diff options
Diffstat (limited to 'tools')
154 files changed, 2781 insertions, 621 deletions
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 5fd7caea4419..488f8e751349 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -94,6 +94,7 @@ #define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define ARM_CPU_PART_CORTEX_X925 0xD85 #define ARM_CPU_PART_CORTEX_A725 0xD87 +#define ARM_CPU_PART_NEOVERSE_N3 0xD8E #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -143,6 +144,7 @@ #define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define AMPERE_CPU_PART_AMPERE1A 0xAC4 #define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ @@ -175,6 +177,7 @@ #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) #define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) +#define MIDR_NEOVERSE_N3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) @@ -212,6 +215,7 @@ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_AMPERE1A MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1A) #define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/tools/arch/arm64/vdso b/tools/arch/arm64/vdso deleted file mode 120000 index 233c7a26f6e5..000000000000 --- a/tools/arch/arm64/vdso +++ /dev/null @@ -1 +0,0 @@ -../../../arch/arm64/kernel/vdso
\ No newline at end of file diff --git a/tools/arch/loongarch/vdso b/tools/arch/loongarch/vdso deleted file mode 120000 index ebda43a82db7..000000000000 --- a/tools/arch/loongarch/vdso +++ /dev/null @@ -1 +0,0 @@ -../../../arch/loongarch/vdso
\ No newline at end of file diff --git a/tools/arch/powerpc/vdso b/tools/arch/powerpc/vdso deleted file mode 120000 index 4e676d1d1cb4..000000000000 --- a/tools/arch/powerpc/vdso +++ /dev/null @@ -1 +0,0 @@ -../../../arch/powerpc/kernel/vdso
\ No newline at end of file diff --git a/tools/arch/s390/vdso b/tools/arch/s390/vdso deleted file mode 120000 index 6cf4c1cebdcd..000000000000 --- a/tools/arch/s390/vdso +++ /dev/null @@ -1 +0,0 @@ -../../../arch/s390/kernel/vdso64
\ No newline at end of file diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 82c6a4d350e0..3ae84c3b8e6d 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -36,6 +36,20 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) +/* + * Architectural memory types that are common to MTRRs, PAT, VMX MSRs, etc. + * Most MSRs support/allow only a subset of memory types, but the values + * themselves are common across all relevant MSRs. + */ +#define X86_MEMTYPE_UC 0ull /* Uncacheable, a.k.a. Strong Uncacheable */ +#define X86_MEMTYPE_WC 1ull /* Write Combining */ +/* RESERVED 2 */ +/* RESERVED 3 */ +#define X86_MEMTYPE_WT 4ull /* Write Through */ +#define X86_MEMTYPE_WP 5ull /* Write Protected */ +#define X86_MEMTYPE_WB 6ull /* Write Back */ +#define X86_MEMTYPE_UC_MINUS 7ull /* Weak Uncacheabled (PAT only) */ + /* FRED MSRs */ #define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ #define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ @@ -247,6 +261,8 @@ #define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) +#define MSR_INTEGRITY_CAPS_SBAF_BIT 8 +#define MSR_INTEGRITY_CAPS_SBAF BIT(MSR_INTEGRITY_CAPS_SBAF_BIT) #define MSR_INTEGRITY_CAPS_SAF_GEN_MASK GENMASK_ULL(10, 9) #define MSR_LBR_NHM_FROM 0x00000680 @@ -363,6 +379,12 @@ #define MSR_IA32_CR_PAT 0x00000277 +#define PAT_VALUE(p0, p1, p2, p3, p4, p5, p6, p7) \ + ((X86_MEMTYPE_ ## p0) | (X86_MEMTYPE_ ## p1 << 8) | \ + (X86_MEMTYPE_ ## p2 << 16) | (X86_MEMTYPE_ ## p3 << 24) | \ + (X86_MEMTYPE_ ## p4 << 32) | (X86_MEMTYPE_ ## p5 << 40) | \ + (X86_MEMTYPE_ ## p6 << 48) | (X86_MEMTYPE_ ## p7 << 56)) + #define MSR_IA32_DEBUGCTLMSR 0x000001d9 #define MSR_IA32_LASTBRANCHFROMIP 0x000001db #define MSR_IA32_LASTBRANCHTOIP 0x000001dc @@ -1157,15 +1179,6 @@ #define MSR_IA32_VMX_VMFUNC 0x00000491 #define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492 -/* VMX_BASIC bits and bitmasks */ -#define VMX_BASIC_VMCS_SIZE_SHIFT 32 -#define VMX_BASIC_TRUE_CTLS (1ULL << 55) -#define VMX_BASIC_64 0x0001000000000000LLU -#define VMX_BASIC_MEM_TYPE_SHIFT 50 -#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU -#define VMX_BASIC_MEM_TYPE_WB 6LLU -#define VMX_BASIC_INOUT 0x0040000000000000LLU - /* Resctrl MSRs: */ /* - Intel: */ #define MSR_IA32_L3_QOS_CFG 0xc81 @@ -1183,11 +1196,6 @@ #define MSR_IA32_SMBA_BW_BASE 0xc0000280 #define MSR_IA32_EVT_CFG_BASE 0xc0000400 -/* MSR_IA32_VMX_MISC bits */ -#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) -#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) -#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F - /* AMD-V MSRs */ #define MSR_VM_CR 0xc0010114 #define MSR_VM_IGNNE 0xc0010115 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index bf57a824f722..a8debbf2f702 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -439,6 +439,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) +#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index 9de35df1afc3..63182a023e9d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -11,6 +11,9 @@ #ifndef __NR_getpgid #define __NR_getpgid 132 #endif +#ifndef __NR_capget +#define __NR_capget 184 +#endif #ifndef __NR_gettid #define __NR_gettid 224 #endif diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h index d0f2043d7132..77311e8d1b5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_64.h +++ b/tools/arch/x86/include/uapi/asm/unistd_64.h @@ -11,6 +11,9 @@ #ifndef __NR_getpgid #define __NR_getpgid 121 #endif +#ifndef __NR_capget +#define __NR_capget 125 +#endif #ifndef __NR_gettid #define __NR_gettid 186 #endif diff --git a/tools/arch/x86/vdso b/tools/arch/x86/vdso deleted file mode 120000 index 7eb962fd3454..000000000000 --- a/tools/arch/x86/vdso +++ /dev/null @@ -1 +0,0 @@ -../../../arch/x86/entry/vdso/
\ No newline at end of file diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 5938cf799dc6..1658596188bf 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -172,7 +172,7 @@ DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd - LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw) + LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0 LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) LIBDW_VERSION_2 := $(word 2, $(subst ., ,$(LIBDW_VERSION))) @@ -181,6 +181,9 @@ ifeq ($(findstring -static,${LDFLAGS}),-static) ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0) DWARFLIBS += -lebl endif + + # Must put -ldl after -lebl for dependency + DWARFLIBS += -ldl endif $(OUTPUT)test-dwarf.bin: diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 0eb24d21aac2..60044b608817 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -36,4 +36,19 @@ #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __GENMASK_U128() depends on _BIT128() which would not work + * in the asm code, as it shifts an 'unsigned __init128' data + * type instead of direct representation of 128 bit constants + * such as long and unsigned long. The fundamental problem is + * that a 128 bit constant will get silently truncated by the + * gcc compiler. + */ +#define GENMASK_U128(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l)) +#endif + #endif /* __LINUX_BITS_H */ diff --git a/tools/include/linux/unaligned.h b/tools/include/linux/unaligned.h index bc0633bc4650..395a4464fe73 100644 --- a/tools/include/linux/unaligned.h +++ b/tools/include/linux/unaligned.h @@ -9,16 +9,7 @@ #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wpacked" #pragma GCC diagnostic ignored "-Wattributes" - -#define __get_unaligned_t(type, ptr) ({ \ - const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ - __pptr->x; \ -}) - -#define __put_unaligned_t(type, val, ptr) do { \ - struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ - __pptr->x = (val); \ -} while (0) +#include <vdso/unaligned.h> #define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h index 3c2a101986a3..5ee30f882736 100644 --- a/tools/include/uapi/linux/bits.h +++ b/tools/include/uapi/linux/bits.h @@ -12,4 +12,7 @@ (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_U128(h, l) \ + ((_BIT128((h)) << 1) - (_BIT128(l))) + #endif /* _UAPI_LINUX_BITS_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1fb3cb2636e6..4a939c90dc2e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1121,6 +1121,9 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[] + * in sync with the definitions below. + */ enum bpf_link_type { BPF_LINK_TYPE_UNSPEC = 0, BPF_LINK_TYPE_RAW_TRACEPOINT = 1, @@ -5519,11 +5522,12 @@ union bpf_attr { * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * - * void *bpf_kptr_xchg(void *map_value, void *ptr) + * void *bpf_kptr_xchg(void *dst, void *ptr) * Description - * Exchange kptr at pointer *map_value* with *ptr*, and return the - * old value. *ptr* can be NULL, otherwise it must be a referenced - * pointer which will be released when this helper is called. + * Exchange kptr at pointer *dst* with *ptr*, and return the old value. + * *dst* can be map value or local kptr. *ptr* can be NULL, otherwise + * it must be a referenced pointer which will be released when this helper + * is called. * Return * The old value of kptr (which can be NULL). The returned pointer * if not NULL, is a reference which must be released using its @@ -6046,11 +6050,6 @@ enum { BPF_F_MARK_ENFORCE = (1ULL << 6), }; -/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -enum { - BPF_F_INGRESS = (1ULL << 0), -}; - /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ enum { BPF_F_TUNINFO_IPV6 = (1ULL << 0), @@ -6197,10 +6196,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; -/* Flags for bpf_redirect_map helper */ +/* Flags for bpf_redirect and bpf_redirect_map helpers */ enum { - BPF_F_BROADCAST = (1ULL << 3), - BPF_F_EXCLUDE_INGRESS = (1ULL << 4), + BPF_F_INGRESS = (1ULL << 0), /* used for skb path */ + BPF_F_BROADCAST = (1ULL << 3), /* used for XDP path */ + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), /* used for XDP path */ +#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) }; #define __bpf_md_ptr(type, name) \ diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index a429381e7ca5..e16be0d37746 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,6 +28,23 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __BIT128() would not work in the asm code, as it shifts an + * 'unsigned __init128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting asm code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index d358add1611c..5d32d53508d9 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -141,7 +141,7 @@ struct in_addr { */ #define IP_PMTUDISC_INTERFACE 4 /* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get - * fragmented if they exeed the interface mtu + * fragmented if they exceed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/tools/include/vdso/unaligned.h b/tools/include/vdso/unaligned.h new file mode 100644 index 000000000000..eee3d2a4dbe4 --- /dev/null +++ b/tools/include/vdso/unaligned.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_UNALIGNED_H +#define __VDSO_UNALIGNED_H + +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define __put_unaligned_t(type, val, ptr) do { \ + struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x = (val); \ +} while (0) + +#endif /* __VDSO_UNALIGNED_H */ diff --git a/tools/lib/thermal/Makefile b/tools/lib/thermal/Makefile index 2d0d255fd0e1..8890fd57b110 100644 --- a/tools/lib/thermal/Makefile +++ b/tools/lib/thermal/Makefile @@ -121,7 +121,9 @@ all: fixdep clean: $(call QUIET_CLEAN, libthermal) $(RM) $(LIBTHERMAL_A) \ - *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBTHERMAL_VERSION) .*.d .*.cmd LIBTHERMAL-CFLAGS $(LIBTHERMAL_PC) + *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBTHERMAL_VERSION) \ + .*.d .*.cmd LIBTHERMAL-CFLAGS $(LIBTHERMAL_PC) \ + $(srctree)/tools/$(THERMAL_UAPI) $(LIBTHERMAL_PC): $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ diff --git a/tools/lib/thermal/sampling.c b/tools/lib/thermal/sampling.c index 70577423a9f0..f67c1f9ea1d7 100644 --- a/tools/lib/thermal/sampling.c +++ b/tools/lib/thermal/sampling.c @@ -16,6 +16,8 @@ static int handle_thermal_sample(struct nl_msg *n, void *arg) struct thermal_handler_param *thp = arg; struct thermal_handler *th = thp->th; + arg = thp->arg; + genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); switch (genlhdr->cmd) { diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index fa050d5a48cd..6eb17cc1a06c 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -22,6 +22,7 @@ #include <time.h> #include <setjmp.h> #include <signal.h> +#include <inttypes.h> #include <sys/types.h> #include <sys/errno.h> #include <sys/fcntl.h> @@ -391,9 +392,9 @@ static void show_page_range(unsigned long voffset, unsigned long offset, if (opt_file) printf("%lx\t", voff); if (opt_list_cgroup) - printf("@%llu\t", (unsigned long long)cgroup0); + printf("@%" PRIu64 "\t", cgroup0); if (opt_list_mapcnt) - printf("%lu\t", mapcnt0); + printf("%" PRIu64 "\t", mapcnt0); printf("%lx\t%lx\t%s\n", index, count, page_flag_name(flags0)); } @@ -419,9 +420,9 @@ static void show_page(unsigned long voffset, unsigned long offset, if (opt_file) printf("%lx\t", voffset); if (opt_list_cgroup) - printf("@%llu\t", (unsigned long long)cgroup); + printf("@%" PRIu64 "\t", cgroup) if (opt_list_mapcnt) - printf("%lu\t", mapcnt); + printf("%" PRIu64 "\t", mapcnt); printf("%lx\t%s\n", offset, page_flag_name(flags)); } diff --git a/tools/mm/slabinfo.c b/tools/mm/slabinfo.c index cfaeaea71042..04e9e6ba86ea 100644 --- a/tools/mm/slabinfo.c +++ b/tools/mm/slabinfo.c @@ -1297,7 +1297,9 @@ static void read_slab_dir(void) slab->cpu_partial_free = get_obj("cpu_partial_free"); slab->alloc_node_mismatch = get_obj("alloc_node_mismatch"); slab->deactivate_bypass = get_obj("deactivate_bypass"); - chdir(".."); + if (chdir("..")) + fatal("Unable to chdir from slab ../%s\n", + slab->name); if (slab->name[0] == ':') alias_targets++; slab++; diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4dcf7a0fd235..d4332675babb 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -147,9 +147,9 @@ ifdef LIBDW_DIR endif DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) - DWARFLIBS += -lelf -ldl -lz -llzma -lbz2 -lzstd + DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd - LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw) + LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw).0.0 LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) LIBDW_VERSION_2 := $(word 2, $(subst ., ,$(LIBDW_VERSION))) @@ -158,6 +158,9 @@ ifeq ($(findstring -static,${LDFLAGS}),-static) ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0) DWARFLIBS += -lebl endif + + # Must put -ldl after -lebl for dependency + DWARFLIBS += -ldl endif FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS) @@ -701,8 +704,8 @@ ifeq ($(BUILD_BPF_SKEL),1) BUILD_BPF_SKEL := 0 else CLANG_VERSION := $(shell $(CLANG) --version | head -1 | sed 's/.*clang version \([[:digit:]]\+.[[:digit:]]\+.[[:digit:]]\+\).*/\1/g') - ifeq ($(call version-lt3,$(CLANG_VERSION),16.0.6),1) - $(warning Warning: Disabled BPF skeletons as at least $(CLANG) version 16.0.6 is reported to be a working setup with the current of BPF based perf features) + ifeq ($(call version-lt3,$(CLANG_VERSION),12.0.1),1) + $(warning Warning: Disabled BPF skeletons as reliable BTF generation needs at least $(CLANG) version 12.0.1) BUILD_BPF_SKEL := 0 endif endif diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f6e847529073..d3f11b90d025 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1399,7 +1399,7 @@ static const struct syscall_fmt syscall_fmts[] = { .arg = { [2] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, }, { .name = "waitid", .errpid = true, .arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, }, - { .name = "write", .errpid = true, + { .name = "write", .arg = { [1] = { .scnprintf = SCA_BUF /* buf */, .from_user = true, }, }, }, }; diff --git a/tools/perf/check-header_ignore_hunks/lib/list_sort.c b/tools/perf/check-header_ignore_hunks/lib/list_sort.c new file mode 100644 index 000000000000..32d98cb34f80 --- /dev/null +++ b/tools/perf/check-header_ignore_hunks/lib/list_sort.c @@ -0,0 +1,31 @@ +@@ -1,5 +1,6 @@ + // SPDX-License-Identifier: GPL-2.0 + #include <linux/kernel.h> ++#include <linux/bug.h> + #include <linux/compiler.h> + #include <linux/export.h> + #include <linux/string.h> +@@ -52,6 +53,7 @@ + struct list_head *a, struct list_head *b) + { + struct list_head *tail = head; ++ u8 count = 0; + + for (;;) { + /* if equal, take 'a' -- important for sort stability */ +@@ -77,6 +79,15 @@ + /* Finish linking remainder of list b on to tail */ + tail->next = b; + do { ++ /* ++ * If the merge is highly unbalanced (e.g. the input is ++ * already sorted), this loop may run many iterations. ++ * Continue callbacks to the client even though no ++ * element comparison is needed, so the client's cmp() ++ * routine can invoke cond_resched() periodically. ++ */ ++ if (unlikely(!++count)) ++ cmp(priv, b, b); + b->prev = tail; + tail = b; + b = b->next; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 5d4f74b30102..a05c1c105c51 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -22,6 +22,7 @@ FILES=( "include/vdso/bits.h" "include/linux/const.h" "include/vdso/const.h" + "include/vdso/unaligned.h" "include/linux/hash.h" "include/linux/list-sort.h" "include/uapi/linux/hw_breakpoint.h" @@ -136,6 +137,30 @@ beauty_check () { check_2 "tools/perf/trace/beauty/$file" "$file" "$@" } +check_ignore_some_hunks () { + orig_file="$1" + tools_file="tools/$orig_file" + hunks_to_ignore="tools/perf/check-header_ignore_hunks/$orig_file" + + if [ ! -f "$hunks_to_ignore" ]; then + echo "$hunks_to_ignore not found. Skipping $orig_file check." + FAILURES+=( + "$tools_file $orig_file" + ) + return + fi + + cmd="diff -u \"$tools_file\" \"$orig_file\" | grep -vf \"$hunks_to_ignore\" | wc -l | grep -qw 0" + + if [ -f "$orig_file" ] && ! eval "$cmd" + then + FAILURES+=( + "$tools_file $orig_file" + ) + fi +} + + # Check if we have the kernel headers (tools/perf/../../include), else # we're probably on a detached tarball, so no point in trying to check # differences. @@ -169,7 +194,6 @@ check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' check include/linux/build_bug.h '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"' check include/linux/ctype.h '-I "isdigit("' check lib/ctype.c '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B' -check lib/list_sort.c '-I "^#include <linux/bug.h>"' # diff non-symmetric files check_2 tools/perf/arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_32.tbl @@ -187,6 +211,10 @@ done check_2 tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h check_2 tools/perf/util/hashmap.c tools/lib/bpf/hashmap.c +# Files with larger differences + +check_ignore_some_hunks lib/list_sort.c + cd tools/perf || exit if [ ${#FAILURES[@]} -gt 0 ] diff --git a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh index b5dc10b2a738..bead723e34af 100755 --- a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh +++ b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh @@ -19,35 +19,74 @@ TEST_RESULT=0 # skip if not supported -BLACKFUNC=`head -n 1 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2` -if [ -z "$BLACKFUNC" ]; then +BLACKFUNC_LIST=`head -n 5 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2` +if [ -z "$BLACKFUNC_LIST" ]; then print_overall_skipped exit 0 fi +# try to find vmlinux with DWARF debug info +VMLINUX_FILE=$(perf probe -v random_probe |& grep "Using.*for symbols" | sed -r 's/^Using (.*) for symbols$/\1/') + # remove all previously added probes clear_all_probes ### adding blacklisted function - -# functions from blacklist should be skipped by perf probe -! $CMD_PERF probe $BLACKFUNC > $LOGS_DIR/adding_blacklisted.log 2> $LOGS_DIR/adding_blacklisted.err -PERF_EXIT_CODE=$? - REGEX_SCOPE_FAIL="Failed to find scope of probe point" REGEX_SKIP_MESSAGE=" is blacklisted function, skip it\." -REGEX_NOT_FOUND_MESSAGE="Probe point \'$BLACKFUNC\' not found." +REGEX_NOT_FOUND_MESSAGE="Probe point \'$RE_EVENT\' not found." REGEX_ERROR_MESSAGE="Error: Failed to add events." REGEX_INVALID_ARGUMENT="Failed to write event: Invalid argument" REGEX_SYMBOL_FAIL="Failed to find symbol at $RE_ADDRESS" -REGEX_OUT_SECTION="$BLACKFUNC is out of \.\w+, skip it" -../common/check_all_lines_matched.pl "$REGEX_SKIP_MESSAGE" "$REGEX_NOT_FOUND_MESSAGE" "$REGEX_ERROR_MESSAGE" "$REGEX_SCOPE_FAIL" "$REGEX_INVALID_ARGUMENT" "$REGEX_SYMBOL_FAIL" "$REGEX_OUT_SECTION" < $LOGS_DIR/adding_blacklisted.err -CHECK_EXIT_CODE=$? - -print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "adding blacklisted function $BLACKFUNC" -(( TEST_RESULT += $? )) - +REGEX_OUT_SECTION="$RE_EVENT is out of \.\w+, skip it" +REGEX_MISSING_DECL_LINE="A function DIE doesn't have decl_line. Maybe broken DWARF?" + +BLACKFUNC="" +SKIP_DWARF=0 + +for BLACKFUNC in $BLACKFUNC_LIST; do + echo "Probing $BLACKFUNC" + + # functions from blacklist should be skipped by perf probe + ! $CMD_PERF probe $BLACKFUNC > $LOGS_DIR/adding_blacklisted.log 2> $LOGS_DIR/adding_blacklisted.err + PERF_EXIT_CODE=$? + + # check for bad DWARF polluting the result + ../common/check_all_patterns_found.pl "$REGEX_MISSING_DECL_LINE" >/dev/null < $LOGS_DIR/adding_blacklisted.err + + if [ $? -eq 0 ]; then + SKIP_DWARF=1 + echo "Result polluted by broken DWARF, trying another probe" + + # confirm that the broken DWARF comes from assembler + if [ -n "$VMLINUX_FILE" ]; then + readelf -wi "$VMLINUX_FILE" | + awk -v probe="$BLACKFUNC" '/DW_AT_language/ { comp_lang = $0 } + $0 ~ probe { if (comp_lang) { print comp_lang }; exit }' | + grep -q "MIPS assembler" + + CHECK_EXIT_CODE=$? + if [ $CHECK_EXIT_CODE -ne 0 ]; then + SKIP_DWARF=0 # broken DWARF while available + break + fi + fi + else + ../common/check_all_lines_matched.pl "$REGEX_SKIP_MESSAGE" "$REGEX_NOT_FOUND_MESSAGE" "$REGEX_ERROR_MESSAGE" "$REGEX_SCOPE_FAIL" "$REGEX_INVALID_ARGUMENT" "$REGEX_SYMBOL_FAIL" "$REGEX_OUT_SECTION" < $LOGS_DIR/adding_blacklisted.err + CHECK_EXIT_CODE=$? + + SKIP_DWARF=0 + break + fi +done + +if [ $SKIP_DWARF -eq 1 ]; then + print_testcase_skipped "adding blacklisted function $BLACKFUNC" +else + print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "adding blacklisted function $BLACKFUNC" + (( TEST_RESULT += $? )) +fi ### listing not-added probe diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h index 13aea8fc3d45..47051871b436 100644 --- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h +++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h @@ -18,8 +18,8 @@ * Vectors 0 ... 