -141,7 +142,7 @@ acpi_clean: cpupower_clean: $(call descend,power/cpupower,clean) -cgroup_clean hv_clean firewire_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean: +cgroup_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean: $(call descend,$(@:_clean=),clean) liblockdep_clean: @@ -176,7 +177,7 @@ build_clean: $(call descend,build,clean) clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \ - perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \ + perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \ vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \ freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \ gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \ diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 820e5751ada7..ba85bb23f060 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -220,10 +220,18 @@ struct kvm_vcpu_events { #define KVM_REG_ARM_PTIMER_CVAL ARM64_SYS_REG(3, 3, 14, 2, 2) #define KVM_REG_ARM_PTIMER_CNT ARM64_SYS_REG(3, 3, 14, 0, 1) -/* EL0 Virtual Timer Registers */ +/* + * EL0 Virtual Timer Registers + * + * WARNING: + * KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined + * with the appropriate register encodings. Their values have been + * accidentally swapped. As this is set API, the definitions here + * must be used, rather than ones derived from the encodings. + */ #define KVM_REG_ARM_TIMER_CTL ARM64_SYS_REG(3, 3, 14, 3, 1) -#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) +#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) /* KVM-as-firmware specific pseudo-registers */ #define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h index 4703d218663a..f83a70e07df8 100644 --- a/tools/arch/arm64/include/uapi/asm/unistd.h +++ b/tools/arch/arm64/include/uapi/asm/unistd.h @@ -19,5 +19,6 @@ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT #define __ARCH_WANT_TIME32_SYSCALLS +#define __ARCH_WANT_SYS_CLONE3 #include <asm-generic/unistd.h> diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index e9b62498fe75..f3327cb56edf 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -220,6 +220,7 @@ #define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (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 */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -357,6 +358,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 8e1d0bb46361..4ea8584682f9 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -10,12 +10,6 @@ * cpu_feature_enabled(). */ -#ifdef CONFIG_X86_INTEL_MPX -# define DISABLE_MPX 0 -#else -# define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31)) -#endif - #ifdef CONFIG_X86_SMAP # define DISABLE_SMAP 0 #else @@ -74,7 +68,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_MPX|DISABLE_SMAP) +#define DISABLED_MASK9 (DISABLE_SMAP) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 084e98da04a7..ebe1685e92dd 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -558,7 +558,14 @@ #define MSR_IA32_EBL_CR_POWERON 0x0000002a #define MSR_EBC_FREQUENCY_ID 0x0000002c #define MSR_SMI_COUNT 0x00000034 -#define MSR_IA32_FEATURE_CONTROL 0x0000003a + +/* Referred to as IA32_FEATURE_CONTROL in Intel's SDM. */ +#define MSR_IA32_FEAT_CTL 0x0000003a +#define FEAT_CTL_LOCKED BIT(0) +#define FEAT_CTL_VMX_ENABLED_INSIDE_SMX BIT(1) +#define FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX BIT(2) +#define FEAT_CTL_LMCE_ENABLED BIT(20) + #define MSR_IA32_TSC_ADJUST 0x0000003b #define MSR_IA32_BNDCFGS 0x00000d90 @@ -566,11 +573,6 @@ #define MSR_IA32_XSS 0x00000da0 -#define FEATURE_CONTROL_LOCKED (1<<0) -#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1) -#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2) -#define FEATURE_CONTROL_LMCE (1<<20) - #define MSR_IA32_APICBASE 0x0000001b #define MSR_IA32_APICBASE_BSP (1<<8) #define MSR_IA32_APICBASE_ENABLE (1<<11) diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 3eb8411ab60e..e95b72ec19bc 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -33,7 +33,7 @@ #define EXIT_REASON_TRIPLE_FAULT 2 #define EXIT_REASON_INIT_SIGNAL 3 -#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 #define EXIT_REASON_TASK_SWITCH 9 #define EXIT_REASON_CPUID 10 @@ -94,7 +94,7 @@ { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ { EXIT_REASON_INIT_SIGNAL, "INIT_SIGNAL" }, \ - { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \ + { EXIT_REASON_INTERRUPT_WINDOW, "INTERRUPT_WINDOW" }, \ { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ { EXIT_REASON_CPUID, "CPUID" }, \ diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index 8908c58bd6cd..53adc1762ec0 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -929,7 +929,7 @@ EndTable GrpTable: Grp3_2 0: TEST Ev,Iz -1: +1: TEST Ev,Iz 2: NOT Ev 3: NEG Ev 4: MUL rAX,Ev diff --git a/tools/bootconfig/.gitignore b/tools/bootconfig/.gitignore new file mode 100644 index 000000000000..e7644dfaa4a7 --- /dev/null +++ b/tools/bootconfig/.gitignore @@ -0,0 +1 @@ +bootconfig diff --git a/tools/bootconfig/Makefile b/tools/bootconfig/Makefile new file mode 100644 index 000000000000..a6146ac64458 --- /dev/null +++ b/tools/bootconfig/Makefile @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for bootconfig command + +bindir ?= /usr/bin + +HEADER = include/linux/bootconfig.h +CFLAGS = -Wall -g -I./include + +PROGS = bootconfig + +all: $(PROGS) + +bootconfig: ../../lib/bootconfig.c main.c $(HEADER) + $(CC) $(filter %.c,$^) $(CFLAGS) -o $@ + +install: $(PROGS) + install bootconfig $(DESTDIR)$(bindir) + +test: bootconfig + ./test-bootconfig.sh + +clean: + $(RM) -f *.o bootconfig diff --git a/tools/bootconfig/include/linux/bootconfig.h b/tools/bootconfig/include/linux/bootconfig.h new file mode 100644 index 000000000000..078cbd2ba651 --- /dev/null +++ b/tools/bootconfig/include/linux/bootconfig.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BOOTCONFIG_LINUX_BOOTCONFIG_H +#define _BOOTCONFIG_LINUX_BOOTCONFIG_H + +#include "../../../../include/linux/bootconfig.h" + +#endif diff --git a/tools/bootconfig/include/linux/bug.h b/tools/bootconfig/include/linux/bug.h new file mode 100644 index 000000000000..7b65a389c0dd --- /dev/null +++ b/tools/bootconfig/include/linux/bug.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SKC_LINUX_BUG_H +#define _SKC_LINUX_BUG_H + +#include <stdio.h> +#include <stdlib.h> + +#define WARN_ON(cond) \ + ((cond) ? printf("Internal warning(%s:%d, %s): %s\n", \ + __FILE__, __LINE__, __func__, #cond) : 0) + +#endif diff --git a/tools/bootconfig/include/linux/ctype.h b/tools/bootconfig/include/linux/ctype.h new file mode 100644 index 000000000000..c56ecc136448 --- /dev/null +++ b/tools/bootconfig/include/linux/ctype.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SKC_LINUX_CTYPE_H +#define _SKC_LINUX_CTYPE_H + +#include <ctype.h> + +#endif diff --git a/tools/bootconfig/include/linux/errno.h b/tools/bootconfig/include/linux/errno.h new file mode 100644 index 000000000000..5d9f91ec2fda --- /dev/null +++ b/tools/bootconfig/include/linux/errno.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SKC_LINUX_ERRNO_H +#define _SKC_LINUX_ERRNO_H + +#include <asm/errno.h> + +#endif diff --git a/tools/bootconfig/include/linux/kernel.h b/tools/bootconfig/include/linux/kernel.h new file mode 100644 index 000000000000..2d93320aa374 --- /dev/null +++ b/tools/bootconfig/include/linux/kernel.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SKC_LINUX_KERNEL_H +#define _SKC_LINUX_KERNEL_H + +#include <stdlib.h> +#include <stdbool.h> + +#include <linux/printk.h> + +typedef unsigned short u16; +typedef unsigned int u32; + +#define unlikely(cond) (cond) + +#define __init +#define __initdata + +#endif diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h new file mode 100644 index 000000000000..7862f217d85d --- /dev/null +++ b/tools/bootconfig/include/linux/memblock.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _XBC_LINUX_MEMBLOCK_H +#define _XBC_LINUX_MEMBLOCK_H + +#include <stdlib.h> + +#define __pa(addr) (addr) +#define SMP_CACHE_BYTES 0 +#define memblock_alloc(size, align) malloc(size) +#define memblock_free(paddr, size) free(paddr) + +#endif diff --git a/tools/bootconfig/include/linux/printk.h b/tools/bootconfig/include/linux/printk.h new file mode 100644 index 000000000000..e978a63d3222 --- /dev/null +++ b/tools/bootconfig/include/linux/printk.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SKC_LINUX_PRINTK_H +#define _SKC_LINUX_PRINTK_H + +#include <stdio.h> + +/* controllable printf */ +extern int pr_output; +#define printk(fmt, ...) \ + (pr_output ? printf(fmt, ##__VA_ARGS__) : 0) + +#define pr_err printk +#define pr_warn printk +#define pr_info printk +#define pr_debug printk + +#endif diff --git a/tools/bootconfig/include/linux/string.h b/tools/bootconfig/include/linux/string.h new file mode 100644 index 000000000000..8267af75153a --- /dev/null +++ b/tools/bootconfig/include/linux/string.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _SKC_LINUX_STRING_H +#define _SKC_LINUX_STRING_H + +#include <string.h> + +/* Copied from lib/string.c */ +static inline char *skip_spaces(const char *str) +{ + while (isspace(*str)) + ++str; + return (char *)str; +} + +static inline char *strim(char *s) +{ + size_t size; + char *end; + + size = strlen(s); + if (!size) + return s; + + end = s + size - 1; + while (end >= s && isspace(*end)) + end--; + *(end + 1) = '\0'; + + return skip_spaces(s); +} + +#endif diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c new file mode 100644 index 000000000000..e18eeb070562 --- /dev/null +++ b/tools/bootconfig/main.c @@ -0,0 +1,354 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Boot config tool for initrd image + */ +#include <stdio.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> + +#include <linux/kernel.h> +#include <linux/bootconfig.h> + +int pr_output = 1; + +static int xbc_show_array(struct xbc_node *node) +{ + const char *val; + int i = 0; + + xbc_array_for_each_value(node, val) { + printf("\"%s\"%s", val, node->next ? ", " : ";\n"); + i++; + } + return i; +} + +static void xbc_show_compact_tree(void) +{ + struct xbc_node *node, *cnode; + int depth = 0, i; + + node = xbc_root_node(); + while (node && xbc_node_is_key(node)) { + for (i = 0; i < depth; i++) + printf("\t"); + cnode = xbc_node_get_child(node); + while (cnode && xbc_node_is_key(cnode) && !cnode->next) { + printf("%s.", xbc_node_get_data(node)); + node = cnode; + cnode = xbc_node_get_child(node); + } + if (cnode && xbc_node_is_key(cnode)) { + printf("%s {\n", xbc_node_get_data(node)); + depth++; + node = cnode; + continue; + } else if (cnode && xbc_node_is_value(cnode)) { + printf("%s = ", xbc_node_get_data(node)); + if (cnode->next) + xbc_show_array(cnode); + else + printf("\"%s\";\n", xbc_node_get_data(cnode)); + } else { + printf("%s;\n", xbc_node_get_data(node)); + } + + if (node->next) { + node = xbc_node_get_next(node); + continue; + } + while (!node->next) { + node = xbc_node_get_parent(node); + if (!node) + return; + if (!xbc_node_get_child(node)->next) + continue; + depth--; + for (i = 0; i < depth; i++) + printf("\t"); + printf("}\n"); + } + node = xbc_node_get_next(node); + } +} + +/* Simple real checksum */ +int checksum(unsigned char *buf, int len) +{ + int i, sum = 0; + + for (i = 0; i < len; i++) + sum += buf[i]; + + return sum; +} + +#define PAGE_SIZE 4096 + +int load_xbc_fd(int fd, char **buf, int size) +{ + int ret; + + *buf = malloc(size + 1); + if (!*buf) + return -ENOMEM; + + ret = read(fd, *buf, size); + if (ret < 0) + return -errno; + (*buf)[size] = '\0'; + + return ret; +} + +/* Return the read size or -errno */ +int load_xbc_file(const char *path, char **buf) +{ + struct stat stat; + int fd, ret; + + fd = open(path, O_RDONLY); + if (fd < 0) + return -errno; + ret = fstat(fd, &stat); + if (ret < 0) + return -errno; + + ret = load_xbc_fd(fd, buf, stat.st_size); + + close(fd); + + return ret; +} + +int load_xbc_from_initrd(int fd, char **buf) +{ + struct stat stat; + int ret; + u32 size = 0, csum = 0, rcsum; + + ret = fstat(fd, &stat); + if (ret < 0) + return -errno; + + if (stat.st_size < 8) + return 0; + + if (lseek(fd, -8, SEEK_END) < 0) { + pr_err("Failed to lseek: %d\n", -errno); + return -errno; + } + + if (read(fd, &size, sizeof(u32)) < 0) + return -errno; + + if (read(fd, &csum, sizeof(u32)) < 0) + return -errno; + + /* Wrong size, maybe no boot config here */ + if (stat.st_size < size + 8) + return 0; + + if (lseek(fd, stat.st_size - 8 - size, SEEK_SET) < 0) { + pr_err("Failed to lseek: %d\n", -errno); + return -errno; + } + + ret = load_xbc_fd(fd, buf, size); + if (ret < 0) + return ret; + + /* Wrong Checksum, maybe no boot config here */ + rcsum = checksum((unsigned char *)*buf, size); + if (csum != rcsum) { + pr_err("checksum error: %d != %d\n", csum, rcsum); + return 0; + } + + ret = xbc_init(*buf); + /* Wrong data, maybe no boot config here */ + if (ret < 0) + return 0; + + return size; +} + +int show_xbc(const char *path) +{ + int ret, fd; + char *buf = NULL; + + fd = open(path, O_RDONLY); + if (fd < 0) { + pr_err("Failed to open initrd %s: %d\n", path, fd); + return -errno; + } + + ret = load_xbc_from_initrd(fd, &buf); + if (ret < 0) + pr_err("Failed to load a boot config from initrd: %d\n", ret); + else + xbc_show_compact_tree(); + + close(fd); + free(buf); + + return ret; +} + +int delete_xbc(const char *path) +{ + struct stat stat; + int ret = 0, fd, size; + char *buf = NULL; + + fd = open(path, O_RDWR); + if (fd < 0) { + pr_err("Failed to open initrd %s: %d\n", path, fd); + return -errno; + } + + /* + * Suppress error messages in xbc_init() because it can be just a + * data which concidentally matches the size and checksum footer. + */ + pr_output = 0; + size = load_xbc_from_initrd(fd, &buf); + pr_output = 1; + if (size < 0) { + ret = size; + pr_err("Failed to load a boot config from initrd: %d\n", ret); + } else if (size > 0) { + ret = fstat(fd, &stat); + if (!ret) + ret = ftruncate(fd, stat.st_size - size - 8); + if (ret) + ret = -errno; + } /* Ignore if there is no boot config in initrd */ + + close(fd); + free(buf); + + return ret; +} + +int apply_xbc(const char *path, const char *xbc_path) +{ + u32 size, csum; + char *buf, *data; + int ret, fd; + + ret = load_xbc_file(xbc_path, &buf); + if (ret < 0) { + pr_err("Failed to load %s : %d\n", xbc_path, ret); + return ret; + } + size = strlen(buf) + 1; + csum = checksum((unsigned char *)buf, size); + + /* Prepare xbc_path data */ + data = malloc(size + 8); + if (!data) + return -ENOMEM; + strcpy(data, buf); + *(u32 *)(data + size) = size; + *(u32 *)(data + size + 4) = csum; + + /* Check the data format */ + ret = xbc_init(buf); + if (ret < 0) { + pr_err("Failed to parse %s: %d\n", xbc_path, ret); + free(data); + free(buf); + return ret; + } + printf("Apply %s to %s\n", xbc_path, path); + printf("\tNumber of nodes: %d\n", ret); + printf("\tSize: %u bytes\n", (unsigned int)size); + printf("\tChecksum: %d\n", (unsigned int)csum); + + /* TODO: Check the options by schema */ + xbc_destroy_all(); + free(buf); + + /* Remove old boot config if exists */ + ret = delete_xbc(path); + if (ret < 0) { + pr_err("Failed to delete previous boot config: %d\n", ret); + return ret; + } + + /* Apply new one */ + fd = open(path, O_RDWR | O_APPEND); + if (fd < 0) { + pr_err("Failed to open %s: %d\n", path, fd); + return fd; + } + /* TODO: Ensure the @path is initramfs/initrd image */ + ret = write(fd, data, size + 8); + if (ret < 0) { + pr_err("Failed to apply a boot config: %d\n", ret); + return ret; + } + close(fd); + free(data); + + return 0; +} + +int usage(void) +{ + printf("Usage: bootconfig [OPTIONS] <INITRD>\n" + " Apply, delete or show boot config to initrd.\n" + " Options:\n" + " -a <config>: Apply boot config to initrd\n" + " -d : Delete boot config file from initrd\n\n" + " If no option is given, show current applied boot config.\n"); + return -1; +} + +int main(int argc, char **argv) +{ + char *path = NULL; + char *apply = NULL; + bool delete = false; + int opt; + + while ((opt = getopt(argc, argv, "hda:")) != -1) { + switch (opt) { + case 'd': + delete = true; + break; + case 'a': + apply = optarg; + break; + case 'h': + default: + return usage(); + } + } + + if (apply && delete) { + pr_err("Error: You can not specify both -a and -d at once.\n"); + return usage(); + } + + if (optind >= argc) { + pr_err("Error: No initrd is specified.\n"); + return usage(); + } + + path = argv[optind]; + + if (apply) + return apply_xbc(path, apply); + else if (delete) + return delete_xbc(path); + + return show_xbc(path); +} diff --git a/tools/bootconfig/samples/bad-array-space-comment.bconf b/tools/bootconfig/samples/bad-array-space-comment.bconf new file mode 100644 index 000000000000..fda19e47d0db --- /dev/null +++ b/tools/bootconfig/samples/bad-array-space-comment.bconf @@ -0,0 +1,5 @@ +key = # comment + "value1", # comment1 + "value2" # comment2 +, + "value3" diff --git a/tools/bootconfig/samples/bad-array.bconf b/tools/bootconfig/samples/bad-array.bconf new file mode 100644 index 000000000000..0174af019d7f --- /dev/null +++ b/tools/bootconfig/samples/bad-array.bconf @@ -0,0 +1,2 @@ +# Array must be comma separated. +key = "value1" "value2" diff --git a/tools/bootconfig/samples/bad-dotword.bconf b/tools/bootconfig/samples/bad-dotword.bconf new file mode 100644 index 000000000000..ba5557b2bdd3 --- /dev/null +++ b/tools/bootconfig/samples/bad-dotword.bconf @@ -0,0 +1,4 @@ +# do not start keyword with . +key { + .word = 1 +} diff --git a/tools/bootconfig/samples/bad-empty.bconf b/tools/bootconfig/samples/bad-empty.bconf new file mode 100644 index 000000000000..2ba3f6cc6a47 --- /dev/null +++ b/tools/bootconfig/samples/bad-empty.bconf @@ -0,0 +1 @@ +# Wrong boot config: comment only diff --git a/tools/bootconfig/samples/bad-keyerror.bconf b/tools/bootconfig/samples/bad-keyerror.bconf new file mode 100644 index 000000000000..b6e247a099d0 --- /dev/null +++ b/tools/bootconfig/samples/bad-keyerror.bconf @@ -0,0 +1,2 @@ +# key word can not contain "," +key,word diff --git a/tools/bootconfig/samples/bad-longkey.bconf b/tools/bootconfig/samples/bad-longkey.bconf new file mode 100644 index 000000000000..eb97369f91a8 --- /dev/null +++ b/tools/bootconfig/samples/bad-longkey.bconf @@ -0,0 +1 @@ +key_word_is_too_long01234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345 diff --git a/tools/bootconfig/samples/bad-manywords.bconf b/tools/bootconfig/samples/bad-manywords.bconf new file mode 100644 index 000000000000..8db81967c48a --- /dev/null +++ b/tools/bootconfig/samples/bad-manywords.bconf @@ -0,0 +1 @@ +key1.is2.too3.long4.5.6.7.8.9.10.11.12.13.14.15.16.17 diff --git a/tools/bootconfig/samples/bad-no-keyword.bconf b/tools/bootconfig/samples/bad-no-keyword.bconf new file mode 100644 index 000000000000..eff26808566c --- /dev/null +++ b/tools/bootconfig/samples/bad-no-keyword.bconf @@ -0,0 +1,2 @@ +# No keyword +{} diff --git a/tools/bootconfig/samples/bad-nonprintable.bconf b/tools/bootconfig/samples/bad-nonprintable.bconf new file mode 100644 index 000000000000..3bb1a2864e52 --- /dev/null +++ b/tools/bootconfig/samples/bad-nonprintable.bconf @@ -0,0 +1,2 @@ +# Non printable +key = "" diff --git a/tools/bootconfig/samples/bad-spaceword.bconf b/tools/bootconfig/samples/bad-spaceword.bconf new file mode 100644 index 000000000000..90c703d32a9a --- /dev/null +++ b/tools/bootconfig/samples/bad-spaceword.bconf @@ -0,0 +1,2 @@ +# No space between words +key . word diff --git a/tools/bootconfig/samples/bad-tree.bconf b/tools/bootconfig/samples/bad-tree.bconf new file mode 100644 index 000000000000..5a6038edcd55 --- /dev/null +++ b/tools/bootconfig/samples/bad-tree.bconf @@ -0,0 +1,5 @@ +# brace is not closing +tree { + node { + value = 1 +} diff --git a/tools/bootconfig/samples/bad-value.bconf b/tools/bootconfig/samples/bad-value.bconf new file mode 100644 index 000000000000..a1217fed86cc --- /dev/null +++ b/tools/bootconfig/samples/bad-value.bconf @@ -0,0 +1,3 @@ +# Quotes error +value = "data + diff --git a/tools/bootconfig/samples/escaped.bconf b/tools/bootconfig/samples/escaped.bconf new file mode 100644 index 000000000000..9f72043b3216 --- /dev/null +++ b/tools/bootconfig/samples/escaped.bconf @@ -0,0 +1,3 @@ +key1 = "A\B\C" +key2 = '\'\'' +key3 = "\\" diff --git a/tools/bootconfig/samples/good-array-space-comment.bconf b/tools/bootconfig/samples/good-array-space-comment.bconf new file mode 100644 index 000000000000..45b938dc0695 --- /dev/null +++ b/tools/bootconfig/samples/good-array-space-comment.bconf @@ -0,0 +1,4 @@ +key = # comment + "value1", # comment1 + "value2" , # comment2 + "value3" diff --git a/tools/bootconfig/samples/good-comment-after-value.bconf b/tools/bootconfig/samples/good-comment-after-value.bconf new file mode 100644 index 000000000000..0d92a853df72 --- /dev/null +++ b/tools/bootconfig/samples/good-comment-after-value.bconf @@ -0,0 +1 @@ +key = "value" # comment diff --git a/tools/bootconfig/samples/good-printables.bconf b/tools/bootconfig/samples/good-printables.bconf new file mode 100644 index 000000000000..ebb985a66ed8 --- /dev/null +++ b/tools/bootconfig/samples/good-printables.bconf @@ -0,0 +1,2 @@ +key = " + !#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~" diff --git a/tools/bootconfig/samples/good-simple.bconf b/tools/bootconfig/samples/good-simple.bconf new file mode 100644 index 000000000000..37dd6d21c176 --- /dev/null +++ b/tools/bootconfig/samples/good-simple.bconf @@ -0,0 +1,11 @@ +# A good simple bootconfig + +key.word1 = 1 +key.word2=2 +key.word3 = 3; + +key { +word4 = 4 } + +key { word5 = 5; word6 = 6 } + diff --git a/tools/bootconfig/samples/good-single.bconf b/tools/bootconfig/samples/good-single.bconf new file mode 100644 index 000000000000..98e55ad8b711 --- /dev/null +++ b/tools/bootconfig/samples/good-single.bconf @@ -0,0 +1,4 @@ +# single key style +key = 1 +key2 = 2 +key3 = "alpha", "beta" diff --git a/tools/bootconfig/samples/good-space-after-value.bconf b/tools/bootconfig/samples/good-space-after-value.bconf new file mode 100644 index 000000000000..56c15cbc5741 --- /dev/null +++ b/tools/bootconfig/samples/good-space-after-value.bconf @@ -0,0 +1 @@ +key = "value" diff --git a/tools/bootconfig/samples/good-tree.bconf b/tools/bootconfig/samples/good-tree.bconf new file mode 100644 index 000000000000..f2ddefc8b52a --- /dev/null +++ b/tools/bootconfig/samples/good-tree.bconf @@ -0,0 +1,12 @@ +key { + word { + tree { + value = "0"} + } + word2 { + tree { + value = 1,2 } + } +} +other.tree { + value = 2; value2 = 3;} diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh new file mode 100755 index 000000000000..1de06de328e2 --- /dev/null +++ b/tools/bootconfig/test-bootconfig.sh @@ -0,0 +1,114 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only + +echo "Boot config test script" + +BOOTCONF=./bootconfig +INITRD=`mktemp initrd-XXXX` +TEMPCONF=`mktemp temp-XXXX.bconf` +NG=0 + +cleanup() { + rm -f $INITRD $TEMPCONF + exit $NG +} + +trap cleanup EXIT TERM + +NO=1 + +xpass() { # pass test command + echo "test case $NO ($3)... " + if ! ($@ && echo "\t\t[OK]"); then + echo "\t\t[NG]"; NG=$((NG + 1)) + fi + NO=$((NO + 1)) +} + +xfail() { # fail test command + echo "test case $NO ($3)... " + if ! (! $@ && echo "\t\t[OK]"); then + echo "\t\t[NG]"; NG=$((NG + 1)) + fi + NO=$((NO + 1)) +} + +echo "Basic command test" +xpass $BOOTCONF $INITRD + +echo "Delete command should success without bootconfig" +xpass $BOOTCONF -d $INITRD + +dd if=/dev/zero of=$INITRD bs=4096 count=1 +echo "key = value;" > $TEMPCONF +bconf_size=$(stat -c %s $TEMPCONF) +initrd_size=$(stat -c %s $INITRD) + +echo "Apply command test" +xpass $BOOTCONF -a $TEMPCONF $INITRD +new_size=$(stat -c %s $INITRD) + +echo "File size check" +xpass test $new_size -eq $(expr $bconf_size + $initrd_size + 9) + +echo "Apply command repeat test" +xpass $BOOTCONF -a $TEMPCONF $INITRD + +echo "File size check" +xpass test $new_size -eq $(stat -c %s $INITRD) + +echo "Delete command check" +xpass $BOOTCONF -d $INITRD + +echo "File size check" +new_size=$(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 +xfail grep -i "failed" $OUTFILE +xfail grep -i "error" $OUTFILE +rm $OUTFILE + +echo "Max node number check" + +echo -n > $TEMPCONF +for i in `seq 1 1024` ; do + echo "node$i" >> $TEMPCONF +done +xpass $BOOTCONF -a $TEMPCONF $INITRD + +echo "badnode" >> $TEMPCONF +xfail $BOOTCONF -a $TEMPCONF $INITRD + +echo "Max filesize check" + +# Max size is 32767 (including terminal byte) +echo -n "data = \"" > $TEMPCONF +dd if=/dev/urandom bs=768 count=32 | base64 -w0 >> $TEMPCONF +echo "\"" >> $TEMPCONF +xfail $BOOTCONF -a $TEMPCONF $INITRD + +truncate -s 32764 $TEMPCONF +echo "\"" >> $TEMPCONF # add 2 bytes + terminal ('\"\n\0') +xpass $BOOTCONF -a $TEMPCONF $INITRD + +echo "=== expected failure cases ===" +for i in samples/bad-* ; do + xfail $BOOTCONF -a $i $INITRD +done + +echo "=== expected success cases ===" +for i in samples/good-* ; do + xpass $BOOTCONF -a $i $INITRD +done + +echo +if [ $NG -eq 0 ]; then + echo "All tests passed" +else + echo "$NG tests failed" +fi diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 5535650800ab..f897eeeb0b4f 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args FEATURE_DISPLAY = libbfd disassembler-four-args check_feat := 1 -NON_CHECK_FEAT_TARGETS := clean bpftool_clean +NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) check_feat := 0 @@ -73,7 +73,7 @@ $(OUTPUT)%.lex.o: $(OUTPUT)%.lex.c PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm -all: $(PROGS) bpftool +all: $(PROGS) bpftool runqslower $(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm' $(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o @@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c -clean: bpftool_clean +clean: bpftool_clean runqslower_clean $(call QUIET_CLEAN, bpf-progs) $(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \ $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.* @@ -97,7 +97,7 @@ clean: bpftool_clean $(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf $(Q)$(RM) -r -- $(OUTPUT)feature -install: $(PROGS) bpftool_install +install: $(PROGS) bpftool_install runqslower_install $(call QUIET_INSTALL, bpf_jit_disasm) $(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin $(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm @@ -115,4 +115,14 @@ bpftool_install: bpftool_clean: $(call descend,bpftool,clean) -.PHONY: all install clean bpftool bpftool_install bpftool_clean +runqslower: + $(call descend,runqslower) + +runqslower_install: + $(call descend,runqslower,install) + +runqslower_clean: + $(call descend,runqslower,clean) + +.PHONY: all install clean bpftool bpftool_install bpftool_clean \ + runqslower runqslower_install runqslower_clean diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst new file mode 100644 index 000000000000..94d91322895a --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -0,0 +1,305 @@ +================ +bpftool-gen +================ +------------------------------------------------------------------------------- +tool for BPF code-generation +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **gen** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMAND* := { **skeleton | **help** } + +GEN COMMANDS +============= + +| **bpftool** **gen skeleton** *FILE* +| **bpftool** **gen help** + +DESCRIPTION +=========== + **bpftool gen skeleton** *FILE* + Generate BPF skeleton C header file for a given *FILE*. + + BPF skeleton is an alternative interface to existing libbpf + APIs for working with BPF objects. Skeleton code is intended + to significantly shorten and simplify code to load and work + with BPF programs from userspace side. Generated code is + tailored to specific input BPF object *FILE*, reflecting its + structure by listing out available maps, program, variables, + etc. Skeleton eliminates the need to lookup mentioned + components by name. Instead, if skeleton instantiation + succeeds, they are populated in skeleton structure as valid + libbpf types (e.g., struct bpf_map pointer) and can be + passed to existing generic libbpf APIs. + + In addition to simple and reliable access to maps and + programs, skeleton provides a storage for BPF links (struct + bpf_link) for each BPF program within BPF object. When + requested, supported BPF programs will be automatically + attached and resulting BPF links stored for further use by + user in pre-allocated fields in skeleton struct. For BPF + programs that can't be automatically attached by libbpf, + user can attach them manually, but store resulting BPF link + in per-program link field. All such set up links will be + automatically destroyed on BPF skeleton destruction. This + eliminates the need for users to manage links manually and + rely on libbpf support to detach programs and free up + resources. + + Another facility provided by BPF skeleton is an interface to + global variables of all supported kinds: mutable, read-only, + as well as extern ones. This interface allows to pre-setup + initial values of variables before BPF object is loaded and + verified by kernel. For non-read-only variables, the same + interface can be used to fetch values of global variables on + userspace side, even if they are modified by BPF code. + + During skeleton generation, contents of source BPF object + *FILE* is embedded within generated code and is thus not + necessary to keep around. This ensures skeleton and BPF + object file are matching 1-to-1 and always stay in sync. + Generated code is dual-licensed under LGPL-2.1 and + BSD-2-Clause licenses. + + It is a design goal and guarantee that skeleton interfaces + are interoperable with generic libbpf APIs. User should + always be able to use skeleton API to create and load BPF + object, and later use libbpf APIs to keep working with + specific maps, programs, etc. + + As part of skeleton, few custom functions are generated. + Each of them is prefixed with object name, derived from + object file name. I.e., if BPF object file name is + **example.o**, BPF object name will be **example**. The + following custom functions are provided in such case: + + - **example__open** and **example__open_opts**. + These functions are used to instantiate skeleton. It + corresponds to libbpf's **bpf_object__open()** API. + **_opts** variants accepts extra **bpf_object_open_opts** + options. + + - **example__load**. + This function creates maps, loads and verifies BPF + programs, initializes global data maps. It corresponds to + libppf's **bpf_object__load** API. + + - **example__open_and_load** combines **example__open** and + **example__load** invocations in one commonly used + operation. + + - **example__attach** and **example__detach** + This pair of functions allow to attach and detach, + correspondingly, already loaded BPF object. Only BPF + programs of types supported by libbpf for auto-attachment + will be auto-attached and their corresponding BPF links + instantiated. For other BPF programs, user can manually + create a BPF link and assign it to corresponding fields in + skeleton struct. **example__detach** will detach both + links created automatically, as well as those populated by + user manually. + + - **example__destroy** + Detach and unload BPF programs, free up all the resources + used by skeleton and BPF object. + + If BPF object has global variables, corresponding structs + with memory layout corresponding to global data data section + layout will be created. Currently supported ones are: *.data*, + *.bss*, *.rodata*, and *.kconfig* structs/data sections. + These data sections/structs can be used to set up initial + values of variables, if set before **example__load**. + Afterwards, if target kernel supports memory-mapped BPF + arrays, same structs can be used to fetch and update + (non-read-only) data from userspace, with same simplicity + as for BPF side. + + **bpftool gen help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, + this option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + + -d, --debug + Print all logs available from libbpf, including debug-level + information. + +EXAMPLES +======== +**$ cat example.c** +:: + + #include <stdbool.h> + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include "bpf_helpers.h" + + const volatile int param1 = 42; + bool global_flag = true; + struct { int x; } data = {}; + + struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 128); + __type(key, int); + __type(value, long); + } my_map SEC(".maps"); + + SEC("raw_tp/sys_enter") + int handle_sys_enter(struct pt_regs *ctx) + { + static long my_static_var; + if (global_flag) + my_static_var++; + else + data.x += param1; + return 0; + } + + SEC("raw_tp/sys_exit") + int handle_sys_exit(struct pt_regs *ctx) + { + int zero = 0; + bpf_map_lookup_elem(&my_map, &zero); + return 0; + } + +This is example BPF application with two BPF programs and a mix of BPF maps +and global variables. + +**$ bpftool gen skeleton example.o** +:: + + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + + /* THIS FILE IS AUTOGENERATED! */ + #ifndef __EXAMPLE_SKEL_H__ + #define __EXAMPLE_SKEL_H__ + + #include <stdlib.h> + #include <bpf/libbpf.h> + + struct example { + struct bpf_object_skeleton *skeleton; + struct bpf_object *obj; + struct { + struct bpf_map *rodata; + struct bpf_map *data; + struct bpf_map *bss; + struct bpf_map *my_map; + } maps; + struct { + struct bpf_program *handle_sys_enter; + struct bpf_program *handle_sys_exit; + } progs; + struct { + struct bpf_link *handle_sys_enter; + struct bpf_link *handle_sys_exit; + } links; + struct example__bss { + struct { + int x; + } data; + } *bss; + struct example__data { + _Bool global_flag; + long int handle_sys_enter_my_static_var; + } *data; + struct example__rodata { + int param1; + } *rodata; + }; + + static void example__destroy(struct example *obj); + static inline struct example *example__open_opts( + const struct bpf_object_open_opts *opts); + static inline struct example *example__open(); + static inline int example__load(struct example *obj); + static inline struct example *example__open_and_load(); + static inline int example__attach(struct example *obj); + static inline void example__detach(struct example *obj); + + #endif /* __EXAMPLE_SKEL_H__ */ + +**$ cat example_user.c** +:: + + #include "example.skel.h" + + int main() + { + struct example *skel; + int err = 0; + + skel = example__open(); + if (!skel) + goto cleanup; + + skel->rodata->param1 = 128; + + err = example__load(skel); + if (err) + goto cleanup; + + err = example__attach(skel); + if (err) + goto cleanup; + + /* all libbpf APIs are usable */ + printf("my_map name: %s\n", bpf_map__name(skel->maps.my_map)); + printf("sys_enter prog FD: %d\n", + bpf_program__fd(skel->progs.handle_sys_enter)); + + /* detach and re-attach sys_exit program */ + bpf_link__destroy(skel->links.handle_sys_exit); + skel->links.handle_sys_exit = + bpf_program__attach(skel->progs.handle_sys_exit); + + printf("my_static_var: %ld\n", + skel->bss->handle_sys_enter_my_static_var); + + cleanup: + example__destroy(skel); + return err; + } + +**# ./example_user** +:: + + my_map name: my_map + sys_enter prog FD: 8 + my_static_var: 7 + +This is a stripped-out version of skeleton generated for above example code. + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-map**\ (8), + **bpftool-prog**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 1c0f7146aab0..cdeae8ae90ba 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -39,9 +39,9 @@ MAP COMMANDS | **bpftool** **map freeze** *MAP* | **bpftool** **map help** | -| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* | **name** *MAP_NAME* } | *DATA* := { [**hex**] *BYTES* } -| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } | *VALUE* := { *DATA* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } | *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** @@ -55,8 +55,9 @@ DESCRIPTION =========== **bpftool map { show | list }** [*MAP*] Show information about loaded maps. If *MAP* is specified - show information only about given map, otherwise list all - maps currently loaded on the system. + show information only about given maps, otherwise list all + maps currently loaded on the system. In case of **name**, + *MAP* may match several maps which will all be shown. Output will start with map ID followed by map type and zero or more named attributes (depending on kernel version). @@ -66,7 +67,8 @@ DESCRIPTION as *FILE*. **bpftool map dump** *MAP* - Dump all entries in a given *MAP*. + Dump all entries in a given *MAP*. In case of **name**, + *MAP* may match several maps which will all be dumped. **bpftool map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] Update map entry for a given *KEY*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 7a374b3c851d..64ddf8a4c518 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -33,7 +33,7 @@ PROG COMMANDS | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } -| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } | *TYPE* := { | **socket** | **kprobe** | **kretprobe** | **classifier** | **action** | | **tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** | @@ -53,8 +53,10 @@ DESCRIPTION =========== **bpftool prog { show | list }** [*PROG*] Show information about loaded programs. If *PROG* is - specified show information only about given program, otherwise - list all programs currently loaded on the system. + specified show information only about given programs, + otherwise list all programs currently loaded on the system. + In case of **tag** or **name**, *PROG* may match several + programs which will all be shown. Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). @@ -68,11 +70,15 @@ DESCRIPTION performed via the **kernel.bpf_stats_enabled** sysctl knob. **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] - Dump eBPF instructions of the program from the kernel. By + Dump eBPF instructions of the programs from the kernel. By default, eBPF will be disassembled and printed to standard output in human-readable format. In this case, **opcodes** controls if raw opcodes should be printed as well. + In case of **tag** or **name**, *PROG* may match several + programs which will all be dumped. However, if **file** or + **visual** is specified, *PROG* must match a single program. + If **file** is specified, the binary image will instead be written to *FILE*. @@ -80,15 +86,17 @@ DESCRIPTION built instead, and eBPF instructions will be presented with CFG in DOT format, on standard output. - If the prog has line_info available, the source line will + If the programs have line_info available, the source line will be displayed by default. If **linum** is specified, the filename, line number and line column will also be displayed on top of the source line. **bpftool prog dump jited** *PROG* [{ **file** *FILE* | **opcodes** | **linum** }] Dump jited image (host machine code) of the program. + If *FILE* is specified image will be written to a file, otherwise it will be disassembled and printed to stdout. + *PROG* must match a single program when **file** is specified. **opcodes** controls if raw opcodes will be printed. diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 6a9c52ef84a9..34239fda69ed 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -81,4 +81,5 @@ SEE ALSO **bpftool-feature**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-btf**\ (8), + **bpftool-gen**\ (8), diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 39bc6f0f4f0b..c4e810335810 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -45,7 +45,7 @@ CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ - -I$(srctree)/tools/lib/bpf \ + -I$(srctree)/tools/lib \ -I$(srctree)/tools/perf CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' ifneq ($(EXTRA_CFLAGS),) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 70493a6da206..754d8395e451 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -59,6 +59,21 @@ _bpftool_get_map_ids_for_type() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_map_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +# Takes map type and adds matching map names to the list of suggestions. +_bpftool_get_map_names_for_type() +{ + local type="$1" + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 "$type" | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_prog_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ @@ -71,6 +86,12 @@ _bpftool_get_prog_tags() command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_prog_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"name": "\(.*\)",$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_btf_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp btf 2>&1 | \ @@ -180,6 +201,52 @@ _bpftool_map_update_get_id() esac } +_bpftool_map_update_get_name() +{ + local command="$1" + + # Is it the map to update, or a map to insert into the map to update? + # Search for "value" keyword. + local idx value + for (( idx=7; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == "value" ]]; then + value=1 + break + fi + done + if [[ $value -eq 0 ]]; then + case "$command" in + push) + _bpftool_get_map_names_for_type stack + ;; + enqueue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + fi + + # Name to complete is for a value. It can be either prog name or map name. This + # depends on the type of the map to update. + local type=$(_bpftool_map_guess_map_type) + case $type in + array_of_maps|hash_of_maps) + _bpftool_get_map_names + return 0 + ;; + prog_array) + _bpftool_get_prog_names + return 0 + ;; + *) + return 0 + ;; + esac +} + _bpftool() { local cur prev words objword @@ -251,7 +318,8 @@ _bpftool() # Completion depends on object and command in use case $object in prog) - # Complete id, only for subcommands that use prog (but no map) ids + # Complete id and name, only for subcommands that use prog (but no + # map) ids/names. case $command in show|list|dump|pin) case $prev in @@ -259,12 +327,16 @@ _bpftool() _bpftool_get_prog_ids return 0 ;; + name) + _bpftool_get_prog_names + return 0 + ;; esac ;; esac - local PROG_TYPE='id pinned tag' - local MAP_TYPE='id pinned' + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' case $command in show|list) [[ $prev != "$command" ]] && return 0 @@ -315,6 +387,9 @@ _bpftool() id) _bpftool_get_prog_ids ;; + name) + _bpftool_get_map_names + ;; pinned) _filedir ;; @@ -335,6 +410,9 @@ _bpftool() id) _bpftool_get_map_ids ;; + name) + _bpftool_get_map_names + ;; pinned) _filedir ;; @@ -399,6 +477,10 @@ _bpftool() _bpftool_get_map_ids return 0 ;; + name) + _bpftool_get_map_names + return 0 + ;; pinned|pinmaps) _filedir return 0 @@ -447,7 +529,7 @@ _bpftool() esac ;; map) - local MAP_TYPE='id pinned' + local MAP_TYPE='id pinned name' case $command in show|list|dump|peek|pop|dequeue|freeze) case $prev in @@ -473,6 +555,24 @@ _bpftool() esac return 0 ;; + name) + case "$command" in + peek) + _bpftool_get_map_names_for_type stack + _bpftool_get_map_names_for_type queue + ;; + pop) + _bpftool_get_map_names_for_type stack + ;; + dequeue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + ;; *) return 0 ;; @@ -520,6 +620,10 @@ _bpftool() _bpftool_get_map_ids return 0 ;; + name) + _bpftool_get_map_names + return 0 + ;; key) COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; @@ -545,6 +649,10 @@ _bpftool() _bpftool_map_update_get_id $command return 0 ;; + name) + _bpftool_map_update_get_name $command + return 0 + ;; key) COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; @@ -553,13 +661,13 @@ _bpftool() # map, depending on the type of the map to update. case "$(_bpftool_map_guess_map_type)" in array_of_maps|hash_of_maps) - local MAP_TYPE='id pinned' + local MAP_TYPE='id pinned name' COMPREPLY+=( $( compgen -W "$MAP_TYPE" \ -- "$cur" ) ) return 0 ;; prog_array) - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' COMPREPLY+=( $( compgen -W "$PROG_TYPE" \ -- "$cur" ) ) return 0 @@ -621,6 +729,10 @@ _bpftool() _bpftool_get_map_ids_for_type perf_event_array return 0 ;; + name) + _bpftool_get_map_names_for_type perf_event_array + return 0 + ;; cpu) return 0 ;; @@ -644,8 +756,8 @@ _bpftool() esac ;; btf) - local PROG_TYPE='id pinned tag' - local MAP_TYPE='id pinned' + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' case $command in dump) case $prev in @@ -676,6 +788,17 @@ _bpftool() esac return 0 ;; + name) + case $pprev in + prog) + _bpftool_get_prog_names + ;; + map) + _bpftool_get_map_names + ;; + esac + return 0 + ;; format) COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) ) ;; @@ -716,6 +839,17 @@ _bpftool() ;; esac ;; + gen) + case $command in + skeleton) + _filedir + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) ) + ;; + esac + ;; cgroup) case $command in show|list|tree) @@ -735,7 +869,7 @@ _bpftool() connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl \ getsockopt setsockopt' local ATTACH_FLAGS='multi override' - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' case $prev in $command) _filedir @@ -760,7 +894,7 @@ _bpftool() elif [[ "$command" == "attach" ]]; then # We have an attach type on the command line, # but it is not the previous word, or - # "id|pinned|tag" (we already checked for + # "id|pinned|tag|name" (we already checked for # that). This should only leave the case when # we need attach flags for "attach" commamnd. _bpftool_one_of_list "$ATTACH_FLAGS" @@ -786,7 +920,7 @@ _bpftool() esac ;; net) - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' local ATTACH_TYPES='xdp xdpgeneric xdpdrv xdpoffload' case $command in show|list) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index e5bc97b71ceb..b3745ed711ba 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -8,15 +8,15 @@ #include <stdio.h> #include <string.h> #include <unistd.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> #include <linux/btf.h> #include <linux/hashtable.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> -#include "btf.h" #include "json_writer.h" #include "main.h" @@ -77,6 +77,20 @@ static const char *btf_var_linkage_str(__u32 linkage) } } +static const char *btf_func_linkage_str(const struct btf_type *t) +{ + switch (btf_vlen(t)) { + case BTF_FUNC_STATIC: + return "static"; + case BTF_FUNC_GLOBAL: + return "global"; + case BTF_FUNC_EXTERN: + return "extern"; + default: + return "(unknown)"; + } +} + static const char *btf_str(const struct btf *btf, __u32 off) { if (!off) @@ -231,12 +245,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" fwd_kind=%s", fwd_kind); break; } - case BTF_KIND_FUNC: - if (json_output) + case BTF_KIND_FUNC: { + const char *linkage = btf_func_linkage_str(t); + + if (json_output) { jsonw_uint_field(w, "type_id", t->type); - else - printf(" type_id=%u", t->type); + jsonw_string_field(w, "linkage", linkage); + } else { + printf(" type_id=%u linkage=%s", t->type, linkage); + } break; + } case BTF_KIND_FUNC_PROTO: { const struct btf_param *p = (const void *)(t + 1); __u16 vlen = BTF_INFO_VLEN(t->info); @@ -370,6 +389,10 @@ static int dump_btf_c(const struct btf *btf, if (IS_ERR(d)) return PTR_ERR(d); + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record)\n"); + printf("#endif\n\n"); + if (root_type_cnt) { for (i = 0; i < root_type_cnt; i++) { err = btf_dump__dump_type(d, root_type_ids[i]); @@ -386,6 +409,10 @@ static int dump_btf_c(const struct btf *btf, } } + printf("#ifndef BPF_NO_PRESERVE_ACCESS_INDEX\n"); + printf("#pragma clang attribute pop\n"); + printf("#endif\n"); + done: btf_dump__free(d); return err; @@ -524,7 +551,7 @@ static int do_dump(int argc, char **argv) if (IS_ERR(btf)) { err = PTR_ERR(btf); btf = NULL; - p_err("failed to load BTF from %s: %s", + p_err("failed to load BTF from %s: %s", *argv, strerror(err)); goto done; } diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 397e5716ab6d..01cc52b834fa 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -8,8 +8,8 @@ #include <linux/bitops.h> #include <linux/btf.h> #include <linux/err.h> +#include <bpf/btf.h> -#include "btf.h" #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 1ef45e55039e..62c6a1d7cd18 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -14,7 +14,7 @@ #include <sys/types.h> #include <unistd.h> -#include <bpf.h> +#include <bpf/bpf.h> #include "main.h" @@ -117,6 +117,25 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) return prog_cnt; } +static int cgroup_has_attached_progs(int cgroup_fd) +{ + enum bpf_attach_type type; + bool no_prog = true; + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + int count = count_attached_bpf_progs(cgroup_fd, type); + + if (count < 0 && errno != EINVAL) + return -1; + + if (count > 0) { + no_prog = false; + break; + } + } + + return no_prog ? 0 : 1; +} static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { @@ -161,6 +180,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, static int do_show(int argc, char **argv) { enum bpf_attach_type type; + int has_attached_progs; const char *path; int cgroup_fd; int ret = -1; @@ -192,6 +212,16 @@ static int do_show(int argc, char **argv) goto exit; } + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + path, strerror(errno)); + goto exit_cgroup; + } else if (!has_attached_progs) { + ret = 0; + goto exit_cgroup; + } + if (json_output) jsonw_start_array(json_wtr); else @@ -212,6 +242,7 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); +exit_cgroup: close(cgroup_fd); exit: return ret; @@ -228,7 +259,7 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftw) { enum bpf_attach_type type; - bool skip = true; + int has_attached_progs; int cgroup_fd; if (typeflag != FTW_D) @@ -240,22 +271,13 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, return SHOW_TREE_FN_ERR; } - for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - int count = count_attached_bpf_progs(cgroup_fd, type); - - if (count < 0 && errno != EINVAL) { - p_err("can't query bpf programs attached to %s: %s", - fpath, strerror(errno)); - close(cgroup_fd); - return SHOW_TREE_FN_ERR; - } - if (count > 0) { - skip = false; - break; - } - } - - if (skip) { + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + fpath, strerror(errno)); + close(cgroup_fd); + return SHOW_TREE_FN_ERR; + } else if (!has_attached_progs) { close(cgroup_fd); return 0; } diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 88264abaa738..b75b8ec5469c 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -20,8 +20,8 @@ #include <sys/stat.h> #include <sys/vfs.h> -#include <bpf.h> -#include <libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/bpf.h> +#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ #include "main.h" diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 03bdc5b3ac49..941873d778d8 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -12,8 +12,8 @@ #include <linux/filter.h> #include <linux/limits.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include <zlib.h> #include "main.h" @@ -572,6 +572,18 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, printf("\n"); } +static void +probe_large_insn_limit(const char *define_prefix, __u32 ifindex) +{ + bool res; + + res = bpf_probe_large_insn_limit(ifindex); + print_bool_feature("have_large_insn_limit", + "Large program size limit", + "LARGE_INSN_LIMIT", + res, define_prefix); +} + static int do_probe(int argc, char **argv) { enum probe_component target = COMPONENT_UNSPEC; @@ -724,6 +736,12 @@ static int do_probe(int argc, char **argv) probe_helpers_for_progtype(i, supported_types[i], define_prefix, ifindex); + print_end_then_start_section("misc", + "Scanning miscellaneous eBPF features...", + "/*** eBPF misc features ***/", + define_prefix); + probe_large_insn_limit(define_prefix, ifindex); + exit_close_json: if (json_output) { /* End current "section" of probes */ diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c new file mode 100644 index 000000000000..f8113b3646f5 --- /dev/null +++ b/tools/bpf/bpftool/gen.c @@ -0,0 +1,609 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <unistd.h> +#include <bpf/btf.h> + +#include "bpf/libbpf_internal.h" +#include "json_writer.h" +#include "main.h" + + +#define MAX_OBJ_NAME_LEN 64 + +static void sanitize_identifier(char *name) +{ + int i; + + for (i = 0; name[i]; i++) + if (!isalnum(name[i]) && name[i] != '_') + name[i] = '_'; +} + +static bool str_has_suffix(const char *str, const char *suffix) +{ + size_t i, n1 = strlen(str), n2 = strlen(suffix); + + if (n1 < n2) + return false; + + for (i = 0; i < n2; i++) { + if (str[n1 - i - 1] != suffix[n2 - i - 1]) + return false; + } + + return true; +} + +static void get_obj_name(char *name, const char *file) +{ + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(name, basename(file), MAX_OBJ_NAME_LEN - 1); + name[MAX_OBJ_NAME_LEN - 1] = '\0'; + if (str_has_suffix(name, ".o")) + name[strlen(name) - 2] = '\0'; + sanitize_identifier(name); +} + +static void get_header_guard(char *guard, const char *obj_name) +{ + int i; + + sprintf(guard, "__%s_SKEL_H__", obj_name); + for (i = 0; guard[i]; i++) + guard[i] = toupper(guard[i]); +} + +static const char *get_map_ident(const struct bpf_map *map) +{ + const char *name = bpf_map__name(map); + + if (!bpf_map__is_internal(map)) + return name; + + if (str_has_suffix(name, ".data")) + return "data"; + else if (str_has_suffix(name, ".rodata")) + return "rodata"; + else if (str_has_suffix(name, ".bss")) + return "bss"; + else if (str_has_suffix(name, ".kconfig")) + return "kconfig"; + else + return NULL; +} + +static void codegen_btf_dump_printf(void *ct, const char *fmt, va_list args) +{ + vprintf(fmt, args); +} + +static int codegen_datasec_def(struct bpf_object *obj, + struct btf *btf, + struct btf_dump *d, + const struct btf_type *sec, + const char *obj_name) +{ + const char *sec_name = btf__name_by_offset(btf, sec->name_off); + const struct btf_var_secinfo *sec_var = btf_var_secinfos(sec); + int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec); + const char *sec_ident; + char var_ident[256]; + + if (strcmp(sec_name, ".data") == 0) + sec_ident = "data"; + else if (strcmp(sec_name, ".bss") == 0) + sec_ident = "bss"; + else if (strcmp(sec_name, ".rodata") == 0) + sec_ident = "rodata"; + else if (strcmp(sec_name, ".kconfig") == 0) + sec_ident = "kconfig"; + else + return 0; + + printf(" struct %s__%s {\n", obj_name, sec_ident); + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .field_name = var_ident, + .indent_level = 2, + ); + int need_off = sec_var->offset, align_off, align; + __u32 var_type_id = var->type; + const struct btf_type *t; + + t = btf__type_by_id(btf, var_type_id); + while (btf_is_mod(t)) { + var_type_id = t->type; + t = btf__type_by_id(btf, var_type_id); + } + + if (off > need_off) { + p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", + sec_name, i, need_off, off); + return -EINVAL; + } + + align = btf__align_of(btf, var->type); + if (align <= 0) { + p_err("Failed to determine alignment of variable '%s': %d", + var_name, align); + return -EINVAL; + } + + align_off = (off + align - 1) / align * align; + if (align_off != need_off) { + printf("\t\tchar __pad%d[%d];\n", + pad_cnt, need_off - off); + pad_cnt++; + } + + /* sanitize variable name, e.g., for static vars inside + * a function, it's name is '<function name>.<variable name>', + * which we'll turn into a '<function name>_<variable name>' + */ + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t\t"); + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + return err; + printf(";\n"); + + off = sec_var->offset + sec_var->size; + } + printf(" } *%s;\n", sec_ident); + return 0; +} + +static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + int n = btf__get_nr_types(btf); + struct btf_dump *d; + int i, err = 0; + + d = btf_dump__new(btf, NULL, NULL, codegen_btf_dump_printf); + if (IS_ERR(d)) + return PTR_ERR(d); + + for (i = 1; i <= n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + + if (!btf_is_datasec(t)) + continue; + + err = codegen_datasec_def(obj, btf, d, t, obj_name); + if (err) + goto out; + } +out: + btf_dump__free(d); + return err; +} + +static int codegen(const char *template, ...) +{ + const char *src, *end; + int skip_tabs = 0, n; + char *s, *dst; + va_list args; + char c; + + n = strlen(template); + s = malloc(n + 1); + if (!s) + return -ENOMEM; + src = template; + dst = s; + + /* find out "baseline" indentation to skip */ + while ((c = *src++)) { + if (c == '\t') { + skip_tabs++; + } else if (c == '\n') { + break; + } else { + p_err("unrecognized character at pos %td in template '%s'", + src - template - 1, template); + return -EINVAL; + } + } + + while (*src) { + /* skip baseline indentation tabs */ + for (n = skip_tabs; n > 0; n--, src++) { + if (*src != '\t') { + p_err("not enough tabs at pos %td in template '%s'", + src - template - 1, template); + return -EINVAL; + } + } + /* trim trailing whitespace */ + end = strchrnul(src, '\n'); + for (n = end - src; n > 0 && isspace(src[n - 1]); n--) + ; + memcpy(dst, src, n); + dst += n; + if (*end) + *dst++ = '\n'; + src = *end ? end + 1 : end; + } + *dst++ = '\0'; + + /* print out using adjusted template */ + va_start(args, template); + n = vprintf(s, args); + va_end(args); + + free(s); + return n; +} + +static int do_skeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; + size_t i, map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN], *obj_data; + struct bpf_object *obj = NULL; + const char *file, *ident; + struct bpf_program *prog; + int fd, len, err = -1; + struct bpf_map *map; + struct btf *btf; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + get_obj_name(obj_name, file); + opts.object_name = obj_name; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (IS_ERR(obj)) { + obj = NULL; + p_err("failed to open BPF object file: %ld", PTR_ERR(obj)); + goto out; + } + + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + if (!ident) { + p_err("ignoring unrecognized internal map '%s'...", + bpf_map__name(map)); + continue; + } + map_cnt++; + } + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + get_header_guard(header_guard, obj_name); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object_skeleton *skeleton; \n\ + struct bpf_object *obj; \n\ + ", + obj_name, header_guard + ); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + if (!ident) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_link *%s;\n", + bpf_program__name(prog)); + } + printf("\t} links;\n"); + } + + btf = bpf_object__btf(obj); + if (btf) { + err = codegen_datasecs(obj, obj_name); + if (err) + goto out; + } + + codegen("\ + \n\ + }; \n\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *obj) \n\ + { \n\ + if (!obj) \n\ + return; \n\ + if (obj->skeleton) \n\ + bpf_object__destroy_skeleton(obj->skeleton);\n\ + free(obj); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj); \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_opts(const struct bpf_object_open_opts *opts) \n\ + { \n\ + struct %1$s *obj; \n\ + \n\ + obj = (typeof(obj))calloc(1, sizeof(*obj)); \n\ + if (!obj) \n\ + return NULL; \n\ + if (%1$s__create_skeleton(obj)) \n\ + goto err; \n\ + if (bpf_object__open_skeleton(obj->skeleton, opts)) \n\ + goto err; \n\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + return %1$s__open_opts(NULL); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *obj) \n\ + { \n\ + return bpf_object__load_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *obj; \n\ + \n\ + obj = %1$s__open(); \n\ + if (!obj) \n\ + return NULL; \n\ + if (%1$s__load(obj)) { \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + return obj; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *obj) \n\ + { \n\ + return bpf_object__attach_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *obj) \n\ + { \n\ + return bpf_object__detach_skeleton(obj->skeleton); \n\ + } \n\ + ", + obj_name + ); + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj) \n\ + { \n\ + struct bpf_object_skeleton *s; \n\ + \n\ + s = (typeof(s))calloc(1, sizeof(*s)); \n\ + if (!s) \n\ + return -1; \n\ + obj->skeleton = s; \n\ + \n\ + s->sz = sizeof(*s); \n\ + s->name = \"%1$s\"; \n\ + s->obj = &obj->obj; \n\ + ", + obj_name + ); + if (map_cnt) { + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) \n\ + goto err; \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + + if (!ident) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (bpf_map__is_internal(map) && + (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } + } + if (prog_cnt) { + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) \n\ + goto err; \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + i++; + } + } + codegen("\ + \n\ + \n\ + s->data_sz = %d; \n\ + s->data = (void *)\"\\ \n\ + ", + file_sz); + + /* embed contents of BPF object file */ + for (i = 0, len = 0; i < file_sz; i++) { + int w = obj_data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!obj_data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)obj_data[i]); + } + + codegen("\ + \n\ + \"; \n\ + \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return -1; \n\ + } \n\ + \n\ + #endif /* %s */ \n\ + ", + header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s gen skeleton FILE\n" + " %1$s gen help\n" + "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name); + + return 0; +} + +static const struct cmd cmds[] = { + { "skeleton", do_skeleton }, + { "help", do_help }, + { 0 } +}; + +int do_gen(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index bfed711258ce..f7f5885aa3ba 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -24,7 +24,7 @@ #include <dis-asm.h> #include <sys/stat.h> #include <limits.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include "json_writer.h" #include "main.h" diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 4764581ff9ea..6d41bbfc6459 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -9,8 +9,8 @@ #include <stdlib.h> #include <string.h> -#include <bpf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include "main.h" @@ -58,7 +58,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -227,6 +227,7 @@ static const struct cmd cmds[] = { { "net", do_net }, { "feature", do_feature }, { "btf", do_btf }, + { "gen", do_gen }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 2899095f8254..4e75b58d3989 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -42,12 +42,12 @@ #define BPF_TAG_FMT "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx" #define HELP_SPEC_PROGRAM \ - "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }" + "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" #define HELP_SPEC_OPTIONS \ "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} |\n" \ "\t {-m|--mapcompat} | {-n|--nomount} }" #define HELP_SPEC_MAP \ - "MAP := { id MAP_ID | pinned FILE }" + "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -155,6 +155,7 @@ int do_net(int argc, char **arg); int do_tracelog(int argc, char **arg); int do_feature(int argc, char **argv); int do_btf(int argc, char **argv); +int do_gen(int argc, char **argv); int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index de61d73b9030..e6c85680b34d 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -15,9 +15,9 @@ #include <sys/types.h> #include <sys/stat.h> -#include <bpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> -#include "btf.h" #include "json_writer.h" #include "main.h" @@ -48,6 +48,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_QUEUE] = "queue", [BPF_MAP_TYPE_STACK] = "stack", [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", + [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -91,10 +92,66 @@ static void *alloc_value(struct bpf_map_info *info) return malloc(info->value_size); } -int map_parse_fd(int *argc, char ***argv) +static int map_fd_by_name(char *name, int **fds) { - int fd; + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get map info (%u): %s", + id, strerror(errno)); + goto err_close_fd; + } + + if (strncmp(name, info.name, BPF_OBJ_NAME_LEN)) { + close(fd); + continue; + } + + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; + } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; +} + +static int map_parse_fds(int *argc, char ***argv, int **fds) +{ if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -108,10 +165,25 @@ int map_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - fd = bpf_map_get_fd_by_id(id); - if (fd < 0) + (*fds)[0] = bpf_map_get_fd_by_id(id); + if ((*fds)[0] < 0) { p_err("get map by id (%u): %s", id, strerror(errno)); - return fd; + return -1; + } + return 1; + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return map_fd_by_name(name, fds); } else if (is_prefix(**argv, "pinned")) { char *path; @@ -120,13 +192,43 @@ int map_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_MAP); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); + if ((*fds)[0] < 0) + return -1; + return 1; } - p_err("expected 'id' or 'pinned', got: '%s'?", **argv); + p_err("expected 'id', 'name' or 'pinned', got: '%s'?", **argv); return -1; } +int map_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several maps match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) { int err; @@ -150,6 +252,7 @@ static int do_dump_btf(const struct btf_dumper *d, struct bpf_map_info *map_info, void *key, void *value) { + __u32 value_id; int ret; /* start of key-value pair */ @@ -163,9 +266,12 @@ static int do_dump_btf(const struct btf_dumper *d, goto err_end_obj; } + value_id = map_info->btf_vmlinux_value_type_id ? + : map_info->btf_value_type_id; + if (!map_is_per_cpu(map_info->type)) { jsonw_name(d->jw, "value"); - ret = btf_dumper_type(d, map_info->btf_value_type_id, value); + ret = btf_dumper_type(d, value_id, value); } else { unsigned int i, n, step; @@ -177,8 +283,7 @@ static int do_dump_btf(const struct btf_dumper *d, jsonw_start_object(d->jw); jsonw_int_field(d->jw, "cpu", i); jsonw_name(d->jw, "value"); - ret = btf_dumper_type(d, map_info->btf_value_type_id, - value + i * step); + ret = btf_dumper_type(d, value_id, value + i * step); jsonw_end_object(d->jw); if (ret) break; @@ -479,6 +584,21 @@ static int parse_elem(char **argv, struct bpf_map_info *info, return -1; } +static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(wtr, "id", info->id); + if (info->type < ARRAY_SIZE(map_type_name)) + jsonw_string_field(wtr, "type", map_type_name[info->type]); + else + jsonw_uint_field(wtr, "type", info->type); + + if (*info->name) + jsonw_string_field(wtr, "name", info->name); + + jsonw_name(wtr, "flags"); + jsonw_printf(wtr, "%d", info->map_flags); +} + static int show_map_close_json(int fd, struct bpf_map_info *info) { char *memlock, *frozen_str; @@ -489,18 +609,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_start_object(json_wtr); - jsonw_uint_field(json_wtr, "id", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - jsonw_string_field(json_wtr, "type", - map_type_name[info->type]); - else - jsonw_uint_field(json_wtr, "type", info->type); - - if (*info->name) - jsonw_string_field(json_wtr, "name", info->name); - - jsonw_name(json_wtr, "flags"); - jsonw_printf(json_wtr, "%d", info->map_flags); + show_map_header_json(info, json_wtr); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); @@ -561,14 +670,8 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) return 0; } -static int show_map_close_plain(int fd, struct bpf_map_info *info) +static void show_map_header_plain(struct bpf_map_info *info) { - char *memlock, *frozen_str; - int frozen = 0; - - memlock = get_fdinfo(fd, "memlock"); - frozen_str = get_fdinfo(fd, "frozen"); - printf("%u: ", info->id); if (info->type < ARRAY_SIZE(map_type_name)) printf("%s ", map_type_name[info->type]); @@ -581,6 +684,17 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) printf("flags 0x%x", info->map_flags); print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); printf("\n"); +} + +static int show_map_close_plain(int fd, struct bpf_map_info *info) +{ + char *memlock, *frozen_str; + int frozen = 0; + + memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); + + show_map_header_plain(info); printf("\tkey %uB value %uB max_entries %u", info->key_size, info->value_size, info->max_entries); @@ -642,6 +756,50 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) return 0; } +static int do_show_subset(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int *fds = NULL; + int nb_fds, i; + int err = -1; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", + strerror(errno)); + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + + if (json_output) + show_map_close_json(fds[i], &info); + else + show_map_close_plain(fds[i], &info); + + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + static int do_show(int argc, char **argv) { struct bpf_map_info info = {}; @@ -653,16 +811,8 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&map_table, BPF_OBJ_MAP); - if (argc == 2) { - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); - if (fd < 0) - return -1; - - if (json_output) - return show_map_close_json(fd, &info); - else - return show_map_close_plain(fd, &info); - } + if (argc == 2) + return do_show_subset(argc, argv); if (argc) return BAD_ARG(); @@ -765,26 +915,75 @@ static int dump_map_elem(int fd, void *key, void *value, return 0; } -static int do_dump(int argc, char **argv) +static int maps_have_btf(int *fds, int nb_fds) { struct bpf_map_info info = {}; - void *key, *value, *prev_key; - unsigned int num_elems = 0; __u32 len = sizeof(info); - json_writer_t *btf_wtr; + int err, i; + + for (i = 0; i < nb_fds; i++) { + err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + return -1; + } + + if (!info.btf_id) + return 0; + } + + return 1; +} + +static struct btf *btf_vmlinux; + +static struct btf *get_map_kv_btf(const struct bpf_map_info *info) +{ struct btf *btf = NULL; - int err; - int fd; - if (argc != 2) - usage(); + if (info->btf_vmlinux_value_type_id) { + if (!btf_vmlinux) { + btf_vmlinux = libbpf_find_kernel_btf(); + if (IS_ERR(btf_vmlinux)) + p_err("failed to get kernel btf"); + } + return btf_vmlinux; + } else if (info->btf_value_type_id) { + int err; + + err = btf__get_from_id(info->btf_id, &btf); + if (err || !btf) { + p_err("failed to get btf"); + btf = err ? ERR_PTR(err) : ERR_PTR(-ESRCH); + } + } - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); - if (fd < 0) - return -1; + return btf; +} - key = malloc(info.key_size); - value = alloc_value(&info); +static void free_map_kv_btf(struct btf *btf) +{ + if (!IS_ERR(btf) && btf != btf_vmlinux) + btf__free(btf); +} + +static void free_btf_vmlinux(void) +{ + if (!IS_ERR(btf_vmlinux)) + btf__free(btf_vmlinux); +} + +static int +map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, + bool show_header) +{ + void *key, *value, *prev_key; + unsigned int num_elems = 0; + struct btf *btf = NULL; + int err; + + key = malloc(info->key_size); + value = alloc_value(info); if (!key || !value) { p_err("mem alloc failed"); err = -1; @@ -793,30 +992,27 @@ static int do_dump(int argc, char **argv) prev_key = NULL; - err = btf__get_from_id(info.btf_id, &btf); - if (err) { - p_err("failed to get btf"); - goto exit_free; - } + if (wtr) { + btf = get_map_kv_btf(info); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + goto exit_free; + } - if (json_output) - jsonw_start_array(json_wtr); - else - if (btf) { - btf_wtr = get_btf_writer(); - if (!btf_wtr) { - p_info("failed to create json writer for btf. falling back to plain output"); - btf__free(btf); - btf = NULL; - } else { - jsonw_start_array(btf_wtr); - } + if (show_header) { + jsonw_start_object(wtr); /* map object */ + show_map_header_json(info, wtr); + jsonw_name(wtr, "elements"); } + jsonw_start_array(wtr); /* elements */ + } else if (show_header) { + show_map_header_plain(info); + } - if (info.type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && - info.value_size != 8) + if (info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + info->value_size != 8) p_info("Warning: cannot read values from %s map with value_size != 8", - map_type_name[info.type]); + map_type_name[info->type]); while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -824,15 +1020,14 @@ static int do_dump(int argc, char **argv) err = 0; break; } - num_elems += dump_map_elem(fd, key, value, &info, btf, btf_wtr); + num_elems += dump_map_elem(fd, key, value, info, btf, wtr); prev_key = key; } - if (json_output) - jsonw_end_array(json_wtr); - else if (btf) { - jsonw_end_array(btf_wtr); - jsonw_destroy(&btf_wtr); + if (wtr) { + jsonw_end_array(wtr); /* elements */ + if (show_header) + jsonw_end_object(wtr); /* map object */ } else { printf("Found %u element%s\n", num_elems, num_elems != 1 ? "s" : ""); @@ -842,11 +1037,78 @@ exit_free: free(key); free(value); close(fd); - btf__free(btf); + free_map_kv_btf(btf); return err; } +static int do_dump(int argc, char **argv) +{ + json_writer_t *wtr = NULL, *btf_wtr = NULL; + struct bpf_map_info info = {}; + int nb_fds, i = 0; + __u32 len = sizeof(info); + int *fds = NULL; + int err = -1; + + if (argc != 2) + usage(); + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output) { + wtr = json_wtr; + } else { + int do_plain_btf; + + do_plain_btf = maps_have_btf(fds, nb_fds); + if (do_plain_btf < 0) + goto exit_close; + + if (do_plain_btf) { + btf_wtr = get_btf_writer(); + wtr = btf_wtr; + if (!btf_wtr) + p_info("failed to create json writer for btf. falling back to plain output"); + } + } + + if (wtr && nb_fds > 1) + jsonw_start_array(wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + if (bpf_obj_get_info_by_fd(fds[i], &info, &len)) { + p_err("can't get map info: %s", strerror(errno)); + break; + } + err = map_dump(fds[i], &info, wtr, nb_fds > 1); + if (!wtr && i != nb_fds - 1) + printf("\n"); + + if (err) + break; + close(fds[i]); + } + if (wtr && nb_fds > 1) + jsonw_end_array(wtr); /* root array */ + + if (btf_wtr) + jsonw_destroy(&btf_wtr); +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(fds); + free_btf_vmlinux(); + return err; +} + static int alloc_key_value(struct bpf_map_info *info, void **key, void **value) { *key = NULL; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 4c5531d1a450..d9b29c17fbb8 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -6,7 +6,7 @@ */ #include <errno.h> #include <fcntl.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include <poll.h> #include <signal.h> #include <stdbool.h> @@ -21,7 +21,7 @@ #include <sys/mman.h> #include <sys/syscall.h> -#include <bpf.h> +#include <bpf/bpf.h> #include <perf-sys.h> #include "main.h" diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 4f52d3151616..c5e3895b7c8b 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -7,7 +7,8 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> #include <net/if.h> #include <linux/if.h> #include <linux/rtnetlink.h> @@ -16,8 +17,8 @@ #include <sys/stat.h> #include <sys/types.h> -#include <bpf.h> -#include <nlattr.h> +#include "bpf/nlattr.h" +#include "bpf/libbpf_internal.h" #include "main.h" #include "netlink_dumper.h" diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c index 550a0f537eed..5f65140b003b 100644 --- a/tools/bpf/bpftool/netlink_dumper.c +++ b/tools/bpf/bpftool/netlink_dumper.c @@ -3,11 +3,11 @@ #include <stdlib.h> #include <string.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include <linux/rtnetlink.h> #include <linux/tc_act/tc_bpf.h> -#include <nlattr.h> +#include "bpf/nlattr.h" #include "main.h" #include "netlink_dumper.h" diff --git a/tools/bpf/bpftool/perf.c b/tools/bpf/bpftool/perf.c index b2046f33e23f..3341aa14acda 100644 --- a/tools/bpf/bpftool/perf.c +++ b/tools/bpf/bpftool/perf.c @@ -13,7 +13,7 @@ #include <unistd.h> #include <ftw.h> -#include <bpf.h> +#include <bpf/bpf.h> #include "main.h" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2ce9c5ba1934..b352ab041160 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -17,14 +17,19 @@ #include <linux/err.h> #include <linux/sizes.h> -#include <bpf.h> -#include <btf.h> -#include <libbpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> #include "cfg.h" #include "main.h" #include "xlated_dumper.h" +enum dump_mode { + DUMP_JITED, + DUMP_XLATED, +}; + static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", @@ -77,11 +82,12 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) strftime(buf, size, "%FT%T%z", &load_tm); } -static int prog_fd_by_tag(unsigned char *tag) +static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) { unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; int err; - int fd; while (true) { struct bpf_prog_info info = {}; @@ -89,36 +95,54 @@ static int prog_fd_by_tag(unsigned char *tag) err = bpf_prog_get_next_id(id, &id); if (err) { - p_err("%s", strerror(errno)); - return -1; + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; } fd = bpf_prog_get_fd_by_id(id); if (fd < 0) { p_err("can't get prog by id (%u): %s", id, strerror(errno)); - return -1; + goto err_close_fds; } err = bpf_obj_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info (%u): %s", id, strerror(errno)); - close(fd); - return -1; + goto err_close_fd; } - if (!memcmp(tag, info.tag, BPF_TAG_SIZE)) - return fd; + if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || + (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { + close(fd); + continue; + } - close(fd); + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; } -int prog_parse_fd(int *argc, char ***argv) +static int prog_parse_fds(int *argc, char ***argv, int **fds) { - int fd; - if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -132,10 +156,12 @@ int prog_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - fd = bpf_prog_get_fd_by_id(id); - if (fd < 0) + (*fds)[0] = bpf_prog_get_fd_by_id(id); + if ((*fds)[0] < 0) { p_err("get by id (%u): %s", id, strerror(errno)); - return fd; + return -1; + } + return 1; } else if (is_prefix(**argv, "tag")) { unsigned char tag[BPF_TAG_SIZE]; @@ -149,7 +175,20 @@ int prog_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - return prog_fd_by_tag(tag); + return prog_fd_by_nametag(tag, fds, true); + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_nametag(name, fds, false); } else if (is_prefix(**argv, "pinned")) { char *path; @@ -158,13 +197,43 @@ int prog_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_PROG); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); + if ((*fds)[0] < 0) + return -1; + return 1; } - p_err("expected 'id', 'tag' or 'pinned', got: '%s'?", **argv); + p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv); return -1; } +int prog_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several programs match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + static void show_prog_maps(int fd, u32 num_maps) { struct bpf_prog_info info = {}; @@ -194,11 +263,8 @@ static void show_prog_maps(int fd, u32 num_maps) } } -static void print_prog_json(struct bpf_prog_info *info, int fd) +static void print_prog_header_json(struct bpf_prog_info *info) { - char *memlock; - - jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) jsonw_string_field(json_wtr, "type", @@ -219,7 +285,14 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns); jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt); } +} +static void print_prog_json(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + jsonw_start_object(json_wtr); + print_prog_header_json(info); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -268,10 +341,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_end_object(json_wtr); } -static void print_prog_plain(struct bpf_prog_info *info, int fd) +static void print_prog_header_plain(struct bpf_prog_info *info) { - char *memlock; - printf("%u: ", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) printf("%s ", prog_type_name[info->type]); @@ -289,6 +360,13 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf(" run_time_ns %lld run_cnt %lld", info->run_time_ns, info->run_cnt); printf("\n"); +} + +static void print_prog_plain(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + print_prog_header_plain(info); if (info->load_time) { char buf[32]; @@ -349,6 +427,40 @@ static int show_prog(int fd) return 0; } +static int do_show_subset(int argc, char **argv) +{ + int *fds = NULL; + int nb_fds, i; + int err = -1; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = show_prog(fds[i]); + if (err) { + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + static int do_show(int argc, char **argv) { __u32 id = 0; @@ -358,15 +470,8 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&prog_table, BPF_OBJ_PROG); - if (argc == 2) { - fd = prog_parse_fd(&argc, &argv); - if (fd < 0) - return -1; - - err = show_prog(fd); - close(fd); - return err; - } + if (argc == 2) + return do_show_subset(argc, argv); if (argc) return BAD_ARG(); @@ -408,101 +513,32 @@ static int do_show(int argc, char **argv) return err; } -static int do_dump(int argc, char **argv) +static int +prog_dump(struct bpf_prog_info *info, enum dump_mode mode, + char *filepath, bool opcodes, bool visual, bool linum) { - struct bpf_prog_info_linear *info_linear; struct bpf_prog_linfo *prog_linfo = NULL; - enum {DUMP_JITED, DUMP_XLATED} mode; const char *disasm_opt = NULL; - struct bpf_prog_info *info; struct dump_data dd = {}; void *func_info = NULL; struct btf *btf = NULL; - char *filepath = NULL; - bool opcodes = false; - bool visual = false; char func_sig[1024]; unsigned char *buf; - bool linum = false; __u32 member_len; - __u64 arrays; ssize_t n; int fd; - if (is_prefix(*argv, "jited")) { - if (disasm_init()) - return -1; - mode = DUMP_JITED; - } else if (is_prefix(*argv, "xlated")) { - mode = DUMP_XLATED; - } else { - p_err("expected 'xlated' or 'jited', got: %s", *argv); - return -1; - } - NEXT_ARG(); - - if (argc < 2) - usage(); - - fd = prog_parse_fd(&argc, &argv); - if (fd < 0) - return -1; - - if (is_prefix(*argv, "file")) { - NEXT_ARG(); - if (!argc) { - p_err("expected file path"); - return -1; - } - - filepath = *argv; - NEXT_ARG(); - } else if (is_prefix(*argv, "opcodes")) { - opcodes = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "visual")) { - visual = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "linum")) { - linum = true; - NEXT_ARG(); - } - - if (argc) { - usage(); - return -1; - } - - if (mode == DUMP_JITED) - arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; - else - arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; - - arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; - arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; - arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; - arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; - arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; - - info_linear = bpf_program__get_prog_info_linear(fd, arrays); - close(fd); - if (IS_ERR_OR_NULL(info_linear)) { - p_err("can't get prog info: %s", strerror(errno)); - return -1; - } - - info = &info_linear->info; if (mode == DUMP_JITED) { if (info->jited_prog_len == 0 || !info->jited_prog_insns) { p_info("no instructions returned"); - goto err_free; + return -1; } buf = (unsigned char *)(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ - if (info->xlated_prog_len == 0) { + if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); - goto err_free; + return -1; } buf = (unsigned char *)info->xlated_prog_insns; member_len = info->xlated_prog_len; @@ -510,7 +546,7 @@ static int do_dump(int argc, char **argv) if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) { p_err("failed to get btf"); - goto err_free; + return -1; } func_info = (void *)info->func_info; @@ -526,7 +562,7 @@ static int do_dump(int argc, char **argv) if (fd < 0) { p_err("can't open file %s: %s", filepath, strerror(errno)); - goto err_free; + return -1; } n = write(fd, buf, member_len); @@ -534,7 +570,7 @@ static int do_dump(int argc, char **argv) if (n != member_len) { p_err("error writing output file: %s", n < 0 ? strerror(errno) : "short write"); - goto err_free; + return -1; } if (json_output) @@ -548,7 +584,7 @@ static int do_dump(int argc, char **argv) info->netns_ino, &disasm_opt); if (!name) - goto err_free; + return -1; } if (info->nr_jited_func_lens && info->jited_func_lens) { @@ -643,12 +679,130 @@ static int do_dump(int argc, char **argv) kernel_syms_destroy(&dd); } - free(info_linear); return 0; +} -err_free: - free(info_linear); - return -1; +static int do_dump(int argc, char **argv) +{ + struct bpf_prog_info_linear *info_linear; + char *filepath = NULL; + bool opcodes = false; + bool visual = false; + enum dump_mode mode; + bool linum = false; + int *fds = NULL; + int nb_fds, i = 0; + int err = -1; + __u64 arrays; + + if (is_prefix(*argv, "jited")) { + if (disasm_init()) + return -1; + mode = DUMP_JITED; + } else if (is_prefix(*argv, "xlated")) { + mode = DUMP_XLATED; + } else { + p_err("expected 'xlated' or 'jited', got: %s", *argv); + return -1; + } + NEXT_ARG(); + + if (argc < 2) + usage(); + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (is_prefix(*argv, "file")) { + NEXT_ARG(); + if (!argc) { + p_err("expected file path"); + goto exit_close; + } + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + filepath = *argv; + NEXT_ARG(); + } else if (is_prefix(*argv, "opcodes")) { + opcodes = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "visual")) { + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + visual = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "linum")) { + linum = true; + NEXT_ARG(); + } + + if (argc) { + usage(); + goto exit_close; + } + + if (mode == DUMP_JITED) + arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; + else + arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; + + arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; + arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; + arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; + arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; + arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + info_linear = bpf_program__get_prog_info_linear(fds[i], arrays); + if (IS_ERR_OR_NULL(info_linear)) { + p_err("can't get prog info: %s", strerror(errno)); + break; + } + + if (json_output && nb_fds > 1) { + jsonw_start_object(json_wtr); /* prog object */ + print_prog_header_json(&info_linear->info); + jsonw_name(json_wtr, "insns"); + } else if (nb_fds > 1) { + print_prog_header_plain(&info_linear->info); + } + + err = prog_dump(&info_linear->info, mode, filepath, opcodes, + visual, linum); + + if (json_output && nb_fds > 1) + jsonw_end_object(json_wtr); /* prog object */ + else if (i != nb_fds - 1 && nb_fds > 1) + printf("\n"); + + free(info_linear); + if (err) + break; + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(fds); + return err; } static int do_pin(int argc, char **argv) diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 5b91ee65a080..8608cd68cdd0 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -7,7 +7,7 @@ #include <stdlib.h> #include <string.h> #include <sys/types.h> -#include <libbpf.h> +#include <bpf/libbpf.h> #include "disasm.h" #include "json_writer.h" diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore new file mode 100644 index 000000000000..90a456a2a72f --- /dev/null +++ b/tools/bpf/runqslower/.gitignore @@ -0,0 +1 @@ +/.output diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile new file mode 100644 index 000000000000..39edd68afa8e --- /dev/null +++ b/tools/bpf/runqslower/Makefile @@ -0,0 +1,84 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +OUTPUT := .output +CLANG ?= clang +LLC ?= llc +LLVM_STRIP ?= llvm-strip +DEFAULT_BPFTOOL := $(OUTPUT)/sbin/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) +LIBBPF_SRC := $(abspath ../../lib/bpf) +BPFOBJ := $(OUTPUT)/libbpf.a +BPF_INCLUDE := $(OUTPUT) +INCLUDES := -I$(BPF_INCLUDE) -I$(OUTPUT) -I$(abspath ../../lib) +CFLAGS := -g -Wall + +# Try to detect best kernel BTF source +KERNEL_REL := $(shell uname -r) +VMLINUX_BTF_PATHS := /sys/kernel/btf/vmlinux /boot/vmlinux-$(KERNEL_REL) +VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword \ + $(wildcard $(VMLINUX_BTF_PATHS)))) + +abs_out := $(abspath $(OUTPUT)) +ifeq ($(V),1) +Q = +msg = +else +Q = @ +msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; +MAKEFLAGS += --no-print-directory +submake_extras := feature_display=0 +endif + +.DELETE_ON_ERROR: + +.PHONY: all clean runqslower +all: runqslower + +runqslower: $(OUTPUT)/runqslower + +clean: + $(call msg,CLEAN) + $(Q)rm -rf $(OUTPUT) runqslower + +$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ) + $(call msg,BINARY,$@) + $(Q)$(CC) $(CFLAGS) $^ -lelf -lz -o $@ + +$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \ + $(OUTPUT)/runqslower.bpf.o + +$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h + +$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL) + $(call msg,GEN-SKEL,$@) + $(Q)$(BPFTOOL) gen skeleton $< > $@ + +$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT) + $(call msg,BPF,$@) + $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + -c $(filter %.c,$^) -o $@ && \ + $(LLVM_STRIP) -g $@ + +$(OUTPUT)/%.o: %.c | $(OUTPUT) + $(call msg,CC,$@) + $(Q)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@ + +$(OUTPUT): + $(call msg,MKDIR,$@) + $(Q)mkdir -p $(OUTPUT) + +$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL) + $(call msg,GEN,$@) + $(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \ + echo "Couldn't find kernel BTF; set VMLINUX_BTF to" \ + "specify its location." >&2; \ + exit 1;\ + fi + $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@ + +$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) \ + OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + +$(DEFAULT_BPFTOOL): + $(Q)$(MAKE) $(submake_extras) -C ../bpftool \ + prefix= OUTPUT=$(abs_out)/ DESTDIR=$(abs_out) install diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c new file mode 100644 index 000000000000..48a39f72fadf --- /dev/null +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "runqslower.h" + +#define TASK_RUNNING 0 + +#define BPF_F_INDEX_MASK 0xffffffffULL +#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK + +const volatile __u64 min_us = 0; +const volatile pid_t targ_pid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 10240); + __type(key, u32); + __type(value, u64); +} start SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); +} events SEC(".maps"); + +/* record enqueue timestamp */ +__always_inline +static int trace_enqueue(u32 tgid, u32 pid) +{ + u64 ts; + + if (!pid || (targ_pid && targ_pid != pid)) + return 0; + + ts = bpf_ktime_get_ns(); + bpf_map_update_elem(&start, &pid, &ts, 0); + return 0; +} + +SEC("tp_btf/sched_wakeup") +int handle__sched_wakeup(u64 *ctx) +{ + /* TP_PROTO(struct task_struct *p) */ + struct task_struct *p = (void *)ctx[0]; + + return trace_enqueue(p->tgid, p->pid); +} + +SEC("tp_btf/sched_wakeup_new") +int handle__sched_wakeup_new(u64 *ctx) +{ + /* TP_PROTO(struct task_struct *p) */ + struct task_struct *p = (void *)ctx[0]; + + return trace_enqueue(p->tgid, p->pid); +} + +SEC("tp_btf/sched_switch") +int handle__sched_switch(u64 *ctx) +{ + /* TP_PROTO(bool preempt, struct task_struct *prev, + * struct task_struct *next) + */ + struct task_struct *prev = (struct task_struct *)ctx[1]; + struct task_struct *next = (struct task_struct *)ctx[2]; + struct event event = {}; + u64 *tsp, delta_us; + long state; + u32 pid; + + /* ivcsw: treat like an enqueue event and store timestamp */ + if (prev->state == TASK_RUNNING) + trace_enqueue(prev->tgid, prev->pid); + + pid = next->pid; + + /* fetch timestamp and calculate delta */ + tsp = bpf_map_lookup_elem(&start, &pid); + if (!tsp) + return 0; /* missed enqueue */ + + delta_us = (bpf_ktime_get_ns() - *tsp) / 1000; + if (min_us && delta_us <= min_us) + return 0; + + event.pid = pid; + event.delta_us = delta_us; + bpf_get_current_comm(&event.task, sizeof(event.task)); + + /* output */ + bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, + &event, sizeof(event)); + + bpf_map_delete_elem(&start, &pid); + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c new file mode 100644 index 000000000000..d89715844952 --- /dev/null +++ b/tools/bpf/runqslower/runqslower.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +// Copyright (c) 2019 Facebook +#include <argp.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/resource.h> +#include <time.h> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include "runqslower.h" +#include "runqslower.skel.h" + +struct env { + pid_t pid; + __u64 min_us; + bool verbose; +} env = { + .min_us = 10000, +}; + +const char *argp_program_version = "runqslower 0.1"; +const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; +const char argp_program_doc[] = +"runqslower Trace long process scheduling delays.\n" +" For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n" +"\n" +"This script traces high scheduling delays between tasks being\n" +"ready to run and them running on CPU after that.\n" +"\n" +"USAGE: runqslower [-p PID] [min_us]\n" +"\n" +"EXAMPLES:\n" +" runqslower # trace run queue latency higher than 10000 us (default)\n" +" runqslower 1000 # trace run queue latency higher than 1000 us\n" +" runqslower -p 123 # trace pid 123 only\n"; + +static const struct argp_option opts[] = { + { "pid", 'p', "PID", 0, "Process PID to trace"}, + { "verbose", 'v', NULL, 0, "Verbose debug output" }, + {}, +}; + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + static int pos_args; + int pid; + long long min_us; + + switch (key) { + case 'v': + env.verbose = true; + break; + case 'p': + errno = 0; + pid = strtol(arg, NULL, 10); + if (errno || pid <= 0) { + fprintf(stderr, "Invalid PID: %s\n", arg); + argp_usage(state); + } + env.pid = pid; + break; + case ARGP_KEY_ARG: + if (pos_args++) { + fprintf(stderr, + "Unrecognized positional argument: %s\n", arg); + argp_usage(state); + } + errno = 0; + min_us = strtoll(arg, NULL, 10); + if (errno || min_us <= 0) { + fprintf(stderr, "Invalid delay (in us): %s\n", arg); + argp_usage(state); + } + env.min_us = min_us; + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !env.verbose) + return 0; + return vfprintf(stderr, format, args); +} + +static int bump_memlock_rlimit(void) +{ + struct rlimit rlim_new = { + .rlim_cur = RLIM_INFINITY, + .rlim_max = RLIM_INFINITY, + }; + + return setrlimit(RLIMIT_MEMLOCK, &rlim_new); +} + +void handle_event(void *ctx, int cpu, void *data, __u32 data_sz) +{ + const struct event *e = data; + struct tm *tm; + char ts[32]; + time_t t; + + time(&t); + tm = localtime(&t); + strftime(ts, sizeof(ts), "%H:%M:%S", tm); + printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us); +} + +void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt) +{ + printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu); +} + +int main(int argc, char **argv) +{ + static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, + }; + struct perf_buffer_opts pb_opts; + struct perf_buffer *pb = NULL; + struct runqslower_bpf *obj; + int err; + + err = argp_parse(&argp, argc, argv, 0, NULL, NULL); + if (err) + return err; + + libbpf_set_print(libbpf_print_fn); + + err = bump_memlock_rlimit(); + if (err) { + fprintf(stderr, "failed to increase rlimit: %d", err); + return 1; + } + + obj = runqslower_bpf__open(); + if (!obj) { + fprintf(stderr, "failed to open and/or load BPF object\n"); + return 1; + } + + /* initialize global data (filtering options) */ + obj->rodata->targ_pid = env.pid; + obj->rodata->min_us = env.min_us; + + err = runqslower_bpf__load(obj); + if (err) { + fprintf(stderr, "failed to load BPF object: %d\n", err); + goto cleanup; + } + + err = runqslower_bpf__attach(obj); + if (err) { + fprintf(stderr, "failed to attach BPF programs\n"); + goto cleanup; + } + + printf("Tracing run queue latency higher than %llu us\n", env.min_us); + printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)"); + + pb_opts.sample_cb = handle_event; + pb_opts.lost_cb = handle_lost_events; + pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, &pb_opts); + err = libbpf_get_error(pb); + if (err) { + pb = NULL; + fprintf(stderr, "failed to open perf buffer: %d\n", err); + goto cleanup; + } + + while ((err = perf_buffer__poll(pb, 100)) >= 0) + ; + printf("Error polling perf buffer: %d\n", err); + +cleanup: + perf_buffer__free(pb); + runqslower_bpf__destroy(obj); + + return err != 0; +} diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h new file mode 100644 index 000000000000..9db225425e5f --- /dev/null +++ b/tools/bpf/runqslower/runqslower.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __RUNQSLOWER_H +#define __RUNQSLOWER_H + +#define TASK_COMM_LEN 16 + +struct event { + char task[TASK_COMM_LEN]; + __u64 delta_us; + pid_t pid; +}; + +#endif /* __RUNQSLOWER_H */ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index f30a89046aa3..7ac0d8088565 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -197,7 +197,7 @@ $(OUTPUT)test-libcrypto.bin: $(BUILD) -lcrypto $(OUTPUT)test-gtk2.bin: - $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) + $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) -Wno-deprecated-declarations $(OUTPUT)test-gtk2-infobar.bin: $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) diff --git a/tools/build/feature/test-clang.cpp b/tools/build/feature/test-clang.cpp index a2b3f092d2f0..7d87075cd1c5 100644 --- a/tools/build/feature/test-clang.cpp +++ b/tools/build/feature/test-clang.cpp @@ -1,9 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 +#include "clang/Basic/Version.h" +#if CLANG_VERSION_MAJOR < 8 #include "clang/Basic/VirtualFileSystem.h" +#endif #include "clang/Driver/Driver.h" #include "clang/Frontend/TextDiagnosticPrinter.h" #include "llvm/ADT/IntrusiveRefCntPtr.h" #include "llvm/Support/ManagedStatic.h" +#if CLANG_VERSION_MAJOR >= 8 +#include "llvm/Support/VirtualFileSystem.h" +#endif #include "llvm/Support/raw_ostream.h" using namespace clang; diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index f79b23582a1d..7427a5ee761b 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -72,7 +72,7 @@ class BlkgIterator: name = BlkgIterator.blkcg_name(blkcg) path = parent_path + '/' + name if parent_path else name blkg = drgn.Object(prog, 'struct blkcg_gq', - address=radix_tree_lookup(blkcg.blkg_tree, q_id)) + address=radix_tree_lookup(blkcg.blkg_tree.address_of_(), q_id)) if not blkg.address_: return @@ -228,7 +228,7 @@ q_id = None root_iocg = None ioc = None -for i, ptr in radix_tree_for_each(blkcg_root.blkg_tree): +for i, ptr in radix_tree_for_each(blkcg_root.blkg_tree.address_of_()): blkg = drgn.Object(prog, 'struct blkcg_gq', address=ptr) try: if devname == blkg.q.kobj.parent.name.string_().decode('utf-8'): diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c index aea2d91ab364..16d629b22c25 100644 --- a/tools/hv/hv_fcopy_daemon.c +++ b/tools/hv/hv_fcopy_daemon.c @@ -80,6 +80,8 @@ static int hv_start_fcopy(struct hv_start_fcopy *smsg) error = 0; done: + if (error) + target_fname[0] = '\0'; return error; } @@ -108,15 +110,29 @@ static int hv_copy_data(struct hv_do_fcopy *cpmsg) return ret; } +/* + * Reset target_fname to "" in the two below functions for hibernation: if + * the fcopy operation is aborted by hibernation, the daemon should remove the + * partially-copied file; to achieve this, the hv_utils driver always fakes a + * CANCEL_FCOPY message upon suspend, and later when the VM resumes back, + * the daemon calls hv_copy_cancel() to remove the file; if a file is copied + * successfully before suspend, hv_copy_finished() must reset target_fname to + * avoid that the file can be incorrectly removed upon resume, since the faked + * CANCEL_FCOPY message is spurious in this case. + */ static int hv_copy_finished(void) { close(target_fd); + target_fname[0] = '\0'; return 0; } static int hv_copy_cancel(void) { close(target_fd); - unlink(target_fname); + if (strlen(target_fname) > 0) { + unlink(target_fname); + target_fname[0] = '\0'; + } return 0; } @@ -131,7 +147,7 @@ void print_usage(char *argv[]) int main(int argc, char *argv[]) { - int fcopy_fd; + int fcopy_fd = -1; int error; int daemonize = 1, long_index = 0, opt; int version = FCOPY_CURRENT_VERSION; @@ -141,7 +157,7 @@ int main(int argc, char *argv[]) struct hv_do_fcopy copy; __u32 kernel_modver; } buffer = { }; - int in_handshake = 1; + int in_handshake; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, @@ -170,6 +186,12 @@ int main(int argc, char *argv[]) openlog("HV_FCOPY", 0, LOG_USER); syslog(LOG_INFO, "starting; pid is:%d", getpid()); +reopen_fcopy_fd: + if (fcopy_fd != -1) + close(fcopy_fd); + /* Remove any possible partially-copied file on error */ + hv_copy_cancel(); + in_handshake = 1; fcopy_fd = open("/dev/vmbus/hv_fcopy", O_RDWR); if (fcopy_fd < 0) { @@ -196,7 +218,7 @@ int main(int argc, char *argv[]) len = pread(fcopy_fd, &buffer, sizeof(buffer), 0); if (len < 0) { syslog(LOG_ERR, "pread failed: %s", strerror(errno)); - exit(EXIT_FAILURE); + goto reopen_fcopy_fd; } if (in_handshake) { @@ -231,9 +253,14 @@ int main(int argc, char *argv[]) } + /* + * pwrite() may return an error due to the faked CANCEL_FCOPY + * message upon hibernation. Ignore the error by resetting the + * dev file, i.e. closing and re-opening it. + */ if (pwrite(fcopy_fd, &error, sizeof(int), 0) != sizeof(int)) { syslog(LOG_ERR, "pwrite failed: %s", strerror(errno)); - exit(EXIT_FAILURE); + goto reopen_fcopy_fd; } } } diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index e9ef4ca6a655..ee9c1bb2293e 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -76,7 +76,7 @@ enum { DNS }; -static int in_hand_shake = 1; +static int in_hand_shake; static char *os_name = ""; static char *os_major = ""; @@ -1360,7 +1360,7 @@ void print_usage(char *argv[]) int main(int argc, char *argv[]) { - int kvp_fd, len; + int kvp_fd = -1, len; int error; struct pollfd pfd; char *p; @@ -1400,14 +1400,6 @@ int main(int argc, char *argv[]) openlog("KVP", 0, LOG_USER); syslog(LOG_INFO, "KVP starting; pid is:%d", getpid()); - kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC); - - if (kvp_fd < 0) { - syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s", - errno, strerror(errno)); - exit(EXIT_FAILURE); - } - /* * Retrieve OS release information. */ @@ -1423,6 +1415,18 @@ int main(int argc, char *argv[]) exit(EXIT_FAILURE); } +reopen_kvp_fd: + if (kvp_fd != -1) + close(kvp_fd); + in_hand_shake = 1; + kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC); + + if (kvp_fd < 0) { + syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s", + errno, strerror(errno)); + exit(EXIT_FAILURE); + } + /* * Register ourselves with the kernel. */ @@ -1456,9 +1460,7 @@ int main(int argc, char *argv[]) if (len != sizeof(struct hv_kvp_msg)) { syslog(LOG_ERR, "read failed; error:%d %s", errno, strerror(errno)); - - close(kvp_fd); - return EXIT_FAILURE; + goto reopen_kvp_fd; } /* @@ -1617,13 +1619,17 @@ int main(int argc, char *argv[]) break; } - /* Send the value back to the kernel. */ + /* + * Send the value back to the kernel. Note: the write() may + * return an error due to hibernation; we can ignore the error + * by resetting the dev file, i.e. closing and re-opening it. + */ kvp_done: len = write(kvp_fd, hv_msg, sizeof(struct hv_kvp_msg)); if (len != sizeof(struct hv_kvp_msg)) { syslog(LOG_ERR, "write failed; error: %d %s", errno, strerror(errno)); - exit(EXIT_FAILURE); + goto reopen_kvp_fd; } } diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c index 92902a88f671..dd111870beee 100644 --- a/tools/hv/hv_vss_daemon.c +++ b/tools/hv/hv_vss_daemon.c @@ -28,6 +28,8 @@ #include <stdbool.h> #include <dirent.h> +static bool fs_frozen; + /* Don't use syslog() in the function since that can cause write to disk */ static int vss_do_freeze(char *dir, unsigned int cmd) { @@ -155,18 +157,27 @@ static int vss_operate(int operation) continue; } error |= vss_do_freeze(ent->mnt_dir, cmd); - if (error && operation == VSS_OP_FREEZE) - goto err; + if (operation == VSS_OP_FREEZE) { + if (error) + goto err; + fs_frozen = true; + } } endmntent(mounts); if (root_seen) { error |= vss_do_freeze("/", cmd); - if (error && operation == VSS_OP_FREEZE) - goto err; + if (operation == VSS_OP_FREEZE) { + if (error) + goto err; + fs_frozen = true; + } } + if (operation == VSS_OP_THAW && !error) + fs_frozen = false; + goto out; err: save_errno = errno; @@ -175,6 +186,7 @@ err: endmntent(mounts); } vss_operate(VSS_OP_THAW); + fs_frozen = false; /* Call syslog after we thaw all filesystems */ if (ent) syslog(LOG_ERR, "FREEZE of %s failed; error:%d %s", @@ -196,13 +208,13 @@ void print_usage(char *argv[]) int main(int argc, char *argv[]) { - int vss_fd, len; + int vss_fd = -1, len; int error; struct pollfd pfd; int op; struct hv_vss_msg vss_msg[1]; int daemonize = 1, long_index = 0, opt; - int in_handshake = 1; + int in_handshake; __u32 kernel_modver; static struct option long_options[] = { @@ -232,6 +244,18 @@ int main(int argc, char *argv[]) openlog("Hyper-V VSS", 0, LOG_USER); syslog(LOG_INFO, "VSS starting; pid is:%d", getpid()); +reopen_vss_fd: + if (vss_fd != -1) + close(vss_fd); + if (fs_frozen) { + if (vss_operate(VSS_OP_THAW) || fs_frozen) { + syslog(LOG_ERR, "failed to thaw file system: err=%d", + errno); + exit(EXIT_FAILURE); + } + } + + in_handshake = 1; vss_fd = open("/dev/vmbus/hv_vss", O_RDWR); if (vss_fd < 0) { syslog(LOG_ERR, "open /dev/vmbus/hv_vss failed; error: %d %s", @@ -284,8 +308,7 @@ int main(int argc, char *argv[]) if (len != sizeof(struct hv_vss_msg)) { syslog(LOG_ERR, "read failed; error:%d %s", errno, strerror(errno)); - close(vss_fd); - return EXIT_FAILURE; + goto reopen_vss_fd; } op = vss_msg->vss_hdr.operation; @@ -312,14 +335,18 @@ int main(int argc, char *argv[]) default: syslog(LOG_ERR, "Illegal op:%d\n", op); } + + /* + * The write() may return an error due to the faked VSS_OP_THAW + * message upon hibernation. Ignore the error by resetting the + * dev file, i.e. closing and re-opening it. + */ vss_msg->error = error; len = write(vss_fd, vss_msg, sizeof(struct hv_vss_msg)); if (len != sizeof(struct hv_vss_msg)) { syslog(LOG_ERR, "write failed; error: %d %s", errno, strerror(errno)); - - if (op == VSS_OP_FREEZE) - vss_operate(VSS_OP_THAW); + goto reopen_vss_fd; } } diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 05dca5c203f3..477a1cae513f 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -15,6 +15,8 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); +int __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits); void bitmap_clear(unsigned long *map, unsigned int start, int len); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) @@ -124,6 +126,15 @@ static inline unsigned long *bitmap_alloc(int nbits) } /* + * bitmap_free - Free bitmap + * @bitmap: pointer to bitmap + */ +static inline void bitmap_free(unsigned long *bitmap) +{ + free(bitmap); +} + +/* * bitmap_scnprintf - print bitmap list into buffer * @bitmap: bitmap * @nbits: size of bitmap @@ -148,4 +159,23 @@ static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, return __bitmap_and(dst, src1, src2, nbits); } +#ifdef __LITTLE_ENDIAN +#define BITMAP_MEM_ALIGNMENT 8 +#else +#define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) +#endif +#define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) +#define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) + +static inline int bitmap_equal(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); + if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) && + IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) + return !memcmp(src1, src2, nbits / 8); + return __bitmap_equal(src1, src2, nbits); +} + #endif /* _PERF_BITOPS_H */ diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 140c8362f113..5fca38fe1ba8 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -14,10 +14,11 @@ #include <linux/bits.h> #include <linux/compiler.h> -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) -#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) -#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) -#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE) +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) +#define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) +#define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) +#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index 980cb9266718..5e9e781905ed 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -17,7 +17,15 @@ int strtobool(const char *s, bool *res); * However uClibc headers also define __GLIBC__ hence the hack below */ #if defined(__GLIBC__) && !defined(__UCLIBC__) +// pragma diagnostic was introduced in gcc 4.6 +#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wredundant-decls" +#endif extern size_t strlcpy(char *dest, const char *src, size_t size); +#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6) +#pragma GCC diagnostic pop +#endif #endif char *str_error_r(int errnum, char *buf, size_t buflen); diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index c160a5354eb6..f94f65d429be 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -11,6 +11,8 @@ #define PROT_WRITE 0x2 /* page can be written */ #define PROT_EXEC 0x4 /* page can be executed */ #define PROT_SEM 0x8 /* page may be used for atomic ops */ +/* 0x10 reserved for arch-specific use */ +/* 0x20 reserved for arch-specific use */ #define PROT_NONE 0x0 /* page can not be accessed */ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 1fc8faa6e973..3a3201e4618e 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -851,8 +851,13 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open) __SYSCALL(__NR_clone3, sys_clone3) #endif +#define __NR_openat2 437 +__SYSCALL(__NR_openat2, sys_openat2) +#define __NR_pidfd_getfd 438 +__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) + #undef __NR_syscalls -#define __NR_syscalls 436 +#define __NR_syscalls 439 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h index 13a58531e6fa..39acc149d843 100644 --- a/tools/include/uapi/asm/bpf_perf_event.h +++ b/tools/include/uapi/asm/bpf_perf_event.h @@ -2,6 +2,8 @@ #include "../../arch/arm64/include/uapi/asm/bpf_perf_event.h" #elif defined(__s390__) #include "../../arch/s390/include/uapi/asm/bpf_perf_event.h" +#elif defined(__riscv) +#include "../../arch/riscv/include/uapi/asm/bpf_perf_event.h" #else #include <uapi/asm-generic/bpf_perf_event.h> #endif diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 5400d7e057f1..829c0a48577f 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -395,6 +395,7 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_PWRITE DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite) #define DRM_IOCTL_I915_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap) #define DRM_IOCTL_I915_GEM_MMAP_GTT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt) +#define DRM_IOCTL_I915_GEM_MMAP_OFFSET DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset) #define DRM_IOCTL_I915_GEM_SET_DOMAIN DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain) #define DRM_IOCTL_I915_GEM_SW_FINISH DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish) #define DRM_IOCTL_I915_GEM_SET_TILING DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling) @@ -793,6 +794,37 @@ struct drm_i915_gem_mmap_gtt { __u64 offset; }; +struct drm_i915_gem_mmap_offset { + /** Handle for the object being mapped. */ + __u32 handle; + __u32 pad; + /** + * Fake offset to use for subsequent mmap call + * + * This is a fixed-size type for 32/64 compatibility. + */ + __u64 offset; + + /** + * Flags for extended behaviour. + * + * It is mandatory that one of the MMAP_OFFSET types + * (GTT, WC, WB, UC, etc) should be included. + */ + __u64 flags; +#define I915_MMAP_OFFSET_GTT 0 +#define I915_MMAP_OFFSET_WC 1 +#define I915_MMAP_OFFSET_WB 2 +#define I915_MMAP_OFFSET_UC 3 + + /* + * Zero-terminated chain of extensions. + * + * No current extensions defined; mbz. + */ + __u64 extensions; +}; + struct drm_i915_gem_set_domain { /** Handle for the object */ __u32 handle; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index dbbcf0b02970..22f235260a3a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -107,6 +107,10 @@ enum bpf_cmd { BPF_MAP_LOOKUP_AND_DELETE_ELEM, BPF_MAP_FREEZE, BPF_BTF_GET_NEXT_ID, + BPF_MAP_LOOKUP_BATCH, + BPF_MAP_LOOKUP_AND_DELETE_BATCH, + BPF_MAP_UPDATE_BATCH, + BPF_MAP_DELETE_BATCH, }; enum bpf_map_type { @@ -136,6 +140,7 @@ enum bpf_map_type { BPF_MAP_TYPE_STACK, BPF_MAP_TYPE_SK_STORAGE, BPF_MAP_TYPE_DEVMAP_HASH, + BPF_MAP_TYPE_STRUCT_OPS, }; /* Note that tracing related programs such as @@ -174,6 +179,8 @@ enum bpf_prog_type { BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_PROG_TYPE_TRACING, + BPF_PROG_TYPE_STRUCT_OPS, + BPF_PROG_TYPE_EXT, }; enum bpf_attach_type { @@ -231,6 +238,11 @@ enum bpf_attach_type { * When children program makes decision (like picking TCP CA or sock bind) * parent program has a chance to override it. * + * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of + * programs for a cgroup. Though it's possible to replace an old program at + * any position by also specifying BPF_F_REPLACE flag and position itself in + * replace_bpf_fd attribute. Old program at this position will be released. + * * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. * A cgroup with NONE doesn't allow any programs in sub-cgroups. * Ex1: @@ -249,6 +261,7 @@ enum bpf_attach_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +#define BPF_F_REPLACE (1U << 2) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -351,7 +364,12 @@ enum bpf_attach_type { /* Enable memory-mapping BPF map */ #define BPF_F_MMAPABLE (1U << 10) -/* flags for BPF_PROG_QUERY */ +/* Flags for BPF_PROG_QUERY. */ + +/* Query effective (directly attached + inherited from ancestor cgroups) + * programs that will be executed for events within a cgroup. + * attach_flags with this flag are returned only for directly attached programs. + */ #define BPF_F_QUERY_EFFECTIVE (1U << 0) enum bpf_stack_build_id_status { @@ -391,6 +409,10 @@ union bpf_attr { __u32 btf_fd; /* fd pointing to a BTF type data */ __u32 btf_key_type_id; /* BTF type_id of the key */ __u32 btf_value_type_id; /* BTF type_id of the value */ + __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel- + * struct stored as the + * map value + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -403,6 +425,23 @@ union bpf_attr { __u64 flags; }; + struct { /* struct used by BPF_MAP_*_BATCH commands */ + __aligned_u64 in_batch; /* start batch, + * NULL to start from beginning + */ + __aligned_u64 out_batch; /* output: next start batch */ + __aligned_u64 keys; + __aligned_u64 values; + __u32 count; /* input/output: + * input: # of key/value + * elements + * output: # of filled elements + */ + __u32 map_fd; + __u64 elem_flags; + __u64 flags; + } batch; + struct { /* anonymous struct used by BPF_PROG_LOAD command */ __u32 prog_type; /* one of enum bpf_prog_type */ __u32 insn_cnt; @@ -442,6 +481,10 @@ union bpf_attr { __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; __u32 attach_flags; + __u32 replace_bpf_fd; /* previously attached eBPF + * program to replace if + * BPF_F_REPLACE is used + */ }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ @@ -1002,9 +1045,9 @@ union bpf_attr { * supports redirection to the egress interface, and accepts no * flag at all. * - * The same effect can be attained with the more generic - * **bpf_redirect_map**\ (), which requires specific maps to be - * used but offers better performance. + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. * Return * For XDP, the helper returns **XDP_REDIRECT** on success or * **XDP_ABORTED** on error. For other program types, the values @@ -1568,13 +1611,11 @@ union bpf_attr { * the caller. Any higher bits in the *flags* argument must be * unset. * - * When used to redirect packets to net devices, this helper - * provides a high performance increase over **bpf_redirect**\ (). - * This is due to various implementation details of the underlying - * mechanisms, one of which is the fact that **bpf_redirect_map**\ - * () tries to send packet as a "bulk" to the device. + * See also bpf_redirect(), which only supports redirecting to an + * ifindex, but doesn't require a map to do so. * Return - * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the **flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description @@ -2693,7 +2734,8 @@ union bpf_attr { * * int bpf_send_signal(u32 sig) * Description - * Send signal *sig* to the current task. + * Send signal *sig* to the process of the current task. + * The signal may be delivered to any of this process's threads. * Return * 0 on success or successfully queued. * @@ -2821,6 +2863,33 @@ union bpf_attr { * Return * On success, the strictly positive length of the string, including * the trailing NUL character. On error, a negative value. + * + * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt) + * Description + * Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock. + * *rcv_nxt* is the ack_seq to be sent out. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_send_signal_thread(u32 sig) + * Description + * Send signal *sig* to the thread corresponding to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * u64 bpf_jiffies64(void) + * Description + * Obtain the 64bit jiffies + * Return + * The 64 bit jiffies */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2938,7 +3007,10 @@ union bpf_attr { FN(probe_read_user), \ FN(probe_read_kernel), \ FN(probe_read_user_str), \ - FN(probe_read_kernel_str), + FN(probe_read_kernel_str), \ + FN(tcp_send_ack), \ + FN(send_signal_thread), \ + FN(jiffies64), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3339,7 +3411,7 @@ struct bpf_map_info { __u32 map_flags; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; - __u32 :32; + __u32 btf_vmlinux_value_type_id; __u64 netns_dev; __u64 netns_ino; __u32 btf_id; diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 63ae4a39e58b..5a667107ad2c 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -22,9 +22,9 @@ struct btf_header { }; /* Max # of type identifier */ -#define BTF_MAX_TYPE 0x0000ffff +#define BTF_MAX_TYPE 0x000fffff /* Max offset into the string section */ -#define BTF_MAX_NAME_OFFSET 0x0000ffff +#define BTF_MAX_NAME_OFFSET 0x00ffffff /* Max # of struct/union/enum members or func args */ #define BTF_MAX_VLEN 0xffff @@ -142,7 +142,14 @@ struct btf_param { enum { BTF_VAR_STATIC = 0, - BTF_VAR_GLOBAL_ALLOCATED, + BTF_VAR_GLOBAL_ALLOCATED = 1, + BTF_VAR_GLOBAL_EXTERN = 2, +}; + +enum btf_func_linkage { + BTF_FUNC_STATIC = 0, + BTF_FUNC_GLOBAL = 1, + BTF_FUNC_EXTERN = 2, }; /* BTF_KIND_VAR is followed by a single "struct btf_var" to describe diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 1f97b33c840e..ca88b7bce553 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -3,6 +3,7 @@ #define _UAPI_LINUX_FCNTL_H #include <asm/fcntl.h> +#include <linux/openat2.h> #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) @@ -100,5 +101,4 @@ #define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */ - #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index 1beb174ad950..0d8a6f47711c 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -8,6 +8,7 @@ #ifndef _UAPI_LINUX_FSCRYPT_H #define _UAPI_LINUX_FSCRYPT_H +#include <linux/ioctl.h> #include <linux/types.h> /* Encryption policy flags */ @@ -109,11 +110,22 @@ struct fscrypt_key_specifier { } u; }; +/* + * Payload of Linux keyring key of type "fscrypt-provisioning", referenced by + * fscrypt_add_key_arg::key_id as an alternative to fscrypt_add_key_arg::raw. + */ +struct fscrypt_provisioning_key_payload { + __u32 type; + __u32 __reserved; + __u8 raw[]; +}; + /* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */ struct fscrypt_add_key_arg { struct fscrypt_key_specifier key_spec; __u32 raw_size; - __u32 __reserved[9]; + __u32 key_id; + __u32 __reserved[8]; __u8 raw[]; }; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8aec8769d944..024af2d1d0af 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -169,6 +169,7 @@ enum { IFLA_MAX_MTU, IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ + IFLA_PERM_ADDRESS, __IFLA_MAX }; @@ -485,6 +486,13 @@ enum macsec_validation_type { MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, }; +enum macsec_offload { + MACSEC_OFFLOAD_OFF = 0, + MACSEC_OFFLOAD_PHY = 1, + __MACSEC_OFFLOAD_END, + MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1, +}; + /* IPVLAN section */ enum { IFLA_IPVLAN_UNSPEC, diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index e7ad9d350a28..1521073b6348 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -76,6 +76,8 @@ enum { #define IPPROTO_MPLS IPPROTO_MPLS IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_MPTCP = 262, /* Multipath TCP connection */ +#define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX }; #endif diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index f0a16b4adbbd..4b95f9a31a2f 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1009,6 +1009,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176 #define KVM_CAP_ARM_NISV_TO_USER 177 #define KVM_CAP_ARM_INJECT_EXT_DABT 178 +#define KVM_CAP_S390_VCPU_RESETS 179 #ifdef KVM_CAP_IRQ_ROUTING @@ -1473,6 +1474,10 @@ struct kvm_enc_region { /* Available with KVM_CAP_ARM_SVE */ #define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int) +/* Available with KVM_CAP_S390_VCPU_RESETS */ +#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) +#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h new file mode 100644 index 000000000000..58b1eb711360 --- /dev/null +++ b/tools/include/uapi/linux/openat2.