diff options
Diffstat (limited to 'tools')
230 files changed, 7388 insertions, 1536 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 964df31da975..66736ff04011 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -484,6 +484,12 @@ enum { */ #define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (1ULL << 0) +/* + * Shutdown caused by a PSCI v1.3 SYSTEM_OFF2 call. + * Valid only when the system event has a type of KVM_SYSTEM_EVENT_SHUTDOWN. + */ +#define KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 (1ULL << 0) + /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 23698d0f4bb4..17b6590748c0 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -215,7 +215,7 @@ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */ #define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */ #define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */ #define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */ @@ -317,6 +317,9 @@ #define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ +#define X86_FEATURE_SHA512 (12*32+ 0) /* SHA512 instructions */ +#define X86_FEATURE_SM3 (12*32+ 1) /* SM3 instructions */ +#define X86_FEATURE_SM4 (12*32+ 2) /* SM4 instructions */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */ @@ -348,6 +351,7 @@ #define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */ #define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_AMD_IBPB_RET (13*32+30) /* IBPB clears return address predictor */ #define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -472,7 +476,9 @@ #define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ #define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ #define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ -#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ +#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* Fast CPPC */ +#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */ +#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */ /* * BUG word(s) @@ -523,4 +529,5 @@ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */ #define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ +#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index a8debbf2f702..88585c1de416 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -440,6 +440,7 @@ struct kvm_sync_regs { #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_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2ff949ea82fa..e71be67f1d86 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -822,11 +822,18 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, printf("%s:\n", sym_name); } - if (disasm_print_insn(img, lens[i], opcodes, - name, disasm_opt, btf, - prog_linfo, ksyms[i], i, - linum)) - goto exit_free; + if (ksyms) { + if (disasm_print_insn(img, lens[i], opcodes, + name, disasm_opt, btf, + prog_linfo, ksyms[i], i, + linum)) + goto exit_free; + } else { + if (disasm_print_insn(img, lens[i], opcodes, + name, disasm_opt, btf, + NULL, 0, 0, false)) + goto exit_free; + } img += lens[i]; diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore new file mode 100644 index 000000000000..0c5bc15d602f --- /dev/null +++ b/tools/hv/.gitignore @@ -0,0 +1,3 @@ +hv_fcopy_uio_daemon +hv_kvp_daemon +hv_vss_daemon diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 7a00f3066a98..0198321d14a2 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,8 +35,6 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define MAX_FOLDER_NAME 15 -#define MAX_PATH_LEN 15 #define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" #define FCOPY_VER_COUNT 1 @@ -51,7 +49,7 @@ static const int fw_versions[] = { #define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ -unsigned char desc[HV_RING_SIZE]; +static unsigned char desc[HV_RING_SIZE]; static int target_fd; static char target_fname[PATH_MAX]; @@ -409,8 +407,8 @@ int main(int argc, char *argv[]) struct vmbus_br txbr, rxbr; void *ring; uint32_t len = HV_RING_SIZE; - char uio_name[MAX_FOLDER_NAME] = {0}; - char uio_dev_path[MAX_PATH_LEN] = {0}; + char uio_name[NAME_MAX] = {0}; + char uio_dev_path[PATH_MAX] = {0}; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, @@ -468,8 +466,10 @@ int main(int argc, char *argv[]) */ ret = pread(fcopy_fd, &tmp, sizeof(int), 0); if (ret < 0) { + if (errno == EINTR || errno == EAGAIN) + continue; syslog(LOG_ERR, "pread failed: %s", strerror(errno)); - continue; + goto close; } len = HV_RING_SIZE; diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh index 058c17b46ffc..268521234d4b 100755 --- a/tools/hv/hv_get_dns_info.sh +++ b/tools/hv/hv_get_dns_info.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # This example script parses /etc/resolv.conf to retrive DNS information. # In the interest of keeping the KVP daemon code free of distro specific @@ -10,4 +10,4 @@ # this script can be based on the Network Manager APIs for retrieving DNS # entries. -cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }' +exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index ae57bf69ad4a..04ba035d67e9 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -725,7 +725,7 @@ static void kvp_get_ipconfig_info(char *if_name, * . */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info"); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name); /* * Execute the command to gather DNS info. @@ -742,7 +742,7 @@ static void kvp_get_ipconfig_info(char *if_name, * Enabled: DHCP enabled. */ - sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name); + sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name); file = popen(cmd, "r"); if (file == NULL) @@ -1606,8 +1606,9 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) * invoke the external script to do its magic. */ - str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s %s", - "hv_set_ifconfig", if_filename, nm_filename); + str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s", + KVP_SCRIPTS_PATH "hv_set_ifconfig", + if_filename, nm_filename); /* * This is a little overcautious, but it's necessary to suppress some * false warnings from gcc 8.0.1. diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index 440a91b35823..2f8baed2b8f7 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1 cp $1 /etc/sysconfig/network-scripts/ -chmod 600 $2 +umask 0177 interface=$(echo $2 | awk -F - '{ print $2 }') filename="${2##*/}" diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index 8073c9e4fe46..cccf62ea2b8f 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -63,6 +63,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_DELTA_VELOCITY] = "deltavelocity", [IIO_COLORTEMP] = "colortemp", [IIO_CHROMATICITY] = "chromaticity", + [IIO_ATTENTION] = "attention", }; static const char * const iio_ev_type_text[] = { @@ -183,6 +184,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_DELTA_VELOCITY: case IIO_COLORTEMP: case IIO_CHROMATICITY: + case IIO_ATTENTION: break; default: return false; @@ -449,6 +451,7 @@ error_free_chrdev_name: enable_events(dev_dir_name, 0); free(chrdev_name); + free(dev_dir_name); return ret; } diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h index 406f7718f9ad..51d2556af54a 100644 --- a/tools/include/uapi/asm-generic/mman.h +++ b/tools/include/uapi/asm-generic/mman.h @@ -19,4 +19,8 @@ #define MCL_FUTURE 2 /* lock all future mappings */ #define MCL_ONFAULT 4 /* lock all pages that are faulted in */ +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) /* Set up a restore token in the shadow stack */ +#define SHADOW_STACK_SET_MARKER (1ULL << 1) /* Set up a top of stack marker in the shadow stack */ + + #endif /* __ASM_GENERIC_MMAN_H */ diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index 281df9139d2b..ffff554a5230 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -126,6 +126,8 @@ #define SCM_TS_OPT_ID 78 +#define SO_RCVPRIORITY 79 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 5bf6148cac2b..88dc393c2bca 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -841,8 +841,17 @@ __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) #define __NR_mseal 462 __SYSCALL(__NR_mseal, sys_mseal) +#define __NR_setxattrat 463 +__SYSCALL(__NR_setxattrat, sys_setxattrat) +#define __NR_getxattrat 464 +__SYSCALL(__NR_getxattrat, sys_getxattrat) +#define __NR_listxattrat 465 +__SYSCALL(__NR_listxattrat, sys_listxattrat) +#define __NR_removexattrat 466 +__SYSCALL(__NR_removexattrat, sys_removexattrat) + #undef __NR_syscalls -#define __NR_syscalls 463 +#define __NR_syscalls 467 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 16122819edfe..7fba37b94401 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -1024,6 +1024,13 @@ struct drm_crtc_queue_sequence { __u64 user_data; /* user data passed to event */ }; +#define DRM_CLIENT_NAME_MAX_LEN 64 +struct drm_set_client_name { + __u64 name_len; + __u64 name; +}; + + #if defined(__cplusplus) } #endif @@ -1288,6 +1295,16 @@ extern "C" { */ #define DRM_IOCTL_MODE_CLOSEFB DRM_IOWR(0xD0, struct drm_mode_closefb) +/** + * DRM_IOCTL_SET_CLIENT_NAME - Attach a name to a drm_file + * + * Having a name allows for easier tracking and debugging. + * The length of the name (without null ending char) must be + * <= DRM_CLIENT_NAME_MAX_LEN. + * The call will fail if the name contains whitespaces or non-printable chars. + */ +#define DRM_IOCTL_SET_CLIENT_NAME DRM_IOWR(0xD1, struct drm_set_client_name) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8516c1ccd57a..7e46ca4cd31b 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -1315,6 +1315,8 @@ enum { IFLA_NETKIT_MODE, IFLA_NETKIT_SCRUB, IFLA_NETKIT_PEER_SCRUB, + IFLA_NETKIT_HEADROOM, + IFLA_NETKIT_TAILROOM, __IFLA_NETKIT_MAX, }; #define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 637efc055145..502ea63b5d2e 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1158,7 +1158,15 @@ enum kvm_device_type { #define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_RISCV_AIA, #define KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_RISCV_AIA + KVM_DEV_TYPE_LOONGARCH_IPI, +#define KVM_DEV_TYPE_LOONGARCH_IPI KVM_DEV_TYPE_LOONGARCH_IPI + KVM_DEV_TYPE_LOONGARCH_EIOINTC, +#define KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_EIOINTC + KVM_DEV_TYPE_LOONGARCH_PCHPIC, +#define KVM_DEV_TYPE_LOONGARCH_PCHPIC KVM_DEV_TYPE_LOONGARCH_PCHPIC + KVM_DEV_TYPE_MAX, + }; struct kvm_vfio_spapr_tce { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 4842c36fdf80..0524d541d4e3 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -511,7 +511,16 @@ struct perf_event_attr { __u16 sample_max_stack; __u16 __reserved_2; __u32 aux_sample_size; - __u32 __reserved_3; + + union { + __u32 aux_action; + struct { + __u32 aux_start_paused : 1, /* start AUX area tracing paused */ + aux_pause : 1, /* on overflow, pause AUX area tracing */ + aux_resume : 1, /* on overflow, resume AUX area tracing */ + __reserved_3 : 29; + }; + }; /* * User provided data if sigtrap=1, passed back to user via diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h index bb6ea517efb5..c53cde425406 100644 --- a/tools/include/uapi/linux/stddef.h +++ b/tools/include/uapi/linux/stddef.h @@ -8,6 +8,13 @@ #define __always_inline __inline__ #endif +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + /** * __struct_group() - Create a mirrored named and anonyomous struct * @@ -20,14 +27,14 @@ * and size: one anonymous and one named. The former's members can be used * normally without sub-struct naming, and the latter can be used to * reason about the start, end, and size of the group of struct members. - * The named struct can also be explicitly tagged for layer reuse, as well - * as both having struct attributes appended. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. */ #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ union { \ struct { MEMBERS } ATTRS; \ - struct TAG { MEMBERS } ATTRS NAME; \ - } + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ + } ATTRS /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index c6d67fc9e57e..83c43dc13313 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -47,6 +47,20 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, */ perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus); + + /* + * Empty cpu lists would eventually get opened as "any" so remove + * genuinely empty ones before they're opened in the wrong place. + */ + if (perf_cpu_map__is_empty(evsel->cpus)) { + struct perf_evsel *next = perf_evlist__next(evlist, evsel); + + perf_evlist__remove(evlist, evsel); + /* Keep idx contiguous */ + if (next) + list_for_each_entry_from(next, &evlist->entries, node) + next->idx--; + } } else if (!evsel->own_cpus || evlist->has_user_cpus || (!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) { /* @@ -80,11 +94,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { - struct perf_evsel *evsel; + struct perf_evsel *evsel, *n; evlist->needs_map_propagation = true; - perf_evlist__for_each_evsel(evlist, evsel) + list_for_each_entry_safe(evsel, n, &evlist->entries, node) __perf_evlist__propagate_maps(evlist, evsel); } diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index d1cdf2a8f826..211df5a93ad9 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -1,5 +1,17 @@ # SPDX-License-Identifier: GPL-2.0 +include ../../scripts/Makefile.arch + +INSTALL ?= install +prefix ?= /usr +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif +libdir ?= $(prefix)/$(libdir_relative) +includedir ?= $(prefix)/include + SUBDIRS = lib generated samples all: $(SUBDIRS) libynl.a @@ -21,5 +33,20 @@ clean distclean: fi \ done rm -f libynl.a + rm -rf pyynl/__pycache__ + rm -rf pyynl/lib/__pycache__ + rm -rf pyynl.egg-info + rm -rf build + +install: libynl.a lib/*.h + @echo -e "\tINSTALL libynl.a" + @$(INSTALL) -d $(DESTDIR)$(libdir) + @$(INSTALL) -m 0644 libynl.a $(DESTDIR)$(libdir)/libynl.a + @echo -e "\tINSTALL libynl headers" + @$(INSTALL) -d $(DESTDIR)$(includedir)/ynl + @$(INSTALL) -m 0644 lib/*.h $(DESTDIR)$(includedir)/ynl/ + @echo -e "\tINSTALL pyynl" + @pip install --prefix=$(DESTDIR)$(prefix) . + @make -C generated install -.PHONY: all clean distclean $(SUBDIRS) +.PHONY: all clean distclean install $(SUBDIRS) diff --git a/tools/net/ynl/generated/.gitignore b/tools/net/ynl/generated/.gitignore index ade488626d26..859a6fb446e1 100644 --- a/tools/net/ynl/generated/.gitignore +++ b/tools/net/ynl/generated/.gitignore @@ -1,2 +1,3 @@ *-user.c *-user.h +*.rst diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile index 7db5240de58a..21f9e299dc75 100644 --- a/tools/net/ynl/generated/Makefile +++ b/tools/net/ynl/generated/Makefile @@ -7,32 +7,44 @@ ifeq ("$(DEBUG)","1") CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan endif +INSTALL ?= install +prefix ?= /usr +datarootdir ?= $(prefix)/share +docdir ?= $(datarootdir)/doc +includedir ?= $(prefix)/include + include ../Makefile.deps YNL_GEN_ARG_ethtool:=--user-header linux/ethtool_netlink.h \ --exclude-op stats-get -TOOL:=../ynl-gen-c.py +TOOL:=../pyynl/ynl_gen_c.py +TOOL_RST:=../pyynl/ynl_gen_rst.py +SPECS_DIR:=../../../../Documentation/netlink/specs GENS_PATHS=$(shell grep -nrI --files-without-match \ 'protocol: netlink' \ - ../../../../Documentation/netlink/specs/) -GENS=$(patsubst ../../../../Documentation/netlink/specs/%.yaml,%,${GENS_PATHS}) + $(SPECS_DIR)) +GENS=$(patsubst $(SPECS_DIR)/%.yaml,%,${GENS_PATHS}) SRCS=$(patsubst %,%-user.c,${GENS}) HDRS=$(patsubst %,%-user.h,${GENS}) OBJS=$(patsubst %,%-user.o,${GENS}) -all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI) +SPECS_PATHS=$(wildcard $(SPECS_DIR)/*.yaml) +SPECS=$(patsubst $(SPECS_DIR)/%.yaml,%,${SPECS_PATHS}) +RSTS=$(patsubst %,%.rst,${SPECS}) + +all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI) $(RSTS) protos.a: $(OBJS) @echo -e "\tAR $@" @ar rcs $@ $(OBJS) -%-user.h: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) +%-user.h: $(SPECS_DIR)/%.yaml $(TOOL) @echo -e "\tGEN $@" @$(TOOL) --mode user --header --spec $< -o $@ $(YNL_GEN_ARG_$*) -%-user.c: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) +%-user.c: $(SPECS_DIR)/%.yaml $(TOOL) @echo -e "\tGEN $@" @$(TOOL) --mode user --source --spec $< -o $@ $(YNL_GEN_ARG_$*) @@ -40,14 +52,37 @@ protos.a: $(OBJS) @echo -e "\tCC $@" @$(COMPILE.c) $(CFLAGS_$*) -o $@ $< +%.rst: $(SPECS_DIR)/%.yaml $(TOOL_RST) + @echo -e "\tGEN_RST $@" + @$(TOOL_RST) -o $@ -i $< + clean: rm -f *.o distclean: clean - rm -f *.c *.h *.a + rm -f *.c *.h *.a *.rst regen: @../ynl-regen.sh -.PHONY: all clean distclean regen +install-headers: $(HDRS) + @echo -e "\tINSTALL generated headers" + @$(INSTALL) -d $(DESTDIR)$(includedir)/ynl + @$(INSTALL) -m 0644 *.h $(DESTDIR)$(includedir)/ynl/ + +install-rsts: $(RSTS) + @echo -e "\tINSTALL generated docs" + @$(INSTALL) -d $(DESTDIR)$(docdir)/ynl + @$(INSTALL) -m 0644 $(RSTS) $(DESTDIR)$(docdir)/ynl/ + +install-specs: + @echo -e "\tINSTALL specs" + @$(INSTALL) -d $(DESTDIR)$(datarootdir)/ynl + @$(INSTALL) -m 0644 ../../../../Documentation/netlink/*.yaml $(DESTDIR)$(datarootdir)/ynl/ + @$(INSTALL) -d $(DESTDIR)$(datarootdir)/ynl/specs + @$(INSTALL) -m 0644 $(SPECS_DIR)/*.yaml $(DESTDIR)$(datarootdir)/ynl/specs/ + +install: install-headers install-rsts install-specs + +.PHONY: all clean distclean regen install install-headers install-rsts install-specs .DEFAULT_GOAL: all diff --git a/tools/net/ynl/lib/.gitignore b/tools/net/ynl/lib/.gitignore index 296c4035dbf2..a4383358ec72 100644 --- a/tools/net/ynl/lib/.gitignore +++ b/tools/net/ynl/lib/.gitignore @@ -1,2 +1 @@ -__pycache__/ *.d diff --git a/tools/net/ynl/lib/Makefile b/tools/net/ynl/lib/Makefile index 94c49cca3dca..4b2b98704ff9 100644 --- a/tools/net/ynl/lib/Makefile +++ b/tools/net/ynl/lib/Makefile @@ -19,7 +19,6 @@ ynl.a: $(OBJS) clean: rm -f *.o *.d *~ - rm -rf __pycache__ distclean: clean rm -f *.a diff --git a/tools/net/ynl/pyproject.toml b/tools/net/ynl/pyproject.toml new file mode 100644 index 000000000000..a81d8779b0e0 --- /dev/null +++ b/tools/net/ynl/pyproject.toml @@ -0,0 +1,24 @@ +[build-system] +requires = ["setuptools>=61.0"] +build-backend = "setuptools.build_meta" + +[project] +name = "pyynl" +authors = [ + {name = "Donald Hunter", email = "donald.hunter@gmail.com"}, + {name = "Jakub Kicinski", email = "kuba@kernel.org"}, +] +description = "yaml netlink (ynl)" +version = "0.0.1" +requires-python = ">=3.9" +dependencies = [ + "pyyaml==6.*", + "jsonschema==4.*" +] + +[tool.setuptools.packages.find] +include = ["pyynl", "pyynl.lib"] + +[project.scripts] +ynl = "pyynl.cli:main" +ynl-ethtool = "pyynl.ethtool:main" diff --git a/tools/net/ynl/pyynl/.gitignore b/tools/net/ynl/pyynl/.gitignore new file mode 100644 index 000000000000..b801cd2d016e --- /dev/null +++ b/tools/net/ynl/pyynl/.gitignore @@ -0,0 +1,2 @@ +__pycache__/ +lib/__pycache__/ diff --git a/tools/net/ynl/pyynl/__init__.py b/tools/net/ynl/pyynl/__init__.py new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/net/ynl/pyynl/__init__.py diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/pyynl/cli.py index 41d9fa5c818d..41d9fa5c818d 100755 --- a/tools/net/ynl/cli.py +++ b/tools/net/ynl/pyynl/cli.py diff --git a/tools/net/ynl/ethtool.py b/tools/net/ynl/pyynl/ethtool.py index ebb0a11f67bf..ebb0a11f67bf 100755 --- a/tools/net/ynl/ethtool.py +++ b/tools/net/ynl/pyynl/ethtool.py diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/pyynl/lib/__init__.py index 9137b83e580a..9137b83e580a 100644 --- a/tools/net/ynl/lib/__init__.py +++ b/tools/net/ynl/pyynl/lib/__init__.py diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/pyynl/lib/nlspec.py index a745739655ad..314ec8007496 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/pyynl/lib/nlspec.py @@ -219,7 +219,10 @@ class SpecAttrSet(SpecElement): else: real_set = family.attr_sets[self.subset_of] for elem in self.yaml['attributes']: - attr = real_set[elem['name']] + real_attr = real_set[elem['name']] + combined_elem = real_attr.yaml | elem + attr = self.new_attr(combined_elem, real_attr.value) + self.attrs[attr.name] = attr self.attrs_by_val[attr.value] = attr diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 01ec01a90e76..08f8bf89cfc2 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -556,10 +556,10 @@ class YnlFamily(SpecFamily): if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED attr_payload = b'' - sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs) + sub_space = attr['nested-attributes'] + sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs) for subname, subvalue in value.items(): - attr_payload += self._add_attr(attr['nested-attributes'], - subname, subvalue, sub_attrs) + attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs) elif attr["type"] == 'flag': if not value: # If value is absent or false then skip attribute creation. @@ -733,41 +733,45 @@ class YnlFamily(SpecFamily): self._rsp_add(rsp, attr_name, None, self._decode_unknown(attr)) continue - if attr_spec["type"] == 'nest': - subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'], search_attrs) - decoded = subdict - elif attr_spec["type"] == 'string': - decoded = attr.as_strz() - elif attr_spec["type"] == 'binary': - decoded = self._decode_binary(attr, attr_spec) - elif attr_spec["type"] == 'flag': - decoded = True - elif attr_spec.is_auto_scalar: - decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order) - elif attr_spec["type"] in NlAttr.type_formats: - decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) - if 'enum' in attr_spec: - decoded = self._decode_enum(decoded, attr_spec) - elif attr_spec.display_hint: - decoded = self._formatted_string(decoded, attr_spec.display_hint) - elif attr_spec["type"] == 'indexed-array': - decoded = self._decode_array_attr(attr, attr_spec) - elif attr_spec["type"] == 'bitfield32': - value, selector = struct.unpack("II", attr.raw) - if 'enum' in attr_spec: - value = self._decode_enum(value, attr_spec) - selector = self._decode_enum(selector, attr_spec) - decoded = {"value": value, "selector": selector} - elif attr_spec["type"] == 'sub-message': - decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) - elif attr_spec["type"] == 'nest-type-value': - decoded = self._decode_nest_type_value(attr, attr_spec) - else: - if not self.process_unknown: - raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') - decoded = self._decode_unknown(attr) - - self._rsp_add(rsp, attr_spec["name"], attr_spec.is_multi, decoded) + try: + if attr_spec["type"] == 'nest': + subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'], search_attrs) + decoded = subdict + elif attr_spec["type"] == 'string': + decoded = attr.as_strz() + elif attr_spec["type"] == 'binary': + decoded = self._decode_binary(attr, attr_spec) + elif attr_spec["type"] == 'flag': + decoded = True + elif attr_spec.is_auto_scalar: + decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order) + elif attr_spec["type"] in NlAttr.type_formats: + decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) + if 'enum' in attr_spec: + decoded = self._decode_enum(decoded, attr_spec) + elif attr_spec.display_hint: + decoded = self._formatted_string(decoded, attr_spec.display_hint) + elif attr_spec["type"] == 'indexed-array': + decoded = self._decode_array_attr(attr, attr_spec) + elif attr_spec["type"] == 'bitfield32': + value, selector = struct.unpack("II", attr.raw) + if 'enum' in attr_spec: + value = self._decode_enum(value, attr_spec) + selector = self._decode_enum(selector, attr_spec) + decoded = {"value": value, "selector": selector} + elif attr_spec["type"] == 'sub-message': + decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) + elif attr_spec["type"] == 'nest-type-value': + decoded = self._decode_nest_type_value(attr, attr_spec) + else: + if not self.process_unknown: + raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') + decoded = self._decode_unknown(attr) + + self._rsp_add(rsp, attr_spec["name"], attr_spec.is_multi, decoded) + except: + print(f"Error decoding '{attr_spec.name}' from '{space}'") + raise return rsp diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index d8201c4b1520..d3a7dfbcf929 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -79,6 +79,20 @@ class Type(SpecAttr): self.enum_name = None delattr(self, "enum_name") + def _get_real_attr(self): + # if the attr is for a subset return the "real" attr (just one down, does not recurse) + return self.family.attr_sets[self.attr_set.subset_of][self.name] + + def set_request(self): + self.request = True + if self.attr_set.subset_of: + self._get_real_attr().set_request() + + def set_reply(self): + self.reply = True + if self.attr_set.subset_of: + self._get_real_attr().set_reply() + def get_limit(self, limit, default=None): value = self.checks.get(limit, default) if value is None: @@ -106,6 +120,10 @@ class Type(SpecAttr): enum_name = f"{self.attr_set.name_prefix}{self.name}" self.enum_name = c_upper(enum_name) + if self.attr_set.subset_of: + if self.checks != self._get_real_attr().checks: + raise Exception("Overriding checks not supported by codegen, yet") + def is_multi_val(self): return None @@ -801,6 +819,8 @@ class EnumSet(SpecEnumSet): self.user_type = 'int' self.value_pfx = yaml.get('name-prefix', f"{family.ident_name}-{yaml['name']}-") + self.header = yaml.get('header', None) + self.enum_cnt_name = yaml.get('enum-cnt-name', None) super().__init__(family, yaml) @@ -1117,17 +1137,17 @@ class Family(SpecFamily): for _, struct in self.pure_nested_structs.items(): if struct.request: for _, arg in struct.member_list(): - arg.request = True + arg.set_request() if struct.reply: for _, arg in struct.member_list(): - arg.reply = True + arg.set_reply() for root_set, rs_members in self.root_sets.items(): for attr, spec in self.attr_sets[root_set].items(): if attr in rs_members['request']: - spec.request = True + spec.set_request() if attr in rs_members['reply']: - spec.reply = True + spec.set_reply() def _load_global_policy(self): global_set = set() @@ -1763,7 +1783,14 @@ def parse_rsp_nested(ri, struct): f'{struct.ptr_name}dst = yarg->data;'] init_lines = [] - _multi_parse(ri, struct, init_lines, local_vars) + if struct.member_list(): + _multi_parse(ri, struct, init_lines, local_vars) + else: + # Empty nest + ri.cw.block_start() + ri.cw.p('return 0;') + ri.cw.block_end() + ri.cw.nl() def parse_rsp_msg(ri, deref=False): @@ -2417,6 +2444,87 @@ def uapi_enum_start(family, cw, obj, ckey='', enum_name='enum-name'): cw.block_start(line=start_line) +def render_uapi_unified(family, cw, max_by_define, separate_ntf): + max_name = c_upper(family.get('cmd-max-name', f"{family.op_prefix}MAX")) + cnt_name = c_upper(family.get('cmd-cnt-name', f"__{family.op_prefix}MAX")) + max_value = f"({cnt_name} - 1)" + + uapi_enum_start(family, cw, family['operations'], 'enum-name') + val = 0 + for op in family.msgs.values(): + if separate_ntf and ('notify' in op or 'event' in op): + continue + + suffix = ',' + if op.value != val: + suffix = f" = {op.value}," + val = op.value + cw.p(op.enum_name + suffix) + val += 1 + cw.nl() + cw.p(cnt_name + ('' if max_by_define else ',')) + if not max_by_define: + cw.p(f"{max_name} = {max_value}") + cw.block_end(line=';') + if max_by_define: + cw.p(f"#define {max_name} {max_value}") + cw.nl() + + +def render_uapi_directional(family, cw, max_by_define): + max_name = f"{family.op_prefix}USER_MAX" + cnt_name = f"__{family.op_prefix}USER_CNT" + max_value = f"({cnt_name} - 1)" + + cw.block_start(line='enum') + cw.p(c_upper(f'{family.name}_MSG_USER_NONE = 0,')) + val = 0 + for op in family.msgs.values(): + if 'do' in op and 'event' not in op: + suffix = ',' + if op.value and op.value != val: + suffix = f" = {op.value}," + val = op.value + cw.p(op.enum_name + suffix) + val += 1 + cw.nl() + cw.p(cnt_name + ('' if max_by_define else ',')) + if not max_by_define: + cw.p(f"{max_name} = {max_value}") + cw.block_end(line=';') + if max_by_define: + cw.p(f"#define {max_name} {max_value}") + cw.nl() + + max_name = f"{family.op_prefix}KERNEL_MAX" + cnt_name = f"__{family.op_prefix}KERNEL_CNT" + max_value = f"({cnt_name} - 1)" + + cw.block_start(line='enum') + cw.p(c_upper(f'{family.name}_MSG_KERNEL_NONE = 0,')) + val = 0 + for op in family.msgs.values(): + if ('do' in op and 'reply' in op['do']) or 'notify' in op or 'event' in op: + enum_name = op.enum_name + if 'event' not in op and 'notify' not in op: + enum_name = f'{enum_name}_REPLY' + + suffix = ',' + if op.value and op.value != val: + suffix = f" = {op.value}," + val = op.value + cw.p(enum_name + suffix) + val += 1 + cw.nl() + cw.p(cnt_name + ('' if max_by_define else ',')) + if not max_by_define: + cw.p(f"{max_name} = {max_value}") + cw.block_end(line=';') + if max_by_define: + cw.p(f"#define {max_name} {max_value}") + cw.nl() + + def render_uapi(family, cw): hdr_prot = f"_UAPI_LINUX_{c_upper(family.uapi_header_name)}_H" hdr_prot = hdr_prot.replace('/', '_') @@ -2440,6 +2548,9 @@ def render_uapi(family, cw): if const['type'] == 'enum' or const['type'] == 'flags': enum = family.consts[const['name']] + if enum.header: + continue + if enum.has_doc(): if enum.has_entry_doc(): cw.p('/**') @@ -2472,9 +2583,12 @@ def render_uapi(family, cw): max_val = f' = {enum.get_mask()},' cw.p(max_name + max_val) else: + cnt_name = enum.enum_cnt_name max_name = c_upper(name_pfx + 'max') - cw.p('__' + max_name + ',') - cw.p(max_name + ' = (__' + max_name + ' - 1)') + if not cnt_name: + cnt_name = '__' + name_pfx + 'max' + cw.p(c_upper(cnt_name) + ',') + cw.p(max_name + ' = (' + c_upper(cnt_name) + ' - 1)') cw.block_end(line=';') cw.nl() elif const['type'] == 'const': @@ -2503,7 +2617,8 @@ def render_uapi(family, cw): val = attr.value val += 1 cw.p(attr.enum_name + suffix) - cw.nl() + if attr_set.items(): + cw.nl() cw.p(attr_set.cnt_name + ('' if max_by_define else ',')) if not max_by_define: cw.p(f"{attr_set.max_name} = {max_value}") @@ -2515,30 +2630,12 @@ def render_uapi(family, cw): # Commands separate_ntf = 'async-prefix' in family['operations'] - max_name = c_upper(family.get('cmd-max-name', f"{family.op_prefix}MAX")) - cnt_name = c_upper(family.get('cmd-cnt-name', f"__{family.op_prefix}MAX")) - max_value = f"({cnt_name} - 1)" - - uapi_enum_start(family, cw, family['operations'], 'enum-name') - val = 0 - for op in family.msgs.values(): - if separate_ntf and ('notify' in op or 'event' in op): - continue - - suffix = ',' - if op.value != val: - suffix = f" = {op.value}," - val = op.value - cw.p(op.enum_name + suffix) - val += 1 - cw.nl() - cw.p(cnt_name + ('' if max_by_define else ',')) - if not max_by_define: - cw.p(f"{max_name} = {max_value}") - cw.block_end(line=';') - if max_by_define: - cw.p(f"#define {max_name} {max_value}") - cw.nl() + if family.msg_id_model == 'unified': + render_uapi_unified(family, cw, max_by_define, separate_ntf) + elif family.msg_id_model == 'directional': + render_uapi_directional(family, cw, max_by_define) + else: + raise Exception(f'Unsupported message enum-model {family.msg_id_model}') if separate_ntf: uapi_enum_start(family, cw, family['operations'], enum_name='async-enum') @@ -2635,7 +2732,8 @@ def find_kernel_root(full_path): def main(): parser = argparse.ArgumentParser(description='Netlink simple parsing generator') - parser.add_argument('--mode', dest='mode', type=str, required=True) + parser.add_argument('--mode', dest='mode', type=str, required=True, + choices=('user', 'kernel', 'uapi')) parser.add_argument('--spec', dest='spec', type=str, required=True) parser.add_argument('--header', dest='header', action='store_true', default=None) parser.add_argument('--source', dest='header', action='store_false') @@ -2662,13 +2760,6 @@ def main(): os.sys.exit(1) return - supported_models = ['unified'] - if args.mode in ['user', 'kernel']: - supported_models += ['directional'] - if parsed.msg_id_model not in supported_models: - print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation') - os.sys.exit(1) - cw = CodeWriter(BaseNlLib(), args.out_file, overwrite=(not args.cmp_out)) _, spec_kernel = find_kernel_root(args.spec) @@ -2696,7 +2787,10 @@ def main(): cw.p('#define ' + hdr_prot) cw.nl() - hdr_file=os.path.basename(args.out_file[:-2]) + ".h" + if args.out_file: + hdr_file = os.path.basename(args.out_file[:-2]) + ".h" + else: + hdr_file = "generated_header_file.h" if args.mode == 'kernel': cw.p('#include <net/netlink.h>') @@ -2718,12 +2812,17 @@ def main(): else: cw.p(f'#include "{hdr_file}"') cw.p('#include "ynl.h"') - headers = [parsed.uapi_header] + headers = [] for definition in parsed['definitions']: if 'header' in definition: headers.append(definition['header']) + if args.mode == 'user': + headers.append(parsed.uapi_header) + seen_header = [] for one in headers: - cw.p(f"#include <{one}>") + if one not in seen_header: + cw.p(f"#include <{one}>") + seen_header.append(one) cw.nl() if args.mode == "user": diff --git a/tools/net/ynl/ynl-gen-rst.py b/tools/net/ynl/pyynl/ynl_gen_rst.py index 6c56d0d726b4..6c56d0d726b4 100755 --- a/tools/net/ynl/ynl-gen-rst.py +++ b/tools/net/ynl/pyynl/ynl_gen_rst.py diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index a37304dcc88e..81b4ecd89100 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause -TOOL=$(dirname $(realpath $0))/ynl-gen-c.py +TOOL=$(dirname $(realpath $0))/pyynl/ynl_gen_c.py force= search= diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f7586f82b967..76060da755b5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_CONTEXT_SWITCH: - if (func && (!next_insn || !next_insn->hint)) { - WARN_INSN(insn, "unsupported instruction in callable function"); - return 1; + if (func) { + if (!next_insn || !next_insn->hint) { + WARN_INSN(insn, "unsupported instruction in callable function"); + return 1; + } + break; } return 0; @@ -4573,6 +4576,8 @@ static int validate_ibt(struct objtool_file *file) !strcmp(sec->name, "__jump_table") || !strcmp(sec->name, "__mcount_loc") || !strcmp(sec->name, ".kcfi_traps") || + !strcmp(sec->name, ".llvm.call-graph-profile") || + !strcmp(sec->name, ".llvm_bb_addr_map") || !strcmp(sec->name, "__tracepoints") || strstr(sec->name, "__patchable_function_entries")) continue; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 3d27983dc908..6f64d611faea 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -224,12 +224,17 @@ int find_symbol_hole_containing(const struct section *sec, unsigned long offset) if (n) return 0; /* not a hole */ - /* didn't find a symbol for which @offset is after it */ - if (!hole.sym) - return 0; /* not a hole */ + /* + * @offset >= sym->offset + sym->len, find symbol after it. + * When hole.sym is empty, use the first node to compute the hole. + * If there is no symbol in the section, the first node will be NULL, + * in which case, -1 is returned to skip the whole section. + */ + if (hole.sym) + n = rb_next(&hole.sym->node); + else + n = rb_first_cached(&sec->symbol_tree); - /* @offset >= sym->offset + sym->len, find symbol after it */ - n = rb_next(&hole.sym->node); if (!n) return -1; /* until end of address space */ diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index f37614cc2c1b..b2174894f9f7 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -19,6 +19,7 @@ NORETURN(__x64_sys_exit_group) NORETURN(arch_cpu_idle_dead) NORETURN(bch2_trans_in_restart_error) NORETURN(bch2_trans_restart_error) +NORETURN(bch2_trans_unlocked_error) NORETURN(cpu_bringup_and_idle) NORETURN(cpu_startup_entry) NORETURN(do_exit) diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 1464c6be6eb3..c844cd5cda62 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -377,3 +377,7 @@ 460 n64 lsm_set_self_attr sys_lsm_set_self_attr 461 n64 lsm_list_modules sys_lsm_list_modules 462 n64 mseal sys_mseal +463 n64 setxattrat sys_setxattrat +464 n64 getxattrat sys_getxattrat +465 n64 listxattrat sys_listxattrat +466 n64 removexattrat sys_removexattrat diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index ebae8415dfbb..d8b4ab78bef0 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -553,3 +553,7 @@ 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules 462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 01071182763e..e9115b4d8b63 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -465,3 +465,7 @@ 460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules 462 common mseal sys_mseal sys_mseal +463 common setxattrat sys_setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat sys_removexattrat diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl index 534c74b14fab..4d0fb2fba7e2 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl @@ -468,3 +468,7 @@ 460 i386 lsm_set_self_attr sys_lsm_set_self_attr 461 i386 lsm_list_modules sys_lsm_list_modules 462 i386 mseal sys_mseal +463 i386 setxattrat sys_setxattrat +464 i386 getxattrat sys_getxattrat +465 i386 listxattrat sys_listxattrat +466 i386 removexattrat sys_removexattrat diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 7093ee21c0d1..5eb708bff1c7 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -386,6 +386,10 @@ 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules 462 common mseal sys_mseal +463 common setxattrat sys_setxattrat +464 common getxattrat sys_getxattrat +465 common listxattrat sys_listxattrat +466 common removexattrat sys_removexattrat # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 272d3c70810e..a56cf8b0a7d4 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1151,8 +1151,9 @@ static int cmp_profile_data(const void *a, const void *b) if (v1 > v2) return -1; - else + if (v1 < v2) return 1; + return 0; } static void print_profile_result(struct perf_ftrace *ftrace) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 8dcf74d3c0a3..4751dd3c6f67 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -508,7 +508,7 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], for (size_t x = 0; x < num_tests; x++) { struct child_test *child_test = child_tests[x]; - if (!child_test) + if (!child_test || child_test->process.pid <= 0) continue; pr_debug3("Killing %d pid %d\n", diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 41ff1affdfcd..726cf8d4da28 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -75,14 +75,12 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u double val, num_cpus_online, num_cpus, num_cores, num_dies, num_packages; int ret; struct expr_parse_ctx *ctx; - bool is_intel = false; char strcmp_cpuid_buf[256]; struct perf_cpu cpu = {-1}; char *cpuid = get_cpuid_allow_env_override(cpu); char *escaped_cpuid1, *escaped_cpuid2; TEST_ASSERT_VAL("get_cpuid", cpuid); - is_intel = strstr(cpuid, "Intel") != NULL; TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0); @@ -245,12 +243,19 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u if (num_dies) // Some platforms do not have CPU die support, for example s390 TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); - TEST_ASSERT_VAL("#system_tsc_freq", expr__parse(&val, ctx, "#system_tsc_freq") == 0); - if (is_intel) - TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0); - else - TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO); + if (expr__parse(&val, ctx, "#system_tsc_freq") == 0) { + bool is_intel = strstr(cpuid, "Intel") != NULL; + + if (is_intel) + TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0); + else + TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO); + } else { +#if defined(__i386__) || defined(__x86_64__) + TEST_ASSERT_VAL("#system_tsc_freq unsupported", 0); +#endif + } /* * Source count returns the number of events aggregating in a leader * event including the leader. Check parsing yields an id. diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c index f8bcee9660d5..d2b066a2b557 100644 --- a/tools/perf/tests/hwmon_pmu.c +++ b/tools/perf/tests/hwmon_pmu.c @@ -65,7 +65,7 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz) { "temp2_label", "test hwmon event2\n", }, { "temp2_input", "50000\n", }, }; - int dirfd, file; + int hwmon_dirfd = -1, test_dirfd = -1, file; struct perf_pmu *hwm = NULL; ssize_t len; @@ -76,19 +76,24 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz) dir[0] = '\0'; return NULL; } - dirfd = open(dir, O_DIRECTORY); - if (dirfd < 0) { + test_dirfd = open(dir, O_PATH|O_DIRECTORY); + if (test_dirfd < 0) { pr_err("Failed to open test directory \"%s\"\n", dir); goto err_out; } /* Create the test hwmon directory and give it a name. */ - if (mkdirat(dirfd, "hwmon1234", 0755) < 0) { + if (mkdirat(test_dirfd, "hwmon1234", 0755) < 0) { pr_err("Failed to mkdir hwmon directory\n"); goto err_out; } - file = openat(dirfd, "hwmon1234/name", O_WRONLY | O_CREAT, 0600); - if (!file) { + hwmon_dirfd = openat(test_dirfd, "hwmon1234", O_DIRECTORY); + if (hwmon_dirfd < 0) { + pr_err("Failed to open test hwmon directory \"%s/hwmon1234\"\n", dir); + goto err_out; + } + file = openat(hwmon_dirfd, "name", O_WRONLY | O_CREAT, 0600); + if (file < 0) { pr_err("Failed to open for writing file \"name\"\n"); goto err_out; } @@ -104,8 +109,8 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz) for (size_t i = 0; i < ARRAY_SIZE(test_items); i++) { const struct test_item *item = &test_items[i]; - file = openat(dirfd, item->name, O_WRONLY | O_CREAT, 0600); - if (!file) { + file = openat(hwmon_dirfd, item->name, O_WRONLY | O_CREAT, 0600); + if (file < 0) { pr_err("Failed to open for writing file \"%s\"\n", item->name); goto err_out; } @@ -119,16 +124,18 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz) } /* Make the PMU reading the files created above. */ - hwm = perf_pmus__add_test_hwmon_pmu(dirfd, "hwmon1234", test_hwmon_name); + hwm = perf_pmus__add_test_hwmon_pmu(hwmon_dirfd, "hwmon1234", test_hwmon_name); if (!hwm) pr_err("Test hwmon creation failed\n"); err_out: if (!hwm) { test_pmu_put(dir, hwm); - if (dirfd >= 0) - close(dirfd); + if (hwmon_dirfd >= 0) + close(hwmon_dirfd); } + if (test_dirfd >= 0) + close(test_dirfd); return hwm; } diff --git a/tools/perf/trace/beauty/fs_at_flags.sh b/tools/perf/trace/beauty/fs_at_flags.sh index e3f13f96a27c..fac4d0c049fc 100755 --- a/tools/perf/trace/beauty/fs_at_flags.sh +++ b/tools/perf/trace/beauty/fs_at_flags.sh @@ -13,13 +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_HANDLE_FID, AT_HANDLE_MNT_ID_UNIQUE and AT_HANDLE_CONNECTABLE 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 ${linux_fcntl} | \ grep -v AT_EACCESS | \ grep -v AT_STATX_SYNC_TYPE | \ grep -v AT_HANDLE_FID | \ grep -v AT_HANDLE_MNT_ID_UNIQUE | \ + grep -v AT_HANDLE_CONNECTABLE | \ grep -v AT_RENAME_NOREPLACE | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h index 87e2dec79fea..6e6907e63bfc 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h @@ -153,9 +153,6 @@ 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. */ - -#if defined(__KERNEL__) -#define AT_GETATTR_NOSEC 0x80000000 -#endif +#define AT_HANDLE_CONNECTABLE 0x002 /* Request a connectable file handle */ #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index 225bc366ffcb..c07008816aca 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -154,7 +154,7 @@ struct mount_attr { */ struct statmount { __u32 size; /* Total size, including strings */ - __u32 mnt_opts; /* [str] Mount options of the mount */ + __u32 mnt_opts; /* [str] Options (comma separated, escaped) */ __u64 mask; /* What results were written */ __u32 sb_dev_major; /* Device ID */ __u32 sb_dev_minor; @@ -173,7 +173,13 @@ struct statmount { __u32 mnt_root; /* [str] Root