31 : system traps and exceptions - hardcoded events * Vectors 32 ... 127 : device interrupts * Vector 128 : legacy int80 syscall interface - * Vectors 129 ... LOCAL_TIMER_VECTOR-1 - * Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts + * Vectors 129 ... FIRST_SYSTEM_VECTOR-1 : device interrupts + * Vectors FIRST_SYSTEM_VECTOR ... 255 : special interrupts * * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table. * diff --git a/tools/perf/trace/beauty/fs_at_flags.sh b/tools/perf/trace/beauty/fs_at_flags.sh index 456f59addf74..e3f13f96a27c 100755 --- a/tools/perf/trace/beauty/fs_at_flags.sh +++ b/tools/perf/trace/beauty/fs_at_flags.sh @@ -13,9 +13,14 @@ printf "static const char *fs_at_flags[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+AT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' # AT_EACCESS is only meaningful to faccessat, so we will special case it there... # AT_STATX_SYNC_TYPE is not a bit, its a mask of AT_STATX_SYNC_AS_STAT, AT_STATX_FORCE_SYNC and AT_STATX_DONT_SYNC +# AT_HANDLE_FID and AT_HANDLE_MNT_ID_UNIQUE are reusing values and are valid only for name_to_handle_at() +# AT_RENAME_NOREPLACE reuses 0x1 and is valid only for renameat2() grep -E $regex ${linux_fcntl} | \ grep -v AT_EACCESS | \ grep -v AT_STATX_SYNC_TYPE | \ + grep -v AT_HANDLE_FID | \ + grep -v AT_HANDLE_MNT_ID_UNIQUE | \ + grep -v AT_RENAME_NOREPLACE | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index df9cdb8bbfb8..d18cc47e89bd 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -327,6 +327,7 @@ struct ucred { * plain text and require encryption */ +#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h index c0bcc185fa48..87e2dec79fea 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h @@ -16,6 +16,9 @@ #define F_DUPFD_QUERY (F_LINUX_SPECIFIC_BASE + 3) +/* Was the file just created? */ +#define F_CREATED_QUERY (F_LINUX_SPECIFIC_BASE + 4) + /* * Cancel a blocking posix lock; internal use only until we expose an * asynchronous lock api to userspace: @@ -87,37 +90,70 @@ #define DN_ATTRIB 0x00000020 /* File changed attibutes */ #define DN_MULTISHOT 0x80000000 /* Don't remove notifier */ +#define AT_FDCWD -100 /* Special value for dirfd used to + indicate openat should use the + current working directory. */ + + +/* Generic flags for the *at(2) family of syscalls. */ + +/* Reserved for per-syscall flags 0xff. */ +#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic + links. */ +/* Reserved for per-syscall flags 0x200 */ +#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */ +#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount + traversal. */ +#define AT_EMPTY_PATH 0x1000 /* Allow empty relative + pathname to operate on dirfd + directly. */ +/* + * These flags are currently statx(2)-specific, but they could be made generic + * in the future and so they should not be used for other per-syscall flags. + */ +#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */ +#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */ +#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */ +#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */ + +#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */ + /* - * The constants AT_REMOVEDIR and AT_EACCESS have the same value. AT_EACCESS is - * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to - * unlinkat. The two functions do completely different things and therefore, - * the flags can be allowed to overlap. For example, passing AT_REMOVEDIR to - * faccessat would be undefined behavior and thus treating it equivalent to - * AT_EACCESS is valid undefined behavior. + * Per-syscall flags for the *at(2) family of syscalls. + * + * These are flags that are so syscall-specific that a user passing these flags + * to the wrong syscall is so "clearly wrong" that we can safely call such + * usage "undefined behaviour". + * + * For example, the constants AT_REMOVEDIR and AT_EACCESS have the same value. + * AT_EACCESS is meaningful only to faccessat, while AT_REMOVEDIR is meaningful + * only to unlinkat. The two functions do completely different things and + * therefore, the flags can be allowed to overlap. For example, passing + * AT_REMOVEDIR to faccessat would be undefined behavior and thus treating it + * equivalent to AT_EACCESS is valid undefined behavior. + * + * Note for implementers: When picking a new per-syscall AT_* flag, try to + * reuse already existing flags first. This leaves us with as many unused bits + * as possible, so we can use them for generic bits in the future if necessary. */ -#define AT_FDCWD -100 /* Special value used to indicate - openat should use the current - working directory. */ -#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */ + +/* Flags for renameat2(2) (must match legacy RENAME_* flags). */ +#define AT_RENAME_NOREPLACE 0x0001 +#define AT_RENAME_EXCHANGE 0x0002 +#define AT_RENAME_WHITEOUT 0x0004 + +/* Flag for faccessat(2). */ #define AT_EACCESS 0x200 /* Test access permitted for effective IDs, not real IDs. */ +/* Flag for unlinkat(2). */ #define AT_REMOVEDIR 0x200 /* Remove directory instead of unlinking file. */ -#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */ -#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */ -#define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */ - -#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */ -#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */ -#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */ -#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */ - -#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */ +/* Flags for name_to_handle_at(2). */ +#define AT_HANDLE_FID 0x200 /* File handle is needed to compare + object identity and may not be + usable with open_by_handle_at(2). */ +#define AT_HANDLE_MNT_ID_UNIQUE 0x001 /* Return the u64 unique mount ID. */ -/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */ -#define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to - compare object identity and may not - be usable to open_by_handle_at(2) */ #if defined(__KERNEL__) #define AT_GETATTR_NOSEC 0x80000000 #endif diff --git a/tools/perf/trace/beauty/include/uapi/linux/sched.h b/tools/perf/trace/beauty/include/uapi/linux/sched.h index 3bac0a8ceab2..359a14cc76a4 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/sched.h +++ b/tools/perf/trace/beauty/include/uapi/linux/sched.h @@ -118,6 +118,7 @@ struct clone_args { /* SCHED_ISO: reserved but not implemented yet */ #define SCHED_IDLE 5 #define SCHED_DEADLINE 6 +#define SCHED_EXT 7 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ #define SCHED_RESET_ON_FORK 0x40000000 diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h index 8bf7e8a0eb6f..4cd513215bcd 100644 --- a/tools/perf/trace/beauty/include/uapi/sound/asound.h +++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h @@ -869,7 +869,7 @@ struct snd_ump_block_info { * Timer section - /dev/snd/timer */ -#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 7) +#define SNDRV_TIMER_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 8) enum { SNDRV_TIMER_CLASS_NONE = -1, @@ -894,6 +894,7 @@ enum { #define SNDRV_TIMER_GLOBAL_RTC 1 /* unused */ #define SNDRV_TIMER_GLOBAL_HPET 2 #define SNDRV_TIMER_GLOBAL_HRTIMER 3 +#define SNDRV_TIMER_GLOBAL_UDRIVEN 4 /* info flags */ #define SNDRV_TIMER_FLG_SLAVE (1<<0) /* cannot be controlled */ @@ -974,6 +975,18 @@ struct snd_timer_status { }; #endif +/* + * This structure describes the userspace-driven timer. Such timers are purely virtual, + * and can only be triggered from software (for instance, by userspace application). + */ +struct snd_timer_uinfo { + /* To pretend being a normal timer, we need to know the resolution in ns. */ + __u64 resolution; + int fd; + unsigned int id; + unsigned char reserved[16]; +}; + #define SNDRV_TIMER_IOCTL_PVERSION _IOR('T', 0x00, int) #define SNDRV_TIMER_IOCTL_NEXT_DEVICE _IOWR('T', 0x01, struct snd_timer_id) #define SNDRV_TIMER_IOCTL_TREAD_OLD _IOW('T', 0x02, int) @@ -990,6 +1003,8 @@ struct snd_timer_status { #define SNDRV_TIMER_IOCTL_CONTINUE _IO('T', 0xa2) #define SNDRV_TIMER_IOCTL_PAUSE _IO('T', 0xa3) #define SNDRV_TIMER_IOCTL_TREAD64 _IOW('T', 0xa4, int) +#define SNDRV_TIMER_IOCTL_CREATE _IOWR('T', 0xa5, struct snd_timer_uinfo) +#define SNDRV_TIMER_IOCTL_TRIGGER _IO('T', 0xa6) #if __BITS_PER_LONG == 64 #define SNDRV_TIMER_IOCTL_TREAD SNDRV_TIMER_IOCTL_TREAD_OLD diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c index ed3ff969b546..2da581ff0c80 100644 --- a/tools/perf/trace/beauty/msg_flags.c +++ b/tools/perf/trace/beauty/msg_flags.c @@ -11,6 +11,9 @@ #ifndef MSG_BATCH #define MSG_BATCH 0x40000 #endif +#ifndef MSG_SOCK_DEVMEM +#define MSG_SOCK_DEVMEM 0x2000000 +#endif #ifndef MSG_ZEROCOPY #define MSG_ZEROCOPY 0x4000000 #endif @@ -57,6 +60,7 @@ static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size, P_MSG_FLAG(MORE); P_MSG_FLAG(WAITFORONE); P_MSG_FLAG(BATCH); + P_MSG_FLAG(SOCK_DEVMEM); P_MSG_FLAG(ZEROCOPY); P_MSG_FLAG(SPLICE_PAGES); P_MSG_FLAG(FASTOPEN); diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index b2f17cca014b..4a62ed593e84 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -288,6 +288,10 @@ int sys_enter_rename(struct syscall_enter_args *args) augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64)); len += augmented_args->arg.size; + /* Every read from userspace is limited to value size */ + if (augmented_args->arg.size > sizeof(augmented_args->arg.value)) + return 1; /* Failure: don't filter */ + struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size; newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value)); @@ -315,6 +319,10 @@ int sys_enter_renameat2(struct syscall_enter_args *args) augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64)); len += augmented_args->arg.size; + /* Every read from userspace is limited to value size */ + if (augmented_args->arg.size > sizeof(augmented_args->arg.value)) + return 1; /* Failure: don't filter */ + struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size; newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value)); @@ -423,8 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid) static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) { bool augmented, do_output = false; - int zero = 0, size, aug_size, index, output = 0, + int zero = 0, size, aug_size, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); + u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */ unsigned int nr, *beauty_map; struct beauty_payload_enter *payload; void *arg, *payload_offset; @@ -477,6 +486,8 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) augmented = true; } else if (size < 0 && size >= -6) { /* buffer */ index = -(size + 1); + barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick. + index &= 7; // Satisfy the bounds checking with the verifier in some kernels. aug_size = args->args[index]; if (aug_size > TRACE_AUG_MAX_BUF) @@ -488,10 +499,17 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } } + /* Augmented data size is limited to sizeof(augmented_arg->unnamed union with value field) */ + if (aug_size > value_size) + aug_size = value_size; + /* write data to payload */ if (augmented) { int written = offsetof(struct augmented_arg, value) + aug_size; + if (written < 0 || written > sizeof(struct augmented_arg)) + return 1; + ((struct augmented_arg *)payload_offset)->size = aug_size; output += written; payload_offset += written; @@ -499,7 +517,7 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } } - if (!do_output) + if (!do_output || (sizeof(struct syscall_enter_args) + output) > sizeof(struct beauty_payload_enter)) return 1; return augmented__beauty_output(ctx, payload, sizeof(struct syscall_enter_args) + output); diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c index 7574a67651bc..69d9a2bcd40b 100644 --- a/tools/perf/util/cap.c +++ b/tools/perf/util/cap.c @@ -7,13 +7,9 @@ #include "debug.h" #include <errno.h> #include <string.h> -#include <unistd.h> #include <linux/capability.h> #include <sys/syscall.h> - -#ifndef SYS_capget -#define SYS_capget 90 -#endif +#include <unistd.h> #define MAX_LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3 @@ -21,9 +17,9 @@ bool perf_cap__capable(int cap, bool *used_root) { struct __user_cap_header_struct header = { .version = _LINUX_CAPABILITY_VERSION_3, - .pid = getpid(), + .pid = 0, }; - struct __user_cap_data_struct data[MAX_LINUX_CAPABILITY_U32S]; + struct __user_cap_data_struct data[MAX_LINUX_CAPABILITY_U32S] = {}; __u32 cap_val; *used_root = false; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 90f32f327b9b..40f047baef81 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -3323,7 +3323,7 @@ static int cs_etm__create_decoders(struct cs_etm_auxtrace *etm) * Don't create decoders for empty queues, mainly because * etmq->format is unknown for empty queues. */ - assert(empty == (etmq->format == UNSET)); + assert(empty || etmq->format != UNSET); if (empty) continue; diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h index 336a3a183a78..bd7505812569 100644 --- a/tools/perf/util/dwarf-aux.h +++ b/tools/perf/util/dwarf-aux.h @@ -9,6 +9,7 @@ #include <elfutils/libdw.h> #include <elfutils/libdwfl.h> #include <elfutils/version.h> +#include <errno.h> struct strbuf; diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 31a223eaf8e6..ee3d43a7ba45 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -19,6 +19,7 @@ #include "util/bpf-filter.h" #include "util/env.h" #include "util/kvm-stat.h" +#include "util/stat.h" #include "util/kwork.h" #include "util/sample.h" #include "util/lock-contention.h" @@ -1355,6 +1356,7 @@ error: unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; +#ifdef HAVE_KVM_STAT_SUPPORT bool kvm_entry_event(struct evsel *evsel __maybe_unused) { return false; @@ -1384,6 +1386,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, char *decode __maybe_unused) { } +#endif // HAVE_KVM_STAT_SUPPORT int find_scripts(char **scripts_array __maybe_unused, char **scripts_path_array __maybe_unused, int num __maybe_unused, int pathlen __maybe_unused) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a18927d792af..3bbf173ad822 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1931,6 +1931,9 @@ int dso__load(struct dso *dso, struct map *map) if (next_slot) { ss_pos++; + if (dso__binary_type(dso) == DSO_BINARY_TYPE__NOT_FOUND) + dso__set_binary_type(dso, symtab_type); + if (syms_ss && runtime_ss) break; } else { diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 7c15dec6900d..6c45ded922b6 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -46,6 +46,11 @@ static const char *const *syscalltbl_native = syscalltbl_mips_n64; #include <asm/syscalls.c> const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID; static const char *const *syscalltbl_native = syscalltbl_loongarch; +#else +const int syscalltbl_native_max_id = 0; +static const char *const syscalltbl_native[] = { + [0] = "unknown", +}; #endif struct syscall { @@ -182,6 +187,11 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name) return audit_name_to_syscall(name, tbl->audit_machine); } +int syscalltbl__id_at_idx(struct syscalltbl *tbl __maybe_unused, int idx) +{ + return idx; +} + int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused, const char *syscall_glob __maybe_unused, int *idx __maybe_unused) { diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 1b6f8f6db7aa..c12f5d8c4bf6 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -308,8 +308,10 @@ static struct dso *machine__find_vdso(struct machine *machine, if (!dso) { dso = dsos__find(&machine->dsos, DSO__NAME_VDSO, true); - if (dso && dso_type != dso__type(dso, machine)) + if (dso && dso_type != dso__type(dso, machine)) { + dso__put(dso); dso = NULL; + } } break; case DSO__TYPE_X32BIT: diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 225f61f9bfca..248ab790d143 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -41,8 +41,8 @@ void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vt u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; bool scx_bpf_consume(u64 dsq_id) __ksym; -void scx_bpf_dispatch_from_dsq_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym; -void scx_bpf_dispatch_from_dsq_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym; +void scx_bpf_dispatch_from_dsq_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak; +void scx_bpf_dispatch_from_dsq_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak; bool scx_bpf_dispatch_from_dsq(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; bool scx_bpf_dispatch_vtime_from_dsq(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; u32 scx_bpf_reenqueue_local(void) __ksym; @@ -71,7 +71,7 @@ s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; bool scx_bpf_task_running(const struct task_struct *p) __ksym; s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym; struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym; -struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym; +struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym __weak; /* * Use the following as @it__iter when calling @@ -320,7 +320,7 @@ u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym; /* * Access a cpumask in read-only mode (typically to check bits). */ -const struct cpumask *cast_mask(struct bpf_cpumask *mask) +static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) { return (const struct cpumask *)mask; } diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index 67e2a7968cc9..5d1f880d1149 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -230,8 +230,8 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags) return; } - /* if !WAKEUP, select_cpu() wasn't called, try direct dispatch */ - if (!(enq_flags & SCX_ENQ_WAKEUP) && + /* if select_cpu() wasn't called, try direct dispatch */ + if (!(enq_flags & SCX_ENQ_CPU_SELECTED) && (cpu = pick_direct_dispatch_cpu(p, scx_bpf_task_cpu(p))) >= 0) { __sync_fetch_and_add(&nr_ddsp_from_enq, 1); scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | cpu, slice_ns, enq_flags); diff --git a/tools/sched_ext/scx_show_state.py b/tools/sched_ext/scx_show_state.py index 8bc626ede1c4..c4b3fdda9a0b 100644 --- a/tools/sched_ext/scx_show_state.py +++ b/tools/sched_ext/scx_show_state.py @@ -35,6 +35,6 @@ print(f'enabled : {read_static_key("__scx_ops_enabled")}') print(f'switching_all : {read_int("scx_switching_all")}') print(f'switched_all : {read_static_key("__scx_switched_all")}') print(f'enable_state : {ops_state_str(enable_state)} ({enable_state})') -print(f'bypass_depth : {read_atomic("scx_ops_bypass_depth")}') +print(f'bypass_depth : {prog["scx_ops_bypass_depth"].value_()}') print(f'nr_rejected : {read_atomic("scx_nr_rejected")}') print(f'enable_seq : {read_atomic("scx_enable_seq")}') diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 90d5afd52dd0..050725afa45d 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -693,26 +693,22 @@ static int mock_decoder_commit(struct cxl_decoder *cxld) return 0; } -static int mock_decoder_reset(struct cxl_decoder *cxld) +static void mock_decoder_reset(struct cxl_decoder *cxld) { struct cxl_port *port = to_cxl_port(cxld->dev.parent); int id = cxld->id; if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0) - return 0; + return; dev_dbg(&port->dev, "%s reset\n", dev_name(&cxld->dev)); - if (port->commit_end != id) { + if (port->commit_end == id) + cxl_port_commit_reap(cxld); + else dev_dbg(&port->dev, "%s: out of order reset, expected decoder%d.