diff options
Diffstat (limited to 'tools')
70 files changed, 1433 insertions, 275 deletions
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 5215e0870bcb..6a71324be628 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -204,7 +204,11 @@ int do_pin_fd(int fd, const char *name) if (err) return err; - return bpf_obj_pin(fd, name); + err = bpf_obj_pin(fd, name); + if (err) + p_err("can't pin the object (%s): %s", name, strerror(errno)); + + return err; } int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) @@ -237,7 +241,7 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) fd = get_fd_by_id(id); if (fd < 0) { - p_err("can't get prog by id (%u): %s", id, strerror(errno)); + p_err("can't open object by id (%u): %s", id, strerror(errno)); return -1; } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 66f04a4846a5..43fdbbfe41bb 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -363,7 +363,9 @@ static int do_show(int argc, char **argv) if (fd < 0) return -1; - return show_prog(fd); + err = show_prog(fd); + close(fd); + return err; } if (argc) diff --git a/tools/hv/hv_get_dhcp_info.sh b/tools/hv/hv_get_dhcp_info.sh index c38686c44656..2f2a3c7df3de 100755 --- a/tools/hv/hv_get_dhcp_info.sh +++ b/tools/hv/hv_get_dhcp_info.sh @@ -13,7 +13,7 @@ # the script prints the string "Disabled" to stdout. # # Each Distro is expected to implement this script in a distro specific -# fashion. For instance on Distros that ship with Network Manager enabled, +# fashion. For instance, on Distros that ship with Network Manager enabled, # this script can be based on the Network Manager APIs for retrieving DHCP # information. diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index d7e06fe0270e..e9ef4ca6a655 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -700,7 +700,7 @@ static void kvp_get_ipconfig_info(char *if_name, /* - * Gather the DNS state. + * Gather the DNS state. * Since there is no standard way to get this information * across various distributions of interest; we just invoke * an external script that needs to be ported across distros @@ -809,7 +809,7 @@ kvp_get_ip_info(int family, char *if_name, int op, int sn_offset = 0; int error = 0; char *buffer; - struct hv_kvp_ipaddr_value *ip_buffer; + struct hv_kvp_ipaddr_value *ip_buffer = NULL; char cidr_mask[5]; /* /xyz */ int weight; int i; @@ -1051,7 +1051,7 @@ static int parse_ip_val_buffer(char *in_buf, int *offset, char *start; /* - * in_buf has sequence of characters that are seperated by + * in_buf has sequence of characters that are separated by * the character ';'. The last sequence does not have the * terminating ";" character. */ @@ -1386,6 +1386,8 @@ int main(int argc, char *argv[]) daemonize = 0; break; case 'h': + print_usage(argv); + exit(0); default: print_usage(argv); exit(EXIT_FAILURE); @@ -1490,7 +1492,7 @@ int main(int argc, char *argv[]) case KVP_OP_GET_IP_INFO: kvp_ip_val = &hv_msg->body.kvp_ip_val; - error = kvp_mac_to_ip(kvp_ip_val); + error = kvp_mac_to_ip(kvp_ip_val); if (error) hv_msg->error = error; diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index 7ed9f85ef908..d10fe35b7f25 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -12,7 +12,7 @@ # be used to configure the interface. # # Each Distro is expected to implement this script in a distro specific -# fashion. For instance on Distros that ship with Network Manager enabled, +# fashion. For instance, on Distros that ship with Network Manager enabled, # this script can be based on the Network Manager APIs for configuring the # interface. # diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c index efe1e34dd91b..92902a88f671 100644 --- a/tools/hv/hv_vss_daemon.c +++ b/tools/hv/hv_vss_daemon.c @@ -42,7 +42,7 @@ static int vss_do_freeze(char *dir, unsigned int cmd) * If a partition is mounted more than once, only the first * FREEZE/THAW can succeed and the later ones will get * EBUSY/EINVAL respectively: there could be 2 cases: - * 1) a user may mount the same partition to differnt directories + * 1) a user may mount the same partition to different directories * by mistake or on purpose; * 2) The subvolume of btrfs appears to have the same partition * mounted more than once. @@ -218,6 +218,8 @@ int main(int argc, char *argv[]) daemonize = 0; break; case 'h': + print_usage(argv); + exit(0); default: print_usage(argv); exit(EXIT_FAILURE); diff --git a/tools/hv/lsvmbus b/tools/hv/lsvmbus index 55e7374bade0..099f2c44dbed 100644 --- a/tools/hv/lsvmbus +++ b/tools/hv/lsvmbus @@ -4,10 +4,10 @@ import os from optparse import OptionParser +help_msg = "print verbose messages. Try -vv, -vvv for more verbose messages" parser = OptionParser() -parser.add_option("-v", "--verbose", dest="verbose", - help="print verbose messages. Try -vv, -vvv for \ - more verbose messages", action="count") +parser.add_option( + "-v", "--verbose", dest="verbose", help=help_msg, action="count") (options, args) = parser.parse_args() @@ -21,27 +21,28 @@ if not os.path.isdir(vmbus_sys_path): exit(-1) vmbus_dev_dict = { - '{0e0b6031-5213-4934-818b-38d90ced39db}' : '[Operating system shutdown]', - '{9527e630-d0ae-497b-adce-e80ab0175caf}' : '[Time Synchronization]', - '{57164f39-9115-4e78-ab55-382f3bd5422d}' : '[Heartbeat]', - '{a9a0f4e7-5a45-4d96-b827-8a841e8c03e6}' : '[Data Exchange]', - '{35fa2e29-ea23-4236-96ae-3a6ebacba440}' : '[Backup (volume checkpoint)]', - '{34d14be3-dee4-41c8-9ae7-6b174977c192}' : '[Guest services]', - '{525074dc-8985-46e2-8057-a307dc18a502}' : '[Dynamic Memory]', - '{cfa8b69e-5b4a-4cc0-b98b-8ba1a1f3f95a}' : 'Synthetic mouse', - '{f912ad6d-2b17-48ea-bd65-f927a61c7684}' : 'Synthetic keyboard', - '{da0a7802-e377-4aac-8e77-0558eb1073f8}' : 'Synthetic framebuffer adapter', - '{f8615163-df3e-46c5-913f-f2d2f965ed0e}' : 'Synthetic network adapter', - '{32412632-86cb-44a2-9b5c-50d1417354f5}' : 'Synthetic IDE Controller', - '{ba6163d9-04a1-4d29-b605-72e2ffb1dc7f}' : 'Synthetic SCSI Controller', - '{2f9bcc4a-0069-4af3-b76b-6fd0be528cda}' : 'Synthetic fiber channel adapter', - '{8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501}' : 'Synthetic RDMA adapter', - '{44c4f61d-4444-4400-9d52-802e27ede19f}' : 'PCI Express pass-through', - '{276aacf4-ac15-426c-98dd-7521ad3f01fe}' : '[Reserved system device]', - '{f8e65716-3cb3-4a06-9a60-1889c5cccab5}' : '[Reserved system device]', - '{3375baf4-9e15-4b30-b765-67acb10d607b}' : '[Reserved system device]', + '{0e0b6031-5213-4934-818b-38d90ced39db}': '[Operating system shutdown]', + '{9527e630-d0ae-497b-adce-e80ab0175caf}': '[Time Synchronization]', + '{57164f39-9115-4e78-ab55-382f3bd5422d}': '[Heartbeat]', + '{a9a0f4e7-5a45-4d96-b827-8a841e8c03e6}': '[Data Exchange]', + '{35fa2e29-ea23-4236-96ae-3a6ebacba440}': '[Backup (volume checkpoint)]', + '{34d14be3-dee4-41c8-9ae7-6b174977c192}': '[Guest services]', + '{525074dc-8985-46e2-8057-a307dc18a502}': '[Dynamic Memory]', + '{cfa8b69e-5b4a-4cc0-b98b-8ba1a1f3f95a}': 'Synthetic mouse', + '{f912ad6d-2b17-48ea-bd65-f927a61c7684}': 'Synthetic keyboard', + '{da0a7802-e377-4aac-8e77-0558eb1073f8}': 'Synthetic framebuffer adapter', + '{f8615163-df3e-46c5-913f-f2d2f965ed0e}': 'Synthetic network adapter', + '{32412632-86cb-44a2-9b5c-50d1417354f5}': 'Synthetic IDE Controller', + '{ba6163d9-04a1-4d29-b605-72e2ffb1dc7f}': 'Synthetic SCSI Controller', + '{2f9bcc4a-0069-4af3-b76b-6fd0be528cda}': 'Synthetic fiber channel adapter', + '{8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501}': 'Synthetic RDMA adapter', + '{44c4f61d-4444-4400-9d52-802e27ede19f}': 'PCI Express pass-through', + '{276aacf4-ac15-426c-98dd-7521ad3f01fe}': '[Reserved system device]', + '{f8e65716-3cb3-4a06-9a60-1889c5cccab5}': '[Reserved system device]', + '{3375baf4-9e15-4b30-b765-67acb10d607b}': '[Reserved system device]', } + def get_vmbus_dev_attr(dev_name, attr): try: f = open('%s/%s/%s' % (vmbus_sys_path, dev_name, attr), 'r') @@ -52,6 +53,7 @@ def get_vmbus_dev_attr(dev_name, attr): return lines + class VMBus_Dev: pass @@ -66,12 +68,13 @@ for f in os.listdir(vmbus_sys_path): chn_vp_mapping = get_vmbus_dev_attr(f, 'channel_vp_mapping') chn_vp_mapping = [c.strip() for c in chn_vp_mapping] - chn_vp_mapping = sorted(chn_vp_mapping, - key = lambda c : int(c.split(':')[0])) + chn_vp_mapping = sorted( + chn_vp_mapping, key=lambda c: int(c.split(':')[0])) - chn_vp_mapping = ['\tRel_ID=%s, target_cpu=%s' % - (c.split(':')[0], c.split(':')[1]) - for c in chn_vp_mapping] + chn_vp_mapping = [ + '\tRel_ID=%s, target_cpu=%s' % + (c.split(':')[0], c.split(':')[1]) for c in chn_vp_mapping + ] d = VMBus_Dev() d.sysfs_path = '%s/%s' % (vmbus_sys_path, f) d.vmbus_id = vmbus_id @@ -85,7 +88,7 @@ for f in os.listdir(vmbus_sys_path): vmbus_dev_list.append(d) -vmbus_dev_list = sorted(vmbus_dev_list, key = lambda d : int(d.vmbus_id)) +vmbus_dev_list = sorted(vmbus_dev_list, key=lambda d: int(d.vmbus_id)) format0 = '%2s: %s' format1 = '%2s: Class_ID = %s - %s\n%s' @@ -95,9 +98,15 @@ for d in vmbus_dev_list: if verbose == 0: print(('VMBUS ID ' + format0) % (d.vmbus_id, d.dev_desc)) elif verbose == 1: - print (('VMBUS ID ' + format1) % \ - (d.vmbus_id, d.class_id, d.dev_desc, d.chn_vp_mapping)) + print( + ('VMBUS ID ' + format1) % + (d.vmbus_id, d.class_id, d.dev_desc, d.chn_vp_mapping) + ) else: - print (('VMBUS ID ' + format2) % \ - (d.vmbus_id, d.class_id, d.dev_desc, \ - d.device_id, d.sysfs_path, d.chn_vp_mapping)) + print( + ('VMBUS ID ' + format2) % + ( + d.vmbus_id, d.class_id, d.dev_desc, + d.device_id, d.sysfs_path, d.chn_vp_mapping + ) + ) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4e455018da65..a5aa7d3ac6a1 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1466,8 +1466,8 @@ union bpf_attr { * If no cookie has been set yet, generate a new cookie. Once * generated, the socket cookie remains stable for the life of the * socket. This helper can be useful for monitoring per socket - * networking traffic statistics as it provides a unique socket - * identifier per namespace. + * networking traffic statistics as it provides a global socket + * identifier that can be assumed unique. * Return * A 8-byte long non-decreasing number on success, or 0 if the * socket field is missing inside *skb*. @@ -1571,8 +1571,11 @@ union bpf_attr { * but this is only implemented for native XDP (with driver * support) as of this writing). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. * * When used to redirect packets to net devices, this helper * provides a high performance increase over **bpf_redirect**\ (). diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 467224feb43b..d821107f55f9 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2018 Facebook */ +#include <endian.