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_OPENAT2_H +#define _UAPI_LINUX_OPENAT2_H + +#include <linux/types.h> + +/* + * Arguments for how openat2(2) should open the target path. If only @flags and + * @mode are non-zero, then openat2(2) operates very similarly to openat(2). + * + * However, unlike openat(2), unknown or invalid bits in @flags result in + * -EINVAL rather than being silently ignored. @mode must be zero unless one of + * {O_CREAT, O_TMPFILE} are set. + * + * @flags: O_* flags. + * @mode: O_CREAT/O_TMPFILE file mode. + * @resolve: RESOLVE_* flags. + */ +struct open_how { + __u64 flags; + __u64 mode; + __u64 resolve; +}; + +/* how->resolve flags for openat2(2). */ +#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings + (includes bind-mounts). */ +#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style + "magic-links". */ +#define RESOLVE_NO_SYMLINKS 0x04 /* Block traversal through all symlinks + (implies OEXT_NO_MAGICLINKS) */ +#define RESOLVE_BENEATH 0x08 /* Block "lexical" trickery like + "..", symlinks, and absolute + paths which escape the dirfd. */ +#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." + be scoped inside the dirfd + (similar to chroot(2)). */ + +#endif /* _UAPI_LINUX_OPENAT2_H */ diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 7da1b37b27aa..07b4f8131e36 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -234,4 +234,8 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) +/* Control reclaim behavior when allocating memory */ +#define PR_SET_IO_FLUSHER 57 +#define PR_GET_IO_FLUSHER 58 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 4a0217832464..2e3bc22c6f20 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -36,6 +36,12 @@ /* Flags for the clone3() syscall. */ #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */ +/* + * cloning flags intersect with CSIGNAL so can be used with unshare and clone3 + * syscalls only: + */ +#define CLONE_NEWTIME 0x00000080 /* New time namespace */ + #ifndef __ASSEMBLY__ /** * struct clone_args - arguments for the clone3 syscall diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index df1153cea0b7..535a7229e1d9 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -26,7 +26,9 @@ #if defined(__KERNEL__) || defined(__linux__) #include <linux/types.h> +#include <asm/byteorder.h> #else +#include <endian.h> #include <sys/ioctl.h> #endif @@ -154,7 +156,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 14) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 15) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -301,7 +303,9 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */ #define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */ - +#if (__BITS_PER_LONG == 32 && defined(__USE_TIME_BITS64)) || defined __KERNEL__ +#define __SND_STRUCT_TIME64 +#endif typedef int __bitwise snd_pcm_state_t; #define SNDRV_PCM_STATE_OPEN ((__force snd_pcm_state_t) 0) /* stream is open */ @@ -317,8 +321,17 @@ typedef int __bitwise snd_pcm_state_t; enum { SNDRV_PCM_MMAP_OFFSET_DATA = 0x00000000, - SNDRV_PCM_MMAP_OFFSET_STATUS = 0x80000000, - SNDRV_PCM_MMAP_OFFSET_CONTROL = 0x81000000, + SNDRV_PCM_MMAP_OFFSET_STATUS_OLD = 0x80000000, + SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD = 0x81000000, + SNDRV_PCM_MMAP_OFFSET_STATUS_NEW = 0x82000000, + SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW = 0x83000000, +#ifdef __SND_STRUCT_TIME64 + SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_NEW, + SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW, +#else + SNDRV_PCM_MMAP_OFFSET_STATUS = SNDRV_PCM_MMAP_OFFSET_STATUS_OLD, + SNDRV_PCM_MMAP_OFFSET_CONTROL = SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD, +#endif }; union snd_pcm_sync_id { @@ -456,8 +469,13 @@ enum { SNDRV_PCM_AUDIO_TSTAMP_TYPE_LAST = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK_SYNCHRONIZED }; +#ifndef __KERNEL__ +/* explicit padding avoids incompatibility between i386 and x86-64 */ +typedef struct { unsigned char pad[sizeof(time_t) - sizeof(int)]; } __time_pad; + struct snd_pcm_status { snd_pcm_state_t state; /* stream state */ + __time_pad pad1; /* align to timespec */ struct timespec trigger_tstamp; /* time when stream was started/stopped/paused */ struct timespec tstamp; /* reference timestamp */ snd_pcm_uframes_t appl_ptr; /* appl ptr */ @@ -473,17 +491,48 @@ struct snd_pcm_status { __u32 audio_tstamp_accuracy; /* in ns units, only valid if indicated in audio_tstamp_data */ unsigned char reserved[52-2*sizeof(struct timespec)]; /* must be filled with zero */ }; +#endif + +/* + * For mmap operations, we need the 64-bit layout, both for compat mode, + * and for y2038 compatibility. For 64-bit applications, the two definitions + * are identical, so we keep the traditional version. + */ +#ifdef __SND_STRUCT_TIME64 +#define __snd_pcm_mmap_status64 snd_pcm_mmap_status +#define __snd_pcm_mmap_control64 snd_pcm_mmap_control +#define __snd_pcm_sync_ptr64 snd_pcm_sync_ptr +#ifdef __KERNEL__ +#define __snd_timespec64 __kernel_timespec +#else +#define __snd_timespec64 timespec +#endif +struct __snd_timespec { + __s32 tv_sec; + __s32 tv_nsec; +}; +#else +#define __snd_pcm_mmap_status snd_pcm_mmap_status +#define __snd_pcm_mmap_control snd_pcm_mmap_control +#define __snd_pcm_sync_ptr snd_pcm_sync_ptr +#define __snd_timespec timespec +struct __snd_timespec64 { + __s64 tv_sec; + __s64 tv_nsec; +}; -struct snd_pcm_mmap_status { +#endif + +struct __snd_pcm_mmap_status { snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */ int pad1; /* Needed for 64 bit alignment */ snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */ - struct timespec tstamp; /* Timestamp */ + struct __snd_timespec tstamp; /* Timestamp */ snd_pcm_state_t suspended_state; /* RO: suspended stream state */ - struct timespec audio_tstamp; /* from sample counter or wall clock */ + struct __snd_timespec audio_tstamp; /* from sample counter or wall clock */ }; -struct snd_pcm_mmap_control { +struct __snd_pcm_mmap_control { snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ }; @@ -492,14 +541,59 @@ struct snd_pcm_mmap_control { #define SNDRV_PCM_SYNC_PTR_APPL (1<<1) /* get appl_ptr from driver (r/w op) */ #define SNDRV_PCM_SYNC_PTR_AVAIL_MIN (1<<2) /* get avail_min from driver */ -struct snd_pcm_sync_ptr { +struct __snd_pcm_sync_ptr { unsigned int flags; union { - struct snd_pcm_mmap_status status; + struct __snd_pcm_mmap_status status; + unsigned char reserved[64]; + } s; + union { + struct __snd_pcm_mmap_control control; + unsigned char reserved[64]; + } c; +}; + +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) +typedef char __pad_before_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)]; +typedef char __pad_after_uframe[0]; +#endif + +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) +typedef char __pad_before_uframe[0]; +typedef char __pad_after_uframe[sizeof(__u64) - sizeof(snd_pcm_uframes_t)]; +#endif + +struct __snd_pcm_mmap_status64 { + snd_pcm_state_t state; /* RO: state - SNDRV_PCM_STATE_XXXX */ + __u32 pad1; /* Needed for 64 bit alignment */ + __pad_before_uframe __pad1; + snd_pcm_uframes_t hw_ptr; /* RO: hw ptr (0...boundary-1) */ + __pad_after_uframe __pad2; + struct __snd_timespec64 tstamp; /* Timestamp */ + snd_pcm_state_t suspended_state;/* RO: suspended stream state */ + __u32 pad3; /* Needed for 64 bit alignment */ + struct __snd_timespec64 audio_tstamp; /* sample counter or wall clock */ +}; + +struct __snd_pcm_mmap_control64 { + __pad_before_uframe __pad1; + snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ + __pad_before_uframe __pad2; + + __pad_before_uframe __pad3; + snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ + __pad_after_uframe __pad4; +}; + +struct __snd_pcm_sync_ptr64 { + __u32 flags; + __u32 pad1; + union { + struct __snd_pcm_mmap_status64 status; unsigned char reserved[64]; } s; union { - struct snd_pcm_mmap_control control; + struct __snd_pcm_mmap_control64 control; unsigned char reserved[64]; } c; }; @@ -584,6 +678,8 @@ enum { #define SNDRV_PCM_IOCTL_STATUS _IOR('A', 0x20, struct snd_pcm_status) #define SNDRV_PCM_IOCTL_DELAY _IOR('A', 0x21, snd_pcm_sframes_t) #define SNDRV_PCM_IOCTL_HWSYNC _IO('A', 0x22) +#define __SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct __snd_pcm_sync_ptr) +#define __SNDRV_PCM_IOCTL_SYNC_PTR64 _IOWR('A', 0x23, struct __snd_pcm_sync_ptr64) #define SNDRV_PCM_IOCTL_SYNC_PTR _IOWR('A', 0x23, struct snd_pcm_sync_ptr) #define SNDRV_PCM_IOCTL_STATUS_EXT _IOWR('A', 0x24, struct snd_pcm_status) #define SNDRV_PCM_IOCTL_CHANNEL_INFO _IOR('A', 0x32, struct snd_pcm_channel_info) @@ -614,7 +710,7 @@ enum { * Raw MIDI section - /dev/snd/midi?? */ -#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 0) +#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 1) enum { SNDRV_RAWMIDI_STREAM_OUTPUT = 0, @@ -648,13 +744,16 @@ struct snd_rawmidi_params { unsigned char reserved[16]; /* reserved for future use */ }; +#ifndef __KERNEL__ struct snd_rawmidi_status { int stream; + __time_pad pad1; struct timespec tstamp; /* Timestamp */ size_t avail; /* available bytes */ size_t xruns; /* count of overruns since last status (in bytes) */ unsigned char reserved[16]; /* reserved for future use */ }; +#endif #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) @@ -667,7 +766,7 @@ struct snd_rawmidi_status { * Timer section - /dev/snd/timer */ -#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 6) +#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7) enum { SNDRV_TIMER_CLASS_NONE = -1, @@ -761,6 +860,7 @@ struct snd_timer_params { unsigned char reserved[60]; /* reserved */ }; +#ifndef __KERNEL__ struct snd_timer_status { struct timespec tstamp; /* Timestamp - last update */ unsigned int resolution; /* current period resolution in ns */ @@ -769,10 +869,11 @@ struct snd_timer_status { unsigned int queue; /* used queue size */ unsigned char reserved[64]; /* reserved */ }; +#endif #define SNDRV_TIMER_IOCTL_PVERSION _IOR('T', 0x00, int) #define SNDRV_TIMER_IOCTL_NEXT_DEVICE _IOWR('T', 0x01, struct snd_timer_id) -#define SNDRV_TIMER_IOCTL_TREAD _IOW('T', 0x02, int) +#define SNDRV_TIMER_IOCTL_TREAD_OLD _IOW('T', 0x02, int) #define SNDRV_TIMER_IOCTL_GINFO _IOWR('T', 0x03, struct snd_timer_ginfo) #define SNDRV_TIMER_IOCTL_GPARAMS _IOW('T', 0x04, struct snd_timer_gparams) #define SNDRV_TIMER_IOCTL_GSTATUS _IOWR('T', 0x05, struct snd_timer_gstatus) @@ -785,6 +886,15 @@ struct snd_timer_status { #define SNDRV_TIMER_IOCTL_STOP _IO('T', 0xa1) #define SNDRV_TIMER_IOCTL_CONTINUE _IO('T', 0xa2) #define SNDRV_TIMER_IOCTL_PAUSE _IO('T', 0xa3) +#define SNDRV_TIMER_IOCTL_TREAD64 _IOW('T', 0xa4, int) + +#if __BITS_PER_LONG == 64 +#define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD +#else +#define SNDRV_TIMER_IOCTL_TREAD ((sizeof(__kernel_long_t) >= sizeof(time_t)) ? \ + SNDRV_TIMER_IOCTL_TREAD_OLD : \ + SNDRV_TIMER_IOCTL_TREAD64) +#endif struct snd_timer_read { unsigned int resolution; @@ -810,11 +920,15 @@ enum { SNDRV_TIMER_EVENT_MRESUME = SNDRV_TIMER_EVENT_RESUME + 10, }; +#ifndef __KERNEL__ struct snd_timer_tread { int event; + __time_pad pad1; struct timespec tstamp; unsigned int val; + __time_pad pad2; }; +#endif /**************************************************************************** * * @@ -822,7 +936,7 @@ struct snd_timer_tread { * * ****************************************************************************/ -#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7) +#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 8) struct snd_ctl_card_info { int card; /* card number */ @@ -860,7 +974,7 @@ typedef int __bitwise snd_ctl_elem_iface_t; #define SNDRV_CTL_ELEM_ACCESS_WRITE (1<<1) #define SNDRV_CTL_ELEM_ACCESS_READWRITE (SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE) #define SNDRV_CTL_ELEM_ACCESS_VOLATILE (1<<2) /* control value may be changed without a notification */ -#define SNDRV_CTL_ELEM_ACCESS_TIMESTAMP (1<<3) /* when was control changed */ +// (1 << 3) is unused. #define SNDRV_CTL_ELEM_ACCESS_TLV_READ (1<<4) /* TLV read is possible */ #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE (1<<5) /* TLV write is possible */ #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE (SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE) @@ -926,11 +1040,7 @@ struct snd_ctl_elem_info { } enumerated; unsigned char reserved[128]; } value; - union { - unsigned short d[4]; /* dimensions */ - unsigned short *d_ptr; /* indirect - obsoleted */ - } dimen; - unsigned char reserved[64-4*sizeof(unsigned short)]; + unsigned char reserved[64]; }; struct snd_ctl_elem_value { @@ -955,8 +1065,7 @@ struct snd_ctl_elem_value { } bytes; struct snd_aes_iec958 iec958; } value; /* RO */ - struct timespec tstamp; - unsigned char reserved[128-sizeof(struct timespec)]; + unsigned char reserved[128]; }; struct snd_ctl_tlv { diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index ad1b9e646c49..4cf93110c259 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -270,6 +270,7 @@ class ArchX86(Arch): def __init__(self, exit_reasons): self.sc_perf_evt_open = 298 self.ioctl_numbers = IOCTL_NUMBERS + self.exit_reason_field = 'exit_reason' self.exit_reasons = exit_reasons def debugfs_is_child(self, field): @@ -289,6 +290,7 @@ class ArchPPC(Arch): # numbers depend on the wordsize. char_ptr_size = ctypes.sizeof(ctypes.c_char_p) self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16 + self.exit_reason_field = 'exit_nr' self.exit_reasons = {} def debugfs_is_child(self, field): @@ -300,6 +302,7 @@ class ArchA64(Arch): def __init__(self): self.sc_perf_evt_open = 241 self.ioctl_numbers = IOCTL_NUMBERS + self.exit_reason_field = 'esr_ec' self.exit_reasons = AARCH64_EXIT_REASONS def debugfs_is_child(self, field): @@ -311,6 +314,7 @@ class ArchS390(Arch): def __init__(self): self.sc_perf_evt_open = 331 self.ioctl_numbers = IOCTL_NUMBERS + self.exit_reason_field = None self.exit_reasons = None def debugfs_is_child(self, field): @@ -541,8 +545,8 @@ class TracepointProvider(Provider): """ filters = {} filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS) - if ARCH.exit_reasons: - filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons) + if ARCH.exit_reason_field and ARCH.exit_reasons: + filters['kvm_exit'] = (ARCH.exit_reason_field, ARCH.exit_reasons) return filters def _get_available_fields(self): diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 11b3885e833e..027b18f7ed8c 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -210,6 +210,7 @@ static bool fs__env_override(struct fs *fs) size_t name_len = strlen(fs->name); /* name + "_PATH" + '\0' */ char upper_name[name_len + 5 + 1]; + memcpy(upper_name, fs->name, name_len); mem_toupper(upper_name, name_len); strcpy(&upper_name[name_len], "_PATH"); @@ -219,7 +220,8 @@ static bool fs__env_override(struct fs *fs) return false; fs->found = true; - strncpy(fs->path, override_path, sizeof(fs->path)); + strncpy(fs->path, override_path, sizeof(fs->path) - 1); + fs->path[sizeof(fs->path) - 1] = '\0'; return true; } diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 38494782be06..5043747ef6c5 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -71,3 +71,18 @@ int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, BITMAP_LAST_WORD_MASK(bits)); return result != 0; } + +int __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + unsigned int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap1[k] != bitmap2[k]) + return 0; + + if (bits % BITS_PER_LONG) + if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) + return 0; + + return 1; +} diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 97830e46d1a0..aee7f1a83c77 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -56,8 +56,8 @@ ifndef VERBOSE endif FEATURE_USER = .libbpf -FEATURE_TESTS = libelf libelf-mmap bpf reallocarray -FEATURE_DISPLAY = libelf bpf +FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray +FEATURE_DISPLAY = libelf zlib bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) @@ -148,6 +148,7 @@ TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ @@ -160,7 +161,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS) +$(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -178,11 +179,11 @@ $(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS) echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force elfdep bpfdep $(BPF_HELPER_DEFS) +$(BPF_IN_STATIC): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h - $(Q)$(srctree)/scripts/bpf_helpers_doc.py --header \ + $(QUIET_GEN)$(srctree)/scripts/bpf_helpers_doc.py --header \ --file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS) $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) @@ -190,7 +191,7 @@ $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(QUIET_LINK)$(CC) $(LDFLAGS) \ --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ - -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -lz -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) @@ -214,6 +215,7 @@ check_abi: $(OUTPUT)libbpf.so "versioned in $(VERSION_SCRIPT)." >&2; \ readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf -s --wide $(OUTPUT)libbpf.so | \ @@ -250,6 +252,7 @@ install_headers: $(BPF_HELPER_DEFS) $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ $(call do_install,btf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \ + $(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \ $(call do_install,xsk.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \ $(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \ @@ -270,20 +273,24 @@ config-clean: $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null clean: - $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ - *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ - *.pc LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ - $(SHARED_OBJDIR) $(STATIC_OBJDIR) + $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ + *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ + $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ + $(addprefix $(OUTPUT), \ + *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf -PHONY += force elfdep bpfdep cscope tags +PHONY += force elfdep zdep bpfdep cscope tags force: elfdep: @if [ "$(feature-libelf)" != "1" ]; then echo "No libelf found"; exit 1 ; fi +zdep: + @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi + bpfdep: @if [ "$(feature-bpf)" != "1" ]; then echo "BPF API too old"; exit 1 ; fi diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 98596e15390f..c6dafe563176 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -32,6 +32,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* * When building perf, unistd.h is overridden. __NR_bpf is * required to be defined explicitly. @@ -95,7 +98,11 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) attr.btf_key_type_id = create_attr->btf_key_type_id; attr.btf_value_type_id = create_attr->btf_value_type_id; attr.map_ifindex = create_attr->map_ifindex; - attr.inner_map_fd = create_attr->inner_map_fd; + if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS) + attr.btf_vmlinux_value_type_id = + create_attr->btf_vmlinux_value_type_id; + else + attr.inner_map_fd = create_attr->inner_map_fd; return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } @@ -228,7 +235,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; attr.expected_attach_type = load_attr->expected_attach_type; - if (attr.prog_type == BPF_PROG_TYPE_TRACING) { + if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS) { + attr.attach_btf_id = load_attr->attach_btf_id; + } else if (attr.prog_type == BPF_PROG_TYPE_TRACING || + attr.prog_type == BPF_PROG_TYPE_EXT) { attr.attach_btf_id = load_attr->attach_btf_id; attr.attach_prog_fd = load_attr->attach_prog_fd; } else { @@ -443,6 +453,64 @@ int bpf_map_freeze(int fd) return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); } +static int bpf_map_batch_common(int cmd, int fd, void *in_batch, + void *out_batch, void *keys, void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_map_batch_opts)) + return -EINVAL; + + memset(&attr, 0, sizeof(attr)); + attr.batch.map_fd = fd; + attr.batch.in_batch = ptr_to_u64(in_batch); + attr.batch.out_batch = ptr_to_u64(out_batch); + attr.batch.keys = ptr_to_u64(keys); + attr.batch.values = ptr_to_u64(values); + attr.batch.count = *count; + attr.batch.elem_flags = OPTS_GET(opts, elem_flags, 0); + attr.batch.flags = OPTS_GET(opts, flags, 0); + + ret = sys_bpf(cmd, &attr, sizeof(attr)); + *count = attr.batch.count; + + return ret; +} + +int bpf_map_delete_batch(int fd, void *keys, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL, + NULL, keys, NULL, count, opts); +} + +int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_LOOKUP_BATCH, fd, in_batch, + out_batch, keys, values, count, opts); +} + +int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_LOOKUP_AND_DELETE_BATCH, + fd, in_batch, out_batch, keys, values, + count, opts); +} + +int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL, + keys, values, count, opts); +} + int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; @@ -467,13 +535,28 @@ int bpf_obj_get(const char *pathname) int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, unsigned int flags) { + DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, opts, + .flags = flags, + ); + + return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts); +} + +int bpf_prog_attach_xattr(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts) +{ union bpf_attr attr; + if (!OPTS_VALID(opts, bpf_prog_attach_opts)) + return -EINVAL; + memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; - attr.attach_flags = flags; + attr.attach_flags = OPTS_GET(opts, flags, 0); + attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 3c791fa8e68e..b976e77316cc 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -28,14 +28,12 @@ #include <stddef.h> #include <stdint.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - struct bpf_create_map_attr { const char *name; enum bpf_map_type map_type; @@ -48,7 +46,10 @@ struct bpf_create_map_attr { __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 map_ifindex; - __u32 inner_map_fd; + union { + __u32 inner_map_fd; + __u32 btf_vmlinux_value_type_id; + }; }; LIBBPF_API int @@ -126,10 +127,43 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); LIBBPF_API int bpf_map_freeze(int fd); + +struct bpf_map_batch_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u64 elem_flags; + __u64 flags; +}; +#define bpf_map_batch_opts__last_field flags + +LIBBPF_API int bpf_map_delete_batch(int fd, void *keys, + __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, + void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts); + LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); + +struct bpf_prog_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + unsigned int flags; + int replace_prog_fd; +}; +#define bpf_prog_attach_opts__last_field replace_prog_fd + LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 0c7d28292898..f69cc208778a 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -25,6 +25,9 @@ #ifndef __always_inline #define __always_inline __attribute__((always_inline)) #endif +#ifndef __weak +#define __weak __attribute__((weak)) +#endif /* * Helper structure used by eBPF C program @@ -44,4 +47,12 @@ enum libbpf_pin_type { LIBBPF_PIN_BY_NAME, }; +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + +#define __kconfig __attribute__((section(".kconfig"))) + #endif diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c index 3ed1a27b5f7c..bafca49cb1e6 100644 --- a/tools/lib/bpf/bpf_prog_linfo.c +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -8,6 +8,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + struct bpf_prog_linfo { void *raw_linfo; void *raw_jited_linfo; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 88efa2bb7137..3d1c25fc97ae 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -8,6 +8,10 @@ #include <fcntl.h> #include <unistd.h> #include <errno.h> +#include <sys/utsname.h> +#include <sys/param.h> +#include <sys/stat.h> +#include <linux/kernel.h> #include <linux/err.h> #include <linux/btf.h> #include <gelf.h> @@ -17,8 +21,11 @@ #include "libbpf_internal.h" #include "hashmap.h" -#define BTF_MAX_NR_TYPES 0x7fffffff -#define BTF_MAX_STR_OFFSET 0x7fffffff +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +#define BTF_MAX_NR_TYPES 0x7fffffffU +#define BTF_MAX_STR_OFFSET 0x7fffffffU static struct btf_type btf_void; @@ -50,7 +57,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) if (btf->types_size == BTF_MAX_NR_TYPES) return -E2BIG; - expand_by = max(btf->types_size >> 2, 16); + expand_by = max(btf->types_size >> 2, 16U); new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); new_types = realloc(btf->types, sizeof(*new_types) * new_size); @@ -278,6 +285,45 @@ done: return nelems * size; } +int btf__align_of(const struct btf *btf, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + __u16 kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + return min(sizeof(void *), (size_t)t->size); + case BTF_KIND_PTR: + return sizeof(void *); + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf__align_of(btf, t->type); + case BTF_KIND_ARRAY: + return btf__align_of(btf, btf_array(t)->type); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + int i, max_align = 1, align; + + for (i = 0; i < vlen; i++, m++) { + align = btf__align_of(btf, m->type); + if (align <= 0) + return align; + max_align = max(max_align, align); + } + + return max_align; + } + default: + pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); + return 0; + } +} + int btf__resolve_type(const struct btf *btf, __u32 type_id) { const struct btf_type *t; @@ -539,6 +585,12 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, return -ENOENT; } + /* .extern datasec size and var offsets were set correctly during + * extern collection step, so just skip straight to sorting variables + */ + if (t->size) + goto sort_vars; + ret = bpf_object__section_size(obj, name, &size); if (ret || !size || (t->size && t->size != size)) { pr_debug("Invalid size for section %s: %u bytes\n", name, size); @@ -575,7 +627,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, vsi->offset = off; } - qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off); +sort_vars: + qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off); return 0; } @@ -1352,7 +1405,7 @@ static int btf_dedup_hypot_map_add(struct btf_dedup *d, if (d->hypot_cnt == d->hypot_cap) { __u32 *new_list; - d->hypot_cap += max(16, d->hypot_cap / 2); + d->hypot_cap += max((size_t)16, d->hypot_cap / 2); new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap); if (!new_list) return -ENOMEM; @@ -1648,7 +1701,7 @@ static int btf_dedup_strings(struct btf_dedup *d) if (strs.cnt + 1 > strs.cap) { struct btf_str_ptr *new_ptrs; - strs.cap += max(strs.cnt / 2, 16); + strs.cap += max(strs.cnt / 2, 16U); new_ptrs = realloc(strs.ptrs, sizeof(strs.ptrs[0]) * strs.cap); if (!new_ptrs) { @@ -2882,3 +2935,89 @@ static int btf_dedup_remap_types(struct btf_dedup *d) } return 0; } + +static struct btf *btf_load_raw(const char *path) +{ + struct btf *btf; + size_t read_cnt; + struct stat st; + void *data; + FILE *f; + + if (stat(path, &st)) + return ERR_PTR(-errno); + + data = malloc(st.st_size); + if (!data) + return ERR_PTR(-ENOMEM); + + f = fopen(path, "rb"); + if (!f) { + btf = ERR_PTR(-errno); + goto cleanup; + } + + read_cnt = fread(data, 1, st.st_size, f); + fclose(f); + if (read_cnt < st.st_size) { + btf = ERR_PTR(-EBADF); + goto cleanup; + } + + btf = btf__new(data, read_cnt); + +cleanup: + free(data); + return btf; +} + +/* + * Probe few well-known locations for vmlinux kernel image and try to load BTF + * data out of it to use for target BTF. + */ +struct btf *libbpf_find_kernel_btf(void) +{ + struct { + const char *path_fmt; + bool raw_btf; + } locations[] = { + /* try canonical vmlinux BTF through sysfs first */ + { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, + /* fall back to trying to find vmlinux ELF on disk otherwise */ + { "/boot/vmlinux-%1$s" }, + { "/lib/modules/%1$s/vmlinux-%1$s" }, + { "/lib/modules/%1$s/build/vmlinux" }, + { "/usr/lib/modules/%1$s/kernel/vmlinux" }, + { "/usr/lib/debug/boot/vmlinux-%1$s" }, + { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, + { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + }; + char path[PATH_MAX + 1]; + struct utsname buf; + struct btf *btf; + int i; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + + if (access(path, R_OK)) + continue; + + if (locations[i].raw_btf) + btf = btf_load_raw(path); + else + btf = btf__parse_elf(path, NULL); + + pr_debug("loading kernel BTF '%s': %ld\n", + path, IS_ERR(btf) ? PTR_ERR(btf) : 0); + if (IS_ERR(btf)) + continue; + + return btf; + } + + pr_warn("failed to find valid kernel BTF\n"); + return ERR_PTR(-ESRCH); +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index d9ac73a02cde..70c1b7ec2bd0 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -8,14 +8,12 @@ #include <linux/btf.h> #include <linux/types.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" #define MAPS_ELF_SEC ".maps" @@ -79,6 +77,7 @@ LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); +LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); @@ -103,6 +102,8 @@ LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf, LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API struct btf *libbpf_find_kernel_btf(void); + struct btf_dedup_opts { unsigned int dedup_table_size; bool dont_resolve_fwds; @@ -127,6 +128,28 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); +struct btf_dump_emit_type_decl_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* optional field name for type declaration, e.g.: + * - struct my_struct <FNAME> + * - void (*<FNAME>)(int) + * - char (*<FNAME>)[123] + */ + const char *field_name; + /* extra indentation level (in number of tabs) to emit for multi-line + * type declarations (e.g., anonymous struct); applies for lines + * starting from the second one (first line is assumed to have + * necessary indentation already + */ + int indent_level; +}; +#define btf_dump_emit_type_decl_opts__last_field indent_level + +LIBBPF_API int +btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts); + /* * A set of helpers for easier BTF types handling */ diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index cb126d8fcf75..bd09ed1710f1 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -18,6 +18,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t"; static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1; @@ -116,6 +119,8 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) va_end(args); } +static int btf_dump_mark_referenced(struct btf_dump *d); + struct btf_dump *btf_dump__new(const struct btf *btf, const struct btf_ext *btf_ext, const struct btf_dump_opts *opts, @@ -137,18 +142,40 @@ struct btf_dump *btf_dump__new(const struct btf *btf, if (IS_ERR(d->type_names)) { err = PTR_ERR(d->type_names); d->type_names = NULL; - btf_dump__free(d); - return ERR_PTR(err); + goto err; } d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); if (IS_ERR(d->ident_names)) { err = PTR_ERR(d->ident_names); d->ident_names = NULL; - btf_dump__free(d); - return ERR_PTR(err); + goto err; + } + d->type_states = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->type_states[0])); + if (!d->type_states) { + err = -ENOMEM; + goto err; + } + d->cached_names = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->cached_names[0])); + if (!d->cached_names) { + err = -ENOMEM; + goto err; } + /* VOID is special */ + d->type_states[0].order_state = ORDERED; + d->type_states[0].emit_state = EMITTED; + + /* eagerly determine referenced types for anon enums */ + err = btf_dump_mark_referenced(d); + if (err) + goto err; + return d; +err: + btf_dump__free(d); + return ERR_PTR(err); } void btf_dump__free(struct btf_dump *d) @@ -175,7 +202,6 @@ void btf_dump__free(struct btf_dump *d) free(d); } -static int btf_dump_mark_referenced(struct btf_dump *d); static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr); static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id); @@ -202,27 +228,6 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) if (id > btf__get_nr_types(d->btf)) return -EINVAL; - /* type states are lazily allocated, as they might not be needed */ - if (!d->type_states) { - d->type_states = calloc(1 + btf__get_nr_types(d->btf), - sizeof(d->type_states[0])); - if (!d->type_states) - return -ENOMEM; - d->cached_names = calloc(1 + btf__get_nr_types(d->btf), - sizeof(d->cached_names[0])); - if (!d->cached_names) - return -ENOMEM; - - /* VOID is special */ - d->type_states[0].order_state = ORDERED; - d->type_states[0].emit_state = EMITTED; - - /* eagerly determine referenced types for anon enums */ - err = btf_dump_mark_referenced(d); - if (err) - return err; - } - d->emit_queue_cnt = 0; err = btf_dump_order_type(d, id, false); if (err < 0) @@ -752,41 +757,6 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } } -static int btf_align_of(const struct btf *btf, __u32 id) -{ - const struct btf_type *t = btf__type_by_id(btf, id); - __u16 kind = btf_kind(t); - - switch (kind) { - case BTF_KIND_INT: - case BTF_KIND_ENUM: - return min(sizeof(void *), t->size); - case BTF_KIND_PTR: - return sizeof(void *); - case BTF_KIND_TYPEDEF: - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - return btf_align_of(btf, t->type); - case BTF_KIND_ARRAY: - return btf_align_of(btf, btf_array(t)->type); - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: { - const struct btf_member *m = btf_members(t); - __u16 vlen = btf_vlen(t); - int i, align = 1; - - for (i = 0; i < vlen; i++, m++) - align = max(align, btf_align_of(btf, m->type)); - - return align; - } - default: - pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); - return 1; - } -} - static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_type *t) { @@ -794,18 +764,18 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, int align, i, bit_sz; __u16 vlen; - align = btf_align_of(btf, id); + align = btf__align_of(btf, id); /* size of a non-packed struct has to be a multiple of its alignment*/ - if (t->size % align) + if (align && t->size % align) return true; m = btf_members(t); vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ for (i = 0; i < vlen; i++, m++) { - align = btf_align_of(btf, m->type); + align = btf__align_of(btf, m->type); bit_sz = btf_member_bitfield_size(t, i); - if (bit_sz == 0 && m->offset % (8 * align) != 0) + if (align && bit_sz == 0 && m->offset % (8 * align) != 0) return true; } @@ -889,7 +859,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, fname = btf_name_of(d, m->name_off); m_sz = btf_member_bitfield_size(t, i); m_off = btf_member_bit_offset(t, i); - align = packed ? 1 : btf_align_of(d->btf, m->type); + align = packed ? 1 : btf__align_of(d->btf, m->type); btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); btf_dump_printf(d, "\n%s", pfx(lvl + 1)); @@ -907,7 +877,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, /* pad at the end, if necessary */ if (is_struct) { - align = packed ? 1 : btf_align_of(d->btf, id); + align = packed ? 1 : btf__align_of(d->btf, id); btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align, lvl + 1); } @@ -1051,6 +1021,21 @@ static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id) * of a stack frame. Some care is required to "pop" stack frames after * processing type declaration chain. */ +int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts) +{ + const char *fname; + int lvl; + + if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts)) + return -EINVAL; + + fname = OPTS_GET(opts, field_name, NULL); + lvl = OPTS_GET(opts, indent_level, 0); + btf_dump_emit_type_decl(d, id, fname, lvl); + return 0; +} + static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, const char *fname, int lvl) { diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 6122272943e6..54c30c802070 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -12,6 +12,9 @@ #include <linux/err.h> #include "hashmap.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* start with 4 buckets */ #define HASHMAP_MIN_CAP_BITS 2 diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 3f09772192f1..7469c7dcc15e 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -18,11 +18,13 @@ #include <stdarg.h> #include <libgen.h> #include <inttypes.h> +#include <limits.h> #include <string.h> #include <unistd.h> #include <endian.h> #include <fcntl.h> #include <errno.h> +#include <ctype.h> #include <asm/unistd.h> #include <linux/err.h> #include <linux/kernel.h> @@ -41,9 +43,11 @@ #include <sys/types.h> #include <sys/vfs.h> #include <sys/utsname.h> +#include <sys/resource.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> +#include <zlib.h> #include "libbpf.h" #include "bpf.h" @@ -52,6 +56,9 @@ #include "libbpf_internal.h" #include "hashmap.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #ifndef EM_BPF #define EM_BPF 247 #endif @@ -67,6 +74,12 @@ #define __printf(a, b) __attribute__((format(printf, a, b))) +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); +static struct bpf_program *bpf_object__find_prog_by_idx(struct bpf_object *obj, + int idx); +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); + static int __base_pr(enum libbpf_print_level level, const char *format, va_list args) { @@ -99,14 +112,33 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) va_end(args); } -#define STRERR_BUFSIZE 128 +static void pr_perm_msg(int err) +{ + struct rlimit limit; + char buf[100]; + + if (err != -EPERM || geteuid() != 0) + return; + + err = getrlimit(RLIMIT_MEMLOCK, &limit); + if (err) + return; + + if (limit.rlim_cur == RLIM_INFINITY) + return; -#define CHECK_ERR(action, err, out) do { \ - err = action; \ - if (err) \ - goto out; \ -} while (0) + if (limit.rlim_cur < 1024) + snprintf(buf, sizeof(buf), "%zu bytes", (size_t)limit.rlim_cur); + else if (limit.rlim_cur < 1024*1024) + snprintf(buf, sizeof(buf), "%.1f KiB", (double)limit.rlim_cur / 1024); + else + snprintf(buf, sizeof(buf), "%.1f MiB", (double)limit.rlim_cur / (1024*1024)); + + pr_warn("permission error while running as root; try raising 'ulimit -l'? current value: %s\n", + buf); +} +#define STRERR_BUFSIZE 128 /* Copied from tools/perf/util/util.h */ #ifndef zfree @@ -144,6 +176,22 @@ struct bpf_capabilities { __u32 btf_datasec:1; /* BPF_F_MMAPABLE is supported for arrays */ __u32 array_mmap:1; + /* BTF_FUNC_GLOBAL is supported */ + __u32 btf_func_global:1; +}; + +enum reloc_type { + RELO_LD64, + RELO_CALL, + RELO_DATA, + RELO_EXTERN, +}; + +struct reloc_desc { + enum reloc_type type; + int insn_idx; + int map_idx; + int sym_off; }; /* @@ -164,16 +212,7 @@ struct bpf_program { size_t insns_cnt, main_prog_cnt; enum bpf_prog_type type; - struct reloc_desc { - enum { - RELO_LD64, - RELO_CALL, - RELO_DATA, - } type; - int insn_idx; - int map_idx; - int sym_off; - } *reloc_desc; + struct reloc_desc *reloc_desc; int nr_reloc; int log_level; @@ -202,22 +241,51 @@ struct bpf_program { __u32 prog_flags; }; +struct bpf_struct_ops { + const char *tname; + const struct btf_type *type; + struct bpf_program **progs; + __u32 *kern_func_off; + /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */ + void *data; + /* e.g. struct bpf_struct_ops_tcp_congestion_ops in + * btf_vmlinux's format. + * struct bpf_struct_ops_tcp_congestion_ops { + * [... some other kernel fields ...] + * struct tcp_congestion_ops data; + * } + * kern_vdata-size == sizeof(struct bpf_struct_ops_tcp_congestion_ops) + * bpf_map__init_kern_struct_ops() will populate the "kern_vdata" + * from "data". + */ + void *kern_vdata; + __u32 type_id; +}; + +#define DATA_SEC ".data" +#define BSS_SEC ".bss" +#define RODATA_SEC ".rodata" +#define KCONFIG_SEC ".kconfig" +#define STRUCT_OPS_SEC ".struct_ops" + enum libbpf_map_type { LIBBPF_MAP_UNSPEC, LIBBPF_MAP_DATA, LIBBPF_MAP_BSS, LIBBPF_MAP_RODATA, + LIBBPF_MAP_KCONFIG, }; static const char * const libbpf_type_to_btf_name[] = { - [LIBBPF_MAP_DATA] = ".data", - [LIBBPF_MAP_BSS] = ".bss", - [LIBBPF_MAP_RODATA] = ".rodata", + [LIBBPF_MAP_DATA] = DATA_SEC, + [LIBBPF_MAP_BSS] = BSS_SEC, + [LIBBPF_MAP_RODATA] = RODATA_SEC, + [LIBBPF_MAP_KCONFIG] = KCONFIG_SEC, }; struct bpf_map { - int fd; char *name; + int fd; int sec_idx; size_t sec_offset; int map_ifindex; @@ -225,17 +293,37 @@ struct bpf_map { struct bpf_map_def def; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 btf_vmlinux_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; enum libbpf_map_type libbpf_type; + void *mmaped; + struct bpf_struct_ops *st_ops; char *pin_path; bool pinned; bool reused; }; -struct bpf_secdata { - void *rodata; - void *data; +enum extern_type { + EXT_UNKNOWN, + EXT_CHAR, + EXT_BOOL, + EXT_INT, + EXT_TRISTATE, + EXT_CHAR_ARR, +}; + +struct extern_desc { + const char *name; + int sym_idx; + int btf_id; + enum extern_type type; + int sz; + int align; + int data_off; + bool is_signed; + bool is_weak; + bool is_set; }; static LIST_HEAD(bpf_objects_list); @@ -250,11 +338,14 @@ struct bpf_object { struct bpf_map *maps; size_t nr_maps; size_t maps_cap; - struct bpf_secdata sections; + + char *kconfig; + struct extern_desc *externs; + int nr_extern; + int kconfig_map_idx; bool loaded; bool has_pseudo_calls; - bool relaxed_core_relocs; /* * Information when doing elf related work. Only valid if fd @@ -270,6 +361,7 @@ struct bpf_object { Elf_Data *data; Elf_Data *rodata; Elf_Data *bss; + Elf_Data *st_ops_data; size_t strtabidx; struct { GElf_Shdr shdr; @@ -279,9 +371,11 @@ struct bpf_object { int maps_shndx; int btf_maps_shndx; int text_shndx; + int symbols_shndx; int data_shndx; int rodata_shndx; int bss_shndx; + int st_ops_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -291,6 +385,10 @@ struct bpf_object { struct list_head list; struct btf *btf; + /* Parse and load BTF vmlinux if any of the programs in the object need + * it at load time. + */ + struct btf *btf_vmlinux; struct btf_ext *btf_ext; void *priv; @@ -509,6 +607,348 @@ static __u32 get_kernel_version(void) return KERNEL_VERSION(major, minor, patch); } +static const struct btf_member * +find_member_by_offset(const struct btf_type *t, __u32 bit_offset) +{ + struct btf_member *m; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + if (btf_member_bit_offset(t, i) == bit_offset) + return m; + } + + return NULL; +} + +static const struct btf_member * +find_member_by_name(const struct btf *btf, const struct btf_type *t, + const char *name) +{ + struct btf_member *m; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + if (!strcmp(btf__name_by_offset(btf, m->name_off), name)) + return m; + } + + return NULL; +} + +#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" +static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, + const char *name, __u32 kind); + +static int +find_struct_ops_kern_types(const struct btf *btf, const char *tname, + const struct btf_type **type, __u32 *type_id, + const struct btf_type **vtype, __u32 *vtype_id, + const struct btf_member **data_member) +{ + const struct btf_type *kern_type, *kern_vtype; + const struct btf_member *kern_data_member; + __s32 kern_vtype_id, kern_type_id; + __u32 i; + + kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + if (kern_type_id < 0) { + pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", + tname); + return kern_type_id; + } + kern_type = btf__type_by_id(btf, kern_type_id); + + /* Find the corresponding "map_value" type that will be used + * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example, + * find "struct bpf_struct_ops_tcp_congestion_ops" from the + * btf_vmlinux. + */ + kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX, + tname, BTF_KIND_STRUCT); + if (kern_vtype_id < 0) { + pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n", + STRUCT_OPS_VALUE_PREFIX, tname); + return kern_vtype_id; + } + kern_vtype = btf__type_by_id(btf, kern_vtype_id); + + /* Find "struct tcp_congestion_ops" from + * struct bpf_struct_ops_tcp_congestion_ops { + * [ ... ] + * struct tcp_congestion_ops data; + * } + */ + kern_data_member = btf_members(kern_vtype); + for (i = 0; i < btf_vlen(kern_vtype); i++, kern_data_member++) { + if (kern_data_member->type == kern_type_id) + break; + } + if (i == btf_vlen(kern_vtype)) { + pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n", + tname, STRUCT_OPS_VALUE_PREFIX, tname); + return -EINVAL; + } + + *type = kern_type; + *type_id = kern_type_id; + *vtype = kern_vtype; + *vtype_id = kern_vtype_id; + *data_member = kern_data_member; + + return 0; +} + +static bool bpf_map__is_struct_ops(const struct bpf_map *map) +{ + return map->def.type == BPF_MAP_TYPE_STRUCT_OPS; +} + +/* Init the map's fields that depend on kern_btf */ +static int bpf_map__init_kern_struct_ops(struct bpf_map *map, + const struct btf *btf, + const struct btf *kern_btf) +{ + const struct btf_member *member, *kern_member, *kern_data_member; + const struct btf_type *type, *kern_type, *kern_vtype; + __u32 i, kern_type_id, kern_vtype_id, kern_data_off; + struct bpf_struct_ops *st_ops; + void *data, *kern_data; + const char *tname; + int err; + + st_ops = map->st_ops; + type = st_ops->type; + tname = st_ops->tname; + err = find_struct_ops_kern_types(kern_btf, tname, + &kern_type, &kern_type_id, + &kern_vtype, &kern_vtype_id, + &kern_data_member); + if (err) + return err; + + pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n", + map->name, st_ops->type_id, kern_type_id, kern_vtype_id); + + map->def.value_size = kern_vtype->size; + map->btf_vmlinux_value_type_id = kern_vtype_id; + + st_ops->kern_vdata = calloc(1, kern_vtype->size); + if (!st_ops->kern_vdata) + return -ENOMEM; + + data = st_ops->data; + kern_data_off = kern_data_member->offset / 8; + kern_data = st_ops->kern_vdata + kern_data_off; + + member = btf_members(type); + for (i = 0; i < btf_vlen(type); i++, member++) { + const struct btf_type *mtype, *kern_mtype; + __u32 mtype_id, kern_mtype_id; + void *mdata, *kern_mdata; + __s64 msize, kern_msize; + __u32 moff, kern_moff; + __u32 kern_member_idx; + const char *mname; + + mname = btf__name_by_offset(btf, member->name_off); + kern_member = find_member_by_name(kern_btf, kern_type, mname); + if (!kern_member) { + pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n", + map->name, mname); + return -ENOTSUP; + } + + kern_member_idx = kern_member - btf_members(kern_type); + if (btf_member_bitfield_size(type, i) || + btf_member_bitfield_size(kern_type, kern_member_idx)) { + pr_warn("struct_ops init_kern %s: bitfield %s is not supported\n", + map->name, mname); + return -ENOTSUP; + } + + moff = member->offset / 8; + kern_moff = kern_member->offset / 8; + + mdata = data + moff; + kern_mdata = kern_data + kern_moff; + + mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id); + kern_mtype = skip_mods_and_typedefs(kern_btf, kern_member->type, + &kern_mtype_id); + if (BTF_INFO_KIND(mtype->info) != + BTF_INFO_KIND(kern_mtype->info)) { + pr_warn("struct_ops init_kern %s: Unmatched member type %s %u != %u(kernel)\n", + map->name, mname, BTF_INFO_KIND(mtype->info), + BTF_INFO_KIND(kern_mtype->info)); + return -ENOTSUP; + } + + if (btf_is_ptr(mtype)) { + struct bpf_program *prog; + + mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id); + kern_mtype = skip_mods_and_typedefs(kern_btf, + kern_mtype->type, + &kern_mtype_id); + if (!btf_is_func_proto(mtype) || + !btf_is_func_proto(kern_mtype)) { + pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n", + map->name, mname); + return -ENOTSUP; + } + + prog = st_ops->progs[i]; + if (!prog) { + pr_debug("struct_ops init_kern %s: func ptr %s is not set\n", + map->name, mname); + continue; + } + + prog->attach_btf_id = kern_type_id; + prog->expected_attach_type = kern_member_idx; + + st_ops->kern_func_off[i] = kern_data_off + kern_moff; + + pr_debug("struct_ops init_kern %s: func ptr %s is set to prog %s from data(+%u) to kern_data(+%u)\n", + map->name, mname, prog->name, moff, + kern_moff); + + continue; + } + + msize = btf__resolve_size(btf, mtype_id); + kern_msize = btf__resolve_size(kern_btf, kern_mtype_id); + if (msize < 0 || kern_msize < 0 || msize != kern_msize) { + pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n", + map->name, mname, (ssize_t)msize, + (ssize_t)kern_msize); + return -ENOTSUP; + } + + pr_debug("struct_ops init_kern %s: copy %s %u bytes from data(+%u) to kern_data(+%u)\n", + map->name, mname, (unsigned int)msize, + moff, kern_moff); + memcpy(kern_mdata, mdata, msize); + } + + return 0; +} + +static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) +{ + struct bpf_map *map; + size_t i; + int err; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + + if (!bpf_map__is_struct_ops(map)) + continue; + + err = bpf_map__init_kern_struct_ops(map, obj->btf, + obj->btf_vmlinux); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) +{ + const struct btf_type *type, *datasec; + const struct btf_var_secinfo *vsi; + struct bpf_struct_ops *st_ops; + const char *tname, *var_name; + __s32 type_id, datasec_id; + const struct btf *btf; + struct bpf_map *map; + __u32 i; + + if (obj->efile.st_ops_shndx == -1) + return 0; + + btf = obj->btf; + datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC, + BTF_KIND_DATASEC); + if (datasec_id < 0) { + pr_warn("struct_ops init: DATASEC %s not found\n", + STRUCT_OPS_SEC); + return -EINVAL; + } + + datasec = btf__type_by_id(btf, datasec_id); + vsi = btf_var_secinfos(datasec); + for (i = 0; i < btf_vlen(datasec); i++, vsi++) { + type = btf__type_by_id(obj->btf, vsi->type); + var_name = btf__name_by_offset(obj->btf, type->name_off); + + type_id = btf__resolve_type(obj->btf, vsi->type); + if (type_id < 0) { + pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n", + vsi->type, STRUCT_OPS_SEC); + return -EINVAL; + } + + type = btf__type_by_id(obj->btf, type_id); + tname = btf__name_by_offset(obj->btf, type->name_off); + if (!tname[0]) { + pr_warn("struct_ops init: anonymous type is not supported\n"); + return -ENOTSUP; + } + if (!btf_is_struct(type)) { + pr_warn("struct_ops init: %s is not a struct\n", tname); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map->sec_idx = obj->efile.st_ops_shndx; + map->sec_offset = vsi->offset; + map->name = strdup(var_name); + if (!map->name) + return -ENOMEM; + + map->def.type = BPF_MAP_TYPE_STRUCT_OPS; + map->def.key_size = sizeof(int); + map->def.value_size = type->size; + map->def.max_entries = 1; + + map->st_ops = calloc(1, sizeof(*map->st_ops)); + if (!map->st_ops) + return -ENOMEM; + st_ops = map->st_ops; + st_ops->data = malloc(type->size); + st_ops->progs = calloc(btf_vlen(type), sizeof(*st_ops->progs)); + st_ops->kern_func_off = malloc(btf_vlen(type) * + sizeof(*st_ops->kern_func_off)); + if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off) + return -ENOMEM; + + if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) { + pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n", + var_name, STRUCT_OPS_SEC); + return -EINVAL; + } + + memcpy(st_ops->data, + obj->efile.st_ops_data->d_buf + vsi->offset, + type->size); + st_ops->tname = tname; + st_ops->type = type; + st_ops->type_id = type_id; + + pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n", + tname, type_id, var_name, vsi->offset); + } + + return 0; +} + static struct bpf_object *bpf_object__new(const char *path, const void *obj_buf, size_t obj_buf_sz, @@ -550,6 +990,8 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.data_shndx = -1; obj->efile.rodata_shndx = -1; obj->efile.bss_shndx = -1; + obj->efile.st_ops_shndx = -1; + obj->kconfig_map_idx = -1; obj->kern_version = get_kernel_version(); obj->loaded = false; @@ -572,6 +1014,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.data = NULL; obj->efile.rodata = NULL; obj->efile.bss = NULL; + obj->efile.st_ops_data = NULL; zfree(&obj->efile.reloc_sects); obj->efile.nr_reloc_sects = 0; @@ -677,16 +1120,6 @@ bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size) return 0; } -static int compare_bpf_map(const void *_a, const void *_b) -{ - const struct bpf_map *a = _a; - const struct bpf_map *b = _b; - - if (a->sec_idx != b->sec_idx) - return a->sec_idx - b->sec_idx; - return a->sec_offset - b->sec_offset; -} - static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) { if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS || @@ -748,15 +1181,18 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name, *size = 0; if (!name) { return -EINVAL; - } else if (!strcmp(name, ".data")) { + } else if (!strcmp(name, DATA_SEC)) { if (obj->efile.data) *size = obj->efile.data->d_size; - } else if (!strcmp(name, ".bss")) { + } else if (!strcmp(name, BSS_SEC)) { if (obj->efile.bss) *size = obj->efile.bss->d_size; - } else if (!strcmp(name, ".rodata")) { + } else if (!strcmp(name, RODATA_SEC)) { if (obj->efile.rodata) *size = obj->efile.rodata->d_size; + } else if (!strcmp(name, STRUCT_OPS_SEC)) { + if (obj->efile.st_ops_data) + *size = obj->efile.st_ops_data->d_size; } else { ret = bpf_object_search_section_size(obj, name, &d_size); if (!ret) @@ -835,13 +1271,43 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return &obj->maps[obj->nr_maps++]; } +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +static char *internal_map_name(struct bpf_object *obj, + enum libbpf_map_type type) +{ + char map_name[BPF_OBJ_NAME_LEN], *p; + const char *sfx = libbpf_type_to_btf_name[type]; + int sfx_len = max((size_t)7, strlen(sfx)); + int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, + strlen(obj->name)); + + snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, + sfx_len, libbpf_type_to_btf_name[type]); + + /* sanitise map name to characters allowed by kernel */ + for (p = map_name; *p && p < map_name + sizeof(map_name); p++) + if (!isalnum(*p) && *p != '_' && *p != '.') + *p = '_'; + + return strdup(map_name); +} + static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, - int sec_idx, Elf_Data *data, void **data_buff) + int sec_idx, void *data, size_t data_sz) { - char map_name[BPF_OBJ_NAME_LEN]; struct bpf_map_def *def; struct bpf_map *map; + int err; map = bpf_object__add_map(obj); if (IS_ERR(map)) @@ -850,9 +1316,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, map->libbpf_type = type; map->sec_idx = sec_idx; map->sec_offset = 0; - snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, - libbpf_type_to_btf_name[type]); - map->name = strdup(map_name); + map->name = internal_map_name(obj, type); if (!map->name) { pr_warn("failed to alloc map name\n"); return -ENOMEM; @@ -861,25 +1325,29 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, def = &map->def; def->type = BPF_MAP_TYPE_ARRAY; def->key_size = sizeof(int); - def->value_size = data->d_size; + def->value_size = data_sz; def->max_entries = 1; - def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0; - if (obj->caps.array_mmap) - def->map_flags |= BPF_F_MMAPABLE; + def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG + ? BPF_F_RDONLY_PROG : 0; + def->map_flags |= BPF_F_MMAPABLE; pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", - map_name, map->sec_idx, map->sec_offset, def->map_flags); + map->name, map->sec_idx, map->sec_offset, def->map_flags); - if (data_buff) { - *data_buff = malloc(data->d_size); - if (!*data_buff) { - zfree(&map->name); - pr_warn("failed to alloc map content buffer\n"); - return -ENOMEM; - } - memcpy(*data_buff, data->d_buf, data->d_size); + map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (map->mmaped == MAP_FAILED) { + err = -errno; + map->mmaped = NULL; + pr_warn("failed to alloc map '%s' content buffer: %d\n", + map->name, err); + zfree(&map->name); + return err; } + if (data) + memcpy(map->mmaped, data, data_sz); + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); return 0; } @@ -888,37 +1356,332 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj) { int err; - if (!obj->caps.global_data) - return 0; /* * Populate obj->maps with libbpf internal maps. */ if (obj->efile.data_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, obj->efile.data_shndx, - obj->efile.data, - &obj->sections.data); + obj->efile.data->d_buf, + obj->efile.data->d_size); if (err) return err; } if (obj->efile.rodata_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, obj->efile.rodata_shndx, - obj->efile.rodata, - &obj->sections.rodata); + obj->efile.rodata->d_buf, + obj->efile.rodata->d_size); if (err) return err; } if (obj->efile.bss_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, obj->efile.bss_shndx, - obj->efile.bss, NULL); + NULL, + obj->efile.bss->d_size); if (err) return err; } return 0; } + +static struct extern_desc *find_extern_by_name(const struct bpf_object *obj, + const void *name) +{ + int i; + + for (i = 0; i < obj->nr_extern; i++) { + if (strcmp(obj->externs[i].name, name) == 0) + return &obj->externs[i]; + } + return NULL; +} + +static int set_ext_value_tri(struct extern_desc *ext, void *ext_val, + char value) +{ + switch (ext->type) { + case EXT_BOOL: + if (value == 'm') { + pr_warn("extern %s=%c should be tristate or char\n", + ext->name, value); + return -EINVAL; + } + *(bool *)ext_val = value == 'y' ? true : false; + break; + case EXT_TRISTATE: + if (value == 'y') + *(enum libbpf_tristate *)ext_val = TRI_YES; + else if (value == 'm') + *(enum libbpf_tristate *)ext_val = TRI_MODULE; + else /* value == 'n' */ + *(enum libbpf_tristate *)ext_val = TRI_NO; + break; + case EXT_CHAR: + *(char *)ext_val = value; + break; + case EXT_UNKNOWN: + case EXT_INT: + case EXT_CHAR_ARR: + default: + pr_warn("extern %s=%c should be bool, tristate, or char\n", + ext->name, value); + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int set_ext_value_str(struct extern_desc *ext, char *ext_val, + const char *value) +{ + size_t len; + + if (ext->type != EXT_CHAR_ARR) { + pr_warn("extern %s=%s should char array\n", ext->name, value); + return -EINVAL; + } + + len = strlen(value); + if (value[len - 1] != '"') { + pr_warn("extern '%s': invalid string config '%s'\n", + ext->name, value); + return -EINVAL; + } + + /* strip quotes */ + len -= 2; + if (len >= ext->sz) { + pr_warn("extern '%s': long string config %s of (%zu bytes) truncated to %d bytes\n", + ext->name, value, len, ext->sz - 1); + len = ext->sz - 1; + } + memcpy(ext_val, value + 1, len); + ext_val[len] = '\0'; + ext->is_set = true; + return 0; +} + +static int parse_u64(const char *value, __u64 *res) +{ + char *value_end; + int err; + + errno = 0; + *res = strtoull(value, &value_end, 0); + if (errno) { + err = -errno; + pr_warn("failed to parse '%s' as integer: %d\n", value, err); + return err; + } + if (*value_end) { + pr_warn("failed to parse '%s' as integer completely\n", value); + return -EINVAL; + } + return 0; +} + +static bool is_ext_value_in_range(const struct extern_desc *ext, __u64 v) +{ + int bit_sz = ext->sz * 8; + + if (ext->sz == 8) + return true; + + /* Validate that value stored in u64 fits in integer of `ext->sz` + * bytes size without any loss of information. If the target integer + * is signed, we rely on the following limits of integer type of + * Y bits and subsequent transformation: + * + * -2^(Y-1) <= X <= 2^(Y-1) - 1 + * 0 <= X + 2^(Y-1) <= 2^Y - 1 + * 0 <= X + 2^(Y-1) < 2^Y + * + * For unsigned target integer, check that all the (64 - Y) bits are + * zero. + */ + if (ext->is_signed) + return v + (1ULL << (bit_sz - 1)) < (1ULL << bit_sz); + else + return (v >> bit_sz) == 0; +} + +static int set_ext_value_num(struct extern_desc *ext, void *ext_val, + __u64 value) +{ + if (ext->type != EXT_INT && ext->type != EXT_CHAR) { + pr_warn("extern %s=%llu should be integer\n", + ext->name, (unsigned long long)value); + return -EINVAL; + } + if (!is_ext_value_in_range(ext, value)) { + pr_warn("extern %s=%llu value doesn't fit in %d bytes\n", + ext->name, (unsigned long long)value, ext->sz); + return -ERANGE; + } + switch (ext->sz) { + case 1: *(__u8 *)ext_val = value; break; + case 2: *(__u16 *)ext_val = value; break; + case 4: *(__u32 *)ext_val = value; break; + case 8: *(__u64 *)ext_val = value; break; + default: + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int bpf_object__process_kconfig_line(struct bpf_object *obj, + char *buf, void *data) +{ + struct extern_desc *ext; + char *sep, *value; + int len, err = 0; + void *ext_val; + __u64 num; + + if (strncmp(buf, "CONFIG_", 7)) + return 0; + + sep = strchr(buf, '='); + if (!sep) { + pr_warn("failed to parse '%s': no separator\n", buf); + return -EINVAL; + } + + /* Trim ending '\n' */ + len = strlen(buf); + if (buf[len - 1] == '\n') + buf[len - 1] = '\0'; + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) { + *sep = '='; + pr_warn("failed to parse '%s': no value\n", buf); + return -EINVAL; + } + + ext = find_extern_by_name(obj, buf); + if (!ext || ext->is_set) + return 0; + + ext_val = data + ext->data_off; + value = sep + 1; + + switch (*value) { + case 'y': case 'n': case 'm': + err = set_ext_value_tri(ext, ext_val, *value); + break; + case '"': + err = set_ext_value_str(ext, ext_val, value); + break; + default: + /* assume integer */ + err = parse_u64(value, &num); + if (err) { + pr_warn("extern %s=%s should be integer\n", + ext->name, value); + return err; + } + err = set_ext_value_num(ext, ext_val, num); + break; + } + if (err) + return err; + pr_debug("extern %s=%s\n", ext->name, value); + return 0; +} + +static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) +{ + char buf[PATH_MAX]; + struct utsname uts; + int len, err = 0; + gzFile file; + + uname(&uts); + len = snprintf(buf, PATH_MAX, "/boot/config-%s", uts.release); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + /* gzopen also accepts uncompressed files. */ + file = gzopen(buf, "r"); + if (!file) + file = gzopen("/proc/config.gz", "r"); + + if (!file) { + pr_warn("failed to open system Kconfig\n"); + return -ENOENT; + } + + while (gzgets(file, buf, sizeof(buf))) { + err = bpf_object__process_kconfig_line(obj, buf, data); + if (err) { + pr_warn("error parsing system Kconfig line '%s': %d\n", + buf, err); + goto out; + } + } + +out: + gzclose(file); + return err; +} + +static int bpf_object__read_kconfig_mem(struct bpf_object *obj, + const char *config, void *data) +{ + char buf[PATH_MAX]; + int err = 0; + FILE *file; + + file = fmemopen((void *)config, strlen(config), "r"); + if (!file) { + err = -errno; + pr_warn("failed to open in-memory Kconfig: %d\n", err); + return err; + } + + while (fgets(buf, sizeof(buf), file)) { + err = bpf_object__process_kconfig_line(obj, buf, data); + if (err) { + pr_warn("error parsing in-memory Kconfig line '%s': %d\n", + buf, err); + break; + } + } + + fclose(file); + return err; +} + +static int bpf_object__init_kconfig_map(struct bpf_object *obj) +{ + struct extern_desc *last_ext; + size_t map_sz; + int err; + + if (obj->nr_extern == 0) + return 0; + + last_ext = &obj->externs[obj->nr_extern - 1]; + map_sz = last_ext->data_off + last_ext->sz; + + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG, + obj->efile.symbols_shndx, + NULL, map_sz); + if (err) + return err; + + obj->kconfig_map_idx = obj->nr_maps - 1; + + return 0; +} + static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { Elf_Data *symbols = obj->efile.symbols; @@ -1060,6 +1823,20 @@ skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) return t; } +static const struct btf_type * +resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t; + + t = skip_mods_and_typedefs(btf, id, NULL); + if (!btf_is_ptr(t)) + return NULL; + + t = skip_mods_and_typedefs(btf, t->type, res_id); + + return btf_is_func_proto(t) ? t : NULL; +} + /* * Fetch integer attribute of BTF map definition. Such attributes are * represented using a pointer to an array, in which dimensionality of array @@ -1242,15 +2019,15 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { - pr_warn("map '%s': can't determine key size for type [%u]: %lld.\n", - map_name, t->type, sz); + pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found key [%u], sz = %lld.\n", - map_name, t->type, sz); + pr_debug("map '%s': found key [%u], sz = %zd.\n", + map_name, t->type, (ssize_t)sz); if (map->def.key_size && map->def.key_size != sz) { - pr_warn("map '%s': conflicting key size %u != %lld.\n", - map_name, map->def.key_size, sz); + pr_warn("map '%s': conflicting key size %u != %zd.\n", + map_name, map->def.key_size, (ssize_t)sz); return -EINVAL; } map->def.key_size = sz; @@ -1285,15 +2062,15 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { - pr_warn("map '%s': can't determine value size for type [%u]: %lld.\n", - map_name, t->type, sz); + pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found value [%u], sz = %lld.\n", - map_name, t->type, sz); + pr_debug("map '%s': found value [%u], sz = %zd.\n", + map_name, t->type, (ssize_t)sz); if (map->def.value_size && map->def.value_size != sz) { - pr_warn("map '%s': conflicting value size %u != %lld.\n", - map_name, map->def.value_size, sz); + pr_warn("map '%s': conflicting value size %u != %zd.\n", + map_name, map->def.value_size, (ssize_t)sz); return -EINVAL; } map->def.value_size = sz; @@ -1393,28 +2170,24 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, return 0; } -static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps, - const char *pin_root_path) +static int bpf_object__init_maps(struct bpf_object *obj, + const struct bpf_object_open_opts *opts) { - bool strict = !relaxed_maps; + const char *pin_root_path; + bool strict; int err; - err = bpf_object__init_user_maps(obj, strict); - if (err) - return err; - - err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path); - if (err) - return err; + strict = !OPTS_GET(opts, relaxed_maps, false); + pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - err = bpf_object__init_global_data_maps(obj); + err = bpf_object__init_user_maps(obj, strict); + err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + err = err ?: bpf_object__init_global_data_maps(obj); + err = err ?: bpf_object__init_kconfig_map(obj); + err = err ?: bpf_object__init_struct_ops_maps(obj); if (err) return err; - if (obj->nr_maps) { - qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), - compare_bpf_map); - } return 0; } @@ -1438,13 +2211,14 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) static void bpf_object__sanitize_btf(struct bpf_object *obj) { + bool has_func_global = obj->caps.btf_func_global; bool has_datasec = obj->caps.btf_datasec; bool has_func = obj->caps.btf_func; struct btf *btf = obj->btf; struct btf_type *t; int i, j, vlen; - if (!obj->btf || (has_func && has_datasec)) + if (!obj->btf || (has_func && has_datasec && has_func_global)) return; for (i = 1; i <= btf__get_nr_types(btf); i++) { @@ -1492,6 +2266,9 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) } else if (!has_func && btf_is_func(t)) { /* replace FUNC with TYPEDEF */ t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); + } else if (!has_func_global && btf_is_func(t)) { + /* replace BTF_FUNC_GLOBAL with BTF_FUNC_STATIC */ + t->info = BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0); } } } @@ -1509,28 +2286,27 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) { - return obj->efile.btf_maps_shndx >= 0; + return obj->efile.btf_maps_shndx >= 0 || + obj->efile.st_ops_shndx >= 0 || + obj->nr_extern > 0; } static int bpf_object__init_btf(struct bpf_object *obj, Elf_Data *btf_data, Elf_Data *btf_ext_data) { - bool btf_required = bpf_object__is_btf_mandatory(obj); - int err = 0; + int err = -ENOENT; if (btf_data) { obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); if (IS_ERR(obj->btf)) { + err = PTR_ERR(obj->btf); + obj->btf = NULL; pr_warn("Error loading ELF section %s: %d.\n", BTF_ELF_SEC, err); goto out; } - err = btf__finalize_data(obj, obj->btf); - if (err) { - pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); - goto out; - } + err = 0; } if (btf_ext_data) { if (!obj->btf) { @@ -1548,22 +2324,72 @@ static int bpf_object__init_btf(struct bpf_object *obj, } } out: - if (err || IS_ERR(obj->btf)) { - if (btf_required) - err = err ? : PTR_ERR(obj->btf); - else - err = 0; - if (!IS_ERR_OR_NULL(obj->btf)) - btf__free(obj->btf); - obj->btf = NULL; + if (err && bpf_object__is_btf_mandatory(obj)) { + pr_warn("BTF is required, but is missing or corrupted.\n"); + return err; } - if (btf_required && !obj->btf) { + return 0; +} + +static int bpf_object__finalize_btf(struct bpf_object *obj) +{ + int err; + + if (!obj->btf) + return 0; + + err = btf__finalize_data(obj, obj->btf); + if (!err) + return 0; + + pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + + if (bpf_object__is_btf_mandatory(obj)) { pr_warn("BTF is required, but is missing or corrupted.\n"); - return err == 0 ? -ENOENT : err; + return -ENOENT; } return 0; } +static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog) +{ + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) + return true; + + /* BPF_PROG_TYPE_TRACING programs which do not attach to other programs + * also need vmlinux BTF + */ + if (prog->type == BPF_PROG_TYPE_TRACING && !prog->attach_prog_fd) + return true; + + return false; +} + +static int bpf_object__load_vmlinux_btf(struct bpf_object *obj) +{ + struct bpf_program *prog; + int err; + + bpf_object__for_each_program(prog, obj) { + if (libbpf_prog_needs_vmlinux_btf(prog)) { + obj->btf_vmlinux = libbpf_find_kernel_btf(); + if (IS_ERR(obj->btf_vmlinux)) { + err = PTR_ERR(obj->btf_vmlinux); + pr_warn("Error loading vmlinux BTF: %d\n", err); + obj->btf_vmlinux = NULL; + return err; + } + return 0; + } + } + + return 0; +} + static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) { int err = 0; @@ -1592,8 +2418,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) return 0; } -static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, - const char *pin_root_path) +static int bpf_object__elf_collect(struct bpf_object *obj) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; @@ -1665,6 +2490,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, return -LIBBPF_ERRNO__FORMAT; } obj->efile.symbols = data; + obj->efile.symbols_shndx = idx; obj->efile.strtabidx = sh.sh_link; } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { if (sh.sh_flags & SHF_EXECINSTR) { @@ -1683,12 +2509,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, name, obj->path, cp); return err; } - } else if (strcmp(name, ".data") == 0) { + } else if (strcmp(name, DATA_SEC) == 0) { obj->efile.data = data; obj->efile.data_shndx = idx; - } else if (strcmp(name, ".rodata") == 0) { + } else if (strcmp(name, RODATA_SEC) == 0) { obj->efile.rodata = data; obj->efile.rodata_shndx = idx; + } else if (strcmp(name, STRUCT_OPS_SEC) == 0) { + obj->efile.st_ops_data = data; + obj->efile.st_ops_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } @@ -1698,7 +2527,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, int sec = sh.sh_info; /* points to other section */ /* Only do relo for section with exec instructions */ - if (!section_have_execinstr(obj, sec)) { + if (!section_have_execinstr(obj, sec) && + strcmp(name, ".rel" STRUCT_OPS_SEC)) { pr_debug("skip relo %s(%d) for section(%d)\n", name, idx, sec); continue; @@ -1716,7 +2546,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, obj->efile.reloc_sects[nr_sects].shdr = sh; obj->efile.reloc_sects[nr_sects].data = data; - } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + } else if (sh.sh_type == SHT_NOBITS && + strcmp(name, BSS_SEC) == 0) { obj->efile.bss = data; obj->efile.bss_shndx = idx; } else { @@ -1728,14 +2559,217 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, pr_warn("Corrupted ELF file: index of strtab invalid\n"); return -LIBBPF_ERRNO__FORMAT; } - err = bpf_object__init_btf(obj, btf_data, btf_ext_data); - if (!err) - err = bpf_object__init_maps(obj, relaxed_maps, pin_root_path); - if (!err) - err = bpf_object__sanitize_and_load_btf(obj); - if (!err) - err = bpf_object__init_prog_names(obj); - return err; + return bpf_object__init_btf(obj, btf_data, btf_ext_data); +} + +static bool sym_is_extern(const GElf_Sym *sym) +{ + int bind = GELF_ST_BIND(sym->st_info); + /* externs are symbols w/ type=NOTYPE, bind=GLOBAL|WEAK, section=UND */ + return sym->st_shndx == SHN_UNDEF && + (bind == STB_GLOBAL || bind == STB_WEAK) && + GELF_ST_TYPE(sym->st_info) == STT_NOTYPE; +} + +static int find_extern_btf_id(const struct btf *btf, const char *ext_name) +{ + const struct btf_type *t; + const char *var_name; + int i, n; + + if (!btf) + return -ESRCH; + + n = btf__get_nr_types(btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(btf, i); + + if (!btf_is_var(t)) + continue; + + var_name = btf__name_by_offset(btf, t->name_off); + if (strcmp(var_name, ext_name)) + continue; + + if (btf_var(t)->linkage != BTF_VAR_GLOBAL_EXTERN) + return -EINVAL; + + return i; + } + + return -ENOENT; +} + +static enum extern_type find_extern_type(const struct btf *btf, int id, + bool *is_signed) +{ + const struct btf_type *t; + const char *name; + + t = skip_mods_and_typedefs(btf, id, NULL); + name = btf__name_by_offset(btf, t->name_off); + + if (is_signed) + *is_signed = false; + switch (btf_kind(t)) { + case BTF_KIND_INT: { + int enc = btf_int_encoding(t); + + if (enc & BTF_INT_BOOL) + return t->size == 1 ? EXT_BOOL : EXT_UNKNOWN; + if (is_signed) + *is_signed = enc & BTF_INT_SIGNED; + if (t->size == 1) + return EXT_CHAR; + if (t->size < 1 || t->size > 8 || (t->size & (t->size - 1))) + return EXT_UNKNOWN; + return EXT_INT; + } + case BTF_KIND_ENUM: + if (t->size != 4) + return EXT_UNKNOWN; + if (strcmp(name, "libbpf_tristate")) + return EXT_UNKNOWN; + return EXT_TRISTATE; + case BTF_KIND_ARRAY: + if (btf_array(t)->nelems == 0) + return EXT_UNKNOWN; + if (find_extern_type(btf, btf_array(t)->type, NULL) != EXT_CHAR) + return EXT_UNKNOWN; + return EXT_CHAR_ARR; + default: + return EXT_UNKNOWN; + } +} + +static int cmp_externs(const void *_a, const void *_b) +{ + const struct extern_desc *a = _a; + const struct extern_desc *b = _b; + + /* descending order by alignment requirements */ + if (a->align != b->align) + return a->align > b->align ? -1 : 1; + /* ascending order by size, within same alignment class */ + if (a->sz != b->sz) + return a->sz < b->sz ? -1 : 1; + /* resolve ties by name */ + return strcmp(a->name, b->name); +} + +static int bpf_object__collect_externs(struct bpf_object *obj) +{ + const struct btf_type *t; + struct extern_desc *ext; + int i, n, off, btf_id; + struct btf_type *sec; + const char *ext_name; + Elf_Scn *scn; + GElf_Shdr sh; + + if (!obj->efile.symbols) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.symbols_shndx); + if (!scn) + return -LIBBPF_ERRNO__FORMAT; + if (gelf_getshdr(scn, &sh) != &sh) + return -LIBBPF_ERRNO__FORMAT; + n = sh.sh_size / sh.sh_entsize; + + pr_debug("looking for externs among %d symbols...\n", n); + for (i = 0; i < n; i++) { + GElf_Sym sym; + + if (!gelf_getsym(obj->efile.symbols, i, &sym)) + return -LIBBPF_ERRNO__FORMAT; + if (!sym_is_extern(&sym)) + continue; + ext_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!ext_name || !ext_name[0]) + continue; + + ext = obj->externs; + ext = reallocarray(ext, obj->nr_extern + 1, sizeof(*ext)); + if (!ext) + return -ENOMEM; + obj->externs = ext; + ext = &ext[obj->nr_extern]; + memset(ext, 0, sizeof(*ext)); + obj->nr_extern++; + + ext->btf_id = find_extern_btf_id(obj->btf, ext_name); + if (ext->btf_id <= 0) { + pr_warn("failed to find BTF for extern '%s': %d\n", + ext_name, ext->btf_id); + return ext->btf_id; + } + t = btf__type_by_id(obj->btf, ext->btf_id); + ext->name = btf__name_by_offset(obj->btf, t->name_off); + ext->sym_idx = i; + ext->is_weak = GELF_ST_BIND(sym.st_info) == STB_WEAK; + ext->sz = btf__resolve_size(obj->btf, t->type); + if (ext->sz <= 0) { + pr_warn("failed to resolve size of extern '%s': %d\n", + ext_name, ext->sz); + return ext->sz; + } + ext->align = btf__align_of(obj->btf, t->type); + if (ext->align <= 0) { + pr_warn("failed to determine alignment of extern '%s': %d\n", + ext_name, ext->align); + return -EINVAL; + } + ext->type = find_extern_type(obj->btf, t->type, + &ext->is_signed); + if (ext->type == EXT_UNKNOWN) { + pr_warn("extern '%s' type is unsupported\n", ext_name); + return -ENOTSUP; + } + } + pr_debug("collected %d externs total\n", obj->nr_extern); + + if (!obj->nr_extern) + return 0; + + /* sort externs by (alignment, size, name) and calculate their offsets + * within a map */ + qsort(obj->externs, obj->nr_extern, sizeof(*ext), cmp_externs); + off = 0; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + ext->data_off = roundup(off, ext->align); + off = ext->data_off + ext->sz; + pr_debug("extern #%d: symbol %d, off %u, name %s\n", + i, ext->sym_idx, ext->data_off, ext->name); + } + + btf_id = btf__find_by_name(obj->btf, KCONFIG_SEC); + if (btf_id <= 0) { + pr_warn("no BTF info found for '%s' datasec\n", KCONFIG_SEC); + return -ESRCH; + } + + sec = (struct btf_type *)btf__type_by_id(obj->btf, btf_id); + sec->size = off; + n = btf_vlen(sec); + for (i = 0; i < n; i++) { + struct btf_var_secinfo *vs = btf_var_secinfos(sec) + i; + + t = btf__type_by_id(obj->btf, vs->type); + ext_name = btf__name_by_offset(obj->btf, t->name_off); + ext = find_extern_by_name(obj, ext_name); + if (!ext) { + pr_warn("failed to find extern definition for BTF var '%s'\n", + ext_name); + return -ESRCH; + } + vs->offset = ext->data_off; + btf_var(t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + } + + return 0; } static struct bpf_program * @@ -1765,6 +2799,19 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, return NULL; } +struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + if (!strcmp(prog->name, name)) + return prog; + } + return NULL; +} + static bool bpf_object__shndx_is_data(const struct bpf_object *obj, int shndx) { @@ -1789,6 +2836,8 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) return LIBBPF_MAP_BSS; else if (shndx == obj->efile.rodata_shndx) return LIBBPF_MAP_RODATA; + else if (shndx == obj->efile.symbols_shndx) + return LIBBPF_MAP_KCONFIG; else return LIBBPF_MAP_UNSPEC; } @@ -1817,7 +2866,8 @@ static int bpf_program__record_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__RELOC; } if (sym->st_value % 8) { - pr_warn("bad call relo offset: %llu\n", (__u64)sym->st_value); + pr_warn("bad call relo offset: %zu\n", + (size_t)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_CALL; @@ -1832,6 +2882,30 @@ static int bpf_program__record_reloc(struct bpf_program *prog, insn_idx, insn->code); return -LIBBPF_ERRNO__RELOC; } + + if (sym_is_extern(sym)) { + int sym_idx = GELF_R_SYM(rel->r_info); + int i, n = obj->nr_extern; + struct extern_desc *ext; + + for (i = 0; i < n; i++) { + ext = &obj->externs[i]; + if (ext->sym_idx == sym_idx) + break; + } + if (i >= n) { + pr_warn("extern relo failed to find extern for sym %d\n", + sym_idx); + return -LIBBPF_ERRNO__RELOC; + } + pr_debug("found extern #%d '%s' (sym %d, off %u) for insn %u\n", + i, ext->name, ext->sym_idx, ext->data_off, insn_idx); + reloc_desc->type = RELO_EXTERN; + reloc_desc->insn_idx = insn_idx; + reloc_desc->sym_off = ext->data_off; + return 0; + } + if (!shdr_idx || shdr_idx >= SHN_LORESERVE) { pr_warn("invalid relo for \'%s\' in special section 0x%x; forgot to initialize global var?..\n", name, shdr_idx); @@ -1859,8 +2933,8 @@ static int bpf_program__record_reloc(struct bpf_program *prog, break; } if (map_idx >= nr_maps) { - pr_warn("map relo failed to find map for sec %u, off %llu\n", - shdr_idx, (__u64)sym->st_value); + pr_warn("map relo failed to find map for sec %u, off %zu\n", + shdr_idx, (size_t)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_LD64; @@ -1875,11 +2949,6 @@ static int bpf_program__record_reloc(struct bpf_program *prog, pr_warn("bad data relo against section %u\n", shdr_idx); return -LIBBPF_ERRNO__RELOC; } - if (!obj->caps.global_data) { - pr_warn("relocation: kernel does not support global \'%s\' variable access in insns[%d]\n", - name, insn_idx); - return -LIBBPF_ERRNO__RELOC; - } for (map_idx = 0; map_idx < nr_maps; map_idx++) { map = &obj->maps[map_idx]; if (map->libbpf_type != type) @@ -1941,9 +3010,9 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name) ? : "<?>"; - pr_debug("relo for shdr %u, symb %llu, value %llu, type %d, bind %d, name %d (\'%s\'), insn %u\n", - (__u32)sym.st_shndx, (__u64)GELF_R_SYM(rel.r_info), - (__u64)sym.st_value, GELF_ST_TYPE(sym.st_info), + pr_debug("relo for shdr %u, symb %zu, value %zu, type %d, bind %d, name %d (\'%s\'), insn %u\n", + (__u32)sym.st_shndx, (size_t)GELF_R_SYM(rel.r_info), + (size_t)sym.st_value, GELF_ST_TYPE(sym.st_info), GELF_ST_BIND(sym.st_info), sym.st_name, name, insn_idx); @@ -1961,8 +3030,12 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) __u32 key_type_id = 0, value_type_id = 0; int ret; - /* if it's BTF-defined map, we don't need to search for type IDs */ - if (map->sec_idx == obj->efile.btf_maps_shndx) + /* if it's BTF-defined map, we don't need to search for type IDs. + * For struct_ops map, it does not need btf_key_type_id and + * btf_value_type_id. + */ + if (map->sec_idx == obj->efile.btf_maps_shndx || + bpf_map__is_struct_ops(map)) return 0; if (!bpf_map__is_internal(map)) { @@ -2166,6 +3239,32 @@ static int bpf_object__probe_btf_func(struct bpf_object *obj) return 0; } +static int bpf_object__probe_btf_func_global(struct bpf_object *obj) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_func_global = 1; + close(btf_fd); + return 1; + } + + return 0; +} + static int bpf_object__probe_btf_datasec(struct bpf_object *obj) { static const char strs[] = "\0x\0.data"; @@ -2221,6 +3320,7 @@ bpf_object__probe_caps(struct bpf_object *obj) bpf_object__probe_name, bpf_object__probe_global_data, bpf_object__probe_btf_func, + bpf_object__probe_btf_func_global, bpf_object__probe_btf_datasec, bpf_object__probe_array_mmap, }; @@ -2298,29 +3398,35 @@ bpf_object__reuse_map(struct bpf_map *map) static int bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) { + enum libbpf_map_type map_type = map->libbpf_type; char *cp, errmsg[STRERR_BUFSIZE]; int err, zero = 0; - __u8 *data; - /* Nothing to do here since kernel already zero-initializes .bss map. */ - if (map->libbpf_type == LIBBPF_MAP_BSS) + /* kernel already zero-initializes .bss map. */ + if (map_type == LIBBPF_MAP_BSS) return 0; - data = map->libbpf_type == LIBBPF_MAP_DATA ? - obj->sections.data : obj->sections.rodata; + err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0); + if (err) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error setting initial map(%s) contents: %s\n", + map->name, cp); + return err; + } - err = bpf_map_update_elem(map->fd, &zero, data, 0); - /* Freeze .rodata map as read-only from syscall side. */ - if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + /* Freeze .rodata and .kconfig map as read-only from syscall side. */ + if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG) { err = bpf_map_freeze(map->fd); if (err) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("Error freezing map(%s) as read-only: %s\n", map->name, cp); - err = 0; + return err; } } - return err; + return 0; } static int @@ -2381,6 +3487,9 @@ bpf_object__create_maps(struct bpf_object *obj) if (bpf_map_type__is_map_in_map(def->type) && map->inner_map_fd >= 0) create_attr.inner_map_fd = map->inner_map_fd; + if (bpf_map__is_struct_ops(map)) + create_attr.btf_vmlinux_value_type_id = + map->btf_vmlinux_value_type_id; if (obj->btf && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); @@ -2411,6 +3520,7 @@ err_out: cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("failed to create map (name: '%s'): %s(%d)\n", map->name, cp, err); + pr_perm_msg(err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; @@ -2536,6 +3646,21 @@ static bool str_is_empty(const char *s) return !s || !s[0]; } +static bool is_flex_arr(const struct btf *btf, + const struct bpf_core_accessor *acc, + const struct btf_array *arr) +{ + const struct btf_type *t; + + /* not a flexible array, if not inside a struct or has non-zero size */ + if (!acc->name || arr->nelems > 0) + return false; + + /* has to be the last member of enclosing struct */ + t = btf__type_by_id(btf, acc->type_id); + return acc->idx == btf_vlen(t) - 1; +} + /* * Turn bpf_field_reloc into a low- and high-level spec representation, * validating correctness along the way, as well as calculating resulting @@ -2573,6 +3698,7 @@ static int bpf_core_spec_parse(const struct btf *btf, struct bpf_core_spec *spec) { int access_idx, parsed_len, i; + struct bpf_core_accessor *acc; const struct btf_type *t; const char *name; __u32 id; @@ -2620,6 +3746,7 @@ static int bpf_core_spec_parse(const struct btf *btf, return -EINVAL; access_idx = spec->raw_spec[i]; + acc = &spec->spec[spec->len]; if (btf_is_composite(t)) { const struct btf_member *m; @@ -2637,18 +3764,23 @@ static int bpf_core_spec_parse(const struct btf *btf, if (str_is_empty(name)) return -EINVAL; - spec->spec[spec->len].type_id = id; - spec->spec[spec->len].idx = access_idx; - spec->spec[spec->len].name = name; + acc->type_id = id; + acc->idx = access_idx; + acc->name = name; spec->len++; } id = m->type; } else if (btf_is_array(t)) { const struct btf_array *a = btf_array(t); + bool flex; t = skip_mods_and_typedefs(btf, a->type, &id); - if (!t || access_idx >= a->nelems) + if (!t) + return -EINVAL; + + flex = is_flex_arr(btf, acc - 1, a); + if (!flex && access_idx >= a->nelems) return -EINVAL; spec->spec[spec->len].type_id = id; @@ -2743,7 +3875,9 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, if (strncmp(local_name, targ_name, local_essent_len) == 0) { pr_debug("[%d] %s: found candidate [%d] %s\n", local_type_id, local_name, i, targ_name); - new_ids = realloc(cand_ids->data, cand_ids->len + 1); + new_ids = reallocarray(cand_ids->data, + cand_ids->len + 1, + sizeof(*cand_ids->data)); if (!new_ids) { err = -ENOMEM; goto err_out; @@ -2953,12 +4087,14 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, */ if (i > 0) { const struct btf_array *a; + bool flex; if (!btf_is_array(targ_type)) return 0; a = btf_array(targ_type); - if (local_acc->idx >= a->nelems) + flex = is_flex_arr(targ_btf, targ_acc - 1, a); + if (!flex && local_acc->idx >= a->nelems) return 0; if (!skip_mods_and_typedefs(targ_btf, a->type, &targ_id)) @@ -3109,25 +4245,38 @@ static int bpf_core_calc_field_relo(const struct bpf_program *prog, */ static int bpf_core_reloc_insn(struct bpf_program *prog, const struct bpf_field_reloc *relo, + int relo_idx, const struct bpf_core_spec *local_spec, const struct bpf_core_spec *targ_spec) { - bool failed = false, validate = true; __u32 orig_val, new_val; struct bpf_insn *insn; + bool validate = true; int insn_idx, err; __u8 class; if (relo->insn_off % sizeof(struct bpf_insn)) return -EINVAL; insn_idx = relo->insn_off / sizeof(struct bpf_insn); + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); if (relo->kind == BPF_FIELD_EXISTS) { orig_val = 1; /* can't generate EXISTS relo w/o local field */ new_val = targ_spec ? 1 : 0; } else if (!targ_spec) { - failed = true; - new_val = (__u32)-1; + pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n", + bpf_program__title(prog, false), relo_idx, insn_idx); + insn->code = BPF_JMP | BPF_CALL; + insn->dst_reg = 0; + insn->src_reg = 0; + insn->off = 0; + /* if this instruction is reachable (not a dead code), + * verifier will complain with the following message: + * invalid func unknown#195896080 + */ + insn->imm = 195896080; /* => 0xbad2310 => "bad relo" */ + return 0; } else { err = bpf_core_calc_field_relo(prog, relo, local_spec, &orig_val, &validate); @@ -3139,26 +4288,47 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, return err; } - insn = &prog->insns[insn_idx]; - class = BPF_CLASS(insn->code); - - if (class == BPF_ALU || class == BPF_ALU64) { + switch (class) { + case BPF_ALU: + case BPF_ALU64: if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; - if (!failed && validate && insn->imm != orig_val) { - pr_warn("prog '%s': unexpected insn #%d value: got %u, exp %u -> %u\n", - bpf_program__title(prog, false), insn_idx, - insn->imm, orig_val, new_val); + if (validate && insn->imm != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, insn->imm, orig_val, new_val); return -EINVAL; } orig_val = insn->imm; insn->imm = new_val; - pr_debug("prog '%s': patched insn #%d (ALU/ALU64)%s imm %u -> %u\n", - bpf_program__title(prog, false), insn_idx, - failed ? " w/ failed reloc" : "", orig_val, new_val); - } else { - pr_warn("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", - bpf_program__title(prog, false), + pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n", + bpf_program__title(prog, false), relo_idx, insn_idx, + orig_val, new_val); + break; + case BPF_LDX: + case BPF_ST: + case BPF_STX: + if (validate && insn->off != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LD/LDX/ST/STX) value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, insn->off, orig_val, new_val); + return -EINVAL; + } + if (new_val > SHRT_MAX) { + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, new_val); + return -ERANGE; + } + orig_val = insn->off; + insn->off = new_val; + pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n", + bpf_program__title(prog, false), relo_idx, insn_idx, + orig_val, new_val); + break; + default: + pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), relo_idx, insn_idx, insn->code, insn->src_reg, insn->dst_reg, insn->off, insn->imm); return -EINVAL; @@ -3167,92 +4337,6 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, return 0; } -static struct btf *btf_load_raw(const char *path) -{ - struct btf *btf; - size_t read_cnt; - struct stat st; - void *data; - FILE *f; - - if (stat(path, &st)) - return ERR_PTR(-errno); - - data = malloc(st.st_size); - if (!data) - return ERR_PTR(-ENOMEM); - - f = fopen(path, "rb"); - if (!f) { - btf = ERR_PTR(-errno); - goto cleanup; - } - - read_cnt = fread(data, 1, st.st_size, f); - fclose(f); - if (read_cnt < st.st_size) { - btf = ERR_PTR(-EBADF); - goto cleanup; - } - - btf = btf__new(data, read_cnt); - -cleanup: - free(data); - return btf; -} - -/* - * Probe few well-known locations for vmlinux kernel image and try to load BTF - * data out of it to use for target BTF. - */ -static struct btf *bpf_core_find_kernel_btf(void) -{ - struct { - const char *path_fmt; - bool raw_btf; - } locations[] = { - /* try canonical vmlinux BTF through sysfs first */ - { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, - /* fall back to trying to find vmlinux ELF on disk otherwise */ - { "/boot/vmlinux-%1$s" }, - { "/lib/modules/%1$s/vmlinux-%1$s" }, - { "/lib/modules/%1$s/build/vmlinux" }, - { "/usr/lib/modules/%1$s/kernel/vmlinux" }, - { "/usr/lib/debug/boot/vmlinux-%1$s" }, - { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, - { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, - }; - char path[PATH_MAX + 1]; - struct utsname buf; - struct btf *btf; - int i; - - uname(&buf); - - for (i = 0; i < ARRAY_SIZE(locations); i++) { - snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); - - if (access(path, R_OK)) - continue; - - if (locations[i].raw_btf) - btf = btf_load_raw(path); - else - btf = btf__parse_elf(path, NULL); - - pr_debug("loading kernel BTF '%s': %ld\n", - path, IS_ERR(btf) ? PTR_ERR(btf) : 0); - if (IS_ERR(btf)) - continue; - - return btf; - } - - pr_warn("failed to find valid kernel BTF\n"); - return ERR_PTR(-ESRCH); -} - /* Output spec definition in the format: * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b @@ -3443,24 +4527,33 @@ static int bpf_core_reloc_field(struct bpf_program *prog, } /* - * For BPF_FIELD_EXISTS relo or when relaxed CO-RE reloc mode is - * requested, it's expected that we might not find any candidates. - * In this case, if field wasn't found in any candidate, the list of - * candidates shouldn't change at all, we'll just handle relocating - * appropriately, depending on relo's kind. + * For BPF_FIELD_EXISTS relo or when used BPF program has field + * existence checks or kernel version/config checks, it's expected + * that we might not find any candidates. In this case, if field + * wasn't found in any candidate, the list of candidates shouldn't + * change at all, we'll just handle relocating appropriately, + * depending on relo's kind. */ if (j > 0) cand_ids->len = j; - if (j == 0 && !prog->obj->relaxed_core_relocs && - relo->kind != BPF_FIELD_EXISTS) { - pr_warn("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", - prog_name, relo_idx, local_id, local_name, spec_str); - return -ESRCH; - } + /* + * If no candidates were found, it might be both a programmer error, + * as well as expected case, depending whether instruction w/ + * relocation is guarded in some way that makes it unreachable (dead + * code) if relocation can't be resolved. This is handled in + * bpf_core_reloc_insn() uniformly by replacing that instruction with + * BPF helper call insn (using invalid helper ID). If that instruction + * is indeed unreachable, then it will be ignored and eliminated by + * verifier. If it was an error, then verifier will complain and point + * to a specific instruction number in its log. + */ + if (j == 0) + pr_debug("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); /* bpf_core_reloc_insn should know how to handle missing targ_spec */ - err = bpf_core_reloc_insn(prog, relo, &local_spec, + err = bpf_core_reloc_insn(prog, relo, relo_idx, &local_spec, j ? &targ_spec : NULL); if (err) { pr_warn("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", @@ -3487,7 +4580,7 @@ bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) if (targ_btf_path) targ_btf = btf__parse_elf(targ_btf_path, NULL); else - targ_btf = bpf_core_find_kernel_btf(); + targ_btf = libbpf_find_kernel_btf(); if (IS_ERR(targ_btf)) { pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf)); return PTR_ERR(targ_btf); @@ -3559,16 +4652,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, size_t new_cnt; int err; - if (relo->type != RELO_CALL) - return -LIBBPF_ERRNO__RELOC; - - if (prog->idx == obj->efile.text_shndx) { - pr_warn("relo in .text insn %d into off %d (insn #%d)\n", - relo->insn_idx, relo->sym_off, relo->sym_off / 8); - return -LIBBPF_ERRNO__RELOC; - } - - if (prog->main_prog_cnt == 0) { + if (prog->idx != obj->efile.text_shndx && prog->main_prog_cnt == 0) { text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx); if (!text) { pr_warn("no .text section found yet relo into text exist\n"); @@ -3598,6 +4682,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, text->insns_cnt, text->section_name, prog->section_name); } + insn = &prog->insns[relo->insn_idx]; insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx; return 0; @@ -3623,27 +4708,37 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) for (i = 0; i < prog->nr_reloc; i++) { struct reloc_desc *relo = &prog->reloc_desc[i]; + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; - if (relo->type == RELO_LD64 || relo->type == RELO_DATA) { - struct bpf_insn *insn = &prog->insns[relo->insn_idx]; - - if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { - pr_warn("relocation out of range: '%s'\n", - prog->section_name); - return -LIBBPF_ERRNO__RELOC; - } + if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { + pr_warn("relocation out of range: '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__RELOC; + } - if (relo->type != RELO_DATA) { - insn[0].src_reg = BPF_PSEUDO_MAP_FD; - } else { - insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; - insn[1].imm = insn[0].imm + relo->sym_off; - } + switch (relo->type) { + case RELO_LD64: + insn[0].src_reg = BPF_PSEUDO_MAP_FD; + insn[0].imm = obj->maps[relo->map_idx].fd; + break; + case RELO_DATA: + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[1].imm = insn[0].imm + relo->sym_off; insn[0].imm = obj->maps[relo->map_idx].fd; - } else if (relo->type == RELO_CALL) { + break; + case RELO_EXTERN: + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + insn[1].imm = relo->sym_off; + break; + case RELO_CALL: err = bpf_program__reloc_text(prog, obj, relo); if (err) return err; + break; + default: + pr_warn("relo #%d: bad relo type %d\n", i, relo->type); + return -EINVAL; } } @@ -3667,8 +4762,28 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return err; } } + /* ensure .text is relocated first, as it's going to be copied as-is + * later for sub-program calls + */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + if (prog->idx != obj->efile.text_shndx) + continue; + + err = bpf_program__relocate(prog, obj); + if (err) { + pr_warn("failed to relocate '%s'\n", prog->section_name); + return err; + } + break; + } + /* now relocate everything but .text, which by now is relocated + * properly, so we can copy raw sub-program instructions as is safely + */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; + if (prog->idx == obj->efile.text_shndx) + continue; err = bpf_program__relocate(prog, obj); if (err) { @@ -3679,6 +4794,10 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return 0; } +static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj, + GElf_Shdr *shdr, + Elf_Data *data); + static int bpf_object__collect_reloc(struct bpf_object *obj) { int i, err; @@ -3699,6 +4818,15 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) return -LIBBPF_ERRNO__INTERNAL; } + if (idx == obj->efile.st_ops_shndx) { + err = bpf_object__collect_struct_ops_map_reloc(obj, + shdr, + data); + if (err) + return err; + continue; + } + prog = bpf_object__find_prog_by_idx(obj, idx); if (!prog) { pr_warn("relocation failed: no section(%d)\n", idx); @@ -3733,7 +4861,10 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = license; - if (prog->type == BPF_PROG_TYPE_TRACING) { + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) { + load_attr.attach_btf_id = prog->attach_btf_id; + } else if (prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) { load_attr.attach_prog_fd = prog->attach_prog_fd; load_attr.attach_btf_id = prog->attach_btf_id; } else { @@ -3778,6 +4909,7 @@ retry_load: ret = -errno; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warn("load bpf program failed: %s\n", cp); + pr_perm_msg(ret); if (log_buf && log_buf[0] != '\0') { ret = -LIBBPF_ERRNO__VERIFY; @@ -3807,11 +4939,19 @@ out: return ret; } -int -bpf_program__load(struct bpf_program *prog, - char *license, __u32 kern_version) +static int libbpf_find_attach_btf_id(struct bpf_program *prog); + +int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { - int err = 0, fd, i; + int err = 0, fd, i, btf_id; + + if (prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) { + btf_id = libbpf_find_attach_btf_id(prog); + if (btf_id <= 0) + return btf_id; + prog->attach_btf_id = btf_id; + } if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { @@ -3835,7 +4975,7 @@ bpf_program__load(struct bpf_program *prog, prog->section_name, prog->instances.nr); } err = load_program(prog, prog->insns, prog->insns_cnt, - license, kern_version, &fd); + license, kern_ver, &fd); if (!err) prog->instances.fds[0] = fd; goto out; @@ -3864,9 +5004,7 @@ bpf_program__load(struct bpf_program *prog, } err = load_program(prog, result.new_insn_ptr, - result.new_insn_cnt, - license, kern_version, &fd); - + result.new_insn_cnt, license, kern_ver, &fd); if (err) { pr_warn("Loading the %dth instance of program '%s' failed\n", i, prog->section_name); @@ -3910,20 +5048,14 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) return 0; } -static int libbpf_find_attach_btf_id(const char *name, - enum bpf_attach_type attach_type, - __u32 attach_prog_fd); static struct bpf_object * __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts) + const struct bpf_object_open_opts *opts) { - const char *pin_root_path; + const char *obj_name, *kconfig; struct bpf_program *prog; struct bpf_object *obj; - const char *obj_name; char tmp_name[64]; - bool relaxed_maps; - __u32 attach_prog_fd; int err; if (elf_version(EV_CURRENT) == EV_NONE) { @@ -3951,23 +5083,32 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, if (IS_ERR(obj)) return obj; - obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false); - relaxed_maps = OPTS_GET(opts, relaxed_maps, false); - pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); - - CHECK_ERR(bpf_object__elf_init(obj), err, out); - CHECK_ERR(bpf_object__check_endianness(obj), err, out); - CHECK_ERR(bpf_object__probe_caps(obj), err, out); - CHECK_ERR(bpf_object__elf_collect(obj, relaxed_maps, pin_root_path), - err, out); - CHECK_ERR(bpf_object__collect_reloc(obj), err, out); + kconfig = OPTS_GET(opts, kconfig, NULL); + if (kconfig) { + obj->kconfig = strdup(kconfig); + if (!obj->kconfig) + return ERR_PTR(-ENOMEM); + } + + err = bpf_object__elf_init(obj); + err = err ? : bpf_object__check_endianness(obj); + err = err ? : bpf_object__elf_collect(obj); + err = err ? : bpf_object__collect_externs(obj); + err = err ? : bpf_object__finalize_btf(obj); + err = err ? : bpf_object__init_maps(obj, opts); + err = err ? : bpf_object__init_prog_names(obj); + err = err ? : bpf_object__collect_reloc(obj); + if (err) + goto out; 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) @@ -3978,15 +5119,9 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, bpf_program__set_type(prog, prog_type); bpf_program__set_expected_attach_type(prog, attach_type); - if (prog_type == BPF_PROG_TYPE_TRACING) { - err = libbpf_find_attach_btf_id(prog->section_name, - attach_type, - attach_prog_fd); - if (err <= 0) - goto out; - prog->attach_btf_id = err; - prog->attach_prog_fd = attach_prog_fd; - } + if (prog_type == BPF_PROG_TYPE_TRACING || + prog_type == BPF_PROG_TYPE_EXT) + prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); } return obj; @@ -4026,7 +5161,7 @@ struct bpf_object *bpf_object__open(const char *path) } struct bpf_object * -bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) { if (!path) return ERR_PTR(-EINVAL); @@ -4038,7 +5173,7 @@ bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts) + const struct bpf_object_open_opts *opts) { if (!obj_buf || obj_buf_sz == 0) return ERR_PTR(-EINVAL); @@ -4070,8 +5205,11 @@ int bpf_object__unload(struct bpf_object *obj) if (!obj) return -EINVAL; - for (i = 0; i < obj->nr_maps; i++) + for (i = 0; i < obj->nr_maps; i++) { zclose(obj->maps[i].fd); + if (obj->maps[i].st_ops) + zfree(&obj->maps[i].st_ops->kern_vdata); + } for (i = 0; i < obj->nr_programs; i++) bpf_program__unload(&obj->programs[i]); @@ -4079,6 +5217,92 @@ int bpf_object__unload(struct bpf_object *obj) return 0; } +static int bpf_object__sanitize_maps(struct bpf_object *obj) +{ + struct bpf_map *m; + + bpf_object__for_each_map(m, obj) { + if (!bpf_map__is_internal(m)) + continue; + if (!obj->caps.global_data) { + pr_warn("kernel doesn't support global data\n"); + return -ENOTSUP; + } + if (!obj->caps.array_mmap) + m->def.map_flags ^= BPF_F_MMAPABLE; + } + + return 0; +} + +static int bpf_object__resolve_externs(struct bpf_object *obj, + const char *extra_kconfig) +{ + bool need_config = false; + struct extern_desc *ext; + int err, i; + void *data; + + if (obj->nr_extern == 0) + return 0; + + data = obj->maps[obj->kconfig_map_idx].mmaped; + + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + + if (strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) { + void *ext_val = data + ext->data_off; + __u32 kver = get_kernel_version(); + + if (!kver) { + pr_warn("failed to get kernel version\n"); + return -EINVAL; + } + err = set_ext_value_num(ext, ext_val, kver); + if (err) + return err; + pr_debug("extern %s=0x%x\n", ext->name, kver); + } else if (strncmp(ext->name, "CONFIG_", 7) == 0) { + need_config = true; + } else { + pr_warn("unrecognized extern '%s'\n", ext->name); + return -EINVAL; + } + } + if (need_config && extra_kconfig) { + err = bpf_object__read_kconfig_mem(obj, extra_kconfig, data); + if (err) + return -EINVAL; + need_config = false; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (!ext->is_set) { + need_config = true; + break; + } + } + } + if (need_config) { + err = bpf_object__read_kconfig_file(obj, data); + if (err) + return -EINVAL; + } + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + + if (!ext->is_set && !ext->is_weak) { + pr_warn("extern %s (strong) not resolved\n", ext->name); + return -ESRCH; + } else if (!ext->is_set) { + pr_debug("extern %s (weak) not resolved, defaulting to zero\n", + ext->name); + } + } + + return 0; +} + int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { struct bpf_object *obj; @@ -4097,9 +5321,21 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) obj->loaded = true; - CHECK_ERR(bpf_object__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); - CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); + err = bpf_object__probe_caps(obj); + err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); + err = err ? : bpf_object__sanitize_and_load_btf(obj); + err = err ? : bpf_object__sanitize_maps(obj); + err = err ? : bpf_object__load_vmlinux_btf(obj); + err = err ? : bpf_object__init_kern_struct_ops_maps(obj); + err = err ? : bpf_object__create_maps(obj); + err = err ? : bpf_object__relocate(obj, attr->target_btf_path); + err = err ? : bpf_object__load_progs(obj, attr->log_level); + + btf__free(obj->btf_vmlinux); + obj->btf_vmlinux = NULL; + + if (err) + goto out; return 0; out: @@ -4670,17 +5906,33 @@ void bpf_object__close(struct bpf_object *obj) btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) { - zfree(&obj->maps[i].name); - zfree(&obj->maps[i].pin_path); - if (obj->maps[i].clear_priv) - obj->maps[i].clear_priv(&obj->maps[i], - obj->maps[i].priv); - obj->maps[i].priv = NULL; - obj->maps[i].clear_priv = NULL; + struct bpf_map *map = &obj->maps[i]; + + if (map->clear_priv) + map->clear_priv(map, map->priv); + map->priv = NULL; + map->clear_priv = NULL; + + if (map->mmaped) { + munmap(map->mmaped, bpf_map_mmap_sz(map)); + map->mmaped = NULL; + } + + if (map->st_ops) { + zfree(&map->st_ops->data); + zfree(&map->st_ops->progs); + zfree(&map->st_ops->kern_func_off); + zfree(&map->st_ops); + } + + zfree(&map->name); + zfree(&map->pin_path); } - zfree(&obj->sections.rodata); - zfree(&obj->sections.data); + zfree(&obj->kconfig); + zfree(&obj->externs); + obj->nr_extern = 0; + zfree(&obj->maps); obj->nr_maps = 0; @@ -4820,6 +6072,11 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } +const char *bpf_program__name(const struct bpf_program *prog) +{ + return prog->name; +} + const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -4936,6 +6193,8 @@ BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING); +BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS); +BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT); enum bpf_attach_type bpf_program__get_expected_attach_type(struct bpf_program *prog) @@ -4972,7 +6231,28 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, */ #define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) -static const struct { +#define SEC_DEF(sec_pfx, ptype, ...) { \ + .sec = sec_pfx, \ + .len = sizeof(sec_pfx) - 1, \ + .prog_type = BPF_PROG_TYPE_##ptype, \ + __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, + struct bpf_program *prog); +static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_trace(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; @@ -4980,24 +6260,43 @@ static const struct { bool is_attachable; bool is_attach_btf; enum bpf_attach_type attach_type; -} section_names[] = { + 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("kprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT), + SEC_DEF("kprobe/", KPROBE, + .attach_fn = attach_kprobe), BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), - BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + SEC_DEF("kretprobe/", KPROBE, + .attach_fn = attach_kprobe), BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), - BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), - BPF_PROG_SEC("tp/", BPF_PROG_TYPE_TRACEPOINT), - BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), - BPF_PROG_SEC("raw_tp/", BPF_PROG_TYPE_RAW_TRACEPOINT), - BPF_PROG_BTF("tp_btf/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_RAW_TP), - BPF_PROG_BTF("fentry/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_FENTRY), - BPF_PROG_BTF("fexit/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_FEXIT), + SEC_DEF("tracepoint/", TRACEPOINT, + .attach_fn = attach_tp), + SEC_DEF("tp/", TRACEPOINT, + .attach_fn = attach_tp), + SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, + .attach_fn = attach_raw_tp), + SEC_DEF("raw_tp/", RAW_TRACEPOINT, + .attach_fn = attach_raw_tp), + SEC_DEF("tp_btf/", TRACING, + .expected_attach_type = BPF_TRACE_RAW_TP, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("fentry/", TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("fexit/", TRACING, + .expected_attach_type = BPF_TRACE_FEXIT, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("freplace/", EXT, + .is_attach_btf = true, + .attach_fn = attach_trace), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), @@ -5052,6 +6351,7 @@ static const struct { BPF_CGROUP_GETSOCKOPT), BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT), + BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS), }; #undef BPF_PROG_SEC_IMPL @@ -5059,12 +6359,26 @@ static const struct { #undef BPF_APROG_SEC #undef BPF_EAPROG_SEC #undef BPF_APROG_COMPAT +#undef SEC_DEF #define MAX_TYPE_NAME_SIZE 32 +static const struct bpf_sec_def *find_sec_def(const char *sec_name) +{ + int i, n = ARRAY_SIZE(section_defs); + + for (i = 0; i < n; i++) { + if (strncmp(sec_name, + section_defs[i].sec, section_defs[i].len)) + continue; + return §ion_defs[i]; + } + return NULL; +} + static char *libbpf_get_type_names(bool attach_type) { - int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE; + int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE; char *buf; buf = malloc(len); @@ -5073,16 +6387,16 @@ static char *libbpf_get_type_names(bool attach_type) buf[0] = '\0'; /* Forge string buf with all available names */ - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (attach_type && !section_names[i].is_attachable) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (attach_type && !section_defs[i].is_attachable) continue; - if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) { + if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { free(buf); return NULL; } strcat(buf, " "); - strcat(buf, section_names[i].sec); + strcat(buf, section_defs[i].sec); } return buf; @@ -5091,57 +6405,205 @@ static char *libbpf_get_type_names(bool attach_type) int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, enum bpf_attach_type *expected_attach_type) { + const struct bpf_sec_def *sec_def; char *type_names; - int i; if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (strncmp(name, section_names[i].sec, section_names[i].len)) - continue; - *prog_type = section_names[i].prog_type; - *expected_attach_type = section_names[i].expected_attach_type; + sec_def = find_sec_def(name); + if (sec_def) { + *prog_type = sec_def->prog_type; + *expected_attach_type = sec_def->expected_attach_type; return 0; } - pr_warn("failed to guess program type from ELF section '%s'\n", name); + + pr_debug("failed to guess program type from ELF section '%s'\n", name); type_names = libbpf_get_type_names(false); if (type_names != NULL) { - pr_info("supported section(type) names are:%s\n", type_names); + pr_debug("supported section(type) names are:%s\n", type_names); free(type_names); } return -ESRCH; } -#define BTF_PREFIX "btf_trace_" +static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, + size_t offset) +{ + struct bpf_map *map; + size_t i; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + if (!bpf_map__is_struct_ops(map)) + continue; + if (map->sec_offset <= offset && + offset - map->sec_offset < map->def.value_size) + return map; + } + + return NULL; +} + +/* Collect the reloc from ELF and populate the st_ops->progs[] */ +static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj, + GElf_Shdr *shdr, + Elf_Data *data) +{ + const struct btf_member *member; + struct bpf_struct_ops *st_ops; + struct bpf_program *prog; + unsigned int shdr_idx; + const struct btf *btf; + struct bpf_map *map; + Elf_Data *symbols; + unsigned int moff; + const char *name; + __u32 member_idx; + GElf_Sym sym; + GElf_Rel rel; + int i, nrels; + + symbols = obj->efile.symbols; + btf = obj->btf; + nrels = shdr->sh_size / shdr->sh_entsize; + for (i = 0; i < nrels; i++) { + if (!gelf_getrel(data, i, &rel)) { + pr_warn("struct_ops reloc: failed to get %d reloc\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + pr_warn("struct_ops reloc: symbol %zx not found\n", + (size_t)GELF_R_SYM(rel.r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + map = find_struct_ops_map_by_offset(obj, rel.r_offset); + if (!map) { + pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n", + (size_t)rel.r_offset); + return -EINVAL; + } + + moff = rel.r_offset - map->sec_offset; + shdr_idx = sym.st_shndx; + st_ops = map->st_ops; + pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n", + map->name, + (long long)(rel.r_info >> 32), + (long long)sym.st_value, + shdr_idx, (size_t)rel.r_offset, + map->sec_offset, sym.st_name, name); + + if (shdr_idx >= SHN_LORESERVE) { + pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n", + map->name, (size_t)rel.r_offset, shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + member = find_member_by_offset(st_ops->type, moff * 8); + if (!member) { + pr_warn("struct_ops reloc %s: cannot find member at moff %u\n", + map->name, moff); + return -EINVAL; + } + member_idx = member - btf_members(st_ops->type); + name = btf__name_by_offset(btf, member->name_off); + + if (!resolve_func_ptr(btf, member->type, NULL)) { + pr_warn("struct_ops reloc %s: cannot relocate non func ptr %s\n", + map->name, name); + return -EINVAL; + } + + prog = bpf_object__find_prog_by_idx(obj, shdr_idx); + if (!prog) { + pr_warn("struct_ops reloc %s: cannot find prog at shdr_idx %u to relocate func ptr %s\n", + map->name, shdr_idx, name); + return -EINVAL; + } + + if (prog->type == BPF_PROG_TYPE_UNSPEC) { + const struct bpf_sec_def *sec_def; + + sec_def = find_sec_def(prog->section_name); + if (sec_def && + sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) { + /* for pr_warn */ + prog->type = sec_def->prog_type; + goto invalid_prog; + } + + prog->type = BPF_PROG_TYPE_STRUCT_OPS; + prog->attach_btf_id = st_ops->type_id; + prog->expected_attach_type = member_idx; + } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || + prog->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != member_idx) { + goto invalid_prog; + } + st_ops->progs[member_idx] = prog; + } + + return 0; + +invalid_prog: + pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", + map->name, prog->name, prog->section_name, prog->type, + prog->attach_btf_id, prog->expected_attach_type, name); + return -EINVAL; +} + +#define BTF_TRACE_PREFIX "btf_trace_" +#define BTF_MAX_NAME_SIZE 128 + +static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, + const char *name, __u32 kind) +{ + char btf_type_name[BTF_MAX_NAME_SIZE]; + int ret; + + ret = snprintf(btf_type_name, sizeof(btf_type_name), + "%s%s", prefix, name); + /* snprintf returns the number of characters written excluding the + * the terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it + * indicates truncation. + */ + if (ret < 0 || ret >= sizeof(btf_type_name)) + return -ENAMETOOLONG; + return btf__find_by_name_kind(btf, btf_type_name, kind); +} + +static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name, + enum bpf_attach_type attach_type) +{ + int err; + + if (attach_type == BPF_TRACE_RAW_TP) + err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name, + BTF_KIND_TYPEDEF); + else + err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); + + return err; +} + int libbpf_find_vmlinux_btf_id(const char *name, enum bpf_attach_type attach_type) { - struct btf *btf = bpf_core_find_kernel_btf(); - char raw_tp_btf[128] = BTF_PREFIX; - char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1; - const char *btf_name; - int err = -EINVAL; - __u32 kind; + struct btf *btf; + btf = libbpf_find_kernel_btf(); if (IS_ERR(btf)) { pr_warn("vmlinux BTF is not found\n"); return -EINVAL; } - if (attach_type == BPF_TRACE_RAW_TP) { - /* prepend "btf_trace_" prefix per kernel convention */ - strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX)); - btf_name = raw_tp_btf; - kind = BTF_KIND_TYPEDEF; - } else { - btf_name = name; - kind = BTF_KIND_FUNC; - } - err = btf__find_by_name_kind(btf, btf_name, kind); - btf__free(btf); - return err; + return __find_vmlinux_btf_id(btf, name, attach_type); } static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) @@ -5177,26 +6639,28 @@ out: return err; } -static int libbpf_find_attach_btf_id(const char *name, - enum bpf_attach_type attach_type, - __u32 attach_prog_fd) +static int libbpf_find_attach_btf_id(struct bpf_program *prog) { + enum bpf_attach_type attach_type = prog->expected_attach_type; + __u32 attach_prog_fd = prog->attach_prog_fd; + const char *name = prog->section_name; int i, err; if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (!section_names[i].is_attach_btf) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (!section_defs[i].is_attach_btf) continue; - if (strncmp(name, section_names[i].sec, section_names[i].len)) + if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; if (attach_prog_fd) - err = libbpf_find_prog_btf_id(name + section_names[i].len, + err = libbpf_find_prog_btf_id(name + section_defs[i].len, attach_prog_fd); else - err = libbpf_find_vmlinux_btf_id(name + section_names[i].len, - attach_type); + err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux, + name + section_defs[i].len, + attach_type); if (err <= 0) pr_warn("%s is not found in vmlinux BTF\n", name); return err; @@ -5214,18 +6678,18 @@ int libbpf_attach_type_by_name(const char *name, if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (strncmp(name, section_names[i].sec, section_names[i].len)) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; - if (!section_names[i].is_attachable) + if (!section_defs[i].is_attachable) return -EINVAL; - *attach_type = section_names[i].attach_type; + *attach_type = section_defs[i].attach_type; return 0; } - pr_warn("failed to guess attach type based on ELF section name '%s'\n", name); + pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); type_names = libbpf_get_type_names(true); if (type_names != NULL) { - pr_info("attachable section(type) names are:%s\n", type_names); + pr_debug("attachable section(type) names are:%s\n", type_names); free(type_names); } @@ -5466,17 +6930,37 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, } struct bpf_link { + int (*detach)(struct bpf_link *link); int (*destroy)(struct bpf_link *link); + bool disconnected; }; +/* Release "ownership" of underlying BPF resource (typically, BPF program + * attached to some BPF hook, e.g., tracepoint, kprobe, etc). Disconnected + * link, when destructed through bpf_link__destroy() call won't attempt to + * detach/unregisted that BPF resource. This is useful in situations where, + * say, attached BPF program has to outlive userspace program that attached it + * in the system. Depending on type of BPF program, though, there might be + * additional steps (like pinning BPF program in BPF FS) necessary to ensure + * exit of userspace program doesn't trigger automatic detachment and clean up + * inside the kernel. + */ +void bpf_link__disconnect(struct bpf_link *link) +{ + link->disconnected = true; +} + int bpf_link__destroy(struct bpf_link *link) { - int err; + int err = 0; if (!link) return 0; - err = link->destroy(link); + if (!link->disconnected && link->detach) + err = link->detach(link); + if (link->destroy) + link->destroy(link); free(link); return err; @@ -5487,7 +6971,7 @@ struct bpf_link_fd { int fd; /* hook FD */ }; -static int bpf_link__destroy_perf_event(struct bpf_link *link) +static int bpf_link__detach_perf_event(struct bpf_link *link) { struct bpf_link_fd *l = (void *)link; int err; @@ -5519,10 +7003,10 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_perf_event; + link->link.detach = &bpf_link__detach_perf_event; link->fd = pfd; if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { @@ -5679,6 +7163,18 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, return link; } +static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + const char *func_name; + bool retprobe; + + func_name = bpf_program__title(prog, false) + sec->len; + retprobe = strcmp(sec->sec, "kretprobe/") == 0; + + return bpf_program__attach_kprobe(prog, retprobe, func_name); +} + struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, @@ -5791,7 +7287,33 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, return link; } -static int bpf_link__destroy_fd(struct bpf_link *link) +static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + char *sec_name, *tp_cat, *tp_name; + struct bpf_link *link; + + sec_name = strdup(bpf_program__title(prog, false)); + if (!sec_name) + return ERR_PTR(-ENOMEM); + + /* extract "tp/<category>/<name>" */ + tp_cat = sec_name + sec->len; + tp_name = strchr(tp_cat, '/'); + if (!tp_name) { + link = ERR_PTR(-EINVAL); + goto out; + } + *tp_name = '\0'; + tp_name++; + + link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); +out: + free(sec_name); + return link; +} + +static int bpf_link__detach_fd(struct bpf_link *link) { struct bpf_link_fd *l = (void *)link; @@ -5812,10 +7334,10 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_fd; + link->link.detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); if (pfd < 0) { @@ -5830,6 +7352,14 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return (struct bpf_link *)link; } +static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + const char *tp_name = bpf_program__title(prog, false) + sec->len; + + return bpf_program__attach_raw_tracepoint(prog, tp_name); +} + struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) { char errmsg[STRERR_BUFSIZE]; @@ -5843,10 +7373,10 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_fd; + link->link.detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(NULL, prog_fd); if (pfd < 0) { @@ -5861,6 +7391,75 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) return (struct bpf_link *)link; } +static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + return bpf_program__attach_trace(prog); +} + +struct bpf_link *bpf_program__attach(struct bpf_program *prog) +{ + const struct bpf_sec_def *sec_def; + + sec_def = find_sec_def(bpf_program__title(prog, false)); + if (!sec_def || !sec_def->attach_fn) + return ERR_PTR(-ESRCH); + + return sec_def->attach_fn(sec_def, prog); +} + +static int bpf_link__detach_struct_ops(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + __u32 zero = 0; + + if (bpf_map_delete_elem(l->fd, &zero)) + return -errno; + + return 0; +} + +struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) +{ + struct bpf_struct_ops *st_ops; + struct bpf_link_fd *link; + __u32 i, zero = 0; + int err; + + if (!bpf_map__is_struct_ops(map) || map->fd == -1) + return ERR_PTR(-EINVAL); + + link = calloc(1, sizeof(*link)); + if (!link) + return ERR_PTR(-EINVAL); + + st_ops = map->st_ops; + for (i = 0; i < btf_vlen(st_ops->type); i++) { + struct bpf_program *prog = st_ops->progs[i]; + void *kern_data; + int prog_fd; + + if (!prog) + continue; + + prog_fd = bpf_program__fd(prog); + kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i]; + *(unsigned long *)kern_data = prog_fd; + } + + err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0); + if (err) { + err = -errno; + free(link); + return ERR_PTR(err); + } + + link->link.detach = bpf_link__detach_struct_ops; + link->fd = map->fd; + + return (struct bpf_link *)link; +} + enum bpf_perf_event_ret bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, @@ -5944,7 +7543,7 @@ struct perf_buffer { size_t mmap_size; struct perf_cpu_buf **cpu_bufs; struct epoll_event *events; - int cpu_cnt; + int cpu_cnt; /* number of allocated CPU buffers */ int epoll_fd; /* perf event FD */ int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ }; @@ -6078,11 +7677,13 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt, static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params *p) { + const char *online_cpus_file = "/sys/devices/system/cpu/online"; struct bpf_map_info map = {}; char msg[STRERR_BUFSIZE]; struct perf_buffer *pb; + bool *online = NULL; __u32 map_info_len; - int err, i; + int err, i, j, n; if (page_cnt & (page_cnt - 1)) { pr_warn("page count should be power of two, but is %zu\n", @@ -6151,20 +7752,32 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, goto error; } - for (i = 0; i < pb->cpu_cnt; i++) { + err = parse_cpu_mask_file(online_cpus_file, &online, &n); + if (err) { + pr_warn("failed to get online CPU mask: %d\n", err); + goto error; + } + + for (i = 0, j = 0; i < pb->cpu_cnt; i++) { struct perf_cpu_buf *cpu_buf; int cpu, map_key; cpu = p->cpu_cnt > 0 ? p->cpus[i] : i; map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i; + /* in case user didn't explicitly requested particular CPUs to + * be attached to, skip offline/not present CPUs + */ + if (p->cpu_cnt <= 0 && (cpu >= n || !online[cpu])) + continue; + cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key); if (IS_ERR(cpu_buf)) { err = PTR_ERR(cpu_buf); goto error; } - pb->cpu_bufs[i] = cpu_buf; + pb->cpu_bufs[j] = cpu_buf; err = bpf_map_update_elem(pb->map_fd, &map_key, &cpu_buf->fd, 0); @@ -6176,21 +7789,25 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, goto error; } - pb->events[i].events = EPOLLIN; - pb->events[i].data.ptr = cpu_buf; + pb->events[j].events = EPOLLIN; + pb->events[j].data.ptr = cpu_buf; if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, - &pb->events[i]) < 0) { + &pb->events[j]) < 0) { err = -errno; pr_warn("failed to epoll_ctl cpu #%d perf FD %d: %s\n", cpu, cpu_buf->fd, libbpf_strerror_r(err, msg, sizeof(msg))); goto error; } + j++; } + pb->cpu_cnt = j; + free(online); return pb; error: + free(online); if (pb) perf_buffer__free(pb); return ERR_PTR(err); @@ -6521,62 +8138,267 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) } } -int libbpf_num_possible_cpus(void) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz) { - static const char *fcpu = "/sys/devices/system/cpu/possible"; - int len = 0, n = 0, il = 0, ir = 0; - unsigned int start = 0, end = 0; - int tmp_cpus = 0; - static int cpus; - char buf[128]; - int error = 0; - int fd = -1; + int err = 0, n, len, start, end = -1; + bool *tmp; - tmp_cpus = READ_ONCE(cpus); - if (tmp_cpus > 0) - return tmp_cpus; + *mask = NULL; + *mask_sz = 0; + + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + while (*s) { + if (*s == ',' || *s == '\n') { + s++; + continue; + } + n = sscanf(s, "%d%n-%d%n", &start, &len, &end, &len); + if (n <= 0 || n > 2) { + pr_warn("Failed to get CPU range %s: %d\n", s, n); + err = -EINVAL; + goto cleanup; + } else if (n == 1) { + end = start; + } + if (start < 0 || start > end) { + pr_warn("Invalid CPU range [%d,%d] in %s\n", + start, end, s); + err = -EINVAL; + goto cleanup; + } + tmp = realloc(*mask, end + 1); + if (!tmp) { + err = -ENOMEM; + goto cleanup; + } + *mask = tmp; + memset(tmp + *mask_sz, 0, start - *mask_sz); + memset(tmp + start, 1, end - start + 1); + *mask_sz = end + 1; + s += len; + } + if (!*mask_sz) { + pr_warn("Empty CPU range\n"); + return -EINVAL; + } + return 0; +cleanup: + free(*mask); + *mask = NULL; + return err; +} + +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz) +{ + int fd, err = 0, len; + char buf[128]; fd = open(fcpu, O_RDONLY); if (fd < 0) { - error = errno; - pr_warn("Failed to open file %s: %s\n", fcpu, strerror(error)); - return -error; + err = -errno; + pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err); + return err; } len = read(fd, buf, sizeof(buf)); close(fd); if (len <= 0) { - error = len ? errno : EINVAL; - pr_warn("Failed to read # of possible cpus from %s: %s\n", - fcpu, strerror(error)); - return -error; + err = len ? -errno : -EINVAL; + pr_warn("Failed to read cpu mask from %s: %d\n", fcpu, err); + return err; } - if (len == sizeof(buf)) { - pr_warn("File %s size overflow\n", fcpu); - return -EOVERFLOW; + if (len >= sizeof(buf)) { + pr_warn("CPU mask is too big in file %s\n", fcpu); + return -E2BIG; } buf[len] = '\0'; - for (ir = 0, tmp_cpus = 0; ir <= len; ir++) { - /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ - if (buf[ir] == ',' || buf[ir] == '\0') { - buf[ir] = '\0'; - n = sscanf(&buf[il], "%u-%u", &start, &end); - if (n <= 0) { - pr_warn("Failed to get # CPUs from %s\n", - &buf[il]); - return -EINVAL; - } else if (n == 1) { - end = start; - } - tmp_cpus += end - start + 1; - il = ir + 1; - } - } - if (tmp_cpus <= 0) { - pr_warn("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); - return -EINVAL; + return parse_cpu_mask_str(buf, mask, mask_sz); +} + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + static int cpus; + int err, n, i, tmp_cpus; + bool *mask; + + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; + + err = parse_cpu_mask_file(fcpu, &mask, &n); + if (err) + return err; + + tmp_cpus = 0; + for (i = 0; i < n; i++) { + if (mask[i]) + tmp_cpus++; } + free(mask); WRITE_ONCE(cpus, tmp_cpus); return tmp_cpus; } + +int bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts, + .object_name = s->name, + ); + struct bpf_object *obj; + int i; + + /* Attempt to preserve opts->object_name, unless overriden by user + * explicitly. Overwriting object name for skeletons is discouraged, + * as it breaks global data maps, because they contain object name + * prefix as their own map name prefix. When skeleton is generated, + * bpftool is making an assumption that this name will stay the same. + */ + if (opts) { + memcpy(&skel_opts, opts, sizeof(*opts)); + if (!opts->object_name) + skel_opts.object_name = s->name; + } + + obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts); + if (IS_ERR(obj)) { + pr_warn("failed to initialize skeleton BPF object '%s': %ld\n", + s->name, PTR_ERR(obj)); + return PTR_ERR(obj); + } + + *s->obj = obj; + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map **map = s->maps[i].map; + const char *name = s->maps[i].name; + void **mmaped = s->maps[i].mmaped; + + *map = bpf_object__find_map_by_name(obj, name); + if (!*map) { + pr_warn("failed to find skeleton map '%s'\n", name); + return -ESRCH; + } + + /* externs shouldn't be pre-setup from user code */ + if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) + *mmaped = (*map)->mmaped; + } + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program **prog = s->progs[i].prog; + const char *name = s->progs[i].name; + + *prog = bpf_object__find_program_by_name(obj, name); + if (!*prog) { + pr_warn("failed to find skeleton program '%s'\n", name); + return -ESRCH; + } + } + + return 0; +} + +int bpf_object__load_skeleton(struct bpf_object_skeleton *s) +{ + int i, err; + + err = bpf_object__load(*s->obj); + if (err) { + pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err); + return err; + } + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map *map = *s->maps[i].map; + size_t mmap_sz = bpf_map_mmap_sz(map); + int prot, map_fd = bpf_map__fd(map); + void **mmaped = s->maps[i].mmaped; + + if (!mmaped) + continue; + + if (!(map->def.map_flags & BPF_F_MMAPABLE)) { + *mmaped = NULL; + continue; + } + + if (map->def.map_flags & BPF_F_RDONLY_PROG) + prot = PROT_READ; + else + prot = PROT_READ | PROT_WRITE; + + /* Remap anonymous mmap()-ed "map initialization image" as + * a BPF map-backed mmap()-ed memory, but preserving the same + * memory address. This will cause kernel to change process' + * page table to point to a different piece of kernel memory, + * but from userspace point of view memory address (and its + * contents, being identical at this point) will stay the + * same. This mapping will be released by bpf_object__close() + * as per normal clean up procedure, so we don't need to worry + * about it from skeleton's clean up perspective. + */ + *mmaped = mmap(map->mmaped, mmap_sz, prot, + MAP_SHARED | MAP_FIXED, map_fd, 0); + if (*mmaped == MAP_FAILED) { + err = -errno; + *mmaped = NULL; + pr_warn("failed to re-mmap() map '%s': %d\n", + bpf_map__name(map), err); + return err; + } + } + + return 0; +} + +int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) +{ + int i; + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program *prog = *s->progs[i].prog; + struct bpf_link **link = s->progs[i].link; + const struct bpf_sec_def *sec_def; + const char *sec_name = bpf_program__title(prog, false); + + sec_def = find_sec_def(sec_name); + if (!sec_def || !sec_def->attach_fn) + continue; + + *link = sec_def->attach_fn(sec_def, prog); + if (IS_ERR(*link)) { + pr_warn("failed to auto-attach program '%s': %ld\n", + bpf_program__name(prog), PTR_ERR(*link)); + return PTR_ERR(*link); + } + } + + return 0; +} + +void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) +{ + int i; + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_link **link = s->progs[i].link; + + if (!IS_ERR_OR_NULL(*link)) + bpf_link__destroy(*link); + *link = NULL; + } +} + +void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) +{ + if (s->progs) + bpf_object__detach_skeleton(s); + if (s->obj) + bpf_object__close(*s->obj); + free(s->maps); + free(s->progs); + free(s); +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 0dbf4bfba0c4..3fe12c9d1f92 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -17,14 +17,12 @@ #include <sys/types.h> // for size_t #include <linux/bpf.