%d\n", dev_name(&cxld->dev), port->id, port->commit_end); - return -EBUSY; - } - - port->commit_end--; cxld->flags &= ~CXL_DECODER_F_ENABLE; - - return 0; } static void default_mock_decoder(struct cxl_decoder *cxld) @@ -1062,7 +1058,7 @@ static void mock_companion(struct acpi_device *adev, struct device *dev) #define SZ_64G (SZ_32G * 2) #endif -static __init int cxl_rch_init(void) +static __init int cxl_rch_topo_init(void) { int rc, i; @@ -1090,30 +1086,8 @@ static __init int cxl_rch_init(void) goto err_bridge; } - for (i = 0; i < ARRAY_SIZE(cxl_rcd); i++) { - int idx = NR_MEM_MULTI + NR_MEM_SINGLE + i; - struct platform_device *rch = cxl_rch[i]; - struct platform_device *pdev; - - pdev = platform_device_alloc("cxl_rcd", idx); - if (!pdev) - goto err_mem; - pdev->dev.parent = &rch->dev; - set_dev_node(&pdev->dev, i % 2); - - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); - goto err_mem; - } - cxl_rcd[i] = pdev; - } - return 0; -err_mem: - for (i = ARRAY_SIZE(cxl_rcd) - 1; i >= 0; i--) - platform_device_unregister(cxl_rcd[i]); err_bridge: for (i = ARRAY_SIZE(cxl_rch) - 1; i >= 0; i--) { struct platform_device *pdev = cxl_rch[i]; @@ -1127,12 +1101,10 @@ err_bridge: return rc; } -static void cxl_rch_exit(void) +static void cxl_rch_topo_exit(void) { int i; - for (i = ARRAY_SIZE(cxl_rcd) - 1; i >= 0; i--) - platform_device_unregister(cxl_rcd[i]); for (i = ARRAY_SIZE(cxl_rch) - 1; i >= 0; i--) { struct platform_device *pdev = cxl_rch[i]; @@ -1143,7 +1115,7 @@ static void cxl_rch_exit(void) } } -static __init int cxl_single_init(void) +static __init int cxl_single_topo_init(void) { int i, rc; @@ -1228,29 +1200,8 @@ static __init int cxl_single_init(void) cxl_swd_single[i] = pdev; } - for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) { - struct platform_device *dport = cxl_swd_single[i]; - struct platform_device *pdev; - - pdev = platform_device_alloc("cxl_mem", NR_MEM_MULTI + i); - if (!pdev) - goto err_mem; - pdev->dev.parent = &dport->dev; - set_dev_node(&pdev->dev, i % 2); - - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); - goto err_mem; - } - cxl_mem_single[i] = pdev; - } - return 0; -err_mem: - for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) - platform_device_unregister(cxl_mem_single[i]); err_dport: for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) platform_device_unregister(cxl_swd_single[i]); @@ -1273,12 +1224,10 @@ err_bridge: return rc; } -static void cxl_single_exit(void) +static void cxl_single_topo_exit(void) { int i; - for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) - platform_device_unregister(cxl_mem_single[i]); for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) platform_device_unregister(cxl_swd_single[i]); for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--) @@ -1295,6 +1244,91 @@ static void cxl_single_exit(void) } } +static void cxl_mem_exit(void) +{ + int i; + + for (i = ARRAY_SIZE(cxl_rcd) - 1; i >= 0; i--) + platform_device_unregister(cxl_rcd[i]); + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); + for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem[i]); +} + +static int cxl_mem_init(void) +{ + int i, rc; + + for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { + struct platform_device *dport = cxl_switch_dport[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_mem", i); + if (!pdev) + goto err_mem; + pdev->dev.parent = &dport->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_mem; + } + cxl_mem[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) { + struct platform_device *dport = cxl_swd_single[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_mem", NR_MEM_MULTI + i); + if (!pdev) + goto err_single; + pdev->dev.parent = &dport->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_single; + } + cxl_mem_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_rcd); i++) { + int idx = NR_MEM_MULTI + NR_MEM_SINGLE + i; + struct platform_device *rch = cxl_rch[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_rcd", idx); + if (!pdev) + goto err_rcd; + pdev->dev.parent = &rch->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_rcd; + } + cxl_rcd[i] = pdev; + } + + return 0; + +err_rcd: + for (i = ARRAY_SIZE(cxl_rcd) - 1; i >= 0; i--) + platform_device_unregister(cxl_rcd[i]); +err_single: + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); +err_mem: + for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem[i]); + return rc; +} + static __init int cxl_test_init(void) { int rc, i; @@ -1407,29 +1441,11 @@ static __init int cxl_test_init(void) cxl_switch_dport[i] = pdev; } - for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { - struct platform_device *dport = cxl_switch_dport[i]; - struct platform_device *pdev; - - pdev = platform_device_alloc("cxl_mem", i); - if (!pdev) - goto err_mem; - pdev->dev.parent = &dport->dev; - set_dev_node(&pdev->dev, i % 2); - - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); - goto err_mem; - } - cxl_mem[i] = pdev; - } - - rc = cxl_single_init(); + rc = cxl_single_topo_init(); if (rc) - goto err_mem; + goto err_dport; - rc = cxl_rch_init(); + rc = cxl_rch_topo_init(); if (rc) goto err_single; @@ -1442,19 +1458,20 @@ static __init int cxl_test_init(void) rc = platform_device_add(cxl_acpi); if (rc) - goto err_add; + goto err_root; + + rc = cxl_mem_init(); + if (rc) + goto err_root; return 0; -err_add: +err_root: platform_device_put(cxl_acpi); err_rch: - cxl_rch_exit(); + cxl_rch_topo_exit(); err_single: - cxl_single_exit(); -err_mem: - for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) - platform_device_unregister(cxl_mem[i]); + cxl_single_topo_exit(); err_dport: for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) platform_device_unregister(cxl_switch_dport[i]); @@ -1486,11 +1503,10 @@ static __exit void cxl_test_exit(void) { int i; + cxl_mem_exit(); platform_device_unregister(cxl_acpi); - cxl_rch_exit(); - cxl_single_exit(); - for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) - platform_device_unregister(cxl_mem[i]); + cxl_rch_topo_exit(); + cxl_single_topo_exit(); for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) platform_device_unregister(cxl_switch_dport[i]); for (i = ARRAY_SIZE(cxl_switch_uport) - 1; i >= 0; i--) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index ad5c4c18c5c6..71916e0e1546 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1673,6 +1673,7 @@ static struct platform_driver cxl_mock_mem_driver = { .name = KBUILD_MODNAME, .dev_groups = cxl_mock_mem_groups, .groups = cxl_mock_mem_core_groups, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, }; diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 1873ddbe16cc..551ae6898c1d 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -36317,6 +36317,28 @@ static inline int check_vma_modification(struct maple_tree *mt) return 0; } +/* + * test to check that bulk stores do not use wr_rebalance as the store + * type. + */ +static inline void check_bulk_rebalance(struct maple_tree *mt) +{ + MA_STATE(mas, mt, ULONG_MAX, ULONG_MAX); + int max = 10; + + build_full_tree(mt, 0, 2); + + /* erase every entry in the tree */ + do { + /* set up bulk store mode */ + mas_expected_entries(&mas, max); + mas_erase(&mas); + MT_BUG_ON(mt, mas.store_type == wr_rebalance); + } while (mas_prev(&mas, 0) != NULL); + + mas_destroy(&mas); +} + void farmer_tests(void) { struct maple_node *node; @@ -36328,6 +36350,10 @@ void farmer_tests(void) check_vma_modification(&tree); mtree_destroy(&tree); + mt_init(&tree); + check_bulk_rebalance(&tree); + mtree_destroy(&tree); + tree.ma_root = xa_mk_value(0); mt_dump(&tree, mt_dump_dec); @@ -36406,9 +36432,93 @@ void farmer_tests(void) check_nomem(&tree); } +static unsigned long get_last_index(struct ma_state *mas) +{ + struct maple_node *node = mas_mn(mas); + enum maple_type mt = mte_node_type(mas->node); + unsigned long *pivots = ma_pivots(node, mt); + unsigned long last_index = mas_data_end(mas); + + BUG_ON(last_index == 0); + + return pivots[last_index - 1] + 1; +} + +/* + * Assert that we handle spanning stores that consume the entirety of the right + * leaf node correctly. + */ +static void test_spanning_store_regression(void) +{ + unsigned long from = 0, to = 0; + DEFINE_MTREE(tree); + MA_STATE(mas, &tree, 0, 0); + + /* + * Build a 3-level tree. We require a parent node below the root node + * and 2 leaf nodes under it, so we can span the entirety of the right + * hand node. + */ + build_full_tree(&tree, 0, 3); + + /* Descend into position at depth 2. */ + mas_reset(&mas); + mas_start(&mas); + mas_descend(&mas); + mas_descend(&mas); + + /* + * We need to establish a tree like the below. + * + * Then we can try a store in [from, to] which results in a spanned + * store across nodes B and C, with the maple state at the time of the + * write being such that only the subtree at A and below is considered. + * + * Height + * 0 Root Node + * / \ + * pivot = to / \ pivot = ULONG_MAX + * / \ + * 1 A [-----] ... + * / \ + * pivot = from / \ pivot = to + * / \ + * 2 (LEAVES) B [-----] [-----] C + * ^--- Last pivot to. + */ + while (true) { + unsigned long tmp = get_last_index(&mas); + + if (mas_next_sibling(&mas)) { + from = tmp; + to = mas.max; + } else { + break; + } + } + + BUG_ON(from == 0 && to == 0); + + /* Perform the store. */ + mas_set_range(&mas, from, to); + mas_store_gfp(&mas, xa_mk_value(0xdead), GFP_KERNEL); + + /* If the regression occurs, the validation will fail. */ + mt_validate(&tree); + + /* Cleanup. */ + __mt_destroy(&tree); +} + +static void regression_tests(void) +{ + test_spanning_store_regression(); +} + void maple_tree_tests(void) { #if !defined(BENCH) + regression_tests(); farmer_tests(); #endif maple_tree_seed(); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index b38199965f99..363d031a16f7 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -88,6 +88,7 @@ TARGETS += rlimits TARGETS += rseq TARGETS += rtc TARGETS += rust +TARGETS += sched_ext TARGETS += seccomp TARGETS += sgx TARGETS += sigaltstack @@ -129,10 +130,10 @@ ifeq ($(filter net/lib,$(TARGETS)),) endif endif -# User can optionally provide a TARGETS skiplist. By default we skip -# BPF since it has cutting edge build time dependencies which require -# more effort to install. -SKIP_TARGETS ?= bpf +# User can optionally provide a TARGETS skiplist. By default we skip +# targets using BPF since it has cutting edge build time dependencies +# which require more effort to install. +SKIP_TARGETS ?= bpf sched_ext ifneq ($(SKIP_TARGETS),) TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS)) override TARGETS := $(TMP) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f04af11df8eb..75016962f795 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -157,7 +157,8 @@ TEST_GEN_PROGS_EXTENDED = \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ - xdp_features bpf_test_no_cfi.ko + xdp_features bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi @@ -263,7 +264,7 @@ $(OUTPUT)/%:%.c ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 riscv)) LLD := lld else -LLD := ld +LLD := $(shell command -v $(LD)) endif # Filter out -static for liburandom_read.so and its dependent targets so that static builds @@ -303,6 +304,19 @@ $(OUTPUT)/bpf_test_no_cfi.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_te $(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_test_no_cfi $(Q)cp bpf_test_no_cfi/bpf_test_no_cfi.ko $@ +$(OUTPUT)/bpf_test_modorder_x.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_modorder_x/Makefile bpf_test_modorder_x/*.[ch]) + $(call msg,MOD,,$@) + $(Q)$(RM) bpf_test_modorder_x/bpf_test_modorder_x.ko # force re-compilation + $(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_test_modorder_x + $(Q)cp bpf_test_modorder_x/bpf_test_modorder_x.ko $@ + +$(OUTPUT)/bpf_test_modorder_y.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_modorder_y/Makefile bpf_test_modorder_y/*.[ch]) + $(call msg,MOD,,$@) + $(Q)$(RM) bpf_test_modorder_y/bpf_test_modorder_y.ko # force re-compilation + $(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_test_modorder_y + $(Q)cp bpf_test_modorder_y/bpf_test_modorder_y.ko $@ + + DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool ifneq ($(CROSS_COMPILE),) CROSS_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool @@ -722,6 +736,8 @@ TRUNNER_EXTRA_SOURCES := test_progs.c \ ip_check_defrag_frags.h TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ $(OUTPUT)/bpf_test_no_cfi.ko \ + $(OUTPUT)/bpf_test_modorder_x.ko \ + $(OUTPUT)/bpf_test_modorder_y.ko \ $(OUTPUT)/liburandom_read.so \ $(OUTPUT)/xdp_synproxy \ $(OUTPUT)/sign-file \ @@ -856,6 +872,8 @@ EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ $(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h \ no_alu32 cpuv4 bpf_gcc bpf_testmod.ko \ bpf_test_no_cfi.ko \ + bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko \ liburandom_read.so) \ $(OUTPUT)/FEATURE-DUMP.selftests diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile b/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile new file mode 100644 index 000000000000..40b25b98ad1b --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile @@ -0,0 +1,19 @@ +BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = bpf_test_modorder_x.ko + +obj-m += bpf_test_modorder_x.o + +all: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean + diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c b/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c new file mode 100644 index 000000000000..0cc747fa912f --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/module.h> +#include <linux/init.h> + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_test_modorder_retx(void) +{ + return 'x'; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(bpf_test_modorder_kfunc_x_ids) +BTF_ID_FLAGS(func, bpf_test_modorder_retx); +BTF_KFUNCS_END(bpf_test_modorder_kfunc_x_ids) + +static const struct btf_kfunc_id_set bpf_test_modorder_x_set = { + .owner = THIS_MODULE, + .set = &bpf_test_modorder_kfunc_x_ids, +}; + +static int __init bpf_test_modorder_x_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + &bpf_test_modorder_x_set); +} + +static void __exit bpf_test_modorder_x_exit(void) +{ +} + +module_init(bpf_test_modorder_x_init); +module_exit(bpf_test_modorder_x_exit); + +MODULE_DESCRIPTION("BPF selftest ordertest module X"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile b/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile new file mode 100644 index 000000000000..52c3ab9d84e2 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile @@ -0,0 +1,19 @@ +BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = bpf_test_modorder_y.ko + +obj-m += bpf_test_modorder_y.o + +all: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean + diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c b/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c new file mode 100644 index 000000000000..c627ee085d13 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/module.h> +#include <linux/init.h> + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_test_modorder_rety(void) +{ + return 'y'; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(bpf_test_modorder_kfunc_y_ids) +BTF_ID_FLAGS(func, bpf_test_modorder_rety); +BTF_KFUNCS_END(bpf_test_modorder_kfunc_y_ids) + +static const struct btf_kfunc_id_set bpf_test_modorder_y_set = { + .owner = THIS_MODULE, + .set = &bpf_test_modorder_kfunc_y_ids, +}; + +static int __init bpf_test_modorder_y_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + &bpf_test_modorder_y_set); +} + +static void __exit bpf_test_modorder_y_exit(void) +{ +} + +module_init(bpf_test_modorder_y_init); +module_exit(bpf_test_modorder_y_exit); + +MODULE_DESCRIPTION("BPF selftest ordertest module Y"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c new file mode 100644 index 000000000000..0ba015686492 --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <linux/bpf.h> +#include <stdio.h> +#include <stdbool.h> +#include <unistd.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <pthread.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <test_maps.h> + +struct test_lpm_key { + __u32 prefix; + __u32 data; +}; + +struct get_next_key_ctx { + struct test_lpm_key key; + bool start; + bool stop; + int map_fd; + int loop; +}; + +static void *get_next_key_fn(void *arg) +{ + struct get_next_key_ctx *ctx = arg; + struct test_lpm_key next_key; + int i = 0; + + while (!ctx->start) + usleep(1); + + while (!ctx->stop && i++ < ctx->loop) + bpf_map_get_next_key(ctx->map_fd, &ctx->key, &next_key); + + return NULL; +} + +static void abort_get_next_key(struct get_next_key_ctx *ctx, pthread_t *tids, + unsigned int nr) +{ + unsigned int i; + + ctx->stop = true; + ctx->start = true; + for (i = 0; i < nr; i++) + pthread_join(tids[i], NULL); +} + +/* This test aims to prevent regression of future. As long as the kernel does + * not panic, it is considered as success. + */ +void test_lpm_trie_map_get_next_key(void) +{ +#define MAX_NR_THREADS 8 + LIBBPF_OPTS(bpf_map_create_opts, create_opts, + .map_flags = BPF_F_NO_PREALLOC); + struct test_lpm_key key = {}; + __u32 val = 0; + int map_fd; + const __u32 max_prefixlen = 8 * (sizeof(key) - sizeof(key.prefix)); + const __u32 max_entries = max_prefixlen + 1; + unsigned int i, nr = MAX_NR_THREADS, loop = 65536; + pthread_t tids[MAX_NR_THREADS]; + struct get_next_key_ctx ctx; + int err; + + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie_map", + sizeof(struct test_lpm_key), sizeof(__u32), + max_entries, &create_opts); + CHECK(map_fd == -1, "bpf_map_create()", "error:%s\n", + strerror(errno)); + + for (i = 0; i <= max_prefixlen; i++) { + key.prefix = i; + err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); + CHECK(err, "bpf_map_update_elem()", "error:%s\n", + strerror(errno)); + } + + ctx.start = false; + ctx.stop = false; + ctx.map_fd = map_fd; + ctx.loop = loop; + memcpy(&ctx.key, &key, sizeof(key)); + + for (i = 0; i < nr; i++) { + err = pthread_create(&tids[i], NULL, get_next_key_fn, &ctx); + if (err) { + abort_get_next_key(&ctx, tids, i); + CHECK(err, "pthread_create", "error %d\n", err); + } + } + + ctx.start = true; + for (i = 0; i < nr; i++) + pthread_join(tids[i], NULL); + + printf("%s:PASS\n", __func__); + + close(map_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 52e6f7570475..f0a3a9c18e9e 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -226,7 +226,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, ASSERT_OK(pthread_create(&thread_id, NULL, &do_nothing_wait, NULL), "pthread_create"); - skel->bss->tid = getpid(); + skel->bss->tid = gettid(); do_dummy_read_opts(skel->progs.dump_task, opts); @@ -249,25 +249,42 @@ static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown, ASSERT_EQ(num_known_tid, num_known, "check_num_known_tid"); } -static void test_task_tid(void) +static void *run_test_task_tid(void *arg) { LIBBPF_OPTS(bpf_iter_attach_opts, opts); union bpf_iter_link_info linfo; int num_unknown_tid, num_known_tid; + ASSERT_NEQ(getpid(), gettid(), "check_new_thread_id"); + memset(&linfo, 0, sizeof(linfo)); - linfo.task.tid = getpid(); + linfo.task.tid = gettid(); opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); test_task_common(&opts, 0, 1); linfo.task.tid = 0; linfo.task.pid = getpid(); - test_task_common(&opts, 1, 1); + /* This includes the parent thread, this thread, + * and the do_nothing_wait thread + */ + test_task_common(&opts, 2, 1); test_task_common_nocheck(NULL, &num_unknown_tid, &num_known_tid); - ASSERT_GT(num_unknown_tid, 1, "check_num_unknown_tid"); + ASSERT_GT(num_unknown_tid, 2, "check_num_unknown_tid"); ASSERT_EQ(num_known_tid, 1, "check_num_known_tid"); + + return NULL; +} + +static void test_task_tid(void) +{ + pthread_t thread_id; + + /* Create a new thread so pid and tid aren't the same */ + ASSERT_OK(pthread_create(&thread_id, NULL, &run_test_task_tid, NULL), + "pthread_create"); + ASSERT_FALSE(pthread_join(thread_id, NULL), "pthread_join"); } static void test_task_pid(void) diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c b/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c index 9250a1e9f9af..3f9ffdf71343 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c @@ -35,7 +35,7 @@ static int send_datagram(void) if (!ASSERT_OK_FD(sock, "create socket")) return sock; - if (!ASSERT_OK(connect(sock, &addr, sizeof(addr)), "connect")) { + if (!ASSERT_OK(connect(sock, (struct sockaddr *)&addr, sizeof(addr)), "connect")) { close(sock); return -1; } diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c index 2570bd4b0cb2..e58a04654238 100644 --- a/tools/testing/selftests/bpf/prog_tests/cpumask.c +++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c @@ -23,6 +23,7 @@ static const char * const cpumask_success_testcases[] = { "test_global_mask_array_l2_rcu", "test_global_mask_nested_rcu", "test_global_mask_nested_deep_rcu", + "test_global_mask_nested_deep_array_rcu", "test_cpumask_weight", }; diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index f3932941bbaa..d50cbd8040d4 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -67,8 +67,9 @@ again: ASSERT_EQ(info.perf_event.kprobe.cookie, PERF_EVENT_COOKIE, "kprobe_cookie"); + ASSERT_EQ(info.perf_event.kprobe.name_len, strlen(KPROBE_FUNC) + 1, + "name_len"); if (!info.perf_event.kprobe.func_name) { - ASSERT_EQ(info.perf_event.kprobe.name_len, 0, "name_len"); info.perf_event.kprobe.func_name = ptr_to_u64(&buf); info.perf_event.kprobe.name_len = sizeof(buf); goto again; @@ -79,8 +80,9 @@ again: ASSERT_EQ(err, 0, "cmp_kprobe_func_name"); break; case BPF_PERF_EVENT_TRACEPOINT: + ASSERT_EQ(info.perf_event.tracepoint.name_len, strlen(TP_NAME) + 1, + "name_len"); if (!info.perf_event.tracepoint.tp_name) { - ASSERT_EQ(info.perf_event.tracepoint.name_len, 0, "name_len"); info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf); info.perf_event.tracepoint.name_len = sizeof(buf); goto again; @@ -96,8 +98,9 @@ again: case BPF_PERF_EVENT_URETPROBE: ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset"); + ASSERT_EQ(info.perf_event.uprobe.name_len, strlen(UPROBE_FILE) + 1, + "name_len"); if (!info.perf_event.uprobe.file_name) { - ASSERT_EQ(info.perf_event.uprobe.name_len, 0, "name_len"); info.perf_event.uprobe.file_name = ptr_to_u64(&buf); info.perf_event.uprobe.name_len = sizeof(buf); goto again; @@ -417,6 +420,15 @@ verify_umulti_link_info(int fd, bool retprobe, __u64 *offsets, if (!ASSERT_NEQ(err, -1, "readlink")) return -1; + memset(&info, 0, sizeof(info)); + err = bpf_link_get_info_by_fd(fd, &info, &len); + if (!ASSERT_OK(err, "bpf_link_get_info_by_fd")) + return -1; + + ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count"); + ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1, + "info.uprobe_multi.path_size"); + for (bit = 0; bit < 8; bit++) { memset(&info, 0, sizeof(info)); info.uprobe_multi.path = ptr_to_u64(path_buf); diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c b/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c new file mode 100644 index 000000000000..48c0560d398e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <testing_helpers.h> + +#include "kfunc_module_order.skel.h" + +static int test_run_prog(const struct bpf_program *prog, + struct bpf_test_run_opts *opts) +{ + int err; + + err = bpf_prog_test_run_opts(bpf_program__fd(prog), opts); + if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) + return err; + + if (!ASSERT_EQ((int)opts->retval, 0, bpf_program__name(prog))) + return -EINVAL; + + return 0; +} + +void test_kfunc_module_order(void) +{ + struct kfunc_module_order *skel; + char pkt_data[64] = {}; + int err = 0; + + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, test_opts, .data_in = pkt_data, + .data_size_in = sizeof(pkt_data)); + + err = load_module("bpf_test_modorder_x.ko", + env_verbosity > VERBOSE_NONE); + if (!ASSERT_OK(err, "load bpf_test_modorder_x.ko")) + return; + + err = load_module("bpf_test_modorder_y.ko", + env_verbosity > VERBOSE_NONE); + if (!ASSERT_OK(err, "load bpf_test_modorder_y.ko")) + goto exit_modx; + + skel = kfunc_module_order__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kfunc_module_order__open_and_load()")) { + err = -EINVAL; + goto exit_mods; + } + + test_run_prog(skel->progs.call_kfunc_xy, &test_opts); + test_run_prog(skel->progs.call_kfunc_yx, &test_opts); + + kfunc_module_order__destroy(skel); +exit_mods: + unload_module("bpf_test_modorder_y", env_verbosity > VERBOSE_NONE); +exit_modx: + unload_module("bpf_test_modorder_x", env_verbosity > VERBOSE_NONE); +} diff --git a/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c index 4297a2a4cb11..2f52fa2641ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c @@ -26,10 +26,43 @@ static const struct nf_link_test nf_hook_link_tests[] = { { .pf = NFPROTO_INET, .priority = 1, .name = "invalid-inet-not-supported", }, - { .pf = NFPROTO_IPV4, .priority = -10000, .expect_success = true, .name = "attach ipv4", }, - { .pf = NFPROTO_IPV6, .priority = 10001, .expect_success = true, .name = "attach ipv6", }, + { + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = -10000, + .flags = 0, + .expect_success = true, + .name = "attach ipv4", + }, + { + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_FORWARD, + .priority = 10001, + .flags = BPF_F_NETFILTER_IP_DEFRAG, + .expect_success = true, + .name = "attach ipv6", + }, }; +static void verify_netfilter_link_info(struct bpf_link *link, const struct nf_link_test nf_expected) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + int err, fd; + + memset(&info, 0, len); + + fd = bpf_link__fd(link); + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_OK(err, "get_link_info"); + + ASSERT_EQ(info.type, BPF_LINK_TYPE_NETFILTER, "info link type"); + ASSERT_EQ(info.netfilter.pf, nf_expected.pf, "info nf protocol family"); + ASSERT_EQ(info.netfilter.hooknum, nf_expected.hooknum, "info nf hooknum"); + ASSERT_EQ(info.netfilter.priority, nf_expected.priority, "info nf priority"); + ASSERT_EQ(info.netfilter.flags, nf_expected.flags, "info nf flags"); +} + void test_netfilter_link_attach(void) { struct test_netfilter_link_attach *skel; @@ -64,6 +97,8 @@ void test_netfilter_link_attach(void) if (!ASSERT_OK_PTR(link, "program attach successful")) continue; + verify_netfilter_link_info(link, nf_hook_link_tests[i]); + link2 = bpf_program__attach_netfilter(prog, &opts); ASSERT_ERR_PTR(link2, "attach program with same pf/hook/priority"); @@ -73,6 +108,9 @@ void test_netfilter_link_attach(void) link2 = bpf_program__attach_netfilter(prog, &opts); if (!ASSERT_OK_PTR(link2, "program reattach successful")) continue; + + verify_netfilter_link_info(link2, nf_hook_link_tests[i]); + if (!ASSERT_OK(bpf_link__destroy(link2), "link destroy")) break; } else { diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index e26b5150fc43..75f7a2ce334b 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -44,6 +44,7 @@ #include "verifier_ld_ind.skel.h" #include "verifier_ldsx.skel.h" #include "verifier_leak_ptr.skel.h" +#include "verifier_linked_scalars.skel.h" #include "verifier_loops1.skel.h" #include "verifier_lwt.skel.h" #include "verifier_map_in_map.skel.h" @@ -53,6 +54,7 @@ #include "verifier_masking.skel.h" #include "verifier_meta_access.skel.h" #include "verifier_movsx.skel.h" +#include "verifier_mtu.skel.h" #include "verifier_netfilter_ctx.skel.h" #include "verifier_netfilter_retcode.skel.h" #include "verifier_bpf_fastcall.skel.h" @@ -170,6 +172,7 @@ void test_verifier_jit_convergence(void) { RUN(verifier_jit_convergence); } void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); } void test_verifier_ldsx(void) { RUN(verifier_ldsx); } void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); } +void test_verifier_linked_scalars(void) { RUN(verifier_linked_scalars); } void test_verifier_loops1(void) { RUN(verifier_loops1); } void test_verifier_lwt(void) { RUN(verifier_lwt); } void test_verifier_map_in_map(void) { RUN(verifier_map_in_map); } @@ -221,6 +224,24 @@ void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_pack void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); } void test_verifier_lsm(void) { RUN(verifier_lsm); } +void test_verifier_mtu(void) +{ + __u64 caps = 0; + int ret; + + /* In case CAP_BPF and CAP_PERFMON is not set */ + ret = cap_enable_effective(1ULL << CAP_BPF | 1ULL << CAP_NET_ADMIN, &caps); + if (!ASSERT_OK(ret, "set_cap_bpf_cap_net_admin")) + return; + ret = cap_disable_effective(1ULL << CAP_SYS_ADMIN | 1ULL << CAP_PERFMON, NULL); + if (!ASSERT_OK(ret, "disable_cap_sys_admin")) + goto restore_cap; + RUN(verifier_mtu); +restore_cap: + if (caps) + cap_enable_effective(caps, NULL); +} + static int init_test_val_map(struct bpf_object *obj, char *map_name) { struct test_val value = { diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index ce6812558287..27ffed17d4be 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 +#include <arpa/inet.h> #include <uapi/linux/bpf.h> #include <linux/if_link.h> +#include <network_helpers.h> +#include <net/if.h> #include <test_progs.h> #include "test_xdp_devmap_helpers.skel.h" @@ -8,31 +11,36 @@ #include "test_xdp_with_devmap_helpers.skel.h" #define IFINDEX_LO 1 +#define TEST_NS "devmap_attach_ns" static void test_xdp_with_devmap_helpers(void) { - struct test_xdp_with_devmap_helpers *skel; + struct test_xdp_with_devmap_helpers *skel = NULL; struct bpf_prog_info info = {}; struct bpf_devmap_val val = { .ifindex = IFINDEX_LO, }; __u32 len = sizeof(info); - int err, dm_fd, map_fd; + int err, dm_fd, dm_fd_redir, map_fd; + struct nstoken *nstoken = NULL; + char data[10] = {}; __u32 idx = 0; + SYS(out_close, "ip netns add %s", TEST_NS); + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto out_close; + SYS(out_close, "ip link set dev lo up"); skel = test_xdp_with_devmap_helpers__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) - return; + goto out_close; - dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); + dm_fd_redir = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd_redir, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap")) goto out_close; - err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); - ASSERT_OK(err, "XDP program detach"); - dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); map_fd = bpf_map__fd(skel->maps.dm_ports); err = bpf_prog_get_info_by_fd(dm_fd, &info, &len); @@ -47,6 +55,22 @@ static void test_xdp_with_devmap_helpers(void) ASSERT_OK(err, "Read devmap entry"); ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id"); + /* send a packet to trigger any potential bugs in there */ + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = 10, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(dm_fd_redir, &opts); + ASSERT_OK(err, "XDP test run"); + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + /* can not attach BPF_XDP_DEVMAP program to a device */ err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_DEVMAP program")) @@ -67,6 +91,8 @@ static void test_xdp_with_devmap_helpers(void) ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to devmap entry"); out_close: + close_netns(nstoken); + SYS_NOFAIL("ip netns del %s", TEST_NS); test_xdp_with_devmap_helpers__destroy(skel); } @@ -124,6 +150,86 @@ out_close: test_xdp_with_devmap_frags_helpers__destroy(skel); } +static void test_xdp_with_devmap_helpers_veth(void) +{ + struct test_xdp_with_devmap_helpers *skel = NULL; + struct bpf_prog_info info = {}; + struct bpf_devmap_val val = {}; + struct nstoken *nstoken = NULL; + __u32 len = sizeof(info); + int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst; + char data[10] = {}; + __u32 idx = 0; + + SYS(out_close, "ip netns add %s", TEST_NS); + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto out_close; + + SYS(out_close, "ip link add veth_src type veth peer name veth_dst"); + SYS(out_close, "ip link set dev veth_src up"); + SYS(out_close, "ip link set dev veth_dst up"); + + val.ifindex = if_nametoindex("veth_src"); + ifindex_dst = if_nametoindex("veth_dst"); + if (!ASSERT_NEQ(val.ifindex, 0, "val.ifindex") || + !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) + goto out_close; + + skel = test_xdp_with_devmap_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) + goto out_close; + + dm_fd_redir = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_xdp_attach(val.ifindex, dm_fd_redir, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "Attach of program with 8-byte devmap")) + goto out_close; + + dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); + map_fd = bpf_map__fd(skel->maps.dm_ports); + err = bpf_prog_get_info_by_fd(dm_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = dm_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add program to devmap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read devmap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id"); + + /* attach dummy to other side to enable reception */ + dm_fd = bpf_program__fd(skel->progs.xdp_dummy_prog); + err = bpf_xdp_attach(ifindex_dst, dm_fd, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "Attach of dummy XDP")) + goto out_close; + + /* send a packet to trigger any potential bugs in there */ + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = 10, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(dm_fd_redir, &opts); + ASSERT_OK(err, "XDP test run"); + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + err = bpf_xdp_detach(val.ifindex, XDP_FLAGS_DRV_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + + err = bpf_xdp_detach(ifindex_dst, XDP_FLAGS_DRV_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + +out_close: + close_netns(nstoken); + SYS_NOFAIL("ip netns del %s", TEST_NS); + test_xdp_with_devmap_helpers__destroy(skel); +} + void serial_test_xdp_devmap_attach(void) { if (test__start_subtest("DEVMAP with programs in entries")) @@ -134,4 +240,7 @@ void serial_test_xdp_devmap_attach(void) if (test__start_subtest("Verifier check of DEVMAP programs")) test_neg_xdp_devmap_helpers(); + + if (test__start_subtest("DEVMAP with programs in entries on veth")) + test_xdp_with_devmap_helpers_veth(); } diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h index b979e91f55f0..4ece7873ba60 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_common.h +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -7,6 +7,11 @@ #include "errno.h" #include <stdbool.h> +/* Should use BTF_FIELDS_MAX, but it is not always available in vmlinux.h, + * so use the hard-coded number as a workaround. + */ +#define CPUMASK_KPTR_FIELDS_MAX 11 + int err; #define private(name) SEC(".bss." #name) __attribute__((aligned(8))) diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c index a988d2823b52..b40b52548ffb 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_failure.c +++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c @@ -10,6 +10,21 @@ char _license[] SEC("license") = "GPL"; +struct kptr_nested_array_2 { + struct bpf_cpumask __kptr * mask; +}; + +struct kptr_nested_array_1 { + /* Make btf_parse_fields() in map_create() return -E2BIG */ + struct kptr_nested_array_2 d_2[CPUMASK_KPTR_FIELDS_MAX + 1]; +}; + +struct kptr_nested_array { + struct kptr_nested_array_1 d_1; +}; + +private(MASK_NESTED) static struct kptr_nested_array global_mask_nested_arr; + /* Prototype for all of the program trace events below: * * TRACE_EVENT(task_newtask, @@ -187,3 +202,23 @@ int BPF_PROG(test_global_mask_rcu_no_null_check, struct task_struct *task, u64 c return 0; } + +SEC("tp_btf/task_newtask") +__failure __msg("has no valid kptr") +int BPF_PROG(test_invalid_nested_array, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *local, *prev; + + local = create_cpumask(); + if (!local) + return 0; + + prev = bpf_kptr_xchg(&global_mask_nested_arr.d_1.d_2[CPUMASK_KPTR_FIELDS_MAX].mask, local); + if (prev) { + bpf_cpumask_release(prev); + err = 3; + return 0; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c index fd8106831c32..80ee469b0b60 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_success.c +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -31,11 +31,59 @@ struct kptr_nested_deep { struct kptr_nested_pair ptr_pairs[3]; }; +struct kptr_nested_deep_array_1_2 { + int dummy; + struct bpf_cpumask __kptr * mask[CPUMASK_KPTR_FIELDS_MAX]; +}; + +struct kptr_nested_deep_array_1_1 { + int dummy; + struct kptr_nested_deep_array_1_2 d_2; +}; + +struct kptr_nested_deep_array_1 { + long dummy; + struct kptr_nested_deep_array_1_1 d_1; +}; + +struct kptr_nested_deep_array_2_2 { + long dummy[2]; + struct bpf_cpumask __kptr * mask; +}; + +struct kptr_nested_deep_array_2_1 { + int dummy; + struct kptr_nested_deep_array_2_2 d_2[CPUMASK_KPTR_FIELDS_MAX]; +}; + +struct kptr_nested_deep_array_2 { + long dummy; + struct kptr_nested_deep_array_2_1 d_1; +}; + +struct kptr_nested_deep_array_3_2 { + long dummy[2]; + struct bpf_cpumask __kptr * mask; +}; + +struct kptr_nested_deep_array_3_1 { + int dummy; + struct kptr_nested_deep_array_3_2 d_2; +}; + +struct kptr_nested_deep_array_3 { + long dummy; + struct kptr_nested_deep_array_3_1 d_1[CPUMASK_KPTR_FIELDS_MAX]; +}; + private(MASK) static struct bpf_cpumask __kptr * global_mask_array[2]; private(MASK) static struct bpf_cpumask __kptr * global_mask_array_l2[2][1]; private(MASK) static struct bpf_cpumask __kptr * global_mask_array_one[1]; private(MASK) static struct kptr_nested global_mask_nested[2]; private(MASK_DEEP) static struct kptr_nested_deep global_mask_nested_deep; +private(MASK_1) static struct kptr_nested_deep_array_1 global_mask_nested_deep_array_1; +private(MASK_2) static struct kptr_nested_deep_array_2 global_mask_nested_deep_array_2; +private(MASK_3) static struct kptr_nested_deep_array_3 global_mask_nested_deep_array_3; static bool is_test_task(void) { @@ -543,12 +591,21 @@ static int _global_mask_array_rcu(struct bpf_cpumask **mask0, goto err_exit; } - /* [<mask 0>, NULL] */ - if (!*mask0 || *mask1) { + /* [<mask 0>, *] */ + if (!*mask0) { err = 2; goto err_exit; } + if (!mask1) + goto err_exit; + + /* [*, NULL] */ + if (*mask1) { + err = 3; + goto err_exit; + } + local = create_cpumask(); if (!local) { err = 9; @@ -632,6 +689,23 @@ int BPF_PROG(test_global_mask_nested_deep_rcu, struct task_struct *task, u64 clo } SEC("tp_btf/task_newtask") +int BPF_PROG(test_global_mask_nested_deep_array_rcu, struct task_struct *task, u64 clone_flags) +{ + int i; + + for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++) + _global_mask_array_rcu(&global_mask_nested_deep_array_1.d_1.d_2.mask[i], NULL); + + for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++) + _global_mask_array_rcu(&global_mask_nested_deep_array_2.d_1.d_2[i].mask, NULL); + + for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++) + _global_mask_array_rcu(&global_mask_nested_deep_array_3.d_1[i].d_2.mask, NULL); + + return 0; +} + +SEC("tp_btf/task_newtask") int BPF_PROG(test_cpumask_weight, struct task_struct *task, u64 clone_flags) { struct bpf_cpumask *local; diff --git a/tools/testing/selftests/bpf/progs/kfunc_module_order.c b/tools/testing/selftests/bpf/progs/kfunc_module_order.c new file mode 100644 index 000000000000..76003d04c95f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_module_order.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +extern int bpf_test_modorder_retx(void) __ksym; +extern int bpf_test_modorder_rety(void) __ksym; + +SEC("classifier") +int call_kfunc_xy(struct __sk_buff *skb) +{ + int ret1, ret2; + + ret1 = bpf_test_modorder_retx(); + ret2 = bpf_test_modorder_rety(); + + return ret1 == 'x' && ret2 == 'y' ? 0 : -1; +} + +SEC("classifier") +int call_kfunc_yx(struct __sk_buff *skb) +{ + int ret1, ret2; + + ret1 = bpf_test_modorder_rety(); + ret2 = bpf_test_modorder_retx(); + + return ret1 == 'y' && ret2 == 'x' ? 0 : -1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 4139a14f9996..92b65a485d4a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -12,7 +12,7 @@ struct { SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { - return bpf_redirect_map(&dm_ports, 1, 0); + return bpf_redirect_map(&dm_ports, 0, 0); } /* invalid program on DEVMAP entry; diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index f4da4d508ddb..7c881bca9af5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -15,6 +15,8 @@ int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak; void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak; +u64 bits_array[511] = {}; + SEC("iter.s/cgroup") __description("bits iter without destroy") __failure __msg("Unreleased reference") @@ -55,9 +57,15 @@ __description("null pointer") __success __retval(0) int null_pointer(void) { - int nr = 0; + struct bpf_iter_bits iter; + int err, nr = 0; int *bit; + err = bpf_iter_bits_new(&iter, NULL, 1); + bpf_iter_bits_destroy(&iter); + if (err != -EINVAL) + return 1; + bpf_for_each(bits, bit, NULL, 1) nr++; return nr; @@ -110,16 +118,16 @@ int bit_index(void) } SEC("syscall") -__description("bits nomem") +__description("bits too big") __success __retval(0) -int bits_nomem(void) +int bits_too_big(void) { u64 data[4]; int nr = 0; int *bit; __builtin_memset(&data, 0xff, sizeof(data)); - bpf_for_each(bits, bit, &data[0], 513) /* Be greater than 512 */ + bpf_for_each(bits, bit, &data[0], 512) /* Be greater than 511 */ nr++; return nr; } @@ -151,3 +159,74 @@ int zero_words(void) nr++; return nr; } + +SEC("syscall") +__description("huge words") +__success __retval(0) +int huge_words(void) +{ + u64 data[8] = {0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1}; + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data[0], 67108865) + nr++; + return nr; +} + +SEC("syscall") +__description("max words") +__success __retval(4) +int max_words(void) +{ + volatile int nr = 0; + int *bit; + + bits_array[0] = (1ULL << 63) | 1U; + bits_array[510] = (1ULL << 33) | (1ULL << 32); + + bpf_for_each(bits, bit, bits_array, 511) { + if (nr == 0 && *bit != 0) + break; + if (nr == 2 && *bit != 32672) + break; + nr++; + } + return nr; +} + +SEC("syscall") +__description("bad words") +__success __retval(0) +int bad_words(void) +{ + void *bad_addr = (void *)-4095; + struct bpf_iter_bits iter; + volatile int nr; + int *bit; + int err; + + err = bpf_iter_bits_new(&iter, bad_addr, 1); + bpf_iter_bits_destroy(&iter); + if (err != -EFAULT) + return 1; + + nr = 0; + bpf_for_each(bits, bit, bad_addr, 1) + nr++; + if (nr != 0) + return 2; + + err = bpf_iter_bits_new(&iter, bad_addr, 4); + bpf_iter_bits_destroy(&iter); + if (err != -EFAULT) + return 3; + + nr = 0; + bpf_for_each(bits, bit, bad_addr, 4) + nr++; + if (nr != 0) + return 4; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c index 9da97d2efcd9..5094c288cfd7 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c +++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c @@ -790,61 +790,6 @@ __naked static void cumulative_stack_depth_subprog(void) :: __imm(bpf_get_smp_processor_id) : __clobber_all); } -SEC("raw_tp") -__arch_x86_64 -__log_level(4) -__msg("stack depth 512") -__xlated("0: r1 = 42") -__xlated("1: *(u64 *)(r10 -512) = r1") -__xlated("2: w0 = ") -__xlated("3: r0 = &(void __percpu *)(r0)") -__xlated("4: r0 = *(u32 *)(r0 +0)") -__xlated("5: exit") -__success -__naked int bpf_fastcall_max_stack_ok(void) -{ - asm volatile( - "r1 = 42;" - "*(u64 *)(r10 - %[max_bpf_stack]) = r1;" - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_smp_processor_id];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - "exit;" - : - : __imm_const(max_bpf_stack, MAX_BPF_STACK), - __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8), - __imm(bpf_get_smp_processor_id) - : __clobber_all - ); -} - -SEC("raw_tp") -__arch_x86_64 -__log_level(4) -__msg("stack depth 520") -__failure -__naked int bpf_fastcall_max_stack_fail(void) -{ - asm volatile( - "r1 = 42;" - "*(u64 *)(r10 - %[max_bpf_stack]) = r1;" - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_smp_processor_id];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - /* call to prandom blocks bpf_fastcall rewrite */ - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_prandom_u32];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - "exit;" - : - : __imm_const(max_bpf_stack, MAX_BPF_STACK), - __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8), - __imm(bpf_get_smp_processor_id), - __imm(bpf_get_prandom_u32) - : __clobber_all - ); -} - SEC("cgroup/getsockname_unix") __xlated("0: r2 = 1") /* bpf_cast_to_kern_ctx is replaced by a single assignment */ diff --git a/tools/testing/selftests/bpf/progs/verifier_const.c b/tools/testing/selftests/bpf/progs/verifier_const.c index 2e533d7eec2f..e118dbb768bf 100644 --- a/tools/testing/selftests/bpf/progs/verifier_const.c +++ b/tools/testing/selftests/bpf/progs/verifier_const.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2024 Isovalent */ -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #include "bpf_misc.h" const volatile long foo = 42; @@ -66,4 +67,32 @@ int tcx6(struct __sk_buff *skb) return TCX_PASS; } +static inline void write_fixed(volatile void *p, __u32 val) +{ + *(volatile __u32 *)p = val; +} + +static inline void write_dyn(void *p, void *val, int len) +{ + bpf_copy_from_user(p, len, val); +} + +SEC("tc/ingress") +__description("rodata/mark: write with unknown reg rejected") +__failure __msg("write into map forbidden") +int tcx7(struct __sk_buff *skb) +{ + write_fixed((void *)&foo, skb->mark); + return TCX_PASS; +} + +SEC("lsm.s/bprm_committed_creds") +__description("rodata/mark: write with unknown reg rejected") +__failure __msg("write into map forbidden") +int BPF_PROG(bprm, struct linux_binprm *bprm) +{ + write_dyn((void *)&foo, &bart, bpf_get_prandom_u32() & 3); + return 0; +} + char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c new file mode 100644 index 000000000000..8f755d2464cf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("scalars: find linked scalars") +__failure +__msg("math between fp pointer and 2147483647 is not allowed") +__naked void scalars(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = 0x80000001 ll; \ + r1 /= 1; \ + r2 = r1; \ + r4 = r1; \ + w2 += 0x7FFFFFFF; \ + w4 += 0; \ + if r2 == 0 goto l1; \ + exit; \ +l1: \ + r4 >>= 63; \ + r3 = 1; \ + r3 -= r4; \ + r3 *= 0x7FFFFFFF; \ + r3 += r10; \ + *(u8*)(r3 - 1) = r0; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c index 028ec855587b..994bbc346d25 100644 --- a/tools/testing/selftests/bpf/progs/verifier_movsx.c +++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c @@ -287,6 +287,46 @@ l0_%=: \ : __clobber_all); } +SEC("socket") +__description("MOV64SX, S8, unsigned range_check") +__success __retval(0) +__naked void mov64sx_s8_range_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x1; \ + r0 += 0xfe; \ + r0 = (s8)r0; \ + if r0 < 0xfffffffffffffffe goto label_%=; \ + r0 = 0; \ + exit; \ +label_%=: \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("MOV32SX, S8, unsigned range_check") +__success __retval(0) +__naked void mov32sx_s8_range_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + w0 &= 0x1; \ + w0 += 0xfe; \ + w0 = (s8)w0; \ + if w0 < 0xfffffffe goto label_%=; \ + r0 = 0; \ + exit; \ +label_%=: \ + exit; \ + " : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + #else SEC("socket") diff --git a/tools/testing/selftests/bpf/progs/verifier_mtu.c b/tools/testing/selftests/bpf/progs/verifier_mtu.c new file mode 100644 index 000000000000..70c7600a26a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_mtu.