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -419,9 +420,9 @@ done: static bool btf_check_endianness(const GElf_Ehdr *ehdr) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#if __BYTE_ORDER == __LITTLE_ENDIAN return ehdr->e_ident[EI_DATA] == ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#elif __BYTE_ORDER == __BIG_ENDIAN return ehdr->e_ident[EI_DATA] == ELFDATA2MSB; #else # error "Unrecognized __BYTE_ORDER__" diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 794dd5064ae8..2b57d7ea7836 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -20,6 +20,7 @@ #include <inttypes.h> #include <string.h> #include <unistd.h> +#include <endian.h> #include <fcntl.h> #include <errno.h> #include <asm/unistd.h> @@ -181,7 +182,6 @@ struct bpf_program { bpf_program_clear_priv_t clear_priv; enum bpf_attach_type expected_attach_type; - int btf_fd; void *func_info; __u32 func_info_rec_size; __u32 func_info_cnt; @@ -312,7 +312,6 @@ void bpf_program__unload(struct bpf_program *prog) prog->instances.nr = -1; zfree(&prog->instances.fds); - zclose(prog->btf_fd); zfree(&prog->func_info); zfree(&prog->line_info); } @@ -391,7 +390,6 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, prog->instances.fds = NULL; prog->instances.nr = -1; prog->type = BPF_PROG_TYPE_UNSPEC; - prog->btf_fd = -1; return 0; errout: @@ -612,10 +610,10 @@ errout: static int bpf_object__check_endianness(struct bpf_object *obj) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#if __BYTE_ORDER == __LITTLE_ENDIAN if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB) return 0; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#elif __BYTE_ORDER == __BIG_ENDIAN if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB) return 0; #else @@ -1377,8 +1375,13 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) if (!has_datasec && kind == BTF_KIND_VAR) { /* replace VAR with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); - t->size = sizeof(int); - *(int *)(t+1) = BTF_INT_ENC(0, 0, 32); + /* + * using size = 1 is the safest choice, 4 will be too + * big and cause kernel BTF validation failure if + * original variable took less than 4 bytes + */ + t->size = 1; + *(int *)(t+1) = BTF_INT_ENC(0, 0, 8); } else if (!has_datasec && kind == BTF_KIND_DATASEC) { /* replace DATASEC with STRUCT */ struct btf_var_secinfo *v = (void *)(t + 1); @@ -1500,6 +1503,12 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) BTF_ELF_SEC, err); btf__free(obj->btf); obj->btf = NULL; + /* btf_ext can't exist without btf, so free it as well */ + if (obj->btf_ext) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } + if (bpf_object__is_btf_mandatory(obj)) return err; } @@ -2276,9 +2285,6 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext); } - if (!insn_offset) - prog->btf_fd = btf__fd(obj->btf); - return 0; } @@ -2451,7 +2457,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *cp, errmsg[STRERR_BUFSIZE]; int log_buf_size = BPF_LOG_BUF_SIZE; char *log_buf; - int ret; + int btf_fd, ret; if (!insns || !insns_cnt) return -EINVAL; @@ -2466,7 +2472,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.license = license; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; - load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0; + /* if .BTF.ext was loaded, kernel supports associated BTF for prog */ + if (prog->obj->btf_ext) + btf_fd = bpf_object__btf_fd(prog->obj); + else + btf_fd = -1; + load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; load_attr.func_info_cnt = prog->func_info_cnt; @@ -4507,13 +4518,13 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, const struct perf_buffer_opts *opts) { struct perf_buffer_params p = {}; - struct perf_event_attr attr = { - .config = PERF_COUNT_SW_BPF_OUTPUT, - .type = PERF_TYPE_SOFTWARE, - .sample_type = PERF_SAMPLE_RAW, - .sample_period = 1, - .wakeup_events = 1, - }; + struct perf_event_attr attr = { 0, }; + + attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.type = PERF_TYPE_SOFTWARE; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; p.attr = &attr; p.sample_cb = opts ? opts->sample_cb : NULL; @@ -4988,13 +4999,15 @@ int libbpf_num_possible_cpus(void) static const char *fcpu = "/sys/devices/system/cpu/possible"; int len = 0, n = 0, il = 0, ir = 0; unsigned int start = 0, end = 0; + int tmp_cpus = 0; static int cpus; char buf[128]; int error = 0; int fd = -1; - if (cpus > 0) - return cpus; + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; fd = open(fcpu, O_RDONLY); if (fd < 0) { @@ -5017,7 +5030,7 @@ int libbpf_num_possible_cpus(void) } buf[len] = '\0'; - for (ir = 0, cpus = 0; ir <= len; ir++) { + for (ir = 0, tmp_cpus = 0; ir <= len; ir++) { /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ if (buf[ir] == ',' || buf[ir] == '\0') { buf[ir] = '\0'; @@ -5029,13 +5042,15 @@ int libbpf_num_possible_cpus(void) } else if (n == 1) { end = start; } - cpus += end - start + 1; + tmp_cpus += end - start + 1; il = ir + 1; } } - if (cpus <= 0) { - pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu); + if (tmp_cpus <= 0) { + pr_warning("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); return -EINVAL; } - return cpus; + + WRITE_ONCE(cpus, tmp_cpus); + return tmp_cpus; } diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 5007b5d4fd2c..680e63066cf3 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -317,17 +317,16 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) static int xsk_get_max_queues(struct xsk_socket *xsk) { - struct ethtool_channels channels; - struct ifreq ifr; + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + struct ifreq ifr = {}; int fd, err, ret; fd = socket(AF_INET, SOCK_DGRAM, 0); if (fd < 0) return -errno; - channels.cmd = ETHTOOL_GCHANNELS; ifr.ifr_data = (void *)&channels; - strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); + memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); ifr.ifr_name[IFNAMSIZ - 1] = '\0'; err = ioctl(fd, SIOCETHTOOL, &ifr); if (err && errno != EOPNOTSUPP) { @@ -335,7 +334,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) goto out; } - if (channels.max_combined == 0 || errno == EOPNOTSUPP) + if (err || channels.max_combined == 0) /* If the device says it has no channels, then all traffic * is sent to a single stream, so max queues = 1. */ @@ -517,7 +516,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, err = -errno; goto out_socket; } - strncpy(xsk->ifname, ifname, IFNAMSIZ - 1); + memcpy(xsk->ifname, ifname, IFNAMSIZ - 1); xsk->ifname[IFNAMSIZ - 1] = '\0'; err = xsk_set_xdp_socket_config(&xsk->config, usr_config); diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 6d148a40551c..adc5a7e44b98 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -242,7 +242,7 @@ $(OUTPUT)doc.dep : $(wildcard *.txt) build-docdep.perl $(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \ mv $@+ $@ --include $(OUPTUT)doc.dep +-include $(OUTPUT)doc.dep _cmds_txt = cmds-ancillaryinterrogators.txt \ cmds-ancillarymanipulators.txt \ diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index a19690a17291..c8c86a0c9b79 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -6,8 +6,9 @@ #include "machine.h" #include "api/fs/fs.h" #include "debug.h" +#include "symbol.h" -int arch__fix_module_text_start(u64 *start, const char *name) +int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) { u64 m_start = *start; char path[PATH_MAX]; @@ -17,7 +18,35 @@ int arch__fix_module_text_start(u64 *start, const char *name) if (sysfs__read_ull(path, (unsigned long long *)start) < 0) { pr_debug2("Using module %s start:%#lx\n", path, m_start); *start = m_start; + } else { + /* Successful read of the modules segment text start address. + * Calculate difference between module start address + * in memory and module text segment start address. + * For example module load address is 0x3ff8011b000 + * (from /proc/modules) and module text segment start + * address is 0x3ff8011b870 (from file above). + * + * Adjust the module size and subtract the GOT table + * size located at the beginning of the module. + */ + *size -= (*start - m_start); } return 0; } + +/* On s390 kernel text segment start is located at very low memory addresses, + * for example 0x10000. Modules are located at very high memory addresses, + * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment + * and beginning of first module's text segment is very big. + * Therefore do not fill this gap and do not assign it to the kernel dso map. + */ +void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) +{ + if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) + /* Last kernel symbol mapped to end of page */ + p->end = roundup(p->end, page_size); + else + p->end = c->start; + pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end); +} diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index a640ca7aaada..513cb2f2fa32 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -379,8 +379,10 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags, /* Allocate and initialize all memory on CPU#0: */ if (init_cpu0) { - orig_mask = bind_to_node(0); - bind_to_memnode(0); + int node = numa_node_of_cpu(0); + + orig_mask = bind_to_node(node); + bind_to_memnode(node); } bytes = bytes0 + HPSIZE; diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 66d5a6658daf..019312810405 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -173,7 +173,7 @@ static int set_tracing_cpumask(struct cpu_map *cpumap) int last_cpu; last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); - mask_size = (last_cpu + 3) / 4 + 1; + mask_size = last_cpu / 4 + 2; /* one more byte for EOS */ mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */ cpumask = malloc(mask_size); diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 1a91a197cafb..d413761621b0 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -453,6 +453,7 @@ static struct fixed { { "inst_retired.any_p", "event=0xc0" }, { "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" }, { "cpu_clk_unhalted.thread", "event=0x3c" }, + { "cpu_clk_unhalted.core", "event=0x3c" }, { "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" }, { NULL, NULL}, }; diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index f80c51d53565..d227d74b28f8 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include "../string2.h" -#include "../config.h" -#include "../../perf.h" +#include "../util/util.h" +#include "../util/string2.h" +#include "../util/config.h" +#include "../perf.h" #include "libslang.h" #include "ui.h" #include "util.h" @@ -14,7 +15,7 @@ #include "browser.h" #include "helpline.h" #include "keysyms.h" -#include "../color.h" +#include "../util/color.h" #include <linux/ctype.h> #include <linux/zalloc.h> diff --git a/tools/perf/ui/tui/progress.c b/tools/perf/ui/tui/progress.c index bc134b82829d..5a24dd3ce4db 100644 --- a/tools/perf/ui/tui/progress.c +++ b/tools/perf/ui/tui/progress.