diff options
Diffstat (limited to 'tools')
242 files changed, 7499 insertions, 2117 deletions
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index d0ce5cfd3ac1..d5b5f2ab87a0 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -277,6 +277,7 @@ #define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC instruction */ #define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 instruction */ #define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS instructions */ +#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -298,6 +299,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index a7c413432b33..01e2650b9585 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -625,6 +625,8 @@ #define MSR_IA32_BNDCFGS_RSVD 0x00000ffc +#define MSR_IA32_XFD 0x000001c4 +#define MSR_IA32_XFD_ERR 0x000001c5 #define MSR_IA32_XSS 0x00000da0 #define MSR_IA32_APICBASE 0x0000001b diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 2ef1f6513c68..5a776a08f78c 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -504,4 +504,8 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ +#define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ +#define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 5a6aac9fa41f..754a07856817 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -10,6 +10,10 @@ #define ARCH_GET_CPUID 0x1011 #define ARCH_SET_CPUID 0x1012 +#define ARCH_GET_XCOMP_SUPP 0x1021 +#define ARCH_GET_XCOMP_PERM 0x1022 +#define ARCH_REQ_XCOMP_PERM 0x1023 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index e9e6166c3f28..5d26f3c6f918 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -83,6 +83,7 @@ struct btf_id { int cnt; }; int addr_cnt; + bool is_set; Elf64_Addr addr[ADDR_CNT]; }; @@ -451,8 +452,10 @@ static int symbols_collect(struct object *obj) * in symbol's size, together with 'cnt' field hence * that - 1. */ - if (id) + if (id) { id->cnt = sym.st_size / sizeof(int) - 1; + id->is_set = true; + } } else { pr_err("FAILED unsupported prefix %s\n", prefix); return -1; @@ -568,9 +571,8 @@ static int id_patch(struct object *obj, struct btf_id *id) int *ptr = data->d_buf; int i; - if (!id->id) { + if (!id->id && !id->is_set) pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); - } for (i = 0; i < id->addr_cnt; i++) { unsigned long addr = id->addr[i]; diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index bbd1150578f7..8791d0e2762b 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -88,5 +88,4 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OU $(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) \ - LIBBPF_OUTPUT=$(BPFOBJ_OUTPUT) \ - LIBBPF_DESTDIR=$(BPF_DESTDIR) CC=$(HOSTCC) LD=$(HOSTLD) + CC=$(HOSTCC) LD=$(HOSTLD) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 45a9a59828c3..ae61f464043a 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -48,7 +48,6 @@ FEATURE_TESTS_BASIC := \ numa_num_possible_cpus \ libperl \ libpython \ - libpython-version \ libslang \ libslang-include-subdir \ libtraceevent \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 0a3244ad9673..1480910c792e 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -32,7 +32,6 @@ FILES= \ test-numa_num_possible_cpus.bin \ test-libperl.bin \ test-libpython.bin \ - test-libpython-version.bin \ test-libslang.bin \ test-libslang-include-subdir.bin \ test-libtraceevent.bin \ @@ -227,9 +226,6 @@ $(OUTPUT)test-libperl.bin: $(OUTPUT)test-libpython.bin: $(BUILD) $(FLAGS_PYTHON_EMBED) -$(OUTPUT)test-libpython-version.bin: - $(BUILD) - $(OUTPUT)test-libbfd.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 920439527291..5ffafb967b6e 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -14,10 +14,6 @@ # include "test-libpython.c" #undef main -#define main main_test_libpython_version -# include "test-libpython-version.c" -#undef main - #define main main_test_libperl # include "test-libperl.c" #undef main @@ -177,7 +173,6 @@ int main(int argc, char *argv[]) { main_test_libpython(); - main_test_libpython_version(); main_test_libperl(); main_test_hello(); main_test_libelf(); @@ -200,7 +195,6 @@ int main(int argc, char *argv[]) main_test_timerfd(); main_test_stackprotector_all(); main_test_libdw_dwarf_unwind(); - main_test_sync_compare_and_swap(argc, argv); main_test_zlib(); main_test_pthread_attr_setaffinity_np(); main_test_pthread_barrier(); diff --git a/tools/build/feature/test-libpython-version.c b/tools/build/feature/test-libpython-version.c deleted file mode 100644 index 47714b942d4d..000000000000 --- a/tools/build/feature/test-libpython-version.c +++ /dev/null @@ -1,11 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <Python.h> - -#if PY_VERSION_HEX >= 0x03000000 - #error -#endif - -int main(void) -{ - return 0; -} diff --git a/tools/include/linux/debug_locks.h b/tools/include/linux/debug_locks.h deleted file mode 100644 index 72d595ce764a..000000000000 --- a/tools/include/linux/debug_locks.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_ -#define _LIBLOCKDEP_DEBUG_LOCKS_H_ - -#include <stddef.h> -#include <linux/compiler.h> -#include <asm/bug.h> - -#define DEBUG_LOCKS_WARN_ON(x) WARN_ON(x) - -extern bool debug_locks; -extern bool debug_locks_silent; - -#endif diff --git a/tools/include/linux/hardirq.h b/tools/include/linux/hardirq.h deleted file mode 100644 index b25580b6a9be..000000000000 --- a/tools/include/linux/hardirq.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_ -#define _LIBLOCKDEP_LINUX_HARDIRQ_H_ - -#define SOFTIRQ_BITS 0UL -#define HARDIRQ_BITS 0UL -#define SOFTIRQ_SHIFT 0UL -#define HARDIRQ_SHIFT 0UL -#define hardirq_count() 0UL -#define softirq_count() 0UL - -#endif diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h deleted file mode 100644 index 501262aee8ff..000000000000 --- a/tools/include/linux/irqflags.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ -#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ - -# define lockdep_hardirq_context() 0 -# define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled() 0 -# define lockdep_softirqs_enabled(p) 0 -# define lockdep_hardirq_enter() do { } while (0) -# define lockdep_hardirq_exit() do { } while (0) -# define lockdep_softirq_enter() do { } while (0) -# define lockdep_softirq_exit() do { } while (0) -# define INIT_TRACE_IRQFLAGS - -# define stop_critical_timings() do { } while (0) -# define start_critical_timings() do { } while (0) - -#define raw_local_irq_disable() do { } while (0) -#define raw_local_irq_enable() do { } while (0) -#define raw_local_irq_save(flags) ((flags) = 0) -#define raw_local_irq_restore(flags) ((void)(flags)) -#define raw_local_save_flags(flags) ((flags) = 0) -#define raw_irqs_disabled_flags(flags) ((void)(flags)) -#define raw_irqs_disabled() 0 -#define raw_safe_halt() - -#define local_irq_enable() do { } while (0) -#define local_irq_disable() do { } while (0) -#define local_irq_save(flags) ((flags) = 0) -#define local_irq_restore(flags) ((void)(flags)) -#define local_save_flags(flags) ((flags) = 0) -#define irqs_disabled() (1) -#define irqs_disabled_flags(flags) ((void)(flags), 0) -#define safe_halt() do { } while (0) - -#define trace_lock_release(x, y) -#define trace_lock_acquire(a, b, c, d, e, f, g) - -#endif diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index a7e54a08fb54..3e8df500cfbd 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -7,6 +7,7 @@ #include <assert.h> #include <linux/build_bug.h> #include <linux/compiler.h> +#include <linux/math.h> #include <endian.h> #include <byteswap.h> @@ -14,8 +15,6 @@ #define UINT_MAX (~0U) #endif -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) - #define PERF_ALIGN(x, a) __PERF_ALIGN_MASK(x, (typeof(x))(a)-1) #define __PERF_ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) @@ -52,15 +51,6 @@ _min1 < _min2 ? _min1 : _min2; }) #endif -#ifndef roundup -#define roundup(x, y) ( \ -{ \ - const typeof(y) __y = y; \ - (((x) + (__y - 1)) / __y) * __y; \ -} \ -) -#endif - #ifndef BUG_ON #ifdef NDEBUG #define BUG_ON(cond) do { if (cond) {} } while (0) @@ -104,16 +94,6 @@ int scnprintf_pad(char * buf, size_t size, const char * fmt, ...); #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) -/* - * This looks more complex than it should be. But we need to - * get the type for the ~ right in round_down (it needs to be - * as wide as the result!), and we want to evaluate the macro - * arguments just once each. - */ -#define __round_mask(x, y) ((__typeof__(x))((y)-1)) -#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) -#define round_down(x, y) ((x) & ~__round_mask(x, y)) - #define current_gfp_context(k) 0 #define synchronize_rcu() diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h deleted file mode 100644 index e56997288f2b..000000000000 --- a/tools/include/linux/lockdep.h +++ /dev/null @@ -1,72 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LOCKDEP_H_ -#define _LIBLOCKDEP_LOCKDEP_H_ - -#include <sys/prctl.h> -#include <sys/syscall.h> -#include <string.h> -#include <limits.h> -#include <linux/utsname.h> -#include <linux/compiler.h> -#include <linux/export.h> -#include <linux/kern_levels.h> -#include <linux/err.h> -#include <linux/rcu.h> -#include <linux/list.h> -#include <linux/hardirq.h> -#include <unistd.h> - -#define MAX_LOCK_DEPTH 63UL - -#define asmlinkage -#define __visible - -#include "../../../include/linux/lockdep.h" - -struct task_struct { - u64 curr_chain_key; - int lockdep_depth; - unsigned int lockdep_recursion; - struct held_lock held_locks[MAX_LOCK_DEPTH]; - gfp_t lockdep_reclaim_gfp; - int pid; - int state; - char comm[17]; -}; - -#define TASK_RUNNING 0 - -extern struct task_struct *__curr(void); - -#define current (__curr()) - -static inline int debug_locks_off(void) -{ - return 1; -} - -#define task_pid_nr(tsk) ((tsk)->pid) - -#define KSYM_NAME_LEN 128 -#define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__) -#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__) -#define pr_warn pr_err -#define pr_cont pr_err - -#define list_del_rcu list_del - -#define atomic_t unsigned long -#define atomic_inc(x) ((*(x))++) - -#define print_tainted() "" -#define static_obj(x) 1 - -#define debug_show_all_locks() -extern void debug_check_no_locks_held(void); - -static __used bool __is_kernel_percpu_address(unsigned long addr, void *can_addr) -{ - return false; -} - -#endif diff --git a/tools/include/linux/math.h b/tools/include/linux/math.h new file mode 100644 index 000000000000..4e7af99ec9eb --- /dev/null +++ b/tools/include/linux/math.h @@ -0,0 +1,25 @@ +#ifndef _TOOLS_MATH_H +#define _TOOLS_MATH_H + +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + +#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) + +#ifndef roundup +#define roundup(x, y) ( \ +{ \ + const typeof(y) __y = y; \ + (((x) + (__y - 1)) / __y) * __y; \ +} \ +) +#endif + +#endif diff --git a/tools/include/linux/proc_fs.h b/tools/include/linux/proc_fs.h deleted file mode 100644 index 8b3b03b64fda..000000000000 --- a/tools/include/linux/proc_fs.h +++ /dev/null @@ -1,4 +0,0 @@ -#ifndef _TOOLS_INCLUDE_LINUX_PROC_FS_H -#define _TOOLS_INCLUDE_LINUX_PROC_FS_H - -#endif /* _TOOLS_INCLUDE_LINUX_PROC_FS_H */ diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index c934572d935c..622266b197d0 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -37,6 +37,4 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) return true; } -#include <linux/lockdep.h> - #endif diff --git a/tools/include/linux/stacktrace.h b/tools/include/linux/stacktrace.h deleted file mode 100644 index ae343ac35bfa..000000000000 --- a/tools/include/linux/stacktrace.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_ -#define _LIBLOCKDEP_LINUX_STACKTRACE_H_ - -#include <execinfo.h> - -struct stack_trace { - unsigned int nr_entries, max_entries; - unsigned long *entries; - int skip; -}; - -static inline void print_stack_trace(struct stack_trace *trace, int spaces) -{ - backtrace_symbols_fd((void **)trace->entries, trace->nr_entries, 1); -} - -#define save_stack_trace(trace) \ - ((trace)->nr_entries = \ - backtrace((void **)(trace)->entries, (trace)->max_entries)) - -static inline int dump_stack(void) -{ - void *array[64]; - size_t size; - - size = backtrace(array, 64); - backtrace_symbols_fd(array, size, 1); - - return 0; -} - -#endif diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 1c5fb86d455a..4557a8b6086f 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret) #define __NR_process_mrelease 448 __SYSCALL(__NR_process_mrelease, sys_process_mrelease) +#define __NR_futex_waitv 449 +__SYSCALL(__NR_futex_waitv, sys_futex_waitv) + #undef __NR_syscalls -#define __NR_syscalls 449 +#define __NR_syscalls 450 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index bde5860b3686..914ebd9290e5 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching { #define I915_TILING_NONE 0 #define I915_TILING_X 1 #define I915_TILING_Y 2 +/* + * Do not add new tiling types here. The I915_TILING_* values are for + * de-tiling fence registers that no longer exist on modern platforms. Although + * the hardware may support new types of tiling in general (e.g., Tile4), we + * do not need to add them to the uapi that is specific to now-defunct ioctls. + */ #define I915_TILING_LAST I915_TILING_Y #define I915_BIT_6_SWIZZLE_NONE 0 @@ -1824,6 +1830,7 @@ struct drm_i915_gem_context_param { * Extensions: * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE) * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND) + * i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT) */ #define I915_CONTEXT_PARAM_ENGINES 0xa @@ -1846,6 +1853,55 @@ struct drm_i915_gem_context_param { * attempted to use it, never re-use this context param number. */ #define I915_CONTEXT_PARAM_RINGSIZE 0xc + +/* + * I915_CONTEXT_PARAM_PROTECTED_CONTENT: + * + * Mark that the context makes use of protected content, which will result + * in the context being invalidated when the protected content session is. + * Given that the protected content session is killed on suspend, the device + * is kept awake for the lifetime of a protected context, so the user should + * make sure to dispose of them once done. + * This flag can only be set at context creation time and, when set to true, + * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE + * to false. This flag can't be set to true in conjunction with setting the + * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example: + * + * .. code-block:: C + * + * struct drm_i915_gem_context_create_ext_setparam p_protected = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_PROTECTED_CONTENT, + * .value = 1, + * } + * }; + * struct drm_i915_gem_context_create_ext_setparam p_norecover = { + * .base = { + * .name = I915_CONTEXT_CREATE_EXT_SETPARAM, + * .next_extension = to_user_pointer(&p_protected), + * }, + * .param = { + * .param = I915_CONTEXT_PARAM_RECOVERABLE, + * .value = 0, + * } + * }; + * struct drm_i915_gem_context_create_ext create = { + * .flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS, + * .extensions = to_user_pointer(&p_norecover); + * }; + * + * ctx_id = gem_context_create_ext(drm_fd, &create); + * + * In addition to the normal failure cases, setting this flag during context + * creation can result in the following errors: + * + * -ENODEV: feature not available + * -EPERM: trying to mark a recoverable or not bannable context as protected + */ +#define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ __u64 value; @@ -2050,6 +2106,135 @@ struct i915_context_engines_bond { } __attribute__((packed)) name__ /** + * struct i915_context_engines_parallel_submit - Configure engine for + * parallel submission. + * + * Setup a slot in the context engine map to allow multiple BBs to be submitted + * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU + * in parallel. Multiple hardware contexts are created internally in the i915 to + * run these BBs. Once a slot is configured for N BBs only N BBs can be + * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user + * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how + * many BBs there are based on the slot's configuration. The N BBs are the last + * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set. + * + * The default placement behavior is to create implicit bonds between each + * context if each context maps to more than 1 physical engine (e.g. context is + * a virtual engine). Also we only allow contexts of same engine class and these + * contexts must be in logically contiguous order. Examples of the placement + * behavior are described below. Lastly, the default is to not allow BBs to be + * preempted mid-batch. Rather insert coordinated preemption points on all + * hardware contexts between each set of BBs. Flags could be added in the future + * to change both of these default behaviors. + * + * Returns -EINVAL if hardware context placement configuration is invalid or if + * the placement configuration isn't supported on the platform / submission + * interface. + * Returns -ENODEV if extension isn't supported on the platform / submission + * interface. + * + * .. code-block:: none + * + * Examples syntax: + * CS[X] = generic engine of same class, logical instance X + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE + * + * Example 1 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=1, + * engines=CS[0],CS[1]) + * + * Results in the following valid placement: + * CS[0], CS[1] + * + * Example 2 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[2],CS[1],CS[3]) + * + * Results in the following valid placements: + * CS[0], CS[1] + * CS[2], CS[3] + * + * This can be thought of as two virtual engines, each containing two + * engines thereby making a 2D array. However, there are bonds tying the + * entries together and placing restrictions on how they can be scheduled. + * Specifically, the scheduler can choose only vertical columns from the 2D + * array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the + * scheduler wants to submit to CS[0], it must also choose CS[1] and vice + * versa. Same for CS[2] requires also using CS[3]. + * VE[0] = CS[0], CS[2] + * VE[1] = CS[1], CS[3] + * + * Example 3 pseudo code: + * set_engines(INVALID) + * set_parallel(engine_index=0, width=2, num_siblings=2, + * engines=CS[0],CS[1],CS[1],CS[3]) + * + * Results in the following valid and invalid placements: + * CS[0], CS[1] + * CS[1], CS[3] - Not logically contiguous, return -EINVAL + */ +struct i915_context_engines_parallel_submit { + /** + * @base: base user extension. + */ + struct i915_user_extension base; + + /** + * @engine_index: slot for parallel engine + */ + __u16 engine_index; + + /** + * @width: number of contexts per parallel engine or in other words the + * number of batches in each submission + */ + __u16 width; + + /** + * @num_siblings: number of siblings per context or in other words the + * number of possible placements for each submission + */ + __u16 num_siblings; + + /** + * @mbz16: reserved for future use; must be zero + */ + __u16 mbz16; + + /** + * @flags: all undefined flags must be zero, currently not defined flags + */ + __u64 flags; + + /** + * @mbz64: reserved for future use; must be zero + */ + __u64 mbz64[3]; + + /** + * @engines: 2-d array of engine instances to configure parallel engine + * + * length = width (i) * num_siblings (j) + * index = j + i * num_siblings + */ + struct i915_engine_class_instance engines[0]; + +} __packed; + +#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \ + struct i915_user_extension base; \ + __u16 engine_index; \ + __u16 width; \ + __u16 num_siblings; \ + __u16 mbz16; \ + __u64 flags; \ + __u64 mbz64[3]; \ + struct i915_engine_class_instance engines[N__]; \ +} __attribute__((packed)) name__ + +/** * DOC: Context Engine Map uAPI * * Context engine map is a new way of addressing engines when submitting batch- @@ -2108,6 +2293,7 @@ struct i915_context_param_engines { __u64 extensions; /* linked chain of extension blocks, 0 terminates */ #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ +#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ struct i915_engine_class_instance engines[0]; } __attribute__((packed)); @@ -2726,14 +2912,20 @@ struct drm_i915_engine_info { /** @flags: Engine flags. */ __u64 flags; +#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE (1 << 0) /** @capabilities: Capabilities of this engine. */ __u64 capabilities; #define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) + /** @logical_instance: Logical instance of engine */ + __u16 logical_instance; + /** @rsvd1: Reserved fields. */ - __u64 rsvd1[4]; + __u16 rsvd1[3]; + /** @rsvd2: Reserved fields. */ + __u64 rsvd2[3]; }; /** @@ -2979,8 +3171,12 @@ struct drm_i915_gem_create_ext { * * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see * struct drm_i915_gem_create_ext_memory_regions. + * + * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see + * struct drm_i915_gem_create_ext_protected_content. */ #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 +#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 __u64 extensions; }; @@ -3038,6 +3234,50 @@ struct drm_i915_gem_create_ext_memory_regions { __u64 regions; }; +/** + * struct drm_i915_gem_create_ext_protected_content - The + * I915_OBJECT_PARAM_PROTECTED_CONTENT extension. + * + * If this extension is provided, buffer contents are expected to be protected + * by PXP encryption and require decryption for scan out and processing. This + * is only possible on platforms that have PXP enabled, on all other scenarios + * using this extension will cause the ioctl to fail and return -ENODEV. The + * flags parameter is reserved for future expansion and must currently be set + * to zero. + * + * The buffer contents are considered invalid after a PXP session teardown. + * + * The encryption is guaranteed to be processed correctly only if the object + * is submitted with a context created using the + * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks + * at submission time on the validity of the objects involved. + * + * Below is an example on how to create a protected object: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_protected_content protected_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT }, + * .flags = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&protected_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_protected_content { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** @flags: reserved for future usage, currently MBZ */ + __u32 flags; +}; + +/* ID of the protected content session managed by i915 when PXP is active */ +#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf + #if defined(__cplusplus) } #endif diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index b3610fdd1fee..4ac53b30b6dc 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -7,24 +7,23 @@ /* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; __u32 collisions; - /* detailed rx_errors: */ __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; /* detailed tx_errors */ __u32 tx_aborted_errors; @@ -37,29 +36,201 @@ struct rtnl_link_stats { __u32 rx_compressed; __u32 tx_compressed; - __u32 rx_nohandler; /* dropped, no handler found */ + __u32 rx_nohandler; }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +242,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ @@ -170,12 +340,29 @@ enum { IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, + + /* device (sysfs) name as parent, used instead + * of IFLA_LINK where there's no parent netdev + */ + IFLA_PARENT_DEV_NAME, + IFLA_PARENT_DEV_BUS_NAME, + __IFLA_MAX }; #define IFLA_MAX (__IFLA_MAX - 1) +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + /* backwards compatibility for userspace */ #ifndef __KERNEL__ #define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) @@ -293,6 +480,7 @@ enum { IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, + IFLA_BR_MCAST_QUERIER_STATE, __IFLA_BR_MAX, }; @@ -346,6 +534,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -433,6 +623,7 @@ enum macvlan_macaddr_mode { }; #define MACVLAN_FLAG_NOPROMISC 1 +#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */ /* VRF section */ enum { @@ -597,6 +788,18 @@ enum ifla_geneve_df { GENEVE_DF_MAX = __GENEVE_DF_END - 1, }; +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + /* PPP section */ enum { IFLA_PPP_UNSPEC, @@ -655,6 +858,7 @@ enum { IFLA_BOND_TLB_DYNAMIC_LB, IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, + IFLA_BOND_MISSED_MAX, __IFLA_BOND_MAX, }; @@ -899,7 +1103,14 @@ enum { #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) -/* HSR section */ +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; enum { IFLA_HSR_UNSPEC, @@ -909,6 +1120,9 @@ enum { IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ IFLA_HSR_SEQ_NR, IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ __IFLA_HSR_MAX, }; @@ -1033,6 +1247,8 @@ enum { #define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5) enum { IFLA_RMNET_UNSPEC, @@ -1048,4 +1264,14 @@ struct ifla_rmnet_flags { __u32 mask; }; +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index a067410ebea5..1daa45268de2 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -269,6 +269,7 @@ struct kvm_xen_exit { #define KVM_EXIT_AP_RESET_HOLD 32 #define KVM_EXIT_X86_BUS_LOCK 33 #define KVM_EXIT_XEN 34 +#define KVM_EXIT_RISCV_SBI 35 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -397,13 +398,23 @@ struct kvm_run { * "ndata" is correct, that new fields are enumerated in "flags", * and that each flag enumerates fields that are 64-bit aligned * and sized (so that ndata+internal.data[] is valid/accurate). + * + * Space beyond the defined fields may be used to store arbitrary + * debug information relating to the emulation failure. It is + * accounted for in "ndata" but the format is unspecified and is + * not represented in "flags". Any such information is *not* ABI! */ struct { __u32 suberror; __u32 ndata; __u64 flags; - __u8 insn_size; - __u8 insn_bytes[15]; + union { + struct { + __u8 insn_size; + __u8 insn_bytes[15]; + }; + }; + /* Arbitrary debug data may follow. */ } emulation_failure; /* KVM_EXIT_OSI */ struct { @@ -469,6 +480,13 @@ struct kvm_run { } msr; /* KVM_EXIT_XEN */ struct kvm_xen_exit xen; + /* KVM_EXIT_RISCV_SBI */ + struct { + unsigned long extension_id; + unsigned long function_id; + unsigned long args[6]; + unsigned long ret[2]; + } riscv_sbi; /* Fix the size of the union. */ char padding[256]; }; @@ -1112,6 +1130,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_BINARY_STATS_FD 203 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #define KVM_CAP_ARM_MTE 205 +#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 #ifdef KVM_CAP_IRQ_ROUTING @@ -1223,11 +1242,16 @@ struct kvm_irqfd { /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ #define KVM_CLOCK_TSC_STABLE 2 +#define KVM_CLOCK_REALTIME (1 << 2) +#define KVM_CLOCK_HOST_TSC (1 << 3) struct kvm_clock_data { __u64 clock; __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; /* For KVM_CAP_SW_TLB */ diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index de45fcd2dcbe..bb73e9a0b24f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -268,5 +268,8 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ # define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ # define PR_SCHED_CORE_MAX 4 +# define PR_SCHED_CORE_SCOPE_THREAD 0 +# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 +# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 5859ca0a1439..5fbb79e30819 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -1002,7 +1002,7 @@ 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 */ -// (1 << 3) is unused. +/* (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) diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index 9dd5f76692ef..223308931d55 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -49,8 +49,8 @@ struct bpf_gen { int nr_fd_array; }; -void bpf_gen__init(struct bpf_gen *gen, int log_level); -int bpf_gen__finish(struct bpf_gen *gen); +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps); +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps); void bpf_gen__free(struct bpf_gen *gen); void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); void bpf_gen__map_create(struct bpf_gen *gen, diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 21dfb930f1d2..8ed02e89c9a9 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -18,7 +18,7 @@ #define MAX_USED_MAPS 64 #define MAX_USED_PROGS 32 #define MAX_KFUNC_DESCS 256 -#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS) +#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS) /* The following structure describes the stack layout of the loader program. * In addition R6 contains the pointer to context. @@ -33,8 +33,8 @@ */ struct loader_stack { __u32 btf_fd; - __u32 prog_fd[MAX_USED_PROGS]; __u32 inner_map_fd; + __u32 prog_fd[MAX_USED_PROGS]; }; #define stack_off(field) \ @@ -42,6 +42,11 @@ struct loader_stack { #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field)) +static int blob_fd_array_off(struct bpf_gen *gen, int index) +{ + return gen->fd_array + index * sizeof(int); +} + static int realloc_insn_buf(struct bpf_gen *gen, __u32 size) { size_t off = gen->insn_cur - gen->insn_start; @@ -102,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in emit(gen, insn2); } -void bpf_gen__init(struct bpf_gen *gen, int log_level) +static int add_data(struct bpf_gen *gen, const void *data, __u32 size); +static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off); + +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps) { - size_t stack_sz = sizeof(struct loader_stack); + size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz; int i; + gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); gen->log_level = log_level; /* save ctx pointer into R6 */ emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1)); @@ -118,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level) emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); + /* amount of stack actually used, only used to calculate iterations, not stack offset */ + nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]); /* jump over cleanup code */ emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, - /* size of cleanup code below */ - (stack_sz / 4) * 3 + 2)); + /* size of cleanup code below (including map fd cleanup) */ + (nr_progs_sz / 4) * 3 + 2 + + /* 6 insns for emit_sys_close_blob, + * 6 insns for debug_regs in emit_sys_close_blob + */ + nr_maps * (6 + (gen->log_level ? 6 : 0)))); /* remember the label where all error branches will jump to */ gen->cleanup_label = gen->insn_cur - gen->insn_start; /* emit cleanup code: close all temp FDs */ - for (i = 0; i < stack_sz; i += 4) { + for (i = 0; i < nr_progs_sz; i += 4) { emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i)); emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); } + for (i = 0; i < nr_maps; i++) + emit_sys_close_blob(gen, blob_fd_array_off(gen, i)); /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); emit(gen, BPF_EXIT_INSN()); @@ -160,8 +177,6 @@ static int add_data(struct bpf_gen *gen, const void *data, __u32 size) */ static int add_map_fd(struct bpf_gen *gen) { - if (!gen->fd_array) - gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); if (gen->nr_maps == MAX_USED_MAPS) { pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS); gen->error = -E2BIG; @@ -174,8 +189,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen) { int cur; - if (!gen->fd_array) - gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); if (gen->nr_fd_array == MAX_KFUNC_DESCS) { cur = add_data(gen, NULL, sizeof(int)); return (cur - gen->fd_array) / sizeof(int); @@ -183,11 +196,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen) return MAX_USED_MAPS + gen->nr_fd_array++; } -static int blob_fd_array_off(struct bpf_gen *gen, int index) -{ - return gen->fd_array + index * sizeof(int); -} - static int insn_bytes_to_bpf_size(__u32 sz) { switch (sz) { @@ -359,10 +367,15 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) __emit_sys_close(gen); } -int bpf_gen__finish(struct bpf_gen *gen) +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) { int i; + if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) { + pr_warn("progs/maps mismatch\n"); + gen->error = -EFAULT; + return gen->error; + } emit_sys_close_stack(gen, stack_off(btf_fd)); for (i = 0; i < gen->nr_progs; i++) move_stack2ctx(gen, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d027e1d620fc..902f1ad5b7e6 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7477,7 +7477,7 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch } if (obj->gen_loader) - bpf_gen__init(obj->gen_loader, extra_log_level); + bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); @@ -7497,7 +7497,7 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch for (i = 0; i < obj->nr_maps; i++) obj->maps[i].fd = -1; if (!err) - err = bpf_gen__finish(obj->gen_loader); + err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); } /* clean up fd_array */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index add39902166d..21735829b860 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3310,6 +3310,9 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio if (!insn->func) return false; + if (insn->func->static_call_tramp) + return true; + /* * CONFIG_UBSAN_TRAP inserts a UD2 when it sees * __builtin_unreachable(). The BUG() macro has an unreachable() after diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 81a4c543ff7e..4b384c907027 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -375,6 +375,7 @@ static int read_symbols(struct elf *elf) return -1; } memset(sym, 0, sizeof(*sym)); + INIT_LIST_HEAD(&sym->pv_target); sym->alias = sym; sym->idx = i; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index c90c7084e45a..bdf699f6552b 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -153,6 +153,10 @@ void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) !strcmp(func->name, "_paravirt_ident_64")) return; + /* already added this function */ + if (!list_empty(&func->pv_target)) + return; + list_add(&func->pv_target, &f->pv_ops[idx].targets); f->pv_ops[idx].clean = false; } diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 2d7df8703cf2..3cf7bac67239 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -469,7 +469,7 @@ This option sets the time out limit. The default value is 500 ms. --switch-events:: Record context switch events i.e. events of type PERF_RECORD_SWITCH or -PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT or CoreSight) +PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE) switch events will be enabled automatically, which can be suppressed by by the option --no-switch-events. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 07e65a061fd3..3df74cf5651a 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -271,8 +271,6 @@ endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) -FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) -FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) FEATURE_CHECK_LDFLAGS-libaio = -lrt @@ -1010,6 +1008,9 @@ ifndef NO_AUXTRACE ifndef NO_AUXTRACE $(call detected,CONFIG_AUXTRACE) CFLAGS += -DHAVE_AUXTRACE_SUPPORT + ifeq ($(feature-reallocarray), 0) + CFLAGS += -DCOMPAT_NEED_REALLOCARRAY + endif endif endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 0777748b6da8..80522bcfafe0 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -516,17 +516,17 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl) $(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@ -socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c -socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh +socket_arrays := $(beauty_outdir)/socket.c +socket_tbl := $(srctree)/tools/perf/trace/beauty/socket.sh -$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl) - $(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@ +$(socket_arrays): $(linux_uapi_dir)/in.h $(beauty_linux_dir)/socket.h $(socket_tbl) + $(Q)$(SHELL) '$(socket_tbl)' $(linux_uapi_dir) $(beauty_linux_dir) > $@ -socket_arrays := $(beauty_outdir)/socket_arrays.c -socket_tbl := $(srctree)/tools/perf/trace/beauty/socket.sh +sockaddr_arrays := $(beauty_outdir)/sockaddr.c +sockaddr_tbl := $(srctree)/tools/perf/trace/beauty/sockaddr.sh -$(socket_arrays): $(beauty_linux_dir)/socket.h $(socket_tbl) - $(Q)$(SHELL) '$(socket_tbl)' $(beauty_linux_dir) > $@ +$(sockaddr_arrays): $(beauty_linux_dir)/socket.h $(sockaddr_tbl) + $(Q)$(SHELL) '$(sockaddr_tbl)' $(beauty_linux_dir) > $@ vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux @@ -736,8 +736,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(sndrv_ctl_ioctl_array) \ $(kcmp_type_array) \ $(kvm_ioctl_array) \ - $(socket_ipproto_array) \ $(socket_arrays) \ + $(sockaddr_arrays) \ $(vhost_virtio_ioctl_array) \ $(madvise_behavior_array) \ $(mmap_flags_array) \ @@ -1113,8 +1113,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(sndrv_pcm_ioctl_array) \ $(OUTPUT)$(kvm_ioctl_array) \ $(OUTPUT)$(kcmp_type_array) \ - $(OUTPUT)$(socket_ipproto_array) \ $(OUTPUT)$(socket_arrays) \ + $(OUTPUT)$(sockaddr_arrays) \ $(OUTPUT)$(vhost_virtio_ioctl_array) \ $(OUTPUT)$(perf_ioctl_array) \ $(OUTPUT)$(prctl_option_array) \ diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/arm/include/arch-tests.h +++ b/tools/perf/arch/arm/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c index 6848101a855f..69561111cc6f 100644 --- a/tools/perf/arch/arm/tests/arch-tests.c +++ b/tools/perf/arch/arm/tests/arch-tests.c @@ -3,18 +3,10 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { +struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "DWARF unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .desc = "Vectors page", - .func = test__vectors_page, - }, - { - .func = NULL, - }, + &suite__vectors_page, + NULL, }; diff --git a/tools/perf/arch/arm/tests/vectors-page.c b/tools/perf/arch/arm/tests/vectors-page.c index 7ffdd79971c8..55a835837466 100644 --- a/tools/perf/arch/arm/tests/vectors-page.c +++ b/tools/perf/arch/arm/tests/vectors-page.c @@ -9,8 +9,7 @@ #define VECTORS__MAP_NAME "[vectors]" -int test__vectors_page(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__vectors_page(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { void *start, *end; @@ -22,3 +21,5 @@ int test__vectors_page(struct test *test __maybe_unused, return TEST_OK; } + +DEFINE_SUITE("Vectors page", vectors_page); diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/arm64/include/arch-tests.h +++ b/tools/perf/arch/arm64/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c index 5b1543c98022..ad16b4f8f63e 100644 --- a/tools/perf/arch/arm64/tests/arch-tests.c +++ b/tools/perf/arch/arm64/tests/arch-tests.c @@ -3,14 +3,9 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { +struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "DWARF unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .func = NULL, - }, + NULL, }; diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index a4420d4df503..2100d46ccf5e 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -23,6 +23,7 @@ #include "../../../util/auxtrace.h" #include "../../../util/record.h" #include "../../../util/arm-spe.h" +#include <tools/libc_compat.h> // reallocarray #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -31,6 +32,8 @@ struct arm_spe_recording { struct auxtrace_record itr; struct perf_pmu *arm_spe_pmu; struct evlist *evlist; + int wrapped_cnt; + bool *wrapped; }; static void arm_spe_set_timestamp(struct auxtrace_record *itr, @@ -84,6 +87,55 @@ static int arm_spe_info_fill(struct auxtrace_record *itr, return 0; } +static void +arm_spe_snapshot_resolve_auxtrace_defaults(struct record_opts *opts, + bool privileged) +{ + /* + * The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size nor + * snapshot size is specified, then the default is 4MiB for privileged users, 128KiB for + * unprivileged users. + * + * The default auxtrace mmap size is 4MiB/page_size for privileged users, 128KiB for + * unprivileged users. If an unprivileged user does not specify mmap pages, the mmap pages + * will be reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the + * user is likely to get an error as they exceed their mlock limmit. + */ + + /* + * No size were given to '-S' or '-m,', so go with the default + */ + if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(4) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } else if (!opts->auxtrace_mmap_pages && !privileged && opts->mmap_pages == UINT_MAX) { + opts->mmap_pages = KiB(256) / page_size; + } + + /* + * '-m,xyz' was specified but no snapshot size, so make the snapshot size as big as the + * auxtrace mmap area. + */ + if (!opts->auxtrace_snapshot_size) + opts->auxtrace_snapshot_size = opts->auxtrace_mmap_pages * (size_t)page_size; + + /* + * '-Sxyz' was specified but no auxtrace mmap area, so make the auxtrace mmap area big + * enough to fit the requested snapshot size. + */ + if (!opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_snapshot_size; + + sz = round_up(sz, page_size) / page_size; + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); + } +} + static int arm_spe_recording_options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts) @@ -115,6 +167,36 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, if (!opts->full_auxtrace) return 0; + /* + * we are in snapshot mode. + */ + if (opts->auxtrace_snapshot_mode) { + /* + * Command arguments '-Sxyz' and/or '-m,xyz' are missing, so fill those in with + * default values. + */ + if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) + arm_spe_snapshot_resolve_auxtrace_defaults(opts, privileged); + + /* + * Snapshot size can't be bigger than the auxtrace area. + */ + if (opts->auxtrace_snapshot_size > opts->auxtrace_mmap_pages * (size_t)page_size) { + pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n", + opts->auxtrace_snapshot_size, + opts->auxtrace_mmap_pages * (size_t)page_size); + return -EINVAL; + } + + /* + * Something went wrong somewhere - this shouldn't happen. + */ + if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) { + pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n"); + return -EINVAL; + } + } + /* We are in full trace mode but '-m,xyz' wasn't specified */ if (!opts->auxtrace_mmap_pages) { if (privileged) { @@ -138,6 +220,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, } } + if (opts->auxtrace_snapshot_mode) + pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME, + opts->auxtrace_snapshot_size); /* * To obtain the auxtrace buffer file descriptor, the auxtrace event @@ -166,8 +251,199 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, tracking_evsel->core.attr.sample_period = 1; /* In per-cpu case, always need the time of mmap events etc */ - if (!perf_cpu_map__empty(cpus)) + if (!perf_cpu_map__empty(cpus)) { evsel__set_sample_bit(tracking_evsel, TIME); + evsel__set_sample_bit(tracking_evsel, CPU); + + /* also track task context switch */ + if (!record_opts__no_switch_events(opts)) + tracking_evsel->core.attr.context_switch = 1; + } + + return 0; +} + +static int arm_spe_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused, + struct record_opts *opts, + const char *str) +{ + unsigned long long snapshot_size = 0; + char *endptr; + + if (str) { + snapshot_size = strtoull(str, &endptr, 0); + if (*endptr || snapshot_size > SIZE_MAX) + return -1; + } + + opts->auxtrace_snapshot_mode = true; + opts->auxtrace_snapshot_size = snapshot_size; + + return 0; +} + +static int arm_spe_snapshot_start(struct auxtrace_record *itr) +{ + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_recording, itr); + struct evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->core.attr.type == ptr->arm_spe_pmu->type) + return evsel__disable(evsel); + } + return -EINVAL; +} + +static int arm_spe_snapshot_finish(struct auxtrace_record *itr) +{ + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_recording, itr); + struct evsel *evsel; + + evlist__for_each_entry(ptr->evlist, evsel) { + if (evsel->core.attr.type == ptr->arm_spe_pmu->type) + return evsel__enable(evsel); + } + return -EINVAL; +} + +static int arm_spe_alloc_wrapped_array(struct arm_spe_recording *ptr, int idx) +{ + bool *wrapped; + int cnt = ptr->wrapped_cnt, new_cnt, i; + + /* + * No need to allocate, so return early. + */ + if (idx < cnt) + return 0; + + /* + * Make ptr->wrapped as big as idx. + */ + new_cnt = idx + 1; + + /* + * Free'ed in arm_spe_recording_free(). + */ + wrapped = reallocarray(ptr->wrapped, new_cnt, sizeof(bool)); + if (!wrapped) + return -ENOMEM; + + /* + * init new allocated values. + */ + for (i = cnt; i < new_cnt; i++) + wrapped[i] = false; + + ptr->wrapped_cnt = new_cnt; + ptr->wrapped = wrapped; + + return 0; +} + +static bool arm_spe_buffer_has_wrapped(unsigned char *buffer, + size_t buffer_size, u64 head) +{ + u64 i, watermark; + u64 *buf = (u64 *)buffer; + size_t buf_size = buffer_size; + + /* + * Defensively handle the case where head might be continually increasing - if its value is + * equal or greater than the size of the ring buffer, then we can safely determine it has + * wrapped around. Otherwise, continue to detect if head might have wrapped. + */ + if (head >= buffer_size) + return true; + + /* + * We want to look the very last 512 byte (chosen arbitrarily) in the ring buffer. + */ + watermark = buf_size - 512; + + /* + * The value of head is somewhere within the size of the ring buffer. This can be that there + * hasn't been enough data to fill the ring buffer yet or the trace time was so long that + * head has numerically wrapped around. To find we need to check if we have data at the + * very end of the ring buffer. We can reliably do this because mmap'ed pages are zeroed + * out and there is a fresh mapping with every new session. + */ + + /* + * head is less than 512 byte from the end of the ring buffer. + */ + if (head > watermark) + watermark = head; + + /* + * Speed things up by using 64 bit transactions (see "u64 *buf" above) + */ + watermark /= sizeof(u64); + buf_size /= sizeof(u64); + + /* + * If we find trace data at the end of the ring buffer, head has