of mount relative to root of fs */ __u32 mnt_point; /* [str] Mountpoint relative to current root */ __u64 mnt_ns_id; /* ID of the mount namespace */ - __u64 __spare2[49]; + __u32 fs_subtype; /* [str] Subtype of fs_type (if any) */ + __u32 sb_source; /* [str] Source string of the mount */ + __u32 opt_num; /* Number of fs options */ + __u32 opt_array; /* [str] Array of nul terminated fs options */ + __u32 opt_sec_num; /* Number of security options */ + __u32 opt_sec_array; /* [str] Array of nul terminated security options */ + __u64 __spare2[46]; char str[]; /* Variable size part containing strings */ }; @@ -207,6 +213,10 @@ struct mnt_id_req { #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ #define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ #define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ +#define STATMOUNT_FS_SUBTYPE 0x00000100U /* Want/got fs_subtype */ +#define STATMOUNT_SB_SOURCE 0x00000200U /* Want/got sb_source */ +#define STATMOUNT_OPT_ARRAY 0x00000400U /* Want/got opt_... */ +#define STATMOUNT_OPT_SEC_ARRAY 0x00000800U /* Want/got opt_sec... */ /* * Special @mnt_id values that can be passed to listmount diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h index 35791791a879..5c6080680cb2 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h +++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h @@ -230,7 +230,7 @@ struct prctl_mm_map { # define PR_PAC_APDBKEY (1UL << 3) # define PR_PAC_APGAKEY (1UL << 4) -/* Tagged user address controls for arm64 */ +/* Tagged user address controls for arm64 and RISC-V */ #define PR_SET_TAGGED_ADDR_CTRL 55 #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) @@ -244,6 +244,9 @@ struct prctl_mm_map { # define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) /* Unused; kept only for source compatibility */ # define PR_MTE_TCF_SHIFT 1 +/* RISC-V pointer masking tag length */ +# define PR_PMLEN_SHIFT 24 +# define PR_PMLEN_MASK (0x7fUL << PR_PMLEN_SHIFT) /* Control reclaim behavior when allocating memory */ #define PR_SET_IO_FLUSHER 57 @@ -328,4 +331,26 @@ struct prctl_mm_map { # define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ # define PR_PPC_DEXCR_CTRL_MASK 0x1f +/* + * Get the current shadow stack configuration for the current thread, + * this will be the value configured via PR_SET_SHADOW_STACK_STATUS. + */ +#define PR_GET_SHADOW_STACK_STATUS 74 + +/* + * Set the current shadow stack configuration. Enabling the shadow + * stack will cause a shadow stack to be allocated for the thread. + */ +#define PR_SET_SHADOW_STACK_STATUS 75 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) +# define PR_SHADOW_STACK_WRITE (1UL << 1) +# define PR_SHADOW_STACK_PUSH (1UL << 2) + +/* + * Prevent further changes to the specified shadow stack + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_SHADOW_STACK_STATUS 76 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 8982f68e7230..e763e8d99a43 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -277,7 +277,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid struct perf_record_header_build_id b; size_t len; - len = sizeof(b) + name_len + 1; + len = name_len + 1; len = PERF_ALIGN(len, sizeof(u64)); memset(&b, 0, sizeof(b)); @@ -286,7 +286,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid misc |= PERF_RECORD_MISC_BUILD_ID_SIZE; b.pid = pid; b.header.misc = misc; - b.header.size = len; + b.header.size = sizeof(b) + len; err = do_write(fd, &b, sizeof(b)); if (err < 0) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f745723d486b..d22c5df1701e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2571,12 +2571,12 @@ try_fallback: if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit)) goto retry_open; - if (err == -EOPNOTSUPP && evsel__precise_ip_fallback(evsel)) - goto retry_open; - if (err == -EINVAL && evsel__detect_missing_features(evsel)) goto fallback_missing_features; + if (evsel__precise_ip_fallback(evsel)) + goto retry_open; + if (evsel__handle_error_quirks(evsel, err)) goto retry_open; diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c index e61429b38ba7..4acb9bb19b84 100644 --- a/tools/perf/util/hwmon_pmu.c +++ b/tools/perf/util/hwmon_pmu.c @@ -258,8 +258,12 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) if (pmu->pmu.sysfs_aliases_loaded) return 0; - /* Use a dup-ed fd as closedir will close it. */ - dup_fd = dup(pmu->hwmon_dir_fd); + /* + * Use a dup-ed fd as closedir will close it. Use openat so that the + * directory contents are refreshed. + */ + dup_fd = openat(pmu->hwmon_dir_fd, ".", O_DIRECTORY); + if (dup_fd == -1) return -ENOMEM; @@ -336,6 +340,9 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) close(fd); } } + if (hashmap__size(&pmu->events) == 0) + pr_debug2("hwmon_pmu: %s has no events\n", pmu->pmu.name); + hashmap__for_each_entry_safe((&pmu->events), cur, tmp, bkt) { union hwmon_pmu_event_key key = { .type_and_num = cur->key, @@ -343,8 +350,8 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu) struct hwmon_pmu_event_value *value = cur->pvalue; if (!test_bit(HWMON_ITEM_INPUT, value->items)) { - pr_debug("hwmon_pmu: removing event '%s%d' that has no input file\n", - hwmon_type_strs[key.type], key.num); + pr_debug("hwmon_pmu: %s removing event '%s%d' that has no input file\n", + pmu->pmu.name, hwmon_type_strs[key.type], key.num); hashmap__delete(&pmu->events, key.type_and_num, &key, &value); zfree(&value->label); zfree(&value->name); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 4f0ac998b0cc..27d5345d2b30 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -134,6 +134,8 @@ struct machine *machine__new_host(void) if (machine__create_kernel_maps(machine) < 0) goto out_delete; + + machine->env = &perf_env; } return machine; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 6d51a4c98ad7..eaa0318e9b87 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1370,7 +1370,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr) { char *buf = strdup(arg); char *p; - int err; + int err = 0; if (!buf) return -ENOMEM; diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 067717bce1d4..a7f7ed01421c 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -33,6 +33,9 @@ name as necessary to disambiguate it from others is necessary. Note that option msr0xXXX is a hex offset, eg. msr0x10 /sys/path... is an absolute path to a sysfs attribute <device> is a perf device from /sys/bus/event_source/devices/<device> eg. cstate_core + On Intel hybrid platforms, instead of one "cpu" perf device there are two, "cpu_core" and "cpu_atom" devices for P and E cores respectively. + Turbostat, in this case, allow user to use "cpu" device and will automatically detect the type of a CPU and translate it to "cpu_core" and "cpu_atom" accordingly. + For a complete example see "ADD PERF COUNTER EXAMPLE #2 (using virtual "cpu" device)". <event> is a perf event for given device from /sys/bus/event_source/devices/<device>/events/<event> eg. c1-residency perf/cstate_core/c1-residency would then use /sys/bus/event_source/devices/cstate_core/events/c1-residency @@ -187,6 +190,8 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors. .PP +\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). Disabled by default. Enable with --enable SysWatt. +.PP \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary. .PP \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM. @@ -387,6 +392,28 @@ CPU pCPU%c1 CPU%c1 .fi +.SH ADD PERF COUNTER EXAMPLE #2 (using virtual cpu device) +Here we run on hybrid, Raptor Lake platform. +We limit turbostat to show output for just cpu0 (pcore) and cpu12 (ecore). +We add a counter showing number of L3 cache misses, using virtual "cpu" device, +labeling it with the column header, "VCMISS". +We add a counter showing number of L3 cache misses, using virtual "cpu_core" device, +labeling it with the column header, "PCMISS". This will fail on ecore cpu12. +We add a counter showing number of L3 cache misses, using virtual "cpu_atom" device, +labeling it with the column header, "ECMISS". This will fail on pcore cpu0. +We display it only once, after the conclusion of 0.1 second sleep. +.nf +sudo ./turbostat --quiet --cpu 0,12 --show CPU --add perf/cpu/cache-misses,cpu,delta,raw,VCMISS --add perf/cpu_core/cache-misses,cpu,delta,raw,PCMISS --add perf/cpu_atom/cache-misses,cpu,delta,raw,ECMISS sleep .1 +turbostat: added_perf_counters_init_: perf/cpu_atom/cache-misses: failed to open counter on cpu0 +turbostat: added_perf_counters_init_: perf/cpu_core/cache-misses: failed to open counter on cpu12 +0.104630 sec +CPU ECMISS PCMISS VCMISS +- 0x0000000000000000 0x0000000000000000 0x0000000000000000 +0 0x0000000000000000 0x0000000000007951 0x0000000000007796 +12 0x000000000001137a 0x0000000000000000 0x0000000000011392 + +.fi + .SH ADD PMT COUNTER EXAMPLE Here we limit turbostat to showing just the CPU number 0. We add two counters, showing crystal clock count and the DC6 residency. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 089220aaa5c9..58a487c225a7 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -31,6 +31,9 @@ ) // end copied section +#define CPUID_LEAF_MODEL_ID 0x1A +#define CPUID_LEAF_MODEL_ID_CORE_TYPE_SHIFT 24 + #define X86_VENDOR_INTEL 0 #include INTEL_FAMILY_HEADER @@ -89,6 +92,9 @@ #define PERF_DEV_NAME_BYTES 32 #define PERF_EVT_NAME_BYTES 32 +#define INTEL_ECORE_TYPE 0x20 +#define INTEL_PCORE_TYPE 0x40 + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE }; @@ -194,6 +200,8 @@ struct msr_counter bic[] = { { 0x0, "SAMMHz", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "SAMAMHz", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "SysWatt", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "Sys_J", NULL, 0, 0, 0, NULL, 0 }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -256,6 +264,8 @@ struct msr_counter bic[] = { #define BIC_SAMMHz (1ULL << 56) #define BIC_SAMACTMHz (1ULL << 57) #define BIC_Diec6 (1ULL << 58) +#define BIC_SysWatt (1ULL << 59) +#define BIC_Sys_J (1ULL << 60) #define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) #define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) @@ -263,7 +273,7 @@ struct msr_counter bic[] = { #define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) #define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC | BIC_SysWatt | BIC_Sys_J) unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; @@ -370,7 +380,6 @@ enum gfx_sysfs_idx { }; struct gfx_sysfs_info { - const char *path; FILE *fp; unsigned int val; unsigned long long val_ull; @@ -502,12 +511,15 @@ enum rapl_msrs { RAPL_AMD_PWR_UNIT = BIT(14), /* 0xc0010299 MSR_AMD_RAPL_POWER_UNIT */ RAPL_AMD_CORE_ENERGY_STAT = BIT(15), /* 0xc001029a MSR_AMD_CORE_ENERGY_STATUS */ RAPL_AMD_PKG_ENERGY_STAT = BIT(16), /* 0xc001029b MSR_AMD_PKG_ENERGY_STATUS */ + RAPL_PLATFORM_ENERGY_LIMIT = BIT(17), /* 0x64c MSR_PLATFORM_ENERGY_LIMIT */ + RAPL_PLATFORM_ENERGY_STATUS = BIT(18), /* 0x64d MSR_PLATFORM_ENERGY_STATUS */ }; #define RAPL_PKG (RAPL_PKG_ENERGY_STATUS | RAPL_PKG_POWER_LIMIT) #define RAPL_DRAM (RAPL_DRAM_ENERGY_STATUS | RAPL_DRAM_POWER_LIMIT) #define RAPL_CORE (RAPL_CORE_ENERGY_STATUS | RAPL_CORE_POWER_LIMIT) #define RAPL_GFX (RAPL_GFX_POWER_LIMIT | RAPL_GFX_ENERGY_STATUS) +#define RAPL_PSYS (RAPL_PLATFORM_ENERGY_STATUS | RAPL_PLATFORM_ENERGY_LIMIT) #define RAPL_PKG_ALL (RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO) #define RAPL_DRAM_ALL (RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_DRAM_POWER_INFO) @@ -708,7 +720,7 @@ static const struct platform_features skl_features = { .has_ext_cst_msrs = 1, .trl_msrs = TRL_BASE, .tcc_offset_bits = 6, - .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX | RAPL_PSYS, .enable_tsc_tweak = 1, }; @@ -725,42 +737,44 @@ static const struct platform_features cnl_features = { .has_ext_cst_msrs = 1, .trl_msrs = TRL_BASE, .tcc_offset_bits = 6, - .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX | RAPL_PSYS, .enable_tsc_tweak = 1, }; +/* Copied from cnl_features, with PC7/PC9 removed */ static const struct platform_features adl_features = { - .has_msr_misc_feature_control = 1, - .has_msr_misc_pwr_mgmt = 1, - .has_nhm_msrs = 1, - .has_config_tdp = 1, - .bclk_freq = BCLK_100MHZ, - .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC8 | PC10, - .cst_limit = CST_LIMIT_HSW, - .has_irtl_msrs = 1, - .has_msr_core_c1_res = 1, - .has_ext_cst_msrs = 1, - .trl_msrs = TRL_BASE, - .tcc_offset_bits = 6, - .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, - .enable_tsc_tweak = 1, + .has_msr_misc_feature_control = cnl_features.has_msr_misc_feature_control, + .has_msr_misc_pwr_mgmt = cnl_features.has_msr_misc_pwr_mgmt, + .has_nhm_msrs = cnl_features.has_nhm_msrs, + .has_config_tdp = cnl_features.has_config_tdp, + .bclk_freq = cnl_features.bclk_freq, + .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC8 | PC10, + .cst_limit = cnl_features.cst_limit, + .has_irtl_msrs = cnl_features.has_irtl_msrs, + .has_msr_core_c1_res = cnl_features.has_msr_core_c1_res, + .has_ext_cst_msrs = cnl_features.has_ext_cst_msrs, + .trl_msrs = cnl_features.trl_msrs, + .tcc_offset_bits = cnl_features.tcc_offset_bits, + .rapl_msrs = cnl_features.rapl_msrs, + .enable_tsc_tweak = cnl_features.enable_tsc_tweak, }; -static const struct platform_features arl_features = { - .has_msr_misc_feature_control = 1, - .has_msr_misc_pwr_mgmt = 1, - .has_nhm_msrs = 1, - .has_config_tdp = 1, - .bclk_freq = BCLK_100MHZ, - .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC10, - .cst_limit = CST_LIMIT_HSW, - .has_irtl_msrs = 1, - .has_msr_core_c1_res = 1, - .has_ext_cst_msrs = 1, - .trl_msrs = TRL_BASE, - .tcc_offset_bits = 6, - .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, - .enable_tsc_tweak = 1, +/* Copied from adl_features, with PC3/PC8 removed */ +static const struct platform_features lnl_features = { + .has_msr_misc_feature_control = adl_features.has_msr_misc_feature_control, + .has_msr_misc_pwr_mgmt = adl_features.has_msr_misc_pwr_mgmt, + .has_nhm_msrs = adl_features.has_nhm_msrs, + .has_config_tdp = adl_features.has_config_tdp, + .bclk_freq = adl_features.bclk_freq, + .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC6 | PC10, + .cst_limit = adl_features.cst_limit, + .has_irtl_msrs = adl_features.has_irtl_msrs, + .has_msr_core_c1_res = adl_features.has_msr_core_c1_res, + .has_ext_cst_msrs = adl_features.has_ext_cst_msrs, + .trl_msrs = adl_features.trl_msrs, + .tcc_offset_bits = adl_features.tcc_offset_bits, + .rapl_msrs = adl_features.rapl_msrs, + .enable_tsc_tweak = adl_features.enable_tsc_tweak, }; static const struct platform_features skx_features = { @@ -790,7 +804,7 @@ static const struct platform_features icx_features = { .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, - .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, .has_fixed_rapl_unit = 1, }; @@ -806,7 +820,7 @@ static const struct platform_features spr_features = { .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, - .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; static const struct platform_features srf_features = { @@ -822,7 +836,7 @@ static const struct platform_features srf_features = { .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, - .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; static const struct platform_features grr_features = { @@ -838,7 +852,7 @@ static const struct platform_features grr_features = { .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, - .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; static const struct platform_features slv_features = { @@ -997,18 +1011,19 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_SAPPHIRERAPIDS_X, &spr_features }, { INTEL_EMERALDRAPIDS_X, &spr_features }, { INTEL_GRANITERAPIDS_X, &spr_features }, + { INTEL_GRANITERAPIDS_D, &spr_features }, { INTEL_LAKEFIELD, &cnl_features }, { INTEL_ALDERLAKE, &adl_features }, { INTEL_ALDERLAKE_L, &adl_features }, { INTEL_RAPTORLAKE, &adl_features }, { INTEL_RAPTORLAKE_P, &adl_features }, { INTEL_RAPTORLAKE_S, &adl_features }, - { INTEL_METEORLAKE, &cnl_features }, - { INTEL_METEORLAKE_L, &cnl_features }, - { INTEL_ARROWLAKE_H, &arl_features }, - { INTEL_ARROWLAKE_U, &arl_features }, - { INTEL_ARROWLAKE, &arl_features }, - { INTEL_LUNARLAKE_M, &arl_features }, + { INTEL_METEORLAKE, &adl_features }, + { INTEL_METEORLAKE_L, &adl_features }, + { INTEL_ARROWLAKE_H, &adl_features }, + { INTEL_ARROWLAKE_U, &adl_features }, + { INTEL_ARROWLAKE, &adl_features }, + { INTEL_LUNARLAKE_M, &lnl_features }, { INTEL_ATOM_SILVERMONT, &slv_features }, { INTEL_ATOM_SILVERMONT_D, &slvd_features }, { INTEL_ATOM_AIRMONT, &amt_features }, @@ -1100,6 +1115,7 @@ enum rapl_rci_index { RAPL_RCI_INDEX_PKG_PERF_STATUS = 4, RAPL_RCI_INDEX_DRAM_PERF_STATUS = 5, RAPL_RCI_INDEX_CORE_ENERGY = 6, + RAPL_RCI_INDEX_ENERGY_PLATFORM = 7, NUM_RAPL_COUNTERS, }; @@ -1126,6 +1142,7 @@ struct rapl_counter_info_t { struct rapl_counter_info_t *rapl_counter_info_perdomain; unsigned int rapl_counter_info_perdomain_size; +#define RAPL_COUNTER_FLAG_PLATFORM_COUNTER (1u << 0) #define RAPL_COUNTER_FLAG_USE_MSR_SUM (1u << 1) struct rapl_counter_arch_info { @@ -1247,6 +1264,19 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .compat_scale = 1.0, .flags = 0, }, + { + .feature_mask = RAPL_PSYS, + .perf_subsys = "power", + .perf_name = "energy-psys", + .msr = MSR_PLATFORM_ENERGY_STATUS, + .msr_mask = 0x00000000FFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM, + .bic = BIC_SysWatt | BIC_Sys_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_PLATFORM_COUNTER | RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, }; struct rapl_counter { @@ -1674,6 +1704,7 @@ enum { IDX_PP1_ENERGY, IDX_PKG_PERF, IDX_DRAM_PERF, + IDX_PSYS_ENERGY, IDX_COUNT, }; @@ -1718,6 +1749,9 @@ off_t idx_to_offset(int idx) case IDX_DRAM_PERF: offset = MSR_DRAM_PERF_STATUS; break; + case IDX_PSYS_ENERGY: + offset = MSR_PLATFORM_ENERGY_STATUS; + break; default: offset = -1; } @@ -1748,6 +1782,9 @@ int offset_to_idx(off_t offset) case MSR_DRAM_PERF_STATUS: idx = IDX_DRAM_PERF; break; + case MSR_PLATFORM_ENERGY_STATUS: + idx = IDX_PSYS_ENERGY; + break; default: idx = -1; } @@ -1769,6 +1806,8 @@ int idx_valid(int idx) return platform->rapl_msrs & RAPL_PKG_PERF_STATUS; case IDX_DRAM_PERF: return platform->rapl_msrs & RAPL_DRAM_PERF_STATUS; + case IDX_PSYS_ENERGY: + return platform->rapl_msrs & RAPL_PSYS; default: return 0; } @@ -1840,6 +1879,10 @@ struct system_summary { struct pkg_data packages; } average; +struct platform_counters { + struct rapl_counter energy_psys; /* MSR_PLATFORM_ENERGY_STATUS */ +} platform_counters_odd, platform_counters_even; + struct cpu_topology { int physical_package_id; int die_id; @@ -1848,6 +1891,7 @@ struct cpu_topology { int logical_node_id; /* 0-based count within the package */ int physical_core_id; int thread_id; + int type; cpu_set_t *put_ids; /* Processing Unit/Thread IDs */ } *cpus; @@ -2291,7 +2335,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: - outp += sprintf(outp, "%s%s", delim, ppmt->name); + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2365,7 +2409,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: - outp += sprintf(outp, "%s%s", delim, ppmt->name); + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2496,13 +2540,18 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: - outp += sprintf(outp, "%s%s", delim, ppmt->name); + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } ppmt = ppmt->next; } + if (DO_BIC(BIC_SysWatt)) + outp += sprintf(outp, "%sSysWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_Sys_J)) + outp += sprintf(outp, "%sSys_J", (printed++ ? delim : "")); + outp += sprintf(outp, "\n"); } @@ -2510,6 +2559,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p { int i; struct msr_counter *mp; + struct platform_counters *pplat_cnt = p == package_odd ? &platform_counters_odd : &platform_counters_even; outp += sprintf(outp, "t %p, c %p, p %p\n", t, c, p); @@ -2581,6 +2631,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores.raw_value); outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx.raw_value); outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram.raw_value); + outp += sprintf(outp, "Joules PSYS: %0llX\n", pplat_cnt->energy_psys.raw_value); outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status.raw_value); outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status.raw_value); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); @@ -2619,6 +2670,9 @@ double rapl_counter_get_value(const struct rapl_counter *c, enum rapl_unit desir */ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { + static int count; + + struct platform_counters *pplat_cnt = NULL; double interval_float, tsc; char *fmt8; int i; @@ -2628,6 +2682,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data char *delim = "\t"; int printed = 0; + if (t == &average.threads) { + pplat_cnt = count & 1 ? &platform_counters_odd : &platform_counters_even; + ++count; + } + /* if showing only 1st thread in core and this isn't one, bail out */ if (show_core_only && !is_cpu_first_thread_in_core(t, c, p)) return 0; @@ -2788,6 +2847,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data } for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { + const unsigned long value_raw = t->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2799,9 +2860,6 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: - const unsigned long value_raw = t->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; - outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; } @@ -2869,6 +2927,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data } for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { + const unsigned long value_raw = c->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2880,9 +2940,6 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: - const unsigned long value_raw = c->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; - outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; } @@ -3068,6 +3125,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data } for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { + const unsigned long value_raw = p->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -3079,14 +3138,18 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: - const unsigned long value_raw = p->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; - outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; } } + if (DO_BIC(BIC_SysWatt) && (t == &average.threads)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&pplat_cnt->energy_psys, RAPL_UNIT_WATTS, interval_float)); + if (DO_BIC(BIC_Sys_J) && (t == &average.threads)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&pplat_cnt->energy_psys, RAPL_UNIT_JOULES, interval_float)); + done: if (*(outp - 1) != '\n') outp += sprintf(outp, "\n"); @@ -3394,6 +3457,11 @@ int delta_cpu(struct thread_data *t, struct core_data *c, return retval; } +void delta_platform(struct platform_counters *new, struct platform_counters *old) +{ + old->energy_psys.raw_value = new->energy_psys.raw_value - old->energy_psys.raw_value; +} + void rapl_counter_clear(struct rapl_counter *c) { c->raw_value = 0; @@ -4123,6 +4191,9 @@ static size_t cstate_counter_info_count_perf(const struct cstate_counter_info_t void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci, unsigned int idx) { + if (rci->source[idx] == COUNTER_SOURCE_NONE) + return; + rc->raw_value = rci->data[idx]; rc->unit = rci->unit[idx]; rc->scale = rci->scale[idx]; @@ -4130,6 +4201,7 @@ void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct pkg_data *p) { + struct platform_counters *pplat_cnt = p == package_odd ? &platform_counters_odd : &platform_counters_even; unsigned long long perf_data[NUM_RAPL_COUNTERS + 1]; struct rapl_counter_info_t *rci; @@ -4157,6 +4229,7 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) { switch (rci->source[i]) { case COUNTER_SOURCE_NONE: + rci->data[i] = 0; break; case COUNTER_SOURCE_PERF: @@ -4195,7 +4268,7 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct } } - BUILD_BUG_ON(NUM_RAPL_COUNTERS != 7); + BUILD_BUG_ON(NUM_RAPL_COUNTERS != 8); write_rapl_counter(&p->energy_pkg, rci, RAPL_RCI_INDEX_ENERGY_PKG); write_rapl_counter(&p->energy_cores, rci, RAPL_RCI_INDEX_ENERGY_CORES); write_rapl_counter(&p->energy_dram, rci, RAPL_RCI_INDEX_DRAM); @@ -4203,6 +4276,7 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct write_rapl_counter(&p->rapl_pkg_perf_status, rci, RAPL_RCI_INDEX_PKG_PERF_STATUS); write_rapl_counter(&p->rapl_dram_perf_status, rci, RAPL_RCI_INDEX_DRAM_PERF_STATUS); write_rapl_counter(&c->core_energy, rci, RAPL_RCI_INDEX_CORE_ENERGY); + write_rapl_counter(&pplat_cnt->energy_psys, rci, RAPL_RCI_INDEX_ENERGY_PLATFORM); return 0; } @@ -5385,6 +5459,9 @@ static int parse_cpu_str(char *cpu_str, cpu_set_t *cpu_set, int cpu_set_size) if (*next == '-') /* no negative cpu numbers */ return 1; + if (*next == '\0' || *next == '\n') + break; + start = strtoul(next, &next, 10); if (start >= CPU_SUBSET_MAXCPUS) @@ -5656,6 +5733,32 @@ int init_thread_id(int cpu) return 0; } +int set_my_cpu_type(void) +{ + unsigned int eax, ebx, ecx, edx; + unsigned int max_level; + + __cpuid(0, max_level, ebx, ecx, edx); + + if (max_level < CPUID_LEAF_MODEL_ID) + return 0; + + __cpuid(CPUID_LEAF_MODEL_ID, eax, ebx, ecx, edx); + + return (eax >> CPUID_LEAF_MODEL_ID_CORE_TYPE_SHIFT); +} + +int set_cpu_hybrid_type(int cpu) +{ + if (cpu_migrate(cpu)) + return -1; + + int type = set_my_cpu_type(); + + cpus[cpu].type = type; + return 0; +} + /* * snapshot_proc_interrupts() * @@ -5728,28 +5831,21 @@ int snapshot_proc_interrupts(void) */ int snapshot_graphics(int idx) { - FILE *fp; int retval; + rewind(gfx_info[idx].fp); + switch (idx) { case GFX_rc6: case SAM_mc6: - fp = fopen_or_die(gfx_info[idx].path, "r"); - retval = fscanf(fp, "%lld", &gfx_info[idx].val_ull); + retval = fscanf(gfx_info[idx].fp, "%lld", &gfx_info[idx].val_ull); if (retval != 1) err(1, "rc6"); - fclose(fp); return 0; case GFX_MHz: case GFX_ACTMHz: case SAM_MHz: case SAM_ACTMHz: - if (gfx_info[idx].fp == NULL) { - gfx_info[idx].fp = fopen_or_die(gfx_info[idx].path, "r"); - } else { - rewind(gfx_info[idx].fp); - fflush(gfx_info[idx].fp); - } retval = fscanf(gfx_info[idx].fp, "%d", &gfx_info[idx].val); if (retval != 1) err(1, "MHz"); @@ -6116,6 +6212,7 @@ restart: re_initialize(); goto restart; } + delta_platform(&platform_counters_odd, &platform_counters_even); compute_average(EVEN_COUNTERS); format_all_counters(EVEN_COUNTERS); flush_output_stdout(); @@ -6139,6 +6236,7 @@ restart: re_initialize(); goto restart; } + delta_platform(&platform_counters_even, &platform_counters_odd); compute_average(ODD_COUNTERS); format_all_counters(ODD_COUNTERS); flush_output_stdout(); @@ -6442,14 +6540,25 @@ static void probe_intel_uncore_frequency(void) probe_intel_uncore_frequency_legacy(); } +static void set_graphics_fp(char *path, int idx) +{ + if (!access(path, R_OK)) + gfx_info[idx].fp = fopen_or_die(path, "r"); +} + +/* Enlarge this if there are /sys/class/drm/card2 ... */ +#define GFX_MAX_CARDS 2 + static void probe_graphics(void) { + char path[PATH_MAX]; + int i; + /* Xe graphics sysfs knobs */ if (!access("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", R_OK)) { FILE *fp; char buf[8]; bool gt0_is_gt; - int idx; fp = fopen("/sys/class/drm/card0/device/tile0/gt0/gtidle/name", "r"); if (!fp) @@ -6468,81 +6577,76 @@ static void probe_graphics(void) else goto next; - idx = gt0_is_gt ? GFX_rc6 : SAM_mc6; - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", gt0_is_gt ? GFX_rc6 : SAM_mc6); - idx = gt0_is_gt ? GFX_MHz : SAM_MHz; - if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", gt0_is_gt ? GFX_MHz : SAM_MHz); - idx = gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz; - if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz); - idx = gt0_is_gt ? SAM_mc6 : GFX_rc6; - if (!access("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", gt0_is_gt ? SAM_mc6 : GFX_rc6); - idx = gt0_is_gt ? SAM_MHz : GFX_MHz; - if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", gt0_is_gt ? SAM_MHz : GFX_MHz); - idx = gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz; - if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", R_OK)) - gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq"; + set_graphics_fp("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz); goto end; } next: /* New i915 graphics sysfs knobs */ - if (!access("/sys/class/drm/card0/gt/gt0/rc6_residency_ms", R_OK)) { - gfx_info[GFX_rc6].path = "/sys/class/drm/card0/gt/gt0/rc6_residency_ms"; + for (i = 0; i < GFX_MAX_CARDS; i++) { + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt0/rc6_residency_ms", i); + if (!access(path, R_OK)) + break; + } - if (!access("/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz", R_OK)) - gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz"; + if (i == GFX_MAX_CARDS) + goto legacy_i915; - if (!access("/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz", R_OK)) - gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz"; + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt0/rc6_residency_ms", i); + set_graphics_fp(path, GFX_rc6); - if (!access("/sys/class/drm/card0/gt/gt1/rc6_residency_ms", R_OK)) - gfx_info[SAM_mc6].path = "/sys/class/drm/card0/gt/gt1/rc6_residency_ms"; + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt0/rps_cur_freq_mhz", i); + set_graphics_fp(path, GFX_MHz); - if (!access("/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz", R_OK)) - gfx_info[SAM_MHz].path = "/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz"; + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt0/rps_act_freq_mhz", i); + set_graphics_fp(path, GFX_ACTMHz); - if (!access("/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz", R_OK)) - gfx_info[SAM_ACTMHz].path = "/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz"; + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt1/rc6_residency_ms", i); + set_graphics_fp(path, SAM_mc6); - goto end; - } + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt1/rps_cur_freq_mhz", i); + set_graphics_fp(path, SAM_MHz); + + snprintf(path, PATH_MAX, "/sys/class/drm/card%d/gt/gt1/rps_act_freq_mhz", i); + set_graphics_fp(path, SAM_ACTMHz); + goto end; + +legacy_i915: /* Fall back to traditional i915 graphics sysfs knobs */ - if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK)) - gfx_info[GFX_rc6].path = "/sys/class/drm/card0/power/rc6_residency_ms"; + set_graphics_fp("/sys/class/drm/card0/power/rc6_residency_ms", GFX_rc6); - if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK)) - gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt_cur_freq_mhz"; - else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) - gfx_info[GFX_MHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz"; + set_graphics_fp("/sys/class/drm/card0/gt_cur_freq_mhz", GFX_MHz); + if (!gfx_info[GFX_MHz].fp) + set_graphics_fp("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", GFX_MHz); - if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK)) - gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt_act_freq_mhz"; - else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) - gfx_info[GFX_ACTMHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz"; + set_graphics_fp("/sys/class/drm/card0/gt_act_freq_mhz", GFX_ACTMHz); + if (!gfx_info[GFX_ACTMHz].fp) + set_graphics_fp("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", GFX_ACTMHz); end: - if (gfx_info[GFX_rc6].path) + if (gfx_info[GFX_rc6].fp) BIC_PRESENT(BIC_GFX_rc6); - if (gfx_info[GFX_MHz].path) + if (gfx_info[GFX_MHz].fp) BIC_PRESENT(BIC_GFXMHz); - if (gfx_info[GFX_ACTMHz].path) + if (gfx_info[GFX_ACTMHz].fp) BIC_PRESENT(BIC_GFXACTMHz); - if (gfx_info[SAM_mc6].path) + if (gfx_info[SAM_mc6].fp) BIC_PRESENT(BIC_SAM_mc6); - if (gfx_info[SAM_MHz].path) + if (gfx_info[SAM_MHz].fp) BIC_PRESENT(BIC_SAMMHz); - if (gfx_info[SAM_ACTMHz].path) + if (gfx_info[SAM_ACTMHz].fp) BIC_PRESENT(BIC_SAMACTMHz); } @@ -6911,8 +7015,8 @@ void rapl_probe_intel(void) unsigned long long msr; unsigned int time_unit; double tdp; - const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt; - const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J; + const unsigned long long bic_watt_bits = BIC_SysWatt | BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt; + const unsigned long long bic_joules_bits = BIC_Sys_J | BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J; if (rapl_joules) bic_enabled &= ~bic_watt_bits; @@ -7572,6 +7676,9 @@ void rapl_perf_init(void) domain_visited[next_domain] = 1; + if ((cai->flags & RAPL_COUNTER_FLAG_PLATFORM_COUNTER) && (cpu != base_cpu)) + continue; + struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[next_domain]; /* Check if the counter is enabled and accessible */ @@ -8196,7 +8303,7 @@ void topology_probe(bool startup) set_max_cpu_num(); topo.num_cpus = 0; for_all_proc_cpus(count_cpus); - if (!summary_only && topo.num_cpus > 1) + if (!summary_only) BIC_PRESENT(BIC_CPU); if (debug > 1) @@ -8284,6 +8391,8 @@ void topology_probe(bool startup) for_all_proc_cpus(init_thread_id); + for_all_proc_cpus(set_cpu_hybrid_type); + /* * For online cpus * find max_core_id, max_package_id @@ -8332,7 +8441,7 @@ void topology_probe(bool startup) topo.cores_per_node = max_core_id + 1; if (debug > 1) fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.cores_per_node); - if (!summary_only && topo.cores_per_node > 1) + if (!summary_only) BIC_PRESENT(BIC_Core); topo.num_die = topo.max_die_id + 1; @@ -8548,6 +8657,35 @@ void check_perf_access(void) bic_enabled &= ~BIC_IPC; } +bool perf_has_hybrid_devices(void) +{ + /* + * 0: unknown + * 1: has separate perf device for p and e core + * -1: doesn't have separate perf device for p and e core + */ + static int cached; + + if (cached > 0) + return true; + + if (cached < 0) + return false; + + if (access("/sys/bus/event_source/devices/cpu_core", F_OK)) { + cached = -1; + return false; + } + + if (access("/sys/bus/event_source/devices/cpu_atom", F_OK)) { + cached = -1; + return false; + } + + cached = 1; + return true; +} + int added_perf_counters_init_(struct perf_counter_info *pinfo) { size_t num_domains = 0; @@ -8604,29 +8742,56 @@ int added_perf_counters_init_(struct perf_counter_info *pinfo) if (domain_visited[next_domain]) continue; - perf_type = read_perf_type(pinfo->device); + /* + * Intel hybrid platforms expose different perf devices for P and E cores. + * Instead of one, "/sys/bus/event_source/devices/cpu" device, there are + * "/sys/bus/event_source/devices/{cpu_core,cpu_atom}". + * + * This makes it more complicated to the user, because most of the counters + * are available on both and have to be handled manually, otherwise. + * + * Code below, allow user to use the old "cpu" name, which is translated accordingly. + */ + const char *perf_device = pinfo->device; + + if (strcmp(perf_device, "cpu") == 0 && perf_has_hybrid_devices()) { + switch (cpus[cpu].type) { + case INTEL_PCORE_TYPE: + perf_device = "cpu_core"; + break; + + case INTEL_ECORE_TYPE: + perf_device = "cpu_atom"; + break; + + default: /* Don't change, we will probably fail and report a problem soon. */ + break; + } + } + + perf_type = read_perf_type(perf_device); if (perf_type == (unsigned int)-1) { warnx("%s: perf/%s/%s: failed to read %s", - __func__, pinfo->device, pinfo->event, "type"); + __func__, perf_device, pinfo->event, "type"); continue; } - perf_config = read_perf_config(pinfo->device, pinfo->event); + perf_config = read_perf_config(perf_device, pinfo->event); if (perf_config == (unsigned int)-1) { warnx("%s: perf/%s/%s: failed to read %s", - __func__, pinfo->device, pinfo->event, "config"); + __func__, perf_device, pinfo->event, "config"); continue; } /* Scale is not required, some counters just don't have it. */ - perf_scale = read_perf_scale(pinfo->device, pinfo->event); + perf_scale = read_perf_scale(perf_device, pinfo->event); if (perf_scale == 0.0) perf_scale = 1.0; fd_perf = open_perf_counter(cpu, perf_type, perf_config, -1, 0); if (fd_perf == -1) { warnx("%s: perf/%s/%s: failed to open counter on cpu%d", - __func__, pinfo->device, pinfo->event, cpu); + __func__, perf_device, pinfo->event, cpu); continue; } @@ -8636,7 +8801,7 @@ int added_perf_counters_init_(struct perf_counter_info *pinfo) if (debug) fprintf(stderr, "Add perf/%s/%s cpu%d: %d\n", - pinfo->device, pinfo->event, cpu, pinfo->fd_perf_per_domain[next_domain]); + perf_device, pinfo->event, cpu, pinfo->fd_perf_per_domain[next_domain]); } pinfo = pinfo->next; @@ -9071,7 +9236,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2024.07.26 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2024.11.30 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -9781,7 +9946,7 @@ void cmdline(int argc, char **argv) * Parse some options early, because they may make other options invalid, * like adding the MSR counter with --add and at the same time using --no-msr. */ - while ((opt = getopt_long_only(argc, argv, "MPn:", long_options, &option_index)) != -1) { + while ((opt = getopt_long_only(argc, argv, "+MPn:", long_options, &option_index)) != -1) { switch (opt) { case 'M': no_msr = 1; @@ -9805,6 +9970,12 @@ void cmdline(int argc, char **argv) break; case 'D': dump_only++; + /* + * Force the no_perf early to prevent using it as a source. + * User asks for raw values, but perf returns them relative + * to the opening of the file descriptor. + */ + no_perf = 1; break; case 'e': /* --enable specified counter */ diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 2f36b7b6418d..625f5b046776 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -40,9 +40,9 @@ void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_fl void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; -bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym; -void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym; -void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym; +bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak; +void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak; +void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak; bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; bool scx_bpf_dsq_move_vtime(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; diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 21deea320bd7..e938156ed0a0 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -97,7 +97,7 @@ restart: SCX_BUG_ON(!cpuset, "Failed to allocate cpuset"); CPU_ZERO(cpuset); CPU_SET(skel->rodata->central_cpu, cpuset); - SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset), + SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset), "Failed to affinitize to central CPU %d (max %d)", skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1); CPU_FREE(cpuset); diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index f6a50f06dfc4..eabfe9f411d9 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -7,8 +7,8 @@ HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ -e s/riscv.*/riscv/ -e s/loongarch.