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -67,28 +65,6 @@ struct bpf_object_open_attr { enum bpf_prog_type prog_type; }; -/* Helper macro to declare and initialize libbpf options struct - * - * This dance with uninitialized declaration, followed by memset to zero, - * followed by assignment using compound literal syntax is done to preserve - * ability to use a nice struct field initialization syntax and **hopefully** - * have all the padding bytes initialized to zero. It's not guaranteed though, - * when copying literal, that compiler won't copy garbage in literal's padding - * bytes, but that's the best way I've found and it seems to work in practice. - * - * Macro declares opts struct of given type and name, zero-initializes, - * including any extra padding, it with memset() and then assigns initial - * values provided by users in struct initializer-syntax as varargs. - */ -#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ - struct TYPE NAME = ({ \ - memset(&NAME, 0, sizeof(struct TYPE)); \ - (struct TYPE) { \ - .sz = sizeof(struct TYPE), \ - __VA_ARGS__ \ - }; \ - }) - struct bpf_object_open_opts { /* size of this struct, for forward/backward compatiblity */ size_t sz; @@ -101,7 +77,11 @@ struct bpf_object_open_opts { const char *object_name; /* parse map definitions non-strictly, allowing extra attributes/data */ bool relaxed_maps; - /* process CO-RE relocations non-strictly, allowing them to fail */ + /* DEPRECATED: handle CO-RE relocations non-strictly, allowing failures. + * Value is ignored. Relocations always are processed non-strictly. + * Non-relocatable instructions are replaced with invalid ones to + * prevent accidental errors. + * */ bool relaxed_core_relocs; /* maps that set the 'pinning' attribute in their definition will have * their pin_path attribute set to a file in this directory, and be @@ -109,15 +89,19 @@ struct bpf_object_open_opts { */ const char *pin_root_path; __u32 attach_prog_fd; + /* Additional kernel config content that augments and overrides + * system Kconfig for CONFIG_xxx externs. + */ + const char *kconfig; }; -#define bpf_object_open_opts__last_field attach_prog_fd +#define bpf_object_open_opts__last_field kconfig LIBBPF_API struct bpf_object *bpf_object__open(const char *path); LIBBPF_API struct bpf_object * -bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts); +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); LIBBPF_API struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts); + const struct bpf_object_open_opts *opts); /* deprecated bpf_object__open variants */ LIBBPF_API struct bpf_object * @@ -126,11 +110,6 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, LIBBPF_API struct bpf_object * bpf_object__open_xattr(struct bpf_object_open_attr *attr); -int bpf_object__section_size(const struct bpf_object *obj, const char *name, - __u32 *size); -int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, - __u32 *off); - enum libbpf_pin_type { LIBBPF_PIN_NONE, /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ @@ -161,6 +140,7 @@ struct bpf_object_load_attr { LIBBPF_API int bpf_object__load(struct bpf_object *obj); LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); LIBBPF_API int bpf_object__unload(struct bpf_object *obj); + LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); @@ -171,6 +151,9 @@ LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * bpf_object__find_program_by_title(const struct bpf_object *obj, const char *title); +LIBBPF_API struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name); LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -214,6 +197,7 @@ LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); +LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog); LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy); @@ -235,9 +219,12 @@ LIBBPF_API void bpf_program__unload(struct bpf_program *prog); struct bpf_link; +LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); LIBBPF_API struct bpf_link * +bpf_program__attach(struct bpf_program *prog); +LIBBPF_API struct bpf_link * bpf_program__attach_perf_event(struct bpf_program *prog, int pfd); LIBBPF_API struct bpf_link * bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe, @@ -256,6 +243,8 @@ bpf_program__attach_raw_tracepoint(struct bpf_program *prog, LIBBPF_API struct bpf_link * bpf_program__attach_trace(struct bpf_program *prog); +struct bpf_map; +LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); struct bpf_insn; /* @@ -332,6 +321,8 @@ LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog); LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog); LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, @@ -352,6 +343,8 @@ LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog); /* * No need for __attribute__((packed)), all members of 'bpf_map_def' @@ -371,7 +364,6 @@ struct bpf_map_def { * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, * so no need to worry about a name clash. */ -struct bpf_map; LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); @@ -512,18 +504,6 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, bpf_perf_event_print_t fn, void *private_data); -struct nlattr; -typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); -int libbpf_netlink_open(unsigned int *nl_pid); -int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); -int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); -int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); -int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, - libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); - struct bpf_prog_linfo; struct bpf_prog_info; @@ -550,6 +530,7 @@ LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex); LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex); +LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex); /* * Get bpf_prog_info in continuous memory @@ -630,6 +611,50 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); */ LIBBPF_API int libbpf_num_possible_cpus(void); +struct bpf_map_skeleton { + const char *name; + struct bpf_map **map; + void **mmaped; +}; + +struct bpf_prog_skeleton { + const char *name; + struct bpf_program **prog; + struct bpf_link **link; +}; + +struct bpf_object_skeleton { + size_t sz; /* size of this struct, for forward/backward compatibility */ + + const char *name; + void *data; + size_t data_sz; + + struct bpf_object **obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */ + struct bpf_prog_skeleton *progs; +}; + +LIBBPF_API int +bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts); +LIBBPF_API int bpf_object__load_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); + +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 8ddc2c40e482..b035122142bb 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -208,3 +208,30 @@ LIBBPF_0.0.6 { btf__find_by_name_kind; libbpf_find_vmlinux_btf_id; } LIBBPF_0.0.5; + +LIBBPF_0.0.7 { + global: + btf_dump__emit_type_decl; + bpf_link__disconnect; + bpf_map__attach_struct_ops; + bpf_map_delete_batch; + bpf_map_lookup_and_delete_batch; + bpf_map_lookup_batch; + bpf_map_update_batch; + bpf_object__find_program_by_name; + bpf_object__attach_skeleton; + bpf_object__destroy_skeleton; + bpf_object__detach_skeleton; + bpf_object__load_skeleton; + bpf_object__open_skeleton; + bpf_probe_large_insn_limit; + bpf_prog_attach_xattr; + bpf_program__attach; + bpf_program__name; + bpf_program__is_extension; + bpf_program__is_struct_ops; + bpf_program__set_extension; + bpf_program__set_struct_ops; + btf__align_of; + libbpf_find_kernel_btf; +} LIBBPF_0.0.6; diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template index ac17fcef2108..b45ed534bdfb 100644 --- a/tools/lib/bpf/libbpf.pc.template +++ b/tools/lib/bpf/libbpf.pc.template @@ -8,5 +8,5 @@ Name: libbpf Description: BPF library Version: @VERSION@ Libs: -L${libdir} -lbpf -Requires.private: libelf +Requires.private: libelf zlib Cflags: -I${includedir} diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h new file mode 100644 index 000000000000..a23ae1ac27eb --- /dev/null +++ b/tools/lib/bpf/libbpf_common.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Common user-facing libbpf helpers. + * + * Copyright (c) 2019 Facebook + */ + +#ifndef __LIBBPF_LIBBPF_COMMON_H +#define __LIBBPF_LIBBPF_COMMON_H + +#include <string.h> + +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + +/* Helper macro to declare and initialize libbpf options struct + * + * This dance with uninitialized declaration, followed by memset to zero, + * followed by assignment using compound literal syntax is done to preserve + * ability to use a nice struct field initialization syntax and **hopefully** + * have all the padding bytes initialized to zero. It's not guaranteed though, + * when copying literal, that compiler won't copy garbage in literal's padding + * bytes, but that's the best way I've found and it seems to work in practice. + * + * Macro declares opts struct of given type and name, zero-initializes, + * including any extra padding, it with memset() and then assigns initial + * values provided by users in struct initializer-syntax as varargs. + */ +#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ + struct TYPE NAME = ({ \ + memset(&NAME, 0, sizeof(struct TYPE)); \ + (struct TYPE) { \ + .sz = sizeof(struct TYPE), \ + __VA_ARGS__ \ + }; \ + }) + +#endif /* __LIBBPF_LIBBPF_COMMON_H */ diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c index 4343e40588c6..0afb51f7a919 100644 --- a/tools/lib/bpf/libbpf_errno.c +++ b/tools/lib/bpf/libbpf_errno.c @@ -13,6 +13,9 @@ #include "libbpf.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) #define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) #define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 97ac17a64a58..8c3afbd97747 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -76,7 +76,7 @@ static inline bool libbpf_validate_opts(const char *opts, for (i = opts_sz; i < user_sz; i++) { if (opts[i]) { - pr_warn("%s has non-zero extra bytes", + pr_warn("%s has non-zero extra bytes\n", type_name); return false; } @@ -95,9 +95,28 @@ static inline bool libbpf_validate_opts(const char *opts, #define OPTS_GET(opts, field, fallback_value) \ (OPTS_HAS(opts, field) ? (opts)->field : fallback_value) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size); +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off); + +struct nlattr; +typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); +int libbpf_netlink_open(unsigned int *nl_pid); +int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); +int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); +int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); +int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); + struct btf_ext_info { /* * info points to the individual info section (e.g. func_info and diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index a9eb8b322671..b782ebef6ac9 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -17,6 +17,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + static bool grep(const char *buffer, const char *pattern) { return !!strstr(buffer, pattern); @@ -103,6 +106,8 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_STRUCT_OPS: + case BPF_PROG_TYPE_EXT: default: break; } @@ -251,6 +256,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_XSKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: + case BPF_MAP_TYPE_STRUCT_OPS: default: break; } @@ -321,3 +327,24 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, return res; } + +/* + * Probe for availability of kernel commit (5.3): + * + * c04c0d2b968a ("bpf: increase complexity limit and maximum program size") + */ +bool bpf_probe_large_insn_limit(__u32 ifindex) +{ + struct bpf_insn insns[BPF_MAXINSNS + 1]; + int i; + + for (i = 0; i < BPF_MAXINSNS; i++) + insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); + insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); + + errno = 0; + probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0, + ifindex); + + return errno != E2BIG && errno != EINVAL; +} diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 5065c1aa1061..431bd25c6cdb 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -15,6 +15,9 @@ #include "libbpf_internal.h" #include "nlattr.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #ifndef SOL_NETLINK #define SOL_NETLINK 270 #endif diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 8db44bbfc66d..0ad41dfea8eb 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -13,6 +13,9 @@ #include <string.h> #include <stdio.h> +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = { [LIBBPF_NLA_U8] = sizeof(uint8_t), [LIBBPF_NLA_U16] = sizeof(uint16_t), diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c index b8064eedc177..146da01979c7 100644 --- a/tools/lib/bpf/str_error.c +++ b/tools/lib/bpf/str_error.c @@ -4,6 +4,9 @@ #include <stdio.h> #include "str_error.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl * libc, while checking strerror_r() return to avoid having to check this in diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 8e0ffa800a71..9807903f121e 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -32,6 +32,9 @@ #include "libbpf_internal.h" #include "xsk.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #ifndef SOL_XDP #define SOL_XDP 283 #endif diff --git a/tools/perf/lib/Build b/tools/lib/perf/Build index 2ef9a4ec6d99..2ef9a4ec6d99 100644 --- a/tools/perf/lib/Build +++ b/tools/lib/perf/Build diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile new file mode 100644 index 000000000000..972754082a85 --- /dev/null +++ b/tools/lib/perf/Documentation/Makefile @@ -0,0 +1,156 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/perf/Documentation/Makefile + +include ../../../scripts/Makefile.include +include ../../../scripts/utilities.mak + +MAN3_TXT = libperf.txt +MAN7_TXT = libperf-counting.txt libperf-sampling.txt +MAN_EX = examples/*.c + +MAN_TXT = $(MAN3_TXT) $(MAN7_TXT) + +_MAN_XML = $(patsubst %.txt,%.xml,$(MAN_TXT)) +_MAN_HTML = $(patsubst %.txt,%.html,$(MAN_TXT)) +_MAN_3 = $(patsubst %.txt,%.3,$(MAN3_TXT)) +_MAN_7 = $(patsubst %.txt,%.7,$(MAN7_TXT)) + +MAN_XML = $(addprefix $(OUTPUT),$(_MAN_XML)) +MAN_HTML = $(addprefix $(OUTPUT),$(_MAN_HTML)) +MAN_3 = $(addprefix $(OUTPUT),$(_MAN_3)) +MAN_7 = $(addprefix $(OUTPUT),$(_MAN_7)) +MAN_X = $(MAN_3) $(MAN_7) + +# Make the path relative to DESTDIR, not prefix +ifndef DESTDIR + prefix ?=$(HOME) +endif + +mandir ?= $(prefix)/share/man +man3dir = $(mandir)/man3 +man7dir = $(mandir)/man7 + +docdir ?= $(prefix)/share/doc/libperf +htmldir = $(docdir)/html +exdir = $(docdir)/examples + +ASCIIDOC = asciidoc +ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf +ASCIIDOC_HTML = xhtml11 +MANPAGE_XSL = manpage-normal.xsl +XMLTO_EXTRA = +XMLTO =xmlto + +INSTALL ?= install +RM ?= rm -f + +# For asciidoc ... +# -7.1.2, no extra settings are needed. +# 8.0-, set ASCIIDOC8. +# + +# For docbook-xsl ... +# -1.68.1, set ASCIIDOC_NO_ROFF? (based on changelog from 1.73.0) +# 1.69.0, no extra settings are needed? +# 1.69.1-1.71.0, set DOCBOOK_SUPPRESS_SP? +# 1.71.1, no extra settings are needed? +# 1.72.0, set DOCBOOK_XSL_172. +# 1.73.0-, set ASCIIDOC_NO_ROFF + +# If you had been using DOCBOOK_XSL_172 in an attempt to get rid +# of 'the ".ft C" problem' in your generated manpages, and you +# instead ended up with weird characters around callouts, try +# using ASCIIDOC_NO_ROFF instead (it works fine with ASCIIDOC8). + +ifdef ASCIIDOC8 + ASCIIDOC_EXTRA += -a asciidoc7compatible +endif +ifdef DOCBOOK_XSL_172 + ASCIIDOC_EXTRA += -a libperf-asciidoc-no-roff + MANPAGE_XSL = manpage-1.72.xsl +else + ifdef ASCIIDOC_NO_ROFF + # docbook-xsl after 1.72 needs the regular XSL, but will not + # pass-thru raw roff codes from asciidoc.conf, so turn them off. + ASCIIDOC_EXTRA += -a libperf-asciidoc-no-roff + endif +endif +ifdef MAN_BOLD_LITERAL + XMLTO_EXTRA += -m manpage-bold-literal.xsl +endif +ifdef DOCBOOK_SUPPRESS_SP + XMLTO_EXTRA += -m manpage-suppress-sp.xsl +endif + +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +export DESTDIR DESTDIR_SQ + +# Please note that there is a minor bug in asciidoc. +# The version after 6.0.3 _will_ include the patch found here: +# http://marc.theaimsgroup.com/?l=libtraceevent&m=111558757202243&w=2 +# +# Until that version is released you may have to apply the patch +# yourself - yes, all 6 characters of it! + +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),w),w) + PRINT_DIR = --no-print-directory +else # "make -w" + NO_SUBDIR = : +endif + +ifneq ($(findstring $(MAKEFLAGS),s),s) + ifneq ($(V),1) + QUIET_ASCIIDOC = @echo ' ASCIIDOC '$@; + QUIET_XMLTO = @echo ' XMLTO '$@; + endif +endif + +all: $(MAN_X) $(MAN_HTML) + +$(MAN_HTML) $(MAN_X): asciidoc.conf + +install-man: all + $(call QUIET_INSTALL, man) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man3dir); \ + $(INSTALL) -m 644 $(MAN_3) $(DESTDIR)$(man3dir); \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \ + $(INSTALL) -m 644 $(MAN_7) $(DESTDIR)$(man7dir); + +install-html: + $(call QUIET_INSTALL, html) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(htmldir); \ + $(INSTALL) -m 644 $(MAN_HTML) $(DESTDIR)$(htmldir); \ + +install-examples: + $(call QUIET_INSTALL, examples) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(exdir); \ + $(INSTALL) -m 644 $(MAN_EX) $(DESTDIR)$(exdir); \ + +CLEAN_FILES = \ + $(MAN_XML) $(addsuffix +,$(MAN_XML)) \ + $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) \ + $(MAN_X) + +clean: + $(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES) + +$(MAN_3): $(OUTPUT)%.3: %.xml + $(QUIET_XMLTO)$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + +$(MAN_7): $(OUTPUT)%.7: %.xml + $(QUIET_XMLTO)$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + +$(MAN_XML): $(OUTPUT)%.xml: %.txt + $(QUIET_ASCIIDOC)$(ASCIIDOC) -b docbook -d manpage \ + $(ASCIIDOC_EXTRA) -alibperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ + +$(MAN_HTML): $(OUTPUT)%.html: %.txt + $(QUIET_ASCIIDOC)$(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \ + $(ASCIIDOC_EXTRA) -aperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ diff --git a/tools/lib/perf/Documentation/asciidoc.conf b/tools/lib/perf/Documentation/asciidoc.conf new file mode 100644 index 000000000000..9d5a5a5ee091 --- /dev/null +++ b/tools/lib/perf/Documentation/asciidoc.conf @@ -0,0 +1,120 @@ +## linktep: macro +# +# Usage: linktep:command[manpage-section] +# +# Note, {0} is the manpage section, while {target} is the command. +# +# Show TEP link as: <command>(<section>); if section is defined, else just show +# the command. + +[macros] +(?su)[\\]?(?P<name>linktep):(?P<target>\S*?)\[(?P<attrlist>.*?)\]= + +[attributes] +asterisk=* +plus=+ +caret=^ +startsb=[ +endsb=] +tilde=~ + +ifdef::backend-docbook[] +[linktep-inlinemacro] +{0%{target}} +{0#<citerefentry>} +{0#<refentrytitle>{target}</refentrytitle><manvolnum>{0}</manvolnum>} +{0#</citerefentry>} +endif::backend-docbook[] + +ifdef::backend-docbook[] +ifndef::tep-asciidoc-no-roff[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +# v1.72 breaks with this because it replaces dots not in roff requests. +[listingblock] +<example><title>{title}</title> +<literallayout> +ifdef::doctype-manpage[] + .ft C +endif::doctype-manpage[] +| +ifdef::doctype-manpage[] + .ft +endif::doctype-manpage[] +</literallayout> +{title#}</example> +endif::tep-asciidoc-no-roff[] + +ifdef::tep-asciidoc-no-roff[] +ifdef::doctype-manpage[] +# The following two small workarounds insert a simple paragraph after screen +[listingblock] +<example><title>{title}</title> +<literallayout> +| +</literallayout><simpara></simpara> +{title#}</example> + +[verseblock] +<formalpara{id? id="{id}"}><title>{title}</title><para> +{title%}<literallayout{id? id="{id}"}> +{title#}<literallayout> +| +</literallayout> +{title#}</para></formalpara> +{title%}<simpara></simpara> +endif::doctype-manpage[] +endif::tep-asciidoc-no-roff[] +endif::backend-docbook[] + +ifdef::doctype-manpage[] +ifdef::backend-docbook[] +[header] +template::[header-declarations] +<refentry> +<refmeta> +<refentrytitle>{mantitle}</refentrytitle> +<manvolnum>{manvolnum}</manvolnum> +<refmiscinfo class="source">libperf</refmiscinfo> +<refmiscinfo class="version">{libperf_version}</refmiscinfo> +<refmiscinfo class="manual">libperf Manual</refmiscinfo> +</refmeta> +<refnamediv> + <refname>{manname1}</refname> + <refname>{manname2}</refname> + <refname>{manname3}</refname> + <refname>{manname4}</refname> + <refname>{manname5}</refname> + <refname>{manname6}</refname> + <refname>{manname7}</refname> + <refname>{manname8}</refname> + <refname>{manname9}</refname> + <refname>{manname10}</refname> + <refname>{manname11}</refname> + <refname>{manname12}</refname> + <refname>{manname13}</refname> + <refname>{manname14}</refname> + <refname>{manname15}</refname> + <refname>{manname16}</refname> + <refname>{manname17}</refname> + <refname>{manname18}</refname> + <refname>{manname19}</refname> + <refname>{manname20}</refname> + <refname>{manname21}</refname> + <refname>{manname22}</refname> + <refname>{manname23}</refname> + <refname>{manname24}</refname> + <refname>{manname25}</refname> + <refname>{manname26}</refname> + <refname>{manname27}</refname> + <refname>{manname28}</refname> + <refname>{manname29}</refname> + <refname>{manname30}</refname> + <refpurpose>{manpurpose}</refpurpose> +</refnamediv> +endif::backend-docbook[] +endif::doctype-manpage[] + +ifdef::backend-xhtml11[] +[linktep-inlinemacro] +<a href="{target}.html">{target}{0?({0})}</a> +endif::backend-xhtml11[] diff --git a/tools/lib/perf/Documentation/examples/sampling.c b/tools/lib/perf/Documentation/examples/sampling.c new file mode 100644 index 000000000000..8e1a926a9cfe --- /dev/null +++ b/tools/lib/perf/Documentation/examples/sampling.c @@ -0,0 +1,119 @@ +#include <linux/perf_event.h> +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <perf/mmap.h> +#include <perf/core.h> +#include <perf/event.h> +#include <stdio.h> +#include <unistd.h> + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +union u64_swap { + __u64 val64; + __u32 val32[2]; +}; + +int main(int argc, char **argv) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_mmap *map; + struct perf_cpu_map *cpus; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .disabled = 1, + .freq = 1, + .sample_freq = 10, + .sample_type = PERF_SAMPLE_IP|PERF_SAMPLE_TID|PERF_SAMPLE_CPU|PERF_SAMPLE_PERIOD, + }; + int err = -1; + union perf_event *event; + + libperf_init(libperf_print); + + cpus = perf_cpu_map__new(NULL); + if (!cpus) { + fprintf(stderr, "failed to create cpus\n"); + return -1; + } + + evlist = perf_evlist__new(); + if (!evlist) { + fprintf(stderr, "failed to create evlist\n"); + goto out_cpus; + } + + evsel = perf_evsel__new(&attr); + if (!evsel) { + fprintf(stderr, "failed to create cycles\n"); + goto out_cpus; + } + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, cpus, NULL); + + err = perf_evlist__open(evlist); + if (err) { + fprintf(stderr, "failed to open evlist\n"); + goto out_evlist; + } + + err = perf_evlist__mmap(evlist, 4); + if (err) { + fprintf(stderr, "failed to mmap evlist\n"); + goto out_evlist; + } + + perf_evlist__enable(evlist); + sleep(3); + perf_evlist__disable(evlist); + + perf_evlist__for_each_mmap(evlist, map, false) { + if (perf_mmap__read_init(map) < 0) + continue; + + while ((event = perf_mmap__read_event(map)) != NULL) { + int cpu, pid, tid; + __u64 ip, period, *array; + union u64_swap u; + + array = event->sample.array; + + ip = *array; + array++; + + u.val64 = *array; + pid = u.val32[0]; + tid = u.val32[1]; + array++; + + u.val64 = *array; + cpu = u.val32[0]; + array++; + + period = *array; + + fprintf(stdout, "cpu %3d, pid %6d, tid %6d, ip %20llx, period %20llu\n", + cpu, pid, tid, ip, period); + + perf_mmap__consume(map); + } + + perf_mmap__read_done(map); + } + +out_evlist: + perf_evlist__delete(evlist); +out_cpus: + perf_cpu_map__put(cpus); + return err; +} diff --git a/tools/lib/perf/Documentation/libperf-counting.txt b/tools/lib/perf/Documentation/libperf-counting.txt new file mode 100644 index 000000000000..cae9757f49c1 --- /dev/null +++ b/tools/lib/perf/Documentation/libperf-counting.txt @@ -0,0 +1,211 @@ +libperf-counting(7) +=================== + +NAME +---- +libperf-counting - counting interface + +DESCRIPTION +----------- +The counting interface provides API to meassure and get count for specific perf events. + +The following test tries to explain count on `counting.c` example. + +It is by no means complete guide to counting, but shows libperf basic API for counting. + +The `counting.c` comes with libbperf package and can be compiled and run like: + +[source,bash] +-- +$ gcc -o counting counting.c -lperf +$ sudo ./counting +count 176792, enabled 176944, run 176944 +count 176242, enabled 176242, run 176242 +-- + +It requires root access, because of the `PERF_COUNT_SW_CPU_CLOCK` event, +which is available only for root. + +The `counting.c` example monitors two events on the current process and displays their count, in a nutshel it: + +* creates events +* adds them to the event list +* opens and enables events through the event list +* does some workload +* disables events +* reads and displays event counts +* destroys the event list + +The first thing you need to do before using libperf is to call init function: + +[source,c] +-- + 8 static int libperf_print(enum libperf_print_level level, + 9 const char *fmt, va_list ap) + 10 { + 11 return vfprintf(stderr, fmt, ap); + 12 } + + 14 int main(int argc, char **argv) + 15 { + ... + 35 libperf_init(libperf_print); +-- + +It will setup the library and sets function for debug output from library. + +The `libperf_print` callback will receive any message with its debug level, +defined as: + +[source,c] +-- +enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, +}; +-- + +Once the setup is complete we start by defining specific events using the `struct perf_event_attr`. + +We create software events for cpu and task: + +[source,c] +-- + 20 struct perf_event_attr attr1 = { + 21 .type = PERF_TYPE_SOFTWARE, + 22 .config = PERF_COUNT_SW_CPU_CLOCK, + 23 .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING, + 24 .disabled = 1, + 25 }; + 26 struct perf_event_attr attr2 = { + 27 .type = PERF_TYPE_SOFTWARE, + 28 .config = PERF_COUNT_SW_TASK_CLOCK, + 29 .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING, + 30 .disabled = 1, + 31 }; +-- + +The `read_format` setup tells perf to include timing details together with each count. + +Next step is to prepare threads map. + +In this case we will monitor current process, so we create threads map with single pid (0): + +[source,c] +-- + 37 threads = perf_thread_map__new_dummy(); + 38 if (!threads) { + 39 fprintf(stderr, "failed to create threads\n"); + 40 return -1; + 41 } + 42 + 43 perf_thread_map__set_pid(threads, 0, 0); +-- + +Now we create libperf's event list, which will serve as holder for the events we want: + +[source,c] +-- + 45 evlist = perf_evlist__new(); + 46 if (!evlist) { + 47 fprintf(stderr, "failed to create evlist\n"); + 48 goto out_threads; + 49 } +-- + +We create libperf's events for the attributes we defined earlier and add them to the list: + +[source,c] +-- + 51 evsel = perf_evsel__new(&attr1); + 52 if (!evsel) { + 53 fprintf(stderr, "failed to create evsel1\n"); + 54 goto out_evlist; + 55 } + 56 + 57 perf_evlist__add(evlist, evsel); + 58 + 59 evsel = perf_evsel__new(&attr2); + 60 if (!evsel) { + 61 fprintf(stderr, "failed to create evsel2\n"); + 62 goto out_evlist; + 63 } + 64 + 65 perf_evlist__add(evlist, evsel); +-- + +Configure event list with the thread map and open events: + +[source,c] +-- + 67 perf_evlist__set_maps(evlist, NULL, threads); + 68 + 69 err = perf_evlist__open(evlist); + 70 if (err) { + 71 fprintf(stderr, "failed to open evsel\n"); + 72 goto out_evlist; + 73 } +-- + +Both events are created as disabled (note the `disabled = 1` assignment above), +so we need to enable the whole list explicitely (both events). + +From this moment events are counting and we can do our workload. + +When we are done we disable the events list. + +[source,c] +-- + 75 perf_evlist__enable(evlist); + 76 + 77 while (count--); + 78 + 79 perf_evlist__disable(evlist); +-- + +Now we need to get the counts from events, following code iterates throught the events list and read counts: + +[source,c] +-- + 81 perf_evlist__for_each_evsel(evlist, evsel) { + 82 perf_evsel__read(evsel, 0, 0, &counts); + 83 fprintf(stdout, "count %llu, enabled %llu, run %llu\n", + 84 counts.val, counts.ena, counts.run); + 85 } +-- + +And finaly cleanup. + +We close the whole events list (both events) and remove it together with the threads map: + +[source,c] +-- + 87 perf_evlist__close(evlist); + 88 + 89 out_evlist: + 90 perf_evlist__delete(evlist); + 91 out_threads: + 92 perf_thread_map__put(threads); + 93 return err; + 94 } +-- + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf(3), libperf-sampling(7) diff --git a/tools/lib/perf/Documentation/libperf-sampling.txt b/tools/lib/perf/Documentation/libperf-sampling.txt new file mode 100644 index 000000000000..d71a7b4fcf5f --- /dev/null +++ b/tools/lib/perf/Documentation/libperf-sampling.txt @@ -0,0 +1,243 @@ +libperf-sampling(7) +=================== + +NAME +---- +libperf-sampling - sampling interface + + +DESCRIPTION +----------- +The sampling interface provides API to meassure and get count for specific perf events. + +The following test tries to explain count on `sampling.c` example. + +It is by no means complete guide to sampling, but shows libperf basic API for sampling. + +The `sampling.c` comes with libbperf package and can be compiled and run like: + +[source,bash] +-- +$ gcc -o sampling sampling.c -lperf +$ sudo ./sampling +cpu 0, pid 0, tid 0, ip ffffffffad06c4e6, period 1 +cpu 0, pid 4465, tid 4469, ip ffffffffad118748, period 18322959 +cpu 0, pid 0, tid 0, ip ffffffffad115722, period 33544846 +cpu 0, pid 4465, tid 4470, ip 7f84fe0cdad6, period 23687474 +cpu 0, pid 0, tid 0, ip ffffffffad9e0349, period 34255790 +cpu 0, pid 4465, tid 4469, ip ffffffffad136581, period 38664069 +cpu 0, pid 0, tid 0, ip ffffffffad9e55e2, period 21922384 +cpu 0, pid 4465, tid 4470, ip 7f84fe0ebebf, period 17655175 +... +-- + +It requires root access, because it uses hardware cycles event. + +The `sampling.c` example profiles/samples all CPUs with hardware cycles, in a nutshel it: + +- creates events +- adds them to the event list +- opens and enables events through the event list +- sleeps for 3 seconds +- disables events +- reads and displays recorded samples +- destroys the event list + +The first thing you need to do before using libperf is to call init function: + +[source,c] +-- + 12 static int libperf_print(enum libperf_print_level level, + 13 const char *fmt, va_list ap) + 14 { + 15 return vfprintf(stderr, fmt, ap); + 16 } + + 23 int main(int argc, char **argv) + 24 { + ... + 40 libperf_init(libperf_print); +-- + +It will setup the library and sets function for debug output from library. + +The `libperf_print` callback will receive any message with its debug level, +defined as: + +[source,c] +-- +enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, +}; +-- + +Once the setup is complete we start by defining cycles event using the `struct perf_event_attr`: + +[source,c] +-- + 29 struct perf_event_attr attr = { + 30 .type = PERF_TYPE_HARDWARE, + 31 .config = PERF_COUNT_HW_CPU_CYCLES, + 32 .disabled = 1, + 33 .freq = 1, + 34 .sample_freq = 10, + 35 .sample_type = PERF_SAMPLE_IP|PERF_SAMPLE_TID|PERF_SAMPLE_CPU|PERF_SAMPLE_PERIOD, + 36 }; +-- + +Next step is to prepare cpus map. + +In this case we will monitor all the available CPUs: + +[source,c] +-- + 42 cpus = perf_cpu_map__new(NULL); + 43 if (!cpus) { + 44 fprintf(stderr, "failed to create cpus\n"); + 45 return -1; + 46 } +-- + +Now we create libperf's event list, which will serve as holder for the cycles event: + +[source,c] +-- + 48 evlist = perf_evlist__new(); + 49 if (!evlist) { + 50 fprintf(stderr, "failed to create evlist\n"); + 51 goto out_cpus; + 52 } +-- + +We create libperf's event for the cycles attribute we defined earlier and add it to the list: + +[source,c] +-- + 54 evsel = perf_evsel__new(&attr); + 55 if (!evsel) { + 56 fprintf(stderr, "failed to create cycles\n"); + 57 goto out_cpus; + 58 } + 59 + 60 perf_evlist__add(evlist, evsel); +-- + +Configure event list with the cpus map and open event: + +[source,c] +-- + 62 perf_evlist__set_maps(evlist, cpus, NULL); + 63 + 64 err = perf_evlist__open(evlist); + 65 if (err) { + 66 fprintf(stderr, "failed to open evlist\n"); + 67 goto out_evlist; + 68 } +-- + +Once the events list is open, we can create memory maps AKA perf ring buffers: + +[source,c] +-- + 70 err = perf_evlist__mmap(evlist, 4); + 71 if (err) { + 72 fprintf(stderr, "failed to mmap evlist\n"); + 73 goto out_evlist; + 74 } +-- + +The event is created as disabled (note the `disabled = 1` assignment above), +so we need to enable the events list explicitely. + +From this moment the cycles event is sampling. + +We will sleep for 3 seconds while the ring buffers get data from all CPUs, then we disable the events list. + +[source,c] +-- + 76 perf_evlist__enable(evlist); + 77 sleep(3); + 78 perf_evlist__disable(evlist); +-- + +Following code walks through the ring buffers and reads stored events/samples: + +[source,c] +-- + 80 perf_evlist__for_each_mmap(evlist, map, false) { + 81 if (perf_mmap__read_init(map) < 0) + 82 continue; + 83 + 84 while ((event = perf_mmap__read_event(map)) != NULL) { + + /* process event */ + +108 perf_mmap__consume(map); +109 } +110 perf_mmap__read_done(map); +111 } + +-- + +Each sample needs to get parsed: + +[source,c] +-- + 85 int cpu, pid, tid; + 86 __u64 ip, period, *array; + 87 union u64_swap u; + 88 + 89 array = event->sample.array; + 90 + 91 ip = *array; + 92 array++; + 93 + 94 u.val64 = *array; + 95 pid = u.val32[0]; + 96 tid = u.val32[1]; + 97 array++; + 98 + 99 u.val64 = *array; +100 cpu = u.val32[0]; +101 array++; +102 +103 period = *array; +104 +105 fprintf(stdout, "cpu %3d, pid %6d, tid %6d, ip %20llx, period %20llu\n", +106 cpu, pid, tid, ip, period); +-- + +And finaly cleanup. + +We close the whole events list (both events) and remove it together with the threads map: + +[source,c] +-- +113 out_evlist: +114 perf_evlist__delete(evlist); +115 out_cpus: +116 perf_cpu_map__put(cpus); +117 return err; +118 } +-- + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf(3), libperf-counting(7) diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt new file mode 100644 index 000000000000..5a6bb512789d --- /dev/null +++ b/tools/lib/perf/Documentation/libperf.txt @@ -0,0 +1,246 @@ +libperf(3) +========== + +NAME +---- +libperf - Linux kernel perf event library + + +SYNOPSIS +-------- +*Generic API:* + +[source,c] +-- + #include <perf/core.h> + + enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, + }; + + typedef int (*libperf_print_fn_t)(enum libperf_print_level level, + const char *, va_list ap); + + void libperf_init(libperf_print_fn_t fn); +-- + +*API to handle cpu maps:* + +[source,c] +-- + #include <perf/cpumap.h> + + struct perf_cpu_map; + + struct perf_cpu_map *perf_cpu_map__dummy_new(void); + struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); + struct perf_cpu_map *perf_cpu_map__read(FILE *file); + struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); + struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other); + void perf_cpu_map__put(struct perf_cpu_map *map); + int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); + int perf_cpu_map__nr(const struct perf_cpu_map *cpus); + bool perf_cpu_map__empty(const struct perf_cpu_map *map); + int perf_cpu_map__max(struct perf_cpu_map *map); + + #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) +-- + +*API to handle thread maps:* + +[source,c] +-- + #include <perf/threadmap.h> + + struct perf_thread_map; + + struct perf_thread_map *perf_thread_map__new_dummy(void); + + void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid); + char *perf_thread_map__comm(struct perf_thread_map *map, int thread); + int perf_thread_map__nr(struct perf_thread_map *threads); + pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread); + + struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); + void perf_thread_map__put(struct perf_thread_map *map); +-- + +*API to handle event lists:* + +[source,c] +-- + #include <perf/evlist.h> + + struct perf_evlist; + + void perf_evlist__add(struct perf_evlist *evlist, + struct perf_evsel *evsel); + void perf_evlist__remove(struct perf_evlist *evlist, + struct perf_evsel *evsel); + struct perf_evlist *perf_evlist__new(void); + void perf_evlist__delete(struct perf_evlist *evlist); + struct perf_evsel* perf_evlist__next(struct perf_evlist *evlist, + struct perf_evsel *evsel); + int perf_evlist__open(struct perf_evlist *evlist); + void perf_evlist__close(struct perf_evlist *evlist); + void perf_evlist__enable(struct perf_evlist *evlist); + void perf_evlist__disable(struct perf_evlist *evlist); + + #define perf_evlist__for_each_evsel(evlist, pos) + + void perf_evlist__set_maps(struct perf_evlist *evlist, + struct perf_cpu_map *cpus, + struct perf_thread_map *threads); + int perf_evlist__poll(struct perf_evlist *evlist, int timeout); + int perf_evlist__filter_pollfd(struct perf_evlist *evlist, + short revents_and_mask); + + int perf_evlist__mmap(struct perf_evlist *evlist, int pages); + void perf_evlist__munmap(struct perf_evlist *evlist); + + struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist, + struct perf_mmap *map, + bool overwrite); + + #define perf_evlist__for_each_mmap(evlist, pos, overwrite) +-- + +*API to handle events:* + +[source,c] +-- + #include <perf/evsel.h>* + + struct perf_evsel; + + struct perf_counts_values { + union { + struct { + uint64_t val; + uint64_t ena; + uint64_t run; + }; + uint64_t values[3]; + }; + }; + + struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr); + void perf_evsel__delete(struct perf_evsel *evsel); + int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); + void perf_evsel__close(struct perf_evsel *evsel); + void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count); + int perf_evsel__enable(struct perf_evsel *evsel); + int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__disable(struct perf_evsel *evsel); + int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); + struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); + struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); + struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); +-- + +*API to handle maps (perf ring buffers):* + +[source,c] +-- + #include <perf/mmap.h> + + struct perf_mmap; + + void perf_mmap__consume(struct perf_mmap *map); + int perf_mmap__read_init(struct perf_mmap *map); + void perf_mmap__read_done(struct perf_mmap *map); + union perf_event *perf_mmap__read_event(struct perf_mmap *map); +-- + +*Structures to access perf API events:* + +[source,c] +-- + #include <perf/event.h> + + struct perf_record_mmap; + struct perf_record_mmap2; + struct perf_record_comm; + struct perf_record_namespaces; + struct perf_record_fork; + struct perf_record_lost; + struct perf_record_lost_samples; + struct perf_record_read; + struct perf_record_throttle; + struct perf_record_ksymbol; + struct perf_record_bpf_event; + struct perf_record_sample; + struct perf_record_switch; + struct perf_record_header_attr; + struct perf_record_record_cpu_map; + struct perf_record_cpu_map_data; + struct perf_record_cpu_map; + struct perf_record_event_update_cpus; + struct perf_record_event_update_scale; + struct perf_record_event_update; + struct perf_trace_event_type; + struct perf_record_header_event_type; + struct perf_record_header_tracing_data; + struct perf_record_header_build_id; + struct perf_record_id_index; + struct perf_record_auxtrace_info; + struct perf_record_auxtrace; + struct perf_record_auxtrace_error; + struct perf_record_aux; + struct perf_record_itrace_start; + struct perf_record_thread_map_entry; + struct perf_record_thread_map; + struct perf_record_stat_config_entry; + struct perf_record_stat_config; + struct perf_record_stat; + struct perf_record_stat_round; + struct perf_record_time_conv; + struct perf_record_header_feature; + struct perf_record_compressed; +-- + +DESCRIPTION +----------- +The libperf library provides an API to access the linux kernel perf +events subsystem. + +Following objects are key to the libperf interface: + +[horizontal] + +struct perf_cpu_map:: Provides a cpu list abstraction. + +struct perf_thread_map:: Provides a thread list abstraction. + +struct perf_evsel:: Provides an abstraction for single a perf event. + +struct perf_evlist:: Gathers several struct perf_evsel object and performs functions on all of them. + +struct perf_mmap:: Provides an abstraction for accessing perf ring buffer. + +The exported API functions bind these objects together. + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf-sampling(7), libperf-counting(7) diff --git a/tools/lib/perf/Documentation/manpage-1.72.xsl b/tools/lib/perf/Documentation/manpage-1.72.xsl new file mode 100644 index 000000000000..b4d315cb8c47 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-1.72.xsl @@ -0,0 +1,14 @@ +<!-- manpage-1.72.xsl: + special settings for manpages rendered from asciidoc+docbook + handles peculiarities in docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the special values for the roff control characters + needed for docbook-xsl 1.72.0 --> +<xsl:param name="git.docbook.backslash">▓</xsl:param> +<xsl:param name="git.docbook.dot" >⌂</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-base.xsl b/tools/lib/perf/Documentation/manpage-base.xsl new file mode 100644 index 000000000000..a264fa616093 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-base.xsl @@ -0,0 +1,35 @@ +<!-- manpage-base.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- these params silence some output from xmlto --> +<xsl:param name="man.output.quietly" select="1"/> +<xsl:param name="refentry.meta.get.quietly" select="1"/> + +<!-- convert asciidoc callouts to man page format; + git.docbook.backslash and git.docbook.dot params + must be supplied by another XSL file or other means --> +<xsl:template match="co"> + <xsl:value-of select="concat( + $git.docbook.backslash,'fB(', + substring-after(@id,'-'),')', + $git.docbook.backslash,'fR')"/> +</xsl:template> +<xsl:template match="calloutlist"> + <xsl:value-of select="$git.docbook.dot"/> + <xsl:text>sp </xsl:text> + <xsl:apply-templates/> + <xsl:text> </xsl:text> +</xsl:template> +<xsl:template match="callout"> + <xsl:value-of select="concat( + $git.docbook.backslash,'fB', + substring-after(@arearefs,'-'), + '. ',$git.docbook.backslash,'fR')"/> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.dot"/> + <xsl:text>br </xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-bold-literal.xsl b/tools/lib/perf/Documentation/manpage-bold-literal.xsl new file mode 100644 index 000000000000..608eb5df6281 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-bold-literal.xsl @@ -0,0 +1,17 @@ +<!-- manpage-bold-literal.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- render literal text as bold (instead of plain or monospace); + this makes literal text easier to distinguish in manpages + viewed on a tty --> +<xsl:template match="literal"> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fB</xsl:text> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fR</xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-normal.xsl b/tools/lib/perf/Documentation/manpage-normal.xsl new file mode 100644 index 000000000000..a48f5b11f3dc --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-normal.xsl @@ -0,0 +1,13 @@ +<!-- manpage-normal.xsl: + special settings for manpages rendered from asciidoc+docbook + handles anything we want to keep away from docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the normal values for the roff control characters --> +<xsl:param name="git.docbook.backslash">\</xsl:param> +<xsl:param name="git.docbook.dot" >.</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-suppress-sp.xsl b/tools/lib/perf/Documentation/manpage-suppress-sp.xsl new file mode 100644 index 000000000000..a63c7632a87d --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-suppress-sp.xsl @@ -0,0 +1,21 @@ +<!-- manpage-suppress-sp.xsl: + special settings for manpages rendered from asciidoc+docbook + handles erroneous, inline .sp in manpage output of some + versions of docbook-xsl --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- attempt to work around spurious .sp at the tail of the line + that some versions of docbook stylesheets seem to add --> +<xsl:template match="simpara"> + <xsl:variable name="content"> + <xsl:apply-templates/> + </xsl:variable> + <xsl:value-of select="normalize-space($content)"/> + <xsl:if test="not(ancestor::authorblurb) and + not(ancestor::personblurb)"> + <xsl:text> </xsl:text> + </xsl:if> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/perf/lib/Makefile b/tools/lib/perf/Makefile index 0f233638ef1f..3718d65cffac 100644 --- a/tools/perf/lib/Makefile +++ b/tools/lib/perf/Makefile @@ -60,7 +60,7 @@ else endif INCLUDES = \ --I$(srctree)/tools/perf/lib/include \ +-I$(srctree)/tools/lib/perf/include \ -I$(srctree)/tools/lib/ \ -I$(srctree)/tools/include \ -I$(srctree)/tools/arch/$(SRCARCH)/include/ \ @@ -181,7 +181,10 @@ install_pkgconfig: $(LIBPERF_PC) $(call QUIET_INSTALL, $(LIBPERF_PC)) \ $(call do_install,$(LIBPERF_PC),$(libdir_SQ)/pkgconfig,644) -install: install_lib install_headers install_pkgconfig +install_doc: + $(Q)$(MAKE) -C Documentation install-man install-html install-examples + +install: install_lib install_headers install_pkgconfig install_doc FORCE: diff --git a/tools/perf/lib/core.c b/tools/lib/perf/core.c index 58fc894b76c5..58fc894b76c5 100644 --- a/tools/perf/lib/core.c +++ b/tools/lib/perf/core.c diff --git a/tools/perf/lib/cpumap.c b/tools/lib/perf/cpumap.c index f93f4e703e4c..f93f4e703e4c 100644 --- a/tools/perf/lib/cpumap.c +++ b/tools/lib/perf/cpumap.c diff --git a/tools/perf/lib/evlist.c b/tools/lib/perf/evlist.c index ae9e65aa2491..5b9f2ca50591 100644 --- a/tools/perf/lib/evlist.c +++ b/tools/lib/perf/evlist.c @@ -164,6 +164,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, evlist->threads = perf_thread_map__get(threads); } + if (!evlist->all_cpus && cpus) + evlist->all_cpus = perf_cpu_map__get(cpus); + perf_evlist__propagate_maps(evlist); } diff --git a/tools/perf/lib/evsel.c b/tools/lib/perf/evsel.c index 4dc06289f4c7..4dc06289f4c7 100644 --- a/tools/perf/lib/evsel.c +++ b/tools/lib/perf/evsel.c diff --git a/tools/perf/lib/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 840d4032587b..840d4032587b 100644 --- a/tools/perf/lib/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index 74dc8c3f0b66..74dc8c3f0b66 100644 --- a/tools/perf/lib/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h diff --git a/tools/perf/lib/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h index 1ffd083b235e..1ffd083b235e 100644 --- a/tools/perf/lib/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h diff --git a/tools/perf/lib/include/internal/lib.h b/tools/lib/perf/include/internal/lib.h index 5175d491b2d4..5175d491b2d4 100644 --- a/tools/perf/lib/include/internal/lib.h +++ b/tools/lib/perf/include/internal/lib.h diff --git a/tools/perf/lib/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h index be7556e0a2b2..be7556e0a2b2 100644 --- a/tools/perf/lib/include/internal/mmap.h +++ b/tools/lib/perf/include/internal/mmap.h diff --git a/tools/perf/lib/include/internal/tests.h b/tools/lib/perf/include/internal/tests.h index 2093e8868a67..2093e8868a67 100644 --- a/tools/perf/lib/include/internal/tests.h +++ b/tools/lib/perf/include/internal/tests.h diff --git a/tools/perf/lib/include/internal/threadmap.h b/tools/lib/perf/include/internal/threadmap.h index df748baf9eda..df748baf9eda 100644 --- a/tools/perf/lib/include/internal/threadmap.h +++ b/tools/lib/perf/include/internal/threadmap.h diff --git a/tools/perf/lib/include/internal/xyarray.h b/tools/lib/perf/include/internal/xyarray.h index 51e35d6c8ec4..51e35d6c8ec4 100644 --- a/tools/perf/lib/include/internal/xyarray.h +++ b/tools/lib/perf/include/internal/xyarray.h diff --git a/tools/perf/lib/include/perf/core.h b/tools/lib/perf/include/perf/core.h index a3f6d68edad7..a3f6d68edad7 100644 --- a/tools/perf/lib/include/perf/core.h +++ b/tools/lib/perf/include/perf/core.h diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 6a17ad730cbc..6a17ad730cbc 100644 --- a/tools/perf/lib/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h diff --git a/tools/perf/lib/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 18106899cb4e..18106899cb4e 100644 --- a/tools/perf/lib/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h diff --git a/tools/perf/lib/include/perf/evlist.h b/tools/lib/perf/include/perf/evlist.h index 0a7479dc13bf..0a7479dc13bf 100644 --- a/tools/perf/lib/include/perf/evlist.h +++ b/tools/lib/perf/include/perf/evlist.h diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h index c82ec39a4ad0..c82ec39a4ad0 100644 --- a/tools/perf/lib/include/perf/evsel.h +++ b/tools/lib/perf/include/perf/evsel.h diff --git a/tools/perf/lib/include/perf/mmap.h b/tools/lib/perf/include/perf/mmap.h index 9508ad90d8b9..9508ad90d8b9 100644 --- a/tools/perf/lib/include/perf/mmap.h +++ b/tools/lib/perf/include/perf/mmap.h diff --git a/tools/perf/lib/include/perf/threadmap.h b/tools/lib/perf/include/perf/threadmap.h index a7c50de8d010..a7c50de8d010 100644 --- a/tools/perf/lib/include/perf/threadmap.h +++ b/tools/lib/perf/include/perf/threadmap.h diff --git a/tools/perf/lib/internal.h b/tools/lib/perf/internal.h index 2c27e158de6b..2c27e158de6b 100644 --- a/tools/perf/lib/internal.h +++ b/tools/lib/perf/internal.h diff --git a/tools/perf/lib/lib.c b/tools/lib/perf/lib.c index 18658931fc71..18658931fc71 100644 --- a/tools/perf/lib/lib.c +++ b/tools/lib/perf/lib.c diff --git a/tools/perf/lib/libperf.map b/tools/lib/perf/libperf.map index 7be1af8a546c..7be1af8a546c 100644 --- a/tools/perf/lib/libperf.map +++ b/tools/lib/perf/libperf.map diff --git a/tools/perf/lib/libperf.pc.template b/tools/lib/perf/libperf.pc.template index 117e4a237b55..117e4a237b55 100644 --- a/tools/perf/lib/libperf.pc.template +++ b/tools/lib/perf/libperf.pc.template diff --git a/tools/perf/lib/mmap.c b/tools/lib/perf/mmap.c index 79d5ed6c38cc..79d5ed6c38cc 100644 --- a/tools/perf/lib/mmap.c +++ b/tools/lib/perf/mmap.c diff --git a/tools/perf/lib/tests/Makefile b/tools/lib/perf/tests/Makefile index a43cd08c5c03..96841775feaf 100644 --- a/tools/perf/lib/tests/Makefile +++ b/tools/lib/perf/tests/Makefile @@ -16,7 +16,7 @@ all: include $(srctree)/tools/scripts/Makefile.include -INCLUDE = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include -I$(srctree)/tools/lib +INCLUDE = -I$(srctree)/tools/lib/perf/include -I$(srctree)/tools/include -I$(srctree)/tools/lib $(TESTS_A): FORCE $(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -o $@ $(subst -a,.c,$@) ../libperf.a $(LIBAPI) diff --git a/tools/perf/lib/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c index c8d45091e7c2..c8d45091e7c2 100644 --- a/tools/perf/lib/tests/test-cpumap.c +++ b/tools/lib/perf/tests/test-cpumap.c diff --git a/tools/perf/lib/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c index 6d8ebe0c2504..6d8ebe0c2504 100644 --- a/tools/perf/lib/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c diff --git a/tools/perf/lib/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index 135722ac965b..135722ac965b 100644 --- a/tools/perf/lib/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c diff --git a/tools/perf/lib/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c index 7dc4d6fbedde..7dc4d6fbedde 100644 --- a/tools/perf/lib/tests/test-threadmap.c +++ b/tools/lib/perf/tests/test-threadmap.c diff --git a/tools/perf/lib/threadmap.c b/tools/lib/perf/threadmap.c index e92c368b0a6c..e92c368b0a6c 100644 --- a/tools/perf/lib/threadmap.c +++ b/tools/lib/perf/threadmap.c diff --git a/tools/perf/lib/xyarray.c b/tools/lib/perf/xyarray.c index dcd901d154bb..dcd901d154bb 100644 --- a/tools/perf/lib/xyarray.c +++ b/tools/lib/perf/xyarray.c diff --git a/tools/lib/string.c b/tools/lib/string.c index f2ae1b87c719..f645343815de 100644 --- a/tools/lib/string.c +++ b/tools/lib/string.c @@ -96,6 +96,10 @@ int strtobool(const char *s, bool *res) * If libc has strlcpy() then that version will override this * implementation: */ +#ifdef __clang__ +#pragma clang diagnostic push +#pragma clang diagnostic ignored "-Wignored-attributes" +#endif size_t __weak strlcpy(char *dest, const char *src, size_t size) { size_t ret = strlen(src); @@ -107,6 +111,9 @@ size_t __weak strlcpy(char *dest, const char *src, size_t size) } return ret; } +#ifdef __clang__ +#pragma clang diagnostic pop +#endif /** * skip_spaces - Removes leading whitespace from @str. diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index d2a19b0bc05a..ee08aeff30a1 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -2,10 +2,6 @@ include ../scripts/Makefile.include include ../scripts/Makefile.arch -ifeq ($(ARCH),x86_64) -ARCH := x86 -endif - # always use the host compiler HOSTAR ?= ar HOSTCC ?= gcc @@ -33,7 +29,7 @@ all: $(OBJTOOL) INCLUDES := -I$(srctree)/tools/include \ -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \ - -I$(srctree)/tools/arch/$(ARCH)/include + -I$(srctree)/tools/arch/$(SRCARCH)/include WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed CFLAGS := -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS) LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS) diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh index 9bd04bbed01e..2a1261bfbb62 100755 --- a/tools/objtool/sync-check.sh +++ b/tools/objtool/sync-check.sh @@ -48,5 +48,3 @@ check arch/x86/include/asm/inat.h '-I "^#include [\"<]\(asm/\)*inat_types.h[ check arch/x86/include/asm/insn.h '-I "^#include [\"<]\(asm/\)*inat.h[\">]"' check arch/x86/lib/inat.c '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"' check arch/x86/lib/insn.c '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]" -I "^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]"' - -cd - diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index e8c972f89357..1b5042f134a8 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -112,6 +112,12 @@ OPTIONS --objdump=<path>:: Path to objdump binary. +--prefix=PREFIX:: +--prefix-strip=N:: + Remove first N entries from source file path names in executables + and add PREFIX. This allows to display source code compiled on systems + with different file system layout. + --skip-missing:: Skip symbols that cannot be annotated. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 8dbe2119686a..db61f16ffa56 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -367,6 +367,12 @@ OPTIONS --objdump=<path>:: Path to objdump binary. +--prefix=PREFIX:: +--prefix-strip=N:: + Remove first N entries from source file path names in executables + and add PREFIX. This allows to display source code compiled on systems + with different file system layout. + --group:: Show event group information together. It forces group output also if there are no groups defined in data file. diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 63f938b887dd..5fbe42bd599b 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -110,6 +110,10 @@ OPTIONS for 'perf sched timehist' --max-stack:: Maximum number of functions to display in backtrace, default 5. +-C=:: +--cpu=:: + Only show events for the given CPU(s) (comma separated list). + -p=:: --pid=:: Only show events for given process ID (comma separated list). diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 5596129a71cf..324b6b53c86b 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -158,6 +158,12 @@ Default is to monitor all CPUS. -M:: --disassembler-style=:: Set disassembler style for objdump. +--prefix=PREFIX:: +--prefix-strip=N:: + Remove first N entries from source file path names in executables + and add PREFIX. This allows to display source code compiled on systems + with different file system layout. + --source:: Interleave source code with assembly code. Enabled by default, disable with --no-source. diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 4934edb5adfd..5d7b947320fb 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -7,6 +7,7 @@ tools/lib/traceevent tools/lib/api tools/lib/bpf tools/lib/subcmd +tools/lib/perf tools/lib/argv_split.c tools/lib/ctype.c tools/lib/hweight.c diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index c90f4146e5a2..80e55e796be9 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -286,7 +286,7 @@ ifeq ($(DEBUG),0) endif endif -INC_FLAGS += -I$(src-perf)/lib/include +INC_FLAGS += -I$(srctree)/tools/lib/perf/include INC_FLAGS += -I$(src-perf)/util/include INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include INC_FLAGS += -I$(srctree)/tools/include/ diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index eae5d5e95952..3eda9d4b88e7 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -230,7 +230,7 @@ LIB_DIR = $(srctree)/tools/lib/api/ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ BPF_DIR = $(srctree)/tools/lib/bpf/ SUBCMD_DIR = $(srctree)/tools/lib/subcmd/ -LIBPERF_DIR = $(srctree)/tools/perf/lib/ +LIBPERF_DIR = $(srctree)/tools/lib/perf/ # Set FEATURE_TESTS to 'all' so all possible feature checkers are executed. # Without this setting the output feature dump file misses some features, for diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index ede040cf82ad..2898cfdf8fe1 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -226,7 +226,7 @@ static int cs_etm_set_sink_attr(struct perf_pmu *pmu, if (term->type != PERF_EVSEL__CONFIG_TERM_DRV_CFG) continue; - sink = term->val.drv_cfg; + sink = term->val.str; snprintf(path, PATH_MAX, "sinks/%s", sink); ret = perf_pmu__scan_file(pmu, path, "%x", &hash); diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index a32e4b72a98f..d730666ab95d 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -1,8 +1,10 @@ #include <stdio.h> #include <stdlib.h> #include <perf/cpumap.h> +#include <util/cpumap.h> #include <internal/cpumap.h> #include <api/fs/fs.h> +#include <errno.h> #include "debug.h" #include "header.h" @@ -12,26 +14,21 @@ #define MIDR_VARIANT_SHIFT 20 #define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT) -char *get_cpuid_str(struct perf_pmu *pmu) +static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) { - char *buf = NULL; - char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); - int cpu; u64 midr = 0; - struct perf_cpu_map *cpus; - FILE *file; + int cpu; - if (!sysfs || !pmu || !pmu->cpus) - return NULL; + if (!sysfs || sz < MIDR_SIZE) + return EINVAL; - buf = malloc(MIDR_SIZE); - if (!buf) - return NULL; + cpus = perf_cpu_map__get(cpus); - /* read midr from list of cpus mapped to this pmu */ - cpus = perf_cpu_map__get(pmu->cpus); for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) { + char path[PATH_MAX]; + FILE *file; + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, sysfs, cpus->map[cpu]); @@ -57,12 +54,48 @@ char *get_cpuid_str(struct perf_pmu *pmu) break; } - if (!midr) { + perf_cpu_map__put(cpus); + + if (!midr) + return EINVAL; + + return 0; +} + +int get_cpuid(char *buf, size_t sz) +{ + struct perf_cpu_map *cpus = perf_cpu_map__new(NULL); + int ret; + + if (!cpus) + return EINVAL; + + ret = _get_cpuid(buf, sz, cpus); + + perf_cpu_map__put(cpus); + + return ret; +} + +char *get_cpuid_str(struct perf_pmu *pmu) +{ + char *buf = NULL; + int res; + + if (!pmu || !pmu->cpus) + return NULL; + + buf = malloc(MIDR_SIZE); + if (!buf) + return NULL; + + /* read midr from list of cpus mapped to this pmu */ + res = _get_cpuid(buf, MIDR_SIZE, pmu->cpus); + if (res) { pr_err("failed to get cpuid string for PMU %s\n", pmu->name); free(buf); buf = NULL; } - perf_cpu_map__put(cpus); return buf; } diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index c29976eca4a8..44d510bc9b78 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -357,6 +357,8 @@ 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 # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 5898662bc8fb..ff61795a4d13 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -535,6 +535,10 @@ int cmd_annotate(int argc, const char **argv) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &annotate.opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), + OPT_STRING(0, "prefix", &annotate.opts.prefix, "prefix", + "Add prefix to source file path names in programs (with --prefix-strip)"), + OPT_STRING(0, "prefix-strip", &annotate.opts.prefix_strip, "N", + "Strip first N entries of source file path name in programs (with --prefix)"), OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "group", &symbol_conf.event_group, @@ -574,6 +578,9 @@ int cmd_annotate(int argc, const char **argv) annotate.sym_hist_filter = argv[0]; } + if (annotate_check_args(&annotate.opts) < 0) + return -EINVAL; + if (symbol_conf.show_nr_samples && annotate.use_gtk) { pr_err("--show-nr-samples is not available in --gtk mode at this time\n"); return ret; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index e69f44941aad..246ac0b4d54f 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -595,8 +595,8 @@ tot_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused, { struct c2c_hist_entry *c2c_left; struct c2c_hist_entry *c2c_right; - unsigned int tot_hitm_left; - unsigned int tot_hitm_right; + uint64_t tot_hitm_left; + uint64_t tot_hitm_right; c2c_left = container_of(left, struct c2c_hist_entry, he); c2c_right = container_of(right, struct c2c_hist_entry, he); @@ -629,7 +629,8 @@ __f ## _cmp(struct perf_hpp_fmt *fmt __maybe_unused, \ \ c2c_left = container_of(left, struct c2c_hist_entry, he); \ c2c_right = container_of(right, struct c2c_hist_entry, he); \ - return c2c_left->stats.__f - c2c_right->stats.__f; \ + return (uint64_t) c2c_left->stats.__f - \ + (uint64_t) c2c_right->stats.__f; \ } #define STAT_FN(__f) \ @@ -682,7 +683,8 @@ ld_llcmiss_cmp(struct perf_hpp_fmt *fmt __maybe_unused, c2c_left = container_of(left, struct c2c_hist_entry, he); c2c_right = container_of(right, struct c2c_hist_entry, he); - return llc_miss(&c2c_left->stats) - llc_miss(&c2c_right->stats); + return (uint64_t) llc_miss(&c2c_left->stats) - + (uint64_t) llc_miss(&c2c_right->stats); } static uint64_t total_records(struct c2c_stats *stats) @@ -2384,7 +2386,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help", true); + key = hist_browser__run(browser, "? - help", true, 0); switch (key) { case 's': @@ -2453,7 +2455,7 @@ static int perf_c2c__hists_browse(struct hists *hists) c2c_browser__update_nr_entries(browser); while (1) { - key = hist_browser__run(browser, "? - help", true); + key = hist_browser__run(browser, "? - help", true, 0); switch (key) { case 'q': diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index fb19ef63cc35..4c301466101b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -62,6 +62,7 @@ #include <linux/string.h> #include <linux/time64.h> #include <linux/zalloc.h> +#include <linux/bitmap.h> struct switch_output { bool enabled; @@ -93,7 +94,7 @@ struct record { bool timestamp_boundary; struct switch_output switch_output; unsigned long long samples; - cpu_set_t affinity_mask; + struct mmap_cpu_mask affinity_mask; unsigned long output_max_size; /* = 0: unlimited */ }; @@ -961,10 +962,15 @@ static struct perf_event_header finished_round_event = { static void record__adjust_affinity(struct record *rec, struct mmap *map) { if (rec->opts.affinity != PERF_AFFINITY_SYS && - !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) { - CPU_ZERO(&rec->affinity_mask); - CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask); - sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask); + !bitmap_equal(rec->affinity_mask.bits, map->affinity_mask.bits, + rec->affinity_mask.nbits)) { + bitmap_zero(rec->affinity_mask.bits, rec->affinity_mask.nbits); + bitmap_or(rec->affinity_mask.bits, rec->affinity_mask.bits, + map->affinity_mask.bits, rec->affinity_mask.nbits); + sched_setaffinity(0, MMAP_CPU_MASK_BYTES(&rec->affinity_mask), + (cpu_set_t *)rec->affinity_mask.bits); + if (verbose == 2) + mmap_cpu_mask__scnprintf(&rec->affinity_mask, "thread"); } } @@ -2433,7 +2439,6 @@ int cmd_record(int argc, const char **argv) # undef REASON #endif - CPU_ZERO(&rec->affinity_mask); rec->opts.affinity = PERF_AFFINITY_SYS; rec->evlist = evlist__new(); @@ -2499,6 +2504,16 @@ int cmd_record(int argc, const char **argv) symbol__init(NULL); + if (rec->opts.affinity != PERF_AFFINITY_SYS) { + rec->affinity_mask.nbits = cpu__max_cpu(); + rec->affinity_mask.bits = bitmap_alloc(rec->affinity_mask.nbits); + if (!rec->affinity_mask.bits) { + pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits); + return -ENOMEM; + } + pr_debug2("thread mask[%zd]: empty\n", rec->affinity_mask.nbits); + } + err = record__auxtrace_init(rec); if (err) goto out; @@ -2613,6 +2628,7 @@ int cmd_record(int argc, const char **argv) err = __cmd_record(&record, argc, argv); out: + bitmap_free(rec->affinity_mask.bits); evlist__delete(rec->evlist); symbol__exit(); auxtrace_record__free(rec->itr); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index de988589d99b..9483b3f0cae3 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -412,10 +412,10 @@ static int report__setup_sample_type(struct report *rep) PERF_SAMPLE_BRANCH_ANY)) rep->nonany_branch_mode = true; -#ifndef HAVE_LIBUNWIND_SUPPORT +#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT) if (dwarf_callchain_users) { - ui__warning("Please install libunwind development packages " - "during the perf build.\n"); + ui__warning("Please install libunwind or libdw " + "development packages during the perf build.\n"); } #endif @@ -1164,7 +1164,8 @@ int cmd_report(int argc, const char **argv) report_callchain_help, &report_parse_callchain_opt, callchain_default_opt), OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, - "Accumulate callchains of children and show total overhead as well"), + "Accumulate callchains of children and show total overhead as well. " + "Enabled by default, use --no-children to disable."), OPT_INTEGER(0, "max-stack", &report.max_stack, "Set the maximum stack depth when parsing the callchain, " "anything beyond the specified depth will be ignored. " @@ -1207,6 +1208,10 @@ int cmd_report(int argc, const char **argv) "Display raw encoding of assembly instructions (default)"), OPT_STRING('M', "disassembler-style", &report.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), + OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix", + "Add prefix to source file path names in programs (with --prefix-strip)"), + OPT_STRING(0, "prefix-strip", &report.annotation_opts.prefix_strip, "N", + "Strip first N entries of source file path name in programs (with --prefix)"), OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period, "Show a column with the sum of periods"), OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set, @@ -1286,6 +1291,9 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; } + if (annotate_check_args(&report.annotation_opts) < 0) + return -EINVAL; + if (report.mmaps_mode) report.tasks_mode = true; diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 8a12d71364c3..82fcc2c15fe4 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -51,6 +51,9 @@ #define SYM_LEN 129 #define MAX_PID 1024000 +static const char *cpu_list; +static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); + struct sched_atom; struct task_desc { @@ -2008,6 +2011,9 @@ static void timehist_print_sample(struct perf_sched *sched, char nstr[30]; u64 wait_time; + if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) + return; + timestamp__scnprintf_usec(t, tstr, sizeof(tstr)); printf("%15s [%04d] ", tstr, sample->cpu); @@ -2994,6 +3000,12 @@ static int perf_sched__timehist(struct perf_sched *sched) if (IS_ERR(session)) return PTR_ERR(session); + if (cpu_list) { + err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap); + if (err < 0) + goto out; + } + evlist = session->evlist; symbol__init(&session->header.env); @@ -3429,6 +3441,7 @@ int cmd_sched(int argc, const char **argv) "analyze events only for given process id(s)"), OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]", "analyze events only for given thread id(s)"), + OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"), OPT_PARENT(sched_options) }; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 795e353de095..8affcab75604 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1512,6 +1512,10 @@ int cmd_top(int argc, const char **argv) "objdump binary to use for disassembly and annotations"), OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), + OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix", + "Add prefix to source file path names in programs (with --prefix-strip)"), + OPT_STRING(0, "prefix-strip", &top.annotation_opts.prefix_strip, "N", + "Strip first N entries of source file path name in programs (with --prefix)"), OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"), OPT_CALLBACK(0, "percent-limit", &top, "percent", "Don't show entries under that percent", parse_percent_limit), @@ -1582,6 +1586,9 @@ int cmd_top(int argc, const char **argv) if (argc) usage_with_options(top_usage, options); + if (annotate_check_args(&top.annotation_opts) < 0) + goto out_delete_evlist; + if (!top.evlist->core.nr_entries && perf_evlist__add_default(top.evlist) < 0) { pr_err("Not enough memory for event selector list\n"); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 46a72ecac427..01d542007c8b 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1065,7 +1065,9 @@ static struct syscall_fmt syscall_fmts[] = { { .name = "poll", .timeout = true, }, { .name = "ppoll", .timeout = true, }, { .name = "prctl", - .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ }, + .arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ + .strtoul = STUL_STRARRAY, + .parm = &strarray__prctl_options, }, [1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ }, [2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, }, { .name = "pread", .alias = "pread64", }, diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 68039a96c1dc..bfb21d049e6c 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -13,6 +13,7 @@ include/uapi/linux/kcmp.h include/uapi/linux/kvm.h include/uapi/linux/in.h include/uapi/linux/mount.h +include/uapi/linux/openat2.h include/uapi/linux/perf_event.h include/uapi/linux/prctl.h include/uapi/linux/sched.h diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c index b9c203219691..65c4ff6892d9 100644 --- a/tools/perf/examples/bpf/5sec.c +++ b/tools/perf/examples/bpf/5sec.c @@ -39,11 +39,13 @@ Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com> */ -#include <bpf.h> +#include <bpf/bpf.h> -int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec) +#define NSEC_PER_SEC 1000000000L + +int probe(hrtimer_nanosleep, rqtp)(void *ctx, int err, long long sec) { - return sec == 5; + return sec / NSEC_PER_SEC == 5ULL; } license(GPL); diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c index 3776d26db9e7..7d7fb0c9fe76 100644 --- a/tools/perf/examples/bpf/empty.c +++ b/tools/perf/examples/bpf/empty.c @@ -1,3 +1,3 @@ -#include <bpf.h> +#include <bpf/bpf.h> license(GPL); diff --git a/tools/perf/examples/bpf/sys_enter_openat.c b/tools/perf/examples/bpf/sys_enter_openat.c index 9cd124b09392..c4481c390d23 100644 --- a/tools/perf/examples/bpf/sys_enter_openat.c +++ b/tools/perf/examples/bpf/sys_enter_openat.c @@ -14,7 +14,7 @@ * the return value. */ -#include <bpf.h> +#include <bpf/bpf.h> struct syscall_enter_openat_args { unsigned long long unused; diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h index 6e61c4bdf548..607189a315b2 100644 --- a/tools/perf/include/bpf/pid_filter.h +++ b/tools/perf/include/bpf/pid_filter.h @@ -3,7 +3,7 @@ #ifndef _PERF_BPF_PID_FILTER_ #define _PERF_BPF_PID_FILTER_ -#include <bpf.h> +#include <bpf/bpf.h> #define pid_filter(name) pid_map(name, bool) diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h index 316af5b2ff35..7ca6fa5463ee 100644 --- a/tools/perf/include/bpf/stdio.h +++ b/tools/perf/include/bpf/stdio.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include <bpf.h> +#include <bpf/bpf.h> struct bpf_map SEC("maps") __bpf_stdout__ = { .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h index ca7877f9a976..d1a35b6c649d 100644 --- a/tools/perf/include/bpf/unistd.h +++ b/tools/perf/include/bpf/unistd.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 -#include <bpf.h> +#include <bpf/bpf.h> static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid; diff --git a/tools/perf/lib/Documentation/Makefile b/tools/perf/lib/Documentation/Makefile deleted file mode 100644 index 586425a88795..000000000000 --- a/tools/perf/lib/Documentation/Makefile +++ /dev/null @@ -1,7 +0,0 @@ -all: - rst2man man/libperf.rst > man/libperf.7 - rst2pdf tutorial/tutorial.rst - -clean: - rm -f man/libperf.7 - rm -f tutorial/tutorial.pdf diff --git a/tools/perf/lib/Documentation/man/libperf.rst b/tools/perf/lib/Documentation/man/libperf.rst deleted file mode 100644 index 09a270fccb9c..000000000000 --- a/tools/perf/lib/Documentation/man/libperf.rst +++ /dev/null @@ -1,100 +0,0 @@ -.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) - -libperf - -The libperf library provides an API to access the linux kernel perf -events subsystem. It provides the following high level objects: - - - struct perf_cpu_map - - struct perf_thread_map - - struct perf_evlist - - struct perf_evsel - -reference -========= -Function reference by header files: - -perf/core.h ------------ -.. code-block:: c - - typedef int (\*libperf_print_fn_t)(enum libperf_print_level level, - const char \*, va_list ap); - - void libperf_set_print(libperf_print_fn_t fn); - -perf/cpumap.h -------------- -.. code-block:: c - - struct perf_cpu_map \*perf_cpu_map__dummy_new(void); - struct perf_cpu_map \*perf_cpu_map__new(const char \*cpu_list); - struct perf_cpu_map \*perf_cpu_map__read(FILE \*file); - struct perf_cpu_map \*perf_cpu_map__get(struct perf_cpu_map \*map); - void perf_cpu_map__put(struct perf_cpu_map \*map); - int perf_cpu_map__cpu(const struct perf_cpu_map \*cpus, int idx); - int perf_cpu_map__nr(const struct perf_cpu_map \*cpus); - perf_cpu_map__for_each_cpu(cpu, idx, cpus) - -perf/threadmap.h ----------------- -.. code-block:: c - - struct perf_thread_map \*perf_thread_map__new_dummy(void); - void perf_thread_map__set_pid(struct perf_thread_map \*map, int thread, pid_t pid); - char \*perf_thread_map__comm(struct perf_thread_map \*map, int thread); - struct perf_thread_map \*perf_thread_map__get(struct perf_thread_map \*map); - void perf_thread_map__put(struct perf_thread_map \*map); - -perf/evlist.h -------------- -.. code-block:: - - void perf_evlist__init(struct perf_evlist \*evlist); - void perf_evlist__add(struct perf_evlist \*evlist, - struct perf_evsel \*evsel); - void perf_evlist__remove(struct perf_evlist \*evlist, - struct perf_evsel \*evsel); - struct perf_evlist \*perf_evlist__new(void); - void perf_evlist__delete(struct perf_evlist \*evlist); - struct perf_evsel\* perf_evlist__next(struct perf_evlist \*evlist, - struct perf_evsel \*evsel); - int perf_evlist__open(struct perf_evlist \*evlist); - void perf_evlist__close(struct perf_evlist \*evlist); - void perf_evlist__enable(struct perf_evlist \*evlist); - void perf_evlist__disable(struct perf_evlist \*evlist); - perf_evlist__for_each_evsel(evlist, pos) - void perf_evlist__set_maps(struct perf_evlist \*evlist, - struct perf_cpu_map \*cpus, - struct perf_thread_map \*threads); - -perf/evsel.h ------------- -.. code-block:: c - - struct perf_counts_values { - union { - struct { - uint64_t val; - uint64_t ena; - uint64_t run; - }; - uint64_t values[3]; - }; - }; - - void perf_evsel__init(struct perf_evsel \*evsel, - struct perf_event_attr \*attr); - struct perf_evsel \*perf_evsel__new(struct perf_event_attr \*attr); - void perf_evsel__delete(struct perf_evsel \*evsel); - int perf_evsel__open(struct perf_evsel \*evsel, struct perf_cpu_map \*cpus, - struct perf_thread_map \*threads); - void perf_evsel__close(struct perf_evsel \*evsel); - int perf_evsel__read(struct perf_evsel \*evsel, int cpu, int thread, - struct perf_counts_values \*count); - int perf_evsel__enable(struct perf_evsel \*evsel); - int perf_evsel__disable(struct perf_evsel \*evsel); - int perf_evsel__apply_filter(struct perf_evsel \*evsel, const char \*filter); - struct perf_cpu_map \*perf_evsel__cpus(struct perf_evsel \*evsel); - struct perf_thread_map \*perf_evsel__threads(struct perf_evsel \*evsel); - struct perf_event_attr \*perf_evsel__attr(struct perf_evsel \*evsel); diff --git a/tools/perf/lib/Documentation/tutorial/tutorial.rst b/tools/perf/lib/Documentation/tutorial/tutorial.rst deleted file mode 100644 index 7be7bc27b385..000000000000 --- a/tools/perf/lib/Documentation/tutorial/tutorial.rst +++ /dev/null @@ -1,123 +0,0 @@ -.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) - -libperf tutorial -================ - -Compile and install libperf from kernel sources -=============================================== -.. code-block:: bash - - git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git - cd linux/tools/perf/lib - make - sudo make install prefix=/usr - -Libperf object -============== -The libperf library provides several high level objects: - -struct perf_cpu_map - Provides a cpu list abstraction. - -struct perf_thread_map - Provides a thread list abstraction. - -struct perf_evsel - Provides an abstraction for single a perf event. - -struct perf_evlist - Gathers several struct perf_evsel object and performs functions on all of them. - -The exported API binds these objects together, -for full reference see the libperf.7 man page. - -Examples -======== -Examples aim to explain libperf functionality on simple use cases. -They are based in on a checked out linux kernel git tree: - -.. code-block:: bash - - $ cd tools/perf/lib/Documentation/tutorial/ - $ ls -d ex-* - ex-1-compile ex-2-evsel-stat ex-3-evlist-stat - -ex-1-compile example -==================== -This example shows the basic usage of *struct perf_cpu_map*, -how to create it and display its cpus: - -.. code-block:: bash - - $ cd ex-1-compile/ - $ make - gcc -o test test.c -lperf - $ ./test - 0 1 2 3 4 5 6 7 - - -The full code listing is here: - -.. code-block:: c - - 1 #include <perf/cpumap.h> - 2 - 3 int main(int argc, char **Argv) - 4 { - 5 struct perf_cpu_map *cpus; - 6 int cpu, tmp; - 7 - 8 cpus = perf_cpu_map__new(NULL); - 9 - 10 perf_cpu_map__for_each_cpu(cpu, tmp, cpus) - 11 fprintf(stdout, "%d ", cpu); - 12 - 13 fprintf(stdout, "\n"); - 14 - 15 perf_cpu_map__put(cpus); - 16 return 0; - 17 } - - -First you need to include the proper header to have *struct perf_cpumap* -declaration and functions: - -.. code-block:: c - - 1 #include <perf/cpumap.h> - - -The *struct perf_cpumap* object is created by *perf_cpu_map__new* call. -The *NULL* argument asks it to populate the object with the current online CPUs list: - -.. code-block:: c - - 8 cpus = perf_cpu_map__new(NULL); - -This is paired with a *perf_cpu_map__put*, that drops its reference at the end, possibly deleting it. - -.. code-block:: c - - 15 perf_cpu_map__put(cpus); - -The iteration through the *struct perf_cpumap* CPUs is done using the *perf_cpu_map__for_each_cpu* -macro which requires 3 arguments: - -- cpu - the cpu numer -- tmp - iteration helper variable -- cpus - the *struct perf_cpumap* object - -.. code-block:: c - - 10 perf_cpu_map__for_each_cpu(cpu, tmp, cpus) - 11 fprintf(stdout, "%d ", cpu); - -ex-2-evsel-stat example -======================= - -TBD - -ex-3-evlist-stat example -======================== - -TBD diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index 415903b48578..da8ec1e8e064 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -263,20 +263,20 @@ int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused if (count1 == 11) pr_debug("failed: RF EFLAG recursion issue detected\n"); else - pr_debug("failed: wrong count for bp1%lld\n", count1); + pr_debug("failed: wrong count for bp1: %lld, expected 1\n", count1); } if (overflows != 3) - pr_debug("failed: wrong overflow hit\n"); + pr_debug("failed: wrong overflow (%d) hit, expected 3\n", overflows); if (overflows_2 != 3) - pr_debug("failed: wrong overflow_2 hit\n"); + pr_debug("failed: wrong overflow_2 (%d) hit, expected 3\n", overflows_2); if (count2 != 3) - pr_debug("failed: wrong count for bp2\n"); + pr_debug("failed: wrong count for bp2 (%lld), expected 3\n", count2); if (count3 != 2) - pr_debug("failed: wrong count for bp3\n"); + pr_debug("failed: wrong count for bp3 (%lld), expected 2\n", count3); return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ? TEST_OK : TEST_FAIL; diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 4ac56741ac5f..29c793ac7d10 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -131,7 +131,6 @@ int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_un TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5); cpu_map__snprint(c, buf, sizeof(buf)); TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7")); - perf_cpu_map__put(a); perf_cpu_map__put(b); perf_cpu_map__put(c); return 0; diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 5a61043c2ff7..d6dfe68a7612 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -213,6 +213,8 @@ size_t syscall_arg__scnprintf_x86_arch_prctl_code(char *bf, size_t size, struct size_t syscall_arg__scnprintf_prctl_option(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_OPTION syscall_arg__scnprintf_prctl_option +extern struct strarray strarray__prctl_options; + size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_arg *arg); #define SCA_PRCTL_ARG2 syscall_arg__scnprintf_prctl_arg2 diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c index ba2179abed00..6fe5ad5f5d3a 100644 --- a/tools/perf/trace/beauty/prctl.c +++ b/tools/perf/trace/beauty/prctl.c @@ -11,9 +11,10 @@ #include "trace/beauty/generated/prctl_option_array.c" +DEFINE_STRARRAY(prctl_options, "PR_"); + static size_t prctl__scnprintf_option(int option, char *bf, size_t size, bool show_prefix) { - static DEFINE_STRARRAY(prctl_options, "PR_"); return strarray__scnprintf(&strarray__prctl_options, bf, size, "%d", show_prefix, option); } diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c index 173c8f760763..e0c13e6a5788 100644 --- a/tools/perf/trace/beauty/sockaddr.c +++ b/tools/perf/trace/beauty/sockaddr.c @@ -72,5 +72,5 @@ size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg if (arg->augmented.args) return syscall_arg__scnprintf_augmented_sockaddr(arg, bf, size); - return scnprintf(bf, size, "%#x", arg->val); + return scnprintf(bf, size, "%#lx", arg->val); } diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index d4d3558fdef4..f36dee499320 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -18,7 +18,9 @@ #include "../../util/evlist.h" #include "../../util/header.h" #include "../../util/hist.h" +#include "../../util/machine.h" #include "../../util/map.h" +#include "../../util/maps.h" #include "../../util/symbol.h" #include "../../util/map_symbol.h" #include "../../util/branch.h" @@ -391,6 +393,57 @@ static void hist_entry__init_have_children(struct hist_entry *he) he->init_have_children = true; } +static bool hist_browser__selection_has_children(struct hist_browser *browser) +{ + struct hist_entry *he = browser->he_selection; + struct map_symbol *ms = browser->selection; + + if (!he || !ms) + return false; + + if (ms == &he->ms) + return he->has_children; + + return container_of(ms, struct callchain_list, ms)->has_children; +} + +static bool hist_browser__he_selection_unfolded(struct hist_browser *browser) +{ + return browser->he_selection ? browser->he_selection->unfolded : false; +} + +static bool hist_browser__selection_unfolded(struct hist_browser *browser) +{ + struct hist_entry *he = browser->he_selection; + struct map_symbol *ms = browser->selection; + + if (!he || !ms) + return false; + + if (ms == &he->ms) + return he->unfolded; + + return container_of(ms, struct callchain_list, ms)->unfolded; +} + +static char *hist_browser__selection_sym_name(struct hist_browser *browser, char *bf, size_t size) +{ + struct hist_entry *he = browser->he_selection; + struct map_symbol *ms = browser->selection; + struct callchain_list *callchain_entry; + + if (!he || !ms) + return NULL; + + if (ms == &he->ms) { + hist_entry__sym_snprintf(he, bf, size, 0); + return bf + 4; // skip the level, e.g. '[k] ' + } + + callchain_entry = container_of(ms, struct callchain_list, ms); + return callchain_list__sym_name(callchain_entry, bf, size, browser->show_dso); +} + static bool hist_browser__toggle_fold(struct hist_browser *browser) { struct hist_entry *he = browser->he_selection; @@ -624,10 +677,81 @@ 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) +{ + switch (key) { + case K_TIMER: { + struct hist_browser_timer *hbt = browser->hbt; + u64 nr_entries; + + WARN_ON_ONCE(!hbt); + + if (hbt) + hbt->timer(hbt->arg); + + if (hist_browser__has_filter(browser) || symbol_conf.report_hierarchy) + hist_browser__update_nr_entries(browser); + + nr_entries = hist_browser__nr_entries(browser); + ui_browser__update_nr_entries(&browser->b, nr_entries); + + if (warn_lost_event && + (browser->hists->stats.nr_lost_warned != + browser->hists->stats.nr_events[PERF_RECORD_LOST])) { + browser->hists->stats.nr_lost_warned = + browser->hists->stats.nr_events[PERF_RECORD_LOST]; + ui_browser__warn_lost_events(&browser->b); + } + + hist_browser__title(browser, title, sizeof(title)); + ui_browser__show_title(&browser->b, title); + break; + } + case 'D': { /* Debug */ + struct hist_entry *h = rb_entry(browser->b.top, struct hist_entry, rb_node); + static int seq; + + ui_helpline__pop(); + ui_helpline__fpush("%d: nr_ent=(%d,%d), etl: %d, rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", + seq++, browser->b.nr_entries, browser->hists->nr_entries, + browser->b.extra_title_lines, browser->b.rows, + browser->b.index, browser->b.top_idx, h->row_offset, h->nr_rows); + } + break; + case 'C': + /* Collapse the whole world. */ + hist_browser__set_folding(browser, false); + break; + case 'c': + /* Collapse the selected entry. */ + hist_browser__set_folding_selected(browser, false); + break; + case 'E': + /* Expand the whole world. */ + hist_browser__set_folding(browser, true); + break; + case 'e': + /* Expand the selected entry. */ + hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser)); + break; + case 'H': + browser->show_headers = !browser->show_headers; + hist_browser__update_rows(browser); + break; + case '+': + if (hist_browser__toggle_fold(browser)) + break; + /* fall thru */ + default: + return -1; + } + + return 0; +} + int hist_browser__run(struct hist_browser *browser, const char *help, - bool warn_lost_event) + bool warn_lost_event, int key) { - int key; char title[160]; struct hist_browser_timer *hbt = browser->hbt; int delay_secs = hbt ? hbt->refresh : 0; @@ -640,79 +764,14 @@ 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)) + goto out; + while (1) { key = ui_browser__run(&browser->b, delay_secs); - switch (key) { - case K_TIMER: { - u64 nr_entries; - - WARN_ON_ONCE(!hbt); - - if (hbt) - hbt->timer(hbt->arg); - - if (hist_browser__has_filter(browser) || - symbol_conf.report_hierarchy) - hist_browser__update_nr_entries(browser); - - nr_entries = hist_browser__nr_entries(browser); - ui_browser__update_nr_entries(&browser->b, nr_entries); - - if (warn_lost_event && - (browser->hists->stats.nr_lost_warned != - browser->hists->stats.nr_events[PERF_RECORD_LOST])) { - browser->hists->stats.nr_lost_warned = - browser->hists->stats.nr_events[PERF_RECORD_LOST]; - ui_browser__warn_lost_events(&browser->b); - } - - hist_browser__title(browser, title, sizeof(title)); - ui_browser__show_title(&browser->b, title); - continue; - } - case 'D': { /* Debug */ - static int seq; - struct hist_entry *h = rb_entry(browser->b.top, - struct hist_entry, rb_node); - ui_helpline__pop(); - ui_helpline__fpush("%d: nr_ent=(%d,%d), etl: %d, rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d", - seq++, browser->b.nr_entries, - browser->hists->nr_entries, - browser->b.extra_title_lines, - browser->b.rows, - browser->b.index, - browser->b.top_idx, - h->row_offset, h->nr_rows); - } - break; - case 'C': - /* Collapse the whole world. */ - hist_browser__set_folding(browser, false); - break; - case 'c': - /* Collapse the selected entry. */ - hist_browser__set_folding_selected(browser, false); + if (hist_browser__handle_hotkey(browser, warn_lost_event, title, key)) break; - case 'E': - /* Expand the whole world. */ - hist_browser__set_folding(browser, true); - break; - case 'e': - /* Expand the selected entry. */ - hist_browser__set_folding_selected(browser, true); - break; - case 'H': - browser->show_headers = !browser->show_headers; - hist_browser__update_rows(browser); - break; - case K_ENTER: - if (hist_browser__toggle_fold(browser)) - break; - /* fall thru */ - default: - goto out; - } } out: ui_browser__hide(&browser->b); @@ -2339,7 +2398,7 @@ close_file_and_continue: closedir(pwd_dir); if (nr_options) { - choice = ui__popup_menu(nr_options, options); + choice = ui__popup_menu(nr_options, options, NULL); if (choice < nr_options && choice >= 0) { tmp = strdup(abs_path[choice]); if (tmp) { @@ -2411,7 +2470,8 @@ add_annotate_opt(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct map_symbol *ms) { - if (ms->sym == NULL || ms->map->dso->annotate_warned) + if (ms->sym == NULL || ms->map->dso->annotate_warned || + symbol__annotation(ms->sym)->src == NULL) return 0; if (asprintf(optstr, "Annotate %s", ms->sym->name) < 0) @@ -2484,11 +2544,8 @@ add_thread_opt(struct hist_browser *browser, struct popup_action *act, return 1; } -static int -do_zoom_dso(struct hist_browser *browser, struct popup_action *act) +static int hists_browser__zoom_map(struct hist_browser *browser, struct map *map) { - struct map *map = act->ms.map; - if (!hists__has(browser->hists, dso) || map == NULL) return 0; @@ -2511,13 +2568,19 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act) } static int +do_zoom_dso(struct hist_browser *browser, struct popup_action *act) +{ + return hists_browser__zoom_map(browser, act->ms.map); +} + +static int add_dso_opt(struct hist_browser *browser, struct popup_action *act, char **optstr, struct map *map) { if (!hists__has(browser->hists, dso) || map == NULL) return 0; - if (asprintf(optstr, "Zoom %s %s DSO", + if (asprintf(optstr, "Zoom %s %s DSO (use the 'k' hotkey to zoom directly into the kernel)", browser->hists->dso_filter ? "out of" : "into", __map__is_kernel(map) ? "the Kernel" : map->dso->short_name) < 0) return 0; @@ -2527,6 +2590,28 @@ add_dso_opt(struct hist_browser *browser, struct popup_action *act, return 1; } +static int do_toggle_callchain(struct hist_browser *browser, struct popup_action *act __maybe_unused) +{ + hist_browser__toggle_fold(browser); + return 0; +} + +static int add_callchain_toggle_opt(struct hist_browser *browser, struct popup_action *act, char **optstr) +{ + char sym_name[512]; + + if (!hist_browser__selection_has_children(browser)) + return 0; + + if (asprintf(optstr, "%s [%s] callchain (one level, same as '+' hotkey, use 'e'/'c' for the whole main level entry)", + hist_browser__selection_unfolded(browser) ? "Collapse" : "Expand", + hist_browser__selection_sym_name(browser, sym_name, sizeof(sym_name))) < 0) + return 0; + + act->fn = do_toggle_callchain; + return 1; +} + static int do_browse_map(struct hist_browser *browser __maybe_unused, struct popup_action *act) @@ -2858,12 +2943,15 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, "For symbolic views (--sort has sym):\n\n" \ "ENTER Zoom into DSO/Threads & Annotate current symbol\n" \ "ESC Zoom out\n" \ + "+ Expand/Collapse one callchain level\n" \ "a Annotate current symbol\n" \ "C Collapse all callchains\n" \ "d Zoom into current DSO\n" \ + "e Expand/Collapse main entry callchains\n" \ "E Expand all callchains\n" \ "F Toggle percentage of filtered entries\n" \ "H Display column headers\n" \ + "k Zoom into the kernel map\n" \ "L Change percent limit\n" \ "m Display context menu\n" \ "S Zoom into current Processor Socket\n" \ @@ -2914,13 +3002,13 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, while (1) { struct thread *thread = NULL; struct map *map = NULL; - int choice = 0; + int choice; int socked_id = -1; - nr_options = 0; - - key = hist_browser__run(browser, helpline, - warn_lost_event); + key = 0; // reset key +do_hotkey: // key came straight from options ui__popup_menu() + choice = nr_options = 0; + key = hist_browser__run(browser, helpline, warn_lost_event, key); if (browser->he_selection != NULL) { thread = hist_browser__selected_thread(browser); @@ -2950,6 +3038,14 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, 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; + } + actions->ms.map = browser->selection->map; actions->ms.sym = browser->selection->sym; do_annotate(browser, actions); @@ -2961,6 +3057,10 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, actions->ms.map = map; do_zoom_dso(browser, actions); continue; + case 'k': + if (browser->selection != NULL) + hists_browser__zoom_map(browser, browser->selection->maps->machine->vmlinux_map); + continue; case 'V': verbose = (verbose + 1) % 4; browser->show_dso = verbose > 0; @@ -3062,6 +3162,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, continue; } + actions->ms.map = map; top = pstack__peek(browser->pstack); if (top == &browser->hists->dso_filter) { /* @@ -3135,6 +3236,7 @@ skip_annotation: &options[nr_options], thread); nr_options += add_dso_opt(browser, &actions[nr_options], &options[nr_options], map); + nr_options += add_callchain_toggle_opt(browser, &actions[nr_options], &options[nr_options]); nr_options += add_map_opt(browser, &actions[nr_options], &options[nr_options], browser->selection ? @@ -3193,10 +3295,13 @@ skip_scripting: do { struct popup_action *act; - choice = ui__popup_menu(nr_options, options); - if (choice == -1 || choice >= nr_options) + choice = ui__popup_menu(nr_options, options, &key); + if (choice == -1) break; + if (choice == nr_options) + goto do_hotkey; + act = &actions[choice]; key = act->fn(browser, act); } while (key == 1); @@ -3492,7 +3597,7 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, memset(&action, 0, sizeof(action)); while (1) { - key = hist_browser__run(browser, "? - help", true); + key = hist_browser__run(browser, "? - help", true, 0); switch (key) { case 'q': diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h index 078f2f2c7abd..1e938d9ffa5e 100644 --- a/tools/perf/ui/browsers/hists.h +++ b/tools/perf/ui/browsers/hists.h @@ -34,7 +34,7 @@ struct hist_browser { struct hist_browser *hist_browser__new(struct hists *hists); void hist_browser__delete(struct hist_browser *browser); int hist_browser__run(struct hist_browser *browser, const char *help, - bool warn_lost_event); + bool warn_lost_event, int key); void hist_browser__init(struct hist_browser *browser, struct hists *hists); #endif /* _PERF_UI_BROWSER_HISTS_H_ */ diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c index 76d356a18790..7cb2d6678039 100644 --- a/tools/perf/ui/browsers/res_sample.c +++ b/tools/perf/ui/browsers/res_sample.c @@ -56,7 +56,7 @@ int res_sample_browse(struct res_sample *res_samples, int num_res, return -1; } } - choice = ui__popup_menu(num_res, names); + choice = ui__popup_menu(num_res, names, NULL); for (i = 0; i < num_res; i++) zfree(&names[i]); free(names); diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c index fc733a6354d4..47d2c7a8cbe1 100644 --- a/tools/perf/ui/browsers/scripts.c +++ b/tools/perf/ui/browsers/scripts.c @@ -126,7 +126,7 @@ static int list_scripts(char *script_name, bool *custom, SCRIPT_FULLPATH_LEN); if (num < 0) num = 0; - choice = ui__popup_menu(num + max_std, (char * const *)names); + choice = ui__popup_menu(num + max_std, (char * const *)names, NULL); if (choice < 0) { ret = -1; goto out; diff --git a/tools/perf/ui/gtk/Build b/tools/perf/ui/gtk/Build index ec22e899a224..eef708c502f4 100644 --- a/tools/perf/ui/gtk/Build +++ b/tools/perf/ui/gtk/Build @@ -1,4 +1,4 @@ -CFLAGS_gtk += -fPIC $(GTK_CFLAGS) +CFLAGS_gtk += -fPIC $(GTK_CFLAGS) -Wno-deprecated-declarations gtk-y += browser.o gtk-y += hists.o @@ -7,3 +7,8 @@ gtk-y += util.o gtk-y += helpline.o gtk-y += progress.o gtk-y += annotate.o +gtk-y += zalloc.o + +$(OUTPUT)ui/gtk/zalloc.o: ../lib/zalloc.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c index b98dd0e31dc1..0f562e2cb1e8 100644 --- a/tools/perf/ui/tui/util.c +++ b/tools/perf/ui/tui/util.c @@ -23,7 +23,7 @@ static void ui_browser__argv_write(struct ui_browser *browser, ui_browser__write_nstring(browser, *arg, browser->width); } -static int popup_menu__run(struct ui_browser *menu) +static int popup_menu__run(struct ui_browser *menu, int *keyp) { int key; @@ -45,6 +45,11 @@ static int popup_menu__run(struct ui_browser *menu) key = -1; break; default: + if (keyp) { + *keyp = key; + key = menu->nr_entries; + break; + } continue; } @@ -55,7 +60,7 @@ static int popup_menu__run(struct ui_browser *menu) return key; } -int ui__popup_menu(int argc, char * const argv[]) +int ui__popup_menu(int argc, char * const argv[], int *keyp) { struct ui_browser menu = { .entries = (void *)argv, @@ -64,8 +69,7 @@ int ui__popup_menu(int argc, char * const argv[]) .write = ui_browser__argv_write, .nr_entries = argc, }; - - return popup_menu__run(&menu); + return popup_menu__run(&menu, keyp); } int ui_browser__input_window(const char *title, const char *text, char *input, diff --git a/tools/perf/ui/util.h b/tools/perf/ui/util.h index 40891942f465..e30cea807564 100644 --- a/tools/perf/ui/util.h +++ b/tools/perf/ui/util.h @@ -5,7 +5,7 @@ #include <stdarg.h> int ui__getch(int delay_secs); -int ui__popup_menu(int argc, char * const argv[]); +int ui__popup_menu(int argc, char * const argv[], int *keyp); int ui__help_window(const char *text); int ui__dialog_yesno(const char *msg); void __ui__info_window(const char *title, const char *text, const char *exit_msg); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index f5e77ed237e8..ca73fb74ad03 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1966,14 +1966,20 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) err = asprintf(&command, "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s -C \"$1\"", + " -l -d %s %s %s %c%s%c %s%s -C \"$1\"", opts->objdump_path ?: "objdump", opts->disassembler_style ? "-M " : "", opts->disassembler_style ?: "", map__rip_2objdump(map, sym->start), map__rip_2objdump(map, sym->end), opts->show_asm_raw ? "" : "--no-show-raw-insn", - opts->annotate_src ? "-S" : ""); + opts->annotate_src ? "-S" : "", + opts->prefix ? "--prefix " : "", + opts->prefix ? '"' : ' ', + opts->prefix ?: "", + opts->prefix ? '"' : ' ', + opts->prefix_strip ? "--prefix-strip=" : "", + opts->prefix_strip ?: ""); if (err < 0) { pr_err("Failure allocating memory for the command to run\n"); @@ -3204,3 +3210,12 @@ out: free(str1); return err; } + +int annotate_check_args(struct annotation_options *args) +{ + if (args->prefix_strip && !args->prefix) { + pr_err("--prefix-strip requires --prefix\n"); + return -1; + } + return 0; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 7075d98f69d9..455403e8fede 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -94,6 +94,8 @@ struct annotation_options { int context; const char *objdump_path; const char *disassembler_style; + const char *prefix; + const char *prefix_strip; unsigned int percent_type; }; @@ -415,4 +417,7 @@ void annotation_config__init(void); int annotate_parse_percent_type(const struct option *opt, const char *_str, int unset); + +int annotate_check_args(struct annotation_options *args); + #endif /* __PERF_ANNOTATE_H */ diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index fc361c3f8570..c8885dfa3667 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -71,7 +71,11 @@ getModuleFromSource(llvm::opt::ArgStringList CFlags, CompilerInstance Clang; Clang.createDiagnostics(); +#if CLANG_VERSION_MAJOR < 9 Clang.setVirtualFileSystem(&*VFS); +#else + Clang.createFileManager(&*VFS); +#endif #if CLANG_VERSION_MAJOR < 4 IntrusiveRefCntPtr<CompilerInvocation> CI = diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a69e64236120..c8dc4450884c 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -808,12 +808,12 @@ static void apply_config_terms(struct evsel *evsel, perf_evsel__reset_sample_bit(evsel, TIME); break; case PERF_EVSEL__CONFIG_TERM_CALLGRAPH: - callgraph_buf = term->val.callgraph; + callgraph_buf = term->val.str; break; case PERF_EVSEL__CONFIG_TERM_BRANCH: - if (term->val.branch && strcmp(term->val.branch, "no")) { + if (term->val.str && strcmp(term->val.str, "no")) { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); - parse_branch_str(term->val.branch, + parse_branch_str(term->val.str, &attr->branch_sample_type); } else perf_evsel__reset_sample_bit(evsel, BRANCH_STACK); @@ -1265,6 +1265,8 @@ static void perf_evsel__free_config_terms(struct evsel *evsel) list_for_each_entry_safe(term, h, &evsel->config_terms, list) { list_del_init(&term->list); + if (term->free_str) + zfree(&term->val.str); free(term); } } diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h index 1f8d2fe0b66e..e026ab67b008 100644 --- a/tools/perf/util/evsel_config.h +++ b/tools/perf/util/evsel_config.h @@ -32,22 +32,21 @@ enum evsel_term_type { struct perf_evsel_config_term { struct list_head list; enum evsel_term_type type; + bool free_str; union { u64 period; u64 freq; bool time; - char *callgraph; - char *drv_cfg; u64 stack_user; int max_stack; bool inherit; bool overwrite; - char *branch; unsigned long max_events; bool percore; bool aux_output; u32 aux_sample_size; u64 cfg_chg; + char *str; } val; bool weak; }; diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index f9a20a39b64a..7d226241f1d7 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -12,7 +12,8 @@ #define MAXIDLEN 256 %} -%pure-parser +%define api.pure full + %parse-param { double *final_val } %parse-param { struct parse_ctx *ctx } %parse-param { const char **pp } diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 93ad27830e2b..4246e7447e54 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2922,7 +2922,7 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) if (ret == -1) return -1; - stctime = st.st_ctime; + stctime = st.st_mtime; fprintf(fp, "# captured on : %s", ctime(&stctime)); fprintf(fp, "# header version : %u\n", header->version); diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index eae47c2509eb..b5af680fc667 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -288,6 +288,7 @@ static const char *kinc_fetch_script = "obj-y := dummy.o\n" "\\$(obj)/%.o: \\$(src)/%.c\n" "\t@echo -n \"\\$(NOSTDINC_FLAGS) \\$(LINUXINCLUDE) \\$(EXTRA_CFLAGS)\"\n" +"\t\\$(CC) -c -o \\$@ \\$<\n" "EOF\n" "touch $TMPDIR/dummy.c\n" "make -s -C $KBUILD_DIR M=$TMPDIR $KBUILD_OPTS dummy.o 2>/dev/null\n" diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index c8c5410315e8..fb5c2cd44d30 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -686,6 +686,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine, dso__set_module_info(dso, m, machine); dso__set_long_name(dso, strdup(filename), true); + dso->kernel = DSO_TYPE_KERNEL; } dso__get(dso); @@ -726,9 +727,17 @@ static int machine__process_ksymbol_register(struct machine *machine, struct map *map = maps__find(&machine->kmaps, event->ksymbol.addr); if (!map) { - map = dso__new_map(event->ksymbol.name); - if (!map) + struct dso *dso = dso__new(event->ksymbol.name); + + if (dso) { + dso->kernel = DSO_TYPE_KERNEL; + map = map__new2(0, dso); + } + + if (!dso || !map) { + dso__put(dso); return -ENOMEM; + } map->start = event->ksymbol.addr; map->end = map->start + event->ksymbol.len; @@ -972,7 +981,6 @@ int machine__create_extra_kernel_map(struct machine *machine, kmap = map__kmap(map); - kmap->kmaps = &machine->kmaps; strlcpy(kmap->name, xm->name, KMAP_NAME_LEN); maps__insert(&machine->kmaps, map); @@ -1082,9 +1090,6 @@ int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unu static int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { - struct kmap *kmap; - struct map *map; - /* In case of renewal the kernel map, destroy previous one */ machine__destroy_kernel_maps(machine); @@ -1093,14 +1098,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) return -1; machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip; - map = machine__kernel_map(machine); - kmap = map__kmap(map); - if (!kmap) - return -1; - - kmap->kmaps = &machine->kmaps; - maps__insert(&machine->kmaps, map); - + maps__insert(&machine->kmaps, machine->vmlinux_map); return 0; } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index fdd5bddb3075..a08ca276098e 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -375,8 +375,13 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name) struct map *map__clone(struct map *from) { - struct map *map = memdup(from, sizeof(*map)); + size_t size = sizeof(struct map); + struct map *map; + + if (from->dso && from->dso->kernel) + size += sizeof(struct kmap); + map = memdup(from, size); if (map != NULL) { refcount_set(&map->refcnt, 1); RB_CLEAR_NODE(&map->rb_node); @@ -538,6 +543,16 @@ void maps__insert(struct maps *maps, struct map *map) __maps__insert(maps, map); ++maps->nr_maps; + if (map->dso && map->dso->kernel) { + struct kmap *kmap = map__kmap(map); + + if (kmap) + kmap->kmaps = maps; + else + pr_err("Internal error: kernel dso with non kernel map\n"); + } + + /* * If we already performed some search by name, then we need to add the just * inserted map and resort. @@ -549,6 +564,7 @@ void maps__insert(struct maps *maps, struct map *map) if (maps_by_name == NULL) { __maps__free_maps_by_name(maps); + up_write(&maps->lock); return; } diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 063d1b93c53d..3b664fa673a6 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -23,6 +23,18 @@ #include "mmap.h" #include "../perf.h" #include <internal/lib.h> /* page_size */ +#include <linux/bitmap.h> + +#define MASK_SIZE 1023 +void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag) +{ + char buf[MASK_SIZE + 1]; + size_t len; + + len = bitmap_scnprintf(mask->bits, mask->nbits, buf, MASK_SIZE); + buf[len] = '\0'; + pr_debug("%p: %s mask[%zd]: %s\n", mask, tag, mask->nbits, buf); +} size_t mmap__mmap_len(struct mmap *map) { @@ -207,6 +219,8 @@ static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused) void mmap__munmap(struct mmap *map) { + bitmap_free(map->affinity_mask.bits); + perf_mmap__aio_munmap(map); if (map->data != NULL) { munmap(map->data, mmap__mmap_len(map)); @@ -215,7 +229,7 @@ void mmap__munmap(struct mmap *map) auxtrace_mmap__munmap(&map->auxtrace_mmap); } -static void build_node_mask(int node, cpu_set_t *mask) +static void build_node_mask(int node, struct mmap_cpu_mask *mask) { int c, cpu, nr_cpus; const struct perf_cpu_map *cpu_map = NULL; @@ -228,17 +242,23 @@ static void build_node_mask(int node, cpu_set_t *mask) for (c = 0; c < nr_cpus; c++) { cpu = cpu_map->map[c]; /* map c index to online cpu index */ if (cpu__get_node(cpu) == node) - CPU_SET(cpu, mask); + set_bit(cpu, mask->bits); } } -static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) +static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) { - CPU_ZERO(&map->affinity_mask); + map->affinity_mask.nbits = cpu__max_cpu(); + map->affinity_mask.bits = bitmap_alloc(map->affinity_mask.nbits); + if (!map->affinity_mask.bits) + return -1; + if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask); else if (mp->affinity == PERF_AFFINITY_CPU) - CPU_SET(map->core.cpu, &map->affinity_mask); + set_bit(map->core.cpu, map->affinity_mask.bits); + + return 0; } int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) @@ -249,7 +269,15 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) return -1; } - perf_mmap__setup_affinity_mask(map, mp); + if (mp->affinity != PERF_AFFINITY_SYS && + perf_mmap__setup_affinity_mask(map, mp)) { + pr_debug2("failed to alloc mmap affinity mask, error %d\n", + errno); + return -1; + } + + if (verbose == 2) + mmap_cpu_mask__scnprintf(&map->affinity_mask, "mmap"); map->core.flush = mp->flush; diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index bee4e83f7109..9d5f589f02ae 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -15,6 +15,15 @@ #include "event.h" struct aiocb; + +struct mmap_cpu_mask { + unsigned long *bits; + size_t nbits; +}; + +#define MMAP_CPU_MASK_BYTES(m) \ + (BITS_TO_LONGS(((struct mmap_cpu_mask *)m)->nbits) * sizeof(unsigned long)) + /** * struct mmap - perf's ring buffer mmap details * @@ -31,7 +40,7 @@ struct mmap { int nr_cblocks; } aio; #endif - cpu_set_t affinity_mask; + struct mmap_cpu_mask affinity_mask; void *data; int comp_level; }; @@ -52,4 +61,6 @@ int perf_mmap__push(struct mmap *md, void *to, size_t mmap__mmap_len(struct mmap *map); +void mmap_cpu_mask__scnprintf(struct mmap_cpu_mask *mask, const char *tag); + #endif /*__PERF_MMAP_H */ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index ed7c008b9c8b..c01ba6f8fdad 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1219,8 +1219,7 @@ static int config_attr(struct perf_event_attr *attr, static int get_config_terms(struct list_head *head_config, struct list_head *head_terms __maybe_unused) { -#define ADD_CONFIG_TERM(__type, __name, __val) \ -do { \ +#define ADD_CONFIG_TERM(__type) \ struct perf_evsel_config_term *__t; \ \ __t = zalloc(sizeof(*__t)); \ @@ -1229,9 +1228,24 @@ do { \ \ INIT_LIST_HEAD(&__t->list); \ __t->type = PERF_EVSEL__CONFIG_TERM_ ## __type; \ - __t->val.__name = __val; \ __t->weak = term->weak; \ - list_add_tail(&__t->list, head_terms); \ + list_add_tail(&__t->list, head_terms) + +#define ADD_CONFIG_TERM_VAL(__type, __name, __val) \ +do { \ + ADD_CONFIG_TERM(__type); \ + __t->val.__name = __val; \ +} while (0) + +#define ADD_CONFIG_TERM_STR(__type, __val) \ +do { \ + ADD_CONFIG_TERM(__type); \ + __t->val.str = strdup(__val); \ + if (!__t->val.str) { \ + zfree(&__t); \ + return -ENOMEM; \ + } \ + __t->free_str = true; \ } while (0) struct parse_events_term *term; @@ -1239,53 +1253,62 @@ do { \ list_for_each_entry(term, head_config, list) { switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: - ADD_CONFIG_TERM(PERIOD, period, term->val.num); + ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: - ADD_CONFIG_TERM(FREQ, freq, term->val.num); + ADD_CONFIG_TERM_VAL(FREQ, freq, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_TIME: - ADD_CONFIG_TERM(TIME, time, term->val.num); + ADD_CONFIG_TERM_VAL(TIME, time, term->val.num); break; case PARSE_EVENTS__TERM_TYPE_CALLGRAPH: - ADD_CONFIG_TERM(CALLGRAPH, callgraph, term->val.str); + ADD_CONFIG_TERM_STR(CALLGRAPH, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: - ADD_CONFIG_TERM(BRANCH, branch, term->val.str); + ADD_CONFIG_TERM_STR(BRANCH, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_STACKSIZE: - ADD_CONFIG_TERM(STACK_USER, stack_user, term->val.num); + ADD_CONFIG_TERM_VAL(STACK_USER, stack_user, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_INHERIT: - ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 1 : 0); + ADD_CONFIG_TERM_VAL(INHERIT, inherit, + term->val.num ? 1 : 0); break; case PARSE_EVENTS__TERM_TYPE_NOINHERIT: - ADD_CONFIG_TERM(INHERIT, inherit, term->val.num ? 0 : 1); + ADD_CONFIG_TERM_VAL(INHERIT, inherit, + term->val.num ? 0 : 1); break; case PARSE_EVENTS__TERM_TYPE_MAX_STACK: - ADD_CONFIG_TERM(MAX_STACK, max_stack, term->val.num); + ADD_CONFIG_TERM_VAL(MAX_STACK, max_stack, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS: - ADD_CONFIG_TERM(MAX_EVENTS, max_events, term->val.num); + ADD_CONFIG_TERM_VAL(MAX_EVENTS, max_events, + term->val.num); break; case PARSE_EVENTS__TERM_TYPE_OVERWRITE: - ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 1 : 0); + ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite, + term->val.num ? 1 : 0); break; case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: - ADD_CONFIG_TERM(OVERWRITE, overwrite, term->val.num ? 0 : 1); + ADD_CONFIG_TERM_VAL(OVERWRITE, overwrite, + term->val.num ? 0 : 1); break; case PARSE_EVENTS__TERM_TYPE_DRV_CFG: - ADD_CONFIG_TERM(DRV_CFG, drv_cfg, term->val.str); + ADD_CONFIG_TERM_STR(DRV_CFG, term->val.str); break; case PARSE_EVENTS__TERM_TYPE_PERCORE: - ADD_CONFIG_TERM(PERCORE, percore, - term->val.num ? true : false); + ADD_CONFIG_TERM_VAL(PERCORE, percore, + term->val.num ? true : false); break; case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: - ADD_CONFIG_TERM(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0); + ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output, + term->val.num ? 1 : 0); break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: - ADD_CONFIG_TERM(AUX_SAMPLE_SIZE, aux_sample_size, term->val.num); + ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size, + term->val.num); break; default: break; @@ -1322,7 +1345,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config, } if (bits) - ADD_CONFIG_TERM(CFG_CHG, cfg_chg, bits); + ADD_CONFIG_TERM_VAL(CFG_CHG, cfg_chg, bits); #undef ADD_CONFIG_TERM return 0; diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index e2eea4e601b4..94f8bcd83582 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -1,4 +1,4 @@ -%pure-parser +%define api.pure full %parse-param {void *_parse_state} %parse-param {void *scanner} %lex-param {void* scanner} diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index c470c49a804f..1c817add6ca4 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -303,7 +303,8 @@ static int convert_variable_type(Dwarf_Die *vr_die, char prefix; /* TODO: check all types */ - if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "x") != 0 && + if (cast && strcmp(cast, "string") != 0 && strcmp(cast, "ustring") && + strcmp(cast, "x") != 0 && strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) { /* Non string type is OK */ /* and respect signedness/hexadecimal cast */ diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 9fcba2872130..ab0cfd790ad0 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -324,8 +324,7 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms, return ret; } -static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, - size_t size, unsigned int width) +int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { return _hist_entry__sym_snprintf(&he->ms, he->ip, he->level, bf, size, width); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 5aff9542d9b7..6c862d62d052 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -164,6 +164,8 @@ static __pure inline bool hist_entry__has_callchains(struct hist_entry *he) return he->callchain_size != 0; } +int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width); + static inline bool hist_entry__has_pairs(struct hist_entry *he) { return !list_empty(&he->pairs.node); diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 6ccf6f6d09df..5b7d6c16d33f 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -193,16 +193,30 @@ static void find_address_in_section(bfd *abfd, asection *section, void *data) bfd_vma pc, vma; bfd_size_type size; struct a2l_data *a2l = data; + flagword flags; if (a2l->found) return; - if ((bfd_get_section_flags(abfd, section) & SEC_ALLOC) == 0) +#ifdef bfd_get_section_flags + flags = bfd_get_section_flags(abfd, section); +#else + flags = bfd_section_flags(section); +#endif + if ((flags & SEC_ALLOC) == 0) return; pc = a2l->addr; +#ifdef bfd_get_section_vma vma = bfd_get_section_vma(abfd, section); +#else + vma = bfd_section_vma(section); +#endif +#ifdef bfd_get_section_size size = bfd_get_section_size(section); +#else + size = bfd_section_size(section); +#endif if (pc < vma || pc >= vma + size) return; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 2c41d47f6f83..90d23cc3c8d4 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -18,7 +18,6 @@ * AGGR_NONE: Use matching CPU * AGGR_THREAD: Not supported? */ -static bool have_frontend_stalled; struct runtime_stat rt_stat; struct stats walltime_nsecs_stats; @@ -144,7 +143,6 @@ void runtime_stat__exit(struct runtime_stat *st) void perf_stat__init_shadow_stats(void) { - have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend"); runtime_stat__init(&rt_stat); } @@ -853,10 +851,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn", ratio); - } else if (have_frontend_stalled) { - out->new_line(config, ctxp); - print_metric(config, ctxp, NULL, "%7.2f ", - "stalled cycles per insn", 0); } } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3b379b1296f1..1077013d8ce2 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -635,9 +635,12 @@ out: static bool symbol__is_idle(const char *name) { const char * const idle_symbols[] = { + "acpi_idle_do_entry", + "acpi_processor_ffh_cstate_enter", "arch_cpu_idle", "cpu_idle", "cpu_startup_entry", + "idle_cpu", "intel_idle", "default_idle", "native_safe_halt", @@ -651,13 +654,17 @@ static bool symbol__is_idle(const char *name) NULL }; int i; + static struct strlist *idle_symbols_list; - for (i = 0; idle_symbols[i]; i++) { - if (!strcmp(idle_symbols[i], name)) - return true; - } + if (idle_symbols_list) + return strlist__has_entry(idle_symbols_list, name); - return false; + idle_symbols_list = strlist__new(NULL, NULL); + + for (i = 0; idle_symbols[i]; i++) + strlist__add(idle_symbols_list, idle_symbols[i]); + + return strlist__has_entry(idle_symbols_list, name); } static int map__process_kallsym_symbol(void *arg, const char *name, diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config index 0111d246d1ca..54a2857c2510 100644 --- a/tools/power/acpi/Makefile.config +++ b/tools/power/acpi/Makefile.config @@ -15,7 +15,7 @@ include $(srctree)/../../scripts/Makefile.include OUTPUT=$(srctree)/ ifeq ("$(origin O)", "command line") - OUTPUT := $(O)/power/acpi/ + OUTPUT := $(O)/tools/power/acpi/ endif #$(info Determined 'OUTPUT' to be $(OUTPUT)) diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index 28c11c6b4d06..d1d18ff5c911 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -3,7 +3,7 @@ * * Module Name: cfsize - Common get file size function * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index 6b41d8b64a00..c3708f30ab3a 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -3,7 +3,7 @@ * * Module Name: getopt * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index d1f3d44e315e..5aaddc79adf7 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -3,7 +3,7 @@ * * Module Name: oslinuxtbl - Linux OSL for obtaining ACPI tables * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c index 30913f124dd5..fd05ddee240f 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixdir.c +++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c @@ -3,7 +3,7 @@ * * Module Name: osunixdir - Unix directory access interfaces * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c index 29dfb47adfeb..c565546e85bc 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixmap.c +++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c @@ -3,7 +3,7 @@ * * Module Name: osunixmap - Unix OSL for file mappings * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index 83d3b3b829b8..5b2fd968535f 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -3,7 +3,7 @@ * * Module Name: osunixxf - UNIX OSL interfaces * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index 2eb0aaa4f462..26a5eae9f87f 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -3,7 +3,7 @@ * * Module Name: acpidump.h - Include file for acpi_dump utility * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index 820baeb5092b..76433296055d 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -3,7 +3,7 @@ * * Module Name: apdump - Dump routines for ACPI tables (acpidump) * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index 16d919bd133b..a682bae4e6f6 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -3,7 +3,7 @@ * * Module Name: apfiles - File-related functions for acpidump utility * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index d8f1b57537d3..046e6b8d6baa 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -3,7 +3,7 @@ * * Module Name: apmain - Main module for the acpidump utility * - * Copyright (C) 2000 - 2019, Intel Corp. + * Copyright (C) 2000 - 2020, Intel Corp. * *****************************************************************************/ diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c index 2f55d4d23446..6e04304560ca 100644 --- a/tools/power/cpupower/lib/cpufreq.c +++ b/tools/power/cpupower/lib/cpufreq.c @@ -332,21 +332,74 @@ void cpufreq_put_available_governors(struct cpufreq_available_governors *any) } -struct cpufreq_frequencies -*cpufreq_get_frequencies(const char *type, unsigned int cpu) +struct cpufreq_available_frequencies +*cpufreq_get_available_frequencies(unsigned int cpu) { - struct cpufreq_frequencies *first = NULL; - struct cpufreq_frequencies *current = NULL; + struct cpufreq_available_frequencies *first = NULL; + struct cpufreq_available_frequencies *current = NULL; char one_value[SYSFS_PATH_MAX]; char linebuf[MAX_LINE_LEN]; - char fname[MAX_LINE_LEN]; unsigned int pos, i; unsigned int len; - snprintf(fname, MAX_LINE_LEN, "scaling_%s_frequencies", type); + len = sysfs_cpufreq_read_file(cpu, "scaling_available_frequencies", + linebuf, sizeof(linebuf)); + if (len == 0) + return NULL; - len = sysfs_cpufreq_read_file(cpu, fname, - linebuf, sizeof(linebuf)); + pos = 0; + for (i = 0; i < len; i++) { + if (linebuf[i] == ' ' || linebuf[i] == '\n') { + if (i - pos < 2) + continue; + if (i - pos >= SYSFS_PATH_MAX) + goto error_out; + if (current) { + current->next = malloc(sizeof(*current)); + if (!current->next) + goto error_out; + current = current->next; + } else { + first = malloc(sizeof(*first)); + if (!first) + goto error_out; + current = first; + } + current->first = first; + current->next = NULL; + + memcpy(one_value, linebuf + pos, i - pos); + one_value[i - pos] = '\0'; + if (sscanf(one_value, "%lu", ¤t->frequency) != 1) + goto error_out; + + pos = i + 1; + } + } + + return first; + + error_out: + while (first) { + current = first->next; + free(first); + first = current; + } + return NULL; +} + +struct cpufreq_available_frequencies +*cpufreq_get_boost_frequencies(unsigned int cpu) +{ + struct cpufreq_available_frequencies *first = NULL; + struct cpufreq_available_frequencies *current = NULL; + char one_value[SYSFS_PATH_MAX]; + char linebuf[MAX_LINE_LEN]; + unsigned int pos, i; + unsigned int len; + + len = sysfs_cpufreq_read_file(cpu, "scaling_boost_frequencies", + linebuf, sizeof(linebuf)); if (len == 0) return NULL; @@ -391,9 +444,9 @@ struct cpufreq_frequencies return NULL; } -void cpufreq_put_frequencies(struct cpufreq_frequencies *any) +void cpufreq_put_available_frequencies(struct cpufreq_available_frequencies *any) { - struct cpufreq_frequencies *tmp, *next; + struct cpufreq_available_frequencies *tmp, *next; if (!any) return; @@ -406,6 +459,11 @@ void cpufreq_put_frequencies(struct cpufreq_frequencies *any) } } +void cpufreq_put_boost_frequencies(struct cpufreq_available_frequencies *any) +{ + cpufreq_put_available_frequencies(any); +} + static struct cpufreq_affected_cpus *sysfs_get_cpu_list(unsigned int cpu, const char *file) { diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h index a55f0d19215b..95f4fd9e2656 100644 --- a/tools/power/cpupower/lib/cpufreq.h +++ b/tools/power/cpupower/lib/cpufreq.h @@ -20,10 +20,10 @@ struct cpufreq_available_governors { struct cpufreq_available_governors *first; }; -struct cpufreq_frequencies { +struct cpufreq_available_frequencies { unsigned long frequency; - struct cpufreq_frequencies *next; - struct cpufreq_frequencies *first; + struct cpufreq_available_frequencies *next; + struct cpufreq_available_frequencies *first; }; @@ -124,11 +124,17 @@ void cpufreq_put_available_governors( * cpufreq_put_frequencies after use. */ -struct cpufreq_frequencies -*cpufreq_get_frequencies(const char *type, unsigned int cpu); +struct cpufreq_available_frequencies +*cpufreq_get_available_frequencies(unsigned int cpu); -void cpufreq_put_frequencies( - struct cpufreq_frequencies *first); +void cpufreq_put_available_frequencies( + struct cpufreq_available_frequencies *first); + +struct cpufreq_available_frequencies +*cpufreq_get_boost_frequencies(unsigned int cpu); + +void cpufreq_put_boost_frequencies( + struct cpufreq_available_frequencies *first); /* determine affected CPUs diff --git a/tools/power/cpupower/man/cpupower.1 b/tools/power/cpupower/man/cpupower.1 index baf741d06e82..a5e4523a219b 100644 --- a/tools/power/cpupower/man/cpupower.1 +++ b/tools/power/cpupower/man/cpupower.1 @@ -62,9 +62,9 @@ all cores Print the package name and version number. .SH "SEE ALSO" -cpupower-set(1), cpupower-info(1), cpupower-idle(1), -cpupower-frequency-set(1), cpupower-frequency-info(1), cpupower-monitor(1), -powertop(1) +cpupower-set(1), cpupower-info(1), cpupower-idle-info(1), +cpupower-idle-set(1), cpupower-frequency-set(1), cpupower-frequency-info(1), +cpupower-monitor(1), powertop(1) .PP .SH AUTHORS .nf diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index e63cf55f81cf..6efc0f6b1b11 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -244,14 +244,14 @@ static int get_boost_mode_x86(unsigned int cpu) static int get_boost_mode(unsigned int cpu) { - struct cpufreq_frequencies *freqs; + struct cpufreq_available_frequencies *freqs; if (cpupower_cpu_info.vendor == X86_VENDOR_AMD || cpupower_cpu_info.vendor == X86_VENDOR_HYGON || cpupower_cpu_info.vendor == X86_VENDOR_INTEL) return get_boost_mode_x86(cpu); - freqs = cpufreq_get_frequencies("boost", cpu); + freqs = cpufreq_get_boost_frequencies(cpu); if (freqs) { printf(_(" boost frequency steps: ")); while (freqs->next) { @@ -261,7 +261,7 @@ static int get_boost_mode(unsigned int cpu) } print_speed(freqs->frequency); printf("\n"); - cpufreq_put_frequencies(freqs); + cpufreq_put_available_frequencies(freqs); } return 0; @@ -475,7 +475,7 @@ static int get_latency(unsigned int cpu, unsigned int human) static void debug_output_one(unsigned int cpu) { - struct cpufreq_frequencies *freqs; + struct cpufreq_available_frequencies *freqs; get_driver(cpu); get_related_cpus(cpu); @@ -483,7 +483,7 @@ static void debug_output_one(unsigned int cpu) get_latency(cpu, 1); get_hardware_limits(cpu, 1); - freqs = cpufreq_get_frequencies("available", cpu); + freqs = cpufreq_get_available_frequencies(cpu); if (freqs) { printf(_(" available frequency steps: ")); while (freqs->next) { @@ -493,7 +493,7 @@ static void debug_output_one(unsigned int cpu) } print_speed(freqs->frequency); printf("\n"); - cpufreq_put_frequencies(freqs); + cpufreq_put_available_frequencies(freqs); } get_available_governors(cpu); diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index 944183f9ed5a..2b2b8167c65b 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -15,7 +15,7 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.1"; +static const char *version_str = "v1.2"; static const int supported_api_ver = 1; static struct isst_if_platform_info isst_platform_info; static char *progname; @@ -1384,14 +1384,10 @@ static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, goto disp_result; } - if (auto_mode) { - if (status) { - ret = set_pbf_core_power(cpu); - if (ret) - goto disp_result; - } else { - isst_pm_qos_config(cpu, 0, 0); - } + if (auto_mode && status) { + ret = set_pbf_core_power(cpu); + if (ret) + goto disp_result; } ret = isst_set_pbf_fact_status(cpu, 1, status); @@ -1408,6 +1404,9 @@ static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, } } + if (auto_mode && !status) + isst_pm_qos_config(cpu, 0, 0); + disp_result: if (status) isst_display_result(cpu, outf, "base-freq", "enable", @@ -1496,14 +1495,10 @@ static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, int ret; int status = *(int *)arg4; - if (auto_mode) { - if (status) { - ret = isst_pm_qos_config(cpu, 1, 1); - if (ret) - goto disp_results; - } else { - isst_pm_qos_config(cpu, 0, 0); - } + if (auto_mode && status) { + ret = isst_pm_qos_config(cpu, 1, 1); + if (ret) + goto disp_results; } ret = isst_set_pbf_fact_status(cpu, 0, status); @@ -1524,6 +1519,9 @@ static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3, ret = isst_set_trl(cpu, fact_trl); if (ret && auto_mode) isst_pm_qos_config(cpu, 0, 0); + } else { + if (auto_mode) + isst_pm_qos_config(cpu, 0, 0); } disp_results: @@ -1638,7 +1636,7 @@ static void set_fact_enable(int arg) if (ret) goto error_disp; } - isst_display_result(i, outf, "turbo-freq --auto", "enable", 0); + isst_display_result(-1, outf, "turbo-freq --auto", "enable", 0); } return; diff --git a/tools/power/x86/intel-speed-select/isst-core.c b/tools/power/x86/intel-speed-select/isst-core.c index d14c7bcd327a..81a119f688a3 100644 --- a/tools/power/x86/intel-speed-select/isst-core.c +++ b/tools/power/x86/intel-speed-select/isst-core.c @@ -6,6 +6,44 @@ #include "isst.h" +int isst_write_pm_config(int cpu, int cp_state) +{ + unsigned int req, resp; + int ret; + + if (cp_state) + req = BIT(16); + else + req = 0; + + ret = isst_send_mbox_command(cpu, WRITE_PM_CONFIG, PM_FEATURE, 0, req, + &resp); + if (ret) + return ret; + + debug_printf("cpu:%d WRITE_PM_CONFIG resp:%x\n", cpu, resp); + + return 0; +} + +int isst_read_pm_config(int cpu, int *cp_state, int *cp_cap) +{ + unsigned int resp; + int ret; + + ret = isst_send_mbox_command(cpu, READ_PM_CONFIG, PM_FEATURE, 0, 0, + &resp); + if (ret) + return ret; + + debug_printf("cpu:%d READ_PM_CONFIG resp:%x\n", cpu, resp); + + *cp_state = resp & BIT(16); + *cp_cap = resp & BIT(0) ? 1 : 0; + + return 0; +} + int isst_get_ctdp_levels(int cpu, struct isst_pkg_ctdp *pkg_dev) { unsigned int resp; @@ -36,6 +74,7 @@ int isst_get_ctdp_levels(int cpu, struct isst_pkg_ctdp *pkg_dev) int isst_get_ctdp_control(int cpu, int config_index, struct isst_pkg_ctdp_level_info *ctdp_level) { + int cp_state, cp_cap; unsigned int resp; int ret; @@ -50,6 +89,15 @@ int isst_get_ctdp_control(int cpu, int config_index, ctdp_level->fact_enabled = !!(resp & BIT(16)); ctdp_level->pbf_enabled = !!