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> -#include "../cache.h" +#include "../../util/cache.h" #include "../progress.h" #include "../libslang.h" #include "../ui.h" diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ac9ad2330f93..163536720149 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1122,7 +1122,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp) goto out; (*rawp)[0] = tmp; - *rawp = skip_spaces(*rawp); + *rawp = strim(*rawp); return 0; diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 3acfbe34ebaf..39cce66b4ebc 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -751,7 +751,10 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) unsigned char *bitmap; int last_cpu = cpu_map__cpu(map, map->nr - 1); - bitmap = zalloc((last_cpu + 7) / 8); + if (buf == NULL) + return 0; + + bitmap = zalloc(last_cpu / 8 + 1); if (bitmap == NULL) { buf[0] = '\0'; return 0; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index cf826eca3aaf..83b2fbbeeb90 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1378,6 +1378,7 @@ static int machine__set_modules_path(struct machine *machine) return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0); } int __weak arch__fix_module_text_start(u64 *start __maybe_unused, + u64 *size __maybe_unused, const char *name __maybe_unused) { return 0; @@ -1389,7 +1390,7 @@ static int machine__create_module(void *arg, const char *name, u64 start, struct machine *machine = arg; struct map *map; - if (arch__fix_module_text_start(&start, name) < 0) + if (arch__fix_module_text_start(&start, &size, name) < 0) return -1; map = machine__findnew_module_map(machine, start, name); diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index f70ab98a7bde..7aa38da26427 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -222,7 +222,7 @@ struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine, struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename); -int arch__fix_module_text_start(u64 *start, const char *name); +int arch__fix_module_text_start(u64 *start, u64 *size, const char *name); int machine__load_kallsyms(struct machine *machine, const char *filename); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 173f3378aaa0..4efde7879474 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -92,6 +92,11 @@ static int prefix_underscores_count(const char *str) return tail - str; } +void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c) +{ + p->end = c->start; +} + const char * __weak arch__normalize_symbol_name(const char *name) { return name; @@ -218,7 +223,7 @@ void symbols__fixup_end(struct rb_root_cached *symbols) curr = rb_entry(nd, struct symbol, rb_node); if (prev->end == prev->start && prev->end != curr->start) - prev->end = curr->start; + arch__symbols__fixup_end(prev, curr); } /* Last entry */ diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 12755b42ea93..183f630cb5f1 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -288,6 +288,7 @@ const char *arch__normalize_symbol_name(const char *name); #define SYMBOL_A 0 #define SYMBOL_B 1 +void arch__symbols__fixup_end(struct symbol *p, struct symbol *c); int arch__compare_symbol_names(const char *namea, const char *nameb); int arch__compare_symbol_names_n(const char *namea, const char *nameb, unsigned int n); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 873ab505ca80..590793cc5142 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -214,14 +214,24 @@ struct comm *thread__comm(const struct thread *thread) struct comm *thread__exec_comm(const struct thread *thread) { - struct comm *comm, *last = NULL; + struct comm *comm, *last = NULL, *second_last = NULL; list_for_each_entry(comm, &thread->comm_list, list) { if (comm->exec) return comm; + second_last = last; last = comm; } + /* + * 'last' with no start time might be the parent's comm of a synthesized + * thread (created by processing a synthesized fork event). For a main + * thread, that is very probably wrong. Prefer a later comm to avoid + * that case. + */ + if (second_last && !last->start && thread->pid_ == thread->tid) + return second_last; + return last; } diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 045f5f7d68ab..13f1e8b9ac52 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -9,9 +9,10 @@ ifeq ("$(origin O)", "command line") endif turbostat : turbostat.c -override CFLAGS += -Wall -I../../../include +override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' +override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 75fc4fb9901c..b2a86438f074 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -39,7 +39,6 @@ FILE *outf; int *fd_percpu; struct timeval interval_tv = {5, 0}; struct timespec interval_ts = {5, 0}; -struct timespec one_msec = {0, 1000000}; unsigned int num_iterations; unsigned int debug; unsigned int quiet; @@ -60,6 +59,7 @@ unsigned int do_irtl_hsw; unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; unsigned int authentic_amd; +unsigned int hygon_genuine; unsigned int max_level, max_extended_level; unsigned int has_invariant_tsc; unsigned int do_nhm_platform_info; @@ -100,6 +100,7 @@ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int has_misc_feature_control; unsigned int first_counter_read = 1; +int ignore_stdin; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -166,6 +167,7 @@ size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size; struct thread_data { struct timeval tv_begin; struct timeval tv_end; + struct timeval tv_delta; unsigned long long tsc; unsigned long long aperf; unsigned long long mperf; @@ -506,6 +508,7 @@ unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAU unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) +#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME) #define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME) #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT) #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) @@ -849,7 +852,6 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "pc8: %016llX\n", p->pc8); outp += sprintf(outp, "pc9: %016llX\n", p->pc9); outp += sprintf(outp, "pc10: %016llX\n", p->pc10); - outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); @@ -911,7 +913,7 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_TOD)) outp += sprintf(outp, "%10ld.%06ld\t", t->tv_end.tv_sec, t->tv_end.tv_usec); - interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0; + interval_float = t->tv_delta.tv_sec + t->tv_delta.tv_usec/1000000.0; tsc = t->tsc * tsc_tweak; @@ -1287,6 +1289,14 @@ delta_core(struct core_data *new, struct core_data *old) } } +int soft_c1_residency_display(int bic) +{ + if (!DO_BIC(BIC_CPU_c1) || use_c1_residency_msr) + return 0; + + return DO_BIC_READ(bic); +} + /* * old = new - old */ @@ -1309,6 +1319,7 @@ delta_thread(struct thread_data *new, struct thread_data *old, * over-write old w/ new so we can print end of interval values */ + timersub(&new->tv_begin, &old->tv_begin, &old->tv_delta); old->tv_begin = new->tv_begin; old->tv_end = new->tv_end; @@ -1322,7 +1333,8 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->c1 = new->c1 - old->c1; - if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || + soft_c1_residency_display(BIC_Avg_MHz)) { if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { old->aperf = new->aperf - old->aperf; old->mperf = new->mperf - old->mperf; @@ -1404,6 +1416,8 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data t->tv_begin.tv_usec = 0; t->tv_end.tv_sec = 0; t->tv_end.tv_usec = 0; + t->tv_delta.tv_sec = 0; + t->tv_delta.tv_usec = 0; t->tsc = 0; t->aperf = 0; @@ -1573,6 +1587,9 @@ void compute_average(struct thread_data *t, struct core_data *c, for_all_cpus(sum_counters, t, c, p); + /* Use the global time delta for the average. */ + average.threads.tv_delta = tv_delta; + average.threads.tsc /= topo.num_cpus; average.threads.aperf /= topo.num_cpus; average.threads.mperf /= topo.num_cpus; @@ -1714,7 +1731,7 @@ void get_apic_id(struct thread_data *t) if (!DO_BIC(BIC_X2APIC)) return; - if (authentic_amd) { + if (authentic_amd || hygon_genuine) { unsigned int topology_extensions; if (max_extended_level < 0x8000001e) @@ -1762,19 +1779,20 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) struct msr_counter *mp; int i; - gettimeofday(&t->tv_begin, (struct timezone *)NULL); - if (cpu_migrate(cpu)) { fprintf(outf, "Could not migrate to CPU %d\n", cpu); return -1; } + gettimeofday(&t->tv_begin, (struct timezone *)NULL); + if (first_counter_read) get_apic_id(t); retry: t->tsc = rdtsc(); /* we are running on local CPU of interest */ - if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || + soft_c1_residency_display(BIC_Avg_MHz)) { unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; /* @@ -1851,20 +1869,20 @@ retry: if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (DO_BIC(BIC_CPU_c3)) { + if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } - if (DO_BIC(BIC_CPU_c6) && !do_knl_cstates) { + if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; - } else if (do_knl_cstates) { + } else if (do_knl_cstates || soft_c1_residency_display(BIC_CPU_c6)) { if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6)) return -7; } - if (DO_BIC(BIC_CPU_c7)) + if (DO_BIC(BIC_CPU_c7) || soft_c1_residency_display(BIC_CPU_c7)) if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7)) return -8; @@ -2912,6 +2930,7 @@ int snapshot_cpu_lpi_us(void) if (retval != 1) { fprintf(stderr, "Disabling Low Power Idle CPU output\n"); BIC_NOT_PRESENT(BIC_CPU_LPI); + fclose(fp); return -1; } @@ -2938,6 +2957,7 @@ int snapshot_sys_lpi_us(void) if (retval != 1) { fprintf(stderr, "Disabling Low Power Idle System output\n"); BIC_NOT_PRESENT(BIC_SYS_LPI); + fclose(fp); return -1; } fclose(fp); @@ -2985,8 +3005,6 @@ static void signal_handler (int signal) fprintf(stderr, "SIGUSR1\n"); break; } - /* make sure this manually-invoked interval is at least 1ms long */ - nanosleep(&one_msec, NULL); } void setup_signal_handler(void) @@ -3005,29 +3023,38 @@ void setup_signal_handler(void) void do_sleep(void) { - struct timeval select_timeout; + struct timeval tout; + struct timespec rest; fd_set readfds; int retval; FD_ZERO(&readfds); FD_SET(0, &readfds); - if (!isatty(fileno(stdin))) { + if (ignore_stdin) { nanosleep(&interval_ts, NULL); return; } - select_timeout = interval_tv; - retval = select(1, &readfds, NULL, NULL, &select_timeout); + tout = interval_tv; + retval = select(1, &readfds, NULL, NULL, &tout); if (retval == 1) { switch (getc(stdin)) { case 'q': exit_requested = 1; break; + case EOF: + /* + * 'stdin' is a pipe closed on the other end. There + * won't be any further input. + */ + ignore_stdin = 1; + /* Sleep the rest of the time */ + rest.tv_sec = (tout.tv_sec + tout.tv_usec / 1000000); + rest.tv_nsec = (tout.tv_usec % 1000000) * 1000; + nanosleep(&rest, NULL); } - /* make sure this manually-invoked interval is at least 1ms long */ - nanosleep(&one_msec, NULL); } } @@ -3209,6 +3236,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) break; case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSX */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -3405,6 +3433,7 @@ int has_config_tdp(unsigned int family, unsigned int model) case INTEL_FAM6_IVYBRIDGE: /* IVB */ case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSX */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -3803,6 +3832,7 @@ double get_tdp_amd(unsigned int family) { switch (family) { case 0x17: + case 0x18: default: /* This is the max stock TDP of HEDT/Server