*/loongarch/) -ifndef ARCH -ARCH := $(HOSTARCH) +ifeq ($(strip $(ARCH)),) +override ARCH := $(HOSTARCH) endif SRCARCH := $(ARCH) diff --git a/tools/testing/cxl/cxl_core_exports.c b/tools/testing/cxl/cxl_core_exports.c index 077e6883921d..f088792a8925 100644 --- a/tools/testing/cxl/cxl_core_exports.c +++ b/tools/testing/cxl/cxl_core_exports.c @@ -4,4 +4,4 @@ #include "cxl.h" /* Exporting of cxl_core symbols that are only used by cxl_test */ -EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, CXL); +EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, "CXL"); diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 050725afa45d..d0337c11f9ee 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -1531,5 +1531,5 @@ MODULE_PARM_DESC(interleave_arithmetic, "Modulo:0, XOR:1"); module_init(cxl_test_init); module_exit(cxl_test_exit); MODULE_LICENSE("GPL v2"); -MODULE_IMPORT_NS(ACPI); -MODULE_IMPORT_NS(CXL); +MODULE_IMPORT_NS("ACPI"); +MODULE_IMPORT_NS("CXL"); diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 71916e0e1546..347c1e7b37bd 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1679,4 +1679,4 @@ static struct platform_driver cxl_mock_mem_driver = { module_platform_driver(cxl_mock_mem_driver); MODULE_LICENSE("GPL v2"); -MODULE_IMPORT_NS(CXL); +MODULE_IMPORT_NS("CXL"); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index f4ce96cc11d4..450c7566c33f 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -76,7 +76,7 @@ int __wrap_acpi_table_parse_cedt(enum acpi_cedt_type id, return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_acpi_table_parse_cedt, ACPI); +EXPORT_SYMBOL_NS_GPL(__wrap_acpi_table_parse_cedt, "ACPI"); acpi_status __wrap_acpi_evaluate_integer(acpi_handle handle, acpi_string pathname, @@ -147,7 +147,7 @@ struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, return cxlhdm; } -EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, "CXL"); int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) { @@ -162,7 +162,7 @@ int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_passthrough_decoder, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_passthrough_decoder, "CXL"); int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, struct cxl_endpoint_dvsec_info *info) @@ -179,7 +179,7 @@ int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enumerate_decoders, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enumerate_decoders, "CXL"); int __wrap_devm_cxl_port_enumerate_dports(struct cxl_port *port) { @@ -194,7 +194,7 @@ int __wrap_devm_cxl_port_enumerate_dports(struct cxl_port *port) return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_port_enumerate_dports, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_port_enumerate_dports, "CXL"); int __wrap_cxl_await_media_ready(struct cxl_dev_state *cxlds) { @@ -209,7 +209,7 @@ int __wrap_cxl_await_media_ready(struct cxl_dev_state *cxlds) return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_await_media_ready, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_await_media_ready, "CXL"); int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, @@ -226,7 +226,7 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, "CXL"); int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, struct cxl_endpoint_dvsec_info *info) @@ -242,7 +242,7 @@ int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, return rc; } -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dvsec_rr_decode, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dvsec_rr_decode, "CXL"); struct cxl_dport *__wrap_devm_cxl_add_rch_dport(struct cxl_port *port, struct device *dport_dev, @@ -266,7 +266,7 @@ struct cxl_dport *__wrap_devm_cxl_add_rch_dport(struct cxl_port *port, return dport; } -EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_rch_dport, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_rch_dport, "CXL"); resource_size_t __wrap_cxl_rcd_component_reg_phys(struct device *dev, struct cxl_dport *dport) @@ -283,7 +283,7 @@ resource_size_t __wrap_cxl_rcd_component_reg_phys(struct device *dev, return component_reg_phys; } -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_rcd_component_reg_phys, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_rcd_component_reg_phys, "CXL"); void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port) { @@ -297,7 +297,7 @@ void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port) cxl_endpoint_parse_cdat(port); put_cxl_mock_ops(index); } -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, "CXL"); void __wrap_cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host) { @@ -309,8 +309,8 @@ void __wrap_cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device put_cxl_mock_ops(index); } -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dport_init_ras_reporting, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dport_init_ras_reporting, "CXL"); MODULE_LICENSE("GPL v2"); -MODULE_IMPORT_NS(ACPI); -MODULE_IMPORT_NS(CXL); +MODULE_IMPORT_NS("ACPI"); +MODULE_IMPORT_NS("CXL"); diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c index 892e990c034a..68a064ce598c 100644 --- a/tools/testing/nvdimm/test/ndtest.c +++ b/tools/testing/nvdimm/test/ndtest.c @@ -883,7 +883,7 @@ static const struct platform_device_id ndtest_id[] = { static struct platform_driver ndtest_driver = { .probe = ndtest_probe, - .remove_new = ndtest_remove, + .remove = ndtest_remove, .driver = { .name = KBUILD_MODNAME, }, diff --git a/tools/testing/selftests/alsa/.gitignore b/tools/testing/selftests/alsa/.gitignore index 12dc3fcd3456..3dd8e1176b89 100644 --- a/tools/testing/selftests/alsa/.gitignore +++ b/tools/testing/selftests/alsa/.gitignore @@ -1,3 +1,5 @@ +global-timer mixer-test pcm-test test-pcmtest-driver +utimer-test diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile index 944279160fed..8dab90ad22bb 100644 --- a/tools/testing/selftests/alsa/Makefile +++ b/tools/testing/selftests/alsa/Makefile @@ -27,5 +27,5 @@ include ../lib.mk $(OUTPUT)/libatest.so: conf.c alsa-local.h $(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@ -$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h +$(OUTPUT)/%: %.c $(OUTPUT)/libatest.so alsa-local.h $(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@ diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S index df3230fdac39..66ab2e0bae5f 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S +++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S @@ -81,32 +81,31 @@ do_syscall: stp x27, x28, [sp, #96] // Set SVCR if we're doing SME - cbz x1, 1f + cbz x1, load_gpr adrp x2, svcr_in ldr x2, [x2, :lo12:svcr_in] msr S3_3_C4_C2_2, x2 -1: // Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR - tbz x2, #SVCR_ZA_SHIFT, 1f + tbz x2, #SVCR_ZA_SHIFT, load_gpr mov w12, #0 ldr x2, =za_in -2: _ldr_za 12, 2 +1: _ldr_za 12, 2 add x2, x2, x1 add x12, x12, #1 cmp x1, x12 - bne 2b + bne 1b // ZT0 mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1 ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \ #ID_AA64SMFR0_EL1_SMEver_WIDTH - cbz x2, 1f + cbz x2, load_gpr adrp x2, zt_in add x2, x2, :lo12:zt_in _ldr_zt 2 -1: +load_gpr: // Load GPRs x8-x28, and save our SP/FP for later comparison ldr x2, =gpr_in add x2, x2, #64 @@ -125,9 +124,9 @@ do_syscall: str x30, [x2], #8 // LR // Load FPRs if we're not doing neither SVE nor streaming SVE - cbnz x0, 1f + cbnz x0, check_sve_in ldr x2, =svcr_in - tbnz x2, #SVCR_SM_SHIFT, 1f + tbnz x2, #SVCR_SM_SHIFT, check_sve_in ldr x2, =fpr_in ldp q0, q1, [x2] @@ -148,8 +147,8 @@ do_syscall: ldp q30, q31, [x2, #16 * 30] b 2f -1: +check_sve_in: // Load the SVE registers if we're doing SVE/SME ldr x2, =z_in @@ -256,32 +255,31 @@ do_syscall: stp q30, q31, [x2, #16 * 30] // Save SVCR if we're doing SME - cbz x1, 1f + cbz x1, check_sve_out mrs x2, S3_3_C4_C2_2 adrp x3, svcr_out str x2, [x3, :lo12:svcr_out] -1: // Save ZA if it's enabled - uses x12 as scratch due to SME STR - tbz x2, #SVCR_ZA_SHIFT, 1f + tbz x2, #SVCR_ZA_SHIFT, check_sve_out mov w12, #0 ldr x2, =za_out -2: _str_za 12, 2 +1: _str_za 12, 2 add x2, x2, x1 add x12, x12, #1 cmp x1, x12 - bne 2b + bne 1b // ZT0 mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1 ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \ #ID_AA64SMFR0_EL1_SMEver_WIDTH - cbz x2, 1f + cbz x2, check_sve_out adrp x2, zt_out add x2, x2, :lo12:zt_out _str_zt 2 -1: +check_sve_out: // Save the SVE state if we have some cbz x0, 1f diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index c2a1842c3d8b..e9c377001f93 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -5,7 +5,6 @@ bpf-syscall* test_verifier test_maps test_lru_map -test_lpm_map test_tag FEATURE-DUMP.libbpf FEATURE-DUMP.selftests diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 6ad3b1ba1920..0a016cd71cba 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -83,7 +83,7 @@ CLANG_CPUV4 := 1 endif # Order correspond to 'make run_tests' order -TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ +TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \ test_sockmap \ test_tcpnotify_user test_sysctl \ test_progs-no_alu32 @@ -129,7 +129,6 @@ TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c) TEST_PROGS := test_kmod.sh \ test_xdp_redirect.sh \ test_xdp_redirect_multi.sh \ - test_xdp_meta.sh \ test_tunnel.sh \ test_lwt_seg6local.sh \ test_lirc_mode2.sh \ diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c index d98c72dc563e..d32e4edac930 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c @@ -20,10 +20,12 @@ #include <string.h> #include <time.h> #include <unistd.h> +#include <endian.h> #include <arpa/inet.h> #include <sys/time.h> #include <bpf/bpf.h> +#include <test_maps.h> #include "bpf_util.h" @@ -33,6 +35,22 @@ struct tlpm_node { uint8_t key[]; }; +struct lpm_trie_bytes_key { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + unsigned char data[8]; +}; + +struct lpm_trie_int_key { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + unsigned int data; +}; + static struct tlpm_node *tlpm_match(struct tlpm_node *list, const uint8_t *key, size_t n_bits); @@ -223,7 +241,7 @@ static void test_lpm_map(int keysize) n_matches = 0; n_matches_after_delete = 0; n_nodes = 1 << 8; - n_lookups = 1 << 16; + n_lookups = 1 << 9; data = alloca(keysize); memset(data, 0, keysize); @@ -770,16 +788,385 @@ static void test_lpm_multi_thread(void) close(map_fd); } -int main(void) +static int lpm_trie_create(unsigned int key_size, unsigned int value_size, unsigned int max_entries) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int fd; + + opts.map_flags = BPF_F_NO_PREALLOC; + fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie", key_size, value_size, max_entries, + &opts); + CHECK(fd < 0, "bpf_map_create", "error %d\n", errno); + + return fd; +} + +static void test_lpm_trie_update_flags(void) +{ + struct lpm_trie_int_key key; + unsigned int value, got; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), 3); + + /* invalid flags (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_F_LOCK); + CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err); + + /* invalid flags (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST | BPF_EXIST); + CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err); + + /* overwrite an empty qp-trie (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite empty qp-trie", "error %d\n", err); + + /* add a new node */ + key.prefixlen = 16; + key.data = 0; + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add the same node as new node (Error) */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err != -EEXIST, "add new elem again", "error %d\n", err); + + /* overwrite the existed node */ + value = 4; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite the node */ + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "update elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite a non-existent node which is the prefix of the first + * node (Error). + */ + key.prefixlen = 8; + key.data = 0; + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err); + + /* add a new node which is the prefix of the first node */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add another new node which will be the sibling of the first node */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 5; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite the third node */ + value = 3; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* delete the second node to make it an intermediate node */ + key.prefixlen = 8; + key.data = 0; + err = bpf_map_delete_elem(fd, &key); + CHECK(err, "del elem", "error %d\n", err); + + /* overwrite the intermediate node (Error) */ + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err); + + close(fd); +} + +static void test_lpm_trie_update_full_map(void) +{ + struct lpm_trie_int_key key; + int value, got; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), 3); + + /* add a new node */ + key.prefixlen = 16; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add new node */ + key.prefixlen = 8; + key.data = 0; + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add new node */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* try to add more node (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 3; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err != -ENOSPC, "add to full trie", "error %d\n", err); + + /* update the value of an existed node with BPF_EXIST */ + key.prefixlen = 16; + key.data = 0; + value = 4; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* update the value of an existed node with BPF_ANY */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 5; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + close(fd); +} + +static int cmp_str(const void *a, const void *b) +{ + const char *str_a = *(const char **)a, *str_b = *(const char **)b; + + return strcmp(str_a, str_b); +} + +/* Save strings in LPM trie. The trailing '\0' for each string will be + * accounted in the prefixlen. The strings returned during the iteration + * should be sorted as expected. + */ +static void test_lpm_trie_iterate_strs(void) +{ + static const char * const keys[] = { + "ab", "abO", "abc", "abo", "abS", "abcd", + }; + const char *sorted_keys[ARRAY_SIZE(keys)]; + struct lpm_trie_bytes_key key, next_key; + unsigned int value, got, i, j, len; + struct lpm_trie_bytes_key *cur; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), ARRAY_SIZE(keys)); + + for (i = 0; i < ARRAY_SIZE(keys); i++) { + unsigned int flags; + + /* add i-th element */ + flags = i % 2 ? BPF_NOEXIST : 0; + len = strlen(keys[i]); + /* include the trailing '\0' */ + key.prefixlen = (len + 1) * 8; + memset(key.data, 0, sizeof(key.data)); + memcpy(key.data, keys[i], len); + value = i + 100; + err = bpf_map_update_elem(fd, &key, &value, flags); + CHECK(err, "add elem", "#%u error %d\n", i, err); + + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "#%u error %d\n", i, err); + CHECK(got != value, "lookup elem", "#%u expect %u got %u\n", i, value, got); + + /* re-add i-th element (Error) */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err != -EEXIST, "re-add elem", "#%u error %d\n", i, err); + + /* Overwrite i-th element */ + flags = i % 2 ? 0 : BPF_EXIST; + value = i; + err = bpf_map_update_elem(fd, &key, &value, flags); + CHECK(err, "update elem", "error %d\n", err); + + /* Lookup #[0~i] elements */ + for (j = 0; j <= i; j++) { + len = strlen(keys[j]); + key.prefixlen = (len + 1) * 8; + memset(key.data, 0, sizeof(key.data)); + memcpy(key.data, keys[j], len); + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "#%u/%u error %d\n", i, j, err); + CHECK(got != j, "lookup elem", "#%u/%u expect %u got %u\n", + i, j, value, got); + } + } + + /* Add element to a full qp-trie (Error) */ + key.prefixlen = sizeof(key.data) * 8; + memset(key.data, 0, sizeof(key.data)); + value = 0; + err = bpf_map_update_elem(fd, &key, &value, 0); + CHECK(err != -ENOSPC, "add to full qp-trie", "error %d\n", err); + + /* Iterate sorted elements: no deletion */ + memcpy(sorted_keys, keys, sizeof(keys)); + qsort(sorted_keys, ARRAY_SIZE(sorted_keys), sizeof(sorted_keys[0]), cmp_str); + cur = NULL; + for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) { + len = strlen(sorted_keys[i]); + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != (len + 1) * 8, "iterate", + "#%u invalid len %u expect %u\n", + i, next_key.prefixlen, (len + 1) * 8); + CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate", + "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]); + + cur = &next_key; + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "more element", "error %d\n", err); + + /* Iterate sorted elements: delete the found key after each iteration */ + cur = NULL; + for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) { + len = strlen(sorted_keys[i]); + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != (len + 1) * 8, "iterate", + "#%u invalid len %u expect %u\n", + i, next_key.prefixlen, (len + 1) * 8); + CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate", + "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]); + + cur = &next_key; + + err = bpf_map_delete_elem(fd, cur); + CHECK(err, "delete", "#%u error %d\n", i, err); + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "non-empty qp-trie", "error %d\n", err); + + close(fd); +} + +/* Use the fixed prefixlen (32) and save integers in LPM trie. The iteration of + * LPM trie will return these integers in big-endian order, therefore, convert + * these integers to big-endian before update. After each iteration, delete the + * found key (the smallest integer) and expect the next iteration will return + * the second smallest number. + */ +static void test_lpm_trie_iterate_ints(void) +{ + struct lpm_trie_int_key key, next_key; + unsigned int i, max_entries; + struct lpm_trie_int_key *cur; + unsigned int *data_set; + int fd, err; + bool value; + + max_entries = 4096; + data_set = calloc(max_entries, sizeof(*data_set)); + CHECK(!data_set, "malloc", "no mem\n"); + for (i = 0; i < max_entries; i++) + data_set[i] = i; + + fd = lpm_trie_create(sizeof(key), sizeof(value), max_entries); + value = true; + for (i = 0; i < max_entries; i++) { + key.prefixlen = 32; + key.data = htobe32(data_set[i]); + + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add elem", "#%u error %d\n", i, err); + } + + cur = NULL; + for (i = 0; i < max_entries; i++) { + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != 32, "iterate", "#%u invalid len %u\n", + i, next_key.prefixlen); + CHECK(be32toh(next_key.data) != data_set[i], "iterate", "#%u got 0x%x exp 0x%x\n", + i, be32toh(next_key.data), data_set[i]); + cur = &next_key; + + /* + * Delete the minimal key, the next call of bpf_get_next_key() + * will return the second minimal key. + */ + err = bpf_map_delete_elem(fd, &next_key); + CHECK(err, "del elem", "#%u elem error %d\n", i, err); + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "more element", "error %d\n", err); + + err = bpf_map_get_next_key(fd, NULL, &next_key); + CHECK(err != -ENOENT, "no-empty qp-trie", "error %d\n", err); + + free(data_set); + + close(fd); +} + +void test_lpm_trie_map_basic_ops(void) { int i; /* we want predictable, pseudo random tests */ srand(0xf00ba1); - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - test_lpm_basic(); test_lpm_order(); @@ -792,6 +1179,10 @@ int main(void) test_lpm_get_next_key(); test_lpm_multi_thread(); - printf("test_lpm: OK\n"); - return 0; + test_lpm_trie_update_flags(); + test_lpm_trie_update_full_map(); + test_lpm_trie_iterate_strs(); + test_lpm_trie_iterate_ints(); + + printf("%s: PASS\n", __func__); } diff --git a/tools/testing/selftests/bpf/map_tests/task_storage_map.c b/tools/testing/selftests/bpf/map_tests/task_storage_map.c index 62971dbf2996..a4121d2248ac 100644 --- a/tools/testing/selftests/bpf/map_tests/task_storage_map.c +++ b/tools/testing/selftests/bpf/map_tests/task_storage_map.c @@ -78,8 +78,8 @@ void test_task_storage_map_stress_lookup(void) CHECK(err, "open_and_load", "error %d\n", err); /* Only for a fully preemptible kernel */ - if (!skel->kconfig->CONFIG_PREEMPT) { - printf("%s SKIP (no CONFIG_PREEMPT)\n", __func__); + if (!skel->kconfig->CONFIG_PREEMPTION) { + printf("%s SKIP (no CONFIG_PREEMPTION)\n", __func__); read_bpf_task_storage_busy__destroy(skel); skips++; return; diff --git a/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c new file mode 100644 index 000000000000..7526de379081 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "bpf/libbpf.h" +#include "changes_pkt_data_freplace.skel.h" +#include "changes_pkt_data.skel.h" +#include <test_progs.h> + +static void print_verifier_log(const char *log) +{ + if (env.verbosity >= VERBOSE_VERY) + fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log); +} + +static void test_aux(const char *main_prog_name, + const char *to_be_replaced, + const char *replacement, + bool expect_load) +{ + struct changes_pkt_data_freplace *freplace = NULL; + struct bpf_program *freplace_prog = NULL; + struct bpf_program *main_prog = NULL; + LIBBPF_OPTS(bpf_object_open_opts, opts); + struct changes_pkt_data *main = NULL; + char log[16*1024]; + int err; + + opts.kernel_log_buf = log; + opts.kernel_log_size = sizeof(log); + if (env.verbosity >= VERBOSE_SUPER) + opts.kernel_log_level = 1 | 2 | 4; + main = changes_pkt_data__open_opts(&opts); + if (!ASSERT_OK_PTR(main, "changes_pkt_data__open")) + goto out; + main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name); + if (!ASSERT_OK_PTR(main_prog, "main_prog")) + goto out; + bpf_program__set_autoload(main_prog, true); + err = changes_pkt_data__load(main); + print_verifier_log(log); + if (!ASSERT_OK(err, "changes_pkt_data__load")) + goto out; + freplace = changes_pkt_data_freplace__open_opts(&opts); + if (!ASSERT_OK_PTR(freplace, "changes_pkt_data_freplace__open")) + goto out; + freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement); + if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog")) + goto out; + bpf_program__set_autoload(freplace_prog, true); + bpf_program__set_autoattach(freplace_prog, true); + bpf_program__set_attach_target(freplace_prog, + bpf_program__fd(main_prog), + to_be_replaced); + err = changes_pkt_data_freplace__load(freplace); + print_verifier_log(log); + if (expect_load) { + ASSERT_OK(err, "changes_pkt_data_freplace__load"); + } else { + ASSERT_ERR(err, "changes_pkt_data_freplace__load"); + ASSERT_HAS_SUBSTR(log, "Extension program changes packet data", "error log"); + } + +out: + changes_pkt_data_freplace__destroy(freplace); + changes_pkt_data__destroy(main); +} + +/* There are two global subprograms in both changes_pkt_data.skel.h: + * - one changes packet data; + * - another does not. + * It is ok to freplace subprograms that change packet data with those + * that either do or do not. It is only ok to freplace subprograms + * that do not change packet data with those that do not as well. + * The below tests check outcomes for each combination of such freplace. + * Also test a case when main subprogram itself is replaced and is a single + * subprogram in a program. + */ +void test_changes_pkt_data_freplace(void) +{ + struct { + const char *main; + const char *to_be_replaced; + bool changes; + } mains[] = { + { "main_with_subprogs", "changes_pkt_data", true }, + { "main_with_subprogs", "does_not_change_pkt_data", false }, + { "main_changes", "main_changes", true }, + { "main_does_not_change", "main_does_not_change", false }, + }; + struct { + const char *func; + bool changes; + } replacements[] = { + { "changes_pkt_data", true }, + { "does_not_change_pkt_data", false } + }; + char buf[64]; + + for (int i = 0; i < ARRAY_SIZE(mains); ++i) { + for (int j = 0; j < ARRAY_SIZE(replacements); ++j) { + snprintf(buf, sizeof(buf), "%s_with_%s", + mains[i].to_be_replaced, replacements[j].func); + if (!test__start_subtest(buf)) + continue; + test_aux(mains[i].main, mains[i].to_be_replaced, replacements[j].func, + mains[i].changes || !replacements[j].changes); + } + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c index 6fa19449297e..43676a9922dc 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c @@ -3,11 +3,14 @@ #include <test_progs.h> #include "raw_tp_null.skel.h" +#include "raw_tp_null_fail.skel.h" void test_raw_tp_null(void) { struct raw_tp_null *skel; + RUN_TESTS(raw_tp_null_fail); + skel = raw_tp_null__open_and_load(); if (!ASSERT_OK_PTR(skel, "raw_tp_null__open_and_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h new file mode 100644 index 000000000000..1bdfb79ef009 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h @@ -0,0 +1,394 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __SOCKET_HELPERS__ +#define __SOCKET_HELPERS__ + +#include <linux/vm_sockets.h> + +/* include/linux/net.h */ +#define SOCK_TYPE_MASK 0xf + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +/* include/linux/cleanup.h */ +#define __get_and_null(p, nullvalue) \ + ({ \ + __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = nullvalue; \ + __val; \ + }) + +#define take_fd(fd) __get_and_null(fd, -EBADF) + +/* Wrappers that fail the test on error and report it. */ + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +static inline void close_fd(int *fd) +{ + if (*fd >= 0) + xclose(*fd); +} + +#define __close_fd __attribute__((cleanup(close_fd))) + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len = 0; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + +static inline int poll_connect(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set wfds; + int r, eval; + socklen_t esize = sizeof(eval); + + FD_ZERO(&wfds); + FD_SET(fd, &wfds); + + r = select(fd + 1, NULL, &wfds, NULL, &timeout); + if (r == 0) + errno = ETIME; + if (r != 1) + return -1; + + if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) + return -1; + if (eval != 0) { + errno = eval; + return -1; + } + + return 0; +} + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + + +static inline int create_pair(int family, int sotype, int *p0, int *p1) +{ + __close_fd int s, c = -1, p = -1; + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int err; + + s = socket_loopback(family, sotype); + if (s < 0) + return s; + + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + c = xsocket(family, sotype, 0); + if (c < 0) + return c; + + err = connect(c, sockaddr(&addr), len); + if (err) { + if (errno != EINPROGRESS) { + FAIL_ERRNO("connect"); + return err; + } + + err = poll_connect(c, IO_TIMEOUT_SEC); + if (err) { + FAIL_ERRNO("poll_connect"); + return err; + } + } + + switch (sotype & SOCK_TYPE_MASK) { + case SOCK_DGRAM: + err = xgetsockname(c, sockaddr(&addr), &len); + if (err) + return err; + + err = xconnect(s, sockaddr(&addr), len); + if (err) + return err; + + *p0 = take_fd(s); + break; + case SOCK_STREAM: + case SOCK_SEQPACKET: + p = xaccept_nonblock(s, NULL, NULL); + if (p < 0) + return p; + + *p0 = take_fd(p); + break; + default: + FAIL("Unsupported socket type %#x", sotype); + return -EOPNOTSUPP; + } + + *p1 = take_fd(c); + return 0; +} + +static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, + int *p0, int *p1) +{ + int err; + + err = create_pair(family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + + return err; +} + +#endif // __SOCKET_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index a2041f8e32eb..884ad87783d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -12,6 +12,7 @@ #include "test_sockmap_progs_query.skel.h" #include "test_sockmap_pass_prog.skel.h" #include "test_sockmap_drop_prog.skel.h" +#include "test_sockmap_change_tail.skel.h" #include "bpf_iter_sockmap.skel.h" #include "sockmap_helpers.h" @@ -108,6 +109,35 @@ out: close(s); } +static void test_sockmap_vsock_delete_on_close(void) +{ + int err, c, p, map; + const int zero = 0; + + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair(AF_VSOCK)")) + return; + + map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), + sizeof(int), 1, NULL); + if (!ASSERT_GE(map, 0, "bpf_map_create")) { + close(c); + goto out; + } + + err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); + close(c); + if (!ASSERT_OK(err, "bpf_map_update")) + goto out; + + err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + ASSERT_OK(err, "after close(), bpf_map_update"); + +out: + close(p); + close(map); +} + static void test_skmsg_helpers(enum bpf_map_type map_type) { struct test_skmsg_load_helpers *skel; @@ -614,6 +644,54 @@ out: test_sockmap_drop_prog__destroy(drop); } +static void test_sockmap_skb_verdict_change_tail(void) +{ + struct test_sockmap_change_tail *skel; + int err, map, verdict; + int c1, p1, sent, recvd; + int zero = 0; + char buf[2]; + + skel = test_sockmap_change_tail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1); + if (!ASSERT_OK(err, "create_pair()")) + goto out; + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + sent = xsend(p1, "Tr", 2, 0); + ASSERT_EQ(sent, 2, "xsend(p1)"); + recvd = recv(c1, buf, 2, 0); + ASSERT_EQ(recvd, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + sent = xsend(p1, "G", 1, 0); + ASSERT_EQ(sent, 1, "xsend(p1)"); + recvd = recv(c1, buf, 2, 0); + ASSERT_EQ(recvd, 2, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + sent = xsend(p1, "E", 1, 0); + ASSERT_EQ(sent, 1, "xsend(p1)"); + recvd = recv(c1, buf, 1, 0); + ASSERT_EQ(recvd, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + +out_close: + close(c1); + close(p1); +out: + test_sockmap_change_tail__destroy(skel); +} + static void test_sockmap_skb_verdict_peek_helper(int map) { int err, c1, p1, zero = 0, sent, recvd, avail; @@ -905,8 +983,10 @@ static void test_sockmap_same_sock(void) err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream); ASSERT_OK(err, "socketpair(af_unix, sock_stream)"); - if (err) + if (err) { + close(tcp); goto out; + } for (i = 0; i < 2; i++) { err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY); @@ -925,24 +1005,70 @@ static void test_sockmap_same_sock(void) ASSERT_OK(err, "bpf_map_update_elem(tcp)"); } + close(tcp); err = bpf_map_delete_elem(map, &zero); - ASSERT_OK(err, "bpf_map_delete_elem(entry)"); + ASSERT_ERR(err, "bpf_map_delete_elem(entry)"); close(stream[0]); close(stream[1]); out: close(dgram); - close(tcp); close(udp); test_sockmap_pass_prog__destroy(skel); } +static void test_sockmap_skb_verdict_vsock_poll(void) +{ + struct test_sockmap_pass_prog *skel; + int err, map, conn, peer; + struct bpf_program *prog; + struct bpf_link *link; + char buf = 'x'; + int zero = 0; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + if (create_pair(AF_VSOCK, SOCK_STREAM, &conn, &peer)) + goto destroy; + + prog = skel->progs.prog_skb_verdict; + map = bpf_map__fd(skel->maps.sock_map_rx); + link = bpf_program__attach_sockmap(prog, map); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap")) + goto close; + + err = bpf_map_update_elem(map, &zero, &conn, BPF_ANY); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + goto detach; + + if (xsend(peer, &buf, 1, 0) != 1) + goto detach; + + err = poll_read(conn, IO_TIMEOUT_SEC); + if (!ASSERT_OK(err, "poll")) + goto detach; + + if (xrecv_nonblock(conn, &buf, 1, 0) != 1) + FAIL("xrecv_nonblock"); +detach: + bpf_link__detach(link); +close: + xclose(conn); + xclose(peer); +destroy: + test_sockmap_pass_prog__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP); if (test__start_subtest("sockhash create_update_free")) test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH); + if (test__start_subtest("sockmap vsock delete on close")) + test_sockmap_vsock_delete_on_close(); if (test__start_subtest("sockmap sk_msg load helpers")) test_skmsg_helpers(BPF_MAP_TYPE_SOCKMAP); if (test__start_subtest("sockhash sk_msg load helpers")) @@ -981,6 +1107,8 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_fionread(true); if (test__start_subtest("sockmap skb_verdict fionread on drop")) test_sockmap_skb_verdict_fionread(false); + if (test__start_subtest("sockmap skb_verdict change tail")) + test_sockmap_skb_verdict_change_tail(); if (test__start_subtest("sockmap skb_verdict msg_f_peek")) test_sockmap_skb_verdict_peek(); if (test__start_subtest("sockmap skb_verdict msg_f_peek with link")) @@ -997,4 +1125,6 @@ void test_sockmap_basic(void) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKMAP); if (test__start_subtest("sockhash sk_msg attach sockhash helpers with link")) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH); + if (test__start_subtest("sockmap skb_verdict vsock poll")) + test_sockmap_skb_verdict_vsock_poll(); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h index 38e35c72bdaa..3e5571dd578d 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -1,139 +1,12 @@ #ifndef __SOCKMAP_HELPERS__ #define __SOCKMAP_HELPERS__ -#include <linux/vm_sockets.h> +#include "socket_helpers.h" -/* include/linux/net.h */ -#define SOCK_TYPE_MASK 0xf - -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #define __always_unused __attribute__((__unused__)) -/* include/linux/cleanup.h */ -#define __get_and_null(p, nullvalue) \ - ({ \ - __auto_type __ptr = &(p); \ - __auto_type __val = *__ptr; \ - *__ptr = nullvalue; \ - __val; \ - }) - -#define take_fd(fd) __get_and_null(fd, -EBADF) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - #define xbpf_map_delete_elem(fd, key) \ ({ \ int __ret = bpf_map_delete_elem((fd), (key)); \ @@ -193,130 +66,6 @@ __ret; \ }) -static inline void close_fd(int *fd) -{ - if (*fd >= 0) - xclose(*fd); -} - -#define __close_fd __attribute__((cleanup(close_fd))) - -static inline int poll_connect(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set wfds; - int r, eval; - socklen_t esize = sizeof(eval); - - FD_ZERO(&wfds); - FD_SET(fd, &wfds); - - r = select(fd + 1, NULL, &wfds, NULL, &timeout); - if (r == 0) - errno = ETIME; - if (r != 1) - return -1; - - if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0) - return -1; - if (eval != 0) { - errno = eval; - return -1; - } - - return 0; -} - -static inline int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static inline int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static inline void init_addr_loopback4(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static inline void init_addr_loopback6(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, - socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) { u64 value; @@ -334,136 +83,4 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); } -static inline int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static inline int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len = 0; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static inline int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} - -static inline int create_pair(int family, int sotype, int *p0, int *p1) -{ - __close_fd int s, c = -1, p = -1; - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int err; - - s = socket_loopback(family, sotype); - if (s < 0) - return s; - - err = xgetsockname(s, sockaddr(&addr), &len); - if (err) - return err; - - c = xsocket(family, sotype, 0); - if (c < 0) - return c; - - err = connect(c, sockaddr(&addr), len); - if (err) { - if (errno != EINPROGRESS) { - FAIL_ERRNO("connect"); - return err; - } - - err = poll_connect(c, IO_TIMEOUT_SEC); - if (err) { - FAIL_ERRNO("poll_connect"); - return err; - } - } - - switch (sotype & SOCK_TYPE_MASK) { - case SOCK_DGRAM: - err = xgetsockname(c, sockaddr(&addr), &len); - if (err) - return err; - - err = xconnect(s, sockaddr(&addr), len); - if (err) - return err; - - *p0 = take_fd(s); - break; - case SOCK_STREAM: - case SOCK_SEQPACKET: - p = xaccept_nonblock(s, NULL, NULL); - if (p < 0) - return p; - - *p0 = take_fd(p); - break; - default: - FAIL("Unsupported socket type %#x", sotype); - return -EOPNOTSUPP; - } - - *p1 = take_fd(c); - return 0; -} - -static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, - int *p0, int *p1) -{ - int err; - - err = create_pair(family, sotype, c0, p0); - if (err) - return err; - - err = create_pair(family, sotype, c1, p1); - if (err) { - close(*c0); - close(*p0); - } - - return err; -} - #endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c index 60f474d965a9..42e822ea352f 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c @@ -197,7 +197,7 @@ static void test_nodeadlock(void) /* Unnecessary recursion and deadlock detection are reproducible * in the preemptible kernel. */ - if (!skel->kconfig->CONFIG_PREEMPT) { + if (!skel->kconfig->CONFIG_PREEMPTION) { test__skip(); goto done; } diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c new file mode 100644 index 000000000000..74752233e779 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <error.h> +#include <test_progs.h> +#include <linux/pkt_cls.h> + +#include "test_tc_change_tail.skel.h" +#include "socket_helpers.h" + +#define LO_IFINDEX 1 + +void test_tc_change_tail(void) +{ + LIBBPF_OPTS(bpf_tcx_opts, tcx_opts); + struct test_tc_change_tail *skel = NULL; + struct bpf_link *link; + int c1, p1; + char buf[2]; + int ret; + + skel = test_tc_change_tail__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tc_change_tail__open_and_load")) + return; + + link = bpf_program__attach_tcx(skel->progs.change_tail, LO_IFINDEX, + &tcx_opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_tcx")) + goto destroy; + + skel->links.change_tail = link; + ret = create_pair(AF_INET, SOCK_DGRAM, &c1, &p1); + if (!ASSERT_OK(ret, "create_pair")) + goto destroy; + + ret = xsend(p1, "Tr", 2, 0); + ASSERT_EQ(ret, 2, "xsend(p1)"); + ret = recv(c1, buf, 2, 0); + ASSERT_EQ(ret, 2, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + ret = xsend(p1, "G", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 2, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret"); + + ret = xsend(p1, "E", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 1, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + + ret = xsend(p1, "Z", 1, 0); + ASSERT_EQ(ret, 1, "xsend(p1)"); + ret = recv(c1, buf, 1, 0); + ASSERT_EQ(ret, 1, "recv(c1)"); + ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret"); + + close(c1); + close(p1); +destroy: + test_tc_change_tail__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c index 151a4210028f..2461d183dee5 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -14,10 +14,16 @@ #include "netlink_helpers.h" #include "tc_helpers.h" +#define NETKIT_HEADROOM 32 +#define NETKIT_TAILROOM 8 + #define MARK 42 #define PRIO 0xeb9f #define ICMP_ECHO 8 +#define FLAG_ADJUST_ROOM (1 << 0) +#define FLAG_SAME_NETNS (1 << 1) + struct icmphdr { __u8 type; __u8 code; @@ -35,7 +41,7 @@ struct iplink_req { }; static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, - bool same_netns, int scrub, int peer_scrub) + int scrub, int peer_scrub, __u32 flags) { struct rtnl_handle rth = { .fd = -1 }; struct iplink_req req = {}; @@ -63,6 +69,10 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, addattr32(&req.n, sizeof(req), IFLA_NETKIT_SCRUB, scrub); addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_SCRUB, peer_scrub); addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode); + if (flags & FLAG_ADJUST_ROOM) { + addattr16(&req.n, sizeof(req), IFLA_NETKIT_HEADROOM, NETKIT_HEADROOM); + addattr16(&req.n, sizeof(req), IFLA_NETKIT_TAILROOM, NETKIT_TAILROOM); + } addattr_nest_end(&req.n, data); addattr_nest_end(&req.n, linkinfo); @@ -87,7 +97,7 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, " addr ee:ff:bb:cc:aa:dd"), "set hwaddress"); } - if (same_netns) { + if (flags & FLAG_SAME_NETNS) { ASSERT_OK(system("ip link set dev " netkit_peer " up"), "up peer"); ASSERT_OK(system("ip addr add dev " netkit_peer " 10.0.0.2/24"), @@ -184,8 +194,8 @@ void serial_test_tc_netkit_basic(void) int err, ifindex; err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, 0); if (err) return; @@ -299,8 +309,8 @@ static void serial_test_tc_netkit_multi_links_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, 0); if (err) return; @@ -428,8 +438,8 @@ static void serial_test_tc_netkit_multi_opts_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, 0); if (err) return; @@ -543,8 +553,8 @@ void serial_test_tc_netkit_device(void) int err, ifindex, ifindex2; err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS, - &ifindex, true, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, FLAG_SAME_NETNS); if (err) return; @@ -655,8 +665,8 @@ static void serial_test_tc_netkit_neigh_links_target(int mode, int target) int err, ifindex; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, 0); if (err) return; @@ -733,8 +743,8 @@ static void serial_test_tc_netkit_pkt_type_mode(int mode) struct bpf_link *link; err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, - &ifindex, true, NETKIT_SCRUB_DEFAULT, - NETKIT_SCRUB_DEFAULT); + &ifindex, NETKIT_SCRUB_DEFAULT, + NETKIT_SCRUB_DEFAULT, FLAG_SAME_NETNS); if (err) return; @@ -799,7 +809,7 @@ void serial_test_tc_netkit_pkt_type(void) serial_test_tc_netkit_pkt_type_mode(NETKIT_L3); } -static void serial_test_tc_netkit_scrub_type(int scrub) +static void serial_test_tc_netkit_scrub_type(int scrub, bool room) { LIBBPF_OPTS(bpf_netkit_opts, optl); struct test_tc_link *skel; @@ -807,7 +817,8 @@ static void serial_test_tc_netkit_scrub_type(int scrub) int err, ifindex; err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS, - &ifindex, false, scrub, scrub); + &ifindex, scrub, scrub, + room ? FLAG_ADJUST_ROOM : 0); if (err) return; @@ -842,6 +853,8 @@ static void serial_test_tc_netkit_scrub_type(int scrub) ASSERT_EQ(skel->bss->seen_tc8, true, "seen_tc8"); ASSERT_EQ(skel->bss->mark, scrub == NETKIT_SCRUB_NONE ? MARK : 0, "mark"); ASSERT_EQ(skel->bss->prio, scrub == NETKIT_SCRUB_NONE ? PRIO : 0, "prio"); + ASSERT_EQ(skel->bss->headroom, room ? NETKIT_HEADROOM : 0, "headroom"); + ASSERT_EQ(skel->bss->tailroom, room ? NETKIT_TAILROOM : 0, "tailroom"); cleanup: test_tc_link__destroy(skel); @@ -852,6 +865,6 @@ cleanup: void serial_test_tc_netkit_scrub(void) { - serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT); - serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE); + serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT, false); + serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE, true); } diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index d9f65adb456b..3ee40ee9413a 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -225,24 +225,7 @@ void test_verifier_xdp(void) { RUN(verifier_xdp); } void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); } 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); -} +void test_verifier_mtu(void) { RUN(verifier_mtu); } static int init_test_val_map(struct bpf_object *obj, char *map_name) { diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index e6a783c7f5db..937da9b7532a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -2,6 +2,14 @@ #include <test_progs.h> #include <network_helpers.h> #include "test_xdp_context_test_run.skel.h" +#include "test_xdp_meta.skel.h" + +#define TX_ADDR "10.0.0.1" +#define RX_ADDR "10.0.0.2" +#define RX_NAME "veth0" +#define TX_NAME "veth1" +#define TX_NETNS "xdp_context_tx" +#define RX_NETNS "xdp_context_rx" void test_xdp_context_error(int prog_fd, struct bpf_test_run_opts opts, __u32 data_meta, __u32 data, __u32 data_end, @@ -103,3 +111,82 @@ void test_xdp_context_test_run(void) test_xdp_context_test_run__destroy(skel); } + +void test_xdp_context_functional(void) +{ + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + struct netns_obj *rx_ns = NULL, *tx_ns = NULL; + struct bpf_program *tc_prog, *xdp_prog; + struct test_xdp_meta *skel = NULL; + struct nstoken *nstoken = NULL; + int rx_ifindex; + int ret; + + tx_ns = netns_new(TX_NETNS, false); + if (!ASSERT_OK_PTR(tx_ns, "create tx_ns")) + return; + + rx_ns = netns_new(RX_NETNS, false); + if (!ASSERT_OK_PTR(rx_ns, "create rx_ns")) + goto close; + + SYS(close, "ip link add " RX_NAME " netns " RX_NETNS + " type veth peer name " TX_NAME " netns " TX_NETNS); + + nstoken = open_netns(RX_NETNS); + if (!ASSERT_OK_PTR(nstoken, "setns rx_ns")) + goto close; + + SYS(close, "ip addr add " RX_ADDR "/24 dev " RX_NAME); + SYS(close, "ip link set dev " RX_NAME " up"); + + skel = test_xdp_meta__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skeleton")) + goto close; + + rx_ifindex = if_nametoindex(RX_NAME); + if (!ASSERT_GE(rx_ifindex, 0, "if_nametoindex rx")) + goto close; + + tc_hook.ifindex = rx_ifindex; + ret = bpf_tc_hook_create(&tc_hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto close; + + tc_prog = bpf_object__find_program_by_name(skel->obj, "ing_cls"); + if (!ASSERT_OK_PTR(tc_prog, "open ing_cls prog")) + goto close; + + tc_opts.prog_fd = bpf_program__fd(tc_prog); + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto close; + + xdp_prog = bpf_object__find_program_by_name(skel->obj, "ing_xdp"); + if (!ASSERT_OK_PTR(xdp_prog, "open ing_xdp prog")) + goto close; + + ret = bpf_xdp_attach(rx_ifindex, + bpf_program__fd(xdp_prog), + 0, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + close_netns(nstoken); + + nstoken = open_netns(TX_NETNS); + if (!ASSERT_OK_PTR(nstoken, "setns tx_ns")) + goto close; + + SYS(close, "ip addr add " TX_ADDR "/24 dev " TX_NAME); + SYS(close, "ip link set dev " TX_NAME " up"); + ASSERT_OK(SYS_NOFAIL("ping -c 1 " RX_ADDR), "ping"); + +close: + close_netns(nstoken); + test_xdp_meta__destroy(skel); + netns_free(rx_ns); + netns_free(tx_ns); +} + diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index eccaf955e394..f45f4352feeb 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -5,6 +5,10 @@ #define XSTR(s) STR(s) #define STR(s) #s +/* Expand a macro and then stringize the expansion */ +#define QUOTE(str) #str +#define EXPAND_QUOTE(str) QUOTE(str) + /* This set of attributes controls behavior of the * test_loader.c:test_loader__run_subtests(). * @@ -106,6 +110,7 @@ * __arch_* Specify on which architecture the test case should be tested. * Several __arch_* annotations could be specified at once. * When test case is not run on current arch it is marked as skipped. + * __caps_unpriv Specify the capabilities that should be set when running the test. */ #define __msg(msg) __attribute__((btf_decl_tag("comment:test_expect_msg=" XSTR(__COUNTER__) "=" msg))) #define __xlated(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated=" XSTR(__COUNTER__) "=" msg))) @@ -129,6 +134,13 @@ #define __arch_x86_64 __arch("X86_64") #define __arch_arm64 __arch("ARM64") #define __arch_riscv64 __arch("RISCV64") +#define __caps_unpriv(caps) __attribute__((btf_decl_tag("comment:test_caps_unpriv=" EXPAND_QUOTE(caps)))) + +/* Define common capabilities tested using __caps_unpriv */ +#define CAP_NET_ADMIN 12 +#define CAP_SYS_ADMIN 21 +#define CAP_PERFMON 38 +#define CAP_BPF 39 /* Convenience macro for use with 'asm volatile' blocks */ #define __naked __attribute__((naked)) diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data.c b/tools/testing/selftests/bpf/progs/changes_pkt_data.c new file mode 100644 index 000000000000..43cada48b28a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/changes_pkt_data.