diff options
Diffstat (limited to 'tools')
98 files changed, 2702 insertions, 315 deletions
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 6673601246b3..eff29645719b 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -793,9 +793,10 @@ #define MSR_AMD64_LBR_SELECT 0xc000010e /* Zen4 */ -#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG 0xc001102e #define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 +#define MSR_ZEN2_BP_CFG_BUG_FIX_BIT 33 /* Fam 19h MSRs */ #define MSR_F19H_UMC_PERF_CTL 0xc0010800 diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 643f707b8f1d..ddabde20585f 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -390,8 +390,10 @@ static int apply_xbc(const char *path, const char *xbc_path) /* Backup the bootconfig data */ data = calloc(size + BOOTCONFIG_ALIGN + BOOTCONFIG_FOOTER_SIZE, 1); - if (!data) + if (!data) { + free(buf); return -ENOMEM; + } memcpy(data, buf, size); /* Check the data format */ diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h index c53cde425406..457498259494 100644 --- a/tools/include/uapi/linux/stddef.h +++ b/tools/include/uapi/linux/stddef.h @@ -3,7 +3,6 @@ #define _LINUX_STDDEF_H - #ifndef __always_inline #define __always_inline __inline__ #endif @@ -36,6 +35,11 @@ struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ } ATTRS +#ifdef __cplusplus +/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ +#define __DECLARE_FLEX_ARRAY(T, member) \ + T member[0] +#else /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union * @@ -52,3 +56,23 @@ TYPE NAME[]; \ } #endif + +#ifndef __counted_by +#define __counted_by(m) +#endif + +#ifndef __counted_by_le +#define __counted_by_le(m) +#endif + +#ifndef __counted_by_be +#define __counted_by_be(m) +#endif + +#ifndef __counted_by_ptr +#define __counted_by_ptr(m) +#endif + +#define __kernel_nonstring + +#endif /* _LINUX_STDDEF_H */ diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index cd5c2543f54d..9478b8f78f26 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -592,13 +592,12 @@ static void emit_signature_match(struct bpf_gen *gen) gen->hash_insn_offset[i] = gen->insn_cur - gen->insn_start; emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_3, 0, 0, 0, 0, 0)); - off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1; + off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 2; if (is_simm16(off)) { emit(gen, BPF_MOV64_IMM(BPF_REG_7, -EINVAL)); emit(gen, BPF_JMP_REG(BPF_JNE, BPF_REG_2, BPF_REG_3, off)); } else { gen->error = -ERANGE; - emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1)); } } } diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index 08205f9fc525..cc53b2f21c44 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -15,9 +15,11 @@ UAPI_PATH:=../../../../include/uapi/ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2) get_hdr_inc2=-D$(1) -D$(2) -include $(UAPI_PATH)/linux/$(3) +CFLAGS_dev-energymodel:=$(call get_hdr_inc,_LINUX_DEV_ENERGYMODEL_H,dev_energymodel.h) CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h) -CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ +CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_TYPELIMITS_H,typelimits.h) \ + $(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \ $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) \ $(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_GENERATED_H,ethtool_netlink_generated.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index f63c6f828735..010aac0c6c67 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -42,6 +42,7 @@ class Netlink: SOL_NETLINK = 270 NETLINK_ADD_MEMBERSHIP = 1 + NETLINK_LISTEN_ALL_NSID = 8 NETLINK_CAP_ACK = 10 NETLINK_EXT_ACK = 11 NETLINK_GET_STRICT_CHK = 12 @@ -680,6 +681,7 @@ class YnlFamily(SpecFamily): Notification API: ynl.ntf_subscribe(mcast_name) -- join a multicast group + ynl.ntf_listen_all_nsid() -- listen on all netns ynl.check_ntf() -- drain pending notifications ynl.poll_ntf(duration=None) -- yield notifications @@ -748,6 +750,23 @@ class YnlFamily(SpecFamily): self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_ADD_MEMBERSHIP, mcast_id) + def ntf_listen_all_nsid(self): + """Enable NETLINK_LISTEN_ALL_NSID to receive notifications from all + namespaces that have an nsid mapped in the current one.""" + self.sock.setsockopt(Netlink.SOL_NETLINK, + Netlink.NETLINK_LISTEN_ALL_NSID, 1) + + @staticmethod + def _decode_nsid(ancdata): + for cmsg_level, cmsg_type, cmsg_data in ancdata: + if (cmsg_level == Netlink.SOL_NETLINK and + cmsg_type == Netlink.NETLINK_LISTEN_ALL_NSID): + nsid = struct.unpack('i', cmsg_data)[0] + if nsid >= 0: + return nsid + return None + return None + def set_recv_dbg(self, enabled): self._recv_dbg = enabled @@ -1235,7 +1254,7 @@ class YnlFamily(SpecFamily): f" when parsing '{attr_spec['name']}'") return raw - def handle_ntf(self, decoded): + def handle_ntf(self, decoded, nsid=None): msg = {} if self.include_raw: msg['raw'] = decoded @@ -1246,15 +1265,22 @@ class YnlFamily(SpecFamily): msg['name'] = op['name'] msg['msg'] = attrs + if nsid is not None: + msg['nsid'] = nsid self.async_msg_queue.put(msg) + def _recvmsg(self, flags=0): + reply, ancdata, _, _ = self.sock.recvmsg(self._recv_size, 4096, flags) + return reply, ancdata + def check_ntf(self): while True: try: - reply = self.sock.recv(self._recv_size, socket.MSG_DONTWAIT) + reply, ancdata = self._recvmsg(socket.MSG_DONTWAIT) except BlockingIOError: return + nsid = self._decode_nsid(ancdata) nms = NlMsgs(reply) self._recv_dbg_print(reply, nms) for nl_msg in nms: @@ -1271,7 +1297,7 @@ class YnlFamily(SpecFamily): print("Unexpected msg id while checking for ntf", decoded) continue - self.handle_ntf(decoded) + self.handle_ntf(decoded, nsid) def poll_ntf(self, duration=None): start_time = time.time() @@ -1335,7 +1361,8 @@ class YnlFamily(SpecFamily): rsp = [] op_rsp = [] while not done: - reply = self.sock.recv(self._recv_size) + reply, ancdata = self._recvmsg() + nsid = self._decode_nsid(ancdata) nms = NlMsgs(reply) self._recv_dbg_print(reply, nms) for nl_msg in nms: @@ -1374,7 +1401,7 @@ class YnlFamily(SpecFamily): # Check if this is a reply to our request if nl_msg.nl_seq not in reqs_by_seq or decoded.cmd() != op.rsp_value: if decoded.cmd() in self.async_msg_ids: - self.handle_ntf(decoded) + self.handle_ntf(decoded, nsid) continue print('Unexpected message: ' + repr(decoded)) continue diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index 0e1e486c1185..cdc3646f2642 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -3212,6 +3212,8 @@ def render_uapi(family, cw): for const in family['definitions']: if const.get('header'): continue + if const.get('scope', 'uapi') != 'uapi': + continue if const['type'] != 'const': cw.writes_defines(defines) @@ -3339,6 +3341,25 @@ def render_uapi(family, cw): cw.p(f'#endif /* {hdr_prot} */') +def render_scoped_consts(family, cw, scope): + defines = [] + for const in family['definitions']: + if const['type'] != 'const': + continue + if const.get('header'): + continue + if const.get('scope') != scope: + continue + name_pfx = const.get('name-prefix', f"{family.ident_name}-") + defines.append([ + c_upper(family.get('c-define-name', + f"{name_pfx}{const['name']}")), + const['value']]) + if defines: + cw.writes_defines(defines) + cw.nl() + + def _render_user_ntf_entry(ri, op): if not ri.family.is_classic(): ri.cw.block_start(line=f"[{op.enum_name}] = ") @@ -3504,8 +3525,12 @@ def main(): cw.p('#include "ynl.h"') headers = [] for definition in parsed['definitions'] + parsed['attribute-sets']: - if 'header' in definition: - headers.append(definition['header']) + if 'header' not in definition: + continue + scope = definition.get('scope', 'uapi') + if scope != 'uapi' and scope != args.mode: + continue + headers.append(definition['header']) if args.mode == 'user': headers.append(parsed.uapi_header) seen_header = [] @@ -3522,6 +3547,7 @@ def main(): for one in args.user_header: cw.p(f'#include "{one}"') else: + render_scoped_consts(parsed, cw, 'user') cw.p('struct ynl_sock;') cw.nl() render_user_family(parsed, cw, True) @@ -3529,6 +3555,7 @@ def main(): if args.mode == "kernel": if args.header: + render_scoped_consts(parsed, cw, 'kernel') for _, struct in sorted(parsed.pure_nested_structs.items()): if struct.request: cw.p('/* Common nested types */') diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 816d5d84816b..5b713837eede 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -111,6 +111,9 @@ build-test: build-test-tarball: @$(MAKE) -f tests/make REUSE_FEATURES_DUMP=1 MK=Makefile SET_PARALLEL=1 --no-print-directory out +check-headers: + @./check-headers.sh + # # All other targets get passed through: # @@ -118,4 +121,4 @@ build-test-tarball: $(print_msg) $(make) -.PHONY: tags TAGS FORCE Makefile +.PHONY: tags TAGS FORCE Makefile build-test build-test-tarball check-headers diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index cee19c923c06..76b35ac19acb 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -285,7 +285,6 @@ goals := $(filter-out all sub-make, $(MAKECMDGOALS)) $(goals) all: sub-make sub-make: fixdep - @./check-headers.sh $(Q)$(MAKE) FIXDEP_BUILT=1 -f Makefile.perf $(goals) else # force_fixdep @@ -565,6 +564,12 @@ fsmount_tbls := $(srctree)/tools/perf/trace/beauty/fsmount.sh $(fsmount_arrays): $(beauty_uapi_linux_dir)/mount.h $(fsmount_tbls) $(Q)$(SHELL) '$(fsmount_tbls)' $(beauty_uapi_linux_dir) > $@ +fsmount_attr_arrays := $(beauty_outdir)/fsmount_attr_arrays.c +fsmount_attr_tbls := $(srctree)/tools/perf/trace/beauty/fsmount_attr.sh + +$(fsmount_attr_arrays): $(beauty_uapi_linux_dir)/mount.h $(fsmount_attr_tbls) + $(Q)$(SHELL) '$(fsmount_attr_tbls)' $(beauty_uapi_linux_dir) > $@ + fspick_arrays := $(beauty_outdir)/fspick_arrays.c fspick_tbls := $(srctree)/tools/perf/trace/beauty/fspick.sh @@ -855,6 +860,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE archheaders \ $(fadvise_advice_array) \ $(fsconfig_arrays) \ $(fsmount_arrays) \ + $(fsmount_attr_arrays) \ $(fspick_arrays) \ $(pkey_alloc_access_rights_array) \ $(sndrv_pcm_ioctl_array) \ @@ -1302,6 +1308,7 @@ clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $( $(OUTPUT)$(fadvise_advice_array) \ $(OUTPUT)$(fsconfig_arrays) \ $(OUTPUT)$(fsmount_arrays) \ + $(OUTPUT)$(fsmount_attr_arrays) \ $(OUTPUT)$(fspick_arrays) \ $(OUTPUT)$(madvise_behavior_array) \ $(OUTPUT)$(mmap_flags_array) \ diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index e58c49d047a2..48615ddccd93 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -771,11 +771,6 @@ static const char *bpf_cmd[] = { }; static DEFINE_STRARRAY(bpf_cmd, "BPF_"); -static const char *fsmount_flags[] = { - [1] = "CLOEXEC", -}; -static DEFINE_STRARRAY(fsmount_flags, "FSMOUNT_"); - #include "trace/beauty/generated/fsconfig_arrays.c" static DEFINE_STRARRAY(fsconfig_cmds, "FSCONFIG_"); @@ -1202,7 +1197,9 @@ static const struct syscall_fmt syscall_fmts[] = { { .name = "fsconfig", .arg = { [1] = STRARRAY(cmd, fsconfig_cmds), }, }, { .name = "fsmount", - .arg = { [1] = STRARRAY_FLAGS(flags, fsmount_flags), + .arg = { [1] = { .scnprintf = SCA_FSMOUNT_FLAGS, /* fsmount_flags */ + .strtoul = STUL_STRARRAYS, + .show_zero = true, }, [2] = { .scnprintf = SCA_FSMOUNT_ATTR_FLAGS, /* attr_flags */ }, }, }, { .name = "fspick", .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 0a07ad158f87..a90c35fa5c12 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -179,6 +179,9 @@ size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_ar size_t syscall_arg__scnprintf_flock(char *bf, size_t size, struct syscall_arg *arg); #define SCA_FLOCK syscall_arg__scnprintf_flock +size_t syscall_arg__scnprintf_fsmount_flags(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_FSMOUNT_FLAGS syscall_arg__scnprintf_fsmount_flags + size_t syscall_arg__scnprintf_fsmount_attr_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_FSMOUNT_ATTR_FLAGS syscall_arg__scnprintf_fsmount_attr_flags diff --git a/tools/perf/trace/beauty/clone.sh b/tools/perf/trace/beauty/clone.sh index 18b6c0d75693..98cb1f8d4a6f 100755 --- a/tools/perf/trace/beauty/clone.sh +++ b/tools/perf/trace/beauty/clone.sh @@ -14,4 +14,8 @@ regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+CLONE_([^_]+[[:alnum:]_]+)[[: grep -E $regex ${linux_sched} | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+CLONE_([^_]+[[:alnum:]_]+)[[:space:]]+\(1ULL[[:space:]]*<<[[:space:]]*([[:digit:]]+)\)[[:space:]]*.*' +grep -E $regex ${linux_sched} | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[%s + 1] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/trace/beauty/fsmount.c b/tools/perf/trace/beauty/fsmount.c index 28c2c16fc1a8..179e649fc72a 100644 --- a/tools/perf/trace/beauty/fsmount.c +++ b/tools/perf/trace/beauty/fsmount.c @@ -16,9 +16,25 @@ #define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */ #endif -static size_t fsmount__scnprintf_attr_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) + +static size_t fsmount__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) { #include "trace/beauty/generated/fsmount_arrays.c" + static DEFINE_STRARRAY(fsmount_flags, "FSMOUNT_"); + + return strarray__scnprintf_flags(&strarray__fsmount_flags, bf, size, show_prefix, flags); +} + +size_t syscall_arg__scnprintf_fsmount_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + unsigned long flags = arg->val; + + return fsmount__scnprintf_flags(flags, bf, size, arg->show_string_prefix); +} + +static size_t fsmount__scnprintf_attr_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) +{ +#include "trace/beauty/generated/fsmount_attr_arrays.c" static DEFINE_STRARRAY(fsmount_attr_flags, "MOUNT_ATTR_"); size_t printed = 0; diff --git a/tools/perf/trace/beauty/fsmount.sh b/tools/perf/trace/beauty/fsmount.sh index 6b67a54cdeee..6d1e80bc15e4 100755 --- a/tools/perf/trace/beauty/fsmount.sh +++ b/tools/perf/trace/beauty/fsmount.sh @@ -9,14 +9,9 @@ fi linux_mount=${beauty_uapi_linux_dir}/mount.h -# Remove MOUNT_ATTR_RELATIME as it is zeros, handle it a special way in the beautifier -# Only handle MOUNT_ATTR_ followed by a capital letter/num as __ is special case -# for things like MOUNT_ATTR__ATIME that is a mask for the possible ATIME handling -# bits. Special case it as well in the beautifier - -printf "static const char *fsmount_attr_flags[] = {\n" -regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOUNT_ATTR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' -grep -E $regex ${linux_mount} | grep -v MOUNT_ATTR_RELATIME | \ +printf "static const char *fsmount_flags[] = {\n" +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+FSMOUNT_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' +grep -E $regex ${linux_mount} | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/trace/beauty/fsmount_attr.sh b/tools/perf/trace/beauty/fsmount_attr.sh new file mode 100644 index 000000000000..6b67a54cdeee --- /dev/null +++ b/tools/perf/trace/beauty/fsmount_attr.