Fam17h chips */ return 250.0; @@ -3841,6 +3871,7 @@ void rapl_probe_intel(unsigned int family, unsigned int model) case INTEL_FAM6_SANDYBRIDGE: case INTEL_FAM6_IVYBRIDGE: case INTEL_FAM6_HASWELL_CORE: /* HSW */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -3982,6 +4013,7 @@ void rapl_probe_amd(unsigned int family, unsigned int model) switch (family) { case 0x17: /* Zen, Zen+ */ + case 0x18: /* Hygon Dhyana */ do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; if (rapl_joules) { BIC_PRESENT(BIC_Pkg_J); @@ -4002,7 +4034,7 @@ void rapl_probe_amd(unsigned int family, unsigned int model) rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f)); rapl_power_units = ldexp(1.0, -(msr & 0xf)); - tdp = get_tdp_amd(model); + tdp = get_tdp_amd(family); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; if (!quiet) @@ -4018,7 +4050,7 @@ void rapl_probe(unsigned int family, unsigned int model) { if (genuine_intel) rapl_probe_intel(family, model); - if (authentic_amd) + if (authentic_amd || hygon_genuine) rapl_probe_amd(family, model); } @@ -4032,6 +4064,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model) switch (model) { case INTEL_FAM6_HASWELL_CORE: /* HSW */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ do_gfx_perf_limit_reasons = 1; case INTEL_FAM6_HASWELL_X: /* HSX */ @@ -4251,6 +4284,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */ case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSW */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -4267,7 +4301,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) } /* - * HSW adds support for additional MSRs: + * HSW ULT added support for C8/C9/C10 MSRs: * * MSR_PKG_C8_RESIDENCY 0x00000630 * MSR_PKG_C9_RESIDENCY 0x00000631 @@ -4278,13 +4312,13 @@ int has_snb_msrs(unsigned int family, unsigned int model) * MSR_PKGC10_IRTL 0x00000635 * */ -int has_hsw_msrs(unsigned int family, unsigned int model) +int has_c8910_msrs(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; switch (model) { - case INTEL_FAM6_HASWELL_CORE: + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ @@ -4568,9 +4602,6 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_XEON_PHI_KNM: return INTEL_FAM6_XEON_PHI_KNL; - case INTEL_FAM6_HASWELL_ULT: - return INTEL_FAM6_HASWELL_CORE; - case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */ return INTEL_FAM6_BROADWELL_X; @@ -4582,7 +4613,11 @@ unsigned int intel_model_duplicates(unsigned int model) return INTEL_FAM6_SKYLAKE_MOBILE; case INTEL_FAM6_ICELAKE_MOBILE: + case INTEL_FAM6_ICELAKE_NNPI: return INTEL_FAM6_CANNONLAKE_MOBILE; + + case INTEL_FAM6_ATOM_TREMONT_X: + return INTEL_FAM6_ATOM_GOLDMONT_X; } return model; } @@ -4600,6 +4635,8 @@ void process_cpuid() genuine_intel = 1; else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65) authentic_amd = 1; + else if (ebx == 0x6f677948 && ecx == 0x656e6975 && edx == 0x6e65476e) + hygon_genuine = 1; if (!quiet) fprintf(outf, "CPUID(0): %.4s%.4s%.4s ", @@ -4820,12 +4857,12 @@ void process_cpuid() BIC_NOT_PRESENT(BIC_CPU_c7); BIC_NOT_PRESENT(BIC_Pkgpc7); } - if (has_hsw_msrs(family, model)) { + if (has_c8910_msrs(family, model)) { BIC_PRESENT(BIC_Pkgpc8); BIC_PRESENT(BIC_Pkgpc9); BIC_PRESENT(BIC_Pkgpc10); } - do_irtl_hsw = has_hsw_msrs(family, model); + do_irtl_hsw = has_c8910_msrs(family, model); if (has_skl_msrs(family, model)) { BIC_PRESENT(BIC_Totl_c0); BIC_PRESENT(BIC_Any_c0); @@ -5123,7 +5160,7 @@ int initialize_counters(int cpu_id) void allocate_output_buffer() { - output_buffer = calloc(1, (1 + topo.num_cpus) * 1024); + output_buffer = calloc(1, (1 + topo.num_cpus) * 2048); outp = output_buffer; if (outp == NULL) err(-1, "calloc output buffer"); @@ -5269,7 +5306,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 19.03.20" + fprintf(outf, "turbostat version 19.08.31" " - Len Brown <lenb@kernel.org>\n"); } diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile index 1fdeef864e7c..666b325a62a2 100644 --- a/tools/power/x86/x86_energy_perf_policy/Makefile +++ b/tools/power/x86/x86_energy_perf_policy/Makefile @@ -9,8 +9,9 @@ ifeq ("$(origin O)", "command line") endif x86_energy_perf_policy : x86_energy_perf_policy.c -override CFLAGS += -Wall -I../../../include +override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' +override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 index 17db1c3af4d0..78c6361898b1 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 @@ -40,7 +40,7 @@ in the same processor package. Hardware P-States (HWP) are effectively an expansion of hardware P-state control from the opportunistic turbo-mode P-state range to include the entire range of available P-states. -On Broadwell Xeon, the initial HWP implementation, EBP influenced HWP. +On Broadwell Xeon, the initial HWP implementation, EPB influenced HWP. That influence was removed in subsequent generations, where it was moved to the Energy_Performance_Preference (EPP) field in diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 34a796b303fe..3fe1eed900d4 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -545,7 +545,7 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw", + while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw:", long_options, &option_index)) != -1) { switch (opt) { case 'a': @@ -1259,6 +1259,15 @@ void probe_dev_msr(void) if (system("/sbin/modprobe msr > /dev/null 2>&1")) err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); } + +static void get_cpuid_or_exit(unsigned int leaf, + unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + if (!__get_cpuid(leaf, eax, ebx, ecx, edx)) + errx(1, "Processor not supported\n"); +} + /* * early_cpuid() * initialize turbo_is_enabled, has_hwp, has_epb @@ -1266,15 +1275,10 @@ void probe_dev_msr(void) */ void early_cpuid(void) { - unsigned int eax, ebx, ecx, edx, max_level; + unsigned int eax, ebx, ecx, edx; unsigned int fms, family, model; - __get_cpuid(0, &max_level, &ebx, &ecx, &edx); - - if (max_level < 6) - errx(1, "Processor not supported\n"); - - __get_cpuid(1, &fms, &ebx, &ecx, &edx); + get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx); family = (fms >> 8) & 0xf; model = (fms >> 4) & 0xf; if (family == 6 || family == 0xf) @@ -1288,7 +1292,7 @@ void early_cpuid(void) bdx_highest_ratio = msr & 0xFF; } - __get_cpuid(0x6, &eax, &ebx, &ecx, &edx); + get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx); turbo_is_enabled = (eax >> 1) & 1; has_hwp = (eax >> 7) & 1; has_epb = (ecx >> 3) & 1; @@ -1306,7 +1310,7 @@ void parse_cpuid(void) eax = ebx = ecx = edx = 0; - __get_cpuid(0, &max_level, &ebx, &ecx, &edx); + get_cpuid_or_exit(0, &max_level, &ebx, &ecx, &edx); if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) genuine_intel = 1; @@ -1315,7 +1319,7 @@ void parse_cpuid(void) fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ", (char *)&ebx, (char *)&edx, (char *)&ecx); - __get_cpuid(1, &fms, &ebx, &ecx, &edx); + get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx); family = (fms >> 8) & 0xf; model = (fms >> 4) & 0xf; stepping = fms & 0xf; @@ -1340,7 +1344,7 @@ void parse_cpuid(void) errx(1, "CPUID: no MSR"); - __get_cpuid(0x6, &eax, &ebx, &ecx, &edx); + get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx); /* turbo_is_enabled already set */ /* has_hwp already set */ has_hwp_notify = eax & (1 << 8); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 11c9c62c3362..96752ebd938f 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -34,6 +34,9 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c))) TEST_GEN_FILES = $(BPF_OBJ_FILES) +BTF_C_FILES = $(wildcard progs/btf_dump_test_case_*.c) +TEST_FILES = $(BTF_C_FILES) + # Also test sub-register code-gen if LLVM has eBPF v3 processor support which # contains both ALU32 and JMP32 instructions. SUBREG_CODEGEN := $(shell echo "int cal(int a) { return a > 0; }" | \ @@ -57,7 +60,8 @@ TEST_PROGS := test_kmod.sh \ test_lirc_mode2.sh \ test_skb_cgroup_id.sh \ test_flow_dissector.sh \ - test_xdp_vlan.sh \ + test_xdp_vlan_mode_generic.sh \ + test_xdp_vlan_mode_native.sh \ test_lwt_ip_encap.sh \ test_tcp_check_syncookie.sh \ test_tc_tunnel.sh \ @@ -67,7 +71,8 @@ TEST_PROGS := test_kmod.sh \ TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh \ tcp_client.py \ - tcp_server.py + tcp_server.py \ + test_xdp_vlan.sh # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \ diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f7a0744db31e..5dc109f4c097 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -34,3 +34,4 @@ CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m CONFIG_IPV6_SIT=m +CONFIG_BPF_JIT=y diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c index 5aeaa284fc47..a68062820410 100644 --- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c @@ -41,8 +41,7 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx) } /* Rewrite destination. */ - if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) && - ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) { + if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) { ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); diff --git a/tools/testing/selftests/bpf/test_btf_dump.c b/tools/testing/selftests/bpf/test_btf_dump.c index 8f850823d35f..6e75dd3cb14f 100644 --- a/tools/testing/selftests/bpf/test_btf_dump.c +++ b/tools/testing/selftests/bpf/test_btf_dump.c @@ -97,6 +97,13 @@ int test_btf_dump_case(int n, struct btf_dump_test_case *test_case) } snprintf(test_file, sizeof(test_file), "progs/%s.c", test_case->name); + if (access(test_file, R_OK) == -1) + /* + * When the test is run with O=, kselftest copies TEST_FILES + * without preserving the directory structure. + */ + snprintf(test_file, sizeof(test_file), "%s.c", + test_case->name); /* * Diff test output and expected test output, contained between * START-EXPECTED-OUTPUT and END-EXPECTED-OUTPUT lines in test case. diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index 2fc4625c1a15..655729004391 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -20,9 +20,9 @@ int main(int argc, char **argv) BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), - BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), - BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */ BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */ @@ -30,7 +30,7 @@ int main(int argc, char **argv) BPF_FUNC_get_local_storage), BPF_MOV64_IMM(BPF_REG_1, 1), BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0), - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1), BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index fb679ac3d4b0..0e6652733462 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -13,6 +13,7 @@ #include <bpf/bpf.h> #include "cgroup_helpers.h" +#include "bpf_endian.h" #include "bpf_rlimit.h" #include "bpf_util.h" @@ -232,7 +233,8 @@ static struct sock_test tests[] = { /* if (ip == expected && port == expected) */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock, src_ip6[3])), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x01000000, 4), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x00000001), 4), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock, src_port)), BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2), @@ -261,7 +263,8 @@ static struct sock_test tests[] = { /* if (ip == expected && port == expected) */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock, src_ip4)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x0100007F, 4), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x7F000001), 4), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock, src_port)), BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2), diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index 51a3a31d1aac..bb8b0da91686 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -1,6 +1,14 @@ #!