(resp & BIT(17)); + ret = isst_read_pm_config(cpu, &cp_state, &cp_cap); + if (ret) { + debug_printf("cpu:%d pm_config is not supported \n", cpu); + } else { + debug_printf("cpu:%d pm_config SST-CP state:%d cap:%d \n", cpu, cp_state, cp_cap); + ctdp_level->sst_cp_support = cp_cap; + ctdp_level->sst_cp_enabled = cp_state; + } + debug_printf( "cpu:%d CONFIG_TDP_GET_TDP_CONTROL resp:%x fact_support:%d pbf_support: %d fact_enabled:%d pbf_enabled:%d\n", cpu, resp, ctdp_level->fact_support, ctdp_level->pbf_support, @@ -779,6 +827,13 @@ int isst_pm_qos_config(int cpu, int enable_clos, int priority_type) debug_printf("Turbo-freq feature must be disabled first\n"); return -EINVAL; } + ret = isst_write_pm_config(cpu, 0); + if (ret) + perror("isst_write_pm_config\n"); + } else { + ret = isst_write_pm_config(cpu, 1); + if (ret) + perror("isst_write_pm_config\n"); } ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_QOS_CONFIG, 0, 0, diff --git a/tools/power/x86/intel-speed-select/isst-display.c b/tools/power/x86/intel-speed-select/isst-display.c index 040dd09d5eee..4fb0c1d49d64 100644 --- a/tools/power/x86/intel-speed-select/isst-display.c +++ b/tools/power/x86/intel-speed-select/isst-display.c @@ -418,6 +418,17 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, snprintf(value, sizeof(value), "unsupported"); format_and_print(outf, base_level + 4, header, value); + snprintf(header, sizeof(header), + "speed-select-core-power"); + if (ctdp_level->sst_cp_support) { + if (ctdp_level->sst_cp_enabled) + snprintf(value, sizeof(value), "enabled"); + else + snprintf(value, sizeof(value), "disabled"); + } else + snprintf(value, sizeof(value), "unsupported"); + format_and_print(outf, base_level + 4, header, value); + if (is_clx_n_platform()) { if (ctdp_level->pbf_support) _isst_pbf_display_information(cpu, outf, @@ -634,13 +645,15 @@ void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd, char header[256]; char value[256]; - snprintf(header, sizeof(header), "package-%d", - get_physical_package_id(cpu)); - format_and_print(outf, 1, header, NULL); - snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu)); - format_and_print(outf, 2, header, NULL); - snprintf(header, sizeof(header), "cpu-%d", cpu); - format_and_print(outf, 3, header, NULL); + if (cpu >= 0) { + snprintf(header, sizeof(header), "package-%d", + get_physical_package_id(cpu)); + format_and_print(outf, 1, header, NULL); + snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu)); + format_and_print(outf, 2, header, NULL); + snprintf(header, sizeof(header), "cpu-%d", cpu); + format_and_print(outf, 3, header, NULL); + } snprintf(header, sizeof(header), "%s", feature); format_and_print(outf, 4, header, NULL); snprintf(header, sizeof(header), "%s", cmd); diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h index cdf0f8a6dbbf..ad5aa6341d0f 100644 --- a/tools/power/x86/intel-speed-select/isst.h +++ b/tools/power/x86/intel-speed-select/isst.h @@ -69,6 +69,10 @@ #define PM_CLOS_OFFSET 0x08 #define PQR_ASSOC_OFFSET 0x20 +#define READ_PM_CONFIG 0x94 +#define WRITE_PM_CONFIG 0x95 +#define PM_FEATURE 0x03 + #define DISP_FREQ_MULTIPLIER 100 struct isst_clos_config { @@ -119,6 +123,8 @@ struct isst_pkg_ctdp_level_info { int pbf_support; int fact_enabled; int pbf_enabled; + int sst_cp_support; + int sst_cp_enabled; int tdp_ratio; int active; int tdp_control; diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py index 2d6d342b148f..256199c7a182 100755 --- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -11,11 +11,11 @@ then this utility enables and collects trace data for a user specified interval and generates performance plots. Prerequisites: - Python version 2.7.x + Python version 2.7.x or higher gnuplot 5.0 or higher - gnuplot-py 1.8 + gnuplot-py 1.8 or higher (Most of the distributions have these required packages. They may be called - gnuplot-py, phython-gnuplot. ) + gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... ) HWP (Hardware P-States are disabled) Kernel config for Linux trace is enabled @@ -104,7 +104,7 @@ def plot_perf_busy_with_sample(cpu_index): if os.path.exists(file_name): output_png = "cpu%03d_perf_busy_vs_samples.png" % cpu_index g_plot = common_all_gnuplot_settings(output_png) - g_plot('set yrange [0:40]') +# autoscale this one, no set y1 range g_plot('set y2range [0:200]') g_plot('set y2tics 0, 10') g_plot('set title "{} : cpu perf busy vs. sample : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now())) @@ -125,7 +125,7 @@ def plot_perf_busy(cpu_index): if os.path.exists(file_name): output_png = "cpu%03d_perf_busy.png" % cpu_index g_plot = common_all_gnuplot_settings(output_png) - g_plot('set yrange [0:40]') +# autoscale this one, no set y1 range g_plot('set y2range [0:200]') g_plot('set y2tics 0, 10') g_plot('set title "{} : perf busy : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now())) @@ -144,9 +144,7 @@ def plot_durations(cpu_index): if os.path.exists(file_name): output_png = "cpu%03d_durations.png" % cpu_index g_plot = common_all_gnuplot_settings(output_png) -# Should autoscale be used here? Should seconds be used here? - g_plot('set yrange [0:5000]') - g_plot('set ytics 0, 500') +# autoscale this one, no set y range g_plot('set title "{} : durations : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now())) g_plot('set ylabel "Timer Duration (MilliSeconds)"') # override common @@ -176,12 +174,12 @@ def plot_pstate_cpu_with_sample(): if os.path.exists('cpu.csv'): output_png = 'all_cpu_pstates_vs_samples.png' g_plot = common_all_gnuplot_settings(output_png) - g_plot('set yrange [0:40]') +# autoscale this one, no set y range # override common g_plot('set xlabel "Samples"') g_plot('set ylabel "P-State"') g_plot('set title "{} : cpu pstate vs. sample : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_SAMPLE, C_TO) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -191,14 +189,14 @@ def plot_pstate_cpu(): output_png = 'all_cpu_pstates.png' g_plot = common_all_gnuplot_settings(output_png) - g_plot('set yrange [0:40]') +# autoscale this one, no set y range g_plot('set ylabel "P-State"') g_plot('set title "{} : cpu pstates : {:%F %H:%M}"'.format(testname, datetime.now())) # the following command is really cool, but doesn't work with the CPU masking option because it aborts on the first missing file. # plot_str = 'plot for [i=0:*] file=sprintf("cpu%03d.csv",i) title_s=sprintf("cpu%03d",i) file using 16:7 pt 7 ps 1 title title_s' # - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_TO) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -212,7 +210,7 @@ def plot_load_cpu(): g_plot('set ylabel "CPU load (percent)"') g_plot('set title "{} : cpu loads : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_LOAD) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -222,11 +220,11 @@ def plot_frequency_cpu(): output_png = 'all_cpu_frequencies.png' g_plot = common_all_gnuplot_settings(output_png) - g_plot('set yrange [0:4]') +# autoscale this one, no set y range g_plot('set ylabel "CPU Frequency (GHz)"') g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -236,12 +234,12 @@ def plot_duration_cpu(): output_png = 'all_cpu_durations.png' g_plot = common_all_gnuplot_settings(output_png) - g_plot('set yrange [0:5000]') +# autoscale this one, no set y range g_plot('set ytics 0, 500') g_plot('set ylabel "Timer Duration (MilliSeconds)"') g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_DURATION) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -255,7 +253,7 @@ def plot_scaled_cpu(): g_plot('set ylabel "Scaled Busy (Unitless)"') g_plot('set title "{} : cpu scaled busy : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_SCALED) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -269,7 +267,7 @@ def plot_boost_cpu(): g_plot('set ylabel "CPU IO Boost (percent)"') g_plot('set title "{} : cpu io boost : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_BOOST) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -283,7 +281,7 @@ def plot_ghz_cpu(): g_plot('set ylabel "TSC Frequency (GHz)"') g_plot('set title "{} : cpu TSC Frequencies (Sanity check calculation) : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_GHZ) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 5d0fddda842c..31c1ca0bb3ee 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -4499,10 +4499,10 @@ void decode_feature_control_msr(void) { unsigned long long msr; - if (!get_msr(base_cpu, MSR_IA32_FEATURE_CONTROL, &msr)) + if (!get_msr(base_cpu, MSR_IA32_FEAT_CTL, &msr)) fprintf(outf, "cpu%d: MSR_IA32_FEATURE_CONTROL: 0x%08llx (%sLocked %s)\n", base_cpu, msr, - msr & FEATURE_CONTROL_LOCKED ? "" : "UN-", + msr & FEAT_CTL_LOCKED ? "" : "UN-", msr & (1 << 18) ? "SGX" : ""); } diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 6aca8d5be159..dbebf05f5931 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -1,10 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 ldflags-y += --wrap=ioremap_wc ldflags-y += --wrap=memremap -ldflags-y += --wrap=devm_ioremap_nocache +ldflags-y += --wrap=devm_ioremap ldflags-y += --wrap=devm_memremap ldflags-y += --wrap=devm_memunmap -ldflags-y += --wrap=ioremap_nocache ldflags-y += --wrap=ioremap ldflags-y += --wrap=iounmap ldflags-y += --wrap=memunmap diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 6271ac757a4b..03e40b3b0106 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -73,7 +73,7 @@ void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size, return fallback_fn(offset, size); } -void __iomem *__wrap_devm_ioremap_nocache(struct device *dev, +void __iomem *__wrap_devm_ioremap(struct device *dev, resource_size_t offset, unsigned long size) { struct nfit_test_resource *nfit_res = get_nfit_res(offset); @@ -81,9 +81,9 @@ void __iomem *__wrap_devm_ioremap_nocache(struct device *dev, if (nfit_res) return (void __iomem *) nfit_res->buf + offset - nfit_res->res.start; - return devm_ioremap_nocache(dev, offset, size); + return devm_ioremap(dev, offset, size); } -EXPORT_SYMBOL(__wrap_devm_ioremap_nocache); +EXPORT_SYMBOL(__wrap_devm_ioremap); void *__wrap_devm_memremap(struct device *dev, resource_size_t offset, size_t size, unsigned long flags) @@ -187,12 +187,6 @@ void __wrap_devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(__wrap_devm_memunmap); -void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) -{ - return __nfit_test_ioremap(offset, size, ioremap_nocache); -} -EXPORT_SYMBOL(__wrap_ioremap_nocache); - void __iomem *__wrap_ioremap(resource_size_t offset, unsigned long size) { return __nfit_test_ioremap(offset, size, ioremap); diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index 0bf5640f1f07..db3c07beb9d1 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -207,8 +207,6 @@ typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t); typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4); -void __iomem *__wrap_ioremap_nocache(resource_size_t offset, - unsigned long size); void __wrap_iounmap(volatile void __iomem *addr); void nfit_test_setup(nfit_test_lookup_fn lookup, nfit_test_evaluate_dsm_fn evaluate); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index b001c602414b..6ec503912bea 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -26,12 +26,14 @@ TARGETS += kexec TARGETS += kvm TARGETS += lib TARGETS += livepatch +TARGETS += lkdtm TARGETS += membarrier TARGETS += memfd TARGETS += memory-hotplug TARGETS += mount TARGETS += mqueue TARGETS += net +TARGETS += net/mptcp TARGETS += netfilter TARGETS += networking/timestamping TARGETS += nsfs @@ -40,6 +42,7 @@ TARGETS += powerpc TARGETS += proc TARGETS += pstore TARGETS += ptrace +TARGETS += openat2 TARGETS += rseq TARGETS += rtc TARGETS += seccomp @@ -50,6 +53,7 @@ TARGETS += splice TARGETS += static_keys TARGETS += sync TARGETS += sysctl +TARGETS += timens ifneq (1, $(quicktest)) TARGETS += timers endif @@ -73,6 +77,12 @@ ifneq ($(SKIP_TARGETS),) override TARGETS := $(TMP) endif +# User can set FORCE_TARGETS to 1 to require all targets to be successfully +# built; make will fail if any of the targets cannot be built. If +# FORCE_TARGETS is not set (the default), make will succeed if at least one +# of the targets gets built. +FORCE_TARGETS ?= + # Clear LDFLAGS and MAKEFLAGS if called from main # Makefile to avoid test build failures when test # Makefile doesn't have explicit build rules. @@ -143,11 +153,14 @@ else endif all: khdr - @for TARGET in $(TARGETS); do \ - BUILD_TARGET=$$BUILD/$$TARGET; \ - mkdir $$BUILD_TARGET -p; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET;\ - done; + @ret=1; \ + for TARGET in $(TARGETS); do \ + BUILD_TARGET=$$BUILD/$$TARGET; \ + mkdir $$BUILD_TARGET -p; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \ + $(if $(FORCE_TARGETS),|| exit); \ + ret=$$((ret * $$?)); \ + done; exit $$ret; run_tests: all @for TARGET in $(TARGETS); do \ @@ -196,10 +209,13 @@ ifdef INSTALL_PATH install -m 744 kselftest/module.sh $(INSTALL_PATH)/kselftest/ install -m 744 kselftest/runner.sh $(INSTALL_PATH)/kselftest/ install -m 744 kselftest/prefix.pl $(INSTALL_PATH)/kselftest/ - @for TARGET in $(TARGETS); do \ + @ret=1; \ + for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ - $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ - done; + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \ + $(if $(FORCE_TARGETS),|| exit); \ + ret=$$((ret * $$?)); \ + done; exit $$ret; @# Ask all targets to emit their test scripts echo "#!/bin/sh" > $(ALL_SCRIPT) diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1ff0a9f49c01..ec464859c6b6 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -21,23 +21,20 @@ test_lirc_mode2_user get_cgroup_id_user test_skb_cgroup_id_user test_socket_cookie -test_cgroup_attach test_cgroup_storage -test_select_reuseport test_flow_dissector flow_dissector_load test_netcnt -test_section_names test_tcpnotify_user test_libbpf test_tcp_check_syncookie_user test_sysctl -libbpf.pc -libbpf.so.* test_hashmap test_btf_dump xdping test_cpp +*.skel.h /no_alu32 /bpf_gcc -bpf_helper_defs.h +/tools + diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index e2fd6f8d579c..257a1aaaa37d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -3,10 +3,12 @@ include ../../../../scripts/Kbuild.include include ../../../scripts/Makefile.arch CURDIR := $(abspath .) -LIBDIR := $(abspath ../../../lib) +TOOLSDIR := $(abspath ../../..) +LIBDIR := $(TOOLSDIR)/lib BPFDIR := $(LIBDIR)/bpf -TOOLSDIR := $(abspath ../../../include) -APIDIR := $(TOOLSDIR)/uapi +TOOLSINCDIR := $(TOOLSDIR)/include +BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool +APIDIR := $(TOOLSINCDIR)/uapi GENDIR := $(abspath ../../../../include/generated) GENHDR := $(GENDIR)/autoconf.h @@ -18,19 +20,19 @@ CLANG ?= clang LLC ?= llc LLVM_OBJCOPY ?= llvm-objcopy BPF_GCC ?= $(shell command -v bpf-gcc;) -CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) \ - -I$(GENDIR) -I$(TOOLSDIR) -I$(CURDIR) \ +CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(CURDIR) -I$(APIDIR) \ + -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) -I$(TOOLSINCDIR) \ -Dbpf_prog_load=bpf_prog_test_load \ -Dbpf_load_program=bpf_test_load_program -LDLIBS += -lcap -lelf -lrt -lpthread +LDLIBS += -lcap -lelf -lz -lrt -lpthread # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ - test_cgroup_storage test_select_reuseport \ + test_cgroup_storage \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \ - test_cgroup_attach test_progs-no_alu32 + test_progs-no_alu32 # Also test bpf-gcc, if present ifneq ($(BPF_GCC),) @@ -71,12 +73,39 @@ TEST_PROGS_EXTENDED := with_addr.sh \ # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ - test_lirc_mode2_user xdping test_cpp + test_lirc_mode2_user xdping test_cpp runqslower TEST_CUSTOM_PROGS = urandom_read +# Emit succinct information message describing current building step +# $1 - generic step name (e.g., CC, LINK, etc); +# $2 - optional "flavor" specifier; if provided, will be emitted as [flavor]; +# $3 - target (assumed to be file); only file name will be emitted; +# $4 - optional extra arg, emitted as-is, if provided. +ifeq ($(V),1) +Q = +msg = +else +Q = @ +msg = @printf ' %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))"; +MAKEFLAGS += --no-print-directory +submake_extras := feature_display=0 +endif + +# override lib.mk's default rules +OVERRIDE_TARGETS := 1 +override define CLEAN + $(call msg,CLEAN) + $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) +endef + include ../lib.mk +SCRATCH_DIR := $(OUTPUT)/tools +BUILD_DIR := $(SCRATCH_DIR)/build +INCLUDE_DIR := $(SCRATCH_DIR)/include +BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a + # Define simple and short `make test_progs`, `make test_sysctl`, etc targets # to build individual tests. # NOTE: Semicolon at the end is critical to override lib.mk's default static @@ -87,13 +116,26 @@ $(notdir $(TEST_GEN_PROGS) \ $(TEST_GEN_PROGS_EXTENDED) \ $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ; +$(OUTPUT)/%:%.c + $(call msg,BINARY,,$@) + $(LINK.c) $^ $(LDLIBS) -o $@ + $(OUTPUT)/urandom_read: urandom_read.c - $(CC) -o $@ $< -Wl,--build-id + $(call msg,BINARY,,$@) + $(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id -$(OUTPUT)/test_stub.o: test_stub.c +$(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ) + $(call msg,CC,,$@) $(CC) -c $(CFLAGS) -o $@ $< -BPFOBJ := $(OUTPUT)/libbpf.a +VMLINUX_BTF_PATHS := $(abspath ../../../../vmlinux) \ + /sys/kernel/btf/vmlinux \ + /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF:= $(firstword $(wildcard $(VMLINUX_BTF_PATHS))) +$(OUTPUT)/runqslower: $(BPFOBJ) + $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ + OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF) \ + BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(BPFOBJ) @@ -110,19 +152,24 @@ $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c $(OUTPUT)/test_netcnt: cgroup_helpers.c $(OUTPUT)/test_sock_fields: cgroup_helpers.c $(OUTPUT)/test_sysctl: cgroup_helpers.c -$(OUTPUT)/test_cgroup_attach: cgroup_helpers.c - -.PHONY: force -# force a rebuild of BPFOBJ when its dependencies are updated -force: +DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) +$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ + $(BPFOBJ) | $(BUILD_DIR)/bpftool + $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ + OUTPUT=$(BUILD_DIR)/bpftool/ \ + prefix= DESTDIR=$(SCRATCH_DIR)/ install -$(BPFOBJ): force - $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ +$(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ + ../../../include/uapi/linux/bpf.h \ + | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf + $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ + DESTDIR=$(SCRATCH_DIR) prefix= all install_headers -BPF_HELPERS := $(OUTPUT)/bpf_helper_defs.h $(wildcard $(BPFDIR)/bpf_*.h) -$(OUTPUT)/bpf_helper_defs.h: - $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ $(OUTPUT)/bpf_helper_defs.h +$(BUILD_DIR)/libbpf $(BUILD_DIR)/bpftool $(INCLUDE_DIR): + $(call msg,MKDIR,,$@) + mkdir -p $@ # Get Clang's default includes on this system, as opposed to those seen by # '-target bpf'. This fixes "missing" files on some architectures/distros, @@ -142,8 +189,8 @@ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ - -I. -I./include/uapi -I$(APIDIR) \ - -I$(BPFDIR) -I$(abspath $(OUTPUT)/../usr/include) + -I$(INCLUDE_DIR) -I$(CURDIR) -I$(CURDIR)/include/uapi \ + -I$(APIDIR) -I$(abspath $(OUTPUT)/../usr/include) CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \ -Wno-compare-distinct-pointer-types @@ -159,27 +206,33 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h # $3 - CFLAGS # $4 - LDFLAGS define CLANG_BPF_BUILD_RULE + $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 define CLANG_NOALU32_BPF_BUILD_RULE + $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC define CLANG_NATIVE_BPF_BUILD_RULE + $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2 endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE + $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2) $(BPF_GCC) $3 $4 -O2 -c $1 -o $2 endef +SKEL_BLACKLIST := btf__% test_pinning_invalid.c + # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES. # Parameters: @@ -195,8 +248,11 @@ TRUNNER_EXTRA_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, \ $$(filter %.c,$(TRUNNER_EXTRA_SOURCES))) TRUNNER_EXTRA_HDRS := $$(filter %.h,$(TRUNNER_EXTRA_SOURCES)) TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h -TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, \ - $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))) +TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c)) +TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)) +TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ + $$(filter-out $(SKEL_BLACKLIST), \ + $$(TRUNNER_BPF_SRCS))) # Evaluate rules now with extra TRUNNER_XXX variables above already defined $$(eval $$(call DEFINE_TEST_RUNNER_RULES,$1,$2)) @@ -212,6 +268,7 @@ define DEFINE_TEST_RUNNER_RULES ifeq ($($(TRUNNER_OUTPUT)-dir),) $(TRUNNER_OUTPUT)-dir := y $(TRUNNER_OUTPUT): + $$(call msg,MKDIR,,$$@) mkdir -p $$@ endif @@ -222,16 +279,23 @@ $(TRUNNER_BPF_PROGS_DIR)$(if $2,-)$2-bpfobjs := y $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_BPF_PROGS_DIR)/%.c \ $(TRUNNER_BPF_PROGS_DIR)/*.h \ - $$(BPF_HELPERS) | $(TRUNNER_OUTPUT) + $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS), \ $(TRUNNER_BPF_LDFLAGS)) + +$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h: \ + $(TRUNNER_OUTPUT)/%.o \ + | $(BPFTOOL) $(TRUNNER_OUTPUT) + $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) + $$(BPFTOOL) gen skeleton $$< > $$@ endif # ensure we set up tests.h header generation rule just once ifeq ($($(TRUNNER_TESTS_DIR)-tests-hdr),) $(TRUNNER_TESTS_DIR)-tests-hdr := y $(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c + $$(call msg,TEST-HDR,$(TRUNNER_BINARY),$$@) $$(shell ( cd $(TRUNNER_TESTS_DIR); \ echo '/* Generated header, do not edit */'; \ ls *.c 2> /dev/null | \ @@ -245,7 +309,9 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \ $(TRUNNER_TESTS_DIR)/%.c \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_BPF_OBJS) \ + $(TRUNNER_BPF_SKELS) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) + $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@) cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ @@ -253,17 +319,20 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_TESTS_HDR) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) + $$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@) $$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@ +# only copy extra resources if in flavored build $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT) ifneq ($2,) - # only copy extra resources if in flavored build + $$(call msg,EXT-COPY,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES)) cp -a $$^ $(TRUNNER_OUTPUT)/ endif $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \ | $(TRUNNER_BINARY)-extras + $$(call msg,BINARY,,$$@) $$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ endef @@ -276,7 +345,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ $(wildcard progs/btf_dump_test_case_*.c) TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE -TRUNNER_BPF_CFLAGS := -I. -I$(OUTPUT) $(BPF_CFLAGS) $(CLANG_CFLAGS) +TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) TRUNNER_BPF_LDFLAGS := -mattr=+alu32 $(eval $(call DEFINE_TEST_RUNNER,test_progs)) @@ -315,12 +384,15 @@ verifier/tests.h: verifier/*.c echo '#endif' \ ) > verifier/tests.h) $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) + $(call msg,BINARY,,$@) $(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ # Make sure we are able to include and link libbpf against c++. -$(OUTPUT)/test_cpp: test_cpp.cpp $(BPFOBJ) +$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) + $(call msg,CXX,,$@) $(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@ -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) \ +EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ - feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc + feature \ + $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc) diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h new file mode 100644 index 000000000000..8f21965ffc6c --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h @@ -0,0 +1,235 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_TCP_HELPERS_H +#define __BPF_TCP_HELPERS_H + +#include <stdbool.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_trace_helpers.h" + +#define BPF_STRUCT_OPS(name, args...) \ +SEC("struct_ops/"#name) \ +BPF_PROG(name, args) + +#define tcp_jiffies32 ((__u32)bpf_jiffies64()) + +struct sock_common { + unsigned char skc_state; +} __attribute__((preserve_access_index)); + +enum sk_pacing { + SK_PACING_NONE = 0, + SK_PACING_NEEDED = 1, + SK_PACING_FQ = 2, +}; + +struct sock { + struct sock_common __sk_common; + unsigned long sk_pacing_rate; + __u32 sk_pacing_status; /* see enum sk_pacing */ +} __attribute__((preserve_access_index)); + +struct inet_sock { + struct sock sk; +} __attribute__((preserve_access_index)); + +struct inet_connection_sock { + struct inet_sock icsk_inet; + __u8 icsk_ca_state:6, + icsk_ca_setsockopt:1, + icsk_ca_dst_locked:1; + struct { + __u8 pending; + } icsk_ack; + __u64 icsk_ca_priv[104 / sizeof(__u64)]; +} __attribute__((preserve_access_index)); + +struct tcp_sock { + struct inet_connection_sock inet_conn; + + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u8 ecn_flags; + __u32 delivered; + __u32 delivered_ce; + __u32 snd_cwnd; + __u32 snd_cwnd_cnt; + __u32 snd_cwnd_clamp; + __u32 snd_ssthresh; + __u8 syn_data:1, /* SYN includes data */ + syn_fastopen:1, /* SYN includes Fast Open option */ + syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ + syn_fastopen_ch:1, /* Active TFO re-enabling probe */ + syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ + save_syn:1, /* Save headers of SYN packet */ + is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */ + syn_smc:1; /* SYN includes SMC */ + __u32 max_packets_out; + __u32 lsndtime; + __u32 prior_cwnd; + __u64 tcp_mstamp; /* most recent packet received/sent */ +} __attribute__((preserve_access_index)); + +static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk) +{ + return (struct inet_connection_sock *)sk; +} + +static __always_inline void *inet_csk_ca(const struct sock *sk) +{ + return (void *)inet_csk(sk)->icsk_ca_priv; +} + +static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk) +{ + return (struct tcp_sock *)sk; +} + +static __always_inline bool before(__u32 seq1, __u32 seq2) +{ + return (__s32)(seq1-seq2) < 0; +} +#define after(seq2, seq1) before(seq1, seq2) + +#define TCP_ECN_OK 1 +#define TCP_ECN_QUEUE_CWR 2 +#define TCP_ECN_DEMAND_CWR 4 +#define TCP_ECN_SEEN 8 + +enum inet_csk_ack_state_t { + ICSK_ACK_SCHED = 1, + ICSK_ACK_TIMER = 2, + ICSK_ACK_PUSHED = 4, + ICSK_ACK_PUSHED2 = 8, + ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */ +}; + +enum tcp_ca_event { + CA_EVENT_TX_START = 0, + CA_EVENT_CWND_RESTART = 1, + CA_EVENT_COMPLETE_CWR = 2, + CA_EVENT_LOSS = 3, + CA_EVENT_ECN_NO_CE = 4, + CA_EVENT_ECN_IS_CE = 5, +}; + +enum tcp_ca_state { + TCP_CA_Open = 0, + TCP_CA_Disorder = 1, + TCP_CA_CWR = 2, + TCP_CA_Recovery = 3, + TCP_CA_Loss = 4 +}; + +struct ack_sample { + __u32 pkts_acked; + __s32 rtt_us; + __u32 in_flight; +} __attribute__((preserve_access_index)); + +struct rate_sample { + __u64 prior_mstamp; /* starting timestamp for interval */ + __u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ + __s32 delivered; /* number of packets delivered over interval */ + long interval_us; /* time for tp->delivered to incr "delivered" */ + __u32 snd_interval_us; /* snd interval for delivered packets */ + __u32 rcv_interval_us; /* rcv interval for delivered packets */ + long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ + int losses; /* number of packets marked lost upon ACK */ + __u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ + __u32 prior_in_flight; /* in flight before this ACK */ + bool is_app_limited; /* is sample from packet with bubble in pipe? */ + bool is_retrans; /* is sample from retransmission? */ + bool is_ack_delayed; /* is this (likely) a delayed ACK? */ +} __attribute__((preserve_access_index)); + +#define TCP_CA_NAME_MAX 16 +#define TCP_CONG_NEEDS_ECN 0x2 + +struct tcp_congestion_ops { + char name[TCP_CA_NAME_MAX]; + __u32 flags; + + /* initialize private data (optional) */ + void (*init)(struct sock *sk); + /* cleanup private data (optional) */ + void (*release)(struct sock *sk); + + /* return slow start threshold (required) */ + __u32 (*ssthresh)(struct sock *sk); + /* do new cwnd calculation (required) */ + void (*cong_avoid)(struct sock *sk, __u32 ack, __u32 acked); + /* call before changing ca_state (optional) */ + void (*set_state)(struct sock *sk, __u8 new_state); + /* call when cwnd event occurs (optional) */ + void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); + /* call when ack arrives (optional) */ + void (*in_ack_event)(struct sock *sk, __u32 flags); + /* new value of cwnd after loss (required) */ + __u32 (*undo_cwnd)(struct sock *sk); + /* hook for packet ack accounting (optional) */ + void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); + /* override sysctl_tcp_min_tso_segs */ + __u32 (*min_tso_segs)(struct sock *sk); + /* returns the multiplier used in tcp_sndbuf_expand (optional) */ + __u32 (*sndbuf_expand)(struct sock *sk); + /* call when packets are delivered to update cwnd and pacing rate, + * after all the ca_state processing. (optional) + */ + void (*cong_control)(struct sock *sk, const struct rate_sample *rs); +}; + +#define min(a, b) ((a) < (b) ? (a) : (b)) +#define max(a, b) ((a) > (b) ? (a) : (b)) +#define min_not_zero(x, y) ({ \ + typeof(x) __x = (x); \ + typeof(y) __y = (y); \ + __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) + +static __always_inline __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) +{ + __u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh); + + acked -= cwnd - tp->snd_cwnd; + tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); + + return acked; +} + +static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp) +{ + return tp->snd_cwnd < tp->snd_ssthresh; +} + +static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + + /* If in slow start, ensure cwnd grows to twice what was ACKed. */ + if (tcp_in_slow_start(tp)) + return tp->snd_cwnd < 2 * tp->max_packets_out; + + return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited); +} + +static __always_inline void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) +{ + /* If credits accumulated at a higher w, apply them gently now. */ + if (tp->snd_cwnd_cnt >= w) { + tp->snd_cwnd_cnt = 0; + tp->snd_cwnd++; + } + + tp->snd_cwnd_cnt += acked; + if (tp->snd_cwnd_cnt >= w) { + __u32 delta = tp->snd_cwnd_cnt / w; + + tp->snd_cwnd_cnt -= delta * w; + tp->snd_cwnd += delta; + } + tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp); +} + +#endif diff --git a/tools/testing/selftests/bpf/bpf_trace_helpers.h b/tools/testing/selftests/bpf/bpf_trace_helpers.h index c76a214a53b0..c6f1354d93fb 100644 --- a/tools/testing/selftests/bpf/bpf_trace_helpers.h +++ b/tools/testing/selftests/bpf/bpf_trace_helpers.h @@ -1,58 +1,120 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ #ifndef __BPF_TRACE_HELPERS_H #define __BPF_TRACE_HELPERS_H -#include "bpf_helpers.h" - -#define __BPF_MAP_0(i, m, v, ...) v -#define __BPF_MAP_1(i, m, v, t, a, ...) m(t, a, ctx[i]) -#define __BPF_MAP_2(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_1(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_3(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_2(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_4(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_3(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_5(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_4(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_6(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_5(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_7(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_6(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_8(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_7(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_9(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_8(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_10(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_9(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_11(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_10(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP_12(i, m, v, t, a, ...) m(t, a, ctx[i]), __BPF_MAP_11(i+1, m, v, __VA_ARGS__) -#define __BPF_MAP(n, ...) __BPF_MAP_##n(0, __VA_ARGS__) - -/* BPF sizeof(void *) is always 8, so no need to cast to long first - * for ptr to avoid compiler warning. +#include <bpf/bpf_helpers.h> + +#define ___bpf_concat(a, b) a ## b +#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#define ___bpf_narg(...) \ + ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#define ___bpf_empty(...) \ + ___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0) + +#define ___bpf_ctx_cast0() ctx +#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] +#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] +#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] +#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] +#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] +#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] +#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] +#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] +#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] +#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9] +#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10] +#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11] +#define ___bpf_ctx_cast(args...) \ + ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) + +/* + * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and + * similar kinds of BPF programs, that accept input arguments as a single + * pointer to untyped u64 array, where each u64 can actually be a typed + * pointer or integer of different size. Instead of requring user to write + * manual casts and work with array elements by index, BPF_PROG macro + * allows user to declare a list of named and typed input arguments in the + * same syntax as for normal C function. All the casting is hidden and + * performed transparently, while user code can just assume working with + * function arguments of specified type and name. + * + * Original raw context argument is preserved as well as 'ctx' argument. + * This is useful when using BPF helpers that expect original context + * as one of the parameters (e.g., for bpf_perf_event_output()). */ -#define __BPF_CAST(t, a, ctx) (t) ctx -#define __BPF_V void -#define __BPF_N - -#define __BPF_DECL_ARGS(t, a, ctx) t a - -#define BPF_TRACE_x(x, sec_name, fname, ret_type, ...) \ -static __always_inline ret_type \ -____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ - \ -SEC(sec_name) \ -ret_type fname(__u64 *ctx) \ -{ \ - return ____##fname(__BPF_MAP(x, __BPF_CAST, __BPF_N, __VA_ARGS__));\ -} \ - \ -static __always_inline \ -ret_type ____##fname(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) - -#define BPF_TRACE_0(sec, fname, ...) BPF_TRACE_x(0, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_1(sec, fname, ...) BPF_TRACE_x(1, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_2(sec, fname, ...) BPF_TRACE_x(2, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_3(sec, fname, ...) BPF_TRACE_x(3, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_4(sec, fname, ...) BPF_TRACE_x(4, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_5(sec, fname, ...) BPF_TRACE_x(5, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_6(sec, fname, ...) BPF_TRACE_x(6, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_7(sec, fname, ...) BPF_TRACE_x(7, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_8(sec, fname, ...) BPF_TRACE_x(8, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_9(sec, fname, ...) BPF_TRACE_x(9, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_10(sec, fname, ...) BPF_TRACE_x(10, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_11(sec, fname, ...) BPF_TRACE_x(11, sec, fname, int, __VA_ARGS__) -#define BPF_TRACE_12(sec, fname, ...) BPF_TRACE_x(12, sec, fname, int, __VA_ARGS__) +#define BPF_PROG(name, args...) \ +name(unsigned long long *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_ctx_cast(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx, ##args) + +struct pt_regs; + +#define ___bpf_kprobe_args0() ctx +#define ___bpf_kprobe_args1(x) \ + ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) +#define ___bpf_kprobe_args2(x, args...) \ + ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) +#define ___bpf_kprobe_args3(x, args...) \ + ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) +#define ___bpf_kprobe_args4(x, args...) \ + ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) +#define ___bpf_kprobe_args5(x, args...) \ + ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args(args...) \ + ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) +/* + * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for + * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific + * low-level way of getting kprobe input arguments from struct pt_regs, and + * provides a familiar typed and named function arguments syntax and + * semantics of accessing kprobe input paremeters. + * + * Original struct pt_regs* context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + */ +#define BPF_KPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) + +#define ___bpf_kretprobe_args0() ctx +#define ___bpf_kretprobe_argsN(x, args...) \ + ___bpf_kprobe_args(args), (void *)PT_REGS_RET(ctx) +#define ___bpf_kretprobe_args(args...) \ + ___bpf_apply(___bpf_kretprobe_args, ___bpf_empty(args))(args) + +/* + * BPF_KRETPROBE is similar to BPF_KPROBE, except, in addition to listing all + * input kprobe arguments, one last extra argument has to be specified, which + * captures kprobe return value. + */ +#define BPF_KRETPROBE(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args);\ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_kretprobe_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) #endif diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index ec219f84e041..a3352a64c067 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -6,7 +6,7 @@ #include <stdlib.h> #include <string.h> #include <errno.h> -#include <libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ static inline unsigned int bpf_num_possible_cpus(void) { diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c new file mode 100644 index 000000000000..f0a64d8ac59a --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <errno.h> +#include <string.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <test_maps.h> + +static void map_batch_update(int map_fd, __u32 max_entries, int *keys, + int *values) +{ + int i, err; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + for (i = 0; i < max_entries; i++) { + keys[i] = i; + values[i] = i + 1; + } + + err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts); + CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno)); +} + +static void map_batch_verify(int *visited, __u32 max_entries, + int *keys, int *values) +{ + int i; + + memset(visited, 0, max_entries * sizeof(*visited)); + for (i = 0; i < max_entries; i++) { + CHECK(keys[i] + 1 != values[i], "key/value checking", + "error: i %d key %d value %d\n", i, keys[i], values[i]); + visited[i] = 1; + } + for (i = 0; i < max_entries; i++) { + CHECK(visited[i] != 1, "visited checking", + "error: keys array at index %d missing\n", i); + } +} + +void test_array_map_batch_ops(void) +{ + struct bpf_create_map_attr xattr = { + .name = "array_map", + .map_type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + }; + int map_fd, *keys, *values, *visited; + __u32 count, total, total_success; + const __u32 max_entries = 10; + bool nospace_err; + __u64 batch = 0; + int err, step; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + xattr.max_entries = max_entries; + map_fd = bpf_create_map_xattr(&xattr); + CHECK(map_fd == -1, + "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + + keys = malloc(max_entries * sizeof(int)); + values = malloc(max_entries * sizeof(int)); + visited = malloc(max_entries * sizeof(int)); + CHECK(!keys || !values || !visited, "malloc()", "error:%s\n", + strerror(errno)); + + /* populate elements to the map */ + map_batch_update(map_fd, max_entries, keys, values); + + /* test 1: lookup in a loop with various steps. */ + total_success = 0; + for (step = 1; step < max_entries; step++) { + map_batch_update(map_fd, max_entries, keys, values); + map_batch_verify(visited, max_entries, keys, values); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * sizeof(*values)); + batch = 0; + total = 0; + /* iteratively lookup/delete elements with 'step' + * elements each. + */ + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_batch(map_fd, + total ? &batch : NULL, &batch, + keys + total, + values + total, + &count, &opts); + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + + } + + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + map_batch_verify(visited, max_entries, keys, values); + + total_success++; + } + + CHECK(total_success == 0, "check total_success", + "unexpected failure\n"); + + printf("%s:PASS\n", __func__); + + free(keys); + free(values); + free(visited); +} diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c new file mode 100644 index 000000000000..976bf415fbdd --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <stdio.h> +#include <errno.h> +#include <string.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <bpf_util.h> +#include <test_maps.h> + +static void map_batch_update(int map_fd, __u32 max_entries, int *keys, + void *values, bool is_pcpu) +{ + typedef BPF_DECLARE_PERCPU(int, value); + value *v = NULL; + int i, j, err; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + if (is_pcpu) + v = (value *)values; + + for (i = 0; i < max_entries; i++) { + keys[i] = i + 1; + if (is_pcpu) + for (j = 0; j < bpf_num_possible_cpus(); j++) + bpf_percpu(v[i], j) = i + 2 + j; + else + ((int *)values)[i] = i + 2; + } + + err = bpf_map_update_batch(map_fd, keys, values, &max_entries, &opts); + CHECK(err, "bpf_map_update_batch()", "error:%s\n", strerror(errno)); +} + +static void map_batch_verify(int *visited, __u32 max_entries, + int *keys, void *values, bool is_pcpu) +{ + typedef BPF_DECLARE_PERCPU(int, value); + value *v = NULL; + int i, j; + + if (is_pcpu) + v = (value *)values; + + memset(visited, 0, max_entries * sizeof(*visited)); + for (i = 0; i < max_entries; i++) { + + if (is_pcpu) { + for (j = 0; j < bpf_num_possible_cpus(); j++) { + CHECK(keys[i] + 1 + j != bpf_percpu(v[i], j), + "key/value checking", + "error: i %d j %d key %d value %d\n", + i, j, keys[i], bpf_percpu(v[i], j)); + } + } else { + CHECK(keys[i] + 1 != ((int *)values)[i], + "key/value checking", + "error: i %d key %d value %d\n", i, keys[i], + ((int *)values)[i]); + } + + visited[i] = 1; + + } + for (i = 0; i < max_entries; i++) { + CHECK(visited[i] != 1, "visited checking", + "error: keys array at index %d missing\n", i); + } +} + +void __test_map_lookup_and_delete_batch(bool is_pcpu) +{ + __u32 batch, count, total, total_success; + typedef BPF_DECLARE_PERCPU(int, value); + int map_fd, *keys, *visited, key; + const __u32 max_entries = 10; + value pcpu_values[max_entries]; + int err, step, value_size; + bool nospace_err; + void *values; + struct bpf_create_map_attr xattr = { + .name = "hash_map", + .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH : + BPF_MAP_TYPE_HASH, + .key_size = sizeof(int), + .value_size = sizeof(int), + }; + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + xattr.max_entries = max_entries; + map_fd = bpf_create_map_xattr(&xattr); + CHECK(map_fd == -1, + "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + + value_size = is_pcpu ? sizeof(value) : sizeof(int); + keys = malloc(max_entries * sizeof(int)); + if (is_pcpu) + values = pcpu_values; + else + values = malloc(max_entries * sizeof(int)); + visited = malloc(max_entries * sizeof(int)); + CHECK(!keys || !values || !visited, "malloc()", + "error:%s\n", strerror(errno)); + + /* test 1: lookup/delete an empty hash table, -ENOENT */ + count = max_entries; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK((err && errno != ENOENT), "empty map", + "error: %s\n", strerror(errno)); + + /* populate elements to the map */ + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + + /* test 2: lookup/delete with count = 0, success */ + count = 0; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK(err, "count = 0", "error: %s\n", strerror(errno)); + + /* test 3: lookup/delete with count = max_entries, success */ + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + count = max_entries; + err = bpf_map_lookup_and_delete_batch(map_fd, NULL, &batch, keys, + values, &count, &opts); + CHECK((err && errno != ENOENT), "count = max_entries", + "error: %s\n", strerror(errno)); + CHECK(count != max_entries, "count = max_entries", + "count = %u, max_entries = %u\n", count, max_entries); + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + + /* bpf_map_get_next_key() should return -ENOENT for an empty map. */ + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", strerror(errno)); + + /* test 4: lookup/delete in a loop with various steps. */ + total_success = 0; + for (step = 1; step < max_entries; step++) { + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + total = 0; + /* iteratively lookup/delete elements with 'step' + * elements each + */ + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_batch(map_fd, + total ? &batch : NULL, + &batch, keys + total, + values + + total * value_size, + &count, &opts); + /* It is possible that we are failing due to buffer size + * not big enough. In such cases, let us just exit and + * go with large steps. Not that a buffer size with + * max_entries should always work. + */ + if (err && errno == ENOSPC) { + nospace_err = true; + break; + } + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + + } + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup with steps", + "total = %u, max_entries = %u\n", total, max_entries); + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + + total = 0; + count = step; + while (total < max_entries) { + if (max_entries - total < step) + count = max_entries - total; + err = bpf_map_delete_batch(map_fd, + keys + total, + &count, &opts); + CHECK((err && errno != ENOENT), "delete batch", + "error: %s\n", strerror(errno)); + total += count; + if (err) + break; + } + CHECK(total != max_entries, "delete with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + /* check map is empty, errono == ENOENT */ + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()", + "error: %s\n", strerror(errno)); + + /* iteratively lookup/delete elements with 'step' + * elements each + */ + map_batch_update(map_fd, max_entries, keys, values, is_pcpu); + memset(keys, 0, max_entries * sizeof(*keys)); + memset(values, 0, max_entries * value_size); + total = 0; + count = step; + nospace_err = false; + while (true) { + err = bpf_map_lookup_and_delete_batch(map_fd, + total ? &batch : NULL, + &batch, keys + total, + values + + total * value_size, + &count, &opts); + /* It is possible that we are failing due to buffer size + * not big enough. In such cases, let us just exit and + * go with large steps. Not that a buffer size with + * max_entries should always work. + */ + if (err && errno == ENOSPC) { + nospace_err = true; + break; + } + + CHECK((err && errno != ENOENT), "lookup with steps", + "error: %s\n", strerror(errno)); + + total += count; + if (err) + break; + } + + if (nospace_err == true) + continue; + + CHECK(total != max_entries, "lookup/delete with steps", + "total = %u, max_entries = %u\n", total, max_entries); + + map_batch_verify(visited, max_entries, keys, values, is_pcpu); + err = bpf_map_get_next_key(map_fd, NULL, &key); + CHECK(!err, "bpf_map_get_next_key()", "error: %s\n", + strerror(errno)); + + total_success++; + } + + CHECK(total_success == 0, "check total_success", + "unexpected failure\n"); + free(keys); + free(visited); + if (!is_pcpu) + free(values); +} + +void htab_map_batch_ops(void) +{ + __test_map_lookup_and_delete_batch(false); + printf("test_%s:PASS\n", __func__); +} + +void htab_percpu_map_batch_ops(void) +{ + __test_map_lookup_and_delete_batch(true); + printf("test_%s:PASS\n", __func__); +} + +void test_htab_map_batch_ops(void) +{ + htab_map_batch_ops(); + htab_percpu_map_batch_ops(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index a83111a32d4a..a0ee87c8e1ea 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -1,26 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> - -#define EMBED_FILE(NAME, PATH) \ -asm ( \ -" .pushsection \".rodata\", \"a\", @progbits \n" \ -" .global "#NAME"_data \n" \ -#NAME"_data: \n" \ -" .incbin \"" PATH "\" \n" \ -#NAME"_data_end: \n" \ -" .global "#NAME"_size \n" \ -" .type "#NAME"_size, @object \n" \ -" .size "#NAME"_size, 4 \n" \ -" .align 4, \n" \ -#NAME"_size: \n" \ -" .int "#NAME"_data_end - "#NAME"_data \n" \ -" .popsection \n" \ -); \ -extern char NAME##_data[]; \ -extern int NAME##_size; +#include "test_attach_probe.skel.h" ssize_t get_base_addr() { - size_t start; + size_t start, offset; char buf[256]; FILE *f; @@ -28,10 +11,11 @@ ssize_t get_base_addr() { if (!f) return -errno; - while (fscanf(f, "%zx-%*x %s %*s\n", &start, buf) == 2) { + while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n", + &start, buf, &offset) == 3) { if (strcmp(buf, "r-xp") == 0) { fclose(f); - return start; + return start - offset; } } @@ -39,30 +23,12 @@ ssize_t get_base_addr() { return -EINVAL; } -EMBED_FILE(probe, "test_attach_probe.o"); - void test_attach_probe(void) { - const char *kprobe_name = "kprobe/sys_nanosleep"; - const char *kretprobe_name = "kretprobe/sys_nanosleep"; - const char *uprobe_name = "uprobe/trigger_func"; - const char *uretprobe_name = "uretprobe/trigger_func"; - const int kprobe_idx = 0, kretprobe_idx = 1; - const int uprobe_idx = 2, uretprobe_idx = 3; - const char *obj_name = "attach_probe"; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts, - .object_name = obj_name, - .relaxed_maps = true, - ); - struct bpf_program *kprobe_prog, *kretprobe_prog; - struct bpf_program *uprobe_prog, *uretprobe_prog; - struct bpf_object *obj; - int err, duration = 0, res; - struct bpf_link *kprobe_link = NULL; - struct bpf_link *kretprobe_link = NULL; - struct bpf_link *uprobe_link = NULL; - struct bpf_link *uretprobe_link = NULL; - int results_map_fd; + int duration = 0; + struct bpf_link *kprobe_link, *kretprobe_link; + struct bpf_link *uprobe_link, *uretprobe_link; + struct test_attach_probe* skel; size_t uprobe_offset; ssize_t base_addr; @@ -72,123 +38,68 @@ void test_attach_probe(void) return; uprobe_offset = (size_t)&get_base_addr - base_addr; - /* open object */ - obj = bpf_object__open_mem(probe_data, probe_size, &open_opts); - if (CHECK(IS_ERR(obj), "obj_open_mem", "err %ld\n", PTR_ERR(obj))) + skel = test_attach_probe__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) return; - - if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name", - "wrong obj name '%s', expected '%s'\n", - bpf_object__name(obj), obj_name)) + if (CHECK(!skel->bss, "check_bss", ".bss wasn't mmap()-ed\n")) goto cleanup; - kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name); - if (CHECK(!kprobe_prog, "find_probe", - "prog '%s' not found\n", kprobe_name)) - goto cleanup; - kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name); - if (CHECK(!kretprobe_prog, "find_probe", - "prog '%s' not found\n", kretprobe_name)) - goto cleanup; - uprobe_prog = bpf_object__find_program_by_title(obj, uprobe_name); - if (CHECK(!uprobe_prog, "find_probe", - "prog '%s' not found\n", uprobe_name)) - goto cleanup; - uretprobe_prog = bpf_object__find_program_by_title(obj, uretprobe_name); - if (CHECK(!uretprobe_prog, "find_probe", - "prog '%s' not found\n", uretprobe_name)) - goto cleanup; - - /* create maps && load programs */ - err = bpf_object__load(obj); - if (CHECK(err, "obj_load", "err %d\n", err)) - goto cleanup; - - /* load maps */ - results_map_fd = bpf_find_map(__func__, obj, "results_map"); - if (CHECK(results_map_fd < 0, "find_results_map", - "err %d\n", results_map_fd)) - goto cleanup; - - kprobe_link = bpf_program__attach_kprobe(kprobe_prog, + kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe, false /* retprobe */, SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", - "err %ld\n", PTR_ERR(kprobe_link))) { - kprobe_link = NULL; + "err %ld\n", PTR_ERR(kprobe_link))) goto cleanup; - } - kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog, + skel->links.handle_kprobe = kprobe_link; + + kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe, true /* retprobe */, SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe", - "err %ld\n", PTR_ERR(kretprobe_link))) { - kretprobe_link = NULL; + "err %ld\n", PTR_ERR(kretprobe_link))) goto cleanup; - } - uprobe_link = bpf_program__attach_uprobe(uprobe_prog, + skel->links.handle_kretprobe = kretprobe_link; + + uprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uprobe, false /* retprobe */, 0 /* self pid */, "/proc/self/exe", uprobe_offset); if (CHECK(IS_ERR(uprobe_link), "attach_uprobe", - "err %ld\n", PTR_ERR(uprobe_link))) { - uprobe_link = NULL; + "err %ld\n", PTR_ERR(uprobe_link))) goto cleanup; - } - uretprobe_link = bpf_program__attach_uprobe(uretprobe_prog, + skel->links.handle_uprobe = uprobe_link; + + uretprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uretprobe, true /* retprobe */, -1 /* any pid */, "/proc/self/exe", uprobe_offset); if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe", - "err %ld\n", PTR_ERR(uretprobe_link))) { - uretprobe_link = NULL; + "err %ld\n", PTR_ERR(uretprobe_link))) goto cleanup; - } + skel->links.handle_uretprobe = uretprobe_link; /* trigger & validate kprobe && kretprobe */ usleep(1); - err = bpf_map_lookup_elem(results_map_fd, &kprobe_idx, &res); - if (CHECK(err, "get_kprobe_res", - "failed to get kprobe res: %d\n", err)) + if (CHECK(skel->bss->kprobe_res != 1, "check_kprobe_res", + "wrong kprobe res: %d\n", skel->bss->kprobe_res)) goto cleanup; - if (CHECK(res != kprobe_idx + 1, "check_kprobe_res", - "wrong kprobe res: %d\n", res)) - goto cleanup; - - err = bpf_map_lookup_elem(results_map_fd, &kretprobe_idx, &res); - if (CHECK(err, "get_kretprobe_res", - "failed to get kretprobe res: %d\n", err)) - goto cleanup; - if (CHECK(res != kretprobe_idx + 1, "check_kretprobe_res", - "wrong kretprobe res: %d\n", res)) + if (CHECK(skel->bss->kretprobe_res != 2, "check_kretprobe_res", + "wrong kretprobe res: %d\n", skel->bss->kretprobe_res)) goto cleanup; /* trigger & validate uprobe & uretprobe */ get_base_addr(); - err = bpf_map_lookup_elem(results_map_fd, &uprobe_idx, &res); - if (CHECK(err, "get_uprobe_res", - "failed to get uprobe res: %d\n", err)) - goto cleanup; - if (CHECK(res != uprobe_idx + 1, "check_uprobe_res", - "wrong uprobe res: %d\n", res)) - goto cleanup; - - err = bpf_map_lookup_elem(results_map_fd, &uretprobe_idx, &res); - if (CHECK(err, "get_uretprobe_res", - "failed to get uretprobe res: %d\n", err)) + if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res", + "wrong uprobe res: %d\n", skel->bss->uprobe_res)) goto cleanup; - if (CHECK(res != uretprobe_idx + 1, "check_uretprobe_res", - "wrong uretprobe res: %d\n", res)) + if (CHECK(skel->bss->uretprobe_res != 4, "check_uretprobe_res", + "wrong uretprobe res: %d\n", skel->bss->uretprobe_res)) goto cleanup; cleanup: - bpf_link__destroy(kprobe_link); - bpf_link__destroy(kretprobe_link); - bpf_link__destroy(uprobe_link); - bpf_link__destroy(uretprobe_link); - bpf_object__close(obj); + test_attach_probe__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c new file mode 100644 index 000000000000..8482bbc67eec --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <linux/err.h> +#include <test_progs.h> +#include "bpf_dctcp.skel.h" +#include "bpf_cubic.skel.h" + +#define min(a, b) ((a) < (b) ? (a) : (b)) + +static const unsigned int total_bytes = 10 * 1024 * 1024; +static const struct timeval timeo_sec = { .tv_sec = 10 }; +static const size_t timeo_optlen = sizeof(timeo_sec); +static int stop, duration; + +static int settimeo(int fd) +{ + int err; + + err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec, + timeo_optlen); + if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n", + errno)) + return -1; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec, + timeo_optlen); + if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n", + errno)) + return -1; + + return 0; +} + +static int settcpca(int fd, const char *tcp_ca) +{ + int err; + + err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca)); + if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n", + errno)) + return -1; + + return 0; +} + +static void *server(void *arg) +{ + int lfd = (int)(long)arg, err = 0, fd; + ssize_t nr_sent = 0, bytes = 0; + char batch[1500]; + + fd = accept(lfd, NULL, NULL); + while (fd == -1) { + if (errno == EINTR) + continue; + err = -errno; + goto done; + } + + if (settimeo(fd)) { + err = -errno; + goto done; + } + + while (bytes < total_bytes && !READ_ONCE(stop)) { + nr_sent = send(fd, &batch, + min(total_bytes - bytes, sizeof(batch)), 0); + if (nr_sent == -1 && errno == EINTR) + continue; + if (nr_sent == -1) { + err = -errno; + break; + } + bytes += nr_sent; + } + + CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n", + bytes, total_bytes, nr_sent, errno); + +done: + if (fd != -1) + close(fd); + if (err) { + WRITE_ONCE(stop, 1); + return ERR_PTR(err); + } + return NULL; +} + +static void do_test(const char *tcp_ca) +{ + struct sockaddr_in6 sa6 = {}; + ssize_t nr_recv = 0, bytes = 0; + int lfd = -1, fd = -1; + pthread_t srv_thread; + socklen_t addrlen = sizeof(sa6); + void *thread_ret; + char batch[1500]; + int err; + + WRITE_ONCE(stop, 0); + + lfd = socket(AF_INET6, SOCK_STREAM, 0); + if (CHECK(lfd == -1, "socket", "errno:%d\n", errno)) + return; + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) { + close(lfd); + return; + } + + if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) || + settimeo(lfd) || settimeo(fd)) + goto done; + + /* bind, listen and start server thread to accept */ + sa6.sin6_family = AF_INET6; + sa6.sin6_addr = in6addr_loopback; + err = bind(lfd, (struct sockaddr *)&sa6, addrlen); + if (CHECK(err == -1, "bind", "errno:%d\n", errno)) + goto done; + err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen); + if (CHECK(err == -1, "getsockname", "errno:%d\n", errno)) + goto done; + err = listen(lfd, 1); + if (CHECK(err == -1, "listen", "errno:%d\n", errno)) + goto done; + err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd); + if (CHECK(err != 0, "pthread_create", "err:%d\n", err)) + goto done; + + /* connect to server */ + err = connect(fd, (struct sockaddr *)&sa6, addrlen); + if (CHECK(err == -1, "connect", "errno:%d\n", errno)) + goto wait_thread; + + /* recv total_bytes */ + while (bytes < total_bytes && !READ_ONCE(stop)) { + nr_recv = recv(fd, &batch, + min(total_bytes - bytes, sizeof(batch)), 0); + if (nr_recv == -1 && errno == EINTR) + continue; + if (nr_recv == -1) + break; + bytes += nr_recv; + } + + CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n", + bytes, total_bytes, nr_recv, errno); + +wait_thread: + WRITE_ONCE(stop, 1); + pthread_join(srv_thread, &thread_ret); + CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld", + PTR_ERR(thread_ret)); +done: + close(lfd); + close(fd); +} + +static void test_cubic(void) +{ + struct bpf_cubic *cubic_skel; + struct bpf_link *link; + + cubic_skel = bpf_cubic__open_and_load(); + if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n")) + return; + + link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic); + if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n", + PTR_ERR(link))) { + bpf_cubic__destroy(cubic_skel); + return; + } + + do_test("bpf_cubic"); + + bpf_link__destroy(link); + bpf_cubic__destroy(cubic_skel); +} + +static void test_dctcp(void) +{ + struct bpf_dctcp *dctcp_skel; + struct bpf_link *link; + + dctcp_skel = bpf_dctcp__open_and_load(); + if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n")) + return; + + link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp); + if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n", + PTR_ERR(link))) { + bpf_dctcp__destroy(dctcp_skel); + return; + } + + do_test("bpf_dctcp"); + + bpf_link__destroy(link); + bpf_dctcp__destroy(dctcp_skel); +} + +void test_bpf_tcp_ca(void) +{ + if (test__start_subtest("dctcp")) + test_dctcp(); + if (test__start_subtest("cubic")) + test_cubic(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index 9486c13af6b2..e9f2f12ba06b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -48,6 +48,8 @@ void test_bpf_verif_scale(void) { "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS }, { "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS }, + { "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, + /* full unroll by llvm */ { "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, { "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT }, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c new file mode 100644 index 000000000000..5b13f2c6c402 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int prog_load(void) +{ + struct bpf_insn prog[] = { + BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); +} + +void test_cgroup_attach_autodetach(void) +{ + __u32 duration = 0, prog_cnt = 4, attach_flags; + int allow_prog[2] = {-1}; + __u32 prog_ids[2] = {0}; + void *ptr = NULL; + int cg = 0, i; + int attempts; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + allow_prog[i] = prog_load(); + if (CHECK(allow_prog[i] < 0, "prog_load", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + } + + if (CHECK_FAIL(setup_cgroup_environment())) + goto err; + + /* create a cgroup, attach two programs and remember their ids */ + cg = create_and_get_cgroup("/cg_autodetach"); + if (CHECK_FAIL(cg < 0)) + goto err; + + if (CHECK_FAIL(join_cgroup("/cg_autodetach"))) + goto err; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (CHECK(bpf_prog_attach(allow_prog[i], cg, + BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog_attach", "prog[%d], errno=%d\n", i, errno)) + goto err; + + /* make sure that programs are attached and run some traffic */ + if (CHECK(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags, + prog_ids, &prog_cnt), + "prog_query", "errno=%d\n", errno)) + goto err; + if (CHECK_FAIL(system(PING_CMD))) + goto err; + + /* allocate some memory (4Mb) to pin the original cgroup */ + ptr = malloc(4 * (1 << 20)); + if (CHECK_FAIL(!ptr)) + goto err; + + /* close programs and cgroup fd */ + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + close(allow_prog[i]); + allow_prog[i] = -1; + } + + close(cg); + cg = 0; + + /* leave the cgroup and remove it. don't detach programs */ + cleanup_cgroup_environment(); + + /* wait for the asynchronous auto-detachment. + * wait for no more than 5 sec and give up. + */ + for (i = 0; i < ARRAY_SIZE(prog_ids); i++) { + for (attempts = 5; attempts >= 0; attempts--) { + int fd = bpf_prog_get_fd_by_id(prog_ids[i]); + + if (fd < 0) + break; + + /* don't leave the fd open */ + close(fd); + + if (CHECK_FAIL(!attempts)) + goto err; + + sleep(1); + } + } + +err: + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (allow_prog[i] >= 0) + close(allow_prog[i]); + if (cg) + close(cg); + free(ptr); + cleanup_cgroup_environment(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c new file mode 100644 index 000000000000..2ff21dbce179 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int map_fd = -1; + +static int prog_load_cnt(int verdict, int val) +{ + int cgroup_storage_fd, percpu_cgroup_storage_fd; + + if (map_fd < 0) + map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); + if (map_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, + sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + if (cgroup_storage_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + percpu_cgroup_storage_fd = bpf_create_map( + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + if (percpu_cgroup_storage_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + struct bpf_insn prog[] = { + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + + BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), + BPF_MOV64_IMM(BPF_REG_1, val), + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0), + + BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), + BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), + + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + int ret; + + ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); + + close(cgroup_storage_fd); + return ret; +} + +void test_cgroup_attach_multi(void) +{ + __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id; + int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; + DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, attach_opts); + int allow_prog[7] = {-1}; + unsigned long long value; + __u32 duration = 0; + int i = 0; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + allow_prog[i] = prog_load_cnt(1, 1 << i); + if (CHECK(allow_prog[i] < 0, "prog_load", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + } + + if (CHECK_FAIL(setup_cgroup_environment())) + goto err; + + cg1 = create_and_get_cgroup("/cg1"); + if (CHECK_FAIL(cg1 < 0)) + goto err; + cg2 = create_and_get_cgroup("/cg1/cg2"); + if (CHECK_FAIL(cg2 < 0)) + goto err; + cg3 = create_and_get_cgroup("/cg1/cg2/cg3"); + if (CHECK_FAIL(cg3 < 0)) + goto err; + cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4"); + if (CHECK_FAIL(cg4 < 0)) + goto err; + cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5"); + if (CHECK_FAIL(cg5 < 0)) + goto err; + + if (CHECK_FAIL(join_cgroup("/cg1/cg2/cg3/cg4/cg5"))) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog0_attach_to_cg1_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "fail_same_prog_attach_to_cg1", "unexpected success\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog1_attach_to_cg1_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog2_attach_to_cg2_override", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog3_attach_to_cg3_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog4_attach_to_cg4_override", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0), + "prog5_attach_to_cg5_none", "errno=%d\n", errno)) + goto err; + + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 1 + 2 + 8 + 32); + + /* query the number of effective progs in cg5 */ + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, NULL, NULL, &prog_cnt)); + CHECK_FAIL(prog_cnt != 4); + /* retrieve prog_ids of effective progs in cg5 */ + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 4); + CHECK_FAIL(attach_flags != 0); + saved_prog_id = prog_ids[0]; + /* check enospc handling */ + prog_ids[0] = 0; + prog_cnt = 2; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt) != -1); + CHECK_FAIL(errno != ENOSPC); + CHECK_FAIL(prog_cnt != 4); + /* check that prog_ids are returned even when buffer is too small */ + CHECK_FAIL(prog_ids[0] != saved_prog_id); + /* retrieve prog_id of single attached prog in cg5 */ + prog_ids[0] = 0; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 1); + CHECK_FAIL(prog_ids[0] != saved_prog_id); + + /* detach bottom program and ping again */ + if (CHECK(bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS), + "prog_detach_from_cg5", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 1 + 2 + 8 + 16); + + /* test replace */ + + attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE; + attach_opts.replace_prog_fd = allow_prog[0]; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_override", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EINVAL); + + attach_opts.flags = BPF_F_REPLACE; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_no_multi", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EINVAL); + + attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE; + attach_opts.replace_prog_fd = -1; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_bad_fd", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EBADF); + + /* replacing a program that is not attached to cgroup should fail */ + attach_opts.replace_prog_fd = allow_prog[3]; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_no_ent", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != ENOENT); + + /* replace 1st from the top program */ + attach_opts.replace_prog_fd = allow_prog[0]; + if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "prog_replace", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 8 + 16); + + /* detach 3rd from bottom program and ping again */ + if (CHECK(!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS), + "fail_prog_detach_from_cg3", "unexpected success\n")) + goto err; + + if (CHECK(bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS), + "prog3_detach_from_cg3", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 16); + + /* detach 2nd from bottom program and ping again */ + if (CHECK(bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS), + "prog_detach_from_cg4", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 4); + + prog_cnt = 4; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 3); + CHECK_FAIL(attach_flags != 0); + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 0); + +err: + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (allow_prog[i] >= 0) + close(allow_prog[i]); + close(cg1); + close(cg2); + close(cg3); + close(cg4); + close(cg5); + cleanup_cgroup_environment(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c new file mode 100644 index 000000000000..9d8cb48b99de --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define FOO "/foo" +#define BAR "/foo/bar/" +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int prog_load(int verdict) +{ + struct bpf_insn prog[] = { + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); +} + +void test_cgroup_attach_override(void) +{ + int drop_prog = -1, allow_prog = -1, foo = -1, bar = -1; + __u32 duration = 0; + + allow_prog = prog_load(1); + if (CHECK(allow_prog < 0, "prog_load_allow", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + + drop_prog = prog_load(0); + if (CHECK(drop_prog < 0, "prog_load_drop", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + + foo = test__join_cgroup(FOO); + if (CHECK(foo < 0, "cgroup_join_foo", "cgroup setup failed\n")) + goto err; + + if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_drop_foo_override", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + bar = test__join_cgroup(BAR); + if (CHECK(bar < 0, "cgroup_join_bar", "cgroup setup failed\n")) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n")) + goto err; + + if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS), + "prog_detach_bar", + "detach prog from %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS), + "prog_detach_foo", + "detach prog from %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0), + "fail_prog_attach_allow_bar_none", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS), + "prog_detach_bar", + "detach prog from %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS), + "fail_prog_detach_foo", + "double detach from %s unexpectedly succeeded\n", FOO)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0), + "prog_attach_allow_foo_none", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0), + "fail_prog_attach_allow_bar_none", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "fail_prog_attach_allow_bar_override", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "fail_prog_attach_allow_foo_override", + "attach prog to %s unexpectedly succeeded\n", FOO)) + goto err; + + if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0), + "prog_attach_drop_foo_none", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + +err: + close(foo); + close(bar); + close(allow_prog); + close(drop_prog); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c new file mode 100644 index 000000000000..b093787e9448 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <test_progs.h> +#include <sys/mman.h> +#include <sys/utsname.h> +#include <linux/version.h> +#include "test_core_extern.skel.h" + +static uint32_t get_kernel_version(void) +{ + uint32_t major, minor, patch; + struct utsname info; + + uname(&info); + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + return KERNEL_VERSION(major, minor, patch); +} + +#define CFG "CONFIG_BPF_SYSCALL=n\n" + +static struct test_case { + const char *name; + const char *cfg; + bool fails; + struct test_core_extern__data data; +} test_cases[] = { + { .name = "default search path", .data = { .bpf_syscall = true } }, + { + .name = "custom values", + .cfg = "CONFIG_BPF_SYSCALL=n\n" + "CONFIG_TRISTATE=m\n" + "CONFIG_BOOL=y\n" + "CONFIG_CHAR=100\n" + "CONFIG_USHORT=30000\n" + "CONFIG_INT=123456\n" + "CONFIG_ULONG=0xDEADBEEFC0DE\n" + "CONFIG_STR=\"abracad\"\n" + "CONFIG_MISSING=0", + .data = { + .bpf_syscall = false, + .tristate_val = TRI_MODULE, + .bool_val = true, + .char_val = 100, + .ushort_val = 30000, + .int_val = 123456, + .ulong_val = 0xDEADBEEFC0DE, + .str_val = "abracad", + }, + }, + /* TRISTATE */ + { .name = "tristate (y)", .cfg = CFG"CONFIG_TRISTATE=y\n", + .data = { .tristate_val = TRI_YES } }, + { .name = "tristate (n)", .cfg = CFG"CONFIG_TRISTATE=n\n", + .data = { .tristate_val = TRI_NO } }, + { .name = "tristate (m)", .cfg = CFG"CONFIG_TRISTATE=m\n", + .data = { .tristate_val = TRI_MODULE } }, + { .name = "tristate (int)", .fails = 1, .cfg = CFG"CONFIG_TRISTATE=1" }, + { .name = "tristate (bad)", .fails = 1, .cfg = CFG"CONFIG_TRISTATE=M" }, + /* BOOL */ + { .name = "bool (y)", .cfg = CFG"CONFIG_BOOL=y\n", + .data = { .bool_val = true } }, + { .name = "bool (n)", .cfg = CFG"CONFIG_BOOL=n\n", + .data = { .bool_val = false } }, + { .name = "bool (tristate)", .fails = 1, .cfg = CFG"CONFIG_BOOL=m" }, + { .name = "bool (int)", .fails = 1, .cfg = CFG"CONFIG_BOOL=1" }, + /* CHAR */ + { .name = "char (tristate)", .cfg = CFG"CONFIG_CHAR=m\n", + .data = { .char_val = 'm' } }, + { .name = "char (bad)", .fails = 1, .cfg = CFG"CONFIG_CHAR=q\n" }, + { .name = "char (empty)", .fails = 1, .cfg = CFG"CONFIG_CHAR=\n" }, + { .name = "char (str)", .fails = 1, .cfg = CFG"CONFIG_CHAR=\"y\"\n" }, + /* STRING */ + { .name = "str (empty)", .cfg = CFG"CONFIG_STR=\"\"\n", + .data = { .str_val = "\0\0\0\0\0\0\0" } }, + { .name = "str (padded)", .cfg = CFG"CONFIG_STR=\"abra\"\n", + .data = { .str_val = "abra\0\0\0" } }, + { .name = "str (too long)", .cfg = CFG"CONFIG_STR=\"abracada\"\n", + .data = { .str_val = "abracad" } }, + { .name = "str (no value)", .fails = 1, .cfg = CFG"CONFIG_STR=\n" }, + { .name = "str (bad value)", .fails = 1, .cfg = CFG"CONFIG_STR=bla\n" }, + /* INTEGERS */ + { + .name = "integer forms", + .cfg = CFG + "CONFIG_CHAR=0xA\n" + "CONFIG_USHORT=0462\n" + "CONFIG_INT=-100\n" + "CONFIG_ULONG=+1000000000000", + .data = { + .char_val = 0xA, + .ushort_val = 0462, + .int_val = -100, + .ulong_val = 1000000000000, + }, + }, + { .name = "int (bad)", .fails = 1, .cfg = CFG"CONFIG_INT=abc" }, + { .name = "int (str)", .fails = 1, .cfg = CFG"CONFIG_INT=\"abc\"" }, + { .name = "int (empty)", .fails = 1, .cfg = CFG"CONFIG_INT=" }, + { .name = "int (mixed)", .fails = 1, .cfg = CFG"CONFIG_INT=123abc" }, + { .name = "int (max)", .cfg = CFG"CONFIG_INT=2147483647", + .data = { .int_val = 2147483647 } }, + { .name = "int (min)", .cfg = CFG"CONFIG_INT=-2147483648", + .data = { .int_val = -2147483648 } }, + { .name = "int (max+1)", .fails = 1, .cfg = CFG"CONFIG_INT=2147483648" }, + { .name = "int (min-1)", .fails = 1, .cfg = CFG"CONFIG_INT=-2147483649" }, + { .name = "ushort (max)", .cfg = CFG"CONFIG_USHORT=65535", + .data = { .ushort_val = 65535 } }, + { .name = "ushort (min)", .cfg = CFG"CONFIG_USHORT=0", + .data = { .ushort_val = 0 } }, + { .name = "ushort (max+1)", .fails = 1, .cfg = CFG"CONFIG_USHORT=65536" }, + { .name = "ushort (min-1)", .fails = 1, .cfg = CFG"CONFIG_USHORT=-1" }, + { .name = "u64 (max)", .cfg = CFG"CONFIG_ULONG=0xffffffffffffffff", + .data = { .ulong_val = 0xffffffffffffffff } }, + { .name = "u64 (min)", .cfg = CFG"CONFIG_ULONG=0", + .data = { .ulong_val = 0 } }, + { .name = "u64 (max+1)", .fails = 1, .cfg = CFG"CONFIG_ULONG=0x10000000000000000" }, +}; + +void test_core_extern(void) +{ + const uint32_t kern_ver = get_kernel_version(); + int err, duration = 0, i, j; + struct test_core_extern *skel = NULL; + uint64_t *got, *exp; + int n = sizeof(*skel->data) / sizeof(uint64_t); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + struct test_case *t = &test_cases[i]; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .kconfig = t->cfg, + ); + + if (!test__start_subtest(t->name)) + continue; + + skel = test_core_extern__open_opts(&opts); + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) + goto cleanup; + err = test_core_extern__load(skel); + if (t->fails) { + CHECK(!err, "skel_load", + "shouldn't succeed open/load of skeleton\n"); + goto cleanup; + } else if (CHECK(err, "skel_load", + "failed to open/load skeleton\n")) { + goto cleanup; + } + err = test_core_extern__attach(skel); + if (CHECK(err, "attach_raw_tp", "failed attach: %d\n", err)) + goto cleanup; + + usleep(1); + + t->data.kern_ver = kern_ver; + t->data.missing_val = 0xDEADC0DE; + got = (uint64_t *)skel->data; + exp = (uint64_t *)&t->data; + for (j = 0; j < n; j++) { + CHECK(got[j] != exp[j], "check_res", + "result #%d: expected %lx, but got %lx\n", + j, exp[j], got[j]); + } +cleanup: + test_core_extern__destroy(skel); + skel = NULL; + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 05fe85281ff7..31e177adbdf1 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -74,6 +74,7 @@ .b123 = 2, \ .c1c = 3, \ .d00d = 4, \ + .f10c = 0, \ }, \ .output_len = sizeof(struct core_reloc_arrays_output) \ } @@ -308,12 +309,15 @@ static struct core_reloc_test_case test_cases[] = { ARRAYS_CASE(arrays), ARRAYS_CASE(arrays___diff_arr_dim), ARRAYS_CASE(arrays___diff_arr_val_sz), + ARRAYS_CASE(arrays___equiv_zero_sz_arr), + ARRAYS_CASE(arrays___fixed_arr), ARRAYS_ERR_CASE(arrays___err_too_small), ARRAYS_ERR_CASE(arrays___err_too_shallow), ARRAYS_ERR_CASE(arrays___err_non_array), ARRAYS_ERR_CASE(arrays___err_wrong_val_type1), ARRAYS_ERR_CASE(arrays___err_wrong_val_type2), + ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr), /* enum/ptr/int handling scenarios */ PRIMITIVES_CASE(primitives), diff --git a/tools/testing/selftests/bpf/prog_tests/cpu_mask.c b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c new file mode 100644 index 000000000000..f7c7e25232be --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <bpf/btf.h> +#include "bpf/libbpf_internal.h" + +static int duration = 0; + +static void validate_mask(int case_nr, const char *exp, bool *mask, int n) +{ + int i; + + for (i = 0; exp[i]; i++) { + if (exp[i] == '1') { + if (CHECK(i + 1 > n, "mask_short", + "case #%d: mask too short, got n=%d, need at least %d\n", + case_nr, n, i + 1)) + return; + CHECK(!mask[i], "cpu_not_set", + "case #%d: mask differs, expected cpu#%d SET\n", + case_nr, i); + } else { + CHECK(i < n && mask[i], "cpu_set", + "case #%d: mask differs, expected cpu#%d UNSET\n", + case_nr, i); + } + } + CHECK(i < n, "mask_long", + "case #%d: mask too long, got n=%d, expected at most %d\n", + case_nr, n, i); +} + +static struct { + const char *cpu_mask; + const char *expect; + bool fails; +} test_cases[] = { + { "0\n", "1", false }, + { "0,2\n", "101", false }, + { "0-2\n", "111", false }, + { "0-2,3-4\n", "11111", false }, + { "0", "1", false }, + { "0-2", "111", false }, + { "0,2", "101", false }, + { "0,1-3", "1111", false }, + { "0,1,2,3", "1111", false }, + { "0,2-3,5", "101101", false }, + { "3-3", "0001", false }, + { "2-4,6,9-10", "00111010011", false }, + /* failure cases */ + { "", "", true }, + { "0-", "", true }, + { "0 ", "", true }, + { "0_1", "", true }, + { "1-0", "", true }, + { "-1", "", true }, +}; + +void test_cpu_mask() +{ + int i, err, n; + bool *mask; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + mask = NULL; + err = parse_cpu_mask_str(test_cases[i].cpu_mask, &mask, &n); + if (test_cases[i].fails) { + CHECK(!err, "should_fail", + "case #%d: parsing should fail!\n", i + 1); + } else { + if (CHECK(err, "parse_err", + "case #%d: cpu mask parsing failed: %d\n", + i + 1, err)) + continue; + validate_mask(i + 1, test_cases[i].expect, mask, n); + } + free(mask); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 40bcff2cc274..235ac4f67f5b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -1,90 +1,55 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "test_pkt_access.skel.h" +#include "fentry_test.skel.h" +#include "fexit_test.skel.h" void test_fentry_fexit(void) { - struct bpf_prog_load_attr attr_fentry = { - .file = "./fentry_test.o", - }; - struct bpf_prog_load_attr attr_fexit = { - .file = "./fexit_test.o", - }; - - struct bpf_object *obj_fentry = NULL, *obj_fexit = NULL, *pkt_obj; - struct bpf_map *data_map_fentry, *data_map_fexit; - char fentry_name[] = "fentry/bpf_fentry_testX"; - char fexit_name[] = "fexit/bpf_fentry_testX"; - int err, pkt_fd, kfree_skb_fd, i; - struct bpf_link *link[12] = {}; - struct bpf_program *prog[12]; - __u32 duration, retval; - const int zero = 0; - u64 result[12]; - - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &pkt_obj, &pkt_fd); - if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) + struct test_pkt_access *pkt_skel = NULL; + struct fentry_test *fentry_skel = NULL; + struct fexit_test *fexit_skel = NULL; + __u64 *fentry_res, *fexit_res; + __u32 duration = 0, retval; + int err, pkt_fd, i; + + pkt_skel = test_pkt_access__open_and_load(); + if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n")) return; - err = bpf_prog_load_xattr(&attr_fentry, &obj_fentry, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) + fentry_skel = fentry_test__open_and_load(); + if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) goto close_prog; - err = bpf_prog_load_xattr(&attr_fexit, &obj_fexit, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) + fexit_skel = fexit_test__open_and_load(); + if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) goto close_prog; - for (i = 0; i < 6; i++) { - fentry_name[sizeof(fentry_name) - 2] = '1' + i; - prog[i] = bpf_object__find_program_by_title(obj_fentry, fentry_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fentry_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map_fentry = bpf_object__find_map_by_name(obj_fentry, "fentry_t.bss"); - if (CHECK(!data_map_fentry, "find_data_map", "data map not found\n")) + err = fentry_test__attach(fentry_skel); + if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) goto close_prog; - - for (i = 6; i < 12; i++) { - fexit_name[sizeof(fexit_name) - 2] = '1' + i - 6; - prog[i] = bpf_object__find_program_by_title(obj_fexit, fexit_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fexit_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map_fexit = bpf_object__find_map_by_name(obj_fexit, "fexit_te.bss"); - if (CHECK(!data_map_fexit, "find_data_map", "data map not found\n")) + err = fexit_test__attach(fexit_skel); + if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) goto close_prog; + pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access); err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); - err = bpf_map_lookup_elem(bpf_map__fd(data_map_fentry), &zero, &result); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - err = bpf_map_lookup_elem(bpf_map__fd(data_map_fexit), &zero, result + 6); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - for (i = 0; i < 12; i++) - if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n", - i % 6 + 1, result[i])) - goto close_prog; + fentry_res = (__u64 *)fentry_skel->bss; + fexit_res = (__u64 *)fexit_skel->bss; + printf("%lld\n", fentry_skel->bss->test1_result); + for (i = 0; i < 6; i++) { + CHECK(fentry_res[i] != 1, "result", + "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); + CHECK(fexit_res[i] != 1, "result", + "fexit_test%d failed err %lld\n", i + 1, fexit_res[i]); + } close_prog: - for (i = 0; i < 12; i++) - if (!IS_ERR_OR_NULL(link[i])) - bpf_link__destroy(link[i]); - bpf_object__close(obj_fentry); - bpf_object__close(obj_fexit); - bpf_object__close(pkt_obj); + test_pkt_access__destroy(pkt_skel); + fentry_test__destroy(fentry_skel); + fexit_test__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 9fb103193878..5cc06021f27d 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -1,64 +1,43 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "test_pkt_access.skel.h" +#include "fentry_test.skel.h" void test_fentry_test(void) { - struct bpf_prog_load_attr attr = { - .file = "./fentry_test.o", - }; - - char prog_name[] = "fentry/bpf_fentry_testX"; - struct bpf_object *obj = NULL, *pkt_obj; - int err, pkt_fd, kfree_skb_fd, i; - struct bpf_link *link[6] = {}; - struct bpf_program *prog[6]; - __u32 duration, retval; - struct bpf_map *data_map; - const int zero = 0; - u64 result[6]; - - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &pkt_obj, &pkt_fd); - if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) + struct test_pkt_access *pkt_skel = NULL; + struct fentry_test *fentry_skel = NULL; + int err, pkt_fd, i; + __u32 duration = 0, retval; + __u64 *result; + + pkt_skel = test_pkt_access__open_and_load(); + if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n")) return; - err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) - goto close_prog; + fentry_skel = fentry_test__open_and_load(); + if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) + goto cleanup; - for (i = 0; i < 6; i++) { - prog_name[sizeof(prog_name) - 2] = '1' + i; - prog[i] = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map = bpf_object__find_map_by_name(obj, "fentry_t.bss"); - if (CHECK(!data_map, "find_data_map", "data map not found\n")) - goto close_prog; + err = fentry_test__attach(fentry_skel); + if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) + goto cleanup; + pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access); err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); - err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - for (i = 0; i < 6; i++) - if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n", - i + 1, result[i])) - goto close_prog; + result = (__u64 *)fentry_skel->bss; + for (i = 0; i < 6; i++) { + if (CHECK(result[i] != 1, "result", + "fentry_test%d failed err %lld\n", i + 1, result[i])) + goto cleanup; + } -close_prog: - for (i = 0; i < 6; i++) - if (!IS_ERR_OR_NULL(link[i])) - bpf_link__destroy(link[i]); - bpf_object__close(obj); - bpf_object__close(pkt_obj); +cleanup: + fentry_test__destroy(fentry_skel); + test_pkt_access__destroy(pkt_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index b426bf2f97e4..cde463af7071 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -11,7 +11,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, int err, pkt_fd, i; struct bpf_link **link = NULL; struct bpf_program **prog = NULL; - __u32 duration, retval; + __u32 duration = 0, retval; struct bpf_map *data_map; const int zero = 0; u64 *result = NULL; @@ -26,7 +26,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, link = calloc(sizeof(struct bpf_link *), prog_cnt); prog = calloc(sizeof(struct bpf_program *), prog_cnt); - result = malloc(prog_cnt * sizeof(u64)); + result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64)); if (CHECK(!link || !prog || !result, "alloc_memory", "failed to alloc memory")) goto close_prog; @@ -98,6 +98,24 @@ static void test_target_yes_callees(void) "fexit/test_pkt_access", "fexit/test_pkt_access_subprog1", "fexit/test_pkt_access_subprog2", + "fexit/test_pkt_access_subprog3", + }; + test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o", + "./test_pkt_access.o", + ARRAY_SIZE(prog_name), + prog_name); +} + +static void test_func_replace(void) +{ + const char *prog_name[] = { + "fexit/test_pkt_access", + "fexit/test_pkt_access_subprog1", + "fexit/test_pkt_access_subprog2", + "fexit/test_pkt_access_subprog3", + "freplace/get_skb_len", + "freplace/get_skb_ifindex", + "freplace/get_constant", }; test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o", "./test_pkt_access.o", @@ -109,4 +127,5 @@ void test_fexit_bpf2bpf(void) { test_target_no_callees(); test_target_yes_callees(); + test_func_replace(); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index f99013222c74..d2c3655dd7a3 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -13,7 +13,7 @@ void test_fexit_test(void) int err, pkt_fd, kfree_skb_fd, i; struct bpf_link *link[6] = {}; struct bpf_program *prog[6]; - __u32 duration, retval; + __u32 duration = 0, retval; struct bpf_map *data_map; const int zero = 0; u64 result[6]; diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 051a6d48762c..16a814eb4d64 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -1,16 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> #include <sys/mman.h> +#include "test_mmap.skel.h" struct map_data { __u64 val[512 * 4]; }; -struct bss_data { - __u64 in_val; - __u64 out_val; -}; - static size_t roundup_page(size_t sz) { long page_size = sysconf(_SC_PAGE_SIZE); @@ -19,41 +15,25 @@ static size_t roundup_page(size_t sz) void test_mmap(void) { - const char *file = "test_mmap.o"; - const char *probe_name = "raw_tracepoint/sys_enter"; - const char *tp_name = "sys_enter"; - const size_t bss_sz = roundup_page(sizeof(struct bss_data)); + const size_t bss_sz = roundup_page(sizeof(struct test_mmap__bss)); 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; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link = NULL; struct bpf_map *data_map, *bss_map; void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; - volatile struct bss_data *bss_data; - volatile struct map_data *map_data; + struct test_mmap__bss *bss_data; + struct map_data *map_data; + struct test_mmap *skel; __u64 val = 0; - obj = bpf_object__open_file("test_mmap.o", NULL); - if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n", - file, PTR_ERR(obj))) + + skel = test_mmap__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) return; - prog = bpf_object__find_program_by_title(obj, probe_name); - if (CHECK(!prog, "find_probe", "prog '%s' not found\n", probe_name)) - goto cleanup; - err = bpf_object__load(obj); - if (CHECK(err, "obj_load", "failed to load prog '%s': %d\n", - probe_name, err)) - goto cleanup; - bss_map = bpf_object__find_map_by_name(obj, "test_mma.bss"); - if (CHECK(!bss_map, "find_bss_map", ".bss map not found\n")) - goto cleanup; - data_map = bpf_object__find_map_by_name(obj, "data_map"); - if (CHECK(!data_map, "find_data_map", "data_map map not found\n")) - goto cleanup; + bss_map = skel->maps.bss; + data_map = skel->maps.data_map; data_map_fd = bpf_map__fd(data_map); bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED, @@ -77,13 +57,15 @@ void test_mmap(void) CHECK_FAIL(bss_data->in_val); CHECK_FAIL(bss_data->out_val); + CHECK_FAIL(skel->bss->in_val); + CHECK_FAIL(skel->bss->out_val); CHECK_FAIL(map_data->val[0]); CHECK_FAIL(map_data->val[1]); CHECK_FAIL(map_data->val[2]); CHECK_FAIL(map_data->val[far]); - link = bpf_program__attach_raw_tracepoint(prog, tp_name); - if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) + err = test_mmap__attach(skel); + if (CHECK(err, "attach_raw_tp", "err %d\n", err)) goto cleanup; bss_data->in_val = 123; @@ -94,6 +76,8 @@ void test_mmap(void) CHECK_FAIL(bss_data->in_val != 123); CHECK_FAIL(bss_data->out_val != 123); + CHECK_FAIL(skel->bss->in_val != 123); + CHECK_FAIL(skel->bss->out_val != 123); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 123); @@ -160,6 +144,8 @@ void test_mmap(void) usleep(1); CHECK_FAIL(bss_data->in_val != 321); CHECK_FAIL(bss_data->out_val != 321); + CHECK_FAIL(skel->bss->in_val != 321); + CHECK_FAIL(skel->bss->out_val != 321); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 321); @@ -203,6 +189,8 @@ void test_mmap(void) map_data = tmp2; CHECK_FAIL(bss_data->in_val != 321); CHECK_FAIL(bss_data->out_val != 321); + CHECK_FAIL(skel->bss->in_val != 321); + CHECK_FAIL(skel->bss->out_val != 321); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 321); @@ -214,7 +202,5 @@ cleanup: CHECK_FAIL(munmap(bss_mmaped, bss_sz)); if (map_mmaped) CHECK_FAIL(munmap(map_mmaped, map_sz)); - if (!IS_ERR_OR_NULL(link)) - bpf_link__destroy(link); - bpf_object__close(obj); + test_mmap__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index 3003fddc0613..1450ea2dd4cc 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -4,6 +4,7 @@ #include <sched.h> #include <sys/socket.h> #include <test_progs.h> +#include "bpf/libbpf_internal.h" static void on_sample(void *ctx, int cpu, void *data, __u32 size) { @@ -19,7 +20,7 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) void test_perf_buffer(void) { - int err, prog_fd, nr_cpus, i, duration = 0; + int err, prog_fd, on_len, nr_on_cpus = 0, nr_cpus, i, duration = 0; const char *prog_name = "kprobe/sys_nanosleep"; const char *file = "./test_perf_buffer.o"; struct perf_buffer_opts pb_opts = {}; @@ -29,15 +30,27 @@ void test_perf_buffer(void) struct bpf_object *obj; struct perf_buffer *pb; struct bpf_link *link; + bool *online; nr_cpus = libbpf_num_possible_cpus(); if (CHECK(nr_cpus < 0, "nr_cpus", "err %d\n", nr_cpus)) return; + err = parse_cpu_mask_file("/sys/devices/system/cpu/online", + &online, &on_len); + if (CHECK(err, "nr_on_cpus", "err %d\n", err)) + return; + + for (i = 0; i < on_len; i++) + if (online[i]) + nr_on_cpus++; + /* load program */ err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd); - if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) - return; + if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) { + obj = NULL; + goto out_close; + } prog = bpf_object__find_program_by_title(obj, prog_name); if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) @@ -64,6 +77,11 @@ void test_perf_buffer(void) /* trigger kprobe on every CPU */ CPU_ZERO(&cpu_seen); for (i = 0; i < nr_cpus; i++) { + if (i >= on_len || !online[i]) { + printf("skipping offline CPU #%d\n", i); + continue; + } + CPU_ZERO(&cpu_set); CPU_SET(i, &cpu_set); @@ -81,8 +99,8 @@ void test_perf_buffer(void) if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) goto out_free_pb; - if (CHECK(CPU_COUNT(&cpu_seen) != nr_cpus, "seen_cpu_cnt", - "expect %d, seen %d\n", nr_cpus, CPU_COUNT(&cpu_seen))) + if (CHECK(CPU_COUNT(&cpu_seen) != nr_on_cpus, "seen_cpu_cnt", + "expect %d, seen %d\n", nr_on_cpus, CPU_COUNT(&cpu_seen))) goto out_free_pb; out_free_pb: @@ -91,4 +109,5 @@ out_detach: bpf_link__destroy(link); out_close: bpf_object__close(obj); + free(online); } diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c index 8a3187dec048..7aecfd9e87d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/probe_user.c +++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c @@ -3,8 +3,7 @@ void test_probe_user(void) { -#define kprobe_name "__sys_connect" - const char *prog_name = "kprobe/" kprobe_name; + const char *prog_name = "kprobe/__sys_connect"; const char *obj_file = "./test_probe_user.o"; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, ); int err, results_map_fd, sock_fd, duration = 0; @@ -33,8 +32,7 @@ void test_probe_user(void) "err %d\n", results_map_fd)) goto cleanup; - kprobe_link = bpf_program__attach_kprobe(kprobe_prog, false, - kprobe_name); + kprobe_link = bpf_program__attach(kprobe_prog); if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", "err %ld\n", PTR_ERR(kprobe_link))) { kprobe_link = NULL; diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c index d90acc13d1ec..563e12120e77 100644 --- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c +++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c @@ -16,14 +16,11 @@ struct rdonly_map_subtest { void test_rdonly_maps(void) { - const char *prog_name_skip_loop = "raw_tracepoint/sys_enter:skip_loop"; - const char *prog_name_part_loop = "raw_tracepoint/sys_enter:part_loop"; - const char *prog_name_full_loop = "raw_tracepoint/sys_enter:full_loop"; const char *file = "test_rdonly_maps.o"; struct rdonly_map_subtest subtests[] = { - { "skip loop", prog_name_skip_loop, 0, 0 }, - { "part loop", prog_name_part_loop, 3, 2 + 3 + 4 }, - { "full loop", prog_name_full_loop, 4, 2 + 3 + 4 + 5 }, + { "skip loop", "skip_loop", 0, 0 }, + { "part loop", "part_loop", 3, 2 + 3 + 4 }, + { "full loop", "full_loop", 4, 2 + 3 + 4 + 5 }, }; int i, err, zero = 0, duration = 0; struct bpf_link *link = NULL; @@ -50,7 +47,7 @@ void test_rdonly_maps(void) if (!test__start_subtest(t->subtest_name)) continue; - prog = bpf_object__find_program_by_title(obj, t->prog_name); + prog = bpf_object__find_program_by_name(obj, t->prog_name); if (CHECK(!prog, "find_prog", "prog '%s' not found\n", t->prog_name)) goto cleanup; diff --git a/tools/testing/selftests/bpf/test_select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 7566c13eb51a..0800036ed654 100644 --- a/tools/testing/selftests/bpf/test_select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -20,8 +20,11 @@ #include <bpf/libbpf.h> #include "bpf_rlimit.h" #include "bpf_util.h" + +#include "test_progs.h" #include "test_select_reuseport_common.h" +#define MAX_TEST_NAME 80 #define MIN_TCPHDR_LEN 20 #define UDPHDR_LEN 8 @@ -30,13 +33,13 @@ #define REUSEPORT_ARRAY_SIZE 32 static int result_map, tmp_index_ovr_map, linum_map, data_check_map; -static enum result expected_results[NR_RESULTS]; +static __u32 expected_results[NR_RESULTS]; static int sk_fds[REUSEPORT_ARRAY_SIZE]; -static int reuseport_array, outer_map; +static int reuseport_array = -1, outer_map = -1; static int select_by_skb_data_prog; -static int saved_tcp_syncookie; +static int saved_tcp_syncookie = -1; static struct bpf_object *obj; -static int saved_tcp_fo; +static int saved_tcp_fo = -1; static __u32 index_zero; static int epfd; @@ -46,16 +49,21 @@ static union sa46 { sa_family_t family; } srv_sa; -#define CHECK(condition, tag, format...) ({ \ - int __ret = !!(condition); \ - if (__ret) { \ - printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \ - printf(format); \ - exit(-1); \ +#define RET_IF(condition, tag, format...) ({ \ + if (CHECK_FAIL(condition)) { \ + printf(tag " " format); \ + return; \ + } \ +}) + +#define RET_ERR(condition, tag, format...) ({ \ + if (CHECK_FAIL(condition)) { \ + printf(tag " " format); \ + return -1; \ } \ }) -static void create_maps(void) +static int create_maps(void) { struct bpf_create_map_attr attr = {}; @@ -67,8 +75,8 @@ static void create_maps(void) attr.max_entries = REUSEPORT_ARRAY_SIZE; reuseport_array = bpf_create_map_xattr(&attr); - CHECK(reuseport_array == -1, "creating reuseport_array", - "reuseport_array:%d errno:%d\n", reuseport_array, errno); + RET_ERR(reuseport_array == -1, "creating reuseport_array", + "reuseport_array:%d errno:%d\n", reuseport_array, errno); /* Creating outer_map */ attr.name = "outer_map"; @@ -78,63 +86,61 @@ static void create_maps(void) attr.max_entries = 1; attr.inner_map_fd = reuseport_array; outer_map = bpf_create_map_xattr(&attr); - CHECK(outer_map == -1, "creating outer_map", - "outer_map:%d errno:%d\n", outer_map, errno); + RET_ERR(outer_map == -1, "creating outer_map", + "outer_map:%d errno:%d\n", outer_map, errno); + + return 0; } -static void prepare_bpf_obj(void) +static int prepare_bpf_obj(void) { struct bpf_program *prog; struct bpf_map *map; int err; - struct bpf_object_open_attr attr = { - .file = "test_select_reuseport_kern.o", - .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, - }; - - obj = bpf_object__open_xattr(&attr); - CHECK(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o", - "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj)); - prog = bpf_program__next(NULL, obj); - CHECK(!prog, "get first bpf_program", "!prog\n"); - bpf_program__set_type(prog, attr.prog_type); + obj = bpf_object__open("test_select_reuseport_kern.o"); + RET_ERR(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o", + "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj)); map = bpf_object__find_map_by_name(obj, "outer_map"); - CHECK(!map, "find outer_map", "!map\n"); + RET_ERR(!map, "find outer_map", "!map\n"); err = bpf_map__reuse_fd(map, outer_map); - CHECK(err, "reuse outer_map", "err:%d\n", err); + RET_ERR(err, "reuse outer_map", "err:%d\n", err); err = bpf_object__load(obj); - CHECK(err, "load bpf_object", "err:%d\n", err); + RET_ERR(err, "load bpf_object", "err:%d\n", err); + prog = bpf_program__next(NULL, obj); + RET_ERR(!prog, "get first bpf_program", "!prog\n"); select_by_skb_data_prog = bpf_program__fd(prog); - CHECK(select_by_skb_data_prog == -1, "get prog fd", - "select_by_skb_data_prog:%d\n", select_by_skb_data_prog); + RET_ERR(select_by_skb_data_prog == -1, "get prog fd", + "select_by_skb_data_prog:%d\n", select_by_skb_data_prog); map = bpf_object__find_map_by_name(obj, "result_map"); - CHECK(!map, "find result_map", "!map\n"); + RET_ERR(!map, "find result_map", "!map\n"); result_map = bpf_map__fd(map); - CHECK(result_map == -1, "get result_map fd", - "result_map:%d\n", result_map); + RET_ERR(result_map == -1, "get result_map fd", + "result_map:%d\n", result_map); map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map"); - CHECK(!map, "find tmp_index_ovr_map", "!map\n"); + RET_ERR(!map, "find tmp_index_ovr_map\n", "!map"); tmp_index_ovr_map = bpf_map__fd(map); - CHECK(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd", - "tmp_index_ovr_map:%d\n", tmp_index_ovr_map); + RET_ERR(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd", + "tmp_index_ovr_map:%d\n", tmp_index_ovr_map); map = bpf_object__find_map_by_name(obj, "linum_map"); - CHECK(!map, "find linum_map", "!map\n"); + RET_ERR(!map, "find linum_map", "!map\n"); linum_map = bpf_map__fd(map); - CHECK(linum_map == -1, "get linum_map fd", - "linum_map:%d\n", linum_map); + RET_ERR(linum_map == -1, "get linum_map fd", + "linum_map:%d\n", linum_map); map = bpf_object__find_map_by_name(obj, "data_check_map"); - CHECK(!map, "find data_check_map", "!map\n"); + RET_ERR(!map, "find data_check_map", "!map\n"); data_check_map = bpf_map__fd(map); - CHECK(data_check_map == -1, "get data_check_map fd", - "data_check_map:%d\n", data_check_map); + RET_ERR(data_check_map == -1, "get data_check_map fd", + "data_check_map:%d\n", data_check_map); + + return 0; } static void sa46_init_loopback(union sa46 *sa, sa_family_t family) @@ -163,65 +169,73 @@ static int read_int_sysctl(const char *sysctl) int fd, ret; fd = open(sysctl, 0); - CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n", - sysctl, fd, errno); + RET_ERR(fd == -1, "open(sysctl)", + "sysctl:%s fd:%d errno:%d\n", sysctl, fd, errno); ret = read(fd, buf, sizeof(buf)); - CHECK(ret <= 0, "read(sysctl)", "sysctl:%s ret:%d errno:%d\n", - sysctl, ret, errno); - close(fd); + RET_ERR(ret <= 0, "read(sysctl)", + "sysctl:%s ret:%d errno:%d\n", sysctl, ret, errno); + close(fd); return atoi(buf); } -static void write_int_sysctl(const char *sysctl, int v) +static int write_int_sysctl(const char *sysctl, int v) { int fd, ret, size; char buf[16]; fd = open(sysctl, O_RDWR); - CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n", - sysctl, fd, errno); + RET_ERR(fd == -1, "open(sysctl)", + "sysctl:%s fd:%d errno:%d\n", sysctl, fd, errno); size = snprintf(buf, sizeof(buf), "%d", v); ret = write(fd, buf, size); - CHECK(ret != size, "write(sysctl)", - "sysctl:%s ret:%d size:%d errno:%d\n", sysctl, ret, size, errno); + RET_ERR(ret != size, "write(sysctl)", + "sysctl:%s ret:%d size:%d errno:%d\n", + sysctl, ret, size, errno); + close(fd); + return 0; } static void restore_sysctls(void) { - write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo); - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie); + if (saved_tcp_fo != -1) + write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo); + if (saved_tcp_syncookie != -1) + write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie); } -static void enable_fastopen(void) +static int enable_fastopen(void) { int fo; fo = read_int_sysctl(TCP_FO_SYSCTL); - write_int_sysctl(TCP_FO_SYSCTL, fo | 7); + if (fo < 0) + return -1; + + return write_int_sysctl(TCP_FO_SYSCTL, fo | 7); } -static void enable_syncookie(void) +static int enable_syncookie(void) { - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2); + return write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2); } -static void disable_syncookie(void) +static int disable_syncookie(void) { - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0); + return write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0); } -static __u32 get_linum(void) +static long get_linum(void) { __u32 linum; int err; err = bpf_map_lookup_elem(linum_map, &index_zero, &linum); - CHECK(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n", - err, errno); + RET_ERR(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n", + err, errno); return linum; } @@ -237,12 +251,12 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, addrlen = sizeof(cli_sa); err = getsockname(cli_fd, (struct sockaddr *)&cli_sa, &addrlen); - CHECK(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n", - err, errno); + RET_IF(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n", + err, errno); err = bpf_map_lookup_elem(data_check_map, &index_zero, &result); - CHECK(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n", - err, errno); + RET_IF(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n", + err, errno); if (type == SOCK_STREAM) { expected.len = MIN_TCPHDR_LEN; @@ -284,22 +298,42 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, printf("expected: (0x%x, %u, %u)\n", expected.eth_protocol, expected.ip_protocol, expected.bind_inany); - CHECK(1, "data_check result != expected", - "bpf_prog_linum:%u\n", get_linum()); + RET_IF(1, "data_check result != expected", + "bpf_prog_linum:%ld\n", get_linum()); } - CHECK(!result.hash, "data_check result.hash empty", - "result.hash:%u", result.hash); + RET_IF(!result.hash, "data_check result.hash empty", + "result.hash:%u", result.hash); expected.len += cmd ? sizeof(*cmd) : 0; if (type == SOCK_STREAM) - CHECK(expected.len > result.len, "expected.len > result.len", - "expected.len:%u result.len:%u bpf_prog_linum:%u\n", - expected.len, result.len, get_linum()); + RET_IF(expected.len > result.len, "expected.len > result.len", + "expected.len:%u result.len:%u bpf_prog_linum:%ld\n", + expected.len, result.len, get_linum()); else - CHECK(expected.len != result.len, "expected.len != result.len", - "expected.len:%u result.len:%u bpf_prog_linum:%u\n", - expected.len, result.len, get_linum()); + RET_IF(expected.len != result.len, "expected.len != result.len", + "expected.len:%u result.len:%u bpf_prog_linum:%ld\n", + expected.len, result.len, get_linum()); +} + +static const char *result_to_str(enum result res) +{ + switch (res) { + case DROP_ERR_INNER_MAP: + return "DROP_ERR_INNER_MAP"; + case DROP_ERR_SKB_DATA: + return "DROP_ERR_SKB_DATA"; + case DROP_ERR_SK_SELECT_REUSEPORT: + return "DROP_ERR_SK_SELECT_REUSEPORT"; + case DROP_MISC: + return "DROP_MISC"; + case PASS: + return "PASS"; + case PASS_ERR_SK_SELECT_REUSEPORT: + return "PASS_ERR_SK_SELECT_REUSEPORT"; + default: + return "UNKNOWN"; + } } static void check_results(void) @@ -310,8 +344,8 @@ static void check_results(void) for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &results[i]); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); } for (i = 0; i < NR_RESULTS; i++) { @@ -337,10 +371,10 @@ static void check_results(void) printf(", %u", expected_results[i]); printf("]\n"); - CHECK(expected_results[broken] != results[broken], - "unexpected result", - "expected_results[%u] != results[%u] bpf_prog_linum:%u\n", - broken, broken, get_linum()); + printf("mismatch on %s (bpf_prog_linum:%ld)\n", result_to_str(broken), + get_linum()); + + CHECK_FAIL(true); } static int send_data(int type, sa_family_t family, void *data, size_t len, @@ -350,17 +384,17 @@ static int send_data(int type, sa_family_t family, void *data, size_t len, int fd, err; fd = socket(family, type, 0); - CHECK(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno); + RET_ERR(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno); sa46_init_loopback(&cli_sa, family); err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa)); - CHECK(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno); + RET_ERR(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno); err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa, sizeof(srv_sa)); - CHECK(err != len && expected >= PASS, - "sendto()", "family:%u err:%d errno:%d expected:%d\n", - family, err, errno, expected); + RET_ERR(err != len && expected >= PASS, + "sendto()", "family:%u err:%d errno:%d expected:%d\n", + family, err, errno, expected); return fd; } @@ -375,47 +409,49 @@ static void do_test(int type, sa_family_t family, struct cmd *cmd, cli_fd = send_data(type, family, cmd, cmd ? sizeof(*cmd) : 0, expected); + if (cli_fd < 0) + return; nev = epoll_wait(epfd, &ev, 1, expected >= PASS ? 5 : 0); - CHECK((nev <= 0 && expected >= PASS) || - (nev > 0 && expected < PASS), - "nev <> expected", - "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n", - nev, expected, type, family, - cmd ? cmd->reuseport_index : -1, - cmd ? cmd->pass_on_failure : -1); + RET_IF((nev <= 0 && expected >= PASS) || + (nev > 0 && expected < PASS), + "nev <> expected", + "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n", + nev, expected, type, family, + cmd ? cmd->reuseport_index : -1, + cmd ? cmd->pass_on_failure : -1); check_results(); check_data(type, family, cmd, cli_fd); if (expected < PASS) return; - CHECK(expected != PASS_ERR_SK_SELECT_REUSEPORT && - cmd->reuseport_index != ev.data.u32, - "check cmd->reuseport_index", - "cmd:(%u, %u) ev.data.u32:%u\n", - cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32); + RET_IF(expected != PASS_ERR_SK_SELECT_REUSEPORT && + cmd->reuseport_index != ev.data.u32, + "check cmd->reuseport_index", + "cmd:(%u, %u) ev.data.u32:%u\n", + cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32); srv_fd = sk_fds[ev.data.u32]; if (type == SOCK_STREAM) { int new_fd = accept(srv_fd, NULL, 0); - CHECK(new_fd == -1, "accept(srv_fd)", - "ev.data.u32:%u new_fd:%d errno:%d\n", - ev.data.u32, new_fd, errno); + RET_IF(new_fd == -1, "accept(srv_fd)", + "ev.data.u32:%u new_fd:%d errno:%d\n", + ev.data.u32, new_fd, errno); nread = recv(new_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT); - CHECK(nread != sizeof(rcv_cmd), - "recv(new_fd)", - "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", - ev.data.u32, nread, sizeof(rcv_cmd), errno); + RET_IF(nread != sizeof(rcv_cmd), + "recv(new_fd)", + "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", + ev.data.u32, nread, sizeof(rcv_cmd), errno); close(new_fd); } else { nread = recv(srv_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT); - CHECK(nread != sizeof(rcv_cmd), - "recv(sk_fds)", - "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", - ev.data.u32, nread, sizeof(rcv_cmd), errno); + RET_IF(nread != sizeof(rcv_cmd), + "recv(sk_fds)", + "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", + ev.data.u32, nread, sizeof(rcv_cmd), errno); } close(cli_fd); @@ -428,18 +464,14 @@ static void test_err_inner_map(int type, sa_family_t family) .pass_on_failure = 0, }; - printf("%s: ", __func__); expected_results[DROP_ERR_INNER_MAP]++; do_test(type, family, &cmd, DROP_ERR_INNER_MAP); - printf("OK\n"); } static void test_err_skb_data(int type, sa_family_t family) { - printf("%s: ", __func__); expected_results[DROP_ERR_SKB_DATA]++; do_test(type, family, NULL, DROP_ERR_SKB_DATA); - printf("OK\n"); } static void test_err_sk_select_port(int type, sa_family_t family) @@ -449,10 +481,8 @@ static void test_err_sk_select_port(int type, sa_family_t family) .pass_on_failure = 0, }; - printf("%s: ", __func__); expected_results[DROP_ERR_SK_SELECT_REUSEPORT]++; do_test(type, family, &cmd, DROP_ERR_SK_SELECT_REUSEPORT); - printf("OK\n"); } static void test_pass(int type, sa_family_t family) @@ -460,14 +490,12 @@ static void test_pass(int type, sa_family_t family) struct cmd cmd; int i; - printf("%s: ", __func__); cmd.pass_on_failure = 0; for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) { expected_results[PASS]++; cmd.reuseport_index = i; do_test(type, family, &cmd, PASS); } - printf("OK\n"); } static void test_syncookie(int type, sa_family_t family) @@ -478,10 +506,11 @@ static void test_syncookie(int type, sa_family_t family) .pass_on_failure = 0, }; - if (type != SOCK_STREAM) + if (type != SOCK_STREAM) { + test__skip(); return; + } - printf("%s: ", __func__); /* * +1 for TCP-SYN and * +1 for the TCP-ACK (ack the syncookie) @@ -497,17 +526,16 @@ static void test_syncookie(int type, sa_family_t family) */ err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &tmp_index, BPF_ANY); - CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)", + "err:%d errno:%d\n", err, errno); do_test(type, family, &cmd, PASS); err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero, &tmp_index); - CHECK(err == -1 || tmp_index != -1, - "lookup_elem(tmp_index_ovr_map)", - "err:%d errno:%d tmp_index:%d\n", - err, errno, tmp_index); + RET_IF(err == -1 || tmp_index != -1, + "lookup_elem(tmp_index_ovr_map)", + "err:%d errno:%d tmp_index:%d\n", + err, errno, tmp_index); disable_syncookie(); - printf("OK\n"); } static void test_pass_on_err(int type, sa_family_t family) @@ -517,10 +545,8 @@ static void test_pass_on_err(int type, sa_family_t family) .pass_on_failure = 1, }; - printf("%s: ", __func__); expected_results[PASS_ERR_SK_SELECT_REUSEPORT] += 1; do_test(type, family, &cmd, PASS_ERR_SK_SELECT_REUSEPORT); - printf("OK\n"); } static void test_detach_bpf(int type, sa_family_t family) @@ -532,46 +558,47 @@ static void test_detach_bpf(int type, sa_family_t family) struct cmd cmd = {}; int optvalue = 0; - printf("%s: ", __func__); err = setsockopt(sk_fds[0], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, &optvalue, sizeof(optvalue)); - CHECK(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); err = setsockopt(sk_fds[1], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, &optvalue, sizeof(optvalue)); - CHECK(err == 0 || errno != ENOENT, "setsockopt(SO_DETACH_REUSEPORT_BPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == 0 || errno != ENOENT, + "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &tmp); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); nr_run_before += tmp; } cli_fd = send_data(type, family, &cmd, sizeof(cmd), PASS); + if (cli_fd < 0) + return; nev = epoll_wait(epfd, &ev, 1, 5); - CHECK(nev <= 0, "nev <= 0", - "nev:%d expected:1 type:%d family:%d data:(0, 0)\n", - nev, type, family); + RET_IF(nev <= 0, "nev <= 0", + "nev:%d expected:1 type:%d family:%d data:(0, 0)\n", + nev, type, family); for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &tmp); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); nr_run_after += tmp; } - CHECK(nr_run_before != nr_run_after, - "nr_run_before != nr_run_after", - "nr_run_before:%u nr_run_after:%u\n", - nr_run_before, nr_run_after); + RET_IF(nr_run_before != nr_run_after, + "nr_run_before != nr_run_after", + "nr_run_before:%u nr_run_after:%u\n", + nr_run_before, nr_run_after); - printf("OK\n"); close(cli_fd); #else - printf("%s: SKIP\n", __func__); + test__skip(); #endif } @@ -594,149 +621,222 @@ static void prepare_sk_fds(int type, sa_family_t family, bool inany) */ for (i = first; i >= 0; i--) { sk_fds[i] = socket(family, type, 0); - CHECK(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n", - i, sk_fds[i], errno); + RET_IF(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n", + i, sk_fds[i], errno); err = setsockopt(sk_fds[i], SOL_SOCKET, SO_REUSEPORT, &optval, sizeof(optval)); - CHECK(err == -1, "setsockopt(SO_REUSEPORT)", - "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "setsockopt(SO_REUSEPORT)", + "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); if (i == first) { err = setsockopt(sk_fds[i], SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &select_by_skb_data_prog, sizeof(select_by_skb_data_prog)); - CHECK(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)", + "err:%d errno:%d\n", err, errno); } err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen); - CHECK(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); if (type == SOCK_STREAM) { err = listen(sk_fds[i], 10); - CHECK(err == -1, "listen()", - "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "listen()", + "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); } err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i], BPF_NOEXIST); - CHECK(err == -1, "update_elem(reuseport_array)", - "sk_fds[%d] err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "update_elem(reuseport_array)", + "sk_fds[%d] err:%d errno:%d\n", i, err, errno); if (i == first) { socklen_t addrlen = sizeof(srv_sa); err = getsockname(sk_fds[i], (struct sockaddr *)&srv_sa, &addrlen); - CHECK(err == -1, "getsockname()", - "sk_fds[%d] err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "getsockname()", + "sk_fds[%d] err:%d errno:%d\n", i, err, errno); } } epfd = epoll_create(1); - CHECK(epfd == -1, "epoll_create(1)", - "epfd:%d errno:%d\n", epfd, errno); + RET_IF(epfd == -1, "epoll_create(1)", + "epfd:%d errno:%d\n", epfd, errno); ev.events = EPOLLIN; for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) { ev.data.u32 = i; err = epoll_ctl(epfd, EPOLL_CTL_ADD, sk_fds[i], &ev); - CHECK(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i); + RET_IF(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i); } } -static void setup_per_test(int type, unsigned short family, bool inany) +static void setup_per_test(int type, sa_family_t family, bool inany, + bool no_inner_map) { int ovr = -1, err; prepare_sk_fds(type, family, inany); err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr, BPF_ANY); - CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)", + "err:%d errno:%d\n", err, errno); + + /* Install reuseport_array to outer_map? */ + if (no_inner_map) + return; + + err = bpf_map_update_elem(outer_map, &index_zero, &reuseport_array, + BPF_ANY); + RET_IF(err == -1, "update_elem(outer_map, 0, reuseport_array)", + "err:%d errno:%d\n", err, errno); } -static void cleanup_per_test(void) +static void cleanup_per_test(bool no_inner_map) { - int i, err; + int i, err, zero = 0; + + memset(expected_results, 0, sizeof(expected_results)); + + for (i = 0; i < NR_RESULTS; i++) { + err = bpf_map_update_elem(result_map, &i, &zero, BPF_ANY); + RET_IF(err, "reset elem in result_map", + "i:%u err:%d errno:%d\n", i, err, errno); + } + + err = bpf_map_update_elem(linum_map, &zero, &zero, BPF_ANY); + RET_IF(err, "reset line number in linum_map", "err:%d errno:%d\n", + err, errno); for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) close(sk_fds[i]); close(epfd); + /* Delete reuseport_array from outer_map? */ + if (no_inner_map) + return; + err = bpf_map_delete_elem(outer_map, &index_zero); - CHECK(err == -1, "delete_elem(outer_map)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "delete_elem(outer_map)", + "err:%d errno:%d\n", err, errno); } static void cleanup(void) { - close(outer_map); - close(reuseport_array); - bpf_object__close(obj); + if (outer_map != -1) + close(outer_map); + if (reuseport_array != -1) + close(reuseport_array); + if (obj) + bpf_object__close(obj); } -static void test_all(void) +static const char *family_str(sa_family_t family) { - /* Extra SOCK_STREAM to test bind_inany==true */ - const int types[] = { SOCK_STREAM, SOCK_DGRAM, SOCK_STREAM }; - const char * const type_strings[] = { "TCP", "UDP", "TCP" }; - const char * const family_strings[] = { "IPv6", "IPv4" }; - const unsigned short families[] = { AF_INET6, AF_INET }; - const bool bind_inany[] = { false, false, true }; - int t, f, err; - - for (f = 0; f < ARRAY_SIZE(families); f++) { - unsigned short family = families[f]; - - for (t = 0; t < ARRAY_SIZE(types); t++) { - bool inany = bind_inany[t]; - int type = types[t]; - - printf("######## %s/%s %s ########\n", - family_strings[f], type_strings[t], - inany ? " INANY " : "LOOPBACK"); - - setup_per_test(type, family, inany); - - test_err_inner_map(type, family); - - /* Install reuseport_array to the outer_map */ - err = bpf_map_update_elem(outer_map, &index_zero, - &reuseport_array, BPF_ANY); - CHECK(err == -1, "update_elem(outer_map)", - "err:%d errno:%d\n", err, errno); - - test_err_skb_data(type, family); - test_err_sk_select_port(type, family); - test_pass(type, family); - test_syncookie(type, family); - test_pass_on_err(type, family); - /* Must be the last test */ - test_detach_bpf(type, family); - - cleanup_per_test(); - printf("\n"); - } + switch (family) { + case AF_INET: + return "IPv4"; + case AF_INET6: + return "IPv6"; + default: + return "unknown"; + } +} + +static const char *sotype_str(int sotype) +{ + switch (sotype) { + case SOCK_STREAM: + return "TCP"; + case SOCK_DGRAM: + return "UDP"; + default: + return "unknown"; } } -int main(int argc, const char **argv) +#define TEST_INIT(fn, ...) { fn, #fn, __VA_ARGS__ } + +static void test_config(int sotype, sa_family_t family, bool inany) { - create_maps(); - prepare_bpf_obj(); + const struct test { + void (*fn)(int sotype, sa_family_t family); + const char *name; + bool no_inner_map; + } tests[] = { + TEST_INIT(test_err_inner_map, true /* no_inner_map */), + TEST_INIT(test_err_skb_data), + TEST_INIT(test_err_sk_select_port), + TEST_INIT(test_pass), + TEST_INIT(test_syncookie), + TEST_INIT(test_pass_on_err), + TEST_INIT(test_detach_bpf), + }; + char s[MAX_TEST_NAME]; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + snprintf(s, sizeof(s), "%s/%s %s %s", + family_str(family), sotype_str(sotype), + inany ? "INANY" : "LOOPBACK", t->name); + + if (!test__start_subtest(s)) + continue; + + setup_per_test(sotype, family, inany, t->no_inner_map); + t->fn(sotype, family); + cleanup_per_test(t->no_inner_map); + } +} + +#define BIND_INANY true + +static void test_all(void) +{ + const struct config { + int sotype; + sa_family_t family; + bool inany; + } configs[] = { + { SOCK_STREAM, AF_INET }, + { SOCK_STREAM, AF_INET, BIND_INANY }, + { SOCK_STREAM, AF_INET6 }, + { SOCK_STREAM, AF_INET6, BIND_INANY }, + { SOCK_DGRAM, AF_INET }, + { SOCK_DGRAM, AF_INET6 }, + }; + const struct config *c; + + for (c = configs; c < configs + ARRAY_SIZE(configs); c++) + test_config(c->sotype, c->family, c->inany); +} + +void test_select_reuseport(void) +{ + if (create_maps()) + goto out; + if (prepare_bpf_obj()) + goto out; + saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); + if (saved_tcp_fo < 0) + goto out; saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); - enable_fastopen(); - disable_syncookie(); - atexit(restore_sysctls); + if (saved_tcp_syncookie < 0) + goto out; - test_all(); + if (enable_fastopen()) + goto out; + if (disable_syncookie()) + goto out; + test_all(); +out: cleanup(); - return 0; + restore_sysctls(); } diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index b607112c64e7..504abb7bfb95 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_send_signal_kern.skel.h" static volatile int sigusr1_received = 0; @@ -9,17 +10,15 @@ static void sigusr1_handler(int signum) } static void test_send_signal_common(struct perf_event_attr *attr, - int prog_type, + bool signal_thread, const char *test_name) { - int err = -1, pmu_fd, prog_fd, info_map_fd, status_map_fd; - const char *file = "./test_send_signal_kern.o"; - struct bpf_object *obj = NULL; + struct test_send_signal_kern *skel; int pipe_c2p[2], pipe_p2c[2]; - __u32 key = 0, duration = 0; + int err = -1, pmu_fd = -1; + __u32 duration = 0; char buf[256]; pid_t pid; - __u64 val; if (CHECK(pipe(pipe_c2p), test_name, "pipe pipe_c2p error: %s\n", strerror(errno))) @@ -73,45 +72,39 @@ static void test_send_signal_common(struct perf_event_attr *attr, close(pipe_c2p[1]); /* close write */ close(pipe_p2c[0]); /* close read */ - err = bpf_prog_load(file, prog_type, &obj, &prog_fd); - if (CHECK(err < 0, test_name, "bpf_prog_load error: %s\n", - strerror(errno))) - goto prog_load_failure; - - pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1, - -1 /* group id */, 0 /* flags */); - if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n", - strerror(errno))) { - err = -1; - goto close_prog; - } + skel = test_send_signal_kern__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open_and_load failed\n")) + goto skel_open_load_failure; - err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); - if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_enable error: %s\n", - strerror(errno))) - goto disable_pmu; - - err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); - if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_set_bpf error: %s\n", - strerror(errno))) - goto disable_pmu; - - err = -1; - info_map_fd = bpf_object__find_map_fd_by_name(obj, "info_map"); - if (CHECK(info_map_fd < 0, test_name, "find map %s error\n", "info_map")) - goto disable_pmu; + if (!attr) { + err = test_send_signal_kern__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed\n")) { + err = -1; + goto destroy_skel; + } + } else { + pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1, + -1 /* group id */, 0 /* flags */); + if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n", + strerror(errno))) { + err = -1; + goto destroy_skel; + } - status_map_fd = bpf_object__find_map_fd_by_name(obj, "status_map"); - if (CHECK(status_map_fd < 0, test_name, "find map %s error\n", "status_map")) - goto disable_pmu; + skel->links.send_signal_perf = + bpf_program__attach_perf_event(skel->progs.send_signal_perf, pmu_fd); + if (CHECK(IS_ERR(skel->links.send_signal_perf), "attach_perf_event", + "err %ld\n", PTR_ERR(skel->links.send_signal_perf))) + goto disable_pmu; + } /* wait until child signal handler installed */ read(pipe_c2p[0], buf, 1); /* trigger the bpf send_signal */ - key = 0; - val = (((__u64)(SIGUSR1)) << 32) | pid; - bpf_map_update_elem(info_map_fd, &key, &val, 0); + skel->bss->pid = pid; + skel->bss->sig = SIGUSR1; + skel->bss->signal_thread = signal_thread; /* notify child that bpf program can send_signal now */ write(pipe_p2c[1], buf, 1); @@ -132,46 +125,20 @@ static void test_send_signal_common(struct perf_event_attr *attr, disable_pmu: close(pmu_fd); -close_prog: - bpf_object__close(obj); -prog_load_failure: +destroy_skel: + test_send_signal_kern__destroy(skel); +skel_open_load_failure: close(pipe_c2p[0]); close(pipe_p2c[1]); wait(NULL); } -static void test_send_signal_tracepoint(void) +static void test_send_signal_tracepoint(bool signal_thread) { - const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id"; - struct perf_event_attr attr = { - .type = PERF_TYPE_TRACEPOINT, - .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN, - .sample_period = 1, - .wakeup_events = 1, - }; - __u32 duration = 0; - int bytes, efd; - char buf[256]; - - efd = open(id_path, O_RDONLY, 0); - if (CHECK(efd < 0, "tracepoint", - "open syscalls/sys_enter_nanosleep/id failure: %s\n", - strerror(errno))) - return; - - bytes = read(efd, buf, sizeof(buf)); - close(efd); - if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint", - "read syscalls/sys_enter_nanosleep/id failure: %s\n", - strerror(errno))) - return; - - attr.config = strtol(buf, NULL, 0); - - test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint"); + test_send_signal_common(NULL, signal_thread, "tracepoint"); } -static void test_send_signal_perf(void) +static void test_send_signal_perf(bool signal_thread) { struct perf_event_attr attr = { .sample_period = 1, @@ -179,15 +146,13 @@ static void test_send_signal_perf(void) .config = PERF_COUNT_SW_CPU_CLOCK, }; - test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, - "perf_sw_event"); + test_send_signal_common(&attr, signal_thread, "perf_sw_event"); } -static void test_send_signal_nmi(void) +static void test_send_signal_nmi(bool signal_thread) { struct perf_event_attr attr = { - .sample_freq = 50, - .freq = 1, + .sample_period = 1, .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, }; @@ -210,16 +175,21 @@ static void test_send_signal_nmi(void) close(pmu_fd); } - test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, - "perf_hw_event"); + test_send_signal_common(&attr, signal_thread, "perf_hw_event"); } void test_send_signal(void) { if (test__start_subtest("send_signal_tracepoint")) - test_send_signal_tracepoint(); + test_send_signal_tracepoint(false); if (test__start_subtest("send_signal_perf")) - test_send_signal_perf(); + test_send_signal_perf(false); if (test__start_subtest("send_signal_nmi")) - test_send_signal_nmi(); + test_send_signal_nmi(false); + if (test__start_subtest("send_signal_tracepoint_thread")) + test_send_signal_tracepoint(true); + if (test__start_subtest("send_signal_perf_thread")) + test_send_signal_perf(true); + if (test__start_subtest("send_signal_nmi_thread")) + test_send_signal_nmi(true); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index a2eb8db8dafb..c6d6b685a946 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -11,6 +11,9 @@ void test_skb_ctx(void) .cb[4] = 5, .priority = 6, .tstamp = 7, + .wire_len = 100, + .gso_segs = 8, + .mark = 9, }; struct bpf_prog_test_run_attr tattr = { .data_in = &pkt_v4, @@ -91,4 +94,8 @@ void test_skb_ctx(void) "ctx_out_tstamp", "skb->tstamp == %lld, expected %d\n", skb.tstamp, 8); + CHECK_ATTR(skb.mark != 10, + "ctx_out_mark", + "skb->mark == %u, expected %d\n", + skb.mark, 10); } diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c new file mode 100644 index 000000000000..9264a2736018 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <test_progs.h> + +struct s { + int a; + long long b; +} __attribute__((packed)); + +#include "test_skeleton.skel.h" + +void test_skeleton(void) +{ + int duration = 0, err; + struct test_skeleton* skel; + struct test_skeleton__bss *bss; + struct test_skeleton__kconfig *kcfg; + + skel = test_skeleton__open(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + + if (CHECK(skel->kconfig, "skel_kconfig", "kconfig is mmaped()!