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__noinline +long changes_pkt_data(struct __sk_buff *sk) +{ + return bpf_skb_pull_data(sk, 0); +} + +__noinline __weak +long does_not_change_pkt_data(struct __sk_buff *sk) +{ + return 0; +} + +SEC("?tc") +int main_with_subprogs(struct __sk_buff *sk) +{ + changes_pkt_data(sk); + does_not_change_pkt_data(sk); + return 0; +} + +SEC("?tc") +int main_changes(struct __sk_buff *sk) +{ + bpf_skb_pull_data(sk, 0); + return 0; +} + +SEC("?tc") +int main_does_not_change(struct __sk_buff *sk) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c new file mode 100644 index 000000000000..f9a622705f1b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("?freplace") +long changes_pkt_data(struct __sk_buff *sk) +{ + return bpf_skb_pull_data(sk, 0); +} + +SEC("?freplace") +long does_not_change_pkt_data(struct __sk_buff *sk) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 8f36c9de7591..dfd817d0348c 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -149,7 +149,7 @@ int ringbuf_release_uninit_dynptr(void *ctx) /* A dynptr can't be used after it has been invalidated */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int use_after_invalid(void *ctx) { struct bpf_dynptr ptr; @@ -428,7 +428,7 @@ int invalid_helper2(void *ctx) /* A bpf_dynptr is invalidated if it's been written into */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int invalid_write1(void *ctx) { struct bpf_dynptr ptr; @@ -1407,7 +1407,7 @@ int invalid_slice_rdwr_rdonly(struct __sk_buff *skb) /* bpf_dynptr_adjust can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_adjust_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1420,7 +1420,7 @@ int dynptr_adjust_invalid(void *ctx) /* bpf_dynptr_is_null can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_is_null_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1433,7 +1433,7 @@ int dynptr_is_null_invalid(void *ctx) /* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_is_rdonly_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1446,7 +1446,7 @@ int dynptr_is_rdonly_invalid(void *ctx) /* bpf_dynptr_size can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_size_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1459,7 +1459,7 @@ int dynptr_size_invalid(void *ctx) /* Only initialized dynptrs can be cloned */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int clone_invalid1(void *ctx) { struct bpf_dynptr ptr1 = {}; @@ -1493,7 +1493,7 @@ int clone_invalid2(struct xdp_md *xdp) /* Invalidating a dynptr should invalidate its clones */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate1(void *ctx) { struct bpf_dynptr clone; @@ -1514,7 +1514,7 @@ int clone_invalidate1(void *ctx) /* Invalidating a dynptr should invalidate its parent */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate2(void *ctx) { struct bpf_dynptr ptr; @@ -1535,7 +1535,7 @@ int clone_invalidate2(void *ctx) /* Invalidating a dynptr should invalidate its siblings */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate3(void *ctx) { struct bpf_dynptr ptr; @@ -1723,7 +1723,7 @@ __noinline long global_call_bpf_dynptr(const struct bpf_dynptr *dynptr) } SEC("?raw_tp") -__failure __msg("arg#1 expected pointer to stack or const struct bpf_dynptr") +__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr") int test_dynptr_reg_type(void *ctx) { struct task_struct *current = NULL; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index ef70b88bccb2..7c969c127573 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1486,4 +1486,30 @@ int iter_subprog_check_stacksafe(const void *ctx) return 0; } +struct bpf_iter_num global_it; + +SEC("raw_tp") +__failure __msg("arg#0 expected pointer to an iterator on stack") +int iter_new_bad_arg(const void *ctx) +{ + bpf_iter_num_new(&global_it, 0, 1); + return 0; +} + +SEC("raw_tp") +__failure __msg("arg#0 expected pointer to an iterator on stack") +int iter_next_bad_arg(const void *ctx) +{ + bpf_iter_num_next(&global_it); + return 0; +} + +SEC("raw_tp") +__failure __msg("arg#0 expected pointer to an iterator on stack") +int iter_destroy_bad_arg(const void *ctx) +{ + bpf_iter_num_destroy(&global_it); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c index d47e59aba6de..f41257eadbb2 100644 --- a/tools/testing/selftests/bpf/progs/iters_state_safety.c +++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c @@ -73,7 +73,7 @@ int create_and_forget_to_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int destroy_without_creating_fail(void *ctx) { /* init with zeros to stop verifier complaining about uninit stack */ @@ -91,7 +91,7 @@ int destroy_without_creating_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int compromise_iter_w_direct_write_fail(void *ctx) { struct bpf_iter_num iter; @@ -143,7 +143,7 @@ int compromise_iter_w_direct_write_and_skip_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int compromise_iter_w_helper_write_fail(void *ctx) { struct bpf_iter_num iter; @@ -230,7 +230,7 @@ int valid_stack_reuse(void *ctx) } SEC("?raw_tp") -__failure __msg("expected uninitialized iter_num as arg #1") +__failure __msg("expected uninitialized iter_num as arg #0") int double_create_fail(void *ctx) { struct bpf_iter_num iter; @@ -258,7 +258,7 @@ int double_create_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int double_destroy_fail(void *ctx) { struct bpf_iter_num iter; @@ -284,7 +284,7 @@ int double_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int next_without_new_fail(void *ctx) { struct bpf_iter_num iter; @@ -305,7 +305,7 @@ int next_without_new_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int next_after_destroy_fail(void *ctx) { struct bpf_iter_num iter; diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c index 4a176e6aede8..6543d5b6e0a9 100644 --- a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c +++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c @@ -79,7 +79,7 @@ int testmod_seq_truncated(const void *ctx) SEC("?raw_tp") __failure -__msg("expected an initialized iter_testmod_seq as arg #2") +__msg("expected an initialized iter_testmod_seq as arg #1") int testmod_seq_getter_before_bad(const void *ctx) { struct bpf_iter_testmod_seq it; @@ -89,7 +89,7 @@ int testmod_seq_getter_before_bad(const void *ctx) SEC("?raw_tp") __failure -__msg("expected an initialized iter_testmod_seq as arg #2") +__msg("expected an initialized iter_testmod_seq as arg #1") int testmod_seq_getter_after_bad(const void *ctx) { struct bpf_iter_testmod_seq it; diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null.c b/tools/testing/selftests/bpf/progs/raw_tp_null.c index 457f34c151e3..5927054b6dd9 100644 --- a/tools/testing/selftests/bpf/progs/raw_tp_null.c +++ b/tools/testing/selftests/bpf/progs/raw_tp_null.c @@ -3,6 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -17,16 +18,14 @@ int BPF_PROG(test_raw_tp_null, struct sk_buff *skb) if (task->pid != tid) return 0; - i = i + skb->mark + 1; - /* The compiler may move the NULL check before this deref, which causes - * the load to fail as deref of scalar. Prevent that by using a barrier. + /* If dead code elimination kicks in, the increment +=2 will be + * removed. For raw_tp programs attaching to tracepoints in kernel + * modules, we mark input arguments as PTR_MAYBE_NULL, so branch + * prediction should never kick in. */ - barrier(); - /* If dead code elimination kicks in, the increment below will - * be removed. For raw_tp programs, we mark input arguments as - * PTR_MAYBE_NULL, so branch prediction should never kick in. - */ - if (!skb) - i += 2; + asm volatile ("%[i] += 1; if %[ctx] != 0 goto +1; %[i] += 2;" + : [i]"+r"(i) + : [ctx]"r"(skb) + : "memory"); return 0; } diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c new file mode 100644 index 000000000000..38d669957bf1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +/* Ensure module parameter has PTR_MAYBE_NULL */ +SEC("tp_btf/bpf_testmod_test_raw_tp_null") +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") +int test_raw_tp_null_bpf_testmod_test_raw_tp_null_arg_1(void *ctx) { + asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u64 *)(r1 +0);" ::: __clobber_all); + return 0; +} + +/* Check NULL marking */ +SEC("tp_btf/sched_pi_setprio") +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") +int test_raw_tp_null_sched_pi_setprio_arg_2(void *ctx) { + asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u64 *)(r1 +0);" ::: __clobber_all); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c index 76556e0b42b2..69da05bb6c63 100644 --- a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c +++ b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c @@ -4,7 +4,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -extern bool CONFIG_PREEMPT __kconfig __weak; +extern bool CONFIG_PREEMPTION __kconfig __weak; extern const int bpf_task_storage_busy __ksym; char _license[] SEC("license") = "GPL"; @@ -24,7 +24,7 @@ int BPF_PROG(read_bpf_task_storage_busy) { int *value; - if (!CONFIG_PREEMPT) + if (!CONFIG_PREEMPTION) return 0; if (bpf_get_current_pid_tgid() >> 32 != pid) diff --git a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c index ea2dbb80f7b3..986829aaf73a 100644 --- a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c +++ b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c @@ -10,7 +10,7 @@ char _license[] SEC("license") = "GPL"; #define EBUSY 16 #endif -extern bool CONFIG_PREEMPT __kconfig __weak; +extern bool CONFIG_PREEMPTION __kconfig __weak; int nr_get_errs = 0; int nr_del_errs = 0; @@ -29,7 +29,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, int ret, zero = 0; int *value; - if (!CONFIG_PREEMPT) + if (!CONFIG_PREEMPTION) return 0; task = bpf_get_current_task_btf(); diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c index d1a57f7d09bd..fe6249d99b31 100644 --- a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c @@ -11,6 +11,8 @@ int subprog_tc(struct __sk_buff *skb) __sink(skb); __sink(ret); + /* let verifier know that 'subprog_tc' can change pointers to skb->data */ + bpf_skb_change_proto(skb, 0, 0); return ret; } diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c index e68667aec6a6..cd4d752bd089 100644 --- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c @@ -45,7 +45,7 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) } SEC("?lsm.s/bpf") -__failure __msg("arg#1 expected pointer to stack or const struct bpf_dynptr") +__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr") int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size) { unsigned long val = 0; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c new file mode 100644 index 000000000000..2796dd8545eb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 ByteDance */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +long change_tail_ret = 1; + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + char *data, *data_end; + + bpf_skb_pull_data(skb, 1); + data = (char *)(unsigned long)skb->data; + data_end = (char *)(unsigned long)skb->data_end; + + if (data + 1 > data_end) + return SK_PASS; + + if (data[0] == 'T') { /* Trim the packet */ + change_tail_ret = bpf_skb_change_tail(skb, skb->len - 1, 0); + return SK_PASS; + } else if (data[0] == 'G') { /* Grow the packet */ + change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0); + return SK_PASS; + } else if (data[0] == 'E') { /* Error */ + change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + return SK_PASS; + } + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c new file mode 100644 index 000000000000..28edafe803f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/udp.h> +#include <linux/pkt_cls.h> + +long change_tail_ret = 1; + +static __always_inline struct iphdr *parse_ip_header(struct __sk_buff *skb, int *ip_proto) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = data; + struct iphdr *iph; + + /* Verify Ethernet header */ + if ((void *)(data + sizeof(*eth)) > data_end) + return NULL; + + /* Skip Ethernet header to get to IP header */ + iph = (void *)(data + sizeof(struct ethhdr)); + + /* Verify IP header */ + if ((void *)(data + sizeof(struct ethhdr) + sizeof(*iph)) > data_end) + return NULL; + + /* Basic IP header validation */ + if (iph->version != 4) /* Only support IPv4 */ + return NULL; + + if (iph->ihl < 5) /* Minimum IP header length */ + return NULL; + + *ip_proto = iph->protocol; + return iph; +} + +static __always_inline struct udphdr *parse_udp_header(struct __sk_buff *skb, struct iphdr *iph) +{ + void *data_end = (void *)(long)skb->data_end; + void *hdr = (void *)iph; + struct udphdr *udp; + + /* Calculate UDP header position */ + udp = hdr + (iph->ihl * 4); + hdr = (void *)udp; + + /* Verify UDP header bounds */ + if ((void *)(hdr + sizeof(*udp)) > data_end) + return NULL; + + return udp; +} + +SEC("tc/ingress") +int change_tail(struct __sk_buff *skb) +{ + int len = skb->len; + struct udphdr *udp; + struct iphdr *iph; + void *data_end; + char *payload; + int ip_proto; + + bpf_skb_pull_data(skb, len); + + data_end = (void *)(long)skb->data_end; + iph = parse_ip_header(skb, &ip_proto); + if (!iph) + return TCX_PASS; + + if (ip_proto != IPPROTO_UDP) + return TCX_PASS; + + udp = parse_udp_header(skb, iph); + if (!udp) + return TCX_PASS; + + payload = (char *)udp + (sizeof(struct udphdr)); + if (payload + 1 > (char *)data_end) + return TCX_PASS; + + if (payload[0] == 'T') { /* Trim the packet */ + change_tail_ret = bpf_skb_change_tail(skb, len - 1, 0); + if (!change_tail_ret) + bpf_skb_change_tail(skb, len, 0); + return TCX_PASS; + } else if (payload[0] == 'G') { /* Grow the packet */ + change_tail_ret = bpf_skb_change_tail(skb, len + 1, 0); + if (!change_tail_ret) + bpf_skb_change_tail(skb, len, 0); + return TCX_PASS; + } else if (payload[0] == 'E') { /* Error */ + change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + return TCX_PASS; + } else if (payload[0] == 'Z') { /* Zero */ + change_tail_ret = bpf_skb_change_tail(skb, 0, 0); + return TCX_PASS; + } + return TCX_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c index 10d825928499..630f12e51b07 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_link.c +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -8,6 +8,7 @@ #include <linux/if_packet.h> #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> char LICENSE[] SEC("license") = "GPL"; @@ -27,6 +28,7 @@ bool seen_host; bool seen_mcast; int mark, prio; +unsigned short headroom, tailroom; SEC("tc/ingress") int tc1(struct __sk_buff *skb) @@ -104,11 +106,24 @@ out: return TCX_PASS; } +struct sk_buff { + struct net_device *dev; +}; + +struct net_device { + unsigned short needed_headroom; + unsigned short needed_tailroom; +}; + SEC("tc/egress") int tc8(struct __sk_buff *skb) { + struct net_device *dev = BPF_CORE_READ((struct sk_buff *)skb, dev); + seen_tc8 = true; mark = skb->mark; prio = skb->priority; + headroom = BPF_CORE_READ(dev, needed_headroom); + tailroom = BPF_CORE_READ(dev, needed_tailroom); return TCX_PASS; } diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c index 5aaf2b065f86..bba3e37f749b 100644 --- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c @@ -7,11 +7,7 @@ #include "bpf_misc.h" SEC("tp_btf/bpf_testmod_test_nullable_bare") -/* This used to be a failure test, but raw_tp nullable arguments can now - * directly be dereferenced, whether they have nullable annotation or not, - * and don't need to be explicitly checked. - */ -__success +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx) { return nullable_ctx->len; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index a7c4a7d49fe6..fe2d71ae0e71 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -8,7 +8,7 @@ #define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1) #define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem -SEC("t") +SEC("tc") int ing_cls(struct __sk_buff *ctx) { __u8 *data, *data_meta, *data_end; @@ -28,7 +28,7 @@ int ing_cls(struct __sk_buff *ctx) return diff ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("x") +SEC("xdp") int ing_xdp(struct xdp_md *ctx) { __u8 *data, *data_meta, *data_end; diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index 7c881bca9af5..8bcddadfc4da 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -32,18 +32,18 @@ int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp) SEC("iter/cgroup") __description("uninitialized iter in ->next()") -__failure __msg("expected an initialized iter_bits as arg #1") +__failure __msg("expected an initialized iter_bits as arg #0") int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) { - struct bpf_iter_bits *it = NULL; + struct bpf_iter_bits it = {}; - bpf_iter_bits_next(it); + bpf_iter_bits_next(&it); return 0; } SEC("iter/cgroup") __description("uninitialized iter in ->destroy()") -__failure __msg("expected an initialized iter_bits as arg #1") +__failure __msg("expected an initialized iter_bits as arg #0") int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) { struct bpf_iter_bits it = {}; diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c index a570e48b917a..28b939572cda 100644 --- a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c @@ -11,7 +11,7 @@ __success __retval(0) __naked void btf_ctx_access_accept(void) { asm volatile (" \ - r2 = *(u32*)(r1 + 8); /* load 2nd argument value (int pointer) */\ + r2 = *(u64 *)(r1 + 8); /* load 2nd argument value (int pointer) */\ r0 = 0; \ exit; \ " ::: __clobber_all); @@ -23,7 +23,43 @@ __success __retval(0) __naked void ctx_access_u32_pointer_accept(void) { asm volatile (" \ - r2 = *(u32*)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ + r2 = *(u64 *)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("fentry/bpf_fentry_test9") +__description("btf_ctx_access u32 pointer reject u32") +__failure __msg("size 4 must be 8") +__naked void ctx_access_u32_pointer_reject_32(void) +{ + asm volatile (" \ + r2 = *(u32 *)(r1 + 0); /* load 1st argument with narrow load */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("fentry/bpf_fentry_test9") +__description("btf_ctx_access u32 pointer reject u16") +__failure __msg("size 2 must be 8") +__naked void ctx_access_u32_pointer_reject_16(void) +{ + asm volatile (" \ + r2 = *(u16 *)(r1 + 0); /* load 1st argument with narrow load */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("fentry/bpf_fentry_test9") +__description("btf_ctx_access u32 pointer reject u8") +__failure __msg("size 1 must be 8") +__naked void ctx_access_u32_pointer_reject_8(void) +{ + asm volatile (" \ + r2 = *(u8 *)(r1 + 0); /* load 1st argument with narrow load */\ r0 = 0; \ exit; \ " ::: __clobber_all); diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c index ec79cbcfde91..87e51a215558 100644 --- a/tools/testing/selftests/bpf/progs/verifier_d_path.c +++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c @@ -11,7 +11,7 @@ __success __retval(0) __naked void d_path_accept(void) { asm volatile (" \ - r1 = *(u32*)(r1 + 0); \ + r1 = *(u64 *)(r1 + 0); \ r2 = r10; \ r2 += -8; \ r6 = 0; \ @@ -31,7 +31,7 @@ __failure __msg("helper call is not allowed in probe") __naked void d_path_reject(void) { asm volatile (" \ - r1 = *(u32*)(r1 + 0); \ + r1 = *(u64 *)(r1 + 0); \ r2 = r10; \ r2 += -8; \ r6 = 0; \ diff --git a/tools/testing/selftests/bpf/progs/verifier_mtu.c b/tools/testing/selftests/bpf/progs/verifier_mtu.c index 70c7600a26a0..4ccf1ebc42d1 100644 --- a/tools/testing/selftests/bpf/progs/verifier_mtu.c +++ b/tools/testing/selftests/bpf/progs/verifier_mtu.c @@ -6,7 +6,9 @@ SEC("tc/ingress") __description("uninit/mtu: write rejected") -__failure __msg("invalid indirect read from stack") +__success +__caps_unpriv(CAP_BPF|CAP_NET_ADMIN) +__failure_unpriv __msg_unpriv("invalid indirect read from stack") int tc_uninit_mtu(struct __sk_buff *ctx) { __u32 mtu; diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c index d3e70e38e442..0d5e56dffabb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_sock.c +++ b/tools/testing/selftests/bpf/progs/verifier_sock.c @@ -50,6 +50,13 @@ struct { __uint(map_flags, BPF_F_NO_PREALLOC); } sk_storage_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + SEC("cgroup/skb") __description("skb->sk: no NULL check") __failure __msg("invalid mem access 'sock_common_or_null'") @@ -1037,4 +1044,53 @@ __naked void sock_create_read_src_port(void) : __clobber_all); } +__noinline +long skb_pull_data2(struct __sk_buff *sk, __u32 len) +{ + return bpf_skb_pull_data(sk, len); +} + +__noinline +long skb_pull_data1(struct __sk_buff *sk, __u32 len) +{ + return skb_pull_data2(sk, len); +} + +/* global function calls bpf_skb_pull_data(), which invalidates packet + * pointers established before global function call. + */ +SEC("tc") +__failure __msg("invalid mem access") +int invalidate_pkt_pointers_from_global_func(struct __sk_buff *sk) +{ + int *p = (void *)(long)sk->data; + + if ((void *)(p + 1) > (void *)(long)sk->data_end) + return TCX_DROP; + skb_pull_data1(sk, 0); + *p = 42; /* this is unsafe */ + return TCX_PASS; +} + +__noinline +int tail_call(struct __sk_buff *sk) +{ + bpf_tail_call_static(sk, &jmp_table, 0); + return 0; +} + +/* Tail calls invalidate packet pointers. */ +SEC("tc") +__failure __msg("invalid mem access") +int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk) +{ + int *p = (void *)(long)sk->data; + + if ((void *)(p + 1) > (void *)(long)sk->data_end) + return TCX_DROP; + tail_call(sk); + *p = 42; /* this is unsafe */ + return TCX_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 671d9f415dbf..1e5a511e8494 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -1244,4 +1244,39 @@ __naked void old_stack_misc_vs_cur_ctx_ptr(void) : __clobber_all); } +SEC("socket") +__description("stack_noperfmon: reject read of invalid slots") +__success +__caps_unpriv(CAP_BPF) +__failure_unpriv __msg_unpriv("invalid read from stack off -8+1 size 8") +__naked void stack_noperfmon_reject_invalid_read(void) +{ + asm volatile (" \ + r2 = 1; \ + r6 = r10; \ + r6 += -8; \ + *(u8 *)(r6 + 0) = r2; \ + r2 = *(u64 *)(r6 + 0); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("stack_noperfmon: narrow spill onto 64-bit scalar spilled slots") +__success +__caps_unpriv(CAP_BPF) +__success_unpriv +__naked void stack_noperfmon_spill_32bit_onto_64bit_slot(void) +{ + asm volatile(" \ + r0 = 0; \ + *(u64 *)(r10 - 8) = r0; \ + *(u32 *)(r10 - 8) = r0; \ + exit; \ +" : + : + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h index ca0162b4dc57..1fcfa5160231 100644 --- a/tools/testing/selftests/bpf/sdt.h +++ b/tools/testing/selftests/bpf/sdt.h @@ -102,6 +102,8 @@ # define STAP_SDT_ARG_CONSTRAINT nZr # elif defined __arm__ # define STAP_SDT_ARG_CONSTRAINT g +# elif defined __loongarch__ +# define STAP_SDT_ARG_CONSTRAINT nmr # else # define STAP_SDT_ARG_CONSTRAINT nor # endif diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 3e9b009580d4..53b06647cf57 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -36,6 +36,7 @@ #define TEST_TAG_ARCH "comment:test_arch=" #define TEST_TAG_JITED_PFX "comment:test_jited=" #define TEST_TAG_JITED_PFX_UNPRIV "comment:test_jited_unpriv=" +#define TEST_TAG_CAPS_UNPRIV "comment:test_caps_unpriv=" /* Warning: duplicated in bpf_misc.h */ #define POINTER_VALUE 0xcafe4all @@ -74,6 +75,7 @@ struct test_subspec { struct expected_msgs jited; int retval; bool execute; + __u64 caps; }; struct test_spec { @@ -276,6 +278,37 @@ static int parse_int(const char *str, int *val, const char *name) return 0; } +static int parse_caps(const char *str, __u64 *val, const char *name) +{ + int cap_flag = 0; + char *token = NULL, *saveptr = NULL; + + char *str_cpy = strdup(str); + if (str_cpy == NULL) { + PRINT_FAIL("Memory allocation failed\n"); + return -EINVAL; + } + + token = strtok_r(str_cpy, "|", &saveptr); + while (token != NULL) { + errno = 0; + if (!strncmp("CAP_", token, sizeof("CAP_") - 1)) { + PRINT_FAIL("define %s constant in bpf_misc.h, failed to parse caps\n", token); + return -EINVAL; + } + cap_flag = strtol(token, NULL, 10); + if (!cap_flag || errno) { + PRINT_FAIL("failed to parse caps %s\n", name); + return -EINVAL; + } + *val |= (1ULL << cap_flag); + token = strtok_r(NULL, "|", &saveptr); + } + + free(str_cpy); + return 0; +} + static int parse_retval(const char *str, int *val, const char *name) { struct { @@ -541,6 +574,12 @@ static int parse_test_spec(struct test_loader *tester, jit_on_next_line = true; } else if (str_has_pfx(s, TEST_BTF_PATH)) { spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1; + } else if (str_has_pfx(s, TEST_TAG_CAPS_UNPRIV)) { + val = s + sizeof(TEST_TAG_CAPS_UNPRIV) - 1; + err = parse_caps(val, &spec->unpriv.caps, "test caps"); + if (err) + goto cleanup; + spec->mode_mask |= UNPRIV; } } @@ -917,6 +956,13 @@ void run_subtest(struct test_loader *tester, test__end_subtest(); return; } + if (subspec->caps) { + err = cap_enable_effective(subspec->caps, NULL); + if (err) { + PRINT_FAIL("failed to set capabilities: %i, %s\n", err, strerror(err)); + goto subtest_cleanup; + } + } } /* Implicitly reset to NULL if next test case doesn't specify */ diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index e5c7ecbe57e3..fd2da2234cc9 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1579,8 +1579,12 @@ static void test_txmsg_redir(int cgrp, struct sockmap_options *opt) static void test_txmsg_redir_wait_sndmem(int cgrp, struct sockmap_options *opt) { - txmsg_redir = 1; opt->tx_wait_mem = true; + txmsg_redir = 1; + test_send_large(opt, cgrp); + + txmsg_redir = 1; + txmsg_apply = 4097; test_send_large(opt, cgrp); opt->tx_wait_mem = false; } diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh deleted file mode 100755 index 2740322c1878..000000000000 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ /dev/null @@ -1,58 +0,0 @@ -#!/bin/sh - -BPF_FILE="test_xdp_meta.bpf.o" -# Kselftest framework requirement - SKIP code is 4. -readonly KSFT_SKIP=4 -readonly NS1="ns1-$(mktemp -u XXXXXX)" -readonly NS2="ns2-$(mktemp -u XXXXXX)" - -cleanup() -{ - if [ "$?" = "0" ]; then - echo "selftests: test_xdp_meta [PASS]"; - else - echo "selftests: test_xdp_meta [FAILED]"; - fi - - set +e - ip link del veth1 2> /dev/null - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null -} - -ip link set dev lo xdp off 2>/dev/null > /dev/null -if [ $? -ne 0 ];then - echo "selftests: [SKIP] Could not run test without the ip xdp support" - exit $KSFT_SKIP -fi -set -e - -ip netns add ${NS1} -ip netns add ${NS2} - -trap cleanup 0 2 3 6 9 - -ip link add veth1 type veth peer name veth2 - -ip link set veth1 netns ${NS1} -ip link set veth2 netns ${NS2} - -ip netns exec ${NS1} ip addr add 10.1.1.11/24 dev veth1 -ip netns exec ${NS2} ip addr add 10.1.1.22/24 dev veth2 - -ip netns exec ${NS1} tc qdisc add dev veth1 clsact -ip netns exec ${NS2} tc qdisc add dev veth2 clsact - -ip netns exec ${NS1} tc filter add dev veth1 ingress bpf da obj ${BPF_FILE} sec t -ip netns exec ${NS2} tc filter add dev veth2 ingress bpf da obj ${BPF_FILE} sec t - -ip netns exec ${NS1} ip link set dev veth1 xdp obj ${BPF_FILE} sec x -ip netns exec ${NS2} ip link set dev veth2 xdp obj ${BPF_FILE} sec x - -ip netns exec ${NS1} ip link set dev veth1 up -ip netns exec ${NS2} ip link set dev veth2 up - -ip netns exec ${NS1} ping -c 1 10.1.1.22 -ip netns exec ${NS2} ping -c 1 10.1.1.11 - -exit 0 diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 2d742fdac6b9..81943c6254e6 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -293,6 +293,10 @@ static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *st return 0; } #else +# ifndef PROCMAP_QUERY_VMA_EXECUTABLE +# define PROCMAP_QUERY_VMA_EXECUTABLE 0x04 +# endif + static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { return -EOPNOTSUPP; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 6f9956eed797..e38675d9b118 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -79,7 +79,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id) .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, - .flags = XSK_UMEM__DEFAULT_FLAGS, + .flags = XDP_UMEM_TX_METADATA_LEN, .tx_metadata_len = sizeof(struct xsk_tx_metadata), }; __u32 idx = 0; @@ -551,6 +551,7 @@ static void hwtstamp_enable(const char *ifname) { struct hwtstamp_config cfg = { .rx_filter = HWTSTAMP_FILTER_ALL, + .tx_type = HWTSTAMP_TX_ON, }; hwtstamp_ioctl(SIOCGHWTSTAMP, ifname, &saved_hwtstamp_cfg); diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 5b2a6a5dd1af..812f656260fb 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -6,7 +6,7 @@ TEST_GEN_FILES += debugfs_target_ids_read_before_terminate_race TEST_GEN_FILES += debugfs_target_ids_pid_leak TEST_GEN_FILES += access_memory access_memory_even -TEST_FILES = _chk_dependency.sh _debugfs_common.sh +TEST_FILES = _chk_dependency.sh _debugfs_common.sh _damon_sysfs.py # functionality tests TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 0fec8f9801ad..469179c18935 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,11 +1,13 @@ # SPDX-License-Identifier: GPL-2.0 TEST_INCLUDES := $(wildcard lib/py/*.py) \ + $(wildcard lib/sh/*.sh) \ ../../net/net_helper.sh \ ../../net/lib.sh \ TEST_PROGS := \ netcons_basic.sh \ + netcons_overflow.sh \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 03a089165d3f..2b10854e4b1e 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -10,7 +10,7 @@ TEST_PROGS := \ mode-2-recovery-updelay.sh \ bond_options.sh \ bond-eth-type-change.sh \ - bond_macvlan.sh + bond_macvlan_ipvlan.sh TEST_FILES := \ lag_lib.sh \ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh deleted file mode 100755 index b609fb6231f4..000000000000 --- a/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh +++ /dev/null @@ -1,99 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Test macvlan over balance-alb - -lib_dir=$(dirname "$0") -source ${lib_dir}/bond_topo_2d1c.sh - -m1_ns="m1-$(mktemp -u XXXXXX)" -m2_ns="m1-$(mktemp -u XXXXXX)" -m1_ip4="192.0.2.11" -m1_ip6="2001:db8::11" -m2_ip4="192.0.2.12" -m2_ip6="2001:db8::12" - -cleanup() -{ - ip -n ${m1_ns} link del macv0 - ip netns del ${m1_ns} - ip -n ${m2_ns} link del macv0 - ip netns del ${m2_ns} - - client_destroy - server_destroy - gateway_destroy -} - -check_connection() -{ - local ns=${1} - local target=${2} - local message=${3:-"macvlan_over_bond"} - RET=0 - - - ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null - check_err $? "ping failed" - log_test "$mode: $message" -} - -macvlan_over_bond() -{ - local param="$1" - RET=0 - - # setup new bond mode - bond_reset "${param}" - - ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge - ip -n ${s_ns} link set macv0 netns ${m1_ns} - ip -n ${m1_ns} link set dev macv0 up - ip -n ${m1_ns} addr add ${m1_ip4}/24 dev macv0 - ip -n ${m1_ns} addr add ${m1_ip6}/24 dev macv0 - - ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge - ip -n ${s_ns} link set macv0 netns ${m2_ns} - ip -n ${m2_ns} link set dev macv0 up - ip -n ${m2_ns} addr add ${m2_ip4}/24 dev macv0 - ip -n ${m2_ns} addr add ${m2_ip6}/24 dev macv0 - - sleep 2 - - check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server" - check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server" - check_connection "${c_ns}" "${m1_ip4}" "IPv4: client->macvlan_1" - check_connection "${c_ns}" "${m1_ip6}" "IPv6: client->macvlan_1" - check_connection "${c_ns}" "${m2_ip4}" "IPv4: client->macvlan_2" - check_connection "${c_ns}" "${m2_ip6}" "IPv6: client->macvlan_2" - check_connection "${m1_ns}" "${m2_ip4}" "IPv4: macvlan_1->macvlan_2" - check_connection "${m1_ns}" "${m2_ip6}" "IPv6: macvlan_1->macvlan_2" - - - sleep 5 - - check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client" - check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client" - check_connection "${m1_ns}" "${c_ip4}" "IPv4: macvlan_1->client" - check_connection "${m1_ns}" "${c_ip6}" "IPv6: macvlan_1->client" - check_connection "${m2_ns}" "${c_ip4}" "IPv4: macvlan_2->client" - check_connection "${m2_ns}" "${c_ip6}" "IPv6: macvlan_2->client" - check_connection "${m2_ns}" "${m1_ip4}" "IPv4: macvlan_2->macvlan_2" - check_connection "${m2_ns}" "${m1_ip6}" "IPv6: macvlan_2->macvlan_2" - - ip -n ${c_ns} neigh flush dev eth0 -} - -trap cleanup EXIT - -setup_prepare -ip netns add ${m1_ns} -ip netns add ${m2_ns} - -modes="active-backup balance-tlb balance-alb" - -for mode in $modes; do - macvlan_over_bond "mode $mode" -done - -exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh new file mode 100755 index 000000000000..c4711272fe45 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh @@ -0,0 +1,96 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test macvlan/ipvlan over bond + +lib_dir=$(dirname "$0") +source ${lib_dir}/bond_topo_2d1c.sh + +xvlan1_ns="xvlan1-$(mktemp -u XXXXXX)" +xvlan2_ns="xvlan2-$(mktemp -u XXXXXX)" +xvlan1_ip4="192.0.2.11" +xvlan1_ip6="2001:db8::11" +xvlan2_ip4="192.0.2.12" +xvlan2_ip6="2001:db8::12" + +cleanup() +{ + client_destroy + server_destroy + gateway_destroy + + ip netns del ${xvlan1_ns} + ip netns del ${xvlan2_ns} +} + +check_connection() +{ + local ns=${1} + local target=${2} + local message=${3} + RET=0 + + ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null + check_err $? "ping failed" + log_test "${bond_mode}/${xvlan_type}_${xvlan_mode}: ${message}" +} + +xvlan_over_bond() +{ + local param="$1" + local xvlan_type="$2" + local xvlan_mode="$3" + RET=0 + + # setup new bond mode + bond_reset "${param}" + + ip -n ${s_ns} link add link bond0 name ${xvlan_type}0 type ${xvlan_type} mode ${xvlan_mode} + ip -n ${s_ns} link set ${xvlan_type}0 netns ${xvlan1_ns} + ip -n ${xvlan1_ns} link set dev ${xvlan_type}0 up + ip -n ${xvlan1_ns} addr add ${xvlan1_ip4}/24 dev ${xvlan_type}0 + ip -n ${xvlan1_ns} addr add ${xvlan1_ip6}/24 dev ${xvlan_type}0 + + ip -n ${s_ns} link add link bond0 name ${xvlan_type}0 type ${xvlan_type} mode ${xvlan_mode} + ip -n ${s_ns} link set ${xvlan_type}0 netns ${xvlan2_ns} + ip -n ${xvlan2_ns} link set dev ${xvlan_type}0 up + ip -n ${xvlan2_ns} addr add ${xvlan2_ip4}/24 dev ${xvlan_type}0 + ip -n ${xvlan2_ns} addr add ${xvlan2_ip6}/24 dev ${xvlan_type}0 + + sleep 2 + + check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server" + check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server" + check_connection "${c_ns}" "${xvlan1_ip4}" "IPv4: client->${xvlan_type}_1" + check_connection "${c_ns}" "${xvlan1_ip6}" "IPv6: client->${xvlan_type}_1" + check_connection "${c_ns}" "${xvlan2_ip4}" "IPv4: client->${xvlan_type}_2" + check_connection "${c_ns}" "${xvlan2_ip6}" "IPv6: client->${xvlan_type}_2" + check_connection "${xvlan1_ns}" "${xvlan2_ip4}" "IPv4: ${xvlan_type}_1->${xvlan_type}_2" + check_connection "${xvlan1_ns}" "${xvlan2_ip6}" "IPv6: ${xvlan_type}_1->${xvlan_type}_2" + + check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client" + check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client" + check_connection "${xvlan1_ns}" "${c_ip4}" "IPv4: ${xvlan_type}_1->client" + check_connection "${xvlan1_ns}" "${c_ip6}" "IPv6: ${xvlan_type}_1->client" + check_connection "${xvlan2_ns}" "${c_ip4}" "IPv4: ${xvlan_type}_2->client" + check_connection "${xvlan2_ns}" "${c_ip6}" "IPv6: ${xvlan_type}_2->client" + check_connection "${xvlan2_ns}" "${xvlan1_ip4}" "IPv4: ${xvlan_type}_2->${xvlan_type}_1" + check_connection "${xvlan2_ns}" "${xvlan1_ip6}" "IPv6: ${xvlan_type}_2->${xvlan_type}_1" + + ip -n ${c_ns} neigh flush dev eth0 +} + +trap cleanup EXIT + +setup_prepare +ip netns add ${xvlan1_ns} +ip netns add ${xvlan2_ns} + +bond_modes="active-backup balance-tlb balance-alb" + +for bond_mode in ${bond_modes}; do + xvlan_over_bond "mode ${bond_mode}" macvlan bridge + xvlan_over_bond "mode ${bond_mode}" ipvlan l2 +done + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 899d7fb6ea8e..dad4e5fda4db 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -3,6 +3,7 @@ CONFIG_BRIDGE=y CONFIG_DUMMY=y CONFIG_IPV6=y CONFIG_MACVLAN=y +CONFIG_IPVLAN=y CONFIG_NET_ACT_GACT=y CONFIG_NET_CLS_FLOWER=y CONFIG_NET_SCH_INGRESS=y diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 8e502a1f8f9b..19a6969643f4 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -619,9 +619,6 @@ int do_server(struct memory_buffer *mem) fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", page_aligned_frags, non_page_aligned_frags); - fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", - page_aligned_frags, non_page_aligned_frags); - cleanup: free(tmp_mem); diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 0b49ce7ae678..ca8a7edff3dd 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -3,7 +3,8 @@ import datetime import random -from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt +import re +from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt, ksft_true from lib.py import NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily from lib.py import KsftSkipEx, KsftFailEx @@ -96,6 +97,13 @@ def _send_traffic_check(cfg, port, name, params): f"traffic on inactive queues ({name}): " + str(cnts)) +def _ntuple_rule_check(cfg, rule_id, ctx_id): + """Check that ntuple rule references RSS context ID""" + text = ethtool(f"-n {cfg.ifname} rule {rule_id}").stdout + pattern = f"RSS Context (ID: )?