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# SPDX-License-Identifier: LGPL-2.1 + +if [ $# -ne 1 ] ; then + beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/ +else + beauty_uapi_linux_dir=$1 +fi + +linux_mount=${beauty_uapi_linux_dir}/mount.h + +# Remove MOUNT_ATTR_RELATIME as it is zeros, handle it a special way in the beautifier +# Only handle MOUNT_ATTR_ followed by a capital letter/num as __ is special case +# for things like MOUNT_ATTR__ATIME that is a mask for the possible ATIME handling +# bits. Special case it as well in the beautifier + +printf "static const char *fsmount_attr_flags[] = {\n" +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOUNT_ATTR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' +grep -E $regex ${linux_mount} | grep -v MOUNT_ATTR_RELATIME | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index ec715ad4bf25..ec4a0a025793 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -415,7 +415,7 @@ struct __kernel_timespec; struct old_timespec32; struct scm_timestamping_internal { - struct timespec64 ts[3]; + ktime_t ts[3]; }; extern void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss); diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index 70b2b661f42c..13f71202845e 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -657,4 +657,16 @@ struct procmap_query { __u64 build_id_addr; /* in */ }; +/* + * Shutdown the filesystem. + */ +#define FS_IOC_SHUTDOWN _IOR('X', 125, __u32) + +/* + * Flags for FS_IOC_SHUTDOWN + */ +#define FS_SHUTDOWN_FLAGS_DEFAULT 0x0 +#define FS_SHUTDOWN_FLAGS_LOGFLUSH 0x1 /* flush log but not data*/ +#define FS_SHUTDOWN_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */ + #endif /* _UAPI_LINUX_FS_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index d9d86598d100..2204708dbf7a 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -110,6 +110,7 @@ enum fsconfig_command { * fsmount() flags. */ #define FSMOUNT_CLOEXEC 0x00000001 +#define FSMOUNT_NAMESPACE 0x00000002 /* Create the mount in a new mount namespace */ /* * Mount attributes. diff --git a/tools/perf/trace/beauty/include/uapi/linux/sched.h b/tools/perf/trace/beauty/include/uapi/linux/sched.h index 359a14cc76a4..33a4624285cd 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/sched.h +++ b/tools/perf/trace/beauty/include/uapi/linux/sched.h @@ -34,8 +34,12 @@ #define CLONE_IO 0x80000000 /* Clone io context */ /* Flags for the clone3() syscall. */ -#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */ -#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */ +#define CLONE_CLEAR_SIGHAND (1ULL << 32) /* Clear any signal handler and reset to SIG_DFL. */ +#define CLONE_INTO_CGROUP (1ULL << 33) /* Clone into a specific cgroup given the right permissions. */ +#define CLONE_AUTOREAP (1ULL << 34) /* Auto-reap child on exit. */ +#define CLONE_NNP (1ULL << 35) /* Set no_new_privs on child. */ +#define CLONE_PIDFD_AUTOKILL (1ULL << 36) /* Kill child when clone pidfd closes. */ +#define CLONE_EMPTY_MNTNS (1ULL << 37) /* Create an empty mount namespace. */ /* * cloning flags intersect with CSIGNAL so can be used with unshare and clone3 @@ -43,6 +47,12 @@ */ #define CLONE_NEWTIME 0x00000080 /* New time namespace */ +/* + * unshare flags share the bit space with clone flags but only apply to the + * unshare syscall: + */ +#define UNSHARE_EMPTY_MNTNS 0x00100000 /* Unshare an empty mount namespace. */ + #ifndef __ASSEMBLY__ /** * struct clone_args - arguments for the clone3 syscall @@ -146,4 +156,7 @@ struct clone_args { SCHED_FLAG_KEEP_ALL | \ SCHED_FLAG_UTIL_CLAMP) +/* Only for sched_getattr() own flag param, if task is SCHED_DEADLINE */ +#define SCHED_GETATTR_FLAG_DL_DYNAMIC 0x01 + #endif /* _UAPI_LINUX_SCHED_H */ diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 418669927fb0..296516eecfd6 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -1523,6 +1523,23 @@ static void mock_companion(struct acpi_device *adev, struct device *dev) #define SZ_64G (SZ_32G * 2) #endif +static int cxl_mock_platform_device_add(struct platform_device *pdev, + struct platform_device **ppdev) +{ + int rc; + + if (ppdev) + *ppdev = pdev; + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + if (ppdev) + *ppdev = NULL; + } + + return rc; +} + static __init int cxl_rch_topo_init(void) { int rc, i; @@ -1537,13 +1554,10 @@ static __init int cxl_rch_topo_init(void) goto err_bridge; mock_companion(adev, &pdev->dev); - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_rch[i]); + if (rc) goto err_bridge; - } - cxl_rch[i] = pdev; mock_pci_bus[idx].bridge = &pdev->dev; rc = sysfs_create_link(&pdev->dev.kobj, &pdev->dev.kobj, "firmware_node"); @@ -1595,13 +1609,10 @@ static __init int cxl_single_topo_init(void) goto err_bridge; mock_companion(adev, &pdev->dev); - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_hb_single[i]); + if (rc) goto err_bridge; - } - cxl_hb_single[i] = pdev; mock_pci_bus[i + NR_CXL_HOST_BRIDGES].bridge = &pdev->dev; rc = sysfs_create_link(&pdev->dev.kobj, &pdev->dev.kobj, "physical_node"); @@ -1620,12 +1631,9 @@ static __init int cxl_single_topo_init(void) goto err_port; pdev->dev.parent = &bridge->dev; - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_root_single[i]); + if (rc) goto err_port; - } - cxl_root_single[i] = pdev; } for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++) { @@ -1638,12 +1646,9 @@ static __init int cxl_single_topo_init(void) goto err_uport; pdev->dev.parent = &root_port->dev; - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_swu_single[i]); + if (rc) goto err_uport; - } - cxl_swu_single[i] = pdev; } for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++) { @@ -1657,12 +1662,9 @@ static __init int cxl_single_topo_init(void) goto err_dport; pdev->dev.parent = &uport->dev; - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_swd_single[i]); + if (rc) goto err_dport; - } - cxl_swd_single[i] = pdev; } return 0; @@ -1735,12 +1737,9 @@ static int cxl_mem_init(void) pdev->dev.parent = &dport->dev; set_dev_node(&pdev->dev, i % 2); - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_mem[i]); + if (rc) goto err_mem; - } - cxl_mem[i] = pdev; } for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) { @@ -1753,12 +1752,9 @@ static int cxl_mem_init(void) pdev->dev.parent = &dport->dev; set_dev_node(&pdev->dev, i % 2); - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_mem_single[i]); + if (rc) goto err_single; - } - cxl_mem_single[i] = pdev; } for (i = 0; i < ARRAY_SIZE(cxl_rcd); i++) { @@ -1772,12 +1768,9 @@ static int cxl_mem_init(void) pdev->dev.parent = &rch->dev; set_dev_node(&pdev->dev, i % 2); - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_rcd[i]); + if (rc) goto err_rcd; - } - cxl_rcd[i] = pdev; } return 0; @@ -1869,13 +1862,10 @@ static __init int cxl_test_init(void) goto err_bridge; mock_companion(adev, &pdev->dev); - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_host_bridge[i]); + if (rc) goto err_bridge; - } - cxl_host_bridge[i] = pdev; mock_pci_bus[i].bridge = &pdev->dev; rc = sysfs_create_link(&pdev->dev.kobj, &pdev->dev.kobj, "physical_node"); @@ -1893,12 +1883,9 @@ static __init int cxl_test_init(void) goto err_port; pdev->dev.parent = &bridge->dev; - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_root_port[i]); + if (rc) goto err_port; - } - cxl_root_port[i] = pdev; } BUILD_BUG_ON(ARRAY_SIZE(cxl_switch_uport) != ARRAY_SIZE(cxl_root_port)); @@ -1911,12 +1898,9 @@ static __init int cxl_test_init(void) goto err_uport; pdev->dev.parent = &root_port->dev; - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_switch_uport[i]); + if (rc) goto err_uport; - } - cxl_switch_uport[i] = pdev; } for (i = 0; i < ARRAY_SIZE(cxl_switch_dport); i++) { @@ -1929,12 +1913,9 @@ static __init int cxl_test_init(void) goto err_dport; pdev->dev.parent = &uport->dev; - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); + rc = cxl_mock_platform_device_add(pdev, &cxl_switch_dport[i]); + if (rc) goto err_dport; - } - cxl_switch_dport[i] = pdev; } rc = cxl_single_topo_init(); @@ -1953,9 +1934,9 @@ static __init int cxl_test_init(void) acpi0017_mock.dev.bus = &platform_bus_type; cxl_acpi->dev.groups = cxl_acpi_groups; - rc = platform_device_add(cxl_acpi); + rc = cxl_mock_platform_device_add(cxl_acpi, NULL); if (rc) - goto err_root; + goto err_rch; rc = cxl_mem_init(); if (rc) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index f829b6f09bc9..fe30181e6336 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -112,6 +112,10 @@ static void test_cubic(void) ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called"); + ASSERT_TRUE(cubic_skel->bss->nodelay_init_reject, "init reject nodelay option"); + ASSERT_TRUE(cubic_skel->bss->nodelay_cwnd_event_tx_start_reject, + "cwnd_event_tx_start reject nodelay option"); + bpf_link__destroy(link); bpf_cubic__destroy(cubic_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c index 8cd298b78e44..04aaf4c9cf5e 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c @@ -14,7 +14,7 @@ static struct { const char *prog_name; int expected_runtime_err; } kfunc_dynptr_tests[] = { - {"dynptr_data_null", -EBADMSG}, + {"dynptr_data_null", -EINVAL}, }; static bool kfunc_not_supported; diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_array_inner_map.c b/tools/testing/selftests/bpf/prog_tests/percpu_array_inner_map.c new file mode 100644 index 000000000000..2a8b2381306b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/percpu_array_inner_map.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +/* + * Test that replacing an inner percpu array map with one that has different + * max_entries is rejected. percpu_array_map_gen_lookup() inlines the + * template's index_mask, so allowing a smaller replacement would cause OOB. + */ +void test_percpu_array_inner_map(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int outer_fd, tmpl_fd, good_fd, bad_fd, err; + int zero = 0; + + /* Create template: percpu array with 8 entries */ + tmpl_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, "tmpl", + sizeof(int), sizeof(long), 8, NULL); + if (!ASSERT_OK_FD(tmpl_fd, "create_tmpl")) + return; + + /* Create outer array-of-maps using template */ + opts.inner_map_fd = tmpl_fd; + outer_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY_OF_MAPS, "outer", + sizeof(int), sizeof(int), 1, &opts); + if (!ASSERT_OK_FD(outer_fd, "create_outer")) + goto close_tmpl; + + /* Insert template as initial inner map */ + err = bpf_map_update_elem(outer_fd, &zero, &tmpl_fd, 0); + if (!ASSERT_OK(err, "insert_tmpl")) + goto close_outer; + + /* Replacement with same max_entries should succeed */ + good_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, "good", + sizeof(int), sizeof(long), 8, NULL); + if (!ASSERT_OK_FD(good_fd, "create_good")) + goto close_outer; + + err = bpf_map_update_elem(outer_fd, &zero, &good_fd, 0); + ASSERT_OK(err, "replace_same_max_entries"); + close(good_fd); + + /* Replacement with fewer max_entries must fail */ + bad_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, "bad", + sizeof(int), sizeof(long), 2, NULL); + if (!ASSERT_OK_FD(bad_fd, "create_bad")) + goto close_outer; + + err = bpf_map_update_elem(outer_fd, &zero, &bad_fd, 0); + ASSERT_ERR(err, "replace_smaller_max_entries"); + close(bad_fd); + +close_outer: + close(outer_fd); +close_tmpl: + close(tmpl_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index b87e7f39e15a..6ed8e149e3d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -417,6 +417,107 @@ static void run_tests(int family, enum bpf_map_type map_type) close(map); } +/* + * Regression test for the KTLS + sockmap (verdict) reverse-order UAF. + * + * Vulnerable sequence: + * 1. Insert receiver socket into sockmap with BPF_SK_SKB_VERDICT program. + * sk->sk_data_ready becomes sk_psock_verdict_data_ready. + * 2. Configure TLS RX: tls_sw_strparser_arm() saves + * sk_psock_verdict_data_ready as rx_ctx->saved_data_ready. + * + * When data arrives, tls_rx_msg_ready() calls saved_data_ready() = + * sk_psock_verdict_data_ready(), which calls tcp_read_skb() and drains + * sk_receive_queue via __skb_unlink() without advancing copied_seq. + * tls_strp_msg_load() then finds the queue empty while tcp_inq() is still + * non-zero, hits WARN_ON_ONCE(!first), and leaves a dangling frag_list + * pointer that tls_decrypt_sg() walks — a use-after-free. + * + * The fix adds a tls_sw_has_ctx_rx() check to sk_psock_verdict_data_ready(), + * mirroring what sk_psock_strp_data_ready() already does: when a TLS RX + * context is present, defer to psock->saved_data_ready (sock_def_readable) + * instead of calling tcp_read_skb(), so TLS retains sole ownership of the + * receive queue. Data is then decrypted and returned correctly by + * tls_sw_recvmsg(). + */ +static void test_sockmap_ktls_verdict_with_tls_rx(int family, int sotype) +{ + struct tls12_crypto_info_aes_gcm_128 crypto_info = {}; + char send_buf[] = "hello ktls sockmap reverse order"; + char recv_buf[sizeof(send_buf)] = {}; + struct test_sockmap_ktls *skel; + int c = -1, p = -1, zero = 0; + int prog_fd, map_fd; + ssize_t n; + int err; + + skel = test_sockmap_ktls__open_and_load(); + if (!ASSERT_TRUE(skel, "open_and_load")) + return; + + err = create_pair(family, sotype, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto out; + + prog_fd = bpf_program__fd(skel->progs.prog_skb_verdict_pass); + map_fd = bpf_map__fd(skel->maps.sock_map_verdict); + + err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_SKB_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach sk_skb verdict")) + goto out; + + /* Step 1: configure TLS TX on sender (no sockmap involvement) */ + err = setsockopt(c, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls")); + if (!ASSERT_OK(err, "setsockopt(TCP_ULP) client")) + goto out; + + crypto_info.info.version = TLS_1_2_VERSION; + crypto_info.info.cipher_type = TLS_CIPHER_AES_GCM_128; + memset(crypto_info.key, 0x01, sizeof(crypto_info.key)); + memset(crypto_info.salt, 0x02, sizeof(crypto_info.salt)); + + err = setsockopt(c, SOL_TLS, TLS_TX, &crypto_info, sizeof(crypto_info)); + if (!ASSERT_OK(err, "setsockopt(TLS_TX)")) + goto out; + + /* Step 2: insert receiver into sockmap BEFORE TLS RX */ + err = bpf_map_update_elem(map_fd, &zero, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + goto out; + + /* Step 3: configure TLS RX AFTER sockmap insertion */ + err = setsockopt(p, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls")); + if (!ASSERT_OK(err, "setsockopt(TCP_ULP) server")) + goto out; + + err = setsockopt(p, SOL_TLS, TLS_RX, &crypto_info, sizeof(crypto_info)); + if (!ASSERT_OK(err, "setsockopt(TLS_RX)")) + goto out; + + /* + * A buggy kernel hits WARN_ON_ONCE in tls_strp_load_anchor_with_queue + * and may UAF in tls_decrypt_sg here. With the fix, + * sk_psock_verdict_data_ready defers to sock_def_readable and TLS + * decrypts the record normally. + */ + n = send(c, send_buf, sizeof(send_buf), 0); + if (!ASSERT_EQ(n, (ssize_t)sizeof(send_buf), "send")) + goto out; + + n = recv_timeout(p, recv_buf, sizeof(recv_buf), 0, 5); + if (!ASSERT_EQ(n, (ssize_t)sizeof(send_buf), "recv")) + goto out; + + ASSERT_OK(memcmp(send_buf, recv_buf, sizeof(send_buf)), "data integrity"); + +out: + if (c != -1) + close(c); + if (p != -1) + close(p); + test_sockmap_ktls__destroy(skel); +} + static void run_ktls_test(int family, int sotype) { if (test__start_subtest("tls simple offload")) @@ -429,6 +530,8 @@ static void run_ktls_test(int family, int sotype) test_sockmap_ktls_tx_no_buf(family, sotype, true); if (test__start_subtest("tls tx with pop")) test_sockmap_ktls_tx_pop(family, sotype); + if (test__start_subtest("tls verdict with tls rx")) + test_sockmap_ktls_verdict_with_tls_rx(family, sotype); } void test_sockmap_ktls(void) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 53637431ec5d..3a41c517b918 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -190,7 +190,7 @@ static int getsetsockopt(void) fd = socket(AF_NETLINK, SOCK_RAW, 0); if (fd < 0) { log_err("Failed to create AF_NETLINK socket"); - return -1; + goto err; } buf.u32 = 1; @@ -211,6 +211,21 @@ static int getsetsockopt(void) } ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); + /* Trick bpf_tcp_sock() with IPPROTO_TCP */ + close(fd); + fd = socket(AF_INET, SOCK_RAW, IPPROTO_TCP); + if (!ASSERT_OK_FD(fd, "socket")) + goto err; + + /* The BPF prog intercepts this before the kernel sees it, any + * optlen works. Go with 4 bytes for simplicity. + */ + buf.u32 = 1; + optlen = sizeof(buf.u32); + err = setsockopt(fd, SOL_TCP, TCP_SAVED_SYN, &buf, optlen); + if (!ASSERT_ERR(err, "setsockopt(TCP_SAVED_SYN)")) + goto err; + free(big_buf); close(fd); return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c index 56685fc03c7e..80e6315da2a5 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c @@ -507,6 +507,10 @@ static void misc(void) ASSERT_EQ(misc_skel->bss->nr_hwtstamp, 0, "nr_hwtstamp"); + ASSERT_TRUE(misc_skel->bss->nodelay_est_ok, "nodelay_est_ok"); + ASSERT_TRUE(misc_skel->bss->nodelay_hdr_len_reject, "nodelay_hdr_len_reject"); + ASSERT_TRUE(misc_skel->bss->nodelay_write_hdr_reject, "nodelay_write_hdr_reject"); + check_linum: ASSERT_FALSE(check_error_linum(&sk_fds), "check_error_linum"); sk_fds_close(&sk_fds); diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index a96b25ebff23..06cd24e37b3f 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -22,6 +22,7 @@ #include "verifier_bswap.skel.h" #include "verifier_btf_ctx_access.skel.h" #include "verifier_btf_unreliable_prog.skel.h" +#include "verifier_call_large_imm.skel.h" #include "verifier_cfg.skel.h" #include "verifier_cgroup_inv_retcode.skel.h" #include "verifier_cgroup_skb.skel.h" @@ -170,6 +171,7 @@ void test_verifier_bpf_trap(void) { RUN(verifier_bpf_trap); } void test_verifier_bswap(void) { RUN(verifier_bswap); } void test_verifier_btf_ctx_access(void) { RUN(verifier_btf_ctx_access); } void test_verifier_btf_unreliable_prog(void) { RUN(verifier_btf_unreliable_prog); } +void test_verifier_call_large_imm(void) { RUN(verifier_call_large_imm); } void test_verifier_cfg(void) { RUN(verifier_cfg); } void test_verifier_cgroup_inv_retcode(void) { RUN(verifier_cgroup_inv_retcode); } void test_verifier_cgroup_skb(void) { RUN(verifier_cgroup_skb); } diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index ce18a4db813f..ebd5a1e69f56 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -16,6 +16,7 @@ #include "bpf_tracing_net.h" #include <bpf/bpf_tracing.h> +#include <errno.h> char _license[] SEC("license") = "GPL"; @@ -170,10 +171,18 @@ static void bictcp_hystart_reset(struct sock *sk) ca->sample_cnt = 0; } +bool nodelay_init_reject = false; +bool nodelay_cwnd_event_tx_start_reject = false; + SEC("struct_ops") void BPF_PROG(bpf_cubic_init, struct sock *sk) { struct bpf_bictcp *ca = inet_csk_ca(sk); + int true_val = 1, ret; + + ret = bpf_setsockopt(sk, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val)); + if (ret == -EOPNOTSUPP) + nodelay_init_reject = true; bictcp_reset(ca); @@ -189,8 +198,13 @@ void BPF_PROG(bpf_cubic_cwnd_event_tx_start, struct sock *sk) { struct bpf_bictcp *ca = inet_csk_ca(sk); __u32 now = tcp_jiffies32; + int true_val = 1, ret; __s32 delta; + ret = bpf_setsockopt(sk, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val)); + if (ret == -EOPNOTSUPP) + nodelay_cwnd_event_tx_start_reject = true; + delta = now - tcp_sk(sk)->lsndtime; /* We were application limited (idle) for a while. diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c index 051e2b6f2694..ac44d60e5066 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_fail.c +++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c @@ -208,6 +208,28 @@ int reject_with_reference(void *ctx) return 0; } +__noinline int global_subprog_may_throw(struct __sk_buff *ctx) +{ + if (ctx->len) + bpf_throw(0); + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference") +int reject_global_subprog_throw_with_reference(struct __sk_buff *ctx) +{ + struct foo *f; + + f = bpf_obj_new(typeof(*f)); + if (!f) + return 0; + if (ctx->protocol) + global_subprog_may_throw(ctx); + bpf_obj_drop(f); + return 0; +} + __noinline static int subprog_ref(struct __sk_buff *ctx) { struct foo *f; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index cb990a7d3d45..5e0b27e7855c 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -149,6 +149,20 @@ int _setsockopt(struct bpf_sockopt *ctx) if (sk && sk->family == AF_NETLINK) goto out; + if (sk && sk->family == AF_INET && sk->type == SOCK_RAW) { + struct bpf_tcp_sock *tp = bpf_tcp_sock(sk); + + if (tp) { + char saved_syn[60]; + + bpf_getsockopt(sk, SOL_TCP, TCP_SAVED_SYN, + &saved_syn, sizeof(saved_syn)); + goto consumed; + } + + goto out; + } + /* Make sure bpf_get_netns_cookie is callable. */ if (bpf_get_netns_cookie(NULL) == 0) @@ -224,6 +238,8 @@ int _setsockopt(struct bpf_sockopt *ctx) return 0; /* couldn't get sk storage */ storage->val = optval[0]; + +consumed: ctx->optlen = -1; /* BPF has consumed this option, don't call kernel * setsockopt handler. */ diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c index d487153a839d..ed5a0011b863 100644 --- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c @@ -29,6 +29,10 @@ unsigned int nr_syn = 0; unsigned int nr_fin = 0; unsigned int nr_hwtstamp = 0; +bool nodelay_est_ok = false; +bool nodelay_hdr_len_reject = false; +bool nodelay_write_hdr_reject = false; + /* Check the header received from the active side */ static int __check_active_hdr_in(struct bpf_sock_ops *skops, bool check_syn) { @@ -300,7 +304,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops) SEC("sockops") int misc_estab(struct bpf_sock_ops *skops) { - int true_val = 1; + int true_val = 1, false_val = 0, ret; switch (skops->op) { case BPF_SOCK_OPS_TCP_LISTEN_CB: @@ -316,10 +320,19 @@ int misc_estab(struct bpf_sock_ops *skops) case BPF_SOCK_OPS_PARSE_HDR_OPT_CB: return handle_parse_hdr(skops); case BPF_SOCK_OPS_HDR_OPT_LEN_CB: + ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val)); + if (ret == -EOPNOTSUPP) + nodelay_hdr_len_reject = true; return handle_hdr_opt_len(skops); case BPF_SOCK_OPS_WRITE_HDR_OPT_CB: + ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val)); + if (ret == -EOPNOTSUPP) + nodelay_write_hdr_reject = true; return handle_write_hdr_opt(skops); case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &false_val, sizeof(false_val)); + if (!ret) + nodelay_est_ok = true; return handle_passive_estab(skops); } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c index 83df4919c224..facafeaf4620 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c @@ -17,6 +17,13 @@ struct { __type(value, int); } sock_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} sock_map_verdict SEC(".maps"); + SEC("sk_msg") int prog_sk_policy(struct sk_msg_md *msg) { @@ -38,3 +45,17 @@ int prog_sk_policy_redir(struct sk_msg_md *msg) bpf_msg_apply_bytes(msg, apply_bytes); return bpf_msg_redirect_map(msg, &sock_map, two, 0); } + +/* + * Verdict program for the reverse-order TLS/sockmap regression test. + * Returns SK_PASS so tcp_read_skb() drains the receive queue via + * sk_psock_verdict_recv() without calling tcp_eat_skb(), which is + * the precondition for the KTLS strparser frag_list UAF. + */ +SEC("sk_skb/verdict") +int prog_skb_verdict_pass(struct __sk_buff *skb) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_call_large_imm.c b/tools/testing/selftests/bpf/progs/verifier_call_large_imm.c new file mode 100644 index 000000000000..7998df07f6a6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_call_large_imm.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +int call_happened = 0; + +/* + * 32765 is the exact minimum number of padding instructions needed to + * trigger the verifier failure, because: + * 1. Counting the wrapper instructions around the padding block (one + * "r0=0" and two "exit" instructions), the actual jump distance + * evaluates to N + 3. + * 2. To overflow the s16 max bound (32767), we need N + 3 > 32767. + * Thus, N = 32765 is the exact minimum padding size required. + */ +static __attribute__((noinline)) void padding_subprog(void) +{ + asm volatile ( + "r0 = 0;" + ".rept 32765;" + "r0 += 0;" + ".endr;" + ::: __clobber_all); +} + +static __attribute__((noinline)) int target_subprog(void) +{ + /* Use volatile variable here to prevent optimization. */ + volatile int magic_ret = 3; + return magic_ret; +} + +SEC("syscall") +__success __retval(3) +int call_large_imm_test(void *ctx) +{ + /* + * Landing pad to handle call error on kernel without the fix, + * preventing kernel panic. + */ + asm volatile ( + "r0 = 0;" + ".rept 32768;" + "r0 += 0;" + ".endr;" + ::: __clobber_all); + + /* + * The call_happened variable is 1 only when the call insn wrongly + * go back to the landing pad above. + */ + if (call_happened == 1) { + /* Use volatile variable here to prevent optimization. */ + volatile int flag = -1; + return flag; + } + + call_happened = 1; + + padding_subprog(); + + return target_subprog(); +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/cgroup/lib/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c index 6a7295347e90..42f54936f4bb 100644 --- a/tools/testing/selftests/cgroup/lib/cgroup_util.c +++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c @@ -106,8 +106,9 @@ int cg_read_strcmp(const char *cgroup, const char *control, /* Handle the case of comparing against empty string */ if (!expected) return -1; - else - size = strlen(expected) + 1; + + /* needs size > 1, otherwise cg_read() reads 0 bytes */ + size = (expected[0] == '\0') ? 2 : strlen(expected) + 1; buf = malloc(size); if (!buf) diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh index 42a6628fb8bc..1c0444729e70 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh @@ -18,7 +18,7 @@ write_test() { echo "testing $interface $value" echo $value > $dir/$interface new=$(cat $dir/$interface) - [[ $value -ne $(cat $dir/$interface) ]] && { + [[ "$value" != "$new" ]] && { echo "$interface write $value failed: new:$new" exit 1 } diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index eeabd34bf083..12f59925500b 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -368,11 +368,15 @@ static int test_percpu_basic(const char *root) for (i = 0; i < 1000; i++) { child = cg_name_indexed(parent, "child", i); - if (!child) - return -1; + if (!child) { + ret = -1; + goto cleanup_children; + } - if (cg_create(child)) + if (cg_create(child)) { + free(child); goto cleanup_children; + } free(child); } diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 85ca4d1ecf9e..82809d5b2478 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -31,6 +31,7 @@ TEST_PROGS = \ hw_stats_l3.sh \ hw_stats_l3_gre.sh \ iou-zcrx.py \ + ipsec_vxlan.py \ irq.py \ loopback.sh \ nic_timestamp.py \ diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config index dd50cb8a7911..8c132ace2b8d 100644 --- a/tools/testing/selftests/drivers/net/hw/config +++ b/tools/testing/selftests/drivers/net/hw/config @@ -3,6 +3,10 @@ CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FUNCTION_ERROR_INJECTION=y +CONFIG_INET6_ESP=y +CONFIG_INET6_ESP_OFFLOAD=y +CONFIG_INET_ESP=y +CONFIG_INET_ESP_OFFLOAD=y CONFIG_IO_URING=y CONFIG_IPV6=y CONFIG_IPV6_GRE=y @@ -14,3 +18,4 @@ CONFIG_NETKIT=y CONFIG_NET_SCH_INGRESS=y CONFIG_UDMABUF=y CONFIG_VXLAN=y +CONFIG_XFRM_USER=y diff --git a/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py b/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py new file mode 100755 index 000000000000..0740a4d85240 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py @@ -0,0 +1,204 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +"""Traffic test for VXLAN + IPsec crypto-offload.""" + +import os + +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge +from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx +from lib.py import CmdExitFailure, NetDrvEpEnv, cmd, defer, ethtool, ip +from lib.py import Iperf3Runner + +# Inner tunnel addresses - TEST-NET-2 (RFC 5737) / doc prefix (RFC 3849) +INNER_V4_LOCAL = "198.51.100.1" +INNER_V4_REMOTE = "198.51.100.2" +INNER_V6_LOCAL = "2001:db8:100::1" +INNER_V6_REMOTE = "2001:db8:100::2" + +# ESP parameters +SPI_OUT = "0x1000" +SPI_IN = "0x1001" +# 128-bit key + 32-bit salt = 20 bytes hex, 128-bit ICV +ESP_AEAD = "aead 'rfc4106(gcm(aes))' 0x" + "01" * 20 + " 128" + + +def xfrm(args, host=None): + """Runs 'ip xfrm' via shell to preserve parentheses in algo names.""" + cmd(f"ip xfrm {args}", shell=True, host=host) + + +def check_xfrm_offload_support(): + """Skips if iproute2 lacks xfrm offload support.""" + out = cmd("ip xfrm state help", fail=False) + if "offload" not in out.stdout + out.stderr: + raise KsftSkipEx("iproute2 too old, missing xfrm offload") + + +def check_esp_hw_offload(cfg): + """Skips if device lacks esp-hw-offload support.""" + check_xfrm_offload_support() + try: + feat = ethtool(f"-k {cfg.ifname}", json=True)[0] + except (CmdExitFailure, IndexError) as e: + raise KsftSkipEx(f"can't query features: {e}") from e + if not feat.get("esp-hw-offload", {}).get("active"): + raise KsftSkipEx("Device does not support esp-hw-offload") + + +def get_tx_drops(cfg): + """Returns TX dropped counter from the physical device.""" + stats = ip("-s -s link show dev " + cfg.ifname, json=True)[0] + return stats["stats64"]["tx"]["dropped"] + + +def setup_vxlan_ipsec(cfg, outer_ipver, inner_ipver): + """Sets up VXLAN tunnel with IPsec transport-mode crypto-offload.""" + vxlan_name = f"vx{os.getpid()}" + local_addr = cfg.addr_v[outer_ipver] + remote_addr = cfg.remote_addr_v[outer_ipver] + + if inner_ipver == "4": + inner_local = f"{INNER_V4_LOCAL}/24" + inner_remote = f"{INNER_V4_REMOTE}/24" + addr_extra = "" + else: + inner_local = f"{INNER_V6_LOCAL}/64" + inner_remote = f"{INNER_V6_REMOTE}/64" + addr_extra = " nodad" + + if outer_ipver == "6": + vxlan_opts = "udp6zerocsumtx udp6zerocsumrx" + else: + vxlan_opts = "noudpcsum" + + # VXLAN tunnel - local side + ip(f"link add {vxlan_name} type vxlan id 100 dstport 4789 {vxlan_opts} " + f"local {local_addr} remote {remote_addr} dev {cfg.ifname}") + defer(ip, f"link del {vxlan_name}") + ip(f"addr add {inner_local} dev {vxlan_name}{addr_extra}") + ip(f"link set {vxlan_name} up") + + # VXLAN tunnel - remote side + ip(f"link add {vxlan_name} type vxlan id 100 dstport 4789 {vxlan_opts} " + f"local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}", + host=cfg.remote) + defer(ip, f"link del {vxlan_name}", host=cfg.remote) + ip(f"addr add {inner_remote} dev {vxlan_name}{addr_extra}", + host=cfg.remote) + ip(f"link set {vxlan_name} up", host=cfg.remote) + + # xfrm state - local outbound SA + xfrm(f"state add src {local_addr} dst {remote_addr} " + f"proto esp spi {SPI_OUT} " + f"{ESP_AEAD} " + f"mode transport offload crypto dev {cfg.ifname} dir out") + defer(xfrm, f"state del src {local_addr} dst {remote_addr} " + f"proto esp spi {SPI_OUT}") + + # xfrm state - local inbound SA + xfrm(f"state add src {remote_addr} dst {local_addr} " + f"proto esp spi {SPI_IN} " + f"{ESP_AEAD} " + f"mode transport offload crypto dev {cfg.ifname} dir in") + defer(xfrm, f"state del src {remote_addr} dst {local_addr} " + f"proto esp spi {SPI_IN}") + + # xfrm state - remote outbound SA (mirror, software crypto) + xfrm(f"state add src {remote_addr} dst {local_addr} " + f"proto esp spi {SPI_IN} " + f"{ESP_AEAD} " + f"mode transport", + host=cfg.remote) + defer(xfrm, f"state del src {remote_addr} dst {local_addr} " + f"proto esp spi {SPI_IN}", host=cfg.remote) + + # xfrm state - remote inbound SA (mirror, software crypto) + xfrm(f"state add src {local_addr} dst {remote_addr} " + f"proto esp spi {SPI_OUT} " + f"{ESP_AEAD} " + f"mode transport", + host=cfg.remote) + defer(xfrm, f"state del src {local_addr} dst {remote_addr} " + f"proto esp spi {SPI_OUT}", host=cfg.remote) + + # xfrm policy - local out + xfrm(f"policy add src {local_addr} dst {remote_addr} " + f"proto udp dport 4789 dir out " + f"tmpl src {local_addr} dst {remote_addr} proto esp mode transport") + defer(xfrm, f"policy del src {local_addr} dst {remote_addr} " + f"proto udp dport 4789 dir out") + + # xfrm policy - local in + xfrm(f"policy add src {remote_addr} dst {local_addr} " + f"proto udp dport 4789 dir in " + f"tmpl src {remote_addr} dst {local_addr} proto esp mode transport") + defer(xfrm, f"policy del src {remote_addr} dst {local_addr} " + f"proto udp dport 4789 dir in") + + # xfrm policy - remote out + xfrm(f"policy add src {remote_addr} dst {local_addr} " + f"proto udp dport 4789 dir out " + f"tmpl src {remote_addr} dst {local_addr} proto esp mode transport", + host=cfg.remote) + defer(xfrm, f"policy del src {remote_addr} dst {local_addr} " + f"proto udp dport 4789 dir out", host=cfg.remote) + + # xfrm policy - remote in + xfrm(f"policy add src {local_addr} dst {remote_addr} " + f"proto udp dport 4789 dir in " + f"tmpl src {local_addr} dst {remote_addr} proto esp mode transport", + host=cfg.remote) + defer(xfrm, f"policy del src {local_addr} dst {remote_addr} " + f"proto udp dport 4789 dir in", host=cfg.remote) + + +def _vxlan_ipsec_variants(): + """Generates outer/inner IP version variants.""" + for outer in ["4", "6"]: + for inner in ["4", "6"]: + yield KsftNamedVariant(f"outer_v{outer}_inner_v{inner}", outer, inner) + + +@ksft_variants(_vxlan_ipsec_variants()) +def test_vxlan_ipsec_crypto_offload(cfg, outer_ipver, inner_ipver): + """Tests VXLAN+IPsec crypto-offload has no TX drops.""" + cfg.require_ipver(outer_ipver) + check_esp_hw_offload(cfg) + + setup_vxlan_ipsec(cfg, outer_ipver, inner_ipver) + + if inner_ipver == "4": + inner_local = INNER_V4_LOCAL + inner_remote = INNER_V4_REMOTE + ping = "ping" + else: + inner_local = INNER_V6_LOCAL + inner_remote = INNER_V6_REMOTE + ping = "ping -6" + + cmd(f"{ping} -c 1 -W 2 {inner_remote}") + + drops_before = get_tx_drops(cfg) + + runner = Iperf3Runner(cfg, server_ip=inner_local, + client_ip=inner_remote) + bw_gbps = runner.measure_bandwidth(reverse=True) + + cfg.wait_hw_stats_settle() + drops_after = get_tx_drops(cfg) + + ksft_eq(drops_after - drops_before, 0, + comment="TX drops during VXLAN+IPsec") + ksft_ge(bw_gbps, 0.1, + comment="Minimum 100Mbps over VXLAN+IPsec") + + +def main(): + """Runs VXLAN+IPsec crypto-offload GSO selftest.""" + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + ksft_run([test_vxlan_ipsec_crypto_offload], args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index f181fa2d38fc..e24660e5c27f 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -48,7 +48,10 @@ class Iperf3Runner: Starts the iperf3 client with the configured options. """ cmdline = self._build_client(streams, duration, reverse) - return cmd(cmdline, background=background, host=self.env.remote) + kwargs = {"background": background, "host": self.env.remote} + if not background: + kwargs["timeout"] = duration + 5 + return cmd(cmdline, **kwargs) def measure_bandwidth(self, reverse=False): """ diff --git a/tools/testing/selftests/drivers/net/shaper.py b/tools/testing/selftests/drivers/net/shaper.py index 11310f19bfa0..e39d270e688d 100755 --- a/tools/testing/selftests/drivers/net/shaper.py +++ b/tools/testing/selftests/drivers/net/shaper.py @@ -1,7 +1,10 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_true, KsftSkipEx +import errno + +from lib.py import ksft_run, ksft_exit +from lib.py import ksft_eq, ksft_raises, ksft_true, KsftSkipEx from lib.py import EthtoolFamily, NetshaperFamily from lib.py import NetDrvEnv from lib.py import NlError @@ -438,6 +441,21 @@ def queue_update(cfg, nl_shaper) -> None: nl_shaper.delete({'ifindex': cfg.ifindex, 'handle': {'scope': 'queue', 'id': i}}) +def dup_leaves(cfg, nl_shaper) -> None: + """ Ensure that the kernel rejects duplicate leaves. """ + if not cfg.groups: + raise KsftSkipEx("device does not support node scope") + + with ksft_raises(NlError) as cm: + nl_shaper.group({ + 'ifindex': cfg.ifindex, + 'leaves':[{'handle': {'scope': 'queue', 'id': 0}}, + {'handle': {'scope': 'queue', 'id': 0}}], + 'handle': {'scope':'node'}, + 'metric': 'bps', + 'bw-max': 10000}) + ksft_eq(cm.exception.error, errno.EINVAL) + def main() -> None: with NetDrvEnv(__file__, queue_count=4) as cfg: cfg.queues = False @@ -453,7 +471,9 @@ def main() -> None: basic_groups, qgroups, delegation, - queue_update], args=(cfg, NetshaperFamily())) + dup_leaves, + queue_update], + args=(cfg, NetshaperFamily())) ksft_exit() diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 6d809f08ab7b..60838b61a2da 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -450,7 +450,7 @@ static inline __noreturn __printf(1, 2) void ksft_exit_skip(const char *msg, ... */ if (ksft_plan || ksft_test_num()) { ksft_cnt.ksft_xskip++; - printf("ok %u # SKIP ", 1 + ksft_test_num()); + printf("ok %u # SKIP ", ksft_test_num()); } else { printf("1..0 # SKIP "); } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 75fb016cd190..cfdce9cd252e 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -76,7 +76,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) memset(s, c, n); } -#define KSELFTEST_PRIO_TEST_F 20000 +#define KSELFTEST_PRIO_TEST 20000 #define KSELFTEST_PRIO_XFAIL 20001 #define TEST_TIMEOUT_DEFAULT 30 @@ -194,7 +194,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) .fixture = &_fixture_global, \ .termsig = _signal, \ .timeout = TEST_TIMEOUT_DEFAULT, }; \ - static void __attribute__((constructor)) _register_##test_name(void) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) _register_##test_name(void) \ { \ __register_test(&_##test_name##_object); \ } \ @@ -238,7 +238,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) FIXTURE_VARIANT(fixture_name); \ static struct __fixture_metadata _##fixture_name##_fixture_object = \ { .name = #fixture_name, }; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) \ _register_##fixture_name##_data(void) \ { \ __register_fixture(&_##fixture_name##_fixture_object); \ @@ -364,7 +364,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) _##fixture_name##_##variant_name##_object = \ { .name = #variant_name, \ .data = &_##fixture_name##_##variant_name##_variant}; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) \ _register_##fixture_name##_##variant_name(void) \ { \ __register_fixture_variant(&_##fixture_name##_fixture_object, \ @@ -468,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) fixture_name##_teardown(_metadata, self, variant); \ } \ static struct __test_metadata *_##fixture_name##_##test_name##_object; \ - static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) \ _register_##fixture_name##_##test_name(void) \ { \ struct __test_metadata *object = mmap(NULL, sizeof(*object), \ @@ -1323,7 +1323,7 @@ static int test_harness_run(int argc, char **argv) return KSFT_FAIL; } -static void __attribute__((constructor)) __constructor_order_first(void) +static void __attribute__((constructor(KSELFTEST_PRIO_TEST))) __constructor_order_first(void) { __constructor_order_forward = true; } diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index e5bbdb5bbdc3..4415c94b2866 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -41,10 +41,10 @@ #include <inttypes.h> #include <limits.h> #include <pthread.h> -#include <sys/mman.h> #include <sys/types.h> #include <sys/stat.h> +#include "kvm_syscalls.h" #include "kvm_util.h" #include "test_util.h" #include "memstress.h" diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index d6528c6f5e03..832ef4dfb99f 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -14,10 +14,10 @@ #include <linux/bitmap.h> #include <linux/falloc.h> #include <linux/sizes.h> -#include <sys/mman.h> #include <sys/types.h> #include <sys/stat.h> +#include "kvm_syscalls.h" #include "kvm_util.h" #include "numaif.h" #include "test_util.h" @@ -510,7 +510,12 @@ static void test_guest_memfd_guest(void) "Default VM type should support INIT_SHARED, supported flags = 0x%x", vm_check_cap(vm, KVM_CAP_GUEST_MEMFD_FLAGS)); - size = vm->page_size; + /* + * Use the max of the host or guest page size for all operations, as + * KVM requires guest_memfd files and memslots to be sized to multiples + * of the host page size. + */ + size = max_t(size_t, vm->page_size, page_size); fd = vm_create_guest_memfd(vm, size, GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_INIT_SHARED); vm_set_user_memory_region2(vm, slot, KVM_MEM_GUEST_MEMFD, gpa, size, NULL, fd, 0); @@ -519,7 +524,7 @@ static void test_guest_memfd_guest(void) memset(mem, 0xaa, size); kvm_munmap(mem, size); - virt_pg_map(vm, gpa, gpa); + virt_map(vm, gpa, gpa, size / vm->page_size); vcpu_args_set(vcpu, 2, gpa, size); vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/include/kvm_syscalls.h b/tools/testing/selftests/kvm/include/kvm_syscalls.h index 843c9904c46f..067a4c9cf452 100644 --- a/tools/testing/selftests/kvm/include/kvm_syscalls.h +++ b/tools/testing/selftests/kvm/include/kvm_syscalls.h @@ -2,8 +2,18 @@ #ifndef SELFTEST_KVM_SYSCALLS_H #define SELFTEST_KVM_SYSCALLS_H +/* + * Include both the kernel and libc versions of mman.h. The kernel provides + * the most up-to-date flags and definitions, while libc provides the syscall + * wrappers tests expect. + */ +#include <linux/mman.h> + +#include <sys/mman.h> #include <sys/syscall.h> +#include <test_util.h> + #define MAP_ARGS0(m,...) #define MAP_ARGS1(m,t,a,...) m(t,a) #define MAP_ARGS2(m,t,a,...) m(t,a), MAP_ARGS1(m,__VA_ARGS__) diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index d9b433b834f1..a56271c237ae 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -19,9 +19,9 @@ #include <errno.h> #include <unistd.h> #include <fcntl.h> -#include <sys/mman.h> #include "kselftest.h" +#include <linux/mman.h> #include <linux/types.h> #define msecs_to_usecs(msec) ((msec) * 1000ULL) diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c index b49690658c60..8be0d09ecf0f 100644 --- a/tools/testing/selftests/kvm/lib/assert.c +++ b/tools/testing/selftests/kvm/lib/assert.c @@ -6,11 +6,14 @@ */ #include "test_util.h" -#include <execinfo.h> + #include <sys/syscall.h> #include "kselftest.h" +#ifdef __GLIBC__ +#include <execinfo.h> + /* Dumps the current stack trace to stderr. */ static void __attribute__((noinline)) test_dump_stack(void); static void test_dump_stack(void) @@ -57,6 +60,9 @@ static void test_dump_stack(void) system(cmd); #pragma GCC diagnostic pop } +#else +static void test_dump_stack(void) {} +#endif static pid_t _gettid(void) { diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index b689c4df4a01..1924a9895834 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -7,7 +7,7 @@ #include "test_util.h" -#include <bits/endian.h> +#include <endian.h> #include <linux/elf.h> #include "kvm_util.h" diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 2a76eca7029d..e08967ef7b7b 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -5,13 +5,13 @@ * Copyright (C) 2018, Google LLC. */ #include "test_util.h" +#include "kvm_syscalls.h" #include "kvm_util.h" #include "processor.h" #include "ucall_common.h" #include <assert.h> #include <sched.h> -#include <sys/mman.h> #include <sys/resource.h> #include <sys/types.h> #include <sys/stat.h> diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 3d02db371422..e977e979470f 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -15,7 +15,6 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <sys/mman.h> #include <time.h> #include <unistd.h> @@ -23,6 +22,7 @@ #include <linux/sizes.h> #include <test_util.h> +#include <kvm_syscalls.h> #include <kvm_util.h> #include <processor.h> #include <ucall_common.h> diff --git a/tools/testing/selftests/kvm/s390/shared_zeropage_test.c b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c index a9e5a01200b8..478381e6f84e 100644 --- a/tools/testing/selftests/kvm/s390/shared_zeropage_test.c +++ b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c @@ -4,11 +4,10 @@ * * Copyright (C) 2024, Red Hat, Inc. */ -#include <sys/mman.h> - #include <linux/fs.h> #include "test_util.h" +#include "kvm_syscalls.h" #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" diff --git a/tools/testing/selftests/kvm/s390/tprot.c b/tools/testing/selftests/kvm/s390/tprot.c index 8054d2b178f0..d86179827a18 100644 --- a/tools/testing/selftests/kvm/s390/tprot.c +++ b/tools/testing/selftests/kvm/s390/tprot.c @@ -4,8 +4,8 @@ * * Copyright IBM Corp. 2021 */ -#include <sys/mman.h> #include "test_util.h" +#include "kvm_syscalls.h" #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 9b919a231c93..e639a9db51ee 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -8,11 +8,11 @@ #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> -#include <sys/mman.h> #include <linux/compiler.h> #include <test_util.h> +#include <kvm_syscalls.h> #include <kvm_util.h> #include <processor.h> diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 7df2bc8eec02..76fcdd1fd3cb 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -220,6 +220,8 @@ static void check_steal_time_uapi(void) }; vcpu_ioctl(vcpu, KVM_HAS_DEVICE_ATTR, &dev); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, 1, 0); + virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, 1); st_ipa = (ulong)ST_GPA_BASE | 1; ret = __vcpu_ioctl(vcpu, KVM_SET_DEVICE_ATTR, &dev); diff --git a/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c index 404f0028e110..0c84c27ea584 100644 --- a/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c +++ b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c @@ -137,6 +137,10 @@ static void run_apic_bus_clock_test(u64 apic_hz, u64 delay_ms, vm_enable_cap(vm, KVM_CAP_X86_APIC_BUS_CYCLES_NS, NSEC_PER_SEC / apic_hz); + TEST_ASSERT_EQ(kvm_check_cap(KVM_CAP_X86_APIC_BUS_CYCLES_NS), 1); + TEST_ASSERT_EQ(vm_check_cap(vm, KVM_CAP_X86_APIC_BUS_CYCLES_NS), + NSEC_PER_SEC / apic_hz); + vcpu = vm_vcpu_add(vm, 0, apic_guest_code); vcpu_args_set(vcpu, 2, apic_hz, delay_ms); diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 788689497e92..77fb4c5d871b 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -986,6 +986,56 @@ TEST_F(hmm, migrate) } /* + * Migrate private file memory to device private memory. + */ +TEST_F(hmm, migrate_file_private) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + int fd; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + fd = hmm_create_file(size); + ASSERT_GE(fd, 0); + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = fd; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + hmm_buffer_free(buffer); +} + +/* * Migrate anonymous memory to device private memory and fault some of it back * to system memory, then try migrating the resulting mix of system and device * private memory to the device. diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index d8468451b3a3..c17b133a81d2 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -103,7 +103,7 @@ RUN_ALL=false RUN_DESTRUCTIVE=false TAP_PREFIX="# " -while getopts "aht:n" OPT; do +while getopts "aht:nd" OPT; do case ${OPT} in "a") RUN_ALL=true ;; "h") usage ;; diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index a275ed584026..f3da38c54d27 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -96,6 +96,7 @@ TEST_PROGS := \ srv6_hl2encap_red_l2vpn_test.sh \ srv6_iptunnel_cache.sh \ stress_reuseport_listen.sh \ + tcp_ecmp_failover.sh \ tcp_fastopen_backup_key.sh \ test_bpf.sh \ test_bridge_backup_port.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh index e8031f68200a..ebdb4c790a5d 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh @@ -4,7 +4,7 @@ ALL_TESTS="vlmc_control_test vlmc_querier_test vlmc_igmp_mld_version_test \ vlmc_last_member_test vlmc_startup_query_test vlmc_membership_test \ vlmc_querier_intvl_test vlmc_query_intvl_test vlmc_query_response_intvl_test \ - vlmc_router_port_test vlmc_filtering_test" + vlmc_router_port_test vlmc_filtering_test vlmc_mcast_toggle_test" NUM_NETIFS=4 CHECK_TC="yes" TEST_GROUP="239.10.10.10" @@ -537,6 +537,34 @@ vlmc_filtering_test() log_test "Disable multicast vlan snooping when vlan filtering is disabled" } +vlmc_mcast_toggle_test() +{ + RET=0 + + ip link add name br1-mcast up type bridge mcast_snooping 1 mcast_querier 1 vlan_filtering 1 + ip link add name dummy1-mcast up master br1-mcast type dummy + + # Enabling per-VLAN multicast snooping should disable the per-port + # multicast context on "dummy1-mcast". + ip link set dev br1-mcast type bridge mcast_vlan_snooping 1 + + # Toggling multicast snooping on the bridge should not affect the + # per-port multicast context on "dummy1-mcast" given that per-VLAN + # multicast snooping is enabled. + ip link set dev br1-mcast type bridge mcast_snooping 0 + ip link set dev br1-mcast type bridge mcast_snooping 1 + + # If both the per-port and per-{port, VLAN} multicast contexts are + # enabled on "dummy1-mcast", removing it from the bridge will result + # in a splat. + ip link set dev dummy1-mcast nomaster + + log_test "Toggling mcast snooping with per-VLAN mcast snooping enabled" + + ip link del dev dummy1-mcast + ip link del dev br1-mcast +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index b2b99889942f..845c26dd01a9 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -273,8 +273,8 @@ setup() ip -netns $ioam_node_beta link set ioam-veth-betaR name veth1 &>/dev/null ip -netns $ioam_node_gamma link set ioam-veth-gamma name veth0 &>/dev/null - ip -netns $ioam_node_alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null ip -netns $ioam_node_alpha addr add 2001:db8:1::50/64 dev veth0 &>/dev/null + ip -netns $ioam_node_alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null ip -netns $ioam_node_alpha link set veth0 up &>/dev/null ip -netns $ioam_node_alpha link set lo up &>/dev/null ip -netns $ioam_node_alpha route add 2001:db8:2::/64 \ diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c index 64f05229ab24..ded3f896e622 100644 --- a/tools/testing/selftests/net/lib/xdp_native.bpf.c +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -268,6 +268,17 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port) return XDP_PASS; } +static __always_inline __u16 csum_fold_helper(__u32 csum) +{ + csum = (csum & 0xffff) + (csum >> 16); + return ~((csum & 0xffff) + (csum >> 16)); +} + +static __always_inline __u16 csum_fold_udp_helper(__u32 csum) +{ + return