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Author: Jesper Dangaard Brouer <hawk@kernel.org> -TESTNAME=xdp_vlan +# Allow wrapper scripts to name test +if [ -z "$TESTNAME" ]; then + TESTNAME=xdp_vlan +fi + +# Default XDP mode +XDP_MODE=xdpgeneric usage() { echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME" @@ -9,9 +17,23 @@ usage() { echo " -v | --verbose : Verbose" echo " --flush : Flush before starting (e.g. after --interactive)" echo " --interactive : Keep netns setup running after test-run" + echo " --mode=XXX : Choose XDP mode (xdp | xdpgeneric | xdpdrv)" echo "" } +valid_xdp_mode() +{ + local mode=$1 + + case "$mode" in + xdpgeneric | xdpdrv | xdp) + return 0 + ;; + *) + return 1 + esac +} + cleanup() { local status=$? @@ -37,7 +59,7 @@ cleanup() # Using external program "getopt" to get --long-options OPTIONS=$(getopt -o hvfi: \ - --long verbose,flush,help,interactive,debug -- "$@") + --long verbose,flush,help,interactive,debug,mode: -- "$@") if (( $? != 0 )); then usage echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?" @@ -60,6 +82,11 @@ while true; do cleanup shift ;; + --mode ) + shift + XDP_MODE=$1 + shift + ;; -- ) shift break @@ -81,8 +108,14 @@ if [ "$EUID" -ne 0 ]; then exit 1 fi -ip link set dev lo xdp off 2>/dev/null > /dev/null -if [ $? -ne 0 ];then +valid_xdp_mode $XDP_MODE +if [ $? -ne 0 ]; then + echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)" + exit 1 +fi + +ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null +if [ $? -ne 0 ]; then echo "selftests: $TESTNAME [SKIP] need ip xdp support" exit 0 fi @@ -155,7 +188,7 @@ ip netns exec ns2 ip link set lo up # At this point, the hosts cannot reach each-other, # because ns2 are using VLAN tags on the packets. -ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Okay ping fails"' +ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' # Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags @@ -166,7 +199,7 @@ export FILE=test_xdp_vlan.o # First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change" export XDP_PROG=xdp_vlan_change -ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # In ns1: egress use TC to add back VLAN tag 4011 # (del cmd) @@ -177,8 +210,8 @@ ip netns exec ns1 tc filter add dev $DEVNS1 egress \ prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push # Now the namespaces can reach each-other, test with ping: -ip netns exec ns2 ping -W 2 -c 3 $IPADDR1 -ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 +ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 # Second test: Replace xdp prog, that fully remove vlan header # @@ -187,9 +220,9 @@ ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 # ETH_P_8021Q indication, and this cause overwriting of our changes. # export XDP_PROG=xdp_vlan_remove_outer2 -ip netns exec ns1 ip link set $DEVNS1 xdp off -ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off +ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # Now the namespaces should still be able reach each-other, test with ping: -ip netns exec ns2 ping -W 2 -c 3 $IPADDR1 -ip netns exec ns1 ping -W 2 -c 3 $IPADDR2 +ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh new file mode 100755 index 000000000000..c515326d6d59 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Exit on failure +set -e + +# Wrapper script to test generic-XDP +export TESTNAME=xdp_vlan_mode_generic +./test_xdp_vlan.sh --mode=xdpgeneric diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh new file mode 100755 index 000000000000..5cf7ce1f16c1 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh @@ -0,0 +1,9 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Exit on failure +set -e + +# Wrapper script to test native-XDP +export TESTNAME=xdp_vlan_mode_native +./test_xdp_vlan.sh --mode=xdpdrv diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index b0fda2877119..d438193804b2 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -975,6 +975,17 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SKB, }, { + "read gso_segs from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, gso_segs)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ "write gso_segs from CGROUP_SKB", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), diff --git a/tools/testing/selftests/bpf/verifier/loops1.c b/tools/testing/selftests/bpf/verifier/loops1.c index 5e980a5ab69d..1fc4e61e9f9f 100644 --- a/tools/testing/selftests/bpf/verifier/loops1.c +++ b/tools/testing/selftests/bpf/verifier/loops1.c @@ -159,3 +159,31 @@ .errstr = "loop detected", .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, +{ + "not-taken loop with back jump to 1st insn", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 123), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 4, -2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .retval = 123, +}, +{ + "taken loop with back jump to 1st insn", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 10), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, -3), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .retval = 55, +}, diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 8219a30853d2..0fc1b6d4b0f9 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -448,6 +448,59 @@ cleanup: } /* + * The test creates a cgroups and freezes it. Then it creates a child cgroup + * and populates it with a task. After that it checks that the child cgroup + * is frozen and the parent cgroup remains frozen too. + */ +static int test_cgfreezer_mkdir(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child = NULL; + int pid; + + parent = cg_name(root, "cg_test_mkdir_A"); + if (!parent) + goto cleanup; + + child = cg_name(parent, "cg_test_mkdir_B"); + if (!child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_freeze_wait(parent, true)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + pid = cg_run_nowait(child, child_fn, NULL); + if (pid < 0) + goto cleanup; + + if (cg_wait_for_proc_count(child, 1)) + goto cleanup; + + if (cg_check_frozen(child, true)) + goto cleanup; + + if (cg_check_frozen(parent, true)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + free(child); + if (parent) + cg_destroy(parent); + free(parent); + return ret; +} + +/* * The test creates two nested cgroups, freezes the parent * and removes the child. Then it checks that the parent cgroup * remains frozen and it's possible to create a new child @@ -815,6 +868,7 @@ struct cgfreezer_test { T(test_cgfreezer_simple), T(test_cgfreezer_tree), T(test_cgfreezer_forkbomb), + T(test_cgfreezer_mkdir), T(test_cgfreezer_rmdir), T(test_cgfreezer_migrate), T(test_cgfreezer_ptrace), diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index ec15c4f6af55..0ac49d91a260 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -10,6 +10,7 @@ #ifndef __KSELFTEST_H #define __KSELFTEST_H +#include <errno.h> #include <stdlib.h> #include <unistd.h> #include <stdarg.h> @@ -81,58 +82,68 @@ static inline void ksft_print_cnts(void) static inline void ksft_print_msg(const char *msg, ...) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("# "); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_pass(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_pass++; va_start(args, msg); printf("ok %d ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_fail(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_fail++; va_start(args, msg); printf("not ok %d ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_skip(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_xskip++; va_start(args, msg); printf("not ok %d # SKIP ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } static inline void ksft_test_result_error(const char *msg, ...) { + int saved_errno = errno; va_list args; ksft_cnt.ksft_error++; va_start(args, msg); printf("not ok %d # error ", ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } @@ -152,10 +163,12 @@ static inline int ksft_exit_fail(void) static inline int ksft_exit_fail_msg(const char *msg, ...) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("Bail out! "); + errno = saved_errno; vprintf(msg, args); va_end(args); @@ -178,10 +191,12 @@ static inline int ksft_exit_xpass(void) static inline int ksft_exit_skip(const char *msg, ...) { if (msg) { + int saved_errno = errno; va_list args; va_start(args, msg); printf("not ok %d # SKIP ", 1 + ksft_test_num()); + errno = saved_errno; vprintf(msg, args); va_end(args); } else { diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 41266af0d3dc..b35da375530a 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,7 +1,7 @@ +/s390x/sync_regs_test /x86_64/cr4_cpuid_sync_test /x86_64/evmcs_test /x86_64/hyperv_cpuid -/x86_64/kvm_create_max_vcpus /x86_64/mmio_warning_test /x86_64/platform_info_test /x86_64/set_sregs_test @@ -13,3 +13,4 @@ /x86_64/vmx_tsc_adjust_test /clear_dirty_log_test /dirty_log_test +/kvm_create_max_vcpus diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config new file mode 100644 index 000000000000..63ed533f73d6 --- /dev/null +++ b/tools/testing/selftests/kvm/config @@ -0,0 +1,3 @@ +CONFIG_KVM=y +CONFIG_KVM_INTEL=y +CONFIG_KVM_AMD=y diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h index 4059014d93ea..4912d23844bc 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/evmcs.h @@ -220,6 +220,8 @@ struct hv_enlightened_vmcs { struct hv_enlightened_vmcs *current_evmcs; struct hv_vp_assist_page *current_vp_assist; +int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id); + static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist) { u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) | diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 6cb34a0fa200..0a5e487dbc50 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1060,9 +1060,11 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i", r); - r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i", - r); + if (kvm_check_cap(KVM_CAP_XCRS)) { + r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i", + r); + } r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i", @@ -1103,9 +1105,11 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", r); - r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i", - r); + if (kvm_check_cap(KVM_CAP_XCRS)) { + r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i", + r); + } r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i", diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 204f847bd065..9cef0455b819 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -12,6 +12,26 @@ bool enable_evmcs; +int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id) +{ + uint16_t evmcs_ver; + + struct kvm_enable_cap enable_evmcs_cap = { + .