{ctx_id}" + ksft_true(re.search(pattern, text), "RSS context not referenced in ntuple rule") + + def test_rss_key_indir(cfg): """Test basics like updating the main RSS key and indirection table.""" @@ -459,6 +467,8 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): ntuple = ethtool_create(cfg, "-N", flow) defer(ethtool, f"-N {cfg.ifname} delete {ntuple}") + _ntuple_rule_check(cfg, ntuple, ctx_id) + for i in range(ctx_cnt): _send_traffic_check(cfg, ports[i], f"context {i}", { 'target': (2+i*2, 3+i*2), diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index 1ea9bb695e94..987e452d3a45 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -5,7 +5,7 @@ import time from pathlib import Path from lib.py import KsftSkipEx, KsftXfailEx from lib.py import ksft_setup -from lib.py import cmd, ethtool, ip +from lib.py import cmd, ethtool, ip, CmdExitFailure from lib.py import NetNS, NetdevSimDev from .remote import Remote @@ -48,6 +48,7 @@ class NetDrvEnv: else: self._ns = NetdevSimDev(**kwargs) self.dev = self._ns.nsims[0].dev + self.ifname = self.dev['ifname'] self.ifindex = self.dev['ifindex'] def __enter__(self): @@ -234,7 +235,12 @@ class NetDrvEpEnv: Good drivers will tell us via ethtool what their sync period is. """ if self._stats_settle_time is None: - data = ethtool("-c " + self.ifname, json=True)[0] + data = {} + try: + data = ethtool("-c " + self.ifname, json=True)[0] + except CmdExitFailure as e: + if "Operation not supported" not in e.cmd.stderr: + raise self._stats_settle_time = 0.025 + \ data.get('stats-block-usecs', 0) / 1000 / 1000 diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh new file mode 100644 index 000000000000..3acaba41ac7b --- /dev/null +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -0,0 +1,225 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This file contains functions and helpers to support the netconsole +# selftests +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +LIBDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +SRCIF="" # to be populated later +SRCIP=192.0.2.1 +DSTIF="" # to be populated later +DSTIP=192.0.2.2 + +PORT="6666" +MSG="netconsole selftest" +USERDATA_KEY="key" +USERDATA_VALUE="value" +TARGET=$(mktemp -u netcons_XXXXX) +DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk) +NETCONS_CONFIGFS="/sys/kernel/config/netconsole" +NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +# NAMESPACE will be populated by setup_ns with a random value +NAMESPACE="" + +# IDs for netdevsim +NSIM_DEV_1_ID=$((256 + RANDOM % 256)) +NSIM_DEV_2_ID=$((512 + RANDOM % 256)) +NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device" + +# Used to create and delete namespaces +source "${LIBDIR}"/../../../../net/lib.sh +source "${LIBDIR}"/../../../../net/net_helper.sh + +# Create netdevsim interfaces +create_ifaces() { + + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" + udevadm settle 2> /dev/null || true + + local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" + local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" + + # These are global variables + SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ + -path "$NSIM1"/net -exec basename {} \;) + DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ + -path "$NSIM2"/net -exec basename {} \;) +} + +link_ifaces() { + local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" + local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) + local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) + + exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}" + exec {INITNS_FD}</proc/self/ns/net + + # Bind the dst interface to namespace + ip link set "${DSTIF}" netns "${NAMESPACE}" + + # Linking one device to the other one (on the other namespace} + if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX" > $NSIM_DEV_SYS_LINK + then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup + exit "${ksft_skip}" + fi +} + +function configure_ip() { + # Configure the IPs for both interfaces + ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" + ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up + + ip addr add "${SRCIP}"/24 dev "${SRCIF}" + ip link set "${SRCIF}" up +} + +function set_network() { + # setup_ns function is coming from lib.sh + setup_ns NAMESPACE + + # Create both interfaces, and assign the destination to a different + # namespace + create_ifaces + + # Link both interfaces back to back + link_ifaces + + configure_ip +} + +function create_dynamic_target() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + + # Create a dynamic target + mkdir "${NETCONS_PATH}" + + echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip + echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip + echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac + echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + + echo 1 > "${NETCONS_PATH}"/enabled +} + +function cleanup() { + local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" + + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove all the keys that got created during the selftest + find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + # Delete netdevsim devices + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" + + # this is coming from lib.sh + cleanup_all_ns + + # Restoring printk configurations + echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk +} + +function set_user_data() { + if [[ ! -d "${NETCONS_PATH}""/userdata" ]] + then + echo "Userdata path not available in ${NETCONS_PATH}/userdata" + exit "${ksft_skip}" + fi + + KEY_PATH="${NETCONS_PATH}/userdata/${USERDATA_KEY}" + mkdir -p "${KEY_PATH}" + VALUE_PATH="${KEY_PATH}""/value" + echo "${USERDATA_VALUE}" > "${VALUE_PATH}" +} + +function listen_port_and_save_to() { + local OUTPUT=${1} + # Just wait for 2 seconds + timeout 2 ip netns exec "${NAMESPACE}" \ + socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" +} + +function validate_result() { + local TMPFILENAME="$1" + + # TMPFILENAME will contain something like: + # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM + # key=value + + # Check if the file exists + if [ ! -f "$TMPFILENAME" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${TMPFILENAME}"; then + echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then + echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + + # Delete the file once it is validated, otherwise keep it + # for debugging purposes + rm "${TMPFILENAME}" + exit "${ksft_pass}" +} + +function check_for_dependencies() { + if [ "$(id -u)" -ne 0 ]; then + echo "This test must be run as root" >&2 + exit "${ksft_skip}" + fi + + if ! which socat > /dev/null ; then + echo "SKIP: socat(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which ip > /dev/null ; then + echo "SKIP: ip(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which udevadm > /dev/null ; then + echo "SKIP: udevadm(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then + echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2 + exit "${ksft_skip}" + fi + + if [ ! -d "${NETCONS_CONFIGFS}" ]; then + echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 + exit "${ksft_skip}" + fi + + if ip link show "${DSTIF}" 2> /dev/null; then + echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 + exit "${ksft_skip}" + fi + + if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then + echo "SKIP: IPs already in use. Skipping it" >&2 + exit "${ksft_skip}" + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh index 0c47faff9274..c068e6c2a580 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -22,20 +22,34 @@ SB_ITC=0 h1_create() { simple_if_init $h1 192.0.1.1/24 + tc qdisc add dev $h1 clsact + + # Add egress filter on $h1 that will guarantee that the packet sent, + # will be the only packet being passed to the device. + tc filter add dev $h1 egress pref 2 handle 102 matchall action drop } h1_destroy() { + tc filter del dev $h1 egress pref 2 handle 102 matchall action drop + tc qdisc del dev $h1 clsact simple_if_fini $h1 192.0.1.1/24 } h2_create() { simple_if_init $h2 192.0.1.2/24 + tc qdisc add dev $h2 clsact + + # Add egress filter on $h2 that will guarantee that the packet sent, + # will be the only packet being passed to the device. + tc filter add dev $h2 egress pref 1 handle 101 matchall action drop } h2_destroy() { + tc filter del dev $h2 egress pref 1 handle 101 matchall action drop + tc qdisc del dev $h2 clsact simple_if_fini $h2 192.0.1.2/24 } @@ -101,6 +115,11 @@ port_pool_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ @@ -109,11 +128,6 @@ port_pool_test() devlink sb occupancy snapshot $DEVLINK_DEV RET=0 - max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ) - check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress pool" - - RET=0 max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ) check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" log_test "physical port's($h2) ingress pool" @@ -122,6 +136,11 @@ port_pool_test() max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ) check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress pool" + + tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass } port_tc_ip_test() @@ -129,6 +148,11 @@ port_tc_ip_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ @@ -139,17 +163,17 @@ port_tc_ip_test() RET=0 max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress TC - IP packet" - - RET=0 - max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) - check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" log_test "physical port's($h2) ingress TC - IP packet" RET=0 max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ) check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress TC - IP packet" + + tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass } port_tc_arp_test() @@ -157,6 +181,9 @@ port_tc_arp_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol arp pref 1 handle 101 flower \ + src_mac $h1mac action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q @@ -166,17 +193,15 @@ port_tc_arp_test() RET=0 max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress TC - ARP packet" - - RET=0 - max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) - check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" log_test "physical port's($h2) ingress TC - ARP packet" RET=0 max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ) check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress TC - ARP packet" + + tc filter del dev $h1 egress protocol arp pref 1 handle 101 flower \ + src_mac $h1mac action pass } setup_prepare() diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index b175f4d966e5..fe765da498e8 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -18,224 +18,8 @@ set -euo pipefail SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") -# Simple script to test dynamic targets in netconsole -SRCIF="" # to be populated later -SRCIP=192.0.2.1 -DSTIF="" # to be populated later -DSTIP=192.0.2.2 +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh -PORT="6666" -MSG="netconsole selftest" -USERDATA_KEY="key" -USERDATA_VALUE="value" -TARGET=$(mktemp -u netcons_XXXXX) -DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk) -NETCONS_CONFIGFS="/sys/kernel/config/netconsole" -NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" -KEY_PATH="${NETCONS_PATH}/userdata/${USERDATA_KEY}" -# NAMESPACE will be populated by setup_ns with a random value -NAMESPACE="" - -# IDs for netdevsim -NSIM_DEV_1_ID=$((256 + RANDOM % 256)) -NSIM_DEV_2_ID=$((512 + RANDOM % 256)) -NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device" - -# Used to create and delete namespaces -source "${SCRIPTDIR}"/../../net/lib.sh -source "${SCRIPTDIR}"/../../net/net_helper.sh - -# Create netdevsim interfaces -create_ifaces() { - - echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" - echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" - udevadm settle 2> /dev/null || true - - local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" - local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" - - # These are global variables - SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ - -path "$NSIM1"/net -exec basename {} \;) - DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ - -path "$NSIM2"/net -exec basename {} \;) -} - -link_ifaces() { - local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" - local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) - local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) - - exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}" - exec {INITNS_FD}</proc/self/ns/net - - # Bind the dst interface to namespace - ip link set "${DSTIF}" netns "${NAMESPACE}" - - # Linking one device to the other one (on the other namespace} - if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX" > $NSIM_DEV_SYS_LINK - then - echo "linking netdevsim1 with netdevsim2 should succeed" - cleanup - exit "${ksft_skip}" - fi -} - -function configure_ip() { - # Configure the IPs for both interfaces - ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" - ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up - - ip addr add "${SRCIP}"/24 dev "${SRCIF}" - ip link set "${SRCIF}" up -} - -function set_network() { - # setup_ns function is coming from lib.sh - setup_ns NAMESPACE - - # Create both interfaces, and assign the destination to a different - # namespace - create_ifaces - - # Link both interfaces back to back - link_ifaces - - configure_ip -} - -function create_dynamic_target() { - DSTMAC=$(ip netns exec "${NAMESPACE}" \ - ip link show "${DSTIF}" | awk '/ether/ {print $2}') - - # Create a dynamic target - mkdir "${NETCONS_PATH}" - - echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip - echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip - echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac - echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name - - echo 1 > "${NETCONS_PATH}"/enabled -} - -function cleanup() { - local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" - - # delete netconsole dynamic reconfiguration - echo 0 > "${NETCONS_PATH}"/enabled - # Remove key - rmdir "${KEY_PATH}" - # Remove the configfs entry - rmdir "${NETCONS_PATH}" - - # Delete netdevsim devices - echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" - echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" - - # this is coming from lib.sh - cleanup_all_ns - - # Restoring printk configurations - echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk -} - -function set_user_data() { - if [[ ! -d "${NETCONS_PATH}""/userdata" ]] - then - echo "Userdata path not available in ${NETCONS_PATH}/userdata" - exit "${ksft_skip}" - fi - - mkdir -p "${KEY_PATH}" - VALUE_PATH="${KEY_PATH}""/value" - echo "${USERDATA_VALUE}" > "${VALUE_PATH}" -} - -function listen_port_and_save_to() { - local OUTPUT=${1} - # Just wait for 2 seconds - timeout 2 ip netns exec "${NAMESPACE}" \ - socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" -} - -function validate_result() { - local TMPFILENAME="$1" - - # TMPFILENAME will contain something like: - # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM - # key=value - - # Check if the file exists - if [ ! -f "$TMPFILENAME" ]; then - echo "FAIL: File was not generated." >&2 - exit "${ksft_fail}" - fi - - if ! grep -q "${MSG}" "${TMPFILENAME}"; then - echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 - cat "${TMPFILENAME}" >&2 - exit "${ksft_fail}" - fi - - if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then - echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2 - cat "${TMPFILENAME}" >&2 - exit "${ksft_fail}" - fi - - # Delete the file once it is validated, otherwise keep it - # for debugging purposes - rm "${TMPFILENAME}" - exit "${ksft_pass}" -} - -function check_for_dependencies() { - if [ "$(id -u)" -ne 0 ]; then - echo "This test must be run as root" >&2 - exit "${ksft_skip}" - fi - - if ! which socat > /dev/null ; then - echo "SKIP: socat(1) is not available" >&2 - exit "${ksft_skip}" - fi - - if ! which ip > /dev/null ; then - echo "SKIP: ip(1) is not available" >&2 - exit "${ksft_skip}" - fi - - if ! which udevadm > /dev/null ; then - echo "SKIP: udevadm(1) is not available" >&2 - exit "${ksft_skip}" - fi - - if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then - echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2 - exit "${ksft_skip}" - fi - - if [ ! -d "${NETCONS_CONFIGFS}" ]; then - echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 - exit "${ksft_skip}" - fi - - if ip link show "${DSTIF}" 2> /dev/null; then - echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 - exit "${ksft_skip}" - fi - - if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then - echo "SKIP: IPs already in use. Skipping it" >&2 - exit "${ksft_skip}" - fi -} - -# ========== # -# Start here # -# ========== # modprobe netdevsim 2> /dev/null || true modprobe netconsole 2> /dev/null || true diff --git a/tools/testing/selftests/drivers/net/netcons_overflow.sh b/tools/testing/selftests/drivers/net/netcons_overflow.sh new file mode 100755 index 000000000000..29bad56448a2 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_overflow.sh @@ -0,0 +1,67 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This test verifies that users can successfully create up to +# MAX_USERDATA_ITEMS userdata entries without encountering any failures. +# +# Additionally, it tests for expected failure when attempting to exceed this +# maximum limit. +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh +# This is coming from netconsole code. Check for it in drivers/net/netconsole.c +MAX_USERDATA_ITEMS=16 + +# Function to create userdata entries +function create_userdata_max_entries() { + # All these keys should be created without any error + for i in $(seq $MAX_USERDATA_ITEMS) + do + # USERDATA_KEY is used by set_user_data + USERDATA_KEY="key"${i} + set_user_data + done +} + +# Function to verify the entry limit +function verify_entry_limit() { + # Allowing the test to fail without exiting, since the next command + # will fail + set +e + mkdir "${NETCONS_PATH}/userdata/key_that_will_fail" 2> /dev/null + ret="$?" + set -e + if [ "$ret" -eq 0 ]; + then + echo "Adding more than ${MAX_USERDATA_ITEMS} entries in userdata should fail, but it didn't" >&2 + ls "${NETCONS_PATH}/userdata/" >&2 + exit "${ksft_fail}" + fi +} + +# ========== # +# Start here # +# ========== # + +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true + +# Check for basic system dependency and exit if not found +check_for_dependencies + +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target +# populate the maximum number of supported keys in userdata +create_userdata_max_entries +# Verify an additional entry is not allowed +verify_entry_limit +exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 30f29096e27c..38303da957ee 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -1,32 +1,37 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -from lib.py import ksft_run, ksft_exit, ksft_eq, KsftSkipEx -from lib.py import EthtoolFamily, NetdevFamily +from lib.py import ksft_disruptive, ksft_exit, ksft_run +from lib.py import ksft_eq, ksft_raises, KsftSkipEx +from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import NetDrvEnv -from lib.py import cmd +from lib.py import cmd, defer, ip +import errno import glob -def sys_get_queues(ifname) -> int: - folders = glob.glob(f'/sys/class/net/{ifname}/queues/rx-*') +def sys_get_queues(ifname, qtype='rx') -> int: + folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*') return len(folders) -def nl_get_queues(cfg, nl): +def nl_get_queues(cfg, nl, qtype='rx'): queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True) if queues: - return len([q for q in queues if q['type'] == 'rx']) + return len([q for q in queues if q['type'] == qtype]) return None def get_queues(cfg, nl) -> None: - queues = nl_get_queues(cfg, nl) - if not queues: - raise KsftSkipEx('queue-get not supported by device') + snl = NetdevFamily(recv_size=4096) - expected = sys_get_queues(cfg.dev['ifname']) - ksft_eq(queues, expected) + for qtype in ['rx', 'tx']: + queues = nl_get_queues(cfg, snl, qtype) + if not queues: + raise KsftSkipEx('queue-get not supported by device') + + expected = sys_get_queues(cfg.dev['ifname'], qtype) + ksft_eq(queues, expected) def addremove_queues(cfg, nl) -> None: @@ -56,9 +61,27 @@ def addremove_queues(cfg, nl) -> None: ksft_eq(queues, expected) +@ksft_disruptive +def check_down(cfg, nl) -> None: + # Check the NAPI IDs before interface goes down and hides them + napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True) + + ip(f"link set dev {cfg.dev['ifname']} down") + defer(ip, f"link set dev {cfg.dev['ifname']} up") + + with ksft_raises(NlError) as cm: + nl.queue_get({'ifindex': cfg.ifindex, 'id': 0, 'type': 'rx'}) + ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT) + + if napis: + with ksft_raises(NlError) as cm: + nl.napi_get({'id': napis[0]['id']}) + ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT) + + def main() -> None: - with NetDrvEnv(__file__, queue_count=3) as cfg: - ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily())) + with NetDrvEnv(__file__, queue_count=100) as cfg: + ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily())) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 63e3c045a3b2..efcc1e10575b 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -2,12 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import subprocess +import time from lib.py import ksft_run, ksft_exit, ksft_pr -from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx +from lib.py import ksft_ge, ksft_eq, ksft_is, ksft_in, ksft_lt, ksft_true, ksft_raises +from lib.py import KsftSkipEx, KsftXfailEx from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv -from lib.py import ip, defer +from lib.py import cmd, ip, defer ethnl = EthtoolFamily() netfam = NetdevFamily() @@ -110,6 +113,23 @@ def qstat_by_ifindex(cfg) -> None: ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key) ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key) + # Sanity check the dumps + queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True) + # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}} + parsed = {} + for entry in queues: + ifindex = entry["ifindex"] + if ifindex not in parsed: + parsed[ifindex] = {"rx":[], "tx": []} + parsed[ifindex][entry["queue-type"]].append(entry['queue-id']) + # Now, validate + for ifindex, queues in parsed.items(): + for qtype in ['rx', 'tx']: + ksft_eq(len(queues[qtype]), len(set(queues[qtype])), + comment="repeated queue keys") + ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1, + comment="missing queue keys") + # Test invalid dumps # 0 is invalid with ksft_raises(NlError) as cm: @@ -157,10 +177,95 @@ def check_down(cfg) -> None: netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True) +def __run_inf_loop(body): + body = body.strip() + if body[-1] != ';': + body += ';' + + return subprocess.Popen(f"while true; do {body} done", shell=True, + stdout=subprocess.PIPE, stderr=subprocess.PIPE) + + +def __stats_increase_sanely(old, new) -> None: + for k in old.keys(): + ksft_ge(new[k], old[k]) + ksft_lt(new[k] - old[k], 1 << 31, comment="likely wrapping error") + + +def procfs_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, which is not an exclusive + lock, make sure drivers can handle parallel reads of stats. + """ + one = __run_inf_loop("cat /proc/net/dev") + defer(one.kill) + two = __run_inf_loop("cat /proc/net/dev") + defer(two.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(one.poll(), None) + ksft_is(two.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + time.sleep(2) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + # defers will kill the loops + + +@ksft_disruptive +def procfs_downup_hammer(cfg) -> None: + """ + Reading stats via procfs only holds the RCU lock, drivers often try + to sleep when reading the stats, or don't protect against races. + """ + # Max out the queues, we'll flip between max and 1 + channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) + if channels['combined-count'] == 0: + rx_type = 'rx' + else: + rx_type = 'combined' + cur_queue_cnt = channels[f'{rx_type}-count'] + max_queue_cnt = channels[f'{rx_type}-max'] + + cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}") + defer(cmd, f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}") + + # Real test stats + stats = __run_inf_loop("cat /proc/net/dev") + defer(stats.kill) + + ipset = f"ip link set dev {cfg.ifname}" + defer(ip, f"link set dev {cfg.ifname} up") + # The "echo -n 1" lets us count iterations below + updown = f"{ipset} down; sleep 0.05; {ipset} up; sleep 0.05; " + \ + f"ethtool -L {cfg.ifname} {rx_type} 1; " + \ + f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}; " + \ + "echo -n 1" + updown = __run_inf_loop(updown) + kill_updown = defer(updown.kill) + + time.sleep(1) + # Make sure the processes are running + ksft_is(stats.poll(), None) + ksft_is(updown.poll(), None) + + rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + # We're looking for crashes, give it extra time + time.sleep(9) + rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] + __stats_increase_sanely(rtstat1, rtstat2) + + kill_updown.exec() + stdout, _ = updown.communicate(timeout=5) + ksft_pr("completed up/down cycles:", len(stdout.decode('utf-8'))) + + def main() -> None: - with NetDrvEnv(__file__) as cfg: + with NetDrvEnv(__file__, queue_count=100) as cfg: ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, - check_down], + check_down, procfs_hammer, procfs_downup_hammer], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 319567f0fae1..81db85a5cc16 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -57,7 +57,6 @@ static int __do_binderfs_test(struct __test_metadata *_metadata) { int fd, ret, saved_errno, result = 1; size_t len; - ssize_t wret; struct binderfs_device device = { 0 }; struct binder_version version = { 0 }; char binderfs_mntpt[] = P_tmpdir "/binderfs_XXXXXX", diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc index a16c6a6f6055..8f1c58f0c239 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc @@ -111,7 +111,7 @@ check_error 'p vfs_read $arg* ^$arg*' # DOUBLE_ARGS if !grep -q 'kernel return probes support:' README; then check_error 'r vfs_read ^$arg*' # NOFENTRY_ARGS fi -check_error 'p vfs_read+8 ^$arg*' # NOFENTRY_ARGS +check_error 'p vfs_read+20 ^$arg*' # NOFENTRY_ARGS check_error 'p vfs_read ^hoge' # NO_BTFARG check_error 'p kfree ^$arg10' # NO_BTFARG (exceed the number of parameters) check_error 'r kfree ^$retval' # NO_RETVAL diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h index e5db897586bb..531228b849da 100644 --- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h +++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h @@ -22,6 +22,9 @@ #define HID_REQ_SET_IDLE HID_REQ_SET_IDLE___not_used #define HID_REQ_SET_PROTOCOL HID_REQ_SET_PROTOCOL___not_used +/* do not define kfunc through vmlinux.h as this messes up our custom hack */ +#define BPF_NO_KFUNC_PROTOTYPES + #include "vmlinux.h" #undef hid_bpf_ctx @@ -91,31 +94,31 @@ struct hid_bpf_ops { /* following are kfuncs exported by HID for HID-BPF */ extern __u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, - const size_t __sz) __ksym; -extern struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id) __ksym; -extern void hid_bpf_release_context(struct hid_bpf_ctx *ctx) __ksym; + const size_t __sz) __weak __ksym; +extern struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id) __weak __ksym; +extern void hid_bpf_release_context(struct hid_bpf_ctx *ctx) __weak __ksym; extern int hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *data, size_t buf__sz, enum hid_report_type type, - enum hid_class_request reqtype) __ksym; + enum hid_class_request reqtype) __weak __ksym; extern int hid_bpf_hw_output_report(struct hid_bpf_ctx *ctx, - __u8 *buf, size_t buf__sz) __ksym; + __u8 *buf, size_t buf__sz) __weak __ksym; extern int hid_bpf_input_report(struct hid_bpf_ctx *ctx, enum hid_report_type type, __u8 *data, - size_t buf__sz) __ksym; + size_t buf__sz) __weak __ksym; extern int hid_bpf_try_input_report(struct hid_bpf_ctx *ctx, enum hid_report_type type, __u8 *data, - size_t buf__sz) __ksym; + size_t buf__sz) __weak __ksym; /* bpf_wq implementation */ extern int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) __weak __ksym; extern int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) __weak __ksym; extern int bpf_wq_set_callback_impl(struct bpf_wq *wq, int (callback_fn)(void *map, int *key, void *wq), - unsigned int flags__k, void *aux__ign) __ksym; + unsigned int flags__k, void *aux__ign) __weak __ksym; #define bpf_wq_set_callback(timer, cb, flags) \ bpf_wq_set_callback_impl(timer, cb, flags, NULL) diff --git a/tools/testing/selftests/hid/run-hid-tools-tests.sh b/tools/testing/selftests/hid/run-hid-tools-tests.sh index bdae8464da86..af1682a53c27 100755 --- a/tools/testing/selftests/hid/run-hid-tools-tests.sh +++ b/tools/testing/selftests/hid/run-hid-tools-tests.sh @@ -2,24 +2,26 @@ # SPDX-License-Identifier: GPL-2.0 # Runs tests for the HID subsystem +KSELFTEST_SKIP_TEST=4 + if ! command -v python3 > /dev/null 2>&1; then echo "hid-tools: [SKIP] python3 not installed" - exit 77 + exit $KSELFTEST_SKIP_TEST fi if ! python3 -c "import pytest" > /dev/null 2>&1; then - echo "hid: [SKIP/ pytest module not installed" - exit 77 + echo "hid: [SKIP] pytest module not installed" + exit $KSELFTEST_SKIP_TEST fi if ! python3 -c "import pytest_tap" > /dev/null 2>&1; then - echo "hid: [SKIP/ pytest_tap module not installed" - exit 77 + echo "hid: [SKIP] pytest_tap module not installed" + exit $KSELFTEST_SKIP_TEST fi if ! python3 -c "import hidtools" > /dev/null 2>&1; then - echo "hid: [SKIP/ hid-tools module not installed" - exit 77 + echo "hid: [SKIP] hid-tools module not installed" + exit $KSELFTEST_SKIP_TEST fi TARGET=${TARGET:=.} diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index 22f6fd5f0f74..64b1f8e1b0cf 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -615,7 +615,12 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain) /* device.c */ TEST_FAIL_NTH(basic_fail_nth, device) { + struct iommu_hwpt_selftest data = { + .iotlb = IOMMU_TEST_IOTLB_DEFAULT, + }; struct iommu_test_hw_info info; + uint32_t fault_id, fault_fd; + uint32_t fault_hwpt_id; uint32_t ioas_id; uint32_t ioas_id2; uint32_t stdev_id; @@ -678,6 +683,15 @@ TEST_FAIL_NTH(basic_fail_nth, device) if (_test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, 0, &vdev_id)) return -1; + if (_test_ioctl_fault_alloc(self->fd, &fault_id, &fault_fd)) + return -1; + close(fault_fd); + + if (_test_cmd_hwpt_alloc(self->fd, idev_id, hwpt_id, fault_id, + IOMMU_HWPT_FAULT_ID_VALID, &fault_hwpt_id, + IOMMU_HWPT_DATA_SELFTEST, &data, sizeof(data))) + return -1; + return 0; } diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index 79a125eb24c2..05a461890671 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -7,6 +7,7 @@ KTAP_TESTNO=1 KTAP_CNT_PASS=0 KTAP_CNT_FAIL=0 +KTAP_CNT_XFAIL=0 KTAP_CNT_SKIP=0 KSFT_PASS=0 @@ -69,6 +70,16 @@ ktap_test_skip() { KTAP_CNT_SKIP=$((KTAP_CNT_SKIP+1)) } +ktap_test_xfail() { + description="$1" + + result="ok" + directive="XFAIL" + __ktap_test "$result" "$description" "$directive" + + KTAP_CNT_XFAIL=$((KTAP_CNT_XFAIL+1)) +} + ktap_test_fail() { description="$1" @@ -99,7 +110,7 @@ ktap_exit_fail_msg() { ktap_finished() { ktap_print_totals - if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP)) -eq "$KSFT_NUM_TESTS" ]; then + if [ $((KTAP_CNT_PASS + KTAP_CNT_SKIP + KTAP_CNT_XFAIL)) -eq "$KSFT_NUM_TESTS" ]; then exit "$KSFT_PASS" else exit "$KSFT_FAIL" @@ -107,5 +118,5 @@ ktap_finished() { } ktap_print_totals() { - echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" + echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:$KTAP_CNT_XFAIL xpass:0 skip:$KTAP_CNT_SKIP error:0" } diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 54ab484d0000..4bc1051848e5 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -47,6 +47,8 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSCOFPMF: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSNPM: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVADE: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVADU: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT: @@ -422,6 +424,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(SSCOFPMF), KVM_ISA_EXT_ARR(SSNPM), KVM_ISA_EXT_ARR(SSTC), + KVM_ISA_EXT_ARR(SVADE), + KVM_ISA_EXT_ARR(SVADU), KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), KVM_ISA_EXT_ARR(SVPBMT), @@ -955,6 +959,8 @@ KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN); KVM_ISA_EXT_SIMPLE_CONFIG(sscofpmf, SSCOFPMF); KVM_ISA_EXT_SIMPLE_CONFIG(ssnpm, SSNPM); KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC); +KVM_ISA_EXT_SIMPLE_CONFIG(svade, SVADE); +KVM_ISA_EXT_SIMPLE_CONFIG(svadu, SVADU); KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL); KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT); @@ -1020,6 +1026,8 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_sscofpmf, &config_ssnpm, &config_sstc, + &config_svade, + &config_svadu, &config_svinval, &config_svnapot, &config_svpbmt, diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 95af2d78fd31..c0c53451a16d 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -9,6 +9,7 @@ #include <fcntl.h> #include <linux/memfd.h> #include <sched.h> +#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <signal.h> @@ -281,6 +282,24 @@ static void *mfd_assert_mmap_shared(int fd) return p; } +static void *mfd_assert_mmap_read_shared(int fd) +{ + void *p; + + p = mmap(NULL, + mfd_def_size, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + static void *mfd_assert_mmap_private(int fd) { void *p; @@ -979,6 +998,30 @@ static void test_seal_future_write(void) close(fd); } +static void test_seal_write_map_read_shared(void) +{ + int fd; + void *p; + + printf("%s SEAL-WRITE-MAP-READ\n", memfd_str); + + fd = mfd_assert_new("kern_memfd_seal_write_map_read", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + + p = mfd_assert_mmap_read_shared(fd); + + mfd_assert_read(fd); + mfd_assert_read_shared(fd); + mfd_fail_write(fd); + + munmap(p, mfd_def_size); + close(fd); +} + /* * Test SEAL_SHRINK * Test whether SEAL_SHRINK actually prevents shrinking @@ -1557,6 +1600,11 @@ static void test_share_fork(char *banner, char *b_suffix) close(fd); } +static bool pid_ns_supported(void) +{ + return access("/proc/self/ns/pid", F_OK) == 0; +} + int main(int argc, char **argv) { pid_t pid; @@ -1587,12 +1635,17 @@ int main(int argc, char **argv) test_seal_write(); test_seal_future_write(); + test_seal_write_map_read_shared(); test_seal_shrink(); test_seal_grow(); test_seal_resize(); - test_sysctl_simple(); - test_sysctl_nested(); + if (pid_ns_supported()) { + test_sysctl_simple(); + test_sysctl_nested(); + } else { + printf("PID namespaces are not supported; skipping sysctl tests\n"); + } test_share_dup("SHARE-DUP", ""); test_share_mmap("SHARE-MMAP", ""); diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c index 432d5af15e66..db63abe5ee5e 100644 --- a/tools/testing/selftests/mm/hugetlb_dio.c +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -76,19 +76,15 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) /* Get the free huge pages after unmap*/ free_hpage_a = get_free_hugepages(); + ksft_print_msg("No. Free pages before allocation : %d\n", free_hpage_b); + ksft_print_msg("No. Free pages after munmap : %d\n", free_hpage_a); + /* * If the no. of free hugepages before allocation and after unmap does * not match - that means there could still be a page which is pinned. */ - if (free_hpage_a != free_hpage_b) { - ksft_print_msg("No. Free pages before allocation : %d\n", free_hpage_b); - ksft_print_msg("No. Free pages after munmap : %d\n", free_hpage_a); - ksft_test_result_fail(": Huge pages not freed!\n"); - } else { - ksft_print_msg("No. Free pages before allocation : %d\n", free_hpage_b); - ksft_print_msg("No. Free pages after munmap : %d\n", free_hpage_a); - ksft_test_result_pass(": Huge pages freed successfully !\n"); - } + ksft_test_result(free_hpage_a == free_hpage_b, + "free huge pages from %u-%u\n", start_off, end_off); } int main(void) diff --git a/tools/testing/selftests/module/find_symbol.sh b/tools/testing/selftests/module/find_symbol.sh index 140364d3c49f..2c56805c9b6e 100755 --- a/tools/testing/selftests/module/find_symbol.sh +++ b/tools/testing/selftests/module/find_symbol.sh @@ -44,10 +44,10 @@ load_mod() local ARCH="$(uname -m)" case "${ARCH}" in x86_64) - perf stat $STATS $MODPROBE test_kallsyms_b + perf stat $STATS $MODPROBE $MOD ;; *) - time $MODPROBE test_kallsyms_b + time $MODPROBE $MOD exit 1 ;; esac diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index cb2fc601de66..73ee88d6b043 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -32,6 +32,7 @@ TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh +TEST_PROGS += cmsg_so_priority.sh TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh TEST_PROGS += netns-name.sh TEST_PROGS += nl_netdev.py @@ -95,6 +96,7 @@ TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh +TEST_PROGS += vlan_bridge_binding.sh TEST_PROGS += bpf_offload.py TEST_PROGS += ipv6_route_update_soft_lockup.sh TEST_PROGS += busy_poll_test.sh diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c index 99b0e8c17fca..04c7ff577bb8 100644 --- a/tools/testing/selftests/net/busy_poller.c +++ b/tools/testing/selftests/net/busy_poller.c @@ -54,16 +54,16 @@ struct epoll_params { #define EPIOCGPARAMS _IOR(EPOLL_IOC_TYPE, 0x02, struct epoll_params) #endif -static uint32_t cfg_port = 8000; +static uint16_t cfg_port = 8000; static struct in_addr cfg_bind_addr = { .s_addr = INADDR_ANY }; static char *cfg_outfile; static int cfg_max_events = 8; -static int cfg_ifindex; +static uint32_t cfg_ifindex; /* busy poll params */ static uint32_t cfg_busy_poll_usecs; -static uint32_t cfg_busy_poll_budget; -static uint32_t cfg_prefer_busy_poll; +static uint16_t cfg_busy_poll_budget; +static uint8_t cfg_prefer_busy_poll; /* IRQ params */ static uint32_t cfg_defer_hard_irqs; @@ -79,6 +79,7 @@ static void usage(const char *filepath) static void parse_opts(int argc, char **argv) { + unsigned long long tmp; int ret; int c; @@ -86,31 +87,40 @@ static void parse_opts(int argc, char **argv) usage(argv[0]); while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) { + /* most options take integer values, except o and b, so reduce + * code duplication a bit for the common case by calling + * strtoull here and leave bounds checking and casting per + * option below. + */ + if (c != 'o' && c != 'b') + tmp = strtoull(optarg, NULL, 0); + switch (c) { case 'u': - cfg_busy_poll_usecs = strtoul(optarg, NULL, 0); - if (cfg_busy_poll_usecs == ULONG_MAX || - cfg_busy_poll_usecs > UINT32_MAX) + if (tmp == ULLONG_MAX || tmp > UINT32_MAX) error(1, ERANGE, "busy_poll_usecs too large"); + + cfg_busy_poll_usecs = (uint32_t)tmp; break; case 'P': - cfg_prefer_busy_poll = strtoul(optarg, NULL, 0); - if (cfg_prefer_busy_poll == ULONG_MAX || - cfg_prefer_busy_poll > 1) + if (tmp == ULLONG_MAX || tmp > 1) error(1, ERANGE, "prefer busy poll should be 0 or 1"); + + cfg_prefer_busy_poll = (uint8_t)tmp; break; case 'g': - cfg_busy_poll_budget = strtoul(optarg, NULL, 0); - if (cfg_busy_poll_budget == ULONG_MAX || - cfg_busy_poll_budget > UINT16_MAX) + if (tmp == ULLONG_MAX || tmp > UINT16_MAX) error(1, ERANGE, "busy poll budget must be [0, UINT16_MAX]"); + + cfg_busy_poll_budget = (uint16_t)tmp; break; case 'p': - cfg_port = strtoul(optarg, NULL, 0); - if (cfg_port > UINT16_MAX) + if (tmp == ULLONG_MAX || tmp > UINT16_MAX) error(1, ERANGE, "port must be <= 65535"); + + cfg_port = (uint16_t)tmp; break; case 'b': ret = inet_aton(optarg, &cfg_bind_addr); @@ -124,41 +134,39 @@ static void parse_opts(int argc, char **argv) error(1, 0, "outfile invalid"); break; case 'm': - cfg_max_events = strtol(optarg, NULL, 0); - - if (cfg_max_events == LONG_MIN || - cfg_max_events == LONG_MAX || - cfg_max_events <= 0) + if (tmp == ULLONG_MAX || tmp > INT_MAX) error(1, ERANGE, - "max events must be > 0 and < LONG_MAX"); + "max events must be > 0 and <= INT_MAX"); + + cfg_max_events = (int)tmp; break; case 'd': - cfg_defer_hard_irqs = strtoul(optarg, NULL, 0); - - if (cfg_defer_hard_irqs == ULONG_MAX || - cfg_defer_hard_irqs > INT32_MAX) + if (tmp == ULLONG_MAX || tmp > INT32_MAX) error(1, ERANGE, "defer_hard_irqs must be <= INT32_MAX"); + + cfg_defer_hard_irqs = (uint32_t)tmp; break; case 'r': - cfg_gro_flush_timeout = strtoull(optarg, NULL, 0); - - if (cfg_gro_flush_timeout == ULLONG_MAX) + if (tmp == ULLONG_MAX || tmp > UINT64_MAX) error(1, ERANGE, - "gro_flush_timeout must be < ULLONG_MAX"); + "gro_flush_timeout must be < UINT64_MAX"); + + cfg_gro_flush_timeout = (uint64_t)tmp; break; case 's': - cfg_irq_suspend_timeout = strtoull(optarg, NULL, 0); - - if (cfg_irq_suspend_timeout == ULLONG_MAX) + if (tmp == ULLONG_MAX || tmp > UINT64_MAX) error(1, ERANGE, "irq_suspend_timeout must be < ULLONG_MAX"); + + cfg_irq_suspend_timeout = (uint64_t)tmp; break; case 'i': - cfg_ifindex = strtoul(optarg, NULL, 0); - if (cfg_ifindex == ULONG_MAX) + if (tmp == ULLONG_MAX || tmp > INT_MAX) error(1, ERANGE, - "ifindex must be < ULONG_MAX"); + "ifindex must be <= INT_MAX"); + + cfg_ifindex = (int)tmp; break; } } @@ -215,7 +223,7 @@ static void setup_queue(void) struct netdev_napi_set_req *set_req = NULL; struct ynl_sock *ys; struct ynl_error yerr; - uint32_t napi_id; + uint32_t napi_id = 0; ys = ynl_sock_create(&ynl_netdev_family, &yerr); if (!ys) @@ -277,8 +285,8 @@ static void run_poller(void) * here */ epoll_params.busy_poll_usecs = cfg_busy_poll_usecs; - epoll_params.busy_poll_budget = (uint16_t)cfg_busy_poll_budget; - epoll_params.prefer_busy_poll = (uint8_t)cfg_prefer_busy_poll; + epoll_params.busy_poll_budget = cfg_busy_poll_budget; + epoll_params.prefer_busy_poll = cfg_prefer_busy_poll; epoll_params.__pad = 0; val = 1; @@ -342,5 +350,9 @@ int main(int argc, char *argv[]) parse_opts(argc, argv); setup_queue(); run_poller(); + + if (cfg_outfile) + free(cfg_outfile); + return 0; } diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index 876c2db02a63..bc314382e4e1 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -59,6 +59,7 @@ struct options { unsigned int proto; } sock; struct option_cmsg_u32 mark; + struct option_cmsg_u32 priority; struct { bool ena; unsigned int delay; @@ -97,6 +98,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin) "\n" "\t\t-m val Set SO_MARK with given value\n" "\t\t-M val Set SO_MARK via setsockopt\n" + "\t\t-P val Set SO_PRIORITY via setsockopt\n" + "\t\t-Q val Set SO_PRIORITY via cmsg\n" "\t\t-d val Set SO_TXTIME with given delay (usec)\n" "\t\t-t Enable time stamp reporting\n" "\t\t-f val Set don't fragment via cmsg\n" @@ -115,7 +118,7 @@ static void cs_parse_args(int argc, char *argv[]) { int o; - while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:")) != -1) { + while ((o = getopt(argc, argv, "46sS:p:P:m:M:n:d:tf:F:c:C:l:L:H:Q:")) != -1) { switch (o) { case 's': opt.silent_send = true; @@ -148,6 +151,10 @@ static void cs_parse_args(int argc, char *argv[]) opt.mark.ena = true; opt.mark.val = atoi(optarg); break; + case 'Q': + opt.priority.ena = true; + opt.priority.val = atoi(optarg); + break; case 'M': opt.sockopt.mark = atoi(optarg); break; @@ -253,6 +260,8 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, SOL_SOCKET, SO_MARK, &opt.mark); ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_SOCKET, SO_PRIORITY, &opt.priority); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag); ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, SOL_IPV6, IPV6_TCLASS, &opt.v6.tclass); diff --git a/tools/testing/selftests/net/cmsg_so_priority.sh b/tools/testing/selftests/net/cmsg_so_priority.sh new file mode 100755 index 000000000000..ee07d8653262 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_so_priority.sh @@ -0,0 +1,151 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +readonly KSFT_SKIP=4 + +IP4=192.0.2.1/24 +TGT4=192.0.2.2 +TGT4_RAW=192.0.2.3 +IP6=2001:db8::1/64 +TGT6=2001:db8::2 +TGT6_RAW=2001:db8::3 +PORT=1234 +TOTAL_TESTS=0 +FAILED_TESTS=0 + +if ! command -v jq &> /dev/null; then + echo "SKIP cmsg_so_priroity.sh test: jq is not installed." >&2 + exit "$KSFT_SKIP" +fi + +check_result() { + ((TOTAL_TESTS++)) + if [ "$1" -ne 0 ]; then + ((FAILED_TESTS++)) + fi +} + +cleanup() +{ + cleanup_ns $NS +} + +trap cleanup EXIT + +setup_ns NS + +create_filter() { + local handle=$1 + local vlan_prio=$2 + local ip_type=$3 + local proto=$4 + local dst_ip=$5 + local ip_proto + + if [[ "$proto" == "u" ]]; then + ip_proto="udp" + elif [[ "$ip_type" == "ipv4" && "$proto" == "i" ]]; then + ip_proto="icmp" + elif [[ "$ip_type" == "ipv6" && "$proto" == "i" ]]; then + ip_proto="icmpv6" + fi + + tc -n $NS filter add dev dummy1 \ + egress pref 1 handle "$handle" proto 802.1q \ + flower vlan_prio "$vlan_prio" vlan_ethtype "$ip_type" \ + dst_ip "$dst_ip" ${ip_proto:+ip_proto $ip_proto} \ + action pass +} + +ip -n $NS link set dev lo up +ip -n $NS link add name dummy1 up type dummy + +ip -n $NS link add link dummy1 name dummy1.10 up type vlan id 10 \ + egress-qos-map 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 + +ip -n $NS address add $IP4 dev dummy1.10 +ip -n $NS address add $IP6 dev dummy1.10 nodad + +ip netns exec $NS sysctl -wq net.ipv4.ping_group_range='0 2147483647' + +ip -n $NS neigh add $TGT4 lladdr 00:11:22:33:44:55 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT6 lladdr 00:11:22:33:44:55 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT4_RAW lladdr 00:11:22:33:44:66 nud permanent \ + dev dummy1.10 +ip -n $NS neigh add $TGT6_RAW lladdr 00:11:22:33:44:66 nud permanent \ + dev dummy1.10 + +tc -n $NS qdisc add dev dummy1 clsact + +FILTER_COUNTER=10 + +for i in 4 6; do + for proto in u i r; do + echo "Test IPV$i, prot: $proto" + for priority in {0..7}; do + if [[ $i == 4 && $proto == "r" ]]; then + TGT=$TGT4_RAW + elif [[ $i == 6 && $proto == "r" ]]; then + TGT=$TGT6_RAW + elif [ $i == 4 ]; then + TGT=$TGT4 + else + TGT=$TGT6 + fi + + handle="${FILTER_COUNTER}${priority}" + + create_filter $handle $priority ipv$i $proto $TGT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + + if [[ $pkts == 0 ]]; then + check_result 0 + else + echo "prio $priority: expected 0, got $pkts" + check_result 1 + fi + + ip netns exec $NS ./cmsg_sender -$i -Q $priority \ + -p $proto $TGT $PORT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + if [[ $pkts == 1 ]]; then + check_result 0 + else + echo "prio $priority -Q: expected 1, got $pkts" + check_result 1 + fi + + ip netns exec $NS ./cmsg_sender -$i -P $priority \ + -p $proto $TGT $PORT + + pkts=$(tc -n $NS -j -s filter show dev dummy1 egress \ + | jq ".[] | select(.options.handle == ${handle}) | \ + .options.actions[0].stats.packets") + if [[ $pkts == 2 ]]; then + check_result 0 + else + echo "prio $priority -P: expected 2, got $pkts" + check_result 1 + fi + done + FILTER_COUNTER=$((FILTER_COUNTER + 10)) + done +done + +if [ $FAILED_TESTS -ne 0 ]; then + echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed" + exit 1 +else + echo "OK - All $TOTAL_TESTS tests passed" + exit 0 +fi diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh index c03151e7791c..c159230c9b62 100755 --- a/tools/testing/selftests/net/fdb_notify.sh +++ b/tools/testing/selftests/net/fdb_notify.sh @@ -49,7 +49,7 @@ test_dup_vxlan_self() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan" dev vx self dst 192.0.2.1 do_test_dup del "vxlan" dev vx self dst 192.0.2.1 @@ -59,7 +59,7 @@ test_dup_vxlan_master() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan master" dev vx master do_test_dup del "vxlan master" dev vx master @@ -79,7 +79,7 @@ test_dup_macvlan_master() ip_link_add br up type bridge vlan_filtering 1 ip_link_add dd up type dummy ip_link_add mv up link dd type macvlan mode passthru - ip_link_master mv br + ip_link_set_master mv br do_test_dup add "macvlan master" dev mv self do_test_dup del "macvlan master" dev mv self diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 1d58b3b87465..847936363a12 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -291,6 +291,37 @@ fib_rule6_test() "$getnomatch" "iif dscp redirect to table" \ "iif dscp no redirect to table" fi + + fib_check_iproute_support "flowlabel" "flowlabel" + if [ $? -eq 0 ]; then + match="flowlabel 0xfffff" + getmatch="flowlabel 0xfffff" + getnomatch="flowlabel 0xf" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "flowlabel redirect to table" \ + "flowlabel no redirect to table" + + match="flowlabel 0xfffff" + getmatch="from $SRC_IP6 iif $DEV flowlabel 0xfffff" + getnomatch="from $SRC_IP6 iif $DEV flowlabel 0xf" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "iif flowlabel redirect to table" \ + "iif flowlabel no redirect to table" + + match="flowlabel 0x08000/0x08000" + getmatch="flowlabel 0xfffff" + getnomatch="flowlabel 0xf7fff" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "flowlabel masked redirect to table" \ + "flowlabel masked no redirect to table" + + match="flowlabel 0x08000/0x08000" + getmatch="from $SRC_IP6 iif $DEV flowlabel 0xfffff" + getnomatch="from $SRC_IP6 iif $DEV flowlabel 0xf7fff" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "iif flowlabel masked redirect to table" \ + "iif flowlabel masked no redirect to table" + fi } fib_rule6_vrf_test() diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 7d885cff8d79..00bde7b6f39e 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -105,6 +105,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ + vxlan_reserved.sh \ vxlan_symmetric_ipv6.sh \ vxlan_symmetric.sh diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index 1c8a26046589..2b5700b61ffa 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding pvid_change" NUM_NETIFS=4 source lib.sh @@ -77,12 +77,16 @@ cleanup() ping_ipv4() { - ping_test $h1 192.0.2.2 + local msg=$1 + + ping_test $h1 192.0.2.2 "$msg" } ping_ipv6() { - ping6_test $h1 2001:db8:1::2 + local msg=$1 + + ping6_test $h1 2001:db8:1::2 "$msg" } learning() @@ -95,6 +99,21 @@ flooding() flood_test $swp2 $h1 $h2 } +pvid_change() +{ + # Test that the changing of the VLAN-aware PVID does not affect + # VLAN-unaware forwarding + bridge vlan add vid 3 dev $swp1 pvid untagged + + ping_ipv4 " with bridge port $swp1 PVID changed" + ping_ipv6 " with bridge port $swp1 PVID changed" + + bridge vlan del vid 3 dev $swp1 + + ping_ipv4 " with bridge port $swp1 PVID deleted" + ping_ipv6 " with bridge port $swp1 PVID deleted" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7337f398f9cc..1fd40bada694 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -932,13 +932,6 @@ packets_rate() echo $(((t1 - t0) / interval)) } -mac_get() -{ - local if_name=$1 - - ip -j link show dev $if_name | jq -r '.