\n")) + goto cleanup; + + err = test_skeleton__load(skel); + if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + goto cleanup; + + bss = skel->bss; + bss->in1 = 1; + bss->in2 = 2; + bss->in3 = 3; + bss->in4 = 4; + bss->in5.a = 5; + bss->in5.b = 6; + kcfg = skel->kconfig; + + err = test_skeleton__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + CHECK(bss->out1 != 1, "res1", "got %d != exp %d\n", bss->out1, 1); + CHECK(bss->out2 != 2, "res2", "got %lld != exp %d\n", bss->out2, 2); + CHECK(bss->out3 != 3, "res3", "got %d != exp %d\n", (int)bss->out3, 3); + CHECK(bss->out4 != 4, "res4", "got %lld != exp %d\n", bss->out4, 4); + CHECK(bss->handler_out5.a != 5, "res5", "got %d != exp %d\n", + bss->handler_out5.a, 5); + CHECK(bss->handler_out5.b != 6, "res6", "got %lld != exp %d\n", + bss->handler_out5.b, 6); + + CHECK(bss->bpf_syscall != kcfg->CONFIG_BPF_SYSCALL, "ext1", + "got %d != exp %d\n", bss->bpf_syscall, kcfg->CONFIG_BPF_SYSCALL); + CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2", + "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION); + +cleanup: + test_skeleton__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c new file mode 100644 index 000000000000..aa43e0bd210c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare + +#include "test_progs.h" + +#define TCP_REPAIR 19 /* TCP sock is under repair right now */ + +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + +static int connected_socket_v4(void) +{ + struct sockaddr_in addr = { + .sin_family = AF_INET, + .sin_port = htons(80), + .sin_addr = { inet_addr("127.0.0.1") }, + }; + socklen_t len = sizeof(addr); + int s, repair, err; + + s = socket(AF_INET, SOCK_STREAM, 0); + if (CHECK_FAIL(s == -1)) + goto error; + + repair = TCP_REPAIR_ON; + err = setsockopt(s, SOL_TCP, TCP_REPAIR, &repair, sizeof(repair)); + if (CHECK_FAIL(err)) + goto error; + + err = connect(s, (struct sockaddr *)&addr, len); + if (CHECK_FAIL(err)) + goto error; + + repair = TCP_REPAIR_OFF_NO_WP; + err = setsockopt(s, SOL_TCP, TCP_REPAIR, &repair, sizeof(repair)); + if (CHECK_FAIL(err)) + goto error; + + return s; +error: + perror(__func__); + close(s); + return -1; +} + +/* Create a map, populate it with one socket, and free the map. */ +static void test_sockmap_create_update_free(enum bpf_map_type map_type) +{ + const int zero = 0; + int s, map, err; + + s = connected_socket_v4(); + if (CHECK_FAIL(s == -1)) + return; + + map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); + if (CHECK_FAIL(map == -1)) { + perror("bpf_create_map"); + goto out; + } + + err = bpf_map_update_elem(map, &zero, &s, BPF_NOEXIST); + if (CHECK_FAIL(err)) { + perror("bpf_map_update"); + goto out; + } + +out: + close(map); + close(s); +} + +void test_sockmap_basic(void) +{ + if (test__start_subtest("sockmap create_update_free")) + test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP); + if (test__start_subtest("sockhash create_update_free")) + test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH); +} diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c index d841dced971f..e8399ae50e77 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c @@ -1,16 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_stacktrace_build_id.skel.h" void test_stacktrace_build_id(void) { + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; - const char *prog_name = "tracepoint/random/urandom_read"; - const char *file = "./test_stacktrace_build_id.o"; - int err, prog_fd, stack_trace_len; + struct test_stacktrace_build_id *skel; + int err, stack_trace_len; __u32 key, previous_key, val, duration = 0; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link = NULL; char buf[256]; int i, j; struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH]; @@ -18,43 +16,24 @@ void test_stacktrace_build_id(void) int retry = 1; retry: - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); - if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + skel = test_stacktrace_build_id__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) return; - prog = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) - goto close_prog; - - link = bpf_program__attach_tracepoint(prog, "random", "urandom_read"); - if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link))) - goto close_prog; + err = test_stacktrace_build_id__attach(skel); + if (CHECK(err, "attach_tp", "err %d\n", err)) + goto cleanup; /* find map fds */ - control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (CHECK(control_map_fd < 0, "bpf_find_map control_map", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n", - err, errno)) - goto disable_pmu; - - stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); - if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; + control_map_fd = bpf_map__fd(skel->maps.control_map); + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + stackmap_fd = bpf_map__fd(skel->maps.stackmap); + stack_amap_fd = bpf_map__fd(skel->maps.stack_amap); if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null"))) - goto disable_pmu; + goto cleanup; if (CHECK_FAIL(system("./urandom_read"))) - goto disable_pmu; + goto cleanup; /* disable stack trace collection */ key = 0; val = 1; @@ -66,23 +45,23 @@ retry: err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = compare_map_keys(stackmap_fd, stackid_hmap_fd); if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = extract_build_id(buf, 256); if (CHECK(err, "get build_id with readelf", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = bpf_map_get_next_key(stackmap_fd, NULL, &key); if (CHECK(err, "get_next_key from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; do { char build_id[64]; @@ -90,7 +69,7 @@ retry: err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs); if (CHECK(err, "lookup_elem from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i) if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID && id_offs[i].offset != 0) { @@ -108,8 +87,7 @@ retry: * try it one more time. */ if (build_id_matches < 1 && retry--) { - bpf_link__destroy(link); - bpf_object__close(obj); + test_stacktrace_build_id__destroy(skel); printf("%s:WARN:Didn't find expected build ID from the map, retrying\n", __func__); goto retry; @@ -117,17 +95,14 @@ retry: if (CHECK(build_id_matches < 1, "build id match", "Didn't find expected build ID from the map\n")) - goto disable_pmu; + goto cleanup; - stack_trace_len = PERF_MAX_STACK_DEPTH - * sizeof(struct bpf_stack_build_id); + stack_trace_len = PERF_MAX_STACK_DEPTH * + sizeof(struct bpf_stack_build_id); err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); CHECK(err, "compare_stack_ips stackmap vs. stack_amap", "err %d errno %d\n", err, errno); -disable_pmu: - bpf_link__destroy(link); - -close_prog: - bpf_object__close(obj); +cleanup: + test_stacktrace_build_id__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index f62aa0eb959b..f002e3090d92 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_stacktrace_build_id.skel.h" static __u64 read_perf_max_sample_freq(void) { @@ -16,19 +17,15 @@ static __u64 read_perf_max_sample_freq(void) void test_stacktrace_build_id_nmi(void) { - int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; - const char *prog_name = "tracepoint/random/urandom_read"; - const char *file = "./test_stacktrace_build_id.o"; - int err, pmu_fd, prog_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd; + struct test_stacktrace_build_id *skel; + int err, pmu_fd; struct perf_event_attr attr = { .freq = 1, .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, }; __u32 key, previous_key, val, duration = 0; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link; char buf[256]; int i, j; struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH]; @@ -38,54 +35,46 @@ void test_stacktrace_build_id_nmi(void) attr.sample_freq = read_perf_max_sample_freq(); retry: - err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd); - if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + skel = test_stacktrace_build_id__open(); + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) return; - prog = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) - goto close_prog; + /* override program type */ + bpf_program__set_perf_event(skel->progs.oncpu); + + err = test_stacktrace_build_id__load(skel); + if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) + goto cleanup; pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu 0 */, -1 /* group id */, 0 /* flags */); - if (CHECK(pmu_fd < 0, "perf_event_open", - "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n", + if (pmu_fd < 0 && errno == ENOENT) { + printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__); + test__skip(); + goto cleanup; + } + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, errno)) - goto close_prog; + goto cleanup; - link = bpf_program__attach_perf_event(prog, pmu_fd); - if (CHECK(IS_ERR(link), "attach_perf_event", - "err %ld\n", PTR_ERR(link))) { + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event", + "err %ld\n", PTR_ERR(skel->links.oncpu))) { close(pmu_fd); - goto close_prog; + goto cleanup; } /* find map fds */ - control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (CHECK(control_map_fd < 0, "bpf_find_map control_map", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n", - err, errno)) - goto disable_pmu; - - stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); - if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; + control_map_fd = bpf_map__fd(skel->maps.control_map); + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + stackmap_fd = bpf_map__fd(skel->maps.stackmap); if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null"))) - goto disable_pmu; + goto cleanup; if (CHECK_FAIL(system("taskset 0x1 ./urandom_read 100000"))) - goto disable_pmu; + goto cleanup; /* disable stack trace collection */ key = 0; val = 1; @@ -97,23 +86,23 @@ retry: err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = compare_map_keys(stackmap_fd, stackid_hmap_fd); if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = extract_build_id(buf, 256); if (CHECK(err, "get build_id with readelf", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = bpf_map_get_next_key(stackmap_fd, NULL, &key); if (CHECK(err, "get_next_key from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; do { char build_id[64]; @@ -121,7 +110,7 @@ retry: err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs); if (CHECK(err, "lookup_elem from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i) if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID && id_offs[i].offset != 0) { @@ -139,8 +128,7 @@ retry: * try it one more time. */ if (build_id_matches < 1 && retry--) { - bpf_link__destroy(link); - bpf_object__close(obj); + test_stacktrace_build_id__destroy(skel); printf("%s:WARN:Didn't find expected build ID from the map, retrying\n", __func__); goto retry; @@ -148,7 +136,7 @@ retry: if (CHECK(build_id_matches < 1, "build id match", "Didn't find expected build ID from the map\n")) - goto disable_pmu; + goto cleanup; /* * We intentionally skip compare_stack_ips(). This is because we @@ -157,8 +145,6 @@ retry: * BPF_STACK_BUILD_ID_IP; */ -disable_pmu: - bpf_link__destroy(link); -close_prog: - bpf_object__close(obj); +cleanup: + test_stacktrace_build_id__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c new file mode 100644 index 000000000000..25b068591e9a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <test_progs.h> + +const char *err_str; +bool found; + +static int libbpf_debug_print(enum libbpf_print_level level, + const char *format, va_list args) +{ + char *log_buf; + + if (level != LIBBPF_WARN || + strcmp(format, "libbpf: \n%s\n")) { + vprintf(format, args); + return 0; + } + + log_buf = va_arg(args, char *); + if (!log_buf) + goto out; + if (strstr(log_buf, err_str) == 0) + found = true; +out: + printf(format, log_buf); + return 0; +} + +extern int extra_prog_load_log_flags; + +static int check_load(const char *file) +{ + struct bpf_prog_load_attr attr; + struct bpf_object *obj = NULL; + int err, prog_fd; + + memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); + attr.file = file; + attr.prog_type = BPF_PROG_TYPE_UNSPEC; + attr.log_level = extra_prog_load_log_flags; + attr.prog_flags = BPF_F_TEST_RND_HI32; + found = false; + err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + bpf_object__close(obj); + return err; +} + +struct test_def { + const char *file; + const char *err_str; +}; + +void test_test_global_funcs(void) +{ + struct test_def tests[] = { + { "test_global_func1.o", "combined stack size of 4 calls is 544" }, + { "test_global_func2.o" }, + { "test_global_func3.o" , "the call stack of 8 frames" }, + { "test_global_func4.o" }, + { "test_global_func5.o" , "expected pointer to ctx, but got PTR" }, + { "test_global_func6.o" , "modified ctx ptr R2" }, + { "test_global_func7.o" , "foo() doesn't return scalar" }, + }; + libbpf_print_fn_t old_print_fn = NULL; + int err, i, duration = 0; + + old_print_fn = libbpf_set_print(libbpf_debug_print); + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + const struct test_def *test = &tests[i]; + + if (!test__start_subtest(test->file)) + continue; + + err_str = test->err_str; + err = check_load(test->file); + CHECK_FAIL(!!err ^ !!err_str); + if (err_str) + CHECK(found, "", "expected string '%s'", err_str); + } + libbpf_set_print(old_print_fn); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c index c32aa28bd93f..465b371a561d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c +++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 Facebook */ #define _GNU_SOURCE #include <sched.h> +#include <sys/prctl.h> #include <test_progs.h> #define MAX_CNT 100000 @@ -17,7 +18,7 @@ static __u64 time_get_ns(void) static int test_task_rename(const char *prog) { int i, fd, duration = 0, err; - char buf[] = "test\n"; + char buf[] = "test_overhead"; __u64 start_time; fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); @@ -66,6 +67,10 @@ void test_test_overhead(void) struct bpf_object *obj; struct bpf_link *link; int err, duration = 0; + char comm[16] = {}; + + if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L))) + return; obj = bpf_object__open_file("./test_overhead.o", NULL); if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) @@ -138,5 +143,6 @@ void test_test_overhead(void) test_run("fexit"); bpf_link__destroy(link); cleanup: + prctl(PR_SET_NAME, comm, 0L, 0L, 0L); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c new file mode 100644 index 000000000000..1f6ccdaed1ac --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE +#include <sched.h> +#include <sys/prctl.h> +#include <test_progs.h> + +#define MAX_TRAMP_PROGS 40 + +struct inst { + struct bpf_object *obj; + struct bpf_link *link_fentry; + struct bpf_link *link_fexit; +}; + +static int test_task_rename(void) +{ + int fd, duration = 0, err; + char buf[] = "test_overhead"; + + fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); + if (CHECK(fd < 0, "open /proc", "err %d", errno)) + return -1; + err = write(fd, buf, sizeof(buf)); + if (err < 0) { + CHECK(err < 0, "task rename", "err %d", errno); + close(fd); + return -1; + } + close(fd); + return 0; +} + +static struct bpf_link *load(struct bpf_object *obj, const char *name) +{ + struct bpf_program *prog; + int duration = 0; + + prog = bpf_object__find_program_by_title(obj, name); + if (CHECK(!prog, "find_probe", "prog '%s' not found\n", name)) + return ERR_PTR(-EINVAL); + return bpf_program__attach_trace(prog); +} + +void test_trampoline_count(void) +{ + const char *fentry_name = "fentry/__set_task_comm"; + const char *fexit_name = "fexit/__set_task_comm"; + const char *object = "test_trampoline_count.o"; + struct inst inst[MAX_TRAMP_PROGS] = {}; + int err, i = 0, duration = 0; + struct bpf_object *obj; + struct bpf_link *link; + char comm[16] = {}; + + /* attach 'allowed' 40 trampoline programs */ + for (i = 0; i < MAX_TRAMP_PROGS; i++) { + obj = bpf_object__open_file(object, NULL); + if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) + goto cleanup; + + err = bpf_object__load(obj); + if (CHECK(err, "obj_load", "err %d\n", err)) + goto cleanup; + inst[i].obj = obj; + + if (rand() % 2) { + link = load(obj, fentry_name); + if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) + goto cleanup; + inst[i].link_fentry = link; + } else { + link = load(obj, fexit_name); + if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) + goto cleanup; + inst[i].link_fexit = link; + } + } + + /* and try 1 extra.. */ + obj = bpf_object__open_file(object, NULL); + if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) + goto cleanup; + + err = bpf_object__load(obj); + if (CHECK(err, "obj_load", "err %d\n", err)) + goto cleanup_extra; + + /* ..that needs to fail */ + link = load(obj, fentry_name); + if (CHECK(!IS_ERR(link), "cannot attach over the limit", "err %ld\n", PTR_ERR(link))) { + bpf_link__destroy(link); + goto cleanup_extra; + } + + /* with E2BIG error */ + CHECK(PTR_ERR(link) != -E2BIG, "proper error check", "err %ld\n", PTR_ERR(link)); + + /* and finaly execute the probe */ + if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L))) + goto cleanup_extra; + CHECK_FAIL(test_task_rename()); + CHECK_FAIL(prctl(PR_SET_NAME, comm, 0L, 0L, 0L)); + +cleanup_extra: + bpf_object__close(obj); +cleanup: + while (--i) { + bpf_link__destroy(inst[i].link_fentry); + bpf_link__destroy(inst[i].link_fexit); + bpf_object__close(inst[i].obj); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c new file mode 100644 index 000000000000..6b56bdc73ebc --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <net/if.h> +#include "test_xdp.skel.h" +#include "test_xdp_bpf2bpf.skel.h" + +void test_xdp_bpf2bpf(void) +{ + __u32 duration = 0, retval, size; + char buf[128]; + int err, pkt_fd, map_fd; + struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + struct iptnl_info value4 = {.family = AF_INET}; + struct test_xdp *pkt_skel = NULL; + struct test_xdp_bpf2bpf *ftrace_skel = NULL; + struct vip key4 = {.protocol = 6, .family = AF_INET}; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + + /* Load XDP program to introspect */ + pkt_skel = test_xdp__open_and_load(); + if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n")) + return; + + pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel); + + map_fd = bpf_map__fd(pkt_skel->maps.vip2tnl); + bpf_map_update_elem(map_fd, &key4, &value4, 0); + + /* Load trace program */ + opts.attach_prog_fd = pkt_fd, + ftrace_skel = test_xdp_bpf2bpf__open_opts(&opts); + if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n")) + goto out; + + err = test_xdp_bpf2bpf__load(ftrace_skel); + if (CHECK(err, "__load", "ftrace skeleton failed\n")) + goto out; + + err = test_xdp_bpf2bpf__attach(ftrace_skel); + if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err)) + goto out; + + /* Run test program */ + err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + + if (CHECK(err || retval != XDP_TX || size != 74 || + iph->protocol != IPPROTO_IPIP, "ipv4", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size)) + goto out; + + /* Verify test results */ + if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), + "result", "fentry failed err %llu\n", + ftrace_skel->bss->test_result_fentry)) + goto out; + + CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result", + "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit); + +out: + test_xdp__destroy(pkt_skel); + test_xdp_bpf2bpf__destroy(ftrace_skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c new file mode 100644 index 000000000000..7185bee16fe4 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +void test_xdp_perf(void) +{ + const char *file = "./xdp_dummy.o"; + __u32 duration, retval, size; + struct bpf_object *obj; + char in[128], out[128]; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (CHECK_FAIL(err)) + return; + + err = bpf_prog_test_run(prog_fd, 1000000, &in[0], 128, + out, &size, &retval, &duration); + + CHECK(err || retval != XDP_PASS || size != 128, + "xdp-perf", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c new file mode 100644 index 000000000000..7897c8f4d363 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -0,0 +1,544 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* WARNING: This implemenation is not necessarily the same + * as the tcp_cubic.c. The purpose is mainly for testing + * the kernel BPF logic. + * + * Highlights: + * 1. CONFIG_HZ .kconfig map is used. + * 2. In bictcp_update(), calculation is changed to use usec + * resolution (i.e. USEC_PER_JIFFY) instead of using jiffies. + * Thus, usecs_to_jiffies() is not used in the bpf_cubic.c. + * 3. In bitctcp_update() [under tcp_friendliness], the original + * "while (ca->ack_cnt > delta)" loop is changed to the equivalent + * "ca->ack_cnt / delta" operation. + */ + +#include <linux/bpf.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +#define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) + +#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation + * max_cwnd = snd_cwnd * beta + */ +#define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ + +/* Two methods of hybrid slow start */ +#define HYSTART_ACK_TRAIN 0x1 +#define HYSTART_DELAY 0x2 + +/* Number of delay samples for detecting the increase of delay */ +#define HYSTART_MIN_SAMPLES 8 +#define HYSTART_DELAY_MIN (4000U) /* 4ms */ +#define HYSTART_DELAY_MAX (16000U) /* 16 ms */ +#define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) + +static int fast_convergence = 1; +static const int beta = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */ +static int initial_ssthresh; +static const int bic_scale = 41; +static int tcp_friendliness = 1; + +static int hystart = 1; +static int hystart_detect = HYSTART_ACK_TRAIN | HYSTART_DELAY; +static int hystart_low_window = 16; +static int hystart_ack_delta_us = 2000; + +static const __u32 cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */ +static const __u32 beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3 + / (BICTCP_BETA_SCALE - beta); +/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3 + * so K = cubic_root( (wmax-cwnd)*rtt/c ) + * the unit of K is bictcp_HZ=2^10, not HZ + * + * c = bic_scale >> 10 + * rtt = 100ms + * + * the following code has been designed and tested for + * cwnd < 1 million packets + * RTT < 100 seconds + * HZ < 1,000,00 (corresponding to 10 nano-second) + */ + +/* 1/c * 2^2*bictcp_HZ * srtt, 2^40 */ +static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ)) + / (bic_scale * 10); + +/* BIC TCP Parameters */ +struct bictcp { + __u32 cnt; /* increase cwnd by 1 after ACKs */ + __u32 last_max_cwnd; /* last maximum snd_cwnd */ + __u32 last_cwnd; /* the last snd_cwnd */ + __u32 last_time; /* time when updated last_cwnd */ + __u32 bic_origin_point;/* origin point of bic function */ + __u32 bic_K; /* time to origin point + from the beginning of the current epoch */ + __u32 delay_min; /* min delay (usec) */ + __u32 epoch_start; /* beginning of an epoch */ + __u32 ack_cnt; /* number of acks */ + __u32 tcp_cwnd; /* estimated tcp cwnd */ + __u16 unused; + __u8 sample_cnt; /* number of samples to decide curr_rtt */ + __u8 found; /* the exit point is found? */ + __u32 round_start; /* beginning of each round */ + __u32 end_seq; /* end_seq of the round */ + __u32 last_ack; /* last time when the ACK spacing is close */ + __u32 curr_rtt; /* the minimum rtt of current round */ +}; + +static inline void bictcp_reset(struct bictcp *ca) +{ + ca->cnt = 0; + ca->last_max_cwnd = 0; + ca->last_cwnd = 0; + ca->last_time = 0; + ca->bic_origin_point = 0; + ca->bic_K = 0; + ca->delay_min = 0; + ca->epoch_start = 0; + ca->ack_cnt = 0; + ca->tcp_cwnd = 0; + ca->found = 0; +} + +extern unsigned long CONFIG_HZ __kconfig; +#define HZ CONFIG_HZ +#define USEC_PER_MSEC 1000UL +#define USEC_PER_SEC 1000000UL +#define USEC_PER_JIFFY (USEC_PER_SEC / HZ) + +static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor) +{ + return dividend / divisor; +} + +#define div64_ul div64_u64 + +#define BITS_PER_U64 (sizeof(__u64) * 8) +static __always_inline int fls64(__u64 x) +{ + int num = BITS_PER_U64 - 1; + + if (x == 0) + return 0; + + if (!(x & (~0ull << (BITS_PER_U64-32)))) { + num -= 32; + x <<= 32; + } + if (!(x & (~0ull << (BITS_PER_U64-16)))) { + num -= 16; + x <<= 16; + } + if (!(x & (~0ull << (BITS_PER_U64-8)))) { + num -= 8; + x <<= 8; + } + if (!(x & (~0ull << (BITS_PER_U64-4)))) { + num -= 4; + x <<= 4; + } + if (!(x & (~0ull << (BITS_PER_U64-2)))) { + num -= 2; + x <<= 2; + } + if (!(x & (~0ull << (BITS_PER_U64-1)))) + num -= 1; + + return num + 1; +} + +static __always_inline __u32 bictcp_clock_us(const struct sock *sk) +{ + return tcp_sk(sk)->tcp_mstamp; +} + +static __always_inline void bictcp_hystart_reset(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + ca->round_start = ca->last_ack = bictcp_clock_us(sk); + ca->end_seq = tp->snd_nxt; + ca->curr_rtt = ~0U; + ca->sample_cnt = 0; +} + +/* "struct_ops/" prefix is not a requirement + * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS + * as long as it is used in one of the func ptr + * under SEC(".struct_ops"). + */ +SEC("struct_ops/bictcp_init") +void BPF_PROG(bictcp_init, struct sock *sk) +{ + struct bictcp *ca = inet_csk_ca(sk); + + bictcp_reset(ca); + + if (hystart) + bictcp_hystart_reset(sk); + + if (!hystart && initial_ssthresh) + tcp_sk(sk)->snd_ssthresh = initial_ssthresh; +} + +/* No prefix in SEC will also work. + * The remaining tcp-cubic functions have an easier way. + */ +SEC("no-sec-prefix-bictcp_cwnd_event") +void BPF_PROG(bictcp_cwnd_event, struct sock *sk, enum tcp_ca_event event) +{ + if (event == CA_EVENT_TX_START) { + struct bictcp *ca = inet_csk_ca(sk); + __u32 now = tcp_jiffies32; + __s32 delta; + + delta = now - tcp_sk(sk)->lsndtime; + + /* We were application limited (idle) for a while. + * Shift epoch_start to keep cwnd growth to cubic curve. + */ + if (ca->epoch_start && delta > 0) { + ca->epoch_start += delta; + if (after(ca->epoch_start, now)) + ca->epoch_start = now; + } + return; + } +} + +/* + * cbrt(x) MSB values for x MSB values in [0..63]. + * Precomputed then refined by hand - Willy Tarreau + * + * For x in [0..63], + * v = cbrt(x << 18) - 1 + * cbrt(x) = (v[x] + 10) >> 6 + */ +static const __u8 v[] = { + /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118, + /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156, + /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179, + /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199, + /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215, + /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229, + /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242, + /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254, +}; + +/* calculate the cubic root of x using a table lookup followed by one + * Newton-Raphson iteration. + * Avg err ~= 0.195% + */ +static __always_inline __u32 cubic_root(__u64 a) +{ + __u32 x, b, shift; + + if (a < 64) { + /* a in [0..63] */ + return ((__u32)v[(__u32)a] + 35) >> 6; + } + + b = fls64(a); + b = ((b * 84) >> 8) - 1; + shift = (a >> (b * 3)); + + /* it is needed for verifier's bound check on v */ + if (shift >= 64) + return 0; + + x = ((__u32)(((__u32)v[shift] + 10) << b)) >> 6; + + /* + * Newton-Raphson iteration + * 2 + * x = ( 2 * x + a / x ) / 3 + * k+1 k k + */ + x = (2 * x + (__u32)div64_u64(a, (__u64)x * (__u64)(x - 1))); + x = ((x * 341) >> 10); + return x; +} + +/* + * Compute congestion window to use. + */ +static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd, + __u32 acked) +{ + __u32 delta, bic_target, max_cnt; + __u64 offs, t; + + ca->ack_cnt += acked; /* count the number of ACKed packets */ + + if (ca->last_cwnd == cwnd && + (__s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) + return; + + /* The CUBIC function can update ca->cnt at most once per jiffy. + * On all cwnd reduction events, ca->epoch_start is set to 0, + * which will force a recalculation of ca->cnt. + */ + if (ca->epoch_start && tcp_jiffies32 == ca->last_time) + goto tcp_friendliness; + + ca->last_cwnd = cwnd; + ca->last_time = tcp_jiffies32; + + if (ca->epoch_start == 0) { + ca->epoch_start = tcp_jiffies32; /* record beginning */ + ca->ack_cnt = acked; /* start counting */ + ca->tcp_cwnd = cwnd; /* syn with cubic */ + + if (ca->last_max_cwnd <= cwnd) { + ca->bic_K = 0; + ca->bic_origin_point = cwnd; + } else { + /* Compute new K based on + * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ) + */ + ca->bic_K = cubic_root(cube_factor + * (ca->last_max_cwnd - cwnd)); + ca->bic_origin_point = ca->last_max_cwnd; + } + } + + /* cubic function - calc*/ + /* calculate c * time^3 / rtt, + * while considering overflow in calculation of time^3 + * (so time^3 is done by using 64 bit) + * and without the support of division of 64bit numbers + * (so all divisions are done by using 32 bit) + * also NOTE the unit of those veriables + * time = (t - K) / 2^bictcp_HZ + * c = bic_scale >> 10 + * rtt = (srtt >> 3) / HZ + * !!! The following code does not have overflow problems, + * if the cwnd < 1 million packets !!! + */ + + t = (__s32)(tcp_jiffies32 - ca->epoch_start) * USEC_PER_JIFFY; + t += ca->delay_min; + /* change the unit from usec to bictcp_HZ */ + t <<= BICTCP_HZ; + t /= USEC_PER_SEC; + + if (t < ca->bic_K) /* t - K */ + offs = ca->bic_K - t; + else + offs = t - ca->bic_K; + + /* c/rtt * (t-K)^3 */ + delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ); + if (t < ca->bic_K) /* below origin*/ + bic_target = ca->bic_origin_point - delta; + else /* above origin*/ + bic_target = ca->bic_origin_point + delta; + + /* cubic function - calc bictcp_cnt*/ + if (bic_target > cwnd) { + ca->cnt = cwnd / (bic_target - cwnd); + } else { + ca->cnt = 100 * cwnd; /* very small increment*/ + } + + /* + * The initial growth of cubic function may be too conservative + * when the available bandwidth is still unknown. + */ + if (ca->last_max_cwnd == 0 && ca->cnt > 20) + ca->cnt = 20; /* increase cwnd 5% per RTT */ + +tcp_friendliness: + /* TCP Friendly */ + if (tcp_friendliness) { + __u32 scale = beta_scale; + __u32 n; + + /* update tcp cwnd */ + delta = (cwnd * scale) >> 3; + if (ca->ack_cnt > delta && delta) { + n = ca->ack_cnt / delta; + ca->ack_cnt -= n * delta; + ca->tcp_cwnd += n; + } + + if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */ + delta = ca->tcp_cwnd - cwnd; + max_cnt = cwnd / delta; + if (ca->cnt > max_cnt) + ca->cnt = max_cnt; + } + } + + /* The maximum rate of cwnd increase CUBIC allows is 1 packet per + * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. + */ + ca->cnt = max(ca->cnt, 2U); +} + +/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */ +void BPF_STRUCT_OPS(bictcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + if (!tcp_is_cwnd_limited(sk)) + return; + + if (tcp_in_slow_start(tp)) { + if (hystart && after(ack, ca->end_seq)) + bictcp_hystart_reset(sk); + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } + bictcp_update(ca, tp->snd_cwnd, acked); + tcp_cong_avoid_ai(tp, ca->cnt, acked); +} + +__u32 BPF_STRUCT_OPS(bictcp_recalc_ssthresh, struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + ca->epoch_start = 0; /* end of epoch */ + + /* Wmax and fast convergence */ + if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence) + ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta)) + / (2 * BICTCP_BETA_SCALE); + else + ca->last_max_cwnd = tp->snd_cwnd; + + return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U); +} + +void BPF_STRUCT_OPS(bictcp_state, struct sock *sk, __u8 new_state) +{ + if (new_state == TCP_CA_Loss) { + bictcp_reset(inet_csk_ca(sk)); + bictcp_hystart_reset(sk); + } +} + +#define GSO_MAX_SIZE 65536 + +/* Account for TSO/GRO delays. + * Otherwise short RTT flows could get too small ssthresh, since during + * slow start we begin with small TSO packets and ca->delay_min would + * not account for long aggregation delay when TSO packets get bigger. + * Ideally even with a very small RTT we would like to have at least one + * TSO packet being sent and received by GRO, and another one in qdisc layer. + * We apply another 100% factor because @rate is doubled at this point. + * We cap the cushion to 1ms. + */ +static __always_inline __u32 hystart_ack_delay(struct sock *sk) +{ + unsigned long rate; + + rate = sk->sk_pacing_rate; + if (!rate) + return 0; + return min((__u64)USEC_PER_MSEC, + div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate)); +} + +static __always_inline void hystart_update(struct sock *sk, __u32 delay) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + __u32 threshold; + + if (hystart_detect & HYSTART_ACK_TRAIN) { + __u32 now = bictcp_clock_us(sk); + + /* first detection parameter - ack-train detection */ + if ((__s32)(now - ca->last_ack) <= hystart_ack_delta_us) { + ca->last_ack = now; + + threshold = ca->delay_min + hystart_ack_delay(sk); + + /* Hystart ack train triggers if we get ack past + * ca->delay_min/2. + * Pacing might have delayed packets up to RTT/2 + * during slow start. + */ + if (sk->sk_pacing_status == SK_PACING_NONE) + threshold >>= 1; + + if ((__s32)(now - ca->round_start) > threshold) { + ca->found = 1; + tp->snd_ssthresh = tp->snd_cwnd; + } + } + } + + if (hystart_detect & HYSTART_DELAY) { + /* obtain the minimum delay of more than sampling packets */ + if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; + + ca->sample_cnt++; + } else { + if (ca->curr_rtt > ca->delay_min + + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { + ca->found = 1; + tp->snd_ssthresh = tp->snd_cwnd; + } + } + } +} + +void BPF_STRUCT_OPS(bictcp_acked, struct sock *sk, + const struct ack_sample *sample) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + __u32 delay; + + /* Some calls are for duplicates without timetamps */ + if (sample->rtt_us < 0) + return; + + /* Discard delay samples right after fast recovery */ + if (ca->epoch_start && (__s32)(tcp_jiffies32 - ca->epoch_start) < HZ) + return; + + delay = sample->rtt_us; + if (delay == 0) + delay = 1; + + /* first time call or link delay decreases */ + if (ca->delay_min == 0 || ca->delay_min > delay) + ca->delay_min = delay; + + /* hystart triggers when cwnd is larger than some threshold */ + if (!ca->found && tcp_in_slow_start(tp) && hystart && + tp->snd_cwnd >= hystart_low_window) + hystart_update(sk, delay); +} + +__u32 BPF_STRUCT_OPS(tcp_reno_undo_cwnd, struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + + return max(tp->snd_cwnd, tp->prior_cwnd); +} + +SEC(".struct_ops") +struct tcp_congestion_ops cubic = { + .init = (void *)bictcp_init, + .ssthresh = (void *)bictcp_recalc_ssthresh, + .cong_avoid = (void *)bictcp_cong_avoid, + .set_state = (void *)bictcp_state, + .undo_cwnd = (void *)tcp_reno_undo_cwnd, + .cwnd_event = (void *)bictcp_cwnd_event, + .pkts_acked = (void *)bictcp_acked, + .name = "bpf_cubic", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c new file mode 100644 index 000000000000..b631fb5032d2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -0,0 +1,216 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +/* WARNING: This implemenation is not necessarily the same + * as the tcp_dctcp.c. The purpose is mainly for testing + * the kernel BPF logic. + */ + +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include "bpf_trace_helpers.h" +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "GPL"; + +#define DCTCP_MAX_ALPHA 1024U + +struct dctcp { + __u32 old_delivered; + __u32 old_delivered_ce; + __u32 prior_rcv_nxt; + __u32 dctcp_alpha; + __u32 next_seq; + __u32 ce_state; + __u32 loss_cwnd; +}; + +static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */ +static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA; + +static __always_inline void dctcp_reset(const struct tcp_sock *tp, + struct dctcp *ca) +{ + ca->next_seq = tp->snd_nxt; + + ca->old_delivered = tp->delivered; + ca->old_delivered_ce = tp->delivered_ce; +} + +SEC("struct_ops/dctcp_init") +void BPF_PROG(dctcp_init, struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct dctcp *ca = inet_csk_ca(sk); + + ca->prior_rcv_nxt = tp->rcv_nxt; + ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); + ca->loss_cwnd = 0; + ca->ce_state = 0; + + dctcp_reset(tp, ca); +} + +SEC("struct_ops/dctcp_ssthresh") +__u32 BPF_PROG(dctcp_ssthresh, struct sock *sk) +{ + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ca->loss_cwnd = tp->snd_cwnd; + return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U); +} + +SEC("struct_ops/dctcp_update_alpha") +void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct dctcp *ca = inet_csk_ca(sk); + + /* Expired RTT */ + if (!before(tp->snd_una, ca->next_seq)) { + __u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; + __u32 alpha = ca->dctcp_alpha; + + /* alpha = (1 - g) * alpha + g * F */ + + alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); + if (delivered_ce) { + __u32 delivered = tp->delivered - ca->old_delivered; + + /* If dctcp_shift_g == 1, a 32bit value would overflow + * after 8 M packets. + */ + delivered_ce <<= (10 - dctcp_shift_g); + delivered_ce /= max(1U, delivered); + + alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA); + } + ca->dctcp_alpha = alpha; + dctcp_reset(tp, ca); + } +} + +static __always_inline void dctcp_react_to_loss(struct sock *sk) +{ + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +SEC("struct_ops/dctcp_state") +void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state)) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ +} + +static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (ce_state == 1) + tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + else + tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; +} + +/* Minimal DCTP CE state machine: + * + * S: 0 <- last pkt was non-CE + * 1 <- last pkt was CE + */ +static __always_inline +void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt, + __u32 *prior_rcv_nxt, __u32 *ce_state) +{ + __u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0; + + if (*ce_state != new_ce_state) { + /* CE state has changed, force an immediate ACK to + * reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { + dctcp_ece_ack_cwr(sk, *ce_state); + bpf_tcp_send_ack(sk, *prior_rcv_nxt); + } + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } + *prior_rcv_nxt = tcp_sk(sk)->rcv_nxt; + *ce_state = new_ce_state; + dctcp_ece_ack_cwr(sk, new_ce_state); +} + +SEC("struct_ops/dctcp_cwnd_event") +void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev) +{ + struct dctcp *ca = inet_csk_ca(sk); + + switch (ev) { + case CA_EVENT_ECN_IS_CE: + case CA_EVENT_ECN_NO_CE: + dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); + break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; + default: + /* Don't care for the rest. */ + break; + } +} + +SEC("struct_ops/dctcp_cwnd_undo") +__u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk) +{ + const struct dctcp *ca = inet_csk_ca(sk); + + return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd); +} + +SEC("struct_ops/tcp_reno_cong_avoid") +void BPF_PROG(tcp_reno_cong_avoid, struct sock *sk, __u32 ack, __u32 acked) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!tcp_is_cwnd_limited(sk)) + return; + + /* In "safe" area, increase. */ + if (tcp_in_slow_start(tp)) { + acked = tcp_slow_start(tp, acked); + if (!acked) + return; + } + /* In dangerous area, increase slowly. */ + tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked); +} + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp_nouse = { + .init = (void *)dctcp_init, + .set_state = (void *)dctcp_state, + .flags = TCP_CONG_NEEDS_ECN, + .name = "bpf_dctcp_nouse", +}; + +SEC(".struct_ops") +struct tcp_congestion_ops dctcp = { + .init = (void *)dctcp_init, + .in_ack_event = (void *)dctcp_update_alpha, + .cwnd_event = (void *)dctcp_cwnd_event, + .ssthresh = (void *)dctcp_ssthresh, + .cong_avoid = (void *)tcp_reno_cong_avoid, + .undo_cwnd = (void *)dctcp_cwnd_undo, + .set_state = (void *)dctcp_state, + .flags = TCP_CONG_NEEDS_ECN, + .name = "bpf_dctcp", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 040a44206f29..9941f0ba471e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -16,8 +16,8 @@ #include <sys/socket.h> #include <linux/if_tunnel.h> #include <linux/mpls.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; #define PROG(F) SEC(#F) int bpf_func_##F diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c new file mode 100644 index 000000000000..65eac371b061 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___equiv_zero_sz_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c new file mode 100644 index 000000000000..ecda2b545ac2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_bad_zero_sz_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c new file mode 100644 index 000000000000..fe1d01232c22 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___fixed_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index 1fd244d35ba9..75085119c5bb 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -9,8 +9,8 @@ #include <linux/in6.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define SRC_REWRITE_IP4 0x7f000004U #define DST_REWRITE_IP4 0x7f000001U diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c index 26397ab7b3c7..506d0f81a375 100644 --- a/tools/testing/selftests/bpf/progs/connect6_prog.c +++ b/tools/testing/selftests/bpf/progs/connect6_prog.c @@ -9,8 +9,8 @@ #include <linux/in6.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define SRC_REWRITE_IP6_0 0 #define SRC_REWRITE_IP6_1 0 diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index 9311489e14b2..6d598cfbdb3e 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -327,6 +327,7 @@ struct core_reloc_arrays_output { char b123; int c1c; int d00d; + int f10c; }; struct core_reloc_arrays_substruct { @@ -339,6 +340,7 @@ struct core_reloc_arrays { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; /* bigger array dimensions */ @@ -347,6 +349,7 @@ struct core_reloc_arrays___diff_arr_dim { char b[3][4][5]; struct core_reloc_arrays_substruct c[4]; struct core_reloc_arrays_substruct d[2][3]; + struct core_reloc_arrays_substruct f[1][3]; }; /* different size of array's value (struct) */ @@ -363,6 +366,29 @@ struct core_reloc_arrays___diff_arr_val_sz { int d; int __padding2; } d[1][2]; + struct { + int __padding1; + int c; + int __padding2; + } f[][2]; +}; + +struct core_reloc_arrays___equiv_zero_sz_arr { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + /* equivalent to flexible array */ + struct core_reloc_arrays_substruct f[0][2]; +}; + +struct core_reloc_arrays___fixed_arr { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + /* not a flexible array anymore, but within access bounds */ + struct core_reloc_arrays_substruct f[1][2]; }; struct core_reloc_arrays___err_too_small { @@ -370,6 +396,7 @@ struct core_reloc_arrays___err_too_small { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_too_shallow { @@ -377,6 +404,7 @@ struct core_reloc_arrays___err_too_shallow { char b[2][3]; /* this one lacks one dimension */ struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_non_array { @@ -384,6 +412,7 @@ struct core_reloc_arrays___err_non_array { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_wrong_val_type { @@ -391,6 +420,16 @@ struct core_reloc_arrays___err_wrong_val_type { char b[2][3][4]; int c[3]; /* value is not a struct */ struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +struct core_reloc_arrays___err_bad_zero_sz_arr { + /* zero-sized array, but not at the end */ + struct core_reloc_arrays_substruct f[0][2]; + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; }; /* diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c index ce41a3475f27..8924e06bdef0 100644 --- a/tools/testing/selftests/bpf/progs/dev_cgroup.c +++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c @@ -7,7 +7,7 @@ #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("cgroup/dev") int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx) diff --git a/tools/testing/selftests/bpf/progs/fentry_test.c b/tools/testing/selftests/bpf/progs/fentry_test.c index 615f7c6bca77..38d3a82144ca 100644 --- a/tools/testing/selftests/bpf/progs/fentry_test.c +++ b/tools/testing/selftests/bpf/progs/fentry_test.c @@ -1,43 +1,46 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_trace_helpers.h" char _license[] SEC("license") = "GPL"; __u64 test1_result = 0; -BPF_TRACE_1("fentry/bpf_fentry_test1", test1, int, a) +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test1, int a) { test1_result = a == 1; return 0; } __u64 test2_result = 0; -BPF_TRACE_2("fentry/bpf_fentry_test2", test2, int, a, __u64, b) +SEC("fentry/bpf_fentry_test2") +int BPF_PROG(test2, int a, __u64 b) { test2_result = a == 2 && b == 3; return 0; } __u64 test3_result = 0; -BPF_TRACE_3("fentry/bpf_fentry_test3", test3, char, a, int, b, __u64, c) +SEC("fentry/bpf_fentry_test3") +int BPF_PROG(test3, char a, int b, __u64 c) { test3_result = a == 4 && b == 5 && c == 6; return 0; } __u64 test4_result = 0; -BPF_TRACE_4("fentry/bpf_fentry_test4", test4, - void *, a, char, b, int, c, __u64, d) +SEC("fentry/bpf_fentry_test4") +int BPF_PROG(test4, void *a, char b, int c, __u64 d) { test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10; return 0; } __u64 test5_result = 0; -BPF_TRACE_5("fentry/bpf_fentry_test5", test5, - __u64, a, void *, b, short, c, int, d, __u64, e) +SEC("fentry/bpf_fentry_test5") +int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e) { test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 && e == 15; @@ -45,8 +48,8 @@ BPF_TRACE_5("fentry/bpf_fentry_test5", test5, } __u64 test6_result = 0; -BPF_TRACE_6("fentry/bpf_fentry_test6", test6, - __u64, a, void *, b, short, c, int, d, void *, e, __u64, f) +SEC("fentry/bpf_fentry_test6") +int BPF_PROG(test6, __u64 a, void *b, short c, int d, void * e, __u64 f) { test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && e == (void *)20 && f == 21; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c index 2d211ee98a1c..c329fccf9842 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c @@ -1,7 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#include <linux/stddef.h> +#include <linux/ipv6.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "bpf_trace_helpers.h" struct sk_buff { @@ -9,8 +12,8 @@ struct sk_buff { }; __u64 test_result = 0; -BPF_TRACE_2("fexit/test_pkt_access", test_main, - struct sk_buff *, skb, int, ret) +SEC("fexit/test_pkt_access") +int BPF_PROG(test_main, struct sk_buff *skb, int ret) { int len; @@ -24,8 +27,8 @@ BPF_TRACE_2("fexit/test_pkt_access", test_main, } __u64 test_result_subprog1 = 0; -BPF_TRACE_2("fexit/test_pkt_access_subprog1", test_subprog1, - struct sk_buff *, skb, int, ret) +SEC("fexit/test_pkt_access_subprog1") +int BPF_PROG(test_subprog1, struct sk_buff *skb, int ret) { int len; @@ -79,4 +82,73 @@ int test_subprog2(struct args_subprog2 *ctx) test_result_subprog2 = 1; return 0; } + +__u64 test_result_subprog3 = 0; +SEC("fexit/test_pkt_access_subprog3") +int BPF_PROG(test_subprog3, int val, struct sk_buff *skb, int ret) +{ + int len; + + __builtin_preserve_access_index(({ + len = skb->len; + })); + if (len != 74 || ret != 74 * val || val != 3) + return 0; + test_result_subprog3 = 1; + return 0; +} + +__u64 test_get_skb_len = 0; +SEC("freplace/get_skb_len") +int new_get_skb_len(struct __sk_buff *skb) +{ + int len = skb->len; + + if (len != 74) + return 0; + test_get_skb_len = 1; + return 74; /* original get_skb_len() returns skb->len */ +} + +__u64 test_get_skb_ifindex = 0; +SEC("freplace/get_skb_ifindex") +int new_get_skb_ifindex(int val, struct __sk_buff *skb, int var) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ipv6hdr ip6, *ip6p; + int ifindex = skb->ifindex; + __u32 eth_proto; + __u32 nh_off; + + /* check that BPF extension can read packet via direct packet access */ + if (data + 14 + sizeof(ip6) > data_end) + return 0; + ip6p = data + 14; + + if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123)) + return 0; + + /* check that legacy packet access helper works too */ + if (bpf_skb_load_bytes(skb, 14, &ip6, sizeof(ip6)) < 0) + return 0; + ip6p = &ip6; + if (ip6p->nexthdr != 6 || ip6p->payload_len != __bpf_constant_htons(123)) + return 0; + + if (ifindex != 1 || val != 3 || var != 1) + return 0; + test_get_skb_ifindex = 1; + return 3; /* original get_skb_ifindex() returns val * ifindex * var */ +} + +volatile __u64 test_get_constant = 0; +SEC("freplace/get_constant") +int new_get_constant(long val) +{ + if (val != 123) + return 0; + test_get_constant = 1; + return test_get_constant; /* original get_constant() returns val - 122 */ +} char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c index ebc0ab7f0f5c..92f3fa47cf40 100644 --- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c +++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf_simple.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_trace_helpers.h" struct sk_buff { @@ -9,8 +9,9 @@ struct sk_buff { }; __u64 test_result = 0; -BPF_TRACE_2("fexit/test_pkt_md_access", test_main2, - struct sk_buff *, skb, int, ret) + +SEC("fexit/test_pkt_md_access") +int BPF_PROG(test_main2, struct sk_buff *skb, int ret) { int len; diff --git a/tools/testing/selftests/bpf/progs/fexit_test.c b/tools/testing/selftests/bpf/progs/fexit_test.c index 86db0d60fb6e..348109b9ea07 100644 --- a/tools/testing/selftests/bpf/progs/fexit_test.c +++ b/tools/testing/selftests/bpf/progs/fexit_test.c @@ -1,45 +1,47 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_trace_helpers.h" char _license[] SEC("license") = "GPL"; __u64 test1_result = 0; -BPF_TRACE_2("fexit/bpf_fentry_test1", test1, int, a, int, ret) +SEC("fexit/bpf_fentry_test1") +int BPF_PROG(test1, int a, int ret) { test1_result = a == 1 && ret == 2; return 0; } __u64 test2_result = 0; -BPF_TRACE_3("fexit/bpf_fentry_test2", test2, int, a, __u64, b, int, ret) +SEC("fexit/bpf_fentry_test2") +int BPF_PROG(test2, int a, __u64 b, int ret) { test2_result = a == 2 && b == 3 && ret == 5; return 0; } __u64 test3_result = 0; -BPF_TRACE_4("fexit/bpf_fentry_test3", test3, char, a, int, b, __u64, c, int, ret) +SEC("fexit/bpf_fentry_test3") +int BPF_PROG(test3, char a, int b, __u64 c, int ret) { test3_result = a == 4 && b == 5 && c == 6 && ret == 15; return 0; } __u64 test4_result = 0; -BPF_TRACE_5("fexit/bpf_fentry_test4", test4, - void *, a, char, b, int, c, __u64, d, int, ret) +SEC("fexit/bpf_fentry_test4") +int BPF_PROG(test4, void *a, char b, int c, __u64 d, int ret) { - test4_result = a == (void *)7 && b == 8 && c == 9 && d == 10 && ret == 34; return 0; } __u64 test5_result = 0; -BPF_TRACE_6("fexit/bpf_fentry_test5", test5, - __u64, a, void *, b, short, c, int, d, __u64, e, int, ret) +SEC("fexit/bpf_fentry_test5") +int BPF_PROG(test5, __u64 a, void *b, short c, int d, __u64 e, int ret) { test5_result = a == 11 && b == (void *)12 && c == 13 && d == 14 && e == 15 && ret == 65; @@ -47,9 +49,8 @@ BPF_TRACE_6("fexit/bpf_fentry_test5", test5, } __u64 test6_result = 0; -BPF_TRACE_7("fexit/bpf_fentry_test6", test6, - __u64, a, void *, b, short, c, int, d, void *, e, __u64, f, - int, ret) +SEC("fexit/bpf_fentry_test6") +int BPF_PROG(test6, __u64 a, void *b, short c, int d, void *e, __u64 f, int ret) { test6_result = a == 16 && b == (void *)17 && c == 18 && d == 19 && e == (void *)20 && f == 21 && ret == 111; diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c index 16c54ade6888..6b42db2fe391 100644 --- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c @@ -2,7 +2,7 @@ // Copyright (c) 2018 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index 974d6f3bb319..8f48a909f079 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -2,8 +2,8 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include <stdbool.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "bpf_trace_helpers.h" char _license[] SEC("license") = "GPL"; @@ -57,8 +57,8 @@ struct meta { /* TRACE_EVENT(kfree_skb, * TP_PROTO(struct sk_buff *skb, void *location), */ -BPF_TRACE_2("tp_btf/kfree_skb", trace_kfree_skb, - struct sk_buff *, skb, void *, location) +SEC("tp_btf/kfree_skb") +int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location) { struct net_device *dev; struct callback_head *ptr; @@ -114,9 +114,9 @@ static volatile struct { bool fexit_test_ok; } result; -BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans, - struct sk_buff *, skb, struct net_device *, dev, - unsigned short, protocol) +SEC("fentry/eth_type_trans") +int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev, + unsigned short protocol) { int len, ifindex; @@ -132,9 +132,9 @@ BPF_TRACE_3("fentry/eth_type_trans", fentry_eth_type_trans, return 0; } -BPF_TRACE_3("fexit/eth_type_trans", fexit_eth_type_trans, - struct sk_buff *, skb, struct net_device *, dev, - unsigned short, protocol) +SEC("fexit/eth_type_trans") +int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, struct net_device *dev, + unsigned short protocol) { int len, ifindex; diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c index 40ac722a9da5..50e66772c046 100644 --- a/tools/testing/selftests/bpf/progs/loop1.c +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -6,8 +6,8 @@ #include <stddef.h> #include <stdbool.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c index bb80f29aa7f7..947bb7e988c2 100644 --- a/tools/testing/selftests/bpf/progs/loop2.c +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -6,8 +6,8 @@ #include <stddef.h> #include <stdbool.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c index 2b9165a7afe1..76e93b31c14b 100644 --- a/tools/testing/selftests/bpf/progs/loop3.c +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -6,8 +6,8 @@ #include <stddef.h> #include <stdbool.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c index 650859022771..b35337926d66 100644 --- a/tools/testing/selftests/bpf/progs/loop4.c +++ b/tools/testing/selftests/bpf/progs/loop4.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/loop5.c b/tools/testing/selftests/bpf/progs/loop5.c index 28d1d668f07c..913791923fa3 100644 --- a/tools/testing/selftests/bpf/progs/loop5.c +++ b/tools/testing/selftests/bpf/progs/loop5.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define barrier() __asm__ __volatile__("": : :"memory") char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c index 38a997852cad..d071adf178bd 100644 --- a/tools/testing/selftests/bpf/progs/netcnt_prog.c +++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c @@ -2,7 +2,7 @@ #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "netcnt_common.h" #define MAX_BPS (3 * 1024 * 1024) diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h index 71d383cc9b85..cc615b82b56e 100644 --- a/tools/testing/selftests/bpf/progs/pyperf.h +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -6,7 +6,7 @@ #include <stddef.h> #include <stdbool.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define FUNCTION_NAME_LEN 64 #define FILE_NAME_LEN 128 @@ -154,7 +154,12 @@ struct { __uint(value_size, sizeof(long long) * 127); } stackmap SEC(".maps"); -static __always_inline int __on_event(struct pt_regs *ctx) +#ifdef GLOBAL_FUNC +__attribute__((noinline)) +#else +static __always_inline +#endif +int __on_event(struct bpf_raw_tracepoint_args *ctx) { uint64_t pid_tgid = bpf_get_current_pid_tgid(); pid_t pid = (pid_t)(pid_tgid >> 32); @@ -254,7 +259,7 @@ static __always_inline int __on_event(struct pt_regs *ctx) } SEC("raw_tracepoint/kfree_skb") -int on_event(struct pt_regs* ctx) +int on_event(struct bpf_raw_tracepoint_args* ctx) { int i, ret = 0; ret |= __on_event(ctx); diff --git a/tools/testing/selftests/bpf/progs/pyperf_global.c b/tools/testing/selftests/bpf/progs/pyperf_global.c new file mode 100644 index 000000000000..079e78a7562b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf_global.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#define STACK_MAX_LEN 50 +#define GLOBAL_FUNC +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c index 0756303676ac..1612a32007b6 100644 --- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c +++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct bpf_map_def SEC("maps") htab = { .type = BPF_MAP_TYPE_HASH, diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c index a91536b1c47e..092d9da536f3 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c @@ -5,8 +5,8 @@ #include <linux/bpf.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define SRC1_IP4 0xAC100001U /* 172.16.0.1 */ #define SRC2_IP4 0x00000000U diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c index a68062820410..255a432bc163 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c @@ -5,8 +5,8 @@ #include <linux/bpf.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define SRC_REWRITE_IP6_0 0 #define SRC_REWRITE_IP6_1 0 diff --git a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c index e4440fdd94cb..0cb5656a22b0 100644 --- a/tools/testing/selftests/bpf/progs/socket_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c @@ -4,8 +4,8 @@ #include <linux/bpf.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> struct socket_cookie { __u64 cookie_key; diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index 9390e0244259..a5c6d5903b22 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -1,6 +1,6 @@ #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c index e80484d98a1a..fdb4bf4408fa 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c @@ -1,7 +1,7 @@ #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index 433e23918a62..4797dc985064 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -1,6 +1,6 @@ #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c index dede0fcd6102..c6d428a8d785 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 4afd2595c08e..9d8c212dde9f 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <netinet/in.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 1bafbb944e37..d5a5eeb5fb52 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -3,7 +3,7 @@ #include <netinet/in.h> #include <netinet/tcp.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index 4bf16e0a1b0e..ad61b722a9de 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -8,7 +8,7 @@ #include <linux/ptrace.h> #include <linux/sched.h> #include <linux/types.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> typedef uint32_t pid_t; struct task_struct {}; diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c index 63531e1a9fa4..1f407e65ae52 100644 --- a/tools/testing/selftests/bpf/progs/tailcall1.c +++ b/tools/testing/selftests/bpf/progs/tailcall1.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c index 21c85c477210..a093e739cf0e 100644 --- a/tools/testing/selftests/bpf/progs/tailcall2.c +++ b/tools/testing/selftests/bpf/progs/tailcall2.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c index 1ecae198b8c1..cabda877cf0a 100644 --- a/tools/testing/selftests/bpf/progs/tailcall3.c +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c index 499388758119..f82075b47d7d 100644 --- a/tools/testing/selftests/bpf/progs/tailcall4.c +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c index 49c64eb53f19..ce5450744fd4 100644 --- a/tools/testing/selftests/bpf/progs/tailcall5.c +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c index 2cf813a06b83..0cb3204ddb18 100644 --- a/tools/testing/selftests/bpf/progs/tcp_rtt.c +++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; __u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_adjust_tail.c index 4cd5e860c903..b7fc85769bdc 100644 --- a/tools/testing/selftests/bpf/progs/test_adjust_tail.c +++ b/tools/testing/selftests/bpf/progs/test_adjust_tail.c @@ -7,7 +7,7 @@ */ #include <linux/bpf.h> #include <linux/if_ether.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c index 534621e38906..dd8fae6660ab 100644 --- a/tools/testing/selftests/bpf/progs/test_attach_probe.c +++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c @@ -3,48 +3,38 @@ #include <linux/ptrace.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 4); - __type(key, int); - __type(value, int); -} results_map SEC(".maps"); +int kprobe_res = 0; +int kretprobe_res = 0; +int uprobe_res = 0; +int uretprobe_res = 0; SEC("kprobe/sys_nanosleep") -int handle_sys_nanosleep_entry(struct pt_regs *ctx) +int handle_kprobe(struct pt_regs *ctx) { - const int key = 0, value = 1; - - bpf_map_update_elem(&results_map, &key, &value, 0); + kprobe_res = 1; return 0; } SEC("kretprobe/sys_nanosleep") -int handle_sys_getpid_return(struct pt_regs *ctx) +int handle_kretprobe(struct pt_regs *ctx) { - const int key = 1, value = 2; - - bpf_map_update_elem(&results_map, &key, &value, 0); + kretprobe_res = 2; return 0; } SEC("uprobe/trigger_func") -int handle_uprobe_entry(struct pt_regs *ctx) +int handle_uprobe(struct pt_regs *ctx) { - const int key = 2, value = 3; - - bpf_map_update_elem(&results_map, &key, &value, 0); + uprobe_res = 3; return 0; } SEC("uretprobe/trigger_func") -int handle_uprobe_return(struct pt_regs *ctx) +int handle_uretprobe(struct pt_regs *ctx) { - const int key = 3, value = 4; - - bpf_map_update_elem(&results_map, &key, &value, 0); + uretprobe_res = 4; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index 62ad7e22105e..88b0566da13d 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2018 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_legacy.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c index fb8d91a1dbe0..a924e53c8e9d 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2018 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "bpf_legacy.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 3f4422044759..983aedd1c072 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2018 Facebook */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_core_extern.c b/tools/testing/selftests/bpf/progs/test_core_extern.c new file mode 100644 index 000000000000..3ac3603ad53d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_extern.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdint.h> +#include <stdbool.h> +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* non-existing BPF helper, to test dead code elimination */ +static int (*bpf_missing_helper)(const void *arg1, int arg2) = (void *) 999; + +extern int LINUX_KERNEL_VERSION __kconfig; +extern bool CONFIG_BPF_SYSCALL __kconfig; /* strong */ +extern enum libbpf_tristate CONFIG_TRISTATE __kconfig __weak; +extern bool CONFIG_BOOL __kconfig __weak; +extern char CONFIG_CHAR __kconfig __weak; +extern uint16_t CONFIG_USHORT __kconfig __weak; +extern int CONFIG_INT __kconfig __weak; +extern uint64_t CONFIG_ULONG __kconfig __weak; +extern const char CONFIG_STR[8] __kconfig __weak; +extern uint64_t CONFIG_MISSING __kconfig __weak; + +uint64_t kern_ver = -1; +uint64_t bpf_syscall = -1; +uint64_t tristate_val = -1; +uint64_t bool_val = -1; +uint64_t char_val = -1; +uint64_t ushort_val = -1; +uint64_t int_val = -1; +uint64_t ulong_val = -1; +char str_val[8] = {-1, -1, -1, -1, -1, -1, -1, -1}; +uint64_t missing_val = -1; + +SEC("raw_tp/sys_enter") +int handle_sys_enter(struct pt_regs *ctx) +{ + int i; + + kern_ver = LINUX_KERNEL_VERSION; + bpf_syscall = CONFIG_BPF_SYSCALL; + tristate_val = CONFIG_TRISTATE; + bool_val = CONFIG_BOOL; + char_val = CONFIG_CHAR; + ushort_val = CONFIG_USHORT; + int_val = CONFIG_INT; + ulong_val = CONFIG_ULONG; + + for (i = 0; i < sizeof(CONFIG_STR); i++) { + str_val[i] = CONFIG_STR[i]; + } + + if (CONFIG_MISSING) + /* invalid, but dead code - never executed */ + missing_val = bpf_missing_helper(ctx, 123); + else + missing_val = 0xDEADC0DE; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c index 89951b684282..51b3f79df523 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; @@ -18,6 +18,7 @@ struct core_reloc_arrays_output { char b123; int c1c; int d00d; + int f01c; }; struct core_reloc_arrays_substruct { @@ -30,6 +31,7 @@ struct core_reloc_arrays { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; #define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) @@ -40,18 +42,16 @@ int test_core_arrays(void *ctx) struct core_reloc_arrays *in = (void *)&data.in; struct core_reloc_arrays_output *out = (void *)&data.out; - /* in->a[2] */ if (CORE_READ(&out->a2, &in->a[2])) return 1; - /* in->b[1][2][3] */ if (CORE_READ(&out->b123, &in->b[1][2][3])) return 1; - /* in->c[1].c */ if (CORE_READ(&out->c1c, &in->c[1].c)) return 1; - /* in->d[0][0].d */ if (CORE_READ(&out->d00d, &in->d[0][0].d)) return 1; + if (CORE_READ(&out->f01c, &in->f[0][1].c)) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c index edc0f7c9e56d..56aec20212b5 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_direct.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c index 6c20e433558b..ab1e647aeb31 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c index 1b7f0ae49cfb..7e45e2bdf6cd 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_existence.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c index b5dbeef540fd..525acc2f841b 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_flavors.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c index c78ab6d28a14..6b5290739806 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ints.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c index 270de441b60a..aba928fd60d3 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c index 292a5c4ee76a..d5756dbdef82 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_misc.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c index 0b28bfacc8fd..8b533db4a7a5 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c index 39279bf0c9db..2b4b6d49c677 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_nesting.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c index ea57973cdd19..2a8975678aa6 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_primitives.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c index d1eb59d4ea64..ca61a5183b88 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_ptr_as_arr.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c index 9e091124d3bd..d7fb6cfc7891 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_size.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_size.c @@ -3,8 +3,8 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" -#include "bpf_core_read.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index 6a4a8f57f174..29817a703984 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* Permit pretty deep stack traces */ #define MAX_STACK_RAWTP 100 diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 32a6073acb99..dd7a4d3dbc0d 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -5,7 +5,7 @@ #include <linux/pkt_cls.h> #include <string.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c new file mode 100644 index 000000000000..880260f6d536 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#ifndef MAX_STACK +#define MAX_STACK (512 - 3 * 32 + 8) +#endif + +static __attribute__ ((noinline)) +int f0(int var, struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + volatile char buf[MAX_STACK] = {}; + + return f0(0, skb) + skb->len; +} + +int f3(int, struct __sk_buff *skb, int); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, skb, 1); +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + volatile char buf[MAX_STACK] = {}; + + return skb->ifindex * val * var; +} + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ + return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func2.c b/tools/testing/selftests/bpf/progs/test_global_func2.c new file mode 100644 index 000000000000..2c18d82923a2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func2.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#define MAX_STACK (512 - 3 * 32) +#include "test_global_func1.c" diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c new file mode 100644 index 000000000000..86f0ecb304fc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func3.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + val; +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb, int var) +{ + return f2(var, skb) + val; +} + +__attribute__ ((noinline)) +int f4(struct __sk_buff *skb) +{ + return f3(1, skb, 2); +} + +__attribute__ ((noinline)) +int f5(struct __sk_buff *skb) +{ + return f4(skb); +} + +__attribute__ ((noinline)) +int f6(struct __sk_buff *skb) +{ + return f5(skb); +} + +__attribute__ ((noinline)) +int f7(struct __sk_buff *skb) +{ + return f6(skb); +} + +#ifndef NO_FN8 +__attribute__ ((noinline)) +int f8(struct __sk_buff *skb) +{ + return f7(skb); +} +#endif + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ +#ifndef NO_FN8 + return f8(skb); +#else + return f7(skb); +#endif +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func4.c b/tools/testing/selftests/bpf/progs/test_global_func4.c new file mode 100644 index 000000000000..610f75edf276 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func4.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#define NO_FN8 +#include "test_global_func3.c" diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c new file mode 100644 index 000000000000..260c25b827ef --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +int f3(int, struct __sk_buff *skb); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, (void *)&val); /* type mismatch */ +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb) +{ + return skb->ifindex * val; +} + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ + return f1(skb) + f2(2, skb) + f3(3, skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c new file mode 100644 index 000000000000..69e19c64e10b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func6.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__attribute__ ((noinline)) +int f1(struct __sk_buff *skb) +{ + return skb->len; +} + +int f3(int, struct __sk_buff *skb); + +__attribute__ ((noinline)) +int f2(int val, struct __sk_buff *skb) +{ + return f1(skb) + f3(val, skb + 1); /* type mismatch */ +} + +__attribute__ ((noinline)) +int f3(int val, struct __sk_buff *skb) +{ + return skb->ifindex * val; +} + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ + return f1(skb) + f2(2, skb) + f3(3, skb); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c new file mode 100644 index 000000000000..309b3f6136bd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_func7.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ +#include <stddef.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__attribute__ ((noinline)) +void foo(struct __sk_buff *skb) +{ + skb->tc_index = 0; +} + +SEC("classifier/test") +int test_cls(struct __sk_buff *skb) +{ + foo(skb); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c index 1d652ee8e73d..33493911d87a 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb.c @@ -17,9 +17,9 @@ #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "test_iptunnel_common.h" -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c index 2e4efe70b1e5..28351936a438 100644 --- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c @@ -13,9 +13,9 @@ #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #include "test_iptunnel_common.h" -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c index 4147130cc3b7..7a6620671a83 100644 --- a/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c +++ b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c @@ -5,7 +5,7 @@ #include <linux/bpf.h> #include <linux/lirc.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("lirc_mode2") int bpf_decoder(unsigned int *sample) diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c index c957d6dfe6d7..d6cb986e7533 100644 --- a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c @@ -4,8 +4,8 @@ #include <linux/bpf.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> struct grehdr { __be16 flags; diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c index 41a3ebcd593d..48ff2b2ad5e7 100644 --- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c @@ -3,8 +3,8 @@ #include <errno.h> #include <linux/seg6_local.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* Packet parsing state machine helpers. */ #define cursor_advance(_cursor, _len) \ diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index 113226115365..1cfeb940cf9f 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -3,7 +3,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <linux/types.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c index bb7ce35f691b..b5c07ae7b68f 100644 --- a/tools/testing/selftests/bpf/progs/test_map_lock.c +++ b/tools/testing/selftests/bpf/progs/test_map_lock.c @@ -2,7 +2,7 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define VAR_NUM 16 diff --git a/tools/testing/selftests/bpf/progs/test_mmap.c b/tools/testing/selftests/bpf/progs/test_mmap.c index e808791b7047..6239596cd14e 100644 --- a/tools/testing/selftests/bpf/progs/test_mmap.c +++ b/tools/testing/selftests/bpf/progs/test_mmap.c @@ -3,7 +3,7 @@ #include <linux/bpf.h> #include <stdint.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c index 3d30c02bdae9..98b9de2fafd0 100644 --- a/tools/testing/selftests/bpf/progs/test_obj_id.c +++ b/tools/testing/selftests/bpf/progs/test_obj_id.c @@ -4,7 +4,7 @@ #include <stddef.h> #include <linux/bpf.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* It is a dumb bpf program such that it must have no * issue to be loaded since testing the verifier is diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index 96c0124a04ba..bfe9fbcb9684 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -1,39 +1,45 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#include <stdbool.h> +#include <stddef.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <linux/ptrace.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #include "bpf_trace_helpers.h" +struct task_struct; + SEC("kprobe/__set_task_comm") -int prog1(struct pt_regs *ctx) +int BPF_KPROBE(prog1, struct task_struct *tsk, const char *buf, bool exec) { - return 0; + return !tsk; } SEC("kretprobe/__set_task_comm") -int prog2(struct pt_regs *ctx) +int BPF_KRETPROBE(prog2, + struct task_struct *tsk, const char *buf, bool exec, + int ret) { - return 0; + return !PT_REGS_PARM1(ctx) && ret; } SEC("raw_tp/task_rename") int prog3(struct bpf_raw_tracepoint_args *ctx) { - return 0; + return !ctx->args[0]; } -struct task_struct; -BPF_TRACE_3("fentry/__set_task_comm", prog4, - struct task_struct *, tsk, const char *, buf, __u8, exec) +SEC("fentry/__set_task_comm") +int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec) { - return 0; + return !tsk; } -BPF_TRACE_3("fexit/__set_task_comm", prog5, - struct task_struct *, tsk, const char *, buf, __u8, exec) +SEC("fexit/__set_task_comm") +int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec) { - return 0; + return !tsk; } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c index 07c09ca5546a..ebfcc9f50c35 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -3,7 +3,8 @@ #include <linux/ptrace.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> +#include "bpf_trace_helpers.h" struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -12,7 +13,7 @@ struct { } perf_buf_map SEC(".maps"); SEC("kprobe/sys_nanosleep") -int handle_sys_nanosleep_entry(struct pt_regs *ctx) +int BPF_KPROBE(handle_sys_nanosleep_entry) { int cpu = bpf_get_smp_processor_id(); diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c index f20e7e00373f..4ef2630292b2 100644 --- a/tools/testing/selftests/bpf/progs/test_pinning.c +++ b/tools/testing/selftests/bpf/progs/test_pinning.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c index 51b38abe7ba1..5412e0c732c7 100644 --- a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c +++ b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index 3a7b4b607ed3..e72eba4a93d2 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -11,8 +11,8 @@ #include <linux/in.h> #include <linux/tcp.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define barrier() __asm__ __volatile__("": : :"memory") int _version SEC("version") = 1; @@ -47,6 +47,38 @@ int test_pkt_access_subprog2(int val, volatile struct __sk_buff *skb) return skb->len * val; } +#define MAX_STACK (512 - 2 * 32) + +__attribute__ ((noinline)) +int get_skb_len(struct __sk_buff *skb) +{ + volatile char buf[MAX_STACK] = {}; + + return skb->len; +} + +__attribute__ ((noinline)) +int get_constant(long val) +{ + return val - 122; +} + +int get_skb_ifindex(int, struct __sk_buff *skb, int); + +__attribute__ ((noinline)) +int test_pkt_access_subprog3(int val, struct __sk_buff *skb) +{ + return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); +} + +__attribute__ ((noinline)) +int get_skb_ifindex(int val, struct __sk_buff *skb, int var) +{ + volatile char buf[MAX_STACK] = {}; + + return skb->ifindex * val * var; +} + SEC("classifier/test_pkt_access") int test_pkt_access(struct __sk_buff *skb) { @@ -82,6 +114,8 @@ int test_pkt_access(struct __sk_buff *skb) return TC_ACT_SHOT; if (test_pkt_access_subprog2(2, skb) != skb->len * 2) return TC_ACT_SHOT; + if (test_pkt_access_subprog3(3, skb) != skb->len * 3 * skb->ifindex) + return TC_ACT_SHOT; if (tcp) { if (((void *)(tcp) + 20) > data_end || proto != 6) return TC_ACT_SHOT; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c index 1db2623021ad..610c74ea9f64 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c @@ -5,7 +5,7 @@ #include <string.h> #include <linux/bpf.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 1871e2ece0c4..d556b1572cc6 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -5,13 +5,14 @@ #include <netinet/in.h> -#include "bpf_helpers.h" -#include "bpf_tracing.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_trace_helpers.h" static struct sockaddr_in old; SEC("kprobe/__sys_connect") -int handle_sys_connect(struct pt_regs *ctx) +int BPF_KPROBE(handle_sys_connect) { void *ptr = (void *)PT_REGS_PARM2(ctx); struct sockaddr_in new; diff --git a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h index 0e014d3b2b36..4dd9806ad73b 100644 --- a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h +++ b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h @@ -6,7 +6,7 @@ #include <linux/if_ether.h> #include <linux/ip.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c index 52d94e8b214d..ecbeea2df259 100644 --- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c +++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c @@ -3,7 +3,7 @@ #include <linux/ptrace.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> static volatile const struct { unsigned a[4]; diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c index 69880c1e7700..a7278f064368 100644 --- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -3,8 +3,8 @@ #include <errno.h> #include <linux/seg6_local.h> #include <linux/bpf.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* Packet parsing state machine helpers. */ #define cursor_advance(_cursor, _len) \ diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index ea7d84f01235..26e77dcc7e91 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -11,8 +11,8 @@ #include <linux/types.h> #include <linux/if_ether.h> -#include "bpf_endian.h" -#include "bpf_helpers.h" +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> #include "test_select_reuseport_common.h" int _version SEC("version") = 1; @@ -62,7 +62,7 @@ struct { goto done; \ }) -SEC("select_by_skb_data") +SEC("sk_reuseport") int _select_by_skb_data(struct sk_reuseport_md *reuse_md) { __u32 linum, index = 0, flags = 0, index_zero = 0; @@ -113,6 +113,12 @@ int _select_by_skb_data(struct sk_reuseport_md *reuse_md) data_check.skb_ports[0] = th->source; data_check.skb_ports[1] = th->dest; + if (th->fin) + /* The connection is being torn down at the end of a + * test. It can't contain a cmd, so return early. + */ + return SK_PASS; + if ((th->doff << 2) + sizeof(*cmd) > data_check.len) GOTO_DONE(DROP_ERR_SKB_DATA); if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy, diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c index 0e6be01157e6..1acc91e87bfc 100644 --- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -2,46 +2,39 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" - -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); - __type(key, __u32); - __type(value, __u64); -} info_map SEC(".maps"); - -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); - __type(key, __u32); - __type(value, __u64); -} status_map SEC(".maps"); - -SEC("send_signal_demo") -int bpf_send_signal_test(void *ctx) +#include <bpf/bpf_helpers.h> + +__u32 sig = 0, pid = 0, status = 0, signal_thread = 0; + +static __always_inline int bpf_send_signal_test(void *ctx) { - __u64 *info_val, *status_val; - __u32 key = 0, pid, sig; int ret; - status_val = bpf_map_lookup_elem(&status_map, &key); - if (!status_val || *status_val != 0) - return 0; - - info_val = bpf_map_lookup_elem(&info_map, &key); - if (!info_val || *info_val == 0) + if (status != 0 || sig == 0 || pid == 0) return 0; - sig = *info_val >> 32; - pid = *info_val & 0xffffFFFF; - if ((bpf_get_current_pid_tgid() >> 32) == pid) { - ret = bpf_send_signal(sig); + if (signal_thread) + ret = bpf_send_signal_thread(sig); + else + ret = bpf_send_signal(sig); if (ret == 0) - *status_val = 1; + status = 1; } return 0; } + +SEC("tracepoint/syscalls/sys_enter_nanosleep") +int send_signal_tp(void *ctx) +{ + return bpf_send_signal_test(ctx); +} + +SEC("perf_event") +int send_signal_perf(void *ctx) +{ + return bpf_send_signal_test(ctx); +} + char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c index cb49ccb707d1..d2b38fa6a5b0 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c @@ -12,8 +12,8 @@ #include <linux/pkt_cls.h> #include <linux/tcp.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c index 68cf9829f5a7..552f2090665c 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c @@ -6,7 +6,7 @@ #include <string.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define NUM_CGROUP_LEVELS 4 diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c index 2a9f4c736ebc..202de3938494 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; @@ -17,6 +17,12 @@ int process(struct __sk_buff *skb) } skb->priority++; skb->tstamp++; + skb->mark++; + + if (skb->wire_len != 100) + return 1; + if (skb->gso_segs != 8) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c new file mode 100644 index 000000000000..de03a90f78ca --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct s { + int a; + long long b; +} __attribute__((packed)); + +int in1 = 0; +long long in2 = 0; +char in3 = '\0'; +long long in4 __attribute__((aligned(64))) = 0; +struct s in5 = {}; + +long long out2 = 0; +char out3 = 0; +long long out4 = 0; +int out1 = 0; + +extern bool CONFIG_BPF_SYSCALL __kconfig; +extern int LINUX_KERNEL_VERSION __kconfig; +bool bpf_syscall = 0; +int kern_ver = 0; + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + static volatile struct s out5; + + out1 = in1; + out2 = in2; + out3 = in3; + out4 = in4; + out5 = in5; + + bpf_syscall = CONFIG_BPF_SYSCALL; + kern_ver = LINUX_KERNEL_VERSION; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c index a47b003623ef..9bcaa37f476a 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -5,8 +5,8 @@ #include <netinet/in.h> #include <stdbool.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> enum bpf_addr_array_idx { ADDR_SRV_IDX, diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c index a43b999c8da2..0d31a3b3505f 100644 --- a/tools/testing/selftests/bpf/progs/test_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -2,7 +2,7 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include <linux/version.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct hmap_elem { volatile int cnt; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index f5638e26865d..0cf0134631b4 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -2,7 +2,7 @@ // Copyright (c) 2018 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #ifndef PERF_MAX_STACK_DEPTH #define PERF_MAX_STACK_DEPTH 127 diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index 3b7e1dca8829..00ed48672620 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -2,7 +2,7 @@ // Copyright (c) 2018 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #ifndef PERF_MAX_STACK_DEPTH #define PERF_MAX_STACK_DEPTH 127 diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c index d22e438198cf..458b0d69133e 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c @@ -7,7 +7,7 @@ #include <linux/stddef.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #ifndef ARRAY_SIZE #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c index cb201cbe11e7..b2e6f9b0894d 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c @@ -7,7 +7,7 @@ #include <linux/stddef.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #ifndef ARRAY_SIZE #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c index 5cbbff416998..2d0b0b82a78a 100644 --- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -7,7 +7,7 @@ #include <linux/stddef.h> #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */ #define MAX_ULONG_STR_LEN 0xF diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c index 0961415ba477..bf28814bfde5 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_edt.c +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -7,8 +7,8 @@ #include <linux/ip.h> #include <linux/pkt_cls.h> #include <linux/tcp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* the maximum delay we are willing to add (drop packets beyond that) */ #define TIME_HORIZON_NS (2000 * 1000 * 1000) diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index 74370e7e286d..37bce7a7c394 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -17,8 +17,8 @@ #include <linux/pkt_cls.h> #include <linux/types.h> -#include "bpf_endian.h" -#include "bpf_helpers.h" +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> static const int cfg_port = 8000; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index d8803dfa8d32..47cbe2eeae43 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -13,8 +13,8 @@ #include <sys/socket.h> #include <linux/tcp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> struct bpf_map_def SEC("maps") results = { .type = BPF_MAP_TYPE_ARRAY, diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c index 87b7d934ce73..adc83a54c352 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c @@ -36,7 +36,7 @@ #include <linux/ipv6.h> #include <linux/version.h> #include <sys/socket.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define _(P) ({typeof(P) val = 0; bpf_probe_read_kernel(&val, sizeof(val), &P); val;}) #define TCP_ESTATS_MAGIC 0xBAADBEEF diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 7fa4595d2b66..1f1966e86e9f 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -10,8 +10,8 @@ #include <linux/types.h> #include <linux/socket.h> #include <linux/tcp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "test_tcpbpf.h" struct { diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index 08346e7765d5..ac63410bb541 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -10,8 +10,8 @@ #include <linux/types.h> #include <linux/socket.h> #include <linux/tcp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "test_tcpnotify.h" struct { diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c index 04bf084517e0..4b825ee122cf 100644 --- a/tools/testing/selftests/bpf/progs/test_tracepoint.c +++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c @@ -2,7 +2,7 @@ // Copyright (c) 2017 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { diff --git a/tools/testing/selftests/bpf/progs/test_trampoline_count.c b/tools/testing/selftests/bpf/progs/test_trampoline_count.c new file mode 100644 index 000000000000..e51e6e3a81c2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_trampoline_count.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdbool.h> +#include <stddef.h> +#include <linux/bpf.h> +#include "bpf_trace_helpers.h" + +struct task_struct; + +SEC("fentry/__set_task_comm") +int BPF_PROG(prog1, struct task_struct *tsk, const char *buf, bool exec) +{ + return 0; +} + +SEC("fexit/__set_task_comm") +int BPF_PROG(prog2, struct task_struct *tsk, const char *buf, bool exec) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 504df69c83df..f48dbfe24ddc 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -19,8 +19,8 @@ #include <linux/socket.h> #include <linux/pkt_cls.h> #include <linux/erspan.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #define ERROR(ret) do {\ char fmt[] = "ERROR line:%d ret:%d\n";\ diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c index f3236ce35f31..d38153dab3dd 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale1.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale1.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define ATTR __attribute__((noinline)) #include "test_jhash.h" diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c index 9897150ed516..f024154c7be7 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define ATTR __always_inline #include "test_jhash.h" diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c index 1848da04ea41..9beb5bf80373 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale3.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale3.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define ATTR __attribute__((noinline)) #include "test_jhash.h" diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 0941c655b07b..31f9bce37491 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -16,8 +16,8 @@ #include <linux/tcp.h> #include <linux/pkt_cls.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "test_iptunnel_common.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c new file mode 100644 index 000000000000..cb8a04ab7a78 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_trace_helpers.h" + +struct net_device { + /* Structure does not need to contain all entries, + * as "preserve_access_index" will use BTF to fix this... + */ + int ifindex; +} __attribute__((preserve_access_index)); + +struct xdp_rxq_info { + /* Structure does not need to contain all entries, + * as "preserve_access_index" will use BTF to fix this... + */ + struct net_device *dev; + __u32 queue_index; +} __attribute__((preserve_access_index)); + +struct xdp_buff { + void *data; + void *data_end; + void *data_meta; + void *data_hard_start; + unsigned long handle; + struct xdp_rxq_info *rxq; +} __attribute__((preserve_access_index)); + +__u64 test_result_fentry = 0; +SEC("fentry/_xdp_tx_iptunnel") +int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) +{ + test_result_fentry = xdp->rxq->dev->ifindex; + return 0; +} + +__u64 test_result_fexit = 0; +SEC("fexit/_xdp_tx_iptunnel") +int BPF_PROG(trace_on_exit, struct xdp_buff *xdp, int ret) +{ + test_result_fexit = ret; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c index 97175f73c3fe..fcabcda30ba3 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -12,8 +12,8 @@ #include <linux/tcp.h> #include <linux/pkt_cls.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "test_iptunnel_common.h" int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index 8d0182650653..a7c4a7d49fe6 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -2,7 +2,7 @@ #include <linux/if_ether.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> #define __round_mask(x, y) ((__typeof__(x))((y) - 1)) #define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index e88d7b9d65ab..8beecec166d9 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -13,8 +13,8 @@ #include <linux/icmpv6.h> #include <linux/tcp.h> #include <linux/udp.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> static __u32 rol32(__u32 word, unsigned int shift) { @@ -86,7 +86,7 @@ u32 jhash(const void *key, u32 length, u32 initval) return c; } -static __attribute__ ((noinline)) +__attribute__ ((noinline)) u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; @@ -96,7 +96,7 @@ u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) return c; } -static __attribute__ ((noinline)) +__attribute__ ((noinline)) u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c index ef9e704be140..a5337cd9400b 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c @@ -10,7 +10,7 @@ * General Public License for more details. */ #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c index 365a7d2d9f5c..134768f6b788 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c @@ -22,8 +22,8 @@ #include <linux/in.h> #include <linux/pkt_cls.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* linux/if_vlan.h have not exposed this as UAPI, thus mirror some here * diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c index 43b0ef1001ed..ea25e8881992 100644 --- a/tools/testing/selftests/bpf/progs/xdp_dummy.c +++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c @@ -2,7 +2,7 @@ #define KBUILD_MODNAME "xdp_dummy" #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("xdp_dummy") int xdp_dummy_prog(struct xdp_md *ctx) diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c index 1c5f298d7196..d037262c8937 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> struct { __uint(type, BPF_MAP_TYPE_DEVMAP); diff --git a/tools/testing/selftests/bpf/progs/xdp_tx.c b/tools/testing/selftests/bpf/progs/xdp_tx.c index 57912e7c94b0..94e6c2b281cb 100644 --- a/tools/testing/selftests/bpf/progs/xdp_tx.c +++ b/tools/testing/selftests/bpf/progs/xdp_tx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> -#include "bpf_helpers.h" +#include <bpf/bpf_helpers.h> SEC("tx") int xdp_tx(struct xdp_md *xdp) diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c index 112a2857f4e2..6b9ca40bd1f4 100644 --- a/tools/testing/selftests/bpf/progs/xdping_kern.c +++ b/tools/testing/selftests/bpf/progs/xdping_kern.c @@ -12,8 +12,8 @@ #include <linux/if_vlan.h> #include <linux/ip.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> #include "xdping.h" diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 3d617e806054..93040ca83e60 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -4148,10 +4148,6 @@ static int do_test_file(unsigned int test_num) if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj))) return PTR_ERR(obj); - err = bpf_object__btf_fd(obj); - if (CHECK(err == -1, "bpf_object__btf_fd: -1")) - goto done; - prog = bpf_program__next(NULL, obj); if (CHECK(!prog, "Cannot find bpf_prog")) { err = -1; diff --git a/tools/testing/selftests/bpf/test_cgroup_attach.c b/tools/testing/selftests/bpf/test_cgroup_attach.c deleted file mode 100644 index 7671909ee1cb..000000000000 --- a/tools/testing/selftests/bpf/test_cgroup_attach.c +++ /dev/null @@ -1,571 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -/* eBPF example program: - * - * - Creates arraymap in kernel with 4 bytes keys and 8 byte values - * - * - Loads eBPF program - * - * The eBPF program accesses the map passed in to store two pieces of - * information. The number of invocations of the program, which maps - * to the number of packets received, is stored to key 0. Key 1 is - * incremented on each iteration by the number of bytes stored in - * the skb. The program also stores the number of received bytes - * in the cgroup storage. - * - * - Attaches the new program to a cgroup using BPF_PROG_ATTACH - * - * - Every second, reads map[0] and map[1] to see how many bytes and - * packets were seen on any socket of tasks in the given cgroup. - */ - -#define _GNU_SOURCE - -#include <stdio.h> -#include <stdlib.h> -#include <assert.h> -#include <sys/resource.h> -#include <sys/time.h> -#include <unistd.h> -#include <linux/filter.h> - -#include <linux/bpf.h> -#include <bpf/bpf.h> - -#include "bpf_util.h" -#include "bpf_rlimit.h" -#include "cgroup_helpers.h" - -#define FOO "/foo" -#define BAR "/foo/bar/" -#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" - -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - -#ifdef DEBUG -#define debug(args...) printf(args) -#else -#define debug(args...) -#endif - -static int prog_load(int verdict) -{ - int ret; - struct bpf_insn prog[] = { - BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ - BPF_EXIT_INSN(), - }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); - - ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, - prog, insns_cnt, "GPL", 0, - bpf_log_buf, BPF_LOG_BUF_SIZE); - - if (ret < 0) { - log_err("Loading program"); - printf("Output from verifier:\n%s\n-------\n", bpf_log_buf); - return 0; - } - return ret; -} - -static int test_foo_bar(void) -{ - int drop_prog, allow_prog, foo = 0, bar = 0, rc = 0; - - allow_prog = prog_load(1); - if (!allow_prog) - goto err; - - drop_prog = prog_load(0); - if (!drop_prog) - goto err; - - if (setup_cgroup_environment()) - goto err; - - /* Create cgroup /foo, get fd, and join it */ - foo = create_and_get_cgroup(FOO); - if (foo < 0) - goto err; - - if (join_cgroup(FOO)) - goto err; - - if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo"); - goto err; - } - - debug("Attached DROP prog. This ping in cgroup /foo should fail...\n"); - assert(system(PING_CMD) != 0); - - /* Create cgroup /foo/bar, get fd, and join it */ - bar = create_and_get_cgroup(BAR); - if (bar < 0) - goto err; - - if (join_cgroup(BAR)) - goto err; - - debug("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n"); - assert(system(PING_CMD) != 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - debug("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n"); - assert(system(PING_CMD) == 0); - - if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo/bar"); - goto err; - } - - debug("Detached PASS from /foo/bar while DROP is attached to /foo.\n" - "This ping in cgroup /foo/bar should fail...\n"); - assert(system(PING_CMD) != 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - if (bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo"); - goto err; - } - - debug("Attached PASS from /foo/bar and detached DROP from /foo.\n" - "This ping in cgroup /foo/bar should pass...\n"); - assert(system(PING_CMD) == 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) { - errno = 0; - log_err("Unexpected success attaching prog to /foo/bar"); - goto err; - } - - if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo/bar"); - goto err; - } - - if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) { - errno = 0; - log_err("Unexpected success in double detach from /foo"); - goto err; - } - - if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching non-overridable prog to /foo"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) { - errno = 0; - log_err("Unexpected success attaching non-overridable prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - errno = 0; - log_err("Unexpected success attaching overridable prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - errno = 0; - log_err("Unexpected success attaching overridable prog to /foo"); - goto err; - } - - if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching different non-overridable prog to /foo"); - goto err; - } - - goto out; - -err: - rc = 1; - -out: - close(foo); - close(bar); - cleanup_cgroup_environment(); - if (!rc) - printf("#override:PASS\n"); - else - printf("#override:FAIL\n"); - return rc; -} - -static int map_fd = -1; - -static int prog_load_cnt(int verdict, int val) -{ - int cgroup_storage_fd, percpu_cgroup_storage_fd; - - if (map_fd < 0) - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); - if (map_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); - if (cgroup_storage_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - percpu_cgroup_storage_fd = bpf_create_map( - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); - if (percpu_cgroup_storage_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - struct bpf_insn prog[] = { - BPF_MOV32_IMM(BPF_REG_0, 0), - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ - BPF_LD_MAP_FD(BPF_REG_1, map_fd), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), - BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ - - BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd), - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), - BPF_MOV64_IMM(BPF_REG_1, val), - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0), - - BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd), - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), - BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), - BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), - - BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ - BPF_EXIT_INSN(), - }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); - int ret; - - ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, - prog, insns_cnt, "GPL", 0, - bpf_log_buf, BPF_LOG_BUF_SIZE); - - if (ret < 0) { - log_err("Loading program"); - printf("Output from verifier:\n%s\n-------\n", bpf_log_buf); - return 0; - } - close(cgroup_storage_fd); - return ret; -} - - -static int test_multiprog(void) -{ - __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id; - int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; - int drop_prog, allow_prog[6] = {}, rc = 0; - unsigned long long value; - int i = 0; - - for (i = 0; i < 6; i++) { - allow_prog[i] = prog_load_cnt(1, 1 << i); - if (!allow_prog[i]) - goto err; - } - drop_prog = prog_load_cnt(0, 1); - if (!drop_prog) - goto err; - - if (setup_cgroup_environment()) - goto err; - - cg1 = create_and_get_cgroup("/cg1"); - if (cg1 < 0) - goto err; - cg2 = create_and_get_cgroup("/cg1/cg2"); - if (cg2 < 0) - goto err; - cg3 = create_and_get_cgroup("/cg1/cg2/cg3"); - if (cg3 < 0) - goto err; - cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4"); - if (cg4 < 0) - goto err; - cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5"); - if (cg5 < 0) - goto err; - - if (join_cgroup("/cg1/cg2/cg3/cg4/cg5")) - goto err; - - if (bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog to cg1"); - goto err; - } - if (!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Unexpected success attaching the same prog to cg1"); - goto err; - } - if (bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog2 to cg1"); - goto err; - } - if (bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to cg2"); - goto err; - } - if (bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog to cg3"); - goto err; - } - if (bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to cg4"); - goto err; - } - if (bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching prog to cg5"); - goto err; - } - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 8 + 32); - - /* query the number of effective progs in cg5 */ - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - NULL, NULL, &prog_cnt) == 0); - assert(prog_cnt == 4); - /* retrieve prog_ids of effective progs in cg5 */ - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 4); - assert(attach_flags == 0); - saved_prog_id = prog_ids[0]; - /* check enospc handling */ - prog_ids[0] = 0; - prog_cnt = 2; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == -1 && - errno == ENOSPC); - assert(prog_cnt == 4); - /* check that prog_ids are returned even when buffer is too small */ - assert(prog_ids[0] == saved_prog_id); - /* retrieve prog_id of single attached prog in cg5 */ - prog_ids[0] = 0; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, - NULL, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 1); - assert(prog_ids[0] == saved_prog_id); - - /* detach bottom program and ping again */ - if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching prog from cg5"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 8 + 16); - - /* detach 3rd from bottom program and ping again */ - errno = 0; - if (!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS)) { - log_err("Unexpected success on detach from cg3"); - goto err; - } - if (bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching from cg3"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 16); - - /* detach 2nd from bottom program and ping again */ - if (bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching prog from cg4"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 4); - - prog_cnt = 4; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 3); - assert(attach_flags == 0); - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, - NULL, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 0); - goto out; -err: - rc = 1; - -out: - for (i = 0; i < 6; i++) - if (allow_prog[i] > 0) - close(allow_prog[i]); - close(cg1); - close(cg2); - close(cg3); - close(cg4); - close(cg5); - cleanup_cgroup_environment(); - if (!rc) - printf("#multi:PASS\n"); - else - printf("#multi:FAIL\n"); - return rc; -} - -static int test_autodetach(void) -{ - __u32 prog_cnt = 4, attach_flags; - int allow_prog[2] = {0}; - __u32 prog_ids[2] = {0}; - int cg = 0, i, rc = -1; - void *ptr = NULL; - int attempts; - - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - allow_prog[i] = prog_load_cnt(1, 1 << i); - if (!allow_prog[i]) - goto err; - } - - if (setup_cgroup_environment()) - goto err; - - /* create a cgroup, attach two programs and remember their ids */ - cg = create_and_get_cgroup("/cg_autodetach"); - if (cg < 0) - goto err; - - if (join_cgroup("/cg_autodetach")) - goto err; - - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - if (bpf_prog_attach(allow_prog[i], cg, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog[%d] to cg:egress", i); - goto err; - } - } - - /* make sure that programs are attached and run some traffic */ - assert(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags, - prog_ids, &prog_cnt) == 0); - assert(system(PING_CMD) == 0); - - /* allocate some memory (4Mb) to pin the original cgroup */ - ptr = malloc(4 * (1 << 20)); - if (!ptr) - goto err; - - /* close programs and cgroup fd */ - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - close(allow_prog[i]); - allow_prog[i] = 0; - } - - close(cg); - cg = 0; - - /* leave the cgroup and remove it. don't detach programs */ - cleanup_cgroup_environment(); - - /* wait for the asynchronous auto-detachment. - * wait for no more than 5 sec and give up. - */ - for (i = 0; i < ARRAY_SIZE(prog_ids); i++) { - for (attempts = 5; attempts >= 0; attempts--) { - int fd = bpf_prog_get_fd_by_id(prog_ids[i]); - - if (fd < 0) - break; - - /* don't leave the fd open */ - close(fd); - - if (!attempts) - goto err; - - sleep(1); - } - } - - rc = 0; -err: - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) - if (allow_prog[i] > 0) - close(allow_prog[i]); - if (cg) - close(cg); - free(ptr); - cleanup_cgroup_environment(); - if (!rc) - printf("#autodetach:PASS\n"); - else - printf("#autodetach:FAIL\n"); - return rc; -} - -int main(void) -{ - int (*tests[])(void) = { - test_foo_bar, - test_multiprog, - test_autodetach, - }; - int errors = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(tests); i++) - if (tests[i]()) - errors++; - - if (errors) - printf("test_cgroup_attach:FAIL\n"); - else - printf("test_cgroup_attach:PASS\n"); - - return errors ? EXIT_FAILURE : EXIT_SUCCESS; -} diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp index f0eb2727b766..a8d2e9a87fbf 100644 --- a/tools/testing/selftests/bpf/test_cpp.cpp +++ b/tools/testing/selftests/bpf/test_cpp.cpp @@ -1,12 +1,16 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#include "libbpf.h" -#include "bpf.h" -#include "btf.h" +#include <iostream> +#include <bpf/libbpf.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include "test_core_extern.skel.h" /* do nothing, just make sure we can link successfully */ int main(int argc, char *argv[]) { + struct test_core_extern *skel; + /* libbpf.h */ libbpf_set_print(NULL); @@ -16,5 +20,11 @@ int main(int argc, char *argv[]) /* btf.h */ btf__new(NULL, 0); + /* BPF skeleton */ + skel = test_core_extern__open_and_load(); + test_core_extern__destroy(skel); + + std::cout << "DONE!" << std::endl; + return 0; } diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh index a8485ae103d1..174b72a64a4c 100755 --- a/tools/testing/selftests/bpf/test_flow_dissector.sh +++ b/tools/testing/selftests/bpf/test_flow_dissector.sh @@ -139,6 +139,20 @@ echo "Testing IPv4 + GRE..." tc filter del dev lo ingress pref 1337 +echo "Testing port range..." +# Drops all IP/UDP packets coming from port 8-10 +tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \ + udp src_port 8-10 action drop + +# Send 10 IPv4/UDP packets from port 7. Filter should not drop any. +./test_flow_dissector -i 4 -f 7 +# Send 10 IPv4/UDP packets from port 9. Filter should drop all. +./test_flow_dissector -i 4 -f 9 -F +# Send 10 IPv4/UDP packets from port 11. Filter should not drop any. +./test_flow_dissector -i 4 -f 11 + +tc filter del dev lo ingress pref 1337 + echo "Testing IPv6..." # Drops all IPv6/UDP packets coming from port 9 tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \ diff --git a/tools/testing/selftests/bpf/test_hashmap.c b/tools/testing/selftests/bpf/test_hashmap.c index b64094c981e3..c490e012c23f 100644 --- a/tools/testing/selftests/bpf/test_hashmap.c +++ b/tools/testing/selftests/bpf/test_hashmap.c @@ -8,7 +8,7 @@ #include <stdio.h> #include <errno.h> #include <linux/err.h> -#include "hashmap.h" +#include "bpf/hashmap.h" #define CHECK(condition, format...) ({ \ int __ret = !!(condition); \ diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 7fa7d08a8104..bab1e6f1d8f1 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -8,7 +8,7 @@ #include <string.h> /* defined in test_progs.h */ -struct test_env env; +struct test_env env = {}; struct prog_test_def { const char *test_name; @@ -29,10 +29,19 @@ struct prog_test_def { static bool should_run(struct test_selector *sel, int num, const char *name) { - if (sel->name && sel->name[0] && !strstr(name, sel->name)) - return false; + int i; + + for (i = 0; i < sel->blacklist.cnt; i++) { + if (strstr(name, sel->blacklist.strs[i])) + return false; + } - if (!sel->num_set) + for (i = 0; i < sel->whitelist.cnt; i++) { + if (strstr(name, sel->whitelist.strs[i])) + return true; + } + + if (!sel->whitelist.cnt && !sel->num_set) return true; return num < sel->num_set_len && sel->num_set[num]; @@ -334,6 +343,7 @@ const char argp_program_doc[] = "BPF selftests test runner"; enum ARG_KEYS { ARG_TEST_NUM = 'n', ARG_TEST_NAME = 't', + ARG_TEST_NAME_BLACKLIST = 'b', ARG_VERIFIER_STATS = 's', ARG_VERBOSE = 'v', }; @@ -341,8 +351,10 @@ enum ARG_KEYS { static const struct argp_option opts[] = { { "num", ARG_TEST_NUM, "NUM", 0, "Run test number NUM only " }, - { "name", ARG_TEST_NAME, "NAME", 0, - "Run tests with names containing NAME" }, + { "name", ARG_TEST_NAME, "NAMES", 0, + "Run tests with names containing any string from NAMES list" }, + { "name-blacklist", ARG_TEST_NAME_BLACKLIST, "NAMES", 0, + "Don't run tests with names containing any string from NAMES list" }, { "verifier-stats", ARG_VERIFIER_STATS, NULL, 0, "Output verifier statistics", }, { "verbose", ARG_VERBOSE, "LEVEL", OPTION_ARG_OPTIONAL, @@ -359,6 +371,41 @@ static int libbpf_print_fn(enum libbpf_print_level level, return 0; } +static int parse_str_list(const char *s, struct str_set *set) +{ + char *input, *state = NULL, *next, **tmp, **strs = NULL; + int cnt = 0; + + input = strdup(s); + if (!input) + return -ENOMEM; + + set->cnt = 0; + set->strs = NULL; + + while ((next = strtok_r(state ? NULL : input, ",", &state))) { + tmp = realloc(strs, sizeof(*strs) * (cnt + 1)); + if (!tmp) + goto err; + strs = tmp; + + strs[cnt] = strdup(next); + if (!strs[cnt]) + goto err; + + cnt++; + } + + set->cnt = cnt; + set->strs = (const char **)strs; + free(input); + return 0; +err: + free(strs); + free(input); + return -ENOMEM; +} + int parse_num_list(const char *s, struct test_selector *sel) { int i, set_len = 0, num, start = 0, end = -1; @@ -449,12 +496,24 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) if (subtest_str) { *subtest_str = '\0'; - env->subtest_selector.name = strdup(subtest_str + 1); - if (!env->subtest_selector.name) + if (parse_str_list(subtest_str + 1, + &env->subtest_selector.whitelist)) + return -ENOMEM; + } + if (parse_str_list(arg, &env->test_selector.whitelist)) + return -ENOMEM; + break; + } + case ARG_TEST_NAME_BLACKLIST: { + char *subtest_str = strchr(arg, '/'); + + if (subtest_str) { + *subtest_str = '\0'; + if (parse_str_list(subtest_str + 1, + &env->subtest_selector.blacklist)) return -ENOMEM; } - env->test_selector.name = strdup(arg); - if (!env->test_selector.name) + if (parse_str_list(arg, &env->test_selector.blacklist)) return -ENOMEM; break; } @@ -617,7 +676,11 @@ int main(int argc, char **argv) printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); + free(env.test_selector.blacklist.strs); + free(env.test_selector.whitelist.strs); free(env.test_selector.num_set); + free(env.subtest_selector.blacklist.strs); + free(env.subtest_selector.whitelist.strs); free(env.subtest_selector.num_set); return env.fail_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 8477df835979..bcfa9ef23fda 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -35,7 +35,7 @@ typedef __u16 __sum16; #include "test_iptunnel_common.h" #include "bpf_util.h" -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> #include "trace_helpers.h" #include "flow_dissector_load.h" @@ -46,8 +46,14 @@ enum verbosity { VERBOSE_SUPER, }; +struct str_set { + const char **strs; + int cnt; +}; + struct test_selector { - const char *name; + struct str_set whitelist; + struct str_set blacklist; bool *num_set; int num_set_len; }; @@ -100,6 +106,7 @@ extern struct ipv6_packet pkt_v6; #define _CHECK(condition, tag, duration, format...) ({ \ int __ret = !!(condition); \ + int __save_errno = errno; \ if (__ret) { \ test__fail(); \ printf("%s:FAIL:%s ", __func__, tag); \ @@ -108,15 +115,18 @@ extern struct ipv6_packet pkt_v6; printf("%s:PASS:%s %d nsec\n", \ __func__, tag, duration); \ } \ + errno = __save_errno; \ __ret; \ }) #define CHECK_FAIL(condition) ({ \ int __ret = !!(condition); \ + int __save_errno = errno; \ if (__ret) { \ test__fail(); \ printf("%s:FAIL:%d\n", __func__, __LINE__); \ } \ + errno = __save_errno; \ __ret; \ }) diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index 0e6652733462..52bf14955797 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -13,7 +13,7 @@ #include <bpf/bpf.h> #include "cgroup_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> #include "bpf_rlimit.h" #include "bpf_util.h" diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 4a851513c842..779e11da979c 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -331,7 +331,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, FILE *file; int i, fp; - file = fopen(".sendpage_tst.tmp", "w+"); + file = tmpfile(); if (!file) { perror("create file for sendpage"); return 1; @@ -340,13 +340,8 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, fwrite(&k, sizeof(char), 1, file); fflush(file); fseek(file, 0, SEEK_SET); - fclose(file); - fp = open(".sendpage_tst.tmp", O_RDONLY); - if (fp < 0) { - perror("reopen file for sendpage"); - return 1; - } + fp = fileno(file); clock_gettime(CLOCK_MONOTONIC, &s->start); for (i = 0; i < cnt; i++) { @@ -354,11 +349,11 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, if (!drop && sent < 0) { perror("send loop error"); - close(fp); + fclose(file); return sent; } else if (drop && sent >= 0) { printf("sendpage loop error expected: %i\n", sent); - close(fp); + fclose(file); return -EIO; } @@ -366,7 +361,7 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt, s->bytes_sent += sent; } clock_gettime(CLOCK_MONOTONIC, &s->end); - close(fp); + fclose(file); return 0; } diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h index d008b41b7d8d..9b4d3a68a91a 100644 --- a/tools/testing/selftests/bpf/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/test_sockmap_kern.h @@ -12,8 +12,8 @@ #include <linux/tcp.h> #include <linux/pkt_cls.h> #include <sys/socket.h> -#include "bpf_helpers.h" -#include "bpf_endian.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> /* Sockmap sample program connects a client and a backend together * using cgroups. diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index 40bd93a6e7ae..d196e2a4a6e0 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -13,7 +13,7 @@ #include <bpf/bpf.h> #include <bpf/libbpf.h> -#include "bpf_endian.h" +#include <bpf/bpf_endian.h> #include "bpf_rlimit.h" #include "bpf_util.h" #include "cgroup_helpers.h" diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index aa4dcfe18050..0383c9b8adc1 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -2,7 +2,7 @@ #ifndef __TRACE_HELPER_H #define __TRACE_HELPER_H -#include <libbpf.h> +#include <bpf/libbpf.h> struct ksym { long addr; diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index c5ca669feb2b..e19ce940cd6a 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -369,7 +369,7 @@ static void *dummy_thread_fn(void *arg) static int test_cgcore_proc_migration(const char *root) { int ret = KSFT_FAIL; - int t, c_threads, n_threads = 13; + int t, c_threads = 0, n_threads = 13; char *src = NULL, *dst = NULL; pthread_t threads[n_threads]; diff --git a/tools/testing/selftests/dmabuf-heaps/Makefile b/tools/testing/selftests/dmabuf-heaps/Makefile new file mode 100644 index 000000000000..607c2acd2082 --- /dev/null +++ b/tools/testing/selftests/dmabuf-heaps/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -static -O3 -Wl,-no-as-needed -Wall -I../../../../usr/include + +TEST_GEN_PROGS = dmabuf-heap + +include ../lib.mk diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c new file mode 100644 index 000000000000..cd5e1f602ac9 --- /dev/null +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -0,0 +1,396 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <dirent.h> +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/types.h> + +#include <linux/dma-buf.h> +#include <drm/drm.h> + +#include "../../../../include/uapi/linux/dma-heap.h" + +#define DEVPATH "/dev/dma_heap" + +static int check_vgem(int fd) +{ + drm_version_t version = { 0 }; + char name[5]; + int ret; + + version.name_len = 4; + version.name = name; + + ret = ioctl(fd, DRM_IOCTL_VERSION, &version); + if (ret) + return 0; + + return !strcmp(name, "vgem"); +} + +static int open_vgem(void) +{ + int i, fd; + const char *drmstr = "/dev/dri/card"; + + fd = -1; + for (i = 0; i < 16; i++) { + char name[80]; + + snprintf(name, 80, "%s%u", drmstr, i); + + fd = open(name, O_RDWR); + if (fd < 0) + continue; + + if (!check_vgem(fd)) { + close(fd); + fd = -1; + continue; + } else { + break; + } + } + return fd; +} + +static int import_vgem_fd(int vgem_fd, int dma_buf_fd, uint32_t *handle) +{ + struct drm_prime_handle import_handle = { + .fd = dma_buf_fd, + .flags = 0, + .handle = 0, + }; + int ret; + + ret = ioctl(vgem_fd, DRM_IOCTL_PRIME_FD_TO_HANDLE, &import_handle); + if (ret == 0) + *handle = import_handle.handle; + return ret; +} + +static void close_handle(int vgem_fd, uint32_t handle) +{ + struct drm_gem_close close = { + .handle = handle, + }; + + ioctl(vgem_fd, DRM_IOCTL_GEM_CLOSE, &close); +} + +static int dmabuf_heap_open(char *name) +{ + int ret, fd; + char buf[256]; + + ret = snprintf(buf, 256, "%s/%s", DEVPATH, name); + if (ret < 0) { + printf("snprintf failed!\n"); + return ret; + } + + fd = open(buf, O_RDWR); + if (fd < 0) + printf("open %s failed!\n", buf); + return fd; +} + +static int dmabuf_heap_alloc_fdflags(int fd, size_t len, unsigned int fd_flags, + unsigned int heap_flags, int *dmabuf_fd) +{ + struct dma_heap_allocation_data data = { + .len = len, + .fd = 0, + .fd_flags = fd_flags, + .heap_flags = heap_flags, + }; + int ret; + + if (!dmabuf_fd) + return -EINVAL; + + ret = ioctl(fd, DMA_HEAP_IOCTL_ALLOC, &data); + if (ret < 0) + return ret; + *dmabuf_fd = (int)data.fd; + return ret; +} + +static int dmabuf_heap_alloc(int fd, size_t len, unsigned int flags, + int *dmabuf_fd) +{ + return dmabuf_heap_alloc_fdflags(fd, len, O_RDWR | O_CLOEXEC, flags, + dmabuf_fd); +} + +static void dmabuf_sync(int fd, int start_stop) +{ + struct dma_buf_sync sync = { + .flags = start_stop | DMA_BUF_SYNC_RW, + }; + int ret; + + ret = ioctl(fd, DMA_BUF_IOCTL_SYNC, &sync); + if (ret) + printf("sync failed %d\n", errno); +} + +#define ONE_MEG (1024 * 1024) + +static int test_alloc_and_import(char *heap_name) +{ + int heap_fd = -1, dmabuf_fd = -1, importer_fd = -1; + uint32_t handle = 0; + void *p = NULL; + int ret; + + printf("Testing heap: %s\n", heap_name); + + heap_fd = dmabuf_heap_open(heap_name); + if (heap_fd < 0) + return -1; + + printf("Allocating 1 MEG\n"); + ret = dmabuf_heap_alloc(heap_fd, ONE_MEG, 0, &dmabuf_fd); + if (ret) { + printf("Allocation Failed!\n"); + ret = -1; + goto out; + } + /* mmap and write a simple pattern */ + p = mmap(NULL, + ONE_MEG, + PROT_READ | PROT_WRITE, + MAP_SHARED, + dmabuf_fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + ret = -1; + goto out; + } + printf("mmap passed\n"); + + dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_START); + memset(p, 1, ONE_MEG / 2); + memset((char *)p + ONE_MEG / 2, 0, ONE_MEG / 2); + dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_END); + + importer_fd = open_vgem(); + if (importer_fd < 0) { + ret = importer_fd; + printf("Failed to open vgem\n"); + goto out; + } + + ret = import_vgem_fd(importer_fd, dmabuf_fd, &handle); + if (ret < 0) { + printf("Failed to import buffer\n"); + goto out; + } + printf("import passed\n"); + + dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_START); + memset(p, 0xff, ONE_MEG); + dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_END); + printf("syncs passed\n"); + + close_handle(importer_fd, handle); + ret = 0; + +out: + if (p) + munmap(p, ONE_MEG); + if (importer_fd >= 0) + close(importer_fd); + if (dmabuf_fd >= 0) + close(dmabuf_fd); + if (heap_fd >= 0) + close(heap_fd); + + return ret; +} + +/* Test the ioctl version compatibility w/ a smaller structure then expected */ +static int dmabuf_heap_alloc_older(int fd, size_t len, unsigned int flags, + int *dmabuf_fd) +{ + int ret; + unsigned int older_alloc_ioctl; + struct dma_heap_allocation_data_smaller { + __u64 len; + __u32 fd; + __u32 fd_flags; + } data = { + .len = len, + .fd = 0, + .fd_flags = O_RDWR | O_CLOEXEC, + }; + + older_alloc_ioctl = _IOWR(DMA_HEAP_IOC_MAGIC, 0x0, + struct dma_heap_allocation_data_smaller); + if (!dmabuf_fd) + return -EINVAL; + + ret = ioctl(fd, older_alloc_ioctl, &data); + if (ret < 0) + return ret; + *dmabuf_fd = (int)data.fd; + return ret; +} + +/* Test the ioctl version compatibility w/ a larger structure then expected */ +static int dmabuf_heap_alloc_newer(int fd, size_t len, unsigned int flags, + int *dmabuf_fd) +{ + int ret; + unsigned int newer_alloc_ioctl; + struct dma_heap_allocation_data_bigger { + __u64 len; + __u32 fd; + __u32 fd_flags; + __u64 heap_flags; + __u64 garbage1; + __u64 garbage2; + __u64 garbage3; + } data = { + .len = len, + .fd = 0, + .fd_flags = O_RDWR | O_CLOEXEC, + .heap_flags = flags, + .garbage1 = 0xffffffff, + .garbage2 = 0x88888888, + .garbage3 = 0x11111111, + }; + + newer_alloc_ioctl = _IOWR(DMA_HEAP_IOC_MAGIC, 0x0, + struct dma_heap_allocation_data_bigger); + if (!dmabuf_fd) + return -EINVAL; + + ret = ioctl(fd, newer_alloc_ioctl, &data); + if (ret < 0) + return ret; + + *dmabuf_fd = (int)data.fd; + return ret; +} + +static int test_alloc_compat(char *heap_name) +{ + int heap_fd = -1, dmabuf_fd = -1; + int ret; + + heap_fd = dmabuf_heap_open(heap_name); + if (heap_fd < 0) + return -1; + + printf("Testing (theoretical)older alloc compat\n"); + ret = dmabuf_heap_alloc_older(heap_fd, ONE_MEG, 0, &dmabuf_fd); + if (ret) { + printf("Older compat allocation failed!\n"); + ret = -1; + goto out; + } + close(dmabuf_fd); + + printf("Testing (theoretical)newer alloc compat\n"); + ret = dmabuf_heap_alloc_newer(heap_fd, ONE_MEG, 0, &dmabuf_fd); + if (ret) { + printf("Newer compat allocation failed!\n"); + ret = -1; + goto out; + } + printf("Ioctl compatibility tests passed\n"); +out: + if (dmabuf_fd >= 0) + close(dmabuf_fd); + if (heap_fd >= 0) + close(heap_fd); + + return ret; +} + +static int test_alloc_errors(char *heap_name) +{ + int heap_fd = -1, dmabuf_fd = -1; + int ret; + + heap_fd = dmabuf_heap_open(heap_name); + if (heap_fd < 0) + return -1; + + printf("Testing expected error cases\n"); + ret = dmabuf_heap_alloc(0, ONE_MEG, 0x111111, &dmabuf_fd); + if (!ret) { + printf("Did not see expected error (invalid fd)!\n"); + ret = -1; + goto out; + } + + ret = dmabuf_heap_alloc(heap_fd, ONE_MEG, 0x111111, &dmabuf_fd); + if (!ret) { + printf("Did not see expected error (invalid heap flags)!\n"); + ret = -1; + goto out; + } + + ret = dmabuf_heap_alloc_fdflags(heap_fd, ONE_MEG, + ~(O_RDWR | O_CLOEXEC), 0, &dmabuf_fd); + if (!ret) { + printf("Did not see expected error (invalid fd flags)!\n"); + ret = -1; + goto out; + } + + printf("Expected error checking passed\n"); +out: + if (dmabuf_fd >= 0) + close(dmabuf_fd); + if (heap_fd >= 0) + close(heap_fd); + + return ret; +} + +int main(void) +{ + DIR *d; + struct dirent *dir; + int ret = -1; + + d = opendir(DEVPATH); + if (!d) { + printf("No %s directory?