been there and has + * numerically wrapped around at least once. + */ + for (i = watermark; i < buf_size; i++) + if (buf[i]) + return true; + + return false; +} + +static int arm_spe_find_snapshot(struct auxtrace_record *itr, int idx, + struct auxtrace_mmap *mm, unsigned char *data, + u64 *head, u64 *old) +{ + int err; + bool wrapped; + struct arm_spe_recording *ptr = + container_of(itr, struct arm_spe_recording, itr); + + /* + * Allocate memory to keep track of wrapping if this is the first + * time we deal with this *mm. + */ + if (idx >= ptr->wrapped_cnt) { + err = arm_spe_alloc_wrapped_array(ptr, idx); + if (err) + return err; + } + + /* + * Check to see if *head has wrapped around. If it hasn't only the + * amount of data between *head and *old is snapshot'ed to avoid + * bloating the perf.data file with zeros. But as soon as *head has + * wrapped around the entire size of the AUX ring buffer it taken. + */ + wrapped = ptr->wrapped[idx]; + if (!wrapped && arm_spe_buffer_has_wrapped(data, mm->len, *head)) { + wrapped = true; + ptr->wrapped[idx] = true; + } + + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", + __func__, idx, (size_t)*old, (size_t)*head, mm->len); + + /* + * No wrap has occurred, we can just use *head and *old. + */ + if (!wrapped) + return 0; + + /* + * *head has wrapped around - adjust *head and *old to pickup the + * entire content of the AUX buffer. + */ + if (*head >= mm->len) { + *old = *head - mm->len; + } else { + *head += mm->len; + *old = *head - mm->len; + } return 0; } @@ -186,6 +462,7 @@ static void arm_spe_recording_free(struct auxtrace_record *itr) struct arm_spe_recording *sper = container_of(itr, struct arm_spe_recording, itr); + free(sper->wrapped); free(sper); } @@ -207,6 +484,10 @@ struct auxtrace_record *arm_spe_recording_init(int *err, sper->arm_spe_pmu = arm_spe_pmu; sper->itr.pmu = arm_spe_pmu; + sper->itr.snapshot_start = arm_spe_snapshot_start; + sper->itr.snapshot_finish = arm_spe_snapshot_finish; + sper->itr.find_snapshot = arm_spe_find_snapshot; + sper->itr.parse_snapshot_options = arm_spe_parse_snapshot_options; sper->itr.recording_options = arm_spe_recording_options; sper->itr.info_priv_size = arm_spe_info_priv_size; sper->itr.info_fill = arm_spe_info_fill; diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 1ca7bc337932..e2c481fcede6 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -363,3 +363,4 @@ 446 n64 landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 n64 process_mrelease sys_process_mrelease +449 n64 futex_waitv sys_futex_waitv diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 7bef917cc84e..15109af9d075 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -528,3 +528,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h index c62538052404..452b3d904521 100644 --- a/tools/perf/arch/powerpc/include/arch-tests.h +++ b/tools/perf/arch/powerpc/include/arch-tests.h @@ -2,6 +2,6 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c index 8c3fbd4af817..eb98c57b5aeb 100644 --- a/tools/perf/arch/powerpc/tests/arch-tests.c +++ b/tools/perf/arch/powerpc/tests/arch-tests.c @@ -3,14 +3,10 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { + +struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "Test dwarf unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif - { - .func = NULL, - }, + NULL, }; diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index df5261e5cfe1..ed9c5c2eafad 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv sys_futex_waitv diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 18b5500ea8bf..fe8f8dd157b4 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -370,6 +370,7 @@ 446 common landlock_restrict_self sys_landlock_restrict_self 447 common memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 9599e7a3f1af..6a1a1b3c0827 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -2,15 +2,15 @@ #ifndef ARCH_TESTS_H #define ARCH_TESTS_H -struct test; +struct test_suite; /* Tests */ -int test__rdpmc(struct test *test, int subtest); -int test__insn_x86(struct test *test, int subtest); -int test__intel_pt_pkt_decoder(struct test *test, int subtest); -int test__bp_modify(struct test *test, int subtest); -int test__x86_sample_parsing(struct test *test, int subtest); +int test__rdpmc(struct test_suite *test, int subtest); +int test__insn_x86(struct test_suite *test, int subtest); +int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest); +int test__bp_modify(struct test_suite *test, int subtest); +int test__x86_sample_parsing(struct test_suite *test, int subtest); -extern struct test arch_tests[]; +extern struct test_suite *arch_tests[]; #endif diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index 71aa67367ad6..64fb73d14d2f 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -3,39 +3,28 @@ #include "tests/tests.h" #include "arch-tests.h" -struct test arch_tests[] = { - { - .desc = "x86 rdpmc", - .func = test__rdpmc, - }, +DEFINE_SUITE("x86 rdpmc", rdpmc); +#ifdef HAVE_AUXTRACE_SUPPORT +DEFINE_SUITE("x86 instruction decoder - new instructions", insn_x86); +DEFINE_SUITE("Intel PT packet decoder", intel_pt_pkt_decoder); +#endif +#if defined(__x86_64__) +DEFINE_SUITE("x86 bp modify", bp_modify); +#endif +DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing); + +struct test_suite *arch_tests[] = { + &suite__rdpmc, #ifdef HAVE_DWARF_UNWIND_SUPPORT - { - .desc = "DWARF unwind", - .func = test__dwarf_unwind, - }, + &suite__dwarf_unwind, #endif #ifdef HAVE_AUXTRACE_SUPPORT - { - .desc = "x86 instruction decoder - new instructions", - .func = test__insn_x86, - }, - { - .desc = "Intel PT packet decoder", - .func = test__intel_pt_pkt_decoder, - }, + &suite__insn_x86, + &suite__intel_pt_pkt_decoder, #endif #if defined(__x86_64__) - { - .desc = "x86 bp modify", - .func = test__bp_modify, - }, + &suite__bp_modify, #endif - { - .desc = "x86 Sample parsing", - .func = test__x86_sample_parsing, - }, - { - .func = NULL, - }, - + &suite__x86_sample_parsing, + NULL, }; diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c index dffcf9b52153..0924ccd9e36d 100644 --- a/tools/perf/arch/x86/tests/bp-modify.c +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -204,7 +204,7 @@ out: return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; } -int test__bp_modify(struct test *test __maybe_unused, +int test__bp_modify(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index 0262b0d8ccf5..94b490c434d0 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -173,7 +173,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64) * verbose (-v) option to see all the instructions and whether or not they * decoded successfully. */ -int test__insn_x86(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__insn_x86(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = 0; diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 27dd8cf9e060..cb5b2c6c3b3b 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -37,7 +37,7 @@ static pid_t spawn(void) * the last read counter value to avoid triggering a WARN_ON_ONCE() in * smp_call_function_many() caused by sending IPIs from NMI context. */ -int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__intel_cqm_count_nmi_context(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct evlist *evlist = NULL; struct evsel *evsel = NULL; diff --git a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c index c933e3dcd0a8..2fc882ab24c1 100644 --- a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c +++ b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c @@ -289,7 +289,7 @@ static int test_one(struct test_data *d) * This test feeds byte sequences to the Intel PT packet decoder and checks the * results. Changes to the packet context are also checked. */ -int test__intel_pt_pkt_decoder(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__intel_pt_pkt_decoder(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct test_data *d = data; int ret; diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c index 1ea916656a2d..498413ad9c97 100644 --- a/tools/perf/arch/x86/tests/rdpmc.c +++ b/tools/perf/arch/x86/tests/rdpmc.c @@ -157,7 +157,7 @@ out_close: return 0; } -int test__rdpmc(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__rdpmc(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int status = 0; int wret = 0; diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c index c92db87e4479..bfbd3662b69e 100644 --- a/tools/perf/arch/x86/tests/sample-parsing.c +++ b/tools/perf/arch/x86/tests/sample-parsing.c @@ -115,7 +115,7 @@ out_free: * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type. * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type. */ -int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) +int test__x86_sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { return do_test(PERF_SAMPLE_WEIGHT_STRUCT); } diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 5d1fe9c35807..137890f78e17 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -233,6 +233,7 @@ int bench_futex_lock_pi(int argc, const char **argv) print_summary(); free(worker); + perf_cpu_map__put(cpu); return ret; err: usage_with_options(bench_futex_lock_pi_usage, options); diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 97fe31fd3a23..f7a5ffebb940 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -294,6 +294,7 @@ int bench_futex_requeue(int argc, const char **argv) print_summary(); free(worker); + perf_cpu_map__put(cpu); return ret; err: usage_with_options(bench_futex_requeue_usage, options); diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index e970e6b9ad53..0983f40b4b40 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -329,6 +329,7 @@ int bench_futex_wake_parallel(int argc, const char **argv) print_summary(); free(blocked_worker); + perf_cpu_map__put(cpu); return ret; } #endif /* HAVE_PTHREAD_BARRIER */ diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 77f058a47790..2226a475e782 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -222,5 +222,6 @@ int bench_futex_wake(int argc, const char **argv) print_summary(); free(worker); + perf_cpu_map__put(cpu); return ret; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index bc5259db5fd9..b9d6306cc14e 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -820,7 +820,7 @@ static int __cmd_inject(struct perf_inject *inject) inject->tool.ordered_events = true; inject->tool.ordering_requires_timestamps = true; /* Allow space in the header for new attributes */ - output_data_offset = 4096; + output_data_offset = roundup(8192 + session->header.data_offset, 4096); if (inject->strip) strip_init(inject); } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 8167ebfe776a..8ae400429870 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -619,14 +619,17 @@ static int report__browse_hists(struct report *rep) int ret; struct perf_session *session = rep->session; struct evlist *evlist = session->evlist; - const char *help = perf_tip(system_path(TIPDIR)); + char *help = NULL, *path = NULL; - if (help == NULL) { + path = system_path(TIPDIR); + if (perf_tip(&help, path) || help == NULL) { /* fallback for people who don't install perf ;-) */ - help = perf_tip(DOCDIR); - if (help == NULL) - help = "Cannot load tips.txt file, please install perf!"; + free(path); + path = system_path(DOCDIR); + if (perf_tip(&help, path) || help == NULL) + help = strdup("Cannot load tips.txt file, please install perf!"); } + free(path); switch (use_browser) { case 1: @@ -651,7 +654,7 @@ static int report__browse_hists(struct report *rep) ret = evlist__tty_browse_hists(evlist, rep, help); break; } - + free(help); return ret; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 624ea12ce5ca..0b52e08e558e 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -979,6 +979,8 @@ static struct syscall_fmt syscall_fmts[] = { .arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, }, { .name = "getrlimit", .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, + { .name = "getsockopt", + .arg = { [1] = STRARRAY(level, socket_level), }, }, { .name = "gettid", .errpid = true, }, { .name = "ioctl", .arg = { @@ -1121,6 +1123,8 @@ static struct syscall_fmt syscall_fmts[] = { .arg = { [0] = STRARRAY(which, itimers), }, }, { .name = "setrlimit", .arg = { [0] = STRARRAY(resource, rlimit_resources), }, }, + { .name = "setsockopt", + .arg = { [1] = STRARRAY(level, socket_level), }, }, { .name = "socket", .arg = { [0] = STRARRAY(family, socket_families), [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, diff --git a/tools/perf/design.txt b/tools/perf/design.txt index a42fab308ff6..aa8cfeabb743 100644 --- a/tools/perf/design.txt +++ b/tools/perf/design.txt @@ -106,6 +106,9 @@ enum perf_hw_id { PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, PERF_COUNT_HW_BRANCH_MISSES = 5, PERF_COUNT_HW_BUS_CYCLES = 6, + PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7, + PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8, + PERF_COUNT_HW_REF_CPU_CYCLES = 9, }; These are standardized types of events that work relatively uniformly diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json new file mode 100644 index 000000000000..b57526fa44f2 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json @@ -0,0 +1,676 @@ +[ + { + "BriefDescription": "Percentage of cycles that are run cycles", + "MetricExpr": "PM_RUN_CYC / PM_CYC * 100", + "MetricGroup": "General", + "MetricName": "RUN_CYCLES_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average cycles per completed instruction", + "MetricExpr": "PM_CYC / PM_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "CYCLES_PER_INSTRUCTION" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled for any reason", + "MetricExpr": "PM_DISP_STALL_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because there was a flush", + "MetricExpr": "PM_DISP_STALL_FLUSH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_FLUSH_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because the MMU was handling a translation miss", + "MetricExpr": "PM_DISP_STALL_TRANSLATION / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_TRANSLATION_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction ERAT miss", + "MetricExpr": "PM_DISP_STALL_IERAT_ONLY_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IERAT_ONLY_MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction TLB miss", + "MetricExpr": "PM_DISP_STALL_ITLB_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_ITLB_MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss", + "MetricExpr": "PM_DISP_STALL_IC_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IC_MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L2", + "MetricExpr": "PM_DISP_STALL_IC_L2 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IC_L2_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L3", + "MetricExpr": "PM_DISP_STALL_IC_L3 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IC_L3_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from any source beyond the local L3", + "MetricExpr": "PM_DISP_STALL_IC_L3MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_IC_L3MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss after a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED_ICMISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_ICMISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L2 after suffering a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L2 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_IC_L2_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L3 after suffering a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_IC_L3_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from any source beyond the local L3 after suffering a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_IC_L3MISS_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to a branch mispredict", + "MetricExpr": "PM_DISP_STALL_BR_MPRED / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_BR_MPRED_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any reason", + "MetricExpr": "PM_DISP_STALL_HELD_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch", + "MetricExpr": "PM_DISP_STALL_HELD_SYNC_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISP_HELD_STALL_SYNC_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch while waiting on the scoreboard", + "MetricExpr": "PM_DISP_STALL_HELD_SCOREBOARD_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISP_HELD_STALL_SCOREBOARD_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch due to issue queue full", + "MetricExpr": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISP_HELD_STALL_ISSQ_FULL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the mapper/SRB was full", + "MetricExpr": "PM_DISP_STALL_HELD_RENAME_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_RENAME_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the STF mapper/SRB was full", + "MetricExpr": "PM_DISP_STALL_HELD_STF_MAPPER_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_STF_MAPPER_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the XVFC mapper/SRB was full", + "MetricExpr": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_XVFC_MAPPER_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any other reason", + "MetricExpr": "PM_DISP_STALL_HELD_OTHER_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_OTHER_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction has been dispatched but not issued for any reason", + "MetricExpr": "PM_ISSUE_STALL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "ISSUE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting to be finished in one of the execution units", + "MetricExpr": "PM_EXEC_STALL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "EXECUTION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction spent executing an NTC instruction that gets flushed some time after dispatch", + "MetricExpr": "PM_EXEC_STALL_NTC_FLUSH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "NTC_FLUSH_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTF instruction finishes at dispatch", + "MetricExpr": "PM_EXEC_STALL_FIN_AT_DISP / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "FIN_AT_DISP_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the branch unit", + "MetricExpr": "PM_EXEC_STALL_BRU / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "BRU_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a simple fixed point instruction that is executing in the LSU", + "MetricExpr": "PM_EXEC_STALL_SIMPLE_FX / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "SIMPLE_FX_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the VSU", + "MetricExpr": "PM_EXEC_STALL_VSU / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "VSU_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting to be finished in one of the execution units", + "MetricExpr": "PM_EXEC_STALL_TRANSLATION / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "TRANSLATION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a load or store that suffered a translation miss", + "MetricExpr": "PM_EXEC_STALL_DERAT_ONLY_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DERAT_ONLY_MISS_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is recovering from a TLB miss", + "MetricExpr": "PM_EXEC_STALL_DERAT_DTLB_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DERAT_DTLB_MISS_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the LSU", + "MetricExpr": "PM_EXEC_STALL_LSU / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "LSU_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a load that is executing in the LSU", + "MetricExpr": "PM_EXEC_STALL_LOAD / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "LOAD_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3", + "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L2L3_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3, with an RC dispatch conflict", + "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L2L3_CONFLICT_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3, without an RC dispatch conflict", + "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L2L3_NOCONFLICT_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a source beyond the local L2 and local L3", + "MetricExpr": "PM_EXEC_STALL_DMISS_L3MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L3MISS_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a neighbor chiplet's L2 or L3 in the same chip", + "MetricExpr": "PM_EXEC_STALL_DMISS_L21_L31 / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_L21_L31_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from L4, local memory or OpenCAPI chip", + "MetricExpr": "PM_EXEC_STALL_DMISS_LMEM / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_LMEM_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a remote chip (cache, L4, memory or OpenCAPI) in the same group", + "MetricExpr": "PM_EXEC_STALL_DMISS_OFF_CHIP / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_OFF_CHIP_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a distant chip (cache, L4, memory or OpenCAPI chip)", + "MetricExpr": "PM_EXEC_STALL_DMISS_OFF_NODE / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DMISS_OFF_NODE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing a TLBIEL instruction", + "MetricExpr": "PM_EXEC_STALL_TLBIEL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "TLBIEL_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is finishing a load after its data has been reloaded from a data source beyond the local L1, OR when the LSU is processing an L1-hit, OR when the NTF instruction merged with another load in the LMQ", + "MetricExpr": "PM_EXEC_STALL_LOAD_FINISH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "LOAD_FINISH_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a store that is executing in the LSU", + "MetricExpr": "PM_EXEC_STALL_STORE / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "STORE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is in the store unit outside of handling store misses or other special store operations", + "MetricExpr": "PM_EXEC_STALL_STORE_PIPE / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "STORE_PIPE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a store whose cache line was not resident in the L1 and had to wait for allocation of the missing line into the L1", + "MetricExpr": "PM_EXEC_STALL_STORE_MISS / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "STORE_MISS_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a TLBIE instruction waiting for a response from the L2", + "MetricExpr": "PM_EXEC_STALL_TLBIE / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "TLBIE_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing a PTESYNC instruction", + "MetricExpr": "PM_EXEC_STALL_PTESYNC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "PTESYNC_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction cannot complete because the thread was blocked", + "MetricExpr": "PM_CMPL_STALL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction cannot complete because it was interrupted by ANY exception", + "MetricExpr": "PM_CMPL_STALL_EXCEPTION / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "EXCEPTION_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is stuck at finish waiting for the non-speculative finish of either a STCX instruction waiting for its result or a load waiting for non-critical sectors of data and ECC", + "MetricExpr": "PM_CMPL_STALL_MEM_ECC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "MEM_ECC_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a STCX instruction waiting for resolution from the nest", + "MetricExpr": "PM_CMPL_STALL_STCX / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "STCX_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a LWSYNC instruction waiting to complete", + "MetricExpr": "PM_CMPL_STALL_LWSYNC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "LWSYNC_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a HWSYNC instruction stuck at finish waiting for a response from the L2", + "MetricExpr": "PM_CMPL_STALL_HWSYNC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "HWSYNC_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction required special handling before completion", + "MetricExpr": "PM_CMPL_STALL_SPECIAL / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "SPECIAL_COMPLETION_STALL_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because fetch was being held, so there was nothing in the pipeline for this thread", + "MetricExpr": "PM_DISP_STALL_FETCH / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_FETCH_CPI" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of power management", + "MetricExpr": "PM_DISP_STALL_HELD_HALT_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "CPI", + "MetricName": "DISPATCHED_HELD_HALT_CPI" + }, + { + "BriefDescription": "Percentage of flushes per completed instruction", + "MetricExpr": "PM_FLUSH / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Others", + "MetricName": "FLUSH_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of flushes due to a branch mispredict per completed instruction", + "MetricExpr": "PM_FLUSH_MPRED / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Others", + "MetricName": "BR_MPRED_FLUSH_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of branch mispredictions per completed instruction", + "MetricExpr": "PM_BR_MPRED_CMPL / PM_RUN_INST_CMPL", + "MetricGroup": "Others", + "MetricName": "BRANCH_MISPREDICTION_RATE" + }, + { + "BriefDescription": "Percentage of finished loads that missed in the L1", + "MetricExpr": "PM_LD_MISS_L1 / PM_LD_REF_L1 * 100", + "MetricGroup": "Others", + "MetricName": "L1_LD_MISS_RATIO", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions that were loads that missed the L1", + "MetricExpr": "PM_LD_MISS_L1 / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Others", + "MetricName": "L1_LD_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions when the DPTEG required for the load/store instruction in execution was missing from the TLB", + "MetricExpr": "PM_DTLB_MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Others", + "MetricName": "DTLB_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of completed instructions dispatched per instruction completed", + "MetricExpr": "PM_INST_DISP / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "DISPATCH_PER_INST_CMPL" + }, + { + "BriefDescription": "Percentage of completed instructions that were a demand load that did not hit in the L1 or L2", + "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "General", + "MetricName": "L2_LD_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions that were demand fetches that missed the L1 icache", + "MetricExpr": "PM_L1_ICACHE_MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Instruction_Misses", + "MetricName": "L1_INST_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions that were demand fetches that reloaded from beyond the L3 icache", + "MetricExpr": "PM_INST_FROM_L3MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "General", + "MetricName": "L3_INST_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of completed instructions per cycle", + "MetricExpr": "PM_INST_CMPL / PM_CYC", + "MetricGroup": "General", + "MetricName": "IPC" + }, + { + "BriefDescription": "Average number of cycles per completed instruction group", + "MetricExpr": "PM_CYC / PM_1PLUS_PPC_CMPL", + "MetricGroup": "General", + "MetricName": "CYCLES_PER_COMPLETED_INSTRUCTIONS_SET" + }, + { + "BriefDescription": "Percentage of cycles when at least 1 instruction dispatched", + "MetricExpr": "PM_1PLUS_PPC_DISP / PM_RUN_CYC * 100", + "MetricGroup": "General", + "MetricName": "CYCLES_ATLEAST_ONE_INST_DISPATCHED", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of finished loads per completed instruction", + "MetricExpr": "PM_LD_REF_L1 / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "LOADS_PER_INST" + }, + { + "BriefDescription": "Average number of finished stores per completed instruction", + "MetricExpr": "PM_ST_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "STORES_PER_INST" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded from beyond the L2 per completed instruction", + "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L2_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded from beyond the L3 per completed instruction", + "MetricExpr": "PM_DATA_FROM_L3MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L3_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of DERAT misses with 4k page size per completed instruction", + "MetricExpr": "PM_DERAT_MISS_4K / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_4K_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of DERAT misses with 64k page size per completed instruction", + "MetricExpr": "PM_DERAT_MISS_64K / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_64K_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of run cycles per completed instruction", + "MetricExpr": "PM_RUN_CYC / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "RUN_CPI" + }, + { + "BriefDescription": "Percentage of DERAT misses per completed instruction", + "MetricExpr": "PM_DERAT_MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of completed instructions per run cycle", + "MetricExpr": "PM_RUN_INST_CMPL / PM_RUN_CYC", + "MetricGroup": "General", + "MetricName": "RUN_IPC" + }, + { + "BriefDescription": "Average number of completed instructions per instruction group", + "MetricExpr": "PM_RUN_INST_CMPL / PM_1PLUS_PPC_CMPL", + "MetricGroup": "General", + "MetricName": "AVERAGE_COMPLETED_INSTRUCTION_SET_SIZE" + }, + { + "BriefDescription": "Average number of finished instructions per completed instructions", + "MetricExpr": "PM_INST_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "INST_FIN_PER_CMPL" + }, + { + "BriefDescription": "Average cycles per completed instruction when the NTF instruction is completing and the finish was overlooked", + "MetricExpr": "PM_EXEC_STALL_UNKNOWN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "EXEC_STALL_UNKOWN_CPI" + }, + { + "BriefDescription": "Percentage of finished branches that were taken", + "MetricExpr": "PM_BR_TAKEN_CMPL / PM_BR_FIN * 100", + "MetricGroup": "General", + "MetricName": "TAKEN_BRANCHES", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of completed instructions that were a demand load that did not hit in the L1, L2, or the L3", + "MetricExpr": "PM_DATA_FROM_L3MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "General", + "MetricName": "L3_LD_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Average number of finished branches per completed instruction", + "MetricExpr": "PM_BR_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "BRANCHES_PER_INST" + }, + { + "BriefDescription": "Average number of instructions finished in the LSU per completed instruction", + "MetricExpr": "PM_LSU_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "LSU_PER_INST" + }, + { + "BriefDescription": "Average number of instructions finished in the VSU per completed instruction", + "MetricExpr": "PM_VSU_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "VSU_PER_INST" + }, + { + "BriefDescription": "Average number of TLBIE instructions finished in the LSU per completed instruction", + "MetricExpr": "PM_TLBIE_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "TLBIE_PER_INST" + }, + { + "BriefDescription": "Average number of STCX instructions finshed per completed instruction", + "MetricExpr": "PM_STCX_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "STXC_PER_INST" + }, + { + "BriefDescription": "Average number of LARX instructions finshed per completed instruction", + "MetricExpr": "PM_LARX_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "LARX_PER_INST" + }, + { + "BriefDescription": "Average number of PTESYNC instructions finshed per completed instruction", + "MetricExpr": "PM_PTESYNC_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "PTESYNC_PER_INST" + }, + { + "BriefDescription": "Average number of simple fixed-point instructions finshed in the store unit per completed instruction", + "MetricExpr": "PM_FX_LSU_FIN / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "FX_PER_INST" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded the L1 cache", + "MetricExpr": "PM_LD_DEMAND_MISS_L1 / PM_LD_MISS_L1 * 100", + "MetricGroup": "General", + "MetricName": "DL1_MISS_RELOADS", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from beyond the local L2", + "MetricExpr": "PM_DATA_FROM_L2MISS / PM_LD_DEMAND_MISS_L1 * 100", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L2_MISS", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from beyond the local L3", + "MetricExpr": "PM_DATA_FROM_L3MISS / PM_LD_DEMAND_MISS_L1 * 100", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L3_MISS", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of cycles stalled due to the NTC instruction waiting for a load miss to resolve from a source beyond the local L2 and local L3", + "MetricExpr": "DMISS_L3MISS_STALL_CPI / RUN_CPI * 100", + "MetricGroup": "General", + "MetricName": "DCACHE_MISS_CPI", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of DERAT misses with 2M page size per completed instruction", + "MetricExpr": "PM_DERAT_MISS_2M / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_2M_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of DERAT misses with 16M page size per completed instruction", + "MetricExpr": "PM_DERAT_MISS_16M / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_16M_MISS_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "DERAT miss ratio for 4K page size", + "MetricExpr": "PM_DERAT_MISS_4K / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_4K_MISS_RATIO" + }, + { + "BriefDescription": "DERAT miss ratio for 2M page size", + "MetricExpr": "PM_DERAT_MISS_2M / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_2M_MISS_RATIO" + }, + { + "BriefDescription": "DERAT miss ratio for 16M page size", + "MetricExpr": "PM_DERAT_MISS_16M / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_16M_MISS_RATIO" + }, + { + "BriefDescription": "DERAT miss ratio for 64K page size", + "MetricExpr": "PM_DERAT_MISS_64K / PM_DERAT_MISS", + "MetricGroup": "Translation", + "MetricName": "DERAT_64K_MISS_RATIO" + }, + { + "BriefDescription": "Percentage of DERAT misses that resulted in TLB reloads", + "MetricExpr": "PM_DTLB_MISS / PM_DERAT_MISS * 100", + "MetricGroup": "Translation", + "MetricName": "DERAT_MISS_RELOAD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of icache misses that were reloaded from beyond the local L3", + "MetricExpr": "PM_INST_FROM_L3MISS / PM_L1_ICACHE_MISS * 100", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_L3_MISS", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of icache reloads from the beyond the L3 per completed instruction", + "MetricExpr": "PM_INST_FROM_L3MISS / PM_RUN_INST_CMPL * 100", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_L3_MISS_RATE", + "ScaleUnit": "1%" + } +] diff --git a/tools/perf/tests/api-io.c b/tools/perf/tests/api-io.c index 2ada86ad6084..e91cf2c127f1 100644 --- a/tools/perf/tests/api-io.c +++ b/tools/perf/tests/api-io.c @@ -289,8 +289,8 @@ static int test_get_dec(void) return ret; } -int test__api_io(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__api_io(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int ret = 0; @@ -302,3 +302,5 @@ int test__api_io(struct test *test __maybe_unused, ret = TEST_FAIL; return ret; } + +DEFINE_SUITE("Test api io", api_io); diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 9b40a25376ae..0f73e300f207 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -178,7 +178,7 @@ static int run_dir(const char *d, const char *perf) return system(cmd) ? TEST_FAIL : TEST_OK; } -int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__attr(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct stat st; char path_perf[PATH_MAX]; @@ -207,3 +207,5 @@ int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused) return TEST_SKIP; } + +DEFINE_SUITE("Setup struct perf_event_attr", attr); diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 7447a4478991..79a980b1e786 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -82,7 +82,7 @@ static int do_test(struct evlist *evlist, int mmap_pages, } -int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__backward_ring_buffer(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0; char pid[16], sbuf[STRERR_BUFSIZE]; @@ -167,3 +167,5 @@ out_delete_evlist: evlist__delete(evlist); return ret; } + +DEFINE_SUITE("Read backward ring buffer", backward_ring_buffer); diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c index 12b805efdca0..384856347236 100644 --- a/tools/perf/tests/bitmap.c +++ b/tools/perf/tests/bitmap.c @@ -40,7 +40,7 @@ static int test_bitmap(const char *str) return ret; } -int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bitmap_print(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to convert map", test_bitmap("1")); TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5")); @@ -51,3 +51,5 @@ int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to convert map", test_bitmap("1-10,12-20,22-30,32-40")); return 0; } + +DEFINE_SUITE("Print bitmap", bitmap_print); diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c index 489b50604cf2..d1ebb5561e5b 100644 --- a/tools/perf/tests/bp_account.c +++ b/tools/perf/tests/bp_account.c @@ -19,6 +19,19 @@ #include "../perf-sys.h" #include "cloexec.h" +/* + * PowerPC and S390 do not support creation of instruction breakpoints using the + * perf_event interface. + * + * Just disable the test for these architectures until these issues are + * resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) +#define BP_ACCOUNT_IS_SUPPORTED 0 +#else +#define BP_ACCOUNT_IS_SUPPORTED 1 +#endif + static volatile long the_var; static noinline int test_function(void) @@ -173,13 +186,18 @@ static int detect_share(int wp_cnt, int bp_cnt) * we create another watchpoint to ensure * the slot accounting is correct */ -int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_accounting(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int has_ioctl = detect_ioctl(); int wp_cnt = detect_cnt(false); int bp_cnt = detect_cnt(true); int share = detect_share(wp_cnt, bp_cnt); + if (!BP_ACCOUNT_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + pr_debug("watchpoints count %d, breakpoints count %d, has_ioctl %d, share %d\n", wp_cnt, bp_cnt, has_ioctl, share); @@ -189,18 +207,4 @@ int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_un return bp_accounting(wp_cnt, share); } -bool test__bp_account_is_supported(void) -{ - /* - * PowerPC and S390 do not support creation of instruction - * breakpoints using the perf_event interface. - * - * Just disable the test for these architectures until these - * issues are resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) - return false; -#else - return true; -#endif -} +DEFINE_SUITE("Breakpoint accounting", bp_accounting); diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index ef37353636d8..1f2908f02389 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -161,11 +161,16 @@ static long long bp_count(int fd) return count; } -int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_signal(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct sigaction sa; long long count1, count2, count3; + if (!BP_SIGNAL_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + /* setup SIGIO signal handler */ memset(&sa, 0, sizeof(struct sigaction)); sa.sa_sigaction = (void *) sig_handler; @@ -285,29 +290,4 @@ int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused TEST_OK : TEST_FAIL; } -bool test__bp_signal_is_supported(void) -{ - /* - * PowerPC and S390 do not support creation of instruction - * breakpoints using the perf_event interface. - * - * ARM requires explicit rounding down of the instruction - * pointer in Thumb mode, and then requires the single-step - * to be handled explicitly in the overflow handler to avoid - * stepping into the SIGIO handler and getting stuck on the - * breakpointed instruction. - * - * Since arm64 has the same issue with arm for the single-step - * handling, this case also gets stuck on the breakpointed - * instruction. - * - * Just disable the test for these architectures until these - * issues are resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || \ - defined(__aarch64__) - return false; -#else - return true; -#endif -} +DEFINE_SUITE("Breakpoint overflow signal handler", bp_signal); diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index eb4dbbddf4ff..4e897c2cf26b 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -59,13 +59,18 @@ static long long bp_count(int fd) #define EXECUTIONS 10000 #define THRESHOLD 100 -int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__bp_signal_overflow(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_event_attr pe; struct sigaction sa; long long count; int fd, i, fails = 0; + if (!BP_SIGNAL_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + /* setup SIGIO signal handler */ memset(&sa, 0, sizeof(struct sigaction)); sa.sa_sigaction = (void *) sig_handler; @@ -133,3 +138,5 @@ int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __may return fails ? TEST_FAIL : TEST_OK; } + +DEFINE_SUITE("Breakpoint overflow sampling", bp_signal_overflow); diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index c52bf10f746e..573490530194 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -62,7 +62,6 @@ static int llseek_loop(void) static struct { enum test_llvm__testcase prog_id; - const char *desc; const char *name; const char *msg_compile_fail; const char *msg_load_fail; @@ -72,7 +71,6 @@ static struct { } bpf_testcase_table[] = { { .prog_id = LLVM_TESTCASE_BASE, - .desc = "Basic BPF filtering", .name = "[basic_bpf_test]", .msg_compile_fail = "fix 'perf test LLVM' first", .msg_load_fail = "load bpf object failed", @@ -81,7 +79,6 @@ static struct { }, { .prog_id = LLVM_TESTCASE_BASE, - .desc = "BPF pinning", .name = "[bpf_pinning]", .msg_compile_fail = "fix kbuild first", .msg_load_fail = "check your vmlinux setting?", @@ -92,7 +89,6 @@ static struct { #ifdef HAVE_BPF_PROLOGUE { .prog_id = LLVM_TESTCASE_BPF_PROLOGUE, - .desc = "BPF prologue generation", .name = "[bpf_prologue_test]", .msg_compile_fail = "fix kbuild first", .msg_load_fail = "check your vmlinux setting?", @@ -283,18 +279,6 @@ out: return ret; } -int test__bpf_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(bpf_testcase_table); -} - -const char *test__bpf_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table)) - return NULL; - return bpf_testcase_table[i].desc; -} - static int check_env(void) { int err; @@ -316,7 +300,7 @@ static int check_env(void) #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wdeprecated-declarations" err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns, - sizeof(insns) / sizeof(insns[0]), + ARRAY_SIZE(insns), license, kver_int, NULL, 0); #pragma GCC diagnostic pop if (err < 0) { @@ -329,7 +313,7 @@ static int check_env(void) return 0; } -int test__bpf(struct test *test __maybe_unused, int i) +static int test__bpf(int i) { int err; @@ -347,21 +331,60 @@ int test__bpf(struct test *test __maybe_unused, int i) err = __test__bpf(i); return err; } +#endif -#else -int test__bpf_subtest_get_nr(void) +static int test__basic_bpf_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return 0; +#ifdef HAVE_LIBBPF_SUPPORT + return test__bpf(0); +#else + pr_debug("Skip BPF test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -const char *test__bpf_subtest_get_desc(int i __maybe_unused) +static int test__bpf_pinning(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return NULL; +#ifdef HAVE_LIBBPF_SUPPORT + return test__bpf(1); +#else + pr_debug("Skip BPF test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -int test__bpf(struct test *test __maybe_unused, int i __maybe_unused) +static int test__bpf_prologue_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_BPF_PROLOGUE) + return test__bpf(2); +#else pr_debug("Skip BPF test because BPF support is not compiled\n"); return TEST_SKIP; +#endif } + + +static struct test_case bpf_tests[] = { +#ifdef HAVE_LIBBPF_SUPPORT + TEST_CASE("Basic BPF filtering", basic_bpf_test), + TEST_CASE("BPF pinning", bpf_pinning), +#ifdef HAVE_BPF_PROLOGUE + TEST_CASE("BPF prologue generation", bpf_prologue_test), +#else + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), +#endif +#else + TEST_CASE_REASON("Basic BPF filtering", basic_bpf_test, "not compiled in"), + TEST_CASE_REASON("BPF pinning", bpf_pinning, "not compiled in"), + TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"), #endif + { .name = NULL, } +}; + +struct test_suite suite__bpf = { + .desc = "BPF filter", + .test_cases = bpf_tests, +}; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index da7dc5e45d0c..8cb5a1c3489e 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -30,350 +30,134 @@ static bool dont_fork; -struct test __weak arch_tests[] = { - { - .func = NULL, - }, +struct test_suite *__weak arch_tests[] = { + NULL, }; -static struct test generic_tests[] = { - { - .desc = "vmlinux symtab matches kallsyms", - .func = test__vmlinux_matches_kallsyms, - }, - { - .desc = "Detect openat syscall event", - .func = test__openat_syscall_event, - }, - { - .desc = "Detect openat syscall event on all cpus", - .func = test__openat_syscall_event_on_all_cpus, - }, - { - .desc = "Read samples using the mmap interface", - .func = test__basic_mmap, - }, - { - .desc = "Test data source output", - .func = test__mem, - }, - { - .desc = "Parse event definition strings", - .func = test__parse_events, - }, - { - .desc = "Simple expression parser", - .func = test__expr, - }, - { - .desc = "PERF_RECORD_* events & perf_sample fields", - .func = test__PERF_RECORD, - }, - { - .desc = "Parse perf pmu format", - .func = test__pmu, - }, - { - .desc = "PMU events", - .func = test__pmu_events, - .subtest = { - .skip_if_fail = false, - .get_nr = test__pmu_events_subtest_get_nr, - .get_desc = test__pmu_events_subtest_get_desc, - .skip_reason = test__pmu_events_subtest_skip_reason, - }, - - }, - { - .desc = "DSO data read", - .func = test__dso_data, - }, - { - .desc = "DSO data cache", - .func = test__dso_data_cache, - }, - { - .desc = "DSO data reopen", - .func = test__dso_data_reopen, - }, - { - .desc = "Roundtrip evsel->name", - .func = test__perf_evsel__roundtrip_name_test, - }, - { - .desc = "Parse sched tracepoints fields", - .func = test__perf_evsel__tp_sched_test, - }, - { - .desc = "syscalls:sys_enter_openat event fields", - .func = test__syscall_openat_tp_fields, - }, - { - .desc = "Setup struct perf_event_attr", - .func = test__attr, - }, - { - .desc = "Match and link multiple hists", - .func = test__hists_link, - }, - { - .desc = "'import perf' in python", - .func = test__python_use, - }, - { - .desc = "Breakpoint overflow signal handler", - .func = test__bp_signal, - .is_supported = test__bp_signal_is_supported, - }, - { - .desc = "Breakpoint overflow sampling", - .func = test__bp_signal_overflow, - .is_supported = test__bp_signal_is_supported, - }, - { - .desc = "Breakpoint accounting", - .func = test__bp_accounting, - .is_supported = test__bp_account_is_supported, - }, - { - .desc = "Watchpoint", - .func = test__wp, - .is_supported = test__wp_is_supported, - .subtest = { - .skip_if_fail = false, - .get_nr = test__wp_subtest_get_nr, - .get_desc = test__wp_subtest_get_desc, - .skip_reason = test__wp_subtest_skip_reason, - }, - }, - { - .desc = "Number of exit events of a simple workload", - .func = test__task_exit, - }, - { - .desc = "Software clock events period values", - .func = test__sw_clock_freq, - }, - { - .desc = "Object code reading", - .func = test__code_reading, - }, - { - .desc = "Sample parsing", - .func = test__sample_parsing, - }, - { - .desc = "Use a dummy software event to keep tracking", - .func = test__keep_tracking, - }, - { - .desc = "Parse with no sample_id_all bit set", - .func = test__parse_no_sample_id_all, - }, - { - .desc = "Filter hist entries", - .func = test__hists_filter, - }, - { - .desc = "Lookup mmap thread", - .func = test__mmap_thread_lookup, - }, - { - .desc = "Share thread maps", - .func = test__thread_maps_share, - }, - { - .desc = "Sort output of hist entries", - .func = test__hists_output, - }, - { - .desc = "Cumulate child hist entries", - .func = test__hists_cumulate, - }, - { - .desc = "Track with sched_switch", - .func = test__switch_tracking, - }, - { - .desc = "Filter fds with revents mask in a fdarray", - .func = test__fdarray__filter, - }, - { - .desc = "Add fd to a fdarray, making it autogrow", - .func = test__fdarray__add, - }, - { - .desc = "kmod_path__parse", - .func = test__kmod_path__parse, - }, - { - .desc = "Thread map", - .func = test__thread_map, - }, - { - .desc = "LLVM search and compile", - .func = test__llvm, - .subtest = { - .skip_if_fail = true, - .get_nr = test__llvm_subtest_get_nr, - .get_desc = test__llvm_subtest_get_desc, - }, - }, - { - .desc = "Session topology", - .func = test__session_topology, - }, - { - .desc = "BPF filter", - .func = test__bpf, - .subtest = { - .skip_if_fail = true, - .get_nr = test__bpf_subtest_get_nr, - .get_desc = test__bpf_subtest_get_desc, - }, - }, - { - .desc = "Synthesize thread map", - .func = test__thread_map_synthesize, - }, - { - .desc = "Remove thread map", - .func = test__thread_map_remove, - }, - { - .desc = "Synthesize cpu map", - .func = test__cpu_map_synthesize, - }, - { - .desc = "Synthesize stat config", - .func = test__synthesize_stat_config, - }, - { - .desc = "Synthesize stat", - .func = test__synthesize_stat, - }, - { - .desc = "Synthesize stat round", - .func = test__synthesize_stat_round, - }, - { - .desc = "Synthesize attr update", - .func = test__event_update, - }, - { - .desc = "Event times", - .func = test__event_times, - }, - { - .desc = "Read backward ring buffer", - .func = test__backward_ring_buffer, - }, - { - .desc = "Print cpu map", - .func = test__cpu_map_print, - }, - { - .desc = "Merge cpu map", - .func = test__cpu_map_merge, - }, - - { - .desc = "Probe SDT events", - .func = test__sdt_event, - }, - { - .desc = "is_printable_array", - .func = test__is_printable_array, - }, - { - .desc = "Print bitmap", - .func = test__bitmap_print, - }, - { - .desc = "perf hooks", - .func = test__perf_hooks, - }, - { - .desc = "builtin clang support", - .func = test__clang, - .subtest = { - .skip_if_fail = true, - .get_nr = test__clang_subtest_get_nr, - .get_desc = test__clang_subtest_get_desc, - } - }, - { - .desc = "unit_number__scnprintf", - .func = test__unit_number__scnprint, - }, - { - .desc = "mem2node", - .func = test__mem2node, - }, - { - .desc = "time utils", - .func = test__time_utils, - }, - { - .desc = "Test jit_write_elf", - .func = test__jit_write_elf, - }, - { - .desc = "Test libpfm4 support", - .func = test__pfm, - .subtest = { - .skip_if_fail = true, - .get_nr = test__pfm_subtest_get_nr, - .get_desc = test__pfm_subtest_get_desc, - } - }, - { - .desc = "Test api io", - .func = test__api_io, - }, - { - .desc = "maps__merge_in", - .func = test__maps__merge_in, - }, - { - .desc = "Demangle Java", - .func = test__demangle_java, - }, - { - .desc = "Demangle OCaml", - .func = test__demangle_ocaml, - }, - { - .desc = "Parse and process metrics", - .func = test__parse_metric, - }, - { - .desc = "PE file support", - .func = test__pe_file_parsing, - }, - { - .desc = "Event expansion for cgroups", - .func = test__expand_cgroup_events, - }, - { - .desc = "Convert perf time to TSC", - .func = test__perf_time_to_tsc, - .is_supported = test__tsc_is_supported, - }, - { - .desc = "dlfilter C API", - .func = test__dlfilter, - }, - { - .func = NULL, - }, +static struct test_suite *generic_tests[] = { + &suite__vmlinux_matches_kallsyms, + &suite__openat_syscall_event, + &suite__openat_syscall_event_on_all_cpus, + &suite__basic_mmap, + &suite__mem, + &suite__parse_events, + &suite__expr, + &suite__PERF_RECORD, + &suite__pmu, + &suite__pmu_events, + &suite__dso_data, + &suite__dso_data_cache, + &suite__dso_data_reopen, + &suite__perf_evsel__roundtrip_name_test, + &suite__perf_evsel__tp_sched_test, + &suite__syscall_openat_tp_fields, + &suite__attr, + &suite__hists_link, + &suite__python_use, + &suite__bp_signal, + &suite__bp_signal_overflow, + &suite__bp_accounting, + &suite__wp, + &suite__task_exit, + &suite__sw_clock_freq, + &suite__code_reading, + &suite__sample_parsing, + &suite__keep_tracking, + &suite__parse_no_sample_id_all, + &suite__hists_filter, + &suite__mmap_thread_lookup, + &suite__thread_maps_share, + &suite__hists_output, + &suite__hists_cumulate, + &suite__switch_tracking, + &suite__fdarray__filter, + &suite__fdarray__add, + &suite__kmod_path__parse, + &suite__thread_map, + &suite__llvm, + &suite__session_topology, + &suite__bpf, + &suite__thread_map_synthesize, + &suite__thread_map_remove, + &suite__cpu_map_synthesize, + &suite__synthesize_stat_config, + &suite__synthesize_stat, + &suite__synthesize_stat_round, + &suite__event_update, + &suite__event_times, + &suite__backward_ring_buffer, + &suite__cpu_map_print, + &suite__cpu_map_merge, + &suite__sdt_event, + &suite__is_printable_array, + &suite__bitmap_print, + &suite__perf_hooks, + &suite__clang, + &suite__unit_number__scnprint, + &suite__mem2node, + &suite__time_utils, + &suite__jit_write_elf, + &suite__pfm, + &suite__api_io, + &suite__maps__merge_in, + &suite__demangle_java, + &suite__demangle_ocaml, + &suite__parse_metric, + &suite__pe_file_parsing, + &suite__expand_cgroup_events, + &suite__perf_time_to_tsc, + &suite__dlfilter, + NULL, }; -static struct test *tests[] = { +static struct test_suite **tests[] = { generic_tests, arch_tests, }; +static int num_subtests(const struct test_suite *t) +{ + int num; + + if (!t->test_cases) + return 0; + + num = 0; + while (t->test_cases[num].name) + num++; + + return num; +} + +static bool has_subtests(const struct test_suite *t) +{ + return num_subtests(t) > 1; +} + +static const char *skip_reason(const struct test_suite *t, int subtest) +{ + if (t->test_cases && subtest >= 0) + return t->test_cases[subtest].skip_reason; + + return NULL; +} + +static const char *test_description(const struct test_suite *t, int subtest) +{ + if (t->test_cases && subtest >= 0) + return t->test_cases[subtest].desc; + + return t->desc; +} + +static test_fnptr test_function(const struct test_suite *t, int subtest) +{ + if (subtest <= 0) + return t->test_cases[0].run_case; + + return t->test_cases[subtest].run_case; +} + static bool perf_test__matches(const char *desc, int curr, int argc, const char *argv[]) { int i; @@ -398,7 +182,7 @@ static bool perf_test__matches(const char *desc, int curr, int argc, const char return false; } -static int run_test(struct test *test, int subtest) +static int run_test(struct test_suite *test, int subtest) { int status, err = -1, child = dont_fork ? 0 : fork(); char sbuf[STRERR_BUFSIZE]; @@ -430,7 +214,7 @@ static int run_test(struct test *test, int subtest) } } - err = test->func(test, subtest); + err = test_function(test, subtest)(test, subtest); if (!dont_fork) exit(err); } @@ -450,24 +234,19 @@ static int run_test(struct test *test, int subtest) return err; } -#define for_each_test(j, t) \ +#define for_each_test(j, k, t) \ for (j = 0; j < ARRAY_SIZE(tests); j++) \ - for (t = &tests[j][0]; t->func; t++) + for (k = 0, t = tests[j][k]; tests[j][k]; k++, t = tests[j][k]) -static int test_and_print(struct test *t, bool force_skip, int subtest) +static int test_and_print(struct test_suite *t, int subtest) { int err; - if (!force_skip) { - pr_debug("\n--- start ---\n"); - err = run_test(t, subtest); - pr_debug("---- end ----\n"); - } else { - pr_debug("\n--- force skipped ---\n"); - err = TEST_SKIP; - } + pr_debug("\n--- start ---\n"); + err = run_test(t, subtest); + pr_debug("---- end ----\n"); - if (!t->subtest.get_nr) + if (!has_subtests(t)) pr_debug("%s:", t->desc); else pr_debug("%s subtest %d:", t->desc, subtest + 1); @@ -477,11 +256,10 @@ static int test_and_print(struct test *t, bool force_skip, int subtest) pr_info(" Ok\n"); break; case TEST_SKIP: { - const char *skip_reason = NULL; - if (t->subtest.skip_reason) - skip_reason = t->subtest.skip_reason(subtest); - if (skip_reason) - color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", skip_reason); + const char *reason = skip_reason(t, subtest); + + if (reason) + color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", reason); else color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n"); } @@ -580,7 +358,7 @@ struct shell_test { const char *file; }; -static int shell_test__run(struct test *test, int subdir __maybe_unused) +static int shell_test__run(struct test_suite *test, int subdir __maybe_unused) { int err; char script[PATH_MAX]; @@ -622,24 +400,34 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, for_each_shell_test(entlist, n_dirs, st.dir, ent) { int curr = i++; char desc[256]; - struct test test = { - .desc = shell_test__description(desc, sizeof(desc), st.dir, ent->d_name), - .func = shell_test__run, + struct test_case test_cases[] = { + { + .desc = shell_test__description(desc, + sizeof(desc), + st.dir, + ent->d_name), + .run_case = shell_test__run, + }, + { .name = NULL, } + }; + struct test_suite test_suite = { + .desc = test_cases[0].desc, + .test_cases = test_cases, .priv = &st, }; - if (!perf_test__matches(test.desc, curr, argc, argv)) + if (!perf_test__matches(test_suite.desc, curr, argc, argv)) continue; st.file = ent->d_name; - pr_info("%2d: %-*s:", i, width, test.desc); + pr_info("%2d: %-*s:", i, width, test_suite.desc); if (intlist__find(skiplist, i)) { color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); continue; } - test_and_print(&test, false, -1); + test_and_print(&test_suite, 0); } for (e = 0; e < n_dirs; e++) @@ -650,33 +438,31 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width, static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) { - struct test *t; - unsigned int j; + struct test_suite *t; + unsigned int j, k; int i = 0; int width = shell_tests__max_desc_width(); - for_each_test(j, t) { - int len = strlen(t->desc); + for_each_test(j, k, t) { + int len = strlen(test_description(t, -1)); if (width < len) width = len; } - for_each_test(j, t) { - int curr = i++, err; + for_each_test(j, k, t) { + int curr = i++; int subi; - if (!perf_test__matches(t->desc, curr, argc, argv)) { + if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) { bool skip = true; int subn; - if (!t->subtest.get_nr) - continue; - - subn = t->subtest.get_nr(); + subn = num_subtests(t); for (subi = 0; subi < subn; subi++) { - if (perf_test__matches(t->subtest.get_desc(subi), curr, argc, argv)) + if (perf_test__matches(test_description(t, subi), + curr, argc, argv)) skip = false; } @@ -684,22 +470,17 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) continue; } - if (t->is_supported && !t->is_supported()) { - pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc); - continue; - } - - pr_info("%2d: %-*s:", i, width, t->desc); + pr_info("%2d: %-*s:", i, width, test_description(t, -1)); if (intlist__find(skiplist, i)) { color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n"); continue; } - if (!t->subtest.get_nr) { - test_and_print(t, false, -1); + if (!has_subtests(t)) { + test_and_print(t, -1); } else { - int subn = t->subtest.get_nr(); + int subn = num_subtests(t); /* * minus 2 to align with normal testcases. * For subtest we print additional '.x' in number. @@ -709,7 +490,6 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) * 35.1: Basic BPF llvm compiling test : Ok */ int subw = width > 2 ? width - 2 : width; - bool skip = false; if (subn <= 0) { color_fprintf(stderr, PERF_COLOR_YELLOW, @@ -719,21 +499,20 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) pr_info("\n"); for (subi = 0; subi < subn; subi++) { - int len = strlen(t->subtest.get_desc(subi)); + int len = strlen(test_description(t, subi)); if (subw < len) subw = len; } for (subi = 0; subi < subn; subi++) { - if (!perf_test__matches(t->subtest.get_desc(subi), curr, argc, argv)) + if (!perf_test__matches(test_description(t, subi), + curr, argc, argv)) continue; pr_info("%2d.%1d: %-*s:", i, subi + 1, subw, - t->subtest.get_desc(subi)); - err = test_and_print(t, skip, subi); - if (err != TEST_OK && t->subtest.skip_if_fail) - skip = true; + test_description(t, subi)); + test_and_print(t, subi); } } } @@ -759,7 +538,7 @@ static int perf_test__list_shell(int argc, const char **argv, int i) for_each_shell_test(entlist, n_dirs, path, ent) { int curr = i++; char bf[256]; - struct test t = { + struct test_suite t = { .desc = shell_test__description(bf, sizeof(bf), path, ent->d_name), }; @@ -778,26 +557,25 @@ static int perf_test__list_shell(int argc, const char **argv, int i) static int perf_test__list(int argc, const char **argv) { - unsigned int j; - struct test *t; + unsigned int j, k; + struct test_suite *t; int i = 0; - for_each_test(j, t) { + for_each_test(j, k, t) { int curr = i++; - if (!perf_test__matches(t->desc, curr, argc, argv) || - (t->is_supported && !t->is_supported())) + if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) continue; - pr_info("%2d: %s\n", i, t->desc); + pr_info("%2d: %s\n", i, test_description(t, -1)); - if (t->subtest.get_nr) { - int subn = t->subtest.get_nr(); + if (has_subtests(t)) { + int subn = num_subtests(t); int subi; for (subi = 0; subi < subn; subi++) pr_info("%2d:%1d: %s\n", i, subi + 1, - t->subtest.get_desc(subi)); + test_description(t, subi)); } } diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c index 2577d3ed1531..a7111005d5b9 100644 --- a/tools/perf/tests/clang.c +++ b/tools/perf/tests/clang.c @@ -3,44 +3,30 @@ #include "c++/clang-c.h" #include <linux/kernel.h> -static struct { - int (*func)(void); - const char *desc; -} clang_testcase_table[] = { -#ifdef HAVE_LIBCLANGLLVM_SUPPORT - { - .func = test__clang_to_IR, - .desc = "builtin clang compile C source to IR", - }, - { - .func = test__clang_to_obj, - .desc = "builtin clang compile C source to ELF object", - }, -#endif -}; - -int test__clang_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(clang_testcase_table); -} - -const char *test__clang_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table)) - return NULL; - return clang_testcase_table[i].desc; -} - #ifndef HAVE_LIBCLANGLLVM_SUPPORT -int test__clang(struct test *test __maybe_unused, int i __maybe_unused) +static int test__clang_to_IR(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { return TEST_SKIP; } -#else -int test__clang(struct test *test __maybe_unused, int i) + +static int test__clang_to_obj(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table)) - return TEST_FAIL; - return clang_testcase_table[i].func(); + return TEST_SKIP; } #endif + +static struct test_case clang_tests[] = { + TEST_CASE_REASON("builtin clang compile C source to IR", clang_to_IR, + "not compiled in"), + TEST_CASE_REASON("builtin clang compile C source to ELF object", + clang_to_obj, + "not compiled in"), + { .name = NULL, } +}; + +struct test_suite suite__clang = { + .desc = "builtin clang support", + .test_cases = clang_tests, +}; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index f439bd49da19..5610767b407f 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -716,7 +716,7 @@ out_err: return err; } -int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__code_reading(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret; @@ -743,3 +743,5 @@ int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unu return -1; }; } + +DEFINE_SUITE("Object code reading", code_reading); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 0472b110fe65..89a155092f85 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -75,7 +75,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, } -int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_synthesize(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_cpu_map *cpus; @@ -111,7 +111,7 @@ static int cpu_map_print(const char *str) return !strcmp(buf, str); } -int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_print(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1")); TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5")); @@ -123,7 +123,7 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un return 0; } -int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__cpu_map_merge(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_cpu_map *a = perf_cpu_map__new("4,2,1"); struct perf_cpu_map *b = perf_cpu_map__new("4,5,7"); @@ -137,3 +137,7 @@ int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_un perf_cpu_map__put(c); return 0; } + +DEFINE_SUITE("Synthesize cpu map", cpu_map_synthesize); +DEFINE_SUITE("Print cpu map", cpu_map_print); +DEFINE_SUITE("Merge cpu map", cpu_map_merge); diff --git a/tools/perf/tests/demangle-java-test.c b/tools/perf/tests/demangle-java-test.c index 8f3b90832fb0..44d1be303b67 100644 --- a/tools/perf/tests/demangle-java-test.c +++ b/tools/perf/tests/demangle-java-test.c @@ -7,7 +7,7 @@ #include "debug.h" #include "demangle-java.h" -int test__demangle_java(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__demangle_java(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_OK; char *buf = NULL; @@ -40,3 +40,5 @@ int test__demangle_java(struct test *test __maybe_unused, int subtest __maybe_un return ret; } + +DEFINE_SUITE("Demangle Java", demangle_java); diff --git a/tools/perf/tests/demangle-ocaml-test.c b/tools/perf/tests/demangle-ocaml-test.c index 0043be812355..90a4285e2ad5 100644 --- a/tools/perf/tests/demangle-ocaml-test.c +++ b/tools/perf/tests/demangle-ocaml-test.c @@ -7,7 +7,7 @@ #include "debug.h" #include "demangle-ocaml.h" -int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__demangle_ocaml(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret = TEST_OK; char *buf = NULL; @@ -41,3 +41,5 @@ int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_u return ret; } + +DEFINE_SUITE("Demangle OCaml", demangle_ocaml); diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c index bc03b5df6828..84352d55347d 100644 --- a/tools/perf/tests/dlfilter-test.c +++ b/tools/perf/tests/dlfilter-test.c @@ -398,7 +398,7 @@ static void test_data__free(struct test_data *td) } } -int test__dlfilter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct test_data td = {.fd = -1}; int pid = getpid(); @@ -414,3 +414,5 @@ int test__dlfilter(struct test *test __maybe_unused, int subtest __maybe_unused) test_data__free(&td); return err; } + +DEFINE_SUITE("dlfilter C API", dlfilter); diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 43e1b01e5afc..3419a4ab5590 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -113,7 +113,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine) return fd; } -int test__dso_data(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; struct dso *dso; @@ -248,7 +248,7 @@ static int set_fd_limit(int n) return setrlimit(RLIMIT_NOFILE, &rlim); } -int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data_cache(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(); @@ -318,7 +318,7 @@ static long new_limit(int count) return ret; } -int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dso_data_reopen(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(), lim = new_limit(3); @@ -393,3 +393,7 @@ int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_ TEST_ASSERT_VAL("failed leaking files", nr == nr_end); return 0; } + +DEFINE_SUITE("DSO data read", dso_data); +DEFINE_SUITE("DSO data cache", dso_data_cache); +DEFINE_SUITE("DSO data reopen", dso_data_reopen); diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index c756284b3b13..2dab2d262060 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -195,7 +195,8 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *th return ret; } -int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__dwarf_unwind(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct machine *machine; struct thread *thread; @@ -237,3 +238,5 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu machine__delete(machine); return err; } + +DEFINE_SUITE("Test dwarf unwind", dwarf_unwind); diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 04ce4401f775..7606eb3df92f 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -216,7 +216,7 @@ out_err: * and checks that enabled and running times * match. */ -int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__event_times(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err, ret = 0; @@ -239,3 +239,5 @@ int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unus #undef _T return ret; } + +DEFINE_SUITE("Event times", event_times); diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index 44a50527f9d9..d01532d40acb 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -83,12 +83,11 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, return 0; } -int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__event_update(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct evsel *evsel; struct event_name tmp; struct evlist *evlist = evlist__new_default(); - char *unit = strdup("KRAVA"); TEST_ASSERT_VAL("failed to get evlist", evlist); @@ -99,7 +98,8 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123); - evsel->unit = unit; + free((char *)evsel->unit); + evsel->unit = strdup("KRAVA"); TEST_ASSERT_VAL("failed to synthesize attr update unit", !perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit)); @@ -119,7 +119,8 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu TEST_ASSERT_VAL("failed to synthesize attr update cpus", !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); - free(unit); evlist__delete(evlist); return 0; } + +DEFINE_SUITE("Synthesize attr update", event_update); diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 4e09f0a312af..fdbf17642e45 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -99,7 +99,8 @@ out_delete_evlist: #define perf_evsel__name_array_test(names, distance) \ __perf_evsel__name_array_test(names, ARRAY_SIZE(names), distance) -int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_evsel__roundtrip_name_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = 0, ret = 0; @@ -120,3 +121,5 @@ int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int return ret; } + +DEFINE_SUITE("Roundtrip evsel->name", perf_evsel__roundtrip_name_test); diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index f9e34bd26cf3..cf4da3d748c2 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -32,7 +32,8 @@ static int evsel__test_field(struct evsel *evsel, const char *name, int size, bo return ret; } -int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_evsel__tp_sched_test(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evsel *evsel = evsel__newtp("sched", "sched_switch"); int ret = 0; @@ -87,3 +88,5 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes evsel__delete(evsel); return ret; } + +DEFINE_SUITE("Parse sched tracepoints fields", perf_evsel__tp_sched_test); diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index 80cff8a3558c..dfefe5b60eb2 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -221,8 +221,8 @@ out: return ret; } -int test__expand_cgroup_events(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__expand_cgroup_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int ret; @@ -240,3 +240,5 @@ int test__expand_cgroup_events(struct test *test __maybe_unused, return ret; } + +DEFINE_SUITE("Event expansion for cgroups", expand_cgroup_events); diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 077783223ce0..d54c5371c6a6 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -62,11 +62,11 @@ static int test(struct expr_parse_ctx *ctx, const char *e, double val2) return 0; } -int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct expr_id_data *val_ptr; const char *p; - double val; + double val, num_cpus, num_cores, num_dies, num_packages; int ret; struct expr_parse_ctx *ctx; @@ -134,6 +134,16 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@", (void **)&val_ptr)); + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("find ids", + expr__find_ids("dash\\-event1 - dash\\-event2", + NULL, ctx) == 0); + TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1", + (void **)&val_ptr)); + TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2", + (void **)&val_ptr)); + /* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */ expr__ctx_clear(ctx); TEST_ASSERT_VAL("find ids", @@ -151,7 +161,33 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused) NULL, ctx) == 0); TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 0); + /* Test toplogy constants appear well ordered. */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0); + TEST_ASSERT_VAL("#num_cores", expr__parse(&num_cores, ctx, "#num_cores") == 0); + TEST_ASSERT_VAL("#num_cpus >= #num_cores", num_cpus >= num_cores); + TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0); + TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies); + TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0); + + if (num_dies) // Some platforms do not have CPU die support, for example s390 + TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); + + /* + * Source count returns the number of events aggregating in a leader + * event including the leader. Check parsing yields an id. + */ + expr__ctx_clear(ctx); + TEST_ASSERT_VAL("source count", + expr__find_ids("source_count(EVENT1)", + NULL, ctx) == 0); + TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1); + TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", + (void **)&val_ptr)); + expr__ctx_free(ctx); return 0; } + +DEFINE_SUITE("Simple expression parser", expr); diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c index d9eca8e86a6b..40983c3574b1 100644 --- a/tools/perf/tests/fdarray.c +++ b/tools/perf/tests/fdarray.c @@ -28,7 +28,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE return printed + fdarray__fprintf(fda, fp); } -int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__fdarray__filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int nr_fds, err = TEST_FAIL; struct fdarray *fda = fdarray__new(5, 5); @@ -89,7 +89,7 @@ out: return err; } -int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__fdarray__add(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct fdarray *fda = fdarray__new(2, 2); @@ -158,3 +158,6 @@ out_delete: out: return err; } + +DEFINE_SUITE("Filter fds with revents mask in a fdarray", fdarray__filter); +DEFINE_SUITE("Add fd to a fdarray, making it autogrow", fdarray__add); diff --git a/tools/perf/tests/genelf.c b/tools/perf/tests/genelf.c index f797f9823e89..95f3be1b683a 100644 --- a/tools/perf/tests/genelf.c +++ b/tools/perf/tests/genelf.c @@ -16,8 +16,8 @@ #define TEMPL "/tmp/perf-test-XXXXXX" -int test__jit_write_elf(struct test *test __maybe_unused, - int subtest __maybe_unused) +static int test__jit_write_elf(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { #ifdef HAVE_JITDUMP static unsigned char x86_code[] = { @@ -49,3 +49,5 @@ int test__jit_write_elf(struct test *test __maybe_unused, return TEST_SKIP; #endif } + +DEFINE_SUITE("Test jit_write_elf", jit_write_elf); diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 890cb1f5bf53..17f4fcd6bdce 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -689,7 +689,7 @@ out: return err; } -int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_cumulate(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -736,3 +736,5 @@ out: return err; } + +DEFINE_SUITE("Cumulate child hist entries", hists_cumulate); diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index ca6120cd1d90..08cbeb9e39ae 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -101,7 +101,7 @@ out: return TEST_FAIL; } -int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -325,3 +325,5 @@ out: return err; } + +DEFINE_SUITE("Filter hist entries", hists_filter); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index a024d3f3a412..c575e13a850d 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -264,7 +264,7 @@ static int validate_link(struct hists *leader, struct hists *other) return __validate_link(leader, 0) || __validate_link(other, 1); } -int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_link(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; struct hists *hists, *first_hists; @@ -339,3 +339,5 @@ out: return err; } + +DEFINE_SUITE("Match and link multiple hists", hists_link); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 8973f35df604..0bde4a768c15 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -575,7 +575,7 @@ out: return err; } -int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__hists_output(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -623,3 +623,5 @@ out: return err; } + +DEFINE_SUITE("Sort output of hist entries", hists_output); diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c index 9c7b3baca4fe..f72de2457ff1 100644 --- a/tools/perf/tests/is_printable_array.c +++ b/tools/perf/tests/is_printable_array.c @@ -5,7 +5,7 @@ #include "debug.h" #include "print_binary.h" -int test__is_printable_array(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__is_printable_array(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 }; char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 }; @@ -36,3 +36,5 @@ int test__is_printable_array(struct test *test __maybe_unused, int subtest __may return TEST_OK; } + +DEFINE_SUITE("is_printable_array", is_printable_array); diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index a0438b0f0805..dd2067312452 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -61,7 +61,7 @@ static int find_comm(struct evlist *evlist, const char *comm) * when an event is disabled but a dummy software event is not disabled. If the * test passes %0 is returned, otherwise %-1 is returned. */ -int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__keep_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, @@ -160,3 +160,5 @@ out_err: return err; } + +DEFINE_SUITE("Use a dummy software event to keep tracking", keep_tracking); diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index e483210b176b..dfe1bd5dabaa 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -47,7 +47,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect) #define M(path, c, e) \ TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e)) -int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__kmod_path__parse(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { /* path alloc_name kmod comp name */ T("/xxxx/xxxx/x-x.ko", true , true, 0 , "[x_x]"); @@ -159,3 +159,5 @@ int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_un return 0; } + +DEFINE_SUITE("kmod_path__parse", kmod_path__parse); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 33e43cce9064..8ac0a3a457ef 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -124,7 +124,7 @@ out: return ret; } -int test__llvm(struct test *test __maybe_unused, int subtest) +static int test__llvm(int subtest) { int ret; void *obj_buf = NULL; @@ -148,32 +148,72 @@ int test__llvm(struct test *test __maybe_unused, int subtest) return ret; } +#endif //HAVE_LIBBPF_SUPPORT -int test__llvm_subtest_get_nr(void) +static int test__llvm__bpf_base_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return __LLVM_TESTCASE_MAX; +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BASE); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -const char *test__llvm_subtest_get_desc(int subtest) -{ - if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) - return NULL; - - return bpf_source_table[subtest].desc; -} -#else //HAVE_LIBBPF_SUPPORT -int test__llvm(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__llvm__bpf_test_kbuild_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_KBUILD); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); return TEST_SKIP; +#endif } -int test__llvm_subtest_get_nr(void) +static int test__llvm__bpf_test_prologue_prog(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return 0; +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BPF_PROLOGUE); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -const char *test__llvm_subtest_get_desc(int subtest __maybe_unused) +static int test__llvm__bpf_test_relocation(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return NULL; +#ifdef HAVE_LIBBPF_SUPPORT + return test__llvm(LLVM_TESTCASE_BPF_RELOCATION); +#else + pr_debug("Skip LLVM test because BPF support is not compiled\n"); + return TEST_SKIP; +#endif } -#endif // HAVE_LIBBPF_SUPPORT + + +static struct test_case llvm_tests[] = { +#ifdef HAVE_LIBBPF_SUPPORT + TEST_CASE("Basic BPF llvm compile", llvm__bpf_base_prog), + TEST_CASE("kbuild searching", llvm__bpf_test_kbuild_prog), + TEST_CASE("Compile source for BPF prologue generation", + llvm__bpf_test_prologue_prog), + TEST_CASE("Compile source for BPF relocation", llvm__bpf_test_relocation), +#else + TEST_CASE_REASON("Basic BPF llvm compile", llvm__bpf_base_prog, "not compiled in"), + TEST_CASE_REASON("kbuild searching", llvm__bpf_test_kbuild_prog, "not compiled in"), + TEST_CASE_REASON("Compile source for BPF prologue generation", + llvm__bpf_test_prologue_prog, "not compiled in"), + TEST_CASE_REASON("Compile source for BPF relocation", + llvm__bpf_test_relocation, "not compiled in"), +#endif + { .name = NULL, } +}; + +struct test_suite suite__llvm = { + .desc = "LLVM search and compile", + .test_cases = llvm_tests, +}; diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index 1ac72919fa35..e308a3296cef 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -33,7 +33,7 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma return TEST_OK; } -int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__maps__merge_in(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct maps maps; unsigned int i; @@ -120,3 +120,5 @@ int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unus maps__exit(&maps); return TEST_OK; } + +DEFINE_SUITE("maps__merge_in", maps__merge_in); diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c index 673a11a6cd1b..56014ec7d49d 100644 --- a/tools/perf/tests/mem.c +++ b/tools/perf/tests/mem.c @@ -23,7 +23,7 @@ static int check(union perf_mem_data_src data_src, return 0; } -int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused) +static int test__mem(struct test_suite *text __maybe_unused, int subtest __maybe_unused) { int ret = 0; union perf_mem_data_src src; @@ -56,3 +56,5 @@ int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused) return ret; } + +DEFINE_SUITE("Test data source output", mem); diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c index e4d0d58b97f8..b17b86391383 100644 --- a/tools/perf/tests/mem2node.c +++ b/tools/perf/tests/mem2node.c @@ -43,7 +43,7 @@ static unsigned long *get_bitmap(const char *str, int nbits) return bm && map ? bm : NULL; } -int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__mem2node(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct mem2node map; struct memory_node nodes[3]; @@ -77,3 +77,5 @@ int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused) mem2node__exit(&map); return 0; } + +DEFINE_SUITE("mem2node", mem2node); diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index d38757db2dc2..90b2feda31ac 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -29,7 +29,7 @@ * Then it checks if the number of syscalls reported as perf events by * the kernel corresponds to the number of syscalls made. */ -int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; union perf_event *event; @@ -164,3 +164,5 @@ out_free_threads: perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Read samples using the mmap interface", basic_mmap); diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 6f2da7a72f67..a4301fc7b770 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -224,7 +224,7 @@ static int mmap_events(synth_cb synth) * * by using all thread objects. */ -int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__mmap_thread_lookup(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { /* perf_event__synthesize_threads synthesize */ TEST_ASSERT_VAL("failed with sythesizing all", @@ -236,3 +236,5 @@ int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __may return 0; } + +DEFINE_SUITE("Lookup mmap thread", mmap_thread_lookup); diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index f7dd6c463f04..cd3dd463783f 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -19,7 +19,8 @@ #include "stat.h" #include "util/counts.h" -int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = -1, fd, cpu; struct perf_cpu_map *cpus; @@ -127,3 +128,5 @@ out_thread_map_delete: perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Detect openat syscall event on all cpus", openat_syscall_event_on_all_cpus); diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 5e4af2f0f14a..a7b2800652e4 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -22,7 +22,8 @@ #define AT_FDCWD -100 #endif -int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct record_opts opts = { .target = { @@ -142,3 +143,5 @@ out_delete_evlist: out: return err; } + +DEFINE_SUITE("syscalls:sys_enter_openat event fields", syscall_openat_tp_fields); diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index 85a8f0fe7aea..7f4c13c4b14d 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -13,7 +13,8 @@ #include "tests.h" #include "util/counts.h" -int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__openat_syscall_event(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = -1, fd; struct evsel *evsel; @@ -66,3 +67,5 @@ out_thread_map_delete: perf_thread_map__put(threads); return err; } + +DEFINE_SUITE("Detect openat syscall event", openat_syscall_event); diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 6af94639b14a..a508f1dbcb2a 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -2276,7 +2276,7 @@ static int test_pmu_events_alias(char *event, char *alias) return test_event(&e); } -int test__parse_events(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__parse_events(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret1, ret2 = 0; char *event, *alias; @@ -2319,3 +2319,5 @@ do { \ return ret2; } + +DEFINE_SUITE("Parse event definition strings", parse_events); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index dfc797ecc750..07b6f4ec024f 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -109,6 +109,7 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, struct evsel *evsel; u64 count; + perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); perf_stat__update_shadow_stats(evsel, count, 0, st); @@ -369,7 +370,7 @@ static int test_metric_group(void) return 0; } -int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("IPC failed", test_ipc() == 0); TEST_ASSERT_VAL("frontend failed", test_frontend() == 0); @@ -383,3 +384,5 @@ int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unu } return 0; } + +DEFINE_SUITE("Parse and process metrics", parse_metric); diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 471273676701..d62e31595ab2 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -67,7 +67,8 @@ struct test_attr_event { * * Return: %0 on success, %-1 if the test fails. */ -int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__parse_no_sample_id_all(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err; @@ -103,3 +104,5 @@ int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest _ return 0; } + +DEFINE_SUITE("Parse with no sample_id_all bit set", parse_no_sample_id_all); diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c index 58b90c42eb38..c09a9fae1689 100644 --- a/tools/perf/tests/pe-file-parsing.c +++ b/tools/perf/tests/pe-file-parsing.c @@ -68,7 +68,7 @@ static int run_dir(const char *d) return TEST_OK; } -int test__pe_file_parsing(struct test *test __maybe_unused, +static int test__pe_file_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct stat st; @@ -89,10 +89,12 @@ int test__pe_file_parsing(struct test *test __maybe_unused, #else -int test__pe_file_parsing(struct test *test __maybe_unused, +static int test__pe_file_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { return TEST_SKIP; } #endif + +DEFINE_SUITE("PE file support", pe_file_parsing); diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c index dd865e0bea12..78cdeb89645e 100644 --- a/tools/perf/tests/perf-hooks.c +++ b/tools/perf/tests/perf-hooks.c @@ -26,7 +26,7 @@ static void the_hook(void *_hook_flags) raise(SIGSEGV); } -int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_hooks(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int hook_flags = 0; @@ -45,3 +45,5 @@ int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unuse return TEST_FAIL; return TEST_OK; } + +DEFINE_SUITE("perf hooks", perf_hooks); diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 0df471bf1590..6354465067b8 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -41,7 +41,7 @@ realloc: return cpu; } -int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .target = { @@ -332,3 +332,5 @@ out_delete_evlist: out: return (err < 0 || errs > 0) ? -1 : 0; } + +DEFINE_SUITE("PERF_RECORD_* events & perf_sample fields", PERF_RECORD); diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 7c56bc1f4cff..d12d0ad81801 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -23,6 +23,16 @@ #include "pmu.h" #include "pmu-hybrid.h" +/* + * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. Just + * enable the test for x86_64/i386 and Arm64 archs. + */ +#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) +#define TSC_IS_SUPPORTED 1 +#else +#define TSC_IS_SUPPORTED 0 +#endif + #define CHECK__(x) { \ while ((x) < 0) { \ pr_debug(#x " failed!