[]["address"]' -} - ether_addr_to_u64() { local addr="$1" diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index c35548767756..ecd34f364125 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -7,7 +7,6 @@ ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \ NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes -REQUIRE_MZ=no source lib.sh diff --git a/tools/testing/selftests/net/forwarding/vxlan_reserved.sh b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh new file mode 100755 index 000000000000..46c31794b91b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh @@ -0,0 +1,352 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|---------------+ +# | +# +----|--------------------------------+ +# | SW | | +# | +--|------------------------------+ | +# | | + $swp1 BR1 (802.1d) | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | id 1000 dstport $VXPORT | | +# | +---------------------------------+ | +# | | +# | 192.0.2.32/28 via 192.0.2.18 | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +--|----------------------------------+ +# | +# +--|----------------------------------+ +# | | | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | +# | VRP2 (vrf) | +# +-------------------------------------+ + +: ${VXPORT:=4789} +: ${ALL_TESTS:=" + default_test + plain_test + reserved_0_test + reserved_10_test + reserved_31_test + reserved_56_test + reserved_63_test + "} + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 + defer simple_if_fini $h1 192.0.2.1/28 + + tc qdisc add dev $h1 clsact + defer tc qdisc del dev $h1 clsact + + tc filter add dev $h1 ingress pref 77 \ + prot ip flower skip_hw ip_proto icmp action drop + defer tc filter del dev $h1 ingress pref 77 +} + +switch_create() +{ + ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip_link_set_addr br1 $(mac_get $swp1) + ip_link_set_up br1 + + ip_link_set_up $rp1 + ip_addr_add $rp1 192.0.2.17/28 + ip_route_add 192.0.2.32/28 nexthop via 192.0.2.18 + + ip_link_set_master $swp1 br1 + ip_link_set_up $swp1 +} + +vrp2_create() +{ + simple_if_init $rp2 192.0.2.18/28 + defer simple_if_fini $rp2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + h1_create + switch_create + + vrp2_create +} + +vxlan_header_bytes() +{ + local vni=$1; shift + local -a extra_bits=("$@") + local -a bits + local i + + for ((i=0; i < 64; i++)); do + bits[i]=0 + done + + # Bit 4 is the I flag and is always on. + bits[4]=1 + + for i in ${extra_bits[@]}; do + bits[i]=1 + done + + # Bits 32..55 carry the VNI + local mask=0x800000 + for ((i=0; i < 24; i++)); do + bits[$((i + 32))]=$(((vni & mask) != 0)) + ((mask >>= 1)) + done + + local bytes + for ((i=0; i < 8; i++)); do + local byte=0 + local j + for ((j=0; j < 8; j++)); do + local bit=${bits[8 * i + j]} + ((byte += bit << (7 - j))) + done + bytes+=$(printf %02x $byte): + done + + echo ${bytes%:} +} + +neg_bytes() +{ + local bytes=$1; shift + + local -A neg=([0]=f [1]=e [2]=d [3]=c [4]=b [5]=a [6]=9 [7]=8 + [8]=7 [9]=6 [a]=5 [b]=4 [c]=3 [d]=2 [e]=1 [f]=0 [:]=:) + local out + local i + + for ((i=0; i < ${#bytes}; i++)); do + local c=${bytes:$i:1} + out+=${neg[$c]} + done + echo $out +} + +vxlan_ping_do() +{ + local count=$1; shift + local dev=$1; shift + local next_hop_mac=$1; shift + local dest_ip=$1; shift + local dest_mac=$1; shift + local vni=$1; shift + local reserved_bits=$1; shift + + local vxlan_header=$(vxlan_header_bytes $vni $reserved_bits) + + $MZ $dev -c $count -d 100msec -q \ + -b $next_hop_mac -B $dest_ip \ + -t udp sp=23456,dp=$VXPORT,p=$(: + )"$vxlan_header:"$( : VXLAN + )"$dest_mac:"$( : ETH daddr + )"00:11:22:33:44:55:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:54:"$( : IP total length + )"99:83:"$( : IP identification + )"40:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"01:"$( : IP proto + )"00:00:"$( : IP header csum + )"$(ipv4_to_bytes 192.0.2.3):"$( : IP saddr + )"$(ipv4_to_bytes 192.0.2.1):"$( : IP daddr + )"08:"$( : ICMP type + )"00:"$( : ICMP code + )"8b:f2:"$( : ICMP csum + )"1f:6a:"$( : ICMP request identifier + )"00:01:"$( : ICMP request seq. number + )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload + )"6d:74:0b:00:00:00:00:00:"$( : + )"10:11:12:13:14:15:16:17:"$( : + )"18:19:1a:1b:1c:1d:1e:1f:"$( : + )"20:21:22:23:24:25:26:27:"$( : + )"28:29:2a:2b:2c:2d:2e:2f:"$( : + )"30:31:32:33:34:35:36:37" +} + +vxlan_device_add() +{ + ip_link_add vx1 up type vxlan id 1000 \ + local 192.0.2.17 dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 100 "$@" + ip_link_set_master vx1 br1 +} + +vxlan_all_reserved_bits() +{ + local i + + for ((i=0; i < 64; i++)); do + if ((i == 4 || i >= 32 && i < 56)); then + continue + fi + echo $i + done +} + +vxlan_ping_vanilla() +{ + vxlan_ping_do 10 $rp2 $(mac_get $rp1) 192.0.2.17 $(mac_get $h1) 1000 +} + +vxlan_ping_reserved() +{ + for bit in $(vxlan_all_reserved_bits); do + vxlan_ping_do 1 $rp2 $(mac_get $rp1) \ + 192.0.2.17 $(mac_get $h1) 1000 "$bit" + ((n++)) + done +} + +vxlan_ping_test() +{ + local what=$1; shift + local get_stat=$1; shift + local expect=$1; shift + + RET=0 + + local t0=$($get_stat) + + "$@" + check_err $? "Failure when running $@" + + local t1=$($get_stat) + local delta=$((t1 - t0)) + + ((expect == delta)) + check_err $? "Expected to capture $expect packets, got $delta." + + log_test "$what" +} + +__default_test_do() +{ + local n_allowed_bits=$1; shift + local what=$1; shift + + vxlan_ping_test "$what: clean packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + 10 vxlan_ping_vanilla + + local t0=$(link_stats_get vx1 rx errors) + vxlan_ping_test "$what: mangled packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + $n_allowed_bits vxlan_ping_reserved + local t1=$(link_stats_get vx1 rx errors) + + RET=0 + local expect=$((39 - n_allowed_bits)) + local delta=$((t1 - t0)) + ((expect == delta)) + check_err $? "Expected $expect error packets, got $delta." + log_test "$what: drops reported" +} + +default_test_do() +{ + vxlan_device_add + __default_test_do 0 "Default" +} + +default_test() +{ + in_defer_scope \ + default_test_do +} + +plain_test_do() +{ + vxlan_device_add reserved_bits 0xf7ffffff000000ff + __default_test_do 0 "reserved_bits 0xf7ffffff000000ff" +} + +plain_test() +{ + in_defer_scope \ + plain_test_do +} + +reserved_test() +{ + local bit=$1; shift + + local allowed_bytes=$(vxlan_header_bytes 0xffffff $bit) + local reserved_bytes=$(neg_bytes $allowed_bytes) + local reserved_bits=${reserved_bytes//:/} + + vxlan_device_add reserved_bits 0x$reserved_bits + __default_test_do 1 "reserved_bits 0x$reserved_bits" +} + +reserved_0_test() +{ + in_defer_scope \ + reserved_test 0 +} + +reserved_10_test() +{ + in_defer_scope \ + reserved_test 10 +} + +reserved_31_test() +{ + in_defer_scope \ + reserved_test 31 +} + +reserved_56_test() +{ + in_defer_scope \ + reserved_test 56 +} + +reserved_63_test() +{ + in_defer_scope \ + reserved_test 63 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8994fec1c38f..0bd9a038a1f0 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -435,6 +435,13 @@ xfail_on_veth() fi } +mac_get() +{ + local if_name=$1 + + ip -j link show dev $if_name | jq -r '.[]["address"]' +} + kill_process() { local pid=$1; shift @@ -451,7 +458,7 @@ ip_link_add() defer ip link del dev "$name" } -ip_link_master() +ip_link_set_master() { local member=$1; shift local master=$1; shift @@ -459,3 +466,62 @@ ip_link_master() ip link set dev "$member" master "$master" defer ip link set dev "$member" nomaster } + +ip_link_set_addr() +{ + local name=$1; shift + local addr=$1; shift + + local old_addr=$(mac_get "$name") + ip link set dev "$name" address "$addr" + defer ip link set dev "$name" address "$old_addr" +} + +ip_link_is_up() +{ + local name=$1; shift + + local state=$(ip -j link show "$name" | + jq -r '(.[].flags[] | select(. == "UP")) // "DOWN"') + [[ $state == "UP" ]] +} + +ip_link_set_up() +{ + local name=$1; shift + + if ! ip_link_is_up "$name"; then + ip link set dev "$name" up + defer ip link set dev "$name" down + fi +} + +ip_link_set_down() +{ + local name=$1; shift + + if ip_link_is_up "$name"; then + ip link set dev "$name" down + defer ip link set dev "$name" up + fi +} + +ip_addr_add() +{ + local name=$1; shift + + ip addr add dev "$name" "$@" + defer ip addr del dev "$name" "$@" +} + +ip_route_add() +{ + ip route add "$@" + defer ip route del "$@" +} + +bridge_vlan_add() +{ + bridge vlan add "$@" + defer bridge vlan del "$@" +} diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 477ae76de93d..3efe005436cd 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -71,6 +71,11 @@ def ksft_in(a, b, comment=""): _fail("Check failed", a, "not in", b, comment) +def ksft_is(a, b, comment=""): + if a is not b: + _fail("Check failed", a, "is not", b, comment) + + def ksft_ge(a, b, comment=""): if a < b: _fail("Check failed", a, "<", b, comment) diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 72590c3f90f1..9e3bcddcf3e8 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -10,7 +10,9 @@ import time class CmdExitFailure(Exception): - pass + def __init__(self, msg, cmd_obj): + super().__init__(msg) + self.cmd = cmd_obj class cmd: @@ -48,7 +50,7 @@ class cmd: if len(stderr) > 0 and stderr[-1] == "\n": stderr = stderr[:-1] raise CmdExitFailure("Command failed: %s\nSTDOUT: %s\nSTDERR: %s" % - (self.proc.args, stdout, stderr)) + (self.proc.args, stdout, stderr), self) class bkg(cmd): diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index a0d689d58c57..ad1e36baee2a 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -13,14 +13,14 @@ try: SPEC_PATH = KSFT_DIR / "net/lib/specs" sys.path.append(tools_full_path.as_posix()) - from net.lib.ynl.lib import YnlFamily, NlError + from net.lib.ynl.pyynl.lib import YnlFamily, NlError else: # Running in tree tools_full_path = KSRC / "tools" SPEC_PATH = KSRC / "Documentation/netlink/specs" sys.path.append(tools_full_path.as_posix()) - from net.ynl.lib import YnlFamily, NlError + from net.ynl.pyynl.lib import YnlFamily, NlError except ModuleNotFoundError as e: ksft_pr("Failed importing `ynl` library from kernel sources") ksft_pr(str(e)) @@ -32,23 +32,23 @@ except ModuleNotFoundError as e: # Set schema='' to avoid jsonschema validation, it's slow # class EthtoolFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('ethtool.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class RtnlFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetdevFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) class NetshaperFamily(YnlFamily): - def __init__(self): + def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), - schema='') + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/netfilter/rpath.sh b/tools/testing/selftests/net/netfilter/rpath.sh index 4485fd7675ed..86ec4e68594d 100755 --- a/tools/testing/selftests/net/netfilter/rpath.sh +++ b/tools/testing/selftests/net/netfilter/rpath.sh @@ -61,9 +61,20 @@ ip -net "$ns2" a a 192.168.42.1/24 dev d0 ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad +# avoid neighbor lookups and enable martian IPv6 pings +ns2_hwaddr=$(ip -net "$ns2" link show dev v0 | \ + sed -n 's, *link/ether \([^ ]*\) .*,\1,p') +ns1_hwaddr=$(ip -net "$ns1" link show dev v0 | \ + sed -n 's, *link/ether \([^ ]*\) .*,\1,p') +ip -net "$ns1" neigh add fec0:42::1 lladdr "$ns2_hwaddr" nud permanent dev v0 +ip -net "$ns1" neigh add fec0:23::1 lladdr "$ns2_hwaddr" nud permanent dev v0 +ip -net "$ns2" neigh add fec0:42::2 lladdr "$ns1_hwaddr" nud permanent dev d0 +ip -net "$ns2" neigh add fec0:23::2 lladdr "$ns1_hwaddr" nud permanent dev v0 + # firewall matches to test [ -n "$iptables" ] && { common='-t raw -A PREROUTING -s 192.168.0.0/16' + common+=' -p icmp --icmp-type echo-request' if ! ip netns exec "$ns2" "$iptables" $common -m rpfilter;then echo "Cannot add rpfilter rule" exit $ksft_skip @@ -72,6 +83,7 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad } [ -n "$ip6tables" ] && { common='-t raw -A PREROUTING -s fec0::/16' + common+=' -p icmpv6 --icmpv6-type echo-request' if ! ip netns exec "$ns2" "$ip6tables" $common -m rpfilter;then echo "Cannot add rpfilter rule" exit $ksft_skip @@ -82,8 +94,10 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad table inet t { chain c { type filter hook prerouting priority raw; - ip saddr 192.168.0.0/16 fib saddr . iif oif exists counter - ip6 saddr fec0::/16 fib saddr . iif oif exists counter + ip saddr 192.168.0.0/16 icmp type echo-request \ + fib saddr . iif oif exists counter + ip6 saddr fec0::/16 icmpv6 type echo-request \ + fib saddr . iif oif exists counter } } EOF diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py index 93d9d914529b..93e8cb671c3d 100755 --- a/tools/testing/selftests/net/nl_netdev.py +++ b/tools/testing/selftests/net/nl_netdev.py @@ -18,6 +18,23 @@ def lo_check(nf) -> None: ksft_eq(len(lo_info['xdp-rx-metadata-features']), 0) +def napi_list_check(nf) -> None: + with NetdevSimDev(queue_count=100) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} up") + + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 100) + + for q in [50, 0, 99]: + for i in range(4): + nsim.dfs_write("queue_reset", f"{q} {i}") + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 100, + comment=f"queue count after reset queue {q} mode {i}") + + def page_pool_check(nf) -> None: with NetdevSimDev() as nsimdev: nsim = nsimdev.nsims[0] @@ -89,7 +106,7 @@ def page_pool_check(nf) -> None: def main() -> None: nf = NetdevFamily() - ksft_run([empty_check, lo_check, page_pool_check], + ksft_run([empty_check, lo_check, page_pool_check, napi_list_check], args=(nf, )) ksft_exit() diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index cc0bfae2bafa..960e1ab4dd04 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -171,8 +171,10 @@ ovs_add_netns_and_veths () { ovs_add_if "$1" "$2" "$4" -u || return 1 fi - [ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \ - tcpdump -i any -s 65535 + if [ $TRACING -eq 1 ]; then + ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553 + ovs_wait grep -q "listening on any" ${ovs_dir}/stderr + fi return 0 } diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index 4071c133f29e..ff989c325eef 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -23,7 +23,7 @@ if [ $# -ne 1 ]; then ktap_exit_fail_msg "usage: $0 <script>" exit "$KSFT_FAIL" fi -script="$1" +script="$(basename $1)" if [ -z "$(which packetdrill)" ]; then ktap_skip_all "packetdrill not found in PATH" @@ -31,16 +31,29 @@ if [ -z "$(which packetdrill)" ]; then fi declare -a optargs +failfunc=ktap_test_fail + if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then optargs+=('--tolerance_usecs=14000') + + # xfail tests that are known flaky with dbg config, not fixable. + # still run them for coverage (and expect 100% pass without dbg). + declare -ar xfail_list=( + "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_timestamping.*.pkt" + "tcp_user_timeout_user-timeout-probe.pkt" + "tcp_zerocopy_epoll_.*.pkt" + ) + readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" + [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail fi ktap_print_header ktap_set_plan 2 -unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $(basename $script) > /dev/null \ - && ktap_test_pass "ipv4" || ktap_test_fail "ipv4" -unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $(basename $script) > /dev/null \ - && ktap_test_pass "ipv6" || ktap_test_fail "ipv6" +unshare -n packetdrill ${ipv4_args[@]} ${optargs[@]} $script > /dev/null \ + && ktap_test_pass "ipv4" || $failfunc "ipv4" +unshare -n packetdrill ${ipv6_args[@]} ${optargs[@]} $script > /dev/null \ + && ktap_test_pass "ipv6" || $failfunc "ipv6" ktap_finished diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt new file mode 100644 index 000000000000..38535701656e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-accept.pkt @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test for blocking accept. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0...0.200 accept(3, ..., ...) = 4 + + +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 257 + + +.1 write(4, ..., 2000) = 2000 + +0 > P. 1:2001(2000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt new file mode 100644 index 000000000000..3692ef102381 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-connect.pkt @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test for blocking connect. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + + +.1...0.200 connect(3, ..., ...) = 0 + + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.1 < S. 0:0(0) ack 1 win 5792 <mss 1460,nop,wscale 2,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt new file mode 100644 index 000000000000..914eabab367a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test for blocking read. +--tolerance_usecs=10000 + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 + + +0...0.100 read(4, ..., 2000) = 2000 + +.1 < P. 1:2001(2000) ack 1 win 257 + +0 > . 1:1(0) ack 2001 + + +.1...0.200 read(4, ..., 2000) = 2000 + +.1 < P. 2001:4001(2000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 + + +.1 < P. 4001:6001(2000) ack 1 win 257 + +0 > . 1:1(0) ack 6001 + +0...0.000 read(4, ..., 1000) = 1000 + +0...0.000 read(4, ..., 1000) = 1000 diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt new file mode 100644 index 000000000000..cec5a0725d95 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-write.pkt @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test for blocking write. +--tolerance_usecs=10000 + +`./defaults.sh +./set_sysctls.py /proc/sys/net/ipv4/tcp_min_tso_segs=10 +` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 50000 <mss 1000,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 50000 + +0 accept(3, ..., ...) = 4 + +// Kernel doubles our value -> sk->sk_sndbuf is set to 42000 + +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [21000], 4) = 0 + +0 getsockopt(4, SOL_SOCKET, SO_SNDBUF, [42000], [4]) = 0 + +// A write of 60000 does not block. + +0...0.300 write(4, ..., 61000) = 61000 // this write() blocks + + +.1 < . 1:1(0) ack 10001 win 50000 + + +.1 < . 1:1(0) ack 30001 win 50000 + +// This ACK should wakeup the write(). An ACK of 35001 does not. + +.1 < . 1:1(0) ack 36001 win 50000 + +// Reset to sysctls defaults. +`/tmp/sysctl_restore_${PPID}.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt new file mode 100644 index 000000000000..8514d6bdbb6d --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-local-close-then-remote-fin.pkt @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test basic connection teardown where local process closes first: +// the local process calls close() first, so we send a FIN, and receive an ACK. +// Then we receive a FIN and ACK it. + +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +.01...0.011 connect(3, ..., ...) = 0 + +0 > S 0:0(0) <...> + +0 < S. 0:0(0) ack 1 win 32768 <mss 1000,nop,wscale 6,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 + + +0 write(3, ..., 1000) = 1000 + +0 > P. 1:1001(1000) ack 1 + +0 < . 1:1(0) ack 1001 win 257 + + +0 close(3) = 0 + +0 > F. 1001:1001(0) ack 1 + +0 < . 1:1(0) ack 1002 win 257 + + +0 < F. 1:1(0) ack 1002 win 257 + +0 > . 1002:1002(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt new file mode 100644 index 000000000000..04103134bd99 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-on-syn-sent.pkt @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test to make sure no RST is being sent when close() +// is called on a socket with SYN_SENT state. + +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <...> + +// Application decideds to close the socket in SYN_SENT state +// Make sure no RST is sent after close(). + +0 close(3) = 0 + +// Receive syn-ack to trigger the send side packet examination: +// If a RESET were sent right after close(), it would have failed with +// a mismatched timestamp. + +.1 < S. 0:0(0) ack 1 win 32000 <mss 1460,nop,wscale 7> + +0 > R 1:1(0) diff --git a/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt b/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt new file mode 100644 index 000000000000..5f3a2914213a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_close_close-remote-fin-then-close.pkt @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +// Verify behavior for the sequence: remote side sends FIN, then we close(). +// Since the remote side (client) closes first, we test our LAST_ACK code path. + +`./defaults.sh` + +// Initialize a server socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +0 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + +// Client closes first. + +.01 < F. 1:1(0) ack 1 win 257 + +0 > . 1:1(0) ack 2 + +// App notices that client closed. + +0 read(4, ..., 1000) = 0 + +// Then we close. + +.01 close(4) = 0 + +0 > F. 1:1(0) ack 2 + +// Client ACKs our FIN. + +.01 < . 2:2(0) ack 2 win 257 + +// Verify that we send RST in response to any incoming segments +// (because the kernel no longer has any record of this socket). + +.01 < . 2:2(0) ack 2 win 257 + +0 > R 2:2(0) diff --git a/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt b/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt new file mode 100644 index 000000000000..643baf3267cf --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ecn_ecn-uses-ect0.pkt @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test ECN: verify that Linux TCP ECN sending code uses ECT0 (not ECT1). +// +`./defaults.sh +sysctl -q net.ipv4.tcp_ecn=1 # fully enabled +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 + +// ECN handshake: send EW flags in SYN packet, E flag in SYN-ACK response ++.002 ... 0.004 connect(4, ..., ...) = 0 + + +0 > SEW 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> ++.002 < SE. 0:0(0) ack 1 win 32767 <mss 1000,nop,wscale 6,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 + +// Write 1 MSS. ++.002 write(4, ..., 1000) = 1000 +// Send 1 MSS with ect0. + +0 > [ect0] P. 1:1001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt new file mode 100644 index 000000000000..f95b9b3c9fa1 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-large.pkt @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP does not append any data from consequent writes to the tail +// skb created for the chunk. The large chunk itself should be packetized as +// usual. +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on +// the tail. + +0 write(4, ..., 10400) = 10400 + +// Write another 10040B chunk with no coalescing options. + +0 send(4, ..., 10400, MSG_EOR) = 10400 + +// Write a 2KB chunk. This chunk should not be appended to the packets created +// the previous chunk. + +0 write(4, ..., 2000) = 2000 + + +0 > P. 1:10001(10000) ack 1 ++.001 < . 1:1(0) ack 10001 win 514 +// Now we have enough room to send out the 2 x 400B packets out. + +0 > P. 10001:20801(10800) ack 1 ++.001 < . 1:1(0) ack 20801 win 514 +// This 2KB packet should be sent alone. + +0 > P. 20801:22801(2000) ack 1 ++.001 < . 1:1(0) ack 22801 win 514 diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt new file mode 100644 index 000000000000..2ff66075288e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-retrans.pkt @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP does not append any data from consequent writes to the tail +// skb created for the chunk. Also, when packets are retransmitted, they +// will not be coalesce into the same skb. +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on +// the tail. + +0 write(4, ..., 10400) = 10400 + +// Write 10 400B chunks with no coalescing options. + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 +// This chunk should not be appended to the skbs created for the previous chunk. + +0 write(4, ..., 10000) = 10000 + + +0 > P. 1:10001(10000) ack 1 ++.001 < . 1:1(0) ack 10001 win 514 +// Now we have enough room to send out the 2 x 400B packets out. + +0 > P. 10001:10801(800) ack 1 +// The 9 remaining 400B chunks should be sent as individual packets. + +0 > P. 10801:11201(400) ack 1 + +0 > P. 11201:11601(400) ack 1 + +0 > P. 11601:12001(400) ack 1 + +0 > P. 12001:12401(400) ack 1 + +0 > P. 12401:12801(400) ack 1 + +0 > P. 12801:13201(400) ack 1 + +0 > P. 13201:13601(400) ack 1 + +0 > P. 13601:14001(400) ack 1 + +0 > P. 14001:14401(400) ack 1 +// The last 10KB chunk should be sent separately. + +0 > P. 14401:24401(10000) ack 1 + ++.001 < . 1:1(0) ack 10401 win 514 ++.001 < . 1:1(0) ack 10801 win 514 ++.001 < . 1:1(0) ack 11201 win 514 ++.001 < . 1:1(0) ack 11601 win 514 ++.001 < . 1:1(0) ack 12001 win 514 <sack 13201:14401,nop,nop> +// TCP should fill the hole but no coalescing should happen, and all +// retransmissions should be sent out as individual packets. + +// Note : This is timeout based retransmit. +// Do not put +0 here or flakes will come back. ++.004~+.008 > P. 12001:12401(400) ack 1 + ++.001 < . 1:1(0) ack 12401 win 514 <sack 13201:14401,nop,nop> + +0 > P. 12401:12801(400) ack 1 + +0 > P. 12801:13201(400) ack 1 ++.001 < . 1:1(0) ack 12801 win 514 <sack 13201:14401,nop,nop> ++.001 < . 1:1(0) ack 14401 win 514 ++.001 < . 1:1(0) ack 24401 win 514 diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt new file mode 100644 index 000000000000..77039c5aac39 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-small.pkt @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP does not append any data from consequent writes to the tail +// skb created for the chunk. +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on +// the tail. + +0 write(4, ..., 10400) = 10400 + +// Write a 400B chunk with no coalescing options. + +0 send(4, ..., 400, MSG_EOR) = 400 + +// This chunk should not be appended to the skbs created for the previous chunk. + +0 write(4, ..., 10000) = 10000 + + +0 > P. 1:10001(10000) ack 1 ++.001 < . 1:1(0) ack 10001 win 514 +// Now we have enough room to send out the 2 x 400B packets out. + +0 > P. 10001:10801(800) ack 1 + +0 > P. 10801:20801(10000) ack 1 ++.001 < . 1:1(0) ack 10401 win 514 ++.001 < . 1:1(0) ack 10801 win 514 ++.001 < . 1:1(0) ack 20801 win 514 diff --git a/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt new file mode 100644 index 000000000000..dd5a06250595 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_eor_no-coalesce-subsequent.pkt @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP does not append any data from consequent writes to the tail +// skb created for the chunk even though we have 10 back-to-back small +// writes. +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +// Write a 10400B chunk to fill the ICW, and have a 400 byte skb sitting on +// the tail. + +0 write(4, ..., 10400) = 10400 + +// Write 10 400B chunks with no coalescing options. + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 + +0 send(4, ..., 400, MSG_EOR) = 400 +// This chunk should not be appended to the skbs created for the previous chunk. + +0 write(4, ..., 10000) = 10000 + + +0 > P. 1:10001(10000) ack 1 ++.001 < . 1:1(0) ack 10001 win 514 +// Now we have enough room to send out the 2 x 400B packets out. + +0 > P. 10001:10801(800) ack 1 +// The 9 remaining 400B chunks should be sent as individual packets. + +0 > P. 10801:11201(400) ack 1 + +0 > P. 11201:11601(400) ack 1 + +0 > P. 11601:12001(400) ack 1 + +0 > P. 12001:12401(400) ack 1 + +0 > P. 12401:12801(400) ack 1 + +0 > P. 12801:13201(400) ack 1 + +0 > P. 13201:13601(400) ack 1 + +0 > P. 13601:14001(400) ack 1 + +0 > P. 14001:14401(400) ack 1 +// The last 10KB chunk should be sent separately. + +0 > P. 14401:24401(10000) ack 1 + ++.001 < . 1:1(0) ack 10401 win 514 ++.001 < . 1:1(0) ack 10801 win 514 ++.001 < . 1:1(0) ack 11201 win 514 ++.001 < . 1:1(0) ack 11601 win 514 ++.001 < . 1:1(0) ack 12001 win 514 ++.001 < . 1:1(0) ack 12401 win 514 ++.001 < . 1:1(0) ack 12801 win 514 ++.001 < . 1:1(0) ack 13201 win 514 ++.001 < . 1:1(0) ack 13601 win 514 ++.001 < . 1:1(0) ack 14001 win 514 ++.001 < . 1:1(0) ack 14401 win 514 ++.001 < . 1:1(0) ack 24401 win 514 diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt new file mode 100644 index 000000000000..0d3c8077e830 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-10pkt-lost-1.pkt @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test PRR-slowstart implementation. +// In this variant we test a simple case where in-flight == ssthresh +// all the way through recovery, so during fast recovery we send one segment +// for each segment SACKed/ACKed. + +// Set up config. +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> +// RTT 100ms + +.1 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Send 10 data segments. + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// Lost packet 1:1001. + +.11 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop> + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop> + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:4001,nop,nop> +// Enter fast recovery. + +0 > . 1:1001(1000) ack 1 + +.01 %{ +assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state +assert tcpi_snd_cwnd == 7, tcpi_snd_cwnd +assert tcpi_snd_ssthresh == 7, tcpi_snd_ssthresh +}% + +// Write some more, which we will send 1 MSS at a time, +// as in-flight segments are SACKed or ACKed. + +.01 write(4, ..., 7000) = 7000 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:5001,nop,nop> + +0 > . 10001:11001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:6001,nop,nop> + +0 > . 11001:12001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:7001,nop,nop> + +0 > . 12001:13001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:8001,nop,nop> + +0 > . 13001:14001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:9001,nop,nop> + +0 > . 14001:15001(1000) ack 1 + + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:10001,nop,nop> + +0 > . 15001:16001(1000) ack 1 + + +.02 < . 1:1(0) ack 10001 win 320 + +0 > P. 16001:17001(1000) ack 1 +// Leave fast recovery. + +.01 %{ +assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state +assert tcpi_snd_cwnd == 7, tcpi_snd_cwnd +assert tcpi_snd_ssthresh == 7, tcpi_snd_ssthresh +}% + + +.03 < . 1:1(0) ack 12001 win 320 + +.02 < . 1:1(0) ack 14001 win 320 + +.02 < . 1:1(0) ack 16001 win 320 + +.02 < . 1:1(0) ack 17001 win 320 diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt new file mode 100644 index 000000000000..7842a10b6967 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost-1_4-11_16.pkt @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test PRR-slowstart implementation. The sender sends 20 packets. Packet +// 1 to 4, and 11 to 16 are dropped. +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + + +.01 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Write 20 data segments. + +0 write(4, ..., 20000) = 20000 + +0 > P. 1:10001(10000) ack 1 + +// Receive first DUPACK, entering PRR part + +.01 < . 1:1(0) ack 1 win 320 <sack 4001:5001,nop,nop> + +0 > . 10001:11001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:6001,nop,nop> + +0 > . 11001:12001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:7001,nop,nop> + +0 > . 1:1001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:8001,nop,nop> + +0 > . 1001:2001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:9001,nop,nop> + +0 > . 2001:3001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:10001,nop,nop> + +0 > . 3001:4001(1000) ack 1 +// Enter PRR CRB ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:11001,nop,nop> + +0 > . 12001:13001(1000) ack 1 ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:12001,nop,nop> + +0 > . 13001:14001(1000) ack 1 +// Enter PRR slow start + +.01 < . 1:1(0) ack 1001 win 320 <sack 4001:12001,nop,nop> + +0 > P. 14001:16001(2000) ack 1 ++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:12001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 > . 16001:17001(1000) ack 1 +// inflight reaches ssthresh, goes into packet conservation mode ++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:13001,nop,nop> + +0 > . 17001:18001(1000) ack 1 ++.002 < . 1:1(0) ack 1001 win 320 <sack 2001:14001,nop,nop> + +0 > . 18001:19001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt new file mode 100644 index 000000000000..b66d7644c3b6 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-30pkt-lost1_4.pkt @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test PRR-slowstart implementation. The sender sends 20 packets. Packet +// 1 to 4 are lost. The sender writes another 10 packets. +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + + +.01 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Send 20 data segments. + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// Lost packet 1,2,3,4 + +.01 < . 1:1(0) ack 1 win 320 <sack 4001:5001,nop,nop> ++.002 < . 1:1(0) ack 1 win 320 <sack 4001:6001,nop,nop> + +0 < . 1:1(0) ack 1 win 320 <sack 4001:7001,nop,nop> + +0 > . 1:1001(1000) ack 1 + +0 < . 1:1(0) ack 1 win 320 <sack 4001:8001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 < . 1:1(0) ack 1 win 320 <sack 4001:9001,nop,nop> + +0 > . 2001:3001(1000) ack 1 + +0 < . 1:1(0) ack 1 win 320 <sack 4001:10001,nop,nop> + +0 > . 3001:4001(1000) ack 1 + +// Receiver ACKs all data. + +.01 < . 1:1(0) ack 1001 win 320 <sack 4001:10001,nop,nop> + +0 < . 1:1(0) ack 2001 win 320 <sack 4001:10001,nop,nop> + +0 < . 1:1(0) ack 3001 win 320 <sack 4001:10001,nop,nop> + +0 < . 1:1(0) ack 10001 win 320 + +// Writes another 10 packets, which the ssthresh*mss amount +// should be sent right away + +.01 write(4, ..., 10000) = 10000 + +0 > . 10001:17001(7000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt new file mode 100644 index 000000000000..8e87bfecabb5 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_fast_recovery_prr-ss-ack-below-snd_una-cubic.pkt @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test PRR-slowstart implementation. +// In this variant we verify that the sender uses SACK info on an ACK +// below snd_una. + +// Set up config. +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 8> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> +// RTT 10ms + +.01 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Send 10 data segments. + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// Lost packet 1:1001,4001:5001,7001:8001. + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop> + +0 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop> + +0 < . 1:1(0) ack 1 win 320 <sack 1001:3001 8001:9001,nop,nop> + +0 > . 1:1001(1000) ack 1 + ++.012 < . 1:1(0) ack 4001 win 320 <sack 8001:9001,nop,nop> + +0 > . 4001:7001(3000) ack 1 + + +0 write(4, ..., 10000) = 10000 + +// The following ACK was reordered - delayed so that it arrives with +// an ACK field below snd_una. Here we check that the newly-SACKed +// 2MSS at 5001:7001 cause us to send out 2 more MSS. ++.002 < . 1:1(0) ack 3001 win 320 <sack 5001:7001,nop,nop> + +0 > . 7001:8001(1000) ack 1 + +0 > . 10001:11001(1000) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt new file mode 100644 index 000000000000..96b01eb5b7a4 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-no-sack.pkt @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test RFC 3042 "Limited Transmit": "sending a new data segment in +// response to each of the first two duplicate acknowledgments that +// arrive at the sender". +// This variation tests a receiver that doesn't support SACK. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Write some data, and send the initial congestion window. + +0 write(4, ..., 15000) = 15000 + +0 > P. 1:10001(10000) ack 1 + +// Limited transmit: on first dupack, send a new data segment. + +.11 < . 1:1(0) ack 1 win 320 + +0 > . 10001:11001(1000) ack 1 + +// Limited transmit: on second dupack, send a new data segment. + +.01 < . 1:1(0) ack 1 win 320 + +0 > . 11001:12001(1000) ack 1 + +// It turned out to be reordering, not loss. +// We have one packet newly acked (1001:3001 were DUP-ACK'd) +// So we revert state back to Open. Slow start cwnd from 10 to 11 +// and send 11 - 9 = 2 packets + +.01 < . 1:1(0) ack 3001 win 320 + +0 > P. 12001:14001(2000) ack 1 + + +.02 < . 1:1(0) ack 5001 win 320 + +0 > P. 14001:15001(1000) ack 1 + +// Client gradually ACKs all data. + +.02 < . 1:1(0) ack 7001 win 320 + +.02 < . 1:1(0) ack 9001 win 320 + +.02 < . 1:1(0) ack 11001 win 320 + +.02 < . 1:1(0) ack 13001 win 320 + +.02 < . 1:1(0) ack 15001 win 320 + +// Clean up. + +.17 close(4) = 0 + +0 > F. 15001:15001(0) ack 1 + +.1 < F. 1:1(0) ack 15002 win 257 + +0 > . 15002:15002(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt new file mode 100644 index 000000000000..642da51ec3a4 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_limited_transmit_limited-transmit-sack.pkt @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test RFC 3042 "Limited Transmit": "sending a new data segment in +// response to each of the first two duplicate acknowledgments that +// arrive at the sender". +// This variation tests a receiver that supports SACK. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 320 + +0 accept(3, ..., ...) = 4 + +// Write some data, and send the initial congestion window. + +0 write(4, ..., 15000) = 15000 + +0 > P. 1:10001(10000) ack 1 + +// Limited transmit: on first dupack, send a new data segment. + +.11 < . 1:1(0) ack 1 win 320 <sack 1001:2001,nop,nop> + +0 > . 10001:11001(1000) ack 1 + +// Limited transmit: on second dupack, send a new data segment. + +.01 < . 1:1(0) ack 1 win 320 <sack 1001:3001,nop,nop> + +0 > . 11001:12001(1000) ack 1 + +// It turned out to be reordering, not loss. + +.01 < . 1:1(0) ack 3001 win 320 + +0 > P. 12001:14001(2000) ack 1 + + +.02 < . 1:1(0) ack 5001 win 320 + +0 > P. 14001:15001(1000) ack 1 + +// Client gradually ACKs all data. + +.02 < . 1:1(0) ack 7001 win 320 + +.02 < . 1:1(0) ack 9001 win 320 + +.02 < . 1:1(0) ack 11001 win 320 + +.02 < . 1:1(0) ack 13001 win 320 + +.02 < . 1:1(0) ack 15001 win 320 + +// Clean up. + +.17 close(4) = 0 + +0 > F. 15001:15001(0) ack 1 + +.1 < F. 1:1(0) ack 15002 win 257 + +0 > . 15002:15002(0) ack 2 diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt new file mode 100644 index 000000000000..7adae7a9ef4a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_https_client.pkt @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +// This is a test inspired by an Android client app using SSL. This +// test verifies using TCP_NODELAY would save application latency +// (Perhaps even better with TCP_NAGLE). +// +`./defaults.sh +ethtool -K tun0 tso off gso off +./set_sysctls.py /proc/sys/net/ipv4/tcp_timestamps=0` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 + +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + + +0 connect(4, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < S. 0:0(0) ack 1 win 5792 <mss 974,nop,nop,sackOK,nop,wscale 7> + +0 > . 1:1(0) ack 1 + +// SSL handshake (resumed session) + +0 write(4, ..., 517) = 517 + +0 > P. 1:518(517) ack 1 + +.1 < . 1:1(0) ack 518 win 229 + + +0 < P. 1:144(143) ack 1 win 229 + +0 > . 518:518(0) ack 144 + +0 read(4, ..., 1000) = 143 + +// Application POST header (51B) and body (2002B) + +0 write(4, ..., 51) = 51 + +0 > P. 518:569(51) ack 144 + +.03 write(4, ..., 2002) = 2002 + +0 > . 569:1543(974) ack 144 + +0 > P. 1543:2517(974) ack 144 +// Without disabling Nagle, this packet will not happen until the remote ACK. + +0 > P. 2517:2571(54) ack 144 + + +.1 < . 1:1(0) ack 2571 win 229 + +// Reset sysctls +`/tmp/sysctl_restore_${PPID}.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt new file mode 100644 index 000000000000..fa9c01813996 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_sendmsg_msg_more.pkt @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test the MSG_MORE flag will correctly corks the tiny writes +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 +// Disable Nagle by default on this socket. + +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + +// Test the basic case: MSG_MORE overwrites TCP_NODELAY and enables Nagle. + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 40}], msg_flags=0}, MSG_MORE) = 40 + +.21~+.215 > P. 1:41(40) ack 1 + +.01 < . 1:1(0) ack 41 win 257 + +// Test unsetting MSG_MORE releases the packet + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 100}], msg_flags=0}, MSG_MORE) = 100 ++.005 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 160}], msg_flags=0}, MSG_MORE) = 160 + +.01 sendmsg(4, {msg_name(...)=..., + msg_iov(3)=[{..., 100}, {..., 200}, {..., 195}], + msg_flags=0}, MSG_MORE) = 495 ++.008 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 5}], msg_flags=0}, 0) = 5 + +0 > P. 41:801(760) ack 1 + +.02 < . 1:1(0) ack 801 win 257 + + +// Test >MSS write will unleash MSS packets but hold on the remaining data. + +.1 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 3100}], msg_flags=0}, MSG_MORE) = 3100 + +0 > . 801:3801(3000) ack 1 ++.003 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 50}], msg_flags=0}, MSG_MORE) = 50 + + +.01 < . 1:1(0) ack 2801 win 257 +// Err... we relase the remaining right after the ACK? note that PUSH is reset + +0 > . 3801:3951(150) ack 1 + +// Test we'll hold on the subsequent writes when inflight (3801:3951) > 0 ++.001 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 1}], msg_flags=0}, MSG_MORE) = 1 ++.002 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 2}], msg_flags=0}, MSG_MORE) = 2 ++.003 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 3}], msg_flags=0}, MSG_MORE) = 3 ++.004 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 4}], msg_flags=0}, MSG_MORE) = 4 + +.02 < . 1:1(0) ack 3951 win 257 + +0 > . 3951:3961(10) ack 1 + +.02 < . 