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("tc/ingress") +__description("uninit/mtu: write rejected") +__failure __msg("invalid indirect read from stack") +int tc_uninit_mtu(struct __sk_buff *ctx) +{ + __u32 mtu; + + bpf_check_mtu(ctx, 0, &mtu, 0, 0); + return TCX_PASS; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 2ecf77b623e0..7c5e5e6d10eb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -760,4 +760,71 @@ __naked void two_old_ids_one_cur_id(void) : __clobber_all); } +SEC("socket") +/* Note the flag, see verifier.c:opt_subreg_zext_lo32_rnd_hi32() */ +__flag(BPF_F_TEST_RND_HI32) +__success +/* This test was added because of a bug in verifier.c:sync_linked_regs(), + * upon range propagation it destroyed subreg_def marks for registers. + * The subreg_def mark is used to decide whether zero extension instructions + * are needed when register is read. When BPF_F_TEST_RND_HI32 is set it + * also causes generation of statements to randomize upper halves of + * read registers. + * + * The test is written in a way to return an upper half of a register + * that is affected by range propagation and must have it's subreg_def + * preserved. This gives a return value of 0 and leads to undefined + * return value if subreg_def mark is not preserved. + */ +__retval(0) +/* Check that verifier believes r1/r0 are zero at exit */ +__log_level(2) +__msg("4: (77) r1 >>= 32 ; R1_w=0") +__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("6: (95) exit") +__msg("from 3 to 4") +__msg("4: (77) r1 >>= 32 ; R1_w=0") +__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("6: (95) exit") +/* Verify that statements to randomize upper half of r1 had not been + * generated. + */ +__xlated("call unknown") +__xlated("r0 &= 2147483647") +__xlated("w1 = w0") +/* This is how disasm.c prints BPF_ZEXT_REG at the moment, x86 and arm + * are the only CI archs that do not need zero extension for subregs. + */ +#if !defined(__TARGET_ARCH_x86) && !defined(__TARGET_ARCH_arm64) +__xlated("w1 = w1") +#endif +__xlated("if w0 < 0xa goto pc+0") +__xlated("r1 >>= 32") +__xlated("r0 = r1") +__xlated("exit") +__naked void linked_regs_and_subreg_def(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* make sure r0 is in 32-bit range, otherwise w1 = w0 won't + * assign same IDs to registers. + */ + "r0 &= 0x7fffffff;" + /* link w1 and w0 via ID */ + "w1 = w0;" + /* 'if' statement propagates range info from w0 to w1, + * but should not affect w1->subreg_def property. + */ + "if w0 < 10 goto +0;" + /* r1 is read here, on archs that require subreg zero + * extension this would cause zext patch generation. + */ + "r1 >>= 32;" + "r0 = r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c index 5a14498d352f..f40e57251e94 100644 --- a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c +++ b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c @@ -2,6 +2,7 @@ /* Converted from tools/testing/selftests/bpf/verifier/search_pruning.c */ #include <linux/bpf.h> +#include <../../../include/linux/filter.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -336,4 +337,26 @@ l0_%=: r1 = 42; \ : __clobber_all); } +/* Without checkpoint forcibly inserted at the back-edge a loop this + * test would take a very long time to verify. + */ +SEC("kprobe") +__failure __log_level(4) +__msg("BPF program is too large.") +__naked void short_loop1(void) +{ + asm volatile ( + " r7 = *(u16 *)(r1 +0);" + "1: r7 += 0x1ab064b9;" + " .8byte %[jset];" /* same as 'if r7 & 0x702000 goto 1b;' */ + " r7 &= 0x1ee60e;" + " r7 += r1;" + " if r7 s> 0x37d2 goto +0;" + " r0 = 0;" + " exit;" + : + : __imm_insn(jset, BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x702000, -2)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index d3c3c3a24150..5e9f16683be5 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -367,7 +367,7 @@ int delete_module(const char *name, int flags) return syscall(__NR_delete_module, name, flags); } -int unload_bpf_testmod(bool verbose) +int unload_module(const char *name, bool verbose) { int ret, cnt = 0; @@ -375,11 +375,11 @@ int unload_bpf_testmod(bool verbose) fprintf(stdout, "Failed to trigger kernel-side RCU sync!\n"); for (;;) { - ret = delete_module("bpf_testmod", 0); + ret = delete_module(name, 0); if (!ret || errno != EAGAIN) break; if (++cnt > 10000) { - fprintf(stdout, "Unload of bpf_testmod timed out\n"); + fprintf(stdout, "Unload of %s timed out\n", name); break; } usleep(100); @@ -388,41 +388,51 @@ int unload_bpf_testmod(bool verbose) if (ret) { if (errno == ENOENT) { if (verbose) - fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); + fprintf(stdout, "%s.ko is already unloaded.\n", name); return -1; } - fprintf(stdout, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); + fprintf(stdout, "Failed to unload %s.ko from kernel: %d\n", name, -errno); return -1; } if (verbose) - fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); + fprintf(stdout, "Successfully unloaded %s.ko.\n", name); return 0; } -int load_bpf_testmod(bool verbose) +int load_module(const char *path, bool verbose) { int fd; if (verbose) - fprintf(stdout, "Loading bpf_testmod.ko...\n"); + fprintf(stdout, "Loading %s...\n", path); - fd = open("bpf_testmod.ko", O_RDONLY); + fd = open(path, O_RDONLY); if (fd < 0) { - fprintf(stdout, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); + fprintf(stdout, "Can't find %s kernel module: %d\n", path, -errno); return -ENOENT; } if (finit_module(fd, "", 0)) { - fprintf(stdout, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); + fprintf(stdout, "Failed to load %s into the kernel: %d\n", path, -errno); close(fd); return -EINVAL; } close(fd); if (verbose) - fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); + fprintf(stdout, "Successfully loaded %s.\n", path); return 0; } +int unload_bpf_testmod(bool verbose) +{ + return unload_module("bpf_testmod", verbose); +} + +int load_bpf_testmod(bool verbose) +{ + return load_module("bpf_testmod.ko", verbose); +} + /* * Trigger synchronize_rcu() in kernel. */ diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index d55f6ab12433..46d7f7089f63 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -38,6 +38,8 @@ int unload_bpf_testmod(bool verbose); int kern_sync_rcu(void); int finit_module(int fd, const char *param_values, int flags); int delete_module(const char *name, int flags); +int load_module(const char *path, bool verbose); +int unload_module(const char *name, bool verbose); static inline __u64 get_time_ns(void) { diff --git a/tools/testing/selftests/bpf/veristat.cfg b/tools/testing/selftests/bpf/veristat.cfg index 1a385061618d..e661ffdcaadf 100644 --- a/tools/testing/selftests/bpf/veristat.cfg +++ b/tools/testing/selftests/bpf/veristat.cfg @@ -15,3 +15,4 @@ test_usdt* test_verif_scale* test_xdp_noinline* xdp_synproxy* +verifier_search_pruning* diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index 41d0859feb7d..edc56e2cc606 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -11,6 +11,8 @@ ALL_TESTS=" lib_dir=$(dirname "$0") source ${lib_dir}/bond_topo_3d1c.sh +c_maddr="33:33:00:00:00:10" +g_maddr="33:33:00:00:02:54" skip_prio() { @@ -240,6 +242,54 @@ arp_validate_test() done } +# Testing correct multicast groups are added to slaves for ns targets +arp_validate_mcast() +{ + RET=0 + local arp_valid=$(cmd_jq "ip -n ${s_ns} -j -d link show bond0" ".[].linkinfo.info_data.arp_validate") + local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + + for i in $(seq 0 2); do + maddr_list=$(ip -n ${s_ns} maddr show dev eth${i}) + + # arp_valid == 0 or active_slave should not join any maddrs + if { [ "$arp_valid" == "null" ] || [ "eth${i}" == ${active_slave} ]; } && \ + echo "$maddr_list" | grep -qE "${c_maddr}|${g_maddr}"; then + RET=1 + check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group" + # arp_valid != 0 and backup_slave should join both maddrs + elif [ "$arp_valid" != "null" ] && [ "eth${i}" != ${active_slave} ] && \ + ( ! echo "$maddr_list" | grep -q "${c_maddr}" || \ + ! echo "$maddr_list" | grep -q "${m_maddr}"); then + RET=1 + check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group" + fi + done + + # Do failover + ip -n ${s_ns} link set ${active_slave} down + # wait for active link change + slowwait 2 active_slave_changed $active_slave + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + + for i in $(seq 0 2); do + maddr_list=$(ip -n ${s_ns} maddr show dev eth${i}) + + # arp_valid == 0 or active_slave should not join any maddrs + if { [ "$arp_valid" == "null" ] || [ "eth${i}" == ${active_slave} ]; } && \ + echo "$maddr_list" | grep -qE "${c_maddr}|${g_maddr}"; then + RET=1 + check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group" + # arp_valid != 0 and backup_slave should join both maddrs + elif [ "$arp_valid" != "null" ] && [ "eth${i}" != ${active_slave} ] && \ + ( ! echo "$maddr_list" | grep -q "${c_maddr}" || \ + ! echo "$maddr_list" | grep -q "${m_maddr}"); then + RET=1 + check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group" + fi + done +} + arp_validate_arp() { local mode=$1 @@ -261,8 +311,10 @@ arp_validate_ns() fi for val in $(seq 0 6); do - arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} arp_validate $val" + arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6},${c_ip6} arp_validate $val" log_test "arp_validate" "$mode ns_ip6_target arp_validate $val" + arp_validate_mcast + log_test "arp_validate" "join mcast group" done } diff --git a/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc b/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc new file mode 100644 index 000000000000..35e8d47d6072 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc @@ -0,0 +1,101 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test tracefs GID mount option +# requires: "[gid=<gid>]":README + +fail() { + local msg="$1" + + echo "FAILED: $msg" + exit_fail +} + +find_alternate_gid() { + local original_gid="$1" + tac /etc/group | grep -v ":$original_gid:" | head -1 | cut -d: -f3 +} + +mount_tracefs_with_options() { + local mount_point="$1" + local options="$2" + + mount -t tracefs -o "$options" nodev "$mount_point" + + setup +} + +unmount_tracefs() { + local mount_point="$1" + + # Need to make sure the mount isn't busy so that we can umount it + (cd $mount_point; finish_ftrace;) + + cleanup +} + +create_instance() { + local mount_point="$1" + local instance="$mount_point/instances/$(mktemp -u test-XXXXXX)" + + mkdir "$instance" + echo "$instance" +} + +remove_instance() { + local instance="$1" + + rmdir "$instance" +} + +check_gid() { + local mount_point="$1" + local expected_gid="$2" + + echo "Checking permission group ..." + + cd "$mount_point" + + for file in "." "events" "events/sched" "events/sched/sched_switch" "events/sched/sched_switch/enable"; do + local gid=`stat -c "%g" $file` + if [ "$gid" -ne "$expected_gid" ]; then + cd - # Return to the previous working directory (tracefs root) + fail "$(realpath $file): Expected group $expected_gid; Got group $gid" + fi + done + + cd - # Return to the previous working directory (tracefs root) +} + +test_gid_mount_option() { + local mount_point=$(get_mount_point) + local mount_options=$(get_mnt_options "$mount_point") + local original_group=$(stat -c "%g" .) + local other_group=$(find_alternate_gid "$original_group") + + # Set up mount options with new GID for testing + local new_options=`echo "$mount_options" | sed -e "s/gid=[0-9]*/gid=$other_group/"` + if [ "$new_options" = "$mount_options" ]; then + new_options="$mount_options,gid=$other_group" + mount_options="$mount_options,gid=$original_group" + fi + + # Unmount existing tracefs instance and mount with new GID + unmount_tracefs "$mount_point" + mount_tracefs_with_options "$mount_point" "$new_options" + + check_gid "$mount_point" "$other_group" + + # Check that files created after the mount inherit the GID + local instance=$(create_instance "$mount_point") + check_gid "$instance" "$other_group" + remove_instance "$instance" + + # Unmount and remount with the original GID + unmount_tracefs "$mount_point" + mount_tracefs_with_options "$mount_point" "$mount_options" + check_gid "$mount_point" "$original_group" +} + +test_gid_mount_option + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc index 094419e190c2..e71cc3ad0bdf 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc @@ -1,24 +1,14 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Test file and directory ownership changes for eventfs +# requires: "[gid=<gid>]":README original_group=`stat -c "%g" .` original_owner=`stat -c "%u" .` -mount_point=`stat -c '%m' .` +local mount_point=$(get_mount_point) -# If stat -c '%m' does not work (e.g. busybox) or failed, try to use the -# current working directory (which should be a tracefs) as the mount point. -if [ ! -d "$mount_point" ]; then - if mount | grep -qw $PWD ; then - mount_point=$PWD - else - # If PWD doesn't work, that is an environmental problem. - exit_unresolved - fi -fi - -mount_options=`mount | grep "$mount_point" | sed -e 's/.*(\(.*\)).*/\1/'` +mount_options=$(get_mnt_options "$mount_point") # find another owner and group that is not the original other_group=`tac /etc/group | grep -v ":$original_group:" | head -1 | cut -d: -f3` diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-profiler.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-profiler.tc new file mode 100644 index 000000000000..ffff8646733c --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-profiler.tc @@ -0,0 +1,31 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: ftrace - function profiler with function graph tracing +# requires: function_profile_enabled set_ftrace_filter function_graph:tracer + +# The function graph tracer can now be run along side of the function +# profiler. But there was a bug that caused the combination of the two +# to crash. It also required the function graph tracer to be started +# first. +# +# This test triggers that bug +# +# We need both function_graph and profiling to run this test + +fail() { # mesg + echo $1 + exit_fail +} + +echo "Enabling function graph tracer:" +echo function_graph > current_tracer +echo "enable profiler" + +# Older kernels do not allow function_profile to be enabled with +# function graph tracer. If the below fails, mark it as unsupported +echo 1 > function_profile_enabled || exit_unsupported + +# Let it run for a bit to make sure nothing explodes +sleep 1 + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 779f3e62ec90..84d6a9c7ad67 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -193,3 +193,28 @@ ftrace_errlog_check() { # err-prefix command-with-error-pos-by-^ command-file # " Command: " and "^\n" => 13 test $(expr 13 + $pos) -eq $N } + +# Helper to get the tracefs mount point +get_mount_point() { + local mount_point=`stat -c '%m' .` + + # If stat -c '%m' does not work (e.g. busybox) or failed, try to use the + # current working directory (which should be a tracefs) as the mount point. + if [ ! -d "$mount_point" ]; then + if mount | grep -qw "$PWD"; then + mount_point=$PWD + else + # If PWD doesn't work, that is an environmental problem. + exit_unresolved + fi + fi + echo "$mount_point" +} + +# Helper function to retrieve mount options for a given mount point +get_mnt_options() { + local mnt_point="$1" + local opts=$(mount | grep -m1 "$mnt_point" | sed -e 's/.*(\(.*\)).*/\1/') + + echo "$opts" +}
\ No newline at end of file diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 38ae31bb07b5..662209f5fabc 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -18,6 +18,7 @@ TEST_PROGS += hid-usb_crash.sh TEST_PROGS += hid-wacom.sh TEST_FILES := run-hid-tools-tests.sh +TEST_FILES += tests CXX ?= $(CROSS_COMPILE)g++ diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh index e7008f614ad7..6a3b8503264e 100755 --- a/tools/testing/selftests/intel_pstate/run.sh +++ b/tools/testing/selftests/intel_pstate/run.sh @@ -44,6 +44,11 @@ if [ $UID != 0 ] && [ $EVALUATE_ONLY == 0 ]; then exit $ksft_skip fi +if ! command -v cpupower &> /dev/null; then + echo $msg cpupower could not be found, please install it >&2 + exit $ksft_skip +fi + max_cpus=$(($(nproc)-1)) function run_test () { @@ -87,9 +92,9 @@ mkt_freq=${_mkt_freq}0 # Get the ranges from cpupower _min_freq=$(cpupower frequency-info -l | tail -1 | awk ' { print $1 } ') -min_freq=$(($_min_freq / 1000)) +min_freq=$((_min_freq / 1000)) _max_freq=$(cpupower frequency-info -l | tail -1 | awk ' { print $2 } ') -max_freq=$(($_max_freq / 1000)) +max_freq=$((_max_freq / 1000)) [ $EVALUATE_ONLY -eq 0 ] && for freq in `seq $max_freq -100 $min_freq` diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 960cf6a77198..48645a2e29da 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -241,13 +241,18 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ -fno-builtin-memcmp -fno-builtin-memcpy \ -fno-builtin-memset -fno-builtin-strnlen \ - -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ - -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ - -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \ - $(KHDR_INCLUDES) + -fno-stack-protector -fno-PIE -fno-strict-aliasing \ + -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_TOOL_ARCH_INCLUDE) \ + -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(ARCH_DIR) \ + -I ../rseq -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES) ifeq ($(ARCH),s390) CFLAGS += -march=z10 endif +ifeq ($(ARCH),x86) +ifeq ($(shell echo "void foo(void) { }" | $(CC) -march=x86-64-v2 -x c - -c -o /dev/null 2>/dev/null; echo "$$?"),0) + CFLAGS += -march=x86-64-v2 +endif +endif ifeq ($(ARCH),arm64) tools_dir := $(top_srcdir)/tools arm64_tools_dir := $(tools_dir)/arch/arm64/tools/ diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c index 2a3fe7914b72..b87e53580bfc 100644 --- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c @@ -68,6 +68,8 @@ struct test_feature_reg { } static const struct reg_ftr_bits ftr_id_aa64dfr0_el1[] = { + S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DoubleLock, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, WRPs, 0), S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, PMUVer, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DebugVer, ID_AA64DFR0_EL1_DebugVer_IMP), REG_FTR_END, @@ -134,6 +136,13 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = { REG_FTR_END, }; +static const struct reg_ftr_bits ftr_id_aa64pfr1_el1[] = { + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR1_EL1, CSV2_frac, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR1_EL1, SSBS, ID_AA64PFR1_EL1_SSBS_NI), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR1_EL1, BT, 0), + REG_FTR_END, +}; + static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ECV, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, EXS, 0), @@ -200,6 +209,7 @@ static struct test_feature_reg test_regs[] = { TEST_REG(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1_el1), TEST_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2_el1), TEST_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0_el1), + TEST_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1_el1), TEST_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0_el1), TEST_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1_el1), TEST_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2_el1), @@ -569,9 +579,9 @@ int main(void) test_cnt = ARRAY_SIZE(ftr_id_aa64dfr0_el1) + ARRAY_SIZE(ftr_id_dfr0_el1) + ARRAY_SIZE(ftr_id_aa64isar0_el1) + ARRAY_SIZE(ftr_id_aa64isar1_el1) + ARRAY_SIZE(ftr_id_aa64isar2_el1) + ARRAY_SIZE(ftr_id_aa64pfr0_el1) + - ARRAY_SIZE(ftr_id_aa64mmfr0_el1) + ARRAY_SIZE(ftr_id_aa64mmfr1_el1) + - ARRAY_SIZE(ftr_id_aa64mmfr2_el1) + ARRAY_SIZE(ftr_id_aa64zfr0_el1) - - ARRAY_SIZE(test_regs) + 2; + ARRAY_SIZE(ftr_id_aa64pfr1_el1) + ARRAY_SIZE(ftr_id_aa64mmfr0_el1) + + ARRAY_SIZE(ftr_id_aa64mmfr1_el1) + ARRAY_SIZE(ftr_id_aa64mmfr2_el1) + + ARRAY_SIZE(ftr_id_aa64zfr0_el1) - ARRAY_SIZE(test_regs) + 2; ksft_set_plan(test_cnt); diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index ba0c8e996035..ce687f8d248f 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -134,7 +134,7 @@ static void test_create_guest_memfd_invalid(struct kvm_vm *vm) size); } - for (flag = 0; flag; flag <<= 1) { + for (flag = BIT(0); flag; flag <<= 1) { fd = __vm_create_guest_memfd(vm, page_size, flag); TEST_ASSERT(fd == -1 && errno == EINVAL, "guest_memfd() with flag '0x%lx' should fail with EINVAL", diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 089b8925b6b2..d7ac122820bf 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -200,7 +200,7 @@ static inline void init_vmcs_control_fields(struct vmx_pages *vmx) if (vmx->eptp_gpa) { uint64_t ept_paddr; struct eptPageTablePointer eptp = { - .memory_type = VMX_BASIC_MEM_TYPE_WB, + .memory_type = X86_MEMTYPE_WB, .page_walk_length = 3, /* + 1 */ .ad_enabled = ept_vpid_cap_supported(VMX_EPT_VPID_CAP_AD_BITS), .address = vmx->eptp_gpa >> PAGE_SHIFT_4K, diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 989ffe0d047f..e3711beff7f3 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -417,7 +417,7 @@ static bool _guest_should_exit(void) */ static noinline void host_perform_sync(struct sync_area *sync) { - alarm(2); + alarm(10); atomic_store_explicit(&sync->sync_flag, true, memory_order_release); while (atomic_load_explicit(&sync->sync_flag, memory_order_acquire)) diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c index 8c579ce714e9..fec03b11b059 100644 --- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c @@ -60,7 +60,7 @@ static bool is_cpuid_mangled(const struct kvm_cpuid_entry2 *entrie) { int i; - for (i = 0; i < sizeof(mangled_cpuids); i++) { + for (i = 0; i < ARRAY_SIZE(mangled_cpuids); i++) { if (mangled_cpuids[i].function == entrie->function && mangled_cpuids[i].index == entrie->index) return true; diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index d2cfc9b494a0..141bf63cbe05 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -1657,7 +1657,7 @@ TEST_F(hmm2, double_map) buffer->fd = -1; buffer->size = size; - buffer->mirror = malloc(npages); + buffer->mirror = malloc(size); ASSERT_NE(buffer->mirror, NULL); /* Reserve a range of addresses. */ diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c index f9ac20c657ec..432d5af15e66 100644 --- a/tools/testing/selftests/mm/hugetlb_dio.c +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -94,8 +94,20 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) int main(void) { size_t pagesize = 0; + int fd; ksft_print_header(); + + /* Open the file to DIO */ + fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664); + if (fd < 0) + ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno)); + close(fd); + + /* Check if huge pages are free */ + if (!get_free_hugepages()) + ksft_exit_skip("No free hugepage, exiting\n"); + ksft_set_plan(4); /* Get base page size */ diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 56d4480e8d3c..8a4d34cce36b 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -1091,7 +1091,7 @@ static void usage(void) fprintf(stderr, "\n\t\"file,all\" mem_type requires kernel built with\n"); fprintf(stderr, "\tCONFIG_READ_ONLY_THP_FOR_FS=y\n"); fprintf(stderr, "\n\tif [dir] is a (sub)directory of a tmpfs mount, tmpfs must be\n"); - fprintf(stderr, "\tmounted with huge=madvise option for khugepaged tests to work\n"); + fprintf(stderr, "\tmounted with huge=advise option for khugepaged tests to work\n"); fprintf(stderr, "\n\tSupported Options:\n"); fprintf(stderr, "\t\t-h: This help message.