\n"); \ @@ -45,7 +55,7 @@ * %0 is returned, otherwise %-1 is returned. If TSC conversion is not * supported then then the test passes but " (not supported)" is printed. */ -int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, @@ -69,6 +79,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture"); + return TEST_SKIP; + } + threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -185,15 +200,4 @@ out_err: return err; } -bool test__tsc_is_supported(void) -{ - /* - * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. - * Just enable the test for x86_64/i386 and Arm64 archs. - */ -#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) - return true; -#else - return false; -#endif -} +DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c index e8fd0da0762b..71b76deb1f92 100644 --- a/tools/perf/tests/pfm.c +++ b/tools/perf/tests/pfm.c @@ -12,27 +12,6 @@ #include <linux/kernel.h> #ifdef HAVE_LIBPFM -static int test__pfm_events(void); -static int test__pfm_group(void); -#endif - -static const struct { - int (*func)(void); - const char *desc; -} pfm_testcase_table[] = { -#ifdef HAVE_LIBPFM - { - .func = test__pfm_events, - .desc = "test of individual --pfm-events", - }, - { - .func = test__pfm_group, - .desc = "test groups of --pfm-events", - }, -#endif -}; - -#ifdef HAVE_LIBPFM static int count_pfm_events(struct perf_evlist *evlist) { struct perf_evsel *evsel; @@ -44,7 +23,8 @@ static int count_pfm_events(struct perf_evlist *evlist) return count; } -static int test__pfm_events(void) +static int test__pfm_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evlist *evlist; struct option opt; @@ -104,7 +84,8 @@ static int test__pfm_events(void) return 0; } -static int test__pfm_group(void) +static int test__pfm_group(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct evlist *evlist; struct option opt; @@ -187,27 +168,27 @@ static int test__pfm_group(void) } return 0; } -#endif - -const char *test__pfm_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(pfm_testcase_table)) - return NULL; - return pfm_testcase_table[i].desc; -} - -int test__pfm_subtest_get_nr(void) +#else +static int test__pfm_events(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { - return (int)ARRAY_SIZE(pfm_testcase_table); + return TEST_SKIP; } -int test__pfm(struct test *test __maybe_unused, int i __maybe_unused) +static int test__pfm_group(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { -#ifdef HAVE_LIBPFM - if (i < 0 || i >= (int)ARRAY_SIZE(pfm_testcase_table)) - return TEST_FAIL; - return pfm_testcase_table[i].func(); -#else return TEST_SKIP; -#endif } +#endif + +static struct test_case pfm_tests[] = { + TEST_CASE_REASON("test of individual --pfm-events", pfm_events, "not compiled in"), + TEST_CASE_REASON("test groups of --pfm-events", pfm_group, "not compiled in"), + { .name = NULL, } +}; + +struct test_suite suite__pfm = { + .desc = "Test libpfm4 support", + .test_cases = pfm_tests, +}; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 9ae894c406d8..df1c9a3cc05b 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -418,7 +418,8 @@ static int compare_alias_to_test_event(struct perf_pmu_alias *alias, } /* Verify generated events from pmu-events.c are as expected */ -static int test_pmu_event_table(void) +static int test__pmu_event_table(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { const struct pmu_event *sys_event_tables = __test_pmu_get_sys_events_table(); const struct pmu_events_map *map = __test_pmu_get_events_map(); @@ -705,7 +706,8 @@ static struct perf_pmu_test_pmu test_pmus[] = { }; /* Test that aliases generated are as expected */ -static int test_aliases(void) +static int test__aliases(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct perf_pmu *pmu = NULL; unsigned long i; @@ -892,7 +894,8 @@ out_err: } -static int test_parsing(void) +static int test__parsing(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { const struct pmu_events_map *cpus_map = pmu_events_map__find(); const struct pmu_events_map *map; @@ -1034,7 +1037,8 @@ out: * or all defined cpus via the 'fake_pmu' * in parse_events. */ -static int test_parsing_fake(void) +static int test__parsing_fake(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { const struct pmu_events_map *map; const struct pmu_event *pe; @@ -1068,55 +1072,16 @@ static int test_parsing_fake(void) return 0; } -static const struct { - int (*func)(void); - const char *desc; -} pmu_events_testcase_table[] = { - { - .func = test_pmu_event_table, - .desc = "PMU event table sanity", - }, - { - .func = test_aliases, - .desc = "PMU event map aliases", - }, - { - .func = test_parsing, - .desc = "Parsing of PMU event table metrics", - }, - { - .func = test_parsing_fake, - .desc = "Parsing of PMU event table metrics with fake PMUs", - }, +static struct test_case pmu_events_tests[] = { + TEST_CASE("PMU event table sanity", pmu_event_table), + TEST_CASE("PMU event map aliases", aliases), + TEST_CASE_REASON("Parsing of PMU event table metrics", parsing, + "some metrics failed"), + TEST_CASE("Parsing of PMU event table metrics with fake PMUs", parsing_fake), + { .name = NULL, } }; -const char *test__pmu_events_subtest_get_desc(int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return NULL; - return pmu_events_testcase_table[subtest].desc; -} - -const char *test__pmu_events_subtest_skip_reason(int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return NULL; - if (pmu_events_testcase_table[subtest].func != test_parsing) - return NULL; - return "some metrics failed"; -} - -int test__pmu_events_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(pmu_events_testcase_table); -} - -int test__pmu_events(struct test *test __maybe_unused, int subtest) -{ - if (subtest < 0 || - subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table)) - return TEST_FAIL; - return pmu_events_testcase_table[subtest].func(); -} +struct test_suite suite__pmu_events = { + .desc = "PMU events", + .test_cases = pmu_events_tests, +}; diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 714e6830a758..8507bd615e97 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -137,7 +137,7 @@ static struct list_head *test_terms_list(void) return &terms; } -int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char *format = test_format_dir_get(); LIST_HEAD(formats); @@ -177,3 +177,5 @@ int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused) test_format_dir_put(format); return ret; } + +DEFINE_SUITE("Parse perf pmu format", pmu); diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 98c6d474aa6f..6b990ee38575 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -9,7 +9,7 @@ #include "tests.h" #include "util/debug.h" -int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__python_use(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char *cmd; int ret; @@ -23,3 +23,5 @@ int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unuse free(cmd); return ret; } + +DEFINE_SUITE("'import perf' in python", python_use); diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index c83a11514129..07f2411b0ad4 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -36,7 +36,7 @@ * These are based on the input value (213) specified * in branch_stack variable. */ -#define BS_EXPECTED_BE 0xa00d000000000000 +#define BS_EXPECTED_BE 0xa000d00000000000 #define BS_EXPECTED_LE 0xd5000000 #define FLAG(s) s->branch_stack->entries[i].flags @@ -368,7 +368,7 @@ out_free: * checks sample format bits separately and together. If the test passes %0 is * returned, otherwise %-1 is returned. */ -int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15}; u64 sample_type; @@ -426,3 +426,5 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u return 0; } + +DEFINE_SUITE("Sample parsing", sample_parsing); diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index ed76c693f65e..919712899251 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -76,7 +76,7 @@ static int search_cached_probe(const char *target, return ret; } -int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused) +static int test__sdt_event(struct test_suite *test __maybe_unused, int subtests __maybe_unused) { int ret = TEST_FAIL; char __tempdir[] = "./test-buildid-XXXXXX"; @@ -114,9 +114,11 @@ error: return ret; } #else -int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused) +static int test__sdt_event(struct test_suite *test __maybe_unused, int subtests __maybe_unused) { pr_debug("Skip SDT event test because SDT support is not compiled\n"); return TEST_SKIP; } #endif + +DEFINE_SUITE("Probe SDT events", sdt_event); diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh index 8a168cf8bacc..49bd875d5122 100755 --- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh +++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh @@ -12,7 +12,7 @@ skip_if_no_z_record() { collect_z_record() { echo "Collecting compressed record file:" - [[ "$(uname -m)" != s390x ]] && gflag='-g' + [ "$(uname -m)" != s390x ] && gflag='-g' $perf_tool record -o $trace_file $gflag -z -F 5000 -- \ dd count=500 if=/dev/urandom of=/dev/null } diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh index 2de7fd0394fd..b30dba455f36 100755 --- a/tools/perf/tests/shell/stat_all_pmu.sh +++ b/tools/perf/tests/shell/stat_all_pmu.sh @@ -7,11 +7,11 @@ set -e for p in $(perf list --raw-dump pmu); do echo "Testing $p" result=$(perf stat -e "$p" true 2>&1) - if [[ ! "$result" =~ "$p" ]] && [[ ! "$result" =~ "<not supported>" ]]; then + if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then # We failed to see the event and it is supported. Possibly the workload was # too small so retry with something longer. result=$(perf stat -e "$p" perf bench internals synthesize 2>&1) - if [[ ! "$result" =~ "$p" ]]; then + if ! echo "$result" | grep -q "$p" ; then echo "Event '$p' not printed in:" echo "$result" exit 1 diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh index 2aed20dc2262..13473aeba489 100755 --- a/tools/perf/tests/shell/stat_bpf_counters.sh +++ b/tools/perf/tests/shell/stat_bpf_counters.sh @@ -23,7 +23,7 @@ compare_number() # skip if --bpf-counters is not supported if ! perf stat --bpf-counters true > /dev/null 2>&1; then - if [ "$1" == "-v" ]; then + if [ "$1" = "-v" ]; then echo "Skipping: --bpf-counters not supported" perf --no-pager stat --bpf-counters true || true fi diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh new file mode 100755 index 000000000000..e59044edc406 --- /dev/null +++ b/tools/perf/tests/shell/test_arm_spe.sh @@ -0,0 +1,89 @@ +#!/bin/sh +# Check Arm SPE trace data recording and synthesized samples + +# Uses the 'perf record' to record trace data of Arm SPE events; +# then verify if any SPE event samples are generated by SPE with +# 'perf script' and 'perf report' commands. + +# SPDX-License-Identifier: GPL-2.0 +# German Gomez <german.gomez@arm.com>, 2021 + +skip_if_no_arm_spe_event() { + perf list | egrep -q 'arm_spe_[0-9]+//' && return 0 + + # arm_spe event doesn't exist + return 2 +} + +skip_if_no_arm_spe_event || exit 2 + +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) +glb_err=0 + +cleanup_files() +{ + rm -f ${perfdata} + exit $glb_err +} + +trap cleanup_files exit term int + +arm_spe_report() { + if [ $2 != 0 ]; then + echo "$1: FAIL" + glb_err=$2 + else + echo "$1: PASS" + fi +} + +perf_script_samples() { + echo "Looking at perf.data file for dumping samples:" + + # from arm-spe.c/arm_spe_synth_events() + events="(ld1-miss|ld1-access|llc-miss|lld-access|tlb-miss|tlb-access|branch-miss|remote-access|memory)" + + # Below is an example of the samples dumping: + # dd 3048 [002] 1 l1d-access: ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so) + # dd 3048 [002] 1 tlb-access: ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so) + # dd 3048 [002] 1 memory: ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so) + perf script -F,-time -i ${perfdata} 2>&1 | \ + egrep " +$1 +[0-9]+ .* +${events}:(.*:)? +" > /dev/null 2>&1 +} + +perf_report_samples() { + echo "Looking at perf.data file for reporting samples:" + + # Below is an example of the samples reporting: + # 73.04% 73.04% dd libc-2.27.so [.] _dl_addr + # 7.71% 7.71% dd libc-2.27.so [.] getenv + # 2.59% 2.59% dd ld-2.27.so [.] strcmp + perf report --stdio -i ${perfdata} 2>&1 | \ + egrep " +[0-9]+\.[0-9]+% +[0-9]+\.[0-9]+% +$1 " > /dev/null 2>&1 +} + +arm_spe_snapshot_test() { + echo "Recording trace with snapshot mode $perfdata" + perf record -o ${perfdata} -e arm_spe// -S \ + -- dd if=/dev/zero of=/dev/null > /dev/null 2>&1 & + PERFPID=$! + + # Wait for perf program + sleep 1 + + # Send signal to snapshot trace data + kill -USR2 $PERFPID + + # Stop perf program + kill $PERFPID + wait $PERFPID + + perf_script_samples dd && + perf_report_samples dd + + err=$? + arm_spe_report "SPE snapshot testing" $err +} + +arm_spe_snapshot_test +exit $glb_err diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c index c1911501c39c..2eb096b5e6da 100644 --- a/tools/perf/tests/stat.c +++ b/tools/perf/tests/stat.c @@ -47,7 +47,8 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat_config(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat_config(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { struct perf_stat_config stat_config = { .aggr_mode = AGGR_CORE, @@ -77,7 +78,7 @@ static int process_stat_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_counts_values count; @@ -103,7 +104,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__synthesize_stat_round(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { TEST_ASSERT_VAL("failed to synthesize stat_config", !perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL, @@ -111,3 +112,7 @@ int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __ return 0; } + +DEFINE_SUITE("Synthesize stat config", synthesize_stat_config); +DEFINE_SUITE("Synthesize stat", synthesize_stat); +DEFINE_SUITE("Synthesize stat round", synthesize_stat_round); diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 74988846be1d..9cd6fec375ee 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -133,7 +133,7 @@ out_delete_evlist: return err; } -int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__sw_clock_freq(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int ret; @@ -143,3 +143,5 @@ int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_un return ret; } + +DEFINE_SUITE("Software clock events period values", sw_clock_freq); diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 62c0ec21aaa8..0c0c2328bf4e 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -321,7 +321,7 @@ out_free_nodes: * evsel->core.system_wide and evsel->tracking flags (respectively) with other events * sometimes enabled or disabled. */ -int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__switch_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { const char *sched_switch = "sched:sched_switch"; struct switch_tracking switch_tracking = { .tids = NULL, }; @@ -588,3 +588,5 @@ out_err: err = -1; goto out; } + +DEFINE_SUITE("Track with sched_switch", switch_tracking); diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 4c2969db59b0..25f075fa9125 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -39,7 +39,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, * if the number of exit event reported by the kernel is 1 or not * in order to check the kernel returns correct number of event. */ -int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__task_exit(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = -1; union perf_event *event; @@ -151,3 +151,5 @@ out_delete_evlist: evlist__delete(evlist); return err; } + +DEFINE_SUITE("Number of exit events of a simple workload", task_exit); diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index fe1306f58495..8f65098110fc 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -27,112 +27,146 @@ enum { TEST_SKIP = -2, }; -struct test { +struct test_suite; + +typedef int (*test_fnptr)(struct test_suite *, int); + +struct test_case { + const char *name; + const char *desc; + const char *skip_reason; + test_fnptr run_case; +}; + +struct test_suite { const char *desc; - int (*func)(struct test *test, int subtest); - struct { - bool skip_if_fail; - int (*get_nr)(void); - const char *(*get_desc)(int subtest); - const char *(*skip_reason)(int subtest); - } subtest; - bool (*is_supported)(void); + struct test_case *test_cases; void *priv; }; +#define DECLARE_SUITE(name) \ + extern struct test_suite suite__##name; + +#define TEST_CASE(description, _name) \ + { \ + .name = #_name, \ + .desc = description, \ + .run_case = test__##_name, \ + } + +#define TEST_CASE_REASON(description, _name, _reason) \ + { \ + .name = #_name, \ + .desc = description, \ + .run_case = test__##_name, \ + .skip_reason = _reason, \ + } + +#define DEFINE_SUITE(description, _name) \ + struct test_case tests__##_name[] = { \ + TEST_CASE(description, _name), \ + { .name = NULL, } \ + }; \ + struct test_suite suite__##_name = { \ + .desc = description, \ + .test_cases = tests__##_name, \ + } + /* Tests */ -int test__vmlinux_matches_kallsyms(struct test *test, int subtest); -int test__openat_syscall_event(struct test *test, int subtest); -int test__openat_syscall_event_on_all_cpus(struct test *test, int subtest); -int test__basic_mmap(struct test *test, int subtest); -int test__PERF_RECORD(struct test *test, int subtest); -int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest); -int test__perf_evsel__tp_sched_test(struct test *test, int subtest); -int test__syscall_openat_tp_fields(struct test *test, int subtest); -int test__pmu(struct test *test, int subtest); -int test__pmu_events(struct test *test, int subtest); -const char *test__pmu_events_subtest_get_desc(int subtest); -const char *test__pmu_events_subtest_skip_reason(int subtest); -int test__pmu_events_subtest_get_nr(void); -int test__attr(struct test *test, int subtest); -int test__dso_data(struct test *test, int subtest); -int test__dso_data_cache(struct test *test, int subtest); -int test__dso_data_reopen(struct test *test, int subtest); -int test__parse_events(struct test *test, int subtest); -int test__hists_link(struct test *test, int subtest); -int test__python_use(struct test *test, int subtest); -int test__bp_signal(struct test *test, int subtest); -int test__bp_signal_overflow(struct test *test, int subtest); -int test__bp_accounting(struct test *test, int subtest); -int test__wp(struct test *test, int subtest); -const char *test__wp_subtest_get_desc(int subtest); -const char *test__wp_subtest_skip_reason(int subtest); -int test__wp_subtest_get_nr(void); -int test__task_exit(struct test *test, int subtest); -int test__mem(struct test *test, int subtest); -int test__sw_clock_freq(struct test *test, int subtest); -int test__code_reading(struct test *test, int subtest); -int test__sample_parsing(struct test *test, int subtest); -int test__keep_tracking(struct test *test, int subtest); -int test__parse_no_sample_id_all(struct test *test, int subtest); -int test__dwarf_unwind(struct test *test, int subtest); -int test__expr(struct test *test, int subtest); -int test__hists_filter(struct test *test, int subtest); -int test__mmap_thread_lookup(struct test *test, int subtest); -int test__thread_maps_share(struct test *test, int subtest); -int test__hists_output(struct test *test, int subtest); -int test__hists_cumulate(struct test *test, int subtest); -int test__switch_tracking(struct test *test, int subtest); -int test__fdarray__filter(struct test *test, int subtest); -int test__fdarray__add(struct test *test, int subtest); -int test__kmod_path__parse(struct test *test, int subtest); -int test__thread_map(struct test *test, int subtest); -int test__llvm(struct test *test, int subtest); -const char *test__llvm_subtest_get_desc(int subtest); -int test__llvm_subtest_get_nr(void); -int test__bpf(struct test *test, int subtest); -const char *test__bpf_subtest_get_desc(int subtest); -int test__bpf_subtest_get_nr(void); -int test__session_topology(struct test *test, int subtest); -int test__thread_map_synthesize(struct test *test, int subtest); -int test__thread_map_remove(struct test *test, int subtest); -int test__cpu_map_synthesize(struct test *test, int subtest); -int test__synthesize_stat_config(struct test *test, int subtest); -int test__synthesize_stat(struct test *test, int subtest); -int test__synthesize_stat_round(struct test *test, int subtest); -int test__event_update(struct test *test, int subtest); -int test__event_times(struct test *test, int subtest); -int test__backward_ring_buffer(struct test *test, int subtest); -int test__cpu_map_print(struct test *test, int subtest); -int test__cpu_map_merge(struct test *test, int subtest); -int test__sdt_event(struct test *test, int subtest); -int test__is_printable_array(struct test *test, int subtest); -int test__bitmap_print(struct test *test, int subtest); -int test__perf_hooks(struct test *test, int subtest); -int test__clang(struct test *test, int subtest); -const char *test__clang_subtest_get_desc(int subtest); -int test__clang_subtest_get_nr(void); -int test__unit_number__scnprint(struct test *test, int subtest); -int test__mem2node(struct test *t, int subtest); -int test__maps__merge_in(struct test *t, int subtest); -int test__time_utils(struct test *t, int subtest); -int test__jit_write_elf(struct test *test, int subtest); -int test__api_io(struct test *test, int subtest); -int test__demangle_java(struct test *test, int subtest); -int test__demangle_ocaml(struct test *test, int subtest); -int test__pfm(struct test *test, int subtest); -const char *test__pfm_subtest_get_desc(int subtest); -int test__pfm_subtest_get_nr(void); -int test__parse_metric(struct test *test, int subtest); -int test__pe_file_parsing(struct test *test, int subtest); -int test__expand_cgroup_events(struct test *test, int subtest); -int test__perf_time_to_tsc(struct test *test, int subtest); -int test__dlfilter(struct test *test, int subtest); - -bool test__bp_signal_is_supported(void); -bool test__bp_account_is_supported(void); -bool test__wp_is_supported(void); -bool test__tsc_is_supported(void); +DECLARE_SUITE(vmlinux_matches_kallsyms); +DECLARE_SUITE(openat_syscall_event); +DECLARE_SUITE(openat_syscall_event_on_all_cpus); +DECLARE_SUITE(basic_mmap); +DECLARE_SUITE(PERF_RECORD); +DECLARE_SUITE(perf_evsel__roundtrip_name_test); +DECLARE_SUITE(perf_evsel__tp_sched_test); +DECLARE_SUITE(syscall_openat_tp_fields); +DECLARE_SUITE(pmu); +DECLARE_SUITE(pmu_events); +DECLARE_SUITE(attr); +DECLARE_SUITE(dso_data); +DECLARE_SUITE(dso_data_cache); +DECLARE_SUITE(dso_data_reopen); +DECLARE_SUITE(parse_events); +DECLARE_SUITE(hists_link); +DECLARE_SUITE(python_use); +DECLARE_SUITE(bp_signal); +DECLARE_SUITE(bp_signal_overflow); +DECLARE_SUITE(bp_accounting); +DECLARE_SUITE(wp); +DECLARE_SUITE(task_exit); +DECLARE_SUITE(mem); +DECLARE_SUITE(sw_clock_freq); +DECLARE_SUITE(code_reading); +DECLARE_SUITE(sample_parsing); +DECLARE_SUITE(keep_tracking); +DECLARE_SUITE(parse_no_sample_id_all); +DECLARE_SUITE(dwarf_unwind); +DECLARE_SUITE(expr); +DECLARE_SUITE(hists_filter); +DECLARE_SUITE(mmap_thread_lookup); +DECLARE_SUITE(thread_maps_share); +DECLARE_SUITE(hists_output); +DECLARE_SUITE(hists_cumulate); +DECLARE_SUITE(switch_tracking); +DECLARE_SUITE(fdarray__filter); +DECLARE_SUITE(fdarray__add); +DECLARE_SUITE(kmod_path__parse); +DECLARE_SUITE(thread_map); +DECLARE_SUITE(llvm); +DECLARE_SUITE(bpf); +DECLARE_SUITE(session_topology); +DECLARE_SUITE(thread_map_synthesize); +DECLARE_SUITE(thread_map_remove); +DECLARE_SUITE(cpu_map_synthesize); +DECLARE_SUITE(synthesize_stat_config); +DECLARE_SUITE(synthesize_stat); +DECLARE_SUITE(synthesize_stat_round); +DECLARE_SUITE(event_update); +DECLARE_SUITE(event_times); +DECLARE_SUITE(backward_ring_buffer); +DECLARE_SUITE(cpu_map_print); +DECLARE_SUITE(cpu_map_merge); +DECLARE_SUITE(sdt_event); +DECLARE_SUITE(is_printable_array); +DECLARE_SUITE(bitmap_print); +DECLARE_SUITE(perf_hooks); +DECLARE_SUITE(clang); +DECLARE_SUITE(unit_number__scnprint); +DECLARE_SUITE(mem2node); +DECLARE_SUITE(maps__merge_in); +DECLARE_SUITE(time_utils); +DECLARE_SUITE(jit_write_elf); +DECLARE_SUITE(api_io); +DECLARE_SUITE(demangle_java); +DECLARE_SUITE(demangle_ocaml); +DECLARE_SUITE(pfm); +DECLARE_SUITE(parse_metric); +DECLARE_SUITE(pe_file_parsing); +DECLARE_SUITE(expand_cgroup_events); +DECLARE_SUITE(perf_time_to_tsc); +DECLARE_SUITE(dlfilter); + +/* + * PowerPC and S390 do not support creation of instruction breakpoints using the + * perf_event interface. + * + * ARM requires explicit rounding down of the instruction pointer in Thumb mode, + * and then requires the single-step to be handled explicitly in the overflow + * handler to avoid stepping into the SIGIO handler and getting stuck on the + * breakpointed instruction. + * + * Since arm64 has the same issue with arm for the single-step handling, this + * case also gets stuck on the breakpointed instruction. + * + * Just disable the test for these architectures until these issues are + * resolved. + */ +#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || defined(__aarch64__) +#define BP_SIGNAL_IS_SUPPORTED 0 +#else +#define BP_SIGNAL_IS_SUPPORTED 1 +#endif #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; @@ -142,7 +176,7 @@ int test__arch_unwind_sample(struct perf_sample *sample, #endif #if defined(__arm__) -int test__vectors_page(struct test *test, int subtest); +DECLARE_SUITE(vectors_page); #endif #endif /* TESTS_H */ diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index d1e208b4a571..e413c1387fcb 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -19,7 +19,7 @@ struct machine; #define NAME (const char *) "perf" #define NAMEUL (unsigned long) NAME -int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *map; @@ -86,7 +86,7 @@ static int process_event(struct perf_tool *tool __maybe_unused, return 0; } -int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map_synthesize(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *threads; @@ -106,7 +106,7 @@ int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __ return 0; } -int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_map_remove(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct perf_thread_map *threads; char *str; @@ -145,3 +145,7 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb perf_thread_map__put(threads); return 0; } + +DEFINE_SUITE("Thread map", thread_map); +DEFINE_SUITE("Synthesize thread map", thread_map_synthesize); +DEFINE_SUITE("Remove thread map", thread_map_remove); diff --git a/tools/perf/tests/thread-maps-share.c b/tools/perf/tests/thread-maps-share.c index 9371484973f2..84edd82c519e 100644 --- a/tools/perf/tests/thread-maps-share.c +++ b/tools/perf/tests/thread-maps-share.c @@ -4,7 +4,7 @@ #include "thread.h" #include "debug.h" -int test__thread_maps_share(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__thread_maps_share(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { struct machines machines; struct machine *machine; @@ -96,3 +96,5 @@ int test__thread_maps_share(struct test *test __maybe_unused, int subtest __mayb machines__exit(&machines); return 0; } + +DEFINE_SUITE("Share thread maps", thread_maps_share); diff --git a/tools/perf/tests/time-utils-test.c b/tools/perf/tests/time-utils-test.c index fe57ca3b6e54..38df10373c1e 100644 --- a/tools/perf/tests/time-utils-test.c +++ b/tools/perf/tests/time-utils-test.c @@ -131,7 +131,7 @@ out: return pass; } -int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__time_utils(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { bool pass = true; @@ -249,3 +249,5 @@ int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused) return pass ? 0 : TEST_FAIL; } + +DEFINE_SUITE("time utils", time_utils); diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 4574c46260d9..869986139146 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -175,7 +175,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) return 0; } -int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__session_topology(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char path[PATH_MAX]; struct perf_cpu_map *map; @@ -201,3 +201,5 @@ free_path: unlink(path); return ret; } + +DEFINE_SUITE("Session topology", session_topology); diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c index 3721757435da..88bcada1c78f 100644 --- a/tools/perf/tests/unit_number__scnprintf.c +++ b/tools/perf/tests/unit_number__scnprintf.c @@ -7,7 +7,7 @@ #include "units.h" #include "debug.h" -int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __maybe_unused) +static int test__unit_number__scnprint(struct test_suite *t __maybe_unused, int subtest __maybe_unused) { struct { u64 n; @@ -38,3 +38,5 @@ int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __may return TEST_OK; } + +DEFINE_SUITE("unit_number__scnprintf", unit_number__scnprint); diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 4f884aabc7f4..e80df13c0420 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -111,7 +111,8 @@ static bool is_ignored_symbol(const char *name, char type) return false; } -int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused) +static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { int err = -1; struct rb_node *nd; @@ -352,3 +353,5 @@ out: machine__exit(&vmlinux); return err; } + +DEFINE_SUITE("vmlinux symtab matches kallsyms", vmlinux_matches_kallsyms); diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c index 9387fa76faa5..9d4c45184e71 100644 --- a/tools/perf/tests/wp.c +++ b/tools/perf/tests/wp.c @@ -21,6 +21,7 @@ do { \ volatile u64 data1; volatile u8 data2[3]; +#ifndef __s390x__ static int wp_read(int fd, long long *count, int size) { int ret = read(fd, count, size); @@ -61,9 +62,14 @@ static int __event(int wp_type, void *wp_addr, unsigned long wp_len) return fd; } +#endif -static int wp_ro_test(void) +static int test__wp_ro(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) || defined(__x86_64__) || defined(__i386__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -79,10 +85,15 @@ static int wp_ro_test(void) close(fd); return 0; +#endif } -static int wp_wo_test(void) +static int test__wp_wo(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -98,10 +109,15 @@ static int wp_wo_test(void) close(fd); return 0; +#endif } -static int wp_rw_test(void) +static int test__wp_rw(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd; unsigned long tmp, tmp1 = rand(); @@ -118,10 +134,15 @@ static int wp_rw_test(void) close(fd); return 0; +#endif } -static int wp_modify_test(void) +static int test__wp_modify(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { +#if defined(__s390x__) + return TEST_SKIP; +#else int fd, ret; unsigned long tmp = rand(); struct perf_event_attr new_attr; @@ -163,93 +184,18 @@ static int wp_modify_test(void) close(fd); return 0; -} - -static bool wp_ro_supported(void) -{ -#if defined (__x86_64__) || defined (__i386__) - return false; -#else - return true; -#endif -} - -static const char *wp_ro_skip_msg(void) -{ -#if defined (__x86_64__) || defined (__i386__) - return "missing hardware support"; -#else - return NULL; #endif } -static struct { - const char *desc; - int (*target_func)(void); - bool (*is_supported)(void); - const char *(*skip_msg)(void); -} wp_testcase_table[] = { - { - .desc = "Read Only Watchpoint", - .target_func = &wp_ro_test, - .is_supported = &wp_ro_supported, - .skip_msg = &wp_ro_skip_msg, - }, - { - .desc = "Write Only Watchpoint", - .target_func = &wp_wo_test, - }, - { - .desc = "Read / Write Watchpoint", - .target_func = &wp_rw_test, - }, - { - .desc = "Modify Watchpoint", - .target_func = &wp_modify_test, - }, +static struct test_case wp_tests[] = { + TEST_CASE_REASON("Read Only Watchpoint", wp_ro, "missing hardware support"), + TEST_CASE_REASON("Write Only Watchpoint", wp_wo, "missing hardware support"), + TEST_CASE_REASON("Read / Write Watchpoint", wp_rw, "missing hardware support"), + TEST_CASE_REASON("Modify Watchpoint", wp_modify, "missing hardware support"), + { .name = NULL, } }; -int test__wp_subtest_get_nr(void) -{ - return (int)ARRAY_SIZE(wp_testcase_table); -} - -const char *test__wp_subtest_get_desc(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return NULL; - return wp_testcase_table[i].desc; -} - -const char *test__wp_subtest_skip_reason(int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return NULL; - if (!wp_testcase_table[i].skip_msg) - return NULL; - return wp_testcase_table[i].skip_msg(); -} - -int test__wp(struct test *test __maybe_unused, int i) -{ - if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) - return TEST_FAIL; - - if (wp_testcase_table[i].is_supported && - !wp_testcase_table[i].is_supported()) - return TEST_SKIP; - - return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL; -} - -/* The s390 so far does not have support for - * instruction breakpoint using the perf_event_open() system call. - */ -bool test__wp_is_supported(void) -{ -#if defined(__s390x__) - return false; -#else - return true; -#endif -} +struct test_suite suite__wp = { + .desc = "Watchpoint", + .test_cases = wp_tests, +}; diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index d6dfe68a7612..f527a46ab4e7 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -62,6 +62,8 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_ extern struct strarray strarray__socket_families; +extern struct strarray strarray__socket_level; + /** * augmented_arg: extra payload for syscall pointer arguments @@ -230,6 +232,9 @@ size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg); #define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol +size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_SK_LEVEL syscall_arg__scnprintf_socket_level + size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c index cd110634ab09..2e0e867c0c1b 100644 --- a/tools/perf/trace/beauty/sockaddr.c +++ b/tools/perf/trace/beauty/sockaddr.c @@ -7,7 +7,7 @@ #include <sys/un.h> #include <arpa/inet.h> -#include "trace/beauty/generated/socket_arrays.c" +#include "trace/beauty/generated/sockaddr.c" DEFINE_STRARRAY(socket_families, "PF_"); static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size) diff --git a/tools/perf/trace/beauty/sockaddr.sh b/tools/perf/trace/beauty/sockaddr.sh new file mode 100755 index 000000000000..3820e5c82293 --- /dev/null +++ b/tools/perf/trace/beauty/sockaddr.sh @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: LGPL-2.1 + +# This one uses a copy from the kernel sources headers that is in a +# place used just for these tools/perf/beauty/ usage, we shouldn't not +# put it in tools/include/linux otherwise they would be used in the +# normal compiler building process and would drag needless stuff from the +# kernel. + +# When what these scripts need is already in tools/include/ then use it, +# otherwise grab and check the copy from the kernel sources just for these +# string table building scripts. + +[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/ + +printf "static const char *socket_families[] = {\n" +# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */ +regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*' + +egrep $regex ${header_dir}/socket.h | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[%s] = \"%s\",\n" | \ + egrep -v "\"(UNIX|MAX)\"" +printf "};\n" diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c index f23a3dda2902..b0870c7b48e5 100644 --- a/tools/perf/trace/beauty/socket.c +++ b/tools/perf/trace/beauty/socket.c @@ -9,9 +9,10 @@ #include <sys/types.h> #include <sys/socket.h> +#include "trace/beauty/generated/socket.c" + static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size, bool show_prefix) { -#include "trace/beauty/generated/socket_ipproto_array.c" static DEFINE_STRARRAY(socket_ipproto, "IPPROTO_"); return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", show_prefix, protocol); @@ -26,3 +27,21 @@ size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct sysc return syscall_arg__scnprintf_int(bf, size, arg); } + +static size_t socket__scnprintf_level(int level, char *bf, size_t size, bool show_prefix) +{ +#if defined(__alpha__) || defined(__hppa__) || defined(__mips__) || defined(__sparc__) + const int sol_socket = 0xffff; +#else + const int sol_socket = 1; +#endif + if (level == sol_socket) + return scnprintf(bf, size, "%sSOCKET", show_prefix ? "SOL_" : ""); + + return strarray__scnprintf(&strarray__socket_level, bf, size, "%d", show_prefix, level); +} + +size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg) +{ + return socket__scnprintf_level(arg->val, bf, size, arg->show_string_prefix); +} diff --git a/tools/perf/trace/beauty/socket.sh b/tools/perf/trace/beauty/socket.sh index 3820e5c82293..76330acb27e5 100755 --- a/tools/perf/trace/beauty/socket.sh +++ b/tools/perf/trace/beauty/socket.sh @@ -1,24 +1,28 @@ #!/bin/sh # SPDX-License-Identifier: LGPL-2.1 -# This one uses a copy from the kernel sources headers that is in a -# place used just for these tools/perf/beauty/ usage, we shouldn't not -# put it in tools/include/linux otherwise they would be used in the -# normal compiler building process and would drag needless stuff from the -# kernel. +if [ $# -gt 0 ] ; then + uapi_header_dir=$1 + beauty_header_dir=$2 +else + uapi_header_dir=tools/include/uapi/linux/ + beauty_header_dir=tools/perf/trace/beauty/include/linux/ +fi -# When what these scripts need is already in tools/include/ then use it, -# otherwise grab and check the copy from the kernel sources just for these -# string table building scripts. +printf "static const char *socket_ipproto[] = {\n" +ipproto_regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' -[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/ +egrep $ipproto_regex ${uapi_header_dir}/in.h | \ + sed -r "s/$ipproto_regex/\2 \1/g" | \ + sort -n | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n\n" -printf "static const char *socket_families[] = {\n" -# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */ -regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*' +printf "static const char *socket_level[] = {\n" +socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+\/.*)?' -egrep $regex ${header_dir}/socket.h | \ - sed -r "s/$regex/\2 \1/g" | \ - xargs printf "\t[%s] = \"%s\",\n" | \ - egrep -v "\"(UNIX|MAX)\"" -printf "};\n" +egrep $socket_level_regex ${beauty_header_dir}/socket.h | \ + sed -r "s/$socket_level_regex/\2 \1/g" | \ + sort -n | xargs printf "\t[%s] = \"%s\",\n" +printf "};\n\n" + +printf 'DEFINE_STRARRAY(socket_level, "SOL_");\n' diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh deleted file mode 100755 index de0f2f29017f..000000000000 --- a/tools/perf/trace/beauty/socket_ipproto.sh +++ /dev/null @@ -1,12 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: LGPL-2.1 - -[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ - -printf "static const char *socket_ipproto[] = {\n" -regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*' - -egrep $regex ${header_dir}/in.h | \ - sed -r "s/$regex/\2 \1/g" | \ - sort | xargs printf "\t[%s] = \"%s\",\n" -printf "};\n" diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index c1f24d004852..5075ecead5f3 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -535,6 +535,18 @@ struct perf_hpp_list perf_hpp_list = { #undef __HPP_SORT_ACC_FN #undef __HPP_SORT_RAW_FN +static void fmt_free(struct perf_hpp_fmt *fmt) +{ + /* + * At this point fmt should be completely + * unhooked, if not it's a bug. + */ + BUG_ON(!list_empty(&fmt->list)); + BUG_ON(!list_empty(&fmt->sort_list)); + + if (fmt->free) + fmt->free(fmt); +} void perf_hpp__init(void) { @@ -598,9 +610,10 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list, list_add(&format->sort_list, &list->sorts); } -void perf_hpp__column_unregister(struct perf_hpp_fmt *format) +static void perf_hpp__column_unregister(struct perf_hpp_fmt *format) { list_del_init(&format->list); + fmt_free(format); } void perf_hpp__cancel_cumulate(void) @@ -672,19 +685,6 @@ next: } -static void fmt_free(struct perf_hpp_fmt *fmt) -{ - /* - * At this point fmt should be completely - * unhooked, if not it's a bug. - */ - BUG_ON(!list_empty(&fmt->list)); - BUG_ON(!list_empty(&fmt->sort_list)); - - if (fmt->free) - fmt->free(fmt); -} - void perf_hpp__reset_output_field(struct perf_hpp_list *list) { struct perf_hpp_fmt *fmt, *tmp; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 8511af55fc3a..01900689dc00 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1255,6 +1255,17 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name); } +void annotation__init(struct annotation *notes) +{ + pthread_mutex_init(¬es->lock, NULL); +} + +void annotation__exit(struct annotation *notes) +{ + annotated_source__delete(notes->src); + pthread_mutex_destroy(¬es->lock); +} + static void annotation_line__add(struct annotation_line *al, struct list_head *head) { list_add_tail(&al->node, head); @@ -3132,7 +3143,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, notes->nr_events = nr_pcnt; annotation__update_column_widths(notes); - sym->annotate2 = true; + sym->annotate2 = 1; return 0; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 3757416bcf46..986f2bbe4870 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -299,6 +299,9 @@ struct annotation { struct annotated_source *src; }; +void annotation__init(struct annotation *notes); +void annotation__exit(struct annotation *notes); + static inline int annotation__cycles_width(struct annotation *notes) { if (notes->have_cycles && notes->options->show_minmax_cycle) diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 32fe41835fa6..3fc528c9270c 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -151,6 +151,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) u64 payload, ip; memset(&decoder->record, 0x0, sizeof(decoder->record)); + decoder->record.context_id = (u64)-1; while (1) { err = arm_spe_get_next_packet(decoder); @@ -180,6 +181,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) case ARM_SPE_COUNTER: break; case ARM_SPE_CONTEXT: + decoder->record.context_id = payload; break; case ARM_SPE_OP_TYPE: if (idx == SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC) { diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index 59bdb7309674..46a8556a9e95 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -38,6 +38,7 @@ struct arm_spe_record { u64 timestamp; u64 virt_addr; u64 phys_addr; + u64 context_id; }; struct arm_spe_insn; diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 58b7069c5a5f..fccac06b573a 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -51,6 +51,7 @@ struct arm_spe { u8 timeless_decoding; u8 data_queued; + u64 sample_type; u8 sample_flc; u8 sample_llc; u8 sample_tlb; @@ -71,6 +72,7 @@ struct arm_spe { u64 kernel_start; unsigned long num_events; + u8 use_ctx_pkt_for_pid; }; struct arm_spe_queue { @@ -100,7 +102,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused, const char *color = PERF_COLOR_BLUE; color_fprintf(stdout, color, - ". ... ARM SPE data: size %zu bytes\n", + ". ... ARM SPE data: size %#zx bytes\n", len); while (len) { @@ -226,6 +228,44 @@ static inline u8 arm_spe_cpumode(struct arm_spe *spe, u64 ip) PERF_RECORD_MISC_USER; } +static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe, + struct auxtrace_queue *queue) +{ + struct arm_spe_queue *speq = queue->priv; + pid_t tid; + + tid = machine__get_current_tid(spe->machine, speq->cpu); + if (tid != -1) { + speq->tid = tid; + thread__zput(speq->thread); + } else + speq->tid = queue->tid; + + if ((!speq->thread) && (speq->tid != -1)) { + speq->thread = machine__find_thread(spe->machine, -1, + speq->tid); + } + + if (speq->thread) { + speq->pid = speq->thread->pid_; + if (queue->cpu == -1) + speq->cpu = speq->thread->cpu; + } +} + +static int arm_spe_set_tid(struct arm_spe_queue *speq, pid_t tid) +{ + struct arm_spe *spe = speq->spe; + int err = machine__set_current_tid(spe->machine, speq->cpu, -1, tid); + + if (err) + return err; + + arm_spe_set_pid_tid_cpu(spe, &spe->queues.queue_array[speq->queue_nr]); + + return 0; +} + static void arm_spe_prep_sample(struct arm_spe *spe, struct arm_spe_queue *speq, union perf_event *event, @@ -248,6 +288,12 @@ static void arm_spe_prep_sample(struct arm_spe *spe, event->sample.header.size = sizeof(struct perf_event_header); } +static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type) +{ + event->header.size = perf_event__sample_event_size(sample, type, 0); + return perf_event__synthesize_sample(event, type, 0, sample); +} + static inline int arm_spe_deliver_synth_event(struct arm_spe *spe, struct arm_spe_queue *speq __maybe_unused, @@ -256,6 +302,12 @@ arm_spe_deliver_synth_event(struct arm_spe *spe, { int ret; + if (spe->synth_opts.inject) { + ret = arm_spe__inject_event(event, sample, spe->sample_type); + if (ret) + return ret; + } + ret = perf_session__deliver_synth_event(spe->session, event, sample); if (ret) pr_err("ARM SPE: failed to deliver event, error %d\n", ret); @@ -460,6 +512,19 @@ static int arm_spe_run_decoder(struct arm_spe_queue *speq, u64 *timestamp) * can correlate samples between Arm SPE trace data and other * perf events with correct time ordering. */ + + /* + * Update pid/tid info. + */ + record = &speq->decoder->record; + if (!spe->timeless_decoding && record->context_id != (u64)-1) { + ret = arm_spe_set_tid(speq, record->context_id); + if (ret) + return ret; + + spe->use_ctx_pkt_for_pid = true; + } + ret = arm_spe_sample(speq); if (ret) return ret; @@ -586,31 +651,6 @@ static bool arm_spe__is_timeless_decoding(struct arm_spe *spe) return timeless_decoding; } -static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe, - struct auxtrace_queue *queue) -{ - struct arm_spe_queue *speq = queue->priv; - pid_t tid; - - tid = machine__get_current_tid(spe->machine, speq->cpu); - if (tid != -1) { - speq->tid = tid; - thread__zput(speq->thread); - } else - speq->tid = queue->tid; - - if ((!speq->thread) && (speq->tid != -1)) { - speq->thread = machine__find_thread(spe->machine, -1, - speq->tid); - } - - if (speq->thread) { - speq->pid = speq->thread->pid_; - if (queue->cpu == -1) - speq->cpu = speq->thread->cpu; - } -} - static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp) { unsigned int queue_nr; @@ -641,7 +681,12 @@ static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp) ts = timestamp; } - arm_spe_set_pid_tid_cpu(spe, queue); + /* + * A previous context-switch event has set pid/tid in the machine's context, so + * here we need to update the pid/tid in the thread and SPE queue. + */ + if (!spe->use_ctx_pkt_for_pid) + arm_spe_set_pid_tid_cpu(spe, queue); ret = arm_spe_run_decoder(speq, &ts); if (ret < 0) { @@ -681,6 +726,25 @@ static int arm_spe_process_timeless_queues(struct arm_spe *spe, pid_t tid, return 0; } +static int arm_spe_context_switch(struct arm_spe *spe, union perf_event *event, + struct perf_sample *sample) +{ + pid_t pid, tid; + int cpu; + + if (!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT)) + return 0; + + pid = event->context_switch.next_prev_pid; + tid = event->context_switch.next_prev_tid; + cpu = sample->cpu; + + if (tid == -1) + pr_warning("context_switch event has no tid\n"); + + return machine__set_current_tid(spe->machine, cpu, pid, tid); +} + static int arm_spe_process_event(struct perf_session *session, union perf_event *event, struct perf_sample *sample, @@ -718,6 +782,13 @@ static int arm_spe_process_event(struct perf_session *session, } } else if (timestamp) { err = arm_spe_process_queues(spe, timestamp); + if (err) + return err; + + if (!spe->use_ctx_pkt_for_pid && + (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE || + event->header.type == PERF_RECORD_SWITCH)) + err = arm_spe_context_switch(spe, event, sample); } return err; @@ -783,7 +854,15 @@ static int arm_spe_flush(struct perf_session *session __maybe_unused, return arm_spe_process_timeless_queues(spe, -1, MAX_TIMESTAMP - 1); - return arm_spe_process_queues(spe, MAX_TIMESTAMP); + ret = arm_spe_process_queues(spe, MAX_TIMESTAMP); + if (ret) + return ret; + + if (!spe->use_ctx_pkt_for_pid) + ui__warning("Arm SPE CONTEXT packets not found in the traces.\n" + "Matching of TIDs to SPE events could be inaccurate.