1:1(0) ack 3961 win 257 + + +// Test the case a MSG_MORE send followed by a write flushes the data + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(1)=[{..., 20}], msg_flags=0}, MSG_MORE) = 20 + +.05 write(4, ..., 20) = 20 + +0 > P. 3961:4001(40) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt b/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt new file mode 100644 index 000000000000..0ddec5f7dc1a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_nagle_sockopt_cork_nodelay.pkt @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP_CORK and TCP_NODELAY sockopt behavior +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 +// Set TCP_CORK sockopt to hold small packets + +0 setsockopt(4, SOL_TCP, TCP_CORK, [1], 4) = 0 + + +0 write(4, ..., 40) = 40 + +.05 write(4, ..., 40) = 40 + +// Unset TCP_CORK should push pending bytes out + +.01 setsockopt(4, SOL_TCP, TCP_CORK, [0], 4) = 0 + +0 > P. 1:81(80) ack 1 + +.01 < . 1:1(0) ack 81 win 257 + +// Set TCP_CORK sockopt to hold small packets + +0 setsockopt(4, SOL_TCP, TCP_CORK, [1], 4) = 0 + + +0 write(4, ..., 40) = 40 + +.05 write(4, ..., 40) = 40 + +// Set TCP_NODELAY sockopt should push pending bytes out + +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + +0 > P. 81:161(80) ack 1 + +.01 < . 1:1(0) ack 161 win 257 + +// Set MSG_MORE to hold small packets + +0 send(4, ..., 40, MSG_MORE) = 40 + +.05 send(4, ..., 40, MSG_MORE) = 40 + +// Set TCP_NODELAY sockopt should push pending bytes out + +.01 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + +0 > . 161:241(80) ack 1 + +.01 < . 1:1(0) ack 241 win 257 diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt new file mode 100644 index 000000000000..310ef31518da --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-route-refresh-ip-tos.pkt @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +// Verify that setsockopt calls that force a route refresh do not +// cause problems matching SACKs with packets in the write queue. +// This variant tests IP_TOS. + +`./defaults.sh` + +// Establish a connection. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_IP, IP_MTU_DISCOVER, [IP_PMTUDISC_DONT], 1) = 0 + +0...0.010 connect(3, ..., ...) = 0 + + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.01 < S. 0:0(0) ack 1 win 65535 <mss 1460,nop,wscale 2,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 + + +.01 write(3, ..., 5840) = 5840 + +0 > P. 1:5841(5840) ack 1 + +.01 < . 1:1(0) ack 5841 win 65535 + + +.01 write(3, ..., 5840) = 5840 + +0 > P. 5841:11681(5840) ack 1 + +.01 < . 1:1(0) ack 11681 win 65535 + + +.01 write(3, ..., 14600) = 14600 + +0 > P. 11681:26281(14600) ack 1 + +// Try the socket option that we know can force a route refresh. + +0 setsockopt(3, SOL_IP, IP_TOS, [4], 1) = 0 +// Then revert to avoid routing/mangling/etc implications of that setting. + +0 setsockopt(3, SOL_IP, IP_TOS, [0], 1) = 0 + +// Verify that we do not retransmit the SACKed segments. + +.01 < . 1:1(0) ack 13141 win 65535 <sack 16061:17521 20441:26281,nop,nop> + +0 > . 13141:16061(2920) ack 1 + +0 > P. 17521:20441(2920) ack 1 + +.01 < . 1:1(0) ack 26281 win 65535 diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt new file mode 100644 index 000000000000..f185e1ac57ea --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-2-6-8-3-9-nofack.pkt @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb. +// This variant tests non-FACK SACK with SACKs coming in the order +// 2 6 8 3 9, to test what happens when we get a new SACKed range +// (for packet 3) that is on the right of an existing SACKed range +// (for packet 2). + +`./defaults.sh` + +// Establish a connection and send 10 MSS. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + + +.1 < . 1:1(0) ack 1 win 257 <sack 2001:3001,nop,nop> ++.001 < . 1:1(0) ack 1 win 257 <sack 2001:3001 6001:7001,nop,nop> ++.001 < . 1:1(0) ack 1 win 257 <sack 2001:3001 6001:7001 8001:9001,nop,nop> + +// 3 SACKed packets, so we enter Fast Recovery. + +0 > . 1:1001(1000) ack 1 + +0 %{ assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state }% + +0 %{ assert tcpi_lost == 6, tcpi_lost }% + +// SACK for 3001:4001. +// This SACK for an adjacent range causes the sender to +// shift the newly-SACKed range onto the previous skb. ++.007 < . 1:1(0) ack 1 win 257 <sack 2001:4001 6001:7001 8001:9001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 %{ assert tcpi_lost == 5, tcpi_lost }% + +0 %{ assert tcpi_reordering == 6, tcpi_reordering }% // 8001:9001 -> 3001:4001 is 6 + +// SACK for 9001:10001. + +.01 < . 1:1(0) ack 1 win 257 <sack 2001:4001 6001:7001 8001:10001,nop,nop> + +0 %{ assert tcpi_lost == 5, tcpi_lost }% + +// ACK for 1:1001 as packets from t=0.303 arrive. ++.083 < . 1:1(0) ack 1001 win 257 <sack 2001:4001 6001:7001 8001:10001,nop,nop> + +0 %{ assert tcpi_lost == 4,tcpi_lost }% + +// ACK for 1:4001 as packets from t=0.310 arrive. ++.017 < . 1:1(0) ack 4001 win 257 <sack 6001:7001 8001:10001,nop,nop> + +0 %{ assert tcpi_lost == 3,tcpi_lost }% + +// ACK for 1:7001 as packets from t=0.320 arrive. + +.01 < . 1:1(0) ack 7001 win 257 <sack 8001:10001,nop,nop> + +// ACK for all data as packets from t=0.403 arrive. + +.1 < . 1:1(0) ack 10001 win 257 + +0 %{ +assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state +assert tcpi_unacked == 0, tcpi_unacked +assert tcpi_sacked == 0, tcpi_sacked +assert tcpi_lost == 0, tcpi_lost +assert tcpi_retrans == 0, tcpi_retrans +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt new file mode 100644 index 000000000000..0093b4973934 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-3-4-8-9-fack.pkt @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb. +// This variant tests the case where we mark packets 0-4 lost, then +// get a SACK for 3, and then a SACK for 4. + +`./defaults.sh` + +// Establish a connection and send 10 MSS. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// SACK for 7001:8001. Using RACK we delay the fast retransmit. + +.1 < . 1:1(0) ack 1 win 257 <sack 7001:8001,nop,nop> +// RACK reordering timer ++.027 > . 1:1001(1000) ack 1 + +0 %{ +assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state +assert tcpi_lost == 7, tcpi_lost # RACK thinks 1:7001 are lost +assert tcpi_reordering == 3, tcpi_reordering +}% + +// SACK for 3001:4001. ++.002 < . 1:1(0) ack 1 win 257 <sack 3001:4001 7001:8001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 %{ +assert tcpi_lost == 6, tcpi_lost # since 3001:4001 is no longer lost +assert tcpi_reordering == 5, tcpi_reordering # 7001:8001 -> 3001:4001 +}% + +// SACK for 4001:5001. +// This SACK for an adjacent range causes the sender to +// shift the newly-SACKed range onto the previous skb. +// It uses the RFC3517 algorithm to mark 1:3001 lost +// because >=3 higher-sequence packets are SACKed. ++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:8001,nop,nop> + +0 > . 2001:3001(1000) ack 1 + +0 %{ +assert tcpi_lost == 5,tcpi_lost # SACK/RFC3517 thinks 1:3001 are lost +}% + +// SACK for 8001:9001. ++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:9001,nop,nop> + +// SACK for 9001:10001. ++.002 < . 1:1(0) ack 1 win 257 <sack 3001:5001 7001:10001,nop,nop> + +0 > . 5001:6001(1000) ack 1 + +// To simplify clean-up, say we get an ACK for all data. + +.1 < . 1:1(0) ack 10001 win 257 + +0 %{ +assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state +assert tcpi_unacked == 0, tcpi_unacked +assert tcpi_sacked == 0, tcpi_sacked +assert tcpi_lost == 0, tcpi_lost +assert tcpi_retrans == 0, tcpi_retrans +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt new file mode 100644 index 000000000000..980a832dc81c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sack_sack-shift-sacked-7-5-6-8-9-fack.pkt @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test shifting of newly-SACKed ranges onto the previous already-SACKed skb. +// This variant tests the case where we mark packets 0-4 lost, then +// get a SACK for 5, and then a SACK for 6. + +`./defaults.sh` + +// Establish a connection and send 10 MSS. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + + +0 write(4, ..., 10000) = 10000 + +0 > P. 1:10001(10000) ack 1 + +// SACK for 7001:8001. Using RACK we delay a fast retransmit. + +.1 < . 1:1(0) ack 1 win 257 <sack 7001:8001,nop,nop> ++.027 > . 1:1001(1000) ack 1 + +0 %{ +assert tcpi_ca_state == TCP_CA_Recovery, tcpi_ca_state +assert tcpi_lost == 7,tcpi_lost # RACK thinks 1:7001 are lost +assert tcpi_reordering == 3, tcpi_reordering +}% + +// SACK for 5001:6001. + +0 < . 1:1(0) ack 1 win 257 <sack 5001:6001 7001:8001,nop,nop> + +0 > . 1001:2001(1000) ack 1 + +0 %{ +assert tcpi_lost == 6, tcpi_lost +assert tcpi_reordering == 3, tcpi_reordering # 7001:8001 -> 5001:6001 is 3 +}% + +// SACK for 6001:7001. +// This SACK for an adjacent range causes the sender to +// shift the newly-SACKed range onto the previous skb. + +0 < . 1:1(0) ack 1 win 257 <sack 5001:8001,nop,nop> + +0 > . 2001:3001(1000) ack 1 + +0 %{ assert tcpi_lost == 5, tcpi_lost }% + +// SACK for 8001:9001. + +0 < . 1:1(0) ack 1 win 257 <sack 5001:9001,nop,nop> + +0 > . 3001:4001(1000) ack 1 + +// SACK for 9001:10001. + +0 < . 1:1(0) ack 1 win 257 <sack 5001:10001,nop,nop> + +0 > . 4001:5001(1000) ack 1 + +// To simplify clean-up, say we get an ACK for all data. + +.1 < . 1:1(0) ack 10001 win 257 + +0 %{ +assert tcpi_ca_state == TCP_CA_Open, tcpi_ca_state +assert tcpi_unacked == 0, tcpi_unacked +assert tcpi_sacked == 0, tcpi_sacked +assert tcpi_lost == 0, tcpi_lost +assert tcpi_retrans == 0, tcpi_retrans +}% diff --git a/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt b/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt new file mode 100644 index 000000000000..6740859a1360 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_sendfile_sendfile-simple.pkt @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +// Simplest possible test of open() and then sendfile(). +// We write some zeroes into a file (since packetdrill expects payloads +// to be all zeroes) and then open() the file, then use sendfile() +// and verify that the correct number of zeroes goes out. + +`./defaults.sh +/bin/rm -f /tmp/testfile +/bin/dd bs=1 count=5 if=/dev/zero of=/tmp/testfile status=none +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +0 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + + +0 open("/tmp/testfile", O_RDONLY) = 5 + +0 sendfile(4, 5, [0], 5) = 5 + +0 > P. 1:6(5) ack 1 diff --git a/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt b/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt new file mode 100644 index 000000000000..0cbd43253236 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_splice_tcp_splice_loop_test.pkt @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +`./defaults.sh` + +// Initialize a server socket + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_IP, IP_FREEBIND, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Connection should get accepted + +0 < S 0:0(0) win 32972 <mss 1460,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <...> + +0 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 + + +0 pipe([5, 6]) = 0 + +0 < U. 1:101(100) ack 1 win 257 urg 100 + +0 splice(4, NULL, 6, NULL, 99, 0) = 99 + +0 splice(4, NULL, 6, NULL, 1, 0) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt new file mode 100644 index 000000000000..8940726a3ec2 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_fastopen-invalid-buf-ptr.pkt @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test TCP fastopen behavior with NULL as buffer pointer, but a non-zero +// buffer length. +`./defaults.sh +./set_sysctls.py /proc/sys/net/ipv4/tcp_timestamps=0` + +// Cache warmup: send a Fast Open cookie request + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 ++0 setsockopt(3, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0 ++0 connect(3, ..., ...) = -1 EINPROGRESS (Operation is now in progress) ++0 > S 0:0(0) <mss 1460,nop,nop,sackOK,nop,wscale 8,FO,nop,nop> ++0 < S. 123:123(0) ack 1 win 14600 <mss 1460,nop,nop,sackOK,nop,wscale 6,FO abcd1234,nop,nop> ++0 > . 1:1(0) ack 1 ++0 close(3) = 0 ++0 > F. 1:1(0) ack 1 ++0 < F. 1:1(0) ack 2 win 92 ++0 > . 2:2(0) ack 2 + +// Test with MSG_FASTOPEN without TCP_FASTOPEN_CONNECT. ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 ++0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0 ++0 sendto(4, NULL, 1, MSG_FASTOPEN, ..., ...) = -1 ++0 close(4) = 0 + +// Test with TCP_FASTOPEN_CONNECT without MSG_FASTOPEN. ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 5 ++0 fcntl(5, F_SETFL, O_RDWR|O_NONBLOCK) = 0 ++0 setsockopt(5, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0 ++0 connect(5, ..., ...) = 0 ++0 sendto(5, NULL, 1, 0, ..., ...) = -1 ++0 close(5) = 0 + +// Test with both TCP_FASTOPEN_CONNECT and MSG_FASTOPEN. ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 6 ++0 fcntl(6, F_SETFL, O_RDWR|O_NONBLOCK) = 0 ++0 setsockopt(6, SOL_TCP, TCP_FASTOPEN_CONNECT, [1], 4) = 0 ++0 connect(6, ..., ...) = 0 ++0 sendto(6, NULL, 1, MSG_FASTOPEN, ..., ...) = -1 ++0 close(6) = 0 + +`/tmp/sysctl_restore_${PPID}.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt new file mode 100644 index 000000000000..b2b2cdf27e20 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that we correctly skip zero-length IOVs. +`./defaults.sh` + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 257 + +0 accept(3, ..., ...) = 4 + +0 setsockopt(4, SOL_TCP, TCP_NODELAY, [1], 4) = 0 + + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(4)=[{..., 0}, {..., 40}, {..., 0}, {..., 20}], + msg_flags=0}, 0) = 60 + +0 > P. 1:61(60) ack 1 + +.01 < . 1:1(0) ack 61 win 257 + + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(4)=[{..., 0}, {..., 0}, {..., 0}, {..., 0}], + msg_flags=0}, MSG_ZEROCOPY) = 0 + + +0 sendmsg(4, {msg_name(...)=..., + msg_iov(4)=[{..., 0}, {..., 10}, {..., 0}, {..., 50}], + msg_flags=0}, MSG_ZEROCOPY) = 60 + +0 > P. 61:121(60) ack 1 + +.01 < . 1:1(0) ack 121 win 257 diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt new file mode 100644 index 000000000000..59f5903f285c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_syscall-invalid-buf-ptr.pkt @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test kernel behavior with NULL as buffer pointer + +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.2 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + + +0 write(4, NULL, 1000) = -1 EFAULT (Bad address) + +0 send(4, NULL, 1000, 0) = -1 EFAULT (Bad address) + +0 sendto(4, NULL, 1000, 0, ..., ...) = -1 EFAULT (Bad address) + + +0 < . 1:1001(1000) ack 1 win 200 + +0 read(4, NULL, 1000) = -1 EFAULT (Bad address) + +0 recv(4, NULL, 1000, 0) = -1 EFAULT (Bad address) + +0 recvfrom(4, NULL, 1000, 0, ..., ...) = -1 EFAULT (Bad address) diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt new file mode 100644 index 000000000000..d7fdb43a8e89 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-last_data_recv.pkt @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test tcpi_last_data_recv for active session +`./defaults.sh` + +// Create a socket and set it to non-blocking. ++0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 ++0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) ++0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + ++0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) ++0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> ++.030 < S. 0:0(0) ack 1 win 10000 <mss 1000,sackOK,nop,nop,nop,wscale 8> ++0 > . 1:1(0) ack 1 + ++1 %{ assert 990 <= tcpi_last_data_recv <= 1010, tcpi_last_data_recv }% + ++0 < . 1:1001(1000) ack 1 win 300 ++0 > . 1:1(0) ack 1001 + ++0 %{ assert tcpi_last_data_recv <= 10, tcpi_last_data_recv }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt new file mode 100644 index 000000000000..a9bcd46f6cb6 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-rwnd-limited.pkt @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test rwnd limited time in tcp_info for client side. + +`./defaults.sh` + +// Create a socket and set it to non-blocking. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +// Server advertises 0 receive window. + +.01 < S. 0:0(0) ack 1 win 0 <mss 1000,nop,nop,sackOK> + + +0 > . 1:1(0) ack 1 + +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0 + +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking + +// Make sure that initial rwnd limited time is 0. + +0 %{ assert tcpi_rwnd_limited == 0, tcpi_rwnd_limited }% + +// Receive window limited time starts here. + +0 write(3, ..., 1000) = 1000 + +// Check that rwnd limited time in tcp_info is around 0.1s. + +.1 %{ assert 98000 <= tcpi_rwnd_limited <= 110000, tcpi_rwnd_limited }% + +// Server opens the receive window. + +.1 < . 1:1(0) ack 1 win 2000 + +// Check that rwnd limited time in tcp_info is around 0.2s. + +0 %{ assert 198000 <= tcpi_rwnd_limited <= 210000, tcpi_rwnd_limited }% + + +0 > P. 1:1001(1000) ack 1 + +// Server advertises a very small receive window. + +.03 < . 1:1(0) ack 1001 win 10 + +// Receive window limited time starts again. + +0 write(3, ..., 1000) = 1000 + +// Server opens the receive window again. + +.1 < . 1:1(0) ack 1001 win 2000 +// Check that rwnd limited time in tcp_info is around 0.3s +// and busy time is 0.3 + 0.03 (server opened small window temporarily). + +0 %{ assert 298000 <= tcpi_rwnd_limited <= 310000, tcpi_rwnd_limited;\ + assert 328000 <= tcpi_busy_time <= 340000, tcpi_busy_time;\ +}% + + +0 > P. 1001:2001(1000) ack 1 + +.02 < . 1:1(0) ack 2001 win 2000 + +0 %{ assert 348000 <= tcpi_busy_time <= 360000, tcpi_busy_time }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt new file mode 100644 index 000000000000..f0de2acd0f8e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_tcp_info_tcp-info-sndbuf-limited.pkt @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test send-buffer-limited time in tcp_info for client side. +`./defaults.sh` + +// Create a socket and set it to non-blocking. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.01 < S. 0:0(0) ack 1 win 10000 <mss 1000,sackOK,nop,nop,nop,wscale 8> + +0 > . 1:1(0) ack 1 + +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0 + +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking + +0 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [10000], 4) = 0 + +0 getsockopt(3, SOL_SOCKET, SO_SNDBUF, [20000], [4]) = 0 + + +.09...0.14 write(3, ..., 150000) = 150000 + + +.01 < . 1:1(0) ack 10001 win 10000 + + +.01 < . 1:1(0) ack 30001 win 10000 + +// cwnd goes from 40(60KB) to 80(120KB), and that we hit the tiny sndbuf limit 10KB + +.01 < . 1:1(0) ack 70001 win 10000 + + +.02 < . 1:1(0) ack 95001 win 10000 + +0 %{ assert 19000 <= tcpi_sndbuf_limited <= 21000, tcpi_sndbuf_limited; \ + assert 49000 <= tcpi_busy_time <= 52000, tcpi_busy_time; \ + assert 0 == tcpi_rwnd_limited, tcpi_rwnd_limited }% + +// This ack frees up enough buffer so we are no longer +// buffer limited (socket flag SOCK_NOSPACE is cleared) + +.02 < . 1:1(0) ack 150001 win 10000 + +0 %{ assert 19000 <= tcpi_sndbuf_limited <= 21000, tcpi_sndbuf_limited;\ + assert 69000 <= tcpi_busy_time <= 73000, tcpi_busy_time;\ + assert 0 == tcpi_rwnd_limited, tcpi_rwnd_limited }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt new file mode 100644 index 000000000000..2087ec0c746a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_client-only-last-byte.pkt @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that tx timestamping sends timestamps only for +// the last byte of each sendmsg. +`./defaults.sh +` + +// Create a socket and set it to non-blocking. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +// Establish connection and verify that there was no error. + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.01 < S. 0:0(0) ack 1 win 20000 <mss 1000,nop,nop,sackOK> + +0 > . 1:1(0) ack 1 + +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0 + +0 fcntl(3, F_SETFL, O_RDWR) = 0 // set back to blocking + + +0 setsockopt(3, SOL_SOCKET, SO_TIMESTAMPING, + [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_ID], 4) = 0 + + +0 write(3, ..., 11000) = 11000 + +0 > P. 1:10001(10000) ack 1 + +.01 < . 1:1(0) ack 10001 win 4000 + +0 > P. 10001:11001(1000) ack 1 + +.01 < . 1:1(0) ack 11001 win 4000 + +// Make sure that internal TCP timestamps are not overwritten and we have sane +// RTT measurement. + +0 %{ +assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt +}% + +// SCM_TSTAMP_SCHED for the last byte should be received almost immediately +// once 10001 is acked at t=20ms. +// setsockopt(..., [SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_OPT_ID], ...) +// is called after when SYN is acked. So, we expect the last byte of the first +// chunk to have a timestamp key of 10999 (i.e., 11000 - 1). + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SCHED, + ee_data=10999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SND for the last byte should be received almost immediately +// once 10001 is acked at t=20ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SND, + ee_data=10999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_ACK for the last byte should be received at t=30ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=30000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_ACK, + ee_data=10999}} + ]}, MSG_ERRQUEUE) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt new file mode 100644 index 000000000000..876024a31110 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_partial.pkt @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test tx timestamping for partial writes (IPv4). +`./defaults.sh +` + +// Create a socket and set it to non-blocking. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 fcntl(3, F_GETFL) = 0x2 (flags O_RDWR) + +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 + +// Establish connection and verify that there was no error. + +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) + +0 > S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8> + +.01 < S. 0:0(0) ack 1 win 2000 <mss 1000,sackOK,TS val 700 ecr 100,nop,wscale 7> + +0 > . 1:1(0) ack 1 <nop,nop,TS val 200 ecr 700> + +0 getsockopt(3, SOL_SOCKET, SO_ERROR, [0], [4]) = 0 + + +0 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [1000], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_TIMESTAMPING, + [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_ID], 4) = 0 + +// We have a partial write. + +0 write(3, ..., 10000) = 2964 + +0 > . 1:989(988) ack 1 <nop,nop,TS val 110 ecr 700> + +0 > P. 989:1977(988) ack 1 <nop,nop,TS val 110 ecr 700> + +.01 < . 1:1(0) ack 1977 win 92 <nop,nop,TS val 800 ecr 200> + +0 > P. 1977:2965(988) ack 1 <nop,nop,TS val 114 ecr 800> + +.01 < . 1:1(0) ack 2965 win 92 <nop,nop,TS val 800 ecr 200> + +// Make sure that internal TCP timestamps are not overwritten and we have sane +// RTT measurement. + +0 %{ +assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt +}% + +// SCM_TSTAMP_SCHED for the first chunk should be received almost immediately +// after the first ack at t=20ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SCHED, + ee_data=2963}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SND for the first chunk should be received almost immediately +// after the first ack at t=20ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SND, + ee_data=2963}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_ACK for the first chunk should be received after the last ack at +// t=30ms. + +0 recvmsg(3, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=30000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_ACK, + ee_data=2963}} + ]}, MSG_ERRQUEUE) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt b/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt new file mode 100644 index 000000000000..84d94780e6be --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_timestamping_server.pkt @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test tx timestamping for server-side (IPv4). +`./defaults.sh +` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.01 < . 1:1(0) ack 1 win 514 + + +0 accept(3, ..., ...) = 4 + +0 setsockopt(4, SOL_SOCKET, SO_TIMESTAMPING, + [SOF_TIMESTAMPING_TX_SCHED | SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_ACK | SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_ID], 4) = 0 + +// Write two 2KB chunks. +// setsockopt(..., [SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_OPT_ID], ...) +// is called after when SYN is acked. So, we expect the last byte of the first +// and the second chunks to have timestamp keys of 1999 (i.e., 2000 - 1) and +// 3999 (i.e., 4000 - 1) respectively. + +0 write(4, ..., 2000) = 2000 + +0 write(4, ..., 2000) = 2000 + +0 > P. 1:2001(2000) ack 1 + +0 > P. 2001:4001(2000) ack 1 + +.01 < . 1:1(0) ack 2001 win 514 + +.01 < . 1:1(0) ack 4001 win 514 + +// Make sure that internal TCP timestamps are not overwritten and we have sane +// RTT measurement. + +0 %{ +assert 5000 <= tcpi_rtt <= 20000, 'srtt=%d us' % tcpi_rtt +}% + +// SCM_TSTAMP_SCHED for the first chunk should be received almost immediately +// after write at t=10ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=10000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SCHED, + ee_data=1999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SND for the first chunk should be received almost immediately +// after write at t=10ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=10000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SND, + ee_data=1999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SCHED for the second chunk should be received almost immediately +// after that at t=10ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=10000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SCHED, + ee_data=3999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_SND for the second chunk should be received almost immediately +// after that at t=10ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=10000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_SND, + ee_data=3999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_ACK for the first chunk should be received at t=20ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=20000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_ACK, + ee_data=1999}} + ]}, MSG_ERRQUEUE) = 0 +// SCM_TSTAMP_ACK for the second chunk should be received at t=30ms. + +0 recvmsg(4, {msg_name(...)=..., + msg_iov(1)=[{...,0}], + msg_flags=MSG_ERRQUEUE|MSG_TRUNC, + msg_control=[ + {cmsg_level=SOL_SOCKET, + cmsg_type=SCM_TIMESTAMPING, + cmsg_data={scm_sec=0,scm_nsec=30000000}}, + {cmsg_level=CMSG_LEVEL_IP, + cmsg_type=CMSG_TYPE_RECVERR, + cmsg_data={ee_errno=ENOMSG, + ee_origin=SO_EE_ORIGIN_TIMESTAMPING, + ee_type=0, + ee_code=0, + ee_info=SCM_TSTAMP_ACK, + ee_data=3999}} + ]}, MSG_ERRQUEUE) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt new file mode 100644 index 000000000000..e61424a7bd0a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_fin_tsval.pkt @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that we send FIN packet with correct TSval +--tcp_ts_tick_usecs=1000 +--tolerance_usecs=7000 + +`./defaults.sh` + +// Create a socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Establish a connection. + +0 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0> + +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100> + +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100> + +0 accept(3, ..., ...) = 4 + + +1 close(4) = 0 +// Check that FIN TSval is updated properly, one second has passed since last sent packet. + +0 > F. 1:1(0) ack 1 <nop,nop,TS val 1200 ecr 200> diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt new file mode 100644 index 000000000000..174ce9a1bfc0 --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_invalid_ack.pkt @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that we reject TS val updates on a packet with invalid ACK sequence + +`./defaults.sh +` + +// Create a socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Establish a connection. + +.1 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0> + +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100> + +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100> + +0 accept(3, ..., ...) = 4 + +// bad packet with high tsval (its ACK sequence is above our sndnxt) + +0 < F. 1:1(0) ack 9999 win 20000 <nop,nop,TS val 200000 ecr 100> + + + +0 < . 1:1001(1000) ack 1 win 20000 <nop,nop,TS val 201 ecr 100> + +0 > . 1:1(0) ack 1001 <nop,nop,TS val 200 ecr 201> diff --git a/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt new file mode 100644 index 000000000000..2e3b3bb7493a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ts_recent_reset_tsval.pkt @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test that we send RST packet with correct TSval +--tcp_ts_tick_usecs=1000 + +`./defaults.sh` + +// Create a socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Establish a connection. + +0 < S 0:0(0) win 20000 <mss 1000,sackOK,TS val 100 ecr 0> + +0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 100 ecr 100> + +.1 < . 1:1(0) ack 1 win 20000 <nop,nop,TS val 200 ecr 100> + +0 accept(3, ..., ...) = 4 + + +0 < . 1:1001(1000) ack 1 win 20000 <nop,nop,TS val 201 ecr 100> + +0 > . 1:1(0) ack 1001 <nop,nop,TS val 200 ecr 201> + + +1 close(4) = 0 +// Check that RST TSval is updated properly, one second has passed since last sent packet. + +0 > R. 1:1(0) ack 1001 <nop,nop,TS val 1200 ecr 201> diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt new file mode 100644 index 000000000000..183051ba0cae --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 + +`./defaults.sh` + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + + +0 < S 0:0(0) win 0 <mss 1460> + +0 > S. 0:0(0) ack 1 <mss 1460> + + +.1 < . 1:1(0) ack 1 win 65530 + +0 accept(3, ..., ...) = 4 + + +0 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0 + +0 write(4, ..., 24) = 24 + +0 > P. 1:25(24) ack 1 + +.1 < . 1:1(0) ack 25 win 65530 + +0 %{ assert tcpi_probes == 0, tcpi_probes; \ + assert tcpi_backoff == 0, tcpi_backoff }% + +// install a qdisc dropping all packets + +0 `tc qdisc delete dev tun0 root 2>/dev/null ; tc qdisc add dev tun0 root pfifo limit 0` + +0 write(4, ..., 24) = 24 + // When qdisc is congested we retry every 500ms + // (TCP_RESOURCE_PROBE_INTERVAL) and therefore + // we retry 6 times before hitting 3s timeout. + // First verify that the connection is alive: ++3.250 write(4, ..., 24) = 24 + // Now verify that shortly after that the socket is dead: + +.100 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out) + + +0 %{ assert tcpi_probes == 6, tcpi_probes; \ + assert tcpi_backoff == 0, tcpi_backoff }% + +0 close(4) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt new file mode 100644 index 000000000000..2efe02bfba9c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user_timeout.pkt @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +`./defaults.sh` + +// Initialize connection + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +.1 < . 1:1(0) ack 1 win 32792 + + + +0 accept(3, ..., ...) = 4 + +// Okay, we received nothing, and decide to close this idle socket. +// We set TCP_USER_TIMEOUT to 3 seconds because really it is not worth +// trying hard to cleanly close this flow, at the price of keeping +// a TCP structure in kernel for about 1 minute ! + +2 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0 + +0 close(4) = 0 + + +0 > F. 1:1(0) ack 1 + +.3~+.400 > F. 1:1(0) ack 1 + +.3~+.400 > F. 1:1(0) ack 1 + +.6~+.800 > F. 1:1(0) ack 1 + +// We finally receive something from the peer, but it is way too late +// Our socket vanished because TCP_USER_TIMEOUT was really small + +0 < . 1:2(1) ack 1 win 32792 + +0 > R 1:1(0) diff --git a/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt b/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt new file mode 100644 index 000000000000..8bd60226ccfc --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_validate_validate-established-no-flags.pkt @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +// Verify that established connections drop a segment without the ACK flag set. + +`./defaults.sh` + +// Create a socket. + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +// Establish a connection. + +0 < S 0:0(0) win 20000 <mss 1000,sackOK,nop,nop> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +.01 < . 1:1(0) ack 1 win 20000 + +0 accept(3, ..., ...) = 4 + +// Receive a segment with no flags set, verify that it's not enqueued. + +.01 < - 1:1001(1000) win 20000 + +0 ioctl(4, SIOCINQ, [0]) = 0 + +// Receive a segment with ACK flag set, verify that it is enqueued. + +.01 < . 1:1001(1000) ack 1 win 20000 + +0 ioctl(4, SIOCINQ, [1000]) = 0 diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 1a706d03bb6b..9a85f93c33d8 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -44,9 +44,11 @@ struct tls_crypto_info_keys { }; static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, - struct tls_crypto_info_keys *tls12) + struct tls_crypto_info_keys *tls12, + char key_generation) { - memset(tls12, 0, sizeof(*tls12)); + memset(tls12, key_generation, sizeof(*tls12)); + memset(tls12, 0, sizeof(struct tls_crypto_info)); switch (cipher_type) { case TLS_CIPHER_CHACHA20_POLY1305: @@ -275,7 +277,7 @@ TEST_F(tls_basic, recseq_wrap) if (self->notls) SKIP(return, "no TLS support"); - tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12, 0); memset(&tls12.aes128.rec_seq, 0xff, sizeof(tls12.aes128.rec_seq)); ASSERT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); @@ -391,7 +393,7 @@ FIXTURE_SETUP(tls) SKIP(return, "Unsupported cipher in FIPS mode"); tls_crypto_info_init(variant->tls_version, variant->cipher_type, - &tls12); + &tls12, 0); ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); @@ -1175,7 +1177,7 @@ TEST_F(tls, bidir) struct tls_crypto_info_keys tls12; tls_crypto_info_init(variant->tls_version, variant->cipher_type, - &tls12); + &tls12, 0); ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, tls12.len); @@ -1614,7 +1616,7 @@ TEST_F(tls, getsockopt) EXPECT_EQ(get.crypto_info.cipher_type, variant->cipher_type); /* get the full crypto_info */ - tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &expect, 0); len = expect.len; memrnd(&get, sizeof(get)); EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &get, &len), 0); @@ -1668,6 +1670,464 @@ TEST_F(tls, recv_efault) EXPECT_EQ(memcmp(rec2, recv_mem + 9, ret - 9), 0); } +#define TLS_RECORD_TYPE_HANDSHAKE 0x16 +/* key_update, length 1, update_not_requested */ +static const char key_update_msg[] = "\x18\x00\x00\x01\x00"; +static void tls_send_keyupdate(struct __test_metadata *_metadata, int fd) +{ + size_t len = sizeof(key_update_msg); + + EXPECT_EQ(tls_send_cmsg(fd, TLS_RECORD_TYPE_HANDSHAKE, + (char *)key_update_msg, len, 0), + len); +} + +static void tls_recv_keyupdate(struct __test_metadata *_metadata, int fd, int flags) +{ + char buf[100]; + + EXPECT_EQ(tls_recv_cmsg(_metadata, fd, TLS_RECORD_TYPE_HANDSHAKE, buf, sizeof(buf), flags), + sizeof(key_update_msg)); + EXPECT_EQ(memcmp(buf, key_update_msg, sizeof(key_update_msg)), 0); +} + +/* set the key to 0 then 1 for RX, immediately to 1 for TX */ +TEST_F(tls_basic, rekey_rx) +{ + struct tls_crypto_info_keys tls12_0, tls12_1; + char const *test_str = "test_message"; + int send_len = strlen(test_str) + 1; + char buf[20]; + int ret; + + if (self->notls) + return; + + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls12_0, 0); + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls12_1, 1); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_1, tls12_1.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_0, tls12_0.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_1, tls12_1.len); + EXPECT_EQ(ret, 0); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + +/* set the key to 0 then 1 for TX, immediately to 1 for RX */ +TEST_F(tls_basic, rekey_tx) +{ + struct tls_crypto_info_keys tls12_0, tls12_1; + char const *test_str = "test_message"; + int send_len = strlen(test_str) + 1; + char buf[20]; + int ret; + + if (self->notls) + return; + + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls12_0, 0); + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls12_1, 1); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_0, tls12_0.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_1, tls12_1.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_1, tls12_1.len); + EXPECT_EQ(ret, 0); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +} + +TEST_F(tls, rekey) +{ + char const *test_str_1 = "test_message_before_rekey"; + char const *test_str_2 = "test_message_after_rekey"; + struct tls_crypto_info_keys tls12; + int send_len; + char buf[100]; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + /* initial send/recv */ + send_len = strlen(test_str_1) + 1; + EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + /* send after rekey */ + send_len = strlen(test_str_2) + 1; + EXPECT_EQ(send(self->fd, test_str_2, send_len, 0), send_len); + + /* can't receive the KeyUpdate without a control message */ + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* recv blocking -> -EKEYEXPIRED */ + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* recv non-blocking -> -EKEYEXPIRED */ + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* update RX key */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + /* recv after rekey */ + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str_2, send_len), 0); +} + +TEST_F(tls, rekey_fail) +{ + char const *test_str_1 = "test_message_before_rekey"; + char const *test_str_2 = "test_message_after_rekey"; + struct tls_crypto_info_keys tls12; + int send_len; + char buf[100]; + + /* initial send/recv */ + send_len = strlen(test_str_1) + 1; + EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + + if (variant->tls_version != TLS_1_3_VERSION) { + /* just check that rekey is not supported and return */ + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1); + EXPECT_EQ(errno, EBUSY); + return; + } + + /* successful update */ + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + /* invalid update: change of version */ + tls_crypto_info_init(TLS_1_2_VERSION, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1); + EXPECT_EQ(errno, EINVAL); + + /* invalid update (RX socket): change of version */ + tls_crypto_info_init(TLS_1_2_VERSION, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), -1); + EXPECT_EQ(errno, EINVAL); + + /* invalid update: change of cipher */ + if (variant->cipher_type == TLS_CIPHER_AES_GCM_256) + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_CHACHA20_POLY1305, &tls12, 1); + else + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_256, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), -1); + EXPECT_EQ(errno, EINVAL); + + /* send after rekey, the invalid updates shouldn't have an effect */ + send_len = strlen(test_str_2) + 1; + EXPECT_EQ(send(self->fd, test_str_2, send_len, 0), send_len); + + /* can't receive the KeyUpdate without a control message */ + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* recv blocking -> -EKEYEXPIRED */ + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* recv non-blocking -> -EKEYEXPIRED */ + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* update RX key */ + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + /* recv after rekey */ + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str_2, send_len), 0); +} + +TEST_F(tls, rekey_peek) +{ + char const *test_str_1 = "test_message_before_rekey"; + struct tls_crypto_info_keys tls12; + int send_len; + char buf[100]; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + send_len = strlen(test_str_1) + 1; + EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + /* can't receive the KeyUpdate without a control message */ + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_PEEK), -1); + + /* peek KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, MSG_PEEK); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* update RX key */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); +} + +TEST_F(tls, splice_rekey) +{ + int send_len = TLS_PAYLOAD_MAX_LEN / 2; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + struct tls_crypto_info_keys tls12; + int p[2]; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); + + /* can't splice the KeyUpdate */ + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), -1); + EXPECT_EQ(errno, EINVAL); + + /* peek KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, MSG_PEEK); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* can't splice before updating the key */ + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), -1); + EXPECT_EQ(errno, EKEYEXPIRED); + + /* update RX key */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, rekey_peek_splice) +{ + char const *test_str_1 = "test_message_before_rekey"; + struct tls_crypto_info_keys tls12; + int send_len; + char buf[100]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int p[2]; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + ASSERT_GE(pipe(p), 0); + + send_len = strlen(test_str_1) + 1; + EXPECT_EQ(send(self->fd, test_str_1, send_len, 0), send_len); + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(memcmp(buf, test_str_1, send_len), 0); + + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, TLS_PAYLOAD_MAX_LEN, 0), send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_recv, test_str_1, send_len), 0); +} + +TEST_F(tls, rekey_getsockopt) +{ + struct tls_crypto_info_keys tls12; + struct tls_crypto_info_keys tls12_get; + socklen_t len; + + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 0); + + len = tls12.len; + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_get, &len), 0); + EXPECT_EQ(len, tls12.len); + EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0); + + len = tls12.len; + EXPECT_EQ(getsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_get, &len), 0); + EXPECT_EQ(len, tls12.len); + EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0); + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + tls_recv_keyupdate(_metadata, self->cfd, 0); + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + len = tls12.len; + EXPECT_EQ(getsockopt(self->fd, SOL_TLS, TLS_TX, &tls12_get, &len), 0); + EXPECT_EQ(len, tls12.len); + EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0); + + len = tls12.len; + EXPECT_EQ(getsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12_get, &len), 0); + EXPECT_EQ(len, tls12.len); + EXPECT_EQ(memcmp(&tls12_get, &tls12, tls12.len), 0); +} + +TEST_F(tls, rekey_poll_pending) +{ + char const *test_str = "test_message_after_rekey"; + struct tls_crypto_info_keys tls12; + struct pollfd pfd = { }; + int send_len; + int ret; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + /* send immediately after rekey */ + send_len = strlen(test_str) + 1; + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + + /* key hasn't been updated, expect cfd to be non-readable */ + pfd.fd = self->cfd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + + ret = fork(); + ASSERT_GE(ret, 0); + + if (ret) { + int pid2, status; + + /* wait before installing the new key */ + sleep(1); + + /* update RX key while poll() is sleeping */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + pid2 = wait(&status); + EXPECT_EQ(pid2, ret); + EXPECT_EQ(status, 0); + } else { + pfd.fd = self->cfd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5000), 1); + + exit(!