csum_fold_helper(csum) ? : 0xffff; +} + static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) { void *data_end = (void *)(long)ctx->data_end; @@ -281,21 +292,22 @@ static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) if (eth->h_proto == bpf_htons(ETH_P_IP)) { struct iphdr *iph = data + sizeof(*eth); - __u16 total_len; if (iph + 1 > (struct iphdr *)data_end) return NULL; - iph->tot_len = bpf_htons(bpf_ntohs(iph->tot_len) + offset); - udph = (void *)eth + sizeof(*iph) + sizeof(*eth); if (!udph || udph + 1 > (struct udphdr *)data_end) return NULL; - len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + len = iph->tot_len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + iph->tot_len = len_new; + iph->check = csum_fold_helper( + bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), ~((__u32)iph->check))); } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { struct ipv6hdr *ipv6h = data + sizeof(*eth); - __u16 payload_len; if (ipv6h + 1 > (struct ipv6hdr *)data_end) return NULL; @@ -304,33 +316,27 @@ static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) if (!udph || udph + 1 > (struct udphdr *)data_end) return NULL; - *udp_csum = ~((__u32)udph->check); - len = ipv6h->payload_len; len_new = bpf_htons(bpf_ntohs(len) + offset); ipv6h->payload_len = len_new; - - *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, - sizeof(len_new), *udp_csum); - - len = udph->len; - len_new = bpf_htons(bpf_ntohs(udph->len) + offset); - *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, - sizeof(len_new), *udp_csum); } else { return NULL; } + len = udph->len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + + *udp_csum = ~((__u32)udph->check); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + udph->len = len_new; return udph; } -static __u16 csum_fold_helper(__u32 csum) -{ - return ~((csum & 0xffff) + (csum >> 16)) ? : 0xffff; -} - static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, unsigned long hdr_len) { @@ -359,7 +365,7 @@ static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, return -1; udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0) return -1; @@ -403,7 +409,7 @@ static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset) return -1; udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); buff_len = bpf_xdp_get_buff_len(ctx); @@ -484,8 +490,7 @@ static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len, return -1; udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); - - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0) return -1; @@ -542,7 +547,7 @@ static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len, return -1; udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) return -1; diff --git a/tools/testing/selftests/net/link_netns.py b/tools/testing/selftests/net/link_netns.py index aab043c59d69..6d1f863b6262 100755 --- a/tools/testing/selftests/net/link_netns.py +++ b/tools/testing/selftests/net/link_netns.py @@ -3,13 +3,14 @@ import time -from lib.py import ksft_run, ksft_exit, ksft_true +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_true from lib.py import ip from lib.py import NetNS, NetNSEnter from lib.py import RtnlFamily LINK_NETNSID = 100 +LINK_NETNSID2 = 200 def test_event() -> None: @@ -32,6 +33,57 @@ def test_event() -> None: "Received unexpected link notification") +def test_event_all_nsid() -> None: + """NETLINK_LISTEN_ALL_NSID notifications: local events must not + carry nsid even with a self-referential mapping. Remote events + must carry the correct nsid.""" + + with NetNS() as ns1, NetNS() as ns2: + net1, net2 = str(ns1), str(ns2) + + with NetNSEnter(net1): + rtnl = RtnlFamily() + rtnl.ntf_listen_all_nsid() + rtnl.ntf_subscribe("rtnlgrp-link") + + # Case 1: no nsid assigned, local event, no nsid expected. + ip("link add dummy-lo type dummy", ns=net1) + + # Case 2: self-referential nsid, local event, still no nsid. + ip(f"netns set {net1} {LINK_NETNSID}", ns=net1) + ip("link add dummy-sr type dummy", ns=net1) + + # Case 3: remote event, nsid present. + ip(f"netns set {net2} {LINK_NETNSID2}", ns=net1) + ip("link add dummy-re type dummy", ns=net2) + + # Collect the three newlink events, ignoring unrelated noise. + events = {} + for msg in rtnl.poll_ntf(duration=1): + if msg['name'] == 'getlink': + ifname = msg['msg'].get('ifname') + if ifname in ('dummy-lo', 'dummy-sr', 'dummy-re'): + events[ifname] = msg + if len(events) == 3: + break + + ksft_true('dummy-lo' in events, "missing local event") + ksft_true(events['dummy-lo'].get('nsid') is None, + "local event without nsid should not carry nsid") + + ksft_true('dummy-sr' in events, "missing self-ref event") + ksft_true(events['dummy-sr'].get('nsid') is None, + "local event with self-ref nsid should not carry nsid") + + ksft_true('dummy-re' in events, "missing remote event") + ksft_eq(events['dummy-re'].get('nsid'), LINK_NETNSID2, + "remote event should carry nsid") + + ip("link del dummy-lo", ns=net1) + ip("link del dummy-sr", ns=net1) + ip("link del dummy-re", ns=net2) + + def validate_link_netns(netns, ifname, link_netnsid) -> bool: link_info = ip(f"-d link show dev {ifname}", ns=netns, json=True) if not link_info: @@ -133,7 +185,12 @@ def test_peer_net() -> None: def main() -> None: - ksft_run([test_event, test_link_net, test_peer_net]) + ksft_run([ + test_event, + test_event_all_nsid, + test_link_net, + test_peer_net, + ]) ksft_exit() diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index a6447f7a31fe..d158678fa6ab 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -401,7 +401,7 @@ do_transfer() mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" local start - start=$(date +%s%3N) + start=$(date +%s%N) ip netns exec ${connector_ns} \ ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $extra_args $connect_addr < "$cin" > "$cout" & @@ -423,7 +423,7 @@ do_transfer() fi local stop - stop=$(date +%s%3N) + stop=$(date +%s%N) if $capture; then sleep 1 @@ -439,7 +439,7 @@ do_transfer() fi local duration - duration=$((stop-start)) + duration=$(((stop-start) / 1000000)) printf "(duration %05sms) " "${duration}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index beec41f6662a..5acd12021e6e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1828,6 +1828,22 @@ chk_add_tx_nr() fi } +chk_add_drop_tx_nr() +{ + local drop_tx_nr=$1 + local count + + print_check "add addr tx drop" + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTxDrop") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$drop_tx_nr" ]; then + fail_test "got $count ADD_ADDR drop[s] TX, expected $drop_tx_nr" + else + print_ok + fi +} + chk_rm_nr() { local rm_addr_nr=$1 @@ -3278,6 +3294,21 @@ add_addr_ports_tests() chk_mpc_endp_attempt ${retl} 1 fi + + # first signal address drops, second one still progresses + if reset "signal addr list progresses after tx drop"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 0 + ip netns exec $ns1 sysctl -q net.ipv4.tcp_timestamps=1 + ip netns exec $ns2 sysctl -q net.ipv4.tcp_timestamps=1 + + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal port 10100 + pm_nl_add_endpoint $ns1 dead:beef:3::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 + chk_add_drop_tx_nr 1 + chk_add_tx_nr 1 1 + chk_add_nr 1 1 0 + fi } bind_tests() diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 5fea7e7df628..5ef6033775c8 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -28,7 +28,7 @@ declare -rx MPTCP_LIB_AF_INET6=10 MPTCP_LIB_SUBTESTS=() MPTCP_LIB_SUBTESTS_DUPLICATED=0 MPTCP_LIB_SUBTEST_FLAKY=0 -MPTCP_LIB_SUBTESTS_LAST_TS_MS= +MPTCP_LIB_SUBTESTS_LAST_TS_NS= MPTCP_LIB_TEST_COUNTER=0 MPTCP_LIB_TEST_FORMAT="%02u %-50s" MPTCP_LIB_IP_MPTCP=0 @@ -236,7 +236,7 @@ mptcp_lib_kversion_ge() { } mptcp_lib_subtests_last_ts_reset() { - MPTCP_LIB_SUBTESTS_LAST_TS_MS="$(date +%s%3N)" + MPTCP_LIB_SUBTESTS_LAST_TS_NS="$(date +%s%N)" } mptcp_lib_subtests_last_ts_reset @@ -255,7 +255,7 @@ __mptcp_lib_result_check_duplicated() { __mptcp_lib_result_add() { local result="${1}" local time="time=" - local ts_prev_ms + local ts_prev_ns shift local id=$((${#MPTCP_LIB_SUBTESTS[@]} + 1)) @@ -265,9 +265,9 @@ __mptcp_lib_result_add() { # not to add two '#' [[ "${*}" != *"#"* ]] && time="# ${time}" - ts_prev_ms="${MPTCP_LIB_SUBTESTS_LAST_TS_MS}" + ts_prev_ns="${MPTCP_LIB_SUBTESTS_LAST_TS_NS}" mptcp_lib_subtests_last_ts_reset - time+="$((MPTCP_LIB_SUBTESTS_LAST_TS_MS - ts_prev_ms))ms" + time+="$(((MPTCP_LIB_SUBTESTS_LAST_TS_NS - ts_prev_ns) / 1000000))ms" MPTCP_LIB_SUBTESTS+=("${result} ${id} - ${KSFT_TEST}: ${*} ${time}") } @@ -474,20 +474,24 @@ mptcp_lib_wait_local_port_listen() { wait_local_port_listen "${@}" "tcp" } +# $1: error file, $2: cmd, $3: expected msg, [$4: expected error] mptcp_lib_check_output() { local err="${1}" local cmd="${2}" local expected="${3}" + local exp_error="${4:-0}" local cmd_ret=0 local out - if ! out=$(${cmd} 2>"${err}"); then - cmd_ret=${?} - fi + out=$(${cmd} 2>"${err}") || cmd_ret=1 - if [ ${cmd_ret} -ne 0 ]; then - mptcp_lib_pr_fail "command execution '${cmd}' stderr" - cat "${err}" + if [ "${cmd_ret}" != "${exp_error}" ]; then + mptcp_lib_pr_fail "unexpected returned code for '${cmd}', info:" + if [ "${exp_error}" = 0 ]; then + cat "${err}" + else + echo "${out}" + fi return 2 elif [ "${out}" = "${expected}" ]; then return 0 diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 123d9d7a0278..04594dfc22b1 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -122,10 +122,12 @@ check() local cmd="$1" local expected="$2" local msg="$3" + local exp_error="$4" local rc=0 mptcp_lib_print_title "$msg" - mptcp_lib_check_output "${err}" "${cmd}" "${expected}" || rc=${?} + mptcp_lib_check_output "${err}" "${cmd}" "${expected}" "${exp_error}" || + rc=${?} if [ ${rc} -eq 2 ]; then mptcp_lib_result_fail "${msg} # error ${rc}" ret=${KSFT_FAIL} @@ -158,13 +160,13 @@ check "show_endpoints" \ "3,10.0.1.3,signal backup")" "dump addrs" del_endpoint 2 -check "get_endpoint 2" "" "simple del addr" +check "get_endpoint 2" "" "simple del addr" 1 check "show_endpoints" \ "$(format_endpoints "1,10.0.1.1" \ "3,10.0.1.3,signal backup")" "dump addrs after del" add_endpoint 10.0.1.3 2>/dev/null -check "get_endpoint 4" "" "duplicate addr" +check "get_endpoint 4" "" "duplicate addr" 1 add_endpoint 10.0.1.4 flags signal check "get_endpoint 4" "$(format_endpoints "4,10.0.1.4,signal")" "id addr increment" @@ -173,7 +175,7 @@ for i in $(seq 5 9); do add_endpoint "10.0.1.${i}" flags signal >/dev/null 2>&1 done check "get_endpoint 9" "$(format_endpoints "9,10.0.1.9,signal")" "hard addr limit" -check "get_endpoint 10" "" "above hard addr limit" +check "get_endpoint 10" "" "above hard addr limit" 1 del_endpoint 9 for i in $(seq 10 255); do @@ -192,9 +194,13 @@ check "show_endpoints" \ flush_endpoint check "show_endpoints" "" "flush addrs" -add_endpoint 10.0.1.1 flags unknown -check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" "ignore unknown flags" -flush_endpoint +# "unknown" flag is only supported by pm_nl_ctl +if ! mptcp_lib_is_ip_mptcp; then + add_endpoint 10.0.1.1 flags unknown + check "show_endpoints" "$(format_endpoints "1,10.0.1.1")" \ + "ignore unknown flags" + flush_endpoint +fi set_limits 9 1 2>/dev/null check "get_limits" "${default_limits}" "rcv addrs above hard limit" diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index ee2d1a5254f8..d953ee218c0f 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -26,6 +26,7 @@ TEST_PROGS := \ nft_concat_range.sh \ nft_conntrack_helper.sh \ nft_fib.sh \ + nft_fib_nexthop.sh \ nft_flowtable.sh \ nft_interface_stress.sh \ nft_meta.sh \ diff --git a/tools/testing/selftests/net/netfilter/nft_fib_nexthop.sh b/tools/testing/selftests/net/netfilter/nft_fib_nexthop.sh new file mode 100755 index 000000000000..c4f203057382 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/nft_fib_nexthop.sh @@ -0,0 +1,152 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# shellcheck disable=SC2154 +# +# Exercise nft_fib6_eval()'s sibling/nh enumeration on three route shapes: +# 1) route via a single external nexthop (nhid) +# 2) route via an external nexthop group (nhid -> group, two members) +# 3) route via old-style multipath (nexthop ... nexthop ...) +# +# In each scenario the route's nexthop set contains veth0 (the iif of the +# test packet). nft_fib6_info_nh_uses_dev() must walk the set and report +# veth0 as a valid oif. For (2) and (3) the matching nexthop is the second +# member, so the walk has to traverse beyond the primary nh. +# +# After sending $PKTS ICMPv6 echo requests from ns1, check two counters on +# nsrouter: +# nf_ok -- `fib daddr . iif oif eq "veth0"` must equal $PKTS +# nf_bad -- `fib daddr . iif oif missing` must stay at 0 +# Both rules also match on iif veth0 and ip6 daddr dead:dead::/64 so that +# kernel-generated ND/MLD/RA traffic cannot pollute the counters. +# +# Topology similar to nft_fib.sh, without ns2; two dummy interfaces on +# nsrouter host extra nh devices: +# +# dead:1::99 dead:1::1 +# ns1 <----veth----> nsrouter --- dummy0 dead:2::1 +# \-- dummy1 dead:9::1 + +source lib.sh + +ret=0 +PKTS=3 + +checktool "nft --version" "run test without nft" +checktool "ip -V" "run test without iproute2" + +setup_ns nsrouter ns1 +trap cleanup_all_ns EXIT + +if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" \ + > /dev/null 2>&1; then + echo "SKIP: No virtual ethernet pair device support in kernel" + exit $ksft_skip +fi + +ip -net "$ns1" link set lo up +ip -net "$ns1" link set eth0 up +ip -net "$ns1" -6 addr add dead:1::99/64 dev eth0 nodad +ip -net "$ns1" -6 route add default via dead:1::1 + +ip -net "$nsrouter" link set lo up +ip -net "$nsrouter" link set veth0 up +ip -net "$nsrouter" -6 addr add dead:1::1/64 dev veth0 nodad + +if ! ip -net "$nsrouter" link add dummy0 type dummy 2>/dev/null; then + echo "SKIP: dummy netdev not available" + exit $ksft_skip +fi +ip -net "$nsrouter" link set dummy0 up +ip -net "$nsrouter" -6 addr add dead:2::1/64 dev dummy0 nodad + +ip -net "$nsrouter" link add dummy1 type dummy +ip -net "$nsrouter" link set dummy1 up +ip -net "$nsrouter" -6 addr add dead:9::1/64 dev dummy1 nodad + +ip netns exec "$nsrouter" sysctl -q net.ipv6.conf.all.forwarding=1 + +load_fib_rule() { + # filter on iif + daddr so the counters only see our test packets + ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF +flush ruleset +table ip6 t { + counter nf_ok { } + counter nf_bad { } + chain c { + type filter hook prerouting priority 0; policy accept; + iif "veth0" ip6 daddr dead:dead::/64 fib daddr . iif oif eq "veth0" counter name nf_ok + iif "veth0" ip6 daddr dead:dead::/64 fib daddr . iif oif missing counter name nf_bad + } +} +EOF +} + +bad_counter() { + local counter=$1 + local expect=$2 + local tag=$3 + + echo "FAIL ($tag): counter $counter has unexpected value (expected \"$expect\")" 1>&2 + ip netns exec "$nsrouter" nft list counter ip6 t "$counter" 1>&2 +} + +run_scenario() { + local what="$1"; shift + # counter output format is "packets PACKET_NUM bytes BYTES_NUM"; + # we only care about the packet count + local expect_ok="packets $PKTS bytes" + local expect_bad="packets 0 bytes" + local lret=0 + + # reset route + nexthop state between scenarios + ip -net "$nsrouter" -6 route del dead:dead::/64 > /dev/null 2>&1 || true + ip -net "$nsrouter" nexthop flush > /dev/null 2>&1 || true + + # run the scenario function passed by the caller + "$@" || echo "WARN ($what): scenario setup returned non-zero" + + load_fib_rule || { echo "FAIL ($what): nft load"; ret=1; return; } + + # ping a daddr inside dead:dead::/64 so fib has to walk the nh set + ip netns exec "$ns1" ping -6 -c "$PKTS" -i 0.1 -W 1 dead:dead::1 \ + > /dev/null 2>&1 || true + + # verify the packets went through the expected fib path + if ! ip netns exec "$nsrouter" nft list counter ip6 t nf_ok | grep -q "$expect_ok"; then + bad_counter nf_ok "$expect_ok" "$what" + lret=1 + fi + if ! ip netns exec "$nsrouter" nft list counter ip6 t nf_bad | grep -q "$expect_bad"; then + bad_counter nf_bad "$expect_bad" "$what" + lret=1 + fi + + if [ $lret -eq 0 ]; then + echo "PASS: $what" + else + ret=1 + fi +} + +scenario_single_nh() { + ip -net "$nsrouter" nexthop add id 1 via dead:1::99 dev veth0 + ip -net "$nsrouter" -6 route add dead:dead::/64 nhid 1 +} +run_scenario "single