\n"); + + return 0; } static void arm_spe_free_queue(void *priv) @@ -920,6 +999,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) else attr.sample_type |= PERF_SAMPLE_TIME; + spe->sample_type = attr.sample_type; + attr.exclude_user = evsel->core.attr.exclude_user; attr.exclude_kernel = evsel->core.attr.exclude_kernel; attr.exclude_hv = evsel->core.attr.exclude_hv; diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 4d3b4cdce176..a517eaa51eb3 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -33,6 +33,33 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id) return err ? ERR_PTR(err) : btf; } +struct bpf_program * __weak +bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return bpf_program__next(prev, obj); +#pragma GCC diagnostic pop +} + +struct bpf_map * __weak +bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return bpf_map__next(prev, obj); +#pragma GCC diagnostic pop +} + +const void * __weak +btf__raw_data(const struct btf *btf_ro, __u32 *size) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return btf__get_raw_data(btf_ro, size); +#pragma GCC diagnostic pop +} + static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len) { int ret = 0; @@ -119,7 +146,11 @@ static int perf_env__fetch_btf(struct perf_env *env, node->data_size = data_size; memcpy(node->data, data, data_size); - perf_env__insert_btf(env, node); + if (!perf_env__insert_btf(env, node)) { + /* Insertion failed because of a duplicate. */ + free(node); + return -1; + } return 0; } diff --git a/tools/perf/util/bpf_skel/bperf.h b/tools/perf/util/bpf_skel/bperf.h deleted file mode 100644 index 186a5551ddb9..000000000000 --- a/tools/perf/util/bpf_skel/bperf.h +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -// Copyright (c) 2021 Facebook - -#ifndef __BPERF_STAT_H -#define __BPERF_STAT_H - -typedef struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); - __uint(max_entries, 1); -} reading_map; - -#endif /* __BPERF_STAT_H */ diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c index b8fa3cb2da23..f193998530d4 100644 --- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c @@ -1,14 +1,23 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bperf.h" #include "bperf_u.h" -reading_map diff_readings SEC(".maps"); -reading_map accum_readings SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} diff_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} accum_readings SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_HASH); diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c index 4f70d1459e86..e2a2d4cd7779 100644 --- a/tools/perf/util/bpf_skel/bperf_leader.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c @@ -1,10 +1,8 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bperf.h" struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -13,8 +11,19 @@ struct { __uint(map_flags, BPF_F_PRESERVE_ELEMS); } events SEC(".maps"); -reading_map prev_readings SEC(".maps"); -reading_map diff_readings SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} prev_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} diff_readings SEC(".maps"); SEC("raw_tp/sched_switch") int BPF_PROG(on_switch) diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c index ab12b4c4ece2..97037d3b3d9f 100644 --- a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c +++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2020 Facebook -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h index 2df8a45bd088..d3731a876b6c 100644 --- a/tools/perf/util/c++/clang-c.h +++ b/tools/perf/util/c++/clang-c.h @@ -12,8 +12,9 @@ extern "C" { extern void perf_clang__init(void); extern void perf_clang__cleanup(void); -extern int test__clang_to_IR(void); -extern int test__clang_to_obj(void); +struct test_suite; +extern int test__clang_to_IR(struct test_suite *test, int subtest); +extern int test__clang_to_obj(struct test_suite *test, int subtest); extern int perf_clang__compile_bpf(const char *filename, void **p_obj_buf, @@ -26,9 +27,6 @@ extern int perf_clang__compile_bpf(const char *filename, static inline void perf_clang__init(void) { } static inline void perf_clang__cleanup(void) { } -static inline int test__clang_to_IR(void) { return -1; } -static inline int test__clang_to_obj(void) { return -1;} - static inline int perf_clang__compile_bpf(const char *filename __maybe_unused, void **p_obj_buf __maybe_unused, diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp index 21b23605f78b..a4683ca53697 100644 --- a/tools/perf/util/c++/clang-test.cpp +++ b/tools/perf/util/c++/clang-test.cpp @@ -35,7 +35,8 @@ __test__clang_to_IR(void) } extern "C" { -int test__clang_to_IR(void) +int test__clang_to_IR(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { perf_clang_scope _scope; @@ -48,7 +49,8 @@ int test__clang_to_IR(void) return -1; } -int test__clang_to_obj(void) +int test__clang_to_obj(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) { perf_clang_scope _scope; diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index ec77e2a7b3ca..51b429c86f98 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -14,14 +14,16 @@ #include "env.h" #include "pmu-hybrid.h" -#define CORE_SIB_FMT \ +#define PACKAGE_CPUS_FMT \ + "%s/devices/system/cpu/cpu%d/topology/package_cpus_list" +#define PACKAGE_CPUS_FMT_OLD \ "%s/devices/system/cpu/cpu%d/topology/core_siblings_list" -#define DIE_SIB_FMT \ +#define DIE_CPUS_FMT \ "%s/devices/system/cpu/cpu%d/topology/die_cpus_list" -#define THRD_SIB_FMT \ - "%s/devices/system/cpu/cpu%d/topology/thread_siblings_list" -#define THRD_SIB_FMT_NEW \ +#define CORE_CPUS_FMT \ "%s/devices/system/cpu/cpu%d/topology/core_cpus_list" +#define CORE_CPUS_FMT_OLD \ + "%s/devices/system/cpu/cpu%d/topology/thread_siblings_list" #define NODE_ONLINE_FMT \ "%s/devices/system/node/online" #define NODE_MEMINFO_FMT \ @@ -39,8 +41,12 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu) u32 i = 0; int ret = -1; - scnprintf(filename, MAXPATHLEN, CORE_SIB_FMT, + scnprintf(filename, MAXPATHLEN, PACKAGE_CPUS_FMT, sysfs__mountpoint(), cpu); + if (access(filename, F_OK) == -1) { + scnprintf(filename, MAXPATHLEN, PACKAGE_CPUS_FMT_OLD, + sysfs__mountpoint(), cpu); + } fp = fopen(filename, "r"); if (!fp) goto try_dies; @@ -54,23 +60,23 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu) if (p) *p = '\0'; - for (i = 0; i < tp->core_sib; i++) { - if (!strcmp(buf, tp->core_siblings[i])) + for (i = 0; i < tp->package_cpus_lists; i++) { + if (!strcmp(buf, tp->package_cpus_list[i])) break; } - if (i == tp->core_sib) { - tp->core_siblings[i] = buf; - tp->core_sib++; + if (i == tp->package_cpus_lists) { + tp->package_cpus_list[i] = buf; + tp->package_cpus_lists++; buf = NULL; len = 0; } ret = 0; try_dies: - if (!tp->die_siblings) + if (!tp->die_cpus_list) goto try_threads; - scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT, + scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT, sysfs__mountpoint(), cpu); fp = fopen(filename, "r"); if (!fp) @@ -85,23 +91,23 @@ try_dies: if (p) *p = '\0'; - for (i = 0; i < tp->die_sib; i++) { - if (!strcmp(buf, tp->die_siblings[i])) + for (i = 0; i < tp->die_cpus_lists; i++) { + if (!strcmp(buf, tp->die_cpus_list[i])) break; } - if (i == tp->die_sib) { - tp->die_siblings[i] = buf; - tp->die_sib++; + if (i == tp->die_cpus_lists) { + tp->die_cpus_list[i] = buf; + tp->die_cpus_lists++; buf = NULL; len = 0; } ret = 0; try_threads: - scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT_NEW, + scnprintf(filename, MAXPATHLEN, CORE_CPUS_FMT, sysfs__mountpoint(), cpu); if (access(filename, F_OK) == -1) { - scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT, + scnprintf(filename, MAXPATHLEN, CORE_CPUS_FMT_OLD, sysfs__mountpoint(), cpu); } fp = fopen(filename, "r"); @@ -115,13 +121,13 @@ try_threads: if (p) *p = '\0'; - for (i = 0; i < tp->thread_sib; i++) { - if (!strcmp(buf, tp->thread_siblings[i])) + for (i = 0; i < tp->core_cpus_lists; i++) { + if (!strcmp(buf, tp->core_cpus_list[i])) break; } - if (i == tp->thread_sib) { - tp->thread_siblings[i] = buf; - tp->thread_sib++; + if (i == tp->core_cpus_lists) { + tp->core_cpus_list[i] = buf; + tp->core_cpus_lists++; buf = NULL; } ret = 0; @@ -139,16 +145,14 @@ void cpu_topology__delete(struct cpu_topology *tp) if (!tp) return; - for (i = 0 ; i < tp->core_sib; i++) - zfree(&tp->core_siblings[i]); + for (i = 0 ; i < tp->package_cpus_lists; i++) + zfree(&tp->package_cpus_list[i]); - if (tp->die_sib) { - for (i = 0 ; i < tp->die_sib; i++) - zfree(&tp->die_siblings[i]); - } + for (i = 0 ; i < tp->die_cpus_lists; i++) + zfree(&tp->die_cpus_list[i]); - for (i = 0 ; i < tp->thread_sib; i++) - zfree(&tp->thread_siblings[i]); + for (i = 0 ; i < tp->core_cpus_lists; i++) + zfree(&tp->core_cpus_list[i]); free(tp); } @@ -164,7 +168,7 @@ static bool has_die_topology(void) if (strncmp(uts.machine, "x86_64", 6)) return false; - scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT, + scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT, sysfs__mountpoint(), 0); if (access(filename, F_OK) == -1) return false; @@ -205,13 +209,13 @@ struct cpu_topology *cpu_topology__new(void) tp = addr; addr += sizeof(*tp); - tp->core_siblings = addr; + tp->package_cpus_list = addr; addr += sz; if (has_die) { - tp->die_siblings = addr; + tp->die_cpus_list = addr; addr += sz; } - tp->thread_siblings = addr; + tp->core_cpus_list = addr; for (i = 0; i < nr; i++) { if (!cpu_map__has(map, i)) diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h index d9af97177068..854e18f9041e 100644 --- a/tools/perf/util/cputopo.h +++ b/tools/perf/util/cputopo.h @@ -5,12 +5,33 @@ #include <linux/types.h> struct cpu_topology { - u32 core_sib; - u32 die_sib; - u32 thread_sib; - char **core_siblings; - char **die_siblings; - char **thread_siblings; + /* The number of unique package_cpus_lists below. */ + u32 package_cpus_lists; + /* The number of unique die_cpu_lists below. */ + u32 die_cpus_lists; + /* The number of unique core_cpu_lists below. */ + u32 core_cpus_lists; + /* + * An array of strings where each string is unique and read from + * /sys/devices/system/cpu/cpuX/topology/package_cpus_list. From the ABI + * each of these is a human-readable list of CPUs sharing the same + * physical_package_id. The format is like 0-3, 8-11, 14,17. + */ + const char **package_cpus_list; + /* + * An array of string where each string is unique and from + * /sys/devices/system/cpu/cpuX/topology/die_cpus_list. From the ABI + * each of these is a human-readable list of CPUs within the same die. + * The format is like 0-3, 8-11, 14,17. + */ + const char **die_cpus_list; + /* + * An array of string where each string is unique and from + * /sys/devices/system/cpu/cpuX/topology/core_cpus_list. From the ABI + * each of these is a human-readable list of CPUs within the same + * core. The format is like 0-3, 8-11, 14,17. + */ + const char **core_cpus_list; }; struct numa_topology_node { diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index f323adb1af85..4f672f7d008c 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -537,7 +537,7 @@ static void cs_etm__dump_event(struct cs_etm_queue *etmq, fprintf(stdout, "\n"); color_fprintf(stdout, color, - ". ... CoreSight %s Trace data: size %zu bytes\n", + ". ... CoreSight %s Trace data: size %#zx bytes\n", cs_etm_decoder__get_name(etmq->decoder), buffer->size); do { diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 17f1dd0680b4..b9904896eb97 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -75,12 +75,13 @@ out: return node; } -void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) +bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) { struct rb_node *parent = NULL; __u32 btf_id = btf_node->id; struct btf_node *node; struct rb_node **p; + bool ret = true; down_write(&env->bpf_progs.lock); p = &env->bpf_progs.btfs.rb_node; @@ -94,6 +95,7 @@ void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) p = &(*p)->rb_right; } else { pr_debug("duplicated btf %u\n", btf_id); + ret = false; goto out; } } @@ -103,6 +105,7 @@ void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node) env->bpf_progs.btfs_cnt++; out: up_write(&env->bpf_progs.lock); + return ret; } struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index 1383876f72b3..163e5ec503a2 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -167,7 +167,7 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node); struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, __u32 prog_id); -void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); +bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node); struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id); int perf_env__numa_node(struct perf_env *env, int cpu); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index ec967fb8d7d9..ac0127be0459 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -241,7 +241,7 @@ void evsel__init(struct evsel *evsel, { perf_evsel__init(&evsel->core, attr, idx); evsel->tracking = !idx; - evsel->unit = ""; + evsel->unit = strdup(""); evsel->scale = 1.0; evsel->max_events = ULONG_MAX; evsel->evlist = NULL; @@ -276,13 +276,8 @@ struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) } if (evsel__is_clock(evsel)) { - /* - * The evsel->unit points to static alias->unit - * so it's ok to use static string in here. - */ - static const char *unit = "msec"; - - evsel->unit = unit; + free((char *)evsel->unit); + evsel->unit = strdup("msec"); evsel->scale = 1e-6; } @@ -420,7 +415,11 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->max_events = orig->max_events; evsel->tool_event = orig->tool_event; - evsel->unit = orig->unit; + free((char *)evsel->unit); + evsel->unit = strdup(orig->unit); + if (evsel->unit == NULL) + goto out_err; + evsel->scale = orig->scale; evsel->snapshot = orig->snapshot; evsel->per_pkg = orig->per_pkg; @@ -1441,6 +1440,7 @@ void evsel__exit(struct evsel *evsel) zfree(&evsel->group_name); zfree(&evsel->name); zfree(&evsel->pmu_name); + zfree(&evsel->unit); zfree(&evsel->metric_id); evsel__zero_per_pkg(evsel); hashmap__free(evsel->per_pkg_mask); @@ -3037,3 +3037,15 @@ void evsel__set_leader(struct evsel *evsel, struct evsel *leader) { evsel->core.leader = &leader->core; } + +int evsel__source_count(const struct evsel *evsel) +{ + struct evsel *pos; + int count = 0; + + evlist__for_each_entry(evsel->evlist, pos) { + if (pos->metric_leader == evsel) + count++; + } + return count; +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 3ea687141afa..29d49a8c1e92 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -489,6 +489,7 @@ struct evsel *evsel__leader(struct evsel *evsel); bool evsel__has_leader(struct evsel *evsel, struct evsel *leader); bool evsel__is_leader(struct evsel *evsel); void evsel__set_leader(struct evsel *evsel, struct evsel *leader); +int evsel__source_count(const struct evsel *evsel); /* * Macro to swap the bit-field postition and size. diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 77c6ad81a923..1d532b9fed29 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -5,13 +5,17 @@ #include <stdlib.h> #include <string.h> #include "metricgroup.h" +#include "cpumap.h" +#include "cputopo.h" #include "debug.h" #include "expr.h" #include "expr-bison.h" #include "expr-flex.h" +#include "smt.h" #include <linux/kernel.h> #include <linux/zalloc.h> #include <ctype.h> +#include <math.h> #ifdef PARSER_DEBUG extern int expr_debug; @@ -19,7 +23,10 @@ extern int expr_debug; struct expr_id_data { union { - double val; + struct { + double val; + int source_count; + } val; struct { double val; const char *metric_name; @@ -137,6 +144,13 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id) /* Caller must make sure id is allocated */ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) { + return expr__add_id_val_source_count(ctx, id, val, /*source_count=*/1); +} + +/* Caller must make sure id is allocated */ +int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id, + double val, int source_count) +{ struct expr_id_data *data_ptr = NULL, *old_data = NULL; char *old_key = NULL; int ret; @@ -144,7 +158,8 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) data_ptr = malloc(sizeof(*data_ptr)); if (!data_ptr) return -ENOMEM; - data_ptr->val = val; + data_ptr->val.val = val; + data_ptr->val.source_count = source_count; data_ptr->kind = EXPR_ID_DATA__VALUE; ret = hashmap__set(ctx->ids, id, data_ptr, @@ -240,7 +255,7 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, switch (data->kind) { case EXPR_ID_DATA__VALUE: - pr_debug2("lookup(%s): val %f\n", id, data->val); + pr_debug2("lookup(%s): val %f\n", id, data->val.val); break; case EXPR_ID_DATA__REF: pr_debug2("lookup(%s): ref metric name %s\n", id, @@ -251,7 +266,7 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, pr_debug("%s failed to count\n", id); return -1; } - pr_debug("processing metric: %s EXIT: %f\n", id, data->val); + pr_debug("processing metric: %s EXIT: %f\n", id, data->ref.val); break; case EXPR_ID_DATA__REF_VALUE: pr_debug2("lookup(%s): ref val %f metric name %s\n", id, @@ -366,7 +381,47 @@ int expr__find_ids(const char *expr, const char *one, double expr_id_data__value(const struct expr_id_data *data) { if (data->kind == EXPR_ID_DATA__VALUE) - return data->val; + return data->val.val; assert(data->kind == EXPR_ID_DATA__REF_VALUE); return data->ref.val; } + +double expr_id_data__source_count(const struct expr_id_data *data) +{ + assert(data->kind == EXPR_ID_DATA__VALUE); + return data->val.source_count; +} + +double expr__get_literal(const char *literal) +{ + static struct cpu_topology *topology; + + if (!strcmp("#smt_on", literal)) + return smt_on() > 0 ? 1.0 : 0.0; + + if (!strcmp("#num_cpus", literal)) + return cpu__max_present_cpu(); + + /* + * Assume that topology strings are consistent, such as CPUs "0-1" + * wouldn't be listed as "0,1", and so after deduplication the number of + * these strings gives an indication of the number of packages, dies, + * etc. + */ + if (!topology) { + topology = cpu_topology__new(); + if (!topology) { + pr_err("Error creating CPU topology"); + return NAN; + } + } + if (!strcmp("#num_packages", literal)) + return topology->package_cpus_lists; + if (!strcmp("#num_dies", literal)) + return topology->die_cpus_lists; + if (!strcmp("#num_cores", literal)) + return topology->core_cpus_lists; + + pr_err("Unrecognized literal '%s'", literal); + return NAN; +} diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index cf81f9166dbb..bd2116983bbb 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -40,6 +40,8 @@ void expr__ctx_free(struct expr_parse_ctx *ctx); void expr__del_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id(struct expr_parse_ctx *ctx, const char *id); int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val); +int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id, + double val, int source_count); int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref); int expr__get_id(struct expr_parse_ctx *ctx, const char *id, struct expr_id_data **data); @@ -55,5 +57,7 @@ int expr__find_ids(const char *expr, const char *one, struct expr_parse_ctx *ids); double expr_id_data__value(const struct expr_id_data *data); +double expr_id_data__source_count(const struct expr_id_data *data); +double expr__get_literal(const char *literal); #endif diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l index bd20f33418ba..0a13eb20c814 100644 --- a/tools/perf/util/expr.l +++ b/tools/perf/util/expr.l @@ -6,6 +6,7 @@ #include <linux/compiler.h> #include "expr.h" #include "expr-bison.h" +#include <math.h> char *expr_get_text(yyscan_t yyscanner); YYSTYPE *expr_get_lval(yyscan_t yyscanner); @@ -77,6 +78,17 @@ static int str(yyscan_t scanner, int token, int runtime) yylval->str = normalize(yylval->str, runtime); return token; } + +static int literal(yyscan_t scanner) +{ + YYSTYPE *yylval = expr_get_lval(scanner); + + yylval->num = expr__get_literal(expr_get_text(scanner)); + if (isnan(yylval->num)) + return EXPR_ERROR; + + return LITERAL; +} %} number ([0-9]+\.?[0-9]*|[0-9]*\.?[0-9]+) @@ -85,6 +97,7 @@ sch [-,=] spec \\{sch} sym [0-9a-zA-Z_\.:@?]+ symbol ({spec}|{sym})+ +literal #[0-9a-zA-Z_\.\-]+ %% struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner); @@ -94,7 +107,8 @@ max { return MAX; } min { return MIN; } if { return IF; } else { return ELSE; } -#smt_on { return SMT_ON; } +source_count { return SOURCE_COUNT; } +{literal} { return literal(yyscanner); } {number} { return value(yyscanner); } {symbol} { return str(yyscanner, ID, sctx->runtime); } "|" { return '|'; } diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index f969dfa525bd..a30b825adb7b 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -3,8 +3,8 @@ #define YYDEBUG 1 #include <assert.h> #include <math.h> +#include <stdlib.h> #include "util/debug.h" -#include "smt.h" #define IN_EXPR_Y 1 #include "expr.h" %} @@ -37,7 +37,7 @@ } ids; } -%token ID NUMBER MIN MAX IF ELSE SMT_ON D_RATIO EXPR_ERROR +%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT EXPR_ERROR %left MIN MAX IF %left '|' %left '^' @@ -46,7 +46,7 @@ %left '-' '+' %left '*' '/' '%' %left NEG NOT -%type <num> NUMBER +%type <num> NUMBER LITERAL %type <str> ID %destructor { free ($$); } <str> %type <ids> expr if_expr @@ -83,6 +83,41 @@ static struct ids union_expr(struct ids ids1, struct ids ids2) return result; } +static struct ids handle_id(struct expr_parse_ctx *ctx, char *id, + bool compute_ids, bool source_count) +{ + struct ids result; + + if (!compute_ids) { + /* + * Compute the event's value from ID. If the ID isn't known then + * it isn't used to compute the formula so set to NAN. + */ + struct expr_id_data *data; + + result.val = NAN; + if (expr__resolve_id(ctx, id, &data) == 0) { + result.val = source_count + ? expr_id_data__source_count(data) + : expr_id_data__value(data); + } + result.ids = NULL; + free(id); + } else { + /* + * Set the value to BOTTOM to show that any value is possible + * when the event is computed. Create a set of just the ID. + */ + result.val = BOTTOM; + result.ids = ids__new(); + if (!result.ids || ids__insert(result.ids, id)) { + pr_err("Error creating IDs for '%s'", id); + free(id); + } + } + return result; +} + /* * If we're not computing ids or $1 and $3 are constants, compute the new * constant value using OP. Its invariant that there are no ids. If computing @@ -168,32 +203,8 @@ expr: NUMBER $$.val = $1; $$.ids = NULL; } -| ID -{ - if (!compute_ids) { - /* - * Compute the event's value from ID. If the ID isn't known then - * it isn't used to compute the formula so set to NAN. - */ - struct expr_id_data *data; - - $$.val = NAN; - if (expr__resolve_id(ctx, $1, &data) == 0) - $$.val = expr_id_data__value(data); - - $$.ids = NULL; - free($1); - } else { - /* - * Set the value to BOTTOM to show that any value is possible - * when the event is computed. Create a set of just the ID. - */ - $$.val = BOTTOM; - $$.ids = ids__new(); - if (!$$.ids || ids__insert($$.ids, $1)) - YYABORT; - } -} +| ID { $$ = handle_id(ctx, $1, compute_ids, /*source_count=*/false); } +| SOURCE_COUNT '(' ID ')' { $$ = handle_id(ctx, $3, compute_ids, /*source_count=*/true); } | expr '|' expr { BINARY_LONG_OP($$, |, $1, $3); } | expr '&' expr { BINARY_LONG_OP($$, &, $1, $3); } | expr '^' expr { BINARY_LONG_OP($$, ^, $1, $3); } @@ -280,9 +291,9 @@ expr: NUMBER $$ = union_expr($3, $5); } } -| SMT_ON +| LITERAL { - $$.val = smt_on() > 0 ? 1.0 : 0.0; + $$.val = $1; $$.ids = NULL; } ; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 56511db8fa03..e3c1a532d059 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -583,21 +583,21 @@ static int write_cpu_topology(struct feat_fd *ff, if (!tp) return -1; - ret = do_write(ff, &tp->core_sib, sizeof(tp->core_sib)); + ret = do_write(ff, &tp->package_cpus_lists, sizeof(tp->package_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->core_sib; i++) { - ret = do_write_string(ff, tp->core_siblings[i]); + for (i = 0; i < tp->package_cpus_lists; i++) { + ret = do_write_string(ff, tp->package_cpus_list[i]); if (ret < 0) goto done; } - ret = do_write(ff, &tp->thread_sib, sizeof(tp->thread_sib)); + ret = do_write(ff, &tp->core_cpus_lists, sizeof(tp->core_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->thread_sib; i++) { - ret = do_write_string(ff, tp->thread_siblings[i]); + for (i = 0; i < tp->core_cpus_lists; i++) { + ret = do_write_string(ff, tp->core_cpus_list[i]); if (ret < 0) break; } @@ -617,15 +617,15 @@ static int write_cpu_topology(struct feat_fd *ff, return ret; } - if (!tp->die_sib) + if (!tp->die_cpus_lists) goto done; - ret = do_write(ff, &tp->die_sib, sizeof(tp->die_sib)); + ret = do_write(ff, &tp->die_cpus_lists, sizeof(tp->die_cpus_lists)); if (ret < 0) goto done; - for (i = 0; i < tp->die_sib; i++) { - ret = do_write_string(ff, tp->die_siblings[i]); + for (i = 0; i < tp->die_cpus_lists; i++) { + ret = do_write_string(ff, tp->die_cpus_list[i]); if (ret < 0) goto done; } @@ -2321,6 +2321,7 @@ out: #define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \ static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \ {\ + free(ff->ph->env.__feat_env); \ ff->ph->env.__feat_env = do_read_string(ff); \ return ff->ph->env.__feat_env ? 0 : -ENOMEM; \ } @@ -4124,6 +4125,7 @@ int perf_event__process_feature(struct perf_session *session, struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; int type = fe->header.type; u64 feat = fe->feat_id; + int ret = 0; if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { pr_warning("invalid record type %d in pipe-mode\n", type); @@ -4141,11 +4143,13 @@ int perf_event__process_feature(struct perf_session *session, ff.size = event->header.size - sizeof(*fe); ff.ph = &session->header; - if (feat_ops[feat].process(&ff, NULL)) - return -1; + if (feat_ops[feat].process(&ff, NULL)) { + ret = -1; + goto out; + } if (!feat_ops[feat].print || !tool->show_feat_hdr) - return 0; + goto out; if (!feat_ops[feat].full_only || tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { @@ -4154,8 +4158,9 @@ int perf_event__process_feature(struct perf_session *session, fprintf(stdout, "# %s info available, use -I to display\n", feat_ops[feat].name); } - - return 0; +out: + free_event_desc(ff.events); + return ret; } size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) @@ -4257,9 +4262,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, switch (ev->type) { case PERF_EVENT_UPDATE__UNIT: + free((char *)evsel->unit); evsel->unit = strdup(ev->data); break; case PERF_EVENT_UPDATE__NAME: + free(evsel->name); evsel->name = strdup(ev->data); break; case PERF_EVENT_UPDATE__SCALE: @@ -4268,11 +4275,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, break; case PERF_EVENT_UPDATE__CPUS: ev_cpus = (struct perf_record_event_update_cpus *)ev->data; - map = cpu_map__new_data(&ev_cpus->cpus); - if (map) + if (map) { + perf_cpu_map__put(evsel->core.own_cpus); evsel->core.own_cpus = map; - else + } else pr_err("failed to get event_update cpus\n"); default: break; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 65fe65ba03c2..b776465e04ef 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -289,15 +289,10 @@ static long hist_time(unsigned long htime) return htime; } -static void he_stat__add_period(struct he_stat *he_stat, u64 period, - u64 weight, u64 ins_lat, u64 p_stage_cyc) +static void he_stat__add_period(struct he_stat *he_stat, u64 period) { - he_stat->period += period; - he_stat->weight += weight; he_stat->nr_events += 1; - he_stat->ins_lat += ins_lat; - he_stat->p_stage_cyc += p_stage_cyc; } static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) @@ -308,9 +303,6 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) dest->period_guest_sys += src->period_guest_sys; dest->period_guest_us += src->period_guest_us; dest->nr_events += src->nr_events; - dest->weight += src->weight; - dest->ins_lat += src->ins_lat; - dest->p_stage_cyc += src->p_stage_cyc; } static void he_stat__decay(struct he_stat *he_stat) @@ -598,9 +590,6 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, struct hist_entry *he; int64_t cmp; u64 period = entry->stat.period; - u64 weight = entry->stat.weight; - u64 ins_lat = entry->stat.ins_lat; - u64 p_stage_cyc = entry->stat.p_stage_cyc; bool leftmost = true; p = &hists->entries_in->rb_root.rb_node; @@ -619,11 +608,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, if (!cmp) { if (sample_self) { - he_stat__add_period(&he->stat, period, weight, ins_lat, p_stage_cyc); + he_stat__add_period(&he->stat, period); hist_entry__add_callchain_period(he, period); } if (symbol_conf.cumulate_callchain) - he_stat__add_period(he->stat_acc, period, weight, ins_lat, p_stage_cyc); + he_stat__add_period(he->stat_acc, period); /* * This mem info was allocated from sample__resolve_mem @@ -733,9 +722,6 @@ __hists__add_entry(struct hists *hists, .stat = { .nr_events = 1, .period = sample->period, - .weight = sample->weight, - .ins_lat = sample->ins_lat, - .p_stage_cyc = sample->p_stage_cyc, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent) | al->filtered, @@ -748,6 +734,9 @@ __hists__add_entry(struct hists *hists, .raw_size = sample->raw_size, .ops = ops, .time = hist_time(sample->time), + .weight = sample->weight, + .ins_lat = sample->ins_lat, + .p_stage_cyc = sample->p_stage_cyc, }, *he = hists__findnew_entry(hists, &entry, al, sample_self); if (!hists->has_callchains && he && he->callchain_size != 0) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 5343b62476e6..621f35ae1efa 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -369,7 +369,6 @@ enum { }; void perf_hpp__init(void); -void perf_hpp__column_unregister(struct perf_hpp_fmt *format); void perf_hpp__cancel_cumulate(void); void perf_hpp__setup_output_field(struct perf_hpp_list *list); void perf_hpp__reset_output_field(struct perf_hpp_list *list); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5bfb6f892489..ba74fdf74af9 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -402,8 +402,10 @@ static int add_event_tool(struct list_head *list, int *idx, if (!evsel) return -ENOMEM; evsel->tool_event = tool_event; - if (tool_event == PERF_TOOL_DURATION_TIME) - evsel->unit = "ns"; + if (tool_event == PERF_TOOL_DURATION_TIME) { + free((char *)evsel->unit); + evsel->unit = strdup("ns"); + } return 0; } @@ -1630,7 +1632,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, if (parse_state->fake_pmu) return 0; - evsel->unit = info.unit; + free((char *)evsel->unit); + evsel->unit = strdup(info.unit); evsel->scale = info.scale; evsel->per_pkg = info.per_pkg; evsel->snapshot = info.snapshot; diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c index 20bacd5972ad..34f1b1b1176c 100644 --- a/tools/perf/util/smt.c +++ b/tools/perf/util/smt.c @@ -15,7 +15,7 @@ int smt_on(void) if (cached) return cached_result; - if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0) + if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) goto done; ncpu = sysconf(_SC_NPROCESSORS_CONF); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 568a88c001c6..a111065b484e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1325,88 +1325,68 @@ struct sort_entry sort_mispredict = { .se_width_idx = HISTC_MISPREDICT, }; -static u64 he_weight(struct hist_entry *he) -{ - return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0; -} - static int64_t -sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right) +sort__weight_cmp(struct hist_entry *left, struct hist_entry *right) { - return he_weight(left) - he_weight(right); + return left->weight - right->weight; } static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he)); + return repsep_snprintf(bf, size, "%-*llu", width, he->weight); } struct sort_entry sort_local_weight = { .se_header = "Local Weight", - .se_cmp = sort__local_weight_cmp, + .se_cmp = sort__weight_cmp, .se_snprintf = hist_entry__local_weight_snprintf, .se_width_idx = HISTC_LOCAL_WEIGHT, }; -static int64_t -sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right) -{ - return left->stat.weight - right->stat.weight; -} - static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight); + return repsep_snprintf(bf, size, "%-*llu", width, + he->weight * he->stat.nr_events); } struct sort_entry sort_global_weight = { .se_header = "Weight", - .se_cmp = sort__global_weight_cmp, + .se_cmp = sort__weight_cmp, .se_snprintf = hist_entry__global_weight_snprintf, .se_width_idx = HISTC_GLOBAL_WEIGHT, }; -static u64 he_ins_lat(struct hist_entry *he) -{ - return he->stat.nr_events ? he->stat.ins_lat / he->stat.nr_events : 0; -} - static int64_t -sort__local_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right) +sort__ins_lat_cmp(struct hist_entry *left, struct hist_entry *right) { - return he_ins_lat(left) - he_ins_lat(right); + return left->ins_lat - right->ins_lat; } static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*u", width, he_ins_lat(he)); + return repsep_snprintf(bf, size, "%-*u", width, he->ins_lat); } struct sort_entry sort_local_ins_lat = { .se_header = "Local INSTR Latency", - .se_cmp = sort__local_ins_lat_cmp, + .se_cmp = sort__ins_lat_cmp, .se_snprintf = hist_entry__local_ins_lat_snprintf, .se_width_idx = HISTC_LOCAL_INS_LAT, }; -static int64_t -sort__global_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right) -{ - return left->stat.ins_lat - right->stat.ins_lat; -} - static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*u", width, he->stat.ins_lat); + return repsep_snprintf(bf, size, "%-*u", width, + he->ins_lat * he->stat.nr_events); } struct sort_entry sort_global_ins_lat = { .se_header = "INSTR Latency", - .se_cmp = sort__global_ins_lat_cmp, + .se_cmp = sort__ins_lat_cmp, .se_snprintf = hist_entry__global_ins_lat_snprintf, .se_width_idx = HISTC_GLOBAL_INS_LAT, }; @@ -1414,13 +1394,13 @@ struct sort_entry sort_global_ins_lat = { static int64_t sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right) { - return left->stat.p_stage_cyc - right->stat.p_stage_cyc; + return left->p_stage_cyc - right->p_stage_cyc; } static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { - return repsep_snprintf(bf, size, "%-*u", width, he->stat.p_stage_cyc); + return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc); } struct sort_entry sort_p_stage_cyc = { diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index b67c469aba79..7b7145501933 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -49,9 +49,6 @@ struct he_stat { u64 period_us; u64 period_guest_sys; u64 period_guest_us; - u64 weight; - u64 ins_lat; - u64 p_stage_cyc; u32 nr_events; }; @@ -109,6 +106,9 @@ struct hist_entry { s32 socket; s32 cpu; u64 code_page_size; + u64 weight; + u64 ins_lat; + u64 p_stage_cyc; u8 cpumode; u8 depth; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index e4fb02b05130..5c7308efa768 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -829,10 +829,12 @@ static int prepare_metric(struct evsel **metric_events, struct saved_value *v; struct stats *stats; u64 metric_total = 0; + int source_count; if (!strcmp(metric_events[i]->name, "duration_time")) { stats = &walltime_nsecs_stats; scale = 1e-9; + source_count = 1; } else { v = saved_value_lookup(metric_events[i], cpu, false, STAT_NONE, 0, st, @@ -841,6 +843,7 @@ static int prepare_metric(struct evsel **metric_events, break; stats = &v->stats; scale = 1.0; + source_count = evsel__source_count(metric_events[i]); if (v->metric_other) metric_total = v->metric_total; @@ -849,7 +852,9 @@ static int prepare_metric(struct evsel **metric_events, if (!n) return -ENOMEM; - expr__add_id_val(pctx, n, metric_total ? : avg_stats(stats) * scale); + expr__add_id_val_source_count(pctx, n, + metric_total ? : avg_stats(stats) * scale, + source_count); } for (j = 0; metric_refs && metric_refs[j].metric_name; j++) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index aa1b7c12fd61..b2ed3140a1fa 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -274,7 +274,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char * if (symbol_conf.priv_size) { if (symbol_conf.init_annotation) { struct annotation *notes = (void *)sym; - pthread_mutex_init(¬es->lock, NULL); + annotation__init(notes); } sym = ((void *)sym) + symbol_conf.priv_size; } @@ -294,6 +294,13 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char * void symbol__delete(struct symbol *sym) { + if (symbol_conf.priv_size) { + if (symbol_conf.init_annotation) { + struct annotation *notes = symbol__annotation(sym); + + annotation__exit(notes); + } + } free(((void *)sym) - symbol_conf.priv_size); } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 166196686f2e..fbf866d82dcc 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -40,22 +40,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, GElf_Shdr *shp, const char *name, size_t *idx); #endif -/** struct symbol - symtab entry - * - * @ignore - resolvable but tools ignore it (e.g. idle routines) +/** + * A symtab entry. When allocated this may be preceded by an annotation (see + * symbol__annotation), a browser_index (see symbol__browser_index) and rb_node + * to sort by name (see struct symbol_name_rb_node). */ struct symbol { struct rb_node rb_node; + /** Range of symbol [start, end). */ u64 start; u64 end; + /** Length of the string name. */ u16 namelen; + /** ELF symbol type as defined for st_info. E.g STT_OBJECT or STT_FUNC. */ u8 type:4; + /** ELF binding type as defined for st_info. E.g. STB_WEAK or STB_GLOBAL. */ u8 binding:4; + /** Set true for kernel symbols of idle routines. */ u8 idle:1; + /** Resolvable but tools ignore it (e.g. idle routines). */ u8 ignore:1; + /** Symbol for an inlined function. */ u8 inlined:1; + /** Has symbol__annotate2 been performed. */ + u8 annotate2:1; + /** Architecture specific. Unused except on PPC where it holds st_other. */ u8 arch_sym; - bool annotate2; + /** The name of length namelen associated with the symbol. */ char name[]; }; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 37a9492edb3e..df3c4671be72 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -379,32 +379,32 @@ fetch_kernel_version(unsigned int *puint, char *str, return 0; } -const char *perf_tip(const char *dirpath) +int perf_tip(char **strp, const char *dirpath) { struct strlist *tips; struct str_node *node; - char *tip = NULL; struct strlist_config conf = { .dirname = dirpath, .file_only = true, }; + int ret = 0; + *strp = NULL; tips = strlist__new("tips.txt", &conf); if (tips == NULL) - return errno == ENOENT ? NULL : - "Tip: check path of tips.txt or get more memory! ;-p"; + return -errno; if (strlist__nr_entries(tips) == 0) goto out; node = strlist__entry(tips, random() % strlist__nr_entries(tips)); - if (asprintf(&tip, "Tip: %s", node->s) < 0) - tip = (char *)"Tip: get more memory! ;-)"; + if (asprintf(strp, "Tip: %s", node->s) < 0) + ret = -ENOMEM; out: strlist__delete(tips); - return tip; + return ret; } char *perf_exe(char *buf, int len) diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index ad737052e597..9f0d36ba77f2 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -39,7 +39,7 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_FMT "%d.%d.%d" #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) -const char *perf_tip(const char *dirpath); +int perf_tip(char **strp, const char *dirpath); #ifndef HAVE_SCHED_GETCPU_SUPPORT int sched_getcpu(void); diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h index 565fccdfe6e9..016cff473cfc 100644 --- a/tools/testing/radix-tree/linux/lockdep.h +++ b/tools/testing/radix-tree/linux/lockdep.h @@ -1,5 +1,8 @@ #ifndef _LINUX_LOCKDEP_H #define _LINUX_LOCKDEP_H + +#include <linux/spinlock.h> + struct lock_class_key { unsigned int a; }; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index cd73dccaeb09..a795bca4c8ec 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -183,7 +183,7 @@ DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ - BPFTOOL_OUTPUT=$(BUILD_DIR)/bpftool/ \ + BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ cp $(RUNQSLOWER_OUTPUT)runqslower $@ diff --git a/tools/testing/selftests/bpf/prog_tests/helper_restricted.c b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c new file mode 100644 index 000000000000..e1de5f80c3b2 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_helper_restricted.skel.h" + +void test_helper_restricted(void) +{ + int prog_i = 0, prog_cnt; + int duration = 0; + + do { + struct test_helper_restricted *test; + int maybeOK; + + test = test_helper_restricted__open(); + if (!ASSERT_OK_PTR(test, "open")) + return; + + prog_cnt = test->skeleton->prog_cnt; + + for (int j = 0; j < prog_cnt; ++j) { + struct bpf_program *prog = *test->skeleton->progs[j].prog; + + maybeOK = bpf_program__set_autoload(prog, prog_i == j); + ASSERT_OK(maybeOK, "set autoload"); + } + + maybeOK = test_helper_restricted__load(test); + CHECK(!maybeOK, test->skeleton->progs[prog_i].name, "helper isn't restricted"); + + test_helper_restricted__destroy(test); + } while (++prog_i < prog_cnt); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c index 94423902685d..c21e3f545371 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c @@ -49,7 +49,7 @@ int dump_unix(struct bpf_iter__unix *ctx) sock_i_ino(sk)); if (unix_sk->addr) { - if (!UNIX_ABSTRACT(unix_sk)) { + if (unix_sk->addr->name->sun_path[0]) { BPF_SEQ_PRINTF(seq, " %s", unix_sk->addr->name->sun_path); } else { /* The name of the abstract UNIX domain socket starts diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index eef5646ddb19..e0f42601be9b 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -6,8 +6,6 @@ #define AF_INET6 10 #define __SO_ACCEPTCON (1 << 16) -#define UNIX_HASH_SIZE 256 -#define UNIX_ABSTRACT(unix_sk) (unix_sk->addr->hash < UNIX_HASH_SIZE) #define SOL_TCP 6 #define TCP_CONGESTION 13 diff --git a/tools/testing/selftests/bpf/progs/test_helper_restricted.c b/tools/testing/selftests/bpf/progs/test_helper_restricted.c new file mode 100644 index 000000000000..68d64c365f90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_helper_restricted.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <time.