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS, + .args[0] = (unsigned long)&evmcs_ver + }; + + vcpu_ioctl(vm, vcpu_id, KVM_ENABLE_CAP, &enable_evmcs_cap); + + /* KVM should return supported EVMCS version range */ + TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) && + (evmcs_ver & 0xff) > 0, + "Incorrect EVMCS version range: %x:%x\n", + evmcs_ver & 0xff, evmcs_ver >> 8); + + return evmcs_ver; +} + /* Allocate memory regions for nested VMX tests. * * Input Args: diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index f95c08343b48..92915e6408e7 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -79,11 +79,6 @@ int main(int argc, char *argv[]) struct kvm_x86_state *state; struct ucall uc; int stage; - uint16_t evmcs_ver; - struct kvm_enable_cap enable_evmcs_cap = { - .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS, - .args[0] = (unsigned long)&evmcs_ver - }; /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); @@ -96,13 +91,7 @@ int main(int argc, char *argv[]) exit(KSFT_SKIP); } - vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); - - /* KVM should return supported EVMCS version range */ - TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) && - (evmcs_ver & 0xff) > 0, - "Incorrect EVMCS version range: %x:%x\n", - evmcs_ver & 0xff, evmcs_ver >> 8); + vcpu_enable_evmcs(vm, VCPU_ID); run = vcpu_state(vm, VCPU_ID); @@ -146,7 +135,7 @@ int main(int argc, char *argv[]) kvm_vm_restart(vm, O_RDWR); vm_vcpu_add(vm, VCPU_ID); vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); + vcpu_enable_evmcs(vm, VCPU_ID); vcpu_load_state(vm, VCPU_ID, state); run = vcpu_state(vm, VCPU_ID); free(state); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index f72b3043db0e..ee59831fbc98 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -18,6 +18,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "vmx.h" #define VCPU_ID 0 @@ -106,12 +107,7 @@ int main(int argc, char *argv[]) { struct kvm_vm *vm; int rv; - uint16_t evmcs_ver; struct kvm_cpuid2 *hv_cpuid_entries; - struct kvm_enable_cap enable_evmcs_cap = { - .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS, - .args[0] = (unsigned long)&evmcs_ver - }; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); @@ -136,14 +132,14 @@ int main(int argc, char *argv[]) free(hv_cpuid_entries); - rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); - - if (rv) { + if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { fprintf(stderr, "Enlightened VMCS is unsupported, skip related test\n"); goto vm_free; } + vcpu_enable_evmcs(vm, VCPU_ID); + hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm); if (!hv_cpuid_entries) return 1; diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index 40050e44ec0a..f9334bd3cce9 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -99,8 +99,8 @@ int main(int argc, char *argv[]) msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO); vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); - test_msr_platform_info_disabled(vm); test_msr_platform_info_enabled(vm); + test_msr_platform_info_disabled(vm); vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index ed7218d166da..853e370e8a39 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -25,24 +25,17 @@ #define VMCS12_REVISION 0x11e57ed0 #define VCPU_ID 5 +bool have_evmcs; + void test_nested_state(struct kvm_vm *vm, struct kvm_nested_state *state) { - volatile struct kvm_run *run; - vcpu_nested_state_set(vm, VCPU_ID, state, false); - run = vcpu_state(vm, VCPU_ID); - vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); } void test_nested_state_expect_errno(struct kvm_vm *vm, struct kvm_nested_state *state, int expected_errno) { - volatile struct kvm_run *run; int rv; rv = vcpu_nested_state_set(vm, VCPU_ID, state, true); @@ -50,12 +43,6 @@ void test_nested_state_expect_errno(struct kvm_vm *vm, "Expected %s (%d) from vcpu_nested_state_set but got rv: %i errno: %s (%d)", strerror(expected_errno), expected_errno, rv, strerror(errno), errno); - run = vcpu_state(vm, VCPU_ID); - vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n", - run->exit_reason, - exit_reason_str(run->exit_reason)); } void test_nested_state_expect_einval(struct kvm_vm *vm, @@ -90,8 +77,9 @@ void set_default_vmx_state(struct kvm_nested_state *state, int size) { memset(state, 0, size); state->flags = KVM_STATE_NESTED_GUEST_MODE | - KVM_STATE_NESTED_RUN_PENDING | - KVM_STATE_NESTED_EVMCS; + KVM_STATE_NESTED_RUN_PENDING; + if (have_evmcs) + state->flags |= KVM_STATE_NESTED_EVMCS; state->format = 0; state->size = size; state->hdr.vmx.vmxon_pa = 0x1000; @@ -141,13 +129,19 @@ void test_vmx_nested_state(struct kvm_vm *vm) /* * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without * setting the nested state but flags other than eVMCS must be clear. + * The eVMCS flag can be set if the enlightened VMCS capability has + * been enabled. */ set_default_vmx_state(state, state_sz); state->hdr.vmx.vmxon_pa = -1ull; state->hdr.vmx.vmcs12_pa = -1ull; test_nested_state_expect_einval(vm, state); - state->flags = KVM_STATE_NESTED_EVMCS; + state->flags &= KVM_STATE_NESTED_EVMCS; + if (have_evmcs) { + test_nested_state_expect_einval(vm, state); + vcpu_enable_evmcs(vm, VCPU_ID); + } test_nested_state(vm, state); /* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */ @@ -232,6 +226,8 @@ int main(int argc, char *argv[]) struct kvm_nested_state state; struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); + have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS); + if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { printf("KVM_CAP_NESTED_STATE not available, skipping test\n"); exit(KSFT_SKIP); diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index edcfeace4655..79b0affd21fb 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -29,13 +29,27 @@ function die() { exit 1 } -# set_dynamic_debug() - setup kernel dynamic debug -# TODO - push and pop this config? +function push_dynamic_debug() { + DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \ + awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}') +} + +function pop_dynamic_debug() { + if [[ -n "$DYNAMIC_DEBUG" ]]; then + echo -n "$DYNAMIC_DEBUG" > /sys/kernel/debug/dynamic_debug/control + fi +} + +# set_dynamic_debug() - save the current dynamic debug config and tweak +# it for the self-tests. Set a script exit trap +# that restores the original config. function set_dynamic_debug() { - cat << EOF > /sys/kernel/debug/dynamic_debug/control -file kernel/livepatch/* +p -func klp_try_switch_task -p -EOF + push_dynamic_debug + trap pop_dynamic_debug EXIT INT TERM HUP + cat <<-EOF > /sys/kernel/debug/dynamic_debug/control + file kernel/livepatch/* +p + func klp_try_switch_task -p + EOF } # loop_until(cmd) - loop a command until it is successful or $MAX_RETRIES, diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 4ce0bc1612f5..c7cced739c34 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -17,7 +17,7 @@ tcp_inq tls txring_overwrite ip_defrag +ipv6_flowlabel +ipv6_flowlabel_mgr so_txtime -flowlabel -flowlabel_mgr tcp_fastopen_backup_key diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index c5c93d5fb3ad..f9ebeac1e6f2 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -212,6 +212,8 @@ check_output() printf " ${out}\n" printf " Expected:\n" printf " ${expected}\n\n" + else + echo " WARNING: Unexpected route entry" fi fi @@ -274,7 +276,7 @@ ipv6_fcnal() run_cmd "$IP nexthop get id 52" log_test $? 0 "Get nexthop by id" - check_nexthop "id 52" "id 52 via 2001:db8:91::2 dev veth1" + check_nexthop "id 52" "id 52 via 2001:db8:91::2 dev veth1 scope link" run_cmd "$IP nexthop del id 52" log_test $? 0 "Delete nexthop by id" @@ -479,12 +481,12 @@ ipv6_fcnal_runtime() run_cmd "$IP -6 nexthop add id 85 dev veth1" run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 85" log_test $? 0 "IPv6 route with device only nexthop" - check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1" + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024 pref medium" run_cmd "$IP nexthop add id 123 group 81/85" run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 123" log_test $? 0 "IPv6 multipath route with nexthop mix - dev only + gw" - check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 nexthop via 2001:db8:91::2 dev veth1 nexthop dev veth1" + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1 pref medium" # # IPv6 route with v4 nexthop - not allowed @@ -538,7 +540,7 @@ ipv4_fcnal() run_cmd "$IP nexthop get id 12" log_test $? 0 "Get nexthop by id" - check_nexthop "id 12" "id 12 via 172.16.1.2 src 172.16.1.1 dev veth1 scope link" + check_nexthop "id 12" "id 12 via 172.16.1.2 dev veth1 scope link" run_cmd "$IP nexthop del id 12" log_test $? 0 "Delete nexthop by id" @@ -685,7 +687,7 @@ ipv4_withv6_fcnal() set +e run_cmd "$IP ro add 172.16.101.1/32 nhid 11" log_test $? 0 "IPv6 nexthop with IPv4 route" - check_route "172.16.101.1" "172.16.101.1 nhid 11 via ${lladdr} dev veth1" + check_route "172.16.101.1" "172.16.101.1 nhid 11 via inet6 ${lladdr} dev veth1" set -e run_cmd "$IP nexthop add id 12 via 172.16.1.2 dev veth1" @@ -694,11 +696,11 @@ ipv4_withv6_fcnal() run_cmd "$IP ro replace 172.16.101.1/32 nhid 101" log_test $? 0 "IPv6 nexthop with IPv4 route" - check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" + check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via inet6 ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" run_cmd "$IP ro replace 172.16.101.1/32 via inet6 ${lladdr} dev veth1" log_test $? 0 "IPv4 route with IPv6 gateway" - check_route "172.16.101.1" "172.16.101.1 via ${lladdr} dev veth1" + check_route "172.16.101.1" "172.16.101.1 via inet6 ${lladdr} dev veth1" run_cmd "$IP ro replace 172.16.101.1/32 via inet6 2001:db8:50::1 dev veth1" log_test $? 2 "IPv4 route with invalid IPv6 gateway" @@ -785,10 +787,10 @@ ipv4_fcnal_runtime() log_test $? 0 "IPv4 route with device only nexthop" check_route "172.16.101.1" "172.16.101.1 nhid 85 dev veth1" - run_cmd "$IP nexthop add id 122 group 21/85" - run_cmd "$IP ro replace 172.16.101.1/32 nhid 122" + run_cmd "$IP nexthop add id 123 group 21/85" + run_cmd "$IP ro replace 172.16.101.1/32 nhid 123" log_test $? 0 "IPv4 multipath route with nexthop mix - dev only + gw" - check_route "172.16.101.1" "172.16.101.1 nhid 85 nexthop via 172.16.1.2 dev veth1 nexthop dev veth1" + check_route "172.16.101.1" "172.16.101.1 nhid 123 nexthop via 172.16.1.2 dev veth1 weight 1 nexthop dev veth1 weight 1" # # IPv4 with IPv6 @@ -820,7 +822,7 @@ ipv4_fcnal_runtime() run_cmd "$IP ro replace 172.16.101.1/32 nhid 101" log_test $? 