\n", DEVPATH); + return -1; + } + + while ((dir = readdir(d)) != NULL) { + if (!strncmp(dir->d_name, ".", 2)) + continue; + if (!strncmp(dir->d_name, "..", 3)) + continue; + + ret = test_alloc_and_import(dir->d_name); + if (ret) + break; + + ret = test_alloc_compat(dir->d_name); + if (ret) + break; + + ret = test_alloc_errors(dir->d_name); + if (ret) + break; + } + closedir(d); + + return ret; +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index b4efb023ae51..d88d8e47d11b 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -50,6 +50,8 @@ ALL_TESTS=" ipv6_mc_dip_reserved_scope_test ipv6_mc_dip_interface_local_scope_test blackhole_route_test + irif_disabled_test + erif_disabled_test " NUM_NETIFS=4 @@ -553,6 +555,116 @@ blackhole_route_test() __blackhole_route_test "6" "2001:db8:2::/120" "ipv6" $h2_ipv6 "icmpv6" } +irif_disabled_test() +{ + local trap_name="irif_disabled" + local group_name="l3_drops" + local t0_packets t0_bytes + local t1_packets t1_bytes + local mz_pid + + RET=0 + + ping_check $trap_name + + devlink_trap_action_set $trap_name "trap" + + # When RIF of a physical port ("Sub-port RIF") is destroyed, we first + # block the STP of the {Port, VLAN} so packets cannot get into the RIF. + # Using bridge enables us to see this trap because when bridge is + # destroyed, there is a small time window that packets can go into the + # RIF, while it is disabled. + ip link add dev br0 type bridge + ip link set dev $rp1 master br0 + ip address flush dev $rp1 + __addr_add_del br0 add 192.0.2.2/24 + ip li set dev br0 up + + t0_packets=$(devlink_trap_rx_packets_get $trap_name) + t0_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + # Generate packets to h2 through br0 RIF that will be removed later + $MZ $h1 -t udp "sp=54321,dp=12345" -c 0 -p 100 -a own -b $rp1mac \ + -B $h2_ipv4 -q & + mz_pid=$! + + # Wait before removing br0 RIF to allow packets to go into the bridge. + sleep 1 + + # Flushing address will dismantle the RIF + ip address flush dev br0 + + t1_packets=$(devlink_trap_rx_packets_get $trap_name) + t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + check_err 1 "Trap stats idle when packets should be trapped" + fi + + log_test "Ingress RIF disabled" + + kill $mz_pid && wait $mz_pid &> /dev/null + ip link set dev $rp1 nomaster + __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 + ip link del dev br0 type bridge + devlink_trap_action_set $trap_name "drop" +} + +erif_disabled_test() +{ + local trap_name="erif_disabled" + local group_name="l3_drops" + local t0_packets t0_bytes + local t1_packets t1_bytes + local mz_pid + + RET=0 + + ping_check $trap_name + + devlink_trap_action_set $trap_name "trap" + ip link add dev br0 type bridge + ip add flush dev $rp1 + ip link set dev $rp1 master br0 + __addr_add_del br0 add 192.0.2.2/24 + ip link set dev br0 up + + t0_packets=$(devlink_trap_rx_packets_get $trap_name) + t0_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + rp2mac=$(mac_get $rp2) + + # Generate packets that should go out through br0 RIF that will be + # removed later + $MZ $h2 -t udp "sp=54321,dp=12345" -c 0 -p 100 -a own -b $rp2mac \ + -B 192.0.2.1 -q & + mz_pid=$! + + sleep 5 + # In order to see this trap we need a route that points to disabled RIF. + # When ipv6 address is flushed, there is a delay and the routes are + # deleted before the RIF and we cannot get state that we have route + # to disabled RIF. + # Delete IPv6 address first and then check this trap with flushing IPv4. + ip -6 add flush dev br0 + ip -4 add flush dev br0 + + t1_packets=$(devlink_trap_rx_packets_get $trap_name) + t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + check_err 1 "Trap stats idle when packets should be trapped" + fi + + log_test "Egress RIF disabled" + + kill $mz_pid && wait $mz_pid &> /dev/null + ip link set dev $rp1 nomaster + __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 + ip link del dev br0 type bridge + devlink_trap_action_set $trap_name "drop" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh new file mode 100755 index 000000000000..039629bb92a3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -0,0 +1,265 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel exceptions functionality over mlxsw. +# Check all exception traps to make sure they are triggered under the right +# conditions. + +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 192.0.2.1/28 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | SW1 | | +# | $swp1 + | +# | 192.0.2.2/28 | +# | | +# | + g1a (gre) | +# | loc=192.0.2.65 | +# | rem=192.0.2.66 | +# | tos=inherit | +# | | +# | + $rp1 | +# | | 198.51.100.1/28 | +# +--|----------------------+ +# | +# +--|----------------------+ +# | | VRF2 | +# | + $rp2 | +# | 198.51.100.2/28 | +# +-------------------------+ + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + decap_error_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +vrf2_create() +{ + simple_if_init $rp2 198.51.100.2/28 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 198.51.100.2/28 +} + +switch_create() +{ + __addr_add_del $swp1 add 192.0.2.2/28 + tc qdisc add dev $swp1 clsact + ip link set dev $swp1 up + + tunnel_create g1 gre 192.0.2.65 192.0.2.66 tos inherit + __addr_add_del g1 add 192.0.2.65/32 + ip link set dev g1 up + + __addr_add_del $rp1 add 198.51.100.1/28 + ip link set dev $rp1 up +} + +switch_destroy() +{ + ip link set dev $rp1 down + __addr_add_del $rp1 del 198.51.100.1/28 + + ip link set dev g1 down + __addr_add_del g1 del 192.0.2.65/32 + tunnel_destroy g1 + + ip link set dev $swp1 down + tc qdisc del dev $swp1 clsact + __addr_add_del $swp1 del 192.0.2.2/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + forwarding_enable + vrf_prepare + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +ecn_payload_get() +{ + p=$(: + )"0"$( : GRE flags + )"0:00:"$( : Reserved + version + )"08:00:"$( : ETH protocol type + )"4"$( : IP version + )"5:"$( : IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"30:"$( : IP TTL + )"01:"$( : IP proto + )"E7:E6:"$( : IP header csum + )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 + )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 + ) + echo $p +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.1.1 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A 192.0.2.66 -B 192.0.2.65 -t ip \ + len=48,tos=$outer_tos,proto=47,p=$payload -q & + + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +ipip_payload_get() +{ + local flags=$1; shift + local key=$1; shift + + p=$(: + )"$flags"$( : GRE flags + )"0:00:"$( : Reserved + version + )"08:00:"$( : ETH protocol type + )"$key"$( : Key + )"4"$( : IP version + )"5:"$( : IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"30:"$( : IP TTL + )"01:"$( : IP proto + )"E7:E6:"$( : IP header csum + )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 + )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 + ) + echo $p +} + +no_matching_tunnel_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local sip=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.1.1 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ipip_payload_get "$@") + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A $sip -B 192.0.2.65 -t ip len=48,proto=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +decap_error_test() +{ + # Correct source IP - the remote address + local sip=192.0.2.66 + + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + no_matching_tunnel_test "Decap error: Source IP check failed" \ + 192.0.2.68 "0" + no_matching_tunnel_test \ + "Decap error: Key exists but was not expected" $sip "2" ":E9:" + + # Destroy the tunnel and create new one with key + __addr_add_del g1 del 192.0.2.65/32 + tunnel_destroy g1 + + tunnel_create g1 gre 192.0.2.65 192.0.2.66 tos inherit key 233 + __addr_add_del g1 add 192.0.2.65/32 + + no_matching_tunnel_test \ + "Decap error: Key does not exist but was expected" $sip "0" + no_matching_tunnel_test \ + "Decap error: Packet has a wrong key field" $sip "2" "E8:" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh new file mode 100755 index 000000000000..fd19161dd4ec --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -0,0 +1,330 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel drops and exceptions functionality over mlxsw. +# Check all traps to make sure they are triggered under the right +# conditions. + +# +--------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|---------------+ +# | +# +----|----------------------------------------------------------------------+ +# | SW | | +# | +--|--------------------------------------------------------------------+ | +# | | + $swp1 BR1 (802.1d) | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | id 1000 dstport $VXPORT | | +# | +-----------------------------------------------------------------------+ | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +----|----------------------------------------------------------------------+ +# | +# +----|--------------------------------------------------------+ +# | | VRF2 | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | +# +-------------------------------------------------------------+ + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + decap_error_test + overlay_smac_is_mc_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +: ${VXPORT:=4789} +export VXPORT + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +switch_create() +{ + ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip link set dev br1 address $(mac_get $swp1) + ip link set dev br1 up + + tc qdisc add dev $swp1 clsact + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link add name vx1 type vxlan id 1000 local 192.0.2.17 \ + dstport "$VXPORT" nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx1 master br1 + ip link set dev vx1 up + + ip address add dev $rp1 192.0.2.17/28 + ip link set dev $rp1 up +} + +switch_destroy() +{ + ip link set dev $rp1 down + ip address del dev $rp1 192.0.2.17/28 + + ip link set dev vx1 down + ip link set dev vx1 nomaster + ip link del dev vx1 + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + tc qdisc del dev $swp1 clsact + + ip link set dev br1 down + ip link del dev br1 +} + +vrf2_create() +{ + simple_if_init $rp2 192.0.2.18/28 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + vrf_prepare + forwarding_enable + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + forwarding_restore + vrf_cleanup +} + +ecn_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"00:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"00:00:00:00:00:00:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"D6:E5:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.2.3 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac -B 192.0.2.17 \ + -t udp sp=12345,dp=$VXPORT,tos=$outer_tos,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +reserved_bits_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"01:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"00:00:00:00:00:00:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"00:00:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +short_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"01:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + ) + echo $p +} + +corrupted_packet_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local payload_get=$1; shift + local mz_pid + + RET=0 + + # In case of too short packet, there is no any inner packet, + # so the matching will always succeed + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower skip_hw src_ip 192.0.2.3 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + payload=$($payload_get) + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac \ + -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +decap_error_test() +{ + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + corrupted_packet_test "Decap error: Reserved bits in use" \ + "reserved_bits_payload_get" + corrupted_packet_test "Decap error: No L2 header" "short_payload_get" +} + +mc_smac_payload_get() +{ + dest_mac=$(mac_get $h1) + source_mac=01:02:03:04:05:06 + p=$(: + )"08:"$( : VXLAN flags + )"00:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"$source_mac:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"00:00:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +overlay_smac_is_mc_test() +{ + local trap_name="overlay_smac_is_mc" + local group_name="tunnel_drops" + local mz_pid + + RET=0 + + # The matching will be checked on devlink_trap_drop_test() + # and the filter will be removed on devlink_trap_drop_cleanup() + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_mac 01:02:03:04:05:06 action pass + + rp1_mac=$(mac_get $rp1) + payload=$(mc_smac_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac \ + -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q & + mz_pid=$! + + devlink_trap_drop_test $trap_name $group_name $swp1 + + log_test "Overlay source MAC is multicast" + + devlink_trap_drop_cleanup $mz_pid $swp1 "ip" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/fib.sh b/tools/testing/selftests/drivers/net/mlxsw/fib.sh new file mode 100755 index 000000000000..eab79b9e58cd --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/fib.sh @@ -0,0 +1,256 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking the FIB offload API on top of mlxsw. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ipv4_identical_routes + ipv4_tos + ipv4_metric + ipv4_replace + ipv4_delete + ipv4_plen + ipv4_replay + ipv4_flush + ipv4_local_replace + ipv6_add + ipv6_metric + ipv6_append_single + ipv6_replace_single + ipv6_metric_multipath + ipv6_append_multipath + ipv6_replace_multipath + ipv6_append_multipath_to_single + ipv6_delete_single + ipv6_delete_multipath + ipv6_replay_single + ipv6_replay_multipath + ipv6_local_replace +" +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh +source $lib_dir/fib_offload_lib.sh + +ipv4_identical_routes() +{ + fib_ipv4_identical_routes_test "testns1" +} + +ipv4_tos() +{ + fib_ipv4_tos_test "testns1" +} + +ipv4_metric() +{ + fib_ipv4_metric_test "testns1" +} + +ipv4_replace() +{ + fib_ipv4_replace_test "testns1" +} + +ipv4_delete() +{ + fib_ipv4_delete_test "testns1" +} + +ipv4_plen() +{ + fib_ipv4_plen_test "testns1" +} + +ipv4_replay_metric() +{ + fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_tos() +{ + fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_plen() +{ + fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay() +{ + ipv4_replay_metric + ipv4_replay_tos + ipv4_replay_plen +} + +ipv4_flush() +{ + fib_ipv4_flush_test "testns1" +} + +ipv4_local_replace() +{ + local ns="testns1" + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add table local 192.0.2.1/32 dev dummy1 + fib4_trap_check $ns "table local 192.0.2.1/32 dev dummy1" false + check_err $? "Local table route not in hardware when should" + + ip -n $ns route add table main 192.0.2.1/32 dev dummy1 + fib4_trap_check $ns "table main 192.0.2.1/32 dev dummy1" true + check_err $? "Main table route in hardware when should not" + + fib4_trap_check $ns "table local 192.0.2.1/32 dev dummy1" false + check_err $? "Local table route was replaced when should not" + + # Test that local routes can replace routes in main table. + ip -n $ns route add table main 192.0.2.2/32 dev dummy1 + fib4_trap_check $ns "table main 192.0.2.2/32 dev dummy1" false + check_err $? "Main table route not in hardware when should" + + ip -n $ns route add table local 192.0.2.2/32 dev dummy1 + fib4_trap_check $ns "table local 192.0.2.2/32 dev dummy1" false + check_err $? "Local table route did not replace route in main table when should" + + fib4_trap_check $ns "table main 192.0.2.2/32 dev dummy1" true + check_err $? "Main table route was not replaced when should" + + log_test "IPv4 local table route replacement" + + ip -n $ns link del dev dummy1 +} + +ipv6_add() +{ + fib_ipv6_add_test "testns1" +} + +ipv6_metric() +{ + fib_ipv6_metric_test "testns1" +} + +ipv6_append_single() +{ + fib_ipv6_append_single_test "testns1" +} + +ipv6_replace_single() +{ + fib_ipv6_replace_single_test "testns1" +} + +ipv6_metric_multipath() +{ + fib_ipv6_metric_multipath_test "testns1" +} + +ipv6_append_multipath() +{ + fib_ipv6_append_multipath_test "testns1" +} + +ipv6_replace_multipath() +{ + fib_ipv6_replace_multipath_test "testns1" +} + +ipv6_append_multipath_to_single() +{ + fib_ipv6_append_multipath_to_single_test "testns1" +} + +ipv6_delete_single() +{ + fib_ipv6_delete_single_test "testns1" +} + +ipv6_delete_multipath() +{ + fib_ipv6_delete_multipath_test "testns1" +} + +ipv6_replay_single() +{ + fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV" +} + +ipv6_replay_multipath() +{ + fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV" +} + +ipv6_local_replace() +{ + local ns="testns1" + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add table local 2001:db8:1::1/128 dev dummy1 + fib6_trap_check $ns "table local 2001:db8:1::1/128 dev dummy1" false + check_err $? "Local table route not in hardware when should" + + ip -n $ns route add table main 2001:db8:1::1/128 dev dummy1 + fib6_trap_check $ns "table main 2001:db8:1::1/128 dev dummy1" true + check_err $? "Main table route in hardware when should not" + + fib6_trap_check $ns "table local 2001:db8:1::1/128 dev dummy1" false + check_err $? "Local table route was replaced when should not" + + # Test that local routes can replace routes in main table. + ip -n $ns route add table main 2001:db8:1::2/128 dev dummy1 + fib6_trap_check $ns "table main 2001:db8:1::2/128 dev dummy1" false + check_err $? "Main table route not in hardware when should" + + ip -n $ns route add table local 2001:db8:1::2/128 dev dummy1 + fib6_trap_check $ns "table local 2001:db8:1::2/128 dev dummy1" false + check_err $? "Local route route did not replace route in main table when should" + + fib6_trap_check $ns "table main 2001:db8:1::2/128 dev dummy1" true + check_err $? "Main table route was not replaced when should" + + log_test "IPv6 local table route replacement" + + ip -n $ns link del dev dummy1 +} + +setup_prepare() +{ + ip netns add testns1 + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + devlink dev reload $DEVLINK_DEV netns testns1 + if [ $? -ne 0 ]; then + echo "Failed to reload into netns \"testns1\"" + exit 1 + fi +} + +cleanup() +{ + pre_cleanup + devlink -N testns1 dev reload $DEVLINK_DEV netns $$ + ip netns del testns1 +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh new file mode 100755 index 000000000000..eff6393ce974 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh @@ -0,0 +1,176 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for port-default priority. Non-IP packets ingress $swp1 and are +# prioritized according to the default priority specified at the port. +# rx_octets_prio_* counters are used to verify the prioritization. +# +# +-----------------------+ +# | H1 | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|------------------+ +# | +# +----|------------------+ +# | SW | | +# | + $swp1 | +# | 192.0.2.2/28 | +# | APP=<prio>,1,0 | +# +-----------------------+ + +ALL_TESTS=" + ping_ipv4 + test_defprio +" + +lib_dir=$(dirname $0)/../../../net/forwarding + +NUM_NETIFS=2 +: ${HIT_TIMEOUT:=1000} # ms +source $lib_dir/lib.sh + +declare -a APP + +defprio_install() +{ + local dev=$1; shift + local prio=$1; shift + local app="app=$prio,1,0" + + lldptool -T -i $dev -V APP $app >/dev/null + lldpad_app_wait_set $dev + APP[$prio]=$app +} + +defprio_uninstall() +{ + local dev=$1; shift + local prio=$1; shift + local app=${APP[$prio]} + + lldptool -T -i $dev -V APP -d $app >/dev/null + lldpad_app_wait_del + unset APP[$prio] +} + +defprio_flush() +{ + local dev=$1; shift + local prio + + if ((${#APP[@]})); then + lldptool -T -i $dev -V APP -d ${APP[@]} >/dev/null + fi + lldpad_app_wait_del + APP=() +} + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +switch_create() +{ + ip link set dev $swp1 up + ip addr add dev $swp1 192.0.2.2/28 +} + +switch_destroy() +{ + defprio_flush $swp1 + ip addr del dev $swp1 192.0.2.2/28 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +wait_for_packets() +{ + local t0=$1; shift + local prio_observe=$1; shift + + local t1=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe) + local delta=$((t1 - t0)) + echo $delta + ((delta >= 10)) +} + +__test_defprio() +{ + local prio_install=$1; shift + local prio_observe=$1; shift + local delta + local key + local i + + RET=0 + + defprio_install $swp1 $prio_install + + local t0=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe) + mausezahn -q $h1 -d 100m -c 10 -t arp reply + delta=$(busywait "$HIT_TIMEOUT" wait_for_packets $t0 $prio_observe) + + check_err $? "Default priority $prio_install/$prio_observe: Expected to capture 10 packets, got $delta." + log_test "Default priority $prio_install/$prio_observe" + + defprio_uninstall $swp1 $prio_install +} + +test_defprio() +{ + local prio + + for prio in {0..7}; do + __test_defprio $prio $prio + done + + defprio_install $swp1 3 + __test_defprio 0 3 + __test_defprio 1 3 + __test_defprio 2 3 + __test_defprio 4 4 + __test_defprio 5 5 + __test_defprio 6 6 + __test_defprio 7 7 + defprio_uninstall $swp1 3 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh index e80be65799ad..faa51012cdac 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh @@ -1,47 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -humanize() -{ - local speed=$1; shift - - for unit in bps Kbps Mbps Gbps; do - if (($(echo "$speed < 1024" | bc))); then - break - fi - - speed=$(echo "scale=1; $speed / 1024" | bc) - done - - echo "$speed${unit}" -} - -rate() -{ - local t0=$1; shift - local t1=$1; shift - local interval=$1; shift - - echo $((8 * (t1 - t0) / interval)) -} - -start_traffic() -{ - local h_in=$1; shift # Where the traffic egresses the host - local sip=$1; shift - local dip=$1; shift - local dmac=$1; shift - - $MZ $h_in -p 8000 -A $sip -B $dip -c 0 \ - -a own -b $dmac -t udp -q & - sleep 1 -} - -stop_traffic() -{ - # Suppress noise from killing mausezahn. - { kill %% && wait %%; } 2>/dev/null -} - check_rate() { local rate=$1; shift @@ -96,3 +54,31 @@ measure_rate() echo $ir $er return $ret } + +bail_on_lldpad() +{ + if systemctl is-active --quiet lldpad; then + + cat >/dev/stderr <<-EOF + WARNING: lldpad is running + + lldpad will likely configure DCB, and this test will + configure Qdiscs. mlxsw does not support both at the + same time, one of them is arbitrarily going to overwrite + the other. That will cause spurious failures (or, + unlikely, passes) of this test. + EOF + + if [[ -z $ALLOW_LLDPAD ]]; then + cat >/dev/stderr <<-EOF + + If you want to run the test anyway, please set + an environment variable ALLOW_LLDPAD to a + non-empty string. + EOF + exit 1 + else + return + fi + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh new file mode 100755 index 000000000000..c9fc4d4885c1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh @@ -0,0 +1,67 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# A driver for the ETS selftest that implements testing in offloaded datapath. +lib_dir=$(dirname $0)/../../../net/forwarding +source $lib_dir/sch_ets_core.sh +source $lib_dir/devlink_lib.sh +source qos_lib.sh + +ALL_TESTS=" + ping_ipv4 + priomap_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr +" + +switch_create() +{ + ets_switch_create + + # Create a bottleneck so that the DWRR process can kick in. + ethtool -s $h2 speed 1000 autoneg off + ethtool -s $swp2 speed 1000 autoneg off + + # Set the ingress quota high and use the three egress TCs to limit the + # amount of traffic that is admitted to the shared buffers. This makes + # sure that there is always enough traffic of all types to select from + # for the DWRR process. + devlink_port_pool_th_set $swp1 0 12 + devlink_tc_bind_pool_th_set $swp1 0 ingress 0 12 + devlink_port_pool_th_set $swp2 4 12 + devlink_tc_bind_pool_th_set $swp2 7 egress 4 5 + devlink_tc_bind_pool_th_set $swp2 6 egress 4 5 + devlink_tc_bind_pool_th_set $swp2 5 egress 4 5 + + # Note: sch_ets_core.sh uses VLAN ingress-qos-map to assign packet + # priorities at $swp1 based on their 802.1p headers. ingress-qos-map is + # not offloaded by mlxsw as of this writing, but the mapping used is + # 1:1, which is the mapping currently hard-coded by the driver. +} + +switch_destroy() +{ + devlink_tc_bind_pool_th_restore $swp2 5 egress + devlink_tc_bind_pool_th_restore $swp2 6 egress + devlink_tc_bind_pool_th_restore $swp2 7 egress + devlink_port_pool_th_restore $swp2 4 + devlink_tc_bind_pool_th_restore $swp1 0 ingress + devlink_port_pool_th_restore $swp1 0 + + ethtool -s $swp2 autoneg on + ethtool -s $h2 autoneg on + + ets_switch_destroy +} + +# Callback from sch_ets_tests.sh +get_stats() +{ + local band=$1; shift + + ethtool_stats_get "$h2" rx_octets_prio_$band +} + +bail_on_lldpad +ets_run diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh new file mode 100755 index 000000000000..c6ce0b448bf3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_ets.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh new file mode 100755 index 000000000000..8d245f331619 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_prio.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh new file mode 100755 index 000000000000..013886061f15 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source qos_lib.sh +bail_on_lldpad + +lib_dir=$(dirname $0)/../../../net/forwarding +TCFLAGS=skip_sw +source $lib_dir/sch_tbf_root.sh diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib.sh b/tools/testing/selftests/drivers/net/netdevsim/fib.sh new file mode 100755 index 000000000000..2f87c3be76a9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/fib.sh @@ -0,0 +1,341 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking the FIB offload API. It makes use of netdevsim +# which registers a listener to the FIB notification chain. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ipv4_identical_routes + ipv4_tos + ipv4_metric + ipv4_replace + ipv4_delete + ipv4_plen + ipv4_replay + ipv4_flush + ipv4_error_path + ipv6_add + ipv6_metric + ipv6_append_single + ipv6_replace_single + ipv6_metric_multipath + ipv6_append_multipath + ipv6_replace_multipath + ipv6_append_multipath_to_single + ipv6_delete_single + ipv6_delete_multipath + ipv6_replay_single + ipv6_replay_multipath + ipv6_error_path +" +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR=1337 +DEV=netdevsim${DEV_ADDR} +DEVLINK_DEV=netdevsim/${DEV} +SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/ +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh +source $lib_dir/fib_offload_lib.sh + +ipv4_identical_routes() +{ + fib_ipv4_identical_routes_test "testns1" +} + +ipv4_tos() +{ + fib_ipv4_tos_test "testns1" +} + +ipv4_metric() +{ + fib_ipv4_metric_test "testns1" +} + +ipv4_replace() +{ + fib_ipv4_replace_test "testns1" +} + +ipv4_delete() +{ + fib_ipv4_delete_test "testns1" +} + +ipv4_plen() +{ + fib_ipv4_plen_test "testns1" +} + +ipv4_replay_metric() +{ + fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_tos() +{ + fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_plen() +{ + fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay() +{ + ipv4_replay_metric + ipv4_replay_tos + ipv4_replay_plen +} + +ipv4_flush() +{ + fib_ipv4_flush_test "testns1" +} + +ipv4_error_path_add() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1 \ + &> /dev/null + done + + log_test "IPv4 error path - add" + + ip -n testns1 link del dev dummy1 +} + +ipv4_error_path_replay() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1 + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null + + log_test "IPv4 error path - replay" + + ip -n testns1 link del dev dummy1 + + # Successfully reload after deleting all the routes. + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV +} + +ipv4_error_path() +{ + # Test the different error paths of the notifiers by limiting the size + # of the "IPv4/fib" resource. + ipv4_error_path_add + ipv4_error_path_replay +} + +ipv6_add() +{ + fib_ipv6_add_test "testns1" +} + +ipv6_metric() +{ + fib_ipv6_metric_test "testns1" +} + +ipv6_append_single() +{ + fib_ipv6_append_single_test "testns1" +} + +ipv6_replace_single() +{ + fib_ipv6_replace_single_test "testns1" +} + +ipv6_metric_multipath() +{ + fib_ipv6_metric_multipath_test "testns1" +} + +ipv6_append_multipath() +{ + fib_ipv6_append_multipath_test "testns1" +} + +ipv6_replace_multipath() +{ + fib_ipv6_replace_multipath_test "testns1" +} + +ipv6_append_multipath_to_single() +{ + fib_ipv6_append_multipath_to_single_test "testns1" +} + +ipv6_delete_single() +{ + fib_ipv6_delete_single_test "testns1" +} + +ipv6_delete_multipath() +{ + fib_ipv6_delete_multipath_test "testns1" +} + +ipv6_replay_single() +{ + fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV" +} + +ipv6_replay_multipath() +{ + fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV" +} + +ipv6_error_path_add_single() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1 \ + &> /dev/null + done + + log_test "IPv6 error path - add single" + + ip -n testns1 link del dev dummy1 +} + +ipv6_error_path_add_multipath() +{ + local lsb + + RET=0 + + for i in $(seq 1 2); do + ip -n testns1 link add name dummy$i type dummy + ip -n testns1 link set dev dummy$i up + ip -n testns1 address add 2001:db8:$i::1/64 dev dummy$i + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:10::${lsb}/128 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 &> /dev/null + done + + log_test "IPv6 error path - add multipath" + + for i in $(seq 1 2); do + ip -n testns1 link del dev dummy$i + done +} + +ipv6_error_path_replay() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1 + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null + + log_test "IPv6 error path - replay" + + ip -n testns1 link del dev dummy1 + + # Successfully reload after deleting all the routes. + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV +} + +ipv6_error_path() +{ + # Test the different error paths of the notifiers by limiting the size + # of the "IPv6/fib" resource. + ipv6_error_path_add_single + ipv6_error_path_add_multipath + ipv6_error_path_replay +} + +setup_prepare() +{ + local netdev + + modprobe netdevsim &> /dev/null + + echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device + while [ ! -d $SYSFS_NET_DIR ] ; do :; done + + ip netns add testns1 + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + devlink dev reload $DEVLINK_DEV netns testns1 + if [ $? -ne 0 ]; then + echo "Failed to reload into netns \"testns1\"" + exit 1 + fi +} + +cleanup() +{ + pre_cleanup + ip netns del testns1 + echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device + modprobe -r netdevsim &> /dev/null +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index 27a54a17da65..f4e92afab14b 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -30,7 +30,7 @@ ftrace_filter_check '*schedule*' '^.*schedule.*$' ftrace_filter_check 'schedule*' '^schedule.*$' # filter by *mid*end -ftrace_filter_check '*aw*lock' '.*aw.*lock$' +ftrace_filter_check '*pin*lock' '.*pin.*lock$' # filter by start*mid* ftrace_filter_check 'mutex*try*' '^mutex.*try.*' diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc index 64cfcc75e3c1..f2ee1e889e13 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -1,6 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: ftrace - function pid filters +# flags: instance # Make sure that function pid matching filter works. # Also test it on an instance directory @@ -96,13 +97,6 @@ do_test() { } do_test - -mkdir instances/foo -cd instances/foo -do_test -cd ../../ -rmdir instances/foo - do_reset exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-syntax-errors.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-syntax-errors.tc new file mode 100644 index 000000000000..d44087a2f3d1 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-syntax-errors.tc @@ -0,0 +1,32 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test histogram parser errors + +if [ ! -f set_event -o ! -d events/kmem ]; then + echo "event tracing is not supported" + exit_unsupported +fi + +if [ ! -f events/kmem/kmalloc/trigger ]; then + echo "event trigger is not supported" + exit_unsupported +fi + +if [ ! -f events/kmem/kmalloc/hist ]; then + echo "hist trigger is not supported" + exit_unsupported +fi + +[ -f error_log ] || exit_unsupported + +check_error() { # command-with-error-pos-by-^ + ftrace_errlog_check 'hist:kmem:kmalloc' "$1" 'events/kmem/kmalloc/trigger' +} + +check_error 'hist:keys=common_pid:vals=bytes_req:sort=common_pid,^junk' # INVALID_SORT_FIELD +check_error 'hist:keys=common_pid:vals=bytes_req:^sort=' # EMPTY_ASSIGNMENT +check_error 'hist:keys=common_pid:vals=bytes_req:^sort=common_pid,' # EMPTY_SORT_FIELD +check_error 'hist:keys=common_pid:vals=bytes_req:sort=common_pid.^junk' # INVALID_SORT_MODIFIER +check_error 'hist:keys=common_pid:vals=bytes_req,bytes_alloc:^sort=common_pid,bytes_req,bytes_alloc' # TOO_MANY_SORT_FIELDS + +exit 0 diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 30996306cabc..23207829ec75 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 INCLUDES := -I../include -I../../ CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) -LDFLAGS := $(LDFLAGS) -pthread -lrt +LDLIBS := -lpthread -lrt HEADERS := \ ../include/futextest.h \ diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index a8d20cbb711c..e84d901f8567 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -91,7 +91,7 @@ run_one() run_many() { echo "TAP version 13" - DIR=$(basename "$PWD") + DIR="${PWD#${BASE_DIR}/}" test_num=0 total=$(echo "$@" | wc -w) echo "1..$total" diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 3138a916574a..d91c53b726e6 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -8,7 +8,7 @@ KSFT_KHDR_INSTALL := 1 UNAME_M := $(shell uname -m) LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/ucall.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c @@ -26,6 +26,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test +TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus @@ -36,6 +37,7 @@ TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_s390x = s390x/memop TEST_GEN_PROGS_s390x += s390x/sync_regs_test +TEST_GEN_PROGS_s390x += s390x/resets TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += kvm_create_max_vcpus @@ -45,9 +47,11 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ - -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. + -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ + -I$(<D) -Iinclude/$(UNAME_M) -I.. no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 29cccaf96baf..ae0d14c2540a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -125,6 +125,12 @@ void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs); int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs); +void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_fpu *fpu); +void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_fpu *fpu); +void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg); +void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg); #ifdef __KVM_HAVE_VCPU_EVENTS void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 635ee6c33ad2..7428513a4c68 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -11,6 +11,8 @@ #include <assert.h> #include <stdint.h> +#include <asm/msr-index.h> + #define X86_EFLAGS_FIXED (1u << 1) #define X86_CR4_VME (1ul << 0) @@ -34,24 +36,24 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) -/* The enum values match the intruction encoding of each register */ -enum x86_register { - RAX = 0, - RCX, - RDX, - RBX, - RSP, - RBP, - RSI, - RDI, - R8, - R9, - R10, - R11, - R12, - R13, - R14, - R15, +/* General Registers in 64-Bit Mode */ +struct gpr64_regs { + u64 rax; + u64 rcx; + u64 rdx; + u64 rbx; + u64 rsp; + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; }; struct desc64 { @@ -218,20 +220,20 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } -static inline uint64_t get_gdt_base(void) +static inline struct desc_ptr get_gdt(void) { struct desc_ptr gdt; __asm__ __volatile__("sgdt %[gdt]" : /* output */ [gdt]"=m"(gdt)); - return gdt.address; + return gdt; } -static inline uint64_t get_idt_base(void) +static inline struct desc_ptr get_idt(void) { struct desc_ptr idt; __asm__ __volatile__("sidt %[idt]" : /* output */ [idt]"=m"(idt)); - return idt.address; + return idt; } #define SET_XMM(__var, __xmm) \ @@ -348,444 +350,6 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); #define X86_CR0_CD (1UL<<30) /* Cache Disable */ #define X86_CR0_PG (1UL<<31) /* Paging */ -/* - * CPU model specific register (MSR) numbers. - */ - -/* x86-64 specific MSRs */ -#define MSR_EFER 0xc0000080 /* extended feature register */ -#define MSR_STAR 0xc0000081 /* legacy mode SYSCALL target */ -#define MSR_LSTAR 0xc0000082 /* long mode SYSCALL target */ -#define MSR_CSTAR 0xc0000083 /* compat mode SYSCALL target */ -#define MSR_SYSCALL_MASK 0xc0000084 /* EFLAGS mask for syscall */ -#define MSR_FS_BASE 0xc0000100 /* 64bit FS base */ -#define MSR_GS_BASE 0xc0000101 /* 64bit GS base */ -#define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */ -#define MSR_TSC_AUX 0xc0000103 /* Auxiliary TSC */ - -/* EFER bits: */ -#define EFER_SCE (1<<0) /* SYSCALL/SYSRET */ -#define EFER_LME (1<<8) /* Long mode enable */ -#define EFER_LMA (1<<10) /* Long mode active (read-only) */ -#define EFER_NX (1<<11) /* No execute enable */ -#define EFER_SVME (1<<12) /* Enable virtualization */ -#define EFER_LMSLE (1<<13) /* Long Mode Segment Limit Enable */ -#define EFER_FFXSR (1<<14) /* Enable Fast FXSAVE/FXRSTOR */ - -/* Intel MSRs. Some also available on other CPUs */ - -#define MSR_PPIN_CTL 0x0000004e -#define MSR_PPIN 0x0000004f - -#define MSR_IA32_PERFCTR0 0x000000c1 -#define MSR_IA32_PERFCTR1 0x000000c2 -#define MSR_FSB_FREQ 0x000000cd -#define MSR_PLATFORM_INFO 0x000000ce -#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31 -#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT) - -#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 -#define NHM_C3_AUTO_DEMOTE (1UL << 25) -#define NHM_C1_AUTO_DEMOTE (1UL << 26) -#define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25) -#define SNB_C1_AUTO_UNDEMOTE (1UL << 27) -#define SNB_C3_AUTO_UNDEMOTE (1UL << 28) - -#define MSR_MTRRcap 0x000000fe -#define MSR_IA32_BBL_CR_CTL 0x00000119 -#define MSR_IA32_BBL_CR_CTL3 0x0000011e - -#define MSR_IA32_SYSENTER_CS 0x00000174 -#define MSR_IA32_SYSENTER_ESP 0x00000175 -#define MSR_IA32_SYSENTER_EIP 0x00000176 - -#define MSR_IA32_MCG_CAP 0x00000179 -#define MSR_IA32_MCG_STATUS 0x0000017a -#define MSR_IA32_MCG_CTL 0x0000017b -#define MSR_IA32_MCG_EXT_CTL 0x000004d0 - -#define MSR_OFFCORE_RSP_0 0x000001a6 -#define MSR_OFFCORE_RSP_1 0x000001a7 -#define MSR_TURBO_RATIO_LIMIT 0x000001ad -#define MSR_TURBO_RATIO_LIMIT1 0x000001ae -#define MSR_TURBO_RATIO_LIMIT2 0x000001af - -#define MSR_LBR_SELECT 0x000001c8 -#define MSR_LBR_TOS 0x000001c9 -#define MSR_LBR_NHM_FROM 0x00000680 -#define MSR_LBR_NHM_TO 0x000006c0 -#define MSR_LBR_CORE_FROM 0x00000040 -#define MSR_LBR_CORE_TO 0x00000060 - -#define MSR_LBR_INFO_0 0x00000dc0 /* ... 0xddf for _31 */ -#define LBR_INFO_MISPRED BIT_ULL(63) -#define LBR_INFO_IN_TX BIT_ULL(62) -#define LBR_INFO_ABORT BIT_ULL(61) -#define LBR_INFO_CYCLES 0xffff - -#define MSR_IA32_PEBS_ENABLE 0x000003f1 -#define MSR_IA32_DS_AREA 0x00000600 -#define MSR_IA32_PERF_CAPABILITIES 0x00000345 -#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 - -#define MSR_IA32_RTIT_CTL 0x00000570 -#define MSR_IA32_RTIT_STATUS 0x00000571 -#define MSR_IA32_RTIT_ADDR0_A 0x00000580 -#define MSR_IA32_RTIT_ADDR0_B 0x00000581 -#define MSR_IA32_RTIT_ADDR1_A 0x00000582 -#define MSR_IA32_RTIT_ADDR1_B 0x00000583 -#define MSR_IA32_RTIT_ADDR2_A 0x00000584 -#define MSR_IA32_RTIT_ADDR2_B 0x00000585 -#define MSR_IA32_RTIT_ADDR3_A 0x00000586 -#define MSR_IA32_RTIT_ADDR3_B 0x00000587 -#define MSR_IA32_RTIT_CR3_MATCH 0x00000572 -#define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560 -#define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561 - -#define MSR_MTRRfix64K_00000 0x00000250 -#define MSR_MTRRfix16K_80000 0x00000258 -#define MSR_MTRRfix16K_A0000 0x00000259 -#define MSR_MTRRfix4K_C0000 0x00000268 -#define MSR_MTRRfix4K_C8000 0x00000269 -#define MSR_MTRRfix4K_D0000 0x0000026a -#define MSR_MTRRfix4K_D8000 0x0000026b -#define MSR_MTRRfix4K_E0000 0x0000026c -#define MSR_MTRRfix4K_E8000 0x0000026d -#define MSR_MTRRfix4K_F0000 0x0000026e -#define MSR_MTRRfix4K_F8000 0x0000026f -#define MSR_MTRRdefType 0x000002ff - -#define MSR_IA32_CR_PAT 0x00000277 - -#define MSR_IA32_DEBUGCTLMSR 0x000001d9 -#define MSR_IA32_LASTBRANCHFROMIP 0x000001db -#define MSR_IA32_LASTBRANCHTOIP 0x000001dc -#define MSR_IA32_LASTINTFROMIP 0x000001dd -#define MSR_IA32_LASTINTTOIP 0x000001de - -/* DEBUGCTLMSR bits (others vary by model): */ -#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ -#define DEBUGCTLMSR_BTF_SHIFT 1 -#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ -#define DEBUGCTLMSR_TR (1UL << 6) -#define DEBUGCTLMSR_BTS (1UL << 7) -#define DEBUGCTLMSR_BTINT (1UL << 8) -#define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) -#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) -#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) -#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 -#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) - -#define MSR_PEBS_FRONTEND 0x000003f7 - -#define MSR_IA32_POWER_CTL 0x000001fc - -#define MSR_IA32_MC0_CTL 0x00000400 -#define MSR_IA32_MC0_STATUS 0x00000401 -#define MSR_IA32_MC0_ADDR 0x00000402 -#define MSR_IA32_MC0_MISC 0x00000403 - -/* C-state Residency Counters */ -#define MSR_PKG_C3_RESIDENCY 0x000003f8 -#define MSR_PKG_C6_RESIDENCY 0x000003f9 -#define MSR_ATOM_PKG_C6_RESIDENCY 0x000003fa -#define MSR_PKG_C7_RESIDENCY 0x000003fa -#define MSR_CORE_C3_RESIDENCY 0x000003fc -#define MSR_CORE_C6_RESIDENCY 0x000003fd -#define MSR_CORE_C7_RESIDENCY 0x000003fe -#define MSR_KNL_CORE_C6_RESIDENCY 0x000003ff -#define MSR_PKG_C2_RESIDENCY 0x0000060d -#define MSR_PKG_C8_RESIDENCY 0x00000630 -#define MSR_PKG_C9_RESIDENCY 0x00000631 -#define MSR_PKG_C10_RESIDENCY 0x00000632 - -/* Interrupt Response Limit */ -#define MSR_PKGC3_IRTL 0x0000060a -#define MSR_PKGC6_IRTL 0x0000060b -#define MSR_PKGC7_IRTL 0x0000060c -#define MSR_PKGC8_IRTL 0x00000633 -#define MSR_PKGC9_IRTL 0x00000634 -#define MSR_PKGC10_IRTL 0x00000635 - -/* Run Time Average Power Limiting (RAPL) Interface */ - -#define MSR_RAPL_POWER_UNIT 0x00000606 - -#define MSR_PKG_POWER_LIMIT 0x00000610 -#define MSR_PKG_ENERGY_STATUS 0x00000611 -#define MSR_PKG_PERF_STATUS 0x00000613 -#define MSR_PKG_POWER_INFO 0x00000614 - -#define MSR_DRAM_POWER_LIMIT 0x00000618 -#define MSR_DRAM_ENERGY_STATUS 0x00000619 -#define MSR_DRAM_PERF_STATUS 0x0000061b -#define MSR_DRAM_POWER_INFO 0x0000061c - -#define MSR_PP0_POWER_LIMIT 0x00000638 -#define MSR_PP0_ENERGY_STATUS 0x00000639 -#define MSR_PP0_POLICY 0x0000063a -#define MSR_PP0_PERF_STATUS 0x0000063b - -#define MSR_PP1_POWER_LIMIT 0x00000640 -#define MSR_PP1_ENERGY_STATUS 0x00000641 -#define MSR_PP1_POLICY 0x00000642 - -/* Config TDP MSRs */ -#define MSR_CONFIG_TDP_NOMINAL 0x00000648 -#define MSR_CONFIG_TDP_LEVEL_1 0x00000649 -#define MSR_CONFIG_TDP_LEVEL_2 0x0000064A -#define MSR_CONFIG_TDP_CONTROL 0x0000064B -#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C - -#define MSR_PLATFORM_ENERGY_STATUS 0x0000064D - -#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 -#define MSR_PKG_ANY_CORE_C0_RES 0x00000659 -#define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A -#define MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B - -#define MSR_CORE_C1_RES 0x00000660 -#define MSR_MODULE_C6_RES_MS 0x00000664 - -#define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668 -#define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669 - -#define MSR_ATOM_CORE_RATIOS 0x0000066a -#define MSR_ATOM_CORE_VIDS 0x0000066b -#define MSR_ATOM_CORE_TURBO_RATIOS 0x0000066c -#define MSR_ATOM_CORE_TURBO_VIDS 0x0000066d - - -#define MSR_CORE_PERF_LIMIT_REASONS 0x00000690 -#define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 -#define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 - -/* Hardware P state interface */ -#define MSR_PPERF 0x0000064e -#define MSR_PERF_LIMIT_REASONS 0x0000064f -#define MSR_PM_ENABLE 0x00000770 -#define MSR_HWP_CAPABILITIES 0x00000771 -#define MSR_HWP_REQUEST_PKG 0x00000772 -#define MSR_HWP_INTERRUPT 0x00000773 -#define MSR_HWP_REQUEST 0x00000774 -#define MSR_HWP_STATUS 0x00000777 - -/* CPUID.6.EAX */ -#define HWP_BASE_BIT (1<<7) -#define HWP_NOTIFICATIONS_BIT (1<<8) -#define HWP_ACTIVITY_WINDOW_BIT (1<<9) -#define HWP_ENERGY_PERF_PREFERENCE_BIT (1<<10) -#define HWP_PACKAGE_LEVEL_REQUEST_BIT (1<<11) - -/* IA32_HWP_CAPABILITIES */ -#define HWP_HIGHEST_PERF(x) (((x) >> 0) & 0xff) -#define HWP_GUARANTEED_PERF(x) (((x) >> 8) & 0xff) -#define HWP_MOSTEFFICIENT_PERF(x) (((x) >> 16) & 0xff) -#define HWP_LOWEST_PERF(x) (((x) >> 24) & 0xff) - -/* IA32_HWP_REQUEST */ -#define HWP_MIN_PERF(x) (x & 0xff) -#define HWP_MAX_PERF(x) ((x & 0xff) << 8) -#define HWP_DESIRED_PERF(x) ((x & 0xff) << 16) -#define HWP_ENERGY_PERF_PREFERENCE(x) (((unsigned long long) x & 0xff) << 24) -#define HWP_EPP_PERFORMANCE 0x00 -#define HWP_EPP_BALANCE_PERFORMANCE 0x80 -#define HWP_EPP_BALANCE_POWERSAVE 0xC0 -#define HWP_EPP_POWERSAVE 0xFF -#define HWP_ACTIVITY_WINDOW(x) ((unsigned long long)(x & 0xff3) << 32) -#define HWP_PACKAGE_CONTROL(x) ((unsigned long long)(x & 0x1) << 42) - -/* IA32_HWP_STATUS */ -#define HWP_GUARANTEED_CHANGE(x) (x & 0x1) -#define HWP_EXCURSION_TO_MINIMUM(x) (x & 0x4) - -/* IA32_HWP_INTERRUPT */ -#define HWP_CHANGE_TO_GUARANTEED_INT(x) (x & 0x1) -#define HWP_EXCURSION_TO_MINIMUM_INT(x) (x & 0x2) - -#define MSR_AMD64_MC0_MASK 0xc0010044 - -#define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x)) -#define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x)) -#define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x)) -#define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x)) - -#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x)) - -/* These are consecutive and not in the normal 4er MCE bank block */ -#define MSR_IA32_MC0_CTL2 0x00000280 -#define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x)) - -#define MSR_P6_PERFCTR0 0x000000c1 -#define MSR_P6_PERFCTR1 0x000000c2 -#define MSR_P6_EVNTSEL0 0x00000186 -#define MSR_P6_EVNTSEL1 0x00000187 - -#define MSR_KNC_PERFCTR0 0x00000020 -#define MSR_KNC_PERFCTR1 0x00000021 -#define MSR_KNC_EVNTSEL0 0x00000028 -#define MSR_KNC_EVNTSEL1 0x00000029 - -/* Alternative perfctr range with full access. */ -#define MSR_IA32_PMC0 0x000004c1 - -/* AMD64 MSRs. Not complete. See the architecture manual for a more - complete list. */ - -#define MSR_AMD64_PATCH_LEVEL 0x0000008b -#define MSR_AMD64_TSC_RATIO 0xc0000104 -#define MSR_AMD64_NB_CFG 0xc001001f -#define MSR_AMD64_PATCH_LOADER 0xc0010020 -#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 -#define MSR_AMD64_OSVW_STATUS 0xc0010141 -#define MSR_AMD64_LS_CFG 0xc0011020 -#define MSR_AMD64_DC_CFG 0xc0011022 -#define MSR_AMD64_BU_CFG2 0xc001102a -#define MSR_AMD64_IBSFETCHCTL 0xc0011030 -#define MSR_AMD64_IBSFETCHLINAD 0xc0011031 -#define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032 -#define MSR_AMD64_IBSFETCH_REG_COUNT 3 -#define MSR_AMD64_IBSFETCH_REG_MASK ((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1) -#define MSR_AMD64_IBSOPCTL 0xc0011033 -#define MSR_AMD64_IBSOPRIP 0xc0011034 -#define MSR_AMD64_IBSOPDATA 0xc0011035 -#define MSR_AMD64_IBSOPDATA2 0xc0011036 -#define MSR_AMD64_IBSOPDATA3 0xc0011037 -#define MSR_AMD64_IBSDCLINAD 0xc0011038 -#define MSR_AMD64_IBSDCPHYSAD 0xc0011039 -#define MSR_AMD64_IBSOP_REG_COUNT 7 -#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1) -#define MSR_AMD64_IBSCTL 0xc001103a -#define MSR_AMD64_IBSBRTARGET 0xc001103b -#define MSR_AMD64_IBSOPDATA4 0xc001103d -#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ -#define MSR_AMD64_SEV 0xc0010131 -#define MSR_AMD64_SEV_ENABLED_BIT 0 -#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) - -/* Fam 17h MSRs */ -#define MSR_F17H_IRPERF 0xc00000e9 - -/* Fam 16h MSRs */ -#define MSR_F16H_L2I_PERF_CTL 0xc0010230 -#define MSR_F16H_L2I_PERF_CTR 0xc0010231 -#define MSR_F16H_DR1_ADDR_MASK 0xc0011019 -#define MSR_F16H_DR2_ADDR_MASK 0xc001101a -#define MSR_F16H_DR3_ADDR_MASK 0xc001101b -#define MSR_F16H_DR0_ADDR_MASK 0xc0011027 - -/* Fam 15h MSRs */ -#define MSR_F15H_PERF_CTL 0xc0010200 -#define MSR_F15H_PERF_CTR 0xc0010201 -#define MSR_F15H_NB_PERF_CTL 0xc0010240 -#define MSR_F15H_NB_PERF_CTR 0xc0010241 -#define MSR_F15H_PTSC 0xc0010280 -#define MSR_F15H_IC_CFG 0xc0011021 - -/* Fam 10h MSRs */ -#define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 -#define FAM10H_MMIO_CONF_ENABLE (1<<0) -#define FAM10H_MMIO_CONF_BUSRANGE_MASK 0xf -#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2 -#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL -#define FAM10H_MMIO_CONF_BASE_SHIFT 20 -#define MSR_FAM10H_NODE_ID 0xc001100c -#define MSR_F10H_DECFG 0xc0011029 -#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 -#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT) - -/* K8 MSRs */ -#define MSR_K8_TOP_MEM1 0xc001001a -#define MSR_K8_TOP_MEM2 0xc001001d -#define MSR_K8_SYSCFG 0xc0010010 -#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT 23 -#define MSR_K8_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT) -#define MSR_K8_INT_PENDING_MSG 0xc0010055 -/* C1E active bits in int pending message */ -#define K8_INTP_C1E_ACTIVE_MASK 0x18000000 -#define MSR_K8_TSEG_ADDR 0xc0010112 -#define MSR_K8_TSEG_MASK 0xc0010113 -#define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */ -#define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */ -#define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */ - -/* K7 MSRs */ -#define MSR_K7_EVNTSEL0 0xc0010000 -#define MSR_K7_PERFCTR0 0xc0010004 -#define MSR_K7_EVNTSEL1 0xc0010001 -#define MSR_K7_PERFCTR1 0xc0010005 -#define MSR_K7_EVNTSEL2 0xc0010002 -#define MSR_K7_PERFCTR2 0xc0010006 -#define MSR_K7_EVNTSEL3 0xc0010003 -#define MSR_K7_PERFCTR3 0xc0010007 -#define MSR_K7_CLK_CTL 0xc001001b -#define MSR_K7_HWCR 0xc0010015 -#define MSR_K7_HWCR_SMMLOCK_BIT 0 -#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) -#define MSR_K7_FID_VID_CTL 0xc0010041 -#define MSR_K7_FID_VID_STATUS 0xc0010042 - -/* K6 MSRs */ -#define MSR_K6_WHCR 0xc0000082 -#define MSR_K6_UWCCR 0xc0000085 -#define MSR_K6_EPMR 0xc0000086 -#define MSR_K6_PSOR 0xc0000087 -#define MSR_K6_PFIR 0xc0000088 - -/* Centaur-Hauls/IDT defined MSRs. */ -#define MSR_IDT_FCR1 0x00000107 -#define MSR_IDT_FCR2 0x00000108 -#define MSR_IDT_FCR3 0x00000109 -#define MSR_IDT_FCR4 0x0000010a - -#define MSR_IDT_MCR0 0x00000110 -#define MSR_IDT_MCR1 0x00000111 -#define MSR_IDT_MCR2 0x00000112 -#define MSR_IDT_MCR3 0x00000113 -#define MSR_IDT_MCR4 0x00000114 -#define MSR_IDT_MCR5 0x00000115 -#define MSR_IDT_MCR6 0x00000116 -#define MSR_IDT_MCR7 0x00000117 -#define MSR_IDT_MCR_CTRL 0x00000120 - -/* VIA Cyrix defined MSRs*/ -#define MSR_VIA_FCR 0x00001107 -#define MSR_VIA_LONGHAUL 0x0000110a -#define MSR_VIA_RNG 0x0000110b -#define MSR_VIA_BCR2 0x00001147 - -/* Transmeta defined MSRs */ -#define MSR_TMTA_LONGRUN_CTRL 0x80868010 -#define MSR_TMTA_LONGRUN_FLAGS 0x80868011 -#define MSR_TMTA_LRTI_READOUT 0x80868018 -#define MSR_TMTA_LRTI_VOLT_MHZ 0x8086801a - -/* Intel defined MSRs. */ -#define MSR_IA32_P5_MC_ADDR 0x00000000 -#define MSR_IA32_P5_MC_TYPE 0x00000001 -#define MSR_IA32_TSC 0x00000010 -#define MSR_IA32_PLATFORM_ID 0x00000017 -#define MSR_IA32_EBL_CR_POWERON 0x0000002a -#define MSR_EBC_FREQUENCY_ID 0x0000002c -#define MSR_SMI_COUNT 0x00000034 -#define MSR_IA32_FEATURE_CONTROL 0x0000003a -#define MSR_IA32_TSC_ADJUST 0x0000003b -#define MSR_IA32_BNDCFGS 0x00000d90 - -#define MSR_IA32_BNDCFGS_RSVD 0x00000ffc - -#define MSR_IA32_XSS 0x00000da0 - -#define FEATURE_CONTROL_LOCKED (1<<0) -#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1) -#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2) -#define FEATURE_CONTROL_LMCE (1<<20) - -#define MSR_IA32_APICBASE 0x0000001b -#define MSR_IA32_APICBASE_BSP (1<<8) -#define MSR_IA32_APICBASE_ENABLE (1<<11) -#define MSR_IA32_APICBASE_BASE (0xfffff<<12) - #define APIC_BASE_MSR 0x800 #define X2APIC_ENABLE (1UL << 10) #define APIC_ICR 0x300 @@ -813,291 +377,7 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); #define APIC_VECTOR_MASK 0x000FF #define APIC_ICR2 0x310 -#define MSR_IA32_TSCDEADLINE 0x000006e0 - -#define MSR_IA32_UCODE_WRITE 0x00000079 -#define MSR_IA32_UCODE_REV 0x0000008b - -#define MSR_IA32_SMM_MONITOR_CTL 0x0000009b -#define MSR_IA32_SMBASE 0x0000009e - -#define MSR_IA32_PERF_STATUS 0x00000198 -#define MSR_IA32_PERF_CTL 0x00000199 -#define INTEL_PERF_CTL_MASK 0xffff -#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 -#define MSR_AMD_PERF_STATUS 0xc0010063 -#define MSR_AMD_PERF_CTL 0xc0010062 - -#define MSR_IA32_MPERF 0x000000e7 -#define MSR_IA32_APERF 0x000000e8 - -#define MSR_IA32_THERM_CONTROL 0x0000019a -#define MSR_IA32_THERM_INTERRUPT 0x0000019b - -#define THERM_INT_HIGH_ENABLE (1 << 0) -#define THERM_INT_LOW_ENABLE (1 << 1) -#define THERM_INT_PLN_ENABLE (1 << 24) - -#define MSR_IA32_THERM_STATUS 0x0000019c - -#define THERM_STATUS_PROCHOT (1 << 0) -#define THERM_STATUS_POWER_LIMIT (1 << 10) - -#define MSR_THERM2_CTL 0x0000019d - -#define MSR_THERM2_CTL_TM_SELECT (1ULL << 16) - -#define MSR_IA32_MISC_ENABLE 0x000001a0 - -#define MSR_IA32_TEMPERATURE_TARGET 0x000001a2 - -#define MSR_MISC_FEATURE_CONTROL 0x000001a4 -#define MSR_MISC_PWR_MGMT 0x000001aa - -#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 -#define ENERGY_PERF_BIAS_PERFORMANCE 0 -#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE 4 -#define ENERGY_PERF_BIAS_NORMAL 6 -#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE 8 -#define ENERGY_PERF_BIAS_POWERSAVE 15 - -#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1 - -#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0) -#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10) - -#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2 - -#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0) -#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) -#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) - -/* Thermal Thresholds Support */ -#define THERM_INT_THRESHOLD0_ENABLE (1 << 15) -#define THERM_SHIFT_THRESHOLD0 8 -#define THERM_MASK_THRESHOLD0 (0x7f << THERM_SHIFT_THRESHOLD0) -#define THERM_INT_THRESHOLD1_ENABLE (1 << 23) -#define THERM_SHIFT_THRESHOLD1 16 -#define THERM_MASK_THRESHOLD1 (0x7f << THERM_SHIFT_THRESHOLD1) -#define THERM_STATUS_THRESHOLD0 (1 << 6) -#define THERM_LOG_THRESHOLD0 (1 << 7) -#define THERM_STATUS_THRESHOLD1 (1 << 8) -#define THERM_LOG_THRESHOLD1 (1 << 9) - -/* MISC_ENABLE bits: architectural */ -#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT 0 -#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) -#define MSR_IA32_MISC_ENABLE_TCC_BIT 1 -#define MSR_IA32_MISC_ENABLE_TCC (1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT) -#define MSR_IA32_MISC_ENABLE_EMON_BIT 7 -#define MSR_IA32_MISC_ENABLE_EMON (1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT) -#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT 11 -#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT) -#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT 12 -#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT) -#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT 16 -#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT) -#define MSR_IA32_MISC_ENABLE_MWAIT_BIT 18 -#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT) -#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT 22 -#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) -#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT 23 -#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT) -#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT 34 -#define MSR_IA32_MISC_ENABLE_XD_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT) - -/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */ -#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT 2 -#define MSR_IA32_MISC_ENABLE_X87_COMPAT (1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT) -#define MSR_IA32_MISC_ENABLE_TM1_BIT 3 -#define MSR_IA32_MISC_ENABLE_TM1 (1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT) -#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT 4 -#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT) -#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT 6 -#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT) -#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT 8 -#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT) -#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT 9 -#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) -#define MSR_IA32_MISC_ENABLE_FERR_BIT 10 -#define MSR_IA32_MISC_ENABLE_FERR (1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT) -#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT 10 -#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX (1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT) -#define MSR_IA32_MISC_ENABLE_TM2_BIT 13 -#define MSR_IA32_MISC_ENABLE_TM2 (1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT) -#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT 19 -#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT) -#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT 20 -#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT) -#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT 24 -#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT (1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT) -#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT 37 -#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT) -#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT 38 -#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT) -#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 -#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) - -/* MISC_FEATURES_ENABLES non-architectural features */ -#define MSR_MISC_FEATURES_ENABLES 0x00000140 - -#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT 0 -#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT) -#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT 1 - -#define MSR_IA32_TSC_DEADLINE 0x000006E0 - -/* P4/Xeon+ specific */ -#define MSR_IA32_MCG_EAX 0x00000180 -#define MSR_IA32_MCG_EBX 0x00000181 -#define MSR_IA32_MCG_ECX 0x00000182 -#define MSR_IA32_MCG_EDX 0x00000183 -#define MSR_IA32_MCG_ESI 0x00000184 -#define MSR_IA32_MCG_EDI 0x00000185 -#define MSR_IA32_MCG_EBP 0x00000186 -#define MSR_IA32_MCG_ESP 0x00000187 -#define MSR_IA32_MCG_EFLAGS 0x00000188 -#define MSR_IA32_MCG_EIP 0x00000189 -#define MSR_IA32_MCG_RESERVED 0x0000018a - -/* Pentium IV performance counter MSRs */ -#define MSR_P4_BPU_PERFCTR0 0x00000300 -#define MSR_P4_BPU_PERFCTR1 0x00000301 -#define MSR_P4_BPU_PERFCTR2 0x00000302 -#define MSR_P4_BPU_PERFCTR3 0x00000303 -#define MSR_P4_MS_PERFCTR0 0x00000304 -#define MSR_P4_MS_PERFCTR1 0x00000305 -#define MSR_P4_MS_PERFCTR2 0x00000306 -#define MSR_P4_MS_PERFCTR3 0x00000307 -#define MSR_P4_FLAME_PERFCTR0 0x00000308 -#define MSR_P4_FLAME_PERFCTR1 0x00000309 -#define MSR_P4_FLAME_PERFCTR2 0x0000030a -#define MSR_P4_FLAME_PERFCTR3 0x0000030b -#define MSR_P4_IQ_PERFCTR0 0x0000030c -#define MSR_P4_IQ_PERFCTR1 0x0000030d -#define MSR_P4_IQ_PERFCTR2 0x0000030e -#define MSR_P4_IQ_PERFCTR3 0x0000030f -#define MSR_P4_IQ_PERFCTR4 0x00000310 -#define MSR_P4_IQ_PERFCTR5 0x00000311 -#define MSR_P4_BPU_CCCR0 0x00000360 -#define MSR_P4_BPU_CCCR1 0x00000361 -#define MSR_P4_BPU_CCCR2 0x00000362 -#define MSR_P4_BPU_CCCR3 0x00000363 -#define MSR_P4_MS_CCCR0 0x00000364 -#define MSR_P4_MS_CCCR1 0x00000365 -#define MSR_P4_MS_CCCR2 0x00000366 -#define MSR_P4_MS_CCCR3 0x00000367 -#define MSR_P4_FLAME_CCCR0 0x00000368 -#define MSR_P4_FLAME_CCCR1 0x00000369 -#define MSR_P4_FLAME_CCCR2 0x0000036a -#define MSR_P4_FLAME_CCCR3 0x0000036b -#define MSR_P4_IQ_CCCR0 0x0000036c -#define MSR_P4_IQ_CCCR1 0x0000036d -#define MSR_P4_IQ_CCCR2 0x0000036e -#define MSR_P4_IQ_CCCR3 0x0000036f -#define MSR_P4_IQ_CCCR4 0x00000370 -#define MSR_P4_IQ_CCCR5 0x00000371 -#define MSR_P4_ALF_ESCR0 0x000003ca -#define MSR_P4_ALF_ESCR1 0x000003cb -#define MSR_P4_BPU_ESCR0 0x000003b2 -#define MSR_P4_BPU_ESCR1 0x000003b3 -#define MSR_P4_BSU_ESCR0 0x000003a0 -#define MSR_P4_BSU_ESCR1 0x000003a1 -#define MSR_P4_CRU_ESCR0 0x000003b8 -#define MSR_P4_CRU_ESCR1 0x000003b9 -#define MSR_P4_CRU_ESCR2 0x000003cc -#define MSR_P4_CRU_ESCR3 0x000003cd -#define MSR_P4_CRU_ESCR4 0x000003e0 -#define MSR_P4_CRU_ESCR5 0x000003e1 -#define MSR_P4_DAC_ESCR0 0x000003a8 -#define MSR_P4_DAC_ESCR1 0x000003a9 -#define MSR_P4_FIRM_ESCR0 0x000003a4 -#define MSR_P4_FIRM_ESCR1 0x000003a5 -#define MSR_P4_FLAME_ESCR0 0x000003a6 -#define MSR_P4_FLAME_ESCR1 0x000003a7 -#define MSR_P4_FSB_ESCR0 0x000003a2 -#define MSR_P4_FSB_ESCR1 0x000003a3 -#define MSR_P4_IQ_ESCR0 0x000003ba -#define MSR_P4_IQ_ESCR1 0x000003bb -#define MSR_P4_IS_ESCR0 0x000003b4 -#define MSR_P4_IS_ESCR1 0x000003b5 -#define MSR_P4_ITLB_ESCR0 0x000003b6 -#define MSR_P4_ITLB_ESCR1 0x000003b7 -#define MSR_P4_IX_ESCR0 0x000003c8 -#define MSR_P4_IX_ESCR1 0x000003c9 -#define MSR_P4_MOB_ESCR0 0x000003aa -#define MSR_P4_MOB_ESCR1 0x000003ab -#define MSR_P4_MS_ESCR0 0x000003c0 -#define MSR_P4_MS_ESCR1 0x000003c1 -#define MSR_P4_PMH_ESCR0 0x000003ac -#define MSR_P4_PMH_ESCR1 0x000003ad -#define MSR_P4_RAT_ESCR0 0x000003bc -#define MSR_P4_RAT_ESCR1 0x000003bd -#define MSR_P4_SAAT_ESCR0 0x000003ae -#define MSR_P4_SAAT_ESCR1 0x000003af -#define MSR_P4_SSU_ESCR0 0x000003be -#define MSR_P4_SSU_ESCR1 0x000003bf /* guess: not in manual */ - -#define MSR_P4_TBPU_ESCR0 0x000003c2 -#define MSR_P4_TBPU_ESCR1 0x000003c3 -#define MSR_P4_TC_ESCR0 0x000003c4 -#define MSR_P4_TC_ESCR1 0x000003c5 -#define MSR_P4_U2L_ESCR0 0x000003b0 -#define MSR_P4_U2L_ESCR1 0x000003b1 - -#define MSR_P4_PEBS_MATRIX_VERT 0x000003f2 - -/* Intel Core-based CPU performance counters */ -#define MSR_CORE_PERF_FIXED_CTR0 0x00000309 -#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a -#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b -#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d -#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e -#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f -#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 - -/* Geode defined MSRs */ -#define MSR_GEODE_BUSCONT_CONF0 0x00001900 - -/* Intel VT MSRs */ -#define MSR_IA32_VMX_BASIC 0x00000480 -#define MSR_IA32_VMX_PINBASED_CTLS 0x00000481 -#define MSR_IA32_VMX_PROCBASED_CTLS 0x00000482 -#define MSR_IA32_VMX_EXIT_CTLS 0x00000483 -#define MSR_IA32_VMX_ENTRY_CTLS 0x00000484 -#define MSR_IA32_VMX_MISC 0x00000485 -#define MSR_IA32_VMX_CR0_FIXED0 0x00000486 -#define MSR_IA32_VMX_CR0_FIXED1 0x00000487 -#define MSR_IA32_VMX_CR4_FIXED0 0x00000488 -#define MSR_IA32_VMX_CR4_FIXED1 0x00000489 -#define MSR_IA32_VMX_VMCS_ENUM 0x0000048a -#define MSR_IA32_VMX_PROCBASED_CTLS2 0x0000048b -#define MSR_IA32_VMX_EPT_VPID_CAP 0x0000048c -#define MSR_IA32_VMX_TRUE_PINBASED_CTLS 0x0000048d -#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e -#define MSR_IA32_VMX_TRUE_EXIT_CTLS 0x0000048f -#define MSR_IA32_VMX_TRUE_ENTRY_CTLS 0x00000490 -#define MSR_IA32_VMX_VMFUNC 0x00000491 - -/* VMX_BASIC bits and bitmasks */ -#define VMX_BASIC_VMCS_SIZE_SHIFT 32 -#define VMX_BASIC_TRUE_CTLS (1ULL << 55) -#define VMX_BASIC_64 0x0001000000000000LLU -#define VMX_BASIC_MEM_TYPE_SHIFT 50 -#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU -#define VMX_BASIC_MEM_TYPE_WB 6LLU -#define VMX_BASIC_INOUT 0x0040000000000000LLU - /* VMX_EPT_VPID_CAP bits */ -#define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21) - -/* MSR_IA32_VMX_MISC bits */ -#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) -#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F -/* AMD-V MSRs */ - -#define MSR_VM_CR 0xc0010114 -#define MSR_VM_IGNNE 0xc0010115 -#define MSR_VM_HSAVE_PA 0xc0010117 +#define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21) #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h new file mode 100644 index 000000000000..f4ea2355dbc2 --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/svm.h @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * tools/testing/selftests/kvm/include/x86_64/svm.h + * This is a copy of arch/x86/include/asm/svm.h + * + */ + +#ifndef SELFTEST_KVM_SVM_H +#define SELFTEST_KVM_SVM_H + +enum { + INTERCEPT_INTR, + INTERCEPT_NMI, + INTERCEPT_SMI, + INTERCEPT_INIT, + INTERCEPT_VINTR, + INTERCEPT_SELECTIVE_CR0, + INTERCEPT_STORE_IDTR, + INTERCEPT_STORE_GDTR, + INTERCEPT_STORE_LDTR, + INTERCEPT_STORE_TR, + INTERCEPT_LOAD_IDTR, + INTERCEPT_LOAD_GDTR, + INTERCEPT_LOAD_LDTR, + INTERCEPT_LOAD_TR, + INTERCEPT_RDTSC, + INTERCEPT_RDPMC, + INTERCEPT_PUSHF, + INTERCEPT_POPF, + INTERCEPT_CPUID, + INTERCEPT_RSM, + INTERCEPT_IRET, + INTERCEPT_INTn, + INTERCEPT_INVD, + INTERCEPT_PAUSE, + INTERCEPT_HLT, + INTERCEPT_INVLPG, + INTERCEPT_INVLPGA, + INTERCEPT_IOIO_PROT, + INTERCEPT_MSR_PROT, + INTERCEPT_TASK_SWITCH, + INTERCEPT_FERR_FREEZE, + INTERCEPT_SHUTDOWN, + INTERCEPT_VMRUN, + INTERCEPT_VMMCALL, + INTERCEPT_VMLOAD, + INTERCEPT_VMSAVE, + INTERCEPT_STGI, + INTERCEPT_CLGI, + INTERCEPT_SKINIT, + INTERCEPT_RDTSCP, + INTERCEPT_ICEBP, + INTERCEPT_WBINVD, + INTERCEPT_MONITOR, + INTERCEPT_MWAIT, + INTERCEPT_MWAIT_COND, + INTERCEPT_XSETBV, + INTERCEPT_RDPRU, +}; + + +struct __attribute__ ((__packed__)) vmcb_control_area { + u32 intercept_cr; + u32 intercept_dr; + u32 intercept_exceptions; + u64 intercept; + u8 reserved_1[40]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u8 reserved_2[3]; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u8 reserved_3[4]; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u64 avic_vapic_bar; + u8 reserved_4[8]; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 virt_ext; + u32 clean; + u32 reserved_5; + u64 next_rip; + u8 insn_len; + u8 insn_bytes[15]; + u64 avic_backing_page; /* Offset 0xe0 */ + u8 reserved_6[8]; /* Offset 0xe8 */ + u64 avic_logical_id; /* Offset 0xf0 */ + u64 avic_physical_id; /* Offset 0xf8 */ + u8 reserved_7[768]; +}; + + +#define TLB_CONTROL_DO_NOTHING 0 +#define TLB_CONTROL_FLUSH_ALL_ASID 1 +#define TLB_CONTROL_FLUSH_ASID 3 +#define TLB_CONTROL_FLUSH_ASID_LOCAL 7 + +#define V_TPR_MASK 0x0f + +#define V_IRQ_SHIFT 8 +#define V_IRQ_MASK (1 << V_IRQ_SHIFT) + +#define V_GIF_SHIFT 9 +#define V_GIF_MASK (1 << V_GIF_SHIFT) + +#define V_INTR_PRIO_SHIFT 16 +#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT) + +#define V_IGN_TPR_SHIFT 20 +#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) + +#define V_INTR_MASKING_SHIFT 24 +#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) + +#define V_GIF_ENABLE_SHIFT 25 +#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT) + +#define AVIC_ENABLE_SHIFT 31 +#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) + +#define LBR_CTL_ENABLE_MASK BIT_ULL(0) +#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) + +#define SVM_INTERRUPT_SHADOW_MASK 1 + +#define SVM_IOIO_STR_SHIFT 2 +#define SVM_IOIO_REP_SHIFT 3 +#define SVM_IOIO_SIZE_SHIFT 4 +#define SVM_IOIO_ASIZE_SHIFT 7 + +#define SVM_IOIO_TYPE_MASK 1 +#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT) +#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT) +#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) +#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) + +#define SVM_VM_CR_VALID_MASK 0x001fULL +#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL +#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL + +#define SVM_NESTED_CTL_NP_ENABLE BIT(0) +#define SVM_NESTED_CTL_SEV_ENABLE BIT(1) + +struct __attribute__ ((__packed__)) vmcb_seg { + u16 selector; + u16 attrib; + u32 limit; + u64 base; +}; + +struct __attribute__ ((__packed__)) vmcb_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + u8 reserved_1[43]; + u8 cpl; + u8 reserved_2[4]; + u64 efer; + u8 reserved_3[112]; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u8 reserved_4[88]; + u64 rsp; + u8 reserved_5[24]; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_6[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; +}; + +struct __attribute__ ((__packed__)) vmcb { + struct vmcb_control_area control; + struct vmcb_save_area save; +}; + +#define SVM_CPUID_FUNC 0x8000000a + +#define SVM_VM_CR_SVM_DISABLE 4 + +#define SVM_SELECTOR_S_SHIFT 4 +#define SVM_SELECTOR_DPL_SHIFT 5 +#define SVM_SELECTOR_P_SHIFT 7 +#define SVM_SELECTOR_AVL_SHIFT 8 +#define SVM_SELECTOR_L_SHIFT 9 +#define SVM_SELECTOR_DB_SHIFT 10 +#define SVM_SELECTOR_G_SHIFT 11 + +#define SVM_SELECTOR_TYPE_MASK (0xf) +#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT) +#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT) +#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT) +#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT) +#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT) +#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT) +#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT) + +#define SVM_SELECTOR_WRITE_MASK (1 << 1) +#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK +#define SVM_SELECTOR_CODE_MASK (1 << 3) + +#define INTERCEPT_CR0_READ 0 +#define INTERCEPT_CR3_READ 3 +#define INTERCEPT_CR4_READ 4 +#define INTERCEPT_CR8_READ 8 +#define INTERCEPT_CR0_WRITE (16 + 0) +#define INTERCEPT_CR3_WRITE (16 + 3) +#define INTERCEPT_CR4_WRITE (16 + 4) +#define INTERCEPT_CR8_WRITE (16 + 8) + +#define INTERCEPT_DR0_READ 0 +#define INTERCEPT_DR1_READ 1 +#define INTERCEPT_DR2_READ 2 +#define INTERCEPT_DR3_READ 3 +#define INTERCEPT_DR4_READ 4 +#define INTERCEPT_DR5_READ 5 +#define INTERCEPT_DR6_READ 6 +#define INTERCEPT_DR7_READ 7 +#define INTERCEPT_DR0_WRITE (16 + 0) +#define INTERCEPT_DR1_WRITE (16 + 1) +#define INTERCEPT_DR2_WRITE (16 + 2) +#define INTERCEPT_DR3_WRITE (16 + 3) +#define INTERCEPT_DR4_WRITE (16 + 4) +#define INTERCEPT_DR5_WRITE (16 + 5) +#define INTERCEPT_DR6_WRITE (16 + 6) +#define INTERCEPT_DR7_WRITE (16 + 7) + +#define SVM_EVTINJ_VEC_MASK 0xff + +#define SVM_EVTINJ_TYPE_SHIFT 8 +#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_VALID (1 << 31) +#define SVM_EVTINJ_VALID_ERR (1 << 11) + +#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK +#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK + +#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR +#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI +#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT +#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT + +#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID +#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR + +#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36 +#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38 +#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44 + +#define SVM_EXITINFO_REG_MASK 0x0F + +#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) + +#endif /* SELFTEST_KVM_SVM_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h new file mode 100644 index 000000000000..cd037917fece --- /dev/null +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * tools/testing/selftests/kvm/include/x86_64/svm_utils.h + * Header for nested SVM testing + * + * Copyright (C) 2020, Red Hat, Inc. + */ + +#ifndef SELFTEST_KVM_SVM_UTILS_H +#define SELFTEST_KVM_SVM_UTILS_H + +#include <stdint.h> +#include "svm.h" +#include "processor.h" + +#define CPUID_SVM_BIT 2 +#define CPUID_SVM BIT_ULL(CPUID_SVM_BIT) + +#define SVM_EXIT_VMMCALL 0x081 + +struct svm_test_data { + /* VMCB */ + struct vmcb *vmcb; /* gva */ + void *vmcb_hva; + uint64_t vmcb_gpa; + + /* host state-save area */ + struct vmcb_save_area *save_area; /* gva */ + void *save_area_hva; + uint64_t save_area_gpa; +}; + +struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva); +void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp); +void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa); +void nested_svm_check_supported(void); + +#endif /* SELFTEST_KVM_SVM_UTILS_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index f52e0ba84fed..3d27069b9ed9 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -18,8 +18,8 @@ /* * Definitions of Primary Processor-Based VM-Execution Controls. */ -#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004 -#define CPU_BASED_USE_TSC_OFFSETING 0x00000008 +#define CPU_BASED_INTR_WINDOW_EXITING 0x00000004 +#define CPU_BASED_USE_TSC_OFFSETTING 0x00000008 #define CPU_BASED_HLT_EXITING 0x00000080 #define CPU_BASED_INVLPG_EXITING 0x00000200 #define CPU_BASED_MWAIT_EXITING 0x00000400 @@ -30,7 +30,7 @@ #define CPU_BASED_CR8_LOAD_EXITING 0x00080000 #define CPU_BASED_CR8_STORE_EXITING 0x00100000 #define CPU_BASED_TPR_SHADOW 0x00200000 -#define CPU_BASED_VIRTUAL_NMI_PENDING 0x00400000 +#define CPU_BASED_NMI_WINDOW_EXITING 0x00400000 #define CPU_BASED_MOV_DR_EXITING 0x00800000 #define CPU_BASED_UNCOND_IO_EXITING 0x01000000 #define CPU_BASED_USE_IO_BITMAPS 0x02000000 @@ -103,7 +103,7 @@ #define EXIT_REASON_EXCEPTION_NMI 0 #define EXIT_REASON_EXTERNAL_INTERRUPT 1 #define EXIT_REASON_TRIPLE_FAULT 2 -#define EXIT_REASON_PENDING_INTERRUPT 7 +#define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 #define EXIT_REASON_TASK_SWITCH 9 #define EXIT_REASON_CPUID 10 diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 41cf45416060..a6dd0401eb50 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1373,6 +1373,42 @@ int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) return ioctl(vcpu->fd, KVM_SET_SREGS, sregs); } +void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu) +{ + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_FPU, fpu); + TEST_ASSERT(ret == 0, "KVM_GET_FPU failed, rc: %i errno: %i (%s)", + ret, errno, strerror(errno)); +} + +void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu) +{ + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_FPU, fpu); + TEST_ASSERT(ret == 0, "KVM_SET_FPU failed, rc: %i errno: %i (%s)", + ret, errno, strerror(errno)); +} + +void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg) +{ + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, reg); + TEST_ASSERT(ret == 0, "KVM_GET_ONE_REG failed, rc: %i errno: %i (%s)", + ret, errno, strerror(errno)); +} + +void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg) +{ + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, reg); + TEST_ASSERT(ret == 0, "KVM_SET_ONE_REG failed, rc: %i errno: %i (%s)", + ret, errno, strerror(errno)); +} + /* * VCPU Ioctl * diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c new file mode 100644 index 000000000000..6e05a8fc3fe0 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * tools/testing/selftests/kvm/lib/x86_64/svm.c + * Helpers used for nested SVM testing + * Largely inspired from KVM unit test svm.c + * + * Copyright (C) 2020, Red Hat, Inc. + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "../kvm_util_internal.h" +#include "processor.h" +#include "svm_util.h" + +struct gpr64_regs guest_regs; +u64 rflags; + +/* Allocate memory regions for nested SVM tests. + * + * Input Args: + * vm - The VM to allocate guest-virtual addresses in. + * + * Output Args: + * p_svm_gva - The guest virtual address for the struct svm_test_data. + * + * Return: + * Pointer to structure with the addresses of the SVM areas. + */ +struct svm_test_data * +vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva) +{ + vm_vaddr_t svm_gva = vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + struct svm_test_data *svm = addr_gva2hva(vm, svm_gva); + + svm->vmcb = (void *)vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + svm->vmcb_hva = addr_gva2hva(vm, (uintptr_t)svm->vmcb); + svm->vmcb_gpa = addr_gva2gpa(vm, (uintptr_t)svm->vmcb); + + svm->save_area = (void *)vm_vaddr_alloc(vm, getpagesize(), + 0x10000, 0, 0); + svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area); + svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area); + + *p_svm_gva = svm_gva; + return svm; +} + +static void vmcb_set_seg(struct vmcb_seg *seg, u16 selector, + u64 base, u32 limit, u32 attr) +{ + seg->selector = selector; + seg->attrib = attr; + seg->limit = limit; + seg->base = base; +} + +void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp) +{ + struct vmcb *vmcb = svm->vmcb; + uint64_t vmcb_gpa = svm->vmcb_gpa; + struct vmcb_save_area *save = &vmcb->save; + struct vmcb_control_area *ctrl = &vmcb->control; + u32 data_seg_attr = 3 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK + | SVM_SELECTOR_DB_MASK | SVM_SELECTOR_G_MASK; + u32 code_seg_attr = 9 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK + | SVM_SELECTOR_L_MASK | SVM_SELECTOR_G_MASK; + uint64_t efer; + + efer = rdmsr(MSR_EFER); + wrmsr(MSR_EFER, efer | EFER_SVME); + wrmsr(MSR_VM_HSAVE_PA, svm->save_area_gpa); + + memset(vmcb, 0, sizeof(*vmcb)); + asm volatile ("vmsave\n\t" : : "a" (vmcb_gpa) : "memory"); + vmcb_set_seg(&save->es, get_es(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->cs, get_cs(), 0, -1U, code_seg_attr); + vmcb_set_seg(&save->ss, get_ss(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->ds, get_ds(), 0, -1U, data_seg_attr); + vmcb_set_seg(&save->gdtr, 0, get_gdt().address, get_gdt().size, 0); + vmcb_set_seg(&save->idtr, 0, get_idt().address, get_idt().size, 0); + + ctrl->asid = 1; + save->cpl = 0; + save->efer = rdmsr(MSR_EFER); + asm volatile ("mov %%cr4, %0" : "=r"(save->cr4) : : "memory"); + asm volatile ("mov %%cr3, %0" : "=r"(save->cr3) : : "memory"); + asm volatile ("mov %%cr0, %0" : "=r"(save->cr0) : : "memory"); + asm volatile ("mov %%dr7, %0" : "=r"(save->dr7) : : "memory"); + asm volatile ("mov %%dr6, %0" : "=r"(save->dr6) : : "memory"); + asm volatile ("mov %%cr2, %0" : "=r"(save->cr2) : : "memory"); + save->g_pat = rdmsr(MSR_IA32_CR_PAT); + save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR); + ctrl->intercept = (1ULL << INTERCEPT_VMRUN) | + (1ULL << INTERCEPT_VMMCALL); + + vmcb->save.rip = (u64)guest_rip; + vmcb->save.rsp = (u64)guest_rsp; + guest_regs.rdi = (u64)svm; +} + +/* + * save/restore 64-bit general registers except rax, rip, rsp + * which are directly handed through the VMCB guest processor state + */ +#define SAVE_GPR_C \ + "xchg %%rbx, guest_regs+0x20\n\t" \ + "xchg %%rcx, guest_regs+0x10\n\t" \ + "xchg %%rdx, guest_regs+0x18\n\t" \ + "xchg %%rbp, guest_regs+0x30\n\t" \ + "xchg %%rsi, guest_regs+0x38\n\t" \ + "xchg %%rdi, guest_regs+0x40\n\t" \ + "xchg %%r8, guest_regs+0x48\n\t" \ + "xchg %%r9, guest_regs+0x50\n\t" \ + "xchg %%r10, guest_regs+0x58\n\t" \ + "xchg %%r11, guest_regs+0x60\n\t" \ + "xchg %%r12, guest_regs+0x68\n\t" \ + "xchg %%r13, guest_regs+0x70\n\t" \ + "xchg %%r14, guest_regs+0x78\n\t" \ + "xchg %%r15, guest_regs+0x80\n\t" + +#define LOAD_GPR_C SAVE_GPR_C + +/* + * selftests do not use interrupts so we dropped clgi/sti/cli/stgi + * for now. registers involved in LOAD/SAVE_GPR_C are eventually + * unmodified so they do not need to be in the clobber list. + */ +void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa) +{ + asm volatile ( + "vmload\n\t" + "mov rflags, %%r15\n\t" // rflags + "mov %%r15, 0x170(%[vmcb])\n\t" + "mov guest_regs, %%r15\n\t" // rax + "mov %%r15, 0x1f8(%[vmcb])\n\t" + LOAD_GPR_C + "vmrun\n\t" + SAVE_GPR_C + "mov 0x170(%[vmcb]), %%r15\n\t" // rflags + "mov %%r15, rflags\n\t" + "mov 0x1f8(%[vmcb]), %%r15\n\t" // rax + "mov %%r15, guest_regs\n\t" + "vmsave\n\t" + : : [vmcb] "r" (vmcb), [vmcb_gpa] "a" (vmcb_gpa) + : "r15", "memory"); +} + +void nested_svm_check_supported(void) +{ + struct kvm_cpuid_entry2 *entry = + kvm_get_supported_cpuid_entry(0x80000001); + + if (!(entry->ecx & CPUID_SVM)) { + fprintf(stderr, "nested SVM not enabled, skipping test\n"); + exit(KSFT_SKIP); + } +} + diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index f6ec97b7eaef..7aaa99ca4dbc 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -157,11 +157,11 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx) * Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON * outside of SMX causes a #GP. */ - required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; - required |= FEATURE_CONTROL_LOCKED; - feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL); + required = FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; + required |= FEAT_CTL_LOCKED; + feature_control = rdmsr(MSR_IA32_FEAT_CTL); if ((feature_control & required) != required) - wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required); + wrmsr(MSR_IA32_FEAT_CTL, feature_control | required); /* Enter VMX root operation. */ *(uint32_t *)(vmx->vmxon) = vmcs_revision(); @@ -288,9 +288,9 @@ static inline void init_vmcs_host_state(void) vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE)); vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE)); vmwrite(HOST_TR_BASE, - get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr()))); - vmwrite(HOST_GDTR_BASE, get_gdt_base()); - vmwrite(HOST_IDTR_BASE, get_idt_base()); + get_desc64_base((struct desc64 *)(get_gdt().address + get_tr()))); + vmwrite(HOST_GDTR_BASE, get_gdt().address); + vmwrite(HOST_IDTR_BASE, get_idt().address); vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP)); vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP)); } diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c new file mode 100644 index 000000000000..1485bc6c8999 --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/resets.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test for s390x CPU resets + * + * Copyright (C) 2020, IBM + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" + +#define VCPU_ID 3 +#define LOCAL_IRQS 32 + +struct kvm_s390_irq buf[VCPU_ID + LOCAL_IRQS]; + +struct kvm_vm *vm; +struct kvm_run *run; +struct kvm_sync_regs *regs; +static uint64_t regs_null[16]; + +static uint64_t crs[16] = { 0x40000ULL, + 0x42000ULL, + 0, 0, 0, 0, 0, + 0x43000ULL, + 0, 0, 0, 0, 0, + 0x44000ULL, + 0, 0 +}; + +static void guest_code_initial(void) +{ + /* Round toward 0 */ + uint32_t fpc = 0x11; + + /* Dirty registers */ + asm volatile ( + " lctlg 0,15,%0\n" + " sfpc %1\n" + : : "Q" (crs), "d" (fpc)); + GUEST_SYNC(0); +} + +static void test_one_reg(uint64_t id, uint64_t value) +{ + struct kvm_one_reg reg; + uint64_t eval_reg; + + reg.addr = (uintptr_t)&eval_reg; + reg.id = id; + vcpu_get_reg(vm, VCPU_ID, ®); + TEST_ASSERT(eval_reg == value, "value == %s", value); +} + +static void assert_noirq(void) +{ + struct kvm_s390_irq_state irq_state; + int irqs; + + irq_state.len = sizeof(buf); + irq_state.buf = (unsigned long)buf; + irqs = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_GET_IRQ_STATE, &irq_state); + /* + * irqs contains the number of retrieved interrupts. Any interrupt + * (notably, the emergency call interrupt we have injected) should + * be cleared by the resets, so this should be 0. + */ + TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d\n", errno); + TEST_ASSERT(!irqs, "IRQ pending"); +} + +static void assert_clear(void) +{ + struct kvm_sregs sregs; + struct kvm_regs regs; + struct kvm_fpu fpu; + + vcpu_regs_get(vm, VCPU_ID, ®s); + TEST_ASSERT(!memcmp(®s.gprs, regs_null, sizeof(regs.gprs)), "grs == 0"); + + vcpu_sregs_get(vm, VCPU_ID, &sregs); + TEST_ASSERT(!memcmp(&sregs.acrs, regs_null, sizeof(sregs.acrs)), "acrs == 0"); + + vcpu_fpu_get(vm, VCPU_ID, &fpu); + TEST_ASSERT(!memcmp(&fpu.fprs, regs_null, sizeof(fpu.fprs)), "fprs == 0"); +} + +static void assert_initial(void) +{ + struct kvm_sregs sregs; + struct kvm_fpu fpu; + + vcpu_sregs_get(vm, VCPU_ID, &sregs); + TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0"); + TEST_ASSERT(sregs.crs[14] == 0xC2000000UL, "cr14 == 0xC2000000"); + TEST_ASSERT(!memcmp(&sregs.crs[1], regs_null, sizeof(sregs.crs[1]) * 12), + "cr1-13 == 0"); + TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0"); + + vcpu_fpu_get(vm, VCPU_ID, &fpu); + TEST_ASSERT(!fpu.fpc, "fpc == 0"); + + test_one_reg(KVM_REG_S390_GBEA, 1); + test_one_reg(KVM_REG_S390_PP, 0); + test_one_reg(KVM_REG_S390_TODPR, 0); + test_one_reg(KVM_REG_S390_CPU_TIMER, 0); + test_one_reg(KVM_REG_S390_CLOCK_COMP, 0); +} + +static void assert_normal(void) +{ + test_one_reg(KVM_REG_S390_PFTOKEN, KVM_S390_PFAULT_TOKEN_INVALID); + assert_noirq(); +} + +static void inject_irq(int cpu_id) +{ + struct kvm_s390_irq_state irq_state; + struct kvm_s390_irq *irq = &buf[0]; + int irqs; + + /* Inject IRQ */ + irq_state.len = sizeof(struct kvm_s390_irq); + irq_state.buf = (unsigned long)buf; + irq->type = KVM_S390_INT_EMERGENCY; + irq->u.emerg.code = cpu_id; + irqs = _vcpu_ioctl(vm, cpu_id, KVM_S390_SET_IRQ_STATE, &irq_state); + TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d\n", errno); +} + +static void test_normal(void) +{ + printf("Testing normal reset\n"); + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code_initial); + run = vcpu_state(vm, VCPU_ID); + regs = &run->s.regs; + + vcpu_run(vm, VCPU_ID); + + inject_irq(VCPU_ID); + + vcpu_ioctl(vm, VCPU_ID, KVM_S390_NORMAL_RESET, 0); + assert_normal(); + kvm_vm_free(vm); +} + +static void test_initial(void) +{ + printf("Testing initial reset\n"); + vm = vm_create_default(VCPU_ID, 0, guest_code_initial); + run = vcpu_state(vm, VCPU_ID); + regs = &run->s.regs; + + vcpu_run(vm, VCPU_ID); + + inject_irq(VCPU_ID); + + vcpu_ioctl(vm, VCPU_ID, KVM_S390_INITIAL_RESET, 0); + assert_normal(); + assert_initial(); + kvm_vm_free(vm); +} + +static void test_clear(void) +{ + printf("Testing clear reset\n"); + vm = vm_create_default(VCPU_ID, 0, guest_code_initial); + run = vcpu_state(vm, VCPU_ID); + regs = &run->s.regs; + + vcpu_run(vm, VCPU_ID); + + inject_irq(VCPU_ID); + + vcpu_ioctl(vm, VCPU_ID, KVM_S390_CLEAR_RESET, 0); + assert_normal(); + assert_initial(); + assert_clear(); + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + setbuf(stdout, NULL); /* Tell stdout not to buffer its content */ + + test_initial(); + if (kvm_check_cap(KVM_CAP_S390_VCPU_RESETS)) { + test_normal(); + test_clear(); + } + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c new file mode 100644 index 000000000000..e280f68f6365 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * svm_vmcall_test + * + * Copyright (C) 2020, Red Hat, Inc. + * + * Nested SVM testing: VMCALL + */ + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" + +#define VCPU_ID 5 + +static struct kvm_vm *vm; + +static void l2_guest_code(struct svm_test_data *svm) +{ + __asm__ __volatile__("vmcall"); +} + +static void l1_guest_code(struct svm_test_data *svm) +{ + #define L2_GUEST_STACK_SIZE 64 + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + /* Prepare for L2 execution. */ + generic_svm_setup(svm, l2_guest_code, + &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + run_guest(vmcb, svm->vmcb_gpa); + + GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL); + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + vm_vaddr_t svm_gva; + + nested_svm_check_supported(); + + vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + vcpu_alloc_svm(vm, &svm_gva); + vcpu_args_set(vm, VCPU_ID, 1, svm_gva); + + for (;;) { + volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Got exit_reason other than KVM_EXIT_IO: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_ASSERT(false, "%s", + (const char *)uc.args[0]); + /* NOT REACHED */ + case UCALL_SYNC: + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, + "Unknown ucall 0x%x.", uc.cmd); + } + } +done: + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index 5590fd2bcf87..69e482a95c47 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -98,7 +98,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages) prepare_vmcs(vmx_pages, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); control = vmreadz(CPU_BASED_VM_EXEC_CONTROL); - control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING; + control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING; vmwrite(CPU_BASED_VM_EXEC_CONTROL, control); vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE); diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 1c8a1963d03f..3ed0134a764d 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -83,17 +83,20 @@ else $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) endif +define INSTALL_SINGLE_RULE + $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) + $(if $(INSTALL_LIST),@echo rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) + $(if $(INSTALL_LIST),@rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/) +endef + define INSTALL_RULE - @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ - fi - @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ - mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ - fi + $(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_FILES)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE) endef install: all diff --git a/tools/testing/selftests/livepatch/README b/tools/testing/selftests/livepatch/README index b73cd0e2dd51..621d325425c2 100644 --- a/tools/testing/selftests/livepatch/README +++ b/tools/testing/selftests/livepatch/README @@ -35,7 +35,7 @@ Adding tests ------------ See the common functions.sh file for the existing collection of utility -functions, most importantly set_dynamic_debug() and check_result(). The +functions, most importantly setup_config() and check_result(). The latter function greps the kernel's ring buffer for "livepatch:" and "test_klp" strings, so tests be sure to include one of those strings for result comparison. Other utility functions include general module diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index a6e3d5517a6f..2aab9791791d 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -64,7 +64,6 @@ function set_dynamic_debug() { } function set_ftrace_enabled() { - local sysctl="$1" result=$(sysctl kernel.ftrace_enabled="$1" 2>&1 | paste --serial --delimiters=' ') echo "livepatch: $result" > /dev/kmsg } diff --git a/tools/testing/selftests/lkdtm/Makefile b/tools/testing/selftests/lkdtm/Makefile new file mode 100644 index 000000000000..1bcc9ee990eb --- /dev/null +++ b/tools/testing/selftests/lkdtm/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for LKDTM regression tests + +include ../lib.mk + +# NOTE: $(OUTPUT) won't get default value if used before lib.mk +TEST_FILES := tests.txt +TEST_GEN_PROGS = $(patsubst %,$(OUTPUT)/%.sh,$(shell awk '{print $$1}' tests.txt | sed -e 's/\#//')) +all: $(TEST_GEN_PROGS) + +$(OUTPUT)/%: run.sh tests.txt + install -m 0744 run.sh $@ diff --git a/tools/testing/selftests/lkdtm/config b/tools/testing/selftests/lkdtm/config new file mode 100644 index 000000000000..d874990e442b --- /dev/null +++ b/tools/testing/selftests/lkdtm/config @@ -0,0 +1 @@ +CONFIG_LKDTM=y diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh new file mode 100755 index 000000000000..dadf819148a4 --- /dev/null +++ b/tools/testing/selftests/lkdtm/run.sh @@ -0,0 +1,92 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# This reads tests.txt for the list of LKDTM tests to invoke. Any marked +# with a leading "#" are skipped. The rest of the line after the +# test name is either the text to look for in dmesg for a "success", +# or the rationale for why a test is marked to be skipped. +# +set -e +TRIGGER=/sys/kernel/debug/provoke-crash/DIRECT +KSELFTEST_SKIP_TEST=4 + +# Verify we have LKDTM available in the kernel. +if [ ! -r $TRIGGER ] ; then + /sbin/modprobe -q lkdtm || true + if [ ! -r $TRIGGER ] ; then + echo "Cannot find $TRIGGER (missing CONFIG_LKDTM?)" + else + echo "Cannot write $TRIGGER (need to run as root?)" + fi + # Skip this test + exit $KSELFTEST_SKIP_TEST +fi + +# Figure out which test to run from our script name. +test=$(basename $0 .sh) +# Look up details about the test from master list of LKDTM tests. +line=$(egrep '^#?'"$test"'\b' tests.txt) +if [ -z "$line" ]; then + echo "Skipped: missing test '$test' in tests.txt" + exit $KSELFTEST_SKIP_TEST +fi +# Check that the test is known to LKDTM. +if ! egrep -q '^'"$test"'$' "$TRIGGER" ; then + echo "Skipped: test '$test' missing in $TRIGGER!" + exit $KSELFTEST_SKIP_TEST +fi + +# Extract notes/expected output from test list. +test=$(echo "$line" | cut -d" " -f1) +if echo "$line" | grep -q ' ' ; then + expect=$(echo "$line" | cut -d" " -f2-) +else + expect="" +fi + +# If the test is commented out, report a skip +if echo "$test" | grep -q '^#' ; then + test=$(echo "$test" | cut -c2-) + if [ -z "$expect" ]; then + expect="crashes entire system" + fi + echo "Skipping $test: $expect" + exit $KSELFTEST_SKIP_TEST +fi + +# If no expected output given, assume an Oops with back trace is success. +if [ -z "$expect" ]; then + expect="call trace:" +fi + +# Clear out dmesg for output reporting +dmesg -c >/dev/null + +# Prepare log for report checking +LOG=$(mktemp --tmpdir -t lkdtm-XXXXXX) +cleanup() { + rm -f "$LOG" +} +trap cleanup EXIT + +# Most shells yell about signals and we're expecting the "cat" process +# to usually be killed by the kernel. So we have to run it in a sub-shell +# and silence errors. +($SHELL -c 'cat <(echo '"$test"') >'"$TRIGGER" 2>/dev/null) || true + +# Record and dump the results +dmesg -c >"$LOG" +cat "$LOG" +# Check for expected output +if egrep -qi "$expect" "$LOG" ; then + echo "$test: saw '$expect': ok" + exit 0 +else + if egrep -qi XFAIL: "$LOG" ; then + echo "$test: saw 'XFAIL': [SKIP]" + exit $KSELFTEST_SKIP_TEST + else + echo "$test: missing '$expect': [FAIL]" + exit 1 + fi +fi diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt new file mode 100644 index 000000000000..92ca32143ae5 --- /dev/null +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -0,0 +1,71 @@ +#PANIC +BUG kernel BUG at +WARNING WARNING: +WARNING_MESSAGE message trigger +EXCEPTION +#LOOP Hangs the system +#EXHAUST_STACK Corrupts memory on failure +#CORRUPT_STACK Crashes entire system on success +#CORRUPT_STACK_STRONG Crashes entire system on success +CORRUPT_LIST_ADD list_add corruption +CORRUPT_LIST_DEL list_del corruption +CORRUPT_USER_DS Invalid address limit on user-mode return +STACK_GUARD_PAGE_LEADING +STACK_GUARD_PAGE_TRAILING +UNSET_SMEP CR4 bits went missing +DOUBLE_FAULT +UNALIGNED_LOAD_STORE_WRITE +#OVERWRITE_ALLOCATION Corrupts memory on failure +#WRITE_AFTER_FREE Corrupts memory on failure +READ_AFTER_FREE +#WRITE_BUDDY_AFTER_FREE Corrupts memory on failure +READ_BUDDY_AFTER_FREE +SLAB_FREE_DOUBLE +SLAB_FREE_CROSS +SLAB_FREE_PAGE +#SOFTLOCKUP Hangs the system +#HARDLOCKUP Hangs the system +#SPINLOCKUP Hangs the system +#HUNG_TASK Hangs the system +EXEC_DATA +EXEC_STACK +EXEC_KMALLOC +EXEC_VMALLOC +EXEC_RODATA +EXEC_USERSPACE +EXEC_NULL +ACCESS_USERSPACE +ACCESS_NULL +WRITE_RO +WRITE_RO_AFTER_INIT +WRITE_KERN +REFCOUNT_INC_OVERFLOW +REFCOUNT_ADD_OVERFLOW +REFCOUNT_INC_NOT_ZERO_OVERFLOW +REFCOUNT_ADD_NOT_ZERO_OVERFLOW +REFCOUNT_DEC_ZERO +REFCOUNT_DEC_NEGATIVE Negative detected: saturated +REFCOUNT_DEC_AND_TEST_NEGATIVE Negative detected: saturated +REFCOUNT_SUB_AND_TEST_NEGATIVE Negative detected: saturated +REFCOUNT_INC_ZERO +REFCOUNT_ADD_ZERO +REFCOUNT_INC_SATURATED Saturation detected: still saturated +REFCOUNT_DEC_SATURATED Saturation detected: still saturated +REFCOUNT_ADD_SATURATED Saturation detected: still saturated +REFCOUNT_INC_NOT_ZERO_SATURATED +REFCOUNT_ADD_NOT_ZERO_SATURATED +REFCOUNT_DEC_AND_TEST_SATURATED Saturation detected: still saturated +REFCOUNT_SUB_AND_TEST_SATURATED Saturation detected: still saturated +#REFCOUNT_TIMING timing only +#ATOMIC_TIMING timing only +USERCOPY_HEAP_SIZE_TO +USERCOPY_HEAP_SIZE_FROM +USERCOPY_HEAP_WHITELIST_TO +USERCOPY_HEAP_WHITELIST_FROM +USERCOPY_STACK_FRAME_TO +USERCOPY_STACK_FRAME_FROM +USERCOPY_STACK_BEYOND +USERCOPY_KERNEL +USERCOPY_KERNEL_DS +STACKLEAK_ERASING OK: the rest of the thread stack is properly erased +CFI_FORWARD_PROTO diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 8aefd81fbc86..ecc52d4c034d 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -22,3 +22,4 @@ ipv6_flowlabel_mgr so_txtime tcp_fastopen_backup_key nettest +fin_ack_lat diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index a8e04d665b69..287ae916ec0b 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -11,6 +11,7 @@ TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh traceroute.sh +TEST_PROGS += fin_ack_lat.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any @@ -18,6 +19,7 @@ TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag TEST_GEN_FILES += so_txtime ipv6_flowlabel ipv6_flowlabel_mgr TEST_GEN_FILES += tcp_fastopen_backup_key +TEST_GEN_FILES += fin_ack_lat TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls @@ -25,5 +27,5 @@ KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma -$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread -$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread +$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread +$(OUTPUT)/tcp_inq: LDLIBS += -lpthread diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 9fd3a0b97f0d..fb5c55dd6df8 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -32,12 +32,17 @@ # lo2: 127.0.0.1/8, ::1/128 # 172.16.2.2/32, 2001:db8:2::2/128 # +# ns-A to ns-C connection - only for VRF and same config +# as ns-A to ns-B +# # server / client nomenclature relative to ns-A VERBOSE=0 NSA_DEV=eth1 +NSA_DEV2=eth2 NSB_DEV=eth1 +NSC_DEV=eth2 VRF=red VRF_TABLE=1101 @@ -45,17 +50,22 @@ VRF_TABLE=1101 NSA_IP=172.16.1.1 NSB_IP=172.16.1.2 VRF_IP=172.16.3.1 +NS_NET=172.16.1.0/24 # IPv6 config NSA_IP6=2001:db8:1::1 NSB_IP6=2001:db8:1::2 VRF_IP6=2001:db8:3::1 +NS_NET6=2001:db8:1::/120 NSA_LO_IP=172.16.2.1 NSB_LO_IP=172.16.2.2 NSA_LO_IP6=2001:db8:2::1 NSB_LO_IP6=2001:db8:2::2 +MD5_PW=abc123 +MD5_WRONG_PW=abc1234 + MCAST=ff02::1 # set after namespace create NSA_LINKIP6= @@ -63,9 +73,11 @@ NSB_LINKIP6= NSA=ns-A NSB=ns-B +NSC=ns-C NSA_CMD="ip netns exec ${NSA}" NSB_CMD="ip netns exec ${NSB}" +NSC_CMD="ip netns exec ${NSC}" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) @@ -195,6 +207,11 @@ run_cmd_nsb() do_run_cmd ${NSB_CMD} $* } +run_cmd_nsc() +{ + do_run_cmd ${NSC_CMD} $* +} + setup_cmd() { local cmd="$*" @@ -401,6 +418,7 @@ cleanup() fi ip netns del ${NSB} + ip netns del ${NSC} >/dev/null 2>&1 } setup() @@ -432,6 +450,12 @@ setup() ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + + # some VRF tests use ns-C which has the same config as + # ns-B but for a device NOT in the VRF + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 else ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} @@ -714,6 +738,218 @@ ipv4_ping() ################################################################################ # IPv4 TCP +# +# MD5 tests without VRF +# +ipv4_tcp_md5_novrf() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_LO_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -l ${NSB_LO_IP} -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Prefix config, client address not in configured prefix" +} + +# +# MD5 tests with VRF +# +ipv4_tcp_md5() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout since server does not have MD5 auth" + run_cmd nettest -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout since server config differs from client" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_LO_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout since client address is outside of prefix" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -l ${NSB_LO_IP} -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config, client address not in configured prefix" + + # + # duplicate config between default VRF and a VRF + # + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF with default VRF pw" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF with default VRF pw" + + # + # negative tests + # + log_start + run_cmd nettest -s -d ${NSA_DEV} -M ${MD5_PW} -r ${NSB_IP} + log_test $? 1 "MD5: VRF: Device must be a VRF - single address" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET} + log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + +} + ipv4_tcp_novrf() { local a @@ -831,6 +1067,8 @@ ipv4_tcp_novrf() show_hint "Should fail 'Connection refused'" run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" + + ipv4_tcp_md5_novrf } ipv4_tcp_vrf() @@ -883,6 +1121,9 @@ ipv4_tcp_vrf() run_cmd nettest -r ${a} -d ${NSA_DEV} log_test_addr ${a} $? 1 "Global server, local connection" + # run MD5 tests + ipv4_tcp_md5 + # # enable VRF global server # @@ -924,8 +1165,8 @@ ipv4_tcp_vrf() for a in ${NSA_IP} ${VRF_IP} do log_start - show_hint "Should fail 'No route to host' since client is not bound to VRF" - run_cmd nettest -s -2 ${VRF} & + show_hint "Should fail 'Connection refused' since client is not bound to VRF" + run_cmd nettest -s -d ${VRF} & sleep 1 run_cmd nettest -r ${a} log_test_addr ${a} $? 1 "Global server, local connection" @@ -1961,6 +2202,218 @@ ipv6_ping() ################################################################################ # IPv6 TCP +# +# MD5 tests without VRF +# +ipv6_tcp_md5_novrf() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_LO_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -l ${NSB_LO_IP6} -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Prefix config, client address not in configured prefix" +} + +# +# MD5 tests with VRF +# +ipv6_tcp_md5() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout since server does not have MD5 auth" + run_cmd nettest -6 -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout since server config differs from client" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_LO_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout since client address is outside of prefix" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -l ${NSB_LO_IP6} -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config, client address not in configured prefix" + + # + # duplicate config between default VRF and a VRF + # + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF with default VRF pw" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF with default VRF pw" + + # + # negative tests + # + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -M ${MD5_PW} -r ${NSB_IP6} + log_test $? 1 "MD5: VRF: Device must be a VRF - single address" + + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET6} + log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + +} + ipv6_tcp_novrf() { local a @@ -2077,6 +2530,8 @@ ipv6_tcp_novrf() run_cmd nettest -6 -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" done + + ipv6_tcp_md5_novrf } ipv6_tcp_vrf() @@ -2145,6 +2600,9 @@ ipv6_tcp_vrf() run_cmd nettest -6 -r ${a} -d ${NSA_DEV} log_test_addr ${a} $? 1 "Global server, local connection" + # run MD5 tests + ipv6_tcp_md5 + # # enable VRF global server # @@ -2205,8 +2663,8 @@ ipv6_tcp_vrf() for a in ${NSA_IP6} ${VRF_IP6} do log_start - show_hint "Fails 'No route to host' since client is not in VRF" - run_cmd nettest -6 -s -2 ${VRF} & + show_hint "Fails 'Connection refused' since client is not in VRF" + run_cmd nettest -6 -s -d ${VRF} & sleep 1 run_cmd nettest -6 -r ${a} log_test_addr ${a} $? 1 "Global server, local connection" diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 6dd403103800..60273f1bc7d9 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -910,6 +910,12 @@ ipv6_rt_replace_mpath() check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" log_test $? 0 "Multipath with single path via multipath attribute" + # multipath with dev-only + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1" + check_route6 "2001:db8:104::/64 dev veth1 metric 1024" + log_test $? 0 "Multipath with dev-only" + # route replace fails - invalid nexthop 1 add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" diff --git a/tools/testing/selftests/net/fin_ack_lat.c b/tools/testing/selftests/net/fin_ack_lat.c new file mode 100644 index 000000000000..70187494b57a --- /dev/null +++ b/tools/testing/selftests/net/fin_ack_lat.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <unistd.h> + +static int child_pid; + +static unsigned long timediff(struct timeval s, struct timeval e) +{ + unsigned long s_us, e_us; + + s_us = s.tv_sec * 1000000 + s.tv_usec; + e_us = e.tv_sec * 1000000 + e.tv_usec; + if (s_us > e_us) + return 0; + return e_us - s_us; +} + +static void client(int port) +{ + int sock = 0; + struct sockaddr_in addr, laddr; + socklen_t len = sizeof(laddr); + struct linger sl; + int flag = 1; + int buffer; + struct timeval start, end; + unsigned long lat, sum_lat = 0, nr_lat = 0; + + while (1) { + gettimeofday(&start, NULL); + + sock = socket(AF_INET, SOCK_STREAM, 0); + if (sock < 0) + error(-1, errno, "socket creation"); + + sl.l_onoff = 1; + sl.l_linger = 0; + if (setsockopt(sock, SOL_SOCKET, SO_LINGER, &sl, sizeof(sl))) + error(-1, errno, "setsockopt(linger)"); + + if (setsockopt(sock, IPPROTO_TCP, TCP_NODELAY, + &flag, sizeof(flag))) + error(-1, errno, "setsockopt(nodelay)"); + + addr.sin_family = AF_INET; + addr.sin_port = htons(port); + + if (inet_pton(AF_INET, "127.0.0.1", &addr.sin_addr) <= 0) + error(-1, errno, "inet_pton"); + + if (connect(sock, (struct sockaddr *)&addr, sizeof(addr)) < 0) + error(-1, errno, "connect"); + + send(sock, &buffer, sizeof(buffer), 0); + if (read(sock, &buffer, sizeof(buffer)) == -1) + error(-1, errno, "waiting read"); + + gettimeofday(&end, NULL); + lat = timediff(start, end); + sum_lat += lat; + nr_lat++; + if (lat < 100000) + goto close; + + if (getsockname(sock, (struct sockaddr *)&laddr, &len) == -1) + error(-1, errno, "getsockname"); + printf("port: %d, lat: %lu, avg: %lu, nr: %lu\n", + ntohs(laddr.sin_port), lat, + sum_lat / nr_lat, nr_lat); +close: + fflush(stdout); + close(sock); + } +} + +static void server(int sock, struct sockaddr_in address) +{ + int accepted; + int addrlen = sizeof(address); + int buffer; + + while (1) { + accepted = accept(sock, (struct sockaddr *)&address, + (socklen_t *)&addrlen); + if (accepted < 0) + error(-1, errno, "accept"); + + if (read(accepted, &buffer, sizeof(buffer)) == -1) + error(-1, errno, "read"); + close(accepted); + } +} + +static void sig_handler(int signum) +{ + kill(SIGTERM, child_pid); + exit(0); +} + +int main(int argc, char const *argv[]) +{ + int sock; + int opt = 1; + struct sockaddr_in address; + struct sockaddr_in laddr; + socklen_t len = sizeof(laddr); + + if (signal(SIGTERM, sig_handler) == SIG_ERR) + error(-1, errno, "signal"); + + sock = socket(AF_INET, SOCK_STREAM, 0); + if (sock < 0) + error(-1, errno, "socket"); + + if (setsockopt(sock, SOL_SOCKET, SO_REUSEADDR | SO_REUSEPORT, + &opt, sizeof(opt)) == -1) + error(-1, errno, "setsockopt"); + + address.sin_family = AF_INET; + address.sin_addr.s_addr = INADDR_ANY; + /* dynamically allocate unused port */ + address.sin_port = 0; + + if (bind(sock, (struct sockaddr *)&address, sizeof(address)) < 0) + error(-1, errno, "bind"); + + if (listen(sock, 3) < 0) + error(-1, errno, "listen"); + + if (getsockname(sock, (struct sockaddr *)&laddr, &len) == -1) + error(-1, errno, "getsockname"); + + fprintf(stderr, "server port: %d\n", ntohs(laddr.sin_port)); + child_pid = fork(); + if (!child_pid) + client(ntohs(laddr.sin_port)); + else + server(sock, laddr); + + return 0; +} diff --git a/tools/testing/selftests/net/fin_ack_lat.sh b/tools/testing/selftests/net/fin_ack_lat.sh new file mode 100755 index 000000000000..a3ff6e0b2c7a --- /dev/null +++ b/tools/testing/selftests/net/fin_ack_lat.sh @@ -0,0 +1,35 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test latency spikes caused by FIN/ACK handling race. + +set +x +set -e + +tmpfile=$(mktemp /tmp/fin_ack_latency.XXXX.log) + +cleanup() { + kill $(pidof fin_ack_lat) + rm -f $tmpfile +} + +trap cleanup EXIT + +do_test() { + RUNTIME=$1 + + ./fin_ack_lat | tee $tmpfile & + PID=$! + + sleep $RUNTIME + NR_SPIKES=$(wc -l $tmpfile | awk '{print $1}') + if [ $NR_SPIKES -gt 0 ] + then + echo "FAIL: $NR_SPIKES spikes detected" + return 1 + fi + return 0 +} + +do_test "30" +echo "test done" diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh new file mode 100644 index 000000000000..66496659bea7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh @@ -0,0 +1,873 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Various helpers and tests to verify FIB offload. + +__fib_trap_check() +{ + local ns=$1; shift + local family=$1; shift + local route=$1; shift + local should_fail=$1; shift + local ret + + ip -n $ns -j -p -$family route show $route \ + | jq -e '.[]["flags"] | contains(["trap"])' &> /dev/null + ret=$? + if [[ $should_fail == "true" ]]; then + if [[ $ret -ne 0 ]]; then + return 0 + else + return 1 + fi + fi + + return $ret +} + +fib_trap_check() +{ + local ns=$1; shift + local family=$1; shift + local route=$1; shift + local should_fail=$1; shift + + busywait 5000 __fib_trap_check $ns $family "$route" $should_fail +} + +fib4_trap_check() +{ + local ns=$1; shift + local route=$1; shift + local should_fail=$1; shift + + fib_trap_check $ns 4 "$route" $should_fail +} + +fib6_trap_check() +{ + local ns=$1; shift + local route=$1; shift + local should_fail=$1; shift + + fib_trap_check $ns 6 "$route" $should_fail +} + +fib_ipv4_identical_routes_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 192.0.2.0/24 dev dummy2 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 tos 0 metric 1024" true + check_err $? "Appended route in hardware when should not" + + ip -n $ns route prepend 192.0.2.0/24 dev dummy3 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy3 tos 0 metric 1024" false + check_err $? "Prepended route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true + check_err $? "Route was not replaced in hardware by prepended one" + + log_test "IPv4 identical routes" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv4_tos_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false + check_err $? "Highest TOS route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true + check_err $? "Lowest TOS route still in hardware when should not" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true + check_err $? "Middle TOS route in hardware when should not" + + log_test "IPv4 routes with TOS" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_metric_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1022 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1023 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv4 routes with metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replace_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025 + ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1025 + + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv4 route replace" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv4_delete_test() +{ + local ns=$1; shift + local metric + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Insert multiple routes with the same prefix and length and varying + # metrics. Make sure that throughout delete operations the lowest + # metric route is the one in hardware. + for metric in $(seq 1024 1026); do + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric + done + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false + check_err $? "Lowest metric route not in hardware when should" + + ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1026 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false + check_err $? "Sole route not in hardware when should" + + log_test "IPv4 route delete" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_plen_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Add two routes with the same key and different prefix length and + # make sure both are in hardware. It can be verfied that both are + # sharing the same leaf by checking the /proc/net/fib_trie + ip -n $ns route add 192.0.2.0/24 dev dummy1 + ip -n $ns route add 192.0.2.0/25 dev dummy1 + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false + check_err $? "/24 not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false + check_err $? "/25 not in hardware when should" + + log_test "IPv4 routes with different prefix length" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_metric_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv4 routes replay - metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_tos_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false + check_err $? "Highest TOS route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true + check_err $? "Lowest TOS route in hardware when should not" + + log_test "IPv4 routes replay - TOS" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_plen_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 + ip -n $ns route add 192.0.2.0/25 dev dummy1 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false + check_err $? "/24 not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false + check_err $? "/25 not in hardware when should" + + log_test "IPv4 routes replay - prefix length" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_flush_test() +{ + local ns=$1; shift + local metric + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Exercise the routes flushing code paths by inserting various + # prefix routes on a netdev and then deleting it. + for metric in $(seq 1 20); do + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric + done + + ip -n $ns link del dev dummy1 + + log_test "IPv4 routes flushing" +} + +fib_ipv6_add_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:1::/64 dev dummy2 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" true + check_err $? "Route in hardware when should not" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after appending route" + + log_test "IPv6 single route add" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_metric_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1022 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1023 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv6 routes with metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv6_append_single_test() +{ + local ns=$1; shift + + # When an IPv6 multipath route is added without the 'nexthop' keyword, + # different code paths are taken compared to when the keyword is used. + # This test tries to verify the former. + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after appending" + + ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1025 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not" + + ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1025 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not after appending" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + log_test "IPv6 append single route without 'nexthop' keyword" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replace_single_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1025 + ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1025 + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv6 single route replace" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_metric_multipath_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 2001:db8:10::/64 metric 1022 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + ip -n $ns route add 2001:db8:10::/64 metric 1023 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv6 multipath routes with metric" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_append_multipath_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:2::2 dev dummy2 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after appending" + + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not" + + ip -n $ns route append 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:2::2 dev dummy2 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not after appending" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + log_test "IPv6 append multipath route with 'nexthop' keyword" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replace_multipath_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route replace 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:3::2 dev dummy3 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv6 multipath route replace" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_append_multipath_to_single_test() +{ + local ns=$1; shift + + # Test that when the first route in the leaf is not a multipath route + # and we try to append a multipath route with the same metric to it, it + # is not notified. + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 dev dummy2 metric 1024" true + check_err $? "Route in hardware when should not" + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after append" + + log_test "IPv6 append multipath route to non-multipath route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_delete_single_test() +{ + local ns=$1; shift + + # Test various deletion scenarios, where only a single route is + # deleted from the FIB node. + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + # Test deletion of a single route when it is the only route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + log_test "IPv6 delete sole single route" + + # Test that deletion of last route does not affect the first one. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after deleting higher metric route" + + log_test "IPv6 delete single route not in hardware" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + # Test that first route is replaced by next single route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete single route - replaced by single" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + # Test that first route is replaced by next multipath route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete single route - replaced by multipath" + + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + # Test deletion of a single nexthop from a multipath route. + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after deleting a single nexthop" + + log_test "IPv6 delete single nexthop" + + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_delete_multipath_test() +{ + local ns=$1; shift + + # Test various deletion scenarios, where an entire multipath route is + # deleted from the FIB node. + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + # Test deletion of a multipath route when it is the only route in the + # FIB node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + log_test "IPv6 delete sole multipath route" + + # Test that deletion of last route does not affect the first one. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after deleting higher metric route" + + log_test "IPv6 delete multipath route not in hardware" + + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + # Test that first route is replaced by next single route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete multipath route - replaced by single" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + # Test that first route is replaced by next multipath route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete multipath route - replaced by multipath" + + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replay_single_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 + ip -n $ns route append 2001:db8:1::/64 dev dummy2 + + devlink -N $ns dev reload $devlink_dev + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1" false + check_err $? "First route not in hardware when should" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2" true + check_err $? "Second route in hardware when should not" + + log_test "IPv6 routes replay - single route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replay_multipath_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + + devlink -N $ns dev reload $devlink_dev + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "First route not in hardware when should" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Second route in hardware when should not" + + log_test "IPv6 routes replay - multipath route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1f64e7348f69..2f5da414aaa7 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -225,6 +225,47 @@ log_info() echo "INFO: $msg" } +busywait() +{ + local timeout=$1; shift + + local start_time="$(date -u +%s%3N)" + while true + do + local out + out=$("$@") + local ret=$? + if ((!ret)); then + echo -n "$out" + return 0 + fi + + local current_time="$(date -u +%s%3N)" + if ((current_time - start_time > timeout)); then + echo -n "$out" + return 1 + fi + done +} + +until_counter_is() +{ + local value=$1; shift + local current=$("$@") + + echo $((current)) + ((current >= value)) +} + +busywait_for_counter() +{ + local timeout=$1; shift + local delta=$1; shift + + local base=$("$@") + busywait "$timeout" until_counter_is $((base + delta)) "$@" +} + setup_wait_dev() { local dev=$1; shift @@ -552,9 +593,10 @@ tc_rule_stats_get() local dev=$1; shift local pref=$1; shift local dir=$1; shift + local selector=${1:-.packets}; shift tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ - | jq '.[1].options.actions[].stats.packets' + | jq ".[1].options.actions[].stats$selector" } ethtool_stats_get() @@ -565,6 +607,30 @@ ethtool_stats_get() ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2 } +humanize() +{ + local speed=$1; shift + + for unit in bps Kbps Mbps Gbps; do + if (($(echo "$speed < 1024" | bc))); then + break + fi + + speed=$(echo "scale=1; $speed / 1024" | bc) + done + + echo "$speed${unit}" +} + +rate() +{ + local t0=$1; shift + local t1=$1; shift + local interval=$1; shift + + echo $((8 * (t1 - t0) / interval)) +} + mac_get() { local if_name=$1 @@ -1065,3 +1131,21 @@ flood_test() flood_unicast_test $br_port $host1_if $host2_if flood_multicast_test $br_port $host1_if $host2_if } + +start_traffic() +{ + local h_in=$1; shift # Where the traffic egresses the host + local sip=$1; shift + local dip=$1; shift + local dmac=$1; shift + + $MZ $h_in -p 8000 -A $sip -B $dip -c 0 \ + -a own -b $dmac -t udp -q & + sleep 1 +} + +stop_traffic() +{ + # Suppress noise from killing mausezahn. + { kill %% && wait %%; } 2>/dev/null +} diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh index e6fd7a18c655..0266443601bc 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh @@ -63,22 +63,23 @@ test_span_gre_mac() { local tundev=$1; shift local direction=$1; shift - local prot=$1; shift local what=$1; shift - local swp3mac=$(mac_get $swp3) - local h3mac=$(mac_get $h3) + case "$direction" in + ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2) + ;; + egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1) + ;; + esac RET=0 mirror_install $swp1 $direction $tundev "matchall $tcflags" - tc filter add dev $h3 ingress pref 77 prot $prot \ - flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \ - action pass + icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac" - mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10 - tc filter del dev $h3 ingress pref 77 + icmp_capture_uninstall h3-${tundev} mirror_uninstall $swp1 $direction log_test "$direction $what: envelope MAC ($tcflags)" @@ -120,14 +121,14 @@ test_ip6gretap() test_gretap_mac() { - test_span_gre_mac gt4 ingress ip "mirror to gretap" - test_span_gre_mac gt4 egress ip "mirror to gretap" + test_span_gre_mac gt4 ingress "mirror to gretap" + test_span_gre_mac gt4 egress "mirror to gretap" } test_ip6gretap_mac() { - test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap" - test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap" + test_span_gre_mac gt6 ingress "mirror to ip6gretap" + test_span_gre_mac gt6 egress "mirror to ip6gretap" } test_all() diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index a75cb51cc5bd..057f91b05098 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -1,9 +1,23 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="ping_ipv4 ping_ipv6" +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + sip_in_class_e + mc_mac_mismatch + ipv4_sip_equal_dip + ipv6_sip_equal_dip + ipv4_dip_link_local +" + NUM_NETIFS=4 source lib.sh +source tc_common.sh + +require_command $MCD +require_command $MC_CLI +table_name=selftests h1_create() { @@ -64,6 +78,8 @@ router_create() ip link set dev $rp1 up ip link set dev $rp2 up + tc qdisc add dev $rp2 clsact + ip address add 192.0.2.1/24 dev $rp1 ip address add 2001:db8:1::1/64 dev $rp1 @@ -79,10 +95,31 @@ router_destroy() ip address del 2001:db8:1::1/64 dev $rp1 ip address del 192.0.2.1/24 dev $rp1 + tc qdisc del dev $rp2 clsact + ip link set dev $rp2 down ip link set dev $rp1 down } +start_mcd() +{ + SMCROUTEDIR="$(mktemp -d)" + + for ((i = 1; i <= $NUM_NETIFS; ++i)); do + echo "phyint ${NETIFS[p$i]} enable" >> \ + $SMCROUTEDIR/$table_name.conf + done + + $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \ + -P $SMCROUTEDIR/$table_name.pid +} + +kill_mcd() +{ + pkill $MCD + rm -rf $SMCROUTEDIR +} + setup_prepare() { h1=${NETIFS[p1]} @@ -91,6 +128,10 @@ setup_prepare() rp2=${NETIFS[p3]} h2=${NETIFS[p4]} + rp1mac=$(mac_get $rp1) + + start_mcd + vrf_prepare h1_create @@ -113,6 +154,8 @@ cleanup() h1_destroy vrf_cleanup + + kill_mcd } ping_ipv4() @@ -125,6 +168,150 @@ ping_ipv6() ping6_test $h1 2001:db8:2::2 } +sip_in_class_e() +{ + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$rp1.rp_filter 0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower src_ip 240.0.0.1 ip_proto udp action pass + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 240.0.0.1 -b $rp1mac -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP in class E" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf.$rp1.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +create_mcast_sg() +{ + local if_name=$1; shift + local s_addr=$1; shift + local mcast=$1; shift + local dest_ifs=${@} + + $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs +} + +delete_mcast_sg() +{ + local if_name=$1; shift + local s_addr=$1; shift + local mcast=$1; shift + local dest_ifs=${@} + + $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs +} + +__mc_mac_mismatch() +{ + local desc=$1; shift + local proto=$1; shift + local sip=$1; shift + local dip=$1; shift + local flags=${1:-""}; shift + local dmac=01:02:03:04:05:06 + + RET=0 + + tc filter add dev $rp2 egress protocol $proto pref 1 handle 101 \ + flower dst_ip $dip action pass + + create_mcast_sg $rp1 $sip $dip $rp2 + + $MZ $flags $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $dmac \ + -B $dip -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Multicast MAC mismatch: $desc" + + delete_mcast_sg $rp1 $sip $dip $rp2 + tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower +} + +mc_mac_mismatch() +{ + __mc_mac_mismatch "IPv4" "ip" 192.0.2.2 225.1.2.3 + __mc_mac_mismatch "IPv6" "ipv6" 2001:db8:1::2 ff0e::3 "-6" +} + +ipv4_sip_equal_dip() +{ + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$rp1.rp_filter 0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower src_ip 198.51.100.2 action pass + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 198.51.100.2 -b $rp1mac -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP is equal to destination IP: IPv4" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf.$rp1.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +ipv6_sip_equal_dip() +{ + RET=0 + + tc filter add dev $rp2 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::2 action pass + + $MZ -6 $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 2001:db8:2::2 -b $rp1mac -B 2001:db8:2::2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP is equal to destination IP: IPv6" + + tc filter del dev $rp2 egress protocol ipv6 pref 1 handle 101 flower +} + +ipv4_dip_link_local() +{ + local dip=169.254.1.1 + + RET=0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower dst_ip $dip action pass + + ip neigh add 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2 + ip route add 169.254.1.0/24 dev $rp2 + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $rp1mac -B $dip -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "IPv4 destination IP is link-local" + + ip route del 169.254.1.0/24 dev $rp2 + ip neigh del 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2 + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh new file mode 100755 index 000000000000..40e0ad1bc4f2 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets.sh @@ -0,0 +1,44 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# A driver for the ETS selftest that implements testing in slowpath. +lib_dir=. +source sch_ets_core.sh + +ALL_TESTS=" + ping_ipv4 + priomap_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr + classifier_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr +" + +switch_create() +{ + ets_switch_create + + # Create a bottleneck so that the DWRR process can kick in. + tc qdisc add dev $swp2 root handle 1: tbf \ + rate 1Gbit burst 1Mbit latency 100ms + PARENT="parent 1:" +} + +switch_destroy() +{ + ets_switch_destroy + tc qdisc del dev $swp2 root +} + +# Callback from sch_ets_tests.sh +get_stats() +{ + local stream=$1; shift + + link_stats_get $h2.1$stream rx bytes +} + +ets_run diff --git a/tools/testing/selftests/net/forwarding/sch_ets_core.sh b/tools/testing/selftests/net/forwarding/sch_ets_core.sh new file mode 100644 index 000000000000..f906fcc66572 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets_core.sh @@ -0,0 +1,300 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This is a template for ETS Qdisc test. +# +# This test sends from H1 several traffic streams with 802.1p-tagged packets. +# The tags are used at $swp1 to prioritize the traffic. Each stream is then +# queued at a different ETS band according to the assigned priority. After +# runnig for a while, counters at H2 are consulted to determine whether the +# traffic scheduling was according to the ETS configuration. +# +# This template is supposed to be embedded by a test driver, which implements +# statistics collection, any HW-specific stuff, and prominently configures the +# system to assure that there is overcommitment at $swp2. That is necessary so +# that the ETS traffic selection algorithm kicks in and has to schedule some +# traffic at the expense of other. +# +# A driver for veth-based testing is in sch_ets.sh, an example of a driver for +# an offloaded data path is in selftests/drivers/net/mlxsw/sch_ets.sh. +# +# +---------------------------------------------------------------------+ +# | H1 | +# | + $h1.10 + $h1.11 + $h1.12 | +# | | 192.0.2.1/28 | 192.0.2.17/28 | 192.0.2.33/28 | +# | | egress-qos-map | egress-qos-map | egress-qos-map | +# | | 0:0 | 0:1 | 0:2 | +# | \____________________ | ____________________/ | +# | \|/ | +# | + $h1 | +# +---------------------------|-----------------------------------------+ +# | +# +---------------------------|-----------------------------------------+ +# | SW + $swp1 | +# | | >1Gbps | +# | ____________________/|\____________________ | +# | / | \ | +# | +--|----------------+ +--|----------------+ +--|----------------+ | +# | | + $swp1.10 | | + $swp1.11 | | + $swp1.12 | | +# | | ingress-qos-map| | ingress-qos-map| | ingress-qos-map| | +# | | 0:0 1:1 2:2 | | 0:0 1:1 2:2 | | 0:0 1:1 2:2 | | +# | | | | | | | | +# | | BR10 | | BR11 | | BR12 | | +# | | | | | | | | +# | | + $swp2.10 | | + $swp2.11 | | + $swp2.12 | | +# | +--|----------------+ +--|----------------+ +--|----------------+ | +# | \____________________ | ____________________/ | +# | \|/ | +# | + $swp2 | +# | | 1Gbps (ethtool or HTB qdisc) | +# | | qdisc ets quanta $W0 $W1 $W2 | +# | | priomap 0 1 2 | +# +---------------------------|-----------------------------------------+ +# | +# +---------------------------|-----------------------------------------+ +# | H2 + $h2 | +# | ____________________/|\____________________ | +# | / | \ | +# | + $h2.10 + $h2.11 + $h2.12 | +# | 192.0.2.2/28 192.0.2.18/28 192.0.2.34/28 | +# +---------------------------------------------------------------------+ + +NUM_NETIFS=4 +CHECK_TC=yes +source $lib_dir/lib.sh +source $lib_dir/sch_ets_tests.sh + +PARENT=root +QDISC_DEV= + +sip() +{ + echo 192.0.2.$((16 * $1 + 1)) +} + +dip() +{ + echo 192.0.2.$((16 * $1 + 2)) +} + +# Callback from sch_ets_tests.sh +ets_start_traffic() +{ + local dst_mac=$(mac_get $h2) + local i=$1; shift + + start_traffic $h1.1$i $(sip $i) $(dip $i) $dst_mac +} + +ETS_CHANGE_QDISC= + +priomap_mode() +{ + echo "Running in priomap mode" + ets_delete_qdisc + ETS_CHANGE_QDISC=ets_change_qdisc_priomap +} + +classifier_mode() +{ + echo "Running in classifier mode" + ets_delete_qdisc + ETS_CHANGE_QDISC=ets_change_qdisc_classifier +} + +ets_change_qdisc_priomap() +{ + local dev=$1; shift + local nstrict=$1; shift + local priomap=$1; shift + local quanta=("${@}") + + local op=$(if [[ -n $QDISC_DEV ]]; then echo change; else echo add; fi) + + tc qdisc $op dev $dev $PARENT handle 10: ets \ + $(if ((nstrict)); then echo strict $nstrict; fi) \ + $(if ((${#quanta[@]})); then echo quanta ${quanta[@]}; fi) \ + priomap $priomap + QDISC_DEV=$dev +} + +ets_change_qdisc_classifier() +{ + local dev=$1; shift + local nstrict=$1; shift + local priomap=$1; shift + local quanta=("${@}") + + local op=$(if [[ -n $QDISC_DEV ]]; then echo change; else echo add; fi) + + tc qdisc $op dev $dev $PARENT handle 10: ets \ + $(if ((nstrict)); then echo strict $nstrict; fi) \ + $(if ((${#quanta[@]})); then echo quanta ${quanta[@]}; fi) + + if [[ $op == add ]]; then + local prio=0 + local band + + for band in $priomap; do + tc filter add dev $dev parent 10: basic \ + match "meta(priority eq $prio)" \ + flowid 10:$((band + 1)) + ((prio++)) + done + fi + QDISC_DEV=$dev +} + +# Callback from sch_ets_tests.sh +ets_change_qdisc() +{ + if [[ -z "$ETS_CHANGE_QDISC" ]]; then + exit 1 + fi + $ETS_CHANGE_QDISC "$@" +} + +ets_delete_qdisc() +{ + if [[ -n $QDISC_DEV ]]; then + tc qdisc del dev $QDISC_DEV $PARENT + QDISC_DEV= + fi +} + +h1_create() +{ + local i; + + simple_if_init $h1 + mtu_set $h1 9900 + for i in {0..2}; do + vlan_create $h1 1$i v$h1 $(sip $i)/28 + ip link set dev $h1.1$i type vlan egress 0:$i + done +} + +h1_destroy() +{ + local i + + for i in {0..2}; do + vlan_destroy $h1 1$i + done + mtu_restore $h1 + simple_if_fini $h1 +} + +h2_create() +{ + local i + + simple_if_init $h2 + mtu_set $h2 9900 + for i in {0..2}; do + vlan_create $h2 1$i v$h2 $(dip $i)/28 + done +} + +h2_destroy() +{ + local i + + for i in {0..2}; do + vlan_destroy $h2 1$i + done + mtu_restore $h2 + simple_if_fini $h2 +} + +ets_switch_create() +{ + local i + + ip link set dev $swp1 up + mtu_set $swp1 9900 + + ip link set dev $swp2 up + mtu_set $swp2 9900 + + for i in {0..2}; do + vlan_create $swp1 1$i + ip link set dev $swp1.1$i type vlan ingress 0:0 1:1 2:2 + + vlan_create $swp2 1$i + + ip link add dev br1$i type bridge + ip link set dev $swp1.1$i master br1$i + ip link set dev $swp2.1$i master br1$i + + ip link set dev br1$i up + ip link set dev $swp1.1$i up + ip link set dev $swp2.1$i up + done +} + +ets_switch_destroy() +{ + local i + + ets_delete_qdisc + + for i in {0..2}; do + ip link del dev br1$i + vlan_destroy $swp2 1$i + vlan_destroy $swp1 1$i + done + + mtu_restore $swp2 + ip link set dev $swp2 down + + mtu_restore $swp1 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + put=$swp2 + hut=$h2 + + vrf_prepare + + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 $(dip 0) " vlan 10" + ping_test $h1.11 $(dip 1) " vlan 11" + ping_test $h1.12 $(dip 2) " vlan 12" +} + +ets_run() +{ + trap cleanup EXIT + + setup_prepare + setup_wait + + tests_run + + exit $EXIT_STATUS +} diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh new file mode 100644 index 000000000000..3c3b204d47e8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh @@ -0,0 +1,227 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Global interface: +# $put -- port under test (e.g. $swp2) +# get_stats($band) -- A function to collect stats for band +# ets_start_traffic($band) -- Start traffic for this band +# ets_change_qdisc($op, $dev, $nstrict, $quanta...) -- Add or change qdisc + +# WS describes the Qdisc configuration. It has one value per band (so the +# number of array elements indicates the number of bands). If the value is +# 0, it is a strict band, otherwise the it's a DRR band and the value is +# that band's quantum. +declare -a WS + +qdisc_describe() +{ + local nbands=${#WS[@]} + local nstrict=0 + local i + + for ((i = 0; i < nbands; i++)); do + if ((!