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct timer { + struct bpf_timer t; +}; + +struct lock { + struct bpf_spin_lock l; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct timer); +} timers SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct lock); +} locks SEC(".maps"); + +static int timer_cb(void *map, int *key, struct timer *timer) +{ + return 0; +} + +static void timer_work(void) +{ + struct timer *timer; + const int key = 0; + + timer = bpf_map_lookup_elem(&timers, &key); + if (timer) { + bpf_timer_init(&timer->t, &timers, CLOCK_MONOTONIC); + bpf_timer_set_callback(&timer->t, timer_cb); + bpf_timer_start(&timer->t, 10E9, 0); + bpf_timer_cancel(&timer->t); + } +} + +static void spin_lock_work(void) +{ + const int key = 0; + struct lock *lock; + + lock = bpf_map_lookup_elem(&locks, &key); + if (lock) { + bpf_spin_lock(&lock->l); + bpf_spin_unlock(&lock->l); + } +} + +SEC("raw_tp/sys_enter") +int raw_tp_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int tp_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("kprobe/sys_nanosleep") +int kprobe_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("perf_event") +int perf_event_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("raw_tp/sys_enter") +int raw_tp_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int tp_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("kprobe/sys_nanosleep") +int kprobe_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("perf_event") +int perf_event_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +const char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c index 8e94e5c080aa..6dc1f28fc4b6 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c +++ b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c @@ -68,7 +68,7 @@ static void set_task_info(struct sock *sk) } SEC("fentry/inet_csk_listen_start") -int BPF_PROG(trace_inet_csk_listen_start, struct sock *sk, int backlog) +int BPF_PROG(trace_inet_csk_listen_start, struct sock *sk) { set_task_info(sk); diff --git a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c index a408ec95cba4..eacda9fe07eb 100644 --- a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c +++ b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c @@ -23,7 +23,7 @@ int BPF_PROG(unix_listen, struct socket *sock, int backlog) if (!unix_sk) return 0; - if (!UNIX_ABSTRACT(unix_sk)) + if (unix_sk->addr->name->sun_path[0]) return 0; len = unix_sk->addr->len - sizeof(short); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 07b88a8f504f..16ce2ad097f4 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -92,6 +92,7 @@ struct bpf_test { int fixup_map_event_output[MAX_FIXUPS]; int fixup_map_reuseport_array[MAX_FIXUPS]; int fixup_map_ringbuf[MAX_FIXUPS]; + int fixup_map_timer[MAX_FIXUPS]; /* Expected verifier log output for result REJECT or VERBOSE_ACCEPT. * Can be a tab-separated sequence of expected strings. An empty string * means no log verification. @@ -604,8 +605,15 @@ static int create_cgroup_storage(bool percpu) * int cnt; * struct bpf_spin_lock l; * }; + * struct bpf_timer { + * __u64 :64; + * __u64 :64; + * } __attribute__((aligned(8))); + * struct timer { + * struct bpf_timer t; + * }; */ -static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; +static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l\0bpf_timer\0timer\0t"; static __u32 btf_raw_types[] = { /* int */ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ @@ -616,6 +624,11 @@ static __u32 btf_raw_types[] = { BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + /* struct bpf_timer */ /* [4] */ + BTF_TYPE_ENC(25, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0), 16), + /* struct timer */ /* [5] */ + BTF_TYPE_ENC(35, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 16), + BTF_MEMBER_ENC(41, 4, 0), /* struct bpf_timer t; */ }; static int load_btf(void) @@ -686,6 +699,29 @@ static int create_sk_storage_map(void) return fd; } +static int create_map_timer(void) +{ + struct bpf_create_map_attr attr = { + .name = "test_map", + .map_type = BPF_MAP_TYPE_ARRAY, + .key_size = 4, + .value_size = 16, + .max_entries = 1, + .btf_key_type_id = 1, + .btf_value_type_id = 5, + }; + int fd, btf_fd; + + btf_fd = load_btf(); + if (btf_fd < 0) + return -1; + attr.btf_fd = btf_fd; + fd = bpf_create_map_xattr(&attr); + if (fd < 0) + printf("Failed to create map with timer\n"); + return fd; +} + static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, @@ -712,6 +748,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_event_output = test->fixup_map_event_output; int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; int *fixup_map_ringbuf = test->fixup_map_ringbuf; + int *fixup_map_timer = test->fixup_map_timer; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -897,6 +934,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_ringbuf++; } while (*fixup_map_ringbuf); } + if (*fixup_map_timer) { + map_fds[21] = create_map_timer(); + do { + prog[*fixup_map_timer].imm = map_fds[21]; + fixup_map_timer++; + } while (*fixup_map_timer); + } } struct libcap { diff --git a/tools/testing/selftests/bpf/verifier/helper_restricted.c b/tools/testing/selftests/bpf/verifier/helper_restricted.c new file mode 100644 index 000000000000..a067b7098b97 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/helper_restricted.c @@ -0,0 +1,196 @@ +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, +{ + "bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + 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_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + 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_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + 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_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + 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_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, diff --git a/tools/testing/selftests/bpf/verifier/map_in_map.c b/tools/testing/selftests/bpf/verifier/map_in_map.c index 2798927ee9ff..128a348b762d 100644 --- a/tools/testing/selftests/bpf/verifier/map_in_map.c +++ b/tools/testing/selftests/bpf/verifier/map_in_map.c @@ -19,6 +19,40 @@ .result = ACCEPT, }, { + "map in map state pruning", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 11), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 4, 14 }, + .flags = BPF_F_TEST_STATE_FREQ, + .result = VERBOSE_ACCEPT, + .errstr = "processed 25 insns", + .prog_type = BPF_PROG_TYPE_XDP, +}, +{ "invalid inner map pointer", .insns = { BPF_ST_MEM(0, BPF_REG_10, -4, 0), diff --git a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c index bfb97383e6b5..b4ec228eb95d 100644 --- a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c @@ -35,7 +35,7 @@ .prog_type = BPF_PROG_TYPE_XDP, }, { - "XDP pkt read, pkt_data' > pkt_end, good access", + "XDP pkt read, pkt_data' > pkt_end, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -88,6 +88,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data' > pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_end > pkt_data', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -106,16 +141,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end > pkt_data', bad access 1", + "XDP pkt read, pkt_end > pkt_data', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -143,6 +178,42 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_end > pkt_data', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end > pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data' < pkt_end, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -161,16 +232,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' < pkt_end, bad access 1", + "XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -198,7 +269,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end < pkt_data', good access", + "XDP pkt read, pkt_data' < pkt_end, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' < pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end < pkt_data', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -251,6 +358,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_end < pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end < pkt_data', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data' >= pkt_end, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -268,15 +410,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' >= pkt_end, bad access 1", + "XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -304,7 +446,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end >= pkt_data', good access", + "XDP pkt read, pkt_data' >= pkt_end, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end >= pkt_data', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -359,7 +535,44 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' <= pkt_end, good access", + "XDP pkt read, pkt_end >= pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' <= pkt_end, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -414,6 +627,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_end <= pkt_data', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -431,15 +681,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end <= pkt_data', bad access 1", + "XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -467,7 +717,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' > pkt_data, good access", + "XDP pkt read, pkt_end <= pkt_data', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end <= pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' > pkt_data, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -520,6 +804,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data > pkt_meta', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -538,16 +857,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data > pkt_meta', bad access 1", + "XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -575,6 +894,42 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data > pkt_meta', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data > pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_meta' < pkt_data, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -593,16 +948,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' < pkt_data, bad access 1", + "XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -630,7 +985,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data < pkt_meta', good access", + "XDP pkt read, pkt_meta' < pkt_data, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data < pkt_meta', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -683,6 +1074,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data < pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_meta' >= pkt_data, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -700,15 +1126,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' >= pkt_data, bad access 1", + "XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -736,7 +1162,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data >= pkt_meta', good access", + "XDP pkt read, pkt_meta' >= pkt_data, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data >= pkt_meta', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -791,7 +1251,44 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' <= pkt_data, good access", + "XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' <= pkt_data, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -846,6 +1343,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data <= pkt_meta', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -863,15 +1397,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data <= pkt_meta', bad access 1", + "XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -898,3 +1432,37 @@ .prog_type = BPF_PROG_TYPE_XDP, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, +{ + "XDP pkt read, pkt_data <= pkt_meta', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 39f2bbe8dd3d..d7b312b44a62 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -3,5 +3,6 @@ TEST_PROGS := gpio-mockup.sh TEST_FILES := gpio-mockup-sysfs.sh TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev +CFLAGS += -O2 -g -Wall -I../../../../usr/include/ include ../lib.mk diff --git a/tools/testing/selftests/gpio/gpio-mockup-cdev.c b/tools/testing/selftests/gpio/gpio-mockup-cdev.c index e83eac71621a..d1640f44f8ac 100644 --- a/tools/testing/selftests/gpio/gpio-mockup-cdev.c +++ b/tools/testing/selftests/gpio/gpio-mockup-cdev.c @@ -117,7 +117,7 @@ int main(int argc, char *argv[]) { char *chip; int opt, ret, cfd, lfd; - unsigned int offset, val, abiv; + unsigned int offset, val = 0, abiv; uint32_t flags_v1; uint64_t flags_v2; diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d4a830139683..3763105029fb 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -23,6 +23,7 @@ /x86_64/platform_info_test /x86_64/set_boot_cpu_id /x86_64/set_sregs_test +/x86_64/sev_migrate_tests /x86_64/smm_test /x86_64/state_test /x86_64/svm_vmcall_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index c23e89dea0b6..c4e34717826a 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -73,7 +73,8 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test -TEST_GEN_PROGS_x86_64 += access_tracking_perf_test +TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test +TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 5d95113c7b7c..d8909032317a 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -47,7 +47,7 @@ #include "guest_modes.h" /* Global variable used to synchronize all of the vCPU threads. */ -static int iteration = -1; +static int iteration; /* Defines what vCPU threads should do during a given iteration. */ static enum { @@ -215,12 +215,11 @@ static bool spin_wait_for_next_iteration(int *current_iteration) return true; } -static void *vcpu_thread_main(void *arg) +static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args) { - struct perf_test_vcpu_args *vcpu_args = arg; struct kvm_vm *vm = perf_test_args.vm; int vcpu_id = vcpu_args->vcpu_id; - int current_iteration = -1; + int current_iteration = 0; while (spin_wait_for_next_iteration(¤t_iteration)) { switch (READ_ONCE(iteration_work)) { @@ -235,8 +234,6 @@ static void *vcpu_thread_main(void *arg) vcpu_last_completed_iteration[vcpu_id] = current_iteration; } - - return NULL; } static void spin_wait_for_vcpu(int vcpu_id, int target_iteration) @@ -277,8 +274,7 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description) static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access, const char *description) { - perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1; - sync_global_to_guest(vm, perf_test_args); + perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1); iteration_work = ITERATION_ACCESS_MEMORY; run_iteration(vm, vcpus, description); } @@ -296,48 +292,16 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus) run_iteration(vm, vcpus, "Mark memory idle"); } -static pthread_t *create_vcpu_threads(int vcpus) -{ - pthread_t *vcpu_threads; - int i; - - vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0])); - TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads."); - - for (i = 0; i < vcpus; i++) { - vcpu_last_completed_iteration[i] = iteration; - pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main, - &perf_test_args.vcpu_args[i]); - } - - return vcpu_threads; -} - -static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus) -{ - int i; - - /* Set done to signal the vCPU threads to exit */ - done = true; - - for (i = 0; i < vcpus; i++) - pthread_join(vcpu_threads[i], NULL); -} - static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *params = arg; struct kvm_vm *vm; - pthread_t *vcpu_threads; int vcpus = params->vcpus; vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1, - params->backing_src); + params->backing_src, !overlap_memory_access); - perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes, - !overlap_memory_access); - - vcpu_threads = create_vcpu_threads(vcpus); + perf_test_start_vcpu_threads(vcpus, vcpu_thread_main); pr_info("\n"); access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory"); @@ -352,8 +316,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) mark_memory_idle(vm, vcpus); access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory"); - terminate_vcpu_threads(vcpu_threads, vcpus); - free(vcpu_threads); + /* Set done to signal the vCPU threads to exit */ + done = true; + + perf_test_join_vcpu_threads(vcpus); perf_test_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 1510b21e6306..6a719d065599 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -42,10 +42,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static size_t demand_paging_size; static char *guest_data_prototype; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; - struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; @@ -68,8 +67,6 @@ static void *vcpu_worker(void *data) ts_diff = timespec_elapsed(start); PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, ts_diff.tv_sec, ts_diff.tv_nsec); - - return NULL; } static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr) @@ -282,7 +279,6 @@ struct test_params { static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; pthread_t *uffd_handler_threads = NULL; struct uffd_handler_args *uffd_args = NULL; struct timespec start; @@ -293,9 +289,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) int r; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, - p->src_type); - - perf_test_args.wr_fract = 1; + p->src_type, p->partition_vcpu_memory_access); demand_paging_size = get_backing_src_pagesz(p->src_type); @@ -304,12 +298,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) "Failed to allocate buffer for guest data pattern"); memset(guest_data_prototype, 0xAB, demand_paging_size); - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - if (p->uffd_mode) { uffd_handler_threads = malloc(nr_vcpus * sizeof(*uffd_handler_threads)); @@ -322,26 +310,15 @@ static void run_test(enum vm_guest_mode mode, void *arg) TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - vm_paddr_t vcpu_gpa; + struct perf_test_vcpu_args *vcpu_args; void *vcpu_hva; void *vcpu_alias; - uint64_t vcpu_mem_size; - - if (p->partition_vcpu_memory_access) { - vcpu_gpa = guest_test_phys_mem + - (vcpu_id * guest_percpu_mem_size); - vcpu_mem_size = guest_percpu_mem_size; - } else { - vcpu_gpa = guest_test_phys_mem; - vcpu_mem_size = guest_percpu_mem_size * nr_vcpus; - } - PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size); + vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; /* Cache the host addresses of the region */ - vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); - vcpu_alias = addr_gpa2alias(vm, vcpu_gpa); + vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa); + vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa); /* * Set up user fault fd to handle demand paging @@ -355,32 +332,18 @@ static void run_test(enum vm_guest_mode mode, void *arg) pipefds[vcpu_id * 2], p->uffd_mode, p->uffd_delay, &uffd_args[vcpu_id], vcpu_hva, vcpu_alias, - vcpu_mem_size); + vcpu_args->pages * perf_test_args.guest_page_size); } } - /* Export the shared variables to the guest */ - sync_global_to_guest(vm, perf_test_args); - pr_info("Finished creating vCPUs and starting uffd threads\n"); clock_gettime(CLOCK_MONOTONIC, &start); - - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); - } - + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); pr_info("Started all vCPUs\n"); - /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - pthread_join(vcpu_threads[vcpu_id], NULL); - PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id); - } - + perf_test_join_vcpu_threads(nr_vcpus); ts_diff = timespec_elapsed(start); - pr_info("All vCPU threads joined\n"); if (p->uffd_mode) { @@ -404,7 +367,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_destroy_vm(vm); free(guest_data_prototype); - free(vcpu_threads); if (p->uffd_mode) { free(uffd_handler_threads); free(uffd_args); diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 7ffab5bd5ce5..1954b964d1cf 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -31,7 +31,7 @@ static bool host_quit; static int iteration; static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; struct kvm_vm *vm = perf_test_args.vm; @@ -41,7 +41,6 @@ static void *vcpu_worker(void *data) struct timespec ts_diff; struct timespec total = (struct timespec){0}; struct timespec avg; - struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; run = vcpu_state(vm, vcpu_id); @@ -83,8 +82,6 @@ static void *vcpu_worker(void *data) pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id], total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec); - - return NULL; } struct test_params { @@ -170,7 +167,6 @@ static void free_bitmaps(unsigned long *bitmaps[], int slots) static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; struct kvm_vm *vm; unsigned long **bitmaps; uint64_t guest_num_pages; @@ -186,9 +182,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct timespec clear_dirty_log_total = (struct timespec){0}; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, - p->slots, p->backing_src); + p->slots, p->backing_src, + p->partition_vcpu_memory_access); - perf_test_args.wr_fract = p->wr_fract; + perf_test_set_wr_fract(vm, p->wr_fract); guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); @@ -203,25 +200,15 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, &cap); } - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - - sync_global_to_guest(vm, perf_test_args); - /* Start the iterations */ iteration = 0; host_quit = false; clock_gettime(CLOCK_MONOTONIC, &start); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) vcpu_last_completed_iteration[vcpu_id] = -1; - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); - } + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); /* Allow the vCPUs to populate memory */ pr_debug("Starting iteration %d - Populating\n", iteration); @@ -290,8 +277,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Tell the vcpu thread to quit */ host_quit = true; - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_join(vcpu_threads[vcpu_id], NULL); + perf_test_join_vcpu_threads(nr_vcpus); avg = timespec_div(get_dirty_log_total, p->iterations); pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", @@ -306,7 +292,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) } free_bitmaps(bitmaps, p->slots); - free(vcpu_threads); perf_test_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 792c60e1b17d..3fcd89e195c7 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -115,7 +115,7 @@ static void guest_code(void) addr = guest_test_virt_mem; addr += (READ_ONCE(random_array[i]) % guest_num_pages) * guest_page_size; - addr &= ~(host_page_size - 1); + addr = align_down(addr, host_page_size); *(uint64_t *)addr = READ_ONCE(iteration); } @@ -737,14 +737,14 @@ static void run_test(enum vm_guest_mode mode, void *arg) if (!p->phys_offset) { guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * guest_page_size; - guest_test_phys_mem &= ~(host_page_size - 1); + guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size); } else { guest_test_phys_mem = p->phys_offset; } #ifdef __s390x__ /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); + guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20); #endif pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index f6b3794f306b..6a1a37f30494 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -82,6 +82,7 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int open_path_or_exit(const char *path, int flags); int open_kvm_dev_path_or_exit(void); int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h index df9f1a3a3ffb..a86f953d8d36 100644 --- a/tools/testing/selftests/kvm/include/perf_test_util.h +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -8,6 +8,8 @@ #ifndef SELFTEST_KVM_PERF_TEST_UTIL_H #define SELFTEST_KVM_PERF_TEST_UTIL_H +#include <pthread.h> + #include "kvm_util.h" /* Default guest test virtual memory offset */ @@ -18,6 +20,7 @@ #define PERF_TEST_MEM_SLOT_INDEX 1 struct perf_test_vcpu_args { + uint64_t gpa; uint64_t gva; uint64_t pages; @@ -27,7 +30,7 @@ struct perf_test_vcpu_args { struct perf_test_args { struct kvm_vm *vm; - uint64_t host_page_size; + uint64_t gpa; uint64_t guest_page_size; int wr_fract; @@ -36,19 +39,15 @@ struct perf_test_args { extern struct perf_test_args perf_test_args; -/* - * Guest physical memory offset of the testing memory slot. - * This will be set to the topmost valid physical address minus - * the test memory size. - */ -extern uint64_t guest_test_phys_mem; - struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, uint64_t vcpu_memory_bytes, int slots, - enum vm_mem_backing_src_type backing_src); + enum vm_mem_backing_src_type backing_src, + bool partition_vcpu_memory_access); void perf_test_destroy_vm(struct kvm_vm *vm); -void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, - uint64_t vcpu_memory_bytes, - bool partition_vcpu_memory_access); + +void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract); + +void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *)); +void perf_test_join_vcpu_threads(int vcpus); #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index f8fddc84c0d3..99e0dcdc923f 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -104,6 +104,7 @@ size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); size_t get_backing_src_pagesz(uint32_t i); +bool is_backing_src_hugetlb(uint32_t i); void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); long get_run_delay(void); @@ -117,4 +118,29 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; } +/* Aligns x up to the next multiple of size. Size must be a power of 2. */ +static inline uint64_t align_up(uint64_t x, uint64_t size) +{ + uint64_t mask = size - 1; + + TEST_ASSERT(size != 0 && !(size & (size - 1)), + "size not a power of 2: %lu", size); + return ((x + mask) & ~mask); +} + +static inline uint64_t align_down(uint64_t x, uint64_t size) +{ + uint64_t x_aligned_up = align_up(x, size); + + if (x == x_aligned_up) + return x; + else + return x_aligned_up - size; +} + +static inline void *align_ptr_up(void *x, size_t size) +{ + return (void *)align_up((unsigned long)x, size); +} + #endif /* SELFTEST_KVM_TEST_UTIL_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 index b7531c83b8ae..587fbe408b99 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h @@ -46,4 +46,6 @@ static inline bool cpu_has_svm(void) return ecx & CPUID_SVM; } +int open_sev_dev_path_or_exit(void); + #endif /* SELFTEST_KVM_SVM_UTILS_H */ diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index f968dfd4ee88..aed9dc3ca1e9 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -12,6 +12,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/resource.h> #include "test_util.h" @@ -40,11 +41,40 @@ int main(int argc, char *argv[]) { int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID); int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); + /* + * Number of file descriptors reqired, KVM_CAP_MAX_VCPUS for vCPU fds + + * an arbitrary number for everything else. + */ + int nr_fds_wanted = kvm_max_vcpus + 100; + struct rlimit rl; pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id); pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus); /* + * Check that we're allowed to open nr_fds_wanted file descriptors and + * try raising the limits if needed. + */ + TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!"); + + if (rl.rlim_cur < nr_fds_wanted) { + rl.rlim_cur = nr_fds_wanted; + if (rl.rlim_max < nr_fds_wanted) { + int old_rlim_max = rl.rlim_max; + rl.rlim_max = nr_fds_wanted; + + int r = setrlimit(RLIMIT_NOFILE, &rl); + if (r < 0) { + printf("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n", + old_rlim_max, nr_fds_wanted); + exit(KSFT_SKIP); + } + } else { + TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!"); + } + } + + /* * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID. * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID * in this case. diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 36407cb0ec85..ba1fdc3dcf4a 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) #ifdef __s390x__ alignment = max(0x100000, alignment); #endif - guest_test_phys_mem &= ~(alignment - 1); + guest_test_phys_mem = align_down(guest_test_phys_mem, alignment); /* Set up the shared data structure test_args */ test_args.vm = vm; diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index eac44f5d0db0..13e8e3dcf984 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -157,8 +157,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) "memsize of 0,\n" " phdr index: %u p_memsz: 0x%" PRIx64, n1, (uint64_t) phdr.p_memsz); - vm_vaddr_t seg_vstart = phdr.p_vaddr; - seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1); + vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size); vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1; seg_vend |= vm->page_size - 1; size_t seg_size = seg_vend - seg_vstart + 1; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 041004c0fda7..8f2e0bb1ef96 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -22,13 +22,17 @@ static int vcpu_mmap_sz(void); -/* Aligns x up to the next multiple of size. Size must be a power of 2. */ -static void *align(void *x, size_t size) +int open_path_or_exit(const char *path, int flags) { - size_t mask = size - 1; - TEST_ASSERT(size != 0 && !(size & (size - 1)), - "size not a power of 2: %lu", size); - return (void *) (((size_t) x + mask) & ~mask); + int fd; + + fd = open(path, flags); + if (fd < 0) { + print_skip("%s not available (errno: %d)", path, errno); + exit(KSFT_SKIP); + } + + return fd; } /* @@ -42,16 +46,7 @@ static void *align(void *x, size_t size) */ static int _open_kvm_dev_path_or_exit(int flags) { - int fd; - - fd = open(KVM_DEV_PATH, flags); - if (fd < 0) { - print_skip("%s not available, is KVM loaded? (errno: %d)", - KVM_DEV_PATH, errno); - exit(KSFT_SKIP); - } - - return fd; + return open_path_or_exit(KVM_DEV_PATH, flags); } int open_kvm_dev_path_or_exit(void) @@ -187,15 +182,15 @@ const char *vm_guest_mode_string(uint32_t i) } const struct vm_guest_mode_params vm_guest_mode_params[] = { - { 52, 48, 0x1000, 12 }, - { 52, 48, 0x10000, 16 }, - { 48, 48, 0x1000, 12 }, - { 48, 48, 0x10000, 16 }, - { 40, 48, 0x1000, 12 }, - { 40, 48, 0x10000, 16 }, - { 0, 0, 0x1000, 12 }, - { 47, 64, 0x1000, 12 }, - { 44, 64, 0x1000, 12 }, + [VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 }, + [VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 }, + [VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 }, + [VM_MODE_P48V48_64K] = { 48, 48, 0x10000, 16 }, + [VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 }, + [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 }, + [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 }, + [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 }, + [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -875,9 +870,17 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, alignment = 1; #endif + /* + * When using THP mmap is not guaranteed to returned a hugepage aligned + * address so we have to pad the mmap. Padding is not needed for HugeTLB + * because mmap will always return an address aligned to the HugeTLB + * page size. + */ if (src_type == VM_MEM_SRC_ANONYMOUS_THP) alignment = max(backing_src_pagesz, alignment); + ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz)); + /* Add enough memory to align up if necessary */ if (alignment > 1) region->mmap_size += alignment; @@ -910,8 +913,13 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); + TEST_ASSERT(!is_backing_src_hugetlb(src_type) || + region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz), + "mmap_start %p is not aligned to HugeTLB page size 0x%lx", + region->mmap_start, backing_src_pagesz); + /* Align host address */ - region->host_mem = align(region->mmap_start, alignment); + region->host_mem = align_ptr_up(region->mmap_start, alignment); /* As needed perform madvise */ if ((src_type == VM_MEM_SRC_ANONYMOUS || @@ -954,7 +962,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, "mmap of alias failed, errno: %i", errno); /* Align host alias address */ - region->host_alias = align(region->mmap_alias, alignment); + region->host_alias = align_ptr_up(region->mmap_alias, alignment); } } diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index 0ef80dbdc116..722df3a28791 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -10,21 +10,40 @@ struct perf_test_args perf_test_args; -uint64_t guest_test_phys_mem; - /* * Guest virtual memory offset of the testing memory slot. * Must not conflict with identity mapped test code. */ static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +struct vcpu_thread { + /* The id of the vCPU. */ + int vcpu_id; + + /* The pthread backing the vCPU. */ + pthread_t thread; + + /* Set to true once the vCPU thread is up and running. */ + bool running; +}; + +/* The vCPU threads involved in this test. */ +static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS]; + +/* The function run by each vCPU thread, as provided by the test. */ +static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *); + +/* Set to true once all vCPU threads are up and running. */ +static bool all_vcpu_threads_running; + /* * Continuously write to the first 8 bytes of each page in the * specified region. */ static void guest_code(uint32_t vcpu_id) { - struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + struct perf_test_args *pta = &perf_test_args; + struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id]; uint64_t gva; uint64_t pages; int i; @@ -37,9 +56,9 @@ static void guest_code(uint32_t vcpu_id) while (true) { for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * perf_test_args.guest_page_size); + uint64_t addr = gva + (i * pta->guest_page_size); - if (i % perf_test_args.wr_fract == 0) + if (i % pta->wr_fract == 0) *(uint64_t *)addr = 0x0123456789ABCDEF; else READ_ONCE(*(uint64_t *)addr); @@ -49,35 +68,81 @@ static void guest_code(uint32_t vcpu_id) } } +void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, + uint64_t vcpu_memory_bytes, + bool partition_vcpu_memory_access) +{ + struct perf_test_args *pta = &perf_test_args; + struct perf_test_vcpu_args *vcpu_args; + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vcpu_args = &pta->vcpu_args[vcpu_id]; + + vcpu_args->vcpu_id = vcpu_id; + if (partition_vcpu_memory_access) { + vcpu_args->gva = guest_test_virt_mem + + (vcpu_id * vcpu_memory_bytes); + vcpu_args->pages = vcpu_memory_bytes / + pta->guest_page_size; + vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes); + } else { + vcpu_args->gva = guest_test_virt_mem; + vcpu_args->pages = (vcpus * vcpu_memory_bytes) / + pta->guest_page_size; + vcpu_args->gpa = pta->gpa; + } + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + + pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_args->gpa, vcpu_args->gpa + + (vcpu_args->pages * pta->guest_page_size)); + } +} + struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, uint64_t vcpu_memory_bytes, int slots, - enum vm_mem_backing_src_type backing_src) + enum vm_mem_backing_src_type backing_src, + bool partition_vcpu_memory_access) { + struct perf_test_args *pta = &perf_test_args; struct kvm_vm *vm; uint64_t guest_num_pages; + uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src); int i; pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - perf_test_args.host_page_size = getpagesize(); - perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size; + /* By default vCPUs will write to memory. */ + pta->wr_fract = 1; + + /* + * Snapshot the non-huge page size. This is used by the guest code to + * access/dirty pages at the logging granularity. + */ + pta->guest_page_size = vm_guest_mode_params[mode].page_size; guest_num_pages = vm_adjust_num_guest_pages(mode, - (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size); + (vcpus * vcpu_memory_bytes) / pta->guest_page_size); - TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0, + TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0, "Guest memory size is not host page size aligned."); - TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, + TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0, "Guest memory size is not guest page size aligned."); TEST_ASSERT(guest_num_pages % slots == 0, "Guest memory cannot be evenly divided into %d slots.", slots); + /* + * Pass guest_num_pages to populate the page tables for test memory. + * The memory is also added to memslot 0, but that's a benign side + * effect as KVM allows aliasing HVAs in meslots. + */ vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES, - (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size, - 0, guest_code, NULL); + guest_num_pages, 0, guest_code, NULL); - perf_test_args.vm = vm; + pta->vm = vm; /* * If there should be more memory in the guest test region than there @@ -90,20 +155,18 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, guest_num_pages, vm_get_max_gfn(vm), vcpus, vcpu_memory_bytes); - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * - perf_test_args.guest_page_size; - guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1); + pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size; + pta->gpa = align_down(pta->gpa, backing_src_pagesz); #ifdef __s390x__ /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); + pta->gpa = align_down(pta->gpa, 1 << 20); #endif - pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa); /* Add extra memory slots for testing */ for (i = 0; i < slots; i++) { uint64_t region_pages = guest_num_pages / slots; - vm_paddr_t region_start = guest_test_phys_mem + - region_pages * perf_test_args.guest_page_size * i; + vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i; vm_userspace_mem_region_add(vm, backing_src, region_start, PERF_TEST_MEM_SLOT_INDEX + i, @@ -111,10 +174,15 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, } /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages); + virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages); + + perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access); ucall_init(vm, NULL); + /* Export the shared variables to the guest. */ + sync_global_to_guest(vm, perf_test_args); + return vm; } @@ -124,36 +192,60 @@ void perf_test_destroy_vm(struct kvm_vm *vm) kvm_vm_free(vm); } -void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, - uint64_t vcpu_memory_bytes, - bool partition_vcpu_memory_access) +void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract) +{ + perf_test_args.wr_fract = wr_fract; + sync_global_to_guest(vm, perf_test_args); +} + +static void *vcpu_thread_main(void *data) +{ + struct vcpu_thread *vcpu = data; + + WRITE_ONCE(vcpu->running, true); + + /* + * Wait for all vCPU threads to be up and running before calling the test- + * provided vCPU thread function. This prevents thread creation (which + * requires taking the mmap_sem in write mode) from interfering with the + * guest faulting in its memory. + */ + while (!READ_ONCE(all_vcpu_threads_running)) + ; + + vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]); + + return NULL; +} + +void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *)) { - vm_paddr_t vcpu_gpa; - struct perf_test_vcpu_args *vcpu_args; int vcpu_id; + vcpu_thread_fn = vcpu_fn; + WRITE_ONCE(all_vcpu_threads_running, false); + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id]; - vcpu_args->vcpu_id = vcpu_id; - if (partition_vcpu_memory_access) { - vcpu_args->gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); - vcpu_args->pages = vcpu_memory_bytes / - perf_test_args.guest_page_size; - vcpu_gpa = guest_test_phys_mem + - (vcpu_id * vcpu_memory_bytes); - } else { - vcpu_args->gva = guest_test_virt_mem; - vcpu_args->pages = (vcpus * vcpu_memory_bytes) / - perf_test_args.guest_page_size; - vcpu_gpa = guest_test_phys_mem; - } + vcpu->vcpu_id = vcpu_id; + WRITE_ONCE(vcpu->running, false); - vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu); + } - pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + - (vcpu_args->pages * perf_test_args.guest_page_size)); + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + while (!READ_ONCE(vcpu_threads[vcpu_id].running)) + ; } + + WRITE_ONCE(all_vcpu_threads_running, true); +} + +void perf_test_join_vcpu_threads(int vcpus) +{ + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) + pthread_join(vcpu_threads[vcpu_id].thread, NULL); } diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index b72429108993..6d23878bbfe1 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -283,6 +283,11 @@ size_t get_backing_src_pagesz(uint32_t i) } } +bool is_backing_src_hugetlb(uint32_t i) +{ + return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB); +} + static void print_available_backing_src_types(const char *prefix) { int i; diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c index 161eba7cd128..0ebc03ce079c 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c @@ -13,6 +13,8 @@ #include "processor.h" #include "svm_util.h" +#define SEV_DEV_PATH "/dev/sev" + struct gpr64_regs guest_regs; u64 rflags; @@ -172,3 +174,14 @@ void nested_svm_check_supported(void) exit(KSFT_SKIP); } } + +/* + * Open SEV_DEV_PATH if available, otherwise exit the entire program. + * + * Return: + * The opened file descriptor of /dev/sev. + */ +int open_sev_dev_path_or_exit(void) +{ + return open_path_or_exit(SEV_DEV_PATH, 0); +} diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 4cfcafea9f5a..1410d0a9141a 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -36,11 +36,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static bool run_vcpus = true; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; - struct perf_test_vcpu_args *vcpu_args = - (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; @@ -59,8 +57,6 @@ static void *vcpu_worker(void *data) "Invalid guest sync status: exit_reason=%s\n", exit_reason_str(run->exit_reason)); } - - return NULL; } struct memslot_antagonist_args { @@ -80,7 +76,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, * Add the dummy memslot just below the perf_test_util memslot, which is * at the top of the guest physical address space. */ - gpa = guest_test_phys_mem - pages * vm_get_page_size(vm); + gpa = perf_test_args.gpa - pages * vm_get_page_size(vm); for (i = 0; i < nr_modifications; i++) { usleep(delay); @@ -100,29 +96,15 @@ struct test_params { static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; struct kvm_vm *vm; - int vcpu_id; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, - VM_MEM_SRC_ANONYMOUS); - - perf_test_args.wr_fract = 1; - - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - - /* Export the shared variables to the guest */ - sync_global_to_guest(vm, perf_test_args); + VM_MEM_SRC_ANONYMOUS, + p->partition_vcpu_memory_access); pr_info("Finished creating vCPUs\n"); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); pr_info("Started all vCPUs\n"); @@ -131,16 +113,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) run_vcpus = false; - /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_join(vcpu_threads[vcpu_id], NULL); - + perf_test_join_vcpu_threads(nr_vcpus); pr_info("All vCPU threads joined\n"); - ucall_uninit(vm); - kvm_vm_free(vm); - - free(vcpu_threads); + perf_test_destroy_vm(vm); } static void help(char *name) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 91d88aaa9899..672915ce73d8 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -165,10 +165,10 @@ static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid, vcpu_set_cpuid(vm, VCPU_ID, cpuid); } -static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, - struct kvm_cpuid2 *best) +static void guest_test_msrs_access(void) { struct kvm_run *run; + struct kvm_vm *vm; struct ucall uc; int stage = 0, r; struct kvm_cpuid_entry2 feat = { @@ -180,11 +180,34 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, struct kvm_cpuid_entry2 dbg = { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }; - struct kvm_enable_cap cap = {0}; - - run = vcpu_state(vm, VCPU_ID); + struct kvm_cpuid2 *best; + vm_vaddr_t msr_gva; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + struct msr_data *msr; while (true) { + vm = vm_create_default(VCPU_ID, 0, guest_msr); + + msr_gva = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); + msr = addr_gva2hva(vm, msr_gva); + + vcpu_args_set(vm, VCPU_ID, 1, msr_gva); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); + + run = vcpu_state(vm, VCPU_ID); + switch (stage) { case 0: /* @@ -315,6 +338,7 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, * capability enabled and guest visible CPUID bit unset. */ cap.cap = KVM_CAP_HYPERV_SYNIC2; + cap.args[0] = 0; vcpu_enable_cap(vm, VCPU_ID, &cap); break; case 22: @@ -461,9 +485,9 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == stage, - "Unexpected stage: %ld (%d expected)\n", - uc.args[1], stage); + TEST_ASSERT(uc.args[1] == 0, + "Unexpected stage: %ld (0 expected)\n", + uc.args[1]); break; case UCALL_ABORT: TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], @@ -474,13 +498,14 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr, } stage++; + kvm_vm_free(vm); } } -static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall, - void *input, void *output, struct kvm_cpuid2 *best) +static void guest_test_hcalls_access(void) { struct kvm_run *run; + struct kvm_vm *vm; struct ucall uc; int stage = 0, r; struct kvm_cpuid_entry2 feat = { @@ -493,10 +518,38 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall struct kvm_cpuid_entry2 dbg = { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES }; - - run = vcpu_state(vm, VCPU_ID); + struct kvm_enable_cap cap = { + .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, + .args = {1} + }; + vm_vaddr_t hcall_page, hcall_params; + struct hcall_data *hcall; + struct kvm_cpuid2 *best; while (true) { + vm = vm_create_default(VCPU_ID, 0, guest_hcall); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + + /* Hypercall input/output */ + hcall_page = vm_vaddr_alloc_pages(vm, 2); + hcall = addr_gva2hva(vm, hcall_page); + memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); + + hcall_params = vm_vaddr_alloc_page(vm); + memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); + + vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); + vcpu_enable_cap(vm, VCPU_ID, &cap); + + vcpu_set_hv_cpuid(vm, VCPU_ID); + + best = kvm_get_supported_hv_cpuid(); + + run = vcpu_state(vm, VCPU_ID); + switch (stage) { case 0: hcall->control = 0xdeadbeef; @@ -606,9 +659,9 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_SYNC: - TEST_ASSERT(uc.args[1] == stage, - "Unexpected stage: %ld (%d expected)\n", - uc.args[1], stage); + TEST_ASSERT(uc.args[1] == 0, + "Unexpected stage: %ld (0 expected)\n", + uc.args[1]); break; case UCALL_ABORT: TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], @@ -619,66 +672,15 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall } stage++; + kvm_vm_free(vm); } } int main(void) { - struct kvm_cpuid2 *best; - struct kvm_vm *vm; - vm_vaddr_t msr_gva, hcall_page, hcall_params; - struct kvm_enable_cap cap = { - .cap = KVM_CAP_HYPERV_ENFORCE_CPUID, - .args = {1} - }; - - /* Test MSRs */ - vm = vm_create_default(VCPU_ID, 0, guest_msr); - - msr_gva = vm_vaddr_alloc_page(vm); - memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize()); - vcpu_args_set(vm, VCPU_ID, 1, msr_gva); - vcpu_enable_cap(vm, VCPU_ID, &cap); - - vcpu_set_hv_cpuid(vm, VCPU_ID); - - best = kvm_get_supported_hv_cpuid(); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); - pr_info("Testing access to Hyper-V specific MSRs\n"); - guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva), - best); - kvm_vm_free(vm); - - /* Test hypercalls */ - vm = vm_create_default(VCPU_ID, 0, guest_hcall); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vm, VCPU_ID); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); - - /* Hypercall input/output */ - hcall_page = vm_vaddr_alloc_pages(vm, 2); - memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); - - hcall_params = vm_vaddr_alloc_page(vm); - memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize()); - - vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params); - vcpu_enable_cap(vm, VCPU_ID, &cap); - - vcpu_set_hv_cpuid(vm, VCPU_ID); - - best = kvm_get_supported_hv_cpuid(); + guest_test_msrs_access(); pr_info("Testing access to Hyper-V hypercalls\n"); - guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params), - addr_gva2hva(vm, hcall_page), - addr_gva2hva(vm, hcall_page) + getpagesize(), - best); - - kvm_vm_free(vm); + guest_test_hcalls_access(); } diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c new file mode 100644 index 000000000000..29b18d565cf4 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c @@ -0,0 +1,348 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/kvm.h> +#include <linux/psp-sev.h> +#include <stdio.h> +#include <sys/ioctl.h> +#include <stdlib.h> +#include <errno.h> +#include <pthread.