external nexthop (nhid -> veth0)" scenario_single_nh + +scenario_nh_group() { + ip -net "$nsrouter" nexthop add id 1 via dead:2::2 dev dummy0 + ip -net "$nsrouter" nexthop add id 2 via dead:1::99 dev veth0 + ip -net "$nsrouter" nexthop add id 100 group 1/2 + ip -net "$nsrouter" -6 route add dead:dead::/64 nhid 100 +} +run_scenario "nexthop group (dummy0 + veth0)" scenario_nh_group + +scenario_old_multipath() { + ip -net "$nsrouter" -6 route add dead:dead::/64 \ + nexthop via dead:2::2 dev dummy0 \ + nexthop via dead:1::99 dev veth0 +} +run_scenario "old-style multipath (sibling on veth0)" scenario_old_multipath + +exit $ret diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index b327d3061ed5..3cdd953f6813 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -26,6 +26,7 @@ tests=" netlink_checks ovsnl: validate netlink attrs and settings upcall_interfaces ovs: test the upcall interfaces tunnel_metadata ovs: test extraction of tunnel metadata + tunnel_refcount ovs: test tunnel vport reference cleanup drop_reason drop: test drop reasons are emitted psample psample: Sampling packets with psample" @@ -830,6 +831,42 @@ test_tunnel_metadata() { return 0 } +test_tunnel_refcount() { + sbxname="test_tunnel_refcount" + sbx_add "${sbxname}" || return 1 + + ovs_sbx "${sbxname}" ip netns add trefns || return 1 + on_exit "ovs_sbx ${sbxname} ip netns del trefns" + + for tun_type in gre vxlan geneve; do + info "testing ${tun_type} tunnel vport refcount" + + ovs_sbx "${sbxname}" ip netns exec trefns \ + python3 $ovs_base/ovs-dpctl.py \ + add-dp dp-${tun_type} || return 1 + + ovs_sbx "${sbxname}" ip netns exec trefns \ + python3 $ovs_base/ovs-dpctl.py \ + add-if --no-lwt -t ${tun_type} \ + dp-${tun_type} ovs-${tun_type}0 || return 1 + + ovs_wait ip -netns trefns link show \ + ovs-${tun_type}0 >/dev/null 2>&1 || return 1 + + info "deleting dp - may hang if reference counting is broken" + ovs_sbx "${sbxname}" ip netns exec trefns \ + python3 $ovs_base/ovs-dpctl.py \ + del-dp dp-${tun_type} & + + dev_removed() { + ! ip -netns trefns link show "$1" >/dev/null 2>&1 + } + ovs_wait dev_removed dp-${tun_type} || return 1 + ovs_wait dev_removed ovs-${tun_type}0 || return 1 + done + return 0 +} + run_test() { ( tname="$1" diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 848f61fdcee0..bbe35e2718d2 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -11,7 +11,6 @@ import logging import math import multiprocessing import re -import socket import struct import sys import time @@ -2069,7 +2068,7 @@ class OvsVport(GenericNetlinkSocket): elif vport_type == "internal": return OvsVport.OVS_VPORT_TYPE_INTERNAL elif vport_type == "gre": - return OvsVport.OVS_VPORT_TYPE_INTERNAL + return OvsVport.OVS_VPORT_TYPE_GRE elif vport_type == "vxlan": return OvsVport.OVS_VPORT_TYPE_VXLAN elif vport_type == "geneve": @@ -2121,6 +2120,7 @@ class OvsVport(GenericNetlinkSocket): ) TUNNEL_DEFAULTS = [("geneve", 6081), + ("gre", 0), ("vxlan", 4789)] for tnl in TUNNEL_DEFAULTS: @@ -2129,9 +2129,13 @@ class OvsVport(GenericNetlinkSocket): dport = tnl[1] if not lwt: + if tnl[0] == "gre": + # GRE tunnels have no options. + break + vportopt = OvsVport.ovs_vport_msg.vportopts() vportopt["attrs"].append( - ["OVS_TUNNEL_ATTR_DST_PORT", socket.htons(dport)] + ["OVS_TUNNEL_ATTR_DST_PORT", dport] ) msg["attrs"].append( ["OVS_VPORT_ATTR_OPTIONS", vportopt] @@ -2145,6 +2149,9 @@ class OvsVport(GenericNetlinkSocket): geneve_port=dport, geneve_collect_metadata=True, geneve_udp_zero_csum6_rx=1) + elif tnl[0] == "gre": + ipr.link("add", ifname=vport_ifname, kind="gretap", + gre_collect_metadata=True) elif tnl[0] == "vxlan": ipr.link("add", ifname=vport_ifname, kind=tnl[0], vxlan_learning=0, vxlan_collect_metadata=1, @@ -2563,7 +2570,7 @@ def print_ovsdp_full(dp_lookup_rep, ifindex, ndb=NDB(), vpl=OvsVport()): if vpo: dpo = vpo.get_attr("OVS_TUNNEL_ATTR_DST_PORT") if dpo: - opts += " tnl-dport:%s" % socket.ntohs(dpo) + opts += " tnl-dport:%s" % dpo print( " port %d: %s (%s%s)" % ( @@ -2632,7 +2639,7 @@ def main(argv): "--ptype", type=str, default="netdev", - choices=["netdev", "internal", "geneve", "vxlan"], + choices=["netdev", "internal", "gre", "geneve", "vxlan"], help="Interface type (default netdev)", ) addifcmd.add_argument( @@ -2645,7 +2652,7 @@ def main(argv): addifcmd.add_argument( "-l", "--lwt", - type=bool, + action=argparse.BooleanOptionalAction, default=True, help="Use LWT infrastructure instead of vport (default true)." ) diff --git a/tools/testing/selftests/net/ovpn/test-close-socket.sh b/tools/testing/selftests/net/ovpn/test-close-socket.sh index af1532b4d2da..ec9a51bbf3c9 100755 --- a/tools/testing/selftests/net/ovpn/test-close-socket.sh +++ b/tools/testing/selftests/net/ovpn/test-close-socket.sh @@ -53,7 +53,7 @@ ovpn_run_ping_traffic() { for p in $(seq 1 ${OVPN_NUM_PEERS}); do ovpn_cmd_ok "send ping traffic to peer ${p}" \ - ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \ + ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \ 5.5.5.$((p + 1)) done } diff --git a/tools/testing/selftests/net/ovpn/test-mark.sh b/tools/testing/selftests/net/ovpn/test-mark.sh index 5a8f47554286..7c1d56e9c525 100755 --- a/tools/testing/selftests/net/ovpn/test-mark.sh +++ b/tools/testing/selftests/net/ovpn/test-mark.sh @@ -66,7 +66,7 @@ ovpn_mark_run_baseline_traffic() { for p in $(seq 1 3); do ovpn_cmd_ok "send baseline traffic to peer ${p}" \ - ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \ + ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \ 5.5.5.$((p + 1)) done } @@ -101,7 +101,7 @@ ovpn_mark_verify_drop_traffic() { local total_count for p in $(seq 1 3); do - if ping_output=$(ip netns exec ovpn_peer0 ping -qfc 500 -w 1 \ + if ping_output=$(ip netns exec ovpn_peer0 ping -qfc 100 -w 1 \ 5.5.5.$((p + 1)) 2>&1); then printf '%s\n' "expected ping to peer ${p} to fail \ after nft drop rule" @@ -144,7 +144,7 @@ ovpn_mark_verify_traffic_recovery() { sleep 1 for p in $(seq 1 3); do ovpn_cmd_ok "send recovery traffic to peer ${p}" \ - ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \ + ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \ 5.5.5.$((p + 1)) done } diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh index b50dbe45a4d0..9b5610837032 100755 --- a/tools/testing/selftests/net/ovpn/test.sh +++ b/tools/testing/selftests/net/ovpn/test.sh @@ -98,10 +98,10 @@ ovpn_run_basic_traffic() { sleep 0.3 ovpn_cmd_ok "send baseline traffic to peer ${p}" \ ip netns exec ovpn_peer0 \ - ping -qfc 500 -w 3 5.5.5.$((p + 1)) + ping -qfc 100 -w 3 5.5.5.$((p + 1)) ovpn_cmd_ok "send large-payload traffic to peer ${p}" \ ip netns exec ovpn_peer0 \ - ping -qfc 500 -s 3000 -w 3 5.5.5.$((p + 1)) + ping -qfc 100 -s 3000 -w 3 5.5.5.$((p + 1)) wait "${tcpdump_pid1}" || return 1 wait "${tcpdump_pid2}" || return 1 @@ -110,7 +110,7 @@ ovpn_run_basic_traffic() { ovpn_run_lan_traffic() { ovpn_cmd_ok "ping LAN behind peer1" \ - ip netns exec ovpn_peer0 ping -qfc 500 -w 3 "${OVPN_LAN_IP}" + ip netns exec ovpn_peer0 ping -qfc 100 -w 3 "${OVPN_LAN_IP}" } ovpn_run_float_mode() { @@ -127,7 +127,7 @@ ovpn_run_float_mode() { for p in $(seq 1 ${OVPN_NUM_PEERS}); do peer_ns="ovpn_peer${p}" ovpn_cmd_ok "ping tunnel after float peer ${p}" \ - ip netns exec "${peer_ns}" ping -qfc 500 -w 3 5.5.5.1 + ip netns exec "${peer_ns}" ping -qfc 100 -w 3 5.5.5.1 done } diff --git a/tools/testing/selftests/net/rds/config b/tools/testing/selftests/net/rds/config index 97db7ecb892a..3d62d0c750a8 100644 --- a/tools/testing/selftests/net/rds/config +++ b/tools/testing/selftests/net/rds/config @@ -1,3 +1,4 @@ +CONFIG_MODULES=n CONFIG_NET_NS=y CONFIG_NET_SCH_NETEM=y CONFIG_RDS=y diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index c499953d4885..ace3a99023ed 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -24,6 +24,8 @@ ALL_TESTS=" kci_test_macsec kci_test_macsec_vlan kci_test_team_bridge_macvlan + kci_test_bridge_promisc_netlink + kci_test_bridge_promisc_sysfs kci_test_ipsec kci_test_ipsec_offload kci_test_fdb_get @@ -61,6 +63,14 @@ check_fail() fi } +sysfs_write() +{ + local val="$1" + local path="$2" + + echo "$val" > "$path" +} + run_cmd_common() { local cmd="$*" @@ -680,6 +690,59 @@ kci_test_team_bridge_macvlan() end_test "PASS: team_bridge_macvlan" } +# Test that changing bridge port flags via the netlink path does not sleep with +# the bridge spin lock held. +kci_test_bridge_promisc_netlink() +{ + local dummy="test_dummy1" + local bridge="test_br1" + local team="test_team1" + local ret=0 + + run_cmd ip link add $team up type team + run_cmd ip link add $bridge up type bridge vlan_filtering 1 + run_cmd ip link add $dummy up type dummy + run_cmd ip link set $dummy master $bridge + run_cmd ip link set $team master $bridge + + # This causes the bridge driver to sync all the static FDB entries to + # the team device (which supports unicast filtering) and remove it from + # promiscuous mode. The call to dev_set_promiscuity() can sleep due to + # Rx mode inlining, which is a problem if the bridge spin lock is held. + run_cmd bridge link set dev $dummy flood off learning off + + run_cmd ip link del $dummy + run_cmd ip link del $bridge + run_cmd ip link del $team + + end_test "PASS: bridge_promisc_netlink" +} + +# Same as kci_test_bridge_promisc_netlink(), but the flags are changed via the +# sysfs path. +kci_test_bridge_promisc_sysfs() +{ + local dummy="test_dummy1" + local bridge="test_br1" + local team="test_team1" + local ret=0 + + run_cmd ip link add $team up type team + run_cmd ip link add $bridge up type bridge vlan_filtering 1 + run_cmd ip link add $dummy up type dummy + run_cmd ip link set $dummy master $bridge + run_cmd ip link set $team master $bridge + + run_cmd sysfs_write 0 /sys/class/net/$dummy/brport/unicast_flood + run_cmd sysfs_write 0 /sys/class/net/$dummy/brport/learning + + run_cmd ip link del $dummy + run_cmd ip link del $bridge + run_cmd ip link del $team + + end_test "PASS: bridge_promisc_sysfs" +} + #------------------------------------------------------------------- # Example commands # ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ diff --git a/tools/testing/selftests/net/tcp_ecmp_failover.sh b/tools/testing/selftests/net/tcp_ecmp_failover.sh new file mode 100755 index 000000000000..5768aa8bff6a --- /dev/null +++ b/tools/testing/selftests/net/tcp_ecmp_failover.sh @@ -0,0 +1,216 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright 2026 Google LLC. +# +# This test verifies TCP flow failover between ECMP routes +# upon carrier loss on the active device. +# +# socat -----------------------------> socat +# | +# .-- veth-c1 -|- veth-s1 --. +# dummy0 -| | |-- dummy0 +# '-- veth-c2 -|- veth-s2 --' +# | +# + +REQUIRE_JQ=no +REQUIRE_MZ=no +NUM_NETIFS=0 + +source forwarding/lib.sh + +CLIENT_IP="10.0.59.1" +SERVER_IP="10.0.92.1" +CLIENT_IP6="2001:db8:5a9a::1" +SERVER_IP6="2001:db8:9292::1" + +setup_server() +{ + IP="ip -n $server" + NS_EXEC="ip netns exec $server" + + $IP link add dummy0 type dummy + $IP link set dummy0 up + + $IP -4 addr add $SERVER_IP/32 dev dummy0 + $IP -6 addr add $SERVER_IP6/128 dev dummy0 nodad + + $IP link set veth-s1 up + $IP link set veth-s2 up + + $IP -4 addr add 192.168.1.2/24 dev veth-s1 + $IP -4 addr add 192.168.2.2/24 dev veth-s2 + + $IP -4 route add $CLIENT_IP/32 \ + nexthop via 192.168.1.1 dev veth-s1 weight 1 \ + nexthop via 192.168.2.1 dev veth-s2 weight 1 + + $IP -6 addr add 2001:db8:1::2/64 dev veth-s1 nodad + $IP -6 addr add 2001:db8:2::2/64 dev veth-s2 nodad + + $IP -6 route add $CLIENT_IP6/128 \ + nexthop via 2001:db8:1::1 dev veth-s1 weight 1 \ + nexthop via 2001:db8:2::1 dev veth-s2 weight 1 +} + +setup_client() +{ + IP="ip -n $client" + NS_EXEC="ip netns exec $client" + + $IP link add dummy0 type dummy + $IP link set dummy0 up + + $IP -4 addr add $CLIENT_IP/32 dev dummy0 + $IP -6 addr add $CLIENT_IP6/128 dev dummy0 nodad + + $IP link set veth-c1 up + $IP link set veth-c2 up + + $IP -4 addr add 192.168.1.1/24 dev veth-c1 + $IP -4 addr add 192.168.2.1/24 dev veth-c2 + + $IP -4 route add $SERVER_IP/32 \ + nexthop via 192.168.1.2 dev veth-c1 weight 1 \ + nexthop via 192.168.2.2 dev veth-c2 weight 1 + + $IP -6 addr add 2001:db8:1::1/64 dev veth-c1 nodad + $IP -6 addr add 2001:db8:2::1/64 dev veth-c2 nodad + + $IP -6 route add $SERVER_IP6/128 \ + nexthop via 2001:db8:1::2 dev veth-c1 weight 1 \ + nexthop via 2001:db8:2::2 dev veth-c2 weight 1 + + # By default, tcp_retries1=3 triggers a route refresh + # after 3 retransmits (~5s). Ensure this never occurs + # for test stability. + $NS_EXEC sysctl -qw net.ipv4.tcp_retries1=100 + + # When NETDEV_CHANGE is issued for a dev tied to an ECMP + # route, RTNH_F_LINKDOWN is flagged and the sernum is + # bumped to invalidate the route via sk_dst_check(). + # + # Without ignore_routes_with_linkdown=1, subsequent + # lookups may still select the same RTNH_F_LINKDOWN route. + $NS_EXEC sysctl -qw net.ipv4.conf.veth-c1.ignore_routes_with_linkdown=1 + $NS_EXEC sysctl -qw net.ipv4.conf.veth-c2.ignore_routes_with_linkdown=1 + + $NS_EXEC sysctl -qw net.ipv6.conf.veth-c1.ignore_routes_with_linkdown=1 + $NS_EXEC sysctl -qw net.ipv6.conf.veth-c2.ignore_routes_with_linkdown=1 +} + +setup() +{ + setup_ns client server + + ip -n "$client" link add veth-c1 type veth peer veth-s1 netns "$server" + ip -n "$client" link add veth-c2 type veth peer veth-s2 netns "$server" + + setup_server + setup_client +} + +cleanup() +{ + cleanup_all_ns > /dev/null 2>&1 +} + +tcp_ecmp_failover() +{ + local pf=$1; shift + local server_ip=$1; shift + local client_ip=$1; shift + + RET=0 + + tcpdump_start veth-s1 "$server" + tcpdump_start veth-s2 "$server" + + ip netns exec "$server" \ + socat -u TCP-LISTEN:8080,pf="$pf",bind="$server_ip",reuseaddr /dev/null & + server_pid=$! + + # Wait for server to start listening. + # Sometimes client fails without this sleep. + sleep 1 + + ip netns exec "$client" \ + socat -u /dev/zero TCP:"$server_ip":8080,pf="$pf",bind="$client_ip" & + client_pid=$! + + # To capture enough packets. + sleep 3 + + tcpdump_stop veth-s1 + tcpdump_stop veth-s2 + + pkts_s1=$(tcpdump_show veth-s1 | wc -l) + pkts_s2=$(tcpdump_show veth-s2 | wc -l) + + tcpdump_cleanup veth-s1 + tcpdump_cleanup veth-s2 + + # Detect the device chosen by the client + if [ "$pkts_s1" -gt "$pkts_s2" ]; then + veth_down=veth-s1 + veth_up=veth-s2 + else + veth_down=veth-s2 + veth_up=veth-s1 + fi + + # Taking down $veth_down causes its peer to lose carrier, + # triggering NETDEV_CHANGE. This flags RTNH_F_LINKDOWN + # and bumps the sernum for the route associated with that + # peer, invalidating the cached dst in the TCP socket. + # + # Consequently, sk_dst_check() fails, forcing the subsequent + # lookup to select the remaining healthy route via $veth_up. + ip -n "$server" link set "$veth_down" down + + tcpdump_start "$veth_up" "$server" + + # To capture enough packets. + sleep 3 + + tcpdump_stop "$veth_up" + + kill -9 "$client_pid" > /dev/null 2>&1 + kill -9 "$server_pid" > /dev/null 2>&1 + wait 2> /dev/null + + pkts=$(tcpdump_show $veth_up | wc -l) + + tcpdump_cleanup "$veth_up" + + if [ "$pkts" -lt 1000 ]; then + RET=$ksft_fail + fi +} + +test_ipv4() +{ + setup + tcp_ecmp_failover IPv4 $SERVER_IP $CLIENT_IP + log_test "TCP IPv4 failover" + cleanup +} + +test_ipv6() +{ + setup + tcp_ecmp_failover IPv6 "[$SERVER_IP6]" "[$CLIENT_IP6]" + log_test "TCP IPv6 failover" + cleanup +} + +require_command socat +require_command tcpdump + +trap cleanup EXIT + +test_ipv4 +test_ipv6 + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 9e2ccea13d70..30a236b8e9f7 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -946,6 +946,49 @@ TEST_F(tls, peek_and_splice) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_to_pipe_small) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + size_t total = 0; + int p[2]; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + + /* Shrink pipe to 1 page (typically 4096 bytes) to force multiple + * splice iterations for a 16384-byte TLS record. + */ + EXPECT_GE(fcntl(p[1], F_SETPIPE_SZ, 4096), 4096); + + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + + while (total < (size_t)send_len) { + ssize_t spliced, drained; + + spliced = splice(self->cfd, NULL, p[1], NULL, + send_len - total, 0); + EXPECT_GT(spliced, 0); + if (spliced <= 