\n"); fprintf(stderr, "\t\t-s: mTHP size, expressed as page order.\n"); diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index b3d21eed203d..a2e71b1636e7 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -241,6 +241,8 @@ static void *fork_event_consumer(void *data) fork_event_args *args = data; struct uffd_msg msg = { 0 }; + ready_for_fork = true; + /* Read until a full msg received */ while (uffd_read_msg(args->parent_uffd, &msg)); @@ -308,8 +310,11 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) /* Prepare a thread to resolve EVENT_FORK */ if (with_event) { + ready_for_fork = false; if (pthread_create(&thread, NULL, fork_event_consumer, &args)) err("pthread_create()"); + while (!ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ } child = fork(); diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index c6a8c732b802..68801e1a9ec2 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -1414,6 +1414,13 @@ TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid) ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/b", 0, 0, 0), 0); ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/BB/b", 0, 0, 0), 0); + ASSERT_EQ(mount("testing", "/mnt/A", "ramfs", MS_NOATIME | MS_NODEV, + "size=100000,mode=700"), 0); + + ASSERT_EQ(mkdir("/mnt/A/AA", 0777), 0); + + ASSERT_EQ(mount("/tmp", "/mnt/A/AA", NULL, MS_BIND | MS_REC, NULL), 0); + open_tree_fd = sys_open_tree(-EBADF, "/mnt/A", AT_RECURSIVE | AT_EMPTY_PATH | @@ -1433,6 +1440,8 @@ TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid) ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/BB/b", 0, 0, 0), 0); ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/b", 0, 0, 0), 0); ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/BB/b", 0, 0, 0), 0); + + (void)umount2("/mnt/A", MNT_DETACH); } TEST_F(mount_setattr, mount_attr_nosymfollow) diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 1c04c780db66..59fe07ee2df9 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -16,8 +16,10 @@ ipsec ipv6_flowlabel ipv6_flowlabel_mgr log.txt +msg_oob msg_zerocopy ncdevmem +netlink-dumps nettest psock_fanout psock_snd diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 649f1fe0dc46..5e86f7a51b43 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -78,6 +78,7 @@ TEST_PROGS += test_vxlan_vnifiltering.sh TEST_GEN_FILES += io_uring_zerocopy_tx TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash +TEST_GEN_PROGS += netlink-dumps TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_GEN_PROGS += sk_so_peek_off diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh index 96c97064f2d3..becc7c3fc809 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh index ff9fb0db9bd1..e5335116a2fd 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh index 12c138785242..7e0cbfdefab0 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh index 83b55c30a5c3..e0844495f3d1 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh index 256607916d92..741bc9c928eb 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh index ad1bcd6334a8..ad9eab4b1367 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh index 24f4ab328bd2..2d91281dc5b7 100644 --- a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh @@ -436,3 +436,83 @@ test_mtu_change() check_err $? log_test "ping GRE IPv6, packet size 1800 after MTU change" } + +topo_flat_remote_change() +{ + local old1=$1; shift + local new1=$1; shift + local old2=$1; shift + local new2=$1; shift + + ip link set dev g1a type ip6gre local $new1 remote $new2 + __addr_add_del g1a add "$new1/128" + __addr_add_del g1a del "$old1/128" + ip -6 route add $new2/128 via 2001:db8:10::2 + ip -6 route del $old2/128 + + ip link set dev g2a type ip6gre local $new2 remote $new1 + __addr_add_del g2a add "$new2/128" + __addr_add_del g2a del "$old2/128" + ip -6 route add vrf v$ol2 $new1/128 via 2001:db8:10::1 + ip -6 route del vrf v$ol2 $old1/128 +} + +flat_remote_change() +{ + local old1=2001:db8:3::1 + local new1=2001:db8:3::10 + local old2=2001:db8:3::2 + local new2=2001:db8:3::20 + + topo_flat_remote_change $old1 $new1 $old2 $new2 +} + +flat_remote_restore() +{ + local old1=2001:db8:3::10 + local new1=2001:db8:3::1 + local old2=2001:db8:3::20 + local new2=2001:db8:3::2 + + topo_flat_remote_change $old1 $new1 $old2 $new2 +} + +topo_hier_remote_change() +{ + local old1=$1; shift + local new1=$1; shift + local old2=$1; shift + local new2=$1; shift + + __addr_add_del dummy1 del "$old1/64" + __addr_add_del dummy1 add "$new1/64" + ip link set dev g1a type ip6gre local $new1 remote $new2 + ip -6 route add vrf v$ul1 $new2/128 via 2001:db8:10::2 + ip -6 route del vrf v$ul1 $old2/128 + + __addr_add_del dummy2 del "$old2/64" + __addr_add_del dummy2 add "$new2/64" + ip link set dev g2a type ip6gre local $new2 remote $new1 + ip -6 route add vrf v$ul2 $new1/128 via 2001:db8:10::1 + ip -6 route del vrf v$ul2 $old1/128 +} + +hier_remote_change() +{ + local old1=2001:db8:3::1 + local new1=2001:db8:3::10 + local old2=2001:db8:3::2 + local new2=2001:db8:3::20 + + topo_hier_remote_change $old1 $new1 $old2 $new2 +} + +hier_remote_restore() +{ + local old1=2001:db8:3::10 + local new1=2001:db8:3::1 + local old2=2001:db8:3::20 + local new2=2001:db8:3::2 + + topo_hier_remote_change $old1 $new1 $old2 $new2 +} diff --git a/tools/testing/selftests/net/forwarding/no_forwarding.sh b/tools/testing/selftests/net/forwarding/no_forwarding.sh index 9e677aa64a06..694ece9ba3a7 100755 --- a/tools/testing/selftests/net/forwarding/no_forwarding.sh +++ b/tools/testing/selftests/net/forwarding/no_forwarding.sh @@ -202,7 +202,7 @@ one_bridge_two_pvids() ip link set $swp2 master br0 bridge vlan add dev $swp1 vid 1 pvid untagged - bridge vlan add dev $swp1 vid 2 pvid untagged + bridge vlan add dev $swp2 vid 2 pvid untagged run_test "Switch ports in VLAN-aware bridge with different PVIDs" diff --git a/tools/testing/selftests/net/lib/py/nsim.py b/tools/testing/selftests/net/lib/py/nsim.py index f571a8b3139b..1a8cbe9acc48 100644 --- a/tools/testing/selftests/net/lib/py/nsim.py +++ b/tools/testing/selftests/net/lib/py/nsim.py @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +import errno import json import os import random diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 57325d57e4c6..b48b4e56826a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -259,6 +259,15 @@ check_mptcp_disabled() mptcp_lib_ns_init disabled_ns print_larger_title "New MPTCP socket can be blocked via sysctl" + + # mainly to cover more code + if ! ip netns exec ${disabled_ns} sysctl net.mptcp >/dev/null; then + mptcp_lib_pr_fail "not able to list net.mptcp sysctl knobs" + mptcp_lib_result_fail "not able to list net.mptcp sysctl knobs" + ret=${KSFT_FAIL} + return 1 + fi + # net.mptcp.enabled should be enabled by default if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then mptcp_lib_pr_fail "net.mptcp.enabled sysctl is not 1 by default" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index e8d0a01b4144..c07e2bd3a315 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -23,6 +23,7 @@ tmpfile="" cout="" err="" capout="" +cappid="" ns1="" ns2="" iptables="iptables" @@ -887,40 +888,62 @@ check_cestab() fi } -do_transfer() +cond_start_capture() { - local listener_ns="$1" - local connector_ns="$2" - local cl_proto="$3" - local srv_proto="$4" - local connect_addr="$5" - - local port=$((10000 + MPTCP_LIB_TEST_COUNTER - 1)) - local cappid - local FAILING_LINKS=${FAILING_LINKS:-""} - local fastclose=${fastclose:-""} - local speed=${speed:-"fast"} + local ns="$1" - :> "$cout" - :> "$sout" :> "$capout" if $capture; then - local capuser - if [ -z $SUDO_USER ] ; then + local capuser capfile + if [ -z $SUDO_USER ]; then capuser="" else capuser="-Z $SUDO_USER" fi - capfile=$(printf "mp_join-%02u-%s.pcap" "$MPTCP_LIB_TEST_COUNTER" "${listener_ns}") + capfile=$(printf "mp_join-%02u-%s.pcap" "$MPTCP_LIB_TEST_COUNTER" "$ns") echo "Capturing traffic for test $MPTCP_LIB_TEST_COUNTER into $capfile" - ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & + ip netns exec "$ns" tcpdump -i any -s 65535 -B 32768 $capuser -w "$capfile" > "$capout" 2>&1 & cappid=$! sleep 1 fi +} + +cond_stop_capture() +{ + if $capture; then + sleep 1 + kill $cappid + cat "$capout" + fi +} + +get_port() +{ + echo "$((10000 + MPTCP_LIB_TEST_COUNTER - 1))" +} + +do_transfer() +{ + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local port + + local FAILING_LINKS=${FAILING_LINKS:-""} + local fastclose=${fastclose:-""} + local speed=${speed:-"fast"} + port=$(get_port) + + :> "$cout" + :> "$sout" + + cond_start_capture ${listener_ns} NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ nstat -n @@ -1007,10 +1030,7 @@ do_transfer() wait $spid local rets=$? - if $capture; then - sleep 1 - kill $cappid - fi + cond_stop_capture NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ nstat | grep Tcp > /tmp/${listener_ns}.out @@ -1026,7 +1046,6 @@ do_transfer() ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" cat /tmp/${connector_ns}.out - cat "$capout" return 1 fi @@ -1043,13 +1062,7 @@ do_transfer() fi rets=$? - if [ $retc -eq 0 ] && [ $rets -eq 0 ];then - cat "$capout" - return 0 - fi - - cat "$capout" - return 1 + [ $retc -eq 0 ] && [ $rets -eq 0 ] } make_file() @@ -2873,6 +2886,32 @@ verify_listener_events() fail_test } +chk_mpc_endp_attempt() +{ + local retl=$1 + local attempts=$2 + + print_check "Connect" + + if [ ${retl} = 124 ]; then + fail_test "timeout on connect" + elif [ ${retl} = 0 ]; then + fail_test "unexpected successful connect" + else + print_ok + + print_check "Attempts" + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPCapableEndpAttempt") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$attempts" ]; then + fail_test "got ${count} MPC attempt[s] on port-based endpoint, expected ${attempts}" + else + print_ok + fi + fi +} + add_addr_ports_tests() { # signal address with port @@ -2963,6 +3002,22 @@ add_addr_ports_tests() chk_join_nr 2 2 2 chk_add_nr 2 2 2 fi + + if reset "port-based signal endpoint must not accept mpc"; then + local port retl count + port=$(get_port) + + cond_start_capture ${ns1} + pm_nl_add_endpoint ${ns1} 10.0.2.1 flags signal port ${port} + mptcp_lib_wait_local_port_listen ${ns1} ${port} + + timeout 1 ip netns exec ${ns2} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s MPTCP 10.0.2.1 >/dev/null 2>&1 + retl=$? + cond_stop_capture + + chk_mpc_endp_attempt ${retl} 1 + fi } syncookies_tests() diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index e6c9e777fead..542f7886a0bc 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -31,6 +31,7 @@ TEST_PROGS += nft_tproxy_tcp.sh TEST_PROGS += nft_tproxy_udp.sh TEST_PROGS += nft_zones_many.sh TEST_PROGS += rpath.sh +TEST_PROGS += vxlan_mtu_frag.sh TEST_PROGS += xt_string.sh TEST_PROGS_EXTENDED = nft_concat_range_perf.sh diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config index c5fe7b34eaf1..43d8b500d391 100644 --- a/tools/testing/selftests/net/netfilter/config +++ b/tools/testing/selftests/net/netfilter/config @@ -7,6 +7,7 @@ CONFIG_BRIDGE_EBT_REDIRECT=m CONFIG_BRIDGE_EBT_T_FILTER=m CONFIG_BRIDGE_NETFILTER=m CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_CGROUP_BPF=y CONFIG_DUMMY=m CONFIG_INET_ESP=m @@ -84,6 +85,7 @@ CONFIG_NFT_SYNPROXY=m CONFIG_NFT_TPROXY=m CONFIG_VETH=m CONFIG_VLAN_8021Q=m +CONFIG_VXLAN=m CONFIG_XFRM_USER=m CONFIG_XFRM_STATISTICS=y CONFIG_NET_PKTGEN=m diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c index dc056fec993b..254ff03297f0 100644 --- a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c +++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c @@ -98,7 +98,7 @@ static int conntrack_data_insert(struct mnl_socket *sock, struct nlmsghdr *nlh, char buf[MNL_SOCKET_BUFFER_SIZE]; struct nlmsghdr *rplnlh; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); @@ -217,7 +217,7 @@ static int conntracK_count_zone(struct mnl_socket *sock, uint16_t zone) struct nfgenmsg *nfh; struct nlattr *nest; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); @@ -264,7 +264,7 @@ static int conntrack_flush_zone(struct mnl_socket *sock, uint16_t zone) struct nfgenmsg *nfh; struct nlattr *nest; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); diff --git a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh index 073e8e62d350..e95ecb37c2b1 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh @@ -32,6 +32,7 @@ source lib.sh IP0=172.30.30.1 IP1=172.30.30.2 +DUMMYNET=10.9.9 PFXL=30 ret=0 @@ -54,6 +55,7 @@ setup_ns ns0 ns1 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 netns exec "$ns0" sysctl -q -w net.ipv4.conf.all.forwarding=1 if ! ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1; then echo "SKIP: Could not add veth device" @@ -65,13 +67,18 @@ if ! ip -net "$ns0" li add tvrf type vrf table 9876; then exit $ksft_skip fi +ip -net "$ns0" link add dummy0 type dummy + ip -net "$ns0" li set veth0 master tvrf +ip -net "$ns0" li set dummy0 master tvrf ip -net "$ns0" li set tvrf up ip -net "$ns0" li set veth0 up +ip -net "$ns0" li set dummy0 up ip -net "$ns1" li set veth0 up ip -net "$ns0" addr add $IP0/$PFXL dev veth0 ip -net "$ns1" addr add $IP1/$PFXL dev veth0 +ip -net "$ns0" addr add $DUMMYNET.1/$PFXL dev dummy0 listener_ready() { @@ -212,9 +219,35 @@ EOF fi } +test_fib() +{ +ip netns exec "$ns0" nft -f - <<EOF +flush ruleset +table ip t { + counter fibcount { } + + chain prerouting { + type filter hook prerouting priority 0; + meta iifname veth0 ip daddr $DUMMYNET.2 fib daddr oif dummy0 counter name fibcount notrack + } +} +EOF + ip -net "$ns1" route add 10.9.9.0/24 via "$IP0" dev veth0 + ip netns exec "$ns1" ping -q -w 1 -c 1 "$DUMMYNET".2 > /dev/null + + if ip netns exec "$ns0" nft list counter t fibcount | grep -q "packets 1"; then + echo "PASS: fib lookup returned exepected output interface" + else + echo "FAIL: fib lookup did not return exepected output interface" + ret=1 + return + fi +} + test_ct_zone_in test_masquerade_vrf "default" test_masquerade_vrf "pfifo" test_masquerade_veth +test_fib exit $ret diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index b3995550856a..a4ee5496f2a1 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -71,6 +71,8 @@ omtu=9000 lmtu=1500 rmtu=2000 +filesize=$((2 * 1024 * 1024)) + usage(){ echo "nft_flowtable.sh [OPTIONS]" echo @@ -81,12 +83,13 @@ usage(){ exit 1 } -while getopts "o:l:r:" o +while getopts "o:l:r:s:" o do case $o in o) omtu=$OPTARG;; l) lmtu=$OPTARG;; r) rmtu=$OPTARG;; + s) filesize=$OPTARG;; *) usage;; esac done @@ -217,18 +220,10 @@ ns2out=$(mktemp) make_file() { - name=$1 - - SIZE=$((RANDOM % (1024 * 128))) - SIZE=$((SIZE + (1024 * 8))) - TSIZE=$((SIZE * 1024)) - - dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null + name="$1" + sz="$2" - SIZE=$((RANDOM % 1024)) - SIZE=$((SIZE + 128)) - TSIZE=$((TSIZE + SIZE)) - dd if=/dev/urandom conf=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null + head -c "$sz" < /dev/urandom > "$name" } check_counters() @@ -246,18 +241,18 @@ check_counters() local fs fs=$(du -sb "$nsin") local max_orig=${fs%%/*} - local max_repl=$((max_orig/4)) + local max_repl=$((max_orig)) # flowtable fastpath should bypass normal routing one, i.e. the counters in forward hook # should always be lower than the size of the transmitted file (max_orig). if [ "$orig_cnt" -gt "$max_orig" ];then - echo "FAIL: $what: original counter $orig_cnt exceeds expected value $max_orig" 1>&2 + echo "FAIL: $what: original counter $orig_cnt exceeds expected value $max_orig, reply counter $repl_cnt" 1>&2 ret=1 ok=0 fi if [ "$repl_cnt" -gt $max_repl ];then - echo "FAIL: $what: reply counter $repl_cnt exceeds expected value $max_repl" 1>&2 + echo "FAIL: $what: reply counter $repl_cnt exceeds expected value $max_repl, original counter $orig_cnt" 1>&2 ret=1 ok=0 fi @@ -455,7 +450,7 @@ test_tcp_forwarding_nat() return $lret } -make_file "$nsin" +make_file "$nsin" "$filesize" # First test: # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed. @@ -664,8 +659,16 @@ if [ "$1" = "" ]; then l=$(((RANDOM%mtu) + low)) r=$(((RANDOM%mtu) + low)) - echo "re-run with random mtus: -o $o -l $l -r $r" - $0 -o "$o" -l "$l" -r "$r" + MINSIZE=$((2 * 1000 * 1000)) + MAXSIZE=$((64 * 1000 * 1000)) + + filesize=$(((RANDOM * RANDOM) % MAXSIZE)) + if [ "$filesize" -lt "$MINSIZE" ]; then + filesize=$((filesize+MINSIZE)) + fi + + echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize" + $0 -o "$o" -l "$l" -r "$r" -s "$filesize" fi exit $ret diff --git a/tools/testing/selftests/net/netfilter/vxlan_mtu_frag.sh b/tools/testing/selftests/net/netfilter/vxlan_mtu_frag.sh new file mode 100755 index 000000000000..912cb9583af1 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/vxlan_mtu_frag.sh @@ -0,0 +1,121 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +if ! modprobe -q -n br_netfilter 2>&1; then + echo "SKIP: Test needs br_netfilter kernel module" + exit $ksft_skip +fi + +cleanup() +{ + cleanup_all_ns +} + +trap cleanup EXIT + +setup_ns host vtep router + +create_topology() +{ + ip link add host-eth0 netns "$host" type veth peer name vtep-host netns "$vtep" + ip link add vtep-router netns "$vtep" type veth peer name router-vtep netns "$router" +} + +setup_host() +{ + # bring ports up + ip -n "$host" addr add 10.0.0.1/24 dev host-eth0 + ip -n "$host" link set host-eth0 up + + # Add VLAN 10,20 + for vid in 10 20; do + ip -n "$host" link add link host-eth0 name host-eth0.$vid type vlan id $vid + ip -n "$host" addr add 10.0.$vid.1/24 dev host-eth0.$vid + ip -n "$host" link set host-eth0.$vid up + done +} + +setup_vtep() +{ + # create bridge on vtep + ip -n "$vtep" link add name br0 type bridge + ip -n "$vtep" link set br0 type bridge vlan_filtering 1 + + # VLAN 10 is untagged PVID + ip -n "$vtep" link set dev vtep-host master br0 + bridge -n "$vtep" vlan add dev vtep-host vid 10 pvid untagged + + # VLAN 20 as other VID + ip -n "$vtep" link set dev vtep-host master br0 + bridge -n "$vtep" vlan add dev vtep-host vid 20 + + # single-vxlan device on vtep + ip -n "$vtep" address add dev vtep-router 60.0.0.1/24 + ip -n "$vtep" link add dev vxd type vxlan external \ + vnifilter local 60.0.0.1 remote 60.0.0.2 dstport 4789 ttl 64 + ip -n "$vtep" link set vxd master br0 + + # Add VLAN-VNI 1-1 mappings + bridge -n "$vtep" link set dev vxd vlan_tunnel on + for vid in 10 20; do + bridge -n "$vtep" vlan add dev vxd vid $vid + bridge -n "$vtep" vlan add dev vxd vid $vid tunnel_info id $vid + bridge -n "$vtep" vni add dev vxd vni $vid + done + + # bring ports up + ip -n "$vtep" link set vxd up + ip -n "$vtep" link set vtep-router up + ip -n "$vtep" link set vtep-host up + ip -n "$vtep" link set dev br0 up +} + +setup_router() +{ + # bring ports up + ip -n "$router" link set router-vtep up +} + +setup() +{ + modprobe -q br_netfilter + create_topology + setup_host + setup_vtep + setup_router +} + +test_large_mtu_untagged_traffic() +{ + ip -n "$vtep" link set vxd mtu 1000 + ip -n "$host" neigh add 10.0.0.2 lladdr ca:fe:ba:be:00:01 dev host-eth0 + ip netns exec "$host" \ + ping -q 10.0.0.2 -I host-eth0 -c 1 -W 0.5 -s2000 > /dev/null 2>&1 + return 0 +} + +test_large_mtu_tagged_traffic() +{ + for vid in 10 20; do + ip -n "$vtep" link set vxd mtu 1000 + ip -n "$host" neigh add 10.0.$vid.2 lladdr ca:fe:ba:be:00:01 dev host-eth0.$vid + ip netns exec "$host" \ + ping -q 10.0.$vid.2 -I host-eth0.$vid -c 1 -W 0.5 -s2000 > /dev/null 2>&1 + done + return 0 +} + +do_test() +{ + # Frames will be dropped so ping will not succeed + # If it doesn't panic, it passes + test_large_mtu_tagged_traffic + test_large_mtu_untagged_traffic +} + +setup && \ +echo "Test for VxLAN fragmentation with large MTU in br_netfilter:" && \ +do_test && echo "PASS!" +exit $? diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c new file mode 100644 index 000000000000..7ee6dcd334df --- /dev/null +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <fcntl.h> +#include <stdio.