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "kselftest.h" +#include "../lib/kvm_util_internal.h" + +#define SEV_POLICY_ES 0b100 + +#define NR_MIGRATE_TEST_VCPUS 4 +#define NR_MIGRATE_TEST_VMS 3 +#define NR_LOCK_TESTING_THREADS 3 +#define NR_LOCK_TESTING_ITERATIONS 10000 + +static void sev_ioctl(int vm_fd, int cmd_id, void *data) +{ + struct kvm_sev_cmd cmd = { + .id = cmd_id, + .data = (uint64_t)data, + .sev_fd = open_sev_dev_path_or_exit(), + }; + int ret; + + ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd); + TEST_ASSERT((ret == 0 || cmd.error == SEV_RET_SUCCESS), + "%d failed: return code: %d, errno: %d, fw error: %d", + cmd_id, ret, errno, cmd.error); +} + +static struct kvm_vm *sev_vm_create(bool es) +{ + struct kvm_vm *vm; + struct kvm_sev_launch_start start = { 0 }; + int i; + + vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + sev_ioctl(vm->fd, es ? KVM_SEV_ES_INIT : KVM_SEV_INIT, NULL); + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) + vm_vcpu_add(vm, i); + if (es) + start.policy |= SEV_POLICY_ES; + sev_ioctl(vm->fd, KVM_SEV_LAUNCH_START, &start); + if (es) + sev_ioctl(vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + return vm; +} + +static struct kvm_vm *aux_vm_create(bool with_vcpus) +{ + struct kvm_vm *vm; + int i; + + vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + if (!with_vcpus) + return vm; + + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) + vm_vcpu_add(vm, i); + + return vm; +} + +static int __sev_migrate_from(int dst_fd, int src_fd) +{ + struct kvm_enable_cap cap = { + .cap = KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM, + .args = { src_fd } + }; + + return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); +} + + +static void sev_migrate_from(int dst_fd, int src_fd) +{ + int ret; + + ret = __sev_migrate_from(dst_fd, src_fd); + TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d\n", ret, errno); +} + +static void test_sev_migrate_from(bool es) +{ + struct kvm_vm *src_vm; + struct kvm_vm *dst_vms[NR_MIGRATE_TEST_VMS]; + int i, ret; + + src_vm = sev_vm_create(es); + for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i) + dst_vms[i] = aux_vm_create(true); + + /* Initial migration from the src to the first dst. */ + sev_migrate_from(dst_vms[0]->fd, src_vm->fd); + + for (i = 1; i < NR_MIGRATE_TEST_VMS; i++) + sev_migrate_from(dst_vms[i]->fd, dst_vms[i - 1]->fd); + + /* Migrate the guest back to the original VM. */ + ret = __sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd); + TEST_ASSERT(ret == -1 && errno == EIO, + "VM that was migrated from should be dead. ret %d, errno: %d\n", ret, + errno); + + kvm_vm_free(src_vm); + for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i) + kvm_vm_free(dst_vms[i]); +} + +struct locking_thread_input { + struct kvm_vm *vm; + int source_fds[NR_LOCK_TESTING_THREADS]; +}; + +static void *locking_test_thread(void *arg) +{ + int i, j; + struct locking_thread_input *input = (struct locking_thread_input *)arg; + + for (i = 0; i < NR_LOCK_TESTING_ITERATIONS; ++i) { + j = i % NR_LOCK_TESTING_THREADS; + __sev_migrate_from(input->vm->fd, input->source_fds[j]); + } + + return NULL; +} + +static void test_sev_migrate_locking(void) +{ + struct locking_thread_input input[NR_LOCK_TESTING_THREADS]; + pthread_t pt[NR_LOCK_TESTING_THREADS]; + int i; + + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) { + input[i].vm = sev_vm_create(/* es= */ false); + input[0].source_fds[i] = input[i].vm->fd; + } + for (i = 1; i < NR_LOCK_TESTING_THREADS; ++i) + memcpy(input[i].source_fds, input[0].source_fds, + sizeof(input[i].source_fds)); + + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) + pthread_create(&pt[i], NULL, locking_test_thread, &input[i]); + + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) + pthread_join(pt[i], NULL); + for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) + kvm_vm_free(input[i].vm); +} + +static void test_sev_migrate_parameters(void) +{ + struct kvm_vm *sev_vm, *sev_es_vm, *vm_no_vcpu, *vm_no_sev, + *sev_es_vm_no_vmsa; + int ret; + + sev_vm = sev_vm_create(/* es= */ false); + sev_es_vm = sev_vm_create(/* es= */ true); + vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + vm_no_sev = aux_vm_create(true); + sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR); + sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL); + vm_vcpu_add(sev_es_vm_no_vmsa, 1); + + ret = __sev_migrate_from(sev_vm->fd, sev_es_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able migrate to SEV enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_migrate_from(sev_es_vm->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm_no_vmsa->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n", + ret, errno); + + ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Migrations require SEV enabled. ret %d, errno: %d\n", ret, + errno); + + kvm_vm_free(sev_vm); + kvm_vm_free(sev_es_vm); + kvm_vm_free(sev_es_vm_no_vmsa); + kvm_vm_free(vm_no_vcpu); + kvm_vm_free(vm_no_sev); +} + +static int __sev_mirror_create(int dst_fd, int src_fd) +{ + struct kvm_enable_cap cap = { + .cap = KVM_CAP_VM_COPY_ENC_CONTEXT_FROM, + .args = { src_fd } + }; + + return ioctl(dst_fd, KVM_ENABLE_CAP, &cap); +} + + +static void sev_mirror_create(int dst_fd, int src_fd) +{ + int ret; + + ret = __sev_mirror_create(dst_fd, src_fd); + TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno); +} + +static void test_sev_mirror(bool es) +{ + struct kvm_vm *src_vm, *dst_vm; + struct kvm_sev_launch_start start = { + .policy = es ? SEV_POLICY_ES : 0 + }; + int i; + + src_vm = sev_vm_create(es); + dst_vm = aux_vm_create(false); + + sev_mirror_create(dst_vm->fd, src_vm->fd); + + /* Check that we can complete creation of the mirror VM. */ + for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i) + vm_vcpu_add(dst_vm, i); + sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start); + if (es) + sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL); + + kvm_vm_free(src_vm); + kvm_vm_free(dst_vm); +} + +static void test_sev_mirror_parameters(void) +{ + struct kvm_vm *sev_vm, *sev_es_vm, *vm_no_vcpu, *vm_with_vcpu; + int ret; + + sev_vm = sev_vm_create(/* es= */ false); + sev_es_vm = sev_vm_create(/* es= */ true); + vm_with_vcpu = aux_vm_create(true); + vm_no_vcpu = aux_vm_create(false); + + ret = __sev_mirror_create(sev_vm->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to self. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(sev_es_vm->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n", + ret, errno); + + ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "Copy context requires SEV enabled. ret %d, errno: %d\n", ret, + errno); + + ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd); + TEST_ASSERT( + ret == -1 && errno == EINVAL, + "SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n", + ret, errno); + + kvm_vm_free(sev_vm); + kvm_vm_free(sev_es_vm); + kvm_vm_free(vm_with_vcpu); + kvm_vm_free(vm_no_vcpu); +} + +static void test_sev_move_copy(void) +{ + struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm; + int ret; + + sev_vm = sev_vm_create(/* es= */ false); + dst_vm = aux_vm_create(true); + mirror_vm = aux_vm_create(false); + dst_mirror_vm = aux_vm_create(false); + + sev_mirror_create(mirror_vm->fd, sev_vm->fd); + ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); + TEST_ASSERT(ret == -1 && errno == EBUSY, + "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, + errno); + + /* The mirror itself can be migrated. */ + sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd); + ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd); + TEST_ASSERT(ret == -1 && errno == EBUSY, + "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret, + errno); + + /* + * mirror_vm is not a mirror anymore, dst_mirror_vm is. Thus, + * the owner can be copied as soon as dst_mirror_vm is gone. + */ + kvm_vm_free(dst_mirror_vm); + sev_migrate_from(dst_vm->fd, sev_vm->fd); + + kvm_vm_free(mirror_vm); + kvm_vm_free(dst_vm); + kvm_vm_free(sev_vm); +} + +int main(int argc, char *argv[]) +{ + if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) { + test_sev_migrate_from(/* es= */ false); + test_sev_migrate_from(/* es= */ true); + test_sev_migrate_locking(); + test_sev_migrate_parameters(); + if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) + test_sev_move_copy(); + } + if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { + test_sev_mirror(/* es= */ false); + test_sev_mirror(/* es= */ true); + test_sev_mirror_parameters(); + } + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index eda0d2a51224..a0699f00b3d6 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -24,8 +24,12 @@ #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) #define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20) +#define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40) #define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20) +#define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40) + +#define EVTCHN_VECTOR 0x10 static struct kvm_vm *vm; @@ -56,15 +60,44 @@ struct vcpu_runstate_info { uint64_t time[4]; }; +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad; /* sizeof(vcpu_info_t) == 64 */ +}; + +struct vcpu_info { + uint8_t evtchn_upcall_pending; + uint8_t evtchn_upcall_mask; + unsigned long evtchn_pending_sel; + struct arch_vcpu_info arch; + struct pvclock_vcpu_time_info time; +}; /* 64 bytes (x86) */ + #define RUNSTATE_running 0 #define RUNSTATE_runnable 1 #define RUNSTATE_blocked 2 #define RUNSTATE_offline 3 +static void evtchn_handler(struct ex_regs *regs) +{ + struct vcpu_info *vi = (void *)VCPU_INFO_VADDR; + vi->evtchn_upcall_pending = 0; + + GUEST_SYNC(0x20); +} + static void guest_code(void) { struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR; + __asm__ __volatile__( + "sti\n" + "nop\n" + ); + + /* Trigger an interrupt injection */ + GUEST_SYNC(0); + /* Test having the host set runstates manually */ GUEST_SYNC(RUNSTATE_runnable); GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0); @@ -153,7 +186,7 @@ int main(int argc, char *argv[]) struct kvm_xen_vcpu_attr vi = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, - .u.gpa = SHINFO_REGION_GPA + 0x40, + .u.gpa = VCPU_INFO_ADDR, }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi); @@ -163,6 +196,16 @@ int main(int argc, char *argv[]) }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock); + struct kvm_xen_hvm_attr vec = { + .type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR, + .u.vector = EVTCHN_VECTOR, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler); + if (do_runstate_tests) { struct kvm_xen_vcpu_attr st = { .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR, @@ -171,9 +214,14 @@ int main(int argc, char *argv[]) vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); } + struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); + vinfo->evtchn_upcall_pending = 0; + struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR); rs->state = 0x5a; + bool evtchn_irq_expected = false; + for (;;) { volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); struct ucall uc; @@ -193,16 +241,21 @@ int main(int argc, char *argv[]) struct kvm_xen_vcpu_attr rst; long rundelay; - /* If no runstate support, bail out early */ - if (!do_runstate_tests) - goto done; - - TEST_ASSERT(rs->state_entry_time == rs->time[0] + - rs->time[1] + rs->time[2] + rs->time[3], - "runstate times don't add up"); + if (do_runstate_tests) + TEST_ASSERT(rs->state_entry_time == rs->time[0] + + rs->time[1] + rs->time[2] + rs->time[3], + "runstate times don't add up"); switch (uc.args[1]) { - case RUNSTATE_running...RUNSTATE_offline: + case 0: + evtchn_irq_expected = true; + vinfo->evtchn_upcall_pending = 1; + break; + + case RUNSTATE_runnable...RUNSTATE_offline: + TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen"); + if (!do_runstate_tests) + goto done; rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; rst.u.runstate.state = uc.args[1]; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); @@ -236,6 +289,10 @@ int main(int argc, char *argv[]) sched_yield(); } while (get_run_delay() < rundelay); break; + case 0x20: + TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ"); + evtchn_irq_expected = false; + break; } break; } diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 7615f29831eb..9897fa9ab953 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -34,6 +34,7 @@ TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += vrf_strict_mode_test.sh +TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 3313566ce906..98e4d5a2f587 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -66,6 +66,10 @@ NSB_LO_IP=172.16.2.2 NSA_LO_IP6=2001:db8:2::1 NSB_LO_IP6=2001:db8:2::2 +# non-local addresses for freebind tests +NL_IP=172.17.1.1 +NL_IP6=2001:db8:4::1 + MD5_PW=abc123 MD5_WRONG_PW=abc1234 @@ -316,6 +320,9 @@ addr2str() ${NSB_LO_IP6}) echo "ns-B loopback IPv6";; ${NSB_LINKIP6}|${NSB_LINKIP6}%*) echo "ns-B IPv6 LLA";; + ${NL_IP}) echo "nonlocal IP";; + ${NL_IP6}) echo "nonlocal IPv6";; + ${VRF_IP}) echo "VRF IP";; ${VRF_IP6}) echo "VRF IPv6";; @@ -1768,6 +1775,14 @@ ipv4_addr_bind_novrf() done # + # raw socket with nonlocal bind + # + a=${NL_IP} + log_start + run_cmd nettest -s -R -P icmp -f -l ${a} -I ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after device bind" + + # # tcp sockets # a=${NSA_IP} @@ -1816,6 +1831,14 @@ ipv4_addr_bind_vrf() log_test_addr ${a} $? 1 "Raw socket bind to out of scope address after VRF bind" # + # raw socket with nonlocal bind + # + a=${NL_IP} + log_start + run_cmd nettest -s -R -P icmp -f -l ${a} -I ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after VRF bind" + + # # tcp sockets # for a in ${NSA_IP} ${VRF_IP} @@ -1965,6 +1988,7 @@ ipv4_rt() a=${NSA_IP} log_start + run_cmd nettest ${varg} -s & sleep 1 run_cmd nettest ${varg} -d ${NSA_DEV} -r ${a} & @@ -3403,6 +3427,14 @@ ipv6_addr_bind_novrf() done # + # raw socket with nonlocal bind + # + a=${NL_IP6} + log_start + run_cmd nettest -6 -s -R -P icmp -f -l ${a} -I ${NSA_DEV} -b + log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address" + + # # tcp sockets # a=${NSA_IP6} @@ -3444,6 +3476,14 @@ ipv6_addr_bind_vrf() log_test_addr ${a} $? 1 "Raw socket bind to invalid local address after vrf bind" # + # raw socket with nonlocal bind + # + a=${NL_IP6} + log_start + run_cmd nettest -6 -s -R -P icmp -f -l ${a} -I ${VRF} -b + log_test_addr ${a} $? 0 "Raw socket bind to nonlocal address after VRF bind" + + # # tcp sockets # # address on enslaved device is valid for the VRF or device in a VRF @@ -4002,8 +4042,8 @@ EOF ################################################################################ # main -TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter" -TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter" +TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_bind ipv4_runtime ipv4_netfilter" +TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_bind ipv6_runtime ipv6_netfilter" TESTS_OTHER="use_cases" PAUSE_ON_FAIL=no @@ -4068,8 +4108,6 @@ do # setup namespaces and config, but do not run any tests setup) setup; exit 0;; vrf_setup) setup "yes"; exit 0;; - - help) echo "Test names: $TESTS"; exit 0;; esac done @@ -4077,3 +4115,11 @@ cleanup 2>/dev/null printf "\nTests passed: %3d\n" ${nsuccess} printf "Tests failed: %3d\n" ${nfail} + +if [ $nfail -ne 0 ]; then + exit 1 # KSFT_FAIL +elif [ $nsuccess -eq 0 ]; then + exit $ksft_skip +fi + +exit 0 # KSFT_PASS diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index b5a69ad191b0..d444ee6aa3cb 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -629,6 +629,66 @@ ipv6_fcnal() log_test $? 0 "Nexthops removed on admin down" } +ipv6_grp_refs() +{ + if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test; need mausezahn tool" + return + fi + + run_cmd "$IP link set dev veth1 up" + run_cmd "$IP link add veth1.10 link veth1 up type vlan id 10" + run_cmd "$IP link add veth1.20 link veth1 up type vlan id 20" + run_cmd "$IP -6 addr add 2001:db8:91::1/64 dev veth1.10" + run_cmd "$IP -6 addr add 2001:db8:92::1/64 dev veth1.20" + run_cmd "$IP -6 neigh add 2001:db8:91::2 lladdr 00:11:22:33:44:55 dev veth1.10" + run_cmd "$IP -6 neigh add 2001:db8:92::2 lladdr 00:11:22:33:44:55 dev veth1.20" + run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1.10" + run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth1.20" + run_cmd "$IP nexthop add id 102 group 100" + run_cmd "$IP route add 2001:db8:101::1/128 nhid 102" + + # create per-cpu dsts through nh 100 + run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1" + + # remove nh 100 from the group to delete the route potentially leaving + # a stale per-cpu dst which holds a reference to the nexthop's net + # device and to the IPv6 route + run_cmd "$IP nexthop replace id 102 group 101" + run_cmd "$IP route del 2001:db8:101::1/128" + + # add both nexthops to the group so a reference is taken on them + run_cmd "$IP nexthop replace id 102 group 100/101" + + # if the bug described in commit "net: nexthop: release IPv6 per-cpu + # dsts when replacing a nexthop group" exists at this point we have + # an unlinked IPv6 route (but not freed due to stale dst) with a + # reference over the group so we delete the group which will again + # only unlink it due to the route reference + run_cmd "$IP nexthop del id 102" + + # delete the nexthop with stale dst, since we have an unlinked + # group with a ref to it and an unlinked IPv6 route with ref to the + # group, the nh will only be unlinked and not freed so the stale dst + # remains forever and we get a net device refcount imbalance + run_cmd "$IP nexthop del id 100" + + # if a reference was lost this command will hang because the net device + # cannot be removed + timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1 + + # we can't cleanup if the command is hung trying to delete the netdev + if [ $? -eq 137 ]; then + return 1 + fi + + # cleanup + run_cmd "$IP link del veth1.20" + run_cmd "$IP nexthop flush" + + return 0 +} + ipv6_grp_fcnal() { local rc @@ -734,6 +794,9 @@ ipv6_grp_fcnal() run_cmd "$IP nexthop add id 108 group 31/24" log_test $? 2 "Nexthop group can not have a blackhole and another nexthop" + + ipv6_grp_refs + log_test $? 0 "Nexthop group replace refcounts" } ipv6_res_grp_fcnal() diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5abe92d55b69..996af1ae3d3d 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -444,24 +444,63 @@ fib_rp_filter_test() setup set -e + ip netns add ns2 + ip netns set ns2 auto + + ip -netns ns2 link set dev lo up + + $IP link add name veth1 type veth peer name veth2 + $IP link set dev veth2 netns ns2 + $IP address add 192.0.2.1/24 dev veth1 + ip -netns ns2 address add 192.0.2.1/24 dev veth2 + $IP link set dev veth1 up + ip -netns ns2 link set dev veth2 up + $IP link set dev lo address 52:54:00:6a:c7:5e - $IP link set dummy0 address 52:54:00:6a:c7:5e - $IP link add dummy1 type dummy - $IP link set dummy1 address 52:54:00:6a:c7:5e - $IP link set dev dummy1 up + $IP link set dev veth1 address 52:54:00:6a:c7:5e + ip -netns ns2 link set dev lo address 52:54:00:6a:c7:5e + ip -netns ns2 link set dev veth2 address 52:54:00:6a:c7:5e + + # 1. (ns2) redirect lo's egress to veth2's egress + ip netns exec ns2 tc qdisc add dev lo parent root handle 1: fq_codel + ip netns exec ns2 tc filter add dev lo parent 1: protocol arp basic \ + action mirred egress redirect dev veth2 + ip netns exec ns2 tc filter add dev lo parent 1: protocol ip basic \ + action mirred egress redirect dev veth2 + + # 2. (ns1) redirect veth1's ingress to lo's ingress + $NS_EXEC tc qdisc add dev veth1 ingress + $NS_EXEC tc filter add dev veth1 ingress protocol arp basic \ + action mirred ingress redirect dev lo + $NS_EXEC tc filter add dev veth1 ingress protocol ip basic \ + action mirred ingress redirect dev lo + + # 3. (ns1) redirect lo's egress to veth1's egress + $NS_EXEC tc qdisc add dev lo parent root handle 1: fq_codel + $NS_EXEC tc filter add dev lo parent 1: protocol arp basic \ + action mirred egress redirect dev veth1 + $NS_EXEC tc filter add dev lo parent 1: protocol ip basic \ + action mirred egress redirect dev veth1 + + # 4. (ns2) redirect veth2's ingress to lo's ingress + ip netns exec ns2 tc qdisc add dev veth2 ingress + ip netns exec ns2 tc filter add dev veth2 ingress protocol arp basic \ + action mirred ingress redirect dev lo + ip netns exec ns2 tc filter add dev veth2 ingress protocol ip basic \ + action mirred ingress redirect dev lo + $NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1 $NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1 $NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1 - - $NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel - $NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo - $NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.accept_local=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1 set +e - run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1" + run_cmd "ip netns exec ns2 ping -w1 -c1 192.0.2.1" log_test $? 0 "rp_filter passes local packets" - run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1" + run_cmd "ip netns exec ns2 ping -w1 -c1 127.0.0.1" log_test $? 0 "rp_filter passes loopback packets" cleanup diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh new file mode 100755 index 000000000000..8748d1b1d95b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh @@ -0,0 +1,543 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="vlmc_control_test vlmc_querier_test vlmc_igmp_mld_version_test \ + vlmc_last_member_test vlmc_startup_query_test vlmc_membership_test \ + vlmc_querier_intvl_test vlmc_query_intvl_test vlmc_query_response_intvl_test \ + vlmc_router_port_test vlmc_filtering_test" +NUM_NETIFS=4 +CHECK_TC="yes" +TEST_GROUP="239.10.10.10" + +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64 + ip link add l $h1 $h1.10 up type vlan id 10 +} + +h1_destroy() +{ + ip link del $h1.10 + simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64 + ip link add l $h2 $h2.10 up type vlan id 10 +} + +h2_destroy() +{ + ip link del $h2.10 + simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add dev br0 type bridge mcast_snooping 1 mcast_querier 1 vlan_filtering 1 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact + + bridge vlan add vid 10-11 dev $swp1 master + bridge vlan add vid 10-11 dev $swp2 master + + ip link set dev br0 type bridge mcast_vlan_snooping 1 + check_err $? "Could not enable global vlan multicast snooping" + log_test "Vlan multicast snooping enable" +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +vlmc_v2join_test() +{ + local expect=$1 + + RET=0 + ip address add dev $h2.10 $TEST_GROUP/32 autojoin + check_err $? "Could not join $TEST_GROUP" + + sleep 5 + bridge -j mdb show dev br0 | + jq -e ".[].mdb[] | select(.grp == \"$TEST_GROUP\" and .vid == 10)" &>/dev/null + if [ $expect -eq 0 ]; then + check_err $? "IGMPv2 report didn't create mdb entry for $TEST_GROUP" + else + check_fail $? "IGMPv2 report shouldn't have created mdb entry for $TEST_GROUP" + fi + + # check if we need to cleanup + if [ $RET -eq 0 ]; then + ip address del dev $h2.10 $TEST_GROUP/32 2>&1 1>/dev/null + sleep 5 + bridge -j mdb show dev br0 | + jq -e ".[].mdb[] | select(.grp == \"$TEST_GROUP\" and \ + .vid == 10)" &>/dev/null + check_fail $? "IGMPv2 leave didn't remove mdb entry for $TEST_GROUP" + fi +} + +vlmc_control_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + log_test "Vlan global options existence" + + RET=0 + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and .mcast_snooping == 1) " &>/dev/null + check_err $? "Wrong default mcast_snooping global option value" + log_test "Vlan mcast_snooping global option default value" + + RET=0 + vlmc_v2join_test 0 + bridge vlan global set vid 10 dev br0 mcast_snooping 0 + check_err $? "Could not disable multicast snooping in vlan 10" + vlmc_v2join_test 1 + log_test "Vlan 10 multicast snooping control" +} + +# setup for general query counting +vlmc_query_cnt_xstats() +{ + local type=$1 + local version=$2 + local dev=$3 + + ip -j link xstats type bridge_slave dev $dev | \ + jq -e ".[].multicast.${type}_queries.tx_v${version}" +} + +vlmc_query_cnt_setup() +{ + local type=$1 + local dev=$2 + + if [[ $type == "igmp" ]]; then + tc filter add dev $dev egress pref 10 prot 802.1Q \ + flower vlan_id 10 vlan_ethtype ipv4 dst_ip 224.0.0.1 ip_proto 2 \ + action pass + else + tc filter add dev $dev egress pref 10 prot 802.1Q \ + flower vlan_id 10 vlan_ethtype ipv6 dst_ip ff02::1 ip_proto icmpv6 \ + action pass + fi + + ip link set dev br0 type bridge mcast_stats_enabled 1 +} + +vlmc_query_cnt_cleanup() +{ + local dev=$1 + + ip link set dev br0 type bridge mcast_stats_enabled 0 + tc filter del dev $dev egress pref 10 +} + +vlmc_check_query() +{ + local type=$1 + local version=$2 + local dev=$3 + local expect=$4 + local time=$5 + local ret=0 + + vlmc_query_cnt_setup $type $dev + + local pre_tx_xstats=$(vlmc_query_cnt_xstats $type $version $dev) + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_querier 1 + ret=$? + if [[ $ret -eq 0 ]]; then + sleep $time + + local tcstats=$(tc_rule_stats_get $dev 10 egress) + local post_tx_xstats=$(vlmc_query_cnt_xstats $type $version $dev) + + if [[ $tcstats != $expect || \ + $(($post_tx_xstats-$pre_tx_xstats)) != $expect || \ + $tcstats != $(($post_tx_xstats-$pre_tx_xstats)) ]]; then + ret=1 + fi + fi + + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_querier 0 + vlmc_query_cnt_cleanup $dev + + return $ret +} + +vlmc_querier_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and .mcast_querier == 0) " &>/dev/null + check_err $? "Wrong default mcast_querier global vlan option value" + log_test "Vlan mcast_querier global option default value" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_querier 1 + check_err $? "Could not enable querier in vlan 10" + log_test "Vlan 10 multicast querier enable" + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_querier 0 + + RET=0 + vlmc_check_query igmp 2 $swp1 1 1 + check_err $? "No vlan tagged IGMPv2 general query packets sent" + log_test "Vlan 10 tagged IGMPv2 general query sent" + + RET=0 + vlmc_check_query mld 1 $swp1 1 1 + check_err $? "No vlan tagged MLD general query packets sent" + log_test "Vlan 10 tagged MLD general query sent" +} + +vlmc_igmp_mld_version_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and .mcast_igmp_version == 2) " &>/dev/null + check_err $? "Wrong default mcast_igmp_version global vlan option value" + log_test "Vlan mcast_igmp_version global option default value" + + RET=0 + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and .mcast_mld_version == 1) " &>/dev/null + check_err $? "Wrong default mcast_mld_version global vlan option value" + log_test "Vlan mcast_mld_version global option default value" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_igmp_version 3 + check_err $? "Could not set mcast_igmp_version in vlan 10" + log_test "Vlan 10 mcast_igmp_version option changed to 3" + + RET=0 + vlmc_check_query igmp 3 $swp1 1 1 + check_err $? "No vlan tagged IGMPv3 general query packets sent" + log_test "Vlan 10 tagged IGMPv3 general query sent" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_mld_version 2 + check_err $? "Could not set mcast_mld_version in vlan 10" + log_test "Vlan 10 mcast_mld_version option changed to 2" + + RET=0 + vlmc_check_query mld 2 $swp1 1 1 + check_err $? "No vlan tagged MLDv2 general query packets sent" + log_test "Vlan 10 tagged MLDv2 general query sent" + + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_igmp_version 2 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_mld_version 1 +} + +vlmc_last_member_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and \ + .mcast_last_member_count == 2) " &>/dev/null + check_err $? "Wrong default mcast_last_member_count global vlan option value" + log_test "Vlan mcast_last_member_count global option default value" + + RET=0 + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and \ + .mcast_last_member_interval == 100) " &>/dev/null + check_err $? "Wrong default mcast_last_member_interval global vlan option value" + log_test "Vlan mcast_last_member_interval global option default value" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_last_member_count 3 + check_err $? "Could not set mcast_last_member_count in vlan 10" + log_test "Vlan 10 mcast_last_member_count option changed to 3" + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_last_member_count 2 + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_last_member_interval 200 + check_err $? "Could not set mcast_last_member_interval in vlan 10" + log_test "Vlan 10 mcast_last_member_interval option changed to 200" + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_last_member_interval 100 +} + +vlmc_startup_query_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and \ + .mcast_startup_query_interval == 3125) " &>/dev/null + check_err $? "Wrong default mcast_startup_query_interval global vlan option value" + log_test "Vlan mcast_startup_query_interval global option default value" + + RET=0 + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and \ + .mcast_startup_query_count == 2) " &>/dev/null + check_err $? "Wrong default mcast_startup_query_count global vlan option value" + log_test "Vlan mcast_startup_query_count global option default value" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_startup_query_interval 100 + check_err $? "Could not set mcast_startup_query_interval in vlan 10" + vlmc_check_query igmp 2 $swp1 2 3 + check_err $? "Wrong number of tagged IGMPv2 general queries sent" + log_test "Vlan 10 mcast_startup_query_interval option changed to 100" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_startup_query_count 3 + check_err $? "Could not set mcast_startup_query_count in vlan 10" + vlmc_check_query igmp 2 $swp1 3 4 + check_err $? "Wrong number of tagged IGMPv2 general queries sent" + log_test "Vlan 10 mcast_startup_query_count option changed to 3" + + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_startup_query_interval 3125 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_startup_query_count 2 +} + +vlmc_membership_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and \ + .mcast_membership_interval == 26000) " &>/dev/null + check_err $? "Wrong default mcast_membership_interval global vlan option value" + log_test "Vlan mcast_membership_interval global option default value" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_membership_interval 200 + check_err $? "Could not set mcast_membership_interval in vlan 10" + log_test "Vlan 10 mcast_membership_interval option changed to 200" + + RET=0 + vlmc_v2join_test 1 + log_test "Vlan 10 mcast_membership_interval mdb entry expire" + + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_membership_interval 26000 +} + +vlmc_querier_intvl_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and \ + .mcast_querier_interval == 25500) " &>/dev/null + check_err $? "Wrong default mcast_querier_interval global vlan option value" + log_test "Vlan mcast_querier_interval global option default value" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_querier_interval 100 + check_err $? "Could not set mcast_querier_interval in vlan 10" + log_test "Vlan 10 mcast_querier_interval option changed to 100" + + RET=0 + ip link add dev br1 type bridge mcast_snooping 1 mcast_querier 1 vlan_filtering 1 \ + mcast_vlan_snooping 1 + bridge vlan add vid 10 dev br1 self pvid untagged + ip link set dev $h1 master br1 + ip link set dev br1 up + bridge vlan add vid 10 dev $h1 master + bridge vlan global set vid 10 dev br1 mcast_snooping 1 mcast_querier 1 + sleep 2 + ip link del dev br1 + ip addr replace 2001:db8:1::1/64 dev $h1 + vlmc_check_query igmp 2 $swp1 1 1 + check_err $? "Wrong number of IGMPv2 general queries after querier interval" + log_test "Vlan 10 mcast_querier_interval expire after outside query" + + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_querier_interval 25500 +} + +vlmc_query_intvl_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and \ + .mcast_query_interval == 12500) " &>/dev/null + check_err $? "Wrong default mcast_query_interval global vlan option value" + log_test "Vlan mcast_query_interval global option default value" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_startup_query_count 0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_query_interval 200 + check_err $? "Could not set mcast_query_interval in vlan 10" + # 1 is sent immediately, then 2 more in the next 5 seconds + vlmc_check_query igmp 2 $swp1 3 5 + check_err $? "Wrong number of tagged IGMPv2 general queries sent" + log_test "Vlan 10 mcast_query_interval option changed to 200" + + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_startup_query_count 2 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_query_interval 12500 +} + +vlmc_query_response_intvl_test() +{ + RET=0 + local goutput=`bridge -j vlan global show` + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10)" &>/dev/null + check_err $? "Could not find vlan 10's global options" + + echo -n $goutput | + jq -e ".[].vlans[] | select(.vlan == 10 and \ + .mcast_query_response_interval == 1000) " &>/dev/null + check_err $? "Wrong default mcast_query_response_interval global vlan option value" + log_test "Vlan mcast_query_response_interval global option default value" + + RET=0 + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_query_response_interval 200 + check_err $? "Could not set mcast_query_response_interval in vlan 10" + log_test "Vlan 10 mcast_query_response_interval option changed to 200" + + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_query_response_interval 1000 +} + +vlmc_router_port_test() +{ + RET=0 + local goutput=`bridge -j -d vlan show` + echo -n $goutput | + jq -e ".[] | select(.ifname == \"$swp1\" and \ + .vlans[].vlan == 10)" &>/dev/null + check_err $? "Could not find port vlan 10's options" + + echo -n $goutput | + jq -e ".[] | select(.ifname == \"$swp1\" and \ + .vlans[].vlan == 10 and \ + .vlans[].mcast_router == 1)" &>/dev/null + check_err $? "Wrong default port mcast_router option value" + log_test "Port vlan 10 option mcast_router default value" + + RET=0 + bridge vlan set vid 10 dev $swp1 mcast_router 2 + check_err $? "Could not set port vlan 10's mcast_router option" + log_test "Port vlan 10 mcast_router option changed to 2" + + RET=0 + tc filter add dev $swp1 egress pref 10 prot 802.1Q \ + flower vlan_id 10 vlan_ethtype ipv4 dst_ip 239.1.1.1 ip_proto udp action pass + tc filter add dev $swp2 egress pref 10 prot 802.1Q \ + flower vlan_id 10 vlan_ethtype ipv4 dst_ip 239.1.1.1 ip_proto udp action pass + bridge vlan set vid 10 dev $swp2 mcast_router 0 + # we need to enable querier and disable query response interval to + # make sure packets are flooded only to router ports + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_querier 1 \ + mcast_query_response_interval 0 + bridge vlan add vid 10 dev br0 self + sleep 1 + mausezahn br0 -Q 10 -c 10 -p 128 -b 01:00:5e:01:01:01 -B 239.1.1.1 \ + -t udp "dp=1024" &>/dev/null + local swp1_tcstats=$(tc_rule_stats_get $swp1 10 egress) + if [[ $swp1_tcstats != 10 ]]; then + check_err 1 "Wrong number of vlan 10 multicast packets flooded" + fi + local swp2_tcstats=$(tc_rule_stats_get $swp2 10 egress) + check_err $swp2_tcstats "Vlan 10 multicast packets flooded to non-router port" + log_test "Flood unknown vlan multicast packets to router port only" + + tc filter del dev $swp2 egress pref 10 + tc filter del dev $swp1 egress pref 10 + bridge vlan del vid 10 dev br0 self + bridge vlan global set vid 10 dev br0 mcast_snooping 1 mcast_query_response_interval 1000 + bridge vlan set vid 10 dev $swp2 mcast_router 1 + bridge vlan set vid 10 dev $swp1 mcast_router 1 +} + +vlmc_filtering_test() +{ + RET=0 + ip link set dev br0 type bridge vlan_filtering 0 + ip -j -d link show dev br0 | \ + jq -e "select(.[0].linkinfo.info_data.mcast_vlan_snooping == 1)" &>/dev/null + check_fail $? "Vlan filtering is disabled but multicast vlan snooping is still enabled" + log_test "Disable multicast vlan snooping when vlan filtering is disabled" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index a4bd1b087303..697994a9278b 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -6,6 +6,7 @@ CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NET_VRF=m CONFIG_BPF_SYSCALL=y CONFIG_CGROUP_BPF=y +CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_MPLS=m CONFIG_NET_ACT_VLAN=m diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index d9eca227136b..de19eb6c38f0 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -3,7 +3,7 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ - gact_trap_test" + gact_trap_test mirred_egress_to_ingress_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -13,10 +13,12 @@ tcflags="skip_hw" h1_create() { simple_if_init $h1 192.0.2.1/24 + tc qdisc add dev $h1 clsact } h1_destroy() { + tc qdisc del dev $h1 clsact simple_if_fini $h1 192.0.2.1/24 } @@ -153,6 +155,49 @@ gact_trap_test() log_test "trap ($tcflags)" } +mirred_egress_to_ingress_test() +{ + RET=0 + + tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action \ + ct commit nat src addr 192.0.2.2 pipe \ + ct clear pipe \ + ct commit nat dst addr 192.0.2.1 pipe \ + mirred ingress redirect dev $h1 + + tc filter add dev $swp1 protocol ip pref 11 handle 111 ingress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action drop + tc filter add dev $swp1 protocol ip pref 12 handle 112 ingress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 0 action pass + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t icmp "ping,id=42,seq=10" -q + + tc_check_packets "dev $h1 egress" 100 1 + check_err $? "didn't mirror first packet" + + tc_check_packets "dev $swp1 ingress" 111 1 + check_fail $? "didn't redirect first packet" + tc_check_packets "dev $swp1 ingress" 112 1 + check_err $? "didn't receive reply to first packet" + + ping 192.0.2.2 -I$h1 -c1 -w1 -q 1>/dev/null 2>&1 + + tc_check_packets "dev $h1 egress" 100 2 + check_err $? "didn't mirror second packet" + tc_check_packets "dev $swp1 ingress" 111 1 + check_fail $? "didn't redirect second packet" + tc_check_packets "dev $swp1 ingress" 112 2 + check_err $? "didn't receive reply to second packet" + + tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower + tc filter del dev $swp1 ingress protocol ip pref 11 handle 111 flower + tc filter del dev $swp1 ingress protocol ip pref 12 handle 112 flower + + log_test "mirred_egress_to_ingress ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh index fdeb44d621eb..3224651db97b 100755 --- a/tools/testing/selftests/net/gre_gso.sh +++ b/tools/testing/selftests/net/gre_gso.sh @@ -118,16 +118,18 @@ gre_gst_test_checks() local addr=$2 local proto=$3 - $NS_EXEC nc $proto -kl $port >/dev/null & + [ "$proto" == 6 ] && addr="[$addr]" + + $NS_EXEC socat - tcp${proto}-listen:$port,reuseaddr,fork >/dev/null & PID=$! while ! $NS_EXEC ss -ltn | grep -q $port; do ((i++)); sleep 0.01; done - cat $TMPFILE | timeout 1 nc $proto -N $addr $port + cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port log_test $? 0 "$name - copy file w/ TSO" ethtool -K veth0 tso off - cat $TMPFILE | timeout 1 nc $proto -N $addr $port + cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port log_test $? 0 "$name - copy file w/ GSO" ethtool -K veth0 tso on @@ -155,8 +157,8 @@ gre6_gso_test() sleep 2 - gre_gst_test_checks GREv6/v4 172.16.2.2 - gre_gst_test_checks GREv6/v6 2001:db8:1::2 -6 + gre_gst_test_checks GREv6/v4 172.16.2.2 4 + gre_gst_test_checks GREv6/v6 2001:db8:1::2 6 cleanup } @@ -212,8 +214,8 @@ if [ ! -x "$(command -v ip)" ]; then exit $ksft_skip fi -if [ ! -x "$(command -v nc)" ]; then - echo "SKIP: Could not run test without nc tool" +if [ ! -x "$(command -v socat)" ]; then + echo "SKIP: Could not run test without socat tool" exit $ksft_skip fi diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore index 7569d892967a..49daae73c41e 100644 --- a/tools/testing/selftests/net/mptcp/.gitignore +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only mptcp_connect +mptcp_inq mptcp_sockopt pm_nl_ctl *.pcap diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index bbf4e448bad9..0356c4501c99 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -8,7 +8,7 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh -TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt +TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq TEST_FILES := settings diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 0faaccd21447..419e71560fd1 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -13,5 +13,9 @@ CONFIG_NFT_COUNTER=m CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XTABLES=m CONFIG_NETFILTER_XT_MATCH_BPF=m -CONFIG_NF_TABLES_IPV4=y -CONFIG_NF_TABLES_IPV6=y +CONFIG_NF_TABLES_INET=y +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SOCKET=m +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IPV6_MULTIPLE_TABLES=y diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 95e81d557b08..98de28ac3ba8 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -73,9 +73,22 @@ static uint32_t cfg_mark; struct cfg_cmsg_types { unsigned int cmsg_enabled:1; unsigned int timestampns:1; + unsigned int tcp_inq:1; }; +struct cfg_sockopt_types { + unsigned int transparent:1; +}; + +struct tcp_inq_state { + unsigned int last; + bool expect_eof; +}; + +static struct tcp_inq_state tcp_inq; + static struct cfg_cmsg_types cfg_cmsg_types; +static struct cfg_sockopt_types cfg_sockopt_types; static void die_usage(void) { @@ -93,6 +106,7 @@ static void die_usage(void) fprintf(stderr, "\t-u -- check mptcp ulp\n"); fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); fprintf(stderr, "\t-c cmsg -- test cmsg type <cmsg>\n"); + fprintf(stderr, "\t-o option -- test sockopt <option>\n"); fprintf(stderr, "\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n"); exit(1); @@ -185,6 +199,22 @@ static void set_mark(int fd, uint32_t mark) } } +static void set_transparent(int fd, int pf) +{ + int one = 1; + + switch (pf) { + case AF_INET: + if (-1 == setsockopt(fd, SOL_IP, IP_TRANSPARENT, &one, sizeof(one))) + perror("IP_TRANSPARENT"); + break; + case AF_INET6: + if (-1 == setsockopt(fd, IPPROTO_IPV6, IPV6_TRANSPARENT, &one, sizeof(one))) + perror("IPV6_TRANSPARENT"); + break; + } +} + static int sock_listen_mptcp(const char * const listenaddr, const char * const port) { @@ -212,6 +242,9 @@ static int sock_listen_mptcp(const char * const listenaddr, sizeof(one))) perror("setsockopt"); + if (cfg_sockopt_types.transparent) + set_transparent(sock, pf); + if (bind(sock, a->ai_addr, a->ai_addrlen) == 0) break; /* success */ @@ -364,7 +397,9 @@ static size_t do_write(const int fd, char *buf, const size_t len) static void process_cmsg(struct msghdr *msgh) { struct __kernel_timespec ts; + bool inq_found = false; bool ts_found = false; + unsigned int inq = 0; struct cmsghdr *cmsg; for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) { @@ -373,12 +408,27 @@ static void process_cmsg(struct msghdr *msgh) ts_found = true; continue; } + if (cmsg->cmsg_level == IPPROTO_TCP && cmsg->cmsg_type == TCP_CM_INQ) { + memcpy(&inq, CMSG_DATA(cmsg), sizeof(inq)); + inq_found = true; + continue; + } + } if (cfg_cmsg_types.timestampns) { if (!ts_found) xerror("TIMESTAMPNS not present\n"); } + + if (cfg_cmsg_types.tcp_inq) { + if (!inq_found) + xerror("TCP_INQ not present\n"); + + if (inq > 1024) + xerror("tcp_inq %u is larger than one kbyte\n", inq); + tcp_inq.last = inq; + } } static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len) @@ -395,10 +445,23 @@ static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len) .msg_controllen = sizeof(msg_buf), }; int flags = 0; + unsigned int last_hint = tcp_inq.last; int ret = recvmsg(fd, &msg, flags); - if (ret <= 0) + if (ret <= 0) { + if (ret == 0 && tcp_inq.expect_eof) + return ret; + + if (ret == 0 && cfg_cmsg_types.tcp_inq) + if (last_hint != 1 && last_hint != 0) + xerror("EOF but last tcp_inq hint was %u\n", last_hint); + return ret; + } + + if (tcp_inq.expect_eof) + xerror("expected EOF, last_hint %u, now %u\n", + last_hint, tcp_inq.last); if (msg.msg_controllen && !cfg_cmsg_types.cmsg_enabled) xerror("got %lu bytes of cmsg data, expected 0\n", @@ -410,6 +473,19 @@ static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len) if (msg.msg_controllen) process_cmsg(&msg); + if (cfg_cmsg_types.tcp_inq) { + if ((size_t)ret < len && last_hint > (unsigned int)ret) { + if (ret + 1 != (int)last_hint) { + int next = read(fd, msg_buf, sizeof(msg_buf)); + + xerror("read %u of %u, last_hint was %u tcp_inq hint now %u next_read returned %d/%m\n", + ret, (unsigned int)len, last_hint, tcp_inq.last, next); + } else { + tcp_inq.expect_eof = true; + } + } + } + return ret; } @@ -919,6 +995,8 @@ static void apply_cmsg_types(int fd, const struct cfg_cmsg_types *cmsg) if (cmsg->timestampns) xsetsockopt(fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, &on, sizeof(on)); + if (cmsg->tcp_inq) + xsetsockopt(fd, IPPROTO_TCP, TCP_INQ, &on, sizeof(on)); } static void parse_cmsg_types(const char *type) @@ -940,10 +1018,36 @@ static void parse_cmsg_types(const char *type) return; } + if (strncmp(type, "TCPINQ", len) == 0) { + cfg_cmsg_types.tcp_inq = 1; + return; + } + fprintf(stderr, "Unrecognized cmsg option %s\n", type); exit(1); } +static void parse_setsock_options(const char *name) +{ + char *next = strchr(name, ','); + unsigned int len = 0; + + if (next) { + parse_setsock_options(next + 1); + len = next - name; + } else { + len = strlen(name); + } + + if (strncmp(name, "TRANSPARENT", len) == 0) { + cfg_sockopt_types.transparent = 1; + return; + } + + fprintf(stderr, "Unrecognized setsockopt option %s\n", name); + exit(1); +} + int main_loop(void) { int fd; @@ -1047,7 +1151,7 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:")) != -1) { + while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:o:")) != -1) { switch (c) { case 'j': cfg_join = true; @@ -1108,6 +1212,9 @@ static void parse_opts(int argc, char **argv) case 'c': parse_cmsg_types(optarg); break; + case 'o': + parse_setsock_options(optarg); + break; } } diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 559173a8e387..a4226b608c68 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -671,6 +671,82 @@ run_tests() run_tests_lo $1 $2 $3 0 } +run_test_transparent() +{ + local connect_addr="$1" + local msg="$2" + + local connector_ns="$ns1" + local listener_ns="$ns2" + local lret=0 + local r6flag="" + + # skip if we don't want v6 + if ! $ipv6 && is_v6 "${connect_addr}"; then + return 0 + fi + +ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" +flush ruleset +table inet mangle { + chain divert { + type filter hook prerouting priority -150; + + meta l4proto tcp socket transparent 1 meta mark set 1 accept + tcp dport 20000 tproxy to :20000 meta mark set 1 accept + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: $msg, could not load nft ruleset" + return + fi + + local local_addr + if is_v6 "${connect_addr}"; then + local_addr="::" + r6flag="-6" + else + local_addr="0.0.0.0" + fi + + ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100 + if [ $? -ne 0 ]; then + ip netns exec "$listener_ns" nft flush ruleset + echo "SKIP: $msg, ip $r6flag rule failed" + return + fi + + ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100 + if [ $? -ne 0 ]; then + ip netns exec "$listener_ns" nft flush ruleset + ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100 + echo "SKIP: $msg, ip route add