${WS[$i]})); then + : $((nstrict++)) + fi + done + + echo -n "ets bands $nbands" + if ((nstrict)); then + echo -n " strict $nstrict" + fi + if ((nstrict < nbands)); then + echo -n " quanta" + for ((i = nstrict; i < nbands; i++)); do + echo -n " ${WS[$i]}" + done + fi +} + +__strict_eval() +{ + local desc=$1; shift + local d=$1; shift + local total=$1; shift + local above=$1; shift + + RET=0 + + if ((! total)); then + check_err 1 "No traffic observed" + log_test "$desc" + return + fi + + local ratio=$(echo "scale=2; 100 * $d / $total" | bc -l) + if ((above)); then + test $(echo "$ratio > 95.0" | bc -l) -eq 1 + check_err $? "Not enough traffic" + log_test "$desc" + log_info "Expected ratio >95% Measured ratio $ratio" + else + test $(echo "$ratio < 5" | bc -l) -eq 1 + check_err $? "Too much traffic" + log_test "$desc" + log_info "Expected ratio <5% Measured ratio $ratio" + fi +} + +strict_eval() +{ + __strict_eval "$@" 1 +} + +notraf_eval() +{ + __strict_eval "$@" 0 +} + +__ets_dwrr_test() +{ + local -a streams=("$@") + + local low_stream=${streams[0]} + local seen_strict=0 + local -a t0 t1 d + local stream + local total + local i + + echo "Testing $(qdisc_describe), streams ${streams[@]}" + + for stream in ${streams[@]}; do + ets_start_traffic $stream + done + + sleep 10 + + t0=($(for stream in ${streams[@]}; do + get_stats $stream + done)) + + sleep 10 + + t1=($(for stream in ${streams[@]}; do + get_stats $stream + done)) + d=($(for ((i = 0; i < ${#streams[@]}; i++)); do + echo $((${t1[$i]} - ${t0[$i]})) + done)) + total=$(echo ${d[@]} | sed 's/ /+/g' | bc) + + for ((i = 0; i < ${#streams[@]}; i++)); do + local stream=${streams[$i]} + if ((seen_strict)); then + notraf_eval "band $stream" ${d[$i]} $total + elif ((${WS[$stream]} == 0)); then + strict_eval "band $stream" ${d[$i]} $total + seen_strict=1 + elif ((stream == low_stream)); then + # Low stream is used as DWRR evaluation reference. + continue + else + multipath_eval "bands $low_stream:$stream" \ + ${WS[$low_stream]} ${WS[$stream]} \ + ${d[0]} ${d[$i]} + fi + done + + for stream in ${streams[@]}; do + stop_traffic + done +} + +ets_dwrr_test_012() +{ + __ets_dwrr_test 0 1 2 +} + +ets_dwrr_test_01() +{ + __ets_dwrr_test 0 1 +} + +ets_dwrr_test_12() +{ + __ets_dwrr_test 1 2 +} + +ets_qdisc_setup() +{ + local dev=$1; shift + local nstrict=$1; shift + local -a quanta=("$@") + + local ndwrr=${#quanta[@]} + local nbands=$((nstrict + ndwrr)) + local nstreams=$(if ((nbands > 3)); then echo 3; else echo $nbands; fi) + local priomap=$(seq 0 $((nstreams - 1))) + local i + + WS=($( + for ((i = 0; i < nstrict; i++)); do + echo 0 + done + for ((i = 0; i < ndwrr; i++)); do + echo ${quanta[$i]} + done + )) + + ets_change_qdisc $dev $nstrict "$priomap" ${quanta[@]} +} + +ets_set_dwrr_uniform() +{ + ets_qdisc_setup $put 0 3300 3300 3300 +} + +ets_set_dwrr_varying() +{ + ets_qdisc_setup $put 0 5000 3500 1500 +} + +ets_set_strict() +{ + ets_qdisc_setup $put 3 +} + +ets_set_mixed() +{ + ets_qdisc_setup $put 1 5000 2500 1500 +} + +ets_change_quantum() +{ + tc class change dev $put classid 10:2 ets quantum 8000 + WS[1]=8000 +} + +ets_set_dwrr_two_bands() +{ + ets_qdisc_setup $put 0 5000 2500 +} + +ets_test_strict() +{ + ets_set_strict + ets_dwrr_test_01 + ets_dwrr_test_12 +} + +ets_test_mixed() +{ + ets_set_mixed + ets_dwrr_test_01 + ets_dwrr_test_12 +} + +ets_test_dwrr() +{ + ets_set_dwrr_uniform + ets_dwrr_test_012 + ets_set_dwrr_varying + ets_dwrr_test_012 + ets_change_quantum + ets_dwrr_test_012 + ets_set_dwrr_two_bands + ets_dwrr_test_01 +} diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_core.sh b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh new file mode 100644 index 000000000000..d1f26cb7cd73 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_core.sh @@ -0,0 +1,233 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This test sends a stream of traffic from H1 through a switch, to H2. On the +# egress port from the switch ($swp2), a shaper is installed. The test verifies +# that the rates on the port match the configured shaper. +# +# In order to test per-class shaping, $swp2 actually contains TBF under PRIO or +# ETS, with two different configurations. Traffic is prioritized using 802.1p. +# +# +-------------------------------------------+ +# | H1 | +# | + $h1.10 $h1.11 + | +# | | 192.0.2.1/28 192.0.2.17/28 | | +# | | | | +# | \______________ _____________/ | +# | \ / | +# | + $h1 | +# +---------------------|---------------------+ +# | +# +---------------------|---------------------+ +# | SW + $swp1 | +# | _______________/ \_______________ | +# | / \ | +# | +-|--------------+ +--------------|-+ | +# | | + $swp1.10 | | $swp1.11 + | | +# | | | | | | +# | | BR10 | | BR11 | | +# | | | | | | +# | | + $swp2.10 | | $swp2.11 + | | +# | +-|--------------+ +--------------|-+ | +# | \_______________ ______________/ | +# | \ / | +# | + $swp2 | +# +---------------------|---------------------+ +# | +# +---------------------|---------------------+ +# | H2 + $h2 | +# | ______________/ \______________ | +# | / \ | +# | | | | +# | + $h2.10 $h2.11 + | +# | 192.0.2.2/28 192.0.2.18/28 | +# +-------------------------------------------+ + +NUM_NETIFS=4 +CHECK_TC="yes" +source $lib_dir/lib.sh + +ipaddr() +{ + local host=$1; shift + local vlan=$1; shift + + echo 192.0.2.$((16 * (vlan - 10) + host)) +} + +host_create() +{ + local dev=$1; shift + local host=$1; shift + + simple_if_init $dev + mtu_set $dev 10000 + + vlan_create $dev 10 v$dev $(ipaddr $host 10)/28 + ip link set dev $dev.10 type vlan egress 0:0 + + vlan_create $dev 11 v$dev $(ipaddr $host 11)/28 + ip link set dev $dev.11 type vlan egress 0:1 +} + +host_destroy() +{ + local dev=$1; shift + + vlan_destroy $dev 11 + vlan_destroy $dev 10 + mtu_restore $dev + simple_if_fini $dev +} + +h1_create() +{ + host_create $h1 1 +} + +h1_destroy() +{ + host_destroy $h1 +} + +h2_create() +{ + host_create $h2 2 + + tc qdisc add dev $h2 clsact + tc filter add dev $h2 ingress pref 1010 prot 802.1q \ + flower $TCFLAGS vlan_id 10 action pass + tc filter add dev $h2 ingress pref 1011 prot 802.1q \ + flower $TCFLAGS vlan_id 11 action pass +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + host_destroy $h2 +} + +switch_create() +{ + local intf + local vlan + + ip link add dev br10 type bridge + ip link add dev br11 type bridge + + for intf in $swp1 $swp2; do + ip link set dev $intf up + mtu_set $intf 10000 + + for vlan in 10 11; do + vlan_create $intf $vlan + ip link set dev $intf.$vlan master br$vlan + ip link set dev $intf.$vlan up + done + done + + for vlan in 10 11; do + ip link set dev $swp1.$vlan type vlan ingress 0:0 1:1 + done + + ip link set dev br10 up + ip link set dev br11 up +} + +switch_destroy() +{ + local intf + local vlan + + # A test may have been interrupted mid-run, with Qdisc installed. Delete + # it here. + tc qdisc del dev $swp2 root 2>/dev/null + + ip link set dev br11 down + ip link set dev br10 down + + for intf in $swp2 $swp1; do + for vlan in 11 10; do + ip link set dev $intf.$vlan down + ip link set dev $intf.$vlan nomaster + vlan_destroy $intf $vlan + done + + mtu_restore $intf + ip link set dev $intf down + done + + ip link del dev br11 + ip link del dev br10 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + swp4=${NETIFS[p7]} + swp5=${NETIFS[p8]} + + h2_mac=$(mac_get $h2) + + vrf_prepare + + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 $(ipaddr 2 10) " vlan 10" + ping_test $h1.11 $(ipaddr 2 11) " vlan 11" +} + +tbf_get_counter() +{ + local vlan=$1; shift + + tc_rule_stats_get $h2 10$vlan ingress .bytes +} + +do_tbf_test() +{ + local vlan=$1; shift + local mbit=$1; shift + + start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 2 $vlan) $h2_mac + sleep 5 # Wait for the burst to dwindle + + local t2=$(busywait_for_counter 1000 +1 tbf_get_counter $vlan) + sleep 10 + local t3=$(tbf_get_counter $vlan) + stop_traffic + + RET=0 + + # Note: TBF uses 10^6 Mbits, not 2^20 ones. + local er=$((mbit * 1000 * 1000)) + local nr=$(rate $t2 $t3 10) + local nr_pct=$((100 * (nr - er) / er)) + ((-5 <= nr_pct && nr_pct <= 5)) + check_err $? "Expected rate $(humanize $er), got $(humanize $nr), which is $nr_pct% off. Required accuracy is +-5%." + + log_test "TC $((vlan - 10)): TBF rate ${mbit}Mbit" +} diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh b/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh new file mode 100755 index 000000000000..84fb6cab88e4 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_ets.sh @@ -0,0 +1,6 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +QDISC="ets strict" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_etsprio.sh diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh new file mode 100644 index 000000000000..8bd85da1905a --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh @@ -0,0 +1,39 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + tbf_test +" +source $lib_dir/sch_tbf_core.sh + +tbf_test_one() +{ + local bs=$1; shift + + tc qdisc replace dev $swp2 parent 10:3 handle 103: tbf \ + rate 400Mbit burst $bs limit 1M + tc qdisc replace dev $swp2 parent 10:2 handle 102: tbf \ + rate 800Mbit burst $bs limit 1M + + do_tbf_test 10 400 $bs + do_tbf_test 11 800 $bs +} + +tbf_test() +{ + # This test is used for both ETS and PRIO. Even though we only need two + # bands, PRIO demands a minimum of three. + tc qdisc add dev $swp2 root handle 10: $QDISC 3 priomap 2 1 0 + tbf_test_one 128K + tc qdisc del dev $swp2 root +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh new file mode 100755 index 000000000000..9c8cb1cb9ba4 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_prio.sh @@ -0,0 +1,6 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +QDISC="prio bands" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_etsprio.sh diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_root.sh b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh new file mode 100755 index 000000000000..72aa21ba88c7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_tbf_root.sh @@ -0,0 +1,33 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + tbf_test +" +: ${lib_dir:=.} +source $lib_dir/sch_tbf_core.sh + +tbf_test_one() +{ + local bs=$1; shift + + tc qdisc replace dev $swp2 root handle 108: tbf \ + rate 400Mbit burst $bs limit 1M + do_tbf_test 10 400 $bs +} + +tbf_test() +{ + tbf_test_one 128K + tc qdisc del dev $swp2 root +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index bb10e33690b2..ce6bea9675c0 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -516,9 +516,9 @@ test_tos() RET=0 tc filter add dev v1 egress pref 77 prot ip \ - flower ip_tos 0x40 action pass - vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10 - vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0 + flower ip_tos 0x14 action pass + vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10 + vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0 tc filter del dev v1 egress pref 77 prot ip log_test "VXLAN: envelope TOS inheritance" diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore new file mode 100644 index 000000000000..d72f07642738 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -0,0 +1,2 @@ +mptcp_connect +*.pcap diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile new file mode 100644 index 000000000000..93de52016dde --- /dev/null +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 + +top_srcdir = ../../../../.. + +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g + +TEST_PROGS := mptcp_connect.sh + +TEST_GEN_FILES = mptcp_connect + +EXTRA_CLEAN := *.pcap + +include ../../lib.mk diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config new file mode 100644 index 000000000000..2499824d9e1c --- /dev/null +++ b/tools/testing/selftests/net/mptcp/config @@ -0,0 +1,4 @@ +CONFIG_MPTCP=y +CONFIG_MPTCP_IPV6=y +CONFIG_VETH=y +CONFIG_NET_SCH_NETEM=m diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c new file mode 100644 index 000000000000..99579c0223c1 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <errno.h> +#include <limits.h> +#include <fcntl.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <unistd.h> + +#include <sys/poll.h> +#include <sys/sendfile.h> +#include <sys/stat.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/mman.h> + +#include <netdb.h> +#include <netinet/in.h> + +#include <linux/tcp.h> + +extern int optind; + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef TCP_ULP +#define TCP_ULP 31 +#endif + +static bool listen_mode; +static int poll_timeout; + +enum cfg_mode { + CFG_MODE_POLL, + CFG_MODE_MMAP, + CFG_MODE_SENDFILE, +}; + +static enum cfg_mode cfg_mode = CFG_MODE_POLL; +static const char *cfg_host; +static const char *cfg_port = "12000"; +static int cfg_sock_proto = IPPROTO_MPTCP; +static bool tcpulp_audit; +static int pf = AF_INET; +static int cfg_sndbuf; + +static void die_usage(void) +{ + fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] -m mode]" + "[ -l ] [ -t timeout ] connect_address\n"); + exit(1); +} + +static const char *getxinfo_strerr(int err) +{ + if (err == EAI_SYSTEM) + return strerror(errno); + + return gai_strerror(err); +} + +static void xgetnameinfo(const struct sockaddr *addr, socklen_t addrlen, + char *host, socklen_t hostlen, + char *serv, socklen_t servlen) +{ + int flags = NI_NUMERICHOST | NI_NUMERICSERV; + int err = getnameinfo(addr, addrlen, host, hostlen, serv, servlen, + flags); + + if (err) { + const char *errstr = getxinfo_strerr(err); + + fprintf(stderr, "Fatal: getnameinfo: %s\n", errstr); + exit(1); + } +} + +static void xgetaddrinfo(const char *node, const char *service, + const struct addrinfo *hints, + struct addrinfo **res) +{ + int err = getaddrinfo(node, service, hints, res); + + if (err) { + const char *errstr = getxinfo_strerr(err); + + fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n", + node ? node : "", service ? service : "", errstr); + exit(1); + } +} + +static void set_sndbuf(int fd, unsigned int size) +{ + int err; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &size, sizeof(size)); + if (err) { + perror("set SO_SNDBUF"); + exit(1); + } +} + +static int sock_listen_mptcp(const char * const listenaddr, + const char * const port) +{ + int sock; + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + .ai_flags = AI_PASSIVE | AI_NUMERICHOST + }; + + hints.ai_family = pf; + + struct addrinfo *a, *addr; + int one = 1; + + xgetaddrinfo(listenaddr, port, &hints, &addr); + hints.ai_family = pf; + + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, cfg_sock_proto); + if (sock < 0) + continue; + + if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one, + sizeof(one))) + perror("setsockopt"); + + if (bind(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + perror("bind"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + + if (sock < 0) { + fprintf(stderr, "Could not create listen socket\n"); + return sock; + } + + if (listen(sock, 20)) { + perror("listen"); + close(sock); + return -1; + } + + return sock; +} + +static bool sock_test_tcpulp(const char * const remoteaddr, + const char * const port) +{ + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *a, *addr; + int sock = -1, ret = 0; + bool test_pass = false; + + hints.ai_family = AF_INET; + + xgetaddrinfo(remoteaddr, port, &hints, &addr); + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, IPPROTO_TCP); + if (sock < 0) { + perror("socket"); + continue; + } + ret = setsockopt(sock, IPPROTO_TCP, TCP_ULP, "mptcp", + sizeof("mptcp")); + if (ret == -1 && errno == EOPNOTSUPP) + test_pass = true; + close(sock); + + if (test_pass) + break; + if (!ret) + fprintf(stderr, + "setsockopt(TCP_ULP) returned 0\n"); + else + perror("setsockopt(TCP_ULP)"); + } + return test_pass; +} + +static int sock_connect_mptcp(const char * const remoteaddr, + const char * const port, int proto) +{ + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *a, *addr; + int sock = -1; + + hints.ai_family = pf; + + xgetaddrinfo(remoteaddr, port, &hints, &addr); + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, proto); + if (sock < 0) { + perror("socket"); + continue; + } + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + perror("connect()"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + return sock; +} + +static size_t do_rnd_write(const int fd, char *buf, const size_t len) +{ + unsigned int do_w; + ssize_t bw; + + do_w = rand() & 0xffff; + if (do_w == 0 || do_w > len) + do_w = len; + + bw = write(fd, buf, do_w); + if (bw < 0) + perror("write"); + + return bw; +} + +static size_t do_write(const int fd, char *buf, const size_t len) +{ + size_t offset = 0; + + while (offset < len) { + size_t written; + ssize_t bw; + + bw = write(fd, buf + offset, len - offset); + if (bw < 0) { + perror("write"); + return 0; + } + + written = (size_t)bw; + offset += written; + } + + return offset; +} + +static ssize_t do_rnd_read(const int fd, char *buf, const size_t len) +{ + size_t cap = rand(); + + cap &= 0xffff; + + if (cap == 0) + cap = 1; + else if (cap > len) + cap = len; + + return read(fd, buf, cap); +} + +static void set_nonblock(int fd) +{ + int flags = fcntl(fd, F_GETFL); + + if (flags == -1) + return; + + fcntl(fd, F_SETFL, flags | O_NONBLOCK); +} + +static int copyfd_io_poll(int infd, int peerfd, int outfd) +{ + struct pollfd fds = { + .fd = peerfd, + .events = POLLIN | POLLOUT, + }; + unsigned int woff = 0, wlen = 0; + char wbuf[8192]; + + set_nonblock(peerfd); + + for (;;) { + char rbuf[8192]; + ssize_t len; + + if (fds.events == 0) + break; + + switch (poll(&fds, 1, poll_timeout)) { + case -1: + if (errno == EINTR) + continue; + perror("poll"); + return 1; + case 0: + fprintf(stderr, "%s: poll timed out (events: " + "POLLIN %u, POLLOUT %u)\n", __func__, + fds.events & POLLIN, fds.events & POLLOUT); + return 2; + } + + if (fds.revents & POLLIN) { + len = do_rnd_read(peerfd, rbuf, sizeof(rbuf)); + if (len == 0) { + /* no more data to receive: + * peer has closed its write side + */ + fds.events &= ~POLLIN; + + if ((fds.events & POLLOUT) == 0) + /* and nothing more to send */ + break; + + /* Else, still have data to transmit */ + } else if (len < 0) { + perror("read"); + return 3; + } + + do_write(outfd, rbuf, len); + } + + if (fds.revents & POLLOUT) { + if (wlen == 0) { + woff = 0; + wlen = read(infd, wbuf, sizeof(wbuf)); + } + + if (wlen > 0) { + ssize_t bw; + + bw = do_rnd_write(peerfd, wbuf + woff, wlen); + if (bw < 0) + return 111; + + woff += bw; + wlen -= bw; + } else if (wlen == 0) { + /* We have no more data to send. */ + fds.events &= ~POLLOUT; + + if ((fds.events & POLLIN) == 0) + /* ... and peer also closed already */ + break; + + /* ... but we still receive. + * Close our write side. + */ + shutdown(peerfd, SHUT_WR); + } else { + if (errno == EINTR) + continue; + perror("read"); + return 4; + } + } + + if (fds.revents & (POLLERR | POLLNVAL)) { + fprintf(stderr, "Unexpected revents: " + "POLLERR/POLLNVAL(%x)\n", fds.revents); + return 5; + } + } + + close(peerfd); + return 0; +} + +static int do_recvfile(int infd, int outfd) +{ + ssize_t r; + + do { + char buf[16384]; + + r = do_rnd_read(infd, buf, sizeof(buf)); + if (r > 0) { + if (write(outfd, buf, r) != r) + break; + } else if (r < 0) { + perror("read"); + } + } while (r > 0); + + return (int)r; +} + +static int do_mmap(int infd, int outfd, unsigned int size) +{ + char *inbuf = mmap(NULL, size, PROT_READ, MAP_SHARED, infd, 0); + ssize_t ret = 0, off = 0; + size_t rem; + + if (inbuf == MAP_FAILED) { + perror("mmap"); + return 1; + } + + rem = size; + + while (rem > 0) { + ret = write(outfd, inbuf + off, rem); + + if (ret < 0) { + perror("write"); + break; + } + + off += ret; + rem -= ret; + } + + munmap(inbuf, size); + return rem; +} + +static int get_infd_size(int fd) +{ + struct stat sb; + ssize_t count; + int err; + + err = fstat(fd, &sb); + if (err < 0) { + perror("fstat"); + return -1; + } + + if ((sb.st_mode & S_IFMT) != S_IFREG) { + fprintf(stderr, "%s: stdin is not a regular file\n", __func__); + return -2; + } + + count = sb.st_size; + if (count > INT_MAX) { + fprintf(stderr, "File too large: %zu\n", count); + return -3; + } + + return (int)count; +} + +static int do_sendfile(int infd, int outfd, unsigned int count) +{ + while (count > 0) { + ssize_t r; + + r = sendfile(outfd, infd, NULL, count); + if (r < 0) { + perror("sendfile"); + return 3; + } + + count -= r; + } + + return 0; +} + +static int copyfd_io_mmap(int infd, int peerfd, int outfd, + unsigned int size) +{ + int err; + + if (listen_mode) { + err = do_recvfile(peerfd, outfd); + if (err) + return err; + + err = do_mmap(infd, peerfd, size); + } else { + err = do_mmap(infd, peerfd, size); + if (err) + return err; + + shutdown(peerfd, SHUT_WR); + + err = do_recvfile(peerfd, outfd); + } + + return err; +} + +static int copyfd_io_sendfile(int infd, int peerfd, int outfd, + unsigned int size) +{ + int err; + + if (listen_mode) { + err = do_recvfile(peerfd, outfd); + if (err) + return err; + + err = do_sendfile(infd, peerfd, size); + } else { + err = do_sendfile(infd, peerfd, size); + if (err) + return err; + err = do_recvfile(peerfd, outfd); + } + + return err; +} + +static int copyfd_io(int infd, int peerfd, int outfd) +{ + int file_size; + + switch (cfg_mode) { + case CFG_MODE_POLL: + return copyfd_io_poll(infd, peerfd, outfd); + case CFG_MODE_MMAP: + file_size = get_infd_size(infd); + if (file_size < 0) + return file_size; + return copyfd_io_mmap(infd, peerfd, outfd, file_size); + case CFG_MODE_SENDFILE: + file_size = get_infd_size(infd); + if (file_size < 0) + return file_size; + return copyfd_io_sendfile(infd, peerfd, outfd, file_size); + } + + fprintf(stderr, "Invalid mode %d\n", cfg_mode); + + die_usage(); + return 1; +} + +static void check_sockaddr(int pf, struct sockaddr_storage *ss, + socklen_t salen) +{ + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + socklen_t wanted_size = 0; + + switch (pf) { + case AF_INET: + wanted_size = sizeof(*sin); + sin = (void *)ss; + if (!sin->sin_port) + fprintf(stderr, "accept: something wrong: ip connection from port 0"); + break; + case AF_INET6: + wanted_size = sizeof(*sin6); + sin6 = (void *)ss; + if (!sin6->sin6_port) + fprintf(stderr, "accept: something wrong: ipv6 connection from port 0"); + break; + default: + fprintf(stderr, "accept: Unknown pf %d, salen %u\n", pf, salen); + return; + } + + if (salen != wanted_size) + fprintf(stderr, "accept: size mismatch, got %d expected %d\n", + (int)salen, wanted_size); + + if (ss->ss_family != pf) + fprintf(stderr, "accept: pf mismatch, expect %d, ss_family is %d\n", + (int)ss->ss_family, pf); +} + +static void check_getpeername(int fd, struct sockaddr_storage *ss, socklen_t salen) +{ + struct sockaddr_storage peerss; + socklen_t peersalen = sizeof(peerss); + + if (getpeername(fd, (struct sockaddr *)&peerss, &peersalen) < 0) { + perror("getpeername"); + return; + } + + if (peersalen != salen) { + fprintf(stderr, "%s: %d vs %d\n", __func__, peersalen, salen); + return; + } + + if (memcmp(ss, &peerss, peersalen)) { + char a[INET6_ADDRSTRLEN]; + char b[INET6_ADDRSTRLEN]; + char c[INET6_ADDRSTRLEN]; + char d[INET6_ADDRSTRLEN]; + + xgetnameinfo((struct sockaddr *)ss, salen, + a, sizeof(a), b, sizeof(b)); + + xgetnameinfo((struct sockaddr *)&peerss, peersalen, + c, sizeof(c), d, sizeof(d)); + + fprintf(stderr, "%s: memcmp failure: accept %s vs peername %s, %s vs %s salen %d vs %d\n", + __func__, a, c, b, d, peersalen, salen); + } +} + +static void check_getpeername_connect(int fd) +{ + struct sockaddr_storage ss; + socklen_t salen = sizeof(ss); + char a[INET6_ADDRSTRLEN]; + char b[INET6_ADDRSTRLEN]; + + if (getpeername(fd, (struct sockaddr *)&ss, &salen) < 0) { + perror("getpeername"); + return; + } + + xgetnameinfo((struct sockaddr *)&ss, salen, + a, sizeof(a), b, sizeof(b)); + + if (strcmp(cfg_host, a) || strcmp(cfg_port, b)) + fprintf(stderr, "%s: %s vs %s, %s vs %s\n", __func__, + cfg_host, a, cfg_port, b); +} + +static void maybe_close(int fd) +{ + unsigned int r = rand(); + + if (r & 1) + close(fd); +} + +int main_loop_s(int listensock) +{ + struct sockaddr_storage ss; + struct pollfd polls; + socklen_t salen; + int remotesock; + + polls.fd = listensock; + polls.events = POLLIN; + + switch (poll(&polls, 1, poll_timeout)) { + case -1: + perror("poll"); + return 1; + case 0: + fprintf(stderr, "%s: timed out\n", __func__); + close(listensock); + return 2; + } + + salen = sizeof(ss); + remotesock = accept(listensock, (struct sockaddr *)&ss, &salen); + if (remotesock >= 0) { + maybe_close(listensock); + check_sockaddr(pf, &ss, salen); + check_getpeername(remotesock, &ss, salen); + + return copyfd_io(0, remotesock, 1); + } + + perror("accept"); + + return 1; +} + +static void init_rng(void) +{ + int fd = open("/dev/urandom", O_RDONLY); + unsigned int foo; + + if (fd > 0) { + int ret = read(fd, &foo, sizeof(foo)); + + if (ret < 0) + srand(fd + foo); + close(fd); + } + + srand(foo); +} + +int main_loop(void) +{ + int fd; + + /* listener is ready. */ + fd = sock_connect_mptcp(cfg_host, cfg_port, cfg_sock_proto); + if (fd < 0) + return 2; + + check_getpeername_connect(fd); + + if (cfg_sndbuf) + set_sndbuf(fd, cfg_sndbuf); + + return copyfd_io(0, fd, 1); +} + +int parse_proto(const char *proto) +{ + if (!strcasecmp(proto, "MPTCP")) + return IPPROTO_MPTCP; + if (!strcasecmp(proto, "TCP")) + return IPPROTO_TCP; + + fprintf(stderr, "Unknown protocol: %s\n.", proto); + die_usage(); + + /* silence compiler warning */ + return 0; +} + +int parse_mode(const char *mode) +{ + if (!strcasecmp(mode, "poll")) + return CFG_MODE_POLL; + if (!strcasecmp(mode, "mmap")) + return CFG_MODE_MMAP; + if (!strcasecmp(mode, "sendfile")) + return CFG_MODE_SENDFILE; + + fprintf(stderr, "Unknown test mode: %s\n", mode); + fprintf(stderr, "Supported modes are:\n"); + fprintf(stderr, "\t\t\"poll\" - interleaved read/write using poll()\n"); + fprintf(stderr, "\t\t\"mmap\" - send entire input file (mmap+write), then read response (-l will read input first)\n"); + fprintf(stderr, "\t\t\"sendfile\" - send entire input file (sendfile), then read response (-l will read input first)\n"); + + die_usage(); + + /* silence compiler warning */ + return 0; +} + +int parse_sndbuf(const char *size) +{ + unsigned long s; + + errno = 0; + + s = strtoul(size, NULL, 0); + + if (errno) { + fprintf(stderr, "Invalid sndbuf size %s (%s)\n", + size, strerror(errno)); + die_usage(); + } + + if (s > INT_MAX) { + fprintf(stderr, "Invalid sndbuf size %s (%s)\n", + size, strerror(ERANGE)); + die_usage(); + } + + cfg_sndbuf = s; + + return 0; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "6lp:s:hut:m:b:")) != -1) { + switch (c) { + case 'l': + listen_mode = true; + break; + case 'p': + cfg_port = optarg; + break; + case 's': + cfg_sock_proto = parse_proto(optarg); + break; + case 'h': + die_usage(); + break; + case 'u': + tcpulp_audit = true; + break; + case '6': + pf = AF_INET6; + break; + case 't': + poll_timeout = atoi(optarg) * 1000; + if (poll_timeout <= 0) + poll_timeout = -1; + break; + case 'm': + cfg_mode = parse_mode(optarg); + break; + case 'b': + cfg_sndbuf = parse_sndbuf(optarg); + break; + } + } + + if (optind + 1 != argc) + die_usage(); + cfg_host = argv[optind]; + + if (strchr(cfg_host, ':')) + pf = AF_INET6; +} + +int main(int argc, char *argv[]) +{ + init_rng(); + + parse_opts(argc, argv); + + if (tcpulp_audit) + return sock_test_tcpulp(cfg_host, cfg_port) ? 0 : 1; + + if (listen_mode) { + int fd = sock_listen_mptcp(cfg_host, cfg_port); + + if (fd < 0) + return 1; + + if (cfg_sndbuf) + set_sndbuf(fd, cfg_sndbuf); + + return main_loop_s(fd); + } + + return main_loop(); +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh new file mode 100755 index 000000000000..d573a0feb98d --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -0,0 +1,595 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +time_start=$(date +%s) + +optstring="b:d:e:l:r:h4cm:" +ret=0 +sin="" +sout="" +cin="" +cout="" +ksft_skip=4 +capture=false +timeout=30 +ipv6=true +ethtool_random_on=true +tc_delay="$((RANDOM%400))" +tc_loss=$((RANDOM%101)) +tc_reorder="" +testmode="" +sndbuf=0 +options_log=true + +if [ $tc_loss -eq 100 ];then + tc_loss=1% +elif [ $tc_loss -ge 10 ]; then + tc_loss=0.$tc_loss% +elif [ $tc_loss -ge 1 ]; then + tc_loss=0.0$tc_loss% +else + tc_loss="" +fi + +usage() { + echo "Usage: $0 [ -a ]" + echo -e "\t-d: tc/netem delay in milliseconds, e.g. \"-d 10\" (default random)" + echo -e "\t-l: tc/netem loss percentage, e.g. \"-l 0.02\" (default random)" + echo -e "\t-r: tc/netem reorder mode, e.g. \"-r 25% 50% gap 5\", use "-r 0" to disable reordering (default random)" + echo -e "\t-e: ethtool features to disable, e.g.: \"-e tso -e gso\" (default: randomly disable any of tso/gso/gro)" + echo -e "\t-4: IPv4 only: disable IPv6 tests (default: test both IPv4 and IPv6)" + echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" + echo -e "\t-b: set sndbuf value (default: use kernel default)" + echo -e "\t-m: test mode (poll, sendfile; default: poll)" +} + +while getopts "$optstring" option;do + case "$option" in + "h") + usage $0 + exit 0 + ;; + "d") + if [ $OPTARG -ge 0 ];then + tc_delay="$OPTARG" + else + echo "-d requires numeric argument, got \"$OPTARG\"" 1>&2 + exit 1 + fi + ;; + "e") + ethtool_args="$ethtool_args $OPTARG off" + ethtool_random_on=false + ;; + "l") + tc_loss="$OPTARG" + ;; + "r") + tc_reorder="$OPTARG" + ;; + "4") + ipv6=false + ;; + "c") + capture=true + ;; + "b") + if [ $OPTARG -ge 0 ];then + sndbuf="$OPTARG" + else + echo "-s requires numeric argument, got \"$OPTARG\"" 1>&2 + exit 1 + fi + ;; + "m") + testmode="$OPTARG" + ;; + "?") + usage $0 + exit 1 + ;; + esac +done + +sec=$(date +%s) +rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) +ns1="ns1-$rndh" +ns2="ns2-$rndh" +ns3="ns3-$rndh" +ns4="ns4-$rndh" + +TEST_COUNT=0 + +cleanup() +{ + rm -f "$cin" "$cout" + rm -f "$sin" "$sout" + rm -f "$capout" + + local netns + for netns in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns del $netns + done +} + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +sin=$(mktemp) +sout=$(mktemp) +cin=$(mktemp) +cout=$(mktemp) +capout=$(mktemp) +trap cleanup EXIT + +for i in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns add $i || exit $ksft_skip + ip -net $i link set lo up +done + +# "$ns1" ns2 ns3 ns4 +# ns1eth2 ns2eth1 ns2eth3 ns3eth2 ns3eth4 ns4eth3 +# - drop 1% -> reorder 25% +# <- TSO off - + +ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" +ip link add ns2eth3 netns "$ns2" type veth peer name ns3eth2 netns "$ns3" +ip link add ns3eth4 netns "$ns3" type veth peer name ns4eth3 netns "$ns4" + +ip -net "$ns1" addr add 10.0.1.1/24 dev ns1eth2 +ip -net "$ns1" addr add dead:beef:1::1/64 dev ns1eth2 nodad + +ip -net "$ns1" link set ns1eth2 up +ip -net "$ns1" route add default via 10.0.1.2 +ip -net "$ns1" route add default via dead:beef:1::2 + +ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1 +ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad +ip -net "$ns2" link set ns2eth1 up + +ip -net "$ns2" addr add 10.0.2.1/24 dev ns2eth3 +ip -net "$ns2" addr add dead:beef:2::1/64 dev ns2eth3 nodad +ip -net "$ns2" link set ns2eth3 up +ip -net "$ns2" route add default via 10.0.2.2 +ip -net "$ns2" route add default via dead:beef:2::2 +ip netns exec "$ns2" sysctl -q net.ipv4.ip_forward=1 +ip netns exec "$ns2" sysctl -q net.ipv6.conf.all.forwarding=1 + +ip -net "$ns3" addr add 10.0.2.2/24 dev ns3eth2 +ip -net "$ns3" addr add dead:beef:2::2/64 dev ns3eth2 nodad +ip -net "$ns3" link set ns3eth2 up + +ip -net "$ns3" addr add 10.0.3.2/24 dev ns3eth4 +ip -net "$ns3" addr add dead:beef:3::2/64 dev ns3eth4 nodad +ip -net "$ns3" link set ns3eth4 up +ip -net "$ns3" route add default via 10.0.2.1 +ip -net "$ns3" route add default via dead:beef:2::1 +ip netns exec "$ns3" sysctl -q net.ipv4.ip_forward=1 +ip netns exec "$ns3" sysctl -q net.ipv6.conf.all.forwarding=1 + +ip -net "$ns4" addr add 10.0.3.1/24 dev ns4eth3 +ip -net "$ns4" addr add dead:beef:3::1/64 dev ns4eth3 nodad +ip -net "$ns4" link set ns4eth3 up +ip -net "$ns4" route add default via 10.0.3.2 +ip -net "$ns4" route add default via dead:beef:3::2 + +set_ethtool_flags() { + local ns="$1" + local dev="$2" + local flags="$3" + + ip netns exec $ns ethtool -K $dev $flags 2>/dev/null + [ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags" +} + +set_random_ethtool_flags() { + local flags="" + local r=$RANDOM + + local pick1=$((r & 1)) + local pick2=$((r & 2)) + local pick3=$((r & 4)) + + [ $pick1 -ne 0 ] && flags="tso off" + [ $pick2 -ne 0 ] && flags="$flags gso off" + [ $pick3 -ne 0 ] && flags="$flags gro off" + + [ -z "$flags" ] && return + + set_ethtool_flags "$1" "$2" "$flags" +} + +if $ethtool_random_on;then + set_random_ethtool_flags "$ns3" ns3eth2 + set_random_ethtool_flags "$ns4" ns4eth3 +else + set_ethtool_flags "$ns3" ns3eth2 "$ethtool_args" + set_ethtool_flags "$ns4" ns4eth3 "$ethtool_args" +fi + +print_file_err() +{ + ls -l "$1" 1>&2 + echo "Trailing bytes are: " + tail -c 27 "$1" +} + +check_transfer() +{ + local in=$1 + local out=$2 + local what=$3 + + cmp "$in" "$out" > /dev/null 2>&1 + if [ $? -ne 0 ] ;then + echo "[ FAIL ] $what does not match (in, out):" + print_file_err "$in" + print_file_err "$out" + + return 1 + fi + + return 0 +} + +check_mptcp_disabled() +{ + local disabled_ns + disabled_ns="ns_disabled-$sech-$(mktemp -u XXXXXX)" + ip netns add ${disabled_ns} || exit $ksft_skip + + # net.mptcp.enabled should be enabled by default + if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then + echo -e "net.mptcp.enabled sysctl is not 1 by default\t\t[ FAIL ]" + ret=1 + return 1 + fi + ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0 + + local err=0 + LANG=C ip netns exec ${disabled_ns} ./mptcp_connect -t $timeout -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \ + grep -q "^socket: Protocol not available$" && err=1 + ip netns delete ${disabled_ns} + + if [ ${err} -eq 0 ]; then + echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]" + ret=1 + return 1 + fi + + echo -e "New MPTCP socket can be blocked via sysctl\t\t[ OK ]" + return 0 +} + +check_mptcp_ulp_setsockopt() +{ + local t retval + t="ns_ulp-$sech-$(mktemp -u XXXXXX)" + + ip netns add ${t} || exit $ksft_skip + if ! ip netns exec ${t} ./mptcp_connect -u -p 10000 -s TCP 127.0.0.1 2>&1; then + printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) allowed\t[ FAIL ]\n" + retval=1 + ret=$retval + else + printf "setsockopt(..., TCP_ULP, \"mptcp\", ...) blocked\t[ OK ]\n" + retval=0 + fi + ip netns del ${t} + return $retval +} + +# $1: IP address +is_v6() +{ + [ -z "${1##*:*}" ] +} + +do_ping() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local ping_args="-q -c 1" + + if is_v6 "${connect_addr}"; then + $ipv6 || return 0 + ping_args="${ping_args} -6" + fi + + ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null + if [ $? -ne 0 ] ; then + echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 + ret=1 + + return 1 + fi + + return 0 +} + +# $1: ns, $2: port +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ + awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} + +do_transfer() +{ + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local local_addr="$6" + local extra_args="" + + local port + port=$((10000+$TEST_COUNT)) + TEST_COUNT=$((TEST_COUNT+1)) + + if [ "$sndbuf" -gt 0 ]; then + extra_args="$extra_args -b $sndbuf" + fi + + if [ -n "$testmode" ]; then + extra_args="$extra_args -m $testmode" + fi + + if [ -n "$extra_args" ] && $options_log; then + options_log=false + echo "INFO: extra options: $extra_args" + fi + + :> "$cout" + :> "$sout" + :> "$capout" + + local addr_port + addr_port=$(printf "%s:%d" ${connect_addr} ${port}) + printf "%.3s %-5s -> %.3s (%-20s) %-5s\t" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto} + + if $capture; then + local capuser + if [ -z $SUDO_USER ] ; then + capuser="" + else + capuser="-Z $SUDO_USER" + fi + + local capfile="${listener_ns}-${connector_ns}-${cl_proto}-${srv_proto}-${connect_addr}.pcap" + + ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & + local cappid=$! + + sleep 1 + fi + + ip netns exec ${listener_ns} ./mptcp_connect -t $timeout -l -p $port -s ${srv_proto} $extra_args $local_addr < "$sin" > "$sout" & + local spid=$! + + wait_local_port_listen "${listener_ns}" "${port}" + + local start + start=$(date +%s%3N) + ip netns exec ${connector_ns} ./mptcp_connect -t $timeout -p $port -s ${cl_proto} $extra_args $connect_addr < "$cin" > "$cout" & + local cpid=$! + + wait $cpid + local retc=$? + wait $spid + local rets=$? + + local stop + stop=$(date +%s%3N) + + if $capture; then + sleep 1 + kill $cappid + fi + + local duration + duration=$((stop-start)) + duration=$(printf "(duration %05sms)" $duration) + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + echo "$duration [ FAIL ] client exit code $retc, server $rets" 1>&2 + echo "\nnetns ${listener_ns} socket stat for $port:" 1>&2 + ip netns exec ${listener_ns} ss -nita 1>&2 -o "sport = :$port" + echo "\nnetns ${connector_ns} socket stat for $port:" 1>&2 + ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port" + + cat "$capout" + return 1 + fi + + check_transfer $sin $cout "file received by client" + retc=$? + check_transfer $cin $sout "file received by server" + rets=$? + + if [ $retc -eq 0 ] && [ $rets -eq 0 ];then + echo "$duration [ OK ]" + cat "$capout" + return 0 + fi + + cat "$capout" + return 1 +} + +make_file() +{ + local name=$1 + local who=$2 + + local SIZE TSIZE + SIZE=$((RANDOM % (1024 * 8))) + TSIZE=$((SIZE * 1024)) + + dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null + + SIZE=$((RANDOM % 1024)) + SIZE=$((SIZE + 128)) + TSIZE=$((TSIZE + SIZE)) + dd if=/dev/urandom conv=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null + echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" + + echo "Created $name (size $TSIZE) containing data sent by $who" +} + +run_tests_lo() +{ + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local loopback="$4" + local lret=0 + + # skip if test programs are running inside same netns for subsequent runs. + if [ $loopback -eq 0 ] && [ ${listener_ns} = ${connector_ns} ]; then + return 0 + fi + + # skip if we don't want v6 + if ! $ipv6 && is_v6 "${connect_addr}"; then + return 0 + fi + + local local_addr + if is_v6 "${connect_addr}"; then + local_addr="::" + else + local_addr="0.0.0.0" + fi + + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + # don't bother testing fallback tcp except for loopback case. + if [ ${listener_ns} != ${connector_ns} ]; then + return 0 + fi + + do_transfer ${listener_ns} ${connector_ns} MPTCP TCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + do_transfer ${listener_ns} ${connector_ns} TCP MPTCP ${connect_addr} ${local_addr} + lret=$? + if [ $lret -ne 0 ]; then + ret=$lret + return 1 + fi + + return 0 +} + +run_tests() +{ + run_tests_lo $1 $2 $3 0 +} + +make_file "$cin" "client" +make_file "$sin" "server" + +check_mptcp_disabled + +check_mptcp_ulp_setsockopt + +echo "INFO: validating network environment with pings" +for sender in "$ns1" "$ns2" "$ns3" "$ns4";do + do_ping "$ns1" $sender 10.0.1.1 + do_ping "$ns1" $sender dead:beef:1::1 + + do_ping "$ns2" $sender 10.0.1.2 + do_ping "$ns2" $sender dead:beef:1::2 + do_ping "$ns2" $sender 10.0.2.1 + do_ping "$ns2" $sender dead:beef:2::1 + + do_ping "$ns3" $sender 10.0.2.2 + do_ping "$ns3" $sender dead:beef:2::2 + do_ping "$ns3" $sender 10.0.3.2 + do_ping "$ns3" $sender dead:beef:3::2 + + do_ping "$ns4" $sender 10.0.3.1 + do_ping "$ns4" $sender dead:beef:3::1 +done + +[ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss +echo -n "INFO: Using loss of $tc_loss " +test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " + +if [ -z "${tc_reorder}" ]; then + reorder1=$((RANDOM%10)) + reorder1=$((100 - reorder1)) + reorder2=$((RANDOM%100)) + + if [ $tc_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then + tc_reorder="reorder ${reorder1}% ${reorder2}%" + echo -n "$tc_reorder " + fi +elif [ "$tc_reorder" = "0" ];then + tc_reorder="" +elif [ "$tc_delay" -gt 0 ];then + # reordering requires some delay + tc_reorder="reorder $tc_reorder" + echo -n "$tc_reorder " +fi + +echo "on ns3eth4" + +tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${tc_delay}ms $tc_reorder + +for sender in $ns1 $ns2 $ns3 $ns4;do + run_tests_lo "$ns1" "$sender" 10.0.1.1 1 + if [ $ret -ne 0 ] ;then + echo "FAIL: Could not even run loopback test" 1>&2 + exit $ret + fi + run_tests_lo "$ns1" $sender dead:beef:1::1 1 + if [ $ret -ne 0 ] ;then + echo "FAIL: Could not even run loopback v6 test" 2>&1 + exit $ret + fi + + run_tests "$ns2" $sender 10.0.1.2 + run_tests "$ns2" $sender dead:beef:1::2 + run_tests "$ns2" $sender 10.0.2.1 + run_tests "$ns2" $sender dead:beef:2::1 + + run_tests "$ns3" $sender 10.0.2.2 + run_tests "$ns3" $sender dead:beef:2::2 + run_tests "$ns3" $sender 10.0.3.2 + run_tests "$ns3" $sender dead:beef:3::2 + + run_tests "$ns4" $sender 10.0.3.1 + run_tests "$ns4" $sender dead:beef:3::1 +done + +time_end=$(date +%s) +time_run=$((time_end-time_start)) + +echo "Time: ${time_run} seconds" + +exit $ret diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings new file mode 100644 index 000000000000..026384c189c9 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/settings @@ -0,0 +1 @@ +timeout=450 diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index c08f4db8330d..93208caacbe6 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -74,7 +74,14 @@ struct sock_args { int use_cmsg; const char *dev; int ifindex; + const char *password; + /* prefix for MD5 password */ + union { + struct sockaddr_in v4; + struct sockaddr_in6 v6; + } md5_prefix; + unsigned int prefix_len; /* expected addresses and device index for connection */ int expected_ifindex; @@ -200,20 +207,33 @@ static void log_address(const char *desc, struct sockaddr *sa) fflush(stdout); } -static int tcp_md5sig(int sd, void *addr, socklen_t alen, const char *password) +static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args) { - struct tcp_md5sig md5sig; - int keylen = password ? strlen(password) : 0; + int keylen = strlen(args->password); + struct tcp_md5sig md5sig = {}; + int opt = TCP_MD5SIG; int rc; - memset(&md5sig, 0, sizeof(md5sig)); - memcpy(&md5sig.tcpm_addr, addr, alen); md5sig.tcpm_keylen = keylen; + memcpy(md5sig.tcpm_key, args->password, keylen); + + if (args->prefix_len) { + opt = TCP_MD5SIG_EXT; + md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_PREFIX; + + md5sig.tcpm_prefixlen = args->prefix_len; + addr = &args->md5_prefix; + } + memcpy(&md5sig.tcpm_addr, addr, alen); + + if (args->ifindex) { + opt = TCP_MD5SIG_EXT; + md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX; - if (keylen) - memcpy(md5sig.tcpm_key, password, keylen); + md5sig.tcpm_ifindex = args->ifindex; + } - rc = setsockopt(sd, IPPROTO_TCP, TCP_MD5SIG, &md5sig, sizeof(md5sig)); + rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig)); if (rc < 0) { /* ENOENT is harmless. Returned when a password is cleared */ if (errno == ENOENT) @@ -254,7 +274,7 @@ static int tcp_md5_remote(int sd, struct sock_args *args) exit(1); } - if (tcp_md5sig(sd, addr, alen, args->password)) + if (tcp_md5sig(sd, addr, alen, args)) return -1; return 0; @@ -1194,7 +1214,7 @@ static int do_server(struct sock_args *args) if (args->password && tcp_md5_remote(lsd, args)) { close(lsd); - return -1; + return 1; } while (1) { @@ -1313,7 +1333,7 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args) if (args->type != SOCK_STREAM) goto out; - if (args->password && tcp_md5sig(sd, addr, alen, args->password)) + if (args->password && tcp_md5sig(sd, addr, alen, args)) goto err; if (args->bind_test_only) @@ -1405,16 +1425,18 @@ enum addr_type { ADDR_TYPE_MCAST, ADDR_TYPE_EXPECTED_LOCAL, ADDR_TYPE_EXPECTED_REMOTE, + ADDR_TYPE_MD5_PREFIX, }; static int convert_addr(struct sock_args *args, const char *_str, enum addr_type atype) { + int pfx_len_max = args->version == AF_INET6 ? 128 : 32; int family = args->version; + char *str, *dev, *sep; struct in6_addr *in6; struct in_addr *in; const char *desc; - char *str, *dev; void *addr; int rc = 0; @@ -1443,6 +1465,30 @@ static int convert_addr(struct sock_args *args, const char *_str, desc = "expected remote"; addr = &args->expected_raddr; break; + case ADDR_TYPE_MD5_PREFIX: + desc = "md5 prefix"; + if (family == AF_INET) { + args->md5_prefix.v4.sin_family = AF_INET; + addr = &args->md5_prefix.v4.sin_addr; + } else if (family == AF_INET6) { + args->md5_prefix.v6.sin6_family = AF_INET6; + addr = &args->md5_prefix.v6.sin6_addr; + } else + return 1; + + sep = strchr(str, '/'); + if (sep) { + *sep = '\0'; + sep++; + if (str_to_uint(sep, 1, pfx_len_max, + &args->prefix_len) != 0) { + fprintf(stderr, "Invalid port\n"); + return 1; + } + } else { + args->prefix_len = pfx_len_max; + } + break; default: log_error("unknown address type"); exit(1); @@ -1522,7 +1568,7 @@ static char *random_msg(int len) return m; } -#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:d:SCi6L:0:1:2:Fbq" +#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:m:d:SCi6L:0:1:2:Fbq" static void print_usage(char *prog) { @@ -1551,6 +1597,7 @@ static void print_usage(char *prog) " -n num number of times to send message\n" "\n" " -M password use MD5 sum protection\n" + " -m prefix/len prefix and length to use for MD5 key\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" "\n" @@ -1642,6 +1689,10 @@ int main(int argc, char *argv[]) case 'M': args.password = optarg; break; + case 'm': + if (convert_addr(&args, optarg, ADDR_TYPE_MD5_PREFIX) < 0) + return 1; + break; case 'S': args.use_setsockopt = 1; break; @@ -1706,11 +1757,16 @@ int main(int argc, char *argv[]) } if (args.password && - (!args.has_remote_ip || args.type != SOCK_STREAM)) { + ((!args.has_remote_ip && !args.prefix_len) || args.type != SOCK_STREAM)) { log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n"); return 1; } + if (args.prefix_len && !args.password) { + log_error("Prefix range for MD5 protection specified without a password\n"); + return 1; + } + if ((args.use_setsockopt || args.use_cmsg) && !args.ifindex) { fprintf(stderr, "Device binding not specified\n"); return 1; diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 34df4c8882af..383bac05ac32 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -12,7 +12,11 @@ #include <arpa/inet.h> #include <error.h> #include <errno.h> +#include <inttypes.h> #include <linux/net_tstamp.h> +#include <linux/errqueue.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> #include <stdbool.h> #include <stdlib.h> #include <stdio.h> @@ -28,7 +32,7 @@ static int cfg_clockid = CLOCK_TAI; static bool cfg_do_ipv4; static bool cfg_do_ipv6; static uint16_t cfg_port = 8000; -static int cfg_variance_us = 2000; +static int cfg_variance_us = 4000; static uint64_t glob_tstart; @@ -43,6 +47,9 @@ static struct timed_send cfg_in[MAX_NUM_PKT]; static struct timed_send cfg_out[MAX_NUM_PKT]; static int cfg_num_pkt; +static int cfg_errq_level; +static int cfg_errq_type; + static uint64_t gettime_ns(void) { struct timespec ts; @@ -90,13 +97,15 @@ static void do_send_one(int fdt, struct timed_send *ts) } -static void do_recv_one(int fdr, struct timed_send *ts) +static bool do_recv_one(int fdr, struct timed_send *ts) { int64_t tstop, texpect; char rbuf[2]; int ret; ret = recv(fdr, rbuf, sizeof(rbuf), 0); + if (ret == -1 && errno == EAGAIN) + return true; if (ret == -1) error(1, errno, "read"); if (ret != 1) @@ -113,6 +122,8 @@ static void do_recv_one(int fdr, struct timed_send *ts) if (labs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); + + return false; } static void do_recv_verify_empty(int fdr) @@ -125,12 +136,70 @@ static void do_recv_verify_empty(int fdr) error(1, 0, "recv: not empty as expected (%d, %d)", ret, errno); } +static void do_recv_errqueue_timeout(int fdt) +{ + char control[CMSG_SPACE(sizeof(struct sock_extended_err)) + + CMSG_SPACE(sizeof(struct sockaddr_in6))] = {0}; + char data[sizeof(struct ipv6hdr) + + sizeof(struct tcphdr) + 1]; + struct sock_extended_err *err; + struct msghdr msg = {0}; + struct iovec iov = {0}; + struct cmsghdr *cm; + int64_t tstamp = 0; + int ret; + + iov.iov_base = data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + while (1) { + ret = recvmsg(fdt, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno == EAGAIN) + break; + if (ret == -1) + error(1, errno, "errqueue"); + if (msg.msg_flags != MSG_ERRQUEUE) + error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags); + + cm = CMSG_FIRSTHDR(&msg); + if (cm->cmsg_level != cfg_errq_level || + cm->cmsg_type != cfg_errq_type) + error(1, 0, "errqueue: type 0x%x.0x%x\n", + cm->cmsg_level, cm->cmsg_type); + + err = (struct sock_extended_err *)CMSG_DATA(cm); + if (err->ee_origin != SO_EE_ORIGIN_TXTIME) + error(1, 0, "errqueue: origin 0x%x\n", err->ee_origin); + if (err->ee_code != ECANCELED) + error(1, 0, "errqueue: code 0x%x\n", err->ee_code); + + tstamp = ((int64_t) err->ee_data) << 32 | err->ee_info; + tstamp -= (int64_t) glob_tstart; + tstamp /= 1000 * 1000; + fprintf(stderr, "send: pkt %c at %" PRId64 "ms dropped\n", + data[ret - 1], tstamp); + + msg.msg_flags = 0; + msg.msg_controllen = sizeof(control); + } + + error(1, 0, "recv: timeout"); +} + static void setsockopt_txtime(int fd) { struct sock_txtime so_txtime_val = { .clockid = cfg_clockid }; struct sock_txtime so_txtime_val_read = { 0 }; socklen_t vallen = sizeof(so_txtime_val); + so_txtime_val.flags = SOF_TXTIME_REPORT_ERRORS; + if (setsockopt(fd, SOL_SOCKET, SO_TXTIME, &so_txtime_val, sizeof(so_txtime_val))) error(1, errno, "setsockopt txtime"); @@ -194,7 +263,8 @@ static void do_test(struct sockaddr *addr, socklen_t alen) for (i = 0; i < cfg_num_pkt; i++) do_send_one(fdt, &cfg_in[i]); for (i = 0; i < cfg_num_pkt; i++) - do_recv_one(fdr, &cfg_out[i]); + if (do_recv_one(fdr, &cfg_out[i])) + do_recv_errqueue_timeout(fdt); do_recv_verify_empty(fdr); @@ -280,6 +350,10 @@ int main(int argc, char **argv) addr6.sin6_family = AF_INET6; addr6.sin6_port = htons(cfg_port); addr6.sin6_addr = in6addr_loopback; + + cfg_errq_level = SOL_IPV6; + cfg_errq_type = IPV6_RECVERR; + do_test((void *)&addr6, sizeof(addr6)); } @@ -289,6 +363,10 @@ int main(int argc, char **argv) addr4.sin_family = AF_INET; addr4.sin_port = htons(cfg_port); addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + + cfg_errq_level = SOL_IP; + cfg_errq_type = IP_RECVERR; + do_test((void *)&addr4, sizeof(addr4)); } diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh index 5aa519328a5b..3f7800eaecb1 100755 --- a/tools/testing/selftests/net/so_txtime.sh +++ b/tools/testing/selftests/net/so_txtime.sh @@ -5,7 +5,12 @@ # Run in network namespace if [[ $# -eq 0 ]]; then - ./in_netns.sh $0 __subprocess + if ! ./in_netns.sh $0 __subprocess; then + # test is time sensitive, can be flaky + echo "test failed: retry once" + ./in_netns.sh $0 __subprocess + fi + exit $? fi @@ -18,7 +23,7 @@ tc qdisc add dev lo root fq ./so_txtime -4 -6 -c mono a,10,b,20 a,10,b,20 ./so_txtime -4 -6 -c mono a,20,b,10 b,20,a,20 -if tc qdisc replace dev lo root etf clockid CLOCK_TAI delta 200000; then +if tc qdisc replace dev lo root etf clockid CLOCK_TAI delta 400000; then ! ./so_txtime -4 -6 -c tai a,-1 a,-1 ! ./so_txtime -4 -6 -c tai a,0 a,0 ./so_txtime -4 -6 -c tai a,10 a,10 diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index de1032b5ddea..08194aa44006 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -2,6 +2,7 @@ # Makefile for netfilter selftests TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ - conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh + conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ + nft_concat_range.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh new file mode 100755 index 000000000000..aca21dde102a --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -0,0 +1,1481 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# nft_concat_range.sh - Tests for sets with concatenation of ranged fields +# +# Copyright (c) 2019 Red Hat GmbH +# +# Author: Stefano Brivio <sbrivio@redhat.com> +# +# shellcheck disable=SC2154,SC2034,SC2016,SC2030,SC2031 +# ^ Configuration and templates sourced with eval, counters reused in subshells + +KSELFTEST_SKIP=4 + +# Available test groups: +# - correctness: check that packets match given entries, and only those +# - concurrency: attempt races between insertion, deletion and lookup +# - timeout: check that packets match entries until they expire +# - performance: estimate matching rate, compare with rbtree and hash baselines +TESTS="correctness concurrency timeout" +[ "${quicktest}" != "1" ] && TESTS="${TESTS} performance" + +# Set types, defined by TYPE_ variables below +TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto + net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port + net_port_mac_proto_net" + +# List of possible paths to pktgen script from kernel tree for performance tests +PKTGEN_SCRIPT_PATHS=" + ../../../samples/pktgen/pktgen_bench_xmit_mode_netif_receive.sh + pktgen/pktgen_bench_xmit_mode_netif_receive.sh" + +# Definition of set types: +# display display text for test report +# type_spec nftables set type specifier +# chain_spec nftables type specifier for rules mapping to set +# dst call sequence of format_*() functions for destination fields +# src call sequence of format_*() functions for source fields +# start initial integer used to generate addresses and ports +# count count of entries to generate and match +# src_delta number summed to destination generator for source fields +# tools list of tools for correctness and timeout tests, any can be used +# proto L4 protocol of test packets +# +# race_repeat race attempts per thread, 0 disables concurrency test for type +# flood_tools list of tools for concurrency tests, any can be used +# flood_proto L4 protocol of test packets for concurrency tests +# flood_spec nftables type specifier for concurrency tests +# +# perf_duration duration of single pktgen injection test +# perf_spec nftables type specifier for performance tests +# perf_dst format_*() functions for destination fields in performance test +# perf_src format_*() functions for source fields in performance test +# perf_entries number of set entries for performance test +# perf_proto L3 protocol of test packets +TYPE_net_port=" +display net,port +type_spec ipv4_addr . inet_service +chain_spec ip daddr . udp dport +dst addr4 port +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto udp +flood_spec ip daddr . udp dport + +perf_duration 5 +perf_spec ip daddr . udp dport +perf_dst addr4 port +perf_src +perf_entries 1000 +perf_proto ipv4 +" + +TYPE_port_net=" +display port,net +type_spec inet_service . ipv4_addr +chain_spec udp dport . ip daddr +dst port addr4 +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto udp +flood_spec udp dport . ip daddr + +perf_duration 5 +perf_spec udp dport . ip daddr +perf_dst port addr4 +perf_src +perf_entries 100 +perf_proto ipv4 +" + +TYPE_net6_port=" +display net6,port +type_spec ipv6_addr . inet_service +chain_spec ip6 daddr . udp dport +dst addr6 port +src +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp6 +flood_spec ip6 daddr . udp dport + +perf_duration 5 +perf_spec ip6 daddr . udp dport +perf_dst addr6 port +perf_src +perf_entries 1000 +perf_proto ipv6 +" + +TYPE_port_proto=" +display port,proto +type_spec inet_service . inet_proto +chain_spec udp dport . meta l4proto +dst port proto +src +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 5 +perf_spec udp dport . meta l4proto +perf_dst port proto +perf_src +perf_entries 30000 +perf_proto ipv4 +" + +TYPE_net6_port_mac=" +display net6,port,mac +type_spec ipv6_addr . inet_service . ether_addr +chain_spec ip6 daddr . udp dport . ether saddr +dst addr6 port +src mac +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 0 + +perf_duration 5 +perf_spec ip6 daddr . udp dport . ether daddr +perf_dst addr6 port mac +perf_src +perf_entries 10 +perf_proto ipv6 +" + +TYPE_net6_port_mac_proto=" +display net6,port,mac,proto +type_spec ipv6_addr . inet_service . ether_addr . inet_proto +chain_spec ip6 daddr . udp dport . ether saddr . meta l4proto +dst addr6 port +src mac proto +start 10 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp6 + +race_repeat 0 + +perf_duration 5 +perf_spec ip6 daddr . udp dport . ether daddr . meta l4proto +perf_dst addr6 port mac proto +perf_src +perf_entries 1000 +perf_proto ipv6 +" + +TYPE_net_port_net=" +display net,port,net +type_spec ipv4_addr . inet_service . ipv4_addr +chain_spec ip daddr . udp dport . ip saddr +dst addr4 port +src addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp +flood_spec ip daddr . udp dport . ip saddr + +perf_duration 0 +" + +TYPE_net6_port_net6_port=" +display net6,port,net6,port +type_spec ipv6_addr . inet_service . ipv6_addr . inet_service +chain_spec ip6 daddr . udp dport . ip6 saddr . udp sport +dst addr6 port +src addr6 port +start 10 +count 5 +src_delta 2000 +tools sendip nc +proto udp6 + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp6 +flood_spec ip6 daddr . tcp dport . ip6 saddr . tcp sport + +perf_duration 0 +" + +TYPE_net_port_mac_proto_net=" +display net,port,mac,proto,net +type_spec ipv4_addr . inet_service . ether_addr . inet_proto . ipv4_addr +chain_spec ip daddr . udp dport . ether saddr . meta l4proto . ip saddr +dst addr4 port +src mac proto addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net_mac=" +display net,mac +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 5 +perf_spec ip daddr . ether daddr +perf_dst addr4 mac +perf_src +perf_entries 1000 +perf_proto ipv4 +" + +TYPE_net_mac_icmp=" +display net,mac - ICMP +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 5 +src_delta 2000 +tools ping +proto icmp + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net6_mac_icmp=" +display net6,mac - ICMPv6 +type_spec ipv6_addr . ether_addr +chain_spec ip6 daddr . ether saddr +dst addr6 +src mac +start 10 +count 50 +src_delta 2000 +tools ping +proto icmp6 + +race_repeat 0 + +perf_duration 0 +" + +TYPE_net_port_proto_net=" +display net,port,proto,net +type_spec ipv4_addr . inet_service . inet_proto . ipv4_addr +chain_spec ip daddr . udp dport . meta l4proto . ip saddr +dst addr4 port proto +src addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc +proto udp + +race_repeat 3 +flood_tools iperf3 iperf netperf +flood_proto tcp +flood_spec ip daddr . tcp dport . meta l4proto . ip saddr + +perf_duration 0 +" + +# Set template for all tests, types and rules are filled in depending on test +set_template=' +flush ruleset + +table inet filter { + counter test { + packets 0 bytes 0 + } + + set test { + type ${type_spec} + flags interval,timeout + } + + chain input { + type filter hook prerouting priority 0; policy accept; + ${chain_spec} @test counter name \"test\" + } +} + +table netdev perf { + counter test { + packets 0 bytes 0 + } + + counter match { + packets 0 bytes 0 + } + + set test { + type ${type_spec} + flags interval + } + + set norange { + type ${type_spec} + } + + set noconcat { + type ${type_spec%% *} + flags interval + } + + chain test { + type filter hook ingress device veth_a priority 0; + } +} +' + +err_buf= +info_buf= + +# Append string to error buffer +err() { + err_buf="${err_buf}${1} +" +} + +# Append string to information buffer +info() { + info_buf="${info_buf}${1} +" +} + +# Flush error buffer to stdout +err_flush() { + printf "%s" "${err_buf}" + err_buf= +} + +# Flush information buffer to stdout +info_flush() { + printf "%s" "${info_buf}" + info_buf= +} + +# Setup veth pair: this namespace receives traffic, B generates it +setup_veth() { + ip netns add B + ip link add veth_a type veth peer name veth_b || return 1 + + ip link set veth_a up + ip link set veth_b netns B + + ip -n B link set veth_b up + + ip addr add dev veth_a 10.0.0.1 + ip route add default dev veth_a + + ip -6 addr add fe80::1/64 dev veth_a nodad + ip -6 addr add 2001:db8::1/64 dev veth_a nodad + ip -6 route add default dev veth_a + + ip -n B route add default dev veth_b + + ip -6 -n B addr add fe80::2/64 dev veth_b nodad + ip -6 -n B addr add 2001:db8::2/64 dev veth_b nodad + ip -6 -n B route add default dev veth_b + + B() { + ip netns exec B "$@" >/dev/null 2>&1 + } + + sleep 2 +} + +# Fill in set template and initialise set +setup_set() { + eval "echo \"${set_template}\"" | nft -f - +} + +# Check that at least one of the needed tools is available +check_tools() { + __tools= + for tool in ${tools}; do + if [ "${tool}" = "nc" ] && [ "${proto}" = "udp6" ] && \ + ! nc -u -w0 1.1.1.1 1 2>/dev/null; then + # Some GNU netcat builds might not support IPv6 + __tools="${__tools} netcat-openbsd" + continue + fi + __tools="${__tools} ${tool}" + + command -v "${tool}" >/dev/null && return 0 + done + err "need one of:${__tools}, skipping" && return 1 +} + +# Set up function to send ICMP packets +setup_send_icmp() { + send_icmp() { + B ping -c1 -W1 "${dst_addr4}" >/dev/null 2>&1 + } +} + +# Set up function to send ICMPv6 packets +setup_send_icmp6() { + if command -v ping6 >/dev/null; then + send_icmp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ping6 -q -c1 -W1 "${dst_addr6}" + } + else + send_icmp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ping -q -6 -c1 -W1 "${dst_addr6}" + } + fi +} + +# Set up function to send single UDP packets on IPv4 +setup_send_udp() { + if command -v sendip >/dev/null; then + send_udp() { + [ -n "${src_port}" ] && src_port="-us ${src_port}" + [ -n "${dst_port}" ] && dst_port="-ud ${dst_port}" + [ -n "${src_addr4}" ] && src_addr4="-is ${src_addr4}" + + # shellcheck disable=SC2086 # sendip needs split options + B sendip -p ipv4 -p udp ${src_addr4} ${src_port} \ + ${dst_port} "${dst_addr4}" + + src_port= + dst_port= + src_addr4= + } + elif command -v nc >/dev/null; then + if nc -u -w0 1.1.1.1 1 2>/dev/null; then + # OpenBSD netcat + nc_opt="-w0" + else + # GNU netcat + nc_opt="-q0" + fi + + send_udp() { + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}" dev veth_b + __src_addr4="-s ${src_addr4}" + fi + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + [ -n "${src_port}" ] && src_port="-p ${src_port}" + + echo "" | B nc -u "${nc_opt}" "${__src_addr4}" \ + "${src_port}" "${dst_addr4}" "${dst_port}" + + src_addr4= + src_port= + } + elif [ -z "$(bash -c 'type -p')" ]; then + send_udp() { + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + B ip route add default dev veth_b + fi + + B bash -c "echo > /dev/udp/${dst_addr4}/${dst_port}" + + if [ -n "${src_addr4}" ]; then + B ip addr del "${src_addr4}/16" dev veth_b + fi + src_addr4= + } + else + return 1 + fi +} + +# Set up function to send single UDP packets on IPv6 +setup_send_udp6() { + if command -v sendip >/dev/null; then + send_udp6() { + [ -n "${src_port}" ] && src_port="-us ${src_port}" + [ -n "${dst_port}" ] && dst_port="-ud ${dst_port}" + if [ -n "${src_addr6}" ]; then + src_addr6="-6s ${src_addr6}" + else + src_addr6="-6s 2001:db8::2" + fi + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + B sendip -p ipv6 -p udp ${src_addr6} ${src_port} \ + ${dst_port} "${dst_addr6}" + + src_port= + dst_port= + src_addr6= + } + elif command -v nc >/dev/null && nc -u -w0 1.1.1.1 1 2>/dev/null; then + # GNU netcat might not work with IPv6, try next tool + send_udp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + else + src_addr6="2001:db8::2" + fi + [ -n "${src_port}" ] && src_port="-p ${src_port}" + + # shellcheck disable=SC2086 # this needs split options + echo "" | B nc -u w0 "-s${src_addr6}" ${src_port} \ + ${dst_addr6} ${dst_port} + + src_addr6= + src_port= + } + elif [ -z "$(bash -c 'type -p')" ]; then + send_udp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + B ip addr add "${src_addr6}" dev veth_b nodad + B bash -c "echo > /dev/udp/${dst_addr6}/${dst_port}" + ip -6 addr del "${dst_addr6}" dev veth_a 2>/dev/null + } + else + return 1 + fi +} + +# Set up function to send TCP traffic on IPv4 +setup_flood_tcp() { + if command -v iperf3 >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b 2>/dev/null + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -c "${dst_addr4}" ${dst_port} ${src_port} \ + ${src_addr4} -l16 -t 1000 + + src_addr4= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 2>/dev/null + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_addr4="${src_addr4}:${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -s -DB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -c "${dst_addr4}" ${dst_port} ${src_addr4} \ + -l20 -t 1000 + + src_addr4= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_tcp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="10.0.0.2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -4 ${dst_port} -L "${dst_addr4}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -4 -H "${dst_addr4}" ${dst_port} \ + -L "${src_addr4}" -l 1000 -t TCP_STREAM + + src_addr4= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Set up function to send TCP traffic on IPv6 +setup_flood_tcp6() { + if command -v iperf3 >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + src_addr6="-B ${src_addr6}" + else + src_addr6="-B 2001:db8::2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr6}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -c "${dst_addr6}" ${dst_port} \ + ${src_port} ${src_addr6} -l16 -t 1000 + + src_addr6= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + src_addr6="-B ${src_addr6}" + else + src_addr6="-B 2001:db8::2" + fi + if [ -n "${src_port}" ]; then + src_addr6="${src_addr6}:${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -s -VDB "${dst_addr6}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -c "${dst_addr6}" -V ${dst_port} \ + ${src_addr6} -l1 -t 1000 + + src_addr6= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_tcp6() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr6}" ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + else + src_addr6="2001:db8::2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -6 ${dst_port} -L "${dst_addr6}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -6 -H "${dst_addr6}" ${dst_port} \ + -L "${src_addr6}" -l 1000 -t TCP_STREAM + + src_addr6= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Set up function to send UDP traffic on IPv4 +setup_flood_udp() { + if command -v iperf3 >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 2>/dev/null + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_port="--cport ${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf3 -s -DB "${dst_addr4}" ${dst_port} + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf3 -u -c "${dst_addr4}" -Z -b 100M -l16 -t1000 \ + ${dst_port} ${src_port} ${src_addr4} + + src_addr4= + src_port= + dst_port= + } + elif command -v iperf >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + src_addr4="-B ${src_addr4}" + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="-B 10.0.0.2" + fi + if [ -n "${src_port}" ]; then + src_addr4="${src_addr4}:${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + iperf -u -sDB "${dst_addr4}" ${dst_port} >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B iperf -u -c "${dst_addr4}" -b 100M -l1 -t1000 \ + ${dst_port} ${src_addr4} + + src_addr4= + src_port= + dst_port= + } + elif command -v netperf >/dev/null; then + flood_udp() { + [ -n "${dst_port}" ] && dst_port="-p ${dst_port}" + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}/16" dev veth_b + else + B ip addr add dev veth_b 10.0.0.2 + src_addr4="10.0.0.2" + fi + if [ -n "${src_port}" ]; then + dst_port="${dst_port},${src_port}" + fi + B ip route add default dev veth_b + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + + # shellcheck disable=SC2086 # this needs split options + netserver -4 ${dst_port} -L "${dst_addr4}" \ + >/dev/null 2>&1 + sleep 2 + + # shellcheck disable=SC2086 # this needs split options + B netperf -4 -H "${dst_addr4}" ${dst_port} \ + -L "${src_addr4}" -l 1000 -t UDP_STREAM + + src_addr4= + src_port= + dst_port= + } + else + return 1 + fi +} + +# Find pktgen script and set up function to start pktgen injection +setup_perf() { + for pktgen_script_path in ${PKTGEN_SCRIPT_PATHS} __notfound; do + command -v "${pktgen_script_path}" >/dev/null && break + done + [ "${pktgen_script_path}" = "__notfound" ] && return 1 + + perf_ipv4() { + ${pktgen_script_path} -s80 \ + -i veth_a -d "${dst_addr4}" -p "${dst_port}" \ + -m "${dst_mac}" \ + -t $(($(nproc) / 5 + 1)) -b10000 -n0 2>/dev/null & + perf_pid=$! + } + perf_ipv6() { + IP6=6 ${pktgen_script_path} -s100 \ + -i veth_a -d "${dst_addr6}" -p "${dst_port}" \ + -m "${dst_mac}" \ + -t $(($(nproc) / 5 + 1)) -b10000 -n0 2>/dev/null & + perf_pid=$! + } +} + +# Clean up before each test +cleanup() { + nft reset counter inet filter test >/dev/null 2>&1 + nft flush ruleset >/dev/null 2>&1 + ip link del dummy0 2>/dev/null + ip route del default 2>/dev/null + ip -6 route del default 2>/dev/null + ip netns del B 2>/dev/null + ip link del veth_a 2>/dev/null + timeout= + killall iperf3 2>/dev/null + killall iperf 2>/dev/null + killall netperf 2>/dev/null + killall netserver 2>/dev/null + rm -f ${tmp} + sleep 2 +} + +# Entry point for setup functions +setup() { + if [ "$(id -u)" -ne 0 ]; then + echo " need to run as root" + exit ${KSELFTEST_SKIP} + fi + + cleanup + check_tools || return 1 + for arg do + if ! eval setup_"${arg}"; then + err " ${arg} not supported" + return 1 + fi + done +} + +# Format integer into IPv4 address, summing 10.0.0.5 (arbitrary) to it +format_addr4() { + a=$((${1} + 16777216 * 10 + 5)) + printf "%i.%i.%i.%i" \ + "$((a / 16777216))" "$((a % 16777216 / 65536))" \ + "$((a % 65536 / 256))" "$((a % 256))" +} + +# Format integer into IPv6 address, summing 2001:db8:: to it +format_addr6() { + printf "2001:db8::%04x:%04x" "$((${1} / 65536))" "$((${1} % 65536))" +} + +# Format integer into EUI-48 address, summing 00:01:00:00:00:00 to it +format_mac() { + printf "00:01:%02x:%02x:%02x:%02x" \ + "$((${1} / 16777216))" "$((${1} % 16777216 / 65536))" \ + "$((${1} % 65536 / 256))" "$((${1} % 256))" +} + +# Format integer into port, avoid 0 port +format_port() { + printf "%i" "$((${1} % 65534 + 1))" +} + +# Drop suffixed '6' from L4 protocol, if any +format_proto() { + printf "%s" "${proto}" | tr -d 6 +} + +# Format destination and source fields into nft concatenated type +format() { + __start= + __end= + __expr="{ " + + for f in ${dst}; do + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + + __start="$(eval format_"${f}" "${start}")" + __end="$(eval format_"${f}" "${end}")" + + if [ "${f}" = "proto" ]; then + __expr="${__expr}${__start}" + else + __expr="${__expr}${__start}-${__end}" + fi + done + for f in ${src}; do + __expr="${__expr} . " + __start="$(eval format_"${f}" "${srcstart}")" + __end="$(eval format_"${f}" "${srcend}")" + + if [ "${f}" = "proto" ]; then + __expr="${__expr}${__start}" + else + __expr="${__expr}${__start}-${__end}" + fi + done + + if [ -n "${timeout}" ]; then + echo "${__expr} timeout ${timeout}s }" + else + echo "${__expr} }" + fi +} + +# Format destination and source fields into nft type, start element only +format_norange() { + __expr="{ " + + for f in ${dst}; do + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + + __expr="${__expr}$(eval format_"${f}" "${start}")" + done + for f in ${src}; do + __expr="${__expr} . $(eval format_"${f}" "${start}")" + done + + echo "${__expr} }" +} + +# Format first destination field into nft type +format_noconcat() { + for f in ${dst}; do + __start="$(eval format_"${f}" "${start}")" + __end="$(eval format_"${f}" "${end}")" + + if [ "${f}" = "proto" ]; then + echo "{ ${__start} }" + else + echo "{ ${__start}-${__end} }" + fi + return + done +} + +# Add single entry to 'test' set in 'inet filter' table +add() { + if ! nft add element inet filter test "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Format and output entries for sets in 'netdev perf' table +add_perf() { + if [ "${1}" = "test" ]; then + echo "add element netdev perf test $(format)" + elif [ "${1}" = "norange" ]; then + echo "add element netdev perf norange $(format_norange)" + elif [ "${1}" = "noconcat" ]; then + echo "add element netdev perf noconcat $(format_noconcat)" + fi +} + +# Add single entry to 'norange' set in 'netdev perf' table +add_perf_norange() { + if ! nft add element netdev perf norange "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Add single entry to 'noconcat' set in 'netdev perf' table +add_perf_noconcat() { + if ! nft add element netdev perf noconcat "${1}"; then + err "Failed to add ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Delete single entry from set +del() { + if ! nft delete element inet filter test "${1}"; then + err "Failed to delete ${1} given ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Return packet count from 'test' counter in 'inet filter' table +count_packets() { + found=0 + for token in $(nft list counter inet filter test); do + [ ${found} -eq 1 ] && echo "${token}" && return + [ "${token}" = "packets" ] && found=1 + done +} + +# Return packet count from 'test' counter in 'netdev perf' table +count_perf_packets() { + found=0 + for token in $(nft list counter netdev perf test); do + [ ${found} -eq 1 ] && echo "${token}" && return + [ "${token}" = "packets" ] && found=1 + done +} + +# Set MAC addresses, send traffic according to specifier +flood() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval flood_\$proto +} + +# Set MAC addresses, start pktgen injection +perf() { + dst_mac="$(format_mac "${1}")" + ip link set veth_a address "${dst_mac}" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval perf_\$perf_proto +} + +# Set MAC addresses, send single packet, check that it matches, reset counter +send_match() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval send_\$proto + if [ "$(count_packets)" != "1" ]; then + err "${proto} packet to:" + err " $(for f in ${dst}; do + eval format_\$f "${1}"; printf ' '; done)" + err "from:" + err " $(for f in ${src}; do + eval format_\$f "${2}"; printf ' '; done)" + err "should have matched ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi + nft reset counter inet filter test >/dev/null +} + +# Set MAC addresses, send single packet, check that it doesn't match +send_nomatch() { + ip link set veth_a address "$(format_mac "${1}")" + ip -n B link set veth_b address "$(format_mac "${2}")" + + for f in ${dst}; do + eval dst_"$f"=\$\(format_\$f "${1}"\) + done + for f in ${src}; do + eval src_"$f"=\$\(format_\$f "${2}"\) + done + eval send_\$proto + if [ "$(count_packets)" != "0" ]; then + err "${proto} packet to:" + err " $(for f in ${dst}; do + eval format_\$f "${1}"; printf ' '; done)" + err "from:" + err " $(for f in ${src}; do + eval format_\$f "${2}"; printf ' '; done)" + err "should not have matched ruleset:" + err "$(nft list ruleset -a)" + return 1 + fi +} + +# Correctness test template: +# - add ranged element, check that packets match it +# - check that packets outside range don't match it +# - remove some elements, check that packets don't match anymore +test_correctness() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + send_nomatch $((end + 1)) $((end + 1 + src_delta)) || return 1 + + # Delete elements now and then + if [ $((i % 3)) -eq 0 ]; then + del "$(format)" || return 1 + for j in $(seq ${start} \ + $((range_size / 2 + 1)) ${end}); do + send_nomatch "${j}" $((j + src_delta)) \ + || return 1 + done + fi + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done +} + +# Concurrency test template: +# - add all the elements +# - start a thread for each physical thread that: +# - adds all the elements +# - flushes the set +# - adds all the elements +# - flushes the entire ruleset +# - adds the set back +# - adds all the elements +# - delete all the elements +test_concurrency() { + proto=${flood_proto} + tools=${flood_tools} + chain_spec=${flood_spec} + setup veth flood_"${proto}" set || return ${KSELFTEST_SKIP} + + range_size=1 + cstart=${start} + flood_pids= + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + + flood "${i}" $((i + src_delta)) & flood_pids="${flood_pids} $!" + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + sleep 10 + + pids= + for c in $(seq 1 "$(nproc)"); do ( + for r in $(seq 1 "${race_repeat}"); do + range_size=1 + + # $start needs to be local to this subshell + # shellcheck disable=SC2030 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush inet filter test 2>/dev/null + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush ruleset + setup set 2>/dev/null + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + range_size=1 + start=${cstart} + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + del "$(format)" 2>/dev/null + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + done + ) & pids="${pids} $!" + done + + # shellcheck disable=SC2046,SC2086 # word splitting wanted here + wait $(for pid in ${pids}; do echo ${pid}; done) + # shellcheck disable=SC2046,SC2086 + kill $(for pid in ${flood_pids}; do echo ${pid}; done) 2>/dev/null + # shellcheck disable=SC2046,SC2086 + wait $(for pid in ${flood_pids}; do echo ${pid}; done) 2>/dev/null + + return 0 +} + +# Timeout test template: +# - add all the elements with 3s timeout while checking that packets match +# - wait 3s after the last insertion, check that packets don't match any entry +test_timeout() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + + timeout=3 + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + sleep 3 + for i in $(seq ${start} $((start + count))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_nomatch "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done +} + +# Performance test template: +# - add concatenated ranged entries +# - add non-ranged concatenated entries (for hash set matching rate baseline) +# - add ranged entries with first field only (for rbhash baseline) +# - start pktgen injection directly on device rx path of this namespace +# - measure drop only rate, hash and rbtree baselines, then matching rate +test_performance() { + chain_spec=${perf_spec} + dst="${perf_dst}" + src="${perf_src}" + setup veth perf set || return ${KSELFTEST_SKIP} + + first=${start} + range_size=1 + for set in test norange noconcat; do + start=${first} + for i in $(seq ${start} $((start + perf_entries))); do + end=$((start + range_size)) + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + elif [ ${start} -eq ${end} ]; then + end=$((start + 1)) + fi + + add_perf ${set} + + start=$((end + range_size)) + done > "${tmp}" + nft -f "${tmp}" + done + + perf $((end - 1)) ${srcstart} + + sleep 2 + + nft add rule netdev perf test counter name \"test\" drop + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline (drop from netdev hook): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec} @norange \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline hash (non-ranged entries): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec%%. *} @noconcat \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + info " baseline rbtree (match on first field only): ${pps}pps" + handle="$(nft -a list chain netdev perf test | grep counter)" + handle="${handle##* }" + nft delete rule netdev perf test handle "${handle}" + + nft add rule "netdev perf test ${chain_spec} @test \ + counter name \"test\" drop" + nft reset counter netdev perf test >/dev/null 2>&1 + sleep "${perf_duration}" + pps="$(printf %10s $(($(count_perf_packets) / perf_duration)))" + p5="$(printf %5s "${perf_entries}")" + info " set with ${p5} full, ranged entries: ${pps}pps" + kill "${perf_pid}" +} + +# Run everything in a separate network namespace +[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } +tmp="$(mktemp)" +trap cleanup EXIT + +# Entry point for test runs +passed=0 +for name in ${TESTS}; do + printf "TEST: %s\n" "${name}" + for type in ${TYPES}; do + eval desc=\$TYPE_"${type}" + IFS=' +' + for __line in ${desc}; do + # shellcheck disable=SC2086 + eval ${__line%% *}=\"${__line##* }\"; + done + IFS=' +' + + if [ "${name}" = "concurrency" ] && \ + [ "${race_repeat}" = "0" ]; then + continue + fi + if [ "${name}" = "performance" ] && \ + [ "${perf_duration}" = "0" ]; then + continue + fi + + printf " %-60s " "${display}" + eval test_"${name}" + ret=$? + + if [ $ret -eq 0 ]; then + printf "[ OK ]\n" + info_flush + passed=$((passed + 1)) + elif [ $ret -eq 1 ]; then + printf "[FAIL]\n" + err_flush + exit 1 + elif [ $ret -eq ${KSELFTEST_SKIP} ]; then + printf "[SKIP]\n" + err_flush + fi + done +done + +[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} diff --git a/tools/testing/selftests/openat2/.gitignore b/tools/testing/selftests/openat2/.gitignore new file mode 100644 index 000000000000..bd68f6c3fd07 --- /dev/null +++ b/tools/testing/selftests/openat2/.gitignore @@ -0,0 +1 @@ +/*_test diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile new file mode 100644 index 000000000000..4b93b1417b86 --- /dev/null +++ b/tools/testing/selftests/openat2/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined +TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test + +include ../lib.mk + +$(TEST_GEN_PROGS): helpers.c diff --git a/tools/testing/selftests/openat2/helpers.c b/tools/testing/selftests/openat2/helpers.c new file mode 100644 index 000000000000..5074681ffdc9 --- /dev/null +++ b/tools/testing/selftests/openat2/helpers.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <string.h> +#include <syscall.h> +#include <limits.h> + +#include "helpers.h" + +bool needs_openat2(const struct open_how *how) +{ + return how->resolve != 0; +} + +int raw_openat2(int dfd, const char *path, void *how, size_t size) +{ + int ret = syscall(__NR_openat2, dfd, path, how, size); + return ret >= 0 ? ret : -errno; +} + +int sys_openat2(int dfd, const char *path, struct open_how *how) +{ + return raw_openat2(dfd, path, how, sizeof(*how)); +} + +int sys_openat(int dfd, const char *path, struct open_how *how) +{ + int ret = openat(dfd, path, how->flags, how->mode); + return ret >= 0 ? ret : -errno; +} + +int sys_renameat2(int olddirfd, const char *oldpath, + int newdirfd, const char *newpath, unsigned int flags) +{ + int ret = syscall(__NR_renameat2, olddirfd, oldpath, + newdirfd, newpath, flags); + return ret >= 0 ? ret : -errno; +} + +int touchat(int dfd, const char *path) +{ + int fd = openat(dfd, path, O_CREAT, 0700); + if (fd >= 0) + close(fd); + return fd; +} + +char *fdreadlink(int fd) +{ + char *target, *tmp; + + E_asprintf(&tmp, "/proc/self/fd/%d", fd); + + target = malloc(PATH_MAX); + if (!target) + ksft_exit_fail_msg("fdreadlink: malloc failed\n"); + memset(target, 0, PATH_MAX); + + E_readlink(tmp, target, PATH_MAX); + free(tmp); + return target; +} + +bool fdequal(int fd, int dfd, const char *path) +{ + char *fdpath, *dfdpath, *other; + bool cmp; + + fdpath = fdreadlink(fd); + dfdpath = fdreadlink(dfd); + + if (!path) + E_asprintf(&other, "%s", dfdpath); + else if (*path == '/') + E_asprintf(&other, "%s", path); + else + E_asprintf(&other, "%s/%s", dfdpath, path); + + cmp = !strcmp(fdpath, other); + + free(fdpath); + free(dfdpath); + free(other); + return cmp; +} + +bool openat2_supported = false; + +void __attribute__((constructor)) init(void) +{ + struct open_how how = {}; + int fd; + + BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_VER0); + + /* Check openat2(2) support. */ + fd = sys_openat2(AT_FDCWD, ".", &how); + openat2_supported = (fd >= 0); + + if (fd >= 0) + close(fd); +} diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h new file mode 100644 index 000000000000..a6ea27344db2 --- /dev/null +++ b/tools/testing/selftests/openat2/helpers.h @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + */ + +#ifndef __RESOLVEAT_H__ +#define __RESOLVEAT_H__ + +#define _GNU_SOURCE +#include <stdint.h> +#include <errno.h> +#include <linux/types.h> +#include "../kselftest.h" + +#define ARRAY_LEN(X) (sizeof (X) / sizeof (*(X))) +#define BUILD_BUG_ON(e) ((void)(sizeof(struct { int:(-!!(e)); }))) + +#ifndef SYS_openat2 +#ifndef __NR_openat2 +#define __NR_openat2 437 +#endif /* __NR_openat2 */ +#define SYS_openat2 __NR_openat2 +#endif /* SYS_openat2 */ + +/* + * Arguments for how openat2(2) should open the target path. If @resolve is + * zero, then openat2(2) operates very similarly to openat(2). + * + * However, unlike openat(2), unknown bits in @flags result in -EINVAL rather + * than being silently ignored. @mode must be zero unless one of {O_CREAT, + * O_TMPFILE} are set. + * + * @flags: O_* flags. + * @mode: O_CREAT/O_TMPFILE file mode. + * @resolve: RESOLVE_* flags. + */ +struct open_how { + __u64 flags; + __u64 mode; + __u64 resolve; +}; + +#define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */ +#define OPEN_HOW_SIZE_LATEST OPEN_HOW_SIZE_VER0 + +bool needs_openat2(const struct open_how *how); + +#ifndef RESOLVE_IN_ROOT +/* how->resolve flags for openat2(2). */ +#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings + (includes bind-mounts). */ +#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style + "magic-links". */ +#define RESOLVE_NO_SYMLINKS 0x04 /* Block traversal through all symlinks + (implies OEXT_NO_MAGICLINKS) */ +#define RESOLVE_BENEATH 0x08 /* Block "lexical" trickery like + "..", symlinks, and absolute + paths which escape the dirfd. */ +#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." + be scoped inside the dirfd + (similar to chroot(2)). */ +#endif /* RESOLVE_IN_ROOT */ + +#define E_func(func, ...) \ + do { \ + if (func(__VA_ARGS__) < 0) \ + ksft_exit_fail_msg("%s:%d %s failed\n", \ + __FILE__, __LINE__, #func);\ + } while (0) + +#define E_asprintf(...) E_func(asprintf, __VA_ARGS__) +#define E_chmod(...) E_func(chmod, __VA_ARGS__) +#define E_dup2(...) E_func(dup2, __VA_ARGS__) +#define E_fchdir(...) E_func(fchdir, __VA_ARGS__) +#define E_fstatat(...) E_func(fstatat, __VA_ARGS__) +#define E_kill(...) E_func(kill, __VA_ARGS__) +#define E_mkdirat(...) E_func(mkdirat, __VA_ARGS__) +#define E_mount(...) E_func(mount, __VA_ARGS__) +#define E_prctl(...) E_func(prctl, __VA_ARGS__) +#define E_readlink(...) E_func(readlink, __VA_ARGS__) +#define E_setresuid(...) E_func(setresuid, __VA_ARGS__) +#define E_symlinkat(...) E_func(symlinkat, __VA_ARGS__) +#define E_touchat(...) E_func(touchat, __VA_ARGS__) +#define E_unshare(...) E_func(unshare, __VA_ARGS__) + +#define E_assert(expr, msg, ...) \ + do { \ + if (!(expr)) \ + ksft_exit_fail_msg("ASSERT(%s:%d) failed (%s): " msg "\n", \ + __FILE__, __LINE__, #expr, ##__VA_ARGS__); \ + } while (0) + +int raw_openat2(int dfd, const char *path, void *how, size_t size); +int sys_openat2(int dfd, const char *path, struct open_how *how); +int sys_openat(int dfd, const char *path, struct open_how *how); +int sys_renameat2(int olddirfd, const char *oldpath, + int newdirfd, const char *newpath, unsigned int flags); + +int touchat(int dfd, const char *path); +char *fdreadlink(int fd); +bool fdequal(int fd, int dfd, const char *path); + +extern bool openat2_supported; + +#endif /* __RESOLVEAT_H__ */ diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c new file mode 100644 index 000000000000..b386367c606b --- /dev/null +++ b/tools/testing/selftests/openat2/openat2_test.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + */ + +#define _GNU_SOURCE +#include <fcntl.h> +#include <sched.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/mount.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> + +#include "../kselftest.h" +#include "helpers.h" + +/* + * O_LARGEFILE is set to 0 by glibc. + * XXX: This is wrong on {mips, parisc, powerpc, sparc}. + */ +#undef O_LARGEFILE +#define O_LARGEFILE 0x8000 + +struct open_how_ext { + struct open_how inner; + uint32_t extra1; + char pad1[128]; + uint32_t extra2; + char pad2[128]; + uint32_t extra3; +}; + +struct struct_test { + const char *name; + struct open_how_ext arg; + size_t size; + int err; +}; + +#define NUM_OPENAT2_STRUCT_TESTS 7 +#define NUM_OPENAT2_STRUCT_VARIATIONS 13 + +void test_openat2_struct(void) +{ + int misalignments[] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 17, 87 }; + + struct struct_test tests[] = { + /* Normal struct. */ + { .name = "normal struct", + .arg.inner.flags = O_RDONLY, + .size = sizeof(struct open_how) }, + /* Bigger struct, with zeroed out end. */ + { .name = "bigger struct (zeroed out)", + .arg.inner.flags = O_RDONLY, + .size = sizeof(struct open_how_ext) }, + + /* TODO: Once expanded, check zero-padding. */ + + /* Smaller than version-0 struct. */ + { .name = "zero-sized 'struct'", + .arg.inner.flags = O_RDONLY, .size = 0, .err = -EINVAL }, + { .name = "smaller-than-v0 struct", + .arg.inner.flags = O_RDONLY, + .size = OPEN_HOW_SIZE_VER0 - 1, .err = -EINVAL }, + + /* Bigger struct, with non-zero trailing bytes. */ + { .name = "bigger struct (non-zero data in first 'future field')", + .arg.inner.flags = O_RDONLY, .arg.extra1 = 0xdeadbeef, + .size = sizeof(struct open_how_ext), .err = -E2BIG }, + { .name = "bigger struct (non-zero data in middle of 'future fields')", + .arg.inner.flags = O_RDONLY, .arg.extra2 = 0xfeedcafe, + .size = sizeof(struct open_how_ext), .err = -E2BIG }, + { .name = "bigger struct (non-zero data at end of 'future fields')", + .arg.inner.flags = O_RDONLY, .arg.extra3 = 0xabad1dea, + .size = sizeof(struct open_how_ext), .err = -E2BIG }, + }; + + BUILD_BUG_ON(ARRAY_LEN(misalignments) != NUM_OPENAT2_STRUCT_VARIATIONS); + BUILD_BUG_ON(ARRAY_LEN(tests) != NUM_OPENAT2_STRUCT_TESTS); + + for (int i = 0; i < ARRAY_LEN(tests); i++) { + struct struct_test *test = &tests[i]; + struct open_how_ext how_ext = test->arg; + + for (int j = 0; j < ARRAY_LEN(misalignments); j++) { + int fd, misalign = misalignments[j]; + char *fdpath = NULL; + bool failed; + void (*resultfn)(const char *msg, ...) = ksft_test_result_pass; + + void *copy = NULL, *how_copy = &how_ext; + + if (!openat2_supported) { + ksft_print_msg("openat2(2) unsupported\n"); + resultfn = ksft_test_result_skip; + goto skip; + } + + if (misalign) { + /* + * Explicitly misalign the structure copying it with the given + * (mis)alignment offset. The other data is set to be non-zero to + * make sure that non-zero bytes outside the struct aren't checked + * + * This is effectively to check that is_zeroed_user() works. + */ + copy = malloc(misalign + sizeof(how_ext)); + how_copy = copy + misalign; + memset(copy, 0xff, misalign); + memcpy(how_copy, &how_ext, sizeof(how_ext)); + } + + fd = raw_openat2(AT_FDCWD, ".", how_copy, test->size); + if (test->err >= 0) + failed = (fd < 0); + else + failed = (fd != test->err); + if (fd >= 0) { + fdpath = fdreadlink(fd); + close(fd); + } + + if (failed) { + resultfn = ksft_test_result_fail; + + ksft_print_msg("openat2 unexpectedly returned "); + if (fdpath) + ksft_print_msg("%d['%s']\n", fd, fdpath); + else + ksft_print_msg("%d (%s)\n", fd, strerror(-fd)); + } + +skip: + if (test->err >= 0) + resultfn("openat2 with %s argument [misalign=%d] succeeds\n", + test->name, misalign); + else + resultfn("openat2 with %s argument [misalign=%d] fails with %d (%s)\n", + test->name, misalign, test->err, + strerror(-test->err)); + + free(copy); + free(fdpath); + fflush(stdout); + } + } +} + +struct flag_test { + const char *name; + struct open_how how; + int err; +}; + +#define NUM_OPENAT2_FLAG_TESTS 23 + +void test_openat2_flags(void) +{ + struct flag_test tests[] = { + /* O_TMPFILE is incompatible with O_PATH and O_CREAT. */ + { .name = "incompatible flags (O_TMPFILE | O_PATH)", + .how.flags = O_TMPFILE | O_PATH | O_RDWR, .err = -EINVAL }, + { .name = "incompatible flags (O_TMPFILE | O_CREAT)", + .how.flags = O_TMPFILE | O_CREAT | O_RDWR, .err = -EINVAL }, + + /* O_PATH only permits certain other flags to be set ... */ + { .name = "compatible flags (O_PATH | O_CLOEXEC)", + .how.flags = O_PATH | O_CLOEXEC }, + { .name = "compatible flags (O_PATH | O_DIRECTORY)", + .how.flags = O_PATH | O_DIRECTORY }, + { .name = "compatible flags (O_PATH | O_NOFOLLOW)", + .how.flags = O_PATH | O_NOFOLLOW }, + /* ... and others are absolutely not permitted. */ + { .name = "incompatible flags (O_PATH | O_RDWR)", + .how.flags = O_PATH | O_RDWR, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_CREAT)", + .how.flags = O_PATH | O_CREAT, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_EXCL)", + .how.flags = O_PATH | O_EXCL, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_NOCTTY)", + .how.flags = O_PATH | O_NOCTTY, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_DIRECT)", + .how.flags = O_PATH | O_DIRECT, .err = -EINVAL }, + { .name = "incompatible flags (O_PATH | O_LARGEFILE)", + .how.flags = O_PATH | O_LARGEFILE, .err = -EINVAL }, + + /* ->mode must only be set with O_{CREAT,TMPFILE}. */ + { .name = "non-zero how.mode and O_RDONLY", + .how.flags = O_RDONLY, .how.mode = 0600, .err = -EINVAL }, + { .name = "non-zero how.mode and O_PATH", + .how.flags = O_PATH, .how.mode = 0600, .err = -EINVAL }, + { .name = "valid how.mode and O_CREAT", + .how.flags = O_CREAT, .how.mode = 0600 }, + { .name = "valid how.mode and O_TMPFILE", + .how.flags = O_TMPFILE | O_RDWR, .how.mode = 0600 }, + /* ->mode must only contain 0777 bits. */ + { .name = "invalid how.mode and O_CREAT", + .how.flags = O_CREAT, + .how.mode = 0xFFFF, .err = -EINVAL }, + { .name = "invalid (very large) how.mode and O_CREAT", + .how.flags = O_CREAT, + .how.mode = 0xC000000000000000ULL, .err = -EINVAL }, + { .name = "invalid how.mode and O_TMPFILE", + .how.flags = O_TMPFILE | O_RDWR, + .how.mode = 0x1337, .err = -EINVAL }, + { .name = "invalid (very large) how.mode and O_TMPFILE", + .how.flags = O_TMPFILE | O_RDWR, + .how.mode = 0x0000A00000000000ULL, .err = -EINVAL }, + + /* ->resolve must only contain RESOLVE_* flags. */ + { .name = "invalid how.resolve and O_RDONLY", + .how.flags = O_RDONLY, + .how.resolve = 0x1337, .err = -EINVAL }, + { .name = "invalid how.resolve and O_CREAT", + .how.flags = O_CREAT, + .how.resolve = 0x1337, .err = -EINVAL }, + { .name = "invalid how.resolve and O_TMPFILE", + .how.flags = O_TMPFILE | O_RDWR, + .how.resolve = 0x1337, .err = -EINVAL }, + { .name = "invalid how.resolve and O_PATH", + .how.flags = O_PATH, + .how.resolve = 0x1337, .err = -EINVAL }, + }; + + BUILD_BUG_ON(ARRAY_LEN(tests) != NUM_OPENAT2_FLAG_TESTS); + + for (int i = 0; i < ARRAY_LEN(tests); i++) { + int fd, fdflags = -1; + char *path, *fdpath = NULL; + bool failed = false; + struct flag_test *test = &tests[i]; + void (*resultfn)(const char *msg, ...) = ksft_test_result_pass; + + if (!openat2_supported) { + ksft_print_msg("openat2(2) unsupported\n"); + resultfn = ksft_test_result_skip; + goto skip; + } + + path = (test->how.flags & O_CREAT) ? "/tmp/ksft.openat2_tmpfile" : "."; + unlink(path); + + fd = sys_openat2(AT_FDCWD, path, &test->how); + if (test->err >= 0) + failed = (fd < 0); + else + failed = (fd != test->err); + if (fd >= 0) { + int otherflags; + + fdpath = fdreadlink(fd); + fdflags = fcntl(fd, F_GETFL); + otherflags = fcntl(fd, F_GETFD); + close(fd); + + E_assert(fdflags >= 0, "fcntl F_GETFL of new fd"); + E_assert(otherflags >= 0, "fcntl F_GETFD of new fd"); + + /* O_CLOEXEC isn't shown in F_GETFL. */ + if (otherflags & FD_CLOEXEC) + fdflags |= O_CLOEXEC; + /* O_CREAT is hidden from F_GETFL. */ + if (test->how.flags & O_CREAT) + fdflags |= O_CREAT; + if (!(test->how.flags & O_LARGEFILE)) + fdflags &= ~O_LARGEFILE; + failed |= (fdflags != test->how.flags); + } + + if (failed) { + resultfn = ksft_test_result_fail; + + ksft_print_msg("openat2 unexpectedly returned "); + if (fdpath) + ksft_print_msg("%d['%s'] with %X (!= %X)\n", + fd, fdpath, fdflags, + test->how.flags); + else + ksft_print_msg("%d (%s)\n", fd, strerror(-fd)); + } + +skip: + if (test->err >= 0) + resultfn("openat2 with %s succeeds\n", test->name); + else + resultfn("openat2 with %s fails with %d (%s)\n", + test->name, test->err, strerror(-test->err)); + + free(fdpath); + fflush(stdout); + } +} + +#define NUM_TESTS (NUM_OPENAT2_STRUCT_VARIATIONS * NUM_OPENAT2_STRUCT_TESTS + \ + NUM_OPENAT2_FLAG_TESTS) + +int main(int argc, char **argv) +{ + ksft_print_header(); + ksft_set_plan(NUM_TESTS); + + test_openat2_struct(); + test_openat2_flags(); + + if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/openat2/rename_attack_test.c b/tools/testing/selftests/openat2/rename_attack_test.c new file mode 100644 index 000000000000..0a770728b436 --- /dev/null +++ b/tools/testing/selftests/openat2/rename_attack_test.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/mount.h> +#include <sys/mman.h> +#include <sys/prctl.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> +#include <syscall.h> +#include <limits.h> +#include <unistd.h> + +#include "../kselftest.h" +#include "helpers.h" + +/* Construct a test directory with the following structure: + * + * root/ + * |-- a/ + * | `-- c/ + * `-- b/ + */ +int setup_testdir(void) +{ + int dfd; + char dirname[] = "/tmp/ksft-openat2-rename-attack.XXXXXX"; + + /* Make the top-level directory. */ + if (!mkdtemp(dirname)) + ksft_exit_fail_msg("setup_testdir: failed to create tmpdir\n"); + dfd = open(dirname, O_PATH | O_DIRECTORY); + if (dfd < 0) + ksft_exit_fail_msg("setup_testdir: failed to open tmpdir\n"); + + E_mkdirat(dfd, "a", 0755); + E_mkdirat(dfd, "b", 0755); + E_mkdirat(dfd, "a/c", 0755); + + return dfd; +} + +/* Swap @dirfd/@a and @dirfd/@b constantly. Parent must kill this process. */ +pid_t spawn_attack(int dirfd, char *a, char *b) +{ + pid_t child = fork(); + if (child != 0) + return child; + + /* If the parent (the test process) dies, kill ourselves too. */ + E_prctl(PR_SET_PDEATHSIG, SIGKILL); + + /* Swap @a and @b. */ + for (;;) + renameat2(dirfd, a, dirfd, b, RENAME_EXCHANGE); + exit(1); +} + +#define NUM_RENAME_TESTS 2 +#define ROUNDS 400000 + +const char *flagname(int resolve) +{ + switch (resolve) { + case RESOLVE_IN_ROOT: + return "RESOLVE_IN_ROOT"; + case RESOLVE_BENEATH: + return "RESOLVE_BENEATH"; + } + return "(unknown)"; +} + +void test_rename_attack(int resolve) +{ + int dfd, afd; + pid_t child; + void (*resultfn)(const char *msg, ...) = ksft_test_result_pass; + int escapes = 0, other_errs = 0, exdevs = 0, eagains = 0, successes = 0; + + struct open_how how = { + .flags = O_PATH, + .resolve = resolve, + }; + + if (!openat2_supported) { + how.resolve = 0; + ksft_print_msg("openat2(2) unsupported -- using openat(2) instead\n"); + } + + dfd = setup_testdir(); + afd = openat(dfd, "a", O_PATH); + if (afd < 0) + ksft_exit_fail_msg("test_rename_attack: failed to open 'a'\n"); + + child = spawn_attack(dfd, "a/c", "b"); + + for (int i = 0; i < ROUNDS; i++) { + int fd; + char *victim_path = "c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../../c/../.."; + + if (openat2_supported) + fd = sys_openat2(afd, victim_path, &how); + else + fd = sys_openat(afd, victim_path, &how); + + if (fd < 0) { + if (fd == -EAGAIN) + eagains++; + else if (fd == -EXDEV) + exdevs++; + else if (fd == -ENOENT) + escapes++; /* escaped outside and got ENOENT... */ + else + other_errs++; /* unexpected error */ + } else { + if (fdequal(fd, afd, NULL)) + successes++; + else + escapes++; /* we got an unexpected fd */ + } + close(fd); + } + + if (escapes > 0) + resultfn = ksft_test_result_fail; + ksft_print_msg("non-escapes: EAGAIN=%d EXDEV=%d E<other>=%d success=%d\n", + eagains, exdevs, other_errs, successes); + resultfn("rename attack with %s (%d runs, got %d escapes)\n", + flagname(resolve), ROUNDS, escapes); + + /* Should be killed anyway, but might as well make sure. */ + E_kill(child, SIGKILL); +} + +#define NUM_TESTS NUM_RENAME_TESTS + +int main(int argc, char **argv) +{ + ksft_print_header(); + ksft_set_plan(NUM_TESTS); + + test_rename_attack(RESOLVE_BENEATH); + test_rename_attack(RESOLVE_IN_ROOT); + + if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/openat2/resolve_test.c b/tools/testing/selftests/openat2/resolve_test.c new file mode 100644 index 000000000000..bbafad440893 --- /dev/null +++ b/tools/testing/selftests/openat2/resolve_test.c @@ -0,0 +1,523 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Aleksa Sarai <cyphar@cyphar.com> + * Copyright (C) 2018-2019 SUSE LLC. + */ + +#define _GNU_SOURCE +#include <fcntl.h> +#include <sched.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/mount.h> +#include <stdlib.h> +#include <stdbool.h> +#include <string.h> + +#include "../kselftest.h" +#include "helpers.h" + +/* + * Construct a test directory with the following structure: + * + * root/ + * |-- procexe -> /proc/self/exe + * |-- procroot -> /proc/self/root + * |-- root/ + * |-- mnt/ [mountpoint] + * | |-- self -> ../mnt/ + * | `-- absself -> /mnt/ + * |-- etc/ + * | `-- passwd + * |-- creatlink -> /newfile3 + * |-- reletc -> etc/ + * |-- relsym -> etc/passwd + * |-- absetc -> /etc/ + * |-- abssym -> /etc/passwd + * |-- abscheeky -> /cheeky + * `-- cheeky/ + * |-- absself -> / + * |-- self -> ../../root/ + * |-- garbageself -> /../../root/ + * |-- passwd -> ../cheeky/../cheeky/../etc/../etc/passwd + * |-- abspasswd -> /../cheeky/../cheeky/../etc/../etc/passwd + * |-- dotdotlink -> ../../../../../../../../../../../../../../etc/passwd + * `-- garbagelink -> /../../../../../../../../../../../../../../etc/passwd + */ +int setup_testdir(void) +{ + int dfd, tmpfd; + char dirname[] = "/tmp/ksft-openat2-testdir.XXXXXX"; + + /* Unshare and make /tmp a new directory. */ + E_unshare(CLONE_NEWNS); + E_mount("", "/tmp", "", MS_PRIVATE, ""); + + /* Make the top-level directory. */ + if (!mkdtemp(dirname)) + ksft_exit_fail_msg("setup_testdir: failed to create tmpdir\n"); + dfd = open(dirname, O_PATH | O_DIRECTORY); + if (dfd < 0) + ksft_exit_fail_msg("setup_testdir: failed to open tmpdir\n"); + + /* A sub-directory which is actually used for tests. */ + E_mkdirat(dfd, "root", 0755); + tmpfd = openat(dfd, "root", O_PATH | O_DIRECTORY); + if (tmpfd < 0) + ksft_exit_fail_msg("setup_testdir: failed to open tmpdir\n"); + close(dfd); + dfd = tmpfd; + + E_symlinkat("/proc/self/exe", dfd, "procexe"); + E_symlinkat("/proc/self/root", dfd, "procroot"); + E_mkdirat(dfd, "root", 0755); + + /* There is no mountat(2), so use chdir. */ + E_mkdirat(dfd, "mnt", 0755); + E_fchdir(dfd); + E_mount("tmpfs", "./mnt", "tmpfs", MS_NOSUID | MS_NODEV, ""); + E_symlinkat("../mnt/", dfd, "mnt/self"); + E_symlinkat("/mnt/", dfd, "mnt/absself"); + + E_mkdirat(dfd, "etc", 0755); + E_touchat(dfd, "etc/passwd"); + + E_symlinkat("/newfile3", dfd, "creatlink"); + E_symlinkat("etc/", dfd, "reletc"); + E_symlinkat("etc/passwd", dfd, "relsym"); + E_symlinkat("/etc/", dfd, "absetc"); + E_symlinkat("/etc/passwd", dfd, "abssym"); + E_symlinkat("/cheeky", dfd, "abscheeky"); + + E_mkdirat(dfd, "cheeky", 0755); + + E_symlinkat("/", dfd, "cheeky/absself"); + E_symlinkat("../../root/", dfd, "cheeky/self"); + E_symlinkat("/../../root/", dfd, "cheeky/garbageself"); + + E_symlinkat("../cheeky/../etc/../etc/passwd", dfd, "cheeky/passwd"); + E_symlinkat("/../cheeky/../etc/../etc/passwd", dfd, "cheeky/abspasswd"); + + E_symlinkat("../../../../../../../../../../../../../../etc/passwd", + dfd, "cheeky/dotdotlink"); + E_symlinkat("/../../../../../../../../../../../../../../etc/passwd", + dfd, "cheeky/garbagelink"); + + return dfd; +} + +struct basic_test { + const char *name; + const char *dir; + const char *path; + struct open_how how; + bool pass; + union { + int err; + const char *path; + } out; +}; + +#define NUM_OPENAT2_OPATH_TESTS 88 + +void test_openat2_opath_tests(void) +{ + int rootfd, hardcoded_fd; + char *procselfexe, *hardcoded_fdpath; + + E_asprintf(&procselfexe, "/proc/%d/exe", getpid()); + rootfd = setup_testdir(); + + hardcoded_fd = open("/dev/null", O_RDONLY); + E_assert(hardcoded_fd >= 0, "open fd to hardcode"); + E_asprintf(&hardcoded_fdpath, "self/fd/%d", hardcoded_fd); + + struct basic_test tests[] = { + /** RESOLVE_BENEATH **/ + /* Attempts to cross dirfd should be blocked. */ + { .name = "[beneath] jump to /", + .path = "/", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] absolute link to $root", + .path = "cheeky/absself", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] chained absolute links to $root", + .path = "abscheeky/absself", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] jump outside $root", + .path = "..", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] temporary jump outside $root", + .path = "../root/", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] symlink temporary jump outside $root", + .path = "cheeky/self", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] chained symlink temporary jump outside $root", + .path = "abscheeky/self", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] garbage links to $root", + .path = "cheeky/garbageself", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] chained garbage links to $root", + .path = "abscheeky/garbageself", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + /* Only relative paths that stay inside dirfd should work. */ + { .name = "[beneath] ordinary path to 'root'", + .path = "root", .how.resolve = RESOLVE_BENEATH, + .out.path = "root", .pass = true }, + { .name = "[beneath] ordinary path to 'etc'", + .path = "etc", .how.resolve = RESOLVE_BENEATH, + .out.path = "etc", .pass = true }, + { .name = "[beneath] ordinary path to 'etc/passwd'", + .path = "etc/passwd", .how.resolve = RESOLVE_BENEATH, + .out.path = "etc/passwd", .pass = true }, + { .name = "[beneath] relative symlink inside $root", + .path = "relsym", .how.resolve = RESOLVE_BENEATH, + .out.path = "etc/passwd", .pass = true }, + { .name = "[beneath] chained-'..' relative symlink inside $root", + .path = "cheeky/passwd", .how.resolve = RESOLVE_BENEATH, + .out.path = "etc/passwd", .pass = true }, + { .name = "[beneath] absolute symlink component outside $root", + .path = "abscheeky/passwd", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] absolute symlink target outside $root", + .path = "abssym", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] absolute path outside $root", + .path = "/etc/passwd", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] cheeky absolute path outside $root", + .path = "cheeky/abspasswd", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] chained cheeky absolute path outside $root", + .path = "abscheeky/abspasswd", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + /* Tricky paths should fail. */ + { .name = "[beneath] tricky '..'-chained symlink outside $root", + .path = "cheeky/dotdotlink", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] tricky absolute + '..'-chained symlink outside $root", + .path = "abscheeky/dotdotlink", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] tricky garbage link outside $root", + .path = "cheeky/garbagelink", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + { .name = "[beneath] tricky absolute + garbage link outside $root", + .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_BENEATH, + .out.err = -EXDEV, .pass = false }, + + /** RESOLVE_IN_ROOT **/ + /* All attempts to cross the dirfd will be scoped-to-root. */ + { .name = "[in_root] jump to /", + .path = "/", .how.resolve = RESOLVE_IN_ROOT, + .out.path = NULL, .pass = true }, + { .name = "[in_root] absolute symlink to /root", + .path = "cheeky/absself", .how.resolve = RESOLVE_IN_ROOT, + .out.path = NULL, .pass = true }, + { .name = "[in_root] chained absolute symlinks to /root", + .path = "abscheeky/absself", .how.resolve = RESOLVE_IN_ROOT, + .out.path = NULL, .pass = true }, + { .name = "[in_root] '..' at root", + .path = "..", .how.resolve = RESOLVE_IN_ROOT, + .out.path = NULL, .pass = true }, + { .name = "[in_root] '../root' at root", + .path = "../root/", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] relative symlink containing '..' above root", + .path = "cheeky/self", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] garbage link to /root", + .path = "cheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] chained garbage links to /root", + .path = "abscheeky/garbageself", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] relative path to 'root'", + .path = "root", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "root", .pass = true }, + { .name = "[in_root] relative path to 'etc'", + .path = "etc", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc", .pass = true }, + { .name = "[in_root] relative path to 'etc/passwd'", + .path = "etc/passwd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] relative symlink to 'etc/passwd'", + .path = "relsym", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] chained-'..' relative symlink to 'etc/passwd'", + .path = "cheeky/passwd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] chained-'..' absolute + relative symlink to 'etc/passwd'", + .path = "abscheeky/passwd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] absolute symlink to 'etc/passwd'", + .path = "abssym", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] absolute path 'etc/passwd'", + .path = "/etc/passwd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] cheeky absolute path 'etc/passwd'", + .path = "cheeky/abspasswd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] chained cheeky absolute path 'etc/passwd'", + .path = "abscheeky/abspasswd", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky '..'-chained symlink outside $root", + .path = "cheeky/dotdotlink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky absolute + '..'-chained symlink outside $root", + .path = "abscheeky/dotdotlink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky absolute path + absolute + '..'-chained symlink outside $root", + .path = "/../../../../abscheeky/dotdotlink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky garbage link outside $root", + .path = "cheeky/garbagelink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky absolute + garbage link outside $root", + .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + { .name = "[in_root] tricky absolute path + absolute + garbage link outside $root", + .path = "/../../../../abscheeky/garbagelink", .how.resolve = RESOLVE_IN_ROOT, + .out.path = "etc/passwd", .pass = true }, + /* O_CREAT should handle trailing symlinks correctly. */ + { .name = "[in_root] O_CREAT of relative path inside $root", + .path = "newfile1", .how.flags = O_CREAT, + .how.mode = 0700, + .how.resolve = RESOLVE_IN_ROOT, + .out.path = "newfile1", .pass = true }, + { .name = "[in_root] O_CREAT of absolute path", + .path = "/newfile2", .how.flags = O_CREAT, + .how.mode = 0700, + .how.resolve = RESOLVE_IN_ROOT, + .out.path = "newfile2", .pass = true }, + { .name = "[in_root] O_CREAT of tricky symlink outside root", + .path = "/creatlink", .how.flags = O_CREAT, + .how.mode = 0700, + .how.resolve = RESOLVE_IN_ROOT, + .out.path = "newfile3", .pass = true }, + + /** RESOLVE_NO_XDEV **/ + /* Crossing *down* into a mountpoint is disallowed. */ + { .name = "[no_xdev] cross into $mnt", + .path = "mnt", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] cross into $mnt/", + .path = "mnt/", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] cross into $mnt/.", + .path = "mnt/.", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + /* Crossing *up* out of a mountpoint is disallowed. */ + { .name = "[no_xdev] goto mountpoint root", + .dir = "mnt", .path = ".", .how.resolve = RESOLVE_NO_XDEV, + .out.path = "mnt", .pass = true }, + { .name = "[no_xdev] cross up through '..'", + .dir = "mnt", .path = "..", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] temporary cross up through '..'", + .dir = "mnt", .path = "../mnt", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] temporary relative symlink cross up", + .dir = "mnt", .path = "self", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] temporary absolute symlink cross up", + .dir = "mnt", .path = "absself", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + /* Jumping to "/" is ok, but later components cannot cross. */ + { .name = "[no_xdev] jump to / directly", + .dir = "mnt", .path = "/", .how.resolve = RESOLVE_NO_XDEV, + .out.path = "/", .pass = true }, + { .name = "[no_xdev] jump to / (from /) directly", + .dir = "/", .path = "/", .how.resolve = RESOLVE_NO_XDEV, + .out.path = "/", .pass = true }, + { .name = "[no_xdev] jump to / then proc", + .path = "/proc/1", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] jump to / then tmp", + .path = "/tmp", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + /* Magic-links are blocked since they can switch vfsmounts. */ + { .name = "[no_xdev] cross through magic-link to self/root", + .dir = "/proc", .path = "self/root", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + { .name = "[no_xdev] cross through magic-link to self/cwd", + .dir = "/proc", .path = "self/cwd", .how.resolve = RESOLVE_NO_XDEV, + .out.err = -EXDEV, .pass = false }, + /* Except magic-link jumps inside the same vfsmount. */ + { .name = "[no_xdev] jump through magic-link to same procfs", + .dir = "/proc", .path = hardcoded_fdpath, .how.resolve = RESOLVE_NO_XDEV, + .out.path = "/proc", .pass = true, }, + + /** RESOLVE_NO_MAGICLINKS **/ + /* Regular symlinks should work. */ + { .name = "[no_magiclinks] ordinary relative symlink", + .path = "relsym", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.path = "etc/passwd", .pass = true }, + /* Magic-links should not work. */ + { .name = "[no_magiclinks] symlink to magic-link", + .path = "procexe", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_magiclinks] normal path to magic-link", + .path = "/proc/self/exe", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_magiclinks] normal path to magic-link with O_NOFOLLOW", + .path = "/proc/self/exe", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.path = procselfexe, .pass = true }, + { .name = "[no_magiclinks] symlink to magic-link path component", + .path = "procroot/etc", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_magiclinks] magic-link path component", + .path = "/proc/self/root/etc", .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_magiclinks] magic-link path component with O_NOFOLLOW", + .path = "/proc/self/root/etc", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_MAGICLINKS, + .out.err = -ELOOP, .pass = false }, + + /** RESOLVE_NO_SYMLINKS **/ + /* Normal paths should work. */ + { .name = "[no_symlinks] ordinary path to '.'", + .path = ".", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = NULL, .pass = true }, + { .name = "[no_symlinks] ordinary path to 'root'", + .path = "root", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "root", .pass = true }, + { .name = "[no_symlinks] ordinary path to 'etc'", + .path = "etc", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "etc", .pass = true }, + { .name = "[no_symlinks] ordinary path to 'etc/passwd'", + .path = "etc/passwd", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "etc/passwd", .pass = true }, + /* Regular symlinks are blocked. */ + { .name = "[no_symlinks] relative symlink target", + .path = "relsym", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] relative symlink component", + .path = "reletc/passwd", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] absolute symlink target", + .path = "abssym", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] absolute symlink component", + .path = "absetc/passwd", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] cheeky garbage link", + .path = "cheeky/garbagelink", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] cheeky absolute + garbage link", + .path = "abscheeky/garbagelink", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] cheeky absolute + absolute symlink", + .path = "abscheeky/absself", .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + /* Trailing symlinks with NO_FOLLOW. */ + { .name = "[no_symlinks] relative symlink with O_NOFOLLOW", + .path = "relsym", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "relsym", .pass = true }, + { .name = "[no_symlinks] absolute symlink with O_NOFOLLOW", + .path = "abssym", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "abssym", .pass = true }, + { .name = "[no_symlinks] trailing symlink with O_NOFOLLOW", + .path = "cheeky/garbagelink", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.path = "cheeky/garbagelink", .pass = true }, + { .name = "[no_symlinks] multiple symlink components with O_NOFOLLOW", + .path = "abscheeky/absself", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + { .name = "[no_symlinks] multiple symlink (and garbage link) components with O_NOFOLLOW", + .path = "abscheeky/garbagelink", .how.flags = O_NOFOLLOW, + .how.resolve = RESOLVE_NO_SYMLINKS, + .out.err = -ELOOP, .pass = false }, + }; + + BUILD_BUG_ON(ARRAY_LEN(tests) != NUM_OPENAT2_OPATH_TESTS); + + for (int i = 0; i < ARRAY_LEN(tests); i++) { + int dfd, fd; + char *fdpath = NULL; + bool failed; + void (*resultfn)(const char *msg, ...) = ksft_test_result_pass; + struct basic_test *test = &tests[i]; + + if (!openat2_supported) { + ksft_print_msg("openat2(2) unsupported\n"); + resultfn = ksft_test_result_skip; + goto skip; + } + + /* Auto-set O_PATH. */ + if (!(test->how.flags & O_CREAT)) + test->how.flags |= O_PATH; + + if (test->dir) + dfd = openat(rootfd, test->dir, O_PATH | O_DIRECTORY); + else + dfd = dup(rootfd); + E_assert(dfd, "failed to openat root '%s': %m", test->dir); + + E_dup2(dfd, hardcoded_fd); + + fd = sys_openat2(dfd, test->path, &test->how); + if (test->pass) + failed = (fd < 0 || !fdequal(fd, rootfd, test->out.path)); + else + failed = (fd != test->out.err); + if (fd >= 0) { + fdpath = fdreadlink(fd); + close(fd); + } + close(dfd); + + if (failed) { + resultfn = ksft_test_result_fail; + + ksft_print_msg("openat2 unexpectedly returned "); + if (fdpath) + ksft_print_msg("%d['%s']\n", fd, fdpath); + else + ksft_print_msg("%d (%s)\n", fd, strerror(-fd)); + } + +skip: + if (test->pass) + resultfn("%s gives path '%s'\n", test->name, + test->out.path ?: "."); + else + resultfn("%s fails with %d (%s)\n", test->name, + test->out.err, strerror(-test->out.err)); + + fflush(stdout); + free(fdpath); + } + + free(procselfexe); + close(rootfd); + + free(hardcoded_fdpath); + close(hardcoded_fd); +} + +#define NUM_TESTS NUM_OPENAT2_OPATH_TESTS + +int main(int argc, char **argv) +{ + ksft_print_header(); + ksft_set_plan(NUM_TESTS); + + /* NOTE: We should be checking for CAP_SYS_ADMIN here... */ + if (geteuid() != 0) + ksft_exit_skip("all tests require euid == 0\n"); + + test_openat2_opath_tests(); + + if (ksft_get_fail_cnt() + ksft_get_error_cnt() > 0) + ksft_exit_fail(); + else + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 8d069490e17b..3a779c084d96 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -2,3 +2,4 @@ pidfd_open_test pidfd_poll_test pidfd_test pidfd_wait +pidfd_getfd_test diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index 43db1b98e845..75a545861375 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS += -g -I../../../../usr/include/ -pthread -TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait +TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait pidfd_getfd_test include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index c6bc68329f4b..d482515604db 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -36,6 +36,10 @@ #define __NR_clone3 -1 #endif +#ifndef __NR_pidfd_getfd +#define __NR_pidfd_getfd -1 +#endif + /* * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c * That means, when it wraps around any pid < 300 will be skipped. @@ -84,4 +88,9 @@ static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); } +static inline int sys_pidfd_getfd(int pidfd, int fd, int flags) +{ + return syscall(__NR_pidfd_getfd, pidfd, fd, flags); +} + #endif /* __PIDFD_H */ diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c new file mode 100644 index 000000000000..401a7c1d0312 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <limits.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/prctl.h> +#include <sys/wait.h> +#include <unistd.h> +#include <sys/socket.h> +#include <linux/kcmp.h> + +#include "pidfd.h" +#include "../kselftest.h" +#include "../kselftest_harness.h" + +/* + * UNKNOWN_FD is an fd number that should never exist in the child, as it is + * used to check the negative case. + */ +#define UNKNOWN_FD 111 +#define UID_NOBODY 65535 + +static int sys_kcmp(pid_t pid1, pid_t pid2, int type, unsigned long idx1, + unsigned long idx2) +{ + return syscall(__NR_kcmp, pid1, pid2, type, idx1, idx2); +} + +static int sys_memfd_create(const char *name, unsigned int flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + +static int __child(int sk, int memfd) +{ + int ret; + char buf; + + /* + * Ensure we don't leave around a bunch of orphaned children if our + * tests fail. + */ + ret = prctl(PR_SET_PDEATHSIG, SIGKILL); + if (ret) { + fprintf(stderr, "%s: Child could not set DEATHSIG\n", + strerror(errno)); + return -1; + } + + ret = send(sk, &memfd, sizeof(memfd), 0); + if (ret != sizeof(memfd)) { + fprintf(stderr, "%s: Child failed to send fd number\n", + strerror(errno)); + return -1; + } + + /* + * The fixture setup is completed at this point. The tests will run. + * + * This blocking recv enables the parent to message the child. + * Either we will read 'P' off of the sk, indicating that we need + * to disable ptrace, or we will read a 0, indicating that the other + * side has closed the sk. This occurs during fixture teardown time, + * indicating that the child should exit. + */ + while ((ret = recv(sk, &buf, sizeof(buf), 0)) > 0) { + if (buf == 'P') { + ret = prctl(PR_SET_DUMPABLE, 0); + if (ret < 0) { + fprintf(stderr, + "%s: Child failed to disable ptrace\n", + strerror(errno)); + return -1; + } + } else { + fprintf(stderr, "Child received unknown command %c\n", + buf); + return -1; + } + ret = send(sk, &buf, sizeof(buf), 0); + if (ret != 1) { + fprintf(stderr, "%s: Child failed to ack\n", + strerror(errno)); + return -1; + } + } + if (ret < 0) { + fprintf(stderr, "%s: Child failed to read from socket\n", + strerror(errno)); + return -1; + } + + return 0; +} + +static int child(int sk) +{ + int memfd, ret; + + memfd = sys_memfd_create("test", 0); + if (memfd < 0) { + fprintf(stderr, "%s: Child could not create memfd\n", + strerror(errno)); + ret = -1; + } else { + ret = __child(sk, memfd); + close(memfd); + } + + close(sk); + return ret; +} + +FIXTURE(child) +{ + /* + * remote_fd is the number of the FD which we are trying to retrieve + * from the child. + */ + int remote_fd; + /* pid points to the child which we are fetching FDs from */ + pid_t pid; + /* pidfd is the pidfd of the child */ + int pidfd; + /* + * sk is our side of the socketpair used to communicate with the child. + * When it is closed, the child will exit. + */ + int sk; +}; + +FIXTURE_SETUP(child) +{ + int ret, sk_pair[2]; + + ASSERT_EQ(0, socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair)) { + TH_LOG("%s: failed to create socketpair", strerror(errno)); + } + self->sk = sk_pair[0]; + + self->pid = fork(); + ASSERT_GE(self->pid, 0); + + if (self->pid == 0) { + close(sk_pair[0]); + if (child(sk_pair[1])) + _exit(EXIT_FAILURE); + _exit(EXIT_SUCCESS); + } + + close(sk_pair[1]); + + self->pidfd = sys_pidfd_open(self->pid, 0); + ASSERT_GE(self->pidfd, 0); + + /* + * Wait for the child to complete setup. It'll send the remote memfd's + * number when ready. + */ + ret = recv(sk_pair[0], &self->remote_fd, sizeof(self->remote_fd), 0); + ASSERT_EQ(sizeof(self->remote_fd), ret); +} + +FIXTURE_TEARDOWN(child) +{ + EXPECT_EQ(0, close(self->pidfd)); + EXPECT_EQ(0, close(self->sk)); + + EXPECT_EQ(0, wait_for_pid(self->pid)); +} + +TEST_F(child, disable_ptrace) +{ + int uid, fd; + char c; + + /* + * Turn into nobody if we're root, to avoid CAP_SYS_PTRACE + * + * The tests should run in their own process, so even this test fails, + * it shouldn't result in subsequent tests failing. + */ + uid = getuid(); + if (uid == 0) + ASSERT_EQ(0, seteuid(UID_NOBODY)); + + ASSERT_EQ(1, send(self->sk, "P", 1, 0)); + ASSERT_EQ(1, recv(self->sk, &c, 1, 0)); + + fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0); + EXPECT_EQ(-1, fd); + EXPECT_EQ(EPERM, errno); + + if (uid == 0) + ASSERT_EQ(0, seteuid(0)); +} + +TEST_F(child, fetch_fd) +{ + int fd, ret; + + fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0); + ASSERT_GE(fd, 0); + + EXPECT_EQ(0, sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd)); + + ret = fcntl(fd, F_GETFD); + ASSERT_GE(ret, 0); + EXPECT_GE(ret & FD_CLOEXEC, 0); + + close(fd); +} + +TEST_F(child, test_unknown_fd) +{ + int fd; + + fd = sys_pidfd_getfd(self->pidfd, UNKNOWN_FD, 0); + EXPECT_EQ(-1, fd) { + TH_LOG("getfd succeeded while fetching unknown fd"); + }; + EXPECT_EQ(EBADF, errno) { + TH_LOG("%s: getfd did not get EBADF", strerror(errno)); + } +} + +TEST(flags_set) +{ + ASSERT_EQ(-1, sys_pidfd_getfd(0, 0, 1)); + EXPECT_EQ(errno, EINVAL); +} + +#if __NR_pidfd_getfd == -1 +int main(void) +{ + fprintf(stderr, "__NR_pidfd_getfd undefined. The pidfd_getfd syscall is unavailable. Test aborting\n"); + return KSFT_SKIP; +} +#else +TEST_HARNESS_MAIN +#endif diff --git a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh index 26112ab5cdf4..f52ed92b53e7 100755 --- a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh +++ b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh @@ -53,9 +53,13 @@ eeh_one_dev() { # is a no-op. echo $dev >/sys/kernel/debug/powerpc/eeh_dev_check - # Enforce a 30s timeout for recovery. Even the IPR, which is infamously - # slow to reset, should recover within 30s. - max_wait=30 + # Default to a 60s timeout when waiting for a device to recover. This + # is an arbitrary default which can be overridden by setting the + # EEH_MAX_WAIT environmental variable when required. + + # The current record holder for longest recovery time is: + # "Adaptec Series 8 12G SAS/PCIe 3" at 39 seconds + max_wait=${EEH_MAX_WAIT:=60} for i in `seq 0 ${max_wait}` ; do if pe_ok $dev ; then diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore index 7101ffd08d66..0ebeaea22641 100644 --- a/tools/testing/selftests/powerpc/mm/.gitignore +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -5,3 +5,4 @@ prot_sao segv_errors wild_bctr large_vm_fork_separation +bad_accesses diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index ed1565809d2b..b9103c4bb414 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -3,7 +3,7 @@ noarg: $(MAKE) -C ../ TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \ - large_vm_fork_separation + large_vm_fork_separation bad_accesses TEST_GEN_PROGS_EXTENDED := tlbie_test TEST_GEN_FILES := tempfile @@ -16,6 +16,7 @@ $(OUTPUT)/prot_sao: ../utils.c $(OUTPUT)/wild_bctr: CFLAGS += -m64 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64 +$(OUTPUT)/bad_accesses: CFLAGS += -m64 $(OUTPUT)/tempfile: dd if=/dev/zero of=$@ bs=64k count=1 diff --git a/tools/testing/selftests/powerpc/mm/bad_accesses.c b/tools/testing/selftests/powerpc/mm/bad_accesses.c new file mode 100644 index 000000000000..adc465f499ef --- /dev/null +++ b/tools/testing/selftests/powerpc/mm/bad_accesses.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0+ +// +// Copyright 2019, Michael Ellerman, IBM Corp. +// +// Test that out-of-bounds reads/writes behave as expected. + +#include <setjmp.