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <unistd.h> + +#include <linux/genetlink.h> +#include <linux/netlink.h> +#include <linux/mqueue.h> + +#include "../kselftest_harness.h" + +static const struct { + struct nlmsghdr nlhdr; + struct genlmsghdr genlhdr; + struct nlattr ahdr; + __u16 val; + __u16 pad; +} dump_policies = { + .nlhdr = { + .nlmsg_len = sizeof(dump_policies), + .nlmsg_type = GENL_ID_CTRL, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP, + .nlmsg_seq = 1, + }, + .genlhdr = { + .cmd = CTRL_CMD_GETPOLICY, + .version = 2, + }, + .ahdr = { + .nla_len = 6, + .nla_type = CTRL_ATTR_FAMILY_ID, + }, + .val = GENL_ID_CTRL, + .pad = 0, +}; + +// Sanity check for the test itself, make sure the dump doesn't fit in one msg +TEST(test_sanity) +{ + int netlink_sock; + char buf[8192]; + ssize_t n; + + netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + ASSERT_GE(netlink_sock, 0); + + n = send(netlink_sock, &dump_policies, sizeof(dump_policies), 0); + ASSERT_EQ(n, sizeof(dump_policies)); + + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + ASSERT_GE(n, sizeof(struct nlmsghdr)); + + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + ASSERT_GE(n, sizeof(struct nlmsghdr)); + + close(netlink_sock); +} + +TEST(close_in_progress) +{ + int netlink_sock; + ssize_t n; + + netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + ASSERT_GE(netlink_sock, 0); + + n = send(netlink_sock, &dump_policies, sizeof(dump_policies), 0); + ASSERT_EQ(n, sizeof(dump_policies)); + + close(netlink_sock); +} + +TEST(close_with_ref) +{ + char cookie[NOTIFY_COOKIE_LEN] = {}; + int netlink_sock, mq_fd; + struct sigevent sigev; + ssize_t n; + + netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + ASSERT_GE(netlink_sock, 0); + + n = send(netlink_sock, &dump_policies, sizeof(dump_policies), 0); + ASSERT_EQ(n, sizeof(dump_policies)); + + mq_fd = syscall(__NR_mq_open, "sed", O_CREAT | O_WRONLY, 0600, 0); + ASSERT_GE(mq_fd, 0); + + memset(&sigev, 0, sizeof(sigev)); + sigev.sigev_notify = SIGEV_THREAD; + sigev.sigev_value.sival_ptr = cookie; + sigev.sigev_signo = netlink_sock; + + syscall(__NR_mq_notify, mq_fd, &sigev); + + close(netlink_sock); + + // give mqueue time to fire + usleep(100 * 1000); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/rds/.gitignore b/tools/testing/selftests/net/rds/.gitignore new file mode 100644 index 000000000000..1c6f04e2aa11 --- /dev/null +++ b/tools/testing/selftests/net/rds/.gitignore @@ -0,0 +1 @@ +include.sh diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile index cf30307a829b..1803c39dbacb 100644 --- a/tools/testing/selftests/net/rds/Makefile +++ b/tools/testing/selftests/net/rds/Makefile @@ -8,6 +8,6 @@ TEST_PROGS := run.sh \ TEST_FILES := include.sh -EXTRA_CLEAN := /tmp/rds_logs +EXTRA_CLEAN := /tmp/rds_logs include.sh include ../../lib.mk diff --git a/tools/testing/selftests/net/rds/test.py b/tools/testing/selftests/net/rds/test.py index e6bb109bcead..4a7178d11193 100755 --- a/tools/testing/selftests/net/rds/test.py +++ b/tools/testing/selftests/net/rds/test.py @@ -14,8 +14,11 @@ import sys import atexit from pwd import getpwuid from os import stat -from lib.py import ip +# Allow utils module to be imported from different directory +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.append(os.path.join(this_dir, "../")) +from lib.py.utils import ip libc = ctypes.cdll.LoadLibrary('libc.so.6') setns = libc.setns diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk index 59cb26cf3f73..1ef24119def0 100644 --- a/tools/testing/selftests/net/ynl.mk +++ b/tools/testing/selftests/net/ynl.mk @@ -19,3 +19,7 @@ $(YNL_OUTPUTS): CFLAGS += \ $(OUTPUT)/libynl.a: $(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl GENS="$(YNL_GENS)" libynl.a $(Q)cp $(top_srcdir)/tools/net/ynl/libynl.a $(OUTPUT)/libynl.a + +EXTRA_CLEAN += \ + $(top_srcdir)/tools/net/ynl/lib/__pycache__ \ + $(top_srcdir)/tools/net/ynl/lib/*.[ado] diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 96e812bdf8a4..5b9772cdf265 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -60,12 +60,6 @@ unsigned int rseq_size = -1U; /* Flags used during rseq registration. */ unsigned int rseq_flags; -/* - * rseq feature size supported by the kernel. 0 if the registration was - * unsuccessful. - */ -unsigned int rseq_feature_size = -1U; - static int rseq_ownership; static int rseq_reg_success; /* At least one rseq registration has succeded. */ @@ -111,6 +105,43 @@ int rseq_available(void) } } +/* The rseq areas need to be at least 32 bytes. */ +static +unsigned int get_rseq_min_alloc_size(void) +{ + unsigned int alloc_size = rseq_size; + + if (alloc_size < ORIG_RSEQ_ALLOC_SIZE) + alloc_size = ORIG_RSEQ_ALLOC_SIZE; + return alloc_size; +} + +/* + * Return the feature size supported by the kernel. + * + * Depending on the value returned by getauxval(AT_RSEQ_FEATURE_SIZE): + * + * 0: Return ORIG_RSEQ_FEATURE_SIZE (20) + * > 0: Return the value from getauxval(AT_RSEQ_FEATURE_SIZE). + * + * It should never return a value below ORIG_RSEQ_FEATURE_SIZE. + */ +static +unsigned int get_rseq_kernel_feature_size(void) +{ + unsigned long auxv_rseq_feature_size, auxv_rseq_align; + + auxv_rseq_align = getauxval(AT_RSEQ_ALIGN); + assert(!auxv_rseq_align || auxv_rseq_align <= RSEQ_THREAD_AREA_ALLOC_SIZE); + + auxv_rseq_feature_size = getauxval(AT_RSEQ_FEATURE_SIZE); + assert(!auxv_rseq_feature_size || auxv_rseq_feature_size <= RSEQ_THREAD_AREA_ALLOC_SIZE); + if (auxv_rseq_feature_size) + return auxv_rseq_feature_size; + else + return ORIG_RSEQ_FEATURE_SIZE; +} + int rseq_register_current_thread(void) { int rc; @@ -119,7 +150,7 @@ int rseq_register_current_thread(void) /* Treat libc's ownership as a successful registration. */ return 0; } - rc = sys_rseq(&__rseq_abi, rseq_size, 0, RSEQ_SIG); + rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); if (rc) { if (RSEQ_READ_ONCE(rseq_reg_success)) { /* Incoherent success/failure within process. */ @@ -140,28 +171,12 @@ int rseq_unregister_current_thread(void) /* Treat libc's ownership as a successful unregistration. */ return 0; } - rc = sys_rseq(&__rseq_abi, rseq_size, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); if (rc) return -1; return 0; } -static -unsigned int get_rseq_feature_size(void) -{ - unsigned long auxv_rseq_feature_size, auxv_rseq_align; - - auxv_rseq_align = getauxval(AT_RSEQ_ALIGN); - assert(!auxv_rseq_align || auxv_rseq_align <= RSEQ_THREAD_AREA_ALLOC_SIZE); - - auxv_rseq_feature_size = getauxval(AT_RSEQ_FEATURE_SIZE); - assert(!auxv_rseq_feature_size || auxv_rseq_feature_size <= RSEQ_THREAD_AREA_ALLOC_SIZE); - if (auxv_rseq_feature_size) - return auxv_rseq_feature_size; - else - return ORIG_RSEQ_FEATURE_SIZE; -} - static __attribute__((constructor)) void rseq_init(void) { @@ -178,28 +193,54 @@ void rseq_init(void) } if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p && *libc_rseq_size_p != 0) { + unsigned int libc_rseq_size; + /* rseq registration owned by glibc */ rseq_offset = *libc_rseq_offset_p; - rseq_size = *libc_rseq_size_p; + libc_rseq_size = *libc_rseq_size_p; rseq_flags = *libc_rseq_flags_p; - rseq_feature_size = get_rseq_feature_size(); - if (rseq_feature_size > rseq_size) - rseq_feature_size = rseq_size; + + /* + * Previous versions of glibc expose the value + * 32 even though the kernel only supported 20 + * bytes initially. Therefore treat 32 as a + * special-case. glibc 2.40 exposes a 20 bytes + * __rseq_size without using getauxval(3) to + * query the supported size, while still allocating a 32 + * bytes area. Also treat 20 as a special-case. + * + * Special-cases are handled by using the following + * value as active feature set size: + * + * rseq_size = min(32, get_rseq_kernel_feature_size()) + */ + switch (libc_rseq_size) { + case ORIG_RSEQ_FEATURE_SIZE: + fallthrough; + case ORIG_RSEQ_ALLOC_SIZE: + { + unsigned int rseq_kernel_feature_size = get_rseq_kernel_feature_size(); + + if (rseq_kernel_feature_size < ORIG_RSEQ_ALLOC_SIZE) + rseq_size = rseq_kernel_feature_size; + else + rseq_size = ORIG_RSEQ_ALLOC_SIZE; + break; + } + default: + /* Otherwise just use the __rseq_size from libc as rseq_size. */ + rseq_size = libc_rseq_size; + break; + } return; } rseq_ownership = 1; if (!rseq_available()) { rseq_size = 0; - rseq_feature_size = 0; return; } rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); rseq_flags = 0; - rseq_feature_size = get_rseq_feature_size(); - if (rseq_feature_size == ORIG_RSEQ_FEATURE_SIZE) - rseq_size = ORIG_RSEQ_ALLOC_SIZE; - else - rseq_size = RSEQ_THREAD_AREA_ALLOC_SIZE; } static __attribute__((destructor)) @@ -209,7 +250,6 @@ void rseq_exit(void) return; rseq_offset = 0; rseq_size = -1U; - rseq_feature_size = -1U; rseq_ownership = 0; } diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index d7364ea4d201..4e217b620e0c 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -68,12 +68,6 @@ extern unsigned int rseq_size; /* Flags used during rseq registration. */ extern unsigned int rseq_flags; -/* - * rseq feature size supported by the kernel. 0 if the registration was - * unsuccessful. - */ -extern unsigned int rseq_feature_size; - enum rseq_mo { RSEQ_MO_RELAXED = 0, RSEQ_MO_CONSUME = 1, /* Unused */ @@ -193,7 +187,7 @@ static inline uint32_t rseq_current_cpu(void) static inline bool rseq_node_id_available(void) { - return (int) rseq_feature_size >= rseq_offsetofend(struct rseq_abi, node_id); + return (int) rseq_size >= rseq_offsetofend(struct rseq_abi, node_id); } /* @@ -207,7 +201,7 @@ static inline uint32_t rseq_current_node_id(void) static inline bool rseq_mm_cid_available(void) { - return (int) rseq_feature_size >= rseq_offsetofend(struct rseq_abi, mm_cid); + return (int) rseq_size >= rseq_offsetofend(struct rseq_abi, mm_cid); } static inline uint32_t rseq_current_mm_cid(void) diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 0754a2c110a1..011762224600 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -3,23 +3,12 @@ include ../../../build/Build.include include ../../../scripts/Makefile.arch include ../../../scripts/Makefile.include -include ../lib.mk -ifneq ($(LLVM),) -ifneq ($(filter %/,$(LLVM)),) -LLVM_PREFIX := $(LLVM) -else ifneq ($(filter -%,$(LLVM)),) -LLVM_SUFFIX := $(LLVM) -endif - -CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as -else -CC := gcc -endif # LLVM +TEST_GEN_PROGS := runner -ifneq ($(CROSS_COMPILE),) -$(error CROSS_COMPILE not supported for scx selftests) -endif # CROSS_COMPILE +# override lib.mk's default rules +OVERRIDE_TARGETS := 1 +include ../lib.mk CURDIR := $(abspath .) REPOROOT := $(abspath ../../../..) @@ -34,18 +23,23 @@ GENHDR := $(GENDIR)/autoconf.h SCXTOOLSDIR := $(TOOLSDIR)/sched_ext SCXTOOLSINCDIR := $(TOOLSDIR)/sched_ext/include -OUTPUT_DIR := $(CURDIR)/build +OUTPUT_DIR := $(OUTPUT)/build OBJ_DIR := $(OUTPUT_DIR)/obj INCLUDE_DIR := $(OUTPUT_DIR)/include BPFOBJ_DIR := $(OBJ_DIR)/libbpf SCXOBJ_DIR := $(OBJ_DIR)/sched_ext BPFOBJ := $(BPFOBJ_DIR)/libbpf.a LIBBPF_OUTPUT := $(OBJ_DIR)/libbpf/libbpf.a -DEFAULT_BPFTOOL := $(OUTPUT_DIR)/sbin/bpftool -HOST_BUILD_DIR := $(OBJ_DIR) -HOST_OUTPUT_DIR := $(OUTPUT_DIR) -VMLINUX_BTF_PATHS ?= ../../../../vmlinux \ +DEFAULT_BPFTOOL := $(OUTPUT_DIR)/host/sbin/bpftool +HOST_OBJ_DIR := $(OBJ_DIR)/host/bpftool +HOST_LIBBPF_OUTPUT := $(OBJ_DIR)/host/libbpf/ +HOST_LIBBPF_DESTDIR := $(OUTPUT_DIR)/host/ +HOST_DESTDIR := $(OUTPUT_DIR)/host/ + +VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ + $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ + ../../../../vmlinux \ /sys/kernel/btf/vmlinux \ /boot/vmlinux-$(shell uname -r) VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) @@ -80,17 +74,23 @@ IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ # Use '-idirafter': Don't interfere with include mechanics except where the # build would have failed anyways. define get_sys_includes -$(shell $(1) -v -E - </dev/null 2>&1 \ +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ -$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') endef +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) + BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ $(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) \ -I$(CURDIR)/include -I$(CURDIR)/include/bpf-compat \ -I$(INCLUDE_DIR) -I$(APIDIR) -I$(SCXTOOLSINCDIR) \ -I$(REPOROOT)/include \ - $(call get_sys_includes,$(CLANG)) \ + $(CLANG_SYS_INCLUDES) \ -Wall -Wno-compare-distinct-pointer-types \ -Wno-incompatible-function-pointer-types \ -O2 -mcpu=v3 @@ -98,7 +98,7 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ # sort removes libbpf duplicates when not cross-building MAKE_DIRS := $(sort $(OBJ_DIR)/libbpf $(OBJ_DIR)/libbpf \ $(OBJ_DIR)/bpftool $(OBJ_DIR)/resolve_btfids \ - $(INCLUDE_DIR) $(SCXOBJ_DIR)) + $(HOST_OBJ_DIR) $(INCLUDE_DIR) $(SCXOBJ_DIR)) $(MAKE_DIRS): $(call msg,MKDIR,,$@) @@ -108,18 +108,19 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ $(APIDIR)/linux/bpf.h \ | $(OBJ_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(OBJ_DIR)/libbpf/ \ + ARCH=$(ARCH) CC="$(CC)" CROSS_COMPILE=$(CROSS_COMPILE) \ EXTRA_CFLAGS='-g -O0 -fPIC' \ DESTDIR=$(OUTPUT_DIR) prefix= all install_headers $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ - $(LIBBPF_OUTPUT) | $(OBJ_DIR)/bpftool + $(LIBBPF_OUTPUT) | $(HOST_OBJ_DIR) $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \ EXTRA_CFLAGS='-g -O0' \ - OUTPUT=$(OBJ_DIR)/bpftool/ \ - LIBBPF_OUTPUT=$(OBJ_DIR)/libbpf/ \ - LIBBPF_DESTDIR=$(OUTPUT_DIR)/ \ - prefix= DESTDIR=$(OUTPUT_DIR)/ install-bin + OUTPUT=$(HOST_OBJ_DIR)/ \ + LIBBPF_OUTPUT=$(HOST_LIBBPF_OUTPUT) \ + LIBBPF_DESTDIR=$(HOST_LIBBPF_DESTDIR) \ + prefix= DESTDIR=$(HOST_DESTDIR) install-bin $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR) ifeq ($(VMLINUX_H),) @@ -150,9 +151,7 @@ $(INCLUDE_DIR)/%.bpf.skel.h: $(SCXOBJ_DIR)/%.bpf.o $(INCLUDE_DIR)/vmlinux.h $(BP override define CLEAN rm -rf $(OUTPUT_DIR) - rm -f *.o *.bpf.o *.bpf.skel.h *.bpf.subskel.h rm -f $(TEST_GEN_PROGS) - rm -f runner endef # Every testcase takes all of the BPF progs are dependencies by default. This @@ -185,7 +184,7 @@ auto-test-targets := \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) -$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) +$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) $(BPFOBJ) $(CC) $(CFLAGS) -c $< -o $@ # Create all of the test targets object files, whose testcase objects will be @@ -196,21 +195,15 @@ $(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) # function doesn't support using implicit rules otherwise. $(testcase-targets): $(SCXOBJ_DIR)/%.o: %.c $(SCXOBJ_DIR)/runner.o $(all_test_bpfprogs) | $(SCXOBJ_DIR) $(eval test=$(patsubst %.o,%.c,$(notdir $@))) - $(CC) $(CFLAGS) -c $< -o $@ $(SCXOBJ_DIR)/runner.o + $(CC) $(CFLAGS) -c $< -o $@ $(SCXOBJ_DIR)/util.o: util.c | $(SCXOBJ_DIR) $(CC) $(CFLAGS) -c $< -o $@ -runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets) +$(OUTPUT)/runner: $(SCXOBJ_DIR)/runner.o $(SCXOBJ_DIR)/util.o $(BPFOBJ) $(testcase-targets) @echo "$(testcase-targets)" $(CC) $(CFLAGS) -o $@ $^ $(LDFLAGS) -TEST_GEN_PROGS := runner - -all: runner - -.PHONY: all clean help - .DEFAULT_GOAL := all .DELETE_ON_ERROR: diff --git a/tools/testing/selftests/sched_ext/create_dsq.bpf.c b/tools/testing/selftests/sched_ext/create_dsq.bpf.c index 23f79ed343f0..2cfc4ffd60e2 100644 --- a/tools/testing/selftests/sched_ext/create_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/create_dsq.bpf.c @@ -51,8 +51,8 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init) SEC(".struct_ops.link") struct sched_ext_ops create_dsq_ops = { - .init_task = create_dsq_init_task, - .exit_task = create_dsq_exit_task, - .init = create_dsq_init, + .init_task = (void *) create_dsq_init_task, + .exit_task = (void *) create_dsq_exit_task, + .init = (void *) create_dsq_init, .name = "create_dsq", }; diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index e97ad41d354a..37d9bf6fb745 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -35,8 +35,8 @@ void BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops ddsp_bogus_dsq_fail_ops = { - .select_cpu = ddsp_bogus_dsq_fail_select_cpu, - .exit = ddsp_bogus_dsq_fail_exit, + .select_cpu = (void *) ddsp_bogus_dsq_fail_select_cpu, + .exit = (void *) ddsp_bogus_dsq_fail_exit, .name = "ddsp_bogus_dsq_fail", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dde7e7dafbfb..dffc97d9cdf1 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -32,8 +32,8 @@ void BPF_STRUCT_OPS(ddsp_vtimelocal_fail_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops ddsp_vtimelocal_fail_ops = { - .select_cpu = ddsp_vtimelocal_fail_select_cpu, - .exit = ddsp_vtimelocal_fail_exit, + .select_cpu = (void *) ddsp_vtimelocal_fail_select_cpu, + .exit = (void *) ddsp_vtimelocal_fail_exit, .name = "ddsp_vtimelocal_fail", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index efb4672decb4..6a7db1502c29 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -56,10 +56,10 @@ void BPF_STRUCT_OPS(dsp_local_on_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops dsp_local_on_ops = { - .select_cpu = dsp_local_on_select_cpu, - .enqueue = dsp_local_on_enqueue, - .dispatch = dsp_local_on_dispatch, - .exit = dsp_local_on_exit, + .select_cpu = (void *) dsp_local_on_select_cpu, + .enqueue = (void *) dsp_local_on_enqueue, + .dispatch = (void *) dsp_local_on_dispatch, + .exit = (void *) dsp_local_on_exit, .name = "dsp_local_on", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c index b0b99531d5d5..e1bd13e48889 100644 --- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c @@ -12,10 +12,18 @@ char _license[] SEC("license") = "GPL"; +u32 exit_kind; + +void BPF_STRUCT_OPS_SLEEPABLE(enq_last_no_enq_fails_exit, struct scx_exit_info *info) +{ + exit_kind = info->kind; +} + SEC(".struct_ops.link") struct sched_ext_ops enq_last_no_enq_fails_ops = { .name = "enq_last_no_enq_fails", /* Need to define ops.enqueue() with SCX_OPS_ENQ_LAST */ .flags = SCX_OPS_ENQ_LAST, + .exit = (void *) enq_last_no_enq_fails_exit, .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c index 2a3eda5e2c0b..73e679953e27 100644 --- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c @@ -31,8 +31,12 @@ static enum scx_test_status run(void *ctx) struct bpf_link *link; link = bpf_map__attach_struct_ops(skel->maps.enq_last_no_enq_fails_ops); - if (link) { - SCX_ERR("Incorrectly succeeded in to attaching scheduler"); + if (!link) { + SCX_ERR("Incorrectly failed at attaching scheduler"); + return SCX_TEST_FAIL; + } + if (!skel->bss->exit_kind) { + SCX_ERR("Incorrectly stayed loaded"); return SCX_TEST_FAIL; } @@ -50,7 +54,7 @@ static void cleanup(void *ctx) struct scx_test enq_last_no_enq_fails = { .name = "enq_last_no_enq_fails", - .description = "Verify we fail to load a scheduler if we specify " + .description = "Verify we eject a scheduler if we specify " "the SCX_OPS_ENQ_LAST flag without defining " "ops.enqueue()", .setup = setup, diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index b3dfc1033cd6..1efb50d61040 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -36,8 +36,8 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, SEC(".struct_ops.link") struct sched_ext_ops enq_select_cpu_fails_ops = { - .select_cpu = enq_select_cpu_fails_select_cpu, - .enqueue = enq_select_cpu_fails_enqueue, + .select_cpu = (void *) enq_select_cpu_fails_select_cpu, + .enqueue = (void *) enq_select_cpu_fails_enqueue, .name = "enq_select_cpu_fails", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index ae12ddaac921..d75d4faf07f6 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -15,6 +15,8 @@ UEI_DEFINE(uei); #define EXIT_CLEANLY() scx_bpf_exit(exit_point, "%d", exit_point) +#define DSQ_ID 0 + s32 BPF_STRUCT_OPS(exit_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { @@ -31,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) if (exit_point == EXIT_ENQUEUE) EXIT_CLEANLY(); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -39,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_consume(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) @@ -67,18 +69,18 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(exit_init) if (exit_point == EXIT_INIT) EXIT_CLEANLY(); - return 0; + return scx_bpf_create_dsq(DSQ_ID, -1); } SEC(".struct_ops.link") struct sched_ext_ops exit_ops = { - .select_cpu = exit_select_cpu, - .enqueue = exit_enqueue, - .dispatch = exit_dispatch, - .init_task = exit_init_task, - .enable = exit_enable, - .exit = exit_exit, - .init = exit_init, + .select_cpu = (void *) exit_select_cpu, + .enqueue = (void *) exit_enqueue, + .dispatch = (void *) exit_dispatch, + .init_task = (void *) exit_init_task, + .enable = (void *) exit_enable, + .exit = (void *) exit_exit, + .init = (void *) exit_init, .name = "exit", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/hotplug.bpf.c b/tools/testing/selftests/sched_ext/hotplug.bpf.c index 8f2601db39f3..6c9f25c9bf53 100644 --- a/tools/testing/selftests/sched_ext/hotplug.bpf.c +++ b/tools/testing/selftests/sched_ext/hotplug.bpf.c @@ -46,16 +46,16 @@ void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_offline, s32 cpu) SEC(".struct_ops.link") struct sched_ext_ops hotplug_cb_ops = { - .cpu_online = hotplug_cpu_online, - .cpu_offline = hotplug_cpu_offline, - .exit = hotplug_exit, + .cpu_online = (void *) hotplug_cpu_online, + .cpu_offline = (void *) hotplug_cpu_offline, + .exit = (void *) hotplug_exit, .name = "hotplug_cbs", .timeout_ms = 1000U, }; SEC(".struct_ops.link") struct sched_ext_ops hotplug_nocb_ops = { - .exit = hotplug_exit, + .exit = (void *) hotplug_exit, .name = "hotplug_nocbs", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c index 47ea89a626c3..5eb9edb1837d 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c @@ -45,9 +45,9 @@ void BPF_STRUCT_OPS(cnt_disable, struct task_struct *p) SEC(".struct_ops.link") struct sched_ext_ops init_enable_count_ops = { - .init_task = cnt_init_task, - .exit_task = cnt_exit_task, - .enable = cnt_enable, - .disable = cnt_disable, + .init_task = (void *) cnt_init_task, + .exit_task = (void *) cnt_exit_task, + .enable = (void *) cnt_enable, + .disable = (void *) cnt_disable, .name = "init_enable_count", }; diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 00bfa9cb95d3..4d4cd8d966db 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -131,34 +131,34 @@ void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) SEC(".struct_ops.link") struct sched_ext_ops maximal_ops = { - .select_cpu = maximal_select_cpu, - .enqueue = maximal_enqueue, - .dequeue = maximal_dequeue, - .dispatch = maximal_dispatch, - .runnable = maximal_runnable, - .running = maximal_running, - .stopping = maximal_stopping, - .quiescent = maximal_quiescent, - .yield = maximal_yield, - .core_sched_before = maximal_core_sched_before, - .set_weight = maximal_set_weight, - .set_cpumask = maximal_set_cpumask, - .update_idle = maximal_update_idle, - .cpu_acquire = maximal_cpu_acquire, - .cpu_release = maximal_cpu_release, - .cpu_online = maximal_cpu_online, - .cpu_offline = maximal_cpu_offline, - .init_task = maximal_init_task, - .enable = maximal_enable, - .exit_task = maximal_exit_task, - .disable = maximal_disable, - .cgroup_init = maximal_cgroup_init, - .cgroup_exit = maximal_cgroup_exit, - .cgroup_prep_move = maximal_cgroup_prep_move, - .cgroup_move = maximal_cgroup_move, - .cgroup_cancel_move = maximal_cgroup_cancel_move, - .cgroup_set_weight = maximal_cgroup_set_weight, - .init = maximal_init, - .exit = maximal_exit, + .select_cpu = (void *) maximal_select_cpu, + .enqueue = (void *) maximal_enqueue, + .dequeue = (void *) maximal_dequeue, + .dispatch = (void *) maximal_dispatch, + .runnable = (void *) maximal_runnable, + .running = (void *) maximal_running, + .stopping = (void *) maximal_stopping, + .quiescent = (void *) maximal_quiescent, + .yield = (void *) maximal_yield, + .core_sched_before = (void *) maximal_core_sched_before, + .set_weight = (void *) maximal_set_weight, + .set_cpumask = (void *) maximal_set_cpumask, + .update_idle = (void *) maximal_update_idle, + .cpu_acquire = (void *) maximal_cpu_acquire, + .cpu_release = (void *) maximal_cpu_release, + .cpu_online = (void *) maximal_cpu_online, + .cpu_offline = (void *) maximal_cpu_offline, + .init_task = (void *) maximal_init_task, + .enable = (void *) maximal_enable, + .exit_task = (void *) maximal_exit_task, + .disable = (void *) maximal_disable, + .cgroup_init = (void *) maximal_cgroup_init, + .cgroup_exit = (void *) maximal_cgroup_exit, + .cgroup_prep_move = (void *) maximal_cgroup_prep_move, + .cgroup_move = (void *) maximal_cgroup_move, + .cgroup_cancel_move = (void *) maximal_cgroup_cancel_move, + .cgroup_set_weight = (void *) maximal_cgroup_set_weight, + .init = (void *) maximal_init, + .exit = (void *) maximal_exit, .name = "maximal", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null.bpf.c b/tools/testing/selftests/sched_ext/maybe_null.bpf.c index 27d0f386acfb..cf4ae870cd4e 100644 --- a/tools/testing/selftests/sched_ext/maybe_null.