0 "IPv4 route with mixed v4-v6 multipath route" - check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" + check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via inet6 ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1" log_test $? 0 "IPv6 nexthop with IPv4 route" diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh index cca2baa03fb8..a8d8e8b3dc81 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -93,18 +93,10 @@ sw1_create() ip route add vrf v$ol1 192.0.2.16/28 \ nexthop dev g1a \ nexthop dev g1b - - tc qdisc add dev $ul1 clsact - tc filter add dev $ul1 egress pref 111 prot ipv4 \ - flower dst_ip 192.0.2.66 action pass - tc filter add dev $ul1 egress pref 222 prot ipv4 \ - flower dst_ip 192.0.2.82 action pass } sw1_destroy() { - tc qdisc del dev $ul1 clsact - ip route del vrf v$ol1 192.0.2.16/28 ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146 @@ -139,10 +131,18 @@ sw2_create() ip route add vrf v$ol2 192.0.2.0/28 \ nexthop dev g2a \ nexthop dev g2b + + tc qdisc add dev $ul2 clsact + tc filter add dev $ul2 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul2 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass } sw2_destroy() { + tc qdisc del dev $ul2 clsact + ip route del vrf v$ol2 192.0.2.0/28 ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145 @@ -187,12 +187,16 @@ setup_prepare() sw1_create sw2_create h2_create + + forwarding_enable } cleanup() { pre_cleanup + forwarding_restore + h2_destroy sw2_destroy sw1_destroy @@ -211,15 +215,15 @@ multipath4_test() nexthop dev g1a weight $weight1 \ nexthop dev g1b weight $weight2 - local t0_111=$(tc_rule_stats_get $ul1 111 egress) - local t0_222=$(tc_rule_stats_get $ul1 222 egress) + local t0_111=$(tc_rule_stats_get $ul2 111 ingress) + local t0_222=$(tc_rule_stats_get $ul2 222 ingress) ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ -d 1msec -t udp "sp=1024,dp=0-32768" - local t1_111=$(tc_rule_stats_get $ul1 111 egress) - local t1_222=$(tc_rule_stats_get $ul1 222 egress) + local t1_111=$(tc_rule_stats_get $ul2 111 ingress) + local t1_222=$(tc_rule_stats_get $ul2 222 ingress) local d111=$((t1_111 - t0_111)) local d222=$((t1_222 - t0_222)) diff --git a/tools/testing/selftests/net/tcp_fastopen_backup_key.sh b/tools/testing/selftests/net/tcp_fastopen_backup_key.sh index 41476399e184..f6e65674b83c 100755 --- a/tools/testing/selftests/net/tcp_fastopen_backup_key.sh +++ b/tools/testing/selftests/net/tcp_fastopen_backup_key.sh @@ -30,7 +30,7 @@ do_test() { ip netns exec "${NETNS}" ./tcp_fastopen_backup_key "$1" val=$(ip netns exec "${NETNS}" nstat -az | \ grep TcpExtTCPFastOpenPassiveFail | awk '{print $2}') - if [ $val -ne 0 ]; then + if [ "$val" != 0 ]; then echo "FAIL: TcpExtTCPFastOpenPassiveFail non-zero" return 1 fi diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 090fff9dbc48..4c285b6e1db8 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,6 +25,80 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 +#ifndef ENOTSUPP +#define ENOTSUPP 524 +#endif + +FIXTURE(tls_basic) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls_basic) +{ + struct sockaddr_in addr; + socklen_t len; + int sfd, ret; + + self->notls = false; + len = sizeof(addr); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + self->fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(self->fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + self->cfd = accept(sfd, &addr, &len); + ASSERT_GE(self->cfd, 0); + + close(sfd); + + ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + ASSERT_EQ(errno, ENOENT); + self->notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + return; + } + + ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(tls_basic) +{ + close(self->fd); + close(self->cfd); +} + +/* Send some data through with ULP but no keys */ +TEST_F(tls_basic, base_base) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +}; + FIXTURE(tls) { int fd, cfd; @@ -165,6 +239,16 @@ TEST_F(tls, msg_more) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST_F(tls, msg_more_unsent) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1); +} + TEST_F(tls, sendmsg_single) { struct msghdr msg; @@ -610,6 +694,42 @@ TEST_F(tls, recv_lowat) EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0); } +TEST_F(tls, bidir) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + int ret; + + if (!self->notls) { + struct tls12_crypto_info_aes_gcm_128 tls12; + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_3_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; + + ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + memset(buf, 0, sizeof(buf)); + + EXPECT_EQ(send(self->cfd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->fd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); +}; + TEST_F(tls, pollin) { char const *test_str = "test_poll"; @@ -837,6 +957,109 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST_F(tls, shutdown) +{ + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + ASSERT_EQ(strlen(test_str) + 1, send_len); + + EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); +} + +TEST_F(tls, shutdown_unsent) +{ + char const *test_str = "test_read"; + int send_len = 10; + + EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); +} + +TEST_F(tls, shutdown_reuse) +{ + struct sockaddr_in addr; + int ret; + + shutdown(self->fd, SHUT_RDWR); + shutdown(self->cfd, SHUT_RDWR); + close(self->cfd); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + ret = bind(self->fd, &addr, sizeof(addr)); + EXPECT_EQ(ret, 0); + ret = listen(self->fd, 10); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EINVAL); + + ret = connect(self->fd, &addr, sizeof(addr)); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EISCONN); +} + +TEST(non_established) { + struct tls12_crypto_info_aes_gcm_256 tls12; + struct sockaddr_in addr; + int sfd, ret, fd; + socklen_t len; + + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + /* TLS ULP not supported */ + if (errno == ENOENT) + return; + EXPECT_EQ(errno, ENOTSUPP); + + ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, ENOTSUPP); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EEXIST); + + close(fd); + close(sfd); +} + TEST(keysizes) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index 5445943bf07f..7a1bf94c5bd3 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -106,6 +106,13 @@ do_overlap() # # 10.0.0.0/24 and 10.0.1.0/24 nodes have been merged as 10.0.0.0/23. ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/23 dir fwd priority 200 action block + + # similar to above: add policies (with partially random address), with shrinking prefixes. + for p in 29 28 27;do + for k in $(seq 1 32); do + ip -net $ns xfrm policy add src 10.253.1.$((RANDOM%255))/$p dst 10.254.1.$((RANDOM%255))/$p dir fwd priority $((200+k)) action block 2>/dev/null + done + done } do_esp_policy_get_check() { diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index fe52488a6f72..16571ac1dab4 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -321,4 +321,52 @@ else ip netns exec nsr1 nft list ruleset fi +KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1) +KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1) +SPI1=$RANDOM +SPI2=$RANDOM + +if [ $SPI1 -eq $SPI2 ]; then + SPI2=$((SPI2+1)) +fi + +do_esp() { + local ns=$1 + local me=$2 + local remote=$3 + local lnet=$4 + local rnet=$5 + local spi_out=$6 + local spi_in=$7 + + ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet + ip -net $ns xfrm state add src $me dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet + + # to encrypt packets as they go out (includes forwarded packets that need encapsulation) + ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 1 action allow + # to fwd decrypted packets after esp processing: + ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 1 action allow + +} + +do_esp nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2 + +do_esp nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1 + +ip netns exec nsr1 nft delete table ip nat + +# restore default routes +ip -net ns2 route del 192.168.10.1 via 10.0.2.1 +ip -net ns2 route add default via 10.0.2.1 +ip -net ns2 route add default via dead:2::1 + +test_tcp_forwarding ns1 ns2 +if [ $? -eq 0 ] ;then + echo "PASS: ipsec tunnel mode for ns1/ns2" +else + echo "FAIL: ipsec tunnel mode for ns1/ns2" + ip netns exec nsr1 nft list ruleset 1>&2 + ip netns exec nsr1 cat /proc/net/xfrm_stat 1>&2 +fi + exit $ret diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 16d84d117bc0..8d069490e17b 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -1,2 +1,4 @@ pidfd_open_test +pidfd_poll_test pidfd_test +pidfd_wait diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index 720b2d884b3c..464c9b76148f 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS += -g -I../../../../usr/include/ -lpthread -TEST_GEN_PROGS := pidfd_test pidfd_open_test +TEST_GEN_PROGS := pidfd_test pidfd_open_test pidfd_poll_test pidfd_wait include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 8452e910463f..c6bc68329f4b 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -16,6 +16,26 @@ #include "../kselftest.h" +#ifndef P_PIDFD +#define P_PIDFD 3 +#endif + +#ifndef CLONE_PIDFD +#define CLONE_PIDFD 0x00001000 +#endif + +#ifndef __NR_pidfd_open +#define __NR_pidfd_open -1 +#endif + +#ifndef __NR_pidfd_send_signal +#define __NR_pidfd_send_signal -1 +#endif + +#ifndef __NR_clone3 +#define __NR_clone3 -1 +#endif + /* * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c * That means, when it wraps around any pid < 300 will be skipped. @@ -53,5 +73,15 @@ again: return WEXITSTATUS(status); } +static inline int sys_pidfd_open(pid_t pid, unsigned int flags) +{ + return syscall(__NR_pidfd_open, pid, flags); +} + +static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, + unsigned int flags) +{ + return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); +} #endif /* __PIDFD_H */ diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c index 0377133dd6dc..b9fe75fc3e51 100644 --- a/tools/testing/selftests/pidfd/pidfd_open_test.c +++ b/tools/testing/selftests/pidfd/pidfd_open_test.c @@ -22,11 +22,6 @@ #include "pidfd.h" #include "../kselftest.h" -static inline int sys_pidfd_open(pid_t pid, unsigned int flags) -{ - return syscall(__NR_pidfd_open, pid, flags); -} - static int safe_int(const char *numstr, int *converted) { char *err = NULL; diff --git a/tools/testing/selftests/pidfd/pidfd_poll_test.c b/tools/testing/selftests/pidfd/pidfd_poll_test.c new file mode 100644 index 000000000000..4b115444dfe9 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_poll_test.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <linux/types.h> +#include <linux/wait.h> +#include <poll.