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "utils.h" + +// Old distros (Ubuntu 16.04 at least) don't define this +#ifndef SEGV_BNDERR +#define SEGV_BNDERR 3 +#endif + +// 64-bit kernel is always here +#define PAGE_OFFSET (0xcul << 60) + +static unsigned long kernel_virt_end; + +static volatile int fault_code; +static volatile unsigned long fault_addr; +static jmp_buf setjmp_env; + +static void segv_handler(int n, siginfo_t *info, void *ctxt_v) +{ + fault_code = info->si_code; + fault_addr = (unsigned long)info->si_addr; + siglongjmp(setjmp_env, 1); +} + +int bad_access(char *p, bool write) +{ + char x; + + fault_code = 0; + fault_addr = 0; + + if (sigsetjmp(setjmp_env, 1) == 0) { + if (write) + *p = 1; + else + x = *p; + + printf("Bad - no SEGV! (%c)\n", x); + return 1; + } + + // If we see MAPERR that means we took a page fault rather than an SLB + // miss. We only expect to take page faults for addresses within the + // valid kernel range. + FAIL_IF(fault_code == SEGV_MAPERR && \ + (fault_addr < PAGE_OFFSET || fault_addr >= kernel_virt_end)); + + FAIL_IF(fault_code != SEGV_MAPERR && fault_code != SEGV_BNDERR); + + return 0; +} + +static int using_hash_mmu(bool *using_hash) +{ + char line[128]; + FILE *f; + int rc; + + f = fopen("/proc/cpuinfo", "r"); + FAIL_IF(!f); + + rc = 0; + while (fgets(line, sizeof(line), f) != NULL) { + if (strcmp(line, "MMU : Hash\n") == 0) { + *using_hash = true; + goto out; + } + + if (strcmp(line, "MMU : Radix\n") == 0) { + *using_hash = false; + goto out; + } + } + + rc = -1; +out: + fclose(f); + return rc; +} + +static int test(void) +{ + unsigned long i, j, addr, region_shift, page_shift, page_size; + struct sigaction sig; + bool hash_mmu; + + sig = (struct sigaction) { + .sa_sigaction = segv_handler, + .sa_flags = SA_SIGINFO, + }; + + FAIL_IF(sigaction(SIGSEGV, &sig, NULL) != 0); + + FAIL_IF(using_hash_mmu(&hash_mmu)); + + page_size = sysconf(_SC_PAGESIZE); + if (page_size == (64 * 1024)) + page_shift = 16; + else + page_shift = 12; + + if (page_size == (64 * 1024) || !hash_mmu) { + region_shift = 52; + + // We have 7 512T regions (4 kernel linear, vmalloc, io, vmemmap) + kernel_virt_end = PAGE_OFFSET + (7 * (512ul << 40)); + } else if (page_size == (4 * 1024) && hash_mmu) { + region_shift = 46; + + // We have 7 64T regions (4 kernel linear, vmalloc, io, vmemmap) + kernel_virt_end = PAGE_OFFSET + (7 * (64ul << 40)); + } else + FAIL_IF(true); + + printf("Using %s MMU, PAGE_SIZE = %dKB start address 0x%016lx\n", + hash_mmu ? "hash" : "radix", + (1 << page_shift) >> 10, + 1ul << region_shift); + + // This generates access patterns like: + // 0x0010000000000000 + // 0x0010000000010000 + // 0x0010000000020000 + // ... + // 0x0014000000000000 + // 0x0018000000000000 + // 0x0020000000000000 + // 0x0020000000010000 + // 0x0020000000020000 + // ... + // 0xf400000000000000 + // 0xf800000000000000 + + for (i = 1; i <= ((0xful << 60) >> region_shift); i++) { + for (j = page_shift - 1; j < 60; j++) { + unsigned long base, delta; + + base = i << region_shift; + delta = 1ul << j; + + if (delta >= base) + break; + + addr = (base | delta) & ~((1 << page_shift) - 1); + + FAIL_IF(bad_access((char *)addr, false)); + FAIL_IF(bad_access((char *)addr, true)); + } + } + + return 0; +} + +int main(void) +{ + return test_harness(test, "bad_accesses"); +} diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c index 7deedbc16b0b..fc477dfe86a2 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c @@ -455,9 +455,8 @@ run_tests(pid_t child_pid, struct ppc_debug_info *dbginfo, bool dawr) if (dbginfo->features & PPC_DEBUG_FEATURE_DATA_BP_RANGE) { test_sethwdebug_exact(child_pid); - if (!is_8xx) - test_sethwdebug_range_aligned(child_pid); - if (dawr && !is_8xx) { + test_sethwdebug_range_aligned(child_pid); + if (dawr || is_8xx) { test_sethwdebug_range_unaligned(child_pid); test_sethwdebug_range_unaligned_dar(child_pid); test_sethwdebug_dawr_max_range(child_pid); diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh index 4e9485590c10..1dbfb62567d2 100755 --- a/tools/testing/selftests/rcutorture/bin/cpus2use.sh +++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh @@ -15,8 +15,15 @@ then exit 0 fi ncpus=`grep '^processor' /proc/cpuinfo | wc -l` -idlecpus=`mpstat | tail -1 | \ - awk -v ncpus=$ncpus '{ print ncpus * ($7 + $NF) / 100 }'` +if mpstat -V > /dev/null 2>&1 +then + idlecpus=`mpstat | tail -1 | \ + awk -v ncpus=$ncpus '{ print ncpus * ($7 + $NF) / 100 }'` +else + # No mpstat command, so use all available CPUs. + echo The mpstat command is not available, so greedily using all CPUs. + idlecpus=$ncpus +fi awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null ' BEGIN { cpus2use = idlecpus; diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh index dc49a3ba6111..30cb5b27d32e 100755 --- a/tools/testing/selftests/rcutorture/bin/jitter.sh +++ b/tools/testing/selftests/rcutorture/bin/jitter.sh @@ -23,25 +23,39 @@ spinmax=${4-1000} n=1 -starttime=`awk 'BEGIN { print systime(); }' < /dev/null` +starttime=`gawk 'BEGIN { print systime(); }' < /dev/null` + +nohotplugcpus= +for i in /sys/devices/system/cpu/cpu[0-9]* +do + if test -f $i/online + then + : + else + curcpu=`echo $i | sed -e 's/^[^0-9]*//'` + nohotplugcpus="$nohotplugcpus $curcpu" + fi +done while : do # Check for done. - t=`awk -v s=$starttime 'BEGIN { print systime() - s; }' < /dev/null` + t=`gawk -v s=$starttime 'BEGIN { print systime() - s; }' < /dev/null` if test "$t" -gt "$duration" then exit 0; fi # Set affinity to randomly selected online CPU - cpus=`grep 1 /sys/devices/system/cpu/*/online | - sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//'` - - # Do not leave out poor old cpu0 which may not be hot-pluggable - if [ ! -f "/sys/devices/system/cpu/cpu0/online" ]; then - cpus="0 $cpus" + if cpus=`grep 1 /sys/devices/system/cpu/*/online 2>&1 | + sed -e 's,/[^/]*$,,' -e 's/^[^0-9]*//'` + then + : + else + cpus= fi + # Do not leave out non-hot-pluggable CPUs + cpus="$cpus $nohotplugcpus" cpumask=`awk -v cpus="$cpus" -v me=$me -v n=$n 'BEGIN { srand(n + me + systime()); diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index 2a7f3f4756a7..9d9a41625dd9 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -25,6 +25,7 @@ stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null | tail -1 | sed -e 's/^\[[ 0-9.]*] //' | awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' | tr -d '\012\015'`" +fwdprog="`grep 'rcu_torture_fwd_prog_cr Duration' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k15nr | head -1 | awk '{ print $14 " " $15 }'`" if test -z "$ngps" then echo "$configfile ------- " $stopstate @@ -39,7 +40,7 @@ else BEGIN { print ngps / dur }' < /dev/null` title="$title ($ngpsps/s)" fi - echo $title $stopstate + echo $title $stopstate $fwdprog nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'` if test -z "$nclosecalls" then diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 33c669619736..e0352304b98b 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -123,7 +123,7 @@ qemu_args=$5 boot_args=$6 cd $KVM -kstarttime=`awk 'BEGIN { print systime() }' < /dev/null` +kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null` if test -z "$TORTURE_BUILDONLY" then echo ' ---' `date`: Starting kernel @@ -133,11 +133,10 @@ fi qemu_args="-enable-kvm -nographic $qemu_args" cpu_count=`configNR_CPUS.sh $resdir/ConfigFragment` cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"` -vcpus=`identify_qemu_vcpus` -if test $cpu_count -gt $vcpus +if test "$cpu_count" -gt "$TORTURE_ALLOTED_CPUS" then - echo CPU count limited from $cpu_count to $vcpus | tee -a $resdir/Warnings - cpu_count=$vcpus + echo CPU count limited from $cpu_count to $TORTURE_ALLOTED_CPUS | tee -a $resdir/Warnings + cpu_count=$TORTURE_ALLOTED_CPUS fi qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`" @@ -177,7 +176,7 @@ do then qemu_pid=`cat "$resdir/qemu_pid"` fi - kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` + kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1 then if test $kruntime -ge $seconds @@ -213,7 +212,7 @@ then oldline="`tail $resdir/console.log`" while : do - kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` + kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null` if kill -0 $qemu_pid > /dev/null 2>&1 then : diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 72518580df23..78d18ab8e954 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -24,7 +24,9 @@ dur=$((30*60)) dryrun="" KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM PATH=${KVM}/bin:$PATH; export PATH -TORTURE_ALLOTED_CPUS="" +. functions.sh + +TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`" TORTURE_DEFCONFIG=defconfig TORTURE_BOOT_IMAGE="" TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD @@ -40,8 +42,6 @@ cpus=0 ds=`date +%Y.%m.%d-%H:%M:%S` jitter="-1" -. functions.sh - usage () { echo "Usage: $scriptname optional arguments:" echo " --bootargs kernel-boot-arguments" @@ -93,6 +93,11 @@ do checkarg --cpus "(number)" "$#" "$2" '^[0-9]*$' '^--' cpus=$2 TORTURE_ALLOTED_CPUS="$2" + max_cpus="`identify_qemu_vcpus`" + if test "$TORTURE_ALLOTED_CPUS" -gt "$max_cpus" + then + TORTURE_ALLOTED_CPUS=$max_cpus + fi shift ;; --datestamp) @@ -198,9 +203,10 @@ fi CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG +defaultconfigs="`tr '\012' ' ' < $CONFIGFRAG/CFLIST`" if test -z "$configs" then - configs="`cat $CONFIGFRAG/CFLIST`" + configs=$defaultconfigs fi if test -z "$resdir" @@ -209,7 +215,7 @@ then fi # Create a file of test-name/#cpus pairs, sorted by decreasing #cpus. -touch $T/cfgcpu +configs_derep= for CF in $configs do case $CF in @@ -222,15 +228,21 @@ do CF1=$CF ;; esac + for ((cur_rep=0;cur_rep<$config_reps;cur_rep++)) + do + configs_derep="$configs_derep $CF1" + done +done +touch $T/cfgcpu +configs_derep="`echo $configs_derep | sed -e "s/\<CFLIST\>/$defaultconfigs/g"`" +for CF1 in $configs_derep +do if test -f "$CONFIGFRAG/$CF1" then cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1` cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"` cpu_count=`configfrag_boot_maxcpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"` - for ((cur_rep=0;cur_rep<$config_reps;cur_rep++)) - do - echo $CF1 $cpu_count >> $T/cfgcpu - done + echo $CF1 $cpu_count >> $T/cfgcpu else echo "The --configs file $CF1 does not exist, terminating." exit 1 diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh index 6fa9bd1ddc09..38e424d2392c 100755 --- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh +++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh @@ -20,58 +20,9 @@ if [ -s "$D/initrd/init" ]; then exit 0 fi -T=${TMPDIR-/tmp}/mkinitrd.sh.$$ -trap 'rm -rf $T' 0 2 -mkdir $T - -cat > $T/init << '__EOF___' -#!/bin/sh -# Run in userspace a few milliseconds every second. This helps to -# exercise the NO_HZ_FULL portions of RCU. The 192 instances of "a" was -# empirically shown to give a nice multi-millisecond burst of user-mode -# execution on a 2GHz CPU, as desired. Modern CPUs will vary from a -# couple of milliseconds up to perhaps 100 milliseconds, which is an -# acceptable range. -# -# Why not calibrate an exact delay? Because within this initrd, we -# are restricted to Bourne-shell builtins, which as far as I know do not -# provide any means of obtaining a fine-grained timestamp. - -a4="a a a a" -a16="$a4 $a4 $a4 $a4" -a64="$a16 $a16 $a16 $a16" -a192="$a64 $a64 $a64" -while : -do - q= - for i in $a192 - do - q="$q $i" - done - sleep 1 -done -__EOF___ - -# Try using dracut to create initrd -if command -v dracut >/dev/null 2>&1 -then - echo Creating $D/initrd using dracut. - # Filesystem creation - dracut --force --no-hostonly --no-hostonly-cmdline --module "base" $T/initramfs.img - cd $D - mkdir -p initrd - cd initrd - zcat $T/initramfs.img | cpio -id - cp $T/init init - chmod +x init - echo Done creating $D/initrd using dracut - exit 0 -fi - -# No dracut, so create a C-language initrd/init program and statically -# link it. This results in a very small initrd, but might be a bit less -# future-proof than dracut. -echo "Could not find dracut, attempting C initrd" +# Create a C-language initrd/init infinite-loop program and statically +# link it. This results in a very small initrd. +echo "Creating a statically linked C-language initrd" cd $D mkdir -p initrd cd initrd diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile index de9c8566672a..2d93d65723c9 100644 --- a/tools/testing/selftests/rtc/Makefile +++ b/tools/testing/selftests/rtc/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -O3 -Wl,-no-as-needed -Wall -LDFLAGS += -lrt -lpthread -lm +LDLIBS += -lrt -lpthread -lm TEST_GEN_PROGS = rtctest diff --git a/tools/testing/selftests/size/get_size.c b/tools/testing/selftests/size/get_size.c index 2ad45b944355..2980b1a63366 100644 --- a/tools/testing/selftests/size/get_size.c +++ b/tools/testing/selftests/size/get_size.c @@ -11,23 +11,35 @@ * own execution. It also attempts to have as few dependencies * on kernel features as possible. * - * It should be statically linked, with startup libs avoided. - * It uses no library calls, and only the following 3 syscalls: + * It should be statically linked, with startup libs avoided. It uses + * no library calls except the syscall() function for the following 3 + * syscalls: * sysinfo(), write(), and _exit() * * For output, it avoids printf (which in some C libraries * has large external dependencies) by implementing it's own * number output and print routines, and using __builtin_strlen() + * + * The test may crash if any of the above syscalls fails because in some + * libc implementations (e.g. the GNU C Library) errno is saved in + * thread-local storage, which does not get initialized due to avoiding + * startup libs. */ #include <sys/sysinfo.h> #include <unistd.h> +#include <sys/syscall.h> #define STDOUT_FILENO 1 static int print(const char *s) { - return write(STDOUT_FILENO, s, __builtin_strlen(s)); + size_t len = 0; + + while (s[len] != '\0') + len++; + + return syscall(SYS_write, STDOUT_FILENO, s, len); } static inline char *num_to_str(unsigned long num, char *buf, int len) @@ -79,12 +91,12 @@ void _start(void) print("TAP version 13\n"); print("# Testing system size.\n"); - ccode = sysinfo(&info); + ccode = syscall(SYS_sysinfo, &info); if (ccode < 0) { print("not ok 1"); print(test_name); print(" ---\n reason: \"could not get sysinfo\"\n ...\n"); - _exit(ccode); + syscall(SYS_exit, ccode); } print("ok 1"); print(test_name); @@ -100,5 +112,5 @@ void _start(void) print(" ...\n"); print("1..1\n"); - _exit(0); + syscall(SYS_exit, 0); } diff --git a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py index e98c36750fae..d34fe06268d2 100644 --- a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py +++ b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py @@ -54,7 +54,7 @@ class SubPlugin(TdcPlugin): shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, - env=ENVIR) + env=os.environ.copy()) (rawout, serr) = proc.communicate() if proc.returncode != 0 and len(serr) > 0: diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json index 2e361cea63bc..98a20faf3198 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json @@ -6,6 +6,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -25,6 +28,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -44,6 +50,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -63,6 +72,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -82,6 +94,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -101,6 +116,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -120,6 +138,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -139,6 +160,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -158,6 +182,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -177,6 +204,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -196,6 +226,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -215,6 +248,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -234,6 +270,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -253,6 +292,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -272,6 +314,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -291,6 +336,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@ -310,6 +358,9 @@ "filter", "basic" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json new file mode 100644 index 000000000000..180593010675 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json @@ -0,0 +1,940 @@ +[ + { + "id": "e90e", + "name": "Add ETS qdisc using bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 2", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "b059", + "name": "Add ETS qdisc using quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 900 800 700", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 4 quanta 1000 900 800 700", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e8e7", + "name": "Add ETS qdisc using strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 3", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "233c", + "name": "Add ETS qdisc using bands + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 quanta 1000 900 800 700", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 4 quanta 1000 900 800 700 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "3d35", + "name": "Add ETS qdisc using bands + strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 3 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7f3b", + "name": "Add ETS qdisc using strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 strict 3 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "4593", + "name": "Add ETS qdisc using strict 0 + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 0 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 2 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "8938", + "name": "Add ETS qdisc using bands + strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 strict 3 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 .*strict 3 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "0782", + "name": "Add ETS qdisc with more bands than quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 quanta 1000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 2 .*quanta 1000 [1-9][0-9]* priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "501b", + "name": "Add ETS qdisc with more bands than strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 1 quanta ([1-9][0-9]* ){2}priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "671a", + "name": "Add ETS qdisc with more bands than strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 1 quanta 1000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 1 quanta 1000 [1-9][0-9]* priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "2a23", + "name": "Add ETS qdisc with 16 bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 16", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "8daf", + "name": "Add ETS qdisc with 17 bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7f95", + "name": "Add ETS qdisc with 17 strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "837a", + "name": "Add ETS qdisc with 16 quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "65b6", + "name": "Add ETS qdisc with 17 quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "b9e9", + "name": "Add ETS qdisc with 16 strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 8 quanta 1 2 3 4 5 6 7 8", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "9877", + "name": "Add ETS qdisc with 17 strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 9 quanta 1 2 3 4 5 6 7 8", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "c696", + "name": "Add ETS qdisc with priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "30c4", + "name": "Add ETS qdisc with quanta + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000 4000 5000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1000 2000 3000 4000 5000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e8ac", + "name": "Add ETS qdisc with strict + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 strict 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "5a7e", + "name": "Add ETS qdisc with quanta + strict + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 2 quanta 1000 2000 3000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*strict 2 quanta 1000 2000 3000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "cb8b", + "name": "Show ETS class :1", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:1", + "matchPattern": "class ets 1:1 root quantum 4000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "1b4e", + "name": "Show ETS class :2", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:2", + "matchPattern": "class ets 1:2 root quantum 3000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "f642", + "name": "Show ETS class :3", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:3", + "matchPattern": "class ets 1:3 root quantum 2000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "0a5f", + "name": "Show ETS strict class", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:1", + "matchPattern": "class ets 1:1 root $", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "f7c8", + "name": "Add ETS qdisc with too many quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 quanta 1000 2000 3000", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "2389", + "name": "Add ETS qdisc with too many strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 strict 3", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "fe3c", + "name": "Add ETS qdisc with too many strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 2 quanta 1000 2000 3000", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "cb04", + "name": "Add ETS qdisc with excess priomap elements", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "c32e", + "name": "Add ETS qdisc with priomap above bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "744c", + "name": "Add ETS qdisc with priomap above quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 500 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7b33", + "name": "Add ETS qdisc with priomap above strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 2 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "dbe6", + "name": "Add ETS qdisc with priomap above strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 1 quanta 1000 500 priomap 0 1 2 3", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "bdb2", + "name": "Add ETS qdisc with priomap within bands with strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 1 quanta 1000 500 priomap 0 1 2 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "39a3", + "name": "Add ETS qdisc with priomap above bands with strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 1 quanta 1000 500 priomap 0 1 2 3 4", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "557c", + "name": "Unset priorities default to the last band", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 priomap 0 0 0 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*priomap 0 0 0 0 3 3 3 3 3 3 3 3 3 3 3 3", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "a347", + "name": "Unset priorities default to the last band -- no priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*priomap 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "39c4", + "name": "Add ETS qdisc with too few bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 0", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "930b", + "name": "Add ETS qdisc with too many bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "406a", + "name": "Add ETS qdisc without parameters", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e51a", + "name": "Zero element in quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 0 800 700", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e7f2", + "name": "Sole zero element in quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 0", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "d6e6", + "name": "No values after the quanta keyword", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta", + "expExitCode": "255", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "28c6", + "name": "Change ETS band quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:1 ets quantum 1500", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1500 2000 3000 priomap ", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "4714", + "name": "Change ETS band without quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:1 ets", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1000 2000 3000 priomap ", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "6979", + "name": "Change quantum of a strict ETS band", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets strict 5" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:2 ets quantum 1500", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*bands 5 .*strict 5", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "9a7d", + "name": "Change ETS strict band without quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets strict 5" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:2 ets", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*bands 5 .*strict 5", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + } +] diff --git a/tools/testing/selftests/timens/.gitignore b/tools/testing/selftests/timens/.gitignore new file mode 100644 index 000000000000..789f21e81028 --- /dev/null +++ b/tools/testing/selftests/timens/.gitignore @@ -0,0 +1,8 @@ +clock_nanosleep +exec +gettime_perf +gettime_perf_cold +procfs +timens +timer +timerfd diff --git a/tools/testing/selftests/timens/Makefile b/tools/testing/selftests/timens/Makefile new file mode 100644 index 000000000000..b4fd9a934654 --- /dev/null +++ b/tools/testing/selftests/timens/Makefile @@ -0,0 +1,7 @@ +TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec +TEST_GEN_PROGS_EXTENDED := gettime_perf + +CFLAGS := -Wall -Werror -pthread +LDLIBS := -lrt -ldl + +include ../lib.mk diff --git a/tools/testing/selftests/timens/clock_nanosleep.c b/tools/testing/selftests/timens/clock_nanosleep.c new file mode 100644 index 000000000000..8e7b7c72ef65 --- /dev/null +++ b/tools/testing/selftests/timens/clock_nanosleep.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sched.h> + +#include <sys/timerfd.h> +#include <sys/syscall.h> +#include <time.h> +#include <unistd.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdint.h> +#include <pthread.h> +#include <signal.h> +#include <string.h> + +#include "log.h" +#include "timens.h" + +void test_sig(int sig) +{ + if (sig == SIGUSR2) + pthread_exit(NULL); +} + +struct thread_args { + struct timespec *now, *rem; + pthread_mutex_t *lock; + int clockid; + int abs; +}; + +void *call_nanosleep(void *_args) +{ + struct thread_args *args = _args; + + clock_nanosleep(args->clockid, args->abs ? TIMER_ABSTIME : 0, args->now, args->rem); + pthread_mutex_unlock(args->lock); + return NULL; +} + +int run_test(int clockid, int abs) +{ + struct timespec now = {}, rem; + struct thread_args args = { .now = &now, .rem = &rem, .clockid = clockid}; + struct timespec start; + pthread_mutex_t lock; + pthread_t thread; + int j, ok, ret; + + signal(SIGUSR1, test_sig); + signal(SIGUSR2, test_sig); + + pthread_mutex_init(&lock, NULL); + pthread_mutex_lock(&lock); + + if (clock_gettime(clockid, &start) == -1) { + if (errno == EINVAL && check_skip(clockid)) + return 0; + return pr_perror("clock_gettime"); + } + + + if (abs) { + now.tv_sec = start.tv_sec; + now.tv_nsec = start.tv_nsec; + } + + now.tv_sec += 3600; + args.abs = abs; + args.lock = &lock; + ret = pthread_create(&thread, NULL, call_nanosleep, &args); + if (ret != 0) { + pr_err("Unable to create a thread: %s", strerror(ret)); + return 1; + } + + /* Wait when the thread will call clock_nanosleep(). */ + ok = 0; + for (j = 0; j < 8; j++) { + /* The maximum timeout is about 5 seconds. */ + usleep(10000 << j); + + /* Try to interrupt clock_nanosleep(). */ + pthread_kill(thread, SIGUSR1); + + usleep(10000 << j); + /* Check whether clock_nanosleep() has been interrupted or not. */ + if (pthread_mutex_trylock(&lock) == 0) { + /**/ + ok = 1; + break; + } + } + if (!ok) + pthread_kill(thread, SIGUSR2); + pthread_join(thread, NULL); + pthread_mutex_destroy(&lock); + + if (!ok) { + ksft_test_result_pass("clockid: %d abs:%d timeout\n", clockid, abs); + return 1; + } + + if (rem.tv_sec < 3300 || rem.tv_sec > 3900) { + pr_fail("clockid: %d abs: %d remain: %ld\n", + clockid, abs, rem.tv_sec); + return 1; + } + ksft_test_result_pass("clockid: %d abs:%d\n", clockid, abs); + + return 0; +} + +int main(int argc, char *argv[]) +{ + int ret, nsfd; + + nscheck(); + + ksft_set_plan(4); + + check_config_posix_timers(); + + if (unshare_timens()) + return 1; + + if (_settime(CLOCK_MONOTONIC, 7 * 24 * 3600)) + return 1; + if (_settime(CLOCK_BOOTTIME, 9 * 24 * 3600)) + return 1; + + nsfd = open("/proc/self/ns/time_for_children", O_RDONLY); + if (nsfd < 0) + return pr_perror("Unable to open timens_for_children"); + + if (setns(nsfd, CLONE_NEWTIME)) + return pr_perror("Unable to set timens"); + + ret = 0; + ret |= run_test(CLOCK_MONOTONIC, 0); + ret |= run_test(CLOCK_MONOTONIC, 1); + ret |= run_test(CLOCK_BOOTTIME_ALARM, 0); + ret |= run_test(CLOCK_BOOTTIME_ALARM, 1); + + if (ret) + ksft_exit_fail(); + ksft_exit_pass(); + return ret; +} diff --git a/tools/testing/selftests/timens/config b/tools/testing/selftests/timens/config new file mode 100644 index 000000000000..4480620f6f49 --- /dev/null +++ b/tools/testing/selftests/timens/config @@ -0,0 +1 @@ +CONFIG_TIME_NS=y diff --git a/tools/testing/selftests/timens/exec.c b/tools/testing/selftests/timens/exec.c new file mode 100644 index 000000000000..87b47b557a7a --- /dev/null +++ b/tools/testing/selftests/timens/exec.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <stdbool.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <unistd.h> +#include <time.h> +#include <string.h> + +#include "log.h" +#include "timens.h" + +#define OFFSET (36000) + +int main(int argc, char *argv[]) +{ + struct timespec now, tst; + int status, i; + pid_t pid; + + if (argc > 1) { + if (sscanf(argv[1], "%ld", &now.tv_sec) != 1) + return pr_perror("sscanf"); + + for (i = 0; i < 2; i++) { + _gettime(CLOCK_MONOTONIC, &tst, i); + if (abs(tst.tv_sec - now.tv_sec) > 5) + return pr_fail("%ld %ld\n", now.tv_sec, tst.tv_sec); + } + return 0; + } + + nscheck(); + + ksft_set_plan(1); + + clock_gettime(CLOCK_MONOTONIC, &now); + + if (unshare_timens()) + return 1; + + if (_settime(CLOCK_MONOTONIC, OFFSET)) + return 1; + + for (i = 0; i < 2; i++) { + _gettime(CLOCK_MONOTONIC, &tst, i); + if (abs(tst.tv_sec - now.tv_sec) > 5) + return pr_fail("%ld %ld\n", + now.tv_sec, tst.tv_sec); + } + + if (argc > 1) + return 0; + + pid = fork(); + if (pid < 0) + return pr_perror("fork"); + + if (pid == 0) { + char now_str[64]; + char *cargv[] = {"exec", now_str, NULL}; + char *cenv[] = {NULL}; + + /* Check that a child process is in the new timens. */ + for (i = 0; i < 2; i++) { + _gettime(CLOCK_MONOTONIC, &tst, i); + if (abs(tst.tv_sec - now.tv_sec - OFFSET) > 5) + return pr_fail("%ld %ld\n", + now.tv_sec + OFFSET, tst.tv_sec); + } + + /* Check for proper vvar offsets after execve. */ + snprintf(now_str, sizeof(now_str), "%ld", now.tv_sec + OFFSET); + execve("/proc/self/exe", cargv, cenv); + return pr_perror("execve"); + } + + if (waitpid(pid, &status, 0) != pid) + return pr_perror("waitpid"); + + if (status) + ksft_exit_fail(); + + ksft_test_result_pass("exec\n"); + ksft_exit_pass(); + return 0; +} diff --git a/tools/testing/selftests/timens/gettime_perf.c b/tools/testing/selftests/timens/gettime_perf.c new file mode 100644 index 000000000000..7bf841a3967b --- /dev/null +++ b/tools/testing/selftests/timens/gettime_perf.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sys/types.h> +#include <sys/stat.h> +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <time.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/syscall.h> +#include <dlfcn.h> + +#include "log.h" +#include "timens.h" + +typedef int (*vgettime_t)(clockid_t, struct timespec *); + +vgettime_t vdso_clock_gettime; + +static void fill_function_pointers(void) +{ + void *vdso = dlopen("linux-vdso.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-gate.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) { + pr_err("[WARN]\tfailed to find vDSO\n"); + return; + } + + vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime"); + if (!vdso_clock_gettime) + pr_err("Warning: failed to find clock_gettime in vDSO\n"); + +} + +static void test(clock_t clockid, char *clockstr, bool in_ns) +{ + struct timespec tp, start; + long i = 0; + const int timeout = 3; + + vdso_clock_gettime(clockid, &start); + tp = start; + for (tp = start; start.tv_sec + timeout > tp.tv_sec || + (start.tv_sec + timeout == tp.tv_sec && + start.tv_nsec > tp.tv_nsec); i++) { + vdso_clock_gettime(clockid, &tp); + } + + ksft_test_result_pass("%s:\tclock: %10s\tcycles:\t%10ld\n", + in_ns ? "ns" : "host", clockstr, i); +} + +int main(int argc, char *argv[]) +{ + time_t offset = 10; + int nsfd; + + ksft_set_plan(8); + + fill_function_pointers(); + + test(CLOCK_MONOTONIC, "monotonic", false); + test(CLOCK_MONOTONIC_COARSE, "monotonic-coarse", false); + test(CLOCK_MONOTONIC_RAW, "monotonic-raw", false); + test(CLOCK_BOOTTIME, "boottime", false); + + nscheck(); + + if (unshare_timens()) + return 1; + + nsfd = open("/proc/self/ns/time_for_children", O_RDONLY); + if (nsfd < 0) + return pr_perror("Can't open a time namespace"); + + if (_settime(CLOCK_MONOTONIC, offset)) + return 1; + if (_settime(CLOCK_BOOTTIME, offset)) + return 1; + + if (setns(nsfd, CLONE_NEWTIME)) + return pr_perror("setns"); + + test(CLOCK_MONOTONIC, "monotonic", true); + test(CLOCK_MONOTONIC_COARSE, "monotonic-coarse", true); + test(CLOCK_MONOTONIC_RAW, "monotonic-raw", true); + test(CLOCK_BOOTTIME, "boottime", true); + + ksft_exit_pass(); + return 0; +} diff --git a/tools/testing/selftests/timens/log.h b/tools/testing/selftests/timens/log.h new file mode 100644 index 000000000000..db64df2a8483 --- /dev/null +++ b/tools/testing/selftests/timens/log.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __SELFTEST_TIMENS_LOG_H__ +#define __SELFTEST_TIMENS_LOG_H__ + +#define pr_msg(fmt, lvl, ...) \ + ksft_print_msg("[%s] (%s:%d)\t" fmt "\n", \ + lvl, __FILE__, __LINE__, ##__VA_ARGS__) + +#define pr_p(func, fmt, ...) func(fmt ": %m", ##__VA_ARGS__) + +#define pr_err(fmt, ...) \ + ({ \ + ksft_test_result_error(fmt "\n", ##__VA_ARGS__); \ + -1; \ + }) + +#define pr_fail(fmt, ...) \ + ({ \ + ksft_test_result_fail(fmt, ##__VA_ARGS__); \ + -1; \ + }) + +#define pr_perror(fmt, ...) pr_p(pr_err, fmt, ##__VA_ARGS__) + +#endif diff --git a/tools/testing/selftests/timens/procfs.c b/tools/testing/selftests/timens/procfs.c new file mode 100644 index 000000000000..43d93f4006b9 --- /dev/null +++ b/tools/testing/selftests/timens/procfs.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <math.h> +#include <sched.h> +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> +#include <time.h> + +#include "log.h" +#include "timens.h" + +/* + * Test shouldn't be run for a day, so add 10 days to child + * time and check parent's time to be in the same day. + */ +#define MAX_TEST_TIME_SEC (60*5) +#define DAY_IN_SEC (60*60*24) +#define TEN_DAYS_IN_SEC (10*DAY_IN_SEC) + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +static int child_ns, parent_ns; + +static int switch_ns(int fd) +{ + if (setns(fd, CLONE_NEWTIME)) + return pr_perror("setns()"); + + return 0; +} + +static int init_namespaces(void) +{ + char path[] = "/proc/self/ns/time_for_children"; + struct stat st1, st2; + + parent_ns = open(path, O_RDONLY); + if (parent_ns <= 0) + return pr_perror("Unable to open %s", path); + + if (fstat(parent_ns, &st1)) + return pr_perror("Unable to stat the parent timens"); + + if (unshare_timens()) + return -1; + + child_ns = open(path, O_RDONLY); + if (child_ns <= 0) + return pr_perror("Unable to open %s", path); + + if (fstat(child_ns, &st2)) + return pr_perror("Unable to stat the timens"); + + if (st1.st_ino == st2.st_ino) + return pr_err("The same child_ns after CLONE_NEWTIME"); + + if (_settime(CLOCK_BOOTTIME, TEN_DAYS_IN_SEC)) + return -1; + + return 0; +} + +static int read_proc_uptime(struct timespec *uptime) +{ + unsigned long up_sec, up_nsec; + FILE *proc; + + proc = fopen("/proc/uptime", "r"); + if (proc == NULL) { + pr_perror("Unable to open /proc/uptime"); + return -1; + } + + if (fscanf(proc, "%lu.%02lu", &up_sec, &up_nsec) != 2) { + if (errno) { + pr_perror("fscanf"); + return -errno; + } + pr_err("failed to parse /proc/uptime"); + return -1; + } + fclose(proc); + + uptime->tv_sec = up_sec; + uptime->tv_nsec = up_nsec; + return 0; +} + +static int check_uptime(void) +{ + struct timespec uptime_new, uptime_old; + time_t uptime_expected; + double prec = MAX_TEST_TIME_SEC; + + if (switch_ns(parent_ns)) + return pr_err("switch_ns(%d)", parent_ns); + + if (read_proc_uptime(&uptime_old)) + return 1; + + if (switch_ns(child_ns)) + return pr_err("switch_ns(%d)", child_ns); + + if (read_proc_uptime(&uptime_new)) + return 1; + + uptime_expected = uptime_old.tv_sec + TEN_DAYS_IN_SEC; + if (fabs(difftime(uptime_new.tv_sec, uptime_expected)) > prec) { + pr_fail("uptime in /proc/uptime: old %ld, new %ld [%ld]", + uptime_old.tv_sec, uptime_new.tv_sec, + uptime_old.tv_sec + TEN_DAYS_IN_SEC); + return 1; + } + + ksft_test_result_pass("Passed for /proc/uptime\n"); + return 0; +} + +int main(int argc, char *argv[]) +{ + int ret = 0; + + nscheck(); + + ksft_set_plan(1); + + if (init_namespaces()) + return 1; + + ret |= check_uptime(); + + if (ret) + ksft_exit_fail(); + ksft_exit_pass(); + return ret; +} diff --git a/tools/testing/selftests/timens/timens.c b/tools/testing/selftests/timens/timens.c new file mode 100644 index 000000000000..559d26e21ba0 --- /dev/null +++ b/tools/testing/selftests/timens/timens.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <stdio.h> +#include <stdbool.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> +#include <time.h> +#include <string.h> + +#include "log.h" +#include "timens.h" + +/* + * Test shouldn't be run for a day, so add 10 days to child + * time and check parent's time to be in the same day. + */ +#define DAY_IN_SEC (60*60*24) +#define TEN_DAYS_IN_SEC (10*DAY_IN_SEC) + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +struct test_clock { + clockid_t id; + char *name; + /* + * off_id is -1 if a clock has own offset, or it contains an index + * which contains a right offset of this clock. + */ + int off_id; + time_t offset; +}; + +#define ct(clock, off_id) { clock, #clock, off_id } +static struct test_clock clocks[] = { + ct(CLOCK_BOOTTIME, -1), + ct(CLOCK_BOOTTIME_ALARM, 1), + ct(CLOCK_MONOTONIC, -1), + ct(CLOCK_MONOTONIC_COARSE, 1), + ct(CLOCK_MONOTONIC_RAW, 1), +}; +#undef ct + +static int child_ns, parent_ns = -1; + +static int switch_ns(int fd) +{ + if (setns(fd, CLONE_NEWTIME)) { + pr_perror("setns()"); + return -1; + } + + return 0; +} + +static int init_namespaces(void) +{ + char path[] = "/proc/self/ns/time_for_children"; + struct stat st1, st2; + + if (parent_ns == -1) { + parent_ns = open(path, O_RDONLY); + if (parent_ns <= 0) + return pr_perror("Unable to open %s", path); + } + + if (fstat(parent_ns, &st1)) + return pr_perror("Unable to stat the parent timens"); + + if (unshare_timens()) + return -1; + + child_ns = open(path, O_RDONLY); + if (child_ns <= 0) + return pr_perror("Unable to open %s", path); + + if (fstat(child_ns, &st2)) + return pr_perror("Unable to stat the timens"); + + if (st1.st_ino == st2.st_ino) + return pr_perror("The same child_ns after CLONE_NEWTIME"); + + return 0; +} + +static int test_gettime(clockid_t clock_index, bool raw_syscall, time_t offset) +{ + struct timespec child_ts_new, parent_ts_old, cur_ts; + char *entry = raw_syscall ? "syscall" : "vdso"; + double precision = 0.0; + + if (check_skip(clocks[clock_index].id)) + return 0; + + switch (clocks[clock_index].id) { + case CLOCK_MONOTONIC_COARSE: + case CLOCK_MONOTONIC_RAW: + precision = -2.0; + break; + } + + if (switch_ns(parent_ns)) + return pr_err("switch_ns(%d)", child_ns); + + if (_gettime(clocks[clock_index].id, &parent_ts_old, raw_syscall)) + return -1; + + child_ts_new.tv_nsec = parent_ts_old.tv_nsec; + child_ts_new.tv_sec = parent_ts_old.tv_sec + offset; + + if (switch_ns(child_ns)) + return pr_err("switch_ns(%d)", child_ns); + + if (_gettime(clocks[clock_index].id, &cur_ts, raw_syscall)) + return -1; + + if (difftime(cur_ts.tv_sec, child_ts_new.tv_sec) < precision) { + ksft_test_result_fail( + "Child's %s (%s) time has not changed: %lu -> %lu [%lu]\n", + clocks[clock_index].name, entry, parent_ts_old.tv_sec, + child_ts_new.tv_sec, cur_ts.tv_sec); + return -1; + } + + if (switch_ns(parent_ns)) + return pr_err("switch_ns(%d)", parent_ns); + + if (_gettime(clocks[clock_index].id, &cur_ts, raw_syscall)) + return -1; + + if (difftime(cur_ts.tv_sec, parent_ts_old.tv_sec) > DAY_IN_SEC) { + ksft_test_result_fail( + "Parent's %s (%s) time has changed: %lu -> %lu [%lu]\n", + clocks[clock_index].name, entry, parent_ts_old.tv_sec, + child_ts_new.tv_sec, cur_ts.tv_sec); + /* Let's play nice and put it closer to original */ + clock_settime(clocks[clock_index].id, &cur_ts); + return -1; + } + + ksft_test_result_pass("Passed for %s (%s)\n", + clocks[clock_index].name, entry); + return 0; +} + +int main(int argc, char *argv[]) +{ + unsigned int i; + time_t offset; + int ret = 0; + + nscheck(); + + check_config_posix_timers(); + + ksft_set_plan(ARRAY_SIZE(clocks) * 2); + + if (init_namespaces()) + return 1; + + /* Offsets have to be set before tasks enter the namespace. */ + for (i = 0; i < ARRAY_SIZE(clocks); i++) { + if (clocks[i].off_id != -1) + continue; + offset = TEN_DAYS_IN_SEC + i * 1000; + clocks[i].offset = offset; + if (_settime(clocks[i].id, offset)) + return 1; + } + + for (i = 0; i < ARRAY_SIZE(clocks); i++) { + if (clocks[i].off_id != -1) + offset = clocks[clocks[i].off_id].offset; + else + offset = clocks[i].offset; + ret |= test_gettime(i, true, offset); + ret |= test_gettime(i, false, offset); + } + + if (ret) + ksft_exit_fail(); + + ksft_exit_pass(); + return !!ret; +} diff --git a/tools/testing/selftests/timens/timens.h b/tools/testing/selftests/timens/timens.h new file mode 100644 index 000000000000..e09e7e39bc52 --- /dev/null +++ b/tools/testing/selftests/timens/timens.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __TIMENS_H__ +#define __TIMENS_H__ + +#include <fcntl.h> +#include <unistd.h> +#include <stdlib.h> +#include <stdbool.h> + +#include "../kselftest.h" + +#ifndef CLONE_NEWTIME +# define CLONE_NEWTIME 0x00000080 +#endif + +static int config_posix_timers = true; + +static inline void check_config_posix_timers(void) +{ + if (timer_create(-1, 0, 0) == -1 && errno == ENOSYS) + config_posix_timers = false; +} + +static inline bool check_skip(int clockid) +{ + if (config_posix_timers) + return false; + + switch (clockid) { + /* Only these clocks are supported without CONFIG_POSIX_TIMERS. */ + case CLOCK_BOOTTIME: + case CLOCK_MONOTONIC: + case CLOCK_REALTIME: + return false; + default: + ksft_test_result_skip("Posix Clocks & timers are not supported\n"); + return true; + } + + return false; +} + +static inline int unshare_timens(void) +{ + if (unshare(CLONE_NEWTIME)) { + if (errno == EPERM) + ksft_exit_skip("need to run as root\n"); + return pr_perror("Can't unshare() timens"); + } + return 0; +} + +static inline int _settime(clockid_t clk_id, time_t offset) +{ + int fd, len; + char buf[4096]; + + if (clk_id == CLOCK_MONOTONIC_COARSE || clk_id == CLOCK_MONOTONIC_RAW) + clk_id = CLOCK_MONOTONIC; + + len = snprintf(buf, sizeof(buf), "%d %ld 0", clk_id, offset); + + fd = open("/proc/self/timens_offsets", O_WRONLY); + if (fd < 0) + return pr_perror("/proc/self/timens_offsets"); + + if (write(fd, buf, len) != len) + return pr_perror("/proc/self/timens_offsets"); + + close(fd); + + return 0; +} + +static inline int _gettime(clockid_t clk_id, struct timespec *res, bool raw_syscall) +{ + int err; + + if (!raw_syscall) { + if (clock_gettime(clk_id, res)) { + pr_perror("clock_gettime(%d)", (int)clk_id); + return -1; + } + return 0; + } + + err = syscall(SYS_clock_gettime, clk_id, res); + if (err) + pr_perror("syscall(SYS_clock_gettime(%d))", (int)clk_id); + + return err; +} + +static inline void nscheck(void) +{ + if (access("/proc/self/ns/time", F_OK) < 0) + ksft_exit_skip("Time namespaces are not supported\n"); +} + +#endif diff --git a/tools/testing/selftests/timens/timer.c b/tools/testing/selftests/timens/timer.c new file mode 100644 index 000000000000..0cca7aafc4bd --- /dev/null +++ b/tools/testing/selftests/timens/timer.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sched.h> + +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <unistd.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdint.h> +#include <signal.h> +#include <time.h> + +#include "log.h" +#include "timens.h" + +int run_test(int clockid, struct timespec now) +{ + struct itimerspec new_value; + long long elapsed; + timer_t fd; + int i; + + for (i = 0; i < 2; i++) { + struct sigevent sevp = {.sigev_notify = SIGEV_NONE}; + int flags = 0; + + new_value.it_value.tv_sec = 3600; + new_value.it_value.tv_nsec = 0; + new_value.it_interval.tv_sec = 1; + new_value.it_interval.tv_nsec = 0; + + if (i == 1) { + new_value.it_value.tv_sec += now.tv_sec; + new_value.it_value.tv_nsec += now.tv_nsec; + } + + if (timer_create(clockid, &sevp, &fd) == -1) { + if (errno == ENOSYS) { + ksft_test_result_skip("Posix Clocks & timers are supported\n"); + return 0; + } + return pr_perror("timerfd_create"); + } + + if (i == 1) + flags |= TIMER_ABSTIME; + if (timer_settime(fd, flags, &new_value, NULL) == -1) + return pr_perror("timerfd_settime"); + + if (timer_gettime(fd, &new_value) == -1) + return pr_perror("timerfd_gettime"); + + elapsed = new_value.it_value.tv_sec; + if (abs(elapsed - 3600) > 60) { + ksft_test_result_fail("clockid: %d elapsed: %lld\n", + clockid, elapsed); + return 1; + } + } + + ksft_test_result_pass("clockid=%d\n", clockid); + + return 0; +} + +int main(int argc, char *argv[]) +{ + int ret, status, len, fd; + char buf[4096]; + pid_t pid; + struct timespec btime_now, mtime_now; + + nscheck(); + + ksft_set_plan(3); + + clock_gettime(CLOCK_MONOTONIC, &mtime_now); + clock_gettime(CLOCK_BOOTTIME, &btime_now); + + if (unshare_timens()) + return 1; + + len = snprintf(buf, sizeof(buf), "%d %d 0\n%d %d 0", + CLOCK_MONOTONIC, 70 * 24 * 3600, + CLOCK_BOOTTIME, 9 * 24 * 3600); + fd = open("/proc/self/timens_offsets", O_WRONLY); + if (fd < 0) + return pr_perror("/proc/self/timens_offsets"); + + if (write(fd, buf, len) != len) + return pr_perror("/proc/self/timens_offsets"); + + close(fd); + mtime_now.tv_sec += 70 * 24 * 3600; + btime_now.tv_sec += 9 * 24 * 3600; + + pid = fork(); + if (pid < 0) + return pr_perror("Unable to fork"); + if (pid == 0) { + ret = 0; + ret |= run_test(CLOCK_BOOTTIME, btime_now); + ret |= run_test(CLOCK_MONOTONIC, mtime_now); + ret |= run_test(CLOCK_BOOTTIME_ALARM, btime_now); + + if (ret) + ksft_exit_fail(); + ksft_exit_pass(); + return ret; + } + + if (waitpid(pid, &status, 0) != pid) + return pr_perror("Unable to wait the child process"); + + if (WIFEXITED(status)) + return WEXITSTATUS(status); + + return 1; +} diff --git a/tools/testing/selftests/timens/timerfd.c b/tools/testing/selftests/timens/timerfd.c new file mode 100644 index 000000000000..eff1ec5ff215 --- /dev/null +++ b/tools/testing/selftests/timens/timerfd.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sched.h> + +#include <sys/timerfd.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <unistd.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdint.h> + +#include "log.h" +#include "timens.h" + +static int tclock_gettime(clock_t clockid, struct timespec *now) +{ + if (clockid == CLOCK_BOOTTIME_ALARM) + clockid = CLOCK_BOOTTIME; + return clock_gettime(clockid, now); +} + +int run_test(int clockid, struct timespec now) +{ + struct itimerspec new_value; + long long elapsed; + int fd, i; + + if (tclock_gettime(clockid, &now)) + return pr_perror("clock_gettime(%d)", clockid); + + for (i = 0; i < 2; i++) { + int flags = 0; + + new_value.it_value.tv_sec = 3600; + new_value.it_value.tv_nsec = 0; + new_value.it_interval.tv_sec = 1; + new_value.it_interval.tv_nsec = 0; + + if (i == 1) { + new_value.it_value.tv_sec += now.tv_sec; + new_value.it_value.tv_nsec += now.tv_nsec; + } + + fd = timerfd_create(clockid, 0); + if (fd == -1) + return pr_perror("timerfd_create(%d)", clockid); + + if (i == 1) + flags |= TFD_TIMER_ABSTIME; + + if (timerfd_settime(fd, flags, &new_value, NULL)) + return pr_perror("timerfd_settime(%d)", clockid); + + if (timerfd_gettime(fd, &new_value)) + return pr_perror("timerfd_gettime(%d)", clockid); + + elapsed = new_value.it_value.tv_sec; + if (abs(elapsed - 3600) > 60) { + ksft_test_result_fail("clockid: %d elapsed: %lld\n", + clockid, elapsed); + return 1; + } + + close(fd); + } + + ksft_test_result_pass("clockid=%d\n", clockid); + + return 0; +} + +int main(int argc, char *argv[]) +{ + int ret, status, len, fd; + char buf[4096]; + pid_t pid; + struct timespec btime_now, mtime_now; + + nscheck(); + + ksft_set_plan(3); + + clock_gettime(CLOCK_MONOTONIC, &mtime_now); + clock_gettime(CLOCK_BOOTTIME, &btime_now); + + if (unshare_timens()) + return 1; + + len = snprintf(buf, sizeof(buf), "%d %d 0\n%d %d 0", + CLOCK_MONOTONIC, 70 * 24 * 3600, + CLOCK_BOOTTIME, 9 * 24 * 3600); + fd = open("/proc/self/timens_offsets", O_WRONLY); + if (fd < 0) + return pr_perror("/proc/self/timens_offsets"); + + if (write(fd, buf, len) != len) + return pr_perror("/proc/self/timens_offsets"); + + close(fd); + mtime_now.tv_sec += 70 * 24 * 3600; + btime_now.tv_sec += 9 * 24 * 3600; + + pid = fork(); + if (pid < 0) + return pr_perror("Unable to fork"); + if (pid == 0) { + ret = 0; + ret |= run_test(CLOCK_BOOTTIME, btime_now); + ret |= run_test(CLOCK_MONOTONIC, mtime_now); + ret |= run_test(CLOCK_BOOTTIME_ALARM, btime_now); + + if (ret) + ksft_exit_fail(); + ksft_exit_pass(); + return ret; + } + + if (waitpid(pid, &status, 0) != pid) + return pr_perror("Unable to wait the child process"); + + if (WIFEXITED(status)) + return WEXITSTATUS(status); + + return 1; +} diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh index 8155c2ea7ccb..b630c7b5950a 100755 --- a/tools/testing/selftests/tpm2/test_smoke.sh +++ b/tools/testing/selftests/tpm2/test_smoke.sh @@ -1,8 +1,17 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) +self.flags = flags -python -m unittest -v tpm2_tests.SmokeTest -python -m unittest -v tpm2_tests.AsyncTest +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + + +if [ -f /dev/tpm0 ] ; then + python -m unittest -v tpm2_tests.SmokeTest + python -m unittest -v tpm2_tests.AsyncTest +else + exit $ksft_skip +fi CLEAR_CMD=$(which tpm2_clear) if [ -n $CLEAR_CMD ]; then diff --git a/tools/testing/selftests/tpm2/test_space.sh b/tools/testing/selftests/tpm2/test_space.sh index a6f5e346635e..180b469c53b4 100755 --- a/tools/testing/selftests/tpm2/test_space.sh +++ b/tools/testing/selftests/tpm2/test_space.sh @@ -1,4 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -python -m unittest -v tpm2_tests.SpaceTest +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ -f /dev/tpmrm0 ] ; then + python -m unittest -v tpm2_tests.SpaceTest +else + exit $ksft_skip +fi diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index 485cf06ef013..389327e9b30a 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -18,6 +18,9 @@ #define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark) #define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark) +/* Just the flags we need, copied from mm.h: */ +#define FOLL_WRITE 0x01 /* check pte is writable */ + struct gup_benchmark { __u64 get_delta_usec; __u64 put_delta_usec; @@ -85,7 +88,8 @@ int main(int argc, char **argv) } gup.nr_pages_per_call = nr_pages; - gup.flags = write; + if (write) + gup.flags |= FOLL_WRITE; fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR); if (fd == -1) diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index a692ea828317..f33714843198 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -112,6 +112,17 @@ echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing." +echo "---------------------------" +echo "running map_fixed_noreplace" +echo "---------------------------" +./map_fixed_noreplace +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "-------------------" echo "running userfaultfd" echo "-------------------" @@ -186,6 +197,17 @@ else echo "[PASS]" fi +echo "-------------------------" +echo "running mlock-random-test" +echo "-------------------------" +./mlock-random-test +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + echo "--------------------" echo "running mlock2-tests" echo "--------------------" @@ -197,6 +219,17 @@ else echo "[PASS]" fi +echo "-----------------" +echo "running thuge-gen" +echo "-----------------" +./thuge-gen +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + if [ $VADDR64 -ne 0 ]; then echo "-----------------------------" echo "running virtual_address_range" diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh new file mode 100755 index 000000000000..138d46b3f330 --- /dev/null +++ b/tools/testing/selftests/wireguard/netns.sh @@ -0,0 +1,550 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. +# +# This script tests the below topology: +# +# ┌─────────────────────┐ ┌──────────────────────────────────┐ ┌─────────────────────┐ +# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │ +# │ │ │ │ │ │ +# │┌────────┐ │ │ ┌────────┐ │ │ ┌────────┐│ +# ││ wg0 │───────────┼───┼────────────│ lo │────────────┼───┼───────────│ wg0 ││ +# │├────────┴──────────┐│ │ ┌───────┴────────┴────────┐ │ │┌──────────┴────────┤│ +# ││192.168.241.1/24 ││ │ │(ns1) (ns2) │ │ ││192.168.241.2/24 ││ +# ││fd00::1/24 ││ │ │127.0.0.1:1 127.0.0.1:2│ │ ││fd00::2/24 ││ +# │└───────────────────┘│ │ │[::]:1 [::]:2 │ │ │└───────────────────┘│ +# └─────────────────────┘ │ └─────────────────────────┘ │ └─────────────────────┘ +# └──────────────────────────────────┘ +# +# After the topology is prepared we run a series of TCP/UDP iperf3 tests between the +# wireguard peers in $ns1 and $ns2. Note that $ns0 is the endpoint for the wg0 +# interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further +# details on how this is accomplished. +set -e + +exec 3>&1 +export LANG=C +export WG_HIDE_KEYS=never +netns0="wg-test-$$-0" +netns1="wg-test-$$-1" +netns2="wg-test-$$-2" +pretty() { echo -e "\x1b[32m\x1b[1m[+] ${1:+NS$1: }${2}\x1b[0m" >&3; } +pp() { pretty "" "$*"; "$@"; } +maybe_exec() { if [[ $BASHPID -eq $$ ]]; then "$@"; else exec "$@"; fi; } +n0() { pretty 0 "$*"; maybe_exec ip netns exec $netns0 "$@"; } +n1() { pretty 1 "$*"; maybe_exec ip netns exec $netns1 "$@"; } +n2() { pretty 2 "$*"; maybe_exec ip netns exec $netns2 "$@"; } +ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; } +ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } +ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } +sleep() { read -t "$1" -N 1 || true; } +waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } +waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } +waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } + +cleanup() { + set +e + exec 2>/dev/null + printf "$orig_message_cost" > /proc/sys/net/core/message_cost + ip0 link del dev wg0 + ip1 link del dev wg0 + ip2 link del dev wg0 + local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)" + [[ -n $to_kill ]] && kill $to_kill + pp ip netns del $netns1 + pp ip netns del $netns2 + pp ip netns del $netns0 + exit +} + +orig_message_cost="$(< /proc/sys/net/core/message_cost)" +trap cleanup EXIT +printf 0 > /proc/sys/net/core/message_cost + +ip netns del $netns0 2>/dev/null || true +ip netns del $netns1 2>/dev/null || true +ip netns del $netns2 2>/dev/null || true +pp ip netns add $netns0 +pp ip netns add $netns1 +pp ip netns add $netns2 +ip0 link set up dev lo + +ip0 link add dev wg0 type wireguard +ip0 link set wg0 netns $netns1 +ip0 link add dev wg0 type wireguard +ip0 link set wg0 netns $netns2 +key1="$(pp wg genkey)" +key2="$(pp wg genkey)" +key3="$(pp wg genkey)" +pub1="$(pp wg pubkey <<<"$key1")" +pub2="$(pp wg pubkey <<<"$key2")" +pub3="$(pp wg pubkey <<<"$key3")" +psk="$(pp wg genpsk)" +[[ -n $key1 && -n $key2 && -n $psk ]] + +configure_peers() { + ip1 addr add 192.168.241.1/24 dev wg0 + ip1 addr add fd00::1/24 dev wg0 + + ip2 addr add 192.168.241.2/24 dev wg0 + ip2 addr add fd00::2/24 dev wg0 + + n1 wg set wg0 \ + private-key <(echo "$key1") \ + listen-port 1 \ + peer "$pub2" \ + preshared-key <(echo "$psk") \ + allowed-ips 192.168.241.2/32,fd00::2/128 + n2 wg set wg0 \ + private-key <(echo "$key2") \ + listen-port 2 \ + peer "$pub1" \ + preshared-key <(echo "$psk") \ + allowed-ips 192.168.241.1/32,fd00::1/128 + + ip1 link set up dev wg0 + ip2 link set up dev wg0 +} +configure_peers + +tests() { + # Ping over IPv4 + n2 ping -c 10 -f -W 1 192.168.241.1 + n1 ping -c 10 -f -W 1 192.168.241.2 + + # Ping over IPv6 + n2 ping6 -c 10 -f -W 1 fd00::1 + n1 ping6 -c 10 -f -W 1 fd00::2 + + # TCP over IPv4 + n2 iperf3 -s -1 -B 192.168.241.2 & + waitiperf $netns2 $! + n1 iperf3 -Z -t 3 -c 192.168.241.2 + + # TCP over IPv6 + n1 iperf3 -s -1 -B fd00::1 & + waitiperf $netns1 $! + n2 iperf3 -Z -t 3 -c fd00::1 + + # UDP over IPv4 + n1 iperf3 -s -1 -B 192.168.241.1 & + waitiperf $netns1 $! + n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1 + + # UDP over IPv6 + n2 iperf3 -s -1 -B fd00::2 & + waitiperf $netns2 $! + n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 +} + +[[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" +big_mtu=$(( 34816 - 1500 + $orig_mtu )) + +# Test using IPv4 as outer transport +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 +# Before calling tests, we first make sure that the stats counters and timestamper are working +n2 ping -c 10 -f -W 1 192.168.241.1 +{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip2 -stats link show dev wg0) +(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) )) +{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip1 -stats link show dev wg0) +(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) )) +read _ rx_bytes tx_bytes < <(n2 wg show wg0 transfer) +(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) )) +read _ rx_bytes tx_bytes < <(n1 wg show wg0 transfer) +(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) )) +read _ timestamp < <(n1 wg show wg0 latest-handshakes) +(( timestamp != 0 )) + +tests +ip1 link set wg0 mtu $big_mtu +ip2 link set wg0 mtu $big_mtu +tests + +ip1 link set wg0 mtu $orig_mtu +ip2 link set wg0 mtu $orig_mtu + +# Test using IPv6 as outer transport +n1 wg set wg0 peer "$pub2" endpoint [::1]:2 +n2 wg set wg0 peer "$pub1" endpoint [::1]:1 +tests +ip1 link set wg0 mtu $big_mtu +ip2 link set wg0 mtu $big_mtu +tests + +# Test that route MTUs work with the padding +ip1 link set wg0 mtu 1300 +ip2 link set wg0 mtu 1300 +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 +n0 iptables -A INPUT -m length --length 1360 -j DROP +n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299 +n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299 +n2 ping -c 1 -W 1 -s 1269 192.168.241.1 +n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299 +n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299 +n0 iptables -F INPUT + +ip1 link set wg0 mtu $orig_mtu +ip2 link set wg0 mtu $orig_mtu + +# Test using IPv4 that roaming works +ip0 -4 addr del 127.0.0.1/8 dev lo +ip0 -4 addr add 127.212.121.99/8 dev lo +n1 wg set wg0 listen-port 9999 +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n1 ping6 -W 1 -c 1 fd00::2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 127.212.121.99:9999" ]] + +# Test using IPv6 that roaming works +n1 wg set wg0 listen-port 9998 +n1 wg set wg0 peer "$pub2" endpoint [::1]:2 +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [::1]:9998" ]] + +# Test that crypto-RP filter works +n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24 +exec 4< <(n1 ncat -l -u -p 1111) +ncat_pid=$! +waitncatudp $netns1 $ncat_pid +n2 ncat -u 192.168.241.1 1111 <<<"X" +read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]] +kill $ncat_pid +more_specific_key="$(pp wg genkey | pp wg pubkey)" +n1 wg set wg0 peer "$more_specific_key" allowed-ips 192.168.241.2/32 +n2 wg set wg0 listen-port 9997 +exec 4< <(n1 ncat -l -u -p 1111) +ncat_pid=$! +waitncatudp $netns1 $ncat_pid +n2 ncat -u 192.168.241.1 1111 <<<"X" +! read -r -N 1 -t 1 out <&4 || false +kill $ncat_pid +n1 wg set wg0 peer "$more_specific_key" remove +[[ $(n1 wg show wg0 endpoints) == "$pub2 [::1]:9997" ]] + +# Test that we can change private keys keys and immediately handshake +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips 192.168.241.2/32 endpoint 127.0.0.1:2 +n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 +n1 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 private-key <(echo "$key3") +n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove +n1 ping -W 1 -c 1 192.168.241.2 + +ip1 link del wg0 +ip2 link del wg0 + +# Test using NAT. We now change the topology to this: +# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐ +# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │ +# │ │ │ │ │ │ +# │ ┌─────┐ ┌─────┐ │ │ ┌──────┐ ┌──────┐ │ │ ┌─────┐ ┌─────┐ │ +# │ │ wg0 │─────────────│vethc│───────────┼────┼────│vethrc│ │vethrs│──────────────┼─────┼──│veths│────────────│ wg0 │ │ +# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├──────┴─────────┐ ├──────┴────────────┐ │ │ ├─────┴──────────┐ ├─────┴──────────┐ │ +# │ │192.168.241.1/24│ │192.168.1.100/24││ │ │192.168.1.1/24 │ │10.0.0.1/24 │ │ │ │10.0.0.100/24 │ │192.168.241.2/24│ │ +# │ │fd00::1/24 │ │ ││ │ │ │ │SNAT:192.168.1.0/24│ │ │ │ │ │fd00::2/24 │ │ +# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └───────────────────┘ │ │ └────────────────┘ └────────────────┘ │ +# └────────────────────────────────────────┘ └────────────────────────────────────────────────┘ └────────────────────────────────────────┘ + +ip1 link add dev wg0 type wireguard +ip2 link add dev wg0 type wireguard +configure_peers + +ip0 link add vethrc type veth peer name vethc +ip0 link add vethrs type veth peer name veths +ip0 link set vethc netns $netns1 +ip0 link set veths netns $netns2 +ip0 link set vethrc up +ip0 link set vethrs up +ip0 addr add 192.168.1.1/24 dev vethrc +ip0 addr add 10.0.0.1/24 dev vethrs +ip1 addr add 192.168.1.100/24 dev vethc +ip1 link set vethc up +ip1 route add default via 192.168.1.1 +ip2 addr add 10.0.0.100/24 dev veths +ip2 link set veths up +waitiface $netns0 vethrc +waitiface $netns0 vethrs +waitiface $netns1 vethc +waitiface $netns2 veths + +n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' +n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout' +n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream' +n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 + +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1 +n1 ping -W 1 -c 1 192.168.241.2 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +# Demonstrate n2 can still send packets to n1, since persistent-keepalive will prevent connection tracking entry from expiring (to see entries: `n0 conntrack -L`). +pp sleep 3 +n2 ping -W 1 -c 1 192.168.241.1 +n1 wg set wg0 peer "$pub2" persistent-keepalive 0 + +# Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs. +ip1 -6 addr add fc00::9/96 dev vethc +ip1 -6 route add default via fc00::1 +ip2 -4 addr add 192.168.99.7/32 dev wg0 +ip2 -6 addr add abab::1111/128 dev wg0 +n1 wg set wg0 fwmark 51820 peer "$pub2" allowed-ips 192.168.99.7,abab::1111 +ip1 -6 route add default dev wg0 table 51820 +ip1 -6 rule add not fwmark 51820 table 51820 +ip1 -6 rule add table main suppress_prefixlength 0 +ip1 -4 route add default dev wg0 table 51820 +ip1 -4 rule add not fwmark 51820 table 51820 +ip1 -4 rule add table main suppress_prefixlength 0 +# Flood the pings instead of sending just one, to trigger routing table reference counting bugs. +n1 ping -W 1 -c 100 -f 192.168.99.7 +n1 ping -W 1 -c 100 -f abab::1111 + +# Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route. +n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 +n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. +n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' +ip0 -4 route add 192.168.241.1 via 10.0.0.100 +n2 wg set wg0 peer "$pub1" remove +[[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]] + +n0 iptables -t nat -F +n0 iptables -t filter -F +n2 iptables -t nat -F +ip0 link del vethrc +ip0 link del vethrs +ip1 link del wg0 +ip2 link del wg0 + +# Test that saddr routing is sticky but not too sticky, changing to this topology: +# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────┐ +# │ $ns1 namespace │ │ $ns2 namespace │ +# │ │ │ │ +# │ ┌─────┐ ┌─────┐ │ │ ┌─────┐ ┌─────┐ │ +# │ │ wg0 │─────────────│veth1│───────────┼────┼──│veth2│────────────│ wg0 │ │ +# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├─────┴──────────┐ ├─────┴──────────┐ │ +# │ │192.168.241.1/24│ │10.0.0.1/24 ││ │ │10.0.0.2/24 │ │192.168.241.2/24│ │ +# │ │fd00::1/24 │ │fd00:aa::1/96 ││ │ │fd00:aa::2/96 │ │fd00::2/24 │ │ +# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └────────────────┘ │ +# └────────────────────────────────────────┘ └────────────────────────────────────────┘ + +ip1 link add dev wg0 type wireguard +ip2 link add dev wg0 type wireguard +configure_peers +ip1 link add veth1 type veth peer name veth2 +ip1 link set veth2 netns $netns2 +n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad' +n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad' +n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth1/accept_dad' +n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth2/accept_dad' +n1 bash -c 'printf 1 > /proc/sys/net/ipv4/conf/veth1/promote_secondaries' + +# First we check that we aren't overly sticky and can fall over to new IPs when old ones are removed +ip1 addr add 10.0.0.1/24 dev veth1 +ip1 addr add fd00:aa::1/96 dev veth1 +ip2 addr add 10.0.0.2/24 dev veth2 +ip2 addr add fd00:aa::2/96 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2 +n1 ping -W 1 -c 1 192.168.241.2 +ip1 addr add 10.0.0.10/24 dev veth1 +ip1 addr del 10.0.0.1/24 dev veth1 +n1 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2 +n1 ping -W 1 -c 1 192.168.241.2 +ip1 addr add fd00:aa::10/96 dev veth1 +ip1 addr del fd00:aa::1/96 dev veth1 +n1 ping -W 1 -c 1 192.168.241.2 + +# Now we show that we can successfully do reply to sender routing +ip1 link set veth1 down +ip2 link set veth2 down +ip1 addr flush dev veth1 +ip2 addr flush dev veth2 +ip1 addr add 10.0.0.1/24 dev veth1 +ip1 addr add 10.0.0.2/24 dev veth1 +ip1 addr add fd00:aa::1/96 dev veth1 +ip1 addr add fd00:aa::2/96 dev veth1 +ip2 addr add 10.0.0.3/24 dev veth2 +ip2 addr add fd00:aa::3/96 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +n2 wg set wg0 peer "$pub1" endpoint 10.0.0.1:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::1]:1" ]] +n2 wg set wg0 peer "$pub1" endpoint 10.0.0.2:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.2:1" ]] +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::2]:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::2]:1" ]] + +# What happens if the inbound destination address belongs to a different interface as the default route? +ip1 link add dummy0 type dummy +ip1 addr add 10.50.0.1/24 dev dummy0 +ip1 link set dummy0 up +ip2 route add 10.50.0.0/24 dev veth2 +n2 wg set wg0 peer "$pub1" endpoint 10.50.0.1:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.50.0.1:1" ]] + +ip1 link del dummy0 +ip1 addr flush dev veth1 +ip2 addr flush dev veth2 +ip1 route flush dev veth1 +ip2 route flush dev veth2 + +# Now we see what happens if another interface route takes precedence over an ongoing one +ip1 link add veth3 type veth peer name veth4 +ip1 link set veth4 netns $netns2 +ip1 addr add 10.0.0.1/24 dev veth1 +ip2 addr add 10.0.0.2/24 dev veth2 +ip1 addr add 10.0.0.3/24 dev veth3 +ip1 link set veth1 up +ip2 link set veth2 up +ip1 link set veth3 up +ip2 link set veth4 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +waitiface $netns1 veth3 +waitiface $netns2 veth4 +ip1 route flush dev veth1 +ip1 route flush dev veth3 +ip1 route add 10.0.0.0/24 dev veth1 src 10.0.0.1 metric 2 +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2 +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +ip1 route add 10.0.0.0/24 dev veth3 src 10.0.0.3 metric 1 +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth1/rp_filter' +n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth4/rp_filter' +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' +n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]] + +ip1 link del veth1 +ip1 link del veth3 +ip1 link del wg0 +ip2 link del wg0 + +# We test that Netlink/IPC is working properly by doing things that usually cause split responses +ip0 link add dev wg0 type wireguard +config=( "[Interface]" "PrivateKey=$(wg genkey)" "[Peer]" "PublicKey=$(wg genkey)" ) +for a in {1..255}; do + for b in {0..255}; do + config+=( "AllowedIPs=$a.$b.0.0/16,$a::$b/128" ) + done +done +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +i=0 +for ip in $(n0 wg show wg0 allowed-ips); do + ((++i)) +done +((i == 255*256*2+1)) +ip0 link del wg0 +ip0 link add dev wg0 type wireguard +config=( "[Interface]" "PrivateKey=$(wg genkey)" ) +for a in {1..40}; do + config+=( "[Peer]" "PublicKey=$(wg genkey)" ) + for b in {1..52}; do + config+=( "AllowedIPs=$a.$b.0.0/16" ) + done +done +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +i=0 +while read -r line; do + j=0 + for ip in $line; do + ((++j)) + done + ((j == 53)) + ((++i)) +done < <(n0 wg show wg0 allowed-ips) +((i == 40)) +ip0 link del wg0 +ip0 link add wg0 type wireguard +config=( ) +for i in {1..29}; do + config+=( "[Peer]" "PublicKey=$(wg genkey)" ) +done +config+=( "[Peer]" "PublicKey=$(wg genkey)" "AllowedIPs=255.2.3.4/32,abcd::255/128" ) +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +n0 wg showconf wg0 > /dev/null +ip0 link del wg0 + +allowedips=( ) +for i in {1..197}; do + allowedips+=( abcd::$i ) +done +saved_ifs="$IFS" +IFS=, +allowedips="${allowedips[*]}" +IFS="$saved_ifs" +ip0 link add wg0 type wireguard +n0 wg set wg0 peer "$pub1" +n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips" +{ + read -r pub allowedips + [[ $pub == "$pub1" && $allowedips == "(none)" ]] + read -r pub allowedips + [[ $pub == "$pub2" ]] + i=0 + for _ in $allowedips; do + ((++i)) + done + ((i == 197)) +} < <(n0 wg show wg0 allowed-ips) +ip0 link del wg0 + +! n0 wg show doesnotexist || false + +ip0 link add wg0 type wireguard +n0 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") +[[ $(n0 wg show wg0 private-key) == "$key1" ]] +[[ $(n0 wg show wg0 preshared-keys) == "$pub2 $psk" ]] +n0 wg set wg0 private-key /dev/null peer "$pub2" preshared-key /dev/null +[[ $(n0 wg show wg0 private-key) == "(none)" ]] +[[ $(n0 wg show wg0 preshared-keys) == "$pub2 (none)" ]] +n0 wg set wg0 peer "$pub2" +n0 wg set wg0 private-key <(echo "$key2") +[[ $(n0 wg show wg0 public-key) == "$pub2" ]] +[[ -z $(n0 wg show wg0 peers) ]] +n0 wg set wg0 peer "$pub2" +[[ -z $(n0 wg show wg0 peers) ]] +n0 wg set wg0 private-key <(echo "$key1") +n0 wg set wg0 peer "$pub2" +[[ $(n0 wg show wg0 peers) == "$pub2" ]] +n0 wg set wg0 private-key <(echo "/${key1:1}") +[[ $(n0 wg show wg0 private-key) == "+${key1:1}" ]] +n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0,10.0.0.0/8,100.0.0.0/10,172.16.0.0/12,192.168.0.0/16 +n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0 +n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75 +n0 wg set wg0 peer "$pub2" allowed-ips ::/0 +n0 wg set wg0 peer "$pub2" remove +low_order_points=( AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= AQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA= 4Ot6fDtBuK4WVuP68Z/EatoJjeucMrH9hmIFFl9JuAA= X5yVvKNQjCSx0LFVnIPvWwREXMRYHI6G2CJO3dCfEVc= 7P///////////////////////////////////////38= 7f///////////////////////////////////////38= 7v///////////////////////////////////////38= ) +n0 wg set wg0 private-key /dev/null ${low_order_points[@]/#/peer } +[[ -z $(n0 wg show wg0 peers) ]] +n0 wg set wg0 private-key <(echo "$key1") ${low_order_points[@]/#/peer } +[[ -z $(n0 wg show wg0 peers) ]] +ip0 link del wg0 + +declare -A objects +while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do + [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue + objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}" +done < /dev/kmsg +alldeleted=1 +for object in "${!objects[@]}"; do + if [[ ${objects["$object"]} != *createddestroyed ]]; then + echo "Error: $object: merely ${objects["$object"]}" >&3 + alldeleted=0 + fi +done +[[ $alldeleted -eq 1 ]] +pretty "" "Objects that were created were also destroyed." diff --git a/tools/testing/selftests/wireguard/qemu/.gitignore b/tools/testing/selftests/wireguard/qemu/.gitignore new file mode 100644 index 000000000000..415b542a9d59 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/.gitignore @@ -0,0 +1,2 @@ +build/ +distfiles/ diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile new file mode 100644 index 000000000000..28d477683e8a --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -0,0 +1,377 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + +PWD := $(shell pwd) + +CHOST := $(shell gcc -dumpmachine) +HOST_ARCH := $(firstword $(subst -, ,$(CHOST))) +ifneq (,$(ARCH)) +CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc)))))) +ifeq (,$(CBUILD)) +$(error The toolchain for $(ARCH) is not installed) +endif +else +CBUILD := $(CHOST) +ARCH := $(firstword $(subst -, ,$(CBUILD))) +endif + +# Set these from the environment to override +KERNEL_PATH ?= $(PWD)/../../../../.. +BUILD_PATH ?= $(PWD)/build/$(ARCH) +DISTFILES_PATH ?= $(PWD)/distfiles +NR_CPUS ?= 4 + +MIRROR := https://download.wireguard.com/qemu-test/distfiles/ + +default: qemu + +# variable name, tarball project name, version, tarball extension, default URI base +define tar_download = +$(1)_VERSION := $(3) +$(1)_NAME := $(2)-$$($(1)_VERSION) +$(1)_TAR := $(DISTFILES_PATH)/$$($(1)_NAME)$(4) +$(1)_PATH := $(BUILD_PATH)/$$($(1)_NAME) +$(call file_download,$$($(1)_NAME)$(4),$(5),$(6)) +endef + +define file_download = +$(DISTFILES_PATH)/$(1): + mkdir -p $(DISTFILES_PATH) + flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' +endef + +$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) +$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) +$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) +$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) +$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) +$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) +$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64)) + +KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) +rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) +WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*) + +export CFLAGS ?= -O3 -pipe +export LDFLAGS ?= +export CPPFLAGS := -I$(BUILD_PATH)/include + +ifeq ($(HOST_ARCH),$(ARCH)) +CROSS_COMPILE_FLAG := --host=$(CHOST) +CFLAGS += -march=native +STRIP := strip +else +$(info Cross compilation: building for $(CBUILD) using $(CHOST)) +CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) +export CROSS_COMPILE=$(CBUILD)- +STRIP := $(CBUILD)-strip +endif +ifeq ($(ARCH),aarch64) +QEMU_ARCH := aarch64 +KERNEL_ARCH := arm64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a53 -machine virt +CFLAGS += -march=armv8-a -mtune=cortex-a53 +endif +else ifeq ($(ARCH),aarch64_be) +QEMU_ARCH := aarch64 +KERNEL_ARCH := arm64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a53 -machine virt +CFLAGS += -march=armv8-a -mtune=cortex-a53 +endif +else ifeq ($(ARCH),arm) +QEMU_ARCH := arm +KERNEL_ARCH := arm +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a15 -machine virt +CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux +endif +else ifeq ($(ARCH),armeb) +QEMU_ARCH := arm +KERNEL_ARCH := arm +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a15 -machine virt +CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due to a compiler bug on big endian. +LDFLAGS += -Wl,--be8 +endif +else ifeq ($(ARCH),x86_64) +QEMU_ARCH := x86_64 +KERNEL_ARCH := x86_64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine q35,accel=kvm +else +QEMU_MACHINE := -cpu Skylake-Server -machine q35 +CFLAGS += -march=skylake-avx512 +endif +else ifeq ($(ARCH),i686) +QEMU_ARCH := i386 +KERNEL_ARCH := x86 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage +ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH)) +QEMU_MACHINE := -cpu host -machine q35,accel=kvm +else +QEMU_MACHINE := -cpu coreduo -machine q35 +CFLAGS += -march=prescott +endif +else ifeq ($(ARCH),mips64) +QEMU_ARCH := mips64 +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EB +else +QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 +CFLAGS += -march=mips64r2 -EB +endif +else ifeq ($(ARCH),mips64el) +QEMU_ARCH := mips64el +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EL +else +QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 +CFLAGS += -march=mips64r2 -EL +endif +else ifeq ($(ARCH),mips) +QEMU_ARCH := mips +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EB +else +QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 +CFLAGS += -march=mips32r2 -EB +endif +else ifeq ($(ARCH),mipsel) +QEMU_ARCH := mipsel +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EL +else +QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 +CFLAGS += -march=mips32r2 -EL +endif +else ifeq ($(ARCH),powerpc64le) +QEMU_ARCH := ppc64 +KERNEL_ARCH := powerpc +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine pseries +else +QEMU_MACHINE := -machine pseries +endif +CFLAGS += -mcpu=powerpc64le -mlong-double-64 +else ifeq ($(ARCH),powerpc) +QEMU_ARCH := ppc +KERNEL_ARCH := powerpc +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500 +else +QEMU_MACHINE := -machine ppce500 +endif +CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt +else ifeq ($(ARCH),m68k) +QEMU_ARCH := m68k +KERNEL_ARCH := m68k +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config) +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE) +else +QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE) +endif +else +$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k) +endif + +REAL_CC := $(CBUILD)-gcc +MUSL_CC := $(BUILD_PATH)/musl-gcc +export CC := $(MUSL_CC) +USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed + +build: $(KERNEL_BZIMAGE) +qemu: $(KERNEL_BZIMAGE) + rm -f $(BUILD_PATH)/result + timeout --foreground 20m qemu-system-$(QEMU_ARCH) \ + -nodefaults \ + -nographic \ + -smp $(NR_CPUS) \ + $(QEMU_MACHINE) \ + -m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \ + -serial stdio \ + -serial file:$(BUILD_PATH)/result \ + -no-reboot \ + -monitor none \ + -kernel $< + grep -Fq success $(BUILD_PATH)/result + +$(BUILD_PATH)/init-cpio-spec.txt: + mkdir -p $(BUILD_PATH) + echo "file /init $(BUILD_PATH)/init 755 0 0" > $@ + echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@ + echo "dir /dev 755 0 0" >> $@ + echo "nod /dev/console 644 0 0 c 5 1" >> $@ + echo "dir /bin 755 0 0" >> $@ + echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@ + echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/wg 755 0 0" >> $@ + echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@ + echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@ + echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@ + echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@ + echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@ + echo "file /bin/xtables-legacy-multi $(IPTABLES_PATH)/iptables/xtables-legacy-multi 755 0 0" >> $@ + echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@ + echo "slink /bin/ping6 ping 777 0 0" >> $@ + echo "dir /lib 755 0 0" >> $@ + echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@ + echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@ + +$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config + mkdir -p $(KERNEL_BUILD_PATH) + cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config + printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config + cat arch/$(ARCH).config >> $(KERNEL_BUILD_PATH)/minimal.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) allnoconfig + cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config + $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,) + +$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) + +$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install + touch $@ + +$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD) + $(MAKE) -C $(MUSL_PATH) + $(STRIP) -s $@ + +$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so + $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers + touch $@ + +$(MUSL_CC): $(MUSL_PATH)/lib/libc.so + sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs + printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc + chmod +x $(BUILD_PATH)/musl-gcc + +$(IPERF_PATH)/.installed: $(IPERF_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + sed -i '1s/^/#include <stdint.h>/' $(IPERF_PATH)/src/cjson.h $(IPERF_PATH)/src/timer.h + sed -i -r 's/-p?g//g' $(IPERF_PATH)/src/Makefile* + touch $@ + +$(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no + $(MAKE) -C $(IPERF_PATH) + $(STRIP) -s $@ + +$(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg + $(STRIP) -s $@ + +$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) + mkdir -p $(BUILD_PATH) + $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $< + $(STRIP) -s $@ + +$(IPUTILS_PATH)/.installed: $(IPUTILS_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS) + sed -i /atexit/d $(IPUTILS_PATH)/ping.c + cd $(IPUTILS_PATH) && $(CC) $(CFLAGS) -std=c99 -o $@ ping.c ping_common.c ping6_common.c iputils_common.c -D_GNU_SOURCE -D'IPUTILS_VERSION(f)=f' -lresolv $(LDFLAGS) + $(STRIP) -s $@ + +$(BASH_PATH)/.installed: $(BASH_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) + cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble + $(MAKE) -C $(BASH_PATH) + $(STRIP) -s $@ + +$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk + printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile + touch $@ + +$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip + $(STRIP) -s $@ + +$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss + $(STRIP) -s $@ + +$(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure + touch $@ + +$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include + $(MAKE) -C $(IPTABLES_PATH) + $(STRIP) -s $@ + +$(NMAP_PATH)/.installed: $(NMAP_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS) + cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux --without-libssh + $(MAKE) -C $(NMAP_PATH)/libpcap + $(MAKE) -C $(NMAP_PATH)/ncat + $(STRIP) -s $@ + +clean: + rm -rf $(BUILD_PATH) + +distclean: clean + rm -rf $(DISTFILES_PATH) + +menuconfig: $(KERNEL_BUILD_PATH)/.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig + +.PHONY: qemu build clean distclean menuconfig +.DELETE_ON_ERROR: diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config new file mode 100644 index 000000000000..3d063bb247bb --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config new file mode 100644 index 000000000000..dbdc7e406a7b --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config @@ -0,0 +1,6 @@ +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/arm.config b/tools/testing/selftests/wireguard/qemu/arch/arm.config new file mode 100644 index 000000000000..148f49905418 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config @@ -0,0 +1,9 @@ +CONFIG_MMU=y +CONFIG_ARCH_MULTI_V7=y +CONFIG_ARCH_VIRT=y +CONFIG_THUMB2_KERNEL=n +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/armeb.config b/tools/testing/selftests/wireguard/qemu/arch/armeb.config new file mode 100644 index 000000000000..bd76b07d00a2 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config @@ -0,0 +1,10 @@ +CONFIG_MMU=y +CONFIG_ARCH_MULTI_V7=y +CONFIG_ARCH_VIRT=y +CONFIG_THUMB2_KERNEL=n +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config new file mode 100644 index 000000000000..a85025d7206e --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/m68k.config b/tools/testing/selftests/wireguard/qemu/arch/m68k.config new file mode 100644 index 000000000000..62a15bdb877e --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config @@ -0,0 +1,9 @@ +CONFIG_MMU=y +CONFIG_M68KCLASSIC=y +CONFIG_M68040=y +CONFIG_MAC=y +CONFIG_SERIAL_PMACZILOG=y +CONFIG_SERIAL_PMACZILOG_TTYS=y +CONFIG_SERIAL_PMACZILOG_CONSOLE=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips.config b/tools/testing/selftests/wireguard/qemu/arch/mips.config new file mode 100644 index 000000000000..df71d6b95546 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config @@ -0,0 +1,11 @@ +CONFIG_CPU_MIPS32_R2=y +CONFIG_MIPS_MALTA=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64.config b/tools/testing/selftests/wireguard/qemu/arch/mips64.config new file mode 100644 index 000000000000..90c783f725c4 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config @@ -0,0 +1,14 @@ +CONFIG_64BIT=y +CONFIG_CPU_MIPS64_R2=y +CONFIG_MIPS32_N32=y +CONFIG_CPU_HAS_MSA=y +CONFIG_MIPS_MALTA=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config new file mode 100644 index 000000000000..435b0b43e00c --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config @@ -0,0 +1,15 @@ +CONFIG_64BIT=y +CONFIG_CPU_MIPS64_R2=y +CONFIG_MIPS32_N32=y +CONFIG_CPU_HAS_MSA=y +CONFIG_MIPS_MALTA=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config new file mode 100644 index 000000000000..62bb50c4a85f --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config @@ -0,0 +1,12 @@ +CONFIG_CPU_MIPS32_R2=y +CONFIG_MIPS_MALTA=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config new file mode 100644 index 000000000000..57957093b71b --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config @@ -0,0 +1,10 @@ +CONFIG_PPC_QEMU_E500=y +CONFIG_FSL_SOC_BOOKE=y +CONFIG_PPC_85xx=y +CONFIG_PHYS_64BIT=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_MATH_EMULATION=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config new file mode 100644 index 000000000000..990c510a9cfa --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config @@ -0,0 +1,12 @@ +CONFIG_PPC64=y +CONFIG_PPC_PSERIES=y +CONFIG_ALTIVEC=y +CONFIG_VSX=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y +CONFIG_PPC_RADIX_MMU=y +CONFIG_HVC_CONSOLE=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config new file mode 100644 index 000000000000..00a1ef4869d5 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config new file mode 100644 index 000000000000..5909e7ef2a5c --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -0,0 +1,66 @@ +CONFIG_LOCALVERSION="-debug" +CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_POINTER=y +CONFIG_STACK_VALIDATION=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_PAGE_EXTENSION=y +CONFIG_PAGE_POISONING=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_FREE=y +CONFIG_DEBUG_OBJECTS_TIMERS=y +CONFIG_DEBUG_OBJECTS_WORK=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y +CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y +CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 +CONFIG_SLUB_DEBUG_ON=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_HAVE_DEBUG_STACKOVERFLOW=y +CONFIG_DEBUG_STACKOVERFLOW=y +CONFIG_HAVE_ARCH_KMEMCHECK=y +CONFIG_HAVE_ARCH_KASAN=y +CONFIG_KASAN=y +CONFIG_KASAN_INLINE=y +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +CONFIG_UBSAN_NO_ALIGNMENT=y +CONFIG_UBSAN_NULL=y +CONFIG_DEBUG_KMEMLEAK=y +CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192 +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_WQ_WATCHDOG=y +CONFIG_SCHED_DEBUG=y +CONFIG_SCHED_INFO=y +CONFIG_SCHEDSTATS=y +CONFIG_SCHED_STACK_END_CHECK=y +CONFIG_DEBUG_TIMEKEEPING=y +CONFIG_TIMER_STATS=y +CONFIG_DEBUG_PREEMPT=y +CONFIG_DEBUG_RT_MUTEXES=y +CONFIG_DEBUG_SPINLOCK=y +CONFIG_DEBUG_MUTEXES=y +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_LOCKING=y +CONFIG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_TRACE_IRQFLAGS=y +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_PI_LIST=y +CONFIG_PROVE_RCU=y +CONFIG_SPARSE_RCU_POINTER=y +CONFIG_RCU_CPU_STALL_TIMEOUT=21 +CONFIG_RCU_TRACE=y +CONFIG_RCU_EQS_DEBUG=y +CONFIG_USER_STACKTRACE_SUPPORT=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_DOUBLEFAULT=y +CONFIG_X86_DEBUG_FPU=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT=y +CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c new file mode 100644 index 000000000000..90bc9813cadc --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/init.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#define _GNU_SOURCE +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <fcntl.h> +#include <sys/wait.h> +#include <sys/mount.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/io.h> +#include <sys/ioctl.h> +#include <sys/reboot.h> +#include <sys/utsname.h> +#include <sys/sendfile.h> +#include <sys/sysmacros.h> +#include <linux/random.h> +#include <linux/version.h> + +__attribute__((noreturn)) static void poweroff(void) +{ + fflush(stdout); + fflush(stderr); + reboot(RB_AUTOBOOT); + sleep(30); + fprintf(stderr, "\x1b[37m\x1b[41m\x1b[1mFailed to power off!!!\x1b[0m\n"); + exit(1); +} + +static void panic(const char *what) +{ + fprintf(stderr, "\n\n\x1b[37m\x1b[41m\x1b[1mSOMETHING WENT HORRIBLY WRONG\x1b[0m\n\n \x1b[31m\x1b[1m%s: %s\x1b[0m\n\n\x1b[37m\x1b[44m\x1b[1mPower off...\x1b[0m\n\n", what, strerror(errno)); + poweroff(); +} + +#define pretty_message(msg) puts("\x1b[32m\x1b[1m" msg "\x1b[0m") + +static void print_banner(void) +{ + struct utsname utsname; + int len; + + if (uname(&utsname) < 0) + panic("uname"); + + len = strlen(" WireGuard Test Suite on ") + strlen(utsname.sysname) + strlen(utsname.release) + strlen(utsname.machine); + printf("\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\x1b[45m\x1b[33m\x1b[1m WireGuard Test Suite on %s %s %s \x1b[0m\n\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\n", len, "", utsname.sysname, utsname.release, utsname.machine, len, ""); +} + +static void seed_rng(void) +{ + int fd; + struct { + int entropy_count; + int buffer_size; + unsigned char buffer[256]; + } entropy = { + .entropy_count = sizeof(entropy.buffer) * 8, + .buffer_size = sizeof(entropy.buffer), + .buffer = "Adding real entropy is not actually important for these tests. Don't try this at home, kids!" + }; + + if (mknod("/dev/urandom", S_IFCHR | 0644, makedev(1, 9))) + panic("mknod(/dev/urandom)"); + fd = open("/dev/urandom", O_WRONLY); + if (fd < 0) + panic("open(urandom)"); + for (int i = 0; i < 256; ++i) { + if (ioctl(fd, RNDADDENTROPY, &entropy) < 0) + panic("ioctl(urandom)"); + } + close(fd); +} + +static void mount_filesystems(void) +{ + pretty_message("[+] Mounting filesystems..."); + mkdir("/dev", 0755); + mkdir("/proc", 0755); + mkdir("/sys", 0755); + mkdir("/tmp", 0755); + mkdir("/run", 0755); + mkdir("/var", 0755); + if (mount("none", "/dev", "devtmpfs", 0, NULL)) + panic("devtmpfs mount"); + if (mount("none", "/proc", "proc", 0, NULL)) + panic("procfs mount"); + if (mount("none", "/sys", "sysfs", 0, NULL)) + panic("sysfs mount"); + if (mount("none", "/tmp", "tmpfs", 0, NULL)) + panic("tmpfs mount"); + if (mount("none", "/run", "tmpfs", 0, NULL)) + panic("tmpfs mount"); + if (mount("none", "/sys/kernel/debug", "debugfs", 0, NULL)) + ; /* Not a problem if it fails.*/ + if (symlink("/run", "/var/run")) + panic("run symlink"); + if (symlink("/proc/self/fd", "/dev/fd")) + panic("fd symlink"); +} + +static void enable_logging(void) +{ + int fd; + pretty_message("[+] Enabling logging..."); + fd = open("/proc/sys/kernel/printk", O_WRONLY); + if (fd >= 0) { + if (write(fd, "9\n", 2) != 2) + panic("write(printk)"); + close(fd); + } + fd = open("/proc/sys/debug/exception-trace", O_WRONLY); + if (fd >= 0) { + if (write(fd, "1\n", 2) != 2) + panic("write(exception-trace)"); + close(fd); + } + fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY); + if (fd >= 0) { + if (write(fd, "1\n", 2) != 2) + panic("write(panic_on_warn)"); + close(fd); + } +} + +static void kmod_selftests(void) +{ + FILE *file; + char line[2048], *start, *pass; + bool success = true; + pretty_message("[+] Module self-tests:"); + file = fopen("/proc/kmsg", "r"); + if (!file) + panic("fopen(kmsg)"); + if (fcntl(fileno(file), F_SETFL, O_NONBLOCK) < 0) + panic("fcntl(kmsg, nonblock)"); + while (fgets(line, sizeof(line), file)) { + start = strstr(line, "wireguard: "); + if (!start) + continue; + start += 11; + *strchrnul(start, '\n') = '\0'; + if (strstr(start, "www.wireguard.com")) + break; + pass = strstr(start, ": pass"); + if (!pass || pass[6] != '\0') { + success = false; + printf(" \x1b[31m* %s\x1b[0m\n", start); + } else + printf(" \x1b[32m* %s\x1b[0m\n", start); + } + fclose(file); + if (!success) { + puts("\x1b[31m\x1b[1m[-] Tests failed! \u2639\x1b[0m"); + poweroff(); + } +} + +static void launch_tests(void) +{ + char cmdline[4096], *success_dev; + int status, fd; + pid_t pid; + + pretty_message("[+] Launching tests..."); + pid = fork(); + if (pid == -1) + panic("fork"); + else if (pid == 0) { + execl("/init.sh", "init", NULL); + panic("exec"); + } + if (waitpid(pid, &status, 0) < 0) + panic("waitpid"); + if (WIFEXITED(status) && WEXITSTATUS(status) == 0) { + pretty_message("[+] Tests successful! :-)"); + fd = open("/proc/cmdline", O_RDONLY); + if (fd < 0) + panic("open(/proc/cmdline)"); + if (read(fd, cmdline, sizeof(cmdline) - 1) <= 0) + panic("read(/proc/cmdline)"); + cmdline[sizeof(cmdline) - 1] = '\0'; + for (success_dev = strtok(cmdline, " \n"); success_dev; success_dev = strtok(NULL, " \n")) { + if (strncmp(success_dev, "wg.success=", 11)) + continue; + memcpy(success_dev + 11 - 5, "/dev/", 5); + success_dev += 11 - 5; + break; + } + if (!success_dev || !strlen(success_dev)) + panic("Unable to find success device"); + + fd = open(success_dev, O_WRONLY); + if (fd < 0) + panic("open(success_dev)"); + if (write(fd, "success\n", 8) != 8) + panic("write(success_dev)"); + close(fd); + } else { + const char *why = "unknown cause"; + int what = -1; + + if (WIFEXITED(status)) { + why = "exit code"; + what = WEXITSTATUS(status); + } else if (WIFSIGNALED(status)) { + why = "signal"; + what = WTERMSIG(status); + } + printf("\x1b[31m\x1b[1m[-] Tests failed with %s %d! \u2639\x1b[0m\n", why, what); + } +} + +static void ensure_console(void) +{ + for (unsigned int i = 0; i < 1000; ++i) { + int fd = open("/dev/console", O_RDWR); + if (fd < 0) { + usleep(50000); + continue; + } + dup2(fd, 0); + dup2(fd, 1); + dup2(fd, 2); + close(fd); + if (write(1, "\0\0\0\0\n", 5) == 5) + return; + } + panic("Unable to open console device"); +} + +static void clear_leaks(void) +{ + int fd; + + fd = open("/sys/kernel/debug/kmemleak", O_WRONLY); + if (fd < 0) + return; + pretty_message("[+] Starting memory leak detection..."); + write(fd, "clear\n", 5); + close(fd); +} + +static void check_leaks(void) +{ + int fd; + + fd = open("/sys/kernel/debug/kmemleak", O_WRONLY); + if (fd < 0) + return; + pretty_message("[+] Scanning for memory leaks..."); + sleep(2); /* Wait for any grace periods. */ + write(fd, "scan\n", 5); + close(fd); + + fd = open("/sys/kernel/debug/kmemleak", O_RDONLY); + if (fd < 0) + return; + if (sendfile(1, fd, NULL, 0x7ffff000) > 0) + panic("Memory leaks encountered"); + close(fd); +} + +int main(int argc, char *argv[]) +{ + seed_rng(); + ensure_console(); + print_banner(); + mount_filesystems(); + kmod_selftests(); + enable_logging(); + clear_leaks(); + launch_tests(); + check_leaks(); + poweroff(); + return 1; +} diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config new file mode 100644 index 000000000000..af9323a0b6e0 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -0,0 +1,88 @@ +CONFIG_LOCALVERSION="" +CONFIG_NET=y +CONFIG_NETDEVICES=y +CONFIG_NET_CORE=y +CONFIG_NET_IPIP=y +CONFIG_DUMMY=y +CONFIG_VETH=y +CONFIG_MULTIUSER=y +CONFIG_NAMESPACES=y +CONFIG_NET_NS=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IPV6=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_NAT=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XT_NAT=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_NF_NAT_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_TTY=y +CONFIG_BINFMT_ELF=y +CONFIG_BINFMT_SCRIPT=y +CONFIG_VDSO=y +CONFIG_VIRTUALIZATION=y +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PARAVIRT=y +CONFIG_KVM_GUEST=y +CONFIG_PARAVIRT_SPINLOCKS=y +CONFIG_PRINTK=y +CONFIG_KALLSYMS=y +CONFIG_BUG=y +CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y +CONFIG_JUMP_LABEL=y +CONFIG_EMBEDDED=n +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_SHMEM=y +CONFIG_SLUB=y +CONFIG_SPARSEMEM_VMEMMAP=y +CONFIG_SMP=y +CONFIG_SCHED_SMT=y +CONFIG_SCHED_MC=y +CONFIG_NUMA=y +CONFIG_PREEMPT=y +CONFIG_NO_HZ=y +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_HZ_PERIODIC=n +CONFIG_HIGH_RES_TIMERS=y +CONFIG_COMPAT_32BIT_TIME=y +CONFIG_ARCH_RANDOM=y +CONFIG_FILE_LOCKING=y +CONFIG_POSIX_TIMERS=y +CONFIG_DEVTMPFS=y +CONFIG_PROC_FS=y +CONFIG_PROC_SYSCTL=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y +CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15 +CONFIG_PRINTK_TIME=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_LEGACY_VSYSCALL_NONE=y +CONFIG_KERNEL_GZIP=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_WQ_WATCHDOG=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y +CONFIG_PANIC_TIMEOUT=-1 +CONFIG_STACKTRACE=y +CONFIG_EARLY_PRINTK=y +CONFIG_GDB_SCRIPTS=y +CONFIG_WIREGUARD=y +CONFIG_WIREGUARD_DEBUG=y diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore index dc5f11faf530..7f7a2ccc30c4 100644 --- a/tools/testing/vsock/.gitignore +++ b/tools/testing/vsock/.gitignore @@ -1,2 +1,3 @@ *.d +vsock_test vsock_diag_test diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 5be687b1e16c..f8293c6910c9 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only all: test -test: vsock_diag_test -vsock_diag_test: vsock_diag_test.o timeout.o control.o +test: vsock_test vsock_diag_test +vsock_test: vsock_test.o timeout.o control.o util.o +vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o -CFLAGS += -g -O2 -Werror -Wall -I. -I../../include/uapi -I../../include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE +CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE .PHONY: all test clean clean: - ${RM} *.o *.d vsock_diag_test + ${RM} *.o *.d vsock_test vsock_diag_test -include *.d diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README index 2cc6d7302db6..4d5045e7d2c3 100644 --- a/tools/testing/vsock/README +++ b/tools/testing/vsock/README @@ -5,12 +5,13 @@ Hyper-V. The following tests are available: + * vsock_test - core AF_VSOCK socket functionality * vsock_diag_test - vsock_diag.ko module for listing open sockets The following prerequisite steps are not automated and must be performed prior to running tests: -1. Build the kernel and these tests. +1. Build the kernel, make headers_install, and build these tests. 2. Install the kernel and tests on the host. 3. Install the kernel and tests inside the guest. 4. Boot the guest and ensure that the AF_VSOCK transport is enabled. diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c index 45f328c6ff23..4874872fc5a3 100644 --- a/tools/testing/vsock/control.c +++ b/tools/testing/vsock/control.c @@ -205,11 +205,22 @@ void control_expectln(const char *str) char *line; line = control_readln(); - if (strcmp(str, line) != 0) { + + control_cmpln(line, str, true); + + free(line); +} + +bool control_cmpln(char *line, const char *str, bool fail) +{ + if (strcmp(str, line) == 0) + return true; + + if (fail) { fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n", str, line); exit(EXIT_FAILURE); } - free(line); + return false; } diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h index 54a07efd267c..51814b4f9ac1 100644 --- a/tools/testing/vsock/control.h +++ b/tools/testing/vsock/control.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef CONTROL_H #define CONTROL_H @@ -9,5 +10,6 @@ void control_cleanup(void); void control_writeln(const char *str); char *control_readln(void); void control_expectln(const char *str); +bool control_cmpln(char *line, const char *str, bool fail); #endif /* CONTROL_H */ diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h index 77db9ce9860a..ecb7c840e65a 100644 --- a/tools/testing/vsock/timeout.h +++ b/tools/testing/vsock/timeout.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef TIMEOUT_H #define TIMEOUT_H diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c new file mode 100644 index 000000000000..93cbd6f603f9 --- /dev/null +++ b/tools/testing/vsock/util.c @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vsock test utilities + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + */ + +#include <errno.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <signal.h> +#include <unistd.h> +#include <assert.h> +#include <sys/epoll.h> + +#include "timeout.h" +#include "control.h" +#include "util.h" + +/* Install signal handlers */ +void init_signals(void) +{ + struct sigaction act = { + .sa_handler = sigalrm, + }; + + sigaction(SIGALRM, &act, NULL); + signal(SIGPIPE, SIG_IGN); +} + +/* Parse a CID in string representation */ +unsigned int parse_cid(const char *str) +{ + char *endptr = NULL; + unsigned long n; + + errno = 0; + n = strtoul(str, &endptr, 10); + if (errno || *endptr != '\0') { + fprintf(stderr, "malformed CID \"%s\"\n", str); + exit(EXIT_FAILURE); + } + return n; +} + +/* Wait for the remote to close the connection */ +void vsock_wait_remote_close(int fd) +{ + struct epoll_event ev; + int epollfd, nfds; + + epollfd = epoll_create1(0); + if (epollfd == -1) { + perror("epoll_create1"); + exit(EXIT_FAILURE); + } + + ev.events = EPOLLRDHUP | EPOLLHUP; + ev.data.fd = fd; + if (epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev) == -1) { + perror("epoll_ctl"); + exit(EXIT_FAILURE); + } + + nfds = epoll_wait(epollfd, &ev, 1, TIMEOUT * 1000); + if (nfds == -1) { + perror("epoll_wait"); + exit(EXIT_FAILURE); + } + + if (nfds == 0) { + fprintf(stderr, "epoll_wait timed out\n"); + exit(EXIT_FAILURE); + } + + assert(nfds == 1); + assert(ev.events & (EPOLLRDHUP | EPOLLHUP)); + assert(ev.data.fd == fd); + + close(epollfd); +} + +/* Connect to <cid, port> and return the file descriptor. */ +int vsock_stream_connect(unsigned int cid, unsigned int port) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = cid, + }, + }; + int ret; + int fd; + + control_expectln("LISTENING"); + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret < 0) { + int old_errno = errno; + + close(fd); + fd = -1; + errno = old_errno; + } + return fd; +} + +/* Listen on <cid, port> and return the first incoming connection. The remote + * address is stored to clientaddrp. clientaddrp may be NULL. + */ +int vsock_stream_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = cid, + }, + }; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } clientaddr; + socklen_t clientaddr_len = sizeof(clientaddr.svm); + int fd; + int client_fd; + int old_errno; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("bind"); + exit(EXIT_FAILURE); + } + + if (listen(fd, 1) < 0) { + perror("listen"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTENING"); + + timeout_begin(TIMEOUT); + do { + client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); + timeout_check("accept"); + } while (client_fd < 0 && errno == EINTR); + timeout_end(); + + old_errno = errno; + close(fd); + errno = old_errno; + + if (client_fd < 0) + return client_fd; + + if (clientaddr_len != sizeof(clientaddr.svm)) { + fprintf(stderr, "unexpected addrlen from accept(2), %zu\n", + (size_t)clientaddr_len); + exit(EXIT_FAILURE); + } + if (clientaddr.sa.sa_family != AF_VSOCK) { + fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n", + clientaddr.sa.sa_family); + exit(EXIT_FAILURE); + } + + if (clientaddrp) + *clientaddrp = clientaddr.svm; + return client_fd; +} + +/* Transmit one byte and check the return value. + * + * expected_ret: + * <0 Negative errno (for testing errors) + * 0 End-of-file + * 1 Success + */ +void send_byte(int fd, int expected_ret, int flags) +{ + const uint8_t byte = 'A'; + ssize_t nwritten; + + timeout_begin(TIMEOUT); + do { + nwritten = send(fd, &byte, sizeof(byte), flags); + timeout_check("write"); + } while (nwritten < 0 && errno == EINTR); + timeout_end(); + + if (expected_ret < 0) { + if (nwritten != -1) { + fprintf(stderr, "bogus send(2) return value %zd\n", + nwritten); + exit(EXIT_FAILURE); + } + if (errno != -expected_ret) { + perror("write"); + exit(EXIT_FAILURE); + } + return; + } + + if (nwritten < 0) { + perror("write"); + exit(EXIT_FAILURE); + } + if (nwritten == 0) { + if (expected_ret == 0) + return; + + fprintf(stderr, "unexpected EOF while sending byte\n"); + exit(EXIT_FAILURE); + } + if (nwritten != sizeof(byte)) { + fprintf(stderr, "bogus send(2) return value %zd\n", nwritten); + exit(EXIT_FAILURE); + } +} + +/* Receive one byte and check the return value. + * + * expected_ret: + * <0 Negative errno (for testing errors) + * 0 End-of-file + * 1 Success + */ +void recv_byte(int fd, int expected_ret, int flags) +{ + uint8_t byte; + ssize_t nread; + + timeout_begin(TIMEOUT); + do { + nread = recv(fd, &byte, sizeof(byte), flags); + timeout_check("read"); + } while (nread < 0 && errno == EINTR); + timeout_end(); + + if (expected_ret < 0) { + if (nread != -1) { + fprintf(stderr, "bogus recv(2) return value %zd\n", + nread); + exit(EXIT_FAILURE); + } + if (errno != -expected_ret) { + perror("read"); + exit(EXIT_FAILURE); + } + return; + } + + if (nread < 0) { + perror("read"); + exit(EXIT_FAILURE); + } + if (nread == 0) { + if (expected_ret == 0) + return; + + fprintf(stderr, "unexpected EOF while receiving byte\n"); + exit(EXIT_FAILURE); + } + if (nread != sizeof(byte)) { + fprintf(stderr, "bogus recv(2) return value %zd\n", nread); + exit(EXIT_FAILURE); + } + if (byte != 'A') { + fprintf(stderr, "unexpected byte read %c\n", byte); + exit(EXIT_FAILURE); + } +} + +/* Run test cases. The program terminates if a failure occurs. */ +void run_tests(const struct test_case *test_cases, + const struct test_opts *opts) +{ + int i; + + for (i = 0; test_cases[i].name; i++) { + void (*run)(const struct test_opts *opts); + char *line; + + printf("%d - %s...", i, test_cases[i].name); + fflush(stdout); + + /* Full barrier before executing the next test. This + * ensures that client and server are executing the + * same test case. In particular, it means whoever is + * faster will not see the peer still executing the + * last test. This is important because port numbers + * can be used by multiple test cases. + */ + if (test_cases[i].skip) + control_writeln("SKIP"); + else + control_writeln("NEXT"); + + line = control_readln(); + if (control_cmpln(line, "SKIP", false) || test_cases[i].skip) { + + printf("skipped\n"); + + free(line); + continue; + } + + control_cmpln(line, "NEXT", true); + free(line); + + if (opts->mode == TEST_MODE_CLIENT) + run = test_cases[i].run_client; + else + run = test_cases[i].run_server; + + if (run) + run(opts); + + printf("ok\n"); + } +} + +void list_tests(const struct test_case *test_cases) +{ + int i; + + printf("ID\tTest name\n"); + + for (i = 0; test_cases[i].name; i++) + printf("%d\t%s\n", i, test_cases[i].name); + + exit(EXIT_FAILURE); +} + +void skip_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str) +{ + unsigned long test_id; + char *endptr = NULL; + + errno = 0; + test_id = strtoul(test_id_str, &endptr, 10); + if (errno || *endptr != '\0') { + fprintf(stderr, "malformed test ID \"%s\"\n", test_id_str); + exit(EXIT_FAILURE); + } + + if (test_id >= test_cases_len) { + fprintf(stderr, "test ID (%lu) larger than the max allowed (%lu)\n", + test_id, test_cases_len - 1); + exit(EXIT_FAILURE); + } + + test_cases[test_id].skip = true; +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h new file mode 100644 index 000000000000..e53dd09d26d9 --- /dev/null +++ b/tools/testing/vsock/util.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef UTIL_H +#define UTIL_H + +#include <sys/socket.h> +#include <linux/vm_sockets.h> + +/* Tests can either run as the client or the server */ +enum test_mode { + TEST_MODE_UNSET, + TEST_MODE_CLIENT, + TEST_MODE_SERVER +}; + +/* Test runner options */ +struct test_opts { + enum test_mode mode; + unsigned int peer_cid; +}; + +/* A test case definition. Test functions must print failures to stderr and + * terminate with exit(EXIT_FAILURE). + */ +struct test_case { + const char *name; /* human-readable name */ + + /* Called when test mode is TEST_MODE_CLIENT */ + void (*run_client)(const struct test_opts *opts); + + /* Called when test mode is TEST_MODE_SERVER */ + void (*run_server)(const struct test_opts *opts); + + bool skip; +}; + +void init_signals(void); +unsigned int parse_cid(const char *str); +int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_stream_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp); +void vsock_wait_remote_close(int fd); +void send_byte(int fd, int expected_ret, int flags); +void recv_byte(int fd, int expected_ret, int flags); +void run_tests(const struct test_case *test_cases, + const struct test_opts *opts); +void list_tests(const struct test_case *test_cases); +void skip_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str); +#endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c index c481101364a4..cec6f5a738e1 100644 --- a/tools/testing/vsock/vsock_diag_test.c +++ b/tools/testing/vsock/vsock_diag_test.c @@ -9,32 +9,22 @@ #include <getopt.h> #include <stdio.h> -#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <errno.h> #include <unistd.h> -#include <signal.h> -#include <sys/socket.h> #include <sys/stat.h> #include <sys/types.h> #include <linux/list.h> #include <linux/net.h> #include <linux/netlink.h> #include <linux/sock_diag.h> +#include <linux/vm_sockets_diag.h> #include <netinet/tcp.h> -#include "../../../include/uapi/linux/vm_sockets.h" -#include "../../../include/uapi/linux/vm_sockets_diag.h" - #include "timeout.h" #include "control.h" - -enum test_mode { - TEST_MODE_UNSET, - TEST_MODE_CLIENT, - TEST_MODE_SERVER -}; +#include "util.h" /* Per-socket status */ struct vsock_stat { @@ -335,7 +325,7 @@ static void free_sock_stat(struct list_head *sockets) free(st); } -static void test_no_sockets(unsigned int peer_cid) +static void test_no_sockets(const struct test_opts *opts) { LIST_HEAD(sockets); @@ -346,7 +336,7 @@ static void test_no_sockets(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_listen_socket_server(unsigned int peer_cid) +static void test_listen_socket_server(const struct test_opts *opts) { union { struct sockaddr sa; @@ -384,35 +374,14 @@ static void test_listen_socket_server(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_connect_client(unsigned int peer_cid) +static void test_connect_client(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = 1234, - .svm_cid = peer_cid, - }, - }; int fd; - int ret; LIST_HEAD(sockets); struct vsock_stat *st; - control_expectln("LISTENING"); - - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - timeout_begin(TIMEOUT); - do { - ret = connect(fd, &addr.sa, sizeof(addr.svm)); - timeout_check("connect"); - } while (ret < 0 && errno == EINTR); - timeout_end(); - - if (ret < 0) { + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { perror("connect"); exit(EXIT_FAILURE); } @@ -430,68 +399,21 @@ static void test_connect_client(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_connect_server(unsigned int peer_cid) +static void test_connect_server(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = 1234, - .svm_cid = VMADDR_CID_ANY, - }, - }; - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } clientaddr; - socklen_t clientaddr_len = sizeof(clientaddr.svm); - LIST_HEAD(sockets); struct vsock_stat *st; - int fd; + LIST_HEAD(sockets); int client_fd; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } - - if (listen(fd, 1) < 0) { - perror("listen"); - exit(EXIT_FAILURE); - } - - control_writeln("LISTENING"); - - timeout_begin(TIMEOUT); - do { - client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); - timeout_check("accept"); - } while (client_fd < 0 && errno == EINTR); - timeout_end(); - + client_fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); if (client_fd < 0) { perror("accept"); exit(EXIT_FAILURE); } - if (clientaddr.sa.sa_family != AF_VSOCK) { - fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n", - clientaddr.sa.sa_family); - exit(EXIT_FAILURE); - } - if (clientaddr.svm.svm_cid != peer_cid) { - fprintf(stderr, "expected peer CID %u from accept(2), got %u\n", - peer_cid, clientaddr.svm.svm_cid); - exit(EXIT_FAILURE); - } read_vsock_stat(&sockets); - check_num_sockets(&sockets, 2); - find_vsock_stat(&sockets, fd); + check_num_sockets(&sockets, 1); st = find_vsock_stat(&sockets, client_fd); check_socket_state(st, TCP_ESTABLISHED); @@ -499,15 +421,10 @@ static void test_connect_server(unsigned int peer_cid) control_expectln("DONE"); close(client_fd); - close(fd); free_sock_stat(&sockets); } -static struct { - const char *name; - void (*run_client)(unsigned int peer_cid); - void (*run_server)(unsigned int peer_cid); -} test_cases[] = { +static struct test_case test_cases[] = { { .name = "No sockets", .run_server = test_no_sockets, @@ -524,30 +441,6 @@ static struct { {}, }; -static void init_signals(void) -{ - struct sigaction act = { - .sa_handler = sigalrm, - }; - - sigaction(SIGALRM, &act, NULL); - signal(SIGPIPE, SIG_IGN); -} - -static unsigned int parse_cid(const char *str) -{ - char *endptr = NULL; - unsigned long int n; - - errno = 0; - n = strtoul(str, &endptr, 10); - if (errno || *endptr != '\0') { - fprintf(stderr, "malformed CID \"%s\"\n", str); - exit(EXIT_FAILURE); - } - return n; -} - static const char optstring[] = ""; static const struct option longopts[] = { { @@ -571,6 +464,16 @@ static const struct option longopts[] = { .val = 'p', }, { + .name = "list", + .has_arg = no_argument, + .val = 'l', + }, + { + .name = "skip", + .has_arg = required_argument, + .val = 's', + }, + { .name = "help", .has_arg = no_argument, .val = '?', @@ -580,7 +483,7 @@ static const struct option longopts[] = { static void usage(void) { - fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid>\n" + fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid> [--list] [--skip=<test_id>]\n" "\n" " Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n" " Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n" @@ -594,7 +497,18 @@ static void usage(void) "listen address and the client requires an address to\n" "connect to.\n" "\n" - "The CID of the other side must be given with --peer-cid=<cid>.\n"); + "The CID of the other side must be given with --peer-cid=<cid>.\n" + "\n" + "Options:\n" + " --help This help message\n" + " --control-host <host> Server IP address to connect to\n" + " --control-port <port> Server port to listen on/connect to\n" + " --mode client|server Server or client mode\n" + " --peer-cid <cid> CID of the other side\n" + " --list List of tests that will be executed\n" + " --skip <test_id> Test ID to skip;\n" + " use multiple --skip options to skip more tests\n" + ); exit(EXIT_FAILURE); } @@ -602,9 +516,10 @@ int main(int argc, char **argv) { const char *control_host = NULL; const char *control_port = NULL; - int mode = TEST_MODE_UNSET; - unsigned int peer_cid = VMADDR_CID_ANY; - int i; + struct test_opts opts = { + .mode = TEST_MODE_UNSET, + .peer_cid = VMADDR_CID_ANY, + }; init_signals(); @@ -620,20 +535,27 @@ int main(int argc, char **argv) break; case 'm': if (strcmp(optarg, "client") == 0) - mode = TEST_MODE_CLIENT; + opts.mode = TEST_MODE_CLIENT; else if (strcmp(optarg, "server") == 0) - mode = TEST_MODE_SERVER; + opts.mode = TEST_MODE_SERVER; else { fprintf(stderr, "--mode must be \"client\" or \"server\"\n"); return EXIT_FAILURE; } break; case 'p': - peer_cid = parse_cid(optarg); + opts.peer_cid = parse_cid(optarg); break; case 'P': control_port = optarg; break; + case 'l': + list_tests(test_cases); + break; + case 's': + skip_test(test_cases, ARRAY_SIZE(test_cases) - 1, + optarg); + break; case '?': default: usage(); @@ -642,35 +564,21 @@ int main(int argc, char **argv) if (!control_port) usage(); - if (mode == TEST_MODE_UNSET) + if (opts.mode == TEST_MODE_UNSET) usage(); - if (peer_cid == VMADDR_CID_ANY) + if (opts.peer_cid == VMADDR_CID_ANY) usage(); if (!control_host) { - if (mode != TEST_MODE_SERVER) + if (opts.mode != TEST_MODE_SERVER) usage(); control_host = "0.0.0.0"; } - control_init(control_host, control_port, mode == TEST_MODE_SERVER); + control_init(control_host, control_port, + opts.mode == TEST_MODE_SERVER); - for (i = 0; test_cases[i].name; i++) { - void (*run)(unsigned int peer_cid); - - printf("%s...", test_cases[i].name); - fflush(stdout); - - if (mode == TEST_MODE_CLIENT) - run = test_cases[i].run_client; - else - run = test_cases[i].run_server; - - if (run) - run(peer_cid); - - printf("ok\n"); - } + run_tests(test_cases, &opts); control_cleanup(); return EXIT_SUCCESS; diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c new file mode 100644 index 000000000000..1d8b93f1af31 --- /dev/null +++ b/tools/testing/vsock/vsock_test.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vsock_test - vsock.ko test suite + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + */ + +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <linux/kernel.h> + +#include "timeout.h" +#include "control.h" +#include "util.h" + +static void test_stream_connection_reset(const struct test_opts *opts) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = opts->peer_cid, + }, + }; + int ret; + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret != -1) { + fprintf(stderr, "expected connect(2) failure, got %d\n", ret); + exit(EXIT_FAILURE); + } + if (errno != ECONNRESET) { + fprintf(stderr, "unexpected connect(2) errno %d\n", errno); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_client_close_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +static void test_stream_client_close_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Wait for the remote to close the connection, before check + * -EPIPE error on send. + */ + vsock_wait_remote_close(fd); + + send_byte(fd, -EPIPE, 0); + recv_byte(fd, 1, 0); + recv_byte(fd, 0, 0); + close(fd); +} + +static void test_stream_server_close_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Wait for the remote to close the connection, before check + * -EPIPE error on send. + */ + vsock_wait_remote_close(fd); + + send_byte(fd, -EPIPE, 0); + recv_byte(fd, 1, 0); + recv_byte(fd, 0, 0); + close(fd); +} + +static void test_stream_server_close_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +/* With the standard socket sizes, VMCI is able to support about 100 + * concurrent stream connections. + */ +#define MULTICONN_NFDS 100 + +static void test_stream_multiconn_client(const struct test_opts *opts) +{ + int fds[MULTICONN_NFDS]; + int i; + + for (i = 0; i < MULTICONN_NFDS; i++) { + fds[i] = vsock_stream_connect(opts->peer_cid, 1234); + if (fds[i] < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + } + + for (i = 0; i < MULTICONN_NFDS; i++) { + if (i % 2) + recv_byte(fds[i], 1, 0); + else + send_byte(fds[i], 1, 0); + } + + for (i = 0; i < MULTICONN_NFDS; i++) + close(fds[i]); +} + +static void test_stream_multiconn_server(const struct test_opts *opts) +{ + int fds[MULTICONN_NFDS]; + int i; + + for (i = 0; i < MULTICONN_NFDS; i++) { + fds[i] = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fds[i] < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + } + + for (i = 0; i < MULTICONN_NFDS; i++) { + if (i % 2) + send_byte(fds[i], 1, 0); + else + recv_byte(fds[i], 1, 0); + } + + for (i = 0; i < MULTICONN_NFDS; i++) + close(fds[i]); +} + +static void test_stream_msg_peek_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +static void test_stream_msg_peek_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_byte(fd, 1, MSG_PEEK); + recv_byte(fd, 1, 0); + close(fd); +} + +static struct test_case test_cases[] = { + { + .name = "SOCK_STREAM connection reset", + .run_client = test_stream_connection_reset, + }, + { + .name = "SOCK_STREAM client close", + .run_client = test_stream_client_close_client, + .run_server = test_stream_client_close_server, + }, + { + .name = "SOCK_STREAM server close", + .run_client = test_stream_server_close_client, + .run_server = test_stream_server_close_server, + }, + { + .name = "SOCK_STREAM multiple connections", + .run_client = test_stream_multiconn_client, + .run_server = test_stream_multiconn_server, + }, + { + .name = "SOCK_STREAM MSG_PEEK", + .run_client = test_stream_msg_peek_client, + .run_server = test_stream_msg_peek_server, + }, + {}, +}; + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "control-host", + .has_arg = required_argument, + .val = 'H', + }, + { + .name = "control-port", + .has_arg = required_argument, + .val = 'P', + }, + { + .name = "mode", + .has_arg = required_argument, + .val = 'm', + }, + { + .name = "peer-cid", + .has_arg = required_argument, + .val = 'p', + }, + { + .name = "list", + .has_arg = no_argument, + .val = 'l', + }, + { + .name = "skip", + .has_arg = required_argument, + .val = 's', + }, + { + .name = "help", + .has_arg = no_argument, + .val = '?', + }, + {}, +}; + +static void usage(void) +{ + fprintf(stderr, "Usage: vsock_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid> [--list] [--skip=<test_id>]\n" + "\n" + " Server: vsock_test --control-port=1234 --mode=server --peer-cid=3\n" + " Client: vsock_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n" + "\n" + "Run vsock.ko tests. Must be launched in both guest\n" + "and host. One side must use --mode=client and\n" + "the other side must use --mode=server.\n" + "\n" + "A TCP control socket connection is used to coordinate tests\n" + "between the client and the server. The server requires a\n" + "listen address and the client requires an address to\n" + "connect to.\n" + "\n" + "The CID of the other side must be given with --peer-cid=<cid>.\n" + "\n" + "Options:\n" + " --help This help message\n" + " --control-host <host> Server IP address to connect to\n" + " --control-port <port> Server port to listen on/connect to\n" + " --mode client|server Server or client mode\n" + " --peer-cid <cid> CID of the other side\n" + " --list List of tests that will be executed\n" + " --skip <test_id> Test ID to skip;\n" + " use multiple --skip options to skip more tests\n" + ); + exit(EXIT_FAILURE); +} + +int main(int argc, char **argv) +{ + const char *control_host = NULL; + const char *control_port = NULL; + struct test_opts opts = { + .mode = TEST_MODE_UNSET, + .peer_cid = VMADDR_CID_ANY, + }; + + init_signals(); + + for (;;) { + int opt = getopt_long(argc, argv, optstring, longopts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'H': + control_host = optarg; + break; + case 'm': + if (strcmp(optarg, "client") == 0) + opts.mode = TEST_MODE_CLIENT; + else if (strcmp(optarg, "server") == 0) + opts.mode = TEST_MODE_SERVER; + else { + fprintf(stderr, "--mode must be \"client\" or \"server\"\n"); + return EXIT_FAILURE; + } + break; + case 'p': + opts.peer_cid = parse_cid(optarg); + break; + case 'P': + control_port = optarg; + break; + case 'l': + list_tests(test_cases); + break; + case 's': + skip_test(test_cases, ARRAY_SIZE(test_cases) - 1, + optarg); + break; + case '?': + default: + usage(); + } + } + + if (!control_port) + usage(); + if (opts.mode == TEST_MODE_UNSET) + usage(); + if (opts.peer_cid == VMADDR_CID_ANY) + usage(); + + if (!control_host) { + if (opts.mode != TEST_MODE_SERVER) + usage(); + control_host = "0.0.0.0"; + } + + control_init(control_host, control_port, + opts.mode == TEST_MODE_SERVER); + + run_tests(test_cases, &opts); + + control_cleanup(); + return EXIT_SUCCESS; +} diff --git a/tools/usb/usbip/README b/tools/usb/usbip/README index 7844490fc603..2fc021c0eae1 100644 --- a/tools/usb/usbip/README +++ b/tools/usb/usbip/README @@ -138,28 +138,28 @@ attached to this host. Local USB devices ================= - busid 1-1 (05a9:a511) - 1-1:1.0 -> ov511 + 1-1:1.0 - busid 3-2 (0711:0902) - 3-2:1.0 -> none + 3-2:1.0 - busid 3-3.1 (08bb:2702) - 3-3.1:1.0 -> snd-usb-audio - 3-3.1:1.1 -> snd-usb-audio + 3-3.1:1.0 + 3-3.1:1.1 - busid 3-3.2 (04bb:0206) - 3-3.2:1.0 -> usb-storage + 3-3.2:1.0 - busid 3-3 (0409:0058) - 3-3:1.0 -> hub + 3-3:1.0 - busid 4-1 (046d:08b2) - 4-1:1.0 -> none - 4-1:1.1 -> none - 4-1:1.2 -> none + 4-1:1.0 + 4-1:1.1 + 4-1:1.2 - busid 5-2 (058f:9254) - 5-2:1.0 -> hub + 5-2:1.0 A USB storage device of busid 3-3.2 is now bound to the usb-storage driver. To export this device, we first mark the device as @@ -180,7 +180,7 @@ Mark the device of busid 3-3.2 as exportable: ... - busid 3-3.2 (04bb:0206) - 3-3.2:1.0 -> usbip-host + 3-3.2:1.0 ... --------------------------- diff --git a/tools/usb/usbip/src/usbip_network.c b/tools/usb/usbip/src/usbip_network.c index d595d72693fb..ed4dc8c14269 100644 --- a/tools/usb/usbip/src/usbip_network.c +++ b/tools/usb/usbip/src/usbip_network.c @@ -50,39 +50,39 @@ void usbip_setup_port_number(char *arg) info("using port %d (\"%s\")", usbip_port, usbip_port_string); } -void usbip_net_pack_uint32_t(int pack, uint32_t *num) +uint32_t usbip_net_pack_uint32_t(int pack, uint32_t num) { uint32_t i; if (pack) - i = htonl(*num); + i = htonl(num); else - i = ntohl(*num); + i = ntohl(num); - *num = i; + return i; } -void usbip_net_pack_uint16_t(int pack, uint16_t *num) +uint16_t usbip_net_pack_uint16_t(int pack, uint16_t num) { uint16_t i; if (pack) - i = htons(*num); + i = htons(num); else - i = ntohs(*num); + i = ntohs(num); - *num = i; + return i; } void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev) { - usbip_net_pack_uint32_t(pack, &udev->busnum); - usbip_net_pack_uint32_t(pack, &udev->devnum); - usbip_net_pack_uint32_t(pack, &udev->speed); + udev->busnum = usbip_net_pack_uint32_t(pack, udev->busnum); + udev->devnum = usbip_net_pack_uint32_t(pack, udev->devnum); + udev->speed = usbip_net_pack_uint32_t(pack, udev->speed); - usbip_net_pack_uint16_t(pack, &udev->idVendor); - usbip_net_pack_uint16_t(pack, &udev->idProduct); - usbip_net_pack_uint16_t(pack, &udev->bcdDevice); + udev->idVendor = usbip_net_pack_uint16_t(pack, udev->idVendor); + udev->idProduct = usbip_net_pack_uint16_t(pack, udev->idProduct); + udev->bcdDevice = usbip_net_pack_uint16_t(pack, udev->bcdDevice); } void usbip_net_pack_usb_interface(int pack __attribute__((unused)), @@ -129,6 +129,14 @@ ssize_t usbip_net_send(int sockfd, void *buff, size_t bufflen) return usbip_net_xmit(sockfd, buff, bufflen, 1); } +static inline void usbip_net_pack_op_common(int pack, + struct op_common *op_common) +{ + op_common->version = usbip_net_pack_uint16_t(pack, op_common->version); + op_common->code = usbip_net_pack_uint16_t(pack, op_common->code); + op_common->status = usbip_net_pack_uint32_t(pack, op_common->status); +} + int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status) { struct op_common op_common; @@ -140,7 +148,7 @@ int usbip_net_send_op_common(int sockfd, uint32_t code, uint32_t status) op_common.code = code; op_common.status = status; - PACK_OP_COMMON(1, &op_common); + usbip_net_pack_op_common(1, &op_common); rc = usbip_net_send(sockfd, &op_common, sizeof(op_common)); if (rc < 0) { @@ -164,7 +172,7 @@ int usbip_net_recv_op_common(int sockfd, uint16_t *code, int *status) goto err; } - PACK_OP_COMMON(0, &op_common); + usbip_net_pack_op_common(0, &op_common); if (op_common.version != USBIP_VERSION) { err("USBIP Kernel and tool version mismatch: %d %d:", diff --git a/tools/usb/usbip/src/usbip_network.h b/tools/usb/usbip/src/usbip_network.h index 555215eae43e..83b4c5344f72 100644 --- a/tools/usb/usbip/src/usbip_network.h +++ b/tools/usb/usbip/src/usbip_network.h @@ -32,12 +32,6 @@ struct op_common { } __attribute__((packed)); -#define PACK_OP_COMMON(pack, op_common) do {\ - usbip_net_pack_uint16_t(pack, &(op_common)->version);\ - usbip_net_pack_uint16_t(pack, &(op_common)->code);\ - usbip_net_pack_uint32_t(pack, &(op_common)->status);\ -} while (0) - /* ---------------------------------------------------------------------- */ /* Dummy Code */ #define OP_UNSPEC 0x00 @@ -163,11 +157,11 @@ struct op_devlist_reply_extra { } while (0) #define PACK_OP_DEVLIST_REPLY(pack, reply) do {\ - usbip_net_pack_uint32_t(pack, &(reply)->ndev);\ + (reply)->ndev = usbip_net_pack_uint32_t(pack, (reply)->ndev);\ } while (0) -void usbip_net_pack_uint32_t(int pack, uint32_t *num); -void usbip_net_pack_uint16_t(int pack, uint16_t *num); +uint32_t usbip_net_pack_uint32_t(int pack, uint32_t num); +uint16_t usbip_net_pack_uint16_t(int pack, uint16_t num); void usbip_net_pack_usb_device(int pack, struct usbip_usb_device *udev); void usbip_net_pack_usb_interface(int pack, struct usbip_usb_interface *uinf); diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c index 68092d15e12b..9b68658b6bb8 100644 --- a/tools/vm/slabinfo.c +++ b/tools/vm/slabinfo.c @@ -720,11 +720,11 @@ static void slab_debug(struct slabinfo *s) return; if (sanity && !s->sanity_checks) { - set_obj(s, "sanity", 1); + set_obj(s, "sanity_checks", 1); } if (!sanity && s->sanity_checks) { if (slab_empty(s)) - set_obj(s, "sanity", 0); + set_obj(s, "sanity_checks", 0); else fprintf(stderr, "%s not empty cannot disable sanity checks\n", s->name); } |