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null.bpf.c @@ -29,8 +29,8 @@ bool BPF_STRUCT_OPS(maybe_null_success_yield, struct task_struct *from, SEC(".struct_ops.link") struct sched_ext_ops maybe_null_success = { - .dispatch = maybe_null_success_dispatch, - .yield = maybe_null_success_yield, - .enable = maybe_null_running, + .dispatch = (void *) maybe_null_success_dispatch, + .yield = (void *) maybe_null_success_yield, + .enable = (void *) maybe_null_running, .name = "minimal", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c index c0641050271d..ec724d7b33d1 100644 --- a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c @@ -19,7 +19,7 @@ void BPF_STRUCT_OPS(maybe_null_fail_dispatch, s32 cpu, struct task_struct *p) SEC(".struct_ops.link") struct sched_ext_ops maybe_null_fail = { - .dispatch = maybe_null_fail_dispatch, - .enable = maybe_null_running, + .dispatch = (void *) maybe_null_fail_dispatch, + .enable = (void *) maybe_null_running, .name = "maybe_null_fail_dispatch", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c index 3c1740028e3b..e6552cace020 100644 --- a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c @@ -22,7 +22,7 @@ bool BPF_STRUCT_OPS(maybe_null_fail_yield, struct task_struct *from, SEC(".struct_ops.link") struct sched_ext_ops maybe_null_fail = { - .yield = maybe_null_fail_yield, - .enable = maybe_null_running, + .yield = (void *) maybe_null_fail_yield, + .enable = (void *) maybe_null_running, .name = "maybe_null_fail_yield", }; diff --git a/tools/testing/selftests/sched_ext/prog_run.bpf.c b/tools/testing/selftests/sched_ext/prog_run.bpf.c index 6a4d7c48e3f2..00c267626a68 100644 --- a/tools/testing/selftests/sched_ext/prog_run.bpf.c +++ b/tools/testing/selftests/sched_ext/prog_run.bpf.c @@ -28,6 +28,6 @@ void BPF_STRUCT_OPS(prog_run_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops prog_run_ops = { - .exit = prog_run_exit, + .exit = (void *) prog_run_exit, .name = "prog_run", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index 2ed2991afafe..f171ac470970 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -35,6 +35,6 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dfl_ops = { - .enqueue = select_cpu_dfl_enqueue, + .enqueue = (void *) select_cpu_dfl_enqueue, .name = "select_cpu_dfl", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 4bb5abb2d369..9efdbb7da928 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -82,8 +82,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dfl_nodispatch_ops = { - .select_cpu = select_cpu_dfl_nodispatch_select_cpu, - .enqueue = select_cpu_dfl_nodispatch_enqueue, - .init_task = select_cpu_dfl_nodispatch_init_task, + .select_cpu = (void *) select_cpu_dfl_nodispatch_select_cpu, + .enqueue = (void *) select_cpu_dfl_nodispatch_enqueue, + .init_task = (void *) select_cpu_dfl_nodispatch_init_task, .name = "select_cpu_dfl_nodispatch", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index f0b96a4a04b2..59bfc4f36167 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -35,7 +35,7 @@ dispatch: SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_ops = { - .select_cpu = select_cpu_dispatch_select_cpu, + .select_cpu = (void *) select_cpu_dispatch_select_cpu, .name = "select_cpu_dispatch", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 7b42ddce0f56..3bbd5fcdfb18 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -30,8 +30,8 @@ void BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_bad_dsq_ops = { - .select_cpu = select_cpu_dispatch_bad_dsq_select_cpu, - .exit = select_cpu_dispatch_bad_dsq_exit, + .select_cpu = (void *) select_cpu_dispatch_bad_dsq_select_cpu, + .exit = (void *) select_cpu_dispatch_bad_dsq_exit, .name = "select_cpu_dispatch_bad_dsq", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 653e3dc0b4dc..0fda57fe0ecf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -31,8 +31,8 @@ void BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_dbl_dsp_ops = { - .select_cpu = select_cpu_dispatch_dbl_dsp_select_cpu, - .exit = select_cpu_dispatch_dbl_dsp_exit, + .select_cpu = (void *) select_cpu_dispatch_dbl_dsp_select_cpu, + .exit = (void *) select_cpu_dispatch_dbl_dsp_exit, .name = "select_cpu_dispatch_dbl_dsp", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index 7f3ebf4fc2ea..e6c67bcf5e6e 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -81,12 +81,12 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(select_cpu_vtime_init) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_vtime_ops = { - .select_cpu = select_cpu_vtime_select_cpu, - .dispatch = select_cpu_vtime_dispatch, - .running = select_cpu_vtime_running, - .stopping = select_cpu_vtime_stopping, - .enable = select_cpu_vtime_enable, - .init = select_cpu_vtime_init, + .select_cpu = (void *) select_cpu_vtime_select_cpu, + .dispatch = (void *) select_cpu_vtime_dispatch, + .running = (void *) select_cpu_vtime_running, + .stopping = (void *) select_cpu_vtime_stopping, + .enable = (void *) select_cpu_vtime_enable, + .init = (void *) select_cpu_vtime_init, .name = "select_cpu_vtime", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json index 24bd0c2a3014..b2ca9d4e991b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/u32.json @@ -329,5 +329,29 @@ "teardown": [ "$TC qdisc del dev $DEV1 parent root drr" ] + }, + { + "id": "1234", + "name": "Exercise IDR leaks by creating/deleting a filter many (2048) times", + "category": [ + "filter", + "u32" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 parent root handle 10: drr", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 2 u32 match ip src 0.0.0.2/32 action drop", + "$TC filter add dev $DEV1 parent 10:0 protocol ip prio 3 u32 match ip src 0.0.0.3/32 action drop" + ], + "cmdUnderTest": "bash -c 'for i in {1..2048} ;do echo filter delete dev $DEV1 pref 3;echo filter add dev $DEV1 parent 10:0 protocol ip prio 3 u32 match ip src 0.0.0.3/32 action drop;done | $TC -b -'", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1", + "matchPattern": "protocol ip pref 3 u32", + "matchCount": "3", + "teardown": [ + "$TC qdisc del dev $DEV1 parent root drr" + ] } ] diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index af9cedbf5357..1cf14a8da438 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -9,10 +9,8 @@ ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64)) TEST_GEN_PROGS += vdso_standalone_test_x86 endif TEST_GEN_PROGS += vdso_test_correctness -ifeq ($(ARCH)$(CONFIG_X86_32),$(filter $(ARCH)$(CONFIG_X86_32),x86 x86_64 loongarch arm64 powerpc s390)) TEST_GEN_PROGS += vdso_test_getrandom TEST_GEN_PROGS += vdso_test_chacha -endif CFLAGS := -std=gnu99 -O2 @@ -37,9 +35,9 @@ $(OUTPUT)/vdso_test_getrandom: CFLAGS += -isystem $(top_srcdir)/tools/include \ $(KHDR_INCLUDES) \ -isystem $(top_srcdir)/include/uapi -$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/tools/arch/$(SRCARCH)/vdso/vgetrandom-chacha.S +$(OUTPUT)/vdso_test_chacha: vgetrandom-chacha.S $(OUTPUT)/vdso_test_chacha: CFLAGS += -idirafter $(top_srcdir)/tools/include \ -idirafter $(top_srcdir)/tools/include/generated \ -idirafter $(top_srcdir)/arch/$(SRCARCH)/include \ -idirafter $(top_srcdir)/include \ - -D__ASSEMBLY__ -Wa,--noexecstack + -Wa,--noexecstack diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c index b1ea532c5996..8757f738b0b1 100644 --- a/tools/testing/selftests/vDSO/vdso_test_chacha.c +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -3,6 +3,7 @@ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ +#include <linux/compiler.h> #include <tools/le_byteshift.h> #include <sys/random.h> #include <sys/auxv.h> @@ -73,10 +74,10 @@ static void reference_chacha20_blocks(uint8_t *dst_bytes, const uint32_t *key, u counter[1] = s[13]; } -typedef uint8_t u8; -typedef uint32_t u32; -typedef uint64_t u64; -#include <vdso/getrandom.h> +void __weak __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint32_t *key, uint32_t *counter, size_t nblocks) +{ + ksft_exit_skip("Not implemented on architecture\n"); +} int main(int argc, char *argv[]) { @@ -90,10 +91,8 @@ int main(int argc, char *argv[]) ksft_set_plan(1); for (unsigned int trial = 0; trial < TRIALS; ++trial) { - if (getrandom(key, sizeof(key), 0) != sizeof(key)) { - printf("getrandom() failed!\n"); - return KSFT_SKIP; - } + if (getrandom(key, sizeof(key), 0) != sizeof(key)) + ksft_exit_skip("getrandom() failed unexpectedly\n"); memset(counter1, 0, sizeof(counter1)); reference_chacha20_blocks(output1, key, counter1, BLOCKS); for (unsigned int split = 0; split < BLOCKS; ++split) { @@ -102,8 +101,10 @@ int main(int argc, char *argv[]) if (split) __arch_chacha20_blocks_nostack(output2, key, counter2, split); __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter2, BLOCKS - split); - if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) - return KSFT_FAIL; + if (memcmp(output1, output2, sizeof(output1))) + ksft_exit_fail_msg("Main loop outputs do not match on trial %u, split %u\n", trial, split); + if (memcmp(counter1, counter2, sizeof(counter1))) + ksft_exit_fail_msg("Main loop counters do not match on trial %u, split %u\n", trial, split); } } memset(counter1, 0, sizeof(counter1)); @@ -113,14 +114,19 @@ int main(int argc, char *argv[]) reference_chacha20_blocks(output1, key, counter1, BLOCKS); __arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS); - if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) - return KSFT_FAIL; + if (memcmp(output1, output2, sizeof(output1))) + ksft_exit_fail_msg("Block limit outputs do not match after first round\n"); + if (memcmp(counter1, counter2, sizeof(counter1))) + ksft_exit_fail_msg("Block limit counters do not match after first round\n"); reference_chacha20_blocks(output1, key, counter1, BLOCKS); __arch_chacha20_blocks_nostack(output2, key, counter2, BLOCKS); - if (memcmp(output1, output2, sizeof(output1)) || memcmp(counter1, counter2, sizeof(counter1))) - return KSFT_FAIL; + if (memcmp(output1, output2, sizeof(output1))) + ksft_exit_fail_msg("Block limit outputs do not match after second round\n"); + if (memcmp(counter1, counter2, sizeof(counter1))) + ksft_exit_fail_msg("Block limit counters do not match after second round\n"); ksft_test_result_pass("chacha: PASS\n"); - return KSFT_PASS; + ksft_exit_pass(); + return 0; } diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index e5e83dbec589..95057f7567db 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -11,6 +11,7 @@ #include <string.h> #include <time.h> #include <unistd.h> +#include <sched.h> #include <signal.h> #include <sys/auxv.h> #include <sys/mman.h> @@ -40,6 +41,9 @@ } while (0) #endif +#define ksft_assert(condition) \ + do { if (!(condition)) ksft_exit_fail_msg("Assertion failed: %s\n", #condition); } while (0) + static struct { pthread_mutex_t lock; void **states; @@ -111,26 +115,19 @@ static void vgetrandom_init(void) const char *version = versions[VDSO_VERSION]; const char *name = names[VDSO_NAMES][6]; unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); - size_t ret; + ssize_t ret; - if (!sysinfo_ehdr) { - printf("AT_SYSINFO_EHDR is not present!\n"); - exit(KSFT_SKIP); - } + if (!sysinfo_ehdr) + ksft_exit_skip("AT_SYSINFO_EHDR is not present\n"); vdso_init_from_sysinfo_ehdr(sysinfo_ehdr); vgrnd.fn = (__typeof__(vgrnd.fn))vdso_sym(version, name); - if (!vgrnd.fn) { - printf("%s is missing!\n", name); - exit(KSFT_FAIL); - } + if (!vgrnd.fn) + ksft_exit_skip("%s@%s symbol is missing from vDSO\n", name, version); ret = VDSO_CALL(vgrnd.fn, 5, NULL, 0, 0, &vgrnd.params, ~0UL); - if (ret == -ENOSYS) { - printf("unsupported architecture\n"); - exit(KSFT_SKIP); - } else if (ret) { - printf("failed to fetch vgetrandom params!\n"); - exit(KSFT_FAIL); - } + if (ret == -ENOSYS) + ksft_exit_skip("CPU does not have runtime support\n"); + else if (ret) + ksft_exit_fail_msg("Failed to fetch vgetrandom params: %zd\n", ret); } static ssize_t vgetrandom(void *buf, size_t len, unsigned long flags) @@ -139,10 +136,7 @@ static ssize_t vgetrandom(void *buf, size_t len, unsigned long flags) if (!state) { state = vgetrandom_get_state(); - if (!state) { - printf("vgetrandom_get_state failed!\n"); - exit(KSFT_FAIL); - } + ksft_assert(state); } return VDSO_CALL(vgrnd.fn, 5, buf, len, flags, state, vgrnd.params.size_of_opaque_state); } @@ -154,7 +148,7 @@ static void *test_vdso_getrandom(void *ctx) for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; ssize_t ret = vgetrandom(&val, sizeof(val), 0); - assert(ret == sizeof(val)); + ksft_assert(ret == sizeof(val)); } return NULL; } @@ -164,7 +158,7 @@ static void *test_libc_getrandom(void *ctx) for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; ssize_t ret = getrandom(&val, sizeof(val), 0); - assert(ret == sizeof(val)); + ksft_assert(ret == sizeof(val)); } return NULL; } @@ -174,7 +168,7 @@ static void *test_syscall_getrandom(void *ctx) for (size_t i = 0; i < TRIALS; ++i) { unsigned int val; ssize_t ret = syscall(__NR_getrandom, &val, sizeof(val), 0); - assert(ret == sizeof(val)); + ksft_assert(ret == sizeof(val)); } return NULL; } @@ -209,7 +203,7 @@ static void bench_multi(void) clock_gettime(CLOCK_MONOTONIC, &start); for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) == 0); + ksft_assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) == 0); for (size_t i = 0; i < THREADS; ++i) pthread_join(threads[i], NULL); clock_gettime(CLOCK_MONOTONIC, &end); @@ -218,7 +212,7 @@ static void bench_multi(void) clock_gettime(CLOCK_MONOTONIC, &start); for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) == 0); + ksft_assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) == 0); for (size_t i = 0; i < THREADS; ++i) pthread_join(threads[i], NULL); clock_gettime(CLOCK_MONOTONIC, &end); @@ -227,7 +221,7 @@ static void bench_multi(void) clock_gettime(CLOCK_MONOTONIC, &start); for (size_t i = 0; i < THREADS; ++i) - assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) == 0); + ksft_assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) == 0); for (size_t i = 0; i < THREADS; ++i) pthread_join(threads[i], NULL); clock_gettime(CLOCK_MONOTONIC, &end); @@ -252,48 +246,46 @@ static void kselftest(void) for (size_t i = 0; i < 1000; ++i) { ssize_t ret = vgetrandom(weird_size, sizeof(weird_size), 0); - if (ret != sizeof(weird_size)) - exit(KSFT_FAIL); + ksft_assert(ret == sizeof(weird_size)); } ksft_test_result_pass("getrandom: PASS\n"); unshare(CLONE_NEWUSER); - assert(unshare(CLONE_NEWTIME) == 0); + ksft_assert(unshare(CLONE_NEWTIME) == 0); child = fork(); - assert(child >= 0); + ksft_assert(child >= 0); if (!child) { vgetrandom_init(); child = getpid(); - assert(ptrace(PTRACE_TRACEME, 0, NULL, NULL) == 0); - assert(kill(child, SIGSTOP) == 0); - assert(vgetrandom(weird_size, sizeof(weird_size), 0) == sizeof(weird_size)); + ksft_assert(ptrace(PTRACE_TRACEME, 0, NULL, NULL) == 0); + ksft_assert(kill(child, SIGSTOP) == 0); + ksft_assert(vgetrandom(weird_size, sizeof(weird_size), 0) == sizeof(weird_size)); _exit(0); } for (;;) { struct ptrace_syscall_info info = { 0 }; int status, ret; - assert(waitpid(child, &status, 0) >= 0); + ksft_assert(waitpid(child, &status, 0) >= 0); if (WIFEXITED(status)) { - if (WEXITSTATUS(status) != 0) - exit(KSFT_FAIL); + ksft_assert(WEXITSTATUS(status) == 0); break; } - assert(WIFSTOPPED(status)); + ksft_assert(WIFSTOPPED(status)); if (WSTOPSIG(status) == SIGSTOP) - assert(ptrace(PTRACE_SETOPTIONS, child, 0, PTRACE_O_TRACESYSGOOD) == 0); + ksft_assert(ptrace(PTRACE_SETOPTIONS, child, 0, PTRACE_O_TRACESYSGOOD) == 0); else if (WSTOPSIG(status) == (SIGTRAP | 0x80)) { - assert(ptrace(PTRACE_GET_SYSCALL_INFO, child, sizeof(info), &info) > 0); + ksft_assert(ptrace(PTRACE_GET_SYSCALL_INFO, child, sizeof(info), &info) > 0); if (info.op == PTRACE_SYSCALL_INFO_ENTRY && info.entry.nr == __NR_getrandom && info.entry.args[0] == (uintptr_t)weird_size && info.entry.args[1] == sizeof(weird_size)) - exit(KSFT_FAIL); + ksft_exit_fail_msg("vgetrandom passed buffer to syscall getrandom unexpectedly\n"); } - assert(ptrace(PTRACE_SYSCALL, child, 0, 0) == 0); + ksft_assert(ptrace(PTRACE_SYSCALL, child, 0, 0) == 0); } ksft_test_result_pass("getrandom timens: PASS\n"); - exit(KSFT_PASS); + ksft_exit_pass(); } static void usage(const char *argv0) diff --git a/tools/testing/selftests/vDSO/vgetrandom-chacha.S b/tools/testing/selftests/vDSO/vgetrandom-chacha.S new file mode 100644 index 000000000000..d6e09af7c0a9 --- /dev/null +++ b/tools/testing/selftests/vDSO/vgetrandom-chacha.S @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#define __ASSEMBLY__ + +#if defined(__aarch64__) +#include "../../../../arch/arm64/kernel/vdso/vgetrandom-chacha.S" +#elif defined(__loongarch__) +#include "../../../../arch/loongarch/vdso/vgetrandom-chacha.S" +#elif defined(__powerpc__) || defined(__powerpc64__) +#include "../../../../arch/powerpc/kernel/vdso/vgetrandom-chacha.S" +#elif defined(__s390x__) +#include "../../../../arch/s390/kernel/vdso64/vgetrandom-chacha.S" +#elif defined(__x86_64__) +#include "../../../../arch/x86/entry/vdso/vgetrandom-chacha.S" +#endif diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index bc71cbca0dde..a1f506ba5578 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -334,7 +334,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c index c53f220eb6cc..b33b47342d41 100644 --- a/tools/testing/vma/vma.c +++ b/tools/testing/vma/vma.c @@ -1522,6 +1522,45 @@ static bool test_copy_vma(void) return true; } +static bool test_expand_only_mode(void) +{ + unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE; + struct mm_struct mm = {}; + VMA_ITERATOR(vmi, &mm, 0); + struct vm_area_struct *vma_prev, *vma; + VMG_STATE(vmg, &mm, &vmi, 0x5000, 0x9000, flags, 5); + + /* + * Place a VMA prior to the one we're expanding so we assert that we do + * not erroneously try to traverse to the previous VMA even though we + * have, through the use of VMG_FLAG_JUST_EXPAND, indicated we do not + * need to do so. + */ + alloc_and_link_vma(&mm, 0, 0x2000, 0, flags); + + /* + * We will be positioned at the prev VMA, but looking to expand to + * 0x9000. + */ + vma_iter_set(&vmi, 0x3000); + vma_prev = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags); + vmg.prev = vma_prev; + vmg.merge_flags = VMG_FLAG_JUST_EXPAND; + + vma = vma_merge_new_range(&vmg); + ASSERT_NE(vma, NULL); + ASSERT_EQ(vma, vma_prev); + ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); + ASSERT_EQ(vma->vm_start, 0x3000); + ASSERT_EQ(vma->vm_end, 0x9000); + ASSERT_EQ(vma->vm_pgoff, 3); + ASSERT_TRUE(vma_write_started(vma)); + ASSERT_EQ(vma_iter_addr(&vmi), 0x3000); + + cleanup_mm(&mm, &vmi); + return true; +} + int main(void) { int num_tests = 0, num_fail = 0; @@ -1553,6 +1592,7 @@ int main(void) TEST(vmi_prealloc_fail); TEST(merge_extend); TEST(copy_vma); + TEST(expand_only_mode); #undef TEST diff --git a/tools/usb/usbip/src/usbip_detach.c b/tools/usb/usbip/src/usbip_detach.c index b29101986b5a..6b78d4a81e95 100644 --- a/tools/usb/usbip/src/usbip_detach.c +++ b/tools/usb/usbip/src/usbip_detach.c @@ -68,6 +68,7 @@ static int detach_port(char *port) } if (!found) { + ret = -1; err("Invalid port %s > maxports %d", port, vhci_driver->nports); goto call_driver_close; diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c index 43d3a6aa1dcf..b9591223437a 100644 --- a/tools/virtio/vringh_test.c +++ b/tools/virtio/vringh_test.c @@ -519,7 +519,7 @@ int main(int argc, char *argv[]) errx(1, "virtqueue_add_sgs: %i", err); __kmalloc_fake = NULL; - /* Host retreives it. */ + /* Host retrieves it. */ vringh_iov_init(&riov, host_riov, ARRAY_SIZE(host_riov)); vringh_iov_init(&wiov, host_wiov, ARRAY_SIZE(host_wiov)); |