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "pidfd.h" +#include "../kselftest.h" + +static bool timeout; + +static void handle_alarm(int sig) +{ + timeout = true; +} + +int main(int argc, char **argv) +{ + struct pollfd fds; + int iter, nevents; + int nr_iterations = 10000; + + fds.events = POLLIN; + + if (argc > 2) + ksft_exit_fail_msg("Unexpected command line argument\n"); + + if (argc == 2) { + nr_iterations = atoi(argv[1]); + if (nr_iterations <= 0) + ksft_exit_fail_msg("invalid input parameter %s\n", + argv[1]); + } + + ksft_print_msg("running pidfd poll test for %d iterations\n", + nr_iterations); + + for (iter = 0; iter < nr_iterations; iter++) { + int pidfd; + int child_pid = fork(); + + if (child_pid < 0) { + if (errno == EAGAIN) { + iter--; + continue; + } + ksft_exit_fail_msg( + "%s - failed to fork a child process\n", + strerror(errno)); + } + + if (child_pid == 0) { + /* Child process just sleeps for a min and exits */ + sleep(60); + exit(EXIT_SUCCESS); + } + + /* Parent kills the child and waits for its death */ + pidfd = sys_pidfd_open(child_pid, 0); + if (pidfd < 0) + ksft_exit_fail_msg("%s - pidfd_open failed\n", + strerror(errno)); + + /* Setup 3 sec alarm - plenty of time */ + if (signal(SIGALRM, handle_alarm) == SIG_ERR) + ksft_exit_fail_msg("%s - signal failed\n", + strerror(errno)); + alarm(3); + + /* Send SIGKILL to the child */ + if (sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0)) + ksft_exit_fail_msg("%s - pidfd_send_signal failed\n", + strerror(errno)); + + /* Wait for the death notification */ + fds.fd = pidfd; + nevents = poll(&fds, 1, -1); + + /* Check for error conditions */ + if (nevents < 0) + ksft_exit_fail_msg("%s - poll failed\n", + strerror(errno)); + + if (nevents != 1) + ksft_exit_fail_msg("unexpected poll result: %d\n", + nevents); + + if (!(fds.revents & POLLIN)) + ksft_exit_fail_msg( + "unexpected event type received: 0x%x\n", + fds.revents); + + if (timeout) + ksft_exit_fail_msg( + "death notification wait timeout\n"); + + close(pidfd); + /* Wait for child to prevent zombies */ + if (waitpid(child_pid, NULL, 0) < 0) + ksft_exit_fail_msg("%s - waitpid failed\n", + strerror(errno)); + + } + + ksft_test_result_pass("pidfd poll test: pass\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index b632965e60eb..7aff2d3b42c0 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -21,20 +21,12 @@ #include "pidfd.h" #include "../kselftest.h" -#ifndef __NR_pidfd_send_signal -#define __NR_pidfd_send_signal -1 -#endif - #define str(s) _str(s) #define _str(s) #s #define CHILD_THREAD_MIN_WAIT 3 /* seconds */ #define MAX_EVENTS 5 -#ifndef CLONE_PIDFD -#define CLONE_PIDFD 0x00001000 -#endif - static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) { size_t stack_size = 1024; @@ -47,12 +39,6 @@ static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) #endif } -static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, - unsigned int flags) -{ - return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); -} - static int signal_received; static void set_signal_received_on_sigusr1(int sig) diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c new file mode 100644 index 000000000000..7079f8eef792 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -0,0 +1,271 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#define _GNU_SOURCE +#include <errno.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <signal.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <sched.h> +#include <string.h> +#include <sys/resource.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "pidfd.h" +#include "../kselftest.h" + +#define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr))) + +static pid_t sys_clone3(struct clone_args *args) +{ + return syscall(__NR_clone3, args, sizeof(struct clone_args)); +} + +static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options, + struct rusage *ru) +{ + return syscall(__NR_waitid, which, pid, info, options, ru); +} + +static int test_pidfd_wait_simple(void) +{ + const char *test_name = "pidfd wait simple"; + int pidfd = -1, status = 0; + pid_t parent_tid = -1; + struct clone_args args = { + .parent_tid = ptr_to_u64(&parent_tid), + .pidfd = ptr_to_u64(&pidfd), + .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, + .exit_signal = SIGCHLD, + }; + int ret; + pid_t pid; + siginfo_t info = { + .si_signo = 0, + }; + + pidfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC); + if (pidfd < 0) + ksft_exit_fail_msg("%s test: failed to open /proc/self %s\n", + test_name, strerror(errno)); + + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + if (pid == 0) + ksft_exit_fail_msg( + "%s test: succeeded to wait on invalid pidfd %s\n", + test_name, strerror(errno)); + close(pidfd); + pidfd = -1; + + pidfd = open("/dev/null", O_RDONLY | O_CLOEXEC); + if (pidfd == 0) + ksft_exit_fail_msg("%s test: failed to open /dev/null %s\n", + test_name, strerror(errno)); + + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + if (pid == 0) + ksft_exit_fail_msg( + "%s test: succeeded to wait on invalid pidfd %s\n", + test_name, strerror(errno)); + close(pidfd); + pidfd = -1; + + pid = sys_clone3(&args); + if (pid < 0) + ksft_exit_fail_msg("%s test: failed to create new process %s\n", + test_name, strerror(errno)); + + if (pid == 0) + exit(EXIT_SUCCESS); + + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + if (pid < 0) + ksft_exit_fail_msg( + "%s test: failed to wait on process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (!WIFEXITED(info.si_status) || WEXITSTATUS(info.si_status)) + ksft_exit_fail_msg( + "%s test: unexpected status received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + close(pidfd); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_EXITED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + ksft_test_result_pass("%s test: Passed\n", test_name); + return 0; +} + +static int test_pidfd_wait_states(void) +{ + const char *test_name = "pidfd wait states"; + int pidfd = -1, status = 0; + pid_t parent_tid = -1; + struct clone_args args = { + .parent_tid = ptr_to_u64(&parent_tid), + .pidfd = ptr_to_u64(&pidfd), + .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, + .exit_signal = SIGCHLD, + }; + int ret; + pid_t pid; + siginfo_t info = { + .si_signo = 0, + }; + + pid = sys_clone3(&args); + if (pid < 0) + ksft_exit_fail_msg("%s test: failed to create new process %s\n", + test_name, strerror(errno)); + + if (pid == 0) { + kill(getpid(), SIGSTOP); + kill(getpid(), SIGSTOP); + exit(EXIT_SUCCESS); + } + + ret = sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to wait on WSTOPPED process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_STOPPED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + ret = sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to send signal to process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + ret = sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to wait WCONTINUED on process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_CONTINUED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + ret = sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED, NULL); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to wait on WUNTRACED process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_STOPPED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + ret = sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to send SIGKILL to process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to wait on WEXITED process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_KILLED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + close(pidfd); + + ksft_test_result_pass("%s test: Passed\n", test_name); + return 0; +} + +int main(int argc, char **argv) +{ + ksft_print_header(); + ksft_set_plan(2); + + test_pidfd_wait_simple(); + test_pidfd_wait_states(); + + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py index affa7f2d9670..9539cffa9e5e 100644 --- a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py +++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py @@ -64,7 +64,7 @@ class SubPlugin(TdcPlugin): cmdlist.insert(0, self.args.NAMES['NS']) cmdlist.insert(0, 'exec') cmdlist.insert(0, 'netns') - cmdlist.insert(0, 'ip') + cmdlist.insert(0, self.args.NAMES['IP']) else: pass @@ -78,16 +78,16 @@ class SubPlugin(TdcPlugin): return command def _ports_create(self): - cmd = 'ip link add $DEV0 type veth peer name $DEV1' + cmd = '$IP link add $DEV0 type veth peer name $DEV1' self._exec_cmd('pre', cmd) - cmd = 'ip link set $DEV0 up' + cmd = '$IP link set $DEV0 up' self._exec_cmd('pre', cmd) if not self.args.namespace: - cmd = 'ip link set $DEV1 up' + cmd = '$IP link set $DEV1 up' self._exec_cmd('pre', cmd) def _ports_destroy(self): - cmd = 'ip link del $DEV0' + cmd = '$IP link del $DEV0' self._exec_cmd('post', cmd) def _ns_create(self): @@ -97,16 +97,16 @@ class SubPlugin(TdcPlugin): ''' self._ports_create() if self.args.namespace: - cmd = 'ip netns add {}'.format(self.args.NAMES['NS']) + cmd = '$IP netns add {}'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) - cmd = 'ip link set $DEV1 netns {}'.format(self.args.NAMES['NS']) + cmd = '$IP link set $DEV1 netns {}'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) - cmd = 'ip -n {} link set $DEV1 up'.format(self.args.NAMES['NS']) + cmd = '$IP -n {} link set $DEV1 up'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) if self.args.device: - cmd = 'ip link set $DEV2 netns {}'.format(self.args.NAMES['NS']) + cmd = '$IP link set $DEV2 netns {}'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) - cmd = 'ip -n {} link set $DEV2 up'.format(self.args.NAMES['NS']) + cmd = '$IP -n {} link set $DEV2 up'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) def _ns_destroy(self): @@ -115,7 +115,7 @@ class SubPlugin(TdcPlugin): devices as well) ''' if self.args.namespace: - cmd = 'ip netns delete {}'.format(self.args.NAMES['NS']) + cmd = '$IP netns delete {}'.format(self.args.NAMES['NS']) self._exec_cmd('post', cmd) def _exec_cmd(self, stage, command): diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json index bf5ebf59c2d4..9cdd2e31ac2c 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json @@ -670,5 +670,52 @@ "teardown": [ "$TC actions flush action skbedit" ] + }, + { + "id": "630c", + "name": "Add batch of 32 skbedit actions with all parameters and cookie", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "706d", + "name": "Delete batch of 32 skbedit actions with all parameters", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json index cc7c7d758008..6503b1ce091f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json @@ -713,5 +713,99 @@ "teardown": [ "$TC actions flush action vlan" ] + }, + { + "id": "294e", + "name": "Add batch of 32 vlan push actions with cookie", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "56f7", + "name": "Delete batch of 32 vlan push actions", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "759f", + "name": "Add batch of 32 vlan pop actions with cookie", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop continue index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action vlan" + ] + }, + { + "id": "c84a", + "name": "Delete batch of 32 vlan pop actions", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action vlan", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] } ] |