0) + break; + + drained = read(p[0], mem_recv + total, spliced); + EXPECT_EQ(drained, spliced); + if (drained <= 0) + break; + + total += drained; + } + + EXPECT_EQ(total, (size_t)send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); + + close(p[0]); + close(p[1]); +} + #define MAX_FRAGS 48 TEST_F(tls, splice_short) { diff --git a/tools/testing/selftests/rdma/rxe_ipv6.sh b/tools/testing/selftests/rdma/rxe_ipv6.sh index b7059bfd6d7c..32dad687a044 100755 --- a/tools/testing/selftests/rdma/rxe_ipv6.sh +++ b/tools/testing/selftests/rdma/rxe_ipv6.sh @@ -8,6 +8,8 @@ RXE_NAME="rxe6" PORT=4791 IP6_ADDR="2001:db8::1/64" +source "$(dirname "$0")/../kselftest/ktap_helpers.sh" + exec > /dev/null # Cleanup function to run on exit (even on failure) @@ -21,8 +23,8 @@ trap cleanup EXIT # 1. Prerequisites check for mod in tun veth rdma_rxe; do if ! modinfo "$mod" >/dev/null 2>&1; then - echo "Error: Kernel module '$mod' not found." - exit 1 + echo "SKIP: Kernel module '$mod' not found." >&2 + exit $KSFT_SKIP fi done diff --git a/tools/testing/selftests/rdma/rxe_rping_between_netns.sh b/tools/testing/selftests/rdma/rxe_rping_between_netns.sh index e5b876f58c6e..e7554fbb8951 100755 --- a/tools/testing/selftests/rdma/rxe_rping_between_netns.sh +++ b/tools/testing/selftests/rdma/rxe_rping_between_netns.sh @@ -8,6 +8,8 @@ IP_A="1.1.1.1" IP_B="1.1.1.2" PORT=4791 +source "$(dirname "$0")/../kselftest/ktap_helpers.sh" + exec > /dev/null # --- Cleanup Routine --- @@ -27,6 +29,11 @@ if [[ $EUID -ne 0 ]]; then exit 1 fi +if ! modinfo rdma_rxe >/dev/null 2>&1; then + echo "SKIP: Kernel module 'rdma_rxe' not found." >&2 + exit $KSFT_SKIP +fi + modprobe rdma_rxe || { echo "Failed to load rdma_rxe"; exit 1; } # --- Setup Network Topology --- diff --git a/tools/testing/selftests/rdma/rxe_socket_with_netns.sh b/tools/testing/selftests/rdma/rxe_socket_with_netns.sh index 002e5098f751..9478657c02c1 100755 --- a/tools/testing/selftests/rdma/rxe_socket_with_netns.sh +++ b/tools/testing/selftests/rdma/rxe_socket_with_netns.sh @@ -4,6 +4,8 @@ PORT=4791 MODS=("tun" "rdma_rxe") +source "$(dirname "$0")/../kselftest/ktap_helpers.sh" + exec > /dev/null # --- Helper: Cleanup Routine --- @@ -26,6 +28,10 @@ if [[ $EUID -ne 0 ]]; then fi for m in "${MODS[@]}"; do + if ! modinfo "$m" >/dev/null 2>&1; then + echo "SKIP: Kernel module '$m' not found." >&2 + exit $KSFT_SKIP + fi modprobe "$m" || { echo "Error: Failed to load $m"; exit 1; } done diff --git a/tools/testing/selftests/rdma/rxe_test_NETDEV_UNREGISTER.sh b/tools/testing/selftests/rdma/rxe_test_NETDEV_UNREGISTER.sh index 021ca451499d..8c18cea7535c 100755 --- a/tools/testing/selftests/rdma/rxe_test_NETDEV_UNREGISTER.sh +++ b/tools/testing/selftests/rdma/rxe_test_NETDEV_UNREGISTER.sh @@ -5,6 +5,8 @@ DEV_NAME="tun0" RXE_NAME="rxe0" RDMA_PORT=4791 +source "$(dirname "$0")/../kselftest/ktap_helpers.sh" + exec > /dev/null # --- Cleanup Routine --- @@ -19,8 +21,8 @@ trap cleanup EXIT # 1. Dependency Check if ! modinfo rdma_rxe >/dev/null 2>&1; then - echo "Error: rdma_rxe module not found." - exit 1 + echo "SKIP: rdma_rxe module not found." >&2 + exit $KSFT_SKIP fi modprobe rdma_rxe diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 4ef90823b652..50d69e22ee7a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -14,14 +14,20 @@ LDLIBS += -lpthread -ldl # still track changes to header files and depend on shared object. OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ - param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice \ - syscall_errors_test slice_test +TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test \ + param_test_benchmark param_test_mm_cid_benchmark -TEST_GEN_PROGS_EXTENDED = librseq.so +TEST_GEN_PROGS_EXTENDED = librseq.so \ + param_test \ + param_test_compare_twice \ + param_test_mm_cid \ + param_test_mm_cid_compare_twice \ + syscall_errors_test \ + legacy_check \ + slice_test \ + check_optimized -TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh +TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh run_legacy_check.sh run_timeslice_test.sh TEST_FILES := settings @@ -62,3 +68,6 @@ $(OUTPUT)/syscall_errors_test: syscall_errors_test.c $(TEST_GEN_PROGS_EXTENDED) $(OUTPUT)/slice_test: slice_test.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@ + +$(OUTPUT)/check_optimized: check_optimized.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h + $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@ diff --git a/tools/testing/selftests/rseq/check_optimized.c b/tools/testing/selftests/rseq/check_optimized.c new file mode 100644 index 000000000000..a13e3f2c8fc6 --- /dev/null +++ b/tools/testing/selftests/rseq/check_optimized.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <string.h> +#include <sys/time.h> + +#include "rseq.h" + +int main(int argc, char **argv) +{ + if (__rseq_register_current_thread(true, false)) + return -1; + return 0; +} diff --git a/tools/testing/selftests/rseq/legacy_check.c b/tools/testing/selftests/rseq/legacy_check.c new file mode 100644 index 000000000000..3f7de4e28303 --- /dev/null +++ b/tools/testing/selftests/rseq/legacy_check.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + +#include <errno.h> +#include <signal.h> +#include <stdint.h> +#include <unistd.h> + +#include "rseq.h" + +#include "../kselftest_harness.h" + +FIXTURE(legacy) +{ +}; + +static int cpu_id_in_sigfn = -1; + +static void sigfn(int sig) +{ + struct rseq_abi *rs = rseq_get_abi(); + + cpu_id_in_sigfn = rs->cpu_id_start; +} + +FIXTURE_SETUP(legacy) +{ + int res = __rseq_register_current_thread(true, true); + + switch (res) { + case -ENOSYS: + SKIP(return, "RSEQ not enabled\n"); + case -EBUSY: + SKIP(return, "GLIBC owns RSEQ. Disable GLIBC RSEQ registration\n"); + default: + ASSERT_EQ(res, 0); + } + + ASSERT_NE(signal(SIGUSR1, sigfn), SIG_ERR); +} + +FIXTURE_TEARDOWN(legacy) +{ +} + +TEST_F(legacy, legacy_test) +{ + struct rseq_abi *rs = rseq_get_abi(); + + ASSERT_NE(rs, NULL); + + /* Overwrite rs::cpu_id_start */ + rs->cpu_id_start = -1; + sleep(1); + ASSERT_NE(rs->cpu_id_start, -1); + + rs->cpu_id_start = -1; + ASSERT_EQ(raise(SIGUSR1), 0); + ASSERT_NE(rs->cpu_id_start, -1); + ASSERT_NE(cpu_id_in_sigfn, -1); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 05d03e679e06..e1e98dbabe4b 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -38,7 +38,7 @@ static int opt_modulo, verbose; static int opt_yield, opt_signal, opt_sleep, opt_disable_rseq, opt_threads = 200, opt_disable_mod = 0, opt_test = 's'; - +static bool opt_rseq_legacy; static long long opt_reps = 5000; static __thread __attribute__((tls_model("initial-exec"))) @@ -281,9 +281,12 @@ unsigned int yield_mod_cnt, nr_abort; } \ } +#define rseq_no_glibc true + #else #define printf_verbose(fmt, ...) +#define rseq_no_glibc false #endif /* BENCHMARK */ @@ -481,7 +484,7 @@ void *test_percpu_spinlock_thread(void *arg) long long i, reps; if (!opt_disable_rseq && thread_data->reg && - rseq_register_current_thread()) + __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { @@ -558,7 +561,7 @@ void *test_percpu_inc_thread(void *arg) long long i, reps; if (!opt_disable_rseq && thread_data->reg && - rseq_register_current_thread()) + __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { @@ -712,7 +715,7 @@ void *test_percpu_list_thread(void *arg) long long i, reps; struct percpu_list *list = (struct percpu_list *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -895,7 +898,7 @@ void *test_percpu_buffer_thread(void *arg) long long i, reps; struct percpu_buffer *buffer = (struct percpu_buffer *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -1105,7 +1108,7 @@ void *test_percpu_memcpy_buffer_thread(void *arg) long long i, reps; struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -1258,7 +1261,7 @@ void *test_membarrier_worker_thread(void *arg) const int iters = opt_reps; int i; - if (rseq_register_current_thread()) { + if (__rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) { fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", errno, strerror(errno)); abort(); @@ -1323,7 +1326,7 @@ void *test_membarrier_manager_thread(void *arg) intptr_t expect_a = 0, expect_b = 0; int cpu_a = 0, cpu_b = 0; - if (rseq_register_current_thread()) { + if (__rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) { fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", errno, strerror(errno)); abort(); @@ -1475,6 +1478,7 @@ static void show_usage(int argc, char **argv) printf(" [-D M] Disable rseq for each M threads\n"); printf(" [-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement, membarrie(r)\n"); printf(" [-M] Push into buffer and memcpy buffer with memory barriers.\n"); + printf(" [-O] Test with optimized RSEQ\n"); printf(" [-v] Verbose output.\n"); printf(" [-h] Show this help.\n"); printf("\n"); @@ -1602,6 +1606,9 @@ int main(int argc, char **argv) case 'M': opt_mo = RSEQ_MO_RELEASE; break; + case 'L': + opt_rseq_legacy = true; + break; default: show_usage(argc, argv); goto error; @@ -1618,7 +1625,7 @@ int main(int argc, char **argv) if (set_signal_handler()) goto error; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) goto error; if (!opt_disable_rseq && !rseq_validate_cpu_id()) { fprintf(stderr, "Error: cpu id getter unavailable\n"); diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h index ecef315204b2..5f4ea2152c2f 100644 --- a/tools/testing/selftests/rseq/rseq-abi.h +++ b/tools/testing/selftests/rseq/rseq-abi.h @@ -192,9 +192,14 @@ struct rseq_abi { struct rseq_abi_slice_ctrl slice_ctrl; /* + * Place holder to push the size above 32 bytes. + */ + __u8 __reserved; + + /* * Flexible array member at end of structure, after last feature field. */ char end[]; -} __attribute__((aligned(4 * sizeof(__u64)))); +} __attribute__((aligned(256))); #endif /* _RSEQ_ABI_H */ diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index a736727b83c1..be0d0a97031e 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -56,6 +56,7 @@ ptrdiff_t rseq_offset; * unsuccessful. */ unsigned int rseq_size = -1U; +static unsigned int rseq_alloc_size; /* Flags used during rseq registration. */ unsigned int rseq_flags; @@ -115,29 +116,17 @@ bool rseq_available(void) } } -/* The rseq areas need to be at least 32 bytes. */ -static -unsigned int get_rseq_min_alloc_size(void) -{ - unsigned int alloc_size = rseq_size; - - if (alloc_size < ORIG_RSEQ_ALLOC_SIZE) - alloc_size = ORIG_RSEQ_ALLOC_SIZE; - return alloc_size; -} - /* * Return the feature size supported by the kernel. * * Depending on the value returned by getauxval(AT_RSEQ_FEATURE_SIZE): * - * 0: Return ORIG_RSEQ_FEATURE_SIZE (20) + * 0: Return ORIG_RSEQ_FEATURE_SIZE (20) * > 0: Return the value from getauxval(AT_RSEQ_FEATURE_SIZE). * * It should never return a value below ORIG_RSEQ_FEATURE_SIZE. */ -static -unsigned int get_rseq_kernel_feature_size(void) +static unsigned int get_rseq_kernel_feature_size(void) { unsigned long auxv_rseq_feature_size, auxv_rseq_align; @@ -152,15 +141,24 @@ unsigned int get_rseq_kernel_feature_size(void) return ORIG_RSEQ_FEATURE_SIZE; } -int rseq_register_current_thread(void) +int __rseq_register_current_thread(bool nolibc, bool legacy) { + unsigned int size; int rc; if (!rseq_ownership) { /* Treat libc's ownership as a successful registration. */ - return 0; + return nolibc ? -EBUSY : 0; } - rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); + + /* The minimal allocation size is 32, which is the legacy allocation size */ + size = get_rseq_kernel_feature_size(); + if (legacy || size < ORIG_RSEQ_ALLOC_SIZE) + rseq_alloc_size = ORIG_RSEQ_ALLOC_SIZE; + else + rseq_alloc_size = size; + + rc = sys_rseq(&__rseq.abi, rseq_alloc_size, 0, RSEQ_SIG); if (rc) { /* * After at least one thread has registered successfully @@ -179,9 +177,8 @@ int rseq_register_current_thread(void) * The first thread to register sets the rseq_size to mimic the libc * behavior. */ - if (RSEQ_READ_ONCE(rseq_size) == 0) { - RSEQ_WRITE_ONCE(rseq_size, get_rseq_kernel_feature_size()); - } + if (RSEQ_READ_ONCE(rseq_size) == 0) + RSEQ_WRITE_ONCE(rseq_size, size); return 0; } @@ -194,7 +191,7 @@ int rseq_unregister_current_thread(void) /* Treat libc's ownership as a successful unregistration. */ return 0; } - rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + rc = sys_rseq(&__rseq.abi, rseq_alloc_size, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); if (rc) return -1; return 0; diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index f51a5fdb0444..c62ebb9290c0 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -8,6 +8,7 @@ #ifndef RSEQ_H #define RSEQ_H +#include <assert.h> #include <stdint.h> #include <stdbool.h> #include <pthread.h> @@ -142,7 +143,12 @@ static inline struct rseq_abi *rseq_get_abi(void) * succeed. A restartable sequence executed from a non-registered * thread will always fail. */ -int rseq_register_current_thread(void); +int __rseq_register_current_thread(bool nolibc, bool legacy); + +static inline int rseq_register_current_thread(void) +{ + return __rseq_register_current_thread(false, false); +} /* * Unregister rseq for current thread. diff --git a/tools/testing/selftests/rseq/run_legacy_check.sh b/tools/testing/selftests/rseq/run_legacy_check.sh new file mode 100755 index 000000000000..5577b46ea092 --- /dev/null +++ b/tools/testing/selftests/rseq/run_legacy_check.sh @@ -0,0 +1,4 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" ./legacy_check diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh index 8d31426ab41f..69a3fa049929 100755 --- a/tools/testing/selftests/rseq/run_param_test.sh +++ b/tools/testing/selftests/rseq/run_param_test.sh @@ -34,6 +34,11 @@ REPS=1000 SLOW_REPS=100 NR_THREADS=$((6*${NR_CPUS})) +# Prevent GLIBC from registering RSEQ so the selftest can run in legacy and +# performance optimized mode. +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" +export GLIBC_TUNABLES + function do_tests() { local i=0 @@ -103,6 +108,40 @@ function inject_blocking() NR_LOOPS= } +echo "Testing in legacy RSEQ mode" +echo "Yield injection (25%)" +inject_blocking -m 4 -y -L + +echo "Yield injection (50%)" +inject_blocking -m 2 -y -L + +echo "Yield injection (100%)" +inject_blocking -m 1 -y -L + +echo "Kill injection (25%)" +inject_blocking -m 4 -k -L + +echo "Kill injection (50%)" +inject_blocking -m 2 -k -L + +echo "Kill injection (100%)" +inject_blocking -m 1 -k -L + +echo "Sleep injection (1ms, 25%)" +inject_blocking -m 4 -s 1 -L + +echo "Sleep injection (1ms, 50%)" +inject_blocking -m 2 -s 1 -L + +echo "Sleep injection (1ms, 100%)" +inject_blocking -m 1 -s 1 -L + +./check_optimized || { + echo "Skipping optimized RSEQ mode test. Not supported"; + exit 0 +} + +echo "Testing in optimized RSEQ mode" echo "Yield injection (25%)" inject_blocking -m 4 -y diff --git a/tools/testing/selftests/rseq/run_timeslice_test.sh b/tools/testing/selftests/rseq/run_timeslice_test.sh new file mode 100755 index 000000000000..551ebed71ec6 --- /dev/null +++ b/tools/testing/selftests/rseq/run_timeslice_test.sh @@ -0,0 +1,14 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ + +# Prevent GLIBC from registering RSEQ so the selftest can run in legacy +# and performance optimized mode. +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" +export GLIBC_TUNABLES + +./check_optimized || { + echo "Skipping optimized RSEQ mode test. Not supported"; + exit 0 +} + +./slice_test diff --git a/tools/testing/selftests/rseq/slice_test.c b/tools/testing/selftests/rseq/slice_test.c index 357122dcb487..e402d4440bc2 100644 --- a/tools/testing/selftests/rseq/slice_test.c +++ b/tools/testing/selftests/rseq/slice_test.c @@ -124,6 +124,13 @@ FIXTURE_SETUP(slice_ext) { cpu_set_t affinity; + if (__rseq_register_current_thread(true, false)) + SKIP(return, "RSEQ not supported\n"); + + if (prctl(PR_RSEQ_SLICE_EXTENSION, PR_RSEQ_SLICE_EXTENSION_SET, + PR_RSEQ_SLICE_EXT_ENABLE, 0, 0)) + SKIP(return, "Time slice extension not supported\n"); + ASSERT_EQ(sched_getaffinity(0, sizeof(affinity), &affinity), 0); /* Pin it on a single CPU. Avoid CPU 0 */ @@ -137,11 +144,6 @@ FIXTURE_SETUP(slice_ext) break; } - ASSERT_EQ(rseq_register_current_thread(), 0); - - ASSERT_EQ(prctl(PR_RSEQ_SLICE_EXTENSION, PR_RSEQ_SLICE_EXTENSION_SET, - PR_RSEQ_SLICE_EXT_ENABLE, 0, 0), 0); - self->noise_params.noise_nsecs = variant->noise_nsecs; self->noise_params.sleep_nsecs = variant->sleep_nsecs; self->noise_params.run = 1; diff --git a/tools/testing/selftests/sched_ext/dequeue.c b/tools/testing/selftests/sched_ext/dequeue.c index 4e93262703ca..383d06e972a4 100644 --- a/tools/testing/selftests/sched_ext/dequeue.c +++ b/tools/testing/selftests/sched_ext/dequeue.c @@ -33,6 +33,7 @@ static void worker_fn(int id) /* Do some work to trigger scheduling events */ for (j = 0; j < 10000; j++) sum += j; + asm volatile("" : : "r"(sum)); /* Sleep to trigger dequeue */ usleep(1000 + (id * 100)); diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index b056eb966871..d0cad6571691 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -1144,6 +1144,620 @@ "teardown": [ "$TC qdisc del dev $DUMMY clsact" ] + }, + { + "id": "531c", + "name": "Redirect multiport: dummy egress -> dev1 ingress -> dummy egress (Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY clsact", + "$TC filter add dev $DUMMY egress protocol ip prio 10 matchall action mirred ingress redirect dev $DEV1 index 1", + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred egress redirect dev $DUMMY index 2" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "index": 1, + "stats": { + "packets": 3 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY clsact", + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "b1d7", + "name": "Redirect singleport: dev1 ingress -> dev1 egress -> dev1 ingress (Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred egress redirect dev $DEV1 index 1" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 egress protocol ip prio 11 matchall action mirred ingress redirect dev $DEV1 index 2", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "egress", + "index": 1, + "stats": { + "packets": 3 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "c66d", + "name": "Redirect multiport: dev1 ingress -> dummy ingress -> dev1 egress (No Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred ingress redirect dev $DUMMY index 1", + "$TC qdisc add dev $DUMMY clsact" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY ingress protocol ip prio 11 matchall action mirred egress redirect dev $DEV1 index 2", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "index": 1, + "stats": { + "packets": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact", + "$TC qdisc del dev $DUMMY clsact" + ] + }, + { + "id": "aa99", + "name": "Redirect multiport: dev1 ingress -> dummy ingress -> dev1 ingress (Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred ingress redirect dev $DUMMY index 1", + "$TC qdisc add dev $DUMMY clsact" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY ingress protocol ip prio 11 matchall action mirred ingress redirect dev $DEV1 index 2", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "index": 1, + "stats": { + "packets": 2, + "overlimits": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact", + "$TC qdisc del dev $DUMMY clsact" + ] + }, + { + "id": "37d7", + "name": "Redirect multiport: dev1 ingress -> dummy egress -> dev1 ingress (Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred egress redirect dev $DUMMY index 1", + "$TC qdisc add dev $DUMMY clsact" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY egress protocol ip prio 11 matchall action mirred ingress redirect dev $DEV1 index 2", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "egress", + "index": 1, + "stats": { + "packets": 3 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact", + "$TC qdisc del dev $DUMMY clsact" + ] + }, + { + "id": "6d02", + "name": "Redirect multiport: dummy egress -> dev1 ingress -> dummy egress, different prios (Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY clsact", + "$TC filter add dev $DUMMY egress protocol ip prio 10 matchall action mirred ingress redirect dev $DEV1 index 1", + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 11 matchall action mirred egress redirect dev $DUMMY index 2" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "index": 1, + "stats": { + "packets": 3 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY clsact", + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "8115", + "name": "Redirect multiport: dev1 ingress -> dummy ingress -> dummy egress -> dev1 egress (No Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred ingress redirect dev $DUMMY index 1", + "$TC qdisc add dev $DUMMY clsact", + "$TC filter add dev $DUMMY ingress protocol ip prio 11 matchall action mirred egress redirect dev $DUMMY index 2" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY egress protocol ip prio 12 matchall action mirred egress redirect dev $DEV1 index 3", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "index": 1, + "stats": { + "packets": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact", + "$TC qdisc del dev $DUMMY clsact" + ] + }, + { + "id": "9eb3", + "name": "Redirect multiport: dev1 ingress -> dummy egress -> dev1 egress (No Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred egress redirect dev $DUMMY index 1", + "$TC qdisc add dev $DUMMY clsact" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY egress protocol ip prio 11 matchall action mirred egress redirect dev $DEV1 index 2", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "egress", + "index": 1, + "stats": { + "packets": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact", + "$TC qdisc del dev $DUMMY clsact" + ] + }, + { + "id": "d837", + "name": "Redirect multiport: dev1 ingress -> dummy egress -> dummy ingress (No Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred egress redirect dev $DUMMY index 1", + "$TC qdisc add dev $DUMMY clsact" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY egress protocol ip prio 11 matchall action mirred ingress redirect dev $DUMMY index 2", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "egress", + "index": 1, + "stats": { + "packets": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact", + "$TC qdisc del dev $DUMMY clsact" + ] + }, + { + "id": "2071", + "name": "Redirect singleport: dev1 ingress -> dev1 ingress (Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred ingress redirect dev $DEV1 index 1", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "index": 1, + "stats": { + "packets": 1, + "overlimits": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "0101", + "name": "Redirect singleport: dummy egress -> dummy ingress (No Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY clsact", + "$TC filter add dev $DUMMY egress protocol ip prio 11 matchall action mirred ingress redirect dev $DUMMY index 1" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "index": 1, + "stats": { + "packets": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY clsact" + ] + }, + { + "id": "cf97", + "name": "Redirect multiport: dev1 ingress -> dummy ingress -> dummy egress (No Loop)", + "category": [ + "filter", + "mirred" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 ingress protocol ip prio 10 matchall action mirred ingress redirect dev $DUMMY index 1", + "$TC qdisc add dev $DUMMY clsact" + ], + "cmdUnderTest": "$TC filter add dev $DUMMY ingress protocol ip prio 11 matchall action mirred egress redirect dev $DUMMY index 2", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -j -s actions get action mirred index 1", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "mirred", + "mirred_action": "redirect", + "direction": "ingress", + "index": 1, + "stats": { + "packets": 1 + }, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact", + "$TC qdisc del dev $DUMMY clsact" + ] } - ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index eefadd0546d3..82c38a13dfbf 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -702,6 +702,7 @@ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem duplicate 100%", "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 1 u32 match ip dst 10.10.10.1/32 flowid 1:1", "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc ls m2 10Mbit", + "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%", "$TC filter add dev $DUMMY parent 1:0 protocol ip prio 2 u32 match ip dst 10.10.10.2/32 flowid 1:2", "ping -c 1 10.10.10.1 -I$DUMMY > /dev/null || true", "$TC filter del dev $DUMMY parent 1:0 protocol ip prio 1", @@ -714,8 +715,8 @@ { "kind": "hfsc", "handle": "1:", - "bytes": 294, - "packets": 3 + "bytes": 392, + "packets": 4 } ], "matchCount": "1", @@ -1136,5 +1137,194 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "7a5f", + "name": "Force red to dequeue from its child's gso_skb with qfq leaf", + "category": [ + "qdisc", + "tbf", + "red", + "qfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b", + "$TC qdisc add dev $DUMMY parent 1: handle 2: red limit 757 min 16 max 24 avpkt 16", + "$TC qdisc add dev $DUMMY parent 2: handle 3: qfq", + "$TC class add dev $DUMMY classid 3:1 parent 3: qfq maxpkt 512 weight 1", + "$TC filter add dev $DUMMY parent 3: protocol ip prio 1 matchall classid 3:1 action ok" + ], + "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "expExitCode": "0", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:", + "matchJSON": [ + { + "kind": "red", + "handle": "2:", + "bytes": 98, + "packets": 1, + "backlog": 0, + "qlen": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "cdae", + "name": "Force sfb to dequeue from its child's gso_skb with qfq leaf", + "category": [ + "qdisc", + "tbf", + "sfb", + "qfq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b", + "$TC qdisc add dev $DUMMY parent 1: handle 2: sfb", + "$TC qdisc add dev $DUMMY parent 2: handle 3: qfq", + "$TC class add dev $DUMMY classid 3:1 parent 3: qfq maxpkt 512 weight 1", + "$TC filter add dev $DUMMY parent 3: protocol ip prio 1 matchall classid 3:1 action ok" + ], + "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "expExitCode": "0", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:", + "matchJSON": [ + { + "kind": "sfb", + "handle": "2:", + "bytes": 98, + "packets": 1, + "backlog": 0, + "qlen": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "291d", + "name": "Force red to dequeue from its child's gso_skb with dualpi2 leaf", + "category": [ + "qdisc", + "tbf", + "red", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b", + "$TC qdisc add dev $DUMMY parent 1: handle 2: red limit 757 min 16 max 24 avpkt 16", + "$TC qdisc add dev $DUMMY parent 2: handle 3: dualpi2" + ], + "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "expExitCode": "0", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:", + "matchJSON": [ + { + "kind": "red", + "handle": "2:", + "bytes": 98, + "packets": 1, + "backlog": 0, + "qlen": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "9c6d", + "name": "Force sfb to dequeue from its child's gso_skb with dualpi2 leaf", + "category": [ + "qdisc", + "tbf", + "sfb", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 88bit burst 1661b peakrate 2257333 minburst 1024 limit 7b", + "$TC qdisc add dev $DUMMY parent 1: handle 2: sfb", + "$TC qdisc add dev $DUMMY parent 2: handle 3: dualpi2" + ], + "cmdUnderTest": "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "expExitCode": "0", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:", + "matchJSON": [ + { + "kind": "sfb", + "handle": "2:", + "bytes": 98, + "packets": 1, + "backlog": 0, + "qlen": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "3a62", + "name": "Try to create a qlen underflow with QFQ/CBS", + "category": [ + "qdisc", + "qfq", + "cbs" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: qfq", + "$TC class add dev $DUMMY classid 1:1 parent 1: qfq", + "$TC class add dev $DUMMY classid 1:2 parent 1: qfq", + "$TC qdisc add dev $DUMMY handle 2: parent 1:1 cbs", + "$TC qdisc add dev $DUMMY handle 3: parent 2: netem delay 5000000000", + "$TC filter add dev $DUMMY parent 1: prio 1 u32 match ip dst 10.10.10.1 classid 1:1 action ok", + "$TC filter add dev $DUMMY parent 1: prio 2 u32 match ip dst 10.10.10.2 classid 1:2 action ok", + "ping -c 1 10.10.10.1 -W0.01 -I$DUMMY || true", + "$IP l set $DUMMY down", + "$IP l set $DUMMY up", + "$TC qdisc replace dev $DUMMY handle 4: parent 2: pfifo" + ], + "cmdUnderTest": "ping -c 1 10.10.10.2 -W0.01 -I$DUMMY", + "expExitCode": "1", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY parent 1:1", + "matchJSON": [ + { + "kind": "cbs", + "handle": "2:", + "bytes": 0, + "packets": 0 + } + ], + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json index 718d2df2aafa..472b672a600d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/netem.json @@ -338,84 +338,34 @@ ] }, { - "id": "d34d", - "name": "NETEM test qdisc duplication restriction in qdisc tree in netem_change root", - "category": ["qdisc", "netem"], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DUMMY root handle 1: netem limit 1", - "$TC qdisc add dev $DUMMY parent 1: handle 2: netem limit 1" - ], - "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 1: netem duplicate 50%", - "expExitCode": "2", - "verifyCmd": "$TC -s qdisc show dev $DUMMY", - "matchPattern": "qdisc netem", - "matchCount": "2", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1:0 root" - ] - }, - { - "id": "b33f", - "name": "NETEM test qdisc duplication restriction in qdisc tree in netem_change non-root", - "category": ["qdisc", "netem"], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DUMMY root handle 1: netem limit 1", - "$TC qdisc add dev $DUMMY parent 1: handle 2: netem limit 1" - ], - "cmdUnderTest": "$TC qdisc change dev $DUMMY handle 2: netem duplicate 50%", - "expExitCode": "2", - "verifyCmd": "$TC -s qdisc show dev $DUMMY", - "matchPattern": "qdisc netem", - "matchCount": "2", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1:0 root" - ] - }, - { - "id": "cafe", - "name": "NETEM test qdisc duplication restriction in qdisc tree", - "category": ["qdisc", "netem"], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DUMMY root handle 1: netem limit 1 duplicate 100%" + "id": "8c17", + "name": "Test netem's recursive duplicate", + "category": [ + "qdisc", + "netem" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1: handle 2: netem duplicate 100%", - "expExitCode": "2", - "verifyCmd": "$TC -s qdisc show dev $DUMMY", - "matchPattern": "qdisc netem", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DUMMY handle 1:0 root" - ] - }, - { - "id": "1337", - "name": "NETEM test qdisc duplication restriction in qdisc tree across branches", - "category": ["qdisc", "netem"], "plugins": { "requires": "nsPlugin" }, "setup": [ - "$TC qdisc add dev $DUMMY parent root handle 1:0 hfsc", - "$TC class add dev $DUMMY parent 1:0 classid 1:1 hfsc rt m2 10Mbit", - "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 netem", - "$TC class add dev $DUMMY parent 1:0 classid 1:2 hfsc rt m2 10Mbit" - ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 netem duplicate 100%", - "expExitCode": "2", - "verifyCmd": "$TC -s qdisc show dev $DUMMY", - "matchPattern": "qdisc netem", - "matchCount": "1", + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: netem limit 1000 duplicate 100%", + "$TC qdisc add dev $DUMMY parent 1: handle 2: netem limit 1000 duplicate 100%" + ], + "cmdUnderTest": "ping -c 1 10.10.11.11 -W 0.01", + "expExitCode": "1", + "verifyCmd": "$TC -s -j qdisc ls dev $DUMMY root", + "matchJSON": [ + { + "kind": "netem", + "handle": "1:", + "bytes": 294, + "packets": 3 + } + ], "teardown": [ - "$TC qdisc del dev $DUMMY handle 1:0 root" + "$TC qdisc del dev $DUMMY handle 1: root" ] - } + } ] diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index fbd9b1e7342a..0b23c09daea5 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -1735,6 +1735,17 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) goto fail; } + /* + * The kernel may reduce nr_hw_queues (e.g. capped to nr_cpu_ids). + * Cap nthreads to the actual queue count to avoid creating extra + * handler threads that will hang during device removal. + * + * per_io_tasks mode is excluded: threads interleave across all + * queues so nthreads > nr_hw_queues is valid and intentional. + */ + if (!ctx->per_io_tasks && dev->nthreads > info->nr_hw_queues) + dev->nthreads = info->nr_hw_queues; + ret = ublk_start_daemon(ctx, dev); ublk_dbg(UBLK_DBG_DEV, "%s: daemon exit %d\n", __func__, ret); if (ret < 0) |