__test_passed(_metadata)); + } +} + +TEST_F(tls, rekey_poll_delay) +{ + char const *test_str = "test_message_after_rekey"; + struct tls_crypto_info_keys tls12; + struct pollfd pfd = { }; + int send_len; + int ret; + + if (variant->tls_version != TLS_1_3_VERSION) + return; + + /* update TX key */ + tls_send_keyupdate(_metadata, self->fd); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12, 1); + EXPECT_EQ(setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len), 0); + + /* get KeyUpdate */ + tls_recv_keyupdate(_metadata, self->cfd, 0); + + ret = fork(); + ASSERT_GE(ret, 0); + + if (ret) { + int pid2, status; + + /* wait before installing the new key */ + sleep(1); + + /* update RX key while poll() is sleeping */ + EXPECT_EQ(setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len), 0); + + sleep(1); + send_len = strlen(test_str) + 1; + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + + pid2 = wait(&status); + EXPECT_EQ(pid2, ret); + EXPECT_EQ(status, 0); + } else { + pfd.fd = self->cfd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5000), 1); + exit(!__test_passed(_metadata)); + } +} + FIXTURE(tls_err) { int fd, cfd; @@ -1696,7 +2156,7 @@ FIXTURE_SETUP(tls_err) int ret; tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128, - &tls12); + &tls12, 0); ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls); @@ -2118,7 +2578,7 @@ TEST(tls_v6ops) { int sfd, ret, fd; socklen_t len, len2; - tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12, 0); addr.sin6_family = AF_INET6; addr.sin6_addr = in6addr_any; @@ -2177,7 +2637,7 @@ TEST(prequeue) { len = sizeof(addr); memrnd(buf, sizeof(buf)); - tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls12); + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls12, 0); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(INADDR_ANY); diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index 640bc43452fa..88fa1d53ba2b 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -92,6 +92,9 @@ run_udp() { echo "udp" run_in_netns ${args} + echo "udp sendmmsg" + run_in_netns ${args} -m + echo "udp gso" run_in_netns ${args} -S 0 diff --git a/tools/testing/selftests/net/vlan_bridge_binding.sh b/tools/testing/selftests/net/vlan_bridge_binding.sh new file mode 100755 index 000000000000..e7cb8c678bde --- /dev/null +++ b/tools/testing/selftests/net/vlan_bridge_binding.sh @@ -0,0 +1,256 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +ALL_TESTS=" + test_binding_on + test_binding_off + test_binding_toggle_on + test_binding_toggle_off + test_binding_toggle_on_when_upper_down + test_binding_toggle_off_when_upper_down + test_binding_toggle_on_when_lower_down + test_binding_toggle_off_when_lower_down +" + +setup_prepare() +{ + local port + + ip_link_add br up type bridge vlan_filtering 1 + + for port in d1 d2 d3; do + ip_link_add $port type veth peer name r$port + ip_link_set_up $port + ip_link_set_up r$port + ip_link_set_master $port br + done + + bridge_vlan_add vid 11 dev br self + bridge_vlan_add vid 11 dev d1 master + + bridge_vlan_add vid 12 dev br self + bridge_vlan_add vid 12 dev d2 master + + bridge_vlan_add vid 13 dev br self + bridge_vlan_add vid 13 dev d1 master + bridge_vlan_add vid 13 dev d2 master + + bridge_vlan_add vid 14 dev br self + bridge_vlan_add vid 14 dev d1 master + bridge_vlan_add vid 14 dev d2 master + bridge_vlan_add vid 14 dev d3 master +} + +operstate_is() +{ + local dev=$1; shift + local expect=$1; shift + + local operstate=$(ip -j link show $dev | jq -r .[].operstate) + if [[ $operstate == UP ]]; then + operstate=1 + elif [[ $operstate == DOWN || $operstate == LOWERLAYERDOWN ]]; then + operstate=0 + fi + echo -n $operstate + [[ $operstate == $expect ]] +} + +check_operstate() +{ + local dev=$1; shift + local expect=$1; shift + local operstate + + operstate=$(busywait 1000 \ + operstate_is "$dev" "$expect") + check_err $? "Got operstate of $operstate, expected $expect" +} + +add_one_vlan() +{ + local link=$1; shift + local id=$1; shift + + ip_link_add $link.$id link $link type vlan id $id "$@" +} + +add_vlans() +{ + add_one_vlan br 11 "$@" + add_one_vlan br 12 "$@" + add_one_vlan br 13 "$@" + add_one_vlan br 14 "$@" +} + +set_vlans() +{ + ip link set dev br.11 "$@" + ip link set dev br.12 "$@" + ip link set dev br.13 "$@" + ip link set dev br.14 "$@" +} + +down_netdevs() +{ + local dev + + for dev in "$@"; do + ip_link_set_down $dev + done +} + +check_operstates() +{ + local opst_11=$1; shift + local opst_12=$1; shift + local opst_13=$1; shift + local opst_14=$1; shift + + check_operstate br.11 $opst_11 + check_operstate br.12 $opst_12 + check_operstate br.13 $opst_13 + check_operstate br.14 $opst_14 +} + +do_test_binding() +{ + local inject=$1; shift + local what=$1; shift + local opsts_d1=$1; shift + local opsts_d2=$1; shift + local opsts_d12=$1; shift + local opsts_d123=$1; shift + + RET=0 + + defer_scope_push + down_netdevs d1 + $inject + check_operstates $opsts_d1 + defer_scope_pop + + defer_scope_push + down_netdevs d2 + $inject + check_operstates $opsts_d2 + defer_scope_pop + + defer_scope_push + down_netdevs d1 d2 + $inject + check_operstates $opsts_d12 + defer_scope_pop + + defer_scope_push + down_netdevs d1 d2 d3 + $inject + check_operstates $opsts_d123 + defer_scope_pop + + log_test "Test bridge_binding $what" +} + +do_test_binding_on() +{ + local inject=$1; shift + local what=$1; shift + + do_test_binding "$inject" "$what" \ + "0 1 1 1" \ + "1 0 1 1" \ + "0 0 0 1" \ + "0 0 0 0" +} + +do_test_binding_off() +{ + local inject=$1; shift + local what=$1; shift + + do_test_binding "$inject" "$what" \ + "1 1 1 1" \ + "1 1 1 1" \ + "1 1 1 1" \ + "0 0 0 0" +} + +test_binding_on() +{ + add_vlans bridge_binding on + set_vlans up + do_test_binding_on : "on" +} + +test_binding_off() +{ + add_vlans bridge_binding off + set_vlans up + do_test_binding_off : "off" +} + +test_binding_toggle_on() +{ + add_vlans bridge_binding off + set_vlans up + set_vlans type vlan bridge_binding on + do_test_binding_on : "off->on" +} + +test_binding_toggle_off() +{ + add_vlans bridge_binding on + set_vlans up + set_vlans type vlan bridge_binding off + do_test_binding_off : "on->off" +} + +dfr_set_binding_on() +{ + set_vlans type vlan bridge_binding on + defer set_vlans type vlan bridge_binding off +} + +dfr_set_binding_off() +{ + set_vlans type vlan bridge_binding off + defer set_vlans type vlan bridge_binding on +} + +test_binding_toggle_on_when_lower_down() +{ + add_vlans bridge_binding off + set_vlans up + do_test_binding_on dfr_set_binding_on "off->on when lower down" +} + +test_binding_toggle_off_when_lower_down() +{ + add_vlans bridge_binding on + set_vlans up + do_test_binding_off dfr_set_binding_off "on->off when lower down" +} + +test_binding_toggle_on_when_upper_down() +{ + add_vlans bridge_binding off + set_vlans type vlan bridge_binding on + set_vlans up + do_test_binding_on : "off->on when upper down" +} + +test_binding_toggle_off_when_upper_down() +{ + add_vlans bridge_binding on + set_vlans type vlan bridge_binding off + set_vlans up + do_test_binding_off : "on->off when upper down" +} + +trap defer_scopes_cleanup EXIT +setup_prepare +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk index d43afe243779..12e7cae251be 100644 --- a/tools/testing/selftests/net/ynl.mk +++ b/tools/testing/selftests/net/ynl.mk @@ -31,7 +31,8 @@ $(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig $(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/pyynl/__pycache__ \ + $(top_srcdir)/tools/net/ynl/pyynl/lib/__pycache__ \ $(top_srcdir)/tools/net/ynl/lib/*.[ado] \ $(OUTPUT)/.libynl-*.sig \ $(OUTPUT)/libynl.a 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 37d9bf6fb745..6f4c3f5a1c5d 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 @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, * If we dispatch to a bogus DSQ that will fall back to the * builtin global DSQ, we fail gracefully. */ - scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, p->scx.dsq_vtime, 0); return cpu; } 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 dffc97d9cdf1..e4a55027778f 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, if (cpu >= 0) { /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ - scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); return cpu; } 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 6a7db1502c29..fbda6bf54671 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,9 +43,12 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - target = bpf_get_prandom_u32() % nr_cpus; + if (p->nr_cpus_allowed == nr_cpus) + target = bpf_get_prandom_u32() % nr_cpus; + else + target = scx_bpf_task_cpu(p); - scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); bpf_task_release(p); } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 472851b56854..0ff27e57fe43 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -34,9 +34,10 @@ static enum scx_test_status run(void *ctx) /* Just sleeping is fine, plenty of scheduling events happening */ sleep(1); - SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); bpf_link__destroy(link); + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + return SCX_TEST_PASS; } @@ -50,7 +51,7 @@ static void cleanup(void *ctx) struct scx_test dsp_local_on = { .name = "dsp_local_on", .description = "Verify we can directly dispatch tasks to a local DSQs " - "from osp.dispatch()", + "from ops.dispatch()", .setup = setup, .run = run, .cleanup = cleanup, 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 1efb50d61040..a7cf868d5e31 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 @@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, /* Can only call from ops.select_cpu() */ scx_bpf_select_cpu_dfl(p, 0, 0, &found); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index d75d4faf07f6..4bc36182d3ff 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -33,7 +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, DSQ_ID, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 4d4cd8d966db..430f5e13bf55 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -12,6 +12,8 @@ char _license[] SEC("license") = "GPL"; +#define DSQ_ID 0 + s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { @@ -20,7 +22,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) @@ -28,7 +30,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev) { - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) @@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight) s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init) { - return 0; + return scx_bpf_create_dsq(DSQ_ID, -1); } void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) 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 f171ac470970..13d0f5be788d 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, } scx_bpf_put_idle_cpumask(idle_mask); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") 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 9efdbb7da928..815f1d5d61ac 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 @@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p, saw_local = true; } - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags); } s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, 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 59bfc4f36167..4bb99699e920 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, cpu = prev_cpu; dispatch: - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0); return cpu; } 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 3bbd5fcdfb18..2a75de11b2cf 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 @@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching to a random DSQ should fail. */ - scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0); return prev_cpu; } 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 0fda57fe0ecf..99d075695c97 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 @@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching twice in a row is disallowed. */ - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); return prev_cpu; } 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 e6c67bcf5e6e..bfcb96cd4954 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -2,8 +2,8 @@ /* * A scheduler that validates that enqueue flags are properly stored and * applied at dispatch time when a task is directly dispatched from - * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and - * making the test a very basic vtime scheduler. + * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(), + * and making the test a very basic vtime scheduler. * * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. * Copyright (c) 2024 David Vernet <dvernet@meta.com> @@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p, cpu = prev_cpu; scx_bpf_test_and_clear_cpu_idle(cpu); ddsp: - scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); + scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); return cpu; } void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) { - if (scx_bpf_consume(VTIME_DSQ)) + if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) consumed = true; } diff --git a/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py b/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py new file mode 100755 index 000000000000..0f44a6199495 --- /dev/null +++ b/tools/testing/selftests/tc-testing/scripts/sfq_rejects_limit_1.py @@ -0,0 +1,21 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Script that checks that SFQ rejects a limit of 1 at the kernel +# level. We can't use iproute2's tc because it does not accept a limit +# of 1. + +import sys +import os + +from pyroute2 import IPRoute +from pyroute2.netlink.exceptions import NetlinkError + +ip = IPRoute() +ifidx = ip.link_lookup(ifname=sys.argv[1]) + +try: + ip.tc('add', 'sfq', ifidx, limit=1) + sys.exit(1) +except NetlinkError: + sys.exit(0) diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json index 996448afe31b..91d120548bf5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json @@ -78,10 +78,10 @@ "setup": [ "$TC qdisc add dev $DEV1 ingress" ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff", + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f", "expExitCode": "0", "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow", - "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass", + "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DEV1 ingress" diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json index 16d51936b385..50e8d72781cb 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json @@ -208,5 +208,25 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "4d6f", + "name": "Check that limit of 1 is rejected", + "category": [ + "qdisc", + "sfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "./scripts/sfq_rejects_limit_1.py $DUMMY", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "sfq", + "matchCount": "0", + "teardown": [ + ] } ] diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README index 84ee217ba8ee..680ce666ceb5 100644 --- a/tools/testing/vsock/README +++ b/tools/testing/vsock/README @@ -36,6 +36,21 @@ Invoke test binaries in both directions as follows: --control-port=1234 \ --peer-cid=3 +Some tests are designed to produce kernel memory leaks. Leaks detection, +however, is deferred to Kernel Memory Leak Detector. It is recommended to enable +kmemleak (CONFIG_DEBUG_KMEMLEAK=y) and explicitly trigger a scan after each test +suite run, e.g. + + # echo clear > /sys/kernel/debug/kmemleak + # $TEST_BINARY ... + # echo "wait for any grace periods" && sleep 2 + # echo scan > /sys/kernel/debug/kmemleak + # echo "wait for kmemleak" && sleep 5 + # echo scan > /sys/kernel/debug/kmemleak + # cat /sys/kernel/debug/kmemleak + +For more information see Documentation/dev-tools/kmemleak.rst. + vsock_perf utility ------------------- 'vsock_perf' is a simple tool to measure vsock performance. It works in diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c index d2deb4b15b94..0066e0324d35 100644 --- a/tools/testing/vsock/control.c +++ b/tools/testing/vsock/control.c @@ -27,6 +27,7 @@ #include "timeout.h" #include "control.h" +#include "util.h" static int control_fd = -1; @@ -50,7 +51,6 @@ void control_init(const char *control_host, for (ai = result; ai; ai = ai->ai_next) { int fd; - int val = 1; fd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol); if (fd < 0) @@ -65,11 +65,8 @@ void control_init(const char *control_host, break; } - if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, - &val, sizeof(val)) < 0) { - perror("setsockopt"); - exit(EXIT_FAILURE); - } + setsockopt_int_check(fd, SOL_SOCKET, SO_REUSEADDR, 1, + "setsockopt SO_REUSEADDR"); if (bind(fd, ai->ai_addr, ai->ai_addrlen) < 0) goto next; diff --git a/tools/testing/vsock/msg_zerocopy_common.c b/tools/testing/vsock/msg_zerocopy_common.c index 5a4bdf7b5132..8622e5a0f8b7 100644 --- a/tools/testing/vsock/msg_zerocopy_common.c +++ b/tools/testing/vsock/msg_zerocopy_common.c @@ -14,16 +14,6 @@ #include "msg_zerocopy_common.h" -void enable_so_zerocopy(int fd) -{ - int val = 1; - - if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) { - perror("setsockopt"); - exit(EXIT_FAILURE); - } -} - void vsock_recv_completion(int fd, const bool *zerocopied) { struct sock_extended_err *serr; diff --git a/tools/testing/vsock/msg_zerocopy_common.h b/tools/testing/vsock/msg_zerocopy_common.h index 3763c5ccedb9..ad14139e93ca 100644 --- a/tools/testing/vsock/msg_zerocopy_common.h +++ b/tools/testing/vsock/msg_zerocopy_common.h @@ -12,7 +12,6 @@ #define VSOCK_RECVERR 1 #endif -void enable_so_zerocopy(int fd); void vsock_recv_completion(int fd, const bool *zerocopied); #endif /* MSG_ZEROCOPY_COMMON_H */ diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index a3d448a075e3..7058dc614c25 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -401,7 +401,7 @@ void recv_buf(int fd, void *buf, size_t len, int flags, ssize_t expected_ret) */ void send_byte(int fd, int expected_ret, int flags) { - const uint8_t byte = 'A'; + static const uint8_t byte = 'A'; send_buf(fd, &byte, sizeof(byte), flags, expected_ret); } @@ -420,7 +420,7 @@ void recv_byte(int fd, int expected_ret, int flags) recv_buf(fd, &byte, sizeof(byte), flags, expected_ret); if (byte != 'A') { - fprintf(stderr, "unexpected byte read %c\n", byte); + fprintf(stderr, "unexpected byte read 0x%02x\n", byte); exit(EXIT_FAILURE); } } @@ -486,8 +486,7 @@ void list_tests(const struct test_case *test_cases) exit(EXIT_FAILURE); } -void skip_test(struct test_case *test_cases, size_t test_cases_len, - const char *test_id_str) +static unsigned long parse_test_id(const char *test_id_str, size_t test_cases_len) { unsigned long test_id; char *endptr = NULL; @@ -505,9 +504,35 @@ void skip_test(struct test_case *test_cases, size_t test_cases_len, exit(EXIT_FAILURE); } + return test_id; +} + +void skip_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str) +{ + unsigned long test_id = parse_test_id(test_id_str, test_cases_len); test_cases[test_id].skip = true; } +void pick_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str) +{ + static bool skip_all = true; + unsigned long test_id; + + if (skip_all) { + unsigned long i; + + for (i = 0; i < test_cases_len; ++i) + test_cases[i].skip = true; + + skip_all = false; + } + + test_id = parse_test_id(test_id_str, test_cases_len); + test_cases[test_id].skip = false; +} + unsigned long hash_djb2(const void *data, size_t len) { unsigned long hash = 5381; @@ -651,3 +676,145 @@ void free_test_iovec(const struct iovec *test_iovec, free(iovec); } + +/* Set "unsigned long long" socket option and check that it's indeed set */ +void setsockopt_ull_check(int fd, int level, int optname, + unsigned long long val, char const *errmsg) +{ + unsigned long long chkval; + socklen_t chklen; + int err; + + err = setsockopt(fd, level, optname, &val, sizeof(val)); + if (err) { + fprintf(stderr, "setsockopt err: %s (%d)\n", + strerror(errno), errno); + goto fail; + } + + chkval = ~val; /* just make storage != val */ + chklen = sizeof(chkval); + + err = getsockopt(fd, level, optname, &chkval, &chklen); + if (err) { + fprintf(stderr, "getsockopt err: %s (%d)\n", + strerror(errno), errno); + goto fail; + } + + if (chklen != sizeof(chkval)) { + fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val), + chklen); + goto fail; + } + + if (chkval != val) { + fprintf(stderr, "value mismatch: set %llu got %llu\n", val, + chkval); + goto fail; + } + return; +fail: + fprintf(stderr, "%s val %llu\n", errmsg, val); + exit(EXIT_FAILURE); +; +} + +/* Set "int" socket option and check that it's indeed set */ +void setsockopt_int_check(int fd, int level, int optname, int val, + char const *errmsg) +{ + int chkval; + socklen_t chklen; + int err; + + err = setsockopt(fd, level, optname, &val, sizeof(val)); + if (err) { + fprintf(stderr, "setsockopt err: %s (%d)\n", + strerror(errno), errno); + goto fail; + } + + chkval = ~val; /* just make storage != val */ + chklen = sizeof(chkval); + + err = getsockopt(fd, level, optname, &chkval, &chklen); + if (err) { + fprintf(stderr, "getsockopt err: %s (%d)\n", + strerror(errno), errno); + goto fail; + } + + if (chklen != sizeof(chkval)) { + fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val), + chklen); + goto fail; + } + + if (chkval != val) { + fprintf(stderr, "value mismatch: set %d got %d\n", val, chkval); + goto fail; + } + return; +fail: + fprintf(stderr, "%s val %d\n", errmsg, val); + exit(EXIT_FAILURE); +} + +static void mem_invert(unsigned char *mem, size_t size) +{ + size_t i; + + for (i = 0; i < size; i++) + mem[i] = ~mem[i]; +} + +/* Set "timeval" socket option and check that it's indeed set */ +void setsockopt_timeval_check(int fd, int level, int optname, + struct timeval val, char const *errmsg) +{ + struct timeval chkval; + socklen_t chklen; + int err; + + err = setsockopt(fd, level, optname, &val, sizeof(val)); + if (err) { + fprintf(stderr, "setsockopt err: %s (%d)\n", + strerror(errno), errno); + goto fail; + } + + /* just make storage != val */ + chkval = val; + mem_invert((unsigned char *)&chkval, sizeof(chkval)); + chklen = sizeof(chkval); + + err = getsockopt(fd, level, optname, &chkval, &chklen); + if (err) { + fprintf(stderr, "getsockopt err: %s (%d)\n", + strerror(errno), errno); + goto fail; + } + + if (chklen != sizeof(chkval)) { + fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val), + chklen); + goto fail; + } + + if (memcmp(&chkval, &val, sizeof(val)) != 0) { + fprintf(stderr, "value mismatch: set %ld:%ld got %ld:%ld\n", + val.tv_sec, val.tv_usec, chkval.tv_sec, chkval.tv_usec); + goto fail; + } + return; +fail: + fprintf(stderr, "%s val %ld:%ld\n", errmsg, val.tv_sec, val.tv_usec); + exit(EXIT_FAILURE); +} + +void enable_so_zerocopy_check(int fd) +{ + setsockopt_int_check(fd, SOL_SOCKET, SO_ZEROCOPY, 1, + "setsockopt SO_ZEROCOPY"); +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index fff22d4a14c0..e62f46b2b92a 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -62,10 +62,19 @@ void run_tests(const struct test_case *test_cases, void list_tests(const struct test_case *test_cases); void skip_test(struct test_case *test_cases, size_t test_cases_len, const char *test_id_str); +void pick_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str); unsigned long hash_djb2(const void *data, size_t len); size_t iovec_bytes(const struct iovec *iov, size_t iovnum); unsigned long iovec_hash_djb2(const struct iovec *iov, size_t iovnum); struct iovec *alloc_test_iovec(const struct iovec *test_iovec, int iovnum); void free_test_iovec(const struct iovec *test_iovec, struct iovec *iovec, int iovnum); +void setsockopt_ull_check(int fd, int level, int optname, + unsigned long long val, char const *errmsg); +void setsockopt_int_check(int fd, int level, int optname, int val, + char const *errmsg); +void setsockopt_timeval_check(int fd, int level, int optname, + struct timeval val, char const *errmsg); +void enable_so_zerocopy_check(int fd); #endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_perf.c b/tools/testing/vsock/vsock_perf.c index 4e8578f815e0..75971ac708c9 100644 --- a/tools/testing/vsock/vsock_perf.c +++ b/tools/testing/vsock/vsock_perf.c @@ -33,7 +33,7 @@ static unsigned int port = DEFAULT_PORT; static unsigned long buf_size_bytes = DEFAULT_BUF_SIZE_BYTES; -static unsigned long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES; +static unsigned long long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES; static bool zerocopy; static void error(const char *s) @@ -133,7 +133,7 @@ static float get_gbps(unsigned long bits, time_t ns_delta) ((float)ns_delta / NSEC_PER_SEC); } -static void run_receiver(unsigned long rcvlowat_bytes) +static void run_receiver(int rcvlowat_bytes) { unsigned int read_cnt; time_t rx_begin_ns; @@ -162,8 +162,8 @@ static void run_receiver(unsigned long rcvlowat_bytes) printf("Run as receiver\n"); printf("Listen port %u\n", port); printf("RX buffer %lu bytes\n", buf_size_bytes); - printf("vsock buffer %lu bytes\n", vsock_buf_bytes); - printf("SO_RCVLOWAT %lu bytes\n", rcvlowat_bytes); + printf("vsock buffer %llu bytes\n", vsock_buf_bytes); + printf("SO_RCVLOWAT %d bytes\n", rcvlowat_bytes); fd = socket(AF_VSOCK, SOCK_STREAM, 0); @@ -251,6 +251,16 @@ static void run_receiver(unsigned long rcvlowat_bytes) close(fd); } +static void enable_so_zerocopy(int fd) +{ + int val = 1; + + if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) { + perror("setsockopt"); + exit(EXIT_FAILURE); + } +} + static void run_sender(int peer_cid, unsigned long to_send_bytes) { time_t tx_begin_ns; @@ -439,7 +449,7 @@ static long strtolx(const char *arg) int main(int argc, char **argv) { unsigned long to_send_bytes = DEFAULT_TO_SEND_BYTES; - unsigned long rcvlowat_bytes = DEFAULT_RCVLOWAT_BYTES; + int rcvlowat_bytes = DEFAULT_RCVLOWAT_BYTES; int peer_cid = -1; bool sender = false; diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 8d38dbf8f41f..1eebbc0d5f61 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -22,12 +22,17 @@ #include <signal.h> #include <sys/ioctl.h> #include <linux/sockios.h> +#include <linux/time64.h> #include "vsock_test_zerocopy.h" #include "timeout.h" #include "control.h" #include "util.h" +/* Basic messages for control_writeulong(), control_readulong() */ +#define CONTROL_CONTINUE 1 +#define CONTROL_DONE 0 + static void test_stream_connection_reset(const struct test_opts *opts) { union { @@ -429,7 +434,7 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) { - unsigned long sock_buf_size; + unsigned long long sock_buf_size; unsigned long remote_hash; unsigned long curr_hash; int fd; @@ -444,17 +449,13 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) sock_buf_size = SOCK_BUF_SIZE; - if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, - &sock_buf_size, sizeof(sock_buf_size))) { - perror("setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); - exit(EXIT_FAILURE); - } + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)"); - if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, - &sock_buf_size, sizeof(sock_buf_size))) { - perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); - exit(EXIT_FAILURE); - } + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); /* Ready to receive data. */ control_writeln("SRVREADY"); @@ -563,7 +564,7 @@ static time_t current_nsec(void) exit(EXIT_FAILURE); } - return (ts.tv_sec * 1000000000ULL) + ts.tv_nsec; + return (ts.tv_sec * NSEC_PER_SEC) + ts.tv_nsec; } #define RCVTIMEO_TIMEOUT_SEC 1 @@ -586,10 +587,8 @@ static void test_seqpacket_timeout_client(const struct test_opts *opts) tv.tv_sec = RCVTIMEO_TIMEOUT_SEC; tv.tv_usec = 0; - if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (void *)&tv, sizeof(tv)) == -1) { - perror("setsockopt(SO_RCVTIMEO)"); - exit(EXIT_FAILURE); - } + setsockopt_timeval_check(fd, SOL_SOCKET, SO_RCVTIMEO, tv, + "setsockopt(SO_RCVTIMEO)"); read_enter_ns = current_nsec(); @@ -605,7 +604,7 @@ static void test_seqpacket_timeout_client(const struct test_opts *opts) } read_overhead_ns = current_nsec() - read_enter_ns - - 1000000000ULL * RCVTIMEO_TIMEOUT_SEC; + NSEC_PER_SEC * RCVTIMEO_TIMEOUT_SEC; if (read_overhead_ns > READ_OVERHEAD_NSEC) { fprintf(stderr, @@ -634,7 +633,8 @@ static void test_seqpacket_timeout_server(const struct test_opts *opts) static void test_seqpacket_bigmsg_client(const struct test_opts *opts) { - unsigned long sock_buf_size; + unsigned long long sock_buf_size; + size_t buf_size; socklen_t len; void *data; int fd; @@ -655,13 +655,20 @@ static void test_seqpacket_bigmsg_client(const struct test_opts *opts) sock_buf_size++; - data = malloc(sock_buf_size); + /* size_t can be < unsigned long long */ + buf_size = (size_t)sock_buf_size; + if (buf_size != sock_buf_size) { + fprintf(stderr, "Returned BUFFER_SIZE too large\n"); + exit(EXIT_FAILURE); + } + + data = malloc(buf_size); if (!data) { perror("malloc"); exit(EXIT_FAILURE); } - send_buf(fd, data, sock_buf_size, 0, -EMSGSIZE); + send_buf(fd, data, buf_size, 0, -EMSGSIZE); control_writeln("CLISENT"); @@ -835,7 +842,7 @@ static void test_stream_poll_rcvlowat_server(const struct test_opts *opts) static void test_stream_poll_rcvlowat_client(const struct test_opts *opts) { - unsigned long lowat_val = RCVLOWAT_BUF_SIZE; + int lowat_val = RCVLOWAT_BUF_SIZE; char buf[RCVLOWAT_BUF_SIZE]; struct pollfd fds; short poll_flags; @@ -847,11 +854,8 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts) exit(EXIT_FAILURE); } - if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT, - &lowat_val, sizeof(lowat_val))) { - perror("setsockopt(SO_RCVLOWAT)"); - exit(EXIT_FAILURE); - } + setsockopt_int_check(fd, SOL_SOCKET, SO_RCVLOWAT, + lowat_val, "setsockopt(SO_RCVLOWAT)"); control_expectln("SRVSENT"); @@ -1357,9 +1361,10 @@ static void test_stream_rcvlowat_def_cred_upd_client(const struct test_opts *opt static void test_stream_credit_update_test(const struct test_opts *opts, bool low_rx_bytes_test) { - size_t recv_buf_size; + int recv_buf_size; struct pollfd fds; size_t buf_size; + unsigned long long sock_buf_size; void *buf; int fd; @@ -1371,11 +1376,12 @@ static void test_stream_credit_update_test(const struct test_opts *opts, buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE; - if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, - &buf_size, sizeof(buf_size))) { - perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); - exit(EXIT_FAILURE); - } + /* size_t can be < unsigned long long */ + sock_buf_size = buf_size; + + setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE, + sock_buf_size, + "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)"); if (low_rx_bytes_test) { /* Set new SO_RCVLOWAT here. This enables sending credit @@ -1384,11 +1390,8 @@ static void test_stream_credit_update_test(const struct test_opts *opts, */ recv_buf_size = 1 + VIRTIO_VSOCK_MAX_PKT_BUF_SIZE; - if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT, - &recv_buf_size, sizeof(recv_buf_size))) { - perror("setsockopt(SO_RCVLOWAT)"); - exit(EXIT_FAILURE); - } + setsockopt_int_check(fd, SOL_SOCKET, SO_RCVLOWAT, + recv_buf_size, "setsockopt(SO_RCVLOWAT)"); } /* Send one dummy byte here, because 'setsockopt()' above also @@ -1430,11 +1433,8 @@ static void test_stream_credit_update_test(const struct test_opts *opts, recv_buf_size++; /* Updating SO_RCVLOWAT will send credit update. */ - if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT, - &recv_buf_size, sizeof(recv_buf_size))) { - perror("setsockopt(SO_RCVLOWAT)"); - exit(EXIT_FAILURE); - } + setsockopt_int_check(fd, SOL_SOCKET, SO_RCVLOWAT, + recv_buf_size, "setsockopt(SO_RCVLOWAT)"); } fds.fd = fd; @@ -1478,6 +1478,236 @@ static void test_stream_cred_upd_on_set_rcvlowat(const struct test_opts *opts) test_stream_credit_update_test(opts, false); } +/* The goal of test leak_acceptq is to stress the race between connect() and + * close(listener). Implementation of client/server loops boils down to: + * + * client server + * ------ ------ + * write(CONTINUE) + * expect(CONTINUE) + * listen() + * write(LISTENING) + * expect(LISTENING) + * connect() close() + */ +#define ACCEPTQ_LEAK_RACE_TIMEOUT 2 /* seconds */ + +static void test_stream_leak_acceptq_client(const struct test_opts *opts) +{ + time_t tout; + int fd; + + tout = current_nsec() + ACCEPTQ_LEAK_RACE_TIMEOUT * NSEC_PER_SEC; + do { + control_writeulong(CONTROL_CONTINUE); + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd >= 0) + close(fd); + } while (current_nsec() < tout); + + control_writeulong(CONTROL_DONE); +} + +/* Test for a memory leak. User is expected to run kmemleak scan, see README. */ +static void test_stream_leak_acceptq_server(const struct test_opts *opts) +{ + int fd; + + while (control_readulong() == CONTROL_CONTINUE) { + fd = vsock_stream_listen(VMADDR_CID_ANY, opts->peer_port); + control_writeln("LISTENING"); + close(fd); + } +} + +/* Test for a memory leak. User is expected to run kmemleak scan, see README. */ +static void test_stream_msgzcopy_leak_errq_client(const struct test_opts *opts) +{ + struct pollfd fds = { 0 }; + int fd; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + enable_so_zerocopy_check(fd); + send_byte(fd, 1, MSG_ZEROCOPY); + + fds.fd = fd; + fds.events = 0; + if (poll(&fds, 1, -1) < 0) { + perror("poll"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_msgzcopy_leak_errq_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_byte(fd, 1, 0); + vsock_wait_remote_close(fd); + close(fd); +} + +/* Test msgzcopy_leak_zcskb is meant to exercise sendmsg() error handling path, + * that might leak an skb. The idea is to fail virtio_transport_init_zcopy_skb() + * by hitting net.core.optmem_max limit in sock_omalloc(), specifically + * + * vsock_connectible_sendmsg + * virtio_transport_stream_enqueue + * virtio_transport_send_pkt_info + * virtio_transport_init_zcopy_skb + * . msg_zerocopy_realloc + * . msg_zerocopy_alloc + * . sock_omalloc + * . sk_omem_alloc + size > sysctl_optmem_max + * return -ENOMEM + * + * We abuse the implementation detail of net/socket.c:____sys_sendmsg(). + * sk_omem_alloc can be precisely bumped by sock_kmalloc(), as it is used to + * fetch user-provided control data. + * + * While this approach works for now, it relies on assumptions regarding the + * implementation and configuration (for example, order of net.core.optmem_max + * can not exceed MAX_PAGE_ORDER), which may not hold in the future. A more + * resilient testing could be implemented by leveraging the Fault injection + * framework (CONFIG_FAULT_INJECTION), e.g. + * + * client# echo N > /sys/kernel/debug/failslab/ignore-gfp-wait + * client# echo 0 > /sys/kernel/debug/failslab/verbose + * + * void client(const struct test_opts *opts) + * { + * char buf[16]; + * int f, s, i; + * + * f = open("/proc/self/fail-nth", O_WRONLY); + * + * for (i = 1; i < 32; i++) { + * control_writeulong(CONTROL_CONTINUE); + * + * s = vsock_stream_connect(opts->peer_cid, opts->peer_port); + * enable_so_zerocopy_check(s); + * + * sprintf(buf, "%d", i); + * write(f, buf, strlen(buf)); + * + * send(s, &(char){ 0 }, 1, MSG_ZEROCOPY); + * + * write(f, "0", 1); + * close(s); + * } + * + * control_writeulong(CONTROL_DONE); + * close(f); + * } + * + * void server(const struct test_opts *opts) + * { + * int fd; + * + * while (control_readulong() == CONTROL_CONTINUE) { + * fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + * vsock_wait_remote_close(fd); + * close(fd); + * } + * } + * + * Refer to Documentation/fault-injection/fault-injection.rst. + */ +#define MAX_PAGE_ORDER 10 /* usually */ +#define PAGE_SIZE 4096 + +/* Test for a memory leak. User is expected to run kmemleak scan, see README. */ +static void test_stream_msgzcopy_leak_zcskb_client(const struct test_opts *opts) +{ + size_t optmem_max, ctl_len, chunk_size; + struct msghdr msg = { 0 }; + struct iovec iov; + char *chunk; + int fd, res; + FILE *f; + + f = fopen("/proc/sys/net/core/optmem_max", "r"); + if (!f) { + perror("fopen(optmem_max)"); + exit(EXIT_FAILURE); + } + + if (fscanf(f, "%zu", &optmem_max) != 1) { + fprintf(stderr, "fscanf(optmem_max) failed\n"); + exit(EXIT_FAILURE); + } + + fclose(f); + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + enable_so_zerocopy_check(fd); + + ctl_len = optmem_max - 1; + if (ctl_len > PAGE_SIZE << MAX_PAGE_ORDER) { + fprintf(stderr, "Try with net.core.optmem_max = 100000\n"); + exit(EXIT_FAILURE); + } + + chunk_size = CMSG_SPACE(ctl_len); + chunk = malloc(chunk_size); + if (!chunk) { + perror("malloc"); + exit(EXIT_FAILURE); + } + memset(chunk, 0, chunk_size); + + iov.iov_base = &(char){ 0 }; + iov.iov_len = 1; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = chunk; + msg.msg_controllen = ctl_len; + + errno = 0; + res = sendmsg(fd, &msg, MSG_ZEROCOPY); + if (res >= 0 || errno != ENOMEM) { + fprintf(stderr, "Expected ENOMEM, got errno=%d res=%d\n", + errno, res); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -1608,6 +1838,21 @@ static struct test_case test_cases[] = { .run_client = test_seqpacket_unsent_bytes_client, .run_server = test_seqpacket_unsent_bytes_server, }, + { + .name = "SOCK_STREAM leak accept queue", + .run_client = test_stream_leak_acceptq_client, + .run_server = test_stream_leak_acceptq_server, + }, + { + .name = "SOCK_STREAM MSG_ZEROCOPY leak MSG_ERRQUEUE", + .run_client = test_stream_msgzcopy_leak_errq_client, + .run_server = test_stream_msgzcopy_leak_errq_server, + }, + { + .name = "SOCK_STREAM MSG_ZEROCOPY leak completion skb", + .run_client = test_stream_msgzcopy_leak_zcskb_client, + .run_server = test_stream_msgzcopy_leak_zcskb_server, + }, {}, }; @@ -1649,6 +1894,11 @@ static const struct option longopts[] = { .val = 's', }, { + .name = "pick", + .has_arg = required_argument, + .val = 't', + }, + { .name = "help", .has_arg = no_argument, .val = '?', @@ -1685,6 +1935,8 @@ static void usage(void) " --peer-cid <cid> CID of the other side\n" " --peer-port <port> AF_VSOCK port used for the test [default: %d]\n" " --list List of tests that will be executed\n" + " --pick <test_id> Test ID to execute selectively;\n" + " use multiple --pick options to select more tests\n" " --skip <test_id> Test ID to skip;\n" " use multiple --skip options to skip more tests\n", DEFAULT_PEER_PORT @@ -1741,6 +1993,10 @@ int main(int argc, char **argv) skip_test(test_cases, ARRAY_SIZE(test_cases) - 1, optarg); break; + case 't': + pick_test(test_cases, ARRAY_SIZE(test_cases) - 1, + optarg); + break; case '?': default: usage(); diff --git a/tools/testing/vsock/vsock_test_zerocopy.c b/tools/testing/vsock/vsock_test_zerocopy.c index 04c376b6937f..9d9a6cb9614a 100644 --- a/tools/testing/vsock/vsock_test_zerocopy.c +++ b/tools/testing/vsock/vsock_test_zerocopy.c @@ -162,7 +162,7 @@ static void test_client(const struct test_opts *opts, } if (test_data->so_zerocopy) - enable_so_zerocopy(fd); + enable_so_zerocopy_check(fd); iovec = alloc_test_iovec(test_data->vecs, test_data->vecs_cnt); diff --git a/tools/testing/vsock/vsock_uring_test.c b/tools/testing/vsock/vsock_uring_test.c index 6c3e6f70c457..5c3078969659 100644 --- a/tools/testing/vsock/vsock_uring_test.c +++ b/tools/testing/vsock/vsock_uring_test.c @@ -73,7 +73,7 @@ static void vsock_io_uring_client(const struct test_opts *opts, } if (msg_zerocopy) - enable_so_zerocopy(fd); + enable_so_zerocopy_check(fd); iovec = alloc_test_iovec(test_data->vecs, test_data->vecs_cnt); diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 8b66387e5f35..4403cc4eba30 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -282,6 +282,21 @@ static void timerlat_hist_header(struct osnoise_tool *tool) } /* + * format_summary_value - format a line of summary value (min, max or avg) + * of hist data + */ +static void format_summary_value(struct trace_seq *seq, + int count, + unsigned long long val, + bool avg) +{ + if (count) + trace_seq_printf(seq, "%9llu ", avg ? val / count : val); + else + trace_seq_printf(seq, "%9c ", '-'); +} + +/* * timerlat_print_summary - print the summary of the hist data to the output */ static void @@ -328,29 +343,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_irq); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].min_irq, + false); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_thread); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].min_thread, + false); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_user); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].min_user, + false); } trace_seq_printf(trace->seq, "\n"); @@ -364,29 +373,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_irq / data->hist[cpu].irq_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].sum_irq, + true); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_thread / data->hist[cpu].thread_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].sum_thread, + true); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_user / data->hist[cpu].user_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].sum_user, + true); } trace_seq_printf(trace->seq, "\n"); @@ -400,29 +403,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_irq); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].max_irq, + false); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_thread); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].max_thread, + false); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_user); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].max_user, + false); } trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); @@ -506,16 +503,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "min: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_irq); + format_summary_value(trace->seq, + sum.irq_count, + sum.min_irq, + false); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_thread); + format_summary_value(trace->seq, + sum.thread_count, + sum.min_thread, + false); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_user); + format_summary_value(trace->seq, + sum.user_count, + sum.min_user, + false); trace_seq_printf(trace->seq, "\n"); @@ -523,16 +526,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "avg: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_irq / sum.irq_count); + format_summary_value(trace->seq, + sum.irq_count, + sum.sum_irq, + true); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_thread / sum.thread_count); + format_summary_value(trace->seq, + sum.thread_count, + sum.sum_thread, + true); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_user / sum.user_count); + format_summary_value(trace->seq, + sum.user_count, + sum.sum_user, + true); trace_seq_printf(trace->seq, "\n"); @@ -540,16 +549,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "max: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_irq); + format_summary_value(trace->seq, + sum.irq_count, + sum.max_irq, + false); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_thread); + format_summary_value(trace->seq, + sum.thread_count, + sum.max_thread, + false); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_user); + format_summary_value(trace->seq, + sum.user_count, + sum.max_user, + false); trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); |