local $local_addr failed" + return + fi + + echo "INFO: test $msg" + + TEST_COUNT=10000 + local extra_args="-o TRANSPARENT" + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \ + ${connect_addr} ${local_addr} "${extra_args}" + lret=$? + + ip netns exec "$listener_ns" nft flush ruleset + ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100 + ip -net "$listener_ns" route del local $local_addr/0 dev lo table 100 + + if [ $lret -ne 0 ]; then + echo "FAIL: $msg, mptcp connection error" 1>&2 + ret=$lret + return 1 + fi + + echo "PASS: $msg" + return 0 +} + run_tests_peekmode() { local peekmode="$1" @@ -794,5 +870,9 @@ run_tests_peekmode "saveWithPeek" run_tests_peekmode "saveAfterPeek" stop_if_error "Tests with peek mode have failed" +# connect to ns4 ip address, ns2 should intercept/proxy +run_test_transparent 10.0.3.1 "tproxy ipv4" +run_test_transparent dead:beef:3::1 "tproxy ipv6" + display_time exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c new file mode 100644 index 000000000000..29f75e2a1116 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -0,0 +1,602 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <string.h> +#include <stdarg.h> +#include <stdbool.h> +#include <stdint.h> +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <unistd.h> +#include <time.h> + +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include <netdb.h> +#include <netinet/in.h> + +#include <linux/tcp.h> +#include <linux/sockios.h> + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef SOL_MPTCP +#define SOL_MPTCP 284 +#endif + +static int pf = AF_INET; +static int proto_tx = IPPROTO_MPTCP; +static int proto_rx = IPPROTO_MPTCP; + +static void die_perror(const char *msg) +{ + perror(msg); + exit(1); +} + +static void die_usage(int r) +{ + fprintf(stderr, "Usage: mptcp_inq [-6] [ -t tcp|mptcp ] [ -r tcp|mptcp]\n"); + exit(r); +} + +static void xerror(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + fputc('\n', stderr); + exit(1); +} + +static const char *getxinfo_strerr(int err) +{ + if (err == EAI_SYSTEM) + return strerror(errno); + + return gai_strerror(err); +} + +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 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, proto_rx); + 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) + xerror("could not create listen socket"); + + if (listen(sock, 20)) + die_perror("listen"); + + return sock; +} + +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) + continue; + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + die_perror("connect"); + } + + if (sock < 0) + xerror("could not create connect socket"); + + freeaddrinfo(addr); + return sock; +} + +static int protostr_to_num(const char *s) +{ + if (strcasecmp(s, "tcp") == 0) + return IPPROTO_TCP; + if (strcasecmp(s, "mptcp") == 0) + return IPPROTO_MPTCP; + + die_usage(1); + return 0; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "h6t:r:")) != -1) { + switch (c) { + case 'h': + die_usage(0); + break; + case '6': + pf = AF_INET6; + break; + case 't': + proto_tx = protostr_to_num(optarg); + break; + case 'r': + proto_rx = protostr_to_num(optarg); + break; + default: + die_usage(1); + break; + } + } +} + +/* wait up to timeout milliseconds */ +static void wait_for_ack(int fd, int timeout, size_t total) +{ + int i; + + for (i = 0; i < timeout; i++) { + int nsd, ret, queued = -1; + struct timespec req; + + ret = ioctl(fd, TIOCOUTQ, &queued); + if (ret < 0) + die_perror("TIOCOUTQ"); + + ret = ioctl(fd, SIOCOUTQNSD, &nsd); + if (ret < 0) + die_perror("SIOCOUTQNSD"); + + if ((size_t)queued > total) + xerror("TIOCOUTQ %u, but only %zu expected\n", queued, total); + assert(nsd <= queued); + + if (queued == 0) + return; + + /* wait for peer to ack rx of all data */ + req.tv_sec = 0; + req.tv_nsec = 1 * 1000 * 1000ul; /* 1ms */ + nanosleep(&req, NULL); + } + + xerror("still tx data queued after %u ms\n", timeout); +} + +static void connect_one_server(int fd, int unixfd) +{ + size_t len, i, total, sent; + char buf[4096], buf2[4096]; + ssize_t ret; + + len = rand() % (sizeof(buf) - 1); + + if (len < 128) + len = 128; + + for (i = 0; i < len ; i++) { + buf[i] = rand() % 26; + buf[i] += 'A'; + } + + buf[i] = '\n'; + + /* un-block server */ + ret = read(unixfd, buf2, 4); + assert(ret == 4); + + assert(strncmp(buf2, "xmit", 4) == 0); + + ret = write(unixfd, &len, sizeof(len)); + assert(ret == (ssize_t)sizeof(len)); + + ret = write(fd, buf, len); + if (ret < 0) + die_perror("write"); + + if (ret != (ssize_t)len) + xerror("short write"); + + ret = read(unixfd, buf2, 4); + assert(strncmp(buf2, "huge", 4) == 0); + + total = rand() % (16 * 1024 * 1024); + total += (1 * 1024 * 1024); + sent = total; + + ret = write(unixfd, &total, sizeof(total)); + assert(ret == (ssize_t)sizeof(total)); + + wait_for_ack(fd, 5000, len); + + while (total > 0) { + if (total > sizeof(buf)) + len = sizeof(buf); + else + len = total; + + ret = write(fd, buf, len); + if (ret < 0) + die_perror("write"); + total -= ret; + + /* we don't have to care about buf content, only + * number of total bytes sent + */ + } + + ret = read(unixfd, buf2, 4); + assert(ret == 4); + assert(strncmp(buf2, "shut", 4) == 0); + + wait_for_ack(fd, 5000, sent); + + ret = write(fd, buf, 1); + assert(ret == 1); + close(fd); + ret = write(unixfd, "closed", 6); + assert(ret == 6); + + close(unixfd); +} + +static void get_tcp_inq(struct msghdr *msgh, unsigned int *inqv) +{ + struct cmsghdr *cmsg; + + for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) { + if (cmsg->cmsg_level == IPPROTO_TCP && cmsg->cmsg_type == TCP_CM_INQ) { + memcpy(inqv, CMSG_DATA(cmsg), sizeof(*inqv)); + return; + } + } + + xerror("could not find TCP_CM_INQ cmsg type"); +} + +static void process_one_client(int fd, int unixfd) +{ + unsigned int tcp_inq; + size_t expect_len; + char msg_buf[4096]; + char buf[4096]; + char tmp[16]; + struct iovec iov = { + .iov_base = buf, + .iov_len = 1, + }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = msg_buf, + .msg_controllen = sizeof(msg_buf), + }; + ssize_t ret, tot; + + ret = write(unixfd, "xmit", 4); + assert(ret == 4); + + ret = read(unixfd, &expect_len, sizeof(expect_len)); + assert(ret == (ssize_t)sizeof(expect_len)); + + if (expect_len > sizeof(buf)) + xerror("expect len %zu exceeds buffer size", expect_len); + + for (;;) { + struct timespec req; + unsigned int queued; + + ret = ioctl(fd, FIONREAD, &queued); + if (ret < 0) + die_perror("FIONREAD"); + if (queued > expect_len) + xerror("FIONREAD returned %u, but only %zu expected\n", + queued, expect_len); + if (queued == expect_len) + break; + + req.tv_sec = 0; + req.tv_nsec = 1000 * 1000ul; + nanosleep(&req, NULL); + } + + /* read one byte, expect cmsg to return expected - 1 */ + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + + if (msg.msg_controllen == 0) + xerror("msg_controllen is 0"); + + get_tcp_inq(&msg, &tcp_inq); + + assert((size_t)tcp_inq == (expect_len - 1)); + + iov.iov_len = sizeof(buf); + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + + /* should have gotten exact remainder of all pending data */ + assert(ret == (ssize_t)tcp_inq); + + /* should be 0, all drained */ + get_tcp_inq(&msg, &tcp_inq); + assert(tcp_inq == 0); + + /* request a large swath of data. */ + ret = write(unixfd, "huge", 4); + assert(ret == 4); + + ret = read(unixfd, &expect_len, sizeof(expect_len)); + assert(ret == (ssize_t)sizeof(expect_len)); + + /* peer should send us a few mb of data */ + if (expect_len <= sizeof(buf)) + xerror("expect len %zu too small\n", expect_len); + + tot = 0; + do { + iov.iov_len = sizeof(buf); + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + + tot += ret; + + get_tcp_inq(&msg, &tcp_inq); + + if (tcp_inq > expect_len - tot) + xerror("inq %d, remaining %d total_len %d\n", + tcp_inq, expect_len - tot, (int)expect_len); + + assert(tcp_inq <= expect_len - tot); + } while ((size_t)tot < expect_len); + + ret = write(unixfd, "shut", 4); + assert(ret == 4); + + /* wait for hangup. Should have received one more byte of data. */ + ret = read(unixfd, tmp, sizeof(tmp)); + assert(ret == 6); + assert(strncmp(tmp, "closed", 6) == 0); + + sleep(1); + + iov.iov_len = 1; + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + assert(ret == 1); + + get_tcp_inq(&msg, &tcp_inq); + + /* tcp_inq should be 1 due to received fin. */ + assert(tcp_inq == 1); + + iov.iov_len = 1; + ret = recvmsg(fd, &msg, 0); + if (ret < 0) + die_perror("recvmsg"); + + /* expect EOF */ + assert(ret == 0); + get_tcp_inq(&msg, &tcp_inq); + assert(tcp_inq == 1); + + close(fd); +} + +static int xaccept(int s) +{ + int fd = accept(s, NULL, 0); + + if (fd < 0) + die_perror("accept"); + + return fd; +} + +static int server(int unixfd) +{ + int fd = -1, r, on = 1; + + switch (pf) { + case AF_INET: + fd = sock_listen_mptcp("127.0.0.1", "15432"); + break; + case AF_INET6: + fd = sock_listen_mptcp("::1", "15432"); + break; + default: + xerror("Unknown pf %d\n", pf); + break; + } + + r = write(unixfd, "conn", 4); + assert(r == 4); + + alarm(15); + r = xaccept(fd); + + if (-1 == setsockopt(r, IPPROTO_TCP, TCP_INQ, &on, sizeof(on))) + die_perror("setsockopt"); + + process_one_client(r, unixfd); + + return 0; +} + +static int client(int unixfd) +{ + int fd = -1; + + alarm(15); + + switch (pf) { + case AF_INET: + fd = sock_connect_mptcp("127.0.0.1", "15432", proto_tx); + break; + case AF_INET6: + fd = sock_connect_mptcp("::1", "15432", proto_tx); + break; + default: + xerror("Unknown pf %d\n", pf); + } + + connect_one_server(fd, unixfd); + + return 0; +} + +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); +} + +static pid_t xfork(void) +{ + pid_t p = fork(); + + if (p < 0) + die_perror("fork"); + else if (p == 0) + init_rng(); + + return p; +} + +static int rcheck(int wstatus, const char *what) +{ + if (WIFEXITED(wstatus)) { + if (WEXITSTATUS(wstatus) == 0) + return 0; + fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus)); + return WEXITSTATUS(wstatus); + } else if (WIFSIGNALED(wstatus)) { + xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus)); + } else if (WIFSTOPPED(wstatus)) { + xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus)); + } + + return 111; +} + +int main(int argc, char *argv[]) +{ + int e1, e2, wstatus; + pid_t s, c, ret; + int unixfds[2]; + + parse_opts(argc, argv); + + e1 = socketpair(AF_UNIX, SOCK_DGRAM, 0, unixfds); + if (e1 < 0) + die_perror("pipe"); + + s = xfork(); + if (s == 0) + return server(unixfds[1]); + + close(unixfds[1]); + + /* wait until server bound a socket */ + e1 = read(unixfds[0], &e1, 4); + assert(e1 == 4); + + c = xfork(); + if (c == 0) + return client(unixfds[0]); + + close(unixfds[0]); + + ret = waitpid(s, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e1 = rcheck(wstatus, "server"); + ret = waitpid(c, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e2 = rcheck(wstatus, "client"); + + return e1 ? e1 : e2; +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index 417b11cafafe..ac9a4d9c1764 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -4,6 +4,7 @@ #include <assert.h> #include <errno.h> +#include <fcntl.h> #include <limits.h> #include <string.h> #include <stdarg.h> @@ -13,6 +14,7 @@ #include <stdio.h> #include <stdlib.h> #include <strings.h> +#include <time.h> #include <unistd.h> #include <sys/socket.h> @@ -594,6 +596,44 @@ static int server(int pipefd) return 0; } +static void test_ip_tos_sockopt(int fd) +{ + uint8_t tos_in, tos_out; + socklen_t s; + int r; + + tos_in = rand() & 0xfc; + r = setsockopt(fd, SOL_IP, IP_TOS, &tos_in, sizeof(tos_out)); + if (r != 0) + die_perror("setsockopt IP_TOS"); + + tos_out = 0; + s = sizeof(tos_out); + r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s); + if (r != 0) + die_perror("getsockopt IP_TOS"); + + if (tos_in != tos_out) + xerror("tos %x != %x socklen_t %d\n", tos_in, tos_out, s); + + if (s != 1) + xerror("tos should be 1 byte"); + + s = 0; + r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s); + if (r != 0) + die_perror("getsockopt IP_TOS 0"); + if (s != 0) + xerror("expect socklen_t == 0"); + + s = -1; + r = getsockopt(fd, SOL_IP, IP_TOS, &tos_out, &s); + if (r != -1 && errno != EINVAL) + die_perror("getsockopt IP_TOS did not indicate -EINVAL"); + if (s != -1) + xerror("expect socklen_t == -1"); +} + static int client(int pipefd) { int fd = -1; @@ -611,6 +651,8 @@ static int client(int pipefd) xerror("Unknown pf %d\n", pf); } + test_ip_tos_sockopt(fd); + connect_one_server(fd, pipefd); return 0; @@ -642,6 +684,25 @@ static int rcheck(int wstatus, const char *what) return 111; } +static void init_rng(void) +{ + int fd = open("/dev/urandom", O_RDONLY); + + if (fd >= 0) { + unsigned int foo; + ssize_t ret; + + /* can't fail */ + ret = read(fd, &foo, sizeof(foo)); + assert(ret == sizeof(foo)); + + close(fd); + srand(foo); + } else { + srand(time(NULL)); + } +} + int main(int argc, char *argv[]) { int e1, e2, wstatus; @@ -650,6 +711,8 @@ int main(int argc, char *argv[]) parse_opts(argc, argv); + init_rng(); + e1 = pipe(pipefds); if (e1 < 0) die_perror("pipe"); diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 41de643788b8..0879da915014 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -178,7 +178,7 @@ do_transfer() timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS,TCPINQ \ ${local_addr} < "$sin" > "$sout" & spid=$! @@ -186,7 +186,7 @@ do_transfer() timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS,TCPINQ \ $connect_addr < "$cin" > "$cout" & cpid=$! @@ -279,6 +279,45 @@ run_tests() fi } +do_tcpinq_test() +{ + ip netns exec "$ns1" ./mptcp_inq "$@" + lret=$? + if [ $lret -ne 0 ];then + ret=$lret + echo "FAIL: mptcp_inq $@" 1>&2 + return $lret + fi + + echo "PASS: TCP_INQ cmsg/ioctl $@" + return $lret +} + +do_tcpinq_tests() +{ + local lret=0 + + ip netns exec "$ns1" iptables -F + ip netns exec "$ns1" ip6tables -F + + for args in "-t tcp" "-r tcp"; do + do_tcpinq_test $args + lret=$? + if [ $lret -ne 0 ] ; then + return $lret + fi + do_tcpinq_test -6 $args + lret=$? + if [ $lret -ne 0 ] ; then + return $lret + fi + done + + do_tcpinq_test -r tcp -t tcp + + return $? +} + sin=$(mktemp) sout=$(mktemp) cin=$(mktemp) @@ -300,4 +339,5 @@ if [ $ret -eq 0 ];then echo "PASS: SOL_MPTCP getsockopt has expected information" fi +do_tcpinq_tests exit $ret diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index b599003eb5ba..d9a6fd2cd9d3 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -85,6 +85,7 @@ struct sock_args { int version; /* AF_INET/AF_INET6 */ int use_setsockopt; + int use_freebind; int use_cmsg; const char *dev; const char *server_dev; @@ -514,6 +515,29 @@ static int set_membership(int sd, uint32_t grp, uint32_t addr, int ifindex) return 0; } +static int set_freebind(int sd, int version) +{ + unsigned int one = 1; + int rc = 0; + + switch (version) { + case AF_INET: + if (setsockopt(sd, SOL_IP, IP_FREEBIND, &one, sizeof(one))) { + log_err_errno("setsockopt(IP_FREEBIND)"); + rc = -1; + } + break; + case AF_INET6: + if (setsockopt(sd, SOL_IPV6, IPV6_FREEBIND, &one, sizeof(one))) { + log_err_errno("setsockopt(IPV6_FREEBIND"); + rc = -1; + } + break; + } + + return rc; +} + static int set_broadcast(int sd) { unsigned int one = 1; @@ -1419,6 +1443,9 @@ static int lsock_init(struct sock_args *args) set_unicast_if(sd, args->ifindex, args->version)) goto err; + if (args->use_freebind && set_freebind(sd, args->version)) + goto err; + if (bind_socket(sd, args)) goto err; @@ -1827,7 +1854,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) return client_status; } -#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" +#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbqf" #define OPT_FORCE_BIND_KEY_IFINDEX 1001 #define OPT_NO_BIND_KEY_IFINDEX 1002 @@ -1864,6 +1891,7 @@ static void print_usage(char *prog) " -I dev bind socket to given device name - server mode\n" " -S use setsockopt (IP_UNICAST_IF or IP_MULTICAST_IF)\n" " to set device binding\n" + " -f bind socket with the IP[V6]_FREEBIND option\n" " -C use cmsg and IP_PKTINFO to specify device binding\n" "\n" " -L len send random message of given length\n" @@ -1999,6 +2027,9 @@ int main(int argc, char *argv[]) case 'S': args.use_setsockopt = 1; break; + case 'f': + args.use_freebind = 1; + break; case 'C': args.use_cmsg = 1; break; diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e61fc4c32ba2..6e468e0f42f7 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -31,6 +31,8 @@ struct tls_crypto_info_keys { struct tls12_crypto_info_chacha20_poly1305 chacha20; struct tls12_crypto_info_sm4_gcm sm4gcm; struct tls12_crypto_info_sm4_ccm sm4ccm; + struct tls12_crypto_info_aes_ccm_128 aesccm128; + struct tls12_crypto_info_aes_gcm_256 aesgcm256; }; size_t len; }; @@ -61,6 +63,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->sm4ccm.info.version = tls_version; tls12->sm4ccm.info.cipher_type = cipher_type; break; + case TLS_CIPHER_AES_CCM_128: + tls12->len = sizeof(struct tls12_crypto_info_aes_ccm_128); + tls12->aesccm128.info.version = tls_version; + tls12->aesccm128.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_AES_GCM_256: + tls12->len = sizeof(struct tls12_crypto_info_aes_gcm_256); + tls12->aesgcm256.info.version = tls_version; + tls12->aesgcm256.info.cipher_type = cipher_type; + break; default: break; } @@ -78,26 +90,21 @@ static void memrnd(void *s, size_t n) *byte++ = rand(); } -FIXTURE(tls_basic) -{ - int fd, cfd; - bool notls; -}; - -FIXTURE_SETUP(tls_basic) +static void ulp_sock_pair(struct __test_metadata *_metadata, + int *fd, int *cfd, bool *notls) { struct sockaddr_in addr; socklen_t len; int sfd, ret; - self->notls = false; + *notls = false; len = sizeof(addr); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(INADDR_ANY); addr.sin_port = 0; - self->fd = socket(AF_INET, SOCK_STREAM, 0); + *fd = socket(AF_INET, SOCK_STREAM, 0); sfd = socket(AF_INET, SOCK_STREAM, 0); ret = bind(sfd, &addr, sizeof(addr)); @@ -108,26 +115,96 @@ FIXTURE_SETUP(tls_basic) ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = connect(*fd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); + *cfd = accept(sfd, &addr, &len); + ASSERT_GE(*cfd, 0); close(sfd); - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); if (ret != 0) { ASSERT_EQ(errno, ENOENT); - self->notls = true; + *notls = true; printf("Failure setting TCP_ULP, testing without tls\n"); return; } - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); ASSERT_EQ(ret, 0); } +/* Produce a basic cmsg */ +static int tls_send_cmsg(int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + int cmsg_len = sizeof(char); + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec vec; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_TLS; + /* test sending non-record types. */ + cmsg->cmsg_type = TLS_SET_RECORD_TYPE; + cmsg->cmsg_len = CMSG_LEN(cmsg_len); + *CMSG_DATA(cmsg) = record_type; + msg.msg_controllen = cmsg->cmsg_len; + + return sendmsg(fd, &msg, flags); +} + +static int tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + struct cmsghdr *cmsg; + unsigned char ctype; + struct msghdr msg; + struct iovec vec; + int n; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + + n = recvmsg(fd, &msg, flags); + + cmsg = CMSG_FIRSTHDR(&msg); + EXPECT_NE(cmsg, NULL); + EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); + EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); + ctype = *((unsigned char *)CMSG_DATA(cmsg)); + EXPECT_EQ(ctype, record_type); + + return n; +} + +FIXTURE(tls_basic) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls_basic) +{ + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); +} + FIXTURE_TEARDOWN(tls_basic) { close(self->fd); @@ -196,63 +273,48 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) .cipher_type = TLS_CIPHER_SM4_CCM, }; +FIXTURE_VARIANT_ADD(tls, 12_aes_ccm) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_AES_CCM_128, +}; + +FIXTURE_VARIANT_ADD(tls, 13_aes_ccm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_AES_CCM_128, +}; + +FIXTURE_VARIANT_ADD(tls, 12_aes_gcm_256) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_AES_GCM_256, +}; + +FIXTURE_VARIANT_ADD(tls, 13_aes_gcm_256) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_AES_GCM_256, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; - struct sockaddr_in addr; - socklen_t len; - int sfd, ret; - - self->notls = false; - len = sizeof(addr); + int ret; tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; - - self->fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); - ret = bind(sfd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - ret = listen(sfd, 10); - ASSERT_EQ(ret, 0); + if (self->notls) + return; - ret = getsockname(sfd, &addr, &len); + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - self->notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); - } - - if (!self->notls) { - ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); - - if (!self->notls) { - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - ASSERT_EQ(ret, 0); - - ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - close(sfd); } FIXTURE_TEARDOWN(tls) @@ -613,6 +675,95 @@ TEST_F(tls, splice_to_pipe) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, splice_dec_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, recv_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int half = send_len / 2; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + /* Recv hald of the record, splice the other half */ + EXPECT_EQ(recv(self->cfd, mem_recv, half, MSG_WAITALL), half); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, half, SPLICE_F_NONBLOCK), + half); + EXPECT_EQ(read(p[0], &mem_recv[half], half), half); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, peek_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int chunk = TLS_PAYLOAD_MAX_LEN / 4; + int n, i, p[2]; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + for (i = 0; i < 4; i++) + EXPECT_EQ(send(self->fd, &mem_send[chunk * i], chunk, 0), + chunk); + + EXPECT_EQ(recv(self->cfd, mem_recv, chunk * 5 / 2, + MSG_WAITALL | MSG_PEEK), + chunk * 5 / 2); + EXPECT_EQ(memcmp(mem_send, mem_recv, chunk * 5 / 2), 0); + + n = 0; + while (n < send_len) { + i = splice(self->cfd, NULL, p[1], NULL, send_len - n, 0); + EXPECT_GT(i, 0); + n += i; + } + EXPECT_EQ(n, send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + TEST_F(tls, recvmsg_single) { char const *test_str = "test_recvmsg_single"; @@ -1193,60 +1344,30 @@ TEST_F(tls, mutliproc_sendpage_writers) TEST_F(tls, control_msg) { - if (self->notls) - return; - - char cbuf[CMSG_SPACE(sizeof(char))]; - char const *test_str = "test_read"; - int cmsg_len = sizeof(char); + char *test_str = "test_read"; char record_type = 100; - struct cmsghdr *cmsg; - struct msghdr msg; int send_len = 10; - struct iovec vec; char buf[10]; - vec.iov_base = (char *)test_str; - vec.iov_len = 10; - memset(&msg, 0, sizeof(struct msghdr)); - msg.msg_iov = &vec; - msg.msg_iovlen = 1; - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_TLS; - /* test sending non-record types. */ - cmsg->cmsg_type = TLS_SET_RECORD_TYPE; - cmsg->cmsg_len = CMSG_LEN(cmsg_len); - *CMSG_DATA(cmsg) = record_type; - msg.msg_controllen = cmsg->cmsg_len; + if (self->notls) + SKIP(return, "no TLS support"); - EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, record_type, test_str, send_len, 0), + send_len); /* Should fail because we didn't provide a control message */ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); - vec.iov_base = buf; - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len); - - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL | MSG_PEEK), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); /* Recv the message again without MSG_PEEK */ - record_type = 0; memset(buf, 0, sizeof(buf)); - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -1301,6 +1422,160 @@ TEST_F(tls, shutdown_reuse) EXPECT_EQ(errno, EISCONN); } +FIXTURE(tls_err) +{ + int fd, cfd; + int fd2, cfd2; + bool notls; +}; + +FIXTURE_VARIANT(tls_err) +{ + uint16_t tls_version; +}; + +FIXTURE_VARIANT_ADD(tls_err, 12_aes_gcm) +{ + .tls_version = TLS_1_2_VERSION, +}; + +FIXTURE_VARIANT_ADD(tls_err, 13_aes_gcm) +{ + .tls_version = TLS_1_3_VERSION, +}; + +FIXTURE_SETUP(tls_err) +{ + struct tls_crypto_info_keys tls12; + int ret; + + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128, + &tls12); + + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); + ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls); + if (self->notls) + return; + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd2, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(tls_err) +{ + close(self->fd); + close(self->cfd); + close(self->fd2); + close(self->cfd2); +} + +TEST_F(tls_err, bad_rec) +{ + char buf[64]; + + if (self->notls) + SKIP(return, "no TLS support"); + + memset(buf, 0x55, sizeof(buf)); + EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf)); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EMSGSIZE); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EAGAIN); +} + +TEST_F(tls_err, bad_auth) +{ + char buf[128]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + memrnd(buf, sizeof(buf) / 2); + EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); + n = recv(self->cfd, buf, sizeof(buf), 0); + EXPECT_GT(n, sizeof(buf) / 2); + + buf[n - 1]++; + + EXPECT_EQ(send(self->fd2, buf, n, 0), n); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_in_large_read) +{ + char txt[3][64]; + char cip[3][128]; + char buf[3 * 128]; + int i, n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Put 3 records in the sockets */ + for (i = 0; i < 3; i++) { + memrnd(txt[i], sizeof(txt[i])); + EXPECT_EQ(send(self->fd, txt[i], sizeof(txt[i]), 0), + sizeof(txt[i])); + n = recv(self->cfd, cip[i], sizeof(cip[i]), 0); + EXPECT_GT(n, sizeof(txt[i])); + /* Break the third message */ + if (i == 2) + cip[2][n - 1]++; + EXPECT_EQ(send(self->fd2, cip[i], n, 0), n); + } + + /* We should be able to receive the first two messages */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt[0]) * 2); + EXPECT_EQ(memcmp(buf, txt[0], sizeof(txt[0])), 0); + EXPECT_EQ(memcmp(buf + sizeof(txt[0]), txt[1], sizeof(txt[1])), 0); + /* Third mesasge is bad */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_cmsg) +{ + char *test_str = "test_read"; + int send_len = 10; + char cip[128]; + char buf[128]; + char txt[64]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Queue up one data record */ + memrnd(txt, sizeof(txt)); + EXPECT_EQ(send(self->fd, txt, sizeof(txt), 0), sizeof(txt)); + n = recv(self->cfd, cip, sizeof(cip), 0); + EXPECT_GT(n, sizeof(txt)); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + n = recv(self->cfd, cip, sizeof(cip), 0); + cip[n - 1]++; /* Break it */ + EXPECT_GT(n, send_len); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt)); + EXPECT_EQ(memcmp(buf, txt, sizeof(txt)), 0); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; @@ -1355,64 +1630,82 @@ TEST(non_established) { TEST(keysizes) { struct tls12_crypto_info_aes_gcm_256 tls12; - struct sockaddr_in addr; - int sfd, ret, fd, cfd; - socklen_t len; + int ret, fd, cfd; bool notls; - notls = false; - len = sizeof(addr); - memset(&tls12, 0, sizeof(tls12)); tls12.info.version = TLS_1_2_VERSION; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); - fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); + if (!notls) { + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + close(fd); + close(cfd); +} + +TEST(tls_v6ops) { + struct tls_crypto_info_keys tls12; + struct sockaddr_in6 addr, addr2; + int sfd, ret, fd; + socklen_t len, len2; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + + addr.sin6_family = AF_INET6; + addr.sin6_addr = in6addr_any; + addr.sin6_port = 0; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + sfd = socket(AF_INET6, SOCK_STREAM, 0); ret = bind(sfd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); ret = listen(sfd, 10); ASSERT_EQ(ret, 0); + len = sizeof(addr); ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); ret = connect(fd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); + len = sizeof(addr); + ret = getsockname(fd, &addr, &len); + ASSERT_EQ(ret, 0); + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); } + ASSERT_EQ(ret, 0); - if (!notls) { - ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, - sizeof(tls12)); - EXPECT_EQ(ret, 0); - } + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); - cfd = accept(sfd, &addr, &len); - ASSERT_GE(cfd, 0); + ret = setsockopt(fd, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); - if (!notls) { - ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - EXPECT_EQ(ret, 0); + len2 = sizeof(addr2); + ret = getsockname(fd, &addr2, &len2); + ASSERT_EQ(ret, 0); - ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, - sizeof(tls12)); - EXPECT_EQ(ret, 0); - } + EXPECT_EQ(len2, len); + EXPECT_EQ(memcmp(&addr, &addr2, len), 0); - close(sfd); close(fd); - close(cfd); + close(sfd); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 8748199ac109..ffca314897c4 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -5,7 +5,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ - ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh + ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ + conntrack_vrf.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh new file mode 100755 index 000000000000..8b5ea9234588 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh @@ -0,0 +1,241 @@ +#!/bin/sh + +# This script demonstrates interaction of conntrack and vrf. +# The vrf driver calls the netfilter hooks again, with oif/iif +# pointing at the VRF device. +# +# For ingress, this means first iteration has iifname of lower/real +# device. In this script, thats veth0. +# Second iteration is iifname set to vrf device, tvrf in this script. +# +# For egress, this is reversed: first iteration has the vrf device, +# second iteration is done with the lower/real/veth0 device. +# +# test_ct_zone_in demonstrates unexpected change of nftables +# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack +# connection on VRF rcv" +# +# It was possible to assign conntrack zone to a packet (or mark it for +# `notracking`) in the prerouting chain before conntrack, based on real iif. +# +# After the change, the zone assignment is lost and the zone is assigned based +# on the VRF master interface (in case such a rule exists). +# assignment is lost. Instead, assignment based on the `iif` matching +# Thus it is impossible to distinguish packets based on the original +# interface. +# +# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem +# that was supposed to be fixed by the commit mentioned above to make sure +# that any fix to test case 1 won't break masquerade again. + +ksft_skip=4 + +IP0=172.30.30.1 +IP1=172.30.30.2 +PFXL=30 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" + +cleanup() +{ + ip netns pids $ns0 | xargs kill 2>/dev/null + ip netns pids $ns1 | xargs kill 2>/dev/null + + ip netns del $ns0 $ns1 +} + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add "$ns0" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns0" + exit $ksft_skip +fi +ip netns add "$ns1" + +trap cleanup EXIT + +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + +ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not add veth device" + exit $ksft_skip +fi + +ip -net $ns0 li add tvrf type vrf table 9876 +if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + exit $ksft_skip +fi + +ip -net $ns0 li set lo up + +ip -net $ns0 li set veth0 master tvrf +ip -net $ns0 li set tvrf up +ip -net $ns0 li set veth0 up +ip -net $ns1 li set veth0 up + +ip -net $ns0 addr add $IP0/$PFXL dev veth0 +ip -net $ns1 addr add $IP1/$PFXL dev veth0 + +ip netns exec $ns1 iperf3 -s > /dev/null 2>&1& +if [ $? -ne 0 ];then + echo "SKIP: Could not start iperf3" + exit $ksft_skip +fi + +# test vrf ingress handling. +# The incoming connection should be placed in conntrack zone 1, +# as decided by the first iteration of the ruleset. +test_ct_zone_in() +{ +ip netns exec $ns0 nft -f - <<EOF +table testct { + chain rawpre { + type filter hook prerouting priority raw; + + iif { veth0, tvrf } counter meta nftrace set 1 + iif veth0 counter ct zone set 1 counter return + iif tvrf counter ct zone set 2 counter return + ip protocol icmp counter + notrack counter + } + + chain rawout { + type filter hook output priority raw; + + oif veth0 counter ct zone set 1 counter return + oif tvrf counter ct zone set 2 counter return + notrack counter + } +} +EOF + ip netns exec $ns1 ping -W 1 -c 1 -I veth0 $IP0 > /dev/null + + # should be in zone 1, not zone 2 + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "PASS: entry found in conntrack zone 1" + else + echo "FAIL: entry not found in conntrack zone 1" + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "FAIL: entry found in zone 2 instead" + else + echo "FAIL: entry not in zone 1 or 2, dumping table" + ip netns exec $ns0 conntrack -L + ip netns exec $ns0 nft list ruleset + fi + fi +} + +# add masq rule that gets evaluated w. outif set to vrf device. +# This tests the first iteration of the packet through conntrack, +# oifname is the vrf device. +test_masquerade_vrf() +{ + local qdisc=$1 + + if [ "$qdisc" != "default" ]; then + tc -net $ns0 qdisc add dev tvrf root $qdisc + fi + + ip netns exec $ns0 conntrack -F 2>/dev/null + +ip netns exec $ns0 nft -f - <<EOF +flush ruleset +table ip nat { + chain rawout { + type filter hook output priority raw; + + oif tvrf ct state untracked counter + } + chain postrouting2 { + type filter hook postrouting priority mangle; + + oif tvrf ct state untracked counter + } + chain postrouting { + type nat hook postrouting priority 0; + # NB: masquerade should always be combined with 'oif(name) bla', + # lack of this is intentional here, we want to exercise double-snat. + ip saddr 172.30.30.0/30 counter masquerade random + } +} +EOF + ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 >/dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' && + ip netns exec $ns0 nft list table ip nat |grep -q 'untracked counter packets [1-9]' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device ($qdisc qdisc)" + else + echo "FAIL: vrf rules have unexpected counter value" + ret=1 + fi + + if [ "$qdisc" != "default" ]; then + tc -net $ns0 qdisc del dev tvrf root + fi +} + +# add masq rule that gets evaluated w. outif set to veth device. +# This tests the 2nd iteration of the packet through conntrack, +# oifname is the lower device (veth0 in this case). +test_masquerade_veth() +{ + ip netns exec $ns0 conntrack -F 2>/dev/null +ip netns exec $ns0 nft -f - <<EOF +flush ruleset +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; + meta oif veth0 ip saddr 172.30.30.0/30 counter masquerade random + } +} +EOF + ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 > /dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device" + else + echo "FAIL: vrf masq rule has unexpected counter value" + ret=1 + fi +} + +test_ct_zone_in +test_masquerade_vrf "default" +test_masquerade_vrf "pfifo" +test_masquerade_veth + +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index 5a4938d6dcf2..ed61f6cab60f 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -23,8 +23,8 @@ TESTS="reported_issues correctness concurrency timeout" # 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" + net_port_net net_mac mac_net net_mac_icmp net6_mac_icmp + net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below BUGS="flush_remove_add" @@ -277,6 +277,23 @@ perf_entries 1000 perf_proto ipv4 " +TYPE_mac_net=" +display mac,net +type_spec ether_addr . ipv4_addr +chain_spec ether saddr . ip saddr +dst +src mac addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + TYPE_net_mac_icmp=" display net,mac - ICMP type_spec ipv4_addr . ether_addr @@ -984,7 +1001,8 @@ format() { fi done for f in ${src}; do - __expr="${__expr} . " + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + __start="$(eval format_"${f}" "${srcstart}")" __end="$(eval format_"${f}" "${srcend}")" diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index da1c1e4b6c86..d88867d2fed7 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -759,19 +759,21 @@ test_port_shadow() local result="" local logmsg="" - echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_r=$! + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" timeout 1 socat -u STDIN UDP:"$daddrc":41404,sourceport=1405 - echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_c=$! + echo ROUTER | ip netns exec "$ns0" timeout 5 socat -u STDIN UDP4-LISTEN:1405 & + sc_r=$! - # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. - echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + echo CLIENT | ip netns exec "$ns2" timeout 5 socat -u STDIN UDP4-LISTEN:1405,reuseport & + sc_c=$! + + sleep 0.3 # ns1 tries to connect to ns0:1405. With default settings this should connect # to client, it matches the conntrack entry created above. - result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + result=$(echo "data" | ip netns exec "$ns1" timeout 1 socat - UDP:"$daddrs":1405,sourceport=41404) if [ "$result" = "$expect" ] ;then echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" @@ -780,7 +782,7 @@ test_port_shadow() ret=1 fi - kill $nc_r $nc_c 2>/dev/null + kill $sc_r $sc_c 2>/dev/null # flush udp entries for next test round, if any ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 @@ -816,11 +818,10 @@ table $family raw { chain prerouting { type filter hook prerouting priority -300; policy accept; meta iif veth0 udp dport 1405 notrack - udp dport 1405 notrack } chain output { type filter hook output priority -300; policy accept; - udp sport 1405 notrack + meta oif veth0 udp sport 1405 notrack } } EOF @@ -851,6 +852,18 @@ test_port_shadowing() { local family="ip" + conntrack -h >/dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without conntrack tool" + return + fi + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without socat tool" + return + fi + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh index 3d202b90b33d..7d27f1f3bc01 100755 --- a/tools/testing/selftests/netfilter/nft_queue.sh +++ b/tools/testing/selftests/netfilter/nft_queue.sh @@ -16,6 +16,10 @@ timeout=4 cleanup() { + ip netns pids ${ns1} | xargs kill 2>/dev/null + ip netns pids ${ns2} | xargs kill 2>/dev/null + ip netns pids ${nsrouter} | xargs kill 2>/dev/null + ip netns del ${ns1} ip netns del ${ns2} ip netns del ${nsrouter} @@ -332,6 +336,55 @@ EOF echo "PASS: tcp via loopback and re-queueing" } +test_icmp_vrf() { + ip -net $ns1 link add tvrf type vrf table 9876 + if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + return + fi + + ip -net $ns1 li set eth0 master tvrf + ip -net $ns1 li set tvrf up + + ip -net $ns1 route add 10.0.2.0/24 via 10.0.1.1 dev eth0 table 9876 +ip netns exec ${ns1} nft -f /dev/stdin <<EOF +flush ruleset +table inet filter { + chain output { + type filter hook output priority 0; policy accept; + meta oifname "tvrf" icmp type echo-request counter queue num 1 + meta oifname "eth0" icmp type echo-request counter queue num 1 + } + chain post { + type filter hook postrouting priority 0; policy accept; + meta oifname "tvrf" icmp type echo-request counter queue num 1 + meta oifname "eth0" icmp type echo-request counter queue num 1 + } +} +EOF + ip netns exec ${ns1} ./nf-queue -q 1 -t $timeout & + local nfqpid=$! + + sleep 1 + ip netns exec ${ns1} ip vrf exec tvrf ping -c 1 10.0.2.99 > /dev/null + + for n in output post; do + for d in tvrf eth0; do + ip netns exec ${ns1} nft list chain inet filter $n | grep -q "oifname \"$d\" icmp type echo-request counter packets 1" + if [ $? -ne 0 ] ; then + echo "FAIL: chain $n: icmp packet counter mismatch for device $d" 1>&2 + ip netns exec ${ns1} nft list ruleset + ret=1 + return + fi + done + done + + wait $nfqpid + [ $? -eq 0 ] && echo "PASS: icmp+nfqueue via vrf" + wait 2>/dev/null +} + ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null @@ -372,5 +425,6 @@ test_queue 20 test_tcp_forward test_tcp_localhost test_tcp_localhost_requeue +test_icmp_vrf exit $ret diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh index ac646376eb01..04633119b29a 100755 --- a/tools/testing/selftests/netfilter/nft_zones_many.sh +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -18,11 +18,17 @@ cleanup() ip netns del $ns } -ip netns add $ns -if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace $gw" - exit $ksft_skip -fi +checktool (){ + if ! $1 > /dev/null 2>&1; then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} + +checktool "nft --version" "run test without nft tool" +checktool "ip -Version" "run test without ip tool" +checktool "socat -V" "run test without socat tool" +checktool "ip netns add $ns" "create net namespace" trap cleanup EXIT @@ -71,7 +77,8 @@ EOF local start=$(date +%s%3N) i=$((i + 10000)) j=$((j + 1)) - dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null + # nft rule in output places each packet in a different zone. + dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 if [ $? -ne 0 ] ;then ret=1 break diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index b71828df5a6d..a3239d5e40c7 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -60,6 +60,8 @@ CONFIG_NET_IFE_SKBTCINDEX=m CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_ETS=m CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_FQ_PIE=m +CONFIG_NETDEVSIM=m # ## Network testing diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 503982b8f295..91832400ddbd 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -68,7 +68,7 @@ "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ "$TC action flush action bpf" diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 88a20c781e49..c6046096d9db 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -15,7 +15,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -37,7 +37,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-9,a-f][0-9,a-f]{0,2} bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-9,a-f][0-9,a-f]{0,2}", "matchCount": "256", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -60,7 +60,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -82,7 +82,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -106,7 +106,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -128,7 +128,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index a3e43189d940..ee22e3447ec7 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -716,6 +716,7 @@ def set_operation_mode(pm, parser, args, remaining): list_test_cases(alltests) exit(0) + exit_code = 0 # KSFT_PASS if len(alltests): req_plugins = pm.get_required_plugins(alltests) try: @@ -724,6 +725,8 @@ def set_operation_mode(pm, parser, args, remaining): print('The following plugins were not found:') print('{}'.format(pde.missing_pg)) catresults = test_runner(pm, args, alltests) + if catresults.count_failures() != 0: + exit_code = 1 # KSFT_FAIL if args.format == 'none': print('Test results output suppression requested\n') else: @@ -748,6 +751,8 @@ def set_operation_mode(pm, parser, args, remaining): gid=int(os.getenv('SUDO_GID'))) else: print('No tests found\n') + exit_code = 4 # KSFT_SKIP + exit(exit_code) def main(): """ @@ -767,8 +772,5 @@ def main(): set_operation_mode(pm, parser, args, remaining) - exit(0) - - if __name__ == "__main__": main() diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index 7fe38c76db44..afb0cd86fa3d 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -1,5 +1,6 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +modprobe netdevsim ./tdc.py -c actions --nobuildebpf ./tdc.py -c qdisc diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index ebc4ee0fe179..8a9461aa0878 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -276,7 +276,11 @@ n0 ping -W 1 -c 1 192.168.241.2 n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7 ip2 link del wg0 ip2 link del wg1 -! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel +read _ _ tx_bytes_before < <(n0 wg show wg1 transfer) +! n0 ping -W 1 -c 10 -f 192.168.241.2 || false +sleep 1 +read _ _ tx_bytes_after < <(n0 wg show wg1 transfer) +(( tx_bytes_after - tx_bytes_before < 70000 )) ip0 link del wg1 ip1 link del wg0 @@ -609,6 +613,28 @@ ip0 link set wg0 up kill $ncat_pid ip0 link del wg0 +# Ensure that dst_cache references don't outlive netns lifetime +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 +ip1 addr add fd00:aa::1/64 dev veth1 +ip2 addr add fd00:aa::2/64 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +ip1 -6 route add default dev veth1 via fd00:aa::2 +ip2 -6 route add default dev veth2 via fd00:aa::1 +n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2 +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1 +n1 ping6 -c 1 fd00::2 +pp ip netns delete $netns1 +pp ip netns delete $netns2 +pp ip netns add $netns1 +pp ip netns add $netns2 + # Ensure there aren't circular reference loops ip1 link add wg1 type wireguard ip2 link add wg2 type wireguard @@ -627,7 +653,7 @@ while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do done < /dev/kmsg alldeleted=1 for object in "${!objects[@]}"; do - if [[ ${objects["$object"]} != *createddestroyed ]]; then + if [[ ${objects["$object"]} != *createddestroyed && ${objects["$object"]} != *createdcreateddestroyeddestroyed ]]; then echo "Error: $object: merely ${objects["$object"]}" >&3 alldeleted=0 fi diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index fe07d97df9fa..2b321b8a96cf 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -47,7 +47,7 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_TRACE_IRQFLAGS=y CONFIG_DEBUG_BUGVERBOSE=y CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_PI_LIST=y +CONFIG_DEBUG_PLIST=y CONFIG_PROVE_RCU=y CONFIG_SPARSE_RCU_POINTER=y CONFIG_RCU_CPU_STALL_TIMEOUT=21 diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index 74db83a0aedd..a9b5a520a1d2 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -66,6 +66,7 @@ CONFIG_PROC_SYSCTL=y CONFIG_SYSFS=y CONFIG_TMPFS=y CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15 +CONFIG_LOG_BUF_SHIFT=18 CONFIG_PRINTK_TIME=y CONFIG_BLK